From 57fcd550eb15bce14a7154736379dfd4ed60ae81 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Wed, 28 Oct 2020 12:31:20 +0100 Subject: drm/ttm: Warn on pinning without holding a reference MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Not technically a problem for ttm, but very likely a driver bug and pretty big time confusing for reviewing code. So warn about it, both at cleanup time (so we catch these for sure) and at pin/unpin time (so we know who's the culprit). Reviewed-by: Huang Rui Reviewed-by: Christian König Signed-off-by: Daniel Vetter Cc: Christian Koenig Cc: Huang Rui Link: https://patchwork.freedesktop.org/patch/msgid/20201028113120.3641237-1-daniel.vetter@ffwll.ch --- include/drm/ttm/ttm_bo_api.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h index 2564e66e67d7..79b9367e0ffd 100644 --- a/include/drm/ttm/ttm_bo_api.h +++ b/include/drm/ttm/ttm_bo_api.h @@ -600,6 +600,7 @@ static inline bool ttm_bo_uses_embedded_gem_object(struct ttm_buffer_object *bo) static inline void ttm_bo_pin(struct ttm_buffer_object *bo) { dma_resv_assert_held(bo->base.resv); + WARN_ON_ONCE(!kref_read(&bo->kref)); ++bo->pin_count; } @@ -613,6 +614,7 @@ static inline void ttm_bo_unpin(struct ttm_buffer_object *bo) { dma_resv_assert_held(bo->base.resv); WARN_ON_ONCE(!bo->pin_count); + WARN_ON_ONCE(!kref_read(&bo->kref)); --bo->pin_count; } -- cgit v1.2.3 From bc2532ab7c20844d16c5cda97d0806eb80ab1275 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Mon, 23 Nov 2020 12:56:45 +0100 Subject: drm/cma-helper: Remove prime infix from GEM object functions These functions are not directly related to PRIME interfaces any longer, but are now GEM object functions. Rename them accordingly and fix the docs. Signed-off-by: Thomas Zimmermann Acked-by: Maxime Ripard Link: https://patchwork.freedesktop.org/patch/msgid/20201123115646.11004-2-tzimmermann@suse.de --- drivers/gpu/drm/drm_gem_cma_helper.c | 20 ++++++++++---------- drivers/gpu/drm/vc4/vc4_bo.c | 4 ++-- include/drm/drm_gem_cma_helper.h | 4 ++-- 3 files changed, 14 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_gem_cma_helper.c b/drivers/gpu/drm/drm_gem_cma_helper.c index 4d5c1d86b022..6a4ef335ebc9 100644 --- a/drivers/gpu/drm/drm_gem_cma_helper.c +++ b/drivers/gpu/drm/drm_gem_cma_helper.c @@ -36,8 +36,8 @@ static const struct drm_gem_object_funcs drm_gem_cma_default_funcs = { .free = drm_gem_cma_free_object, .print_info = drm_gem_cma_print_info, - .get_sg_table = drm_gem_cma_prime_get_sg_table, - .vmap = drm_gem_cma_prime_vmap, + .get_sg_table = drm_gem_cma_get_sg_table, + .vmap = drm_gem_cma_vmap, .vm_ops = &drm_gem_cma_vm_ops, }; @@ -424,18 +424,18 @@ void drm_gem_cma_print_info(struct drm_printer *p, unsigned int indent, EXPORT_SYMBOL(drm_gem_cma_print_info); /** - * drm_gem_cma_prime_get_sg_table - provide a scatter/gather table of pinned + * drm_gem_cma_get_sg_table - provide a scatter/gather table of pinned * pages for a CMA GEM object * @obj: GEM object * - * This function exports a scatter/gather table suitable for PRIME usage by + * This function exports a scatter/gather table by * calling the standard DMA mapping API. Drivers using the CMA helpers should * set this as their &drm_gem_object_funcs.get_sg_table callback. * * Returns: * A pointer to the scatter/gather table of pinned pages or NULL on failure. */ -struct sg_table *drm_gem_cma_prime_get_sg_table(struct drm_gem_object *obj) +struct sg_table *drm_gem_cma_get_sg_table(struct drm_gem_object *obj) { struct drm_gem_cma_object *cma_obj = to_drm_gem_cma_obj(obj); struct sg_table *sgt; @@ -456,7 +456,7 @@ out: kfree(sgt); return ERR_PTR(ret); } -EXPORT_SYMBOL_GPL(drm_gem_cma_prime_get_sg_table); +EXPORT_SYMBOL_GPL(drm_gem_cma_get_sg_table); /** * drm_gem_cma_prime_import_sg_table - produce a CMA GEM object from another @@ -528,13 +528,13 @@ int drm_gem_cma_prime_mmap(struct drm_gem_object *obj, EXPORT_SYMBOL_GPL(drm_gem_cma_prime_mmap); /** - * drm_gem_cma_prime_vmap - map a CMA GEM object into the kernel's virtual + * drm_gem_cma_vmap - map a CMA GEM object into the kernel's virtual * address space * @obj: GEM object * @map: Returns the kernel virtual address of the CMA GEM object's backing * store. * - * This function maps a buffer exported via DRM PRIME into the kernel's + * This function maps a buffer into the kernel's * virtual address space. Since the CMA buffers are already mapped into the * kernel virtual address space this simply returns the cached virtual * address. Drivers using the CMA helpers should set this as their DRM @@ -543,7 +543,7 @@ EXPORT_SYMBOL_GPL(drm_gem_cma_prime_mmap); * Returns: * 0 on success, or a negative error code otherwise. */ -int drm_gem_cma_prime_vmap(struct drm_gem_object *obj, struct dma_buf_map *map) +int drm_gem_cma_vmap(struct drm_gem_object *obj, struct dma_buf_map *map) { struct drm_gem_cma_object *cma_obj = to_drm_gem_cma_obj(obj); @@ -551,7 +551,7 @@ int drm_gem_cma_prime_vmap(struct drm_gem_object *obj, struct dma_buf_map *map) return 0; } -EXPORT_SYMBOL_GPL(drm_gem_cma_prime_vmap); +EXPORT_SYMBOL_GPL(drm_gem_cma_vmap); /** * drm_gem_cma_prime_import_sg_table_vmap - PRIME import another driver's diff --git a/drivers/gpu/drm/vc4/vc4_bo.c b/drivers/gpu/drm/vc4/vc4_bo.c index 469d1b4f2643..813e6cb3f9af 100644 --- a/drivers/gpu/drm/vc4/vc4_bo.c +++ b/drivers/gpu/drm/vc4/vc4_bo.c @@ -385,7 +385,7 @@ static const struct vm_operations_struct vc4_vm_ops = { static const struct drm_gem_object_funcs vc4_gem_object_funcs = { .free = vc4_free_object, .export = vc4_prime_export, - .get_sg_table = drm_gem_cma_prime_get_sg_table, + .get_sg_table = drm_gem_cma_get_sg_table, .vmap = vc4_prime_vmap, .vm_ops = &vc4_vm_ops, }; @@ -794,7 +794,7 @@ int vc4_prime_vmap(struct drm_gem_object *obj, struct dma_buf_map *map) return -EINVAL; } - return drm_gem_cma_prime_vmap(obj, map); + return drm_gem_cma_vmap(obj, map); } struct drm_gem_object * diff --git a/include/drm/drm_gem_cma_helper.h b/include/drm/drm_gem_cma_helper.h index 5605c1b8f779..4680275ab339 100644 --- a/include/drm/drm_gem_cma_helper.h +++ b/include/drm/drm_gem_cma_helper.h @@ -96,14 +96,14 @@ unsigned long drm_gem_cma_get_unmapped_area(struct file *filp, void drm_gem_cma_print_info(struct drm_printer *p, unsigned int indent, const struct drm_gem_object *obj); -struct sg_table *drm_gem_cma_prime_get_sg_table(struct drm_gem_object *obj); +struct sg_table *drm_gem_cma_get_sg_table(struct drm_gem_object *obj); struct drm_gem_object * drm_gem_cma_prime_import_sg_table(struct drm_device *dev, struct dma_buf_attachment *attach, struct sg_table *sgt); int drm_gem_cma_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma); -int drm_gem_cma_prime_vmap(struct drm_gem_object *obj, struct dma_buf_map *map); +int drm_gem_cma_vmap(struct drm_gem_object *obj, struct dma_buf_map *map); /** * DRM_GEM_CMA_DRIVER_OPS_WITH_DUMB_CREATE - CMA GEM driver operations -- cgit v1.2.3 From f5ca8eb6f9bd5ea76e11bbcee09528e2d71fa920 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Mon, 23 Nov 2020 12:56:46 +0100 Subject: drm/cma-helper: Implement mmap as GEM CMA object functions The new GEM object function drm_gem_cma_mmap() sets the VMA flags and offset as in the old implementation and immediately maps in the buffer's memory pages. Changing CMA helpers to use the GEM object function allows for the removal of the special implementations for mmap and gem_prime_mmap callbacks. The regular functions drm_gem_mmap() and drm_gem_prime_mmap() are now used. Signed-off-by: Thomas Zimmermann Acked-by: Maxime Ripard Link: https://patchwork.freedesktop.org/patch/msgid/20201123115646.11004-3-tzimmermann@suse.de --- drivers/gpu/drm/drm_file.c | 3 +- drivers/gpu/drm/drm_gem_cma_helper.c | 121 +++++++++++------------------------ drivers/gpu/drm/pl111/pl111_drv.c | 2 +- drivers/gpu/drm/vc4/vc4_bo.c | 2 +- include/drm/drm_gem_cma_helper.h | 10 +-- 5 files changed, 44 insertions(+), 94 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c index b50380fa80ce..80886d50d0f1 100644 --- a/drivers/gpu/drm/drm_file.c +++ b/drivers/gpu/drm/drm_file.c @@ -113,8 +113,7 @@ bool drm_dev_needs_global_mutex(struct drm_device *dev) * The memory mapping implementation will vary depending on how the driver * manages memory. Legacy drivers will use the deprecated drm_legacy_mmap() * function, modern drivers should use one of the provided memory-manager - * specific implementations. For GEM-based drivers this is drm_gem_mmap(), and - * for drivers which use the CMA GEM helpers it's drm_gem_cma_mmap(). + * specific implementations. For GEM-based drivers this is drm_gem_mmap(). * * No other file operations are supported by the DRM userspace API. Overall the * following is an example &file_operations structure:: diff --git a/drivers/gpu/drm/drm_gem_cma_helper.c b/drivers/gpu/drm/drm_gem_cma_helper.c index 6a4ef335ebc9..7942cf05cd93 100644 --- a/drivers/gpu/drm/drm_gem_cma_helper.c +++ b/drivers/gpu/drm/drm_gem_cma_helper.c @@ -38,6 +38,7 @@ static const struct drm_gem_object_funcs drm_gem_cma_default_funcs = { .print_info = drm_gem_cma_print_info, .get_sg_table = drm_gem_cma_get_sg_table, .vmap = drm_gem_cma_vmap, + .mmap = drm_gem_cma_mmap, .vm_ops = &drm_gem_cma_vm_ops, }; @@ -277,62 +278,6 @@ const struct vm_operations_struct drm_gem_cma_vm_ops = { }; EXPORT_SYMBOL_GPL(drm_gem_cma_vm_ops); -static int drm_gem_cma_mmap_obj(struct drm_gem_cma_object *cma_obj, - struct vm_area_struct *vma) -{ - int ret; - - /* - * Clear the VM_PFNMAP flag that was set by drm_gem_mmap(), and set the - * vm_pgoff (used as a fake buffer offset by DRM) to 0 as we want to map - * the whole buffer. - */ - vma->vm_flags &= ~VM_PFNMAP; - vma->vm_pgoff = 0; - - ret = dma_mmap_wc(cma_obj->base.dev->dev, vma, cma_obj->vaddr, - cma_obj->paddr, vma->vm_end - vma->vm_start); - if (ret) - drm_gem_vm_close(vma); - - return ret; -} - -/** - * drm_gem_cma_mmap - memory-map a CMA GEM object - * @filp: file object - * @vma: VMA for the area to be mapped - * - * This function implements an augmented version of the GEM DRM file mmap - * operation for CMA objects: In addition to the usual GEM VMA setup it - * immediately faults in the entire object instead of using on-demaind - * faulting. Drivers which employ the CMA helpers should use this function - * as their ->mmap() handler in the DRM device file's file_operations - * structure. - * - * Instead of directly referencing this function, drivers should use the - * DEFINE_DRM_GEM_CMA_FOPS().macro. - * - * Returns: - * 0 on success or a negative error code on failure. - */ -int drm_gem_cma_mmap(struct file *filp, struct vm_area_struct *vma) -{ - struct drm_gem_cma_object *cma_obj; - struct drm_gem_object *gem_obj; - int ret; - - ret = drm_gem_mmap(filp, vma); - if (ret) - return ret; - - gem_obj = vma->vm_private_data; - cma_obj = to_drm_gem_cma_obj(gem_obj); - - return drm_gem_cma_mmap_obj(cma_obj, vma); -} -EXPORT_SYMBOL_GPL(drm_gem_cma_mmap); - #ifndef CONFIG_MMU /** * drm_gem_cma_get_unmapped_area - propose address for mapping in noMMU cases @@ -500,33 +445,6 @@ drm_gem_cma_prime_import_sg_table(struct drm_device *dev, } EXPORT_SYMBOL_GPL(drm_gem_cma_prime_import_sg_table); -/** - * drm_gem_cma_prime_mmap - memory-map an exported CMA GEM object - * @obj: GEM object - * @vma: VMA for the area to be mapped - * - * This function maps a buffer imported via DRM PRIME into a userspace - * process's address space. Drivers that use the CMA helpers should set this - * as their &drm_driver.gem_prime_mmap callback. - * - * Returns: - * 0 on success or a negative error code on failure. - */ -int drm_gem_cma_prime_mmap(struct drm_gem_object *obj, - struct vm_area_struct *vma) -{ - struct drm_gem_cma_object *cma_obj; - int ret; - - ret = drm_gem_mmap_obj(obj, obj->size, vma); - if (ret < 0) - return ret; - - cma_obj = to_drm_gem_cma_obj(obj); - return drm_gem_cma_mmap_obj(cma_obj, vma); -} -EXPORT_SYMBOL_GPL(drm_gem_cma_prime_mmap); - /** * drm_gem_cma_vmap - map a CMA GEM object into the kernel's virtual * address space @@ -553,6 +471,43 @@ int drm_gem_cma_vmap(struct drm_gem_object *obj, struct dma_buf_map *map) } EXPORT_SYMBOL_GPL(drm_gem_cma_vmap); +/** + * drm_gem_cma_mmap - memory-map an exported CMA GEM object + * @obj: GEM object + * @vma: VMA for the area to be mapped + * + * This function maps a buffer into a userspace process's address space. + * In addition to the usual GEM VMA setup it immediately faults in the entire + * object instead of using on-demand faulting. Drivers that use the CMA + * helpers should set this as their &drm_gem_object_funcs.mmap callback. + * + * Returns: + * 0 on success or a negative error code on failure. + */ +int drm_gem_cma_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma) +{ + struct drm_gem_cma_object *cma_obj; + int ret; + + /* + * Clear the VM_PFNMAP flag that was set by drm_gem_mmap(), and set the + * vm_pgoff (used as a fake buffer offset by DRM) to 0 as we want to map + * the whole buffer. + */ + vma->vm_pgoff -= drm_vma_node_start(&obj->vma_node); + vma->vm_flags &= ~VM_PFNMAP; + + cma_obj = to_drm_gem_cma_obj(obj); + + ret = dma_mmap_wc(cma_obj->base.dev->dev, vma, cma_obj->vaddr, + cma_obj->paddr, vma->vm_end - vma->vm_start); + if (ret) + drm_gem_vm_close(vma); + + return ret; +} +EXPORT_SYMBOL_GPL(drm_gem_cma_mmap); + /** * drm_gem_cma_prime_import_sg_table_vmap - PRIME import another driver's * scatter/gather table and get the virtual address of the buffer diff --git a/drivers/gpu/drm/pl111/pl111_drv.c b/drivers/gpu/drm/pl111/pl111_drv.c index 40e6708fbbe2..e4dcaef6c143 100644 --- a/drivers/gpu/drm/pl111/pl111_drv.c +++ b/drivers/gpu/drm/pl111/pl111_drv.c @@ -228,7 +228,7 @@ static const struct drm_driver pl111_drm_driver = { .prime_handle_to_fd = drm_gem_prime_handle_to_fd, .prime_fd_to_handle = drm_gem_prime_fd_to_handle, .gem_prime_import_sg_table = pl111_gem_import_sg_table, - .gem_prime_mmap = drm_gem_cma_prime_mmap, + .gem_prime_mmap = drm_gem_prime_mmap, #if defined(CONFIG_DEBUG_FS) .debugfs_init = pl111_debugfs_init, diff --git a/drivers/gpu/drm/vc4/vc4_bo.c b/drivers/gpu/drm/vc4/vc4_bo.c index 813e6cb3f9af..dc316cb79e00 100644 --- a/drivers/gpu/drm/vc4/vc4_bo.c +++ b/drivers/gpu/drm/vc4/vc4_bo.c @@ -782,7 +782,7 @@ int vc4_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma) return -EINVAL; } - return drm_gem_cma_prime_mmap(obj, vma); + return drm_gem_prime_mmap(obj, vma); } int vc4_prime_vmap(struct drm_gem_object *obj, struct dma_buf_map *map) diff --git a/include/drm/drm_gem_cma_helper.h b/include/drm/drm_gem_cma_helper.h index 4680275ab339..0a9711caa3e8 100644 --- a/include/drm/drm_gem_cma_helper.h +++ b/include/drm/drm_gem_cma_helper.h @@ -59,7 +59,7 @@ struct drm_gem_cma_object { .poll = drm_poll,\ .read = drm_read,\ .llseek = noop_llseek,\ - .mmap = drm_gem_cma_mmap,\ + .mmap = drm_gem_mmap,\ DRM_GEM_CMA_UNMAPPED_AREA_FOPS \ } @@ -76,9 +76,6 @@ int drm_gem_cma_dumb_create(struct drm_file *file_priv, struct drm_device *drm, struct drm_mode_create_dumb *args); -/* set vm_flags and we can change the VM attribute to other one at here */ -int drm_gem_cma_mmap(struct file *filp, struct vm_area_struct *vma); - /* allocate physical memory */ struct drm_gem_cma_object *drm_gem_cma_create(struct drm_device *drm, size_t size); @@ -101,9 +98,8 @@ struct drm_gem_object * drm_gem_cma_prime_import_sg_table(struct drm_device *dev, struct dma_buf_attachment *attach, struct sg_table *sgt); -int drm_gem_cma_prime_mmap(struct drm_gem_object *obj, - struct vm_area_struct *vma); int drm_gem_cma_vmap(struct drm_gem_object *obj, struct dma_buf_map *map); +int drm_gem_cma_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma); /** * DRM_GEM_CMA_DRIVER_OPS_WITH_DUMB_CREATE - CMA GEM driver operations @@ -123,7 +119,7 @@ int drm_gem_cma_vmap(struct drm_gem_object *obj, struct dma_buf_map *map); .prime_handle_to_fd = drm_gem_prime_handle_to_fd, \ .prime_fd_to_handle = drm_gem_prime_fd_to_handle, \ .gem_prime_import_sg_table = drm_gem_cma_prime_import_sg_table, \ - .gem_prime_mmap = drm_gem_cma_prime_mmap + .gem_prime_mmap = drm_gem_prime_mmap /** * DRM_GEM_CMA_DRIVER_OPS - CMA GEM driver operations -- cgit v1.2.3 From 18f7608a67fca8b8305b3557e2c00bca54785acd Mon Sep 17 00:00:00 2001 From: Christian König Date: Mon, 23 Nov 2020 14:56:49 +0100 Subject: drm/ttm: nuke ttm_dma_tt_init MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Not used any more. Signed-off-by: Christian König Acked-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/403837/ --- drivers/gpu/drm/ttm/ttm_tt.c | 13 ------------- include/drm/ttm/ttm_tt.h | 2 -- 2 files changed, 15 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c index da9eeffe0c6d..77ba784425dd 100644 --- a/drivers/gpu/drm/ttm/ttm_tt.c +++ b/drivers/gpu/drm/ttm/ttm_tt.c @@ -162,19 +162,6 @@ void ttm_tt_fini(struct ttm_tt *ttm) } EXPORT_SYMBOL(ttm_tt_fini); -int ttm_dma_tt_init(struct ttm_tt *ttm, struct ttm_buffer_object *bo, - uint32_t page_flags, enum ttm_caching caching) -{ - ttm_tt_init_fields(ttm, bo, page_flags, caching); - - if (ttm_dma_tt_alloc_page_directory(ttm)) { - pr_err("Failed allocating page table\n"); - return -ENOMEM; - } - return 0; -} -EXPORT_SYMBOL(ttm_dma_tt_init); - int ttm_sg_tt_init(struct ttm_tt *ttm, struct ttm_buffer_object *bo, uint32_t page_flags, enum ttm_caching caching) { diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h index da27e9d8fa64..6c8eb9a4de81 100644 --- a/include/drm/ttm/ttm_tt.h +++ b/include/drm/ttm/ttm_tt.h @@ -99,8 +99,6 @@ int ttm_tt_create(struct ttm_buffer_object *bo, bool zero_alloc); */ int ttm_tt_init(struct ttm_tt *ttm, struct ttm_buffer_object *bo, uint32_t page_flags, enum ttm_caching caching); -int ttm_dma_tt_init(struct ttm_tt *ttm_dma, struct ttm_buffer_object *bo, - uint32_t page_flags, enum ttm_caching caching); int ttm_sg_tt_init(struct ttm_tt *ttm_dma, struct ttm_buffer_object *bo, uint32_t page_flags, enum ttm_caching caching); -- cgit v1.2.3 From c67e62790f5c156705fb162da840c6d89d0af6e0 Mon Sep 17 00:00:00 2001 From: Christian König Date: Thu, 8 Oct 2020 12:57:32 +0200 Subject: drm/prime: split array import functions v4 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Mapping the imported pages of a DMA-buf into an userspace process doesn't work as expected. But we have reoccurring requests on this approach, so split the functions for this and document that dma_buf_mmap() needs to be used instead. v2: split it into two functions v3: rebased on latest changes v4: update commit message a bit Signed-off-by: Christian König Acked-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/403838/ --- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 9 ++-- drivers/gpu/drm/drm_prime.c | 64 ++++++++++++++++++----------- drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c | 3 +- drivers/gpu/drm/mediatek/mtk_drm_gem.c | 2 +- drivers/gpu/drm/msm/msm_gem.c | 2 +- drivers/gpu/drm/nouveau/nouveau_bo.c | 5 +-- drivers/gpu/drm/omapdrm/omap_gem.c | 3 +- drivers/gpu/drm/radeon/radeon_ttm.c | 9 ++-- drivers/gpu/drm/vgem/vgem_drv.c | 3 +- drivers/gpu/drm/xen/xen_drm_front_gem.c | 4 +- include/drm/drm_prime.h | 7 ++-- 11 files changed, 60 insertions(+), 51 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 02748e030322..a34fedcc8b61 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -918,8 +918,8 @@ static int amdgpu_ttm_tt_pin_userptr(struct ttm_bo_device *bdev, goto release_sg; /* convert SG to linear array of pages and dma addresses */ - drm_prime_sg_to_page_addr_arrays(ttm->sg, NULL, gtt->ttm.dma_address, - ttm->num_pages); + drm_prime_sg_to_dma_addr_array(ttm->sg, gtt->ttm.dma_address, + ttm->num_pages); return 0; @@ -1264,9 +1264,8 @@ static int amdgpu_ttm_tt_populate(struct ttm_bo_device *bdev, ttm->sg = sgt; } - drm_prime_sg_to_page_addr_arrays(ttm->sg, NULL, - gtt->ttm.dma_address, - ttm->num_pages); + drm_prime_sg_to_dma_addr_array(ttm->sg, gtt->ttm.dma_address, + ttm->num_pages); return 0; } diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c index 7db55fce35d8..683aa29ecd3b 100644 --- a/drivers/gpu/drm/drm_prime.c +++ b/drivers/gpu/drm/drm_prime.c @@ -978,44 +978,58 @@ struct drm_gem_object *drm_gem_prime_import(struct drm_device *dev, EXPORT_SYMBOL(drm_gem_prime_import); /** - * drm_prime_sg_to_page_addr_arrays - convert an sg table into a page array + * drm_prime_sg_to_page_array - convert an sg table into a page array * @sgt: scatter-gather table to convert - * @pages: optional array of page pointers to store the page array in - * @addrs: optional array to store the dma bus address of each page + * @pages: array of page pointers to store the pages in + * @max_entries: size of the passed-in array + * + * Exports an sg table into an array of pages. + * + * This function is deprecated and strongly discouraged to be used. + * The page array is only useful for page faults and those can corrupt fields + * in the struct page if they are not handled by the exporting driver. + */ +int __deprecated drm_prime_sg_to_page_array(struct sg_table *sgt, + struct page **pages, + int max_entries) +{ + struct sg_page_iter page_iter; + struct page **p = pages; + + for_each_sgtable_page(sgt, &page_iter, 0) { + if (WARN_ON(p - pages >= max_entries)) + return -1; + *p++ = sg_page_iter_page(&page_iter); + } + return 0; +} +EXPORT_SYMBOL(drm_prime_sg_to_page_array); + +/** + * drm_prime_sg_to_dma_addr_array - convert an sg table into a dma addr array + * @sgt: scatter-gather table to convert + * @addrs: array to store the dma bus address of each page * @max_entries: size of both the passed-in arrays * - * Exports an sg table into an array of pages and addresses. This is currently - * required by the TTM driver in order to do correct fault handling. + * Exports an sg table into an array of addresses. * - * Drivers can use this in their &drm_driver.gem_prime_import_sg_table + * Drivers should use this in their &drm_driver.gem_prime_import_sg_table * implementation. */ -int drm_prime_sg_to_page_addr_arrays(struct sg_table *sgt, struct page **pages, - dma_addr_t *addrs, int max_entries) +int drm_prime_sg_to_dma_addr_array(struct sg_table *sgt, dma_addr_t *addrs, + int max_entries) { struct sg_dma_page_iter dma_iter; - struct sg_page_iter page_iter; - struct page **p = pages; dma_addr_t *a = addrs; - if (pages) { - for_each_sgtable_page(sgt, &page_iter, 0) { - if (WARN_ON(p - pages >= max_entries)) - return -1; - *p++ = sg_page_iter_page(&page_iter); - } - } - if (addrs) { - for_each_sgtable_dma_page(sgt, &dma_iter, 0) { - if (WARN_ON(a - addrs >= max_entries)) - return -1; - *a++ = sg_page_iter_dma_address(&dma_iter); - } + for_each_sgtable_dma_page(sgt, &dma_iter, 0) { + if (WARN_ON(a - addrs >= max_entries)) + return -1; + *a++ = sg_page_iter_dma_address(&dma_iter); } - return 0; } -EXPORT_SYMBOL(drm_prime_sg_to_page_addr_arrays); +EXPORT_SYMBOL(drm_prime_sg_to_dma_addr_array); /** * drm_prime_gem_destroy - helper to clean up a PRIME-imported GEM object diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c index d9bd83203a15..b390dd4d60b7 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c @@ -135,8 +135,7 @@ struct drm_gem_object *etnaviv_gem_prime_import_sg_table(struct drm_device *dev, goto fail; } - ret = drm_prime_sg_to_page_addr_arrays(sgt, etnaviv_obj->pages, - NULL, npages); + ret = drm_prime_sg_to_page_array(sgt, etnaviv_obj->pages, npages); if (ret) goto fail; diff --git a/drivers/gpu/drm/mediatek/mtk_drm_gem.c b/drivers/gpu/drm/mediatek/mtk_drm_gem.c index 28a2ee1336ef..280ea0d5e840 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_gem.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_gem.c @@ -260,7 +260,7 @@ int mtk_drm_gem_prime_vmap(struct drm_gem_object *obj, struct dma_buf_map *map) return -ENOMEM; } - drm_prime_sg_to_page_addr_arrays(sgt, mtk_gem->pages, NULL, npages); + drm_prime_sg_to_page_array(sgt, mtk_gem->pages, npages); mtk_gem->kvaddr = vmap(mtk_gem->pages, npages, VM_MAP, pgprot_writecombine(PAGE_KERNEL)); diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index 311721ceee50..f995cb02b63d 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -1180,7 +1180,7 @@ struct drm_gem_object *msm_gem_import(struct drm_device *dev, goto fail; } - ret = drm_prime_sg_to_page_addr_arrays(sgt, msm_obj->pages, NULL, npages); + ret = drm_prime_sg_to_page_array(sgt, msm_obj->pages, npages); if (ret) { mutex_unlock(&msm_obj->lock); goto fail; diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index c30f088cefcc..645e7091dffc 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -1235,9 +1235,8 @@ nouveau_ttm_tt_populate(struct ttm_bo_device *bdev, return 0; if (slave && ttm->sg) { - drm_prime_sg_to_page_addr_arrays(ttm->sg, NULL, - ttm_dma->dma_address, - ttm->num_pages); + drm_prime_sg_to_dma_addr_array(ttm->sg, ttm_dma->dma_address, + ttm->num_pages); return 0; } diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c index 30d299ca8795..38af6195d959 100644 --- a/drivers/gpu/drm/omapdrm/omap_gem.c +++ b/drivers/gpu/drm/omapdrm/omap_gem.c @@ -1324,8 +1324,7 @@ struct drm_gem_object *omap_gem_new_dmabuf(struct drm_device *dev, size_t size, } omap_obj->pages = pages; - ret = drm_prime_sg_to_page_addr_arrays(sgt, pages, NULL, - npages); + ret = drm_prime_sg_to_page_array(sgt, pages, npages); if (ret) { omap_gem_free_object(obj); obj = ERR_PTR(-ENOMEM); diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index 917419bf1578..f1f7adb67c8e 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -395,8 +395,8 @@ static int radeon_ttm_tt_pin_userptr(struct ttm_bo_device *bdev, struct ttm_tt * if (r) goto release_sg; - drm_prime_sg_to_page_addr_arrays(ttm->sg, NULL, gtt->ttm.dma_address, - ttm->num_pages); + drm_prime_sg_to_dma_addr_array(ttm->sg, gtt->ttm.dma_address, + ttm->num_pages); return 0; @@ -574,9 +574,8 @@ static int radeon_ttm_tt_populate(struct ttm_bo_device *bdev, } if (slave && ttm->sg) { - drm_prime_sg_to_page_addr_arrays(ttm->sg, NULL, - gtt->ttm.dma_address, - ttm->num_pages); + drm_prime_sg_to_dma_addr_array(ttm->sg, gtt->ttm.dma_address, + ttm->num_pages); return 0; } diff --git a/drivers/gpu/drm/vgem/vgem_drv.c b/drivers/gpu/drm/vgem/vgem_drv.c index f8635ccaf9a1..a0e75f1d5d01 100644 --- a/drivers/gpu/drm/vgem/vgem_drv.c +++ b/drivers/gpu/drm/vgem/vgem_drv.c @@ -356,8 +356,7 @@ static struct drm_gem_object *vgem_prime_import_sg_table(struct drm_device *dev, } obj->pages_pin_count++; /* perma-pinned */ - drm_prime_sg_to_page_addr_arrays(obj->table, obj->pages, NULL, - npages); + drm_prime_sg_to_page_array(obj->table, obj->pages, npages); return &obj->base; } diff --git a/drivers/gpu/drm/xen/xen_drm_front_gem.c b/drivers/gpu/drm/xen/xen_drm_front_gem.c index 74db5a840bed..b293c67230ef 100644 --- a/drivers/gpu/drm/xen/xen_drm_front_gem.c +++ b/drivers/gpu/drm/xen/xen_drm_front_gem.c @@ -220,8 +220,8 @@ xen_drm_front_gem_import_sg_table(struct drm_device *dev, xen_obj->sgt_imported = sgt; - ret = drm_prime_sg_to_page_addr_arrays(sgt, xen_obj->pages, - NULL, xen_obj->num_pages); + ret = drm_prime_sg_to_page_array(sgt, xen_obj->pages, + xen_obj->num_pages); if (ret < 0) return ERR_PTR(ret); diff --git a/include/drm/drm_prime.h b/include/drm/drm_prime.h index 0991a47a1567..54f2c58305d2 100644 --- a/include/drm/drm_prime.h +++ b/include/drm/drm_prime.h @@ -105,8 +105,9 @@ struct drm_gem_object *drm_gem_prime_import(struct drm_device *dev, void drm_prime_gem_destroy(struct drm_gem_object *obj, struct sg_table *sg); -int drm_prime_sg_to_page_addr_arrays(struct sg_table *sgt, struct page **pages, - dma_addr_t *addrs, int max_pages); - +int drm_prime_sg_to_page_array(struct sg_table *sgt, struct page **pages, + int max_pages); +int drm_prime_sg_to_dma_addr_array(struct sg_table *sgt, dma_addr_t *addrs, + int max_pages); #endif /* __DRM_PRIME_H__ */ -- cgit v1.2.3 From 57e4bc8a48dd751eacae80b5ea3b0f08dd3452b0 Mon Sep 17 00:00:00 2001 From: Sam Ravnborg Date: Sat, 28 Nov 2020 23:41:05 +0100 Subject: video: fbdev: sstfb: Updated logging to fix set but not used warnings Fix set but not used warnings by introducing no_printk variants for the internal logging system for this driver. Fix a new warning that popped up now that logging was checked for correct printf format strings. A more invasive fix had been to replace all the internal logging with standard logging primitives - thats for another day. v2: - Update subject (Lee) Signed-off-by: Sam Ravnborg Acked-by: Thomas Zimmermann Cc: Sam Ravnborg Cc: Daniel Vetter Cc: Arnd Bergmann Cc: Bartlomiej Zolnierkiewicz Cc: Alex Dewar Cc: Jani Nikula Cc: linux-fbdev@vger.kernel.org Cc: Lee Jones Link: https://patchwork.freedesktop.org/patch/msgid/20201128224114.1033617-20-sam@ravnborg.org --- drivers/video/fbdev/sstfb.c | 2 +- include/video/sstfb.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/video/fbdev/sstfb.c b/drivers/video/fbdev/sstfb.c index c05cdabeb11c..27d4b0ace2d6 100644 --- a/drivers/video/fbdev/sstfb.c +++ b/drivers/video/fbdev/sstfb.c @@ -1390,7 +1390,7 @@ static int sstfb_probe(struct pci_dev *pdev, const struct pci_device_id *id) fix->smem_start, info->screen_base, fix->smem_len >> 20); - f_ddprintk("regbase_virt: %#lx\n", par->mmio_vbase); + f_ddprintk("regbase_virt: %p\n", par->mmio_vbase); f_ddprintk("membase_phys: %#lx\n", fix->smem_start); f_ddprintk("fbbase_virt: %p\n", info->screen_base); diff --git a/include/video/sstfb.h b/include/video/sstfb.h index 28384f354773..d4a5e41d1173 100644 --- a/include/video/sstfb.h +++ b/include/video/sstfb.h @@ -23,7 +23,7 @@ # define SST_DEBUG_FUNC 1 # define SST_DEBUG_VAR 1 #else -# define dprintk(X...) +# define dprintk(X...) no_printk(X) # define SST_DEBUG_REG 0 # define SST_DEBUG_FUNC 0 # define SST_DEBUG_VAR 0 @@ -48,7 +48,7 @@ #if (SST_DEBUG_FUNC > 1) # define f_ddprintk(X...) dprintk(" " X) #else -# define f_ddprintk(X...) +# define f_ddprintk(X...) no_printk(X) #endif #if (SST_DEBUG_FUNC > 2) # define f_dddprintk(X...) dprintk(" " X) -- cgit v1.2.3 From 5cf82904264190cd6c0edf65ce144ebb2b8be7f4 Mon Sep 17 00:00:00 2001 From: Christian König Date: Tue, 17 Nov 2020 15:44:07 +0100 Subject: drm/ttm/drivers: remove unecessary ttm_module.h include v2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit ttm_module.h deals with internals of TTM and should never be include outside of it. v2: also move the file around Signed-off-by: Christian König Acked-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/404885/ --- drivers/gpu/drm/amd/amdgpu/amdgpu.h | 1 - drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 1 - drivers/gpu/drm/nouveau/nouveau_drv.h | 1 - drivers/gpu/drm/qxl/qxl_drv.h | 1 - drivers/gpu/drm/qxl/qxl_ttm.c | 1 - drivers/gpu/drm/radeon/radeon.h | 1 - drivers/gpu/drm/radeon/radeon_ttm.c | 1 - drivers/gpu/drm/ttm/ttm_agp_backend.c | 1 - drivers/gpu/drm/ttm/ttm_bo.c | 3 +- drivers/gpu/drm/ttm/ttm_bo_vm.c | 1 - drivers/gpu/drm/ttm/ttm_memory.c | 3 +- drivers/gpu/drm/ttm/ttm_module.c | 3 +- drivers/gpu/drm/ttm/ttm_module.h | 40 +++++++++++++++++++++++++++ drivers/gpu/drm/ttm/ttm_range_manager.c | 1 - drivers/gpu/drm/vmwgfx/ttm_object.c | 1 - drivers/gpu/drm/vmwgfx/vmwgfx_drv.c | 1 - drivers/gpu/drm/vmwgfx/vmwgfx_drv.h | 1 - drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c | 1 - drivers/gpu/drm/vmwgfx/vmwgfx_thp.c | 1 - include/drm/ttm/ttm_bo_driver.h | 1 - include/drm/ttm/ttm_module.h | 40 --------------------------- 21 files changed, 46 insertions(+), 59 deletions(-) create mode 100644 drivers/gpu/drm/ttm/ttm_module.h delete mode 100644 include/drm/ttm/ttm_module.h (limited to 'include') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 6eceef23d838..b2ccf944a318 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -55,7 +55,6 @@ #include #include #include -#include #include #include diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index a34fedcc8b61..ec93d4fdabbd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -46,7 +46,6 @@ #include #include #include -#include #include #include diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h index 9d04d1b36434..c802d3d1ba39 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drv.h +++ b/drivers/gpu/drm/nouveau/nouveau_drv.h @@ -55,7 +55,6 @@ #include #include #include -#include #include diff --git a/drivers/gpu/drm/qxl/qxl_drv.h b/drivers/gpu/drm/qxl/qxl_drv.h index 8bd0f916dfbc..83b54f0dad61 100644 --- a/drivers/gpu/drm/qxl/qxl_drv.h +++ b/drivers/gpu/drm/qxl/qxl_drv.h @@ -46,7 +46,6 @@ #include #include #include -#include #include #include "qxl_dev.h" diff --git a/drivers/gpu/drm/qxl/qxl_ttm.c b/drivers/gpu/drm/qxl/qxl_ttm.c index d42e750cbdd3..38e2b117a085 100644 --- a/drivers/gpu/drm/qxl/qxl_ttm.c +++ b/drivers/gpu/drm/qxl/qxl_ttm.c @@ -31,7 +31,6 @@ #include #include #include -#include #include #include "qxl_drv.h" diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index 28cb8ced91b9..428c561a4e2c 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -75,7 +75,6 @@ #include #include #include -#include #include #include diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index f1f7adb67c8e..a3432c6343ba 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -46,7 +46,6 @@ #include #include #include -#include #include #include "radeon_reg.h" diff --git a/drivers/gpu/drm/ttm/ttm_agp_backend.c b/drivers/gpu/drm/ttm/ttm_agp_backend.c index 03c86628e4ac..8f9fa4188897 100644 --- a/drivers/gpu/drm/ttm/ttm_agp_backend.c +++ b/drivers/gpu/drm/ttm/ttm_agp_backend.c @@ -32,7 +32,6 @@ #define pr_fmt(fmt) "[TTM] " fmt -#include #include #include #include diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index fc6b619c0329..02cc5d247c0d 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -31,7 +31,6 @@ #define pr_fmt(fmt) "[TTM] " fmt -#include #include #include #include @@ -43,6 +42,8 @@ #include #include +#include "ttm_module.h" + static void ttm_bo_global_kobj_release(struct kobject *kobj); /* diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c index 2944fa0af493..144a4940b6b6 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_vm.c +++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c @@ -31,7 +31,6 @@ #define pr_fmt(fmt) "[TTM] " fmt -#include #include #include #include diff --git a/drivers/gpu/drm/ttm/ttm_memory.c b/drivers/gpu/drm/ttm/ttm_memory.c index 5ed1fc8f2ace..a3bfbd9cea68 100644 --- a/drivers/gpu/drm/ttm/ttm_memory.c +++ b/drivers/gpu/drm/ttm/ttm_memory.c @@ -29,7 +29,6 @@ #define pr_fmt(fmt) "[TTM] " fmt #include -#include #include #include #include @@ -39,6 +38,8 @@ #include #include +#include "ttm_module.h" + #define TTM_MEMORY_ALLOC_RETRIES 4 struct ttm_mem_global ttm_mem_glob; diff --git a/drivers/gpu/drm/ttm/ttm_module.c b/drivers/gpu/drm/ttm/ttm_module.c index 6ff40c041d79..c0906437cb1c 100644 --- a/drivers/gpu/drm/ttm/ttm_module.c +++ b/drivers/gpu/drm/ttm/ttm_module.c @@ -32,9 +32,10 @@ #include #include #include -#include #include +#include "ttm_module.h" + static DECLARE_WAIT_QUEUE_HEAD(exit_q); static atomic_t device_released; diff --git a/drivers/gpu/drm/ttm/ttm_module.h b/drivers/gpu/drm/ttm/ttm_module.h new file mode 100644 index 000000000000..45fa318c1585 --- /dev/null +++ b/drivers/gpu/drm/ttm/ttm_module.h @@ -0,0 +1,40 @@ +/************************************************************************** + * + * Copyright 2008-2009 VMware, Inc., Palo Alto, CA., USA + * All Rights Reserved. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the + * "Software"), to deal in the Software without restriction, including + * without limitation the rights to use, copy, modify, merge, publish, + * distribute, sub license, and/or sell copies of the Software, and to + * permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice (including the + * next paragraph) shall be included in all copies or substantial portions + * of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, + * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + * USE OR OTHER DEALINGS IN THE SOFTWARE. + * + **************************************************************************/ +/* + * Authors: Thomas Hellstrom + */ + +#ifndef _TTM_MODULE_H_ +#define _TTM_MODULE_H_ + +#include +struct kobject; + +#define TTM_PFX "[TTM] " +extern struct kobject *ttm_get_kobj(void); + +#endif /* _TTM_MODULE_H_ */ diff --git a/drivers/gpu/drm/ttm/ttm_range_manager.c b/drivers/gpu/drm/ttm/ttm_range_manager.c index e0952444cea9..a39305f742da 100644 --- a/drivers/gpu/drm/ttm/ttm_range_manager.c +++ b/drivers/gpu/drm/ttm/ttm_range_manager.c @@ -29,7 +29,6 @@ * Authors: Thomas Hellstrom */ -#include #include #include #include diff --git a/drivers/gpu/drm/vmwgfx/ttm_object.c b/drivers/gpu/drm/vmwgfx/ttm_object.c index 16077785ad47..0fe869d0fad1 100644 --- a/drivers/gpu/drm/vmwgfx/ttm_object.c +++ b/drivers/gpu/drm/vmwgfx/ttm_object.c @@ -59,7 +59,6 @@ #define pr_fmt(fmt) "[TTM] " fmt -#include #include #include #include diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 216daf93022c..0008be02d31c 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -35,7 +35,6 @@ #include #include #include -#include #include #include "ttm_object.h" diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index b45becbb00f8..5b9a28157dd3 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -39,7 +39,6 @@ #include #include -#include #include "ttm_lock.h" #include "ttm_object.h" diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c index be325a62c178..8fe26e32f920 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c @@ -29,7 +29,6 @@ */ #include "vmwgfx_drv.h" -#include #include #include #include diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c b/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c index 155ca3a5c7e5..e8e79de255cf 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c @@ -5,7 +5,6 @@ * Copyright (C) 2007-2019 Vmware, Inc. All rights reservedd. */ #include "vmwgfx_drv.h" -#include #include #include diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index f02f7cf9ae90..b1d1ce9740c4 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -39,7 +39,6 @@ #include "ttm_bo_api.h" #include "ttm_memory.h" -#include "ttm_module.h" #include "ttm_placement.h" #include "ttm_tt.h" #include "ttm_pool.h" diff --git a/include/drm/ttm/ttm_module.h b/include/drm/ttm/ttm_module.h deleted file mode 100644 index 45fa318c1585..000000000000 --- a/include/drm/ttm/ttm_module.h +++ /dev/null @@ -1,40 +0,0 @@ -/************************************************************************** - * - * Copyright 2008-2009 VMware, Inc., Palo Alto, CA., USA - * All Rights Reserved. - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the - * "Software"), to deal in the Software without restriction, including - * without limitation the rights to use, copy, modify, merge, publish, - * distribute, sub license, and/or sell copies of the Software, and to - * permit persons to whom the Software is furnished to do so, subject to - * the following conditions: - * - * The above copyright notice and this permission notice (including the - * next paragraph) shall be included in all copies or substantial portions - * of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL - * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, - * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR - * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE - * USE OR OTHER DEALINGS IN THE SOFTWARE. - * - **************************************************************************/ -/* - * Authors: Thomas Hellstrom - */ - -#ifndef _TTM_MODULE_H_ -#define _TTM_MODULE_H_ - -#include -struct kobject; - -#define TTM_PFX "[TTM] " -extern struct kobject *ttm_get_kobj(void); - -#endif /* _TTM_MODULE_H_ */ -- cgit v1.2.3 From 348fb0cb0a79bce03f402d689bbe0bf666577531 Mon Sep 17 00:00:00 2001 From: Tvrtko Ursulin Date: Tue, 1 Dec 2020 13:17:57 +0000 Subject: drm/i915/pmu: Deprecate I915_PMU_LAST and optimize state tracking Adding any kinds of "last" abi markers is usually a mistake which I repeated when implementing the PMU because it felt convenient at the time. This patch marks I915_PMU_LAST as deprecated and stops the internal implementation using it for sizing the event status bitmask and array. New way of sizing the fields is a bit less elegant, but it omits reserving slots for tracking events we are not interested in, and as such saves some runtime space. Adding sampling events is likely to be a special event and the new plumbing needed will be easily detected in testing. Existing asserts against the bitfield and array sizes are keeping the code safe. First event which gets the new treatment in this new scheme are the interrupts - which neither needs any tracking in i915 pmu nor needs waking up the GPU to read it. v2: * Streamline helper names. (Chris) v3: * Comment which events need tracking. (Chris) Signed-off-by: Tvrtko Ursulin Cc: Chris Wilson Reviewed-by: Chris Wilson Link: https://patchwork.freedesktop.org/patch/msgid/20201201131757.206367-1-tvrtko.ursulin@linux.intel.com --- drivers/gpu/drm/i915/i915_pmu.c | 84 ++++++++++++++++++++++++++++++----------- drivers/gpu/drm/i915/i915_pmu.h | 35 +++++++++++------ include/uapi/drm/i915_drm.h | 2 +- 3 files changed, 87 insertions(+), 34 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c index cd786ad12be7..97bb4aaa5236 100644 --- a/drivers/gpu/drm/i915/i915_pmu.c +++ b/drivers/gpu/drm/i915/i915_pmu.c @@ -27,8 +27,6 @@ BIT(I915_SAMPLE_WAIT) | \ BIT(I915_SAMPLE_SEMA)) -#define ENGINE_SAMPLE_BITS (1 << I915_PMU_SAMPLE_BITS) - static cpumask_t i915_pmu_cpumask; static unsigned int i915_pmu_target_cpu = -1; @@ -57,17 +55,42 @@ static bool is_engine_config(u64 config) return config < __I915_PMU_OTHER(0); } -static unsigned int config_enabled_bit(u64 config) +static unsigned int other_bit(const u64 config) +{ + unsigned int val; + + switch (config) { + case I915_PMU_ACTUAL_FREQUENCY: + val = __I915_PMU_ACTUAL_FREQUENCY_ENABLED; + break; + case I915_PMU_REQUESTED_FREQUENCY: + val = __I915_PMU_REQUESTED_FREQUENCY_ENABLED; + break; + case I915_PMU_RC6_RESIDENCY: + val = __I915_PMU_RC6_RESIDENCY_ENABLED; + break; + default: + /* + * Events that do not require sampling, or tracking state + * transitions between enabled and disabled can be ignored. + */ + return -1; + } + + return I915_ENGINE_SAMPLE_COUNT + val; +} + +static unsigned int config_bit(const u64 config) { if (is_engine_config(config)) return engine_config_sample(config); else - return ENGINE_SAMPLE_BITS + (config - __I915_PMU_OTHER(0)); + return other_bit(config); } -static u64 config_enabled_mask(u64 config) +static u64 config_mask(u64 config) { - return BIT_ULL(config_enabled_bit(config)); + return BIT_ULL(config_bit(config)); } static bool is_engine_event(struct perf_event *event) @@ -75,15 +98,20 @@ static bool is_engine_event(struct perf_event *event) return is_engine_config(event->attr.config); } -static unsigned int event_enabled_bit(struct perf_event *event) +static unsigned int event_bit(struct perf_event *event) +{ + return config_bit(event->attr.config); +} + +static bool event_read_needs_wakeref(const struct perf_event *event) { - return config_enabled_bit(event->attr.config); + return event->attr.config == I915_PMU_RC6_RESIDENCY; } static bool pmu_needs_timer(struct i915_pmu *pmu, bool gpu_active) { struct drm_i915_private *i915 = container_of(pmu, typeof(*i915), pmu); - u64 enable; + u32 enable; /* * Only some counters need the sampling timer. @@ -96,8 +124,8 @@ static bool pmu_needs_timer(struct i915_pmu *pmu, bool gpu_active) * Mask out all the ones which do not need the timer, or in * other words keep all the ones that could need the timer. */ - enable &= config_enabled_mask(I915_PMU_ACTUAL_FREQUENCY) | - config_enabled_mask(I915_PMU_REQUESTED_FREQUENCY) | + enable &= config_mask(I915_PMU_ACTUAL_FREQUENCY) | + config_mask(I915_PMU_REQUESTED_FREQUENCY) | ENGINE_SAMPLE_MASK; /* @@ -189,7 +217,7 @@ static void park_rc6(struct drm_i915_private *i915) { struct i915_pmu *pmu = &i915->pmu; - if (pmu->enable & config_enabled_mask(I915_PMU_RC6_RESIDENCY)) + if (pmu->enable & config_mask(I915_PMU_RC6_RESIDENCY)) pmu->sample[__I915_SAMPLE_RC6].cur = __get_rc6(&i915->gt); pmu->sleep_last = ktime_get(); @@ -344,8 +372,8 @@ add_sample_mult(struct i915_pmu_sample *sample, u32 val, u32 mul) static bool frequency_sampling_enabled(struct i915_pmu *pmu) { return pmu->enable & - (config_enabled_mask(I915_PMU_ACTUAL_FREQUENCY) | - config_enabled_mask(I915_PMU_REQUESTED_FREQUENCY)); + (config_mask(I915_PMU_ACTUAL_FREQUENCY) | + config_mask(I915_PMU_REQUESTED_FREQUENCY)); } static void @@ -363,7 +391,7 @@ frequency_sample(struct intel_gt *gt, unsigned int period_ns) if (!intel_gt_pm_get_if_awake(gt)) return; - if (pmu->enable & config_enabled_mask(I915_PMU_ACTUAL_FREQUENCY)) { + if (pmu->enable & config_mask(I915_PMU_ACTUAL_FREQUENCY)) { u32 val; /* @@ -385,7 +413,7 @@ frequency_sample(struct intel_gt *gt, unsigned int period_ns) intel_gpu_freq(rps, val), period_ns / 1000); } - if (pmu->enable & config_enabled_mask(I915_PMU_REQUESTED_FREQUENCY)) { + if (pmu->enable & config_mask(I915_PMU_REQUESTED_FREQUENCY)) { add_sample_mult(&pmu->sample[__I915_SAMPLE_FREQ_REQ], intel_gpu_freq(rps, rps->cur_freq), period_ns / 1000); @@ -627,12 +655,19 @@ static void i915_pmu_enable(struct perf_event *event) { struct drm_i915_private *i915 = container_of(event->pmu, typeof(*i915), pmu.base); - unsigned int bit = event_enabled_bit(event); + bool need_wakeref = event_read_needs_wakeref(event); struct i915_pmu *pmu = &i915->pmu; - intel_wakeref_t wakeref; + intel_wakeref_t wakeref = 0; unsigned long flags; + unsigned int bit; + + if (need_wakeref) + wakeref = intel_runtime_pm_get(&i915->runtime_pm); + + bit = event_bit(event); + if (bit == -1) + goto update; - wakeref = intel_runtime_pm_get(&i915->runtime_pm); spin_lock_irqsave(&pmu->lock, flags); /* @@ -644,7 +679,7 @@ static void i915_pmu_enable(struct perf_event *event) GEM_BUG_ON(pmu->enable_count[bit] == ~0); if (pmu->enable_count[bit] == 0 && - config_enabled_mask(I915_PMU_RC6_RESIDENCY) & BIT_ULL(bit)) { + config_mask(I915_PMU_RC6_RESIDENCY) & BIT_ULL(bit)) { pmu->sample[__I915_SAMPLE_RC6_LAST_REPORTED].cur = 0; pmu->sample[__I915_SAMPLE_RC6].cur = __get_rc6(&i915->gt); pmu->sleep_last = ktime_get(); @@ -684,6 +719,7 @@ static void i915_pmu_enable(struct perf_event *event) spin_unlock_irqrestore(&pmu->lock, flags); +update: /* * Store the current counter value so we can report the correct delta * for all listeners. Even when the event was already enabled and has @@ -691,17 +727,21 @@ static void i915_pmu_enable(struct perf_event *event) */ local64_set(&event->hw.prev_count, __i915_pmu_event_read(event)); - intel_runtime_pm_put(&i915->runtime_pm, wakeref); + if (wakeref) + intel_runtime_pm_put(&i915->runtime_pm, wakeref); } static void i915_pmu_disable(struct perf_event *event) { struct drm_i915_private *i915 = container_of(event->pmu, typeof(*i915), pmu.base); - unsigned int bit = event_enabled_bit(event); + unsigned int bit = event_bit(event); struct i915_pmu *pmu = &i915->pmu; unsigned long flags; + if (bit == -1) + return; + spin_lock_irqsave(&pmu->lock, flags); if (is_engine_event(event)) { diff --git a/drivers/gpu/drm/i915/i915_pmu.h b/drivers/gpu/drm/i915/i915_pmu.h index a24885ab415c..e33be99e6454 100644 --- a/drivers/gpu/drm/i915/i915_pmu.h +++ b/drivers/gpu/drm/i915/i915_pmu.h @@ -14,6 +14,21 @@ struct drm_i915_private; +/** + * Non-engine events that we need to track enabled-disabled transition and + * current state. + */ +enum i915_pmu_tracked_events { + __I915_PMU_ACTUAL_FREQUENCY_ENABLED = 0, + __I915_PMU_REQUESTED_FREQUENCY_ENABLED, + __I915_PMU_RC6_RESIDENCY_ENABLED, + __I915_PMU_TRACKED_EVENT_COUNT, /* count marker */ +}; + +/** + * Slots used from the sampling timer (non-engine events) with some extras for + * convenience. + */ enum { __I915_SAMPLE_FREQ_ACT = 0, __I915_SAMPLE_FREQ_REQ, @@ -28,8 +43,7 @@ enum { * It is also used to know to needed number of event reference counters. */ #define I915_PMU_MASK_BITS \ - ((1 << I915_PMU_SAMPLE_BITS) + \ - (I915_PMU_LAST + 1 - __I915_PMU_OTHER(0))) + (I915_ENGINE_SAMPLE_COUNT + __I915_PMU_TRACKED_EVENT_COUNT) #define I915_ENGINE_SAMPLE_COUNT (I915_SAMPLE_SEMA + 1) @@ -66,18 +80,17 @@ struct i915_pmu { */ struct hrtimer timer; /** - * @enable: Bitmask of all currently enabled events. + * @enable: Bitmask of specific enabled events. + * + * For some events we need to track their state and do some internal + * house keeping. * - * Bits are derived from uAPI event numbers in a way that low 16 bits - * correspond to engine event _sample_ _type_ (I915_SAMPLE_QUEUED is - * bit 0), and higher bits correspond to other events (for instance - * I915_PMU_ACTUAL_FREQUENCY is bit 16 etc). + * Each engine event sampler type and event listed in enum + * i915_pmu_tracked_events gets a bit in this field. * - * In other words, low 16 bits are not per engine but per engine - * sampler type, while the upper bits are directly mapped to other - * event types. + * Low bits are engine samplers and other events continue from there. */ - u64 enable; + u32 enable; /** * @timer_last: diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index fa1f3d62f9a6..6edcb2b6c708 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -178,7 +178,7 @@ enum drm_i915_pmu_engine_sample { #define I915_PMU_INTERRUPTS __I915_PMU_OTHER(2) #define I915_PMU_RC6_RESIDENCY __I915_PMU_OTHER(3) -#define I915_PMU_LAST I915_PMU_RC6_RESIDENCY +#define I915_PMU_LAST /* Deprecated - do not use */ I915_PMU_RC6_RESIDENCY /* Each region is a minimum of 16k, and there are at most 255 of them. */ -- cgit v1.2.3 From a7e2e1c50450c6a0f020b35960edecbe25dde520 Mon Sep 17 00:00:00 2001 From: Simon Ser Date: Mon, 30 Nov 2020 16:26:12 +0000 Subject: drm: document that user-space should force-probe connectors It seems like we can't have nice things, so let's just document the disappointing behaviour instead. The previous version assumed the kernel would perform the probing work when appropriate, however this is not the case today. Update the documentation to reflect reality. v2: - Improve commit message to explain why this change is made (Pekka) - Keep the bit about flickering (Daniel) - Explain when user-space should force-probe, and when it shouldn't (Daniel) Signed-off-by: Simon Ser Fixes: 2ac5ef3b2362 ("drm: document drm_mode_get_connector") Reviewed-by: Daniel Vetter Reviewed-by: Pekka Paalanen Cc: Ville Syrjala Link: https://patchwork.freedesktop.org/patch/msgid/AxqLnTAsFCRishOVB5CLsqIesmrMrm7oytnOVB7oPA@cp7-web-043.plabs.ch --- include/uapi/drm/drm_mode.h | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h index b49fbf2bdc40..1c064627e6c3 100644 --- a/include/uapi/drm/drm_mode.h +++ b/include/uapi/drm/drm_mode.h @@ -414,15 +414,12 @@ enum drm_mode_subconnector { * * If the @count_modes field is set to zero, the kernel will perform a forced * probe on the connector to refresh the connector status, modes and EDID. - * A forced-probe can be slow and the ioctl will block. A force-probe can cause - * flickering and temporary freezes, so it should not be performed - * automatically. + * A forced-probe can be slow, might cause flickering and the ioctl will block. * - * User-space shouldn't need to force-probe connectors in general: the kernel - * will automatically take care of probing connectors that don't support - * hot-plug detection when appropriate. However, user-space may force-probe - * connectors on user request (e.g. clicking a "Scan connectors" button, or - * opening a UI to manage screens). + * User-space needs to force-probe connectors to ensure their metadata is + * up-to-date at startup and after receiving a hot-plug event. User-space + * may perform a forced-probe when the user explicitly requests it. User-space + * shouldn't perform a forced-probe in other situations. */ struct drm_mode_get_connector { /** @encoders_ptr: Pointer to ``__u32`` array of object IDs. */ -- cgit v1.2.3 From d96bc380a50f1e89769d38dd9c5739be3cb014b2 Mon Sep 17 00:00:00 2001 From: Tian Tao Date: Wed, 2 Dec 2020 17:26:51 +0800 Subject: drm/irq: Add the new api to install irq Add new api devm_drm_irq_install() to register interrupts, no need to call drm_irq_uninstall() when the drm module is removed. Signed-off-by: Tian Tao Reviewed-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/1606901212-8214-3-git-send-email-tiantao6@hisilicon.com --- drivers/gpu/drm/drm_irq.c | 32 ++++++++++++++++++++++++++++++++ include/drm/drm_irq.h | 2 +- 2 files changed, 33 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c index 09d6e9e2e075..803af4bbd214 100644 --- a/drivers/gpu/drm/drm_irq.c +++ b/drivers/gpu/drm/drm_irq.c @@ -214,6 +214,38 @@ int drm_irq_uninstall(struct drm_device *dev) } EXPORT_SYMBOL(drm_irq_uninstall); +static void devm_drm_irq_uninstall(void *data) +{ + drm_irq_uninstall(data); +} + +/** + * devm_drm_irq_install - install IRQ handler + * @dev: DRM device + * @irq: IRQ number to install the handler for + * + * devm_drm_irq_install is a help function of drm_irq_install. + * + * if the driver uses devm_drm_irq_install, there is no need + * to call drm_irq_uninstall when the drm module get unloaded, + * as this will done automagically. + * + * Returns: + * Zero on success or a negative error code on failure. + */ +int devm_drm_irq_install(struct drm_device *dev, int irq) +{ + int ret; + + ret = drm_irq_install(dev, irq); + if (ret) + return ret; + + return devm_add_action_or_reset(dev->dev, + devm_drm_irq_uninstall, dev); +} +EXPORT_SYMBOL(devm_drm_irq_install); + #if IS_ENABLED(CONFIG_DRM_LEGACY) int drm_legacy_irq_control(struct drm_device *dev, void *data, struct drm_file *file_priv) diff --git a/include/drm/drm_irq.h b/include/drm/drm_irq.h index d77f6e65b1c6..631b22f9757d 100644 --- a/include/drm/drm_irq.h +++ b/include/drm/drm_irq.h @@ -28,5 +28,5 @@ struct drm_device; int drm_irq_install(struct drm_device *dev, int irq); int drm_irq_uninstall(struct drm_device *dev); - +int devm_drm_irq_install(struct drm_device *dev, int irq); #endif -- cgit v1.2.3 From 1cdd3f739f4e839e77b83bb3238150c41905c748 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Fri, 4 Dec 2020 11:29:32 +0200 Subject: drm: Remove drmm_add_final_kfree() declaration from public headers The drmm_add_final_kfree() function is declared in the include/drm/drm_managed.h public header, but has become an internal API not exposed to drivers. Drop it from drm_managed.h as it's already declared in drm_internal.h. Signed-off-by: Laurent Pinchart Acked-by: Thomas Zimmermann Signed-off-by: Sam Ravnborg Link: https://patchwork.freedesktop.org/patch/msgid/20201204092932.21636-1-laurent.pinchart+renesas@ideasonboard.com --- include/drm/drm_managed.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/drm/drm_managed.h b/include/drm/drm_managed.h index ca4114633bf9..b45c6fbf53ac 100644 --- a/include/drm/drm_managed.h +++ b/include/drm/drm_managed.h @@ -44,8 +44,6 @@ int __must_check __drmm_add_action_or_reset(struct drm_device *dev, drmres_release_t action, void *data, const char *name); -void drmm_add_final_kfree(struct drm_device *dev, void *container); - void *drmm_kmalloc(struct drm_device *dev, size_t size, gfp_t gfp) __malloc; /** -- cgit v1.2.3 From 8935ff00e3b110e47e3a291ff11951eb1066b1ae Mon Sep 17 00:00:00 2001 From: Luben Tuikov Date: Thu, 3 Dec 2020 22:17:18 -0500 Subject: drm/scheduler: "node" --> "list" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Rename "node" to "list" in struct drm_sched_job, in order to make it consistent with what we see being used throughout gpu_scheduler.h, for instance in struct drm_sched_entity, as well as the rest of DRM and the kernel. Signed-off-by: Luben Tuikov Reviewed-by: Christian König Link: https://patchwork.freedesktop.org/patch/403515/ Cc: Alexander Deucher Cc: Andrey Grodzovsky Cc: Christian König Cc: Daniel Vetter Signed-off-by: Christian König --- drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c | 6 +++--- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 2 +- drivers/gpu/drm/scheduler/sched_main.c | 23 ++++++++++++----------- include/drm/gpu_scheduler.h | 4 ++-- 5 files changed, 19 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c index 5c1f3725c741..8358cae0b5a4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c @@ -1427,7 +1427,7 @@ static void amdgpu_ib_preempt_job_recovery(struct drm_gpu_scheduler *sched) struct dma_fence *fence; spin_lock(&sched->job_list_lock); - list_for_each_entry(s_job, &sched->ring_mirror_list, node) { + list_for_each_entry(s_job, &sched->ring_mirror_list, list) { fence = sched->ops->run_job(s_job); dma_fence_put(fence); } @@ -1459,10 +1459,10 @@ static void amdgpu_ib_preempt_mark_partial_job(struct amdgpu_ring *ring) no_preempt: spin_lock(&sched->job_list_lock); - list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) { + list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, list) { if (dma_fence_is_signaled(&s_job->s_fence->finished)) { /* remove job from ring_mirror_list */ - list_del_init(&s_job->node); + list_del_init(&s_job->list); sched->ops->free_job(s_job); continue; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 7560b05e4ac1..4df6de81cd41 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -4128,7 +4128,7 @@ bool amdgpu_device_has_job_running(struct amdgpu_device *adev) spin_lock(&ring->sched.job_list_lock); job = list_first_entry_or_null(&ring->sched.ring_mirror_list, - struct drm_sched_job, node); + struct drm_sched_job, list); spin_unlock(&ring->sched.job_list_lock); if (job) return true; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index dcfe8a3b03ff..aca52a46b93d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -271,7 +271,7 @@ void amdgpu_job_stop_all_jobs_on_sched(struct drm_gpu_scheduler *sched) } /* Signal all jobs already scheduled to HW */ - list_for_each_entry(s_job, &sched->ring_mirror_list, node) { + list_for_each_entry(s_job, &sched->ring_mirror_list, list) { struct drm_sched_fence *s_fence = s_job->s_fence; dma_fence_set_error(&s_fence->finished, -EHWPOISON); diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index c6332d75025e..c52eba407ebd 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -272,7 +272,7 @@ static void drm_sched_job_begin(struct drm_sched_job *s_job) struct drm_gpu_scheduler *sched = s_job->sched; spin_lock(&sched->job_list_lock); - list_add_tail(&s_job->node, &sched->ring_mirror_list); + list_add_tail(&s_job->list, &sched->ring_mirror_list); drm_sched_start_timeout(sched); spin_unlock(&sched->job_list_lock); } @@ -287,7 +287,7 @@ static void drm_sched_job_timedout(struct work_struct *work) /* Protects against concurrent deletion in drm_sched_get_cleanup_job */ spin_lock(&sched->job_list_lock); job = list_first_entry_or_null(&sched->ring_mirror_list, - struct drm_sched_job, node); + struct drm_sched_job, list); if (job) { /* @@ -295,7 +295,7 @@ static void drm_sched_job_timedout(struct work_struct *work) * drm_sched_cleanup_jobs. It will be reinserted back after sched->thread * is parked at which point it's safe. */ - list_del_init(&job->node); + list_del_init(&job->list); spin_unlock(&sched->job_list_lock); job->sched->ops->timedout_job(job); @@ -392,7 +392,7 @@ void drm_sched_stop(struct drm_gpu_scheduler *sched, struct drm_sched_job *bad) * Add at the head of the queue to reflect it was the earliest * job extracted. */ - list_add(&bad->node, &sched->ring_mirror_list); + list_add(&bad->list, &sched->ring_mirror_list); /* * Iterate the job list from later to earlier one and either deactive @@ -400,7 +400,8 @@ void drm_sched_stop(struct drm_gpu_scheduler *sched, struct drm_sched_job *bad) * signaled. * This iteration is thread safe as sched thread is stopped. */ - list_for_each_entry_safe_reverse(s_job, tmp, &sched->ring_mirror_list, node) { + list_for_each_entry_safe_reverse(s_job, tmp, &sched->ring_mirror_list, + list) { if (s_job->s_fence->parent && dma_fence_remove_callback(s_job->s_fence->parent, &s_job->cb)) { @@ -411,7 +412,7 @@ void drm_sched_stop(struct drm_gpu_scheduler *sched, struct drm_sched_job *bad) * Locking here is for concurrent resume timeout */ spin_lock(&sched->job_list_lock); - list_del_init(&s_job->node); + list_del_init(&s_job->list); spin_unlock(&sched->job_list_lock); /* @@ -462,7 +463,7 @@ void drm_sched_start(struct drm_gpu_scheduler *sched, bool full_recovery) * so no new jobs are being inserted or removed. Also concurrent * GPU recovers can't run in parallel. */ - list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) { + list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, list) { struct dma_fence *fence = s_job->s_fence->parent; atomic_inc(&sched->hw_rq_count); @@ -505,7 +506,7 @@ void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched) bool found_guilty = false; struct dma_fence *fence; - list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) { + list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, list) { struct drm_sched_fence *s_fence = s_job->s_fence; if (!found_guilty && atomic_read(&s_job->karma) > sched->hang_limit) { @@ -565,7 +566,7 @@ int drm_sched_job_init(struct drm_sched_job *job, return -ENOMEM; job->id = atomic64_inc_return(&sched->job_id_count); - INIT_LIST_HEAD(&job->node); + INIT_LIST_HEAD(&job->list); return 0; } @@ -684,11 +685,11 @@ drm_sched_get_cleanup_job(struct drm_gpu_scheduler *sched) spin_lock(&sched->job_list_lock); job = list_first_entry_or_null(&sched->ring_mirror_list, - struct drm_sched_job, node); + struct drm_sched_job, list); if (job && dma_fence_is_signaled(&job->s_fence->finished)) { /* remove job from ring_mirror_list */ - list_del_init(&job->node); + list_del_init(&job->list); } else { job = NULL; /* queue timeout for next job */ diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index 92436553fd6a..3add0072bd37 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -189,14 +189,14 @@ struct drm_sched_fence *to_drm_sched_fence(struct dma_fence *f); */ struct drm_sched_job { struct spsc_node queue_node; + struct list_head list; struct drm_gpu_scheduler *sched; struct drm_sched_fence *s_fence; struct dma_fence_cb finish_cb; - struct list_head node; uint64_t id; atomic_t karma; enum drm_sched_priority s_priority; - struct drm_sched_entity *entity; + struct drm_sched_entity *entity; struct dma_fence_cb cb; }; -- cgit v1.2.3 From 6efa4b465cfdaa9be251ba043253e302ddb9976f Mon Sep 17 00:00:00 2001 From: Luben Tuikov Date: Thu, 3 Dec 2020 22:17:19 -0500 Subject: gpu/drm: ring_mirror_list --> pending_list MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Rename "ring_mirror_list" to "pending_list", to describe what something is, not what it does, how it's used, or how the hardware implements it. This also abstracts the actual hardware implementation, i.e. how the low-level driver communicates with the device it drives, ring, CAM, etc., shouldn't be exposed to DRM. The pending_list keeps jobs submitted, which are out of our control. Usually this means they are pending execution status in hardware, but the latter definition is a more general (inclusive) definition. Signed-off-by: Luben Tuikov Acked-by: Christian König Link: https://patchwork.freedesktop.org/patch/405573/ Cc: Alexander Deucher Cc: Andrey Grodzovsky Cc: Christian König Cc: Daniel Vetter Signed-off-by: Christian König --- drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 2 +- drivers/gpu/drm/scheduler/sched_main.c | 34 ++++++++++++++--------------- include/drm/gpu_scheduler.h | 10 ++++----- 5 files changed, 27 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c index 8358cae0b5a4..db77a5bdfa45 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c @@ -1427,7 +1427,7 @@ static void amdgpu_ib_preempt_job_recovery(struct drm_gpu_scheduler *sched) struct dma_fence *fence; spin_lock(&sched->job_list_lock); - list_for_each_entry(s_job, &sched->ring_mirror_list, list) { + list_for_each_entry(s_job, &sched->pending_list, list) { fence = sched->ops->run_job(s_job); dma_fence_put(fence); } @@ -1459,7 +1459,7 @@ static void amdgpu_ib_preempt_mark_partial_job(struct amdgpu_ring *ring) no_preempt: spin_lock(&sched->job_list_lock); - list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, list) { + list_for_each_entry_safe(s_job, tmp, &sched->pending_list, list) { if (dma_fence_is_signaled(&s_job->s_fence->finished)) { /* remove job from ring_mirror_list */ list_del_init(&s_job->list); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 4df6de81cd41..fbae600aa5f9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -4127,8 +4127,8 @@ bool amdgpu_device_has_job_running(struct amdgpu_device *adev) continue; spin_lock(&ring->sched.job_list_lock); - job = list_first_entry_or_null(&ring->sched.ring_mirror_list, - struct drm_sched_job, list); + job = list_first_entry_or_null(&ring->sched.pending_list, + struct drm_sched_job, list); spin_unlock(&ring->sched.job_list_lock); if (job) return true; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index aca52a46b93d..ff48101bab55 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -271,7 +271,7 @@ void amdgpu_job_stop_all_jobs_on_sched(struct drm_gpu_scheduler *sched) } /* Signal all jobs already scheduled to HW */ - list_for_each_entry(s_job, &sched->ring_mirror_list, list) { + list_for_each_entry(s_job, &sched->pending_list, list) { struct drm_sched_fence *s_fence = s_job->s_fence; dma_fence_set_error(&s_fence->finished, -EHWPOISON); diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index c52eba407ebd..b694df12aaba 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -198,7 +198,7 @@ EXPORT_SYMBOL(drm_sched_dependency_optimized); static void drm_sched_start_timeout(struct drm_gpu_scheduler *sched) { if (sched->timeout != MAX_SCHEDULE_TIMEOUT && - !list_empty(&sched->ring_mirror_list)) + !list_empty(&sched->pending_list)) schedule_delayed_work(&sched->work_tdr, sched->timeout); } @@ -258,7 +258,7 @@ void drm_sched_resume_timeout(struct drm_gpu_scheduler *sched, { spin_lock(&sched->job_list_lock); - if (list_empty(&sched->ring_mirror_list)) + if (list_empty(&sched->pending_list)) cancel_delayed_work(&sched->work_tdr); else mod_delayed_work(system_wq, &sched->work_tdr, remaining); @@ -272,7 +272,7 @@ static void drm_sched_job_begin(struct drm_sched_job *s_job) struct drm_gpu_scheduler *sched = s_job->sched; spin_lock(&sched->job_list_lock); - list_add_tail(&s_job->list, &sched->ring_mirror_list); + list_add_tail(&s_job->list, &sched->pending_list); drm_sched_start_timeout(sched); spin_unlock(&sched->job_list_lock); } @@ -286,7 +286,7 @@ static void drm_sched_job_timedout(struct work_struct *work) /* Protects against concurrent deletion in drm_sched_get_cleanup_job */ spin_lock(&sched->job_list_lock); - job = list_first_entry_or_null(&sched->ring_mirror_list, + job = list_first_entry_or_null(&sched->pending_list, struct drm_sched_job, list); if (job) { @@ -371,7 +371,7 @@ EXPORT_SYMBOL(drm_sched_increase_karma); * Stop the scheduler and also removes and frees all completed jobs. * Note: bad job will not be freed as it might be used later and so it's * callers responsibility to release it manually if it's not part of the - * mirror list any more. + * pending list any more. * */ void drm_sched_stop(struct drm_gpu_scheduler *sched, struct drm_sched_job *bad) @@ -392,15 +392,15 @@ void drm_sched_stop(struct drm_gpu_scheduler *sched, struct drm_sched_job *bad) * Add at the head of the queue to reflect it was the earliest * job extracted. */ - list_add(&bad->list, &sched->ring_mirror_list); + list_add(&bad->list, &sched->pending_list); /* * Iterate the job list from later to earlier one and either deactive - * their HW callbacks or remove them from mirror list if they already + * their HW callbacks or remove them from pending list if they already * signaled. * This iteration is thread safe as sched thread is stopped. */ - list_for_each_entry_safe_reverse(s_job, tmp, &sched->ring_mirror_list, + list_for_each_entry_safe_reverse(s_job, tmp, &sched->pending_list, list) { if (s_job->s_fence->parent && dma_fence_remove_callback(s_job->s_fence->parent, @@ -408,7 +408,7 @@ void drm_sched_stop(struct drm_gpu_scheduler *sched, struct drm_sched_job *bad) atomic_dec(&sched->hw_rq_count); } else { /* - * remove job from ring_mirror_list. + * remove job from pending_list. * Locking here is for concurrent resume timeout */ spin_lock(&sched->job_list_lock); @@ -463,7 +463,7 @@ void drm_sched_start(struct drm_gpu_scheduler *sched, bool full_recovery) * so no new jobs are being inserted or removed. Also concurrent * GPU recovers can't run in parallel. */ - list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, list) { + list_for_each_entry_safe(s_job, tmp, &sched->pending_list, list) { struct dma_fence *fence = s_job->s_fence->parent; atomic_inc(&sched->hw_rq_count); @@ -494,7 +494,7 @@ void drm_sched_start(struct drm_gpu_scheduler *sched, bool full_recovery) EXPORT_SYMBOL(drm_sched_start); /** - * drm_sched_resubmit_jobs - helper to relunch job from mirror ring list + * drm_sched_resubmit_jobs - helper to relunch job from pending ring list * * @sched: scheduler instance * @@ -506,7 +506,7 @@ void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched) bool found_guilty = false; struct dma_fence *fence; - list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, list) { + list_for_each_entry_safe(s_job, tmp, &sched->pending_list, list) { struct drm_sched_fence *s_fence = s_job->s_fence; if (!found_guilty && atomic_read(&s_job->karma) > sched->hang_limit) { @@ -665,7 +665,7 @@ static void drm_sched_process_job(struct dma_fence *f, struct dma_fence_cb *cb) * * @sched: scheduler instance * - * Returns the next finished job from the mirror list (if there is one) + * Returns the next finished job from the pending list (if there is one) * ready for it to be destroyed. */ static struct drm_sched_job * @@ -675,7 +675,7 @@ drm_sched_get_cleanup_job(struct drm_gpu_scheduler *sched) /* * Don't destroy jobs while the timeout worker is running OR thread - * is being parked and hence assumed to not touch ring_mirror_list + * is being parked and hence assumed to not touch pending_list */ if ((sched->timeout != MAX_SCHEDULE_TIMEOUT && !cancel_delayed_work(&sched->work_tdr)) || @@ -684,11 +684,11 @@ drm_sched_get_cleanup_job(struct drm_gpu_scheduler *sched) spin_lock(&sched->job_list_lock); - job = list_first_entry_or_null(&sched->ring_mirror_list, + job = list_first_entry_or_null(&sched->pending_list, struct drm_sched_job, list); if (job && dma_fence_is_signaled(&job->s_fence->finished)) { - /* remove job from ring_mirror_list */ + /* remove job from pending_list */ list_del_init(&job->list); } else { job = NULL; @@ -858,7 +858,7 @@ int drm_sched_init(struct drm_gpu_scheduler *sched, init_waitqueue_head(&sched->wake_up_worker); init_waitqueue_head(&sched->job_scheduled); - INIT_LIST_HEAD(&sched->ring_mirror_list); + INIT_LIST_HEAD(&sched->pending_list); spin_lock_init(&sched->job_list_lock); atomic_set(&sched->hw_rq_count, 0); INIT_DELAYED_WORK(&sched->work_tdr, drm_sched_job_timedout); diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index 3add0072bd37..2e0c368e19f6 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -174,7 +174,7 @@ struct drm_sched_fence *to_drm_sched_fence(struct dma_fence *f); * @sched: the scheduler instance on which this job is scheduled. * @s_fence: contains the fences for the scheduling of job. * @finish_cb: the callback for the finished fence. - * @node: used to append this struct to the @drm_gpu_scheduler.ring_mirror_list. + * @node: used to append this struct to the @drm_gpu_scheduler.pending_list. * @id: a unique id assigned to each job scheduled on the scheduler. * @karma: increment on every hang caused by this job. If this exceeds the hang * limit of the scheduler then the job is marked guilty and will not @@ -203,7 +203,7 @@ struct drm_sched_job { static inline bool drm_sched_invalidate_job(struct drm_sched_job *s_job, int threshold) { - return (s_job && atomic_inc_return(&s_job->karma) > threshold); + return s_job && atomic_inc_return(&s_job->karma) > threshold; } /** @@ -260,8 +260,8 @@ struct drm_sched_backend_ops { * @work_tdr: schedules a delayed call to @drm_sched_job_timedout after the * timeout interval is over. * @thread: the kthread on which the scheduler which run. - * @ring_mirror_list: the list of jobs which are currently in the job queue. - * @job_list_lock: lock to protect the ring_mirror_list. + * @pending_list: the list of jobs which are currently in the job queue. + * @job_list_lock: lock to protect the pending_list. * @hang_limit: once the hangs by a job crosses this limit then it is marked * guilty and it will be considered for scheduling further. * @score: score to help loadbalancer pick a idle sched @@ -282,7 +282,7 @@ struct drm_gpu_scheduler { atomic64_t job_id_count; struct delayed_work work_tdr; struct task_struct *thread; - struct list_head ring_mirror_list; + struct list_head pending_list; spinlock_t job_list_lock; int hang_limit; atomic_t score; -- cgit v1.2.3 From a8f65ba3c2655125c4933f2f6a7e1f4938859bba Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Tue, 8 Dec 2020 14:33:53 +0200 Subject: drm/dsc: add helper for calculating rc buffer size from DPCD Add a helper for calculating the rc buffer size from the DCPD offsets DP_DSC_RC_BUF_BLK_SIZE and DP_DSC_RC_BUF_SIZE. Cc: Alex Deucher Cc: Harry Wentland Cc: Manasi Navare Cc: Vandita Kulkarni Reviewed-by: Vandita Kulkarni Acked-by: Daniel Vetter Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/6c6aee22740fe7a8cf2b8e768bfda378850cf59a.1607429866.git.jani.nikula@intel.com --- drivers/gpu/drm/drm_dsc.c | 27 +++++++++++++++++++++++++++ include/drm/drm_dsc.h | 1 + 2 files changed, 28 insertions(+) (limited to 'include') diff --git a/drivers/gpu/drm/drm_dsc.c b/drivers/gpu/drm/drm_dsc.c index 09afbc01ea94..ff602f7ec65b 100644 --- a/drivers/gpu/drm/drm_dsc.c +++ b/drivers/gpu/drm/drm_dsc.c @@ -49,6 +49,33 @@ void drm_dsc_dp_pps_header_init(struct dp_sdp_header *pps_header) } EXPORT_SYMBOL(drm_dsc_dp_pps_header_init); +/** + * drm_dsc_dp_rc_buffer_size - get rc buffer size in bytes + * @rc_buffer_block_size: block size code, according to DPCD offset 62h + * @rc_buffer_size: number of blocks - 1, according to DPCD offset 63h + * + * return: + * buffer size in bytes, or 0 on invalid input + */ +int drm_dsc_dp_rc_buffer_size(u8 rc_buffer_block_size, u8 rc_buffer_size) +{ + int size = 1024 * (rc_buffer_size + 1); + + switch (rc_buffer_block_size) { + case DP_DSC_RC_BUF_BLK_SIZE_1: + return 1 * size; + case DP_DSC_RC_BUF_BLK_SIZE_4: + return 4 * size; + case DP_DSC_RC_BUF_BLK_SIZE_16: + return 16 * size; + case DP_DSC_RC_BUF_BLK_SIZE_64: + return 64 * size; + default: + return 0; + } +} +EXPORT_SYMBOL(drm_dsc_dp_rc_buffer_size); + /** * drm_dsc_pps_payload_pack() - Populates the DSC PPS * diff --git a/include/drm/drm_dsc.h b/include/drm/drm_dsc.h index 732f32740c86..e66560174ff1 100644 --- a/include/drm/drm_dsc.h +++ b/include/drm/drm_dsc.h @@ -602,6 +602,7 @@ struct drm_dsc_pps_infoframe { } __packed; void drm_dsc_dp_pps_header_init(struct dp_sdp_header *pps_header); +int drm_dsc_dp_rc_buffer_size(u8 rc_buffer_block_size, u8 rc_buffer_size); void drm_dsc_pps_payload_pack(struct drm_dsc_picture_parameter_set *pps_sdp, const struct drm_dsc_config *dsc_cfg); int drm_dsc_compute_rc_parameters(struct drm_dsc_config *vdsc_cfg); -- cgit v1.2.3 From c365d304d69ab2a38e1431323d17a216b7930e32 Mon Sep 17 00:00:00 2001 From: Luben Tuikov Date: Wed, 9 Dec 2020 17:31:42 -0500 Subject: drm/sched: Add missing structure comment MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a missing structure comment for the recently added @list member. Cc: Stephen Rothwell Cc: Daniel Vetter Cc: Christian König Fixes: 8935ff00e3b1 ("drm/scheduler: "node" --> "list"") Reported-by: Stephen Rothwell Signed-off-by: Luben Tuikov Reviewed-by: Christian König Signed-off-by: Christian König Link: https://patchwork.freedesktop.org/patch/406546/ --- include/drm/gpu_scheduler.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index 2e0c368e19f6..975e8a67947f 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -171,10 +171,10 @@ struct drm_sched_fence *to_drm_sched_fence(struct dma_fence *f); * struct drm_sched_job - A job to be run by an entity. * * @queue_node: used to append this struct to the queue of jobs in an entity. + * @list: a job participates in a "pending" and "done" lists. * @sched: the scheduler instance on which this job is scheduled. * @s_fence: contains the fences for the scheduling of job. * @finish_cb: the callback for the finished fence. - * @node: used to append this struct to the @drm_gpu_scheduler.pending_list. * @id: a unique id assigned to each job scheduled on the scheduler. * @karma: increment on every hang caused by this job. If this exceeds the hang * limit of the scheduler then the job is marked guilty and will not -- cgit v1.2.3 From 26e08a6da54c575c69a113ab0c41c2890c0d613d Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Fri, 4 Dec 2020 21:02:42 +0100 Subject: dma-buf: Fix kerneldoc formatting I wanted to look up something and noticed the hyperlink doesn't work. While fixing that also noticed a trivial kerneldoc comment typo in the same section, fix that too. Reviewed-by: Michael J. Ruhl Reviewed-by: Simon Ser Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20201204200242.2671481-1-daniel.vetter@ffwll.ch --- Documentation/driver-api/dma-buf.rst | 2 +- include/linux/dma-buf-map.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/Documentation/driver-api/dma-buf.rst b/Documentation/driver-api/dma-buf.rst index d6b2a195dbed..a2133d69872c 100644 --- a/Documentation/driver-api/dma-buf.rst +++ b/Documentation/driver-api/dma-buf.rst @@ -190,7 +190,7 @@ DMA Fence uABI/Sync File Indefinite DMA Fences ~~~~~~~~~~~~~~~~~~~~~ -At various times &dma_fence with an indefinite time until dma_fence_wait() +At various times struct dma_fence with an indefinite time until dma_fence_wait() finishes have been proposed. Examples include: * Future fences, used in HWC1 to signal when a buffer isn't used by the display diff --git a/include/linux/dma-buf-map.h b/include/linux/dma-buf-map.h index 583a3a1f9447..278d489e4bdd 100644 --- a/include/linux/dma-buf-map.h +++ b/include/linux/dma-buf-map.h @@ -122,7 +122,7 @@ struct dma_buf_map { /** * DMA_BUF_MAP_INIT_VADDR - Initializes struct dma_buf_map to an address in system memory - * @vaddr: A system-memory address + * @vaddr_: A system-memory address */ #define DMA_BUF_MAP_INIT_VADDR(vaddr_) \ { \ -- cgit v1.2.3 From e11bfb99d6ece23b772b57c29fa80448639fd6e5 Mon Sep 17 00:00:00 2001 From: Christian König Date: Wed, 9 Dec 2020 15:07:50 +0100 Subject: drm/ttm: cleanup BO size handling v3 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Based on an idea from Dave, but cleaned up a bit. We had multiple fields for essentially the same thing. Now bo->base.size is the original size of the BO in arbitrary units, usually bytes. bo->mem.num_pages is the size in number of pages in the resource domain of bo->mem.mem_type. v2: use the GEM object size instead of the BO size v3: fix printks in some places Signed-off-by: Christian König Reviewed-by: Huang Rui (v1) Acked-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/406831/ --- drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_object.h | 4 +-- drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 6 ++--- drivers/gpu/drm/amd/amdgpu/mes_v10_1.c | 2 +- drivers/gpu/drm/nouveau/nouveau_bo.c | 10 ++++---- drivers/gpu/drm/nouveau/nouveau_display.c | 8 +++--- drivers/gpu/drm/nouveau/nouveau_prime.c | 4 +-- drivers/gpu/drm/nouveau/nv17_fence.c | 2 +- drivers/gpu/drm/nouveau/nv50_fence.c | 2 +- drivers/gpu/drm/qxl/qxl_object.h | 2 +- drivers/gpu/drm/radeon/radeon_cs.c | 3 ++- drivers/gpu/drm/radeon/radeon_object.c | 13 +++++----- drivers/gpu/drm/radeon/radeon_object.h | 4 +-- drivers/gpu/drm/radeon/radeon_prime.c | 4 +-- drivers/gpu/drm/radeon/radeon_trace.h | 2 +- drivers/gpu/drm/radeon/radeon_ttm.c | 2 +- drivers/gpu/drm/ttm/ttm_bo.c | 35 +++++++++------------------ drivers/gpu/drm/ttm/ttm_bo_util.c | 12 ++++----- drivers/gpu/drm/ttm/ttm_bo_vm.c | 6 ++--- drivers/gpu/drm/ttm/ttm_tt.c | 2 +- drivers/gpu/drm/vmwgfx/vmwgfx_blit.c | 4 +-- drivers/gpu/drm/vmwgfx/vmwgfx_bo.c | 6 ++--- drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c | 2 +- drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c | 4 +-- drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c | 5 ++-- drivers/gpu/drm/vmwgfx/vmwgfx_kms.c | 2 +- drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c | 8 +++--- drivers/gpu/drm/vmwgfx/vmwgfx_resource.c | 2 +- drivers/gpu/drm/vmwgfx/vmwgfx_shader.c | 3 +-- drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c | 4 +-- drivers/gpu/drm/vmwgfx/vmwgfx_surface.c | 7 +++--- include/drm/ttm/ttm_bo_api.h | 9 +++---- include/drm/ttm/ttm_resource.h | 1 - 36 files changed, 84 insertions(+), 104 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index e5919efca870..c4c93f19d273 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -269,7 +269,7 @@ static struct sg_table *amdgpu_dma_buf_map(struct dma_buf_attachment *attach, case TTM_PL_TT: sgt = drm_prime_pages_to_sg(obj->dev, bo->tbo.ttm->pages, - bo->tbo.num_pages); + bo->tbo.ttm->num_pages); if (IS_ERR(sgt)) return sgt; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index 056cb87d09ea..52bcd1b5582f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -121,7 +121,7 @@ uint64_t amdgpu_gmc_agp_addr(struct ttm_buffer_object *bo) { struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev); - if (bo->num_pages != 1 || bo->ttm->caching == ttm_cached) + if (bo->ttm->num_pages != 1 || bo->ttm->caching == ttm_cached) return AMDGPU_BO_INVALID_OFFSET; if (bo->ttm->dma_address[0] + PAGE_SIZE >= adev->gmc.agp_size) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index c6c9723d3d8a..381ecc4788d5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -787,7 +787,7 @@ int amdgpu_bo_kmap(struct amdgpu_bo *bo, void **ptr) if (r < 0) return r; - r = ttm_bo_kmap(&bo->tbo, 0, bo->tbo.num_pages, &bo->kmap); + r = ttm_bo_kmap(&bo->tbo, 0, bo->tbo.mem.num_pages, &bo->kmap); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h index ed47cbac4f75..a99a5cde42dd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h @@ -174,12 +174,12 @@ static inline void amdgpu_bo_unreserve(struct amdgpu_bo *bo) static inline unsigned long amdgpu_bo_size(struct amdgpu_bo *bo) { - return bo->tbo.num_pages << PAGE_SHIFT; + return bo->tbo.base.size; } static inline unsigned amdgpu_bo_ngpu_pages(struct amdgpu_bo *bo) { - return (bo->tbo.num_pages << PAGE_SHIFT) / AMDGPU_GPU_PAGE_SIZE; + return bo->tbo.base.size / AMDGPU_GPU_PAGE_SIZE; } static inline unsigned amdgpu_bo_gpu_page_alignment(struct amdgpu_bo *bo) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h index ee9480d14cbc..20715ddbb746 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h @@ -127,7 +127,7 @@ TRACE_EVENT(amdgpu_bo_create, TP_fast_assign( __entry->bo = bo; - __entry->pages = bo->tbo.num_pages; + __entry->pages = bo->tbo.mem.num_pages; __entry->type = bo->tbo.mem.mem_type; __entry->prefer = bo->preferred_domains; __entry->allow = bo->allowed_domains; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index ec93d4fdabbd..5346891a3f73 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -636,7 +636,7 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict, out: /* update statistics */ - atomic64_add((u64)bo->num_pages << PAGE_SHIFT, &adev->num_bytes_moved); + atomic64_add(bo->base.size, &adev->num_bytes_moved); amdgpu_bo_move_notify(bo, evict, new_mem); return 0; } @@ -2131,7 +2131,7 @@ int amdgpu_fill_buffer(struct amdgpu_bo *bo, return r; } - num_pages = bo->tbo.num_pages; + num_pages = bo->tbo.mem.num_pages; mm_node = bo->tbo.mem.mm_node; num_loops = 0; while (num_pages) { @@ -2161,7 +2161,7 @@ int amdgpu_fill_buffer(struct amdgpu_bo *bo, } } - num_pages = bo->tbo.num_pages; + num_pages = bo->tbo.mem.num_pages; mm_node = bo->tbo.mem.mm_node; while (num_pages) { diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v10_1.c b/drivers/gpu/drm/amd/amdgpu/mes_v10_1.c index 985e454463e1..7f30629f21a2 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v10_1.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v10_1.c @@ -554,7 +554,7 @@ static int mes_v10_1_allocate_eop_buf(struct amdgpu_device *adev) return r; } - memset(eop, 0, adev->mes.eop_gpu_obj->tbo.mem.size); + memset(eop, 0, adev->mes.eop_gpu_obj->tbo.base.size); amdgpu_bo_kunmap(adev->mes.eop_gpu_obj); amdgpu_bo_unreserve(adev->mes.eop_gpu_obj); diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index bc542ac4c4b6..c1a675b8fc43 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -473,10 +473,10 @@ nouveau_bo_pin(struct nouveau_bo *nvbo, uint32_t domain, bool contig) switch (bo->mem.mem_type) { case TTM_PL_VRAM: - drm->gem.vram_available -= bo->mem.size; + drm->gem.vram_available -= bo->base.size; break; case TTM_PL_TT: - drm->gem.gart_available -= bo->mem.size; + drm->gem.gart_available -= bo->base.size; break; default: break; @@ -504,10 +504,10 @@ nouveau_bo_unpin(struct nouveau_bo *nvbo) if (!nvbo->bo.pin_count) { switch (bo->mem.mem_type) { case TTM_PL_VRAM: - drm->gem.vram_available += bo->mem.size; + drm->gem.vram_available += bo->base.size; break; case TTM_PL_TT: - drm->gem.gart_available += bo->mem.size; + drm->gem.gart_available += bo->base.size; break; default: break; @@ -913,7 +913,7 @@ nouveau_bo_vm_bind(struct ttm_buffer_object *bo, struct ttm_resource *new_reg, return 0; if (drm->client.device.info.family >= NV_DEVICE_INFO_V0_CELSIUS) { - *new_tile = nv10_bo_set_tiling(dev, offset, new_reg->size, + *new_tile = nv10_bo_set_tiling(dev, offset, bo->base.size, nvbo->mode, nvbo->zeta); } diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c index bceb48a2dfca..17831ee897ea 100644 --- a/drivers/gpu/drm/nouveau/nouveau_display.c +++ b/drivers/gpu/drm/nouveau/nouveau_display.c @@ -286,11 +286,11 @@ nouveau_check_bl_size(struct nouveau_drm *drm, struct nouveau_bo *nvbo, bl_size = bw * bh * (1 << tile_mode) * gob_size; - DRM_DEBUG_KMS("offset=%u stride=%u h=%u tile_mode=0x%02x bw=%u bh=%u gob_size=%u bl_size=%llu size=%lu\n", + DRM_DEBUG_KMS("offset=%u stride=%u h=%u tile_mode=0x%02x bw=%u bh=%u gob_size=%u bl_size=%llu size=%zu\n", offset, stride, h, tile_mode, bw, bh, gob_size, bl_size, - nvbo->bo.mem.size); + nvbo->bo.base.size); - if (bl_size + offset > nvbo->bo.mem.size) + if (bl_size + offset > nvbo->bo.base.size) return -ERANGE; return 0; @@ -363,7 +363,7 @@ nouveau_framebuffer_new(struct drm_device *dev, } else { uint32_t size = mode_cmd->pitches[i] * height; - if (size + mode_cmd->offsets[i] > nvbo->bo.mem.size) + if (size + mode_cmd->offsets[i] > nvbo->bo.base.size) return -ERANGE; } } diff --git a/drivers/gpu/drm/nouveau/nouveau_prime.c b/drivers/gpu/drm/nouveau/nouveau_prime.c index 2f16b5249283..347488685f74 100644 --- a/drivers/gpu/drm/nouveau/nouveau_prime.c +++ b/drivers/gpu/drm/nouveau/nouveau_prime.c @@ -30,9 +30,9 @@ struct sg_table *nouveau_gem_prime_get_sg_table(struct drm_gem_object *obj) { struct nouveau_bo *nvbo = nouveau_gem_object(obj); - int npages = nvbo->bo.num_pages; - return drm_prime_pages_to_sg(obj->dev, nvbo->bo.ttm->pages, npages); + return drm_prime_pages_to_sg(obj->dev, nvbo->bo.ttm->pages, + nvbo->bo.ttm->num_pages); } struct drm_gem_object *nouveau_gem_prime_import_sg_table(struct drm_device *dev, diff --git a/drivers/gpu/drm/nouveau/nv17_fence.c b/drivers/gpu/drm/nouveau/nv17_fence.c index 1253fdec712d..b1cd8d7dd87d 100644 --- a/drivers/gpu/drm/nouveau/nv17_fence.c +++ b/drivers/gpu/drm/nouveau/nv17_fence.c @@ -80,7 +80,7 @@ nv17_fence_context_new(struct nouveau_channel *chan) struct nv10_fence_chan *fctx; struct ttm_resource *reg = &priv->bo->bo.mem; u32 start = reg->start * PAGE_SIZE; - u32 limit = start + reg->size - 1; + u32 limit = start + priv->bo->bo.base.size - 1; int ret = 0; fctx = chan->fence = kzalloc(sizeof(*fctx), GFP_KERNEL); diff --git a/drivers/gpu/drm/nouveau/nv50_fence.c b/drivers/gpu/drm/nouveau/nv50_fence.c index 447238e3cbe7..1625826505f6 100644 --- a/drivers/gpu/drm/nouveau/nv50_fence.c +++ b/drivers/gpu/drm/nouveau/nv50_fence.c @@ -39,7 +39,7 @@ nv50_fence_context_new(struct nouveau_channel *chan) struct nv10_fence_chan *fctx; struct ttm_resource *reg = &priv->bo->bo.mem; u32 start = reg->start * PAGE_SIZE; - u32 limit = start + reg->size - 1; + u32 limit = start + priv->bo->bo.base.size - 1; int ret; fctx = chan->fence = kzalloc(sizeof(*fctx), GFP_KERNEL); diff --git a/drivers/gpu/drm/qxl/qxl_object.h b/drivers/gpu/drm/qxl/qxl_object.h index ebf24c9d2bf2..e60a8f88e226 100644 --- a/drivers/gpu/drm/qxl/qxl_object.h +++ b/drivers/gpu/drm/qxl/qxl_object.h @@ -50,7 +50,7 @@ static inline void qxl_bo_unreserve(struct qxl_bo *bo) static inline unsigned long qxl_bo_size(struct qxl_bo *bo) { - return bo->tbo.num_pages << PAGE_SHIFT; + return bo->tbo.base.size; } static inline u64 qxl_bo_mmap_offset(struct qxl_bo *bo) diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c index 21ce2f9502c0..4f35c32957be 100644 --- a/drivers/gpu/drm/radeon/radeon_cs.c +++ b/drivers/gpu/drm/radeon/radeon_cs.c @@ -401,7 +401,8 @@ static int cmp_size_smaller_first(void *priv, struct list_head *a, struct radeon_bo_list *lb = list_entry(b, struct radeon_bo_list, tv.head); /* Sort A before B if A is smaller. */ - return (int)la->robj->tbo.num_pages - (int)lb->robj->tbo.num_pages; + return (int)la->robj->tbo.mem.num_pages - + (int)lb->robj->tbo.mem.num_pages; } /** diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c index ab81e35cb060..9a999930e3dd 100644 --- a/drivers/gpu/drm/radeon/radeon_object.c +++ b/drivers/gpu/drm/radeon/radeon_object.c @@ -54,20 +54,19 @@ static void radeon_update_memory_usage(struct radeon_bo *bo, unsigned mem_type, int sign) { struct radeon_device *rdev = bo->rdev; - u64 size = (u64)bo->tbo.num_pages << PAGE_SHIFT; switch (mem_type) { case TTM_PL_TT: if (sign > 0) - atomic64_add(size, &rdev->gtt_usage); + atomic64_add(bo->tbo.base.size, &rdev->gtt_usage); else - atomic64_sub(size, &rdev->gtt_usage); + atomic64_sub(bo->tbo.base.size, &rdev->gtt_usage); break; case TTM_PL_VRAM: if (sign > 0) - atomic64_add(size, &rdev->vram_usage); + atomic64_add(bo->tbo.base.size, &rdev->vram_usage); else - atomic64_sub(size, &rdev->vram_usage); + atomic64_sub(bo->tbo.base.size, &rdev->vram_usage); break; } } @@ -256,7 +255,7 @@ int radeon_bo_kmap(struct radeon_bo *bo, void **ptr) } return 0; } - r = ttm_bo_kmap(&bo->tbo, 0, bo->tbo.num_pages, &bo->kmap); + r = ttm_bo_kmap(&bo->tbo, 0, bo->tbo.mem.num_pages, &bo->kmap); if (r) { return r; } @@ -610,7 +609,7 @@ int radeon_bo_get_surface_reg(struct radeon_bo *bo) out: radeon_set_surface_reg(rdev, i, bo->tiling_flags, bo->pitch, bo->tbo.mem.start << PAGE_SHIFT, - bo->tbo.num_pages << PAGE_SHIFT); + bo->tbo.base.size); return 0; } diff --git a/drivers/gpu/drm/radeon/radeon_object.h b/drivers/gpu/drm/radeon/radeon_object.h index d606e9a935e3..9896d8231fe5 100644 --- a/drivers/gpu/drm/radeon/radeon_object.h +++ b/drivers/gpu/drm/radeon/radeon_object.h @@ -109,12 +109,12 @@ static inline u64 radeon_bo_gpu_offset(struct radeon_bo *bo) static inline unsigned long radeon_bo_size(struct radeon_bo *bo) { - return bo->tbo.num_pages << PAGE_SHIFT; + return bo->tbo.base.size; } static inline unsigned radeon_bo_ngpu_pages(struct radeon_bo *bo) { - return (bo->tbo.num_pages << PAGE_SHIFT) / RADEON_GPU_PAGE_SIZE; + return bo->tbo.base.size / RADEON_GPU_PAGE_SIZE; } static inline unsigned radeon_bo_gpu_page_alignment(struct radeon_bo *bo) diff --git a/drivers/gpu/drm/radeon/radeon_prime.c b/drivers/gpu/drm/radeon/radeon_prime.c index 088d39a51c0d..0a09dbaba289 100644 --- a/drivers/gpu/drm/radeon/radeon_prime.c +++ b/drivers/gpu/drm/radeon/radeon_prime.c @@ -34,9 +34,9 @@ struct sg_table *radeon_gem_prime_get_sg_table(struct drm_gem_object *obj) { struct radeon_bo *bo = gem_to_radeon_bo(obj); - int npages = bo->tbo.num_pages; - return drm_prime_pages_to_sg(obj->dev, bo->tbo.ttm->pages, npages); + return drm_prime_pages_to_sg(obj->dev, bo->tbo.ttm->pages, + bo->tbo.ttm->num_pages); } struct drm_gem_object *radeon_gem_prime_import_sg_table(struct drm_device *dev, diff --git a/drivers/gpu/drm/radeon/radeon_trace.h b/drivers/gpu/drm/radeon/radeon_trace.h index c93f3ab3c4e3..1729cb9a95c5 100644 --- a/drivers/gpu/drm/radeon/radeon_trace.h +++ b/drivers/gpu/drm/radeon/radeon_trace.h @@ -22,7 +22,7 @@ TRACE_EVENT(radeon_bo_create, TP_fast_assign( __entry->bo = bo; - __entry->pages = bo->tbo.num_pages; + __entry->pages = bo->tbo.mem.num_pages; ), TP_printk("bo=%p, pages=%u", __entry->bo, __entry->pages) ); diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index a3432c6343ba..ea365ac6f4f1 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -274,7 +274,7 @@ static int radeon_bo_move(struct ttm_buffer_object *bo, bool evict, out: /* update statistics */ - atomic64_add((u64)bo->num_pages << PAGE_SHIFT, &rdev->num_bytes_moved); + atomic64_add(bo->base.size, &rdev->num_bytes_moved); radeon_bo_move_notify(bo, evict, new_mem); return 0; } diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 02cc5d247c0d..2196e3d3ef29 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -72,9 +72,9 @@ static void ttm_bo_mem_space_debug(struct ttm_buffer_object *bo, struct ttm_resource_manager *man; int i, mem_type; - drm_printf(&p, "No space for %p (%lu pages, %luK, %luM)\n", - bo, bo->mem.num_pages, bo->mem.size >> 10, - bo->mem.size >> 20); + drm_printf(&p, "No space for %p (%lu pages, %zuK, %zuM)\n", + bo, bo->mem.num_pages, bo->base.size >> 10, + bo->base.size >> 20); for (i = 0; i < placement->num_placement; i++) { mem_type = placement->placement[i].mem_type; drm_printf(&p, " placement[%d]=0x%08X (%d)\n", @@ -268,7 +268,7 @@ static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo, goto out_err; } - ctx->bytes_moved += bo->num_pages << PAGE_SHIFT; + ctx->bytes_moved += bo->base.size; return 0; out_err: @@ -985,8 +985,7 @@ static int ttm_bo_move_buffer(struct ttm_buffer_object *bo, memset(&hop, 0, sizeof(hop)); - mem.num_pages = bo->num_pages; - mem.size = mem.num_pages << PAGE_SHIFT; + mem.num_pages = PAGE_ALIGN(bo->base.size) >> PAGE_SHIFT; mem.page_alignment = bo->mem.page_alignment; mem.bus.offset = 0; mem.bus.addr = NULL; @@ -1102,7 +1101,7 @@ EXPORT_SYMBOL(ttm_bo_validate); int ttm_bo_init_reserved(struct ttm_bo_device *bdev, struct ttm_buffer_object *bo, - unsigned long size, + size_t size, enum ttm_bo_type type, struct ttm_placement *placement, uint32_t page_alignment, @@ -1113,9 +1112,8 @@ int ttm_bo_init_reserved(struct ttm_bo_device *bdev, void (*destroy) (struct ttm_buffer_object *)) { struct ttm_mem_global *mem_glob = &ttm_mem_glob; - int ret = 0; - unsigned long num_pages; bool locked; + int ret = 0; ret = ttm_mem_global_alloc(mem_glob, acc_size, ctx); if (ret) { @@ -1127,16 +1125,6 @@ int ttm_bo_init_reserved(struct ttm_bo_device *bdev, return -ENOMEM; } - num_pages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT; - if (num_pages == 0) { - pr_err("Illegal buffer object size\n"); - if (destroy) - (*destroy)(bo); - else - kfree(bo); - ttm_mem_global_free(mem_glob, acc_size); - return -EINVAL; - } bo->destroy = destroy ? destroy : ttm_bo_default_destroy; kref_init(&bo->kref); @@ -1145,10 +1133,8 @@ int ttm_bo_init_reserved(struct ttm_bo_device *bdev, INIT_LIST_HEAD(&bo->swap); bo->bdev = bdev; bo->type = type; - bo->num_pages = num_pages; - bo->mem.size = num_pages << PAGE_SHIFT; bo->mem.mem_type = TTM_PL_SYSTEM; - bo->mem.num_pages = bo->num_pages; + bo->mem.num_pages = PAGE_ALIGN(size) >> PAGE_SHIFT; bo->mem.mm_node = NULL; bo->mem.page_alignment = page_alignment; bo->mem.bus.offset = 0; @@ -1166,9 +1152,10 @@ int ttm_bo_init_reserved(struct ttm_bo_device *bdev, } if (!ttm_bo_uses_embedded_gem_object(bo)) { /* - * bo.gem is not initialized, so we have to setup the + * bo.base is not initialized, so we have to setup the * struct elements we want use regardless. */ + bo->base.size = size; dma_resv_init(&bo->base._resv); drm_vma_node_reset(&bo->base.vma_node); } @@ -1210,7 +1197,7 @@ EXPORT_SYMBOL(ttm_bo_init_reserved); int ttm_bo_init(struct ttm_bo_device *bdev, struct ttm_buffer_object *bo, - unsigned long size, + size_t size, enum ttm_bo_type type, struct ttm_placement *placement, uint32_t page_alignment, diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c index 5bbc1339d28e..398d5013fc39 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_util.c +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c @@ -431,9 +431,9 @@ int ttm_bo_kmap(struct ttm_buffer_object *bo, map->virtual = NULL; map->bo = bo; - if (num_pages > bo->num_pages) + if (num_pages > bo->mem.num_pages) return -EINVAL; - if (start_page > bo->num_pages) + if ((start_page + num_pages) > bo->mem.num_pages) return -EINVAL; ret = ttm_mem_io_reserve(bo->bdev, &bo->mem); @@ -485,14 +485,14 @@ int ttm_bo_vmap(struct ttm_buffer_object *bo, struct dma_buf_map *map) if (mem->bus.is_iomem) { void __iomem *vaddr_iomem; - size_t size = bo->num_pages << PAGE_SHIFT; if (mem->bus.addr) vaddr_iomem = (void __iomem *)mem->bus.addr; else if (mem->bus.caching == ttm_write_combined) - vaddr_iomem = ioremap_wc(mem->bus.offset, size); + vaddr_iomem = ioremap_wc(mem->bus.offset, + bo->base.size); else - vaddr_iomem = ioremap(mem->bus.offset, size); + vaddr_iomem = ioremap(mem->bus.offset, bo->base.size); if (!vaddr_iomem) return -ENOMEM; @@ -517,7 +517,7 @@ int ttm_bo_vmap(struct ttm_buffer_object *bo, struct dma_buf_map *map) * or to make the buffer object look contiguous. */ prot = ttm_io_prot(bo, mem, PAGE_KERNEL); - vaddr = vmap(ttm->pages, bo->num_pages, 0, prot); + vaddr = vmap(ttm->pages, ttm->num_pages, 0, prot); if (!vaddr) return -ENOMEM; diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c index 144a4940b6b6..6dc96cf66744 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_vm.c +++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c @@ -198,7 +198,7 @@ static vm_fault_t ttm_bo_vm_insert_huge(struct vm_fault *vmf, /* Fault should not cross bo boundary. */ page_offset &= ~(fault_page_size - 1); - if (page_offset + fault_page_size > bo->num_pages) + if (page_offset + fault_page_size > bo->mem.num_pages) goto out_fallback; if (bo->mem.bus.is_iomem) @@ -306,7 +306,7 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf, page_last = vma_pages(vma) + vma->vm_pgoff - drm_vma_node_start(&bo->base.vma_node); - if (unlikely(page_offset >= bo->num_pages)) + if (unlikely(page_offset >= bo->mem.num_pages)) return VM_FAULT_SIGBUS; prot = ttm_io_prot(bo, &bo->mem, prot); @@ -469,7 +469,7 @@ int ttm_bo_vm_access(struct vm_area_struct *vma, unsigned long addr, << PAGE_SHIFT); int ret; - if (len < 1 || (offset + len) >> PAGE_SHIFT > bo->num_pages) + if (len < 1 || (offset + len) >> PAGE_SHIFT > bo->mem.num_pages) return -EIO; ret = ttm_bo_reserve(bo, true, false, NULL); diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c index 77ba784425dd..7f75a13163f0 100644 --- a/drivers/gpu/drm/ttm/ttm_tt.c +++ b/drivers/gpu/drm/ttm/ttm_tt.c @@ -129,7 +129,7 @@ static void ttm_tt_init_fields(struct ttm_tt *ttm, uint32_t page_flags, enum ttm_caching caching) { - ttm->num_pages = bo->num_pages; + ttm->num_pages = PAGE_ALIGN(bo->base.size) >> PAGE_SHIFT; ttm->caching = ttm_cached; ttm->page_flags = page_flags; ttm->dma_address = NULL; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c index f21881e087db..9f2779ddcf08 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c @@ -482,8 +482,8 @@ int vmw_bo_cpu_blit(struct ttm_buffer_object *dst, d.src_addr = NULL; d.dst_pages = dst->ttm->pages; d.src_pages = src->ttm->pages; - d.dst_num_pages = dst->num_pages; - d.src_num_pages = src->num_pages; + d.dst_num_pages = dst->mem.num_pages; + d.src_num_pages = src->mem.num_pages; d.dst_prot = ttm_io_prot(dst, &dst->mem, PAGE_KERNEL); d.src_prot = ttm_io_prot(src, &src->mem, PAGE_KERNEL); d.diff = diff; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c index 263d76ae43f0..63dbc44eebe0 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c @@ -223,7 +223,7 @@ int vmw_bo_pin_in_start_of_vram(struct vmw_private *dev_priv, uint32_t new_flags; place = vmw_vram_placement.placement[0]; - place.lpfn = bo->num_pages; + place.lpfn = bo->mem.num_pages; placement.num_placement = 1; placement.placement = &place; placement.num_busy_placement = 1; @@ -244,7 +244,7 @@ int vmw_bo_pin_in_start_of_vram(struct vmw_private *dev_priv, * that situation. */ if (bo->mem.mem_type == TTM_PL_VRAM && - bo->mem.start < bo->num_pages && + bo->mem.start < bo->mem.num_pages && bo->mem.start > 0 && buf->base.pin_count == 0) { ctx.interruptible = false; @@ -391,7 +391,7 @@ void *vmw_bo_map_and_cache(struct vmw_buffer_object *vbo) if (virtual) return virtual; - ret = ttm_bo_kmap(bo, 0, bo->num_pages, &vbo->map); + ret = ttm_bo_kmap(bo, 0, bo->mem.num_pages, &vbo->map); if (ret) DRM_ERROR("Buffer object map failed: %d.\n", ret); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c index 984d8884357d..a077e420d2ff 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c @@ -430,7 +430,7 @@ static int vmw_cotable_resize(struct vmw_resource *res, size_t new_size) * Do a page by page copy of COTables. This eliminates slow vmap()s. * This should really be a TTM utility. */ - for (i = 0; i < old_bo->num_pages; ++i) { + for (i = 0; i < old_bo->mem.num_pages; ++i) { bool dummy; ret = ttm_bo_kmap(old_bo, i, 1, &old_map); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index e67e2e8f6e6f..6c016001721d 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -1042,7 +1042,7 @@ static int vmw_query_bo_switch_prepare(struct vmw_private *dev_priv, if (unlikely(new_query_bo != sw_context->cur_query_bo)) { - if (unlikely(new_query_bo->base.num_pages > 4)) { + if (unlikely(new_query_bo->base.mem.num_pages > 4)) { VMW_DEBUG_USER("Query buffer too large.\n"); return -EINVAL; } @@ -1541,7 +1541,7 @@ static int vmw_cmd_dma(struct vmw_private *dev_priv, return ret; /* Make sure DMA doesn't cross BO boundaries. */ - bo_size = vmw_bo->base.num_pages * PAGE_SIZE; + bo_size = vmw_bo->base.base.size; if (unlikely(cmd->body.guest.ptr.offset > bo_size)) { VMW_DEBUG_USER("Invalid DMA offset.\n"); return -EINVAL; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c index 8fe26e32f920..1774960d1b89 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c @@ -64,20 +64,19 @@ static int vmw_gmrid_man_get_node(struct ttm_resource_manager *man, spin_lock(&gman->lock); if (gman->max_gmr_pages > 0) { - gman->used_gmr_pages += bo->num_pages; + gman->used_gmr_pages += mem->num_pages; if (unlikely(gman->used_gmr_pages > gman->max_gmr_pages)) goto nospace; } mem->mm_node = gman; mem->start = id; - mem->num_pages = bo->num_pages; spin_unlock(&gman->lock); return 0; nospace: - gman->used_gmr_pages -= bo->num_pages; + gman->used_gmr_pages -= mem->num_pages; spin_unlock(&gman->lock); ida_free(&gman->gmr_ida, id); return -ENOSPC; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index bc67f2b930e1..7dc96125e5c2 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -1220,7 +1220,7 @@ static int vmw_kms_new_framebuffer_bo(struct vmw_private *dev_priv, int ret; requested_size = mode_cmd->height * mode_cmd->pitches[0]; - if (unlikely(requested_size > bo->base.num_pages * PAGE_SIZE)) { + if (unlikely(requested_size > bo->base.base.size)) { DRM_ERROR("Screen buffer object size is too small " "for requested mode.\n"); return -EINVAL; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c b/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c index 0b76b3d17d4c..0a900afc66ff 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c @@ -232,7 +232,7 @@ void vmw_bo_dirty_unmap(struct vmw_buffer_object *vbo, int vmw_bo_dirty_add(struct vmw_buffer_object *vbo) { struct vmw_bo_dirty *dirty = vbo->dirty; - pgoff_t num_pages = vbo->base.num_pages; + pgoff_t num_pages = vbo->base.mem.num_pages; size_t size, acc_size; int ret; static struct ttm_operation_ctx ctx = { @@ -413,7 +413,7 @@ vm_fault_t vmw_bo_vm_mkwrite(struct vm_fault *vmf) return ret; page_offset = vmf->pgoff - drm_vma_node_start(&bo->base.vma_node); - if (unlikely(page_offset >= bo->num_pages)) { + if (unlikely(page_offset >= bo->mem.num_pages)) { ret = VM_FAULT_SIGBUS; goto out_unlock; } @@ -456,7 +456,7 @@ vm_fault_t vmw_bo_vm_fault(struct vm_fault *vmf) page_offset = vmf->pgoff - drm_vma_node_start(&bo->base.vma_node); - if (page_offset >= bo->num_pages || + if (page_offset >= bo->mem.num_pages || vmw_resources_clean(vbo, page_offset, page_offset + PAGE_SIZE, &allowed_prefault)) { @@ -531,7 +531,7 @@ vm_fault_t vmw_bo_vm_huge_fault(struct vm_fault *vmf, page_offset = vmf->pgoff - drm_vma_node_start(&bo->base.vma_node); - if (page_offset >= bo->num_pages || + if (page_offset >= bo->mem.num_pages || vmw_resources_clean(vbo, page_offset, page_offset + PAGE_SIZE, &allowed_prefault)) { diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c index 00b535831a7a..f6e8fdfc76e5 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c @@ -360,7 +360,7 @@ static int vmw_resource_buf_alloc(struct vmw_resource *res, int ret; if (likely(res->backup)) { - BUG_ON(res->backup->base.num_pages * PAGE_SIZE < size); + BUG_ON(res->backup->base.base.size < size); return 0; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c index f328aa5839a2..e76a720f841e 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c @@ -856,8 +856,7 @@ static int vmw_shader_define(struct drm_device *dev, struct drm_file *file_priv, return ret; } - if ((u64)buffer->base.num_pages * PAGE_SIZE < - (u64)size + (u64)offset) { + if ((u64)buffer->base.base.size < (u64)size + (u64)offset) { VMW_DEBUG_USER("Illegal buffer- or shader size.\n"); ret = -EINVAL; goto out_bad_arg; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c index 5b04ec047ef3..27ab2c50312b 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c @@ -512,7 +512,7 @@ static void vmw_stdu_bo_fifo_commit(struct vmw_kms_dirty *dirty) cmd->body.host.mipmap = 0; cmd->body.transfer = ddirty->transfer; suffix->suffixSize = sizeof(*suffix); - suffix->maximumOffset = ddirty->buf->base.num_pages * PAGE_SIZE; + suffix->maximumOffset = ddirty->buf->base.base.size; if (ddirty->transfer == SVGA3D_WRITE_HOST_VRAM) { blit_size += sizeof(struct vmw_stdu_update); @@ -1238,7 +1238,7 @@ static uint32_t vmw_stdu_bo_populate_update(struct vmw_du_update_plane *update, vfbbo = container_of(update->vfb, typeof(*vfbbo), base); suffix->suffixSize = sizeof(*suffix); - suffix->maximumOffset = vfbbo->buffer->base.num_pages * PAGE_SIZE; + suffix->maximumOffset = vfbbo->buffer->base.base.size; vmw_stdu_populate_update(&suffix[1], stdu->base.unit, bb->x1, bb->x2, bb->y1, bb->y2); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c index 3914bfee0533..fa9be30bec6c 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c @@ -1550,8 +1550,7 @@ vmw_gb_surface_define_internal(struct drm_device *dev, &res->backup, &user_srf->backup_base); if (ret == 0) { - if (res->backup->base.num_pages * PAGE_SIZE < - res->backup_size) { + if (res->backup->base.base.size < res->backup_size) { VMW_DEBUG_USER("Surface backup buffer too small.\n"); vmw_bo_unreference(&res->backup); ret = -EINVAL; @@ -1614,7 +1613,7 @@ vmw_gb_surface_define_internal(struct drm_device *dev, if (res->backup) { rep->buffer_map_handle = drm_vma_node_offset_addr(&res->backup->base.base.vma_node); - rep->buffer_size = res->backup->base.num_pages * PAGE_SIZE; + rep->buffer_size = res->backup->base.base.size; rep->buffer_handle = backup_handle; } else { rep->buffer_map_handle = 0; @@ -1692,7 +1691,7 @@ vmw_gb_surface_reference_internal(struct drm_device *dev, rep->crep.buffer_handle = backup_handle; rep->crep.buffer_map_handle = drm_vma_node_offset_addr(&srf->res.backup->base.base.vma_node); - rep->crep.buffer_size = srf->res.backup->base.num_pages * PAGE_SIZE; + rep->crep.buffer_size = srf->res.backup->base.base.size; rep->creq.version = drm_vmw_gb_surface_v1; rep->creq.svga3d_flags_upper_32_bits = diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h index 79b9367e0ffd..0d4e3fccaa8a 100644 --- a/include/drm/ttm/ttm_bo_api.h +++ b/include/drm/ttm/ttm_bo_api.h @@ -125,7 +125,6 @@ struct ttm_buffer_object { struct ttm_bo_device *bdev; enum ttm_bo_type type; void (*destroy) (struct ttm_buffer_object *); - unsigned long num_pages; size_t acc_size; /** @@ -397,13 +396,11 @@ size_t ttm_bo_dma_acc_size(struct ttm_bo_device *bdev, int ttm_bo_init_reserved(struct ttm_bo_device *bdev, struct ttm_buffer_object *bo, - unsigned long size, - enum ttm_bo_type type, + size_t size, enum ttm_bo_type type, struct ttm_placement *placement, uint32_t page_alignment, struct ttm_operation_ctx *ctx, - size_t acc_size, - struct sg_table *sg, + size_t acc_size, struct sg_table *sg, struct dma_resv *resv, void (*destroy) (struct ttm_buffer_object *)); @@ -445,7 +442,7 @@ int ttm_bo_init_reserved(struct ttm_bo_device *bdev, * -ERESTARTSYS: Interrupted by signal while sleeping waiting for resources. */ int ttm_bo_init(struct ttm_bo_device *bdev, struct ttm_buffer_object *bo, - unsigned long size, enum ttm_bo_type type, + size_t size, enum ttm_bo_type type, struct ttm_placement *placement, uint32_t page_alignment, bool interrubtible, size_t acc_size, struct sg_table *sg, struct dma_resv *resv, diff --git a/include/drm/ttm/ttm_resource.h b/include/drm/ttm/ttm_resource.h index f48a70d39ac5..ad6da99770e9 100644 --- a/include/drm/ttm/ttm_resource.h +++ b/include/drm/ttm/ttm_resource.h @@ -171,7 +171,6 @@ struct ttm_bus_placement { struct ttm_resource { void *mm_node; unsigned long start; - unsigned long size; unsigned long num_pages; uint32_t page_alignment; uint32_t mem_type; -- cgit v1.2.3 From ddadd40892f31a6653cf104e274f7d2ae764eabb Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Fri, 4 Dec 2020 16:11:32 +0100 Subject: drm: Introduce an atomic_commit_setup function Private objects storing a state shared across all CRTCs need to be carefully handled to avoid a use-after-free issue. The proper way to do this to track all the commits using that shared state and wait for the previous commits to be done before going on with the current one to avoid the reordering of commits that could occur. However, this commit setup needs to be done after drm_atomic_helper_setup_commit(), because before the CRTC commit structure hasn't been allocated before, and before the workqueue is scheduled, because we would be potentially reordered already otherwise. That means that drivers currently have to roll their own drm_atomic_helper_commit() function, even though it would be identical if not for the commit setup. Let's introduce a hook to do so that would be called as part of drm_atomic_helper_commit, allowing us to reuse the atomic helpers. Reviewed-by: Daniel Vetter Suggested-by: Daniel Vetter Signed-off-by: Maxime Ripard Link: https://patchwork.freedesktop.org/patch/msgid/20201204151138.1739736-2-maxime@cerno.tech --- drivers/gpu/drm/drm_atomic_helper.c | 9 +++++++++ include/drm/drm_modeset_helper_vtables.h | 21 +++++++++++++++++++++ 2 files changed, 30 insertions(+) (limited to 'include') diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index ba1507036f26..7fcf91ecb1d9 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -2040,6 +2040,9 @@ crtc_or_fake_commit(struct drm_atomic_state *state, struct drm_crtc *crtc) * should always call this function from their * &drm_mode_config_funcs.atomic_commit hook. * + * Drivers that need to extend the commit setup to private objects can use the + * &drm_mode_config_helper_funcs.atomic_commit_setup hook. + * * To be able to use this support drivers need to use a few more helper * functions. drm_atomic_helper_wait_for_dependencies() must be called before * actually committing the hardware state, and for nonblocking commits this call @@ -2083,8 +2086,11 @@ int drm_atomic_helper_setup_commit(struct drm_atomic_state *state, struct drm_plane *plane; struct drm_plane_state *old_plane_state, *new_plane_state; struct drm_crtc_commit *commit; + const struct drm_mode_config_helper_funcs *funcs; int i, ret; + funcs = state->dev->mode_config.helper_private; + for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { commit = kzalloc(sizeof(*commit), GFP_KERNEL); if (!commit) @@ -2169,6 +2175,9 @@ int drm_atomic_helper_setup_commit(struct drm_atomic_state *state, new_plane_state->commit = drm_crtc_commit_get(commit); } + if (funcs && funcs->atomic_commit_setup) + return funcs->atomic_commit_setup(state); + return 0; } EXPORT_SYMBOL(drm_atomic_helper_setup_commit); diff --git a/include/drm/drm_modeset_helper_vtables.h b/include/drm/drm_modeset_helper_vtables.h index 16ff3fa148f5..cbe613858a93 100644 --- a/include/drm/drm_modeset_helper_vtables.h +++ b/include/drm/drm_modeset_helper_vtables.h @@ -1395,6 +1395,27 @@ struct drm_mode_config_helper_funcs { * drm_atomic_helper_commit_tail(). */ void (*atomic_commit_tail)(struct drm_atomic_state *state); + + /** + * @atomic_commit_setup: + * + * This hook is used by the default atomic_commit() hook implemented in + * drm_atomic_helper_commit() together with the nonblocking helpers (see + * drm_atomic_helper_setup_commit()) to extend the DRM commit setup. It + * is not used by the atomic helpers. + * + * This function is called at the end of + * drm_atomic_helper_setup_commit(), so once the commit has been + * properly setup across the generic DRM object states. It allows + * drivers to do some additional commit tracking that isn't related to a + * CRTC, plane or connector, tracked in a &drm_private_obj structure. + * + * Note that the documentation of &drm_private_obj has more details on + * how one should implement this. + * + * This hook is optional. + */ + int (*atomic_commit_setup)(struct drm_atomic_state *state); }; #endif -- cgit v1.2.3 From 27125e86b797deea4c42dc35fb0a71fd1d5ae53a Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Fri, 4 Dec 2020 16:11:33 +0100 Subject: drm: Document use-after-free gotcha with private objects The private objects have a gotcha that could result in a use-after-free, make sure it's properly documented. Reviewed-by: Daniel Vetter Signed-off-by: Maxime Ripard Link: https://patchwork.freedesktop.org/patch/msgid/20201204151138.1739736-3-maxime@cerno.tech --- include/drm/drm_atomic.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include') diff --git a/include/drm/drm_atomic.h b/include/drm/drm_atomic.h index 54e051a957df..ce7023e9115d 100644 --- a/include/drm/drm_atomic.h +++ b/include/drm/drm_atomic.h @@ -248,6 +248,26 @@ struct drm_private_state_funcs { * drm_dev_register() * 2/ all calls to drm_atomic_private_obj_fini() must be done after calling * drm_dev_unregister() + * + * If that private object is used to store a state shared by multiple + * CRTCs, proper care must be taken to ensure that non-blocking commits are + * properly ordered to avoid a use-after-free issue. + * + * Indeed, assuming a sequence of two non-blocking &drm_atomic_commit on two + * different &drm_crtc using different &drm_plane and &drm_connector, so with no + * resources shared, there's no guarantee on which commit is going to happen + * first. However, the second &drm_atomic_commit will consider the first + * &drm_private_obj its old state, and will be in charge of freeing it whenever + * the second &drm_atomic_commit is done. + * + * If the first &drm_atomic_commit happens after it, it will consider its + * &drm_private_obj the new state and will be likely to access it, resulting in + * an access to a freed memory region. Drivers should store (and get a reference + * to) the &drm_crtc_commit structure in our private state in + * &drm_mode_config_helper_funcs.atomic_commit_setup, and then wait for that + * commit to complete as the first step of + * &drm_mode_config_helper_funcs.atomic_commit_tail, similar to + * drm_atomic_helper_wait_for_dependencies(). */ struct drm_private_obj { /** -- cgit v1.2.3 From 6ca2ab8086af8434a4c0990882321a345c3cc2c6 Mon Sep 17 00:00:00 2001 From: Tomi Valkeinen Date: Fri, 11 Dec 2020 13:42:36 +0200 Subject: drm: automatic legacy gamma support To support legacy gamma ioctls the drivers need to set drm_crtc_funcs.gamma_set either to a custom implementation or to drm_atomic_helper_legacy_gamma_set. Most of the atomic drivers do the latter. We can simplify this by making the core handle it automatically. Move the drm_atomic_helper_legacy_gamma_set() functionality into drm_color_mgmt.c to make drm_mode_gamma_set_ioctl() use drm_crtc_funcs.gamma_set if set or GAMMA_LUT property if not. Signed-off-by: Tomi Valkeinen Reviewed-by: Laurent Pinchart Reviewed-by: Philippe Cornu Link: https://patchwork.freedesktop.org/patch/msgid/20201211114237.213288-2-tomi.valkeinen@ti.com --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 1 - drivers/gpu/drm/arm/display/komeda/komeda_crtc.c | 1 - drivers/gpu/drm/arm/malidp_crtc.c | 1 - drivers/gpu/drm/armada/armada_crtc.c | 1 - drivers/gpu/drm/ast/ast_mode.c | 1 - drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c | 1 - drivers/gpu/drm/drm_atomic_helper.c | 70 -------------- drivers/gpu/drm/drm_color_mgmt.c | 111 ++++++++++++++++++++-- drivers/gpu/drm/i915/display/intel_display.c | 1 - drivers/gpu/drm/ingenic/ingenic-drm-drv.c | 2 - drivers/gpu/drm/mediatek/mtk_drm_crtc.c | 1 - drivers/gpu/drm/nouveau/dispnv50/head.c | 2 - drivers/gpu/drm/omapdrm/omap_crtc.c | 1 - drivers/gpu/drm/rcar-du/rcar_du_crtc.c | 1 - drivers/gpu/drm/rockchip/rockchip_drm_vop.c | 1 - drivers/gpu/drm/stm/ltdc.c | 1 - drivers/gpu/drm/vc4/vc4_crtc.c | 1 - drivers/gpu/drm/vc4/vc4_txp.c | 1 - include/drm/drm_atomic_helper.h | 4 - 19 files changed, 102 insertions(+), 101 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index c23896207e9d..5675c1f9368a 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -5452,7 +5452,6 @@ static void dm_disable_vblank(struct drm_crtc *crtc) static const struct drm_crtc_funcs amdgpu_dm_crtc_funcs = { .reset = dm_crtc_reset_state, .destroy = amdgpu_dm_crtc_destroy, - .gamma_set = drm_atomic_helper_legacy_gamma_set, .set_config = drm_atomic_helper_set_config, .page_flip = drm_atomic_helper_page_flip, .atomic_duplicate_state = dm_crtc_duplicate_state, diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_crtc.c b/drivers/gpu/drm/arm/display/komeda/komeda_crtc.c index 4b485eb512e2..59172acb9738 100644 --- a/drivers/gpu/drm/arm/display/komeda/komeda_crtc.c +++ b/drivers/gpu/drm/arm/display/komeda/komeda_crtc.c @@ -550,7 +550,6 @@ static void komeda_crtc_vblank_disable(struct drm_crtc *crtc) } static const struct drm_crtc_funcs komeda_crtc_funcs = { - .gamma_set = drm_atomic_helper_legacy_gamma_set, .destroy = drm_crtc_cleanup, .set_config = drm_atomic_helper_set_config, .page_flip = drm_atomic_helper_page_flip, diff --git a/drivers/gpu/drm/arm/malidp_crtc.c b/drivers/gpu/drm/arm/malidp_crtc.c index 108e7a31bd26..494075ddbef6 100644 --- a/drivers/gpu/drm/arm/malidp_crtc.c +++ b/drivers/gpu/drm/arm/malidp_crtc.c @@ -510,7 +510,6 @@ static void malidp_crtc_disable_vblank(struct drm_crtc *crtc) } static const struct drm_crtc_funcs malidp_crtc_funcs = { - .gamma_set = drm_atomic_helper_legacy_gamma_set, .destroy = drm_crtc_cleanup, .set_config = drm_atomic_helper_set_config, .page_flip = drm_atomic_helper_page_flip, diff --git a/drivers/gpu/drm/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c index 3ebcf5a52c8b..b7bb90ae787f 100644 --- a/drivers/gpu/drm/armada/armada_crtc.c +++ b/drivers/gpu/drm/armada/armada_crtc.c @@ -820,7 +820,6 @@ static const struct drm_crtc_funcs armada_crtc_funcs = { .cursor_set = armada_drm_crtc_cursor_set, .cursor_move = armada_drm_crtc_cursor_move, .destroy = armada_drm_crtc_destroy, - .gamma_set = drm_atomic_helper_legacy_gamma_set, .set_config = drm_atomic_helper_set_config, .page_flip = drm_atomic_helper_page_flip, .atomic_duplicate_state = drm_atomic_helper_crtc_duplicate_state, diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c index 9db371f4054f..5b0ec785c516 100644 --- a/drivers/gpu/drm/ast/ast_mode.c +++ b/drivers/gpu/drm/ast/ast_mode.c @@ -903,7 +903,6 @@ static void ast_crtc_atomic_destroy_state(struct drm_crtc *crtc, static const struct drm_crtc_funcs ast_crtc_funcs = { .reset = ast_crtc_reset, - .gamma_set = drm_atomic_helper_legacy_gamma_set, .destroy = drm_crtc_cleanup, .set_config = drm_atomic_helper_set_config, .page_flip = drm_atomic_helper_page_flip, diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c index c58fa00b4848..05ad75d155e8 100644 --- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c +++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c @@ -473,7 +473,6 @@ static const struct drm_crtc_funcs atmel_hlcdc_crtc_funcs = { .atomic_destroy_state = atmel_hlcdc_crtc_destroy_state, .enable_vblank = atmel_hlcdc_crtc_enable_vblank, .disable_vblank = atmel_hlcdc_crtc_disable_vblank, - .gamma_set = drm_atomic_helper_legacy_gamma_set, }; int atmel_hlcdc_crtc_create(struct drm_device *dev) diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index 7fcf91ecb1d9..a84dc427cf82 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -3508,76 +3508,6 @@ fail: } EXPORT_SYMBOL(drm_atomic_helper_page_flip_target); -/** - * drm_atomic_helper_legacy_gamma_set - set the legacy gamma correction table - * @crtc: CRTC object - * @red: red correction table - * @green: green correction table - * @blue: green correction table - * @size: size of the tables - * @ctx: lock acquire context - * - * Implements support for legacy gamma correction table for drivers - * that support color management through the DEGAMMA_LUT/GAMMA_LUT - * properties. See drm_crtc_enable_color_mgmt() and the containing chapter for - * how the atomic color management and gamma tables work. - */ -int drm_atomic_helper_legacy_gamma_set(struct drm_crtc *crtc, - u16 *red, u16 *green, u16 *blue, - uint32_t size, - struct drm_modeset_acquire_ctx *ctx) -{ - struct drm_device *dev = crtc->dev; - struct drm_atomic_state *state; - struct drm_crtc_state *crtc_state; - struct drm_property_blob *blob = NULL; - struct drm_color_lut *blob_data; - int i, ret = 0; - bool replaced; - - state = drm_atomic_state_alloc(crtc->dev); - if (!state) - return -ENOMEM; - - blob = drm_property_create_blob(dev, - sizeof(struct drm_color_lut) * size, - NULL); - if (IS_ERR(blob)) { - ret = PTR_ERR(blob); - blob = NULL; - goto fail; - } - - /* Prepare GAMMA_LUT with the legacy values. */ - blob_data = blob->data; - for (i = 0; i < size; i++) { - blob_data[i].red = red[i]; - blob_data[i].green = green[i]; - blob_data[i].blue = blue[i]; - } - - state->acquire_ctx = ctx; - crtc_state = drm_atomic_get_crtc_state(state, crtc); - if (IS_ERR(crtc_state)) { - ret = PTR_ERR(crtc_state); - goto fail; - } - - /* Reset DEGAMMA_LUT and CTM properties. */ - replaced = drm_property_replace_blob(&crtc_state->degamma_lut, NULL); - replaced |= drm_property_replace_blob(&crtc_state->ctm, NULL); - replaced |= drm_property_replace_blob(&crtc_state->gamma_lut, blob); - crtc_state->color_mgmt_changed |= replaced; - - ret = drm_atomic_commit(state); - -fail: - drm_atomic_state_put(state); - drm_property_blob_put(blob); - return ret; -} -EXPORT_SYMBOL(drm_atomic_helper_legacy_gamma_set); - /** * drm_atomic_helper_bridge_propagate_bus_fmt() - Propagate output format to * the input end of a bridge diff --git a/drivers/gpu/drm/drm_color_mgmt.c b/drivers/gpu/drm/drm_color_mgmt.c index 3bcabc2f6e0e..553f423a8498 100644 --- a/drivers/gpu/drm/drm_color_mgmt.c +++ b/drivers/gpu/drm/drm_color_mgmt.c @@ -22,6 +22,7 @@ #include +#include #include #include #include @@ -89,9 +90,8 @@ * modes) appropriately. * * There is also support for a legacy gamma table, which is set up by calling - * drm_mode_crtc_set_gamma_size(). Drivers which support both should use - * drm_atomic_helper_legacy_gamma_set() to alias the legacy gamma ramp with the - * "GAMMA_LUT" property above. + * drm_mode_crtc_set_gamma_size(). The DRM core will then alias the legacy gamma + * ramp with "GAMMA_LUT". * * Support for different non RGB color encodings is controlled through * &drm_plane specific COLOR_ENCODING and COLOR_RANGE properties. They @@ -156,9 +156,6 @@ EXPORT_SYMBOL(drm_color_ctm_s31_32_to_qm_n); * optional. The gamma and degamma properties are only attached if * their size is not 0 and ctm_property is only attached if has_ctm is * true. - * - * Drivers should use drm_atomic_helper_legacy_gamma_set() to implement the - * legacy &drm_crtc_funcs.gamma_set callback. */ void drm_crtc_enable_color_mgmt(struct drm_crtc *crtc, uint degamma_lut_size, @@ -231,6 +228,102 @@ int drm_mode_crtc_set_gamma_size(struct drm_crtc *crtc, } EXPORT_SYMBOL(drm_mode_crtc_set_gamma_size); +/** + * drm_crtc_supports_legacy_gamma - does the crtc support legacy gamma correction table + * @crtc: CRTC object + * + * Returns true/false if the given crtc supports setting the legacy gamma + * correction table. + */ +static bool drm_crtc_supports_legacy_gamma(struct drm_crtc *crtc) +{ + u32 gamma_id = crtc->dev->mode_config.gamma_lut_property->base.id; + + if (!crtc->gamma_size) + return false; + + if (crtc->funcs->gamma_set) + return true; + + return !!drm_mode_obj_find_prop_id(&crtc->base, gamma_id); +} + +/** + * drm_crtc_legacy_gamma_set - set the legacy gamma correction table + * @crtc: CRTC object + * @red: red correction table + * @green: green correction table + * @blue: green correction table + * @size: size of the tables + * @ctx: lock acquire context + * + * Implements support for legacy gamma correction table for drivers + * that have set drm_crtc_funcs.gamma_set or that support color management + * through the DEGAMMA_LUT/GAMMA_LUT properties. See + * drm_crtc_enable_color_mgmt() and the containing chapter for + * how the atomic color management and gamma tables work. + * + * This function sets the gamma using drm_crtc_funcs.gamma_set if set, or + * alternatively using crtc color management properties. + */ +static int drm_crtc_legacy_gamma_set(struct drm_crtc *crtc, + u16 *red, u16 *green, u16 *blue, + u32 size, + struct drm_modeset_acquire_ctx *ctx) +{ + struct drm_device *dev = crtc->dev; + struct drm_atomic_state *state; + struct drm_crtc_state *crtc_state; + struct drm_property_blob *blob; + struct drm_color_lut *blob_data; + int i, ret = 0; + bool replaced; + + if (crtc->funcs->gamma_set) + return crtc->funcs->gamma_set(crtc, red, green, blue, size, ctx); + + state = drm_atomic_state_alloc(crtc->dev); + if (!state) + return -ENOMEM; + + blob = drm_property_create_blob(dev, + sizeof(struct drm_color_lut) * size, + NULL); + if (IS_ERR(blob)) { + ret = PTR_ERR(blob); + blob = NULL; + goto fail; + } + + /* Prepare GAMMA_LUT with the legacy values. */ + blob_data = blob->data; + for (i = 0; i < size; i++) { + blob_data[i].red = red[i]; + blob_data[i].green = green[i]; + blob_data[i].blue = blue[i]; + } + + state->acquire_ctx = ctx; + crtc_state = drm_atomic_get_crtc_state(state, crtc); + if (IS_ERR(crtc_state)) { + ret = PTR_ERR(crtc_state); + goto fail; + } + + /* Set GAMMA_LUT and reset DEGAMMA_LUT and CTM */ + replaced = drm_property_replace_blob(&crtc_state->degamma_lut, NULL); + replaced |= drm_property_replace_blob(&crtc_state->ctm, NULL); + replaced |= drm_property_replace_blob(&crtc_state->gamma_lut, blob); + crtc_state->color_mgmt_changed |= replaced; + + ret = drm_atomic_commit(state); + +fail: + drm_atomic_state_put(state); + drm_property_blob_put(blob); + return ret; +} + /** * drm_mode_gamma_set_ioctl - set the gamma table * @dev: DRM device @@ -262,7 +355,7 @@ int drm_mode_gamma_set_ioctl(struct drm_device *dev, if (!crtc) return -ENOENT; - if (crtc->funcs->gamma_set == NULL) + if (!drm_crtc_supports_legacy_gamma(crtc)) return -ENOSYS; /* memcpy into gamma store */ @@ -290,8 +383,8 @@ int drm_mode_gamma_set_ioctl(struct drm_device *dev, goto out; } - ret = crtc->funcs->gamma_set(crtc, r_base, g_base, b_base, - crtc->gamma_size, &ctx); + ret = drm_crtc_legacy_gamma_set(crtc, r_base, g_base, b_base, + crtc->gamma_size, &ctx); out: DRM_MODESET_LOCK_ALL_END(dev, ctx, ret); diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 53a00cf3fa32..3d53ec508a66 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -17267,7 +17267,6 @@ fail: } #define INTEL_CRTC_FUNCS \ - .gamma_set = drm_atomic_helper_legacy_gamma_set, \ .set_config = drm_atomic_helper_set_config, \ .destroy = intel_crtc_destroy, \ .page_flip = drm_atomic_helper_page_flip, \ diff --git a/drivers/gpu/drm/ingenic/ingenic-drm-drv.c b/drivers/gpu/drm/ingenic/ingenic-drm-drv.c index 42d335d3a114..7bb31fbee29d 100644 --- a/drivers/gpu/drm/ingenic/ingenic-drm-drv.c +++ b/drivers/gpu/drm/ingenic/ingenic-drm-drv.c @@ -774,8 +774,6 @@ static const struct drm_crtc_funcs ingenic_drm_crtc_funcs = { .enable_vblank = ingenic_drm_enable_vblank, .disable_vblank = ingenic_drm_disable_vblank, - - .gamma_set = drm_atomic_helper_legacy_gamma_set, }; static const struct drm_plane_helper_funcs ingenic_drm_plane_helper_funcs = { diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c index bfe994230543..b665bd498a4a 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c @@ -619,7 +619,6 @@ static const struct drm_crtc_funcs mtk_crtc_funcs = { .reset = mtk_drm_crtc_reset, .atomic_duplicate_state = mtk_drm_crtc_duplicate_state, .atomic_destroy_state = mtk_drm_crtc_destroy_state, - .gamma_set = drm_atomic_helper_legacy_gamma_set, .enable_vblank = mtk_drm_crtc_enable_vblank, .disable_vblank = mtk_drm_crtc_disable_vblank, }; diff --git a/drivers/gpu/drm/nouveau/dispnv50/head.c b/drivers/gpu/drm/nouveau/dispnv50/head.c index 537c1ef2e464..ec361d17e900 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/head.c +++ b/drivers/gpu/drm/nouveau/dispnv50/head.c @@ -503,7 +503,6 @@ nv50_head_destroy(struct drm_crtc *crtc) static const struct drm_crtc_funcs nv50_head_func = { .reset = nv50_head_reset, - .gamma_set = drm_atomic_helper_legacy_gamma_set, .destroy = nv50_head_destroy, .set_config = drm_atomic_helper_set_config, .page_flip = drm_atomic_helper_page_flip, @@ -518,7 +517,6 @@ nv50_head_func = { static const struct drm_crtc_funcs nvd9_head_func = { .reset = nv50_head_reset, - .gamma_set = drm_atomic_helper_legacy_gamma_set, .destroy = nv50_head_destroy, .set_config = drm_atomic_helper_set_config, .page_flip = drm_atomic_helper_page_flip, diff --git a/drivers/gpu/drm/omapdrm/omap_crtc.c b/drivers/gpu/drm/omapdrm/omap_crtc.c index 7d66269ad998..b97f21cf4a91 100644 --- a/drivers/gpu/drm/omapdrm/omap_crtc.c +++ b/drivers/gpu/drm/omapdrm/omap_crtc.c @@ -741,7 +741,6 @@ static const struct drm_crtc_funcs omap_crtc_funcs = { .set_config = drm_atomic_helper_set_config, .destroy = omap_crtc_destroy, .page_flip = drm_atomic_helper_page_flip, - .gamma_set = drm_atomic_helper_legacy_gamma_set, .atomic_duplicate_state = omap_crtc_duplicate_state, .atomic_destroy_state = drm_atomic_helper_crtc_destroy_state, .atomic_set_property = omap_crtc_atomic_set_property, diff --git a/drivers/gpu/drm/rcar-du/rcar_du_crtc.c b/drivers/gpu/drm/rcar-du/rcar_du_crtc.c index b5fb941e0f53..f93e0750431d 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_crtc.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_crtc.c @@ -1144,7 +1144,6 @@ static const struct drm_crtc_funcs crtc_funcs_gen3 = { .set_crc_source = rcar_du_crtc_set_crc_source, .verify_crc_source = rcar_du_crtc_verify_crc_source, .get_crc_sources = rcar_du_crtc_get_crc_sources, - .gamma_set = drm_atomic_helper_legacy_gamma_set, }; /* ----------------------------------------------------------------------------- diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c index d1e05482641b..8d15cabdcb02 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c @@ -1643,7 +1643,6 @@ static const struct drm_crtc_funcs vop_crtc_funcs = { .disable_vblank = vop_crtc_disable_vblank, .set_crc_source = vop_crtc_set_crc_source, .verify_crc_source = vop_crtc_verify_crc_source, - .gamma_set = drm_atomic_helper_legacy_gamma_set, }; static void vop_fb_unref_worker(struct drm_flip_work *work, void *val) diff --git a/drivers/gpu/drm/stm/ltdc.c b/drivers/gpu/drm/stm/ltdc.c index 3980677435cb..7812094f93d6 100644 --- a/drivers/gpu/drm/stm/ltdc.c +++ b/drivers/gpu/drm/stm/ltdc.c @@ -713,7 +713,6 @@ static const struct drm_crtc_funcs ltdc_crtc_funcs = { .enable_vblank = ltdc_crtc_enable_vblank, .disable_vblank = ltdc_crtc_disable_vblank, .get_vblank_timestamp = drm_crtc_vblank_helper_get_vblank_timestamp, - .gamma_set = drm_atomic_helper_legacy_gamma_set, }; /* diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c index ee4f657a5ce0..a8199a257328 100644 --- a/drivers/gpu/drm/vc4/vc4_crtc.c +++ b/drivers/gpu/drm/vc4/vc4_crtc.c @@ -871,7 +871,6 @@ static const struct drm_crtc_funcs vc4_crtc_funcs = { .reset = vc4_crtc_reset, .atomic_duplicate_state = vc4_crtc_duplicate_state, .atomic_destroy_state = vc4_crtc_destroy_state, - .gamma_set = drm_atomic_helper_legacy_gamma_set, .enable_vblank = vc4_enable_vblank, .disable_vblank = vc4_disable_vblank, .get_vblank_timestamp = drm_crtc_vblank_helper_get_vblank_timestamp, diff --git a/drivers/gpu/drm/vc4/vc4_txp.c b/drivers/gpu/drm/vc4/vc4_txp.c index 8aa5220885f4..e4b782e42f69 100644 --- a/drivers/gpu/drm/vc4/vc4_txp.c +++ b/drivers/gpu/drm/vc4/vc4_txp.c @@ -382,7 +382,6 @@ static const struct drm_crtc_funcs vc4_txp_crtc_funcs = { .reset = vc4_crtc_reset, .atomic_duplicate_state = vc4_crtc_duplicate_state, .atomic_destroy_state = vc4_crtc_destroy_state, - .gamma_set = drm_atomic_helper_legacy_gamma_set, .enable_vblank = vc4_txp_enable_vblank, .disable_vblank = vc4_txp_disable_vblank, }; diff --git a/include/drm/drm_atomic_helper.h b/include/drm/drm_atomic_helper.h index 5f47720440fa..4045e2507e11 100644 --- a/include/drm/drm_atomic_helper.h +++ b/include/drm/drm_atomic_helper.h @@ -147,10 +147,6 @@ int drm_atomic_helper_page_flip_target( uint32_t flags, uint32_t target, struct drm_modeset_acquire_ctx *ctx); -int drm_atomic_helper_legacy_gamma_set(struct drm_crtc *crtc, - u16 *red, u16 *green, u16 *blue, - uint32_t size, - struct drm_modeset_acquire_ctx *ctx); /** * drm_atomic_crtc_for_each_plane - iterate over planes currently attached to CRTC -- cgit v1.2.3 From 3d1a88e1051f5d788d789011823d9accc4e03dad Mon Sep 17 00:00:00 2001 From: Christian König Date: Fri, 27 Nov 2020 15:14:34 +0100 Subject: drm/ttm: cleanup LRU handling further MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We only completely delete the BO from the LRU on destruction. Signed-off-by: Christian König Acked-by: Andrey Grodzovsky Link: https://patchwork.freedesktop.org/patch/404618/ --- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 4 ++- drivers/gpu/drm/qxl/qxl_release.c | 2 +- drivers/gpu/drm/ttm/ttm_bo.c | 60 ++++++++++++++-------------------- drivers/gpu/drm/ttm/ttm_execbuf_util.c | 4 +-- include/drm/ttm/ttm_bo_api.h | 2 ++ include/drm/ttm/ttm_bo_driver.h | 5 +-- 6 files changed, 36 insertions(+), 41 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 0768c8686983..ad91c0c3c423 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -653,9 +653,11 @@ void amdgpu_vm_move_to_lru_tail(struct amdgpu_device *adev, if (!bo->parent) continue; - ttm_bo_move_to_lru_tail(&bo->tbo, &vm->lru_bulk_move); + ttm_bo_move_to_lru_tail(&bo->tbo, &bo->tbo.mem, + &vm->lru_bulk_move); if (bo->shadow) ttm_bo_move_to_lru_tail(&bo->shadow->tbo, + &bo->shadow->tbo.mem, &vm->lru_bulk_move); } spin_unlock(&ttm_bo_glob.lru_lock); diff --git a/drivers/gpu/drm/qxl/qxl_release.c b/drivers/gpu/drm/qxl/qxl_release.c index e75e364655b8..0fcfc952d5e9 100644 --- a/drivers/gpu/drm/qxl/qxl_release.c +++ b/drivers/gpu/drm/qxl/qxl_release.c @@ -456,7 +456,7 @@ void qxl_release_fence_buffer_objects(struct qxl_release *release) bo = entry->bo; dma_resv_add_shared_fence(bo->base.resv, &release->base); - ttm_bo_move_to_lru_tail(bo, NULL); + ttm_bo_move_to_lru_tail(bo, &bo->mem, NULL); dma_resv_unlock(bo->base.resv); } spin_unlock(&ttm_bo_glob.lru_lock); diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index c702ec5445f7..31e8b3da5563 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -110,40 +110,14 @@ static struct kobj_type ttm_bo_glob_kobj_type = { .default_attrs = ttm_bo_global_attrs }; -static void ttm_bo_add_mem_to_lru(struct ttm_buffer_object *bo, - struct ttm_resource *mem) -{ - struct ttm_bo_device *bdev = bo->bdev; - struct ttm_resource_manager *man; - - if (!list_empty(&bo->lru) || bo->pin_count) - return; - - man = ttm_manager_type(bdev, mem->mem_type); - list_add_tail(&bo->lru, &man->lru[bo->priority]); - - if (man->use_tt && bo->ttm && - !(bo->ttm->page_flags & (TTM_PAGE_FLAG_SG | - TTM_PAGE_FLAG_SWAPPED))) { - list_add_tail(&bo->swap, &ttm_bo_glob.swap_lru[bo->priority]); - } -} - static void ttm_bo_del_from_lru(struct ttm_buffer_object *bo) { struct ttm_bo_device *bdev = bo->bdev; - bool notify = false; - if (!list_empty(&bo->swap)) { - list_del_init(&bo->swap); - notify = true; - } - if (!list_empty(&bo->lru)) { - list_del_init(&bo->lru); - notify = true; - } + list_del_init(&bo->swap); + list_del_init(&bo->lru); - if (notify && bdev->driver->del_from_lru_notify) + if (bdev->driver->del_from_lru_notify) bdev->driver->del_from_lru_notify(bo); } @@ -156,12 +130,30 @@ static void ttm_bo_bulk_move_set_pos(struct ttm_lru_bulk_move_pos *pos, } void ttm_bo_move_to_lru_tail(struct ttm_buffer_object *bo, + struct ttm_resource *mem, struct ttm_lru_bulk_move *bulk) { + struct ttm_bo_device *bdev = bo->bdev; + struct ttm_resource_manager *man; + dma_resv_assert_held(bo->base.resv); - ttm_bo_del_from_lru(bo); - ttm_bo_add_mem_to_lru(bo, &bo->mem); + if (bo->pin_count) + return; + + man = ttm_manager_type(bdev, mem->mem_type); + list_move_tail(&bo->lru, &man->lru[bo->priority]); + if (man->use_tt && bo->ttm && + !(bo->ttm->page_flags & (TTM_PAGE_FLAG_SG | + TTM_PAGE_FLAG_SWAPPED))) { + struct list_head *swap; + + swap = &ttm_bo_glob.swap_lru[bo->priority]; + list_move_tail(&bo->swap, swap); + } + + if (bdev->driver->del_from_lru_notify) + bdev->driver->del_from_lru_notify(bo); if (bulk && !bo->pin_count) { switch (bo->mem.mem_type) { @@ -517,8 +509,7 @@ static void ttm_bo_release(struct kref *kref) */ if (WARN_ON(bo->pin_count)) { bo->pin_count = 0; - ttm_bo_del_from_lru(bo); - ttm_bo_add_mem_to_lru(bo, &bo->mem); + ttm_bo_move_to_lru_tail(bo, &bo->mem, NULL); } kref_init(&bo->kref); @@ -860,8 +851,7 @@ static int ttm_bo_mem_placement(struct ttm_buffer_object *bo, mem->placement = place->flags; spin_lock(&ttm_bo_glob.lru_lock); - ttm_bo_del_from_lru(bo); - ttm_bo_add_mem_to_lru(bo, mem); + ttm_bo_move_to_lru_tail(bo, mem, NULL); spin_unlock(&ttm_bo_glob.lru_lock); return 0; diff --git a/drivers/gpu/drm/ttm/ttm_execbuf_util.c b/drivers/gpu/drm/ttm/ttm_execbuf_util.c index 8a8f1a6a83a6..9fa36ed59429 100644 --- a/drivers/gpu/drm/ttm/ttm_execbuf_util.c +++ b/drivers/gpu/drm/ttm/ttm_execbuf_util.c @@ -55,7 +55,7 @@ void ttm_eu_backoff_reservation(struct ww_acquire_ctx *ticket, list_for_each_entry(entry, list, head) { struct ttm_buffer_object *bo = entry->bo; - ttm_bo_move_to_lru_tail(bo, NULL); + ttm_bo_move_to_lru_tail(bo, &bo->mem, NULL); dma_resv_unlock(bo->base.resv); } spin_unlock(&ttm_bo_glob.lru_lock); @@ -162,7 +162,7 @@ void ttm_eu_fence_buffer_objects(struct ww_acquire_ctx *ticket, dma_resv_add_shared_fence(bo->base.resv, fence); else dma_resv_add_excl_fence(bo->base.resv, fence); - ttm_bo_move_to_lru_tail(bo, NULL); + ttm_bo_move_to_lru_tail(bo, &bo->mem, NULL); dma_resv_unlock(bo->base.resv); } spin_unlock(&ttm_bo_glob.lru_lock); diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h index 0d4e3fccaa8a..e17be324d95f 100644 --- a/include/drm/ttm/ttm_bo_api.h +++ b/include/drm/ttm/ttm_bo_api.h @@ -309,6 +309,7 @@ void ttm_bo_put(struct ttm_buffer_object *bo); * ttm_bo_move_to_lru_tail * * @bo: The buffer object. + * @mem: Resource object. * @bulk: optional bulk move structure to remember BO positions * * Move this BO to the tail of all lru lists used to lookup and reserve an @@ -316,6 +317,7 @@ void ttm_bo_put(struct ttm_buffer_object *bo); * held, and is used to make a BO less likely to be considered for eviction. */ void ttm_bo_move_to_lru_tail(struct ttm_buffer_object *bo, + struct ttm_resource *mem, struct ttm_lru_bulk_move *bulk); /** diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index b1d1ce9740c4..423348414c59 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -491,10 +491,11 @@ static inline int ttm_bo_reserve_slowpath(struct ttm_buffer_object *bo, return 0; } -static inline void ttm_bo_move_to_lru_tail_unlocked(struct ttm_buffer_object *bo) +static inline void +ttm_bo_move_to_lru_tail_unlocked(struct ttm_buffer_object *bo) { spin_lock(&ttm_bo_glob.lru_lock); - ttm_bo_move_to_lru_tail(bo, NULL); + ttm_bo_move_to_lru_tail(bo, &bo->mem, NULL); spin_unlock(&ttm_bo_glob.lru_lock); } -- cgit v1.2.3 From de9114ece5dfcc422164a24a687785843ed92c47 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Fri, 11 Dec 2020 16:58:40 +0100 Subject: dma-buf: Remove kmap kerneldoc vestiges MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Also try to clarify a bit when dma_buf_begin/end_cpu_access should be called. Acked-by: Christian König Signed-off-by: Daniel Vetter Cc: Thomas Zimmermann Cc: Sumit Semwal Cc: "Christian König" Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Link: https://patchwork.freedesktop.org/patch/msgid/20201211155843.3348718-1-daniel.vetter@ffwll.ch --- drivers/dma-buf/dma-buf.c | 20 ++++++++++++++------ include/linux/dma-buf.h | 25 +++++++++---------------- 2 files changed, 23 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index e63684d4cd90..a12fdffa130f 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -1001,15 +1001,15 @@ EXPORT_SYMBOL_GPL(dma_buf_move_notify); * vmalloc space might be limited and result in vmap calls failing. * * Interfaces:: + * * void \*dma_buf_vmap(struct dma_buf \*dmabuf) * void dma_buf_vunmap(struct dma_buf \*dmabuf, void \*vaddr) * * The vmap call can fail if there is no vmap support in the exporter, or if - * it runs out of vmalloc space. Fallback to kmap should be implemented. Note - * that the dma-buf layer keeps a reference count for all vmap access and - * calls down into the exporter's vmap function only when no vmapping exists, - * and only unmaps it once. Protection against concurrent vmap/vunmap calls is - * provided by taking the dma_buf->lock mutex. + * it runs out of vmalloc space. Note that the dma-buf layer keeps a reference + * count for all vmap access and calls down into the exporter's vmap function + * only when no vmapping exists, and only unmaps it once. Protection against + * concurrent vmap/vunmap calls is provided by taking the &dma_buf.lock mutex. * * - For full compatibility on the importer side with existing userspace * interfaces, which might already support mmap'ing buffers. This is needed in @@ -1098,6 +1098,11 @@ static int __dma_buf_begin_cpu_access(struct dma_buf *dmabuf, * dma_buf_end_cpu_access(). Only when cpu access is braketed by both calls is * it guaranteed to be coherent with other DMA access. * + * This function will also wait for any DMA transactions tracked through + * implicit synchronization in &dma_buf.resv. For DMA transactions with explicit + * synchronization this function will only ensure cache coherency, callers must + * ensure synchronization with such DMA transactions on their own. + * * Can return negative error values, returns 0 on success. */ int dma_buf_begin_cpu_access(struct dma_buf *dmabuf, @@ -1199,7 +1204,10 @@ EXPORT_SYMBOL_GPL(dma_buf_mmap); * This call may fail due to lack of virtual mapping address space. * These calls are optional in drivers. The intended use for them * is for mapping objects linear in kernel space for high use objects. - * Please attempt to use kmap/kunmap before thinking about these interfaces. + * + * To ensure coherency users must call dma_buf_begin_cpu_access() and + * dma_buf_end_cpu_access() around any cpu access performed through this + * mapping. * * Returns 0 on success, or a negative errno code otherwise. */ diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index cf72699cb2bc..7eca37c8b10c 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -183,24 +183,19 @@ struct dma_buf_ops { * @begin_cpu_access: * * This is called from dma_buf_begin_cpu_access() and allows the - * exporter to ensure that the memory is actually available for cpu - * access - the exporter might need to allocate or swap-in and pin the - * backing storage. The exporter also needs to ensure that cpu access is - * coherent for the access direction. The direction can be used by the - * exporter to optimize the cache flushing, i.e. access with a different + * exporter to ensure that the memory is actually coherent for cpu + * access. The exporter also needs to ensure that cpu access is coherent + * for the access direction. The direction can be used by the exporter + * to optimize the cache flushing, i.e. access with a different * direction (read instead of write) might return stale or even bogus * data (e.g. when the exporter needs to copy the data to temporary * storage). * - * This callback is optional. + * Note that this is both called through the DMA_BUF_IOCTL_SYNC IOCTL + * command for userspace mappings established through @mmap, and also + * for kernel mappings established with @vmap. * - * FIXME: This is both called through the DMA_BUF_IOCTL_SYNC command - * from userspace (where storage shouldn't be pinned to avoid handing - * de-factor mlock rights to userspace) and for the kernel-internal - * users of the various kmap interfaces, where the backing storage must - * be pinned to guarantee that the atomic kmap calls can succeed. Since - * there's no in-kernel users of the kmap interfaces yet this isn't a - * real problem. + * This callback is optional. * * Returns: * @@ -216,9 +211,7 @@ struct dma_buf_ops { * * This is called from dma_buf_end_cpu_access() when the importer is * done accessing the CPU. The exporter can use this to flush caches and - * unpin any resources pinned in @begin_cpu_access. - * The result of any dma_buf kmap calls after end_cpu_access is - * undefined. + * undo anything else done in @begin_cpu_access. * * This callback is optional. * -- cgit v1.2.3 From 85804b70cca68d77bca419b493ab843bf710de68 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Fri, 11 Dec 2020 16:58:41 +0100 Subject: dma-buf: some kerneldoc formatting fixes MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Noticed while reviewing the output. Adds a bunch more links and fixes the function interface quoting. Acked-by: Christian König Signed-off-by: Daniel Vetter Cc: Thomas Zimmermann Cc: Sumit Semwal Cc: "Christian König" Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Link: https://patchwork.freedesktop.org/patch/msgid/20201211155843.3348718-2-daniel.vetter@ffwll.ch --- drivers/dma-buf/dma-buf.c | 31 ++++++++++++++++++------------- include/linux/dma-buf.h | 6 +++--- 2 files changed, 21 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index a12fdffa130f..e1fa6c6f02c4 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -480,7 +480,7 @@ err_alloc_file: * * 4. Once a driver is done with a shared buffer it needs to call * dma_buf_detach() (after cleaning up any mappings) and then release the - * reference acquired with dma_buf_get by calling dma_buf_put(). + * reference acquired with dma_buf_get() by calling dma_buf_put(). * * For the detailed semantics exporters are expected to implement see * &dma_buf_ops. @@ -496,9 +496,10 @@ err_alloc_file: * by the exporter. see &struct dma_buf_export_info * for further details. * - * Returns, on success, a newly created dma_buf object, which wraps the - * supplied private data and operations for dma_buf_ops. On either missing - * ops, or error in allocating struct dma_buf, will return negative error. + * Returns, on success, a newly created struct dma_buf object, which wraps the + * supplied private data and operations for struct dma_buf_ops. On either + * missing ops, or error in allocating struct dma_buf, will return negative + * error. * * For most cases the easiest way to create @exp_info is through the * %DEFINE_DMA_BUF_EXPORT_INFO macro. @@ -584,7 +585,7 @@ err_module: EXPORT_SYMBOL_GPL(dma_buf_export); /** - * dma_buf_fd - returns a file descriptor for the given dma_buf + * dma_buf_fd - returns a file descriptor for the given struct dma_buf * @dmabuf: [in] pointer to dma_buf for which fd is required. * @flags: [in] flags to give to fd * @@ -608,10 +609,10 @@ int dma_buf_fd(struct dma_buf *dmabuf, int flags) EXPORT_SYMBOL_GPL(dma_buf_fd); /** - * dma_buf_get - returns the dma_buf structure related to an fd - * @fd: [in] fd associated with the dma_buf to be returned + * dma_buf_get - returns the struct dma_buf related to an fd + * @fd: [in] fd associated with the struct dma_buf to be returned * - * On success, returns the dma_buf structure associated with an fd; uses + * On success, returns the struct dma_buf associated with an fd; uses * file's refcounting done by fget to increase refcount. returns ERR_PTR * otherwise. */ @@ -653,8 +654,7 @@ void dma_buf_put(struct dma_buf *dmabuf) EXPORT_SYMBOL_GPL(dma_buf_put); /** - * dma_buf_dynamic_attach - Add the device to dma_buf's attachments list; optionally, - * calls attach() of dma_buf_ops to allow device-specific attach functionality + * dma_buf_dynamic_attach - Add the device to dma_buf's attachments list * @dmabuf: [in] buffer to attach device to. * @dev: [in] device to be attached. * @importer_ops: [in] importer operations for the attachment @@ -663,6 +663,9 @@ EXPORT_SYMBOL_GPL(dma_buf_put); * Returns struct dma_buf_attachment pointer for this attachment. Attachments * must be cleaned up by calling dma_buf_detach(). * + * Optionally this calls &dma_buf_ops.attach to allow device-specific attach + * functionality. + * * Returns: * * A pointer to newly created &dma_buf_attachment on success, or a negative @@ -769,12 +772,13 @@ struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf, EXPORT_SYMBOL_GPL(dma_buf_attach); /** - * dma_buf_detach - Remove the given attachment from dmabuf's attachments list; - * optionally calls detach() of dma_buf_ops for device-specific detach + * dma_buf_detach - Remove the given attachment from dmabuf's attachments list * @dmabuf: [in] buffer to detach from. * @attach: [in] attachment to be detached; is free'd after this call. * * Clean up a device attachment obtained by calling dma_buf_attach(). + * + * Optionally this calls &dma_buf_ops.detach for device-specific detach. */ void dma_buf_detach(struct dma_buf *dmabuf, struct dma_buf_attachment *attach) { @@ -1061,11 +1065,12 @@ EXPORT_SYMBOL_GPL(dma_buf_move_notify); * shootdowns would increase the complexity quite a bit. * * Interface:: + * * int dma_buf_mmap(struct dma_buf \*, struct vm_area_struct \*, * unsigned long); * * If the importing subsystem simply provides a special-purpose mmap call to - * set up a mapping in userspace, calling do_mmap with dma_buf->file will + * set up a mapping in userspace, calling do_mmap with &dma_buf.file will * equally achieve that for a dma-buf object. */ diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 7eca37c8b10c..43802a31b25d 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -85,10 +85,10 @@ struct dma_buf_ops { /** * @pin: * - * This is called by dma_buf_pin and lets the exporter know that the + * This is called by dma_buf_pin() and lets the exporter know that the * DMA-buf can't be moved any more. * - * This is called with the dmabuf->resv object locked and is mutual + * This is called with the &dmabuf.resv object locked and is mutual * exclusive with @cache_sgt_mapping. * * This callback is optional and should only be used in limited use @@ -103,7 +103,7 @@ struct dma_buf_ops { /** * @unpin: * - * This is called by dma_buf_unpin and lets the exporter know that the + * This is called by dma_buf_unpin() and lets the exporter know that the * DMA-buf can be moved again. * * This is called with the dmabuf->resv object locked and is mutual -- cgit v1.2.3 From c545781e1c55ab680dcc49c37212d5327b9d6812 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Fri, 11 Dec 2020 16:58:43 +0100 Subject: dma-buf: doc polish for pin/unpin MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Motivated by a discussion with Christian and Thomas: Try to untangle a bit what's relevant for importers and what's relevant for exporters. Also add an assert that really only dynamic importers use the api function, anything else doesn't make sense. Acked-by: Christian König Signed-off-by: Daniel Vetter Cc: Thomas Zimmermann Cc: Sumit Semwal Cc: "Christian König" Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Link: https://patchwork.freedesktop.org/patch/msgid/20201211155843.3348718-4-daniel.vetter@ffwll.ch --- drivers/dma-buf/dma-buf.c | 19 ++++++++++++++++--- include/linux/dma-buf.h | 8 +++++--- 2 files changed, 21 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index a0a02ef888da..b8465243eca2 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -809,9 +809,15 @@ EXPORT_SYMBOL_GPL(dma_buf_detach); /** * dma_buf_pin - Lock down the DMA-buf - * * @attach: [in] attachment which should be pinned * + * Only dynamic importers (who set up @attach with dma_buf_dynamic_attach()) may + * call this, and only for limited use cases like scanout and not for temporary + * pin operations. It is not permitted to allow userspace to pin arbitrary + * amounts of buffers through this interface. + * + * Buffers must be unpinned by calling dma_buf_unpin(). + * * Returns: * 0 on success, negative error code on failure. */ @@ -820,6 +826,8 @@ int dma_buf_pin(struct dma_buf_attachment *attach) struct dma_buf *dmabuf = attach->dmabuf; int ret = 0; + WARN_ON(!dma_buf_attachment_is_dynamic(attach)); + dma_resv_assert_held(dmabuf->resv); if (dmabuf->ops->pin) @@ -830,14 +838,19 @@ int dma_buf_pin(struct dma_buf_attachment *attach) EXPORT_SYMBOL_GPL(dma_buf_pin); /** - * dma_buf_unpin - Remove lock from DMA-buf - * + * dma_buf_unpin - Unpin a DMA-buf * @attach: [in] attachment which should be unpinned + * + * This unpins a buffer pinned by dma_buf_pin() and allows the exporter to move + * any mapping of @attach again and inform the importer through + * &dma_buf_attach_ops.move_notify. */ void dma_buf_unpin(struct dma_buf_attachment *attach) { struct dma_buf *dmabuf = attach->dmabuf; + WARN_ON(!dma_buf_attachment_is_dynamic(attach)); + dma_resv_assert_held(dmabuf->resv); if (dmabuf->ops->unpin) diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 43802a31b25d..628681bf6c99 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -86,13 +86,15 @@ struct dma_buf_ops { * @pin: * * This is called by dma_buf_pin() and lets the exporter know that the - * DMA-buf can't be moved any more. + * DMA-buf can't be moved any more. The exporter should pin the buffer + * into system memory to make sure it is generally accessible by other + * devices. * * This is called with the &dmabuf.resv object locked and is mutual * exclusive with @cache_sgt_mapping. * - * This callback is optional and should only be used in limited use - * cases like scanout and not for temporary pin operations. + * This is called automatically for non-dynamic importers from + * dma_buf_attach(). * * Returns: * -- cgit v1.2.3 From a1b766d1b3646b5ef90f0fa7b42fd99bbd166766 Mon Sep 17 00:00:00 2001 From: Simon Ser Date: Thu, 17 Dec 2020 12:32:17 +0100 Subject: drm/doc: atomic implicitly enables other caps Document that enabling atomic also enables universal planes and aspect ratio modes. Signed-off-by: Simon Ser Reviewed-by: Daniel Vetter Cc: Pekka Paalanen Link: https://patchwork.freedesktop.org/patch/msgid/20201217113220.102271-7-contact@emersion.fr --- include/uapi/drm/drm.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h index 808b48a93330..5c31aea1f342 100644 --- a/include/uapi/drm/drm.h +++ b/include/uapi/drm/drm.h @@ -678,7 +678,9 @@ struct drm_get_cap { /** * DRM_CLIENT_CAP_ATOMIC * - * If set to 1, the DRM core will expose atomic properties to userspace + * If set to 1, the DRM core will expose atomic properties to userspace. This + * implicitly enables &DRM_CLIENT_CAP_UNIVERSAL_PLANES and + * &DRM_CLIENT_CAP_ASPECT_RATIO. */ #define DRM_CLIENT_CAP_ATOMIC 3 -- cgit v1.2.3 From 8c3b1ba0e7ea9a80b0ee4b4445ea59c806787813 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Tue, 15 Dec 2020 15:44:56 +0000 Subject: drm/i915/gt: Track the overall awake/busy time Since we wake the GT up before executing a request, and go to sleep as soon as it is retired, the GT wake time not only represents how long the device is powered up, but also provides a summary, albeit an overestimate, of the device runtime (i.e. the rc0 time to compare against rc6 time). v2: s/busy/awake/ v3: software-gt-awake-time and I915_PMU_SOFTWARE_GT_AWAKE_TIME Signed-off-by: Chris Wilson Reviewed-by: Tvrtko Ursulin Cc: Matthew Brost Reported-by: kernel test robot Link: https://patchwork.freedesktop.org/patch/msgid/20201215154456.13954-1-chris@chris-wilson.co.uk --- drivers/gpu/drm/i915/gt/debugfs_gt_pm.c | 5 +++- drivers/gpu/drm/i915/gt/intel_gt_pm.c | 49 ++++++++++++++++++++++++++++++++ drivers/gpu/drm/i915/gt/intel_gt_pm.h | 2 ++ drivers/gpu/drm/i915/gt/intel_gt_types.h | 24 ++++++++++++++++ drivers/gpu/drm/i915/i915_debugfs.c | 5 ++-- drivers/gpu/drm/i915/i915_pmu.c | 6 ++++ include/uapi/drm/i915_drm.h | 1 + 7 files changed, 89 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/i915/gt/debugfs_gt_pm.c b/drivers/gpu/drm/i915/gt/debugfs_gt_pm.c index 174a24553322..8975717ace06 100644 --- a/drivers/gpu/drm/i915/gt/debugfs_gt_pm.c +++ b/drivers/gpu/drm/i915/gt/debugfs_gt_pm.c @@ -11,6 +11,7 @@ #include "i915_drv.h" #include "intel_gt.h" #include "intel_gt_clock_utils.h" +#include "intel_gt_pm.h" #include "intel_llc.h" #include "intel_rc6.h" #include "intel_rps.h" @@ -558,7 +559,9 @@ static int rps_boost_show(struct seq_file *m, void *data) seq_printf(m, "RPS enabled? %s\n", yesno(intel_rps_is_enabled(rps))); seq_printf(m, "RPS active? %s\n", yesno(intel_rps_is_active(rps))); - seq_printf(m, "GPU busy? %s\n", yesno(gt->awake)); + seq_printf(m, "GPU busy? %s, %llums\n", + yesno(gt->awake), + ktime_to_ms(intel_gt_get_awake_time(gt))); seq_printf(m, "Boosts outstanding? %d\n", atomic_read(&rps->num_waiters)); seq_printf(m, "Interactive? %d\n", READ_ONCE(rps->power.interactive)); diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c index 274aa0dd7050..c94e8ac884eb 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c @@ -39,6 +39,28 @@ static void user_forcewake(struct intel_gt *gt, bool suspend) intel_gt_pm_put(gt); } +static void runtime_begin(struct intel_gt *gt) +{ + local_irq_disable(); + write_seqcount_begin(>->stats.lock); + gt->stats.start = ktime_get(); + gt->stats.active = true; + write_seqcount_end(>->stats.lock); + local_irq_enable(); +} + +static void runtime_end(struct intel_gt *gt) +{ + local_irq_disable(); + write_seqcount_begin(>->stats.lock); + gt->stats.active = false; + gt->stats.total = + ktime_add(gt->stats.total, + ktime_sub(ktime_get(), gt->stats.start)); + write_seqcount_end(>->stats.lock); + local_irq_enable(); +} + static int __gt_unpark(struct intel_wakeref *wf) { struct intel_gt *gt = container_of(wf, typeof(*gt), wakeref); @@ -67,6 +89,7 @@ static int __gt_unpark(struct intel_wakeref *wf) i915_pmu_gt_unparked(i915); intel_gt_unpark_requests(gt); + runtime_begin(gt); return 0; } @@ -79,6 +102,7 @@ static int __gt_park(struct intel_wakeref *wf) GT_TRACE(gt, "\n"); + runtime_end(gt); intel_gt_park_requests(gt); i915_vma_parked(gt); @@ -106,6 +130,7 @@ static const struct intel_wakeref_ops wf_ops = { void intel_gt_pm_init_early(struct intel_gt *gt) { intel_wakeref_init(>->wakeref, gt->uncore->rpm, &wf_ops); + seqcount_mutex_init(>->stats.lock, >->wakeref.mutex); } void intel_gt_pm_init(struct intel_gt *gt) @@ -339,6 +364,30 @@ int intel_gt_runtime_resume(struct intel_gt *gt) return intel_uc_runtime_resume(>->uc); } +static ktime_t __intel_gt_get_awake_time(const struct intel_gt *gt) +{ + ktime_t total = gt->stats.total; + + if (gt->stats.active) + total = ktime_add(total, + ktime_sub(ktime_get(), gt->stats.start)); + + return total; +} + +ktime_t intel_gt_get_awake_time(const struct intel_gt *gt) +{ + unsigned int seq; + ktime_t total; + + do { + seq = read_seqcount_begin(>->stats.lock); + total = __intel_gt_get_awake_time(gt); + } while (read_seqcount_retry(>->stats.lock, seq)); + + return total; +} + #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) #include "selftest_gt_pm.c" #endif diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.h b/drivers/gpu/drm/i915/gt/intel_gt_pm.h index 60f0e2fbe55c..63846a856e7e 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_pm.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.h @@ -58,6 +58,8 @@ int intel_gt_resume(struct intel_gt *gt); void intel_gt_runtime_suspend(struct intel_gt *gt); int intel_gt_runtime_resume(struct intel_gt *gt); +ktime_t intel_gt_get_awake_time(const struct intel_gt *gt); + static inline bool is_mock_gt(const struct intel_gt *gt) { return I915_SELFTEST_ONLY(gt->awake == -ENODEV); diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h index 6d39a4a11bf3..c7bde529feab 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_types.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h @@ -87,6 +87,30 @@ struct intel_gt { u32 pm_guc_events; + struct { + bool active; + + /** + * @lock: Lock protecting the below fields. + */ + seqcount_mutex_t lock; + + /** + * @total: Total time this engine was busy. + * + * Accumulated time not counting the most recent block in cases + * where engine is currently busy (active > 0). + */ + ktime_t total; + + /** + * @start: Timestamp of the last idle to active transition. + * + * Idle is defined as active == 0, active is active > 0. + */ + ktime_t start; + } stats; + struct intel_engine_cs *engine[I915_NUM_ENGINES]; struct intel_engine_cs *engine_class[MAX_ENGINE_CLASS + 1] [MAX_ENGINE_INSTANCE + 1]; diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index 263074c2c097..f29487ea4528 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -1314,9 +1314,10 @@ static int i915_engine_info(struct seq_file *m, void *unused) wakeref = intel_runtime_pm_get(&i915->runtime_pm); - seq_printf(m, "GT awake? %s [%d]\n", + seq_printf(m, "GT awake? %s [%d], %llums\n", yesno(i915->gt.awake), - atomic_read(&i915->gt.wakeref.count)); + atomic_read(&i915->gt.wakeref.count), + ktime_to_ms(intel_gt_get_awake_time(&i915->gt))); seq_printf(m, "CS timestamp frequency: %u Hz\n", RUNTIME_INFO(i915)->cs_timestamp_frequency_hz); diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c index 37716a89c682..7af4fabe5594 100644 --- a/drivers/gpu/drm/i915/i915_pmu.c +++ b/drivers/gpu/drm/i915/i915_pmu.c @@ -509,6 +509,8 @@ config_status(struct drm_i915_private *i915, u64 config) if (!HAS_RC6(i915)) return -ENODEV; break; + case I915_PMU_SOFTWARE_GT_AWAKE_TIME: + break; default: return -ENOENT; } @@ -616,6 +618,9 @@ static u64 __i915_pmu_event_read(struct perf_event *event) case I915_PMU_RC6_RESIDENCY: val = get_rc6(&i915->gt); break; + case I915_PMU_SOFTWARE_GT_AWAKE_TIME: + val = ktime_to_ns(intel_gt_get_awake_time(&i915->gt)); + break; } } @@ -916,6 +921,7 @@ create_event_attributes(struct i915_pmu *pmu) __event(I915_PMU_REQUESTED_FREQUENCY, "requested-frequency", "M"), __event(I915_PMU_INTERRUPTS, "interrupts", NULL), __event(I915_PMU_RC6_RESIDENCY, "rc6-residency", "ns"), + __event(I915_PMU_SOFTWARE_GT_AWAKE_TIME, "software-gt-awake-time", "ns"), }; static const struct { enum drm_i915_pmu_engine_sample sample; diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index 6edcb2b6c708..1987e2ea79a3 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -177,6 +177,7 @@ enum drm_i915_pmu_engine_sample { #define I915_PMU_REQUESTED_FREQUENCY __I915_PMU_OTHER(1) #define I915_PMU_INTERRUPTS __I915_PMU_OTHER(2) #define I915_PMU_RC6_RESIDENCY __I915_PMU_OTHER(3) +#define I915_PMU_SOFTWARE_GT_AWAKE_TIME __I915_PMU_OTHER(4) #define I915_PMU_LAST /* Deprecated - do not use */ I915_PMU_RC6_RESIDENCY -- cgit v1.2.3 From 9bb85a6e29de5f9e1194c918dbfafbb3fcbbb157 Mon Sep 17 00:00:00 2001 From: Swati Sharma Date: Fri, 18 Dec 2020 16:07:09 +0530 Subject: drm/edid: Add additional HFVSDB fields for HDMI2.1 The HDMI2.1 extends HFVSDB (HDMI Forum Vendor Specific Data block) to have fields related to newly defined methods of FRL (Fixed Rate Link) levels, number of lanes supported, DSC Color bit depth, VRR min/max, FVA (Fast Vactive), ALLM etc. This patch adds the new HFVSDB fields that are required for HDMI2.1. v2: Minor fixes + consistent naming for DPCD register masks (Uma Shankar) Signed-off-by: Swati Sharma Signed-off-by: Ankit Nautiyal Reviewed-by: Uma Shankar [Jani: Fixed checkpatch FROM_SIGN_OFF_MISMATCH.] Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/20201218103723.30844-2-ankit.k.nautiyal@intel.com --- include/drm/drm_edid.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include') diff --git a/include/drm/drm_edid.h b/include/drm/drm_edid.h index e97daf6ffbb1..a158f585f658 100644 --- a/include/drm/drm_edid.h +++ b/include/drm/drm_edid.h @@ -229,6 +229,36 @@ struct detailed_timing { DRM_EDID_YCBCR420_DC_36 | \ DRM_EDID_YCBCR420_DC_30) +/* HDMI 2.1 additional fields */ +#define DRM_EDID_MAX_FRL_RATE_MASK 0xf0 +#define DRM_EDID_FAPA_START_LOCATION (1 << 0) +#define DRM_EDID_ALLM (1 << 1) +#define DRM_EDID_FVA (1 << 2) + +/* Deep Color specific */ +#define DRM_EDID_DC_30BIT_420 (1 << 0) +#define DRM_EDID_DC_36BIT_420 (1 << 1) +#define DRM_EDID_DC_48BIT_420 (1 << 2) + +/* VRR specific */ +#define DRM_EDID_CNMVRR (1 << 3) +#define DRM_EDID_CINEMA_VRR (1 << 4) +#define DRM_EDID_MDELTA (1 << 5) +#define DRM_EDID_VRR_MAX_UPPER_MASK 0xc0 +#define DRM_EDID_VRR_MAX_LOWER_MASK 0xff +#define DRM_EDID_VRR_MIN_MASK 0x3f + +/* DSC specific */ +#define DRM_EDID_DSC_10BPC (1 << 0) +#define DRM_EDID_DSC_12BPC (1 << 1) +#define DRM_EDID_DSC_16BPC (1 << 2) +#define DRM_EDID_DSC_ALL_BPP (1 << 3) +#define DRM_EDID_DSC_NATIVE_420 (1 << 6) +#define DRM_EDID_DSC_1P2 (1 << 7) +#define DRM_EDID_DSC_MAX_FRL_RATE_MASK 0xf0 +#define DRM_EDID_DSC_MAX_SLICES 0xf +#define DRM_EDID_DSC_TOTAL_CHUNK_KBYTES 0x3f + /* ELD Header Block */ #define DRM_ELD_HEADER_BLOCK_SIZE 4 -- cgit v1.2.3 From 4499d488f6eeb1f1d6a5c10c0c96361c02bb5145 Mon Sep 17 00:00:00 2001 From: Swati Sharma Date: Fri, 18 Dec 2020 16:07:10 +0530 Subject: drm/edid: Parse MAX_FRL field from HFVSDB block This patch parses MAX_FRL field to get the MAX rate in Gbps that the HDMI 2.1 panel can support in FRL mode. Source need this field to determine the optimal rate between the source and sink during FRL training. v2: Fixed minor bugs, and removed extra wrapper function (Uma Shankar) Signed-off-by: Swati Sharma Signed-off-by: Ankit Nautiyal Reviewed-by: Uma Shankar [Jani: Fixed checkpatch FROM_SIGN_OFF_MISMATCH, PARENTHESIS_ALIGNMENT.] Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/20201218103723.30844-3-ankit.k.nautiyal@intel.com --- drivers/gpu/drm/drm_edid.c | 44 ++++++++++++++++++++++++++++++++++++++++++++ include/drm/drm_connector.h | 6 ++++++ 2 files changed, 50 insertions(+) (limited to 'include') diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index 631125b46e04..184d97230453 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -4849,6 +4849,41 @@ static void drm_parse_vcdb(struct drm_connector *connector, const u8 *db) info->rgb_quant_range_selectable = true; } +static +void drm_get_max_frl_rate(int max_frl_rate, u8 *max_lanes, u8 *max_rate_per_lane) +{ + switch (max_frl_rate) { + case 1: + *max_lanes = 3; + *max_rate_per_lane = 3; + break; + case 2: + *max_lanes = 3; + *max_rate_per_lane = 6; + break; + case 3: + *max_lanes = 4; + *max_rate_per_lane = 6; + break; + case 4: + *max_lanes = 4; + *max_rate_per_lane = 8; + break; + case 5: + *max_lanes = 4; + *max_rate_per_lane = 10; + break; + case 6: + *max_lanes = 4; + *max_rate_per_lane = 12; + break; + case 0: + default: + *max_lanes = 0; + *max_rate_per_lane = 0; + } +} + static void drm_parse_ycbcr420_deep_color_info(struct drm_connector *connector, const u8 *db) { @@ -4902,6 +4937,15 @@ static void drm_parse_hdmi_forum_vsdb(struct drm_connector *connector, } } + if (hf_vsdb[7]) { + u8 max_frl_rate; + + DRM_DEBUG_KMS("hdmi_21 sink detected. parsing edid\n"); + max_frl_rate = (hf_vsdb[7] & DRM_EDID_MAX_FRL_RATE_MASK) >> 4; + drm_get_max_frl_rate(max_frl_rate, &hdmi->max_lanes, + &hdmi->max_frl_rate_per_lane); + } + drm_parse_ycbcr420_deep_color_info(connector, hf_vsdb); } diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h index 928136556174..f351bf10c076 100644 --- a/include/drm/drm_connector.h +++ b/include/drm/drm_connector.h @@ -207,6 +207,12 @@ struct drm_hdmi_info { /** @y420_dc_modes: bitmap of deep color support index */ u8 y420_dc_modes; + + /** @max_frl_rate_per_lane: support fixed rate link */ + u8 max_frl_rate_per_lane; + + /** @max_lanes: supported by sink */ + u8 max_lanes; }; /** -- cgit v1.2.3 From 76ee7b905678f415b49af9c2d4932844db8f01cd Mon Sep 17 00:00:00 2001 From: Ankit Nautiyal Date: Fri, 18 Dec 2020 16:07:11 +0530 Subject: drm/edid: Parse DSC1.2 cap fields from HFVSDB block This patch parses HFVSDB fields for DSC1.2 capabilities of an HDMI2.1 sink. These fields are required by a source to understand the DSC capability of the sink, to set appropriate PPS parameters, before transmitting compressed data stream. v2: Addressed following issues as suggested by Uma Shankar: -Added a new struct for hdmi dsc cap -Fixed bugs in macros usage. Signed-off-by: Ankit Nautiyal Reviewed-by: Uma Shankar [Jani: Fixed checkpatch PARENTHESIS_ALIGNMENT.] Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/20201218103723.30844-4-ankit.k.nautiyal@intel.com --- drivers/gpu/drm/drm_edid.c | 59 +++++++++++++++++++++++++++++++++++++++++++++ include/drm/drm_connector.h | 43 +++++++++++++++++++++++++++++++++ 2 files changed, 102 insertions(+) (limited to 'include') diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index 184d97230453..84be2bbd7549 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -4939,11 +4939,70 @@ static void drm_parse_hdmi_forum_vsdb(struct drm_connector *connector, if (hf_vsdb[7]) { u8 max_frl_rate; + u8 dsc_max_frl_rate; + u8 dsc_max_slices; + struct drm_hdmi_dsc_cap *hdmi_dsc = &hdmi->dsc_cap; DRM_DEBUG_KMS("hdmi_21 sink detected. parsing edid\n"); max_frl_rate = (hf_vsdb[7] & DRM_EDID_MAX_FRL_RATE_MASK) >> 4; drm_get_max_frl_rate(max_frl_rate, &hdmi->max_lanes, &hdmi->max_frl_rate_per_lane); + hdmi_dsc->v_1p2 = hf_vsdb[11] & DRM_EDID_DSC_1P2; + + if (hdmi_dsc->v_1p2) { + hdmi_dsc->native_420 = hf_vsdb[11] & DRM_EDID_DSC_NATIVE_420; + hdmi_dsc->all_bpp = hf_vsdb[11] & DRM_EDID_DSC_ALL_BPP; + + if (hf_vsdb[11] & DRM_EDID_DSC_16BPC) + hdmi_dsc->bpc_supported = 16; + else if (hf_vsdb[11] & DRM_EDID_DSC_12BPC) + hdmi_dsc->bpc_supported = 12; + else if (hf_vsdb[11] & DRM_EDID_DSC_10BPC) + hdmi_dsc->bpc_supported = 10; + else + hdmi_dsc->bpc_supported = 0; + + dsc_max_frl_rate = (hf_vsdb[12] & DRM_EDID_DSC_MAX_FRL_RATE_MASK) >> 4; + drm_get_max_frl_rate(dsc_max_frl_rate, &hdmi_dsc->max_lanes, + &hdmi_dsc->max_frl_rate_per_lane); + hdmi_dsc->total_chunk_kbytes = hf_vsdb[13] & DRM_EDID_DSC_TOTAL_CHUNK_KBYTES; + + dsc_max_slices = hf_vsdb[12] & DRM_EDID_DSC_MAX_SLICES; + switch (dsc_max_slices) { + case 1: + hdmi_dsc->max_slices = 1; + hdmi_dsc->clk_per_slice = 340; + break; + case 2: + hdmi_dsc->max_slices = 2; + hdmi_dsc->clk_per_slice = 340; + break; + case 3: + hdmi_dsc->max_slices = 4; + hdmi_dsc->clk_per_slice = 340; + break; + case 4: + hdmi_dsc->max_slices = 8; + hdmi_dsc->clk_per_slice = 340; + break; + case 5: + hdmi_dsc->max_slices = 8; + hdmi_dsc->clk_per_slice = 400; + break; + case 6: + hdmi_dsc->max_slices = 12; + hdmi_dsc->clk_per_slice = 400; + break; + case 7: + hdmi_dsc->max_slices = 16; + hdmi_dsc->clk_per_slice = 400; + break; + case 0: + default: + hdmi_dsc->max_slices = 0; + hdmi_dsc->clk_per_slice = 0; + } + } } drm_parse_ycbcr420_deep_color_info(connector, hf_vsdb); diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h index f351bf10c076..06d24e36268e 100644 --- a/include/drm/drm_connector.h +++ b/include/drm/drm_connector.h @@ -175,6 +175,46 @@ struct drm_scdc { struct drm_scrambling scrambling; }; +/** + * struct drm_hdmi_dsc_cap - DSC capabilities of HDMI sink + * + * Describes the DSC support provided by HDMI 2.1 sink. + * The information is fetched fom additional HFVSDB blocks defined + * for HDMI 2.1. + */ +struct drm_hdmi_dsc_cap { + /** @v_1p2: flag for dsc1.2 version support by sink */ + bool v_1p2; + + /** @native_420: Does sink support DSC with 4:2:0 compression */ + bool native_420; + + /** + * @all_bpp: Does sink support all bpp with 4:4:4: or 4:2:2 + * compressed formats + */ + bool all_bpp; + + /** + * @bpc_supported: compressed bpc supported by sink : 10, 12 or 16 bpc + */ + u8 bpc_supported; + + /** @max_slices: maximum number of Horizontal slices supported by */ + u8 max_slices; + + /** @clk_per_slice : max pixel clock in MHz supported per slice */ + int clk_per_slice; + + /** @max_lanes : dsc max lanes supported for Fixed rate Link training */ + u8 max_lanes; + + /** @max_frl_rate_per_lane : maximum frl rate with DSC per lane */ + u8 max_frl_rate_per_lane; + + /** @total_chunk_kbytes: max size of chunks in KBs supported per line*/ + u8 total_chunk_kbytes; +}; /** * struct drm_hdmi_info - runtime information about the connected HDMI sink @@ -213,6 +253,9 @@ struct drm_hdmi_info { /** @max_lanes: supported by sink */ u8 max_lanes; + + /** @dsc_cap: DSC capabilities of the sink */ + struct drm_hdmi_dsc_cap dsc_cap; }; /** -- cgit v1.2.3 From ce32a6239de6480fa535c1409de98e24dd5ec721 Mon Sep 17 00:00:00 2001 From: Ankit Nautiyal Date: Fri, 18 Dec 2020 16:07:12 +0530 Subject: drm/dp_helper: Add Helpers for FRL Link Training support for DP-HDMI2.1 PCON This patch adds support for configuring a PCON device, connected as a DP branched device to enable FRL Link training with a HDMI2.1 + sink. v2: Fixed typos and addressed other review comments from Uma Shankar. -changed the commit message for better clarity (Uma Shankar) -removed unnecessary argument supplied to a drm helper function. -fixed return value for max frl read from pcon. v3: Removed DPCD 0x3035 for MAX Sink FRL b/w as per new version of spec. Signed-off-by: Ankit Nautiyal Reviewed-by: Uma Shankar (v2) Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/20201218103723.30844-5-ankit.k.nautiyal@intel.com --- drivers/gpu/drm/drm_dp_helper.c | 263 ++++++++++++++++++++++++++++++++++++++++ include/drm/drm_dp_helper.h | 70 +++++++++++ 2 files changed, 333 insertions(+) (limited to 'include') diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c index 37ec3b94389c..5890e0ba2eb9 100644 --- a/drivers/gpu/drm/drm_dp_helper.c +++ b/drivers/gpu/drm/drm_dp_helper.c @@ -2596,3 +2596,266 @@ void drm_dp_vsc_sdp_log(const char *level, struct device *dev, #undef DP_SDP_LOG } EXPORT_SYMBOL(drm_dp_vsc_sdp_log); + +/** + * drm_dp_get_pcon_max_frl_bw() - maximum frl supported by PCON + * @dpcd: DisplayPort configuration data + * @port_cap: port capabilities + * + * Returns maximum frl bandwidth supported by PCON in GBPS, + * returns 0 if not supported. + */ +int drm_dp_get_pcon_max_frl_bw(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4]) +{ + int bw; + u8 buf; + + buf = port_cap[2]; + bw = buf & DP_PCON_MAX_FRL_BW; + + switch (bw) { + case DP_PCON_MAX_9GBPS: + return 9; + case DP_PCON_MAX_18GBPS: + return 18; + case DP_PCON_MAX_24GBPS: + return 24; + case DP_PCON_MAX_32GBPS: + return 32; + case DP_PCON_MAX_40GBPS: + return 40; + case DP_PCON_MAX_48GBPS: + return 48; + case DP_PCON_MAX_0GBPS: + default: + return 0; + } + + return 0; +} +EXPORT_SYMBOL(drm_dp_get_pcon_max_frl_bw); + +/** + * drm_dp_pcon_frl_prepare() - Prepare PCON for FRL. + * @aux: DisplayPort AUX channel + * + * Returns 0 if success, else returns negative error code. + */ +int drm_dp_pcon_frl_prepare(struct drm_dp_aux *aux, bool enable_frl_ready_hpd) +{ + int ret; + u8 buf = DP_PCON_ENABLE_SOURCE_CTL_MODE | + DP_PCON_ENABLE_LINK_FRL_MODE; + + if (enable_frl_ready_hpd) + buf |= DP_PCON_ENABLE_HPD_READY; + + ret = drm_dp_dpcd_writeb(aux, DP_PCON_HDMI_LINK_CONFIG_1, buf); + + return ret; +} +EXPORT_SYMBOL(drm_dp_pcon_frl_prepare); + +/** + * drm_dp_pcon_is_frl_ready() - Is PCON ready for FRL + * @aux: DisplayPort AUX channel + * + * Returns true if success, else returns false. + */ +bool drm_dp_pcon_is_frl_ready(struct drm_dp_aux *aux) +{ + int ret; + u8 buf; + + ret = drm_dp_dpcd_readb(aux, DP_PCON_HDMI_TX_LINK_STATUS, &buf); + if (ret < 0) + return false; + + if (buf & DP_PCON_FRL_READY) + return true; + + return false; +} +EXPORT_SYMBOL(drm_dp_pcon_is_frl_ready); + +/** + * drm_dp_pcon_frl_configure_1() - Set HDMI LINK Configuration-Step1 + * @aux: DisplayPort AUX channel + * @max_frl_gbps: maximum frl bw to be configured between PCON and HDMI sink + * @concurrent_mode: true if concurrent mode or operation is required, + * false otherwise. + * + * Returns 0 if success, else returns negative error code. + */ + +int drm_dp_pcon_frl_configure_1(struct drm_dp_aux *aux, int max_frl_gbps, + bool concurrent_mode) +{ + int ret; + u8 buf; + + ret = drm_dp_dpcd_readb(aux, DP_PCON_HDMI_LINK_CONFIG_1, &buf); + if (ret < 0) + return ret; + + if (concurrent_mode) + buf |= DP_PCON_ENABLE_CONCURRENT_LINK; + else + buf &= ~DP_PCON_ENABLE_CONCURRENT_LINK; + + switch (max_frl_gbps) { + case 9: + buf |= DP_PCON_ENABLE_MAX_BW_9GBPS; + break; + case 18: + buf |= DP_PCON_ENABLE_MAX_BW_18GBPS; + break; + case 24: + buf |= DP_PCON_ENABLE_MAX_BW_24GBPS; + break; + case 32: + buf |= DP_PCON_ENABLE_MAX_BW_32GBPS; + break; + case 40: + buf |= DP_PCON_ENABLE_MAX_BW_40GBPS; + break; + case 48: + buf |= DP_PCON_ENABLE_MAX_BW_48GBPS; + break; + case 0: + buf |= DP_PCON_ENABLE_MAX_BW_0GBPS; + break; + default: + return -EINVAL; + } + + ret = drm_dp_dpcd_writeb(aux, DP_PCON_HDMI_LINK_CONFIG_1, buf); + if (ret < 0) + return ret; + + return 0; +} +EXPORT_SYMBOL(drm_dp_pcon_frl_configure_1); + +/** + * drm_dp_pcon_frl_configure_2() - Set HDMI Link configuration Step-2 + * @aux: DisplayPort AUX channel + * @max_frl_mask : Max FRL BW to be tried by the PCON with HDMI Sink + * @extended_train_mode : true for Extended Mode, false for Normal Mode. + * In Normal mode, the PCON tries each frl bw from the max_frl_mask starting + * from min, and stops when link training is successful. In Extended mode, all + * frl bw selected in the mask are trained by the PCON. + * + * Returns 0 if success, else returns negative error code. + */ +int drm_dp_pcon_frl_configure_2(struct drm_dp_aux *aux, int max_frl_mask, + bool extended_train_mode) +{ + int ret; + u8 buf = max_frl_mask; + + if (extended_train_mode) + buf |= DP_PCON_FRL_LINK_TRAIN_EXTENDED; + + ret = drm_dp_dpcd_writeb(aux, DP_PCON_HDMI_LINK_CONFIG_2, buf); + if (ret < 0) + return ret; + + return 0; +} +EXPORT_SYMBOL(drm_dp_pcon_frl_configure_2); + +/** + * drm_dp_pcon_reset_frl_config() - Re-Set HDMI Link configuration. + * @aux: DisplayPort AUX channel + * + * Returns 0 if success, else returns negative error code. + */ +int drm_dp_pcon_reset_frl_config(struct drm_dp_aux *aux) +{ + int ret; + + ret = drm_dp_dpcd_writeb(aux, DP_PCON_HDMI_LINK_CONFIG_1, 0x0); + if (ret < 0) + return ret; + + return 0; +} +EXPORT_SYMBOL(drm_dp_pcon_reset_frl_config); + +/** + * drm_dp_pcon_frl_enable() - Enable HDMI link through FRL + * @aux: DisplayPort AUX channel + * + * Returns 0 if success, else returns negative error code. + */ +int drm_dp_pcon_frl_enable(struct drm_dp_aux *aux) +{ + int ret; + u8 buf = 0; + + ret = drm_dp_dpcd_readb(aux, DP_PCON_HDMI_LINK_CONFIG_1, &buf); + if (ret < 0) + return ret; + if (!(buf & DP_PCON_ENABLE_SOURCE_CTL_MODE)) { + DRM_DEBUG_KMS("PCON in Autonomous mode, can't enable FRL\n"); + return -EINVAL; + } + buf |= DP_PCON_ENABLE_HDMI_LINK; + ret = drm_dp_dpcd_writeb(aux, DP_PCON_HDMI_LINK_CONFIG_1, buf); + if (ret < 0) + return ret; + + return 0; +} +EXPORT_SYMBOL(drm_dp_pcon_frl_enable); + +/** + * drm_dp_pcon_hdmi_link_active() - check if the PCON HDMI LINK status is active. + * @aux: DisplayPort AUX channel + * + * Returns true if link is active else returns false. + */ +bool drm_dp_pcon_hdmi_link_active(struct drm_dp_aux *aux) +{ + u8 buf; + int ret; + + ret = drm_dp_dpcd_readb(aux, DP_PCON_HDMI_TX_LINK_STATUS, &buf); + if (ret < 0) + return false; + + return buf & DP_PCON_HDMI_TX_LINK_ACTIVE; +} +EXPORT_SYMBOL(drm_dp_pcon_hdmi_link_active); + +/** + * drm_dp_pcon_hdmi_link_mode() - get the PCON HDMI LINK MODE + * @aux: DisplayPort AUX channel + * @frl_trained_mask: pointer to store bitmask of the trained bw configuration. + * Valid only if the MODE returned is FRL. For Normal Link training mode + * only 1 of the bits will be set, but in case of Extended mode, more than + * one bits can be set. + * + * Returns the link mode : TMDS or FRL on success, else returns negative error + * code. + */ +int drm_dp_pcon_hdmi_link_mode(struct drm_dp_aux *aux, u8 *frl_trained_mask) +{ + u8 buf; + int mode; + int ret; + + ret = drm_dp_dpcd_readb(aux, DP_PCON_HDMI_POST_FRL_STATUS, &buf); + if (ret < 0) + return ret; + + mode = buf & DP_PCON_HDMI_LINK_MODE; + + if (frl_trained_mask && DP_PCON_HDMI_MODE_FRL == mode) + *frl_trained_mask = (buf & DP_PCON_HDMI_FRL_TRAINED_BW) >> 1; + + return mode; +} +EXPORT_SYMBOL(drm_dp_pcon_hdmi_link_mode); diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h index 6b40258927bf..c66f570eadc2 100644 --- a/include/drm/drm_dp_helper.h +++ b/include/drm/drm_dp_helper.h @@ -411,6 +411,17 @@ struct drm_device; # define DP_DS_10BPC 1 # define DP_DS_12BPC 2 # define DP_DS_16BPC 3 +/* HDMI2.1 PCON FRL CONFIGURATION */ +# define DP_PCON_MAX_FRL_BW (7 << 2) +# define DP_PCON_MAX_0GBPS (0 << 2) +# define DP_PCON_MAX_9GBPS (1 << 2) +# define DP_PCON_MAX_18GBPS (2 << 2) +# define DP_PCON_MAX_24GBPS (3 << 2) +# define DP_PCON_MAX_32GBPS (4 << 2) +# define DP_PCON_MAX_40GBPS (5 << 2) +# define DP_PCON_MAX_48GBPS (6 << 2) +# define DP_PCON_SOURCE_CTL_MODE (1 << 5) + /* offset 3 for DVI */ # define DP_DS_DVI_DUAL_LINK (1 << 1) # define DP_DS_DVI_HIGH_COLOR_DEPTH (1 << 2) @@ -1054,6 +1065,51 @@ struct drm_device; #define DP_CEC_TX_MESSAGE_BUFFER 0x3020 #define DP_CEC_MESSAGE_BUFFER_LENGTH 0x10 +/* PCON CONFIGURE-1 FRL FOR HDMI SINK */ +#define DP_PCON_HDMI_LINK_CONFIG_1 0x305A +# define DP_PCON_ENABLE_MAX_FRL_BW (7 << 0) +# define DP_PCON_ENABLE_MAX_BW_0GBPS 0 +# define DP_PCON_ENABLE_MAX_BW_9GBPS 1 +# define DP_PCON_ENABLE_MAX_BW_18GBPS 2 +# define DP_PCON_ENABLE_MAX_BW_24GBPS 3 +# define DP_PCON_ENABLE_MAX_BW_32GBPS 4 +# define DP_PCON_ENABLE_MAX_BW_40GBPS 5 +# define DP_PCON_ENABLE_MAX_BW_48GBPS 6 +# define DP_PCON_ENABLE_SOURCE_CTL_MODE (1 << 3) +# define DP_PCON_ENABLE_CONCURRENT_LINK (1 << 4) +# define DP_PCON_ENABLE_LINK_FRL_MODE (1 << 5) +# define DP_PCON_ENABLE_HPD_READY (1 << 6) +# define DP_PCON_ENABLE_HDMI_LINK (1 << 7) + +/* PCON CONFIGURE-2 FRL FOR HDMI SINK */ +#define DP_PCON_HDMI_LINK_CONFIG_2 0x305B +# define DP_PCON_MAX_LINK_BW_MASK (0x3F << 0) +# define DP_PCON_FRL_BW_MASK_9GBPS (1 << 0) +# define DP_PCON_FRL_BW_MASK_18GBPS (1 << 1) +# define DP_PCON_FRL_BW_MASK_24GBPS (1 << 2) +# define DP_PCON_FRL_BW_MASK_32GBPS (1 << 3) +# define DP_PCON_FRL_BW_MASK_40GBPS (1 << 4) +# define DP_PCON_FRL_BW_MASK_48GBPS (1 << 5) +# define DP_PCON_FRL_LINK_TRAIN_EXTENDED (1 << 6) + +/* PCON HDMI LINK STATUS */ +#define DP_PCON_HDMI_TX_LINK_STATUS 0x303B +# define DP_PCON_HDMI_TX_LINK_ACTIVE (1 << 0) +# define DP_PCON_FRL_READY (1 << 1) + +/* PCON HDMI POST FRL STATUS */ +#define DP_PCON_HDMI_POST_FRL_STATUS 0x3036 +# define DP_PCON_HDMI_LINK_MODE (1 << 0) +# define DP_PCON_HDMI_MODE_TMDS 0 +# define DP_PCON_HDMI_MODE_FRL 1 +# define DP_PCON_HDMI_FRL_TRAINED_BW (0x3F << 1) +# define DP_PCON_FRL_TRAINED_BW_9GBPS (1 << 1) +# define DP_PCON_FRL_TRAINED_BW_18GBPS (1 << 2) +# define DP_PCON_FRL_TRAINED_BW_24GBPS (1 << 3) +# define DP_PCON_FRL_TRAINED_BW_32GBPS (1 << 4) +# define DP_PCON_FRL_TRAINED_BW_40GBPS (1 << 5) +# define DP_PCON_FRL_TRAINED_BW_48GBPS (1 << 6) + #define DP_PROTOCOL_CONVERTER_CONTROL_0 0x3050 /* DP 1.3 */ # define DP_HDMI_DVI_OUTPUT_CONFIG (1 << 0) /* DP 1.3 */ #define DP_PROTOCOL_CONVERTER_CONTROL_1 0x3051 /* DP 1.3 */ @@ -1967,4 +2023,18 @@ int drm_dp_get_phy_test_pattern(struct drm_dp_aux *aux, struct drm_dp_phy_test_params *data); int drm_dp_set_phy_test_pattern(struct drm_dp_aux *aux, struct drm_dp_phy_test_params *data, u8 dp_rev); +int drm_dp_get_pcon_max_frl_bw(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4]); +int drm_dp_pcon_frl_prepare(struct drm_dp_aux *aux, bool enable_frl_ready_hpd); +bool drm_dp_pcon_is_frl_ready(struct drm_dp_aux *aux); +int drm_dp_pcon_frl_configure_1(struct drm_dp_aux *aux, int max_frl_gbps, + bool concurrent_mode); +int drm_dp_pcon_frl_configure_2(struct drm_dp_aux *aux, int max_frl_mask, + bool extended_train_mode); +int drm_dp_pcon_reset_frl_config(struct drm_dp_aux *aux); +int drm_dp_pcon_frl_enable(struct drm_dp_aux *aux); + +bool drm_dp_pcon_hdmi_link_active(struct drm_dp_aux *aux); +int drm_dp_pcon_hdmi_link_mode(struct drm_dp_aux *aux, u8 *frl_trained_mask); + #endif /* _DRM_DP_HELPER_H_ */ -- cgit v1.2.3 From 3ce98018c8f9a5de857a9f4bcd300ecf9fc8280b Mon Sep 17 00:00:00 2001 From: Swati Sharma Date: Fri, 18 Dec 2020 16:07:13 +0530 Subject: drm/dp_helper: Add support for link failure detection There are specific DPCDs defined for detecting link failures between the PCON and HDMI sink and check the link status. In case of link failure, PCON will communicate the same using an IRQ_HPD to source. HDMI sink would have indicated the same to PCON using SCDC interrupt mechanism. While source can always read final HDMI sink's status using I2C over AUX, it is easier and faster to read the PCONs already read HDMI sink status registers. This patch adds the DPCDs required for link failure detection and provide a helper function for printing error count/lane which might help in debugging the link failure issues. v2: Addressed comments from Uma Shankar: -rephrased the commit message, as per the code. -fixed styling issues -added documentation for the helper function. Signed-off-by: Swati Sharma Signed-off-by: Ankit Nautiyal Reviewed-by: Uma Shankar [Jani: Fixed checkpatch PARENTHESIS_ALIGNMENT.] Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/20201218103723.30844-6-ankit.k.nautiyal@intel.com --- drivers/gpu/drm/drm_dp_helper.c | 39 +++++++++++++++++++++++++++++++++++++++ include/drm/drm_dp_helper.h | 17 +++++++++++++++++ 2 files changed, 56 insertions(+) (limited to 'include') diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c index 5890e0ba2eb9..404bc0ba9475 100644 --- a/drivers/gpu/drm/drm_dp_helper.c +++ b/drivers/gpu/drm/drm_dp_helper.c @@ -2859,3 +2859,42 @@ int drm_dp_pcon_hdmi_link_mode(struct drm_dp_aux *aux, u8 *frl_trained_mask) return mode; } EXPORT_SYMBOL(drm_dp_pcon_hdmi_link_mode); + +/** + * drm_dp_pcon_hdmi_frl_link_error_count() - print the error count per lane + * during link failure between PCON and HDMI sink + * @aux: DisplayPort AUX channel + * @connector: DRM connector + * code. + **/ + +void drm_dp_pcon_hdmi_frl_link_error_count(struct drm_dp_aux *aux, + struct drm_connector *connector) +{ + u8 buf, error_count; + int i, num_error; + struct drm_hdmi_info *hdmi = &connector->display_info.hdmi; + + for (i = 0; i < hdmi->max_lanes; i++) { + if (drm_dp_dpcd_readb(aux, DP_PCON_HDMI_ERROR_STATUS_LN0 + i, &buf) < 0) + return; + + error_count = buf & DP_PCON_HDMI_ERROR_COUNT_MASK; + switch (error_count) { + case DP_PCON_HDMI_ERROR_COUNT_HUNDRED_PLUS: + num_error = 100; + break; + case DP_PCON_HDMI_ERROR_COUNT_TEN_PLUS: + num_error = 10; + break; + case DP_PCON_HDMI_ERROR_COUNT_THREE_PLUS: + num_error = 3; + break; + default: + num_error = 0; + } + + DRM_ERROR("More than %d errors since the last read for lane %d", num_error, i); + } +} +EXPORT_SYMBOL(drm_dp_pcon_hdmi_frl_link_error_count); diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h index c66f570eadc2..84ba30e4eeb3 100644 --- a/include/drm/drm_dp_helper.h +++ b/include/drm/drm_dp_helper.h @@ -946,6 +946,11 @@ struct drm_device; # define DP_CEC_IRQ (1 << 2) #define DP_LINK_SERVICE_IRQ_VECTOR_ESI0 0x2005 /* 1.2 */ +# define RX_CAP_CHANGED (1 << 0) +# define LINK_STATUS_CHANGED (1 << 1) +# define STREAM_STATUS_CHANGED (1 << 2) +# define HDMI_LINK_STATUS_CHANGED (1 << 3) +# define CONNECTED_OFF_ENTRY_REQUESTED (1 << 4) #define DP_PSR_ERROR_STATUS 0x2006 /* XXX 1.2? */ # define DP_PSR_LINK_CRC_ERROR (1 << 0) @@ -1120,6 +1125,16 @@ struct drm_device; #define DP_PROTOCOL_CONVERTER_CONTROL_2 0x3052 /* DP 1.3 */ # define DP_CONVERSION_TO_YCBCR422_ENABLE (1 << 0) /* DP 1.3 */ +/* PCON Downstream HDMI ERROR Status per Lane */ +#define DP_PCON_HDMI_ERROR_STATUS_LN0 0x3037 +#define DP_PCON_HDMI_ERROR_STATUS_LN1 0x3038 +#define DP_PCON_HDMI_ERROR_STATUS_LN2 0x3039 +#define DP_PCON_HDMI_ERROR_STATUS_LN3 0x303A +# define DP_PCON_HDMI_ERROR_COUNT_MASK (0x7 << 0) +# define DP_PCON_HDMI_ERROR_COUNT_THREE_PLUS (1 << 0) +# define DP_PCON_HDMI_ERROR_COUNT_TEN_PLUS (1 << 1) +# define DP_PCON_HDMI_ERROR_COUNT_HUNDRED_PLUS (1 << 2) + /* HDCP 1.3 and HDCP 2.2 */ #define DP_AUX_HDCP_BKSV 0x68000 #define DP_AUX_HDCP_RI_PRIME 0x68005 @@ -2036,5 +2051,7 @@ int drm_dp_pcon_frl_enable(struct drm_dp_aux *aux); bool drm_dp_pcon_hdmi_link_active(struct drm_dp_aux *aux); int drm_dp_pcon_hdmi_link_mode(struct drm_dp_aux *aux, u8 *frl_trained_mask); +void drm_dp_pcon_hdmi_frl_link_error_count(struct drm_dp_aux *aux, + struct drm_connector *connector); #endif /* _DRM_DP_HELPER_H_ */ -- cgit v1.2.3 From e2e16da398d9149ede0162a55f44537582aed2e7 Mon Sep 17 00:00:00 2001 From: Ankit Nautiyal Date: Tue, 22 Dec 2020 17:50:27 +0200 Subject: drm/dp_helper: Add support for Configuring DSC for HDMI2.1 Pcon This patch adds registers for getting DSC encoder capability for a HDMI2.1 PCon. It also addes helper functions to configure DSC between the PCON and HDMI2.1 sink. v2: Corrected offset for DSC encoder bpc and minor changes. Also added helper functions for getting pcon dsc encoder capabilities as suggested by Uma Shankar. v3: Only setting the DSC bits for the Protocol Converter control registers, avoiding overwritining color conversion bits. Signed-off-by: Ankit Nautiyal Reviewed-by: Uma Shankar (v2) [Jani: Fixed checkpatch BLOCK_COMMENT_STYLE.] Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/20201218103723.30844-7-ankit.k.nautiyal@intel.com --- drivers/gpu/drm/drm_dp_helper.c | 203 ++++++++++++++++++++++++++++++++++++++++ include/drm/drm_dp_helper.h | 114 ++++++++++++++++++++++ 2 files changed, 317 insertions(+) (limited to 'include') diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c index 404bc0ba9475..3b4e96bfb1c3 100644 --- a/drivers/gpu/drm/drm_dp_helper.c +++ b/drivers/gpu/drm/drm_dp_helper.c @@ -2898,3 +2898,206 @@ void drm_dp_pcon_hdmi_frl_link_error_count(struct drm_dp_aux *aux, } } EXPORT_SYMBOL(drm_dp_pcon_hdmi_frl_link_error_count); + +/* + * drm_dp_pcon_enc_is_dsc_1_2 - Does PCON Encoder supports DSC 1.2 + * @pcon_dsc_dpcd: DSC capabilities of the PCON DSC Encoder + * + * Returns true is PCON encoder is DSC 1.2 else returns false. + */ +bool drm_dp_pcon_enc_is_dsc_1_2(const u8 pcon_dsc_dpcd[DP_PCON_DSC_ENCODER_CAP_SIZE]) +{ + u8 buf; + u8 major_v, minor_v; + + buf = pcon_dsc_dpcd[DP_PCON_DSC_VERSION - DP_PCON_DSC_ENCODER]; + major_v = (buf & DP_PCON_DSC_MAJOR_MASK) >> DP_PCON_DSC_MAJOR_SHIFT; + minor_v = (buf & DP_PCON_DSC_MINOR_MASK) >> DP_PCON_DSC_MINOR_SHIFT; + + if (major_v == 1 && minor_v == 2) + return true; + + return false; +} +EXPORT_SYMBOL(drm_dp_pcon_enc_is_dsc_1_2); + +/* + * drm_dp_pcon_dsc_max_slices - Get max slices supported by PCON DSC Encoder + * @pcon_dsc_dpcd: DSC capabilities of the PCON DSC Encoder + * + * Returns maximum no. of slices supported by the PCON DSC Encoder. + */ +int drm_dp_pcon_dsc_max_slices(const u8 pcon_dsc_dpcd[DP_PCON_DSC_ENCODER_CAP_SIZE]) +{ + u8 slice_cap1, slice_cap2; + + slice_cap1 = pcon_dsc_dpcd[DP_PCON_DSC_SLICE_CAP_1 - DP_PCON_DSC_ENCODER]; + slice_cap2 = pcon_dsc_dpcd[DP_PCON_DSC_SLICE_CAP_2 - DP_PCON_DSC_ENCODER]; + + if (slice_cap2 & DP_PCON_DSC_24_PER_DSC_ENC) + return 24; + if (slice_cap2 & DP_PCON_DSC_20_PER_DSC_ENC) + return 20; + if (slice_cap2 & DP_PCON_DSC_16_PER_DSC_ENC) + return 16; + if (slice_cap1 & DP_PCON_DSC_12_PER_DSC_ENC) + return 12; + if (slice_cap1 & DP_PCON_DSC_10_PER_DSC_ENC) + return 10; + if (slice_cap1 & DP_PCON_DSC_8_PER_DSC_ENC) + return 8; + if (slice_cap1 & DP_PCON_DSC_6_PER_DSC_ENC) + return 6; + if (slice_cap1 & DP_PCON_DSC_4_PER_DSC_ENC) + return 4; + if (slice_cap1 & DP_PCON_DSC_2_PER_DSC_ENC) + return 2; + if (slice_cap1 & DP_PCON_DSC_1_PER_DSC_ENC) + return 1; + + return 0; +} +EXPORT_SYMBOL(drm_dp_pcon_dsc_max_slices); + +/* + * drm_dp_pcon_dsc_max_slice_width() - Get max slice width for Pcon DSC encoder + * @pcon_dsc_dpcd: DSC capabilities of the PCON DSC Encoder + * + * Returns maximum width of the slices in pixel width i.e. no. of pixels x 320. + */ +int drm_dp_pcon_dsc_max_slice_width(const u8 pcon_dsc_dpcd[DP_PCON_DSC_ENCODER_CAP_SIZE]) +{ + u8 buf; + + buf = pcon_dsc_dpcd[DP_PCON_DSC_MAX_SLICE_WIDTH - DP_PCON_DSC_ENCODER]; + + return buf * DP_DSC_SLICE_WIDTH_MULTIPLIER; +} +EXPORT_SYMBOL(drm_dp_pcon_dsc_max_slice_width); + +/* + * drm_dp_pcon_dsc_bpp_incr() - Get bits per pixel increment for PCON DSC encoder + * @pcon_dsc_dpcd: DSC capabilities of the PCON DSC Encoder + * + * Returns the bpp precision supported by the PCON encoder. + */ +int drm_dp_pcon_dsc_bpp_incr(const u8 pcon_dsc_dpcd[DP_PCON_DSC_ENCODER_CAP_SIZE]) +{ + u8 buf; + + buf = pcon_dsc_dpcd[DP_PCON_DSC_BPP_INCR - DP_PCON_DSC_ENCODER]; + + switch (buf & DP_PCON_DSC_BPP_INCR_MASK) { + case DP_PCON_DSC_ONE_16TH_BPP: + return 16; + case DP_PCON_DSC_ONE_8TH_BPP: + return 8; + case DP_PCON_DSC_ONE_4TH_BPP: + return 4; + case DP_PCON_DSC_ONE_HALF_BPP: + return 2; + case DP_PCON_DSC_ONE_BPP: + return 1; + } + + return 0; +} +EXPORT_SYMBOL(drm_dp_pcon_dsc_bpp_incr); + +static +int drm_dp_pcon_configure_dsc_enc(struct drm_dp_aux *aux, u8 pps_buf_config) +{ + u8 buf; + int ret; + + ret = drm_dp_dpcd_readb(aux, DP_PROTOCOL_CONVERTER_CONTROL_2, &buf); + if (ret < 0) + return ret; + + buf |= DP_PCON_ENABLE_DSC_ENCODER; + + if (pps_buf_config <= DP_PCON_ENC_PPS_OVERRIDE_EN_BUFFER) { + buf &= ~DP_PCON_ENCODER_PPS_OVERRIDE_MASK; + buf |= pps_buf_config << 2; + } + + ret = drm_dp_dpcd_writeb(aux, DP_PROTOCOL_CONVERTER_CONTROL_2, buf); + if (ret < 0) + return ret; + + return 0; +} + +/** + * drm_dp_pcon_pps_default() - Let PCON fill the default pps parameters + * for DSC1.2 between PCON & HDMI2.1 sink + * @aux: DisplayPort AUX channel + * + * Returns 0 on success, else returns negative error code. + */ +int drm_dp_pcon_pps_default(struct drm_dp_aux *aux) +{ + int ret; + + ret = drm_dp_pcon_configure_dsc_enc(aux, DP_PCON_ENC_PPS_OVERRIDE_DISABLED); + if (ret < 0) + return ret; + + return 0; +} +EXPORT_SYMBOL(drm_dp_pcon_pps_default); + +/** + * drm_dp_pcon_pps_override_buf() - Configure PPS encoder override buffer for + * HDMI sink + * @aux: DisplayPort AUX channel + * @pps_buf: 128 bytes to be written into PPS buffer for HDMI sink by PCON. + * + * Returns 0 on success, else returns negative error code. + */ +int drm_dp_pcon_pps_override_buf(struct drm_dp_aux *aux, u8 pps_buf[128]) +{ + int ret; + + ret = drm_dp_dpcd_write(aux, DP_PCON_HDMI_PPS_OVERRIDE_BASE, &pps_buf, 128); + if (ret < 0) + return ret; + + ret = drm_dp_pcon_configure_dsc_enc(aux, DP_PCON_ENC_PPS_OVERRIDE_EN_BUFFER); + if (ret < 0) + return ret; + + return 0; +} +EXPORT_SYMBOL(drm_dp_pcon_pps_override_buf); + +/* + * drm_dp_pcon_pps_override_param() - Write PPS parameters to DSC encoder + * override registers + * @aux: DisplayPort AUX channel + * @pps_param: 3 Parameters (2 Bytes each) : Slice Width, Slice Height, + * bits_per_pixel. + * + * Returns 0 on success, else returns negative error code. + */ +int drm_dp_pcon_pps_override_param(struct drm_dp_aux *aux, u8 pps_param[6]) +{ + int ret; + + ret = drm_dp_dpcd_write(aux, DP_PCON_HDMI_PPS_OVRD_SLICE_HEIGHT, &pps_param[0], 2); + if (ret < 0) + return ret; + ret = drm_dp_dpcd_write(aux, DP_PCON_HDMI_PPS_OVRD_SLICE_WIDTH, &pps_param[2], 2); + if (ret < 0) + return ret; + ret = drm_dp_dpcd_write(aux, DP_PCON_HDMI_PPS_OVRD_BPP, &pps_param[4], 2); + if (ret < 0) + return ret; + + ret = drm_dp_pcon_configure_dsc_enc(aux, DP_PCON_ENC_PPS_OVERRIDE_EN_BUFFER); + if (ret < 0) + return ret; + + return 0; +} +EXPORT_SYMBOL(drm_dp_pcon_pps_override_param); diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h index 84ba30e4eeb3..e909c66b205a 100644 --- a/include/drm/drm_dp_helper.h +++ b/include/drm/drm_dp_helper.h @@ -441,6 +441,84 @@ struct drm_device; # define DP_FEC_CORR_BLK_ERROR_COUNT_CAP (1 << 2) # define DP_FEC_BIT_ERROR_COUNT_CAP (1 << 3) +/* DP-HDMI2.1 PCON DSC ENCODER SUPPORT */ +#define DP_PCON_DSC_ENCODER_CAP_SIZE 0xC /* 0x9E - 0x92 */ +#define DP_PCON_DSC_ENCODER 0x092 +# define DP_PCON_DSC_ENCODER_SUPPORTED (1 << 0) +# define DP_PCON_DSC_PPS_ENC_OVERRIDE (1 << 1) + +/* DP-HDMI2.1 PCON DSC Version */ +#define DP_PCON_DSC_VERSION 0x093 +# define DP_PCON_DSC_MAJOR_MASK (0xF << 0) +# define DP_PCON_DSC_MINOR_MASK (0xF << 4) +# define DP_PCON_DSC_MAJOR_SHIFT 0 +# define DP_PCON_DSC_MINOR_SHIFT 4 + +/* DP-HDMI2.1 PCON DSC RC Buffer block size */ +#define DP_PCON_DSC_RC_BUF_BLK_INFO 0x094 +# define DP_PCON_DSC_RC_BUF_BLK_SIZE (0x3 << 0) +# define DP_PCON_DSC_RC_BUF_BLK_1KB 0 +# define DP_PCON_DSC_RC_BUF_BLK_4KB 1 +# define DP_PCON_DSC_RC_BUF_BLK_16KB 2 +# define DP_PCON_DSC_RC_BUF_BLK_64KB 3 + +/* DP-HDMI2.1 PCON DSC RC Buffer size */ +#define DP_PCON_DSC_RC_BUF_SIZE 0x095 + +/* DP-HDMI2.1 PCON DSC Slice capabilities-1 */ +#define DP_PCON_DSC_SLICE_CAP_1 0x096 +# define DP_PCON_DSC_1_PER_DSC_ENC (0x1 << 0) +# define DP_PCON_DSC_2_PER_DSC_ENC (0x1 << 1) +# define DP_PCON_DSC_4_PER_DSC_ENC (0x1 << 3) +# define DP_PCON_DSC_6_PER_DSC_ENC (0x1 << 4) +# define DP_PCON_DSC_8_PER_DSC_ENC (0x1 << 5) +# define DP_PCON_DSC_10_PER_DSC_ENC (0x1 << 6) +# define DP_PCON_DSC_12_PER_DSC_ENC (0x1 << 7) + +#define DP_PCON_DSC_BUF_BIT_DEPTH 0x097 +# define DP_PCON_DSC_BIT_DEPTH_MASK (0xF << 0) +# define DP_PCON_DSC_DEPTH_9_BITS 0 +# define DP_PCON_DSC_DEPTH_10_BITS 1 +# define DP_PCON_DSC_DEPTH_11_BITS 2 +# define DP_PCON_DSC_DEPTH_12_BITS 3 +# define DP_PCON_DSC_DEPTH_13_BITS 4 +# define DP_PCON_DSC_DEPTH_14_BITS 5 +# define DP_PCON_DSC_DEPTH_15_BITS 6 +# define DP_PCON_DSC_DEPTH_16_BITS 7 +# define DP_PCON_DSC_DEPTH_8_BITS 8 + +#define DP_PCON_DSC_BLOCK_PREDICTION 0x098 +# define DP_PCON_DSC_BLOCK_PRED_SUPPORT (0x1 << 0) + +#define DP_PCON_DSC_ENC_COLOR_FMT_CAP 0x099 +# define DP_PCON_DSC_ENC_RGB (0x1 << 0) +# define DP_PCON_DSC_ENC_YUV444 (0x1 << 1) +# define DP_PCON_DSC_ENC_YUV422_S (0x1 << 2) +# define DP_PCON_DSC_ENC_YUV422_N (0x1 << 3) +# define DP_PCON_DSC_ENC_YUV420_N (0x1 << 4) + +#define DP_PCON_DSC_ENC_COLOR_DEPTH_CAP 0x09A +# define DP_PCON_DSC_ENC_8BPC (0x1 << 1) +# define DP_PCON_DSC_ENC_10BPC (0x1 << 2) +# define DP_PCON_DSC_ENC_12BPC (0x1 << 3) + +#define DP_PCON_DSC_MAX_SLICE_WIDTH 0x09B + +/* DP-HDMI2.1 PCON DSC Slice capabilities-2 */ +#define DP_PCON_DSC_SLICE_CAP_2 0x09C +# define DP_PCON_DSC_16_PER_DSC_ENC (0x1 << 0) +# define DP_PCON_DSC_20_PER_DSC_ENC (0x1 << 1) +# define DP_PCON_DSC_24_PER_DSC_ENC (0x1 << 2) + +/* DP-HDMI2.1 PCON HDMI TX Encoder Bits/pixel increment */ +#define DP_PCON_DSC_BPP_INCR 0x09E +# define DP_PCON_DSC_BPP_INCR_MASK (0x7 << 0) +# define DP_PCON_DSC_ONE_16TH_BPP 0 +# define DP_PCON_DSC_ONE_8TH_BPP 1 +# define DP_PCON_DSC_ONE_4TH_BPP 2 +# define DP_PCON_DSC_ONE_HALF_BPP 3 +# define DP_PCON_DSC_ONE_BPP 4 + /* DP Extended DSC Capabilities */ #define DP_DSC_BRANCH_OVERALL_THROUGHPUT_0 0x0a0 /* DP 1.4a SCR */ #define DP_DSC_BRANCH_OVERALL_THROUGHPUT_1 0x0a1 @@ -1124,6 +1202,12 @@ struct drm_device; # define DP_HDMI_FORCE_SCRAMBLING (1 << 3) /* DP 1.4 */ #define DP_PROTOCOL_CONVERTER_CONTROL_2 0x3052 /* DP 1.3 */ # define DP_CONVERSION_TO_YCBCR422_ENABLE (1 << 0) /* DP 1.3 */ +# define DP_PCON_ENABLE_DSC_ENCODER (1 << 1) +# define DP_PCON_ENCODER_PPS_OVERRIDE_MASK (0x3 << 2) +# define DP_PCON_ENC_PPS_OVERRIDE_DISABLED 0 +# define DP_PCON_ENC_PPS_OVERRIDE_EN_PARAMS 1 +# define DP_PCON_ENC_PPS_OVERRIDE_EN_BUFFER 2 + /* PCON Downstream HDMI ERROR Status per Lane */ #define DP_PCON_HDMI_ERROR_STATUS_LN0 0x3037 @@ -1135,6 +1219,29 @@ struct drm_device; # define DP_PCON_HDMI_ERROR_COUNT_TEN_PLUS (1 << 1) # define DP_PCON_HDMI_ERROR_COUNT_HUNDRED_PLUS (1 << 2) +/* PCON HDMI CONFIG PPS Override Buffer + * Valid Offsets to be added to Base : 0-127 + */ +#define DP_PCON_HDMI_PPS_OVERRIDE_BASE 0x3100 + +/* PCON HDMI CONFIG PPS Override Parameter: Slice height + * Offset-0 8LSBs of the Slice height. + * Offset-1 8MSBs of the Slice height. + */ +#define DP_PCON_HDMI_PPS_OVRD_SLICE_HEIGHT 0x3180 + +/* PCON HDMI CONFIG PPS Override Parameter: Slice width + * Offset-0 8LSBs of the Slice width. + * Offset-1 8MSBs of the Slice width. + */ +#define DP_PCON_HDMI_PPS_OVRD_SLICE_WIDTH 0x3182 + +/* PCON HDMI CONFIG PPS Override Parameter: bits_per_pixel + * Offset-0 8LSBs of the bits_per_pixel. + * Offset-1 2MSBs of the bits_per_pixel. + */ +#define DP_PCON_HDMI_PPS_OVRD_BPP 0x3184 + /* HDCP 1.3 and HDCP 2.2 */ #define DP_AUX_HDCP_BKSV 0x68000 #define DP_AUX_HDCP_RI_PRIME 0x68005 @@ -2053,5 +2160,12 @@ bool drm_dp_pcon_hdmi_link_active(struct drm_dp_aux *aux); int drm_dp_pcon_hdmi_link_mode(struct drm_dp_aux *aux, u8 *frl_trained_mask); void drm_dp_pcon_hdmi_frl_link_error_count(struct drm_dp_aux *aux, struct drm_connector *connector); +bool drm_dp_pcon_enc_is_dsc_1_2(const u8 pcon_dsc_dpcd[DP_PCON_DSC_ENCODER_CAP_SIZE]); +int drm_dp_pcon_dsc_max_slices(const u8 pcon_dsc_dpcd[DP_PCON_DSC_ENCODER_CAP_SIZE]); +int drm_dp_pcon_dsc_max_slice_width(const u8 pcon_dsc_dpcd[DP_PCON_DSC_ENCODER_CAP_SIZE]); +int drm_dp_pcon_dsc_bpp_incr(const u8 pcon_dsc_dpcd[DP_PCON_DSC_ENCODER_CAP_SIZE]); +int drm_dp_pcon_pps_default(struct drm_dp_aux *aux); +int drm_dp_pcon_pps_override_buf(struct drm_dp_aux *aux, u8 pps_buf[128]); +int drm_dp_pcon_pps_override_param(struct drm_dp_aux *aux, u8 pps_param[6]); #endif /* _DRM_DP_HELPER_H_ */ -- cgit v1.2.3 From 07c9b8634fb6c5c3fd4cdf363bdf472a365789d0 Mon Sep 17 00:00:00 2001 From: Ankit Nautiyal Date: Fri, 18 Dec 2020 16:07:15 +0530 Subject: drm/dp_helper: Add helpers to configure PCONs RGB-YCbCr Conversion DP Specification for DP2.0 to HDMI2.1 Pcon specifies support for conversion of colorspace from RGB to YCbCr. https://groups.vesa.org/wg/DP/document/previewpdf/15651 This patch adds the relavant registers and helper functions to get the capability and set the color conversion bits for rgb->ycbcr conversion through PCON. v2: As suggested in review comments: -Fixed bug in the check condition in a drm_helper as reported by Dan Carpenter and Kernel test robot. (Dan Carepenter) -Modified the color-conversion cap helper function, to accommodate BT709 and BT2020 colorspace. (Uma Shankar) -Added spec details for the new cap for color conversion. (Uma Shankar) Signed-off-by: Ankit Nautiyal Reviewed-by: Uma Shankar Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/20201218103723.30844-8-ankit.k.nautiyal@intel.com --- drivers/gpu/drm/drm_dp_helper.c | 61 +++++++++++++++++++++++++++++++++++++++++ include/drm/drm_dp_helper.h | 19 ++++++++++++- 2 files changed, 79 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c index 3b4e96bfb1c3..153086027482 100644 --- a/drivers/gpu/drm/drm_dp_helper.c +++ b/drivers/gpu/drm/drm_dp_helper.c @@ -949,6 +949,38 @@ bool drm_dp_downstream_444_to_420_conversion(const u8 dpcd[DP_RECEIVER_CAP_SIZE] } EXPORT_SYMBOL(drm_dp_downstream_444_to_420_conversion); +/** + * drm_dp_downstream_rgb_to_ycbcr_conversion() - determine downstream facing port + * RGB->YCbCr conversion capability + * @dpcd: DisplayPort configuration data + * @port_cap: downstream facing port capabilities + * @colorspc: Colorspace for which conversion cap is sought + * + * Returns: whether the downstream facing port can convert RGB->YCbCr for a given + * colorspace. + */ +bool drm_dp_downstream_rgb_to_ycbcr_conversion(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4], + u8 color_spc) +{ + if (!drm_dp_is_branch(dpcd)) + return false; + + if (dpcd[DP_DPCD_REV] < 0x13) + return false; + + switch (port_cap[0] & DP_DS_PORT_TYPE_MASK) { + case DP_DS_PORT_TYPE_HDMI: + if ((dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DETAILED_CAP_INFO_AVAILABLE) == 0) + return false; + + return port_cap[3] & color_spc; + default: + return false; + } +} +EXPORT_SYMBOL(drm_dp_downstream_rgb_to_ycbcr_conversion); + /** * drm_dp_downstream_mode() - return a mode for downstream facing port * @dev: DRM device @@ -3101,3 +3133,32 @@ int drm_dp_pcon_pps_override_param(struct drm_dp_aux *aux, u8 pps_param[6]) return 0; } EXPORT_SYMBOL(drm_dp_pcon_pps_override_param); + +/* + * drm_dp_pcon_convert_rgb_to_ycbcr() - Configure the PCon to convert RGB to Ycbcr + * @aux: displayPort AUX channel + * @color_spc: Color-space/s for which conversion is to be enabled, 0 for disable. + * + * Returns 0 on success, else returns negative error code. + */ +int drm_dp_pcon_convert_rgb_to_ycbcr(struct drm_dp_aux *aux, u8 color_spc) +{ + int ret; + u8 buf; + + ret = drm_dp_dpcd_readb(aux, DP_PROTOCOL_CONVERTER_CONTROL_2, &buf); + if (ret < 0) + return ret; + + if (color_spc & DP_CONVERSION_RGB_YCBCR_MASK) + buf |= (color_spc & DP_CONVERSION_RGB_YCBCR_MASK); + else + buf &= ~DP_CONVERSION_RGB_YCBCR_MASK; + + ret = drm_dp_dpcd_writeb(aux, DP_PROTOCOL_CONVERTER_CONTROL_2, buf); + if (ret < 0) + return ret; + + return 0; +} +EXPORT_SYMBOL(drm_dp_pcon_convert_rgb_to_ycbcr); diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h index e909c66b205a..6236f212da61 100644 --- a/include/drm/drm_dp_helper.h +++ b/include/drm/drm_dp_helper.h @@ -432,6 +432,17 @@ struct drm_device; # define DP_DS_HDMI_YCBCR444_TO_422_CONV (1 << 3) # define DP_DS_HDMI_YCBCR444_TO_420_CONV (1 << 4) +/* + * VESA DP-to-HDMI PCON Specification adds caps for colorspace + * conversion in DFP cap DPCD 83h. Sec6.1 Table-3. + * Based on the available support the source can enable + * color conversion by writing into PROTOCOL_COVERTER_CONTROL_2 + * DPCD 3052h. + */ +# define DP_DS_HDMI_BT601_RGB_YCBCR_CONV (1 << 5) +# define DP_DS_HDMI_BT709_RGB_YCBCR_CONV (1 << 6) +# define DP_DS_HDMI_BT2020_RGB_YCBCR_CONV (1 << 7) + #define DP_MAX_DOWNSTREAM_PORTS 0x10 /* DP Forward error Correction Registers */ @@ -1207,7 +1218,10 @@ struct drm_device; # define DP_PCON_ENC_PPS_OVERRIDE_DISABLED 0 # define DP_PCON_ENC_PPS_OVERRIDE_EN_PARAMS 1 # define DP_PCON_ENC_PPS_OVERRIDE_EN_BUFFER 2 - +# define DP_CONVERSION_RGB_YCBCR_MASK (7 << 4) +# define DP_CONVERSION_BT601_RGB_YCBCR_ENABLE (1 << 4) +# define DP_CONVERSION_BT709_RGB_YCBCR_ENABLE (1 << 5) +# define DP_CONVERSION_BT2020_RGB_YCBCR_ENABLE (1 << 6) /* PCON Downstream HDMI ERROR Status per Lane */ #define DP_PCON_HDMI_ERROR_STATUS_LN0 0x3037 @@ -2167,5 +2181,8 @@ int drm_dp_pcon_dsc_bpp_incr(const u8 pcon_dsc_dpcd[DP_PCON_DSC_ENCODER_CAP_SIZE int drm_dp_pcon_pps_default(struct drm_dp_aux *aux); int drm_dp_pcon_pps_override_buf(struct drm_dp_aux *aux, u8 pps_buf[128]); int drm_dp_pcon_pps_override_param(struct drm_dp_aux *aux, u8 pps_param[6]); +bool drm_dp_downstream_rgb_to_ycbcr_conversion(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4], u8 color_spc); +int drm_dp_pcon_convert_rgb_to_ycbcr(struct drm_dp_aux *aux, u8 color_spc); #endif /* _DRM_DP_HELPER_H_ */ -- cgit v1.2.3 From f7005142dacea1769fba0152c493aaa61b33205c Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Mon, 21 Dec 2020 17:29:34 +0200 Subject: spi: uapi: unify SPI modes into a single spi.h header This change moves all the SPI mode bits into a separate 'spi.h' header in uAPI. This is meant to re-use these definitions inside the kernel as well as export them to userspace (via uAPI). The SPI mode definitions have usually been duplicated between between 'include/linux/spi/spi.h' and 'include/uapi/linux/spi/spidev.h', so whenever adding a new entry, this would need to be put in both headers. They've been moved from 'include/linux/spi/spi.h', since that seems a bit more complete; the bits have descriptions and there is the SPI_MODE_X_MASK. This change also does a conversion of these bitfields to _BITUL() macro. Reviewed-by: Andy Shevchenko Signed-off-by: Alexandru Ardelean Link: https://lore.kernel.org/r/20201221152936.53873-1-alexandru.ardelean@analog.com Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 23 ++--------------------- include/uapi/linux/spi/spi.h | 31 +++++++++++++++++++++++++++++++ include/uapi/linux/spi/spidev.h | 30 +----------------------------- 3 files changed, 34 insertions(+), 50 deletions(-) create mode 100644 include/uapi/linux/spi/spi.h (limited to 'include') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index aa09fdc8042d..a08c3f37e202 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -15,6 +15,8 @@ #include #include +#include + struct dma_chan; struct property_entry; struct spi_controller; @@ -165,27 +167,6 @@ struct spi_device { u8 bits_per_word; bool rt; u32 mode; -#define SPI_CPHA 0x01 /* clock phase */ -#define SPI_CPOL 0x02 /* clock polarity */ -#define SPI_MODE_0 (0|0) /* (original MicroWire) */ -#define SPI_MODE_1 (0|SPI_CPHA) -#define SPI_MODE_2 (SPI_CPOL|0) -#define SPI_MODE_3 (SPI_CPOL|SPI_CPHA) -#define SPI_MODE_X_MASK (SPI_CPOL|SPI_CPHA) -#define SPI_CS_HIGH 0x04 /* chipselect active high? */ -#define SPI_LSB_FIRST 0x08 /* per-word bits-on-wire */ -#define SPI_3WIRE 0x10 /* SI/SO signals shared */ -#define SPI_LOOP 0x20 /* loopback mode */ -#define SPI_NO_CS 0x40 /* 1 dev/bus, no chipselect */ -#define SPI_READY 0x80 /* slave pulls low to pause */ -#define SPI_TX_DUAL 0x100 /* transmit with 2 wires */ -#define SPI_TX_QUAD 0x200 /* transmit with 4 wires */ -#define SPI_RX_DUAL 0x400 /* receive with 2 wires */ -#define SPI_RX_QUAD 0x800 /* receive with 4 wires */ -#define SPI_CS_WORD 0x1000 /* toggle cs after each word */ -#define SPI_TX_OCTAL 0x2000 /* transmit with 8 wires */ -#define SPI_RX_OCTAL 0x4000 /* receive with 8 wires */ -#define SPI_3WIRE_HIZ 0x8000 /* high impedance turnaround */ int irq; void *controller_state; void *controller_data; diff --git a/include/uapi/linux/spi/spi.h b/include/uapi/linux/spi/spi.h new file mode 100644 index 000000000000..703b586f35df --- /dev/null +++ b/include/uapi/linux/spi/spi.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +#ifndef _UAPI_SPI_H +#define _UAPI_SPI_H + +#include + +#define SPI_CPHA _BITUL(0) /* clock phase */ +#define SPI_CPOL _BITUL(1) /* clock polarity */ + +#define SPI_MODE_0 (0|0) /* (original MicroWire) */ +#define SPI_MODE_1 (0|SPI_CPHA) +#define SPI_MODE_2 (SPI_CPOL|0) +#define SPI_MODE_3 (SPI_CPOL|SPI_CPHA) +#define SPI_MODE_X_MASK (SPI_CPOL|SPI_CPHA) + +#define SPI_CS_HIGH _BITUL(2) /* chipselect active high? */ +#define SPI_LSB_FIRST _BITUL(3) /* per-word bits-on-wire */ +#define SPI_3WIRE _BITUL(4) /* SI/SO signals shared */ +#define SPI_LOOP _BITUL(5) /* loopback mode */ +#define SPI_NO_CS _BITUL(6) /* 1 dev/bus, no chipselect */ +#define SPI_READY _BITUL(7) /* slave pulls low to pause */ +#define SPI_TX_DUAL _BITUL(8) /* transmit with 2 wires */ +#define SPI_TX_QUAD _BITUL(9) /* transmit with 4 wires */ +#define SPI_RX_DUAL _BITUL(10) /* receive with 2 wires */ +#define SPI_RX_QUAD _BITUL(11) /* receive with 4 wires */ +#define SPI_CS_WORD _BITUL(12) /* toggle cs after each word */ +#define SPI_TX_OCTAL _BITUL(13) /* transmit with 8 wires */ +#define SPI_RX_OCTAL _BITUL(14) /* receive with 8 wires */ +#define SPI_3WIRE_HIZ _BITUL(15) /* high impedance turnaround */ + +#endif /* _UAPI_SPI_H */ diff --git a/include/uapi/linux/spi/spidev.h b/include/uapi/linux/spi/spidev.h index d56427c0b3e0..0c3da08f2aff 100644 --- a/include/uapi/linux/spi/spidev.h +++ b/include/uapi/linux/spi/spidev.h @@ -25,35 +25,7 @@ #include #include - -/* User space versions of kernel symbols for SPI clocking modes, - * matching - */ - -#define SPI_CPHA 0x01 -#define SPI_CPOL 0x02 - -#define SPI_MODE_0 (0|0) -#define SPI_MODE_1 (0|SPI_CPHA) -#define SPI_MODE_2 (SPI_CPOL|0) -#define SPI_MODE_3 (SPI_CPOL|SPI_CPHA) - -#define SPI_CS_HIGH 0x04 -#define SPI_LSB_FIRST 0x08 -#define SPI_3WIRE 0x10 -#define SPI_LOOP 0x20 -#define SPI_NO_CS 0x40 -#define SPI_READY 0x80 -#define SPI_TX_DUAL 0x100 -#define SPI_TX_QUAD 0x200 -#define SPI_RX_DUAL 0x400 -#define SPI_RX_QUAD 0x800 -#define SPI_CS_WORD 0x1000 -#define SPI_TX_OCTAL 0x2000 -#define SPI_RX_OCTAL 0x4000 -#define SPI_3WIRE_HIZ 0x8000 - -/*---------------------------------------------------------------------------*/ +#include /* IOCTL commands */ -- cgit v1.2.3 From d962608ce2188a1d46ec9d356d6fad5cd6fc0341 Mon Sep 17 00:00:00 2001 From: Dragos Bogdan Date: Mon, 21 Dec 2020 17:29:35 +0200 Subject: spi: Add SPI_NO_TX/RX support Transmit/receive only is a valid SPI mode. For example, the MOSI/TX line might be missing from an ADC while for a DAC the MISO/RX line may be optional. This patch adds these two new modes: SPI_NO_TX and SPI_NO_RX. This way, the drivers will be able to identify if any of these two lines is missing and to adjust the transfers accordingly. Signed-off-by: Dragos Bogdan Signed-off-by: Alexandru Ardelean Link: https://lore.kernel.org/r/20201221152936.53873-2-alexandru.ardelean@analog.com Signed-off-by: Mark Brown --- drivers/spi/spi.c | 25 ++++++++++++++++++++----- include/linux/spi/spi.h | 17 +++++++++++++++++ include/uapi/linux/spi/spi.h | 10 ++++++++++ 3 files changed, 47 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 51d7c004fbab..ca75f4036eda 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -1941,6 +1941,9 @@ static int of_spi_parse_dt(struct spi_controller *ctlr, struct spi_device *spi, /* Device DUAL/QUAD mode */ if (!of_property_read_u32(nc, "spi-tx-bus-width", &value)) { switch (value) { + case 0: + spi->mode |= SPI_NO_TX; + break; case 1: break; case 2: @@ -1962,6 +1965,9 @@ static int of_spi_parse_dt(struct spi_controller *ctlr, struct spi_device *spi, if (!of_property_read_u32(nc, "spi-rx-bus-width", &value)) { switch (value) { + case 0: + spi->mode |= SPI_NO_RX; + break; case 1: break; case 2: @@ -3329,12 +3335,16 @@ int spi_setup(struct spi_device *spi) unsigned bad_bits, ugly_bits; int status; - /* check mode to prevent that DUAL and QUAD set at the same time + /* + * check mode to prevent that any two of DUAL, QUAD and NO_MOSI/MISO + * are set at the same time */ - if (((spi->mode & SPI_TX_DUAL) && (spi->mode & SPI_TX_QUAD)) || - ((spi->mode & SPI_RX_DUAL) && (spi->mode & SPI_RX_QUAD))) { + if ((hweight_long(spi->mode & + (SPI_TX_DUAL | SPI_TX_QUAD | SPI_NO_TX)) > 1) || + (hweight_long(spi->mode & + (SPI_RX_DUAL | SPI_RX_QUAD | SPI_NO_RX)) > 1)) { dev_err(&spi->dev, - "setup: can not select dual and quad at the same time\n"); + "setup: can not select any two of dual, quad and no-rx/tx at the same time\n"); return -EINVAL; } /* if it is SPI_3WIRE mode, DUAL and QUAD should be forbidden @@ -3348,7 +3358,8 @@ int spi_setup(struct spi_device *spi) * SPI_CS_WORD has a fallback software implementation, * so it is ignored here. */ - bad_bits = spi->mode & ~(spi->controller->mode_bits | SPI_CS_WORD); + bad_bits = spi->mode & ~(spi->controller->mode_bits | SPI_CS_WORD | + SPI_NO_TX | SPI_NO_RX); /* nothing prevents from working with active-high CS in case if it * is driven by GPIO. */ @@ -3610,6 +3621,8 @@ static int __spi_validate(struct spi_device *spi, struct spi_message *message) * 2. check tx/rx_nbits match the mode in spi_device */ if (xfer->tx_buf) { + if (spi->mode & SPI_NO_TX) + return -EINVAL; if (xfer->tx_nbits != SPI_NBITS_SINGLE && xfer->tx_nbits != SPI_NBITS_DUAL && xfer->tx_nbits != SPI_NBITS_QUAD) @@ -3623,6 +3636,8 @@ static int __spi_validate(struct spi_device *spi, struct spi_message *message) } /* check transfer rx_nbits */ if (xfer->rx_buf) { + if (spi->mode & SPI_NO_RX) + return -EINVAL; if (xfer->rx_nbits != SPI_NBITS_SINGLE && xfer->rx_nbits != SPI_NBITS_DUAL && xfer->rx_nbits != SPI_NBITS_QUAD) diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index a08c3f37e202..9bfdfaf286eb 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -6,6 +6,7 @@ #ifndef __LINUX_SPI_H #define __LINUX_SPI_H +#include #include #include #include @@ -166,6 +167,18 @@ struct spi_device { u8 chip_select; u8 bits_per_word; bool rt; +#define SPI_NO_TX BIT(31) /* no transmit wire */ +#define SPI_NO_RX BIT(30) /* no receive wire */ + /* + * All bits defined above should be covered by SPI_MODE_KERNEL_MASK. + * The SPI_MODE_KERNEL_MASK has the SPI_MODE_USER_MASK counterpart, + * which is defined in 'include/uapi/linux/spi/spi.h'. + * The bits defined here are from bit 31 downwards, while in + * SPI_MODE_USER_MASK are from 0 upwards. + * These bits must not overlap. A static assert check should make sure of that. + * If adding extra bits, make sure to decrease the bit index below as well. + */ +#define SPI_MODE_KERNEL_MASK (~(BIT(30) - 1)) u32 mode; int irq; void *controller_state; @@ -189,6 +202,10 @@ struct spi_device { */ }; +/* Make sure that SPI_MODE_KERNEL_MASK & SPI_MODE_USER_MASK don't overlap */ +static_assert((SPI_MODE_KERNEL_MASK & SPI_MODE_USER_MASK) == 0, + "SPI_MODE_USER_MASK & SPI_MODE_KERNEL_MASK must not overlap"); + static inline struct spi_device *to_spi_device(struct device *dev) { return dev ? container_of(dev, struct spi_device, dev) : NULL; diff --git a/include/uapi/linux/spi/spi.h b/include/uapi/linux/spi/spi.h index 703b586f35df..236a85f08ded 100644 --- a/include/uapi/linux/spi/spi.h +++ b/include/uapi/linux/spi/spi.h @@ -28,4 +28,14 @@ #define SPI_RX_OCTAL _BITUL(14) /* receive with 8 wires */ #define SPI_3WIRE_HIZ _BITUL(15) /* high impedance turnaround */ +/* + * All the bits defined above should be covered by SPI_MODE_USER_MASK. + * The SPI_MODE_USER_MASK has the SPI_MODE_KERNEL_MASK counterpart in + * 'include/linux/spi/spi.h'. The bits defined here are from bit 0 upwards + * while in SPI_MODE_KERNEL_MASK they are from the other end downwards. + * These bits must not overlap. A static assert check should make sure of that. + * If adding extra bits, make sure to increase the bit index below as well. + */ +#define SPI_MODE_USER_MASK (_BITUL(16) - 1) + #endif /* _UAPI_SPI_H */ -- cgit v1.2.3 From 0eb76ba29d16df2951d37c54ca279c4e5630b071 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Fri, 11 Dec 2020 13:27:15 +0100 Subject: crypto: remove cipher routines from public crypto API The cipher routines in the crypto API are mostly intended for templates implementing skcipher modes generically in software, and shouldn't be used outside of the crypto subsystem. So move the prototypes and all related definitions to a new header file under include/crypto/internal. Also, let's use the new module namespace feature to move the symbol exports into a new namespace CRYPTO_INTERNAL. Signed-off-by: Ard Biesheuvel Acked-by: Eric Biggers Signed-off-by: Herbert Xu --- Documentation/crypto/api-skcipher.rst | 4 +- arch/arm/crypto/aes-neonbs-glue.c | 3 + arch/s390/crypto/aes_s390.c | 2 + crypto/adiantum.c | 2 + crypto/ansi_cprng.c | 2 + crypto/cbc.c | 1 + crypto/ccm.c | 2 + crypto/cfb.c | 2 + crypto/cipher.c | 7 +- crypto/cmac.c | 2 + crypto/ctr.c | 2 + crypto/drbg.c | 2 + crypto/ecb.c | 1 + crypto/essiv.c | 2 + crypto/keywrap.c | 2 + crypto/ofb.c | 2 + crypto/pcbc.c | 2 + crypto/skcipher.c | 2 + crypto/testmgr.c | 3 + crypto/vmac.c | 2 + crypto/xcbc.c | 2 + crypto/xts.c | 2 + drivers/crypto/geode-aes.c | 2 + drivers/crypto/inside-secure/safexcel.c | 1 + drivers/crypto/inside-secure/safexcel_hash.c | 1 + drivers/crypto/qat/qat_common/adf_ctl_drv.c | 1 + drivers/crypto/qat/qat_common/qat_algs.c | 1 + drivers/crypto/vmx/aes.c | 1 + drivers/crypto/vmx/vmx.c | 1 + include/crypto/algapi.h | 39 ----- include/crypto/internal/cipher.h | 218 +++++++++++++++++++++++++++ include/crypto/internal/skcipher.h | 1 + include/linux/crypto.h | 163 -------------------- 33 files changed, 273 insertions(+), 207 deletions(-) create mode 100644 include/crypto/internal/cipher.h (limited to 'include') diff --git a/Documentation/crypto/api-skcipher.rst b/Documentation/crypto/api-skcipher.rst index 1aaf8985894b..04d6cc5357c8 100644 --- a/Documentation/crypto/api-skcipher.rst +++ b/Documentation/crypto/api-skcipher.rst @@ -28,8 +28,8 @@ Symmetric Key Cipher Request Handle Single Block Cipher API ----------------------- -.. kernel-doc:: include/linux/crypto.h +.. kernel-doc:: include/crypto/internal/cipher.h :doc: Single Block Cipher API -.. kernel-doc:: include/linux/crypto.h +.. kernel-doc:: include/crypto/internal/cipher.h :functions: crypto_alloc_cipher crypto_free_cipher crypto_has_cipher crypto_cipher_blocksize crypto_cipher_setkey crypto_cipher_encrypt_one crypto_cipher_decrypt_one diff --git a/arch/arm/crypto/aes-neonbs-glue.c b/arch/arm/crypto/aes-neonbs-glue.c index f70af1d0514b..5c6cd3c63cbc 100644 --- a/arch/arm/crypto/aes-neonbs-glue.c +++ b/arch/arm/crypto/aes-neonbs-glue.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -23,6 +24,8 @@ MODULE_ALIAS_CRYPTO("cbc(aes)-all"); MODULE_ALIAS_CRYPTO("ctr(aes)"); MODULE_ALIAS_CRYPTO("xts(aes)"); +MODULE_IMPORT_NS(CRYPTO_INTERNAL); + asmlinkage void aesbs_convert_key(u8 out[], u32 const rk[], int rounds); asmlinkage void aesbs_ecb_encrypt(u8 out[], u8 const in[], u8 const rk[], diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c index 73044634d342..54c7536f2482 100644 --- a/arch/s390/crypto/aes_s390.c +++ b/arch/s390/crypto/aes_s390.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include #include @@ -1055,3 +1056,4 @@ MODULE_ALIAS_CRYPTO("aes-all"); MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm"); MODULE_LICENSE("GPL"); +MODULE_IMPORT_NS(CRYPTO_INTERNAL); diff --git a/crypto/adiantum.c b/crypto/adiantum.c index ce4d5725342c..84450130cb6b 100644 --- a/crypto/adiantum.c +++ b/crypto/adiantum.c @@ -32,6 +32,7 @@ #include #include +#include #include #include #include @@ -616,3 +617,4 @@ MODULE_DESCRIPTION("Adiantum length-preserving encryption mode"); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Eric Biggers "); MODULE_ALIAS_CRYPTO("adiantum"); +MODULE_IMPORT_NS(CRYPTO_INTERNAL); diff --git a/crypto/ansi_cprng.c b/crypto/ansi_cprng.c index c475c1129ff2..3f512efaba3a 100644 --- a/crypto/ansi_cprng.c +++ b/crypto/ansi_cprng.c @@ -7,6 +7,7 @@ * (C) Neil Horman */ +#include #include #include #include @@ -470,3 +471,4 @@ subsys_initcall(prng_mod_init); module_exit(prng_mod_fini); MODULE_ALIAS_CRYPTO("stdrng"); MODULE_ALIAS_CRYPTO("ansi_cprng"); +MODULE_IMPORT_NS(CRYPTO_INTERNAL); diff --git a/crypto/cbc.c b/crypto/cbc.c index 0d9509dff891..6c03e96b945f 100644 --- a/crypto/cbc.c +++ b/crypto/cbc.c @@ -6,6 +6,7 @@ */ #include +#include #include #include #include diff --git a/crypto/ccm.c b/crypto/ccm.c index 494d70901186..6b815ece51c6 100644 --- a/crypto/ccm.c +++ b/crypto/ccm.c @@ -6,6 +6,7 @@ */ #include +#include #include #include #include @@ -954,3 +955,4 @@ MODULE_ALIAS_CRYPTO("ccm_base"); MODULE_ALIAS_CRYPTO("rfc4309"); MODULE_ALIAS_CRYPTO("ccm"); MODULE_ALIAS_CRYPTO("cbcmac"); +MODULE_IMPORT_NS(CRYPTO_INTERNAL); diff --git a/crypto/cfb.c b/crypto/cfb.c index 4e5219bbcd19..0d664dfb47bc 100644 --- a/crypto/cfb.c +++ b/crypto/cfb.c @@ -20,6 +20,7 @@ */ #include +#include #include #include #include @@ -250,3 +251,4 @@ module_exit(crypto_cfb_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("CFB block cipher mode of operation"); MODULE_ALIAS_CRYPTO("cfb"); +MODULE_IMPORT_NS(CRYPTO_INTERNAL); diff --git a/crypto/cipher.c b/crypto/cipher.c index fd78150deb1c..b47141ed4a9f 100644 --- a/crypto/cipher.c +++ b/crypto/cipher.c @@ -9,6 +9,7 @@ */ #include +#include #include #include #include @@ -53,7 +54,7 @@ int crypto_cipher_setkey(struct crypto_cipher *tfm, return cia->cia_setkey(crypto_cipher_tfm(tfm), key, keylen); } -EXPORT_SYMBOL_GPL(crypto_cipher_setkey); +EXPORT_SYMBOL_NS_GPL(crypto_cipher_setkey, CRYPTO_INTERNAL); static inline void cipher_crypt_one(struct crypto_cipher *tfm, u8 *dst, const u8 *src, bool enc) @@ -81,11 +82,11 @@ void crypto_cipher_encrypt_one(struct crypto_cipher *tfm, { cipher_crypt_one(tfm, dst, src, true); } -EXPORT_SYMBOL_GPL(crypto_cipher_encrypt_one); +EXPORT_SYMBOL_NS_GPL(crypto_cipher_encrypt_one, CRYPTO_INTERNAL); void crypto_cipher_decrypt_one(struct crypto_cipher *tfm, u8 *dst, const u8 *src) { cipher_crypt_one(tfm, dst, src, false); } -EXPORT_SYMBOL_GPL(crypto_cipher_decrypt_one); +EXPORT_SYMBOL_NS_GPL(crypto_cipher_decrypt_one, CRYPTO_INTERNAL); diff --git a/crypto/cmac.c b/crypto/cmac.c index df36be1efb81..f4a5d3bfb376 100644 --- a/crypto/cmac.c +++ b/crypto/cmac.c @@ -11,6 +11,7 @@ * Author: Kazunori Miyazawa */ +#include #include #include #include @@ -313,3 +314,4 @@ module_exit(crypto_cmac_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("CMAC keyed hash algorithm"); MODULE_ALIAS_CRYPTO("cmac"); +MODULE_IMPORT_NS(CRYPTO_INTERNAL); diff --git a/crypto/ctr.c b/crypto/ctr.c index c39fcffba27f..23c698b22013 100644 --- a/crypto/ctr.c +++ b/crypto/ctr.c @@ -7,6 +7,7 @@ #include #include +#include #include #include #include @@ -358,3 +359,4 @@ MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("CTR block cipher mode of operation"); MODULE_ALIAS_CRYPTO("rfc3686"); MODULE_ALIAS_CRYPTO("ctr"); +MODULE_IMPORT_NS(CRYPTO_INTERNAL); diff --git a/crypto/drbg.c b/crypto/drbg.c index 3132967a1749..1b4587e0ddad 100644 --- a/crypto/drbg.c +++ b/crypto/drbg.c @@ -98,6 +98,7 @@ */ #include +#include #include /*************************************************************** @@ -2161,3 +2162,4 @@ MODULE_DESCRIPTION("NIST SP800-90A Deterministic Random Bit Generator (DRBG) " CRYPTO_DRBG_HMAC_STRING CRYPTO_DRBG_CTR_STRING); MODULE_ALIAS_CRYPTO("stdrng"); +MODULE_IMPORT_NS(CRYPTO_INTERNAL); diff --git a/crypto/ecb.c b/crypto/ecb.c index 69a687cbdf21..71fbb0543d64 100644 --- a/crypto/ecb.c +++ b/crypto/ecb.c @@ -6,6 +6,7 @@ */ #include +#include #include #include #include diff --git a/crypto/essiv.c b/crypto/essiv.c index d012be23d496..8bcc5bdcb2a9 100644 --- a/crypto/essiv.c +++ b/crypto/essiv.c @@ -30,6 +30,7 @@ #include #include +#include #include #include #include @@ -643,3 +644,4 @@ module_exit(essiv_module_exit); MODULE_DESCRIPTION("ESSIV skcipher/aead wrapper for block encryption"); MODULE_LICENSE("GPL v2"); MODULE_ALIAS_CRYPTO("essiv"); +MODULE_IMPORT_NS(CRYPTO_INTERNAL); diff --git a/crypto/keywrap.c b/crypto/keywrap.c index 0355cce21b1e..3517773bc7f7 100644 --- a/crypto/keywrap.c +++ b/crypto/keywrap.c @@ -85,6 +85,7 @@ #include #include #include +#include #include struct crypto_kw_block { @@ -316,3 +317,4 @@ MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Stephan Mueller "); MODULE_DESCRIPTION("Key Wrapping (RFC3394 / NIST SP800-38F)"); MODULE_ALIAS_CRYPTO("kw"); +MODULE_IMPORT_NS(CRYPTO_INTERNAL); diff --git a/crypto/ofb.c b/crypto/ofb.c index 2ec68e3f2c55..b630fdecceee 100644 --- a/crypto/ofb.c +++ b/crypto/ofb.c @@ -8,6 +8,7 @@ */ #include +#include #include #include #include @@ -102,3 +103,4 @@ module_exit(crypto_ofb_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("OFB block cipher mode of operation"); MODULE_ALIAS_CRYPTO("ofb"); +MODULE_IMPORT_NS(CRYPTO_INTERNAL); diff --git a/crypto/pcbc.c b/crypto/pcbc.c index ae921fb74dc9..7030f59e46b6 100644 --- a/crypto/pcbc.c +++ b/crypto/pcbc.c @@ -10,6 +10,7 @@ */ #include +#include #include #include #include @@ -191,3 +192,4 @@ module_exit(crypto_pcbc_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("PCBC block cipher mode of operation"); MODULE_ALIAS_CRYPTO("pcbc"); +MODULE_IMPORT_NS(CRYPTO_INTERNAL); diff --git a/crypto/skcipher.c b/crypto/skcipher.c index b4dae640de9f..ff16d05644c7 100644 --- a/crypto/skcipher.c +++ b/crypto/skcipher.c @@ -10,6 +10,7 @@ */ #include +#include #include #include #include @@ -986,3 +987,4 @@ EXPORT_SYMBOL_GPL(skcipher_alloc_instance_simple); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Symmetric key cipher type"); +MODULE_IMPORT_NS(CRYPTO_INTERNAL); diff --git a/crypto/testmgr.c b/crypto/testmgr.c index 321e38eef51b..a896d77e9611 100644 --- a/crypto/testmgr.c +++ b/crypto/testmgr.c @@ -33,10 +33,13 @@ #include #include #include +#include #include #include "internal.h" +MODULE_IMPORT_NS(CRYPTO_INTERNAL); + static bool notests; module_param(notests, bool, 0644); MODULE_PARM_DESC(notests, "disable crypto self-tests"); diff --git a/crypto/vmac.c b/crypto/vmac.c index 9b565d1040d6..4633b2dda1e0 100644 --- a/crypto/vmac.c +++ b/crypto/vmac.c @@ -36,6 +36,7 @@ #include #include #include +#include #include /* @@ -693,3 +694,4 @@ module_exit(vmac_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("VMAC hash algorithm"); MODULE_ALIAS_CRYPTO("vmac64"); +MODULE_IMPORT_NS(CRYPTO_INTERNAL); diff --git a/crypto/xcbc.c b/crypto/xcbc.c index af3b7eb5d7c7..6074c5c1da49 100644 --- a/crypto/xcbc.c +++ b/crypto/xcbc.c @@ -6,6 +6,7 @@ * Kazunori Miyazawa */ +#include #include #include #include @@ -272,3 +273,4 @@ module_exit(crypto_xcbc_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("XCBC keyed hash algorithm"); MODULE_ALIAS_CRYPTO("xcbc"); +MODULE_IMPORT_NS(CRYPTO_INTERNAL); diff --git a/crypto/xts.c b/crypto/xts.c index ad45b009774b..6c12f30dbdd6 100644 --- a/crypto/xts.c +++ b/crypto/xts.c @@ -7,6 +7,7 @@ * Based on ecb.c * Copyright (c) 2006 Herbert Xu */ +#include #include #include #include @@ -464,3 +465,4 @@ module_exit(xts_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("XTS block cipher mode"); MODULE_ALIAS_CRYPTO("xts"); +MODULE_IMPORT_NS(CRYPTO_INTERNAL); diff --git a/drivers/crypto/geode-aes.c b/drivers/crypto/geode-aes.c index f4f18bfc2247..4ee010f39912 100644 --- a/drivers/crypto/geode-aes.c +++ b/drivers/crypto/geode-aes.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include @@ -434,3 +435,4 @@ module_pci_driver(geode_aes_driver); MODULE_AUTHOR("Advanced Micro Devices, Inc."); MODULE_DESCRIPTION("Geode LX Hardware AES driver"); MODULE_LICENSE("GPL"); +MODULE_IMPORT_NS(CRYPTO_INTERNAL); diff --git a/drivers/crypto/inside-secure/safexcel.c b/drivers/crypto/inside-secure/safexcel.c index 2e1562108a85..30aedfcfee7c 100644 --- a/drivers/crypto/inside-secure/safexcel.c +++ b/drivers/crypto/inside-secure/safexcel.c @@ -1999,3 +1999,4 @@ MODULE_AUTHOR("Ofer Heifetz "); MODULE_AUTHOR("Igal Liberman "); MODULE_DESCRIPTION("Support for SafeXcel cryptographic engines: EIP97 & EIP197"); MODULE_LICENSE("GPL v2"); +MODULE_IMPORT_NS(CRYPTO_INTERNAL); diff --git a/drivers/crypto/inside-secure/safexcel_hash.c b/drivers/crypto/inside-secure/safexcel_hash.c index 50fb6d90a2e0..bc60b5802256 100644 --- a/drivers/crypto/inside-secure/safexcel_hash.c +++ b/drivers/crypto/inside-secure/safexcel_hash.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/crypto/qat/qat_common/adf_ctl_drv.c b/drivers/crypto/qat/qat_common/adf_ctl_drv.c index eb9b3be9d8eb..96b437bfe3de 100644 --- a/drivers/crypto/qat/qat_common/adf_ctl_drv.c +++ b/drivers/crypto/qat/qat_common/adf_ctl_drv.c @@ -464,3 +464,4 @@ MODULE_AUTHOR("Intel"); MODULE_DESCRIPTION("Intel(R) QuickAssist Technology"); MODULE_ALIAS_CRYPTO("intel_qat"); MODULE_VERSION(ADF_DRV_VERSION); +MODULE_IMPORT_NS(CRYPTO_INTERNAL); diff --git a/drivers/crypto/qat/qat_common/qat_algs.c b/drivers/crypto/qat/qat_common/qat_algs.c index 31c7a206a629..ff78c73c47e3 100644 --- a/drivers/crypto/qat/qat_common/qat_algs.c +++ b/drivers/crypto/qat/qat_common/qat_algs.c @@ -4,6 +4,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/crypto/vmx/aes.c b/drivers/crypto/vmx/aes.c index 2bc5d4e1adf4..d05c02baebcf 100644 --- a/drivers/crypto/vmx/aes.c +++ b/drivers/crypto/vmx/aes.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include "aesp8-ppc.h" diff --git a/drivers/crypto/vmx/vmx.c b/drivers/crypto/vmx/vmx.c index 3e0335fb406c..87a194455d6a 100644 --- a/drivers/crypto/vmx/vmx.c +++ b/drivers/crypto/vmx/vmx.c @@ -78,3 +78,4 @@ MODULE_DESCRIPTION("IBM VMX cryptographic acceleration instructions " "support on Power 8"); MODULE_LICENSE("GPL"); MODULE_VERSION("1.0.0"); +MODULE_IMPORT_NS(CRYPTO_INTERNAL); diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h index 18dd7a4aaf7d..86f0748009af 100644 --- a/include/crypto/algapi.h +++ b/include/crypto/algapi.h @@ -189,45 +189,6 @@ static inline void *crypto_instance_ctx(struct crypto_instance *inst) return inst->__ctx; } -struct crypto_cipher_spawn { - struct crypto_spawn base; -}; - -static inline int crypto_grab_cipher(struct crypto_cipher_spawn *spawn, - struct crypto_instance *inst, - const char *name, u32 type, u32 mask) -{ - type &= ~CRYPTO_ALG_TYPE_MASK; - type |= CRYPTO_ALG_TYPE_CIPHER; - mask |= CRYPTO_ALG_TYPE_MASK; - return crypto_grab_spawn(&spawn->base, inst, name, type, mask); -} - -static inline void crypto_drop_cipher(struct crypto_cipher_spawn *spawn) -{ - crypto_drop_spawn(&spawn->base); -} - -static inline struct crypto_alg *crypto_spawn_cipher_alg( - struct crypto_cipher_spawn *spawn) -{ - return spawn->base.alg; -} - -static inline struct crypto_cipher *crypto_spawn_cipher( - struct crypto_cipher_spawn *spawn) -{ - u32 type = CRYPTO_ALG_TYPE_CIPHER; - u32 mask = CRYPTO_ALG_TYPE_MASK; - - return __crypto_cipher_cast(crypto_spawn_tfm(&spawn->base, type, mask)); -} - -static inline struct cipher_alg *crypto_cipher_alg(struct crypto_cipher *tfm) -{ - return &crypto_cipher_tfm(tfm)->__crt_alg->cra_cipher; -} - static inline struct crypto_async_request *crypto_get_backlog( struct crypto_queue *queue) { diff --git a/include/crypto/internal/cipher.h b/include/crypto/internal/cipher.h new file mode 100644 index 000000000000..a9174ba90250 --- /dev/null +++ b/include/crypto/internal/cipher.h @@ -0,0 +1,218 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (c) 2002 James Morris + * Copyright (c) 2002 David S. Miller (davem@redhat.com) + * Copyright (c) 2005 Herbert Xu + * + * Portions derived from Cryptoapi, by Alexander Kjeldaas + * and Nettle, by Niels Möller. + */ + +#ifndef _CRYPTO_INTERNAL_CIPHER_H +#define _CRYPTO_INTERNAL_CIPHER_H + +#include + +struct crypto_cipher { + struct crypto_tfm base; +}; + +/** + * DOC: Single Block Cipher API + * + * The single block cipher API is used with the ciphers of type + * CRYPTO_ALG_TYPE_CIPHER (listed as type "cipher" in /proc/crypto). + * + * Using the single block cipher API calls, operations with the basic cipher + * primitive can be implemented. These cipher primitives exclude any block + * chaining operations including IV handling. + * + * The purpose of this single block cipher API is to support the implementation + * of templates or other concepts that only need to perform the cipher operation + * on one block at a time. Templates invoke the underlying cipher primitive + * block-wise and process either the input or the output data of these cipher + * operations. + */ + +static inline struct crypto_cipher *__crypto_cipher_cast(struct crypto_tfm *tfm) +{ + return (struct crypto_cipher *)tfm; +} + +/** + * crypto_alloc_cipher() - allocate single block cipher handle + * @alg_name: is the cra_name / name or cra_driver_name / driver name of the + * single block cipher + * @type: specifies the type of the cipher + * @mask: specifies the mask for the cipher + * + * Allocate a cipher handle for a single block cipher. The returned struct + * crypto_cipher is the cipher handle that is required for any subsequent API + * invocation for that single block cipher. + * + * Return: allocated cipher handle in case of success; IS_ERR() is true in case + * of an error, PTR_ERR() returns the error code. + */ +static inline struct crypto_cipher *crypto_alloc_cipher(const char *alg_name, + u32 type, u32 mask) +{ + type &= ~CRYPTO_ALG_TYPE_MASK; + type |= CRYPTO_ALG_TYPE_CIPHER; + mask |= CRYPTO_ALG_TYPE_MASK; + + return __crypto_cipher_cast(crypto_alloc_base(alg_name, type, mask)); +} + +static inline struct crypto_tfm *crypto_cipher_tfm(struct crypto_cipher *tfm) +{ + return &tfm->base; +} + +/** + * crypto_free_cipher() - zeroize and free the single block cipher handle + * @tfm: cipher handle to be freed + */ +static inline void crypto_free_cipher(struct crypto_cipher *tfm) +{ + crypto_free_tfm(crypto_cipher_tfm(tfm)); +} + +/** + * crypto_has_cipher() - Search for the availability of a single block cipher + * @alg_name: is the cra_name / name or cra_driver_name / driver name of the + * single block cipher + * @type: specifies the type of the cipher + * @mask: specifies the mask for the cipher + * + * Return: true when the single block cipher is known to the kernel crypto API; + * false otherwise + */ +static inline int crypto_has_cipher(const char *alg_name, u32 type, u32 mask) +{ + type &= ~CRYPTO_ALG_TYPE_MASK; + type |= CRYPTO_ALG_TYPE_CIPHER; + mask |= CRYPTO_ALG_TYPE_MASK; + + return crypto_has_alg(alg_name, type, mask); +} + +/** + * crypto_cipher_blocksize() - obtain block size for cipher + * @tfm: cipher handle + * + * The block size for the single block cipher referenced with the cipher handle + * tfm is returned. The caller may use that information to allocate appropriate + * memory for the data returned by the encryption or decryption operation + * + * Return: block size of cipher + */ +static inline unsigned int crypto_cipher_blocksize(struct crypto_cipher *tfm) +{ + return crypto_tfm_alg_blocksize(crypto_cipher_tfm(tfm)); +} + +static inline unsigned int crypto_cipher_alignmask(struct crypto_cipher *tfm) +{ + return crypto_tfm_alg_alignmask(crypto_cipher_tfm(tfm)); +} + +static inline u32 crypto_cipher_get_flags(struct crypto_cipher *tfm) +{ + return crypto_tfm_get_flags(crypto_cipher_tfm(tfm)); +} + +static inline void crypto_cipher_set_flags(struct crypto_cipher *tfm, + u32 flags) +{ + crypto_tfm_set_flags(crypto_cipher_tfm(tfm), flags); +} + +static inline void crypto_cipher_clear_flags(struct crypto_cipher *tfm, + u32 flags) +{ + crypto_tfm_clear_flags(crypto_cipher_tfm(tfm), flags); +} + +/** + * crypto_cipher_setkey() - set key for cipher + * @tfm: cipher handle + * @key: buffer holding the key + * @keylen: length of the key in bytes + * + * The caller provided key is set for the single block cipher referenced by the + * cipher handle. + * + * Note, the key length determines the cipher type. Many block ciphers implement + * different cipher modes depending on the key size, such as AES-128 vs AES-192 + * vs. AES-256. When providing a 16 byte key for an AES cipher handle, AES-128 + * is performed. + * + * Return: 0 if the setting of the key was successful; < 0 if an error occurred + */ +int crypto_cipher_setkey(struct crypto_cipher *tfm, + const u8 *key, unsigned int keylen); + +/** + * crypto_cipher_encrypt_one() - encrypt one block of plaintext + * @tfm: cipher handle + * @dst: points to the buffer that will be filled with the ciphertext + * @src: buffer holding the plaintext to be encrypted + * + * Invoke the encryption operation of one block. The caller must ensure that + * the plaintext and ciphertext buffers are at least one block in size. + */ +void crypto_cipher_encrypt_one(struct crypto_cipher *tfm, + u8 *dst, const u8 *src); + +/** + * crypto_cipher_decrypt_one() - decrypt one block of ciphertext + * @tfm: cipher handle + * @dst: points to the buffer that will be filled with the plaintext + * @src: buffer holding the ciphertext to be decrypted + * + * Invoke the decryption operation of one block. The caller must ensure that + * the plaintext and ciphertext buffers are at least one block in size. + */ +void crypto_cipher_decrypt_one(struct crypto_cipher *tfm, + u8 *dst, const u8 *src); + +struct crypto_cipher_spawn { + struct crypto_spawn base; +}; + +static inline int crypto_grab_cipher(struct crypto_cipher_spawn *spawn, + struct crypto_instance *inst, + const char *name, u32 type, u32 mask) +{ + type &= ~CRYPTO_ALG_TYPE_MASK; + type |= CRYPTO_ALG_TYPE_CIPHER; + mask |= CRYPTO_ALG_TYPE_MASK; + return crypto_grab_spawn(&spawn->base, inst, name, type, mask); +} + +static inline void crypto_drop_cipher(struct crypto_cipher_spawn *spawn) +{ + crypto_drop_spawn(&spawn->base); +} + +static inline struct crypto_alg *crypto_spawn_cipher_alg( + struct crypto_cipher_spawn *spawn) +{ + return spawn->base.alg; +} + +static inline struct crypto_cipher *crypto_spawn_cipher( + struct crypto_cipher_spawn *spawn) +{ + u32 type = CRYPTO_ALG_TYPE_CIPHER; + u32 mask = CRYPTO_ALG_TYPE_MASK; + + return __crypto_cipher_cast(crypto_spawn_tfm(&spawn->base, type, mask)); +} + +static inline struct cipher_alg *crypto_cipher_alg(struct crypto_cipher *tfm) +{ + return &crypto_cipher_tfm(tfm)->__crt_alg->cra_cipher; +} + +#endif diff --git a/include/crypto/internal/skcipher.h b/include/crypto/internal/skcipher.h index 10226c12c5df..9dd6c0c17eb8 100644 --- a/include/crypto/internal/skcipher.h +++ b/include/crypto/internal/skcipher.h @@ -9,6 +9,7 @@ #define _CRYPTO_INTERNAL_SKCIPHER_H #include +#include #include #include #include diff --git a/include/linux/crypto.h b/include/linux/crypto.h index ef90e07c9635..9b55cd6b1f1b 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -636,10 +636,6 @@ struct crypto_tfm { void *__crt_ctx[] CRYPTO_MINALIGN_ATTR; }; -struct crypto_cipher { - struct crypto_tfm base; -}; - struct crypto_comp { struct crypto_tfm base; }; @@ -743,165 +739,6 @@ static inline unsigned int crypto_tfm_ctx_alignment(void) return __alignof__(tfm->__crt_ctx); } -/** - * DOC: Single Block Cipher API - * - * The single block cipher API is used with the ciphers of type - * CRYPTO_ALG_TYPE_CIPHER (listed as type "cipher" in /proc/crypto). - * - * Using the single block cipher API calls, operations with the basic cipher - * primitive can be implemented. These cipher primitives exclude any block - * chaining operations including IV handling. - * - * The purpose of this single block cipher API is to support the implementation - * of templates or other concepts that only need to perform the cipher operation - * on one block at a time. Templates invoke the underlying cipher primitive - * block-wise and process either the input or the output data of these cipher - * operations. - */ - -static inline struct crypto_cipher *__crypto_cipher_cast(struct crypto_tfm *tfm) -{ - return (struct crypto_cipher *)tfm; -} - -/** - * crypto_alloc_cipher() - allocate single block cipher handle - * @alg_name: is the cra_name / name or cra_driver_name / driver name of the - * single block cipher - * @type: specifies the type of the cipher - * @mask: specifies the mask for the cipher - * - * Allocate a cipher handle for a single block cipher. The returned struct - * crypto_cipher is the cipher handle that is required for any subsequent API - * invocation for that single block cipher. - * - * Return: allocated cipher handle in case of success; IS_ERR() is true in case - * of an error, PTR_ERR() returns the error code. - */ -static inline struct crypto_cipher *crypto_alloc_cipher(const char *alg_name, - u32 type, u32 mask) -{ - type &= ~CRYPTO_ALG_TYPE_MASK; - type |= CRYPTO_ALG_TYPE_CIPHER; - mask |= CRYPTO_ALG_TYPE_MASK; - - return __crypto_cipher_cast(crypto_alloc_base(alg_name, type, mask)); -} - -static inline struct crypto_tfm *crypto_cipher_tfm(struct crypto_cipher *tfm) -{ - return &tfm->base; -} - -/** - * crypto_free_cipher() - zeroize and free the single block cipher handle - * @tfm: cipher handle to be freed - */ -static inline void crypto_free_cipher(struct crypto_cipher *tfm) -{ - crypto_free_tfm(crypto_cipher_tfm(tfm)); -} - -/** - * crypto_has_cipher() - Search for the availability of a single block cipher - * @alg_name: is the cra_name / name or cra_driver_name / driver name of the - * single block cipher - * @type: specifies the type of the cipher - * @mask: specifies the mask for the cipher - * - * Return: true when the single block cipher is known to the kernel crypto API; - * false otherwise - */ -static inline int crypto_has_cipher(const char *alg_name, u32 type, u32 mask) -{ - type &= ~CRYPTO_ALG_TYPE_MASK; - type |= CRYPTO_ALG_TYPE_CIPHER; - mask |= CRYPTO_ALG_TYPE_MASK; - - return crypto_has_alg(alg_name, type, mask); -} - -/** - * crypto_cipher_blocksize() - obtain block size for cipher - * @tfm: cipher handle - * - * The block size for the single block cipher referenced with the cipher handle - * tfm is returned. The caller may use that information to allocate appropriate - * memory for the data returned by the encryption or decryption operation - * - * Return: block size of cipher - */ -static inline unsigned int crypto_cipher_blocksize(struct crypto_cipher *tfm) -{ - return crypto_tfm_alg_blocksize(crypto_cipher_tfm(tfm)); -} - -static inline unsigned int crypto_cipher_alignmask(struct crypto_cipher *tfm) -{ - return crypto_tfm_alg_alignmask(crypto_cipher_tfm(tfm)); -} - -static inline u32 crypto_cipher_get_flags(struct crypto_cipher *tfm) -{ - return crypto_tfm_get_flags(crypto_cipher_tfm(tfm)); -} - -static inline void crypto_cipher_set_flags(struct crypto_cipher *tfm, - u32 flags) -{ - crypto_tfm_set_flags(crypto_cipher_tfm(tfm), flags); -} - -static inline void crypto_cipher_clear_flags(struct crypto_cipher *tfm, - u32 flags) -{ - crypto_tfm_clear_flags(crypto_cipher_tfm(tfm), flags); -} - -/** - * crypto_cipher_setkey() - set key for cipher - * @tfm: cipher handle - * @key: buffer holding the key - * @keylen: length of the key in bytes - * - * The caller provided key is set for the single block cipher referenced by the - * cipher handle. - * - * Note, the key length determines the cipher type. Many block ciphers implement - * different cipher modes depending on the key size, such as AES-128 vs AES-192 - * vs. AES-256. When providing a 16 byte key for an AES cipher handle, AES-128 - * is performed. - * - * Return: 0 if the setting of the key was successful; < 0 if an error occurred - */ -int crypto_cipher_setkey(struct crypto_cipher *tfm, - const u8 *key, unsigned int keylen); - -/** - * crypto_cipher_encrypt_one() - encrypt one block of plaintext - * @tfm: cipher handle - * @dst: points to the buffer that will be filled with the ciphertext - * @src: buffer holding the plaintext to be encrypted - * - * Invoke the encryption operation of one block. The caller must ensure that - * the plaintext and ciphertext buffers are at least one block in size. - */ -void crypto_cipher_encrypt_one(struct crypto_cipher *tfm, - u8 *dst, const u8 *src); - -/** - * crypto_cipher_decrypt_one() - decrypt one block of ciphertext - * @tfm: cipher handle - * @dst: points to the buffer that will be filled with the plaintext - * @src: buffer holding the ciphertext to be decrypted - * - * Invoke the decryption operation of one block. The caller must ensure that - * the plaintext and ciphertext buffers are at least one block in size. - */ -void crypto_cipher_decrypt_one(struct crypto_cipher *tfm, - u8 *dst, const u8 *src); - static inline struct crypto_comp *__crypto_comp_cast(struct crypto_tfm *tfm) { return (struct crypto_comp *)tfm; -- cgit v1.2.3 From 057edc9c8bb2d5ff5b058b521792c392428a0714 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 23 Dec 2020 00:09:53 -0800 Subject: crypto: blake2s - move update and final logic to internal/blake2s.h Move most of blake2s_update() and blake2s_final() into new inline functions __blake2s_update() and __blake2s_final() in include/crypto/internal/blake2s.h so that this logic can be shared by the shash helper functions. This will avoid duplicating this logic between the library and shash implementations. Signed-off-by: Eric Biggers Acked-by: Ard Biesheuvel Signed-off-by: Herbert Xu --- include/crypto/internal/blake2s.h | 41 +++++++++++++++++++++++++++++++++ lib/crypto/blake2s.c | 48 +++++++-------------------------------- 2 files changed, 49 insertions(+), 40 deletions(-) (limited to 'include') diff --git a/include/crypto/internal/blake2s.h b/include/crypto/internal/blake2s.h index 6e376ae6b6b5..42deba4b8cee 100644 --- a/include/crypto/internal/blake2s.h +++ b/include/crypto/internal/blake2s.h @@ -4,6 +4,7 @@ #define BLAKE2S_INTERNAL_H #include +#include struct blake2s_tfm_ctx { u8 key[BLAKE2S_KEY_SIZE]; @@ -23,4 +24,44 @@ static inline void blake2s_set_lastblock(struct blake2s_state *state) state->f[0] = -1; } +typedef void (*blake2s_compress_t)(struct blake2s_state *state, + const u8 *block, size_t nblocks, u32 inc); + +static inline void __blake2s_update(struct blake2s_state *state, + const u8 *in, size_t inlen, + blake2s_compress_t compress) +{ + const size_t fill = BLAKE2S_BLOCK_SIZE - state->buflen; + + if (unlikely(!inlen)) + return; + if (inlen > fill) { + memcpy(state->buf + state->buflen, in, fill); + (*compress)(state, state->buf, 1, BLAKE2S_BLOCK_SIZE); + state->buflen = 0; + in += fill; + inlen -= fill; + } + if (inlen > BLAKE2S_BLOCK_SIZE) { + const size_t nblocks = DIV_ROUND_UP(inlen, BLAKE2S_BLOCK_SIZE); + /* Hash one less (full) block than strictly possible */ + (*compress)(state, in, nblocks - 1, BLAKE2S_BLOCK_SIZE); + in += BLAKE2S_BLOCK_SIZE * (nblocks - 1); + inlen -= BLAKE2S_BLOCK_SIZE * (nblocks - 1); + } + memcpy(state->buf + state->buflen, in, inlen); + state->buflen += inlen; +} + +static inline void __blake2s_final(struct blake2s_state *state, u8 *out, + blake2s_compress_t compress) +{ + blake2s_set_lastblock(state); + memset(state->buf + state->buflen, 0, + BLAKE2S_BLOCK_SIZE - state->buflen); /* Padding */ + (*compress)(state, state->buf, 1, state->buflen); + cpu_to_le32_array(state->h, ARRAY_SIZE(state->h)); + memcpy(out, state->h, state->outlen); +} + #endif /* BLAKE2S_INTERNAL_H */ diff --git a/lib/crypto/blake2s.c b/lib/crypto/blake2s.c index 6a4b6b78d630..c64ac8bfb6a9 100644 --- a/lib/crypto/blake2s.c +++ b/lib/crypto/blake2s.c @@ -15,55 +15,23 @@ #include #include #include -#include + +#if IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_BLAKE2S) +# define blake2s_compress blake2s_compress_arch +#else +# define blake2s_compress blake2s_compress_generic +#endif void blake2s_update(struct blake2s_state *state, const u8 *in, size_t inlen) { - const size_t fill = BLAKE2S_BLOCK_SIZE - state->buflen; - - if (unlikely(!inlen)) - return; - if (inlen > fill) { - memcpy(state->buf + state->buflen, in, fill); - if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_BLAKE2S)) - blake2s_compress_arch(state, state->buf, 1, - BLAKE2S_BLOCK_SIZE); - else - blake2s_compress_generic(state, state->buf, 1, - BLAKE2S_BLOCK_SIZE); - state->buflen = 0; - in += fill; - inlen -= fill; - } - if (inlen > BLAKE2S_BLOCK_SIZE) { - const size_t nblocks = DIV_ROUND_UP(inlen, BLAKE2S_BLOCK_SIZE); - /* Hash one less (full) block than strictly possible */ - if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_BLAKE2S)) - blake2s_compress_arch(state, in, nblocks - 1, - BLAKE2S_BLOCK_SIZE); - else - blake2s_compress_generic(state, in, nblocks - 1, - BLAKE2S_BLOCK_SIZE); - in += BLAKE2S_BLOCK_SIZE * (nblocks - 1); - inlen -= BLAKE2S_BLOCK_SIZE * (nblocks - 1); - } - memcpy(state->buf + state->buflen, in, inlen); - state->buflen += inlen; + __blake2s_update(state, in, inlen, blake2s_compress); } EXPORT_SYMBOL(blake2s_update); void blake2s_final(struct blake2s_state *state, u8 *out) { WARN_ON(IS_ENABLED(DEBUG) && !out); - blake2s_set_lastblock(state); - memset(state->buf + state->buflen, 0, - BLAKE2S_BLOCK_SIZE - state->buflen); /* Padding */ - if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_BLAKE2S)) - blake2s_compress_arch(state, state->buf, 1, state->buflen); - else - blake2s_compress_generic(state, state->buf, 1, state->buflen); - cpu_to_le32_array(state->h, ARRAY_SIZE(state->h)); - memcpy(out, state->h, state->outlen); + __blake2s_final(state, out, blake2s_compress); memzero_explicit(state, sizeof(*state)); } EXPORT_SYMBOL(blake2s_final); -- cgit v1.2.3 From 8c4a93a1270ddffc7660ae43fa8030ecfe9c06d9 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 23 Dec 2020 00:09:54 -0800 Subject: crypto: blake2s - share the "shash" API boilerplate code Add helper functions for shash implementations of BLAKE2s to include/crypto/internal/blake2s.h, taking advantage of __blake2s_update() and __blake2s_final() that were added by the previous patch to share more code between the library and shash implementations. crypto_blake2s_setkey() and crypto_blake2s_init() are usable as shash_alg::setkey and shash_alg::init directly, while crypto_blake2s_update() and crypto_blake2s_final() take an extra 'blake2s_compress_t' function pointer parameter. This allows the implementation of the compression function to be overridden, which is the only part that optimized implementations really care about. The new functions are inline functions (similar to those in sha1_base.h, sha256_base.h, and sm3_base.h) because this avoids needing to add a new module blake2s_helpers.ko, they aren't *too* long, and this avoids indirect calls which are expensive these days. Note that they can't go in blake2s_generic.ko, as that would require selecting CRYPTO_BLAKE2S from CRYPTO_BLAKE2S_X86, which would cause a recursive dependency. Finally, use these new helper functions in the x86 implementation of BLAKE2s. (This part should be a separate patch, but unfortunately the x86 implementation used the exact same function names like "crypto_blake2s_update()", so it had to be updated at the same time.) Signed-off-by: Eric Biggers Acked-by: Ard Biesheuvel Signed-off-by: Herbert Xu --- arch/x86/crypto/blake2s-glue.c | 74 ++++---------------------------------- crypto/blake2s_generic.c | 76 +++++---------------------------------- include/crypto/internal/blake2s.h | 65 ++++++++++++++++++++++++++++++--- 3 files changed, 76 insertions(+), 139 deletions(-) (limited to 'include') diff --git a/arch/x86/crypto/blake2s-glue.c b/arch/x86/crypto/blake2s-glue.c index 4dcb2ee89efc..a40365ab301e 100644 --- a/arch/x86/crypto/blake2s-glue.c +++ b/arch/x86/crypto/blake2s-glue.c @@ -58,75 +58,15 @@ void blake2s_compress_arch(struct blake2s_state *state, } EXPORT_SYMBOL(blake2s_compress_arch); -static int crypto_blake2s_setkey(struct crypto_shash *tfm, const u8 *key, - unsigned int keylen) +static int crypto_blake2s_update_x86(struct shash_desc *desc, + const u8 *in, unsigned int inlen) { - struct blake2s_tfm_ctx *tctx = crypto_shash_ctx(tfm); - - if (keylen == 0 || keylen > BLAKE2S_KEY_SIZE) - return -EINVAL; - - memcpy(tctx->key, key, keylen); - tctx->keylen = keylen; - - return 0; -} - -static int crypto_blake2s_init(struct shash_desc *desc) -{ - struct blake2s_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm); - struct blake2s_state *state = shash_desc_ctx(desc); - const int outlen = crypto_shash_digestsize(desc->tfm); - - if (tctx->keylen) - blake2s_init_key(state, outlen, tctx->key, tctx->keylen); - else - blake2s_init(state, outlen); - - return 0; -} - -static int crypto_blake2s_update(struct shash_desc *desc, const u8 *in, - unsigned int inlen) -{ - struct blake2s_state *state = shash_desc_ctx(desc); - const size_t fill = BLAKE2S_BLOCK_SIZE - state->buflen; - - if (unlikely(!inlen)) - return 0; - if (inlen > fill) { - memcpy(state->buf + state->buflen, in, fill); - blake2s_compress_arch(state, state->buf, 1, BLAKE2S_BLOCK_SIZE); - state->buflen = 0; - in += fill; - inlen -= fill; - } - if (inlen > BLAKE2S_BLOCK_SIZE) { - const size_t nblocks = DIV_ROUND_UP(inlen, BLAKE2S_BLOCK_SIZE); - /* Hash one less (full) block than strictly possible */ - blake2s_compress_arch(state, in, nblocks - 1, BLAKE2S_BLOCK_SIZE); - in += BLAKE2S_BLOCK_SIZE * (nblocks - 1); - inlen -= BLAKE2S_BLOCK_SIZE * (nblocks - 1); - } - memcpy(state->buf + state->buflen, in, inlen); - state->buflen += inlen; - - return 0; + return crypto_blake2s_update(desc, in, inlen, blake2s_compress_arch); } -static int crypto_blake2s_final(struct shash_desc *desc, u8 *out) +static int crypto_blake2s_final_x86(struct shash_desc *desc, u8 *out) { - struct blake2s_state *state = shash_desc_ctx(desc); - - blake2s_set_lastblock(state); - memset(state->buf + state->buflen, 0, - BLAKE2S_BLOCK_SIZE - state->buflen); /* Padding */ - blake2s_compress_arch(state, state->buf, 1, state->buflen); - cpu_to_le32_array(state->h, ARRAY_SIZE(state->h)); - memcpy(out, state->h, state->outlen); - memzero_explicit(state, sizeof(*state)); - - return 0; + return crypto_blake2s_final(desc, out, blake2s_compress_arch); } #define BLAKE2S_ALG(name, driver_name, digest_size) \ @@ -141,8 +81,8 @@ static int crypto_blake2s_final(struct shash_desc *desc, u8 *out) .digestsize = digest_size, \ .setkey = crypto_blake2s_setkey, \ .init = crypto_blake2s_init, \ - .update = crypto_blake2s_update, \ - .final = crypto_blake2s_final, \ + .update = crypto_blake2s_update_x86, \ + .final = crypto_blake2s_final_x86, \ .descsize = sizeof(struct blake2s_state), \ } diff --git a/crypto/blake2s_generic.c b/crypto/blake2s_generic.c index b89536c3671c..72fe480f9bd6 100644 --- a/crypto/blake2s_generic.c +++ b/crypto/blake2s_generic.c @@ -1,5 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 OR MIT /* + * shash interface to the generic implementation of BLAKE2s + * * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. */ @@ -10,75 +12,15 @@ #include #include -static int crypto_blake2s_setkey(struct crypto_shash *tfm, const u8 *key, - unsigned int keylen) +static int crypto_blake2s_update_generic(struct shash_desc *desc, + const u8 *in, unsigned int inlen) { - struct blake2s_tfm_ctx *tctx = crypto_shash_ctx(tfm); - - if (keylen == 0 || keylen > BLAKE2S_KEY_SIZE) - return -EINVAL; - - memcpy(tctx->key, key, keylen); - tctx->keylen = keylen; - - return 0; + return crypto_blake2s_update(desc, in, inlen, blake2s_compress_generic); } -static int crypto_blake2s_init(struct shash_desc *desc) +static int crypto_blake2s_final_generic(struct shash_desc *desc, u8 *out) { - struct blake2s_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm); - struct blake2s_state *state = shash_desc_ctx(desc); - const int outlen = crypto_shash_digestsize(desc->tfm); - - if (tctx->keylen) - blake2s_init_key(state, outlen, tctx->key, tctx->keylen); - else - blake2s_init(state, outlen); - - return 0; -} - -static int crypto_blake2s_update(struct shash_desc *desc, const u8 *in, - unsigned int inlen) -{ - struct blake2s_state *state = shash_desc_ctx(desc); - const size_t fill = BLAKE2S_BLOCK_SIZE - state->buflen; - - if (unlikely(!inlen)) - return 0; - if (inlen > fill) { - memcpy(state->buf + state->buflen, in, fill); - blake2s_compress_generic(state, state->buf, 1, BLAKE2S_BLOCK_SIZE); - state->buflen = 0; - in += fill; - inlen -= fill; - } - if (inlen > BLAKE2S_BLOCK_SIZE) { - const size_t nblocks = DIV_ROUND_UP(inlen, BLAKE2S_BLOCK_SIZE); - /* Hash one less (full) block than strictly possible */ - blake2s_compress_generic(state, in, nblocks - 1, BLAKE2S_BLOCK_SIZE); - in += BLAKE2S_BLOCK_SIZE * (nblocks - 1); - inlen -= BLAKE2S_BLOCK_SIZE * (nblocks - 1); - } - memcpy(state->buf + state->buflen, in, inlen); - state->buflen += inlen; - - return 0; -} - -static int crypto_blake2s_final(struct shash_desc *desc, u8 *out) -{ - struct blake2s_state *state = shash_desc_ctx(desc); - - blake2s_set_lastblock(state); - memset(state->buf + state->buflen, 0, - BLAKE2S_BLOCK_SIZE - state->buflen); /* Padding */ - blake2s_compress_generic(state, state->buf, 1, state->buflen); - cpu_to_le32_array(state->h, ARRAY_SIZE(state->h)); - memcpy(out, state->h, state->outlen); - memzero_explicit(state, sizeof(*state)); - - return 0; + return crypto_blake2s_final(desc, out, blake2s_compress_generic); } #define BLAKE2S_ALG(name, driver_name, digest_size) \ @@ -93,8 +35,8 @@ static int crypto_blake2s_final(struct shash_desc *desc, u8 *out) .digestsize = digest_size, \ .setkey = crypto_blake2s_setkey, \ .init = crypto_blake2s_init, \ - .update = crypto_blake2s_update, \ - .final = crypto_blake2s_final, \ + .update = crypto_blake2s_update_generic, \ + .final = crypto_blake2s_final_generic, \ .descsize = sizeof(struct blake2s_state), \ } diff --git a/include/crypto/internal/blake2s.h b/include/crypto/internal/blake2s.h index 42deba4b8cee..2ea0a8f5e7f4 100644 --- a/include/crypto/internal/blake2s.h +++ b/include/crypto/internal/blake2s.h @@ -1,16 +1,16 @@ /* SPDX-License-Identifier: GPL-2.0 OR MIT */ +/* + * Helper functions for BLAKE2s implementations. + * Keep this in sync with the corresponding BLAKE2b header. + */ #ifndef BLAKE2S_INTERNAL_H #define BLAKE2S_INTERNAL_H #include +#include #include -struct blake2s_tfm_ctx { - u8 key[BLAKE2S_KEY_SIZE]; - unsigned int keylen; -}; - void blake2s_compress_generic(struct blake2s_state *state,const u8 *block, size_t nblocks, const u32 inc); @@ -27,6 +27,8 @@ static inline void blake2s_set_lastblock(struct blake2s_state *state) typedef void (*blake2s_compress_t)(struct blake2s_state *state, const u8 *block, size_t nblocks, u32 inc); +/* Helper functions for BLAKE2s shared by the library and shash APIs */ + static inline void __blake2s_update(struct blake2s_state *state, const u8 *in, size_t inlen, blake2s_compress_t compress) @@ -64,4 +66,57 @@ static inline void __blake2s_final(struct blake2s_state *state, u8 *out, memcpy(out, state->h, state->outlen); } +/* Helper functions for shash implementations of BLAKE2s */ + +struct blake2s_tfm_ctx { + u8 key[BLAKE2S_KEY_SIZE]; + unsigned int keylen; +}; + +static inline int crypto_blake2s_setkey(struct crypto_shash *tfm, + const u8 *key, unsigned int keylen) +{ + struct blake2s_tfm_ctx *tctx = crypto_shash_ctx(tfm); + + if (keylen == 0 || keylen > BLAKE2S_KEY_SIZE) + return -EINVAL; + + memcpy(tctx->key, key, keylen); + tctx->keylen = keylen; + + return 0; +} + +static inline int crypto_blake2s_init(struct shash_desc *desc) +{ + const struct blake2s_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm); + struct blake2s_state *state = shash_desc_ctx(desc); + unsigned int outlen = crypto_shash_digestsize(desc->tfm); + + if (tctx->keylen) + blake2s_init_key(state, outlen, tctx->key, tctx->keylen); + else + blake2s_init(state, outlen); + return 0; +} + +static inline int crypto_blake2s_update(struct shash_desc *desc, + const u8 *in, unsigned int inlen, + blake2s_compress_t compress) +{ + struct blake2s_state *state = shash_desc_ctx(desc); + + __blake2s_update(state, in, inlen, compress); + return 0; +} + +static inline int crypto_blake2s_final(struct shash_desc *desc, u8 *out, + blake2s_compress_t compress) +{ + struct blake2s_state *state = shash_desc_ctx(desc); + + __blake2s_final(state, out, compress); + return 0; +} + #endif /* BLAKE2S_INTERNAL_H */ -- cgit v1.2.3 From 42ad8cf821f0d8564c393e9ad7d00a1a271d18ae Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 23 Dec 2020 00:09:55 -0800 Subject: crypto: blake2s - optimize blake2s initialization If no key was provided, then don't waste time initializing the block buffer, as its initial contents won't be used. Also, make crypto_blake2s_init() and blake2s() call a single internal function __blake2s_init() which treats the key as optional, rather than conditionally calling blake2s_init() or blake2s_init_key(). This reduces the compiled code size, as previously both blake2s_init() and blake2s_init_key() were being inlined into these two callers, except when the key size passed to blake2s() was a compile-time constant. These optimizations aren't that significant for BLAKE2s. However, the equivalent optimizations will be more significant for BLAKE2b, as everything is twice as big in BLAKE2b. And it's good to keep things consistent rather than making optimizations for BLAKE2b but not BLAKE2s. Signed-off-by: Eric Biggers Acked-by: Ard Biesheuvel Signed-off-by: Herbert Xu --- include/crypto/blake2s.h | 53 ++++++++++++++++++++------------------- include/crypto/internal/blake2s.h | 5 +--- 2 files changed, 28 insertions(+), 30 deletions(-) (limited to 'include') diff --git a/include/crypto/blake2s.h b/include/crypto/blake2s.h index b471deac28ff..734ed22b7a6a 100644 --- a/include/crypto/blake2s.h +++ b/include/crypto/blake2s.h @@ -43,29 +43,34 @@ enum blake2s_iv { BLAKE2S_IV7 = 0x5BE0CD19UL, }; -void blake2s_update(struct blake2s_state *state, const u8 *in, size_t inlen); -void blake2s_final(struct blake2s_state *state, u8 *out); - -static inline void blake2s_init_param(struct blake2s_state *state, - const u32 param) +static inline void __blake2s_init(struct blake2s_state *state, size_t outlen, + const void *key, size_t keylen) { - *state = (struct blake2s_state){{ - BLAKE2S_IV0 ^ param, - BLAKE2S_IV1, - BLAKE2S_IV2, - BLAKE2S_IV3, - BLAKE2S_IV4, - BLAKE2S_IV5, - BLAKE2S_IV6, - BLAKE2S_IV7, - }}; + state->h[0] = BLAKE2S_IV0 ^ (0x01010000 | keylen << 8 | outlen); + state->h[1] = BLAKE2S_IV1; + state->h[2] = BLAKE2S_IV2; + state->h[3] = BLAKE2S_IV3; + state->h[4] = BLAKE2S_IV4; + state->h[5] = BLAKE2S_IV5; + state->h[6] = BLAKE2S_IV6; + state->h[7] = BLAKE2S_IV7; + state->t[0] = 0; + state->t[1] = 0; + state->f[0] = 0; + state->f[1] = 0; + state->buflen = 0; + state->outlen = outlen; + if (keylen) { + memcpy(state->buf, key, keylen); + memset(&state->buf[keylen], 0, BLAKE2S_BLOCK_SIZE - keylen); + state->buflen = BLAKE2S_BLOCK_SIZE; + } } static inline void blake2s_init(struct blake2s_state *state, const size_t outlen) { - blake2s_init_param(state, 0x01010000 | outlen); - state->outlen = outlen; + __blake2s_init(state, outlen, NULL, 0); } static inline void blake2s_init_key(struct blake2s_state *state, @@ -75,12 +80,12 @@ static inline void blake2s_init_key(struct blake2s_state *state, WARN_ON(IS_ENABLED(DEBUG) && (!outlen || outlen > BLAKE2S_HASH_SIZE || !key || !keylen || keylen > BLAKE2S_KEY_SIZE)); - blake2s_init_param(state, 0x01010000 | keylen << 8 | outlen); - memcpy(state->buf, key, keylen); - state->buflen = BLAKE2S_BLOCK_SIZE; - state->outlen = outlen; + __blake2s_init(state, outlen, key, keylen); } +void blake2s_update(struct blake2s_state *state, const u8 *in, size_t inlen); +void blake2s_final(struct blake2s_state *state, u8 *out); + static inline void blake2s(u8 *out, const u8 *in, const u8 *key, const size_t outlen, const size_t inlen, const size_t keylen) @@ -91,11 +96,7 @@ static inline void blake2s(u8 *out, const u8 *in, const u8 *key, outlen > BLAKE2S_HASH_SIZE || keylen > BLAKE2S_KEY_SIZE || (!key && keylen))); - if (keylen) - blake2s_init_key(&state, outlen, key, keylen); - else - blake2s_init(&state, outlen); - + __blake2s_init(&state, outlen, key, keylen); blake2s_update(&state, in, inlen); blake2s_final(&state, out); } diff --git a/include/crypto/internal/blake2s.h b/include/crypto/internal/blake2s.h index 2ea0a8f5e7f4..867ef3753f5c 100644 --- a/include/crypto/internal/blake2s.h +++ b/include/crypto/internal/blake2s.h @@ -93,10 +93,7 @@ static inline int crypto_blake2s_init(struct shash_desc *desc) struct blake2s_state *state = shash_desc_ctx(desc); unsigned int outlen = crypto_shash_digestsize(desc->tfm); - if (tctx->keylen) - blake2s_init_key(state, outlen, tctx->key, tctx->keylen); - else - blake2s_init(state, outlen); + __blake2s_init(state, outlen, tctx->key, tctx->keylen); return 0; } -- cgit v1.2.3 From 7d87131fadd53a0401b5c078dd64e58c3ea6994c Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 23 Dec 2020 00:09:56 -0800 Subject: crypto: blake2s - add comment for blake2s_state fields The first three fields of 'struct blake2s_state' are used in assembly code, which isn't immediately obvious, so add a comment to this effect. Signed-off-by: Eric Biggers Acked-by: Ard Biesheuvel Signed-off-by: Herbert Xu --- include/crypto/blake2s.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/crypto/blake2s.h b/include/crypto/blake2s.h index 734ed22b7a6a..f1c8330a61a9 100644 --- a/include/crypto/blake2s.h +++ b/include/crypto/blake2s.h @@ -24,6 +24,7 @@ enum blake2s_lengths { }; struct blake2s_state { + /* 'h', 't', and 'f' are used in assembly code, so keep them as-is. */ u32 h[8]; u32 t[2]; u32 f[2]; -- cgit v1.2.3 From 8786841bc2020f7f2513a6c74e64912f07b9c0dc Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 23 Dec 2020 00:09:57 -0800 Subject: crypto: blake2s - adjust include guard naming Use the full path in the include guards for the BLAKE2s headers to avoid ambiguity and to match the convention for most files in include/crypto/. Signed-off-by: Eric Biggers Acked-by: Ard Biesheuvel Signed-off-by: Herbert Xu --- include/crypto/blake2s.h | 6 +++--- include/crypto/internal/blake2s.h | 6 +++--- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/crypto/blake2s.h b/include/crypto/blake2s.h index f1c8330a61a9..3f06183c2d80 100644 --- a/include/crypto/blake2s.h +++ b/include/crypto/blake2s.h @@ -3,8 +3,8 @@ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. */ -#ifndef BLAKE2S_H -#define BLAKE2S_H +#ifndef _CRYPTO_BLAKE2S_H +#define _CRYPTO_BLAKE2S_H #include #include @@ -105,4 +105,4 @@ static inline void blake2s(u8 *out, const u8 *in, const u8 *key, void blake2s256_hmac(u8 *out, const u8 *in, const u8 *key, const size_t inlen, const size_t keylen); -#endif /* BLAKE2S_H */ +#endif /* _CRYPTO_BLAKE2S_H */ diff --git a/include/crypto/internal/blake2s.h b/include/crypto/internal/blake2s.h index 867ef3753f5c..8e50d487500f 100644 --- a/include/crypto/internal/blake2s.h +++ b/include/crypto/internal/blake2s.h @@ -4,8 +4,8 @@ * Keep this in sync with the corresponding BLAKE2b header. */ -#ifndef BLAKE2S_INTERNAL_H -#define BLAKE2S_INTERNAL_H +#ifndef _CRYPTO_INTERNAL_BLAKE2S_H +#define _CRYPTO_INTERNAL_BLAKE2S_H #include #include @@ -116,4 +116,4 @@ static inline int crypto_blake2s_final(struct shash_desc *desc, u8 *out, return 0; } -#endif /* BLAKE2S_INTERNAL_H */ +#endif /* _CRYPTO_INTERNAL_BLAKE2S_H */ -- cgit v1.2.3 From bbda6e0f1303953c855ee3669655a81b69fbe899 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 23 Dec 2020 00:09:58 -0800 Subject: crypto: blake2s - include instead of Address the following checkpatch warning: WARNING: Use #include instead of Signed-off-by: Eric Biggers Acked-by: Ard Biesheuvel Signed-off-by: Herbert Xu --- include/crypto/blake2s.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/crypto/blake2s.h b/include/crypto/blake2s.h index 3f06183c2d80..bc3fb59442ce 100644 --- a/include/crypto/blake2s.h +++ b/include/crypto/blake2s.h @@ -6,12 +6,11 @@ #ifndef _CRYPTO_BLAKE2S_H #define _CRYPTO_BLAKE2S_H +#include #include #include #include -#include - enum blake2s_lengths { BLAKE2S_BLOCK_SIZE = 64, BLAKE2S_HASH_SIZE = 32, -- cgit v1.2.3 From 28dcca4cc0c01e2467549a36b1b0eacfdb01236c Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 23 Dec 2020 00:10:01 -0800 Subject: crypto: blake2b - sync with blake2s implementation Sync the BLAKE2b code with the BLAKE2s code as much as possible: - Move a lot of code into new headers and , and adjust it to be like the corresponding BLAKE2s code, i.e. like and . - Rename constants, e.g. BLAKE2B_*_DIGEST_SIZE => BLAKE2B_*_HASH_SIZE. - Use a macro BLAKE2B_ALG() to define the shash_alg structs. - Export blake2b_compress_generic() for use as a fallback. This makes it much easier to add optimized implementations of BLAKE2b, as optimized implementations can use the helper functions crypto_blake2b_{setkey,init,update,final}() and blake2b_compress_generic(). The ARM implementation will use these. But this change is also helpful because it eliminates unnecessary differences between the BLAKE2b and BLAKE2s code, so that the same improvements can easily be made to both. (The two algorithms are basically identical, except for the word size and constants.) It also makes it straightforward to add a library API for BLAKE2b in the future if/when it's needed. This change does make the BLAKE2b code slightly more complicated than it needs to be, as it doesn't actually provide a library API yet. For example, __blake2b_update() doesn't really need to exist yet; it could just be inlined into crypto_blake2b_update(). But I believe this is outweighed by the benefits of keeping the code in sync. Signed-off-by: Eric Biggers Acked-by: Ard Biesheuvel Signed-off-by: Herbert Xu --- crypto/blake2b_generic.c | 226 ++++++++------------------------------ include/crypto/blake2b.h | 67 +++++++++++ include/crypto/internal/blake2b.h | 115 +++++++++++++++++++ 3 files changed, 230 insertions(+), 178 deletions(-) create mode 100644 include/crypto/blake2b.h create mode 100644 include/crypto/internal/blake2b.h (limited to 'include') diff --git a/crypto/blake2b_generic.c b/crypto/blake2b_generic.c index a2ffe60e06d3..963f7fe0e4ea 100644 --- a/crypto/blake2b_generic.c +++ b/crypto/blake2b_generic.c @@ -20,36 +20,11 @@ #include #include -#include #include #include +#include #include -#define BLAKE2B_160_DIGEST_SIZE (160 / 8) -#define BLAKE2B_256_DIGEST_SIZE (256 / 8) -#define BLAKE2B_384_DIGEST_SIZE (384 / 8) -#define BLAKE2B_512_DIGEST_SIZE (512 / 8) - -enum blake2b_constant { - BLAKE2B_BLOCKBYTES = 128, - BLAKE2B_KEYBYTES = 64, -}; - -struct blake2b_state { - u64 h[8]; - u64 t[2]; - u64 f[2]; - u8 buf[BLAKE2B_BLOCKBYTES]; - size_t buflen; -}; - -static const u64 blake2b_IV[8] = { - 0x6a09e667f3bcc908ULL, 0xbb67ae8584caa73bULL, - 0x3c6ef372fe94f82bULL, 0xa54ff53a5f1d36f1ULL, - 0x510e527fade682d1ULL, 0x9b05688c2b3e6c1fULL, - 0x1f83d9abfb41bd6bULL, 0x5be0cd19137e2179ULL -}; - static const u8 blake2b_sigma[12][16] = { { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 }, { 14, 10, 4, 8, 9, 15, 13, 6, 1, 12, 0, 2, 11, 7, 5, 3 }, @@ -95,8 +70,8 @@ static void blake2b_increment_counter(struct blake2b_state *S, const u64 inc) G(r,7,v[ 3],v[ 4],v[ 9],v[14]); \ } while (0) -static void blake2b_compress(struct blake2b_state *S, - const u8 block[BLAKE2B_BLOCKBYTES]) +static void blake2b_compress_one_generic(struct blake2b_state *S, + const u8 block[BLAKE2B_BLOCK_SIZE]) { u64 m[16]; u64 v[16]; @@ -108,14 +83,14 @@ static void blake2b_compress(struct blake2b_state *S, for (i = 0; i < 8; ++i) v[i] = S->h[i]; - v[ 8] = blake2b_IV[0]; - v[ 9] = blake2b_IV[1]; - v[10] = blake2b_IV[2]; - v[11] = blake2b_IV[3]; - v[12] = blake2b_IV[4] ^ S->t[0]; - v[13] = blake2b_IV[5] ^ S->t[1]; - v[14] = blake2b_IV[6] ^ S->f[0]; - v[15] = blake2b_IV[7] ^ S->f[1]; + v[ 8] = BLAKE2B_IV0; + v[ 9] = BLAKE2B_IV1; + v[10] = BLAKE2B_IV2; + v[11] = BLAKE2B_IV3; + v[12] = BLAKE2B_IV4 ^ S->t[0]; + v[13] = BLAKE2B_IV5 ^ S->t[1]; + v[14] = BLAKE2B_IV6 ^ S->f[0]; + v[15] = BLAKE2B_IV7 ^ S->f[1]; ROUND(0); ROUND(1); @@ -139,159 +114,54 @@ static void blake2b_compress(struct blake2b_state *S, #undef G #undef ROUND -struct blake2b_tfm_ctx { - u8 key[BLAKE2B_KEYBYTES]; - unsigned int keylen; -}; - -static int blake2b_setkey(struct crypto_shash *tfm, const u8 *key, - unsigned int keylen) +void blake2b_compress_generic(struct blake2b_state *state, + const u8 *block, size_t nblocks, u32 inc) { - struct blake2b_tfm_ctx *tctx = crypto_shash_ctx(tfm); - - if (keylen == 0 || keylen > BLAKE2B_KEYBYTES) - return -EINVAL; - - memcpy(tctx->key, key, keylen); - tctx->keylen = keylen; - - return 0; + do { + blake2b_increment_counter(state, inc); + blake2b_compress_one_generic(state, block); + block += BLAKE2B_BLOCK_SIZE; + } while (--nblocks); } +EXPORT_SYMBOL(blake2b_compress_generic); -static int blake2b_init(struct shash_desc *desc) +static int crypto_blake2b_update_generic(struct shash_desc *desc, + const u8 *in, unsigned int inlen) { - struct blake2b_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm); - struct blake2b_state *state = shash_desc_ctx(desc); - const int digestsize = crypto_shash_digestsize(desc->tfm); - - memset(state, 0, sizeof(*state)); - memcpy(state->h, blake2b_IV, sizeof(state->h)); - - /* Parameter block is all zeros except index 0, no xor for 1..7 */ - state->h[0] ^= 0x01010000 | tctx->keylen << 8 | digestsize; - - if (tctx->keylen) { - /* - * Prefill the buffer with the key, next call to _update or - * _final will process it - */ - memcpy(state->buf, tctx->key, tctx->keylen); - state->buflen = BLAKE2B_BLOCKBYTES; - } - return 0; + return crypto_blake2b_update(desc, in, inlen, blake2b_compress_generic); } -static int blake2b_update(struct shash_desc *desc, const u8 *in, - unsigned int inlen) +static int crypto_blake2b_final_generic(struct shash_desc *desc, u8 *out) { - struct blake2b_state *state = shash_desc_ctx(desc); - const size_t left = state->buflen; - const size_t fill = BLAKE2B_BLOCKBYTES - left; - - if (!inlen) - return 0; - - if (inlen > fill) { - state->buflen = 0; - /* Fill buffer */ - memcpy(state->buf + left, in, fill); - blake2b_increment_counter(state, BLAKE2B_BLOCKBYTES); - /* Compress */ - blake2b_compress(state, state->buf); - in += fill; - inlen -= fill; - while (inlen > BLAKE2B_BLOCKBYTES) { - blake2b_increment_counter(state, BLAKE2B_BLOCKBYTES); - blake2b_compress(state, in); - in += BLAKE2B_BLOCKBYTES; - inlen -= BLAKE2B_BLOCKBYTES; - } - } - memcpy(state->buf + state->buflen, in, inlen); - state->buflen += inlen; - - return 0; + return crypto_blake2b_final(desc, out, blake2b_compress_generic); } -static int blake2b_final(struct shash_desc *desc, u8 *out) -{ - struct blake2b_state *state = shash_desc_ctx(desc); - const int digestsize = crypto_shash_digestsize(desc->tfm); - size_t i; - - blake2b_increment_counter(state, state->buflen); - /* Set last block */ - state->f[0] = (u64)-1; - /* Padding */ - memset(state->buf + state->buflen, 0, BLAKE2B_BLOCKBYTES - state->buflen); - blake2b_compress(state, state->buf); - - /* Avoid temporary buffer and switch the internal output to LE order */ - for (i = 0; i < ARRAY_SIZE(state->h); i++) - __cpu_to_le64s(&state->h[i]); - - memcpy(out, state->h, digestsize); - return 0; -} +#define BLAKE2B_ALG(name, driver_name, digest_size) \ + { \ + .base.cra_name = name, \ + .base.cra_driver_name = driver_name, \ + .base.cra_priority = 100, \ + .base.cra_flags = CRYPTO_ALG_OPTIONAL_KEY, \ + .base.cra_blocksize = BLAKE2B_BLOCK_SIZE, \ + .base.cra_ctxsize = sizeof(struct blake2b_tfm_ctx), \ + .base.cra_module = THIS_MODULE, \ + .digestsize = digest_size, \ + .setkey = crypto_blake2b_setkey, \ + .init = crypto_blake2b_init, \ + .update = crypto_blake2b_update_generic, \ + .final = crypto_blake2b_final_generic, \ + .descsize = sizeof(struct blake2b_state), \ + } static struct shash_alg blake2b_algs[] = { - { - .base.cra_name = "blake2b-160", - .base.cra_driver_name = "blake2b-160-generic", - .base.cra_priority = 100, - .base.cra_flags = CRYPTO_ALG_OPTIONAL_KEY, - .base.cra_blocksize = BLAKE2B_BLOCKBYTES, - .base.cra_ctxsize = sizeof(struct blake2b_tfm_ctx), - .base.cra_module = THIS_MODULE, - .digestsize = BLAKE2B_160_DIGEST_SIZE, - .setkey = blake2b_setkey, - .init = blake2b_init, - .update = blake2b_update, - .final = blake2b_final, - .descsize = sizeof(struct blake2b_state), - }, { - .base.cra_name = "blake2b-256", - .base.cra_driver_name = "blake2b-256-generic", - .base.cra_priority = 100, - .base.cra_flags = CRYPTO_ALG_OPTIONAL_KEY, - .base.cra_blocksize = BLAKE2B_BLOCKBYTES, - .base.cra_ctxsize = sizeof(struct blake2b_tfm_ctx), - .base.cra_module = THIS_MODULE, - .digestsize = BLAKE2B_256_DIGEST_SIZE, - .setkey = blake2b_setkey, - .init = blake2b_init, - .update = blake2b_update, - .final = blake2b_final, - .descsize = sizeof(struct blake2b_state), - }, { - .base.cra_name = "blake2b-384", - .base.cra_driver_name = "blake2b-384-generic", - .base.cra_priority = 100, - .base.cra_flags = CRYPTO_ALG_OPTIONAL_KEY, - .base.cra_blocksize = BLAKE2B_BLOCKBYTES, - .base.cra_ctxsize = sizeof(struct blake2b_tfm_ctx), - .base.cra_module = THIS_MODULE, - .digestsize = BLAKE2B_384_DIGEST_SIZE, - .setkey = blake2b_setkey, - .init = blake2b_init, - .update = blake2b_update, - .final = blake2b_final, - .descsize = sizeof(struct blake2b_state), - }, { - .base.cra_name = "blake2b-512", - .base.cra_driver_name = "blake2b-512-generic", - .base.cra_priority = 100, - .base.cra_flags = CRYPTO_ALG_OPTIONAL_KEY, - .base.cra_blocksize = BLAKE2B_BLOCKBYTES, - .base.cra_ctxsize = sizeof(struct blake2b_tfm_ctx), - .base.cra_module = THIS_MODULE, - .digestsize = BLAKE2B_512_DIGEST_SIZE, - .setkey = blake2b_setkey, - .init = blake2b_init, - .update = blake2b_update, - .final = blake2b_final, - .descsize = sizeof(struct blake2b_state), - } + BLAKE2B_ALG("blake2b-160", "blake2b-160-generic", + BLAKE2B_160_HASH_SIZE), + BLAKE2B_ALG("blake2b-256", "blake2b-256-generic", + BLAKE2B_256_HASH_SIZE), + BLAKE2B_ALG("blake2b-384", "blake2b-384-generic", + BLAKE2B_384_HASH_SIZE), + BLAKE2B_ALG("blake2b-512", "blake2b-512-generic", + BLAKE2B_512_HASH_SIZE), }; static int __init blake2b_mod_init(void) diff --git a/include/crypto/blake2b.h b/include/crypto/blake2b.h new file mode 100644 index 000000000000..18875f16f8ca --- /dev/null +++ b/include/crypto/blake2b.h @@ -0,0 +1,67 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ + +#ifndef _CRYPTO_BLAKE2B_H +#define _CRYPTO_BLAKE2B_H + +#include +#include +#include +#include + +enum blake2b_lengths { + BLAKE2B_BLOCK_SIZE = 128, + BLAKE2B_HASH_SIZE = 64, + BLAKE2B_KEY_SIZE = 64, + + BLAKE2B_160_HASH_SIZE = 20, + BLAKE2B_256_HASH_SIZE = 32, + BLAKE2B_384_HASH_SIZE = 48, + BLAKE2B_512_HASH_SIZE = 64, +}; + +struct blake2b_state { + /* 'h', 't', and 'f' are used in assembly code, so keep them as-is. */ + u64 h[8]; + u64 t[2]; + u64 f[2]; + u8 buf[BLAKE2B_BLOCK_SIZE]; + unsigned int buflen; + unsigned int outlen; +}; + +enum blake2b_iv { + BLAKE2B_IV0 = 0x6A09E667F3BCC908ULL, + BLAKE2B_IV1 = 0xBB67AE8584CAA73BULL, + BLAKE2B_IV2 = 0x3C6EF372FE94F82BULL, + BLAKE2B_IV3 = 0xA54FF53A5F1D36F1ULL, + BLAKE2B_IV4 = 0x510E527FADE682D1ULL, + BLAKE2B_IV5 = 0x9B05688C2B3E6C1FULL, + BLAKE2B_IV6 = 0x1F83D9ABFB41BD6BULL, + BLAKE2B_IV7 = 0x5BE0CD19137E2179ULL, +}; + +static inline void __blake2b_init(struct blake2b_state *state, size_t outlen, + const void *key, size_t keylen) +{ + state->h[0] = BLAKE2B_IV0 ^ (0x01010000 | keylen << 8 | outlen); + state->h[1] = BLAKE2B_IV1; + state->h[2] = BLAKE2B_IV2; + state->h[3] = BLAKE2B_IV3; + state->h[4] = BLAKE2B_IV4; + state->h[5] = BLAKE2B_IV5; + state->h[6] = BLAKE2B_IV6; + state->h[7] = BLAKE2B_IV7; + state->t[0] = 0; + state->t[1] = 0; + state->f[0] = 0; + state->f[1] = 0; + state->buflen = 0; + state->outlen = outlen; + if (keylen) { + memcpy(state->buf, key, keylen); + memset(&state->buf[keylen], 0, BLAKE2B_BLOCK_SIZE - keylen); + state->buflen = BLAKE2B_BLOCK_SIZE; + } +} + +#endif /* _CRYPTO_BLAKE2B_H */ diff --git a/include/crypto/internal/blake2b.h b/include/crypto/internal/blake2b.h new file mode 100644 index 000000000000..982fe5e8471c --- /dev/null +++ b/include/crypto/internal/blake2b.h @@ -0,0 +1,115 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ +/* + * Helper functions for BLAKE2b implementations. + * Keep this in sync with the corresponding BLAKE2s header. + */ + +#ifndef _CRYPTO_INTERNAL_BLAKE2B_H +#define _CRYPTO_INTERNAL_BLAKE2B_H + +#include +#include +#include + +void blake2b_compress_generic(struct blake2b_state *state, + const u8 *block, size_t nblocks, u32 inc); + +static inline void blake2b_set_lastblock(struct blake2b_state *state) +{ + state->f[0] = -1; +} + +typedef void (*blake2b_compress_t)(struct blake2b_state *state, + const u8 *block, size_t nblocks, u32 inc); + +static inline void __blake2b_update(struct blake2b_state *state, + const u8 *in, size_t inlen, + blake2b_compress_t compress) +{ + const size_t fill = BLAKE2B_BLOCK_SIZE - state->buflen; + + if (unlikely(!inlen)) + return; + if (inlen > fill) { + memcpy(state->buf + state->buflen, in, fill); + (*compress)(state, state->buf, 1, BLAKE2B_BLOCK_SIZE); + state->buflen = 0; + in += fill; + inlen -= fill; + } + if (inlen > BLAKE2B_BLOCK_SIZE) { + const size_t nblocks = DIV_ROUND_UP(inlen, BLAKE2B_BLOCK_SIZE); + /* Hash one less (full) block than strictly possible */ + (*compress)(state, in, nblocks - 1, BLAKE2B_BLOCK_SIZE); + in += BLAKE2B_BLOCK_SIZE * (nblocks - 1); + inlen -= BLAKE2B_BLOCK_SIZE * (nblocks - 1); + } + memcpy(state->buf + state->buflen, in, inlen); + state->buflen += inlen; +} + +static inline void __blake2b_final(struct blake2b_state *state, u8 *out, + blake2b_compress_t compress) +{ + int i; + + blake2b_set_lastblock(state); + memset(state->buf + state->buflen, 0, + BLAKE2B_BLOCK_SIZE - state->buflen); /* Padding */ + (*compress)(state, state->buf, 1, state->buflen); + for (i = 0; i < ARRAY_SIZE(state->h); i++) + __cpu_to_le64s(&state->h[i]); + memcpy(out, state->h, state->outlen); +} + +/* Helper functions for shash implementations of BLAKE2b */ + +struct blake2b_tfm_ctx { + u8 key[BLAKE2B_KEY_SIZE]; + unsigned int keylen; +}; + +static inline int crypto_blake2b_setkey(struct crypto_shash *tfm, + const u8 *key, unsigned int keylen) +{ + struct blake2b_tfm_ctx *tctx = crypto_shash_ctx(tfm); + + if (keylen == 0 || keylen > BLAKE2B_KEY_SIZE) + return -EINVAL; + + memcpy(tctx->key, key, keylen); + tctx->keylen = keylen; + + return 0; +} + +static inline int crypto_blake2b_init(struct shash_desc *desc) +{ + const struct blake2b_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm); + struct blake2b_state *state = shash_desc_ctx(desc); + unsigned int outlen = crypto_shash_digestsize(desc->tfm); + + __blake2b_init(state, outlen, tctx->key, tctx->keylen); + return 0; +} + +static inline int crypto_blake2b_update(struct shash_desc *desc, + const u8 *in, unsigned int inlen, + blake2b_compress_t compress) +{ + struct blake2b_state *state = shash_desc_ctx(desc); + + __blake2b_update(state, in, inlen, compress); + return 0; +} + +static inline int crypto_blake2b_final(struct shash_desc *desc, u8 *out, + blake2b_compress_t compress) +{ + struct blake2b_state *state = shash_desc_ctx(desc); + + __blake2b_final(state, out, compress); + return 0; +} + +#endif /* _CRYPTO_INTERNAL_BLAKE2B_H */ -- cgit v1.2.3 From b8dd6a8ae5019070c0a1a21f571010f14f1fc9ce Mon Sep 17 00:00:00 2001 From: Martin Blumenstingl Date: Mon, 21 Dec 2020 19:36:24 +0100 Subject: dt-bindings: clock: meson8b: remove non-existing clock macros CLKID_UNUSED and CLKID_XTAL aren't valid clocks. Remove them since there are no consumers of this anymore. Signed-off-by: Martin Blumenstingl Signed-off-by: Jerome Brunet Link: https://lore.kernel.org/r/20201221183624.932649-3-martin.blumenstingl@googlemail.com --- include/dt-bindings/clock/meson8b-clkc.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/dt-bindings/clock/meson8b-clkc.h b/include/dt-bindings/clock/meson8b-clkc.h index 4c5965ae1df4..f33781338eda 100644 --- a/include/dt-bindings/clock/meson8b-clkc.h +++ b/include/dt-bindings/clock/meson8b-clkc.h @@ -6,8 +6,6 @@ #ifndef __MESON8B_CLKC_H #define __MESON8B_CLKC_H -#define CLKID_UNUSED 0 -#define CLKID_XTAL 1 #define CLKID_PLL_FIXED 2 #define CLKID_PLL_VID 3 #define CLKID_PLL_SYS 4 -- cgit v1.2.3 From f35a2a99100fbed583efaf07919ef071cd75b059 Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Thu, 10 Dec 2020 16:38:27 +0100 Subject: drm/encoder: make encoder control functions optional Simple managed encoders do not require the .destroy callback, make the whole funcs structure optional. Signed-off-by: Philipp Zabel Reviewed-by: Laurent Pinchart Reviewed-by: Daniel Vetter --- drivers/gpu/drm/drm_encoder.c | 4 ++-- drivers/gpu/drm/drm_mode_config.c | 2 +- include/drm/drm_encoder.h | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_encoder.c b/drivers/gpu/drm/drm_encoder.c index e555281f43d4..b0b86a3c08f5 100644 --- a/drivers/gpu/drm/drm_encoder.c +++ b/drivers/gpu/drm/drm_encoder.c @@ -72,7 +72,7 @@ int drm_encoder_register_all(struct drm_device *dev) int ret = 0; drm_for_each_encoder(encoder, dev) { - if (encoder->funcs->late_register) + if (encoder->funcs && encoder->funcs->late_register) ret = encoder->funcs->late_register(encoder); if (ret) return ret; @@ -86,7 +86,7 @@ void drm_encoder_unregister_all(struct drm_device *dev) struct drm_encoder *encoder; drm_for_each_encoder(encoder, dev) { - if (encoder->funcs->early_unregister) + if (encoder->funcs && encoder->funcs->early_unregister) encoder->funcs->early_unregister(encoder); } } diff --git a/drivers/gpu/drm/drm_mode_config.c b/drivers/gpu/drm/drm_mode_config.c index f1affc1bb679..e56a7f877f48 100644 --- a/drivers/gpu/drm/drm_mode_config.c +++ b/drivers/gpu/drm/drm_mode_config.c @@ -195,7 +195,7 @@ void drm_mode_config_reset(struct drm_device *dev) crtc->funcs->reset(crtc); drm_for_each_encoder(encoder, dev) - if (encoder->funcs->reset) + if (encoder->funcs && encoder->funcs->reset) encoder->funcs->reset(encoder); drm_connector_list_iter_begin(dev, &conn_iter); diff --git a/include/drm/drm_encoder.h b/include/drm/drm_encoder.h index 5dfa5f7a80a7..833123637fbf 100644 --- a/include/drm/drm_encoder.h +++ b/include/drm/drm_encoder.h @@ -89,7 +89,7 @@ struct drm_encoder_funcs { * @head: list management * @base: base KMS object * @name: human readable name, can be overwritten by the driver - * @funcs: control functions + * @funcs: control functions, can be NULL for simple managed encoders * @helper_private: mid-layer private data * * CRTCs drive pixels to encoders, which convert them into signals -- cgit v1.2.3 From ca5092d04d86986c03b6e0042e2f1cd119c50f5d Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Thu, 10 Dec 2020 16:38:28 +0100 Subject: drm: add drmm_encoder_alloc() Add an alternative to drm_encoder_init() that allocates and initializes an encoder and registers drm_encoder_cleanup() with drmm_add_action_or_reset(). Signed-off-by: Philipp Zabel Reviewed-by: Laurent Pinchart Reviewed-by: Daniel Vetter --- drivers/gpu/drm/drm_encoder.c | 109 +++++++++++++++++++++++++++++++++--------- include/drm/drm_encoder.h | 30 ++++++++++++ 2 files changed, 116 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_encoder.c b/drivers/gpu/drm/drm_encoder.c index b0b86a3c08f5..72e982323a5e 100644 --- a/drivers/gpu/drm/drm_encoder.c +++ b/drivers/gpu/drm/drm_encoder.c @@ -26,6 +26,7 @@ #include #include #include +#include #include "drm_crtc_internal.h" @@ -91,25 +92,11 @@ void drm_encoder_unregister_all(struct drm_device *dev) } } -/** - * drm_encoder_init - Init a preallocated encoder - * @dev: drm device - * @encoder: the encoder to init - * @funcs: callbacks for this encoder - * @encoder_type: user visible type of the encoder - * @name: printf style format string for the encoder name, or NULL for default name - * - * Initialises a preallocated encoder. Encoder should be subclassed as part of - * driver encoder objects. At driver unload time drm_encoder_cleanup() should be - * called from the driver's &drm_encoder_funcs.destroy hook. - * - * Returns: - * Zero on success, error code on failure. - */ -int drm_encoder_init(struct drm_device *dev, - struct drm_encoder *encoder, - const struct drm_encoder_funcs *funcs, - int encoder_type, const char *name, ...) +__printf(5, 0) +static int __drm_encoder_init(struct drm_device *dev, + struct drm_encoder *encoder, + const struct drm_encoder_funcs *funcs, + int encoder_type, const char *name, va_list ap) { int ret; @@ -125,11 +112,7 @@ int drm_encoder_init(struct drm_device *dev, encoder->encoder_type = encoder_type; encoder->funcs = funcs; if (name) { - va_list ap; - - va_start(ap, name); encoder->name = kvasprintf(GFP_KERNEL, name, ap); - va_end(ap); } else { encoder->name = kasprintf(GFP_KERNEL, "%s-%d", drm_encoder_enum_list[encoder_type].name, @@ -150,6 +133,44 @@ out_put: return ret; } + +/** + * drm_encoder_init - Init a preallocated encoder + * @dev: drm device + * @encoder: the encoder to init + * @funcs: callbacks for this encoder + * @encoder_type: user visible type of the encoder + * @name: printf style format string for the encoder name, or NULL for default name + * + * Initializes a preallocated encoder. Encoder should be subclassed as part of + * driver encoder objects. At driver unload time the driver's + * &drm_encoder_funcs.destroy hook should call drm_encoder_cleanup() and kfree() + * the encoder structure. The encoder structure should not be allocated with + * devm_kzalloc(). + * + * Note: consider using drmm_encoder_alloc() instead of drm_encoder_init() to + * let the DRM managed resource infrastructure take care of cleanup and + * deallocation. + * + * Returns: + * Zero on success, error code on failure. + */ +int drm_encoder_init(struct drm_device *dev, + struct drm_encoder *encoder, + const struct drm_encoder_funcs *funcs, + int encoder_type, const char *name, ...) +{ + va_list ap; + int ret; + + WARN_ON(!funcs->destroy); + + va_start(ap, name); + ret = __drm_encoder_init(dev, encoder, funcs, encoder_type, name, ap); + va_end(ap); + + return ret; +} EXPORT_SYMBOL(drm_encoder_init); /** @@ -181,6 +202,48 @@ void drm_encoder_cleanup(struct drm_encoder *encoder) } EXPORT_SYMBOL(drm_encoder_cleanup); +static void drmm_encoder_alloc_release(struct drm_device *dev, void *ptr) +{ + struct drm_encoder *encoder = ptr; + + if (WARN_ON(!encoder->dev)) + return; + + drm_encoder_cleanup(encoder); +} + +void *__drmm_encoder_alloc(struct drm_device *dev, size_t size, size_t offset, + const struct drm_encoder_funcs *funcs, + int encoder_type, const char *name, ...) +{ + void *container; + struct drm_encoder *encoder; + va_list ap; + int ret; + + if (WARN_ON(funcs && funcs->destroy)) + return ERR_PTR(-EINVAL); + + container = drmm_kzalloc(dev, size, GFP_KERNEL); + if (!container) + return ERR_PTR(-EINVAL); + + encoder = container + offset; + + va_start(ap, name); + ret = __drm_encoder_init(dev, encoder, funcs, encoder_type, name, ap); + va_end(ap); + if (ret) + return ERR_PTR(ret); + + ret = drmm_add_action_or_reset(dev, drmm_encoder_alloc_release, encoder); + if (ret) + return ERR_PTR(ret); + + return container; +} +EXPORT_SYMBOL(__drmm_encoder_alloc); + static struct drm_crtc *drm_encoder_get_crtc(struct drm_encoder *encoder) { struct drm_connector *connector; diff --git a/include/drm/drm_encoder.h b/include/drm/drm_encoder.h index 833123637fbf..5bf78b5bcb2b 100644 --- a/include/drm/drm_encoder.h +++ b/include/drm/drm_encoder.h @@ -194,6 +194,36 @@ int drm_encoder_init(struct drm_device *dev, const struct drm_encoder_funcs *funcs, int encoder_type, const char *name, ...); +__printf(6, 7) +void *__drmm_encoder_alloc(struct drm_device *dev, + size_t size, size_t offset, + const struct drm_encoder_funcs *funcs, + int encoder_type, + const char *name, ...); + +/** + * drmm_encoder_alloc - Allocate and initialize an encoder + * @dev: drm device + * @type: the type of the struct which contains struct &drm_encoder + * @member: the name of the &drm_encoder within @type + * @funcs: callbacks for this encoder (optional) + * @encoder_type: user visible type of the encoder + * @name: printf style format string for the encoder name, or NULL for default name + * + * Allocates and initializes an encoder. Encoder should be subclassed as part of + * driver encoder objects. Cleanup is automatically handled through registering + * drm_encoder_cleanup() with drmm_add_action(). + * + * The @drm_encoder_funcs.destroy hook must be NULL. + * + * Returns: + * Pointer to new encoder, or ERR_PTR on failure. + */ +#define drmm_encoder_alloc(dev, type, member, funcs, encoder_type, name, ...) \ + ((type *)__drmm_encoder_alloc(dev, sizeof(type), \ + offsetof(type, member), funcs, \ + encoder_type, name, ##__VA_ARGS__)) + /** * drm_encoder_index - find the index of a registered encoder * @encoder: encoder to find index for -- cgit v1.2.3 From 59abba48c4299481053411f6a4de5df67b2c998f Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Thu, 10 Dec 2020 16:38:29 +0100 Subject: drm/simple_kms_helper: add drmm_simple_encoder_alloc() Add an alternative to drm_simple_encoder_init() that allocates and initializes a simple encoder and registers drm_encoder_cleanup() with drmm_add_action_or_reset(). Signed-off-by: Philipp Zabel Reviewed-by: Laurent Pinchart Reviewed-by: Daniel Vetter --- drivers/gpu/drm/drm_simple_kms_helper.c | 14 ++++++++++++-- include/drm/drm_simple_kms_helper.h | 24 ++++++++++++++++++++++++ 2 files changed, 36 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_simple_kms_helper.c b/drivers/gpu/drm/drm_simple_kms_helper.c index 743e57c1b44f..6ce8f5cd1eb5 100644 --- a/drivers/gpu/drm/drm_simple_kms_helper.c +++ b/drivers/gpu/drm/drm_simple_kms_helper.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -55,8 +56,9 @@ static const struct drm_encoder_funcs drm_simple_encoder_funcs_cleanup = { * stored in the device structure. Free the encoder's memory as part of * the device release function. * - * FIXME: Later improvements to DRM's resource management may allow for - * an automated kfree() of the encoder's memory. + * Note: consider using drmm_simple_encoder_alloc() instead of + * drm_simple_encoder_init() to let the DRM managed resource infrastructure + * take care of cleanup and deallocation. * * Returns: * Zero on success, error code on failure. @@ -71,6 +73,14 @@ int drm_simple_encoder_init(struct drm_device *dev, } EXPORT_SYMBOL(drm_simple_encoder_init); +void *__drmm_simple_encoder_alloc(struct drm_device *dev, size_t size, + size_t offset, int encoder_type) +{ + return __drmm_encoder_alloc(dev, size, offset, NULL, encoder_type, + NULL); +} +EXPORT_SYMBOL(__drmm_simple_encoder_alloc); + static enum drm_mode_status drm_simple_kms_crtc_mode_valid(struct drm_crtc *crtc, const struct drm_display_mode *mode) diff --git a/include/drm/drm_simple_kms_helper.h b/include/drm/drm_simple_kms_helper.h index a026375464ff..e6dbf3161c2f 100644 --- a/include/drm/drm_simple_kms_helper.h +++ b/include/drm/drm_simple_kms_helper.h @@ -185,4 +185,28 @@ int drm_simple_encoder_init(struct drm_device *dev, struct drm_encoder *encoder, int encoder_type); +void *__drmm_simple_encoder_alloc(struct drm_device *dev, size_t size, + size_t offset, int encoder_type); + +/** + * drmm_simple_encoder_alloc - Allocate and initialize an encoder with basic + * functionality. + * @dev: drm device + * @type: the type of the struct which contains struct &drm_encoder + * @member: the name of the &drm_encoder within @type. + * @encoder_type: user visible type of the encoder + * + * Allocates and initializes an encoder that has no further functionality. + * Settings for possible CRTC and clones are left to their initial values. + * Cleanup is automatically handled through registering drm_encoder_cleanup() + * with drmm_add_action(). + * + * Returns: + * Pointer to new encoder, or ERR_PTR on failure. + */ +#define drmm_simple_encoder_alloc(dev, type, member, encoder_type) \ + ((type *)__drmm_simple_encoder_alloc(dev, sizeof(type), \ + offsetof(type, member), \ + encoder_type)) + #endif /* __LINUX_DRM_SIMPLE_KMS_HELPER_H */ -- cgit v1.2.3 From 0a1b813f06f1009d1d44d48888e92e3a59ea0be3 Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Thu, 10 Dec 2020 16:38:30 +0100 Subject: drm/plane: add drmm_universal_plane_alloc() Add an alternative to drm_universal_plane_init() that allocates and initializes a plane and registers drm_plane_cleanup() with drmm_add_action_or_reset(). Signed-off-by: Philipp Zabel Reviewed-by: Laurent Pinchart Reviewed-by: Daniel Vetter --- drivers/gpu/drm/drm_plane.c | 134 ++++++++++++++++++++++++++++++++++---------- include/drm/drm_plane.h | 42 ++++++++++++++ 2 files changed, 147 insertions(+), 29 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_plane.c b/drivers/gpu/drm/drm_plane.c index e6231947f987..8b9471a59919 100644 --- a/drivers/gpu/drm/drm_plane.c +++ b/drivers/gpu/drm/drm_plane.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include "drm_crtc_internal.h" @@ -152,31 +153,16 @@ done: return 0; } -/** - * drm_universal_plane_init - Initialize a new universal plane object - * @dev: DRM device - * @plane: plane object to init - * @possible_crtcs: bitmask of possible CRTCs - * @funcs: callbacks for the new plane - * @formats: array of supported formats (DRM_FORMAT\_\*) - * @format_count: number of elements in @formats - * @format_modifiers: array of struct drm_format modifiers terminated by - * DRM_FORMAT_MOD_INVALID - * @type: type of plane (overlay, primary, cursor) - * @name: printf style format string for the plane name, or NULL for default name - * - * Initializes a plane object of type @type. - * - * Returns: - * Zero on success, error code on failure. - */ -int drm_universal_plane_init(struct drm_device *dev, struct drm_plane *plane, - uint32_t possible_crtcs, - const struct drm_plane_funcs *funcs, - const uint32_t *formats, unsigned int format_count, - const uint64_t *format_modifiers, - enum drm_plane_type type, - const char *name, ...) +__printf(9, 0) +static int __drm_universal_plane_init(struct drm_device *dev, + struct drm_plane *plane, + uint32_t possible_crtcs, + const struct drm_plane_funcs *funcs, + const uint32_t *formats, + unsigned int format_count, + const uint64_t *format_modifiers, + enum drm_plane_type type, + const char *name, va_list ap) { struct drm_mode_config *config = &dev->mode_config; unsigned int format_modifier_count = 0; @@ -237,11 +223,7 @@ int drm_universal_plane_init(struct drm_device *dev, struct drm_plane *plane, } if (name) { - va_list ap; - - va_start(ap, name); plane->name = kvasprintf(GFP_KERNEL, name, ap); - va_end(ap); } else { plane->name = kasprintf(GFP_KERNEL, "plane-%d", drm_num_planes(dev)); @@ -286,8 +268,102 @@ int drm_universal_plane_init(struct drm_device *dev, struct drm_plane *plane, return 0; } + +/** + * drm_universal_plane_init - Initialize a new universal plane object + * @dev: DRM device + * @plane: plane object to init + * @possible_crtcs: bitmask of possible CRTCs + * @funcs: callbacks for the new plane + * @formats: array of supported formats (DRM_FORMAT\_\*) + * @format_count: number of elements in @formats + * @format_modifiers: array of struct drm_format modifiers terminated by + * DRM_FORMAT_MOD_INVALID + * @type: type of plane (overlay, primary, cursor) + * @name: printf style format string for the plane name, or NULL for default name + * + * Initializes a plane object of type @type. The &drm_plane_funcs.destroy hook + * should call drm_plane_cleanup() and kfree() the plane structure. The plane + * structure should not be allocated with devm_kzalloc(). + * + * Note: consider using drmm_universal_plane_alloc() instead of + * drm_universal_plane_init() to let the DRM managed resource infrastructure + * take care of cleanup and deallocation. + * + * Returns: + * Zero on success, error code on failure. + */ +int drm_universal_plane_init(struct drm_device *dev, struct drm_plane *plane, + uint32_t possible_crtcs, + const struct drm_plane_funcs *funcs, + const uint32_t *formats, unsigned int format_count, + const uint64_t *format_modifiers, + enum drm_plane_type type, + const char *name, ...) +{ + va_list ap; + int ret; + + WARN_ON(!funcs->destroy); + + va_start(ap, name); + ret = __drm_universal_plane_init(dev, plane, possible_crtcs, funcs, + formats, format_count, format_modifiers, + type, name, ap); + va_end(ap); + return ret; +} EXPORT_SYMBOL(drm_universal_plane_init); +static void drmm_universal_plane_alloc_release(struct drm_device *dev, void *ptr) +{ + struct drm_plane *plane = ptr; + + if (WARN_ON(!plane->dev)) + return; + + drm_plane_cleanup(plane); +} + +void *__drmm_universal_plane_alloc(struct drm_device *dev, size_t size, + size_t offset, uint32_t possible_crtcs, + const struct drm_plane_funcs *funcs, + const uint32_t *formats, unsigned int format_count, + const uint64_t *format_modifiers, + enum drm_plane_type type, + const char *name, ...) +{ + void *container; + struct drm_plane *plane; + va_list ap; + int ret; + + if (WARN_ON(!funcs || funcs->destroy)) + return ERR_PTR(-EINVAL); + + container = drmm_kzalloc(dev, size, GFP_KERNEL); + if (!container) + return ERR_PTR(-ENOMEM); + + plane = container + offset; + + va_start(ap, name); + ret = __drm_universal_plane_init(dev, plane, possible_crtcs, funcs, + formats, format_count, format_modifiers, + type, name, ap); + va_end(ap); + if (ret) + return ERR_PTR(ret); + + ret = drmm_add_action_or_reset(dev, drmm_universal_plane_alloc_release, + plane); + if (ret) + return ERR_PTR(ret); + + return container; +} +EXPORT_SYMBOL(__drmm_universal_plane_alloc); + int drm_plane_register_all(struct drm_device *dev) { unsigned int num_planes = 0; diff --git a/include/drm/drm_plane.h b/include/drm/drm_plane.h index 1d82b264e5e4..8ef06ee1c8eb 100644 --- a/include/drm/drm_plane.h +++ b/include/drm/drm_plane.h @@ -764,6 +764,48 @@ int drm_plane_init(struct drm_device *dev, bool is_primary); void drm_plane_cleanup(struct drm_plane *plane); +__printf(10, 11) +void *__drmm_universal_plane_alloc(struct drm_device *dev, + size_t size, size_t offset, + uint32_t possible_crtcs, + const struct drm_plane_funcs *funcs, + const uint32_t *formats, + unsigned int format_count, + const uint64_t *format_modifiers, + enum drm_plane_type plane_type, + const char *name, ...); + +/** + * drmm_universal_plane_alloc - Allocate and initialize an universal plane object + * @dev: DRM device + * @type: the type of the struct which contains struct &drm_plane + * @member: the name of the &drm_plane within @type + * @possible_crtcs: bitmask of possible CRTCs + * @funcs: callbacks for the new plane + * @formats: array of supported formats (DRM_FORMAT\_\*) + * @format_count: number of elements in @formats + * @format_modifiers: array of struct drm_format modifiers terminated by + * DRM_FORMAT_MOD_INVALID + * @plane_type: type of plane (overlay, primary, cursor) + * @name: printf style format string for the plane name, or NULL for default name + * + * Allocates and initializes a plane object of type @type. Cleanup is + * automatically handled through registering drm_plane_cleanup() with + * drmm_add_action(). + * + * The @drm_plane_funcs.destroy hook must be NULL. + * + * Returns: + * Pointer to new plane, or ERR_PTR on failure. + */ +#define drmm_universal_plane_alloc(dev, type, member, possible_crtcs, funcs, formats, \ + format_count, format_modifiers, plane_type, name, ...) \ + ((type *)__drmm_universal_plane_alloc(dev, sizeof(type), \ + offsetof(type, member), \ + possible_crtcs, funcs, formats, \ + format_count, format_modifiers, \ + plane_type, name, ##__VA_ARGS__)) + /** * drm_plane_index - find the index of a registered plane * @plane: plane to find index for -- cgit v1.2.3 From 9dbb70fd663770418daab07590f4f534eb7a4931 Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Thu, 10 Dec 2020 16:38:31 +0100 Subject: drm/crtc: add drmm_crtc_alloc_with_planes() Add an alternative to drm_crtc_init_with_planes() that allocates and initializes a crtc and registers drm_crtc_cleanup() with drmm_add_action_or_reset(). Signed-off-by: Philipp Zabel Reviewed-by: Laurent Pinchart Reviewed-by: Daniel Vetter --- drivers/gpu/drm/drm_crtc.c | 125 +++++++++++++++++++++++++++++++++++---------- include/drm/drm_crtc.h | 33 ++++++++++++ 2 files changed, 130 insertions(+), 28 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c index 74090fc3aa55..7e02555009ff 100644 --- a/drivers/gpu/drm/drm_crtc.c +++ b/drivers/gpu/drm/drm_crtc.c @@ -38,6 +38,7 @@ #include #include #include +#include #include #include #include @@ -240,30 +241,12 @@ struct dma_fence *drm_crtc_create_fence(struct drm_crtc *crtc) * Nearest Neighbor scaling filter */ -/** - * drm_crtc_init_with_planes - Initialise a new CRTC object with - * specified primary and cursor planes. - * @dev: DRM device - * @crtc: CRTC object to init - * @primary: Primary plane for CRTC - * @cursor: Cursor plane for CRTC - * @funcs: callbacks for the new CRTC - * @name: printf style format string for the CRTC name, or NULL for default name - * - * Inits a new object created as base part of a driver crtc object. Drivers - * should use this function instead of drm_crtc_init(), which is only provided - * for backwards compatibility with drivers which do not yet support universal - * planes). For really simple hardware which has only 1 plane look at - * drm_simple_display_pipe_init() instead. - * - * Returns: - * Zero on success, error code on failure. - */ -int drm_crtc_init_with_planes(struct drm_device *dev, struct drm_crtc *crtc, - struct drm_plane *primary, - struct drm_plane *cursor, - const struct drm_crtc_funcs *funcs, - const char *name, ...) +__printf(6, 0) +static int __drm_crtc_init_with_planes(struct drm_device *dev, struct drm_crtc *crtc, + struct drm_plane *primary, + struct drm_plane *cursor, + const struct drm_crtc_funcs *funcs, + const char *name, va_list ap) { struct drm_mode_config *config = &dev->mode_config; int ret; @@ -291,11 +274,7 @@ int drm_crtc_init_with_planes(struct drm_device *dev, struct drm_crtc *crtc, return ret; if (name) { - va_list ap; - - va_start(ap, name); crtc->name = kvasprintf(GFP_KERNEL, name, ap); - va_end(ap); } else { crtc->name = kasprintf(GFP_KERNEL, "crtc-%d", drm_num_crtcs(dev)); @@ -339,8 +318,98 @@ int drm_crtc_init_with_planes(struct drm_device *dev, struct drm_crtc *crtc, return 0; } + +/** + * drm_crtc_init_with_planes - Initialise a new CRTC object with + * specified primary and cursor planes. + * @dev: DRM device + * @crtc: CRTC object to init + * @primary: Primary plane for CRTC + * @cursor: Cursor plane for CRTC + * @funcs: callbacks for the new CRTC + * @name: printf style format string for the CRTC name, or NULL for default name + * + * Inits a new object created as base part of a driver crtc object. Drivers + * should use this function instead of drm_crtc_init(), which is only provided + * for backwards compatibility with drivers which do not yet support universal + * planes). For really simple hardware which has only 1 plane look at + * drm_simple_display_pipe_init() instead. + * The &drm_crtc_funcs.destroy hook should call drm_crtc_cleanup() and kfree() + * the crtc structure. The crtc structure should not be allocated with + * devm_kzalloc(). + * + * Note: consider using drmm_crtc_alloc_with_planes() instead of + * drm_crtc_init_with_planes() to let the DRM managed resource infrastructure + * take care of cleanup and deallocation. + * + * Returns: + * Zero on success, error code on failure. + */ +int drm_crtc_init_with_planes(struct drm_device *dev, struct drm_crtc *crtc, + struct drm_plane *primary, + struct drm_plane *cursor, + const struct drm_crtc_funcs *funcs, + const char *name, ...) +{ + va_list ap; + int ret; + + WARN_ON(!funcs->destroy); + + va_start(ap, name); + ret = __drm_crtc_init_with_planes(dev, crtc, primary, cursor, funcs, + name, ap); + va_end(ap); + + return ret; +} EXPORT_SYMBOL(drm_crtc_init_with_planes); +static void drmm_crtc_alloc_with_planes_cleanup(struct drm_device *dev, + void *ptr) +{ + struct drm_crtc *crtc = ptr; + + drm_crtc_cleanup(crtc); +} + +void *__drmm_crtc_alloc_with_planes(struct drm_device *dev, + size_t size, size_t offset, + struct drm_plane *primary, + struct drm_plane *cursor, + const struct drm_crtc_funcs *funcs, + const char *name, ...) +{ + void *container; + struct drm_crtc *crtc; + va_list ap; + int ret; + + if (WARN_ON(!funcs || funcs->destroy)) + return ERR_PTR(-EINVAL); + + container = drmm_kzalloc(dev, size, GFP_KERNEL); + if (!container) + return ERR_PTR(-ENOMEM); + + crtc = container + offset; + + va_start(ap, name); + ret = __drm_crtc_init_with_planes(dev, crtc, primary, cursor, funcs, + name, ap); + va_end(ap); + if (ret) + return ERR_PTR(ret); + + ret = drmm_add_action_or_reset(dev, drmm_crtc_alloc_with_planes_cleanup, + crtc); + if (ret) + return ERR_PTR(ret); + + return container; +} +EXPORT_SYMBOL(__drmm_crtc_alloc_with_planes); + /** * drm_crtc_cleanup - Clean up the core crtc usage * @crtc: CRTC to cleanup diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h index 5f43d64d2a07..540e2e43ec93 100644 --- a/include/drm/drm_crtc.h +++ b/include/drm/drm_crtc.h @@ -1223,6 +1223,39 @@ int drm_crtc_init_with_planes(struct drm_device *dev, const char *name, ...); void drm_crtc_cleanup(struct drm_crtc *crtc); +__printf(7, 8) +void *__drmm_crtc_alloc_with_planes(struct drm_device *dev, + size_t size, size_t offset, + struct drm_plane *primary, + struct drm_plane *cursor, + const struct drm_crtc_funcs *funcs, + const char *name, ...); + +/** + * drm_crtc_alloc_with_planes - Allocate and initialize a new CRTC object with + * specified primary and cursor planes. + * @dev: DRM device + * @type: the type of the struct which contains struct &drm_crtc + * @member: the name of the &drm_crtc within @type. + * @primary: Primary plane for CRTC + * @cursor: Cursor plane for CRTC + * @funcs: callbacks for the new CRTC + * @name: printf style format string for the CRTC name, or NULL for default name + * + * Allocates and initializes a new crtc object. Cleanup is automatically + * handled through registering drmm_crtc_cleanup() with drmm_add_action(). + * + * The @drm_crtc_funcs.destroy hook must be NULL. + * + * Returns: + * Pointer to new crtc, or ERR_PTR on failure. + */ +#define drmm_crtc_alloc_with_planes(dev, type, member, primary, cursor, funcs, name, ...) \ + ((type *)__drmm_crtc_alloc_with_planes(dev, sizeof(type), \ + offsetof(type, member), \ + primary, cursor, funcs, \ + name, ##__VA_ARGS__)) + /** * drm_crtc_index - find the index of a registered CRTC * @crtc: CRTC to find index for -- cgit v1.2.3 From b5a8d233a588b3acf2a7a3a8da30f8f68f376626 Mon Sep 17 00:00:00 2001 From: Loic Poulain Date: Mon, 4 Jan 2021 17:14:50 +0100 Subject: bus: mhi: core: Add device hardware reset support The MHI specification allows to perform a hard reset of the device when writing to the SOC_RESET register. It can be used to completely restart the device (e.g. in case of unrecoverable MHI error). This is up to the MHI controller driver to determine when this hard reset should be used, and in case of MHI errors, should be used as a reset of last resort (after standard MHI stack reset). This function is a stateless function, the MHI layer do nothing except triggering the reset by writing into the right register(s), this is up to the caller to ensure right mhi_controller state (e.g. unregister the controller if necessary). Signed-off-by: Loic Poulain Reviewed-by: Manivannan Sadhasivam Signed-off-by: Manivannan Sadhasivam --- drivers/bus/mhi/core/main.c | 13 +++++++++++++ include/linux/mhi.h | 9 +++++++++ 2 files changed, 22 insertions(+) (limited to 'include') diff --git a/drivers/bus/mhi/core/main.c b/drivers/bus/mhi/core/main.c index d34d7e90e38d..9b425402767c 100644 --- a/drivers/bus/mhi/core/main.c +++ b/drivers/bus/mhi/core/main.c @@ -135,6 +135,19 @@ enum mhi_state mhi_get_mhi_state(struct mhi_controller *mhi_cntrl) } EXPORT_SYMBOL_GPL(mhi_get_mhi_state); +void mhi_soc_reset(struct mhi_controller *mhi_cntrl) +{ + if (mhi_cntrl->reset) { + mhi_cntrl->reset(mhi_cntrl); + return; + } + + /* Generic MHI SoC reset */ + mhi_write_reg(mhi_cntrl, mhi_cntrl->regs, MHI_SOC_RESET_REQ_OFFSET, + MHI_SOC_RESET_REQ); +} +EXPORT_SYMBOL_GPL(mhi_soc_reset); + int mhi_map_single_no_bb(struct mhi_controller *mhi_cntrl, struct mhi_buf_info *buf_info) { diff --git a/include/linux/mhi.h b/include/linux/mhi.h index 562862ff819c..54afcae1709a 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -347,6 +347,7 @@ struct mhi_controller_config { * @unmap_single: CB function to destroy TRE buffer * @read_reg: Read a MHI register via the physical link (required) * @write_reg: Write a MHI register via the physical link (required) + * @reset: Controller specific reset function (optional) * @buffer_len: Bounce buffer length * @index: Index of the MHI controller instance * @bounce_buf: Use of bounce buffer @@ -437,6 +438,7 @@ struct mhi_controller { u32 *out); void (*write_reg)(struct mhi_controller *mhi_cntrl, void __iomem *addr, u32 val); + void (*reset)(struct mhi_controller *mhi_cntrl); size_t buffer_len; int index; @@ -672,6 +674,13 @@ enum mhi_ee_type mhi_get_exec_env(struct mhi_controller *mhi_cntrl); */ enum mhi_state mhi_get_mhi_state(struct mhi_controller *mhi_cntrl); +/** + * mhi_soc_reset - Trigger a device reset. This can be used as a last resort + * to reset and recover a device. + * @mhi_cntrl: MHI controller + */ +void mhi_soc_reset(struct mhi_controller *mhi_cntrl); + /** * mhi_device_get - Disable device low power mode * @mhi_dev: Device associated with the channel -- cgit v1.2.3 From 14e43bf435612639cab01541fce7cc41bf7e370b Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Tue, 22 Sep 2020 09:44:18 -0700 Subject: vfs: don't unnecessarily clone write access for writable fds There's no need for mnt_want_write_file() to increment mnt_writers when the file is already open for writing, provided that mnt_drop_write_file() is changed to conditionally decrement it. We seem to have ended up in the current situation because mnt_want_write_file() used to be paired with mnt_drop_write(), due to mnt_drop_write_file() not having been added yet. So originally mnt_want_write_file() had to always increment mnt_writers. But later mnt_drop_write_file() was added, and all callers of mnt_want_write_file() were paired with it. This makes the compatibility between mnt_want_write_file() and mnt_drop_write() no longer necessary. Therefore, make __mnt_want_write_file() and __mnt_drop_write_file() skip incrementing mnt_writers on files already open for writing. This removes the only caller of mnt_clone_write(), so remove that too. Signed-off-by: Eric Biggers Signed-off-by: Al Viro --- Documentation/filesystems/porting.rst | 7 +++++ fs/namespace.c | 53 +++++++++++++---------------------- include/linux/mount.h | 1 - 3 files changed, 27 insertions(+), 34 deletions(-) (limited to 'include') diff --git a/Documentation/filesystems/porting.rst b/Documentation/filesystems/porting.rst index 867036aa90b8..6a6d3e673b48 100644 --- a/Documentation/filesystems/porting.rst +++ b/Documentation/filesystems/porting.rst @@ -865,3 +865,10 @@ no matter what. Everything is handled by the caller. clone_private_mount() returns a longterm mount now, so the proper destructor of its result is kern_unmount() or kern_unmount_array(). + +--- + +**mandatory** + +mnt_want_write_file() can now only be paired with mnt_drop_write_file(), +whereas previously it could be paired with mnt_drop_write() as well. diff --git a/fs/namespace.c b/fs/namespace.c index d2db7dfe232b..9f2d94e0f3e0 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -359,51 +359,37 @@ int mnt_want_write(struct vfsmount *m) } EXPORT_SYMBOL_GPL(mnt_want_write); -/** - * mnt_clone_write - get write access to a mount - * @mnt: the mount on which to take a write - * - * This is effectively like mnt_want_write, except - * it must only be used to take an extra write reference - * on a mountpoint that we already know has a write reference - * on it. This allows some optimisation. - * - * After finished, mnt_drop_write must be called as usual to - * drop the reference. - */ -int mnt_clone_write(struct vfsmount *mnt) -{ - /* superblock may be r/o */ - if (__mnt_is_readonly(mnt)) - return -EROFS; - preempt_disable(); - mnt_inc_writers(real_mount(mnt)); - preempt_enable(); - return 0; -} -EXPORT_SYMBOL_GPL(mnt_clone_write); - /** * __mnt_want_write_file - get write access to a file's mount * @file: the file who's mount on which to take a write * - * This is like __mnt_want_write, but it takes a file and can - * do some optimisations if the file is open for write already + * This is like __mnt_want_write, but if the file is already open for writing it + * skips incrementing mnt_writers (since the open file already has a reference) + * and instead only does the check for emergency r/o remounts. This must be + * paired with __mnt_drop_write_file. */ int __mnt_want_write_file(struct file *file) { - if (!(file->f_mode & FMODE_WRITER)) - return __mnt_want_write(file->f_path.mnt); - else - return mnt_clone_write(file->f_path.mnt); + if (file->f_mode & FMODE_WRITER) { + /* + * Superblock may have become readonly while there are still + * writable fd's, e.g. due to a fs error with errors=remount-ro + */ + if (__mnt_is_readonly(file->f_path.mnt)) + return -EROFS; + return 0; + } + return __mnt_want_write(file->f_path.mnt); } /** * mnt_want_write_file - get write access to a file's mount * @file: the file who's mount on which to take a write * - * This is like mnt_want_write, but it takes a file and can - * do some optimisations if the file is open for write already + * This is like mnt_want_write, but if the file is already open for writing it + * skips incrementing mnt_writers (since the open file already has a reference) + * and instead only does the freeze protection and the check for emergency r/o + * remounts. This must be paired with mnt_drop_write_file. */ int mnt_want_write_file(struct file *file) { @@ -449,7 +435,8 @@ EXPORT_SYMBOL_GPL(mnt_drop_write); void __mnt_drop_write_file(struct file *file) { - __mnt_drop_write(file->f_path.mnt); + if (!(file->f_mode & FMODE_WRITER)) + __mnt_drop_write(file->f_path.mnt); } void mnt_drop_write_file(struct file *file) diff --git a/include/linux/mount.h b/include/linux/mount.h index aaf343b38671..b43191fe6af7 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -79,7 +79,6 @@ struct path; extern int mnt_want_write(struct vfsmount *mnt); extern int mnt_want_write_file(struct file *file); -extern int mnt_clone_write(struct vfsmount *mnt); extern void mnt_drop_write(struct vfsmount *mnt); extern void mnt_drop_write_file(struct file *file); extern void mntput(struct vfsmount *mnt); -- cgit v1.2.3 From de332bf242787dc39b0cf4493dc989d6d9fdce93 Mon Sep 17 00:00:00 2001 From: Liu Ying Date: Wed, 2 Dec 2020 13:33:37 +0800 Subject: clk: imx: clk-imx8qxp: Add SCU clocks support for DC0 bypass clocks This patch adds SCU clocks support for i.MX8qxp DC0 subsystem bypass clocks. Cc: Michael Turquette Cc: Stephen Boyd Cc: Shawn Guo Cc: Sascha Hauer Cc: Pengutronix Kernel Team Cc: Fabio Estevam Cc: NXP Linux Team Cc: Dong Aisheng Cc: Rob Herring Signed-off-by: Liu Ying Signed-off-by: Shawn Guo --- drivers/clk/imx/clk-imx8qxp.c | 2 ++ include/dt-bindings/clock/imx8-clock.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include') diff --git a/drivers/clk/imx/clk-imx8qxp.c b/drivers/clk/imx/clk-imx8qxp.c index b48643e42e8a..af6a5454ad49 100644 --- a/drivers/clk/imx/clk-imx8qxp.c +++ b/drivers/clk/imx/clk-imx8qxp.c @@ -119,6 +119,8 @@ static int imx8qxp_clk_probe(struct platform_device *pdev) clks[IMX_DC0_DISP1_CLK] = imx_clk_scu("dc0_disp1_clk", IMX_SC_R_DC_0, IMX_SC_PM_CLK_MISC1, clk_cells); clks[IMX_DC0_PLL0_CLK] = imx_clk_scu("dc0_pll0_clk", IMX_SC_R_DC_0_PLL_0, IMX_SC_PM_CLK_PLL, clk_cells); clks[IMX_DC0_PLL1_CLK] = imx_clk_scu("dc0_pll1_clk", IMX_SC_R_DC_0_PLL_1, IMX_SC_PM_CLK_PLL, clk_cells); + clks[IMX_DC0_BYPASS0_CLK] = imx_clk_scu("dc0_bypass0_clk", IMX_SC_R_DC_0_VIDEO0, IMX_SC_PM_CLK_BYPASS, clk_cells); + clks[IMX_DC0_BYPASS1_CLK] = imx_clk_scu("dc0_bypass1_clk", IMX_SC_R_DC_0_VIDEO1, IMX_SC_PM_CLK_BYPASS, clk_cells); /* MIPI-LVDS SS */ clks[IMX_MIPI0_I2C0_CLK] = imx_clk_scu("mipi0_i2c0_clk", IMX_SC_R_MIPI_0_I2C_0, IMX_SC_PM_CLK_MISC2, clk_cells); diff --git a/include/dt-bindings/clock/imx8-clock.h b/include/dt-bindings/clock/imx8-clock.h index 673a8c662340..82b1fc8d1ee0 100644 --- a/include/dt-bindings/clock/imx8-clock.h +++ b/include/dt-bindings/clock/imx8-clock.h @@ -64,6 +64,8 @@ #define IMX_DC0_PLL1_CLK 81 #define IMX_DC0_DISP0_CLK 82 #define IMX_DC0_DISP1_CLK 83 +#define IMX_DC0_BYPASS0_CLK 84 +#define IMX_DC0_BYPASS1_CLK 85 /* MIPI-LVDS SS */ #define IMX_MIPI_IPG_CLK 90 -- cgit v1.2.3 From 2551952e802cab4c01081c1c880643795af2afb8 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Fri, 14 Jun 2013 02:55:25 +0200 Subject: drm: Add default modes for connectors in unknown state The DRM CRTC helpers add default modes to connectors in the connected state if no mode can be retrieved from the connector. This behaviour is useful for VGA or DVI outputs that have no connected DDC bus. However, in such cases, the status of the output usually can't be retrieved and is reported as connector_status_unknown. Extend the addition of default modes to connectors in an unknown state to support outputs that can retrieve neither the modes nor the connection status. Signed-off-by: Laurent Pinchart Acked-by: Sam Ravnborg Reviewed-by: Daniel Vetter --- drivers/gpu/drm/drm_probe_helper.c | 3 ++- include/drm/drm_modeset_helper_vtables.h | 8 +++++++- 2 files changed, 9 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c index d6017726cc2a..ad59a51eab6d 100644 --- a/drivers/gpu/drm/drm_probe_helper.c +++ b/drivers/gpu/drm/drm_probe_helper.c @@ -515,7 +515,8 @@ retry: if (count == 0 && connector->status == connector_status_connected) count = drm_add_override_edid_modes(connector); - if (count == 0 && connector->status == connector_status_connected) + if (count == 0 && (connector->status == connector_status_connected || + connector->status == connector_status_unknown)) count = drm_add_modes_noedid(connector, 1024, 768); count += drm_helper_probe_add_cmdline_mode(connector); if (count == 0) diff --git a/include/drm/drm_modeset_helper_vtables.h b/include/drm/drm_modeset_helper_vtables.h index 16ff3fa148f5..0d184d526a22 100644 --- a/include/drm/drm_modeset_helper_vtables.h +++ b/include/drm/drm_modeset_helper_vtables.h @@ -866,13 +866,19 @@ struct drm_connector_helper_funcs { * The usual way to implement this is to cache the EDID retrieved in the * probe callback somewhere in the driver-private connector structure. * In this function drivers then parse the modes in the EDID and add - * them by calling drm_add_edid_modes(). But connectors that driver a + * them by calling drm_add_edid_modes(). But connectors that drive a * fixed panel can also manually add specific modes using * drm_mode_probed_add(). Drivers which manually add modes should also * make sure that the &drm_connector.display_info, * &drm_connector.width_mm and &drm_connector.height_mm fields are * filled in. * + * Note that the caller function will automatically add standard VESA + * DMT modes up to 1024x768 if the .get_modes() helper operation returns + * no mode and if the connector status is connector_status_connected or + * connector_status_unknown. There is no need to call + * drm_add_modes_noedid() manually in that case. + * * Virtual drivers that just want some standard VESA mode with a given * resolution can call drm_add_modes_noedid(), and mark the preferred * one using drm_set_preferred_mode(). -- cgit v1.2.3 From 47f10854ca8958c5bf31c3a3fcd8e2c73ccc9925 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Fri, 15 Sep 2017 01:12:02 +0300 Subject: drm: Don't export the drm_gem_dumb_destroy() function The drm_gem_dumb_destroy() isn't used in drivers, don't export it. Signed-off-by: Laurent Pinchart Reviewed-by: Daniel Vetter --- drivers/gpu/drm/drm_dumb_buffers.c | 8 +++++--- drivers/gpu/drm/drm_gem.c | 12 +----------- drivers/gpu/drm/drm_internal.h | 3 +++ include/drm/drm_gem.h | 3 --- 4 files changed, 9 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_dumb_buffers.c b/drivers/gpu/drm/drm_dumb_buffers.c index d18a740fe0f1..ad17fa21cebb 100644 --- a/drivers/gpu/drm/drm_dumb_buffers.c +++ b/drivers/gpu/drm/drm_dumb_buffers.c @@ -29,6 +29,7 @@ #include #include "drm_crtc_internal.h" +#include "drm_internal.h" /** * DOC: overview @@ -46,9 +47,10 @@ * KMS frame buffers. * * To support dumb objects drivers must implement the &drm_driver.dumb_create - * operation. &drm_driver.dumb_destroy defaults to drm_gem_dumb_destroy() if - * not set and &drm_driver.dumb_map_offset defaults to - * drm_gem_dumb_map_offset(). See the callbacks for further details. + * and &drm_driver.dumb_map_offset operations (the latter defaults to + * drm_gem_dumb_map_offset() if not set). Drivers that don't use GEM handles + * additionally need to implement the &drm_driver.dumb_destroy operation. See + * the callbacks for further details. * * Note that dumb objects may not be used for gpu acceleration, as has been * attempted on some ARM embedded platforms. Such drivers really must have diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index 92f89cee213e..34b2f111c01c 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -335,22 +335,12 @@ out: } EXPORT_SYMBOL_GPL(drm_gem_dumb_map_offset); -/** - * drm_gem_dumb_destroy - dumb fb callback helper for gem based drivers - * @file: drm file-private structure to remove the dumb handle from - * @dev: corresponding drm_device - * @handle: the dumb handle to remove - * - * This implements the &drm_driver.dumb_destroy kms driver callback for drivers - * which use gem to manage their backing storage. - */ int drm_gem_dumb_destroy(struct drm_file *file, struct drm_device *dev, - uint32_t handle) + u32 handle) { return drm_gem_handle_delete(file, handle); } -EXPORT_SYMBOL(drm_gem_dumb_destroy); /** * drm_gem_handle_create_tail - internal functions to create a handle diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h index 81d386b5b92a..fad2249ee67b 100644 --- a/drivers/gpu/drm/drm_internal.h +++ b/drivers/gpu/drm/drm_internal.h @@ -191,6 +191,9 @@ void drm_gem_unpin(struct drm_gem_object *obj); int drm_gem_vmap(struct drm_gem_object *obj, struct dma_buf_map *map); void drm_gem_vunmap(struct drm_gem_object *obj, struct dma_buf_map *map); +int drm_gem_dumb_destroy(struct drm_file *file, struct drm_device *dev, + u32 handle); + /* drm_debugfs.c drm_debugfs_crc.c */ #if defined(CONFIG_DEBUG_FS) int drm_debugfs_init(struct drm_minor *minor, int minor_id, diff --git a/include/drm/drm_gem.h b/include/drm/drm_gem.h index 5e6daa1c982f..240049566592 100644 --- a/include/drm/drm_gem.h +++ b/include/drm/drm_gem.h @@ -416,8 +416,5 @@ int drm_gem_fence_array_add_implicit(struct xarray *fence_array, bool write); int drm_gem_dumb_map_offset(struct drm_file *file, struct drm_device *dev, u32 handle, u64 *offset); -int drm_gem_dumb_destroy(struct drm_file *file, - struct drm_device *dev, - uint32_t handle); #endif /* __DRM_GEM_H__ */ -- cgit v1.2.3 From 8dbe1b4a15977f31f6b3b79e577ad96a795c9827 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Thu, 20 Feb 2020 17:16:28 +0200 Subject: drm: Move legacy device list out of drm_driver The drm_driver structure contains a single field (legacy_dev_list) that is modified by the DRM core, used to store a linked list of legacy DRM devices associated with the driver. In order to make the structure const, move the field out to a global variable. This requires locking access to the global where the local field didn't require serialization, but this only affects legacy drivers, and isn't in any hot path. While at it, compile-out the legacy_dev_list field when DRM_LEGACY isn't defined. Signed-off-by: Laurent Pinchart Reviewed-by: Daniel Vetter Reviewed-by: Emil Velikov --- drivers/gpu/drm/drm_pci.c | 25 +++++++++++++++++-------- include/drm/drm_device.h | 10 +++------- include/drm/drm_drv.h | 2 -- 3 files changed, 20 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_pci.c b/drivers/gpu/drm/drm_pci.c index 6dba4b8ce4fe..dfb138aaccba 100644 --- a/drivers/gpu/drm/drm_pci.c +++ b/drivers/gpu/drm/drm_pci.c @@ -24,6 +24,8 @@ #include #include +#include +#include #include #include @@ -36,6 +38,9 @@ #include "drm_legacy.h" #ifdef CONFIG_DRM_LEGACY +/* List of devices hanging off drivers with stealth attach. */ +static LIST_HEAD(legacy_dev_list); +static DEFINE_MUTEX(legacy_dev_list_lock); /** * drm_pci_alloc - Allocate a PCI consistent memory block, for DMA. @@ -225,10 +230,11 @@ static int drm_get_pci_dev(struct pci_dev *pdev, if (ret) goto err_agp; - /* No locking needed since shadow-attach is single-threaded since it may - * only be called from the per-driver module init hook. */ - if (drm_core_check_feature(dev, DRIVER_LEGACY)) - list_add_tail(&dev->legacy_dev_list, &driver->legacy_dev_list); + if (drm_core_check_feature(dev, DRIVER_LEGACY)) { + mutex_lock(&legacy_dev_list_lock); + list_add_tail(&dev->legacy_dev_list, &legacy_dev_list); + mutex_unlock(&legacy_dev_list_lock); + } return 0; @@ -261,7 +267,6 @@ int drm_legacy_pci_init(struct drm_driver *driver, struct pci_driver *pdriver) return -EINVAL; /* If not using KMS, fall back to stealth mode manual scanning. */ - INIT_LIST_HEAD(&driver->legacy_dev_list); for (i = 0; pdriver->id_table[i].vendor != 0; i++) { pid = &pdriver->id_table[i]; @@ -304,11 +309,15 @@ void drm_legacy_pci_exit(struct drm_driver *driver, struct pci_driver *pdriver) if (!(driver->driver_features & DRIVER_LEGACY)) { WARN_ON(1); } else { - list_for_each_entry_safe(dev, tmp, &driver->legacy_dev_list, + mutex_lock(&legacy_dev_list_lock); + list_for_each_entry_safe(dev, tmp, &legacy_dev_list, legacy_dev_list) { - list_del(&dev->legacy_dev_list); - drm_put_dev(dev); + if (dev->driver == driver) { + list_del(&dev->legacy_dev_list); + drm_put_dev(dev); + } } + mutex_unlock(&legacy_dev_list_lock); } DRM_INFO("Module unloaded\n"); } diff --git a/include/drm/drm_device.h b/include/drm/drm_device.h index 283a93ce4617..bd5abe7cd48f 100644 --- a/include/drm/drm_device.h +++ b/include/drm/drm_device.h @@ -51,13 +51,6 @@ enum switch_power_state { * may contain multiple heads. */ struct drm_device { - /** - * @legacy_dev_list: - * - * List of devices per driver for stealth attach cleanup - */ - struct list_head legacy_dev_list; - /** @if_version: Highest interface version set */ int if_version; @@ -336,6 +329,9 @@ struct drm_device { /* Everything below here is for legacy driver, never use! */ /* private: */ #if IS_ENABLED(CONFIG_DRM_LEGACY) + /* List of devices per driver for stealth attach cleanup */ + struct list_head legacy_dev_list; + /* Context handle management - linked list of context handles */ struct list_head ctxlist; diff --git a/include/drm/drm_drv.h b/include/drm/drm_drv.h index 02787319246a..827838e0a97e 100644 --- a/include/drm/drm_drv.h +++ b/include/drm/drm_drv.h @@ -499,8 +499,6 @@ struct drm_driver { /* Everything below here is for legacy driver, never use! */ /* private: */ - /* List of devices hanging off this driver with stealth attach. */ - struct list_head legacy_dev_list; int (*firstopen) (struct drm_device *); void (*preclose) (struct drm_device *, struct drm_file *file_priv); int (*dma_ioctl) (struct drm_device *dev, void *data, struct drm_file *file_priv); -- cgit v1.2.3 From b1dda997a8a98fcb98189e5f4ee3108bc3da3d21 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Fri, 21 Feb 2020 00:19:22 +0200 Subject: drm: Use a const drm_driver for legacy PCI devices Now that the legacy PCI support code doesn't need to write to the drm_driver structure, it can be treated as const through the whole DRM core, unconditionally. This allows declaring the structure as const in all drivers, removing one possible attack vector. Signed-off-by: Laurent Pinchart Reviewed-by: Daniel Vetter --- drivers/gpu/drm/drm_drv.c | 4 ---- drivers/gpu/drm/drm_pci.c | 8 +++++--- include/drm/drm_device.h | 4 ---- include/drm/drm_legacy.h | 10 ++++++---- 4 files changed, 11 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c index 734303802bc3..3f57e880685e 100644 --- a/drivers/gpu/drm/drm_drv.c +++ b/drivers/gpu/drm/drm_drv.c @@ -589,11 +589,7 @@ static int drm_dev_init(struct drm_device *dev, kref_init(&dev->ref); dev->dev = get_device(parent); -#ifdef CONFIG_DRM_LEGACY - dev->driver = (struct drm_driver *)driver; -#else dev->driver = driver; -#endif INIT_LIST_HEAD(&dev->managed.resources); spin_lock_init(&dev->managed.lock); diff --git a/drivers/gpu/drm/drm_pci.c b/drivers/gpu/drm/drm_pci.c index dfb138aaccba..5370e6b492fd 100644 --- a/drivers/gpu/drm/drm_pci.c +++ b/drivers/gpu/drm/drm_pci.c @@ -201,7 +201,7 @@ static void drm_pci_agp_init(struct drm_device *dev) static int drm_get_pci_dev(struct pci_dev *pdev, const struct pci_device_id *ent, - struct drm_driver *driver) + const struct drm_driver *driver) { struct drm_device *dev; int ret; @@ -255,7 +255,8 @@ err_free: * * Return: 0 on success or a negative error code on failure. */ -int drm_legacy_pci_init(struct drm_driver *driver, struct pci_driver *pdriver) +int drm_legacy_pci_init(const struct drm_driver *driver, + struct pci_driver *pdriver) { struct pci_dev *pdev = NULL; const struct pci_device_id *pid; @@ -300,7 +301,8 @@ EXPORT_SYMBOL(drm_legacy_pci_init); * Unregister a DRM driver shadow-attached through drm_legacy_pci_init(). This * is deprecated and only used by dri1 drivers. */ -void drm_legacy_pci_exit(struct drm_driver *driver, struct pci_driver *pdriver) +void drm_legacy_pci_exit(const struct drm_driver *driver, + struct pci_driver *pdriver) { struct drm_device *dev, *tmp; diff --git a/include/drm/drm_device.h b/include/drm/drm_device.h index bd5abe7cd48f..939904ae88fc 100644 --- a/include/drm/drm_device.h +++ b/include/drm/drm_device.h @@ -76,11 +76,7 @@ struct drm_device { } managed; /** @driver: DRM driver managing the device */ -#ifdef CONFIG_DRM_LEGACY - struct drm_driver *driver; -#else const struct drm_driver *driver; -#endif /** * @dev_private: diff --git a/include/drm/drm_legacy.h b/include/drm/drm_legacy.h index 852d7451eeb1..8ed04e9be997 100644 --- a/include/drm/drm_legacy.h +++ b/include/drm/drm_legacy.h @@ -198,8 +198,10 @@ struct drm_dma_handle *drm_pci_alloc(struct drm_device *dev, size_t size, size_t align); void drm_pci_free(struct drm_device *dev, struct drm_dma_handle *dmah); -int drm_legacy_pci_init(struct drm_driver *driver, struct pci_driver *pdriver); -void drm_legacy_pci_exit(struct drm_driver *driver, struct pci_driver *pdriver); +int drm_legacy_pci_init(const struct drm_driver *driver, + struct pci_driver *pdriver); +void drm_legacy_pci_exit(const struct drm_driver *driver, + struct pci_driver *pdriver); #else @@ -214,13 +216,13 @@ static inline void drm_pci_free(struct drm_device *dev, { } -static inline int drm_legacy_pci_init(struct drm_driver *driver, +static inline int drm_legacy_pci_init(const struct drm_driver *driver, struct pci_driver *pdriver) { return -EINVAL; } -static inline void drm_legacy_pci_exit(struct drm_driver *driver, +static inline void drm_legacy_pci_exit(const struct drm_driver *driver, struct pci_driver *pdriver) { } -- cgit v1.2.3 From 4ec908d2104026c67e4eb0fee722ed6893622763 Mon Sep 17 00:00:00 2001 From: Jun Nie Date: Fri, 4 Dec 2020 15:53:44 +0800 Subject: dt-bindings: interconnect: Add Qualcomm MSM8939 DT bindings The Qualcomm MSM8939 platform has several bus fabrics that could be controlled and tuned dynamically according to the bandwidth demand. Signed-off-by: Jun Nie Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20201204075345.5161-5-jun.nie@linaro.org Signed-off-by: Georgi Djakov --- .../devicetree/bindings/interconnect/qcom,rpm.yaml | 4 + include/dt-bindings/interconnect/qcom,msm8939.h | 105 +++++++++++++++++++++ 2 files changed, 109 insertions(+) create mode 100644 include/dt-bindings/interconnect/qcom,msm8939.h (limited to 'include') diff --git a/Documentation/devicetree/bindings/interconnect/qcom,rpm.yaml b/Documentation/devicetree/bindings/interconnect/qcom,rpm.yaml index d720b68b3ead..983d71fb5399 100644 --- a/Documentation/devicetree/bindings/interconnect/qcom,rpm.yaml +++ b/Documentation/devicetree/bindings/interconnect/qcom,rpm.yaml @@ -23,6 +23,10 @@ properties: - qcom,msm8916-bimc - qcom,msm8916-pcnoc - qcom,msm8916-snoc + - qcom,msm8939-bimc + - qcom,msm8939-pcnoc + - qcom,msm8939-snoc + - qcom,msm8939-snoc-mm - qcom,qcs404-bimc - qcom,qcs404-pcnoc - qcom,qcs404-snoc diff --git a/include/dt-bindings/interconnect/qcom,msm8939.h b/include/dt-bindings/interconnect/qcom,msm8939.h new file mode 100644 index 000000000000..c22369a4b9f5 --- /dev/null +++ b/include/dt-bindings/interconnect/qcom,msm8939.h @@ -0,0 +1,105 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Qualcomm interconnect IDs + * + * Copyright (c) 2020, Linaro Ltd. + * Author: Jun Nie + */ + +#ifndef __DT_BINDINGS_INTERCONNECT_QCOM_MSM8939_H +#define __DT_BINDINGS_INTERCONNECT_QCOM_MSM8939_H + +#define BIMC_SNOC_SLV 0 +#define MASTER_QDSS_BAM 1 +#define MASTER_QDSS_ETR 2 +#define MASTER_SNOC_CFG 3 +#define PCNOC_SNOC_SLV 4 +#define SLAVE_APSS 5 +#define SLAVE_CATS_128 6 +#define SLAVE_OCMEM_64 7 +#define SLAVE_IMEM 8 +#define SLAVE_QDSS_STM 9 +#define SLAVE_SRVC_SNOC 10 +#define SNOC_BIMC_0_MAS 11 +#define SNOC_BIMC_1_MAS 12 +#define SNOC_BIMC_2_MAS 13 +#define SNOC_INT_0 14 +#define SNOC_INT_1 15 +#define SNOC_INT_BIMC 16 +#define SNOC_PCNOC_MAS 17 +#define SNOC_QDSS_INT 18 + +#define MASTER_VIDEO_P0 0 +#define MASTER_JPEG 1 +#define MASTER_VFE 2 +#define MASTER_MDP_PORT0 3 +#define MASTER_MDP_PORT1 4 +#define MASTER_CPP 5 +#define SNOC_MM_INT_0 6 +#define SNOC_MM_INT_1 7 +#define SNOC_MM_INT_2 8 + +#define BIMC_SNOC_MAS 0 +#define MASTER_AMPSS_M0 1 +#define MASTER_GRAPHICS_3D 2 +#define MASTER_TCU0 3 +#define SLAVE_AMPSS_L2 4 +#define SLAVE_EBI_CH0 5 +#define SNOC_BIMC_0_SLV 6 +#define SNOC_BIMC_1_SLV 7 +#define SNOC_BIMC_2_SLV 8 + +#define MASTER_BLSP_1 0 +#define MASTER_DEHR 1 +#define MASTER_LPASS 2 +#define MASTER_CRYPTO_CORE0 3 +#define MASTER_SDCC_1 4 +#define MASTER_SDCC_2 5 +#define MASTER_SPDM 6 +#define MASTER_USB_HS1 7 +#define MASTER_USB_HS2 8 +#define PCNOC_INT_0 9 +#define PCNOC_INT_1 10 +#define PCNOC_MAS_0 11 +#define PCNOC_MAS_1 12 +#define PCNOC_SLV_0 13 +#define PCNOC_SLV_1 14 +#define PCNOC_SLV_2 15 +#define PCNOC_SLV_3 16 +#define PCNOC_SLV_4 17 +#define PCNOC_SLV_8 18 +#define PCNOC_SLV_9 19 +#define PCNOC_SNOC_MAS 20 +#define SLAVE_BIMC_CFG 21 +#define SLAVE_BLSP_1 22 +#define SLAVE_BOOT_ROM 23 +#define SLAVE_CAMERA_CFG 24 +#define SLAVE_CLK_CTL 25 +#define SLAVE_CRYPTO_0_CFG 26 +#define SLAVE_DEHR_CFG 27 +#define SLAVE_DISPLAY_CFG 28 +#define SLAVE_GRAPHICS_3D_CFG 29 +#define SLAVE_IMEM_CFG 30 +#define SLAVE_LPASS 31 +#define SLAVE_MPM 32 +#define SLAVE_MSG_RAM 33 +#define SLAVE_MSS 34 +#define SLAVE_PDM 35 +#define SLAVE_PMIC_ARB 36 +#define SLAVE_PCNOC_CFG 37 +#define SLAVE_PRNG 38 +#define SLAVE_QDSS_CFG 39 +#define SLAVE_RBCPR_CFG 40 +#define SLAVE_SDCC_1 41 +#define SLAVE_SDCC_2 42 +#define SLAVE_SECURITY 43 +#define SLAVE_SNOC_CFG 44 +#define SLAVE_SPDM 45 +#define SLAVE_TCSR 46 +#define SLAVE_TLMM 47 +#define SLAVE_USB_HS1 48 +#define SLAVE_USB_HS2 49 +#define SLAVE_VENUS_CFG 50 +#define SNOC_PCNOC_SLV 51 + +#endif -- cgit v1.2.3 From 877c39acf507d5447fca0459febb6aa04eb5ed7f Mon Sep 17 00:00:00 2001 From: Simon Ser Date: Tue, 22 Dec 2020 14:35:22 +0100 Subject: drm/doc: re-format drm.h file comment Our documentation build system chokes on \file comments: ./include/uapi/drm/drm.h:2: warning: Cannot understand * \file drm.h on line 2 - I thought it was a doc line Remove all of the slash-directives, and demote to a normal comment. Keep the historical information because it predates Git. v3: keep the comment (Daniel) Signed-off-by: Simon Ser Acked-by: Daniel Vetter Cc: Pekka Paalanen Link: https://patchwork.freedesktop.org/patch/msgid/20201222133524.160842-4-contact@emersion.fr --- include/uapi/drm/drm.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h index 5c31aea1f342..a3ee8e01c295 100644 --- a/include/uapi/drm/drm.h +++ b/include/uapi/drm/drm.h @@ -1,11 +1,10 @@ -/** - * \file drm.h +/* * Header for the Direct Rendering Manager * - * \author Rickard E. (Rik) Faith + * Author: Rickard E. (Rik) Faith * - * \par Acknowledgments: - * Dec 1999, Richard Henderson , move to generic \c cmpxchg. + * Acknowledgments: + * Dec 1999, Richard Henderson , move to generic cmpxchg. */ /* -- cgit v1.2.3 From 0e0dc448005583a602c8751b7d4cb9e994dd2314 Mon Sep 17 00:00:00 2001 From: Simon Ser Date: Tue, 22 Dec 2020 14:35:23 +0100 Subject: drm/doc: demote old doc-comments in drm.h Sphinx doesn't like old doc-comments in drm.h and generates warnings like: ./include/uapi/drm/drm.h:87: warning: cannot understand function prototype: 'struct drm_clip_rect ' ./include/uapi/drm/drm.h:97: warning: cannot understand function prototype: 'struct drm_drawable_info ' ./include/uapi/drm/drm.h:105: warning: cannot understand function prototype: 'struct drm_tex_region ' ... Demote these to regular comments, because converting all of them is quite a lot of work (also requires documenting all of the struct fields for instance). Also many of these structures aren't really used by modern user-space. We can easily convert these remaining old comments to Sphinx style on a one-by-one basis. Signed-off-by: Simon Ser Acked-by: Daniel Vetter Cc: Pekka Paalanen Link: https://patchwork.freedesktop.org/patch/msgid/20201222133524.160842-5-contact@emersion.fr --- include/uapi/drm/drm.h | 84 +++++++++++++++++++++++++------------------------- 1 file changed, 42 insertions(+), 42 deletions(-) (limited to 'include') diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h index a3ee8e01c295..0827037c5484 100644 --- a/include/uapi/drm/drm.h +++ b/include/uapi/drm/drm.h @@ -84,7 +84,7 @@ typedef unsigned int drm_context_t; typedef unsigned int drm_drawable_t; typedef unsigned int drm_magic_t; -/** +/* * Cliprect. * * \warning: If you change this structure, make sure you change @@ -100,7 +100,7 @@ struct drm_clip_rect { unsigned short y2; }; -/** +/* * Drawable information. */ struct drm_drawable_info { @@ -108,7 +108,7 @@ struct drm_drawable_info { struct drm_clip_rect *rects; }; -/** +/* * Texture region, */ struct drm_tex_region { @@ -119,7 +119,7 @@ struct drm_tex_region { unsigned int age; }; -/** +/* * Hardware lock. * * The lock structure is a simple cache-line aligned integer. To avoid @@ -131,7 +131,7 @@ struct drm_hw_lock { char padding[60]; /**< Pad to cache line */ }; -/** +/* * DRM_IOCTL_VERSION ioctl argument type. * * \sa drmGetVersion(). @@ -148,7 +148,7 @@ struct drm_version { char __user *desc; /**< User-space buffer to hold desc */ }; -/** +/* * DRM_IOCTL_GET_UNIQUE ioctl argument type. * * \sa drmGetBusid() and drmSetBusId(). @@ -167,7 +167,7 @@ struct drm_block { int unused; }; -/** +/* * DRM_IOCTL_CONTROL ioctl argument type. * * \sa drmCtlInstHandler() and drmCtlUninstHandler(). @@ -182,7 +182,7 @@ struct drm_control { int irq; }; -/** +/* * Type of memory to map. */ enum drm_map_type { @@ -194,7 +194,7 @@ enum drm_map_type { _DRM_CONSISTENT = 5 /**< Consistent memory for PCI DMA */ }; -/** +/* * Memory mapping flags. */ enum drm_map_flags { @@ -213,7 +213,7 @@ struct drm_ctx_priv_map { void *handle; /**< Handle of map */ }; -/** +/* * DRM_IOCTL_GET_MAP, DRM_IOCTL_ADD_MAP and DRM_IOCTL_RM_MAP ioctls * argument type. * @@ -230,7 +230,7 @@ struct drm_map { /* Private data */ }; -/** +/* * DRM_IOCTL_GET_CLIENT ioctl argument type. */ struct drm_client { @@ -262,7 +262,7 @@ enum drm_stat_type { /* Add to the *END* of the list */ }; -/** +/* * DRM_IOCTL_GET_STATS ioctl argument type. */ struct drm_stats { @@ -273,7 +273,7 @@ struct drm_stats { } data[15]; }; -/** +/* * Hardware locking flags. */ enum drm_lock_flags { @@ -288,7 +288,7 @@ enum drm_lock_flags { _DRM_HALT_CUR_QUEUES = 0x20 /**< Halt all current queues */ }; -/** +/* * DRM_IOCTL_LOCK, DRM_IOCTL_UNLOCK and DRM_IOCTL_FINISH ioctl argument type. * * \sa drmGetLock() and drmUnlock(). @@ -298,7 +298,7 @@ struct drm_lock { enum drm_lock_flags flags; }; -/** +/* * DMA flags * * \warning @@ -327,7 +327,7 @@ enum drm_dma_flags { _DRM_DMA_LARGER_OK = 0x40 /**< Larger-than-requested buffers OK */ }; -/** +/* * DRM_IOCTL_ADD_BUFS and DRM_IOCTL_MARK_BUFS ioctl argument type. * * \sa drmAddBufs(). @@ -350,7 +350,7 @@ struct drm_buf_desc { */ }; -/** +/* * DRM_IOCTL_INFO_BUFS ioctl argument type. */ struct drm_buf_info { @@ -358,7 +358,7 @@ struct drm_buf_info { struct drm_buf_desc __user *list; }; -/** +/* * DRM_IOCTL_FREE_BUFS ioctl argument type. */ struct drm_buf_free { @@ -366,7 +366,7 @@ struct drm_buf_free { int __user *list; }; -/** +/* * Buffer information * * \sa drm_buf_map. @@ -378,7 +378,7 @@ struct drm_buf_pub { void __user *address; /**< Address of buffer */ }; -/** +/* * DRM_IOCTL_MAP_BUFS ioctl argument type. */ struct drm_buf_map { @@ -391,7 +391,7 @@ struct drm_buf_map { struct drm_buf_pub __user *list; /**< Buffer information */ }; -/** +/* * DRM_IOCTL_DMA ioctl argument type. * * Indices here refer to the offset into the buffer list in drm_buf_get. @@ -416,7 +416,7 @@ enum drm_ctx_flags { _DRM_CONTEXT_2DONLY = 0x02 }; -/** +/* * DRM_IOCTL_ADD_CTX ioctl argument type. * * \sa drmCreateContext() and drmDestroyContext(). @@ -426,7 +426,7 @@ struct drm_ctx { enum drm_ctx_flags flags; }; -/** +/* * DRM_IOCTL_RES_CTX ioctl argument type. */ struct drm_ctx_res { @@ -434,14 +434,14 @@ struct drm_ctx_res { struct drm_ctx __user *contexts; }; -/** +/* * DRM_IOCTL_ADD_DRAW and DRM_IOCTL_RM_DRAW ioctl argument type. */ struct drm_draw { drm_drawable_t handle; }; -/** +/* * DRM_IOCTL_UPDATE_DRAW ioctl argument type. */ typedef enum { @@ -455,14 +455,14 @@ struct drm_update_draw { unsigned long long data; }; -/** +/* * DRM_IOCTL_GET_MAGIC and DRM_IOCTL_AUTH_MAGIC ioctl argument type. */ struct drm_auth { drm_magic_t magic; }; -/** +/* * DRM_IOCTL_IRQ_BUSID ioctl argument type. * * \sa drmGetInterruptFromBusID(). @@ -504,7 +504,7 @@ struct drm_wait_vblank_reply { long tval_usec; }; -/** +/* * DRM_IOCTL_WAIT_VBLANK ioctl argument type. * * \sa drmWaitVBlank(). @@ -517,7 +517,7 @@ union drm_wait_vblank { #define _DRM_PRE_MODESET 1 #define _DRM_POST_MODESET 2 -/** +/* * DRM_IOCTL_MODESET_CTL ioctl argument type * * \sa drmModesetCtl(). @@ -527,7 +527,7 @@ struct drm_modeset_ctl { __u32 cmd; }; -/** +/* * DRM_IOCTL_AGP_ENABLE ioctl argument type. * * \sa drmAgpEnable(). @@ -536,7 +536,7 @@ struct drm_agp_mode { unsigned long mode; /**< AGP mode */ }; -/** +/* * DRM_IOCTL_AGP_ALLOC and DRM_IOCTL_AGP_FREE ioctls argument type. * * \sa drmAgpAlloc() and drmAgpFree(). @@ -548,7 +548,7 @@ struct drm_agp_buffer { unsigned long physical; /**< Physical used by i810 */ }; -/** +/* * DRM_IOCTL_AGP_BIND and DRM_IOCTL_AGP_UNBIND ioctls argument type. * * \sa drmAgpBind() and drmAgpUnbind(). @@ -558,7 +558,7 @@ struct drm_agp_binding { unsigned long offset; /**< In bytes -- will round to page boundary */ }; -/** +/* * DRM_IOCTL_AGP_INFO ioctl argument type. * * \sa drmAgpVersionMajor(), drmAgpVersionMinor(), drmAgpGetMode(), @@ -579,7 +579,7 @@ struct drm_agp_info { unsigned short id_device; }; -/** +/* * DRM_IOCTL_SG_ALLOC ioctl argument type. */ struct drm_scatter_gather { @@ -587,7 +587,7 @@ struct drm_scatter_gather { unsigned long handle; /**< Used for mapping / unmapping */ }; -/** +/* * DRM_IOCTL_SET_VERSION ioctl argument type. */ struct drm_set_version { @@ -597,14 +597,14 @@ struct drm_set_version { int drm_dd_minor; }; -/** DRM_IOCTL_GEM_CLOSE ioctl argument type */ +/* DRM_IOCTL_GEM_CLOSE ioctl argument type */ struct drm_gem_close { /** Handle of the object to be closed. */ __u32 handle; __u32 pad; }; -/** DRM_IOCTL_GEM_FLINK ioctl argument type */ +/* DRM_IOCTL_GEM_FLINK ioctl argument type */ struct drm_gem_flink { /** Handle for the object being named */ __u32 handle; @@ -613,7 +613,7 @@ struct drm_gem_flink { __u32 name; }; -/** DRM_IOCTL_GEM_OPEN ioctl argument type */ +/* DRM_IOCTL_GEM_OPEN ioctl argument type */ struct drm_gem_open { /** Name of object being opened */ __u32 name; @@ -651,7 +651,7 @@ struct drm_gem_open { #define DRM_CAP_SYNCOBJ 0x13 #define DRM_CAP_SYNCOBJ_TIMELINE 0x14 -/** DRM_IOCTL_GET_CAP ioctl argument type */ +/* DRM_IOCTL_GET_CAP ioctl argument type */ struct drm_get_cap { __u64 capability; __u64 value; @@ -699,7 +699,7 @@ struct drm_get_cap { */ #define DRM_CLIENT_CAP_WRITEBACK_CONNECTORS 5 -/** DRM_IOCTL_SET_CLIENT_CAP ioctl argument type */ +/* DRM_IOCTL_SET_CLIENT_CAP ioctl argument type */ struct drm_set_client_cap { __u64 capability; __u64 value; @@ -951,7 +951,7 @@ extern "C" { #define DRM_IOCTL_MODE_GETFB2 DRM_IOWR(0xCE, struct drm_mode_fb_cmd2) -/** +/* * Device specific ioctls should only be in their respective headers * The device specific ioctl range is from 0x40 to 0x9f. * Generic IOCTLS restart at 0xA0. @@ -962,7 +962,7 @@ extern "C" { #define DRM_COMMAND_BASE 0x40 #define DRM_COMMAND_END 0xA0 -/** +/* * Header for events written back to userspace on the drm fd. The * type defines the type of event, the length specifies the total * length of the event (including the header), and user_data is -- cgit v1.2.3 From 7d8ac172d7f1098acc58023819117f7c26d4b604 Mon Sep 17 00:00:00 2001 From: José Roberto de Souza Date: Mon, 4 Jan 2021 12:56:51 -0800 Subject: drm: Add function to convert rect in 16.16 fixed format to regular format MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Much more clear to read one function call than four lines doing this conversion. v7: - function renamed - calculating width and height before truncate - inlined v10: - renamed parameters from source and destination to src and dst to match sister functions Cc: Ville Syrjälä Cc: dri-devel@lists.freedesktop.org Cc: Gwan-gyeong Mun Reviewed-by: Gwan-gyeong Mun Signed-off-by: José Roberto de Souza Link: https://patchwork.freedesktop.org/patch/msgid/20210104205654.238928-1-jose.souza@intel.com --- include/drm/drm_rect.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/drm/drm_rect.h b/include/drm/drm_rect.h index e7f4d24cdd00..39f2deee709c 100644 --- a/include/drm/drm_rect.h +++ b/include/drm/drm_rect.h @@ -206,6 +206,19 @@ static inline bool drm_rect_equals(const struct drm_rect *r1, r1->y1 == r2->y1 && r1->y2 == r2->y2; } +/** + * drm_rect_fp_to_int - Convert a rect in 16.16 fixed point form to int form. + * @dst: rect to be stored the converted value + * @src: rect in 16.16 fixed point form + */ +static inline void drm_rect_fp_to_int(struct drm_rect *dst, + const struct drm_rect *src) +{ + drm_rect_init(dst, src->x1 >> 16, src->y1 >> 16, + drm_rect_width(src) >> 16, + drm_rect_height(src) >> 16); +} + bool drm_rect_intersect(struct drm_rect *r, const struct drm_rect *clip); bool drm_rect_clip_scaled(struct drm_rect *src, struct drm_rect *dst, const struct drm_rect *clip); -- cgit v1.2.3 From ac7b79fd190b02e7151bc7d2b9da692f537657f3 Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Sat, 19 Dec 2020 20:46:08 -0800 Subject: inotify, memcg: account inotify instances to kmemcg Currently the fs sysctl inotify/max_user_instances is used to limit the number of inotify instances on the system. For systems running multiple workloads, the per-user namespace sysctl max_inotify_instances can be used to further partition inotify instances. However there is no easy way to set a sensible system level max limit on inotify instances and further partition it between the workloads. It is much easier to charge the underlying resource (i.e. memory) behind the inotify instances to the memcg of the workload and let their memory limits limit the number of inotify instances they can create. With inotify instances charged to memcg, the admin can simply set max_user_instances to INT_MAX and let the memcg limits of the jobs limit their inotify instances. Link: https://lore.kernel.org/r/20201220044608.1258123-1-shakeelb@google.com Reviewed-by: Amir Goldstein Signed-off-by: Shakeel Butt Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify_user.c | 2 +- fs/notify/group.c | 25 ++++++++++++++++++++----- fs/notify/inotify/inotify_user.c | 4 ++-- include/linux/fsnotify_backend.h | 1 + 4 files changed, 24 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 3e01d8f2ab90..7e7afc2b62e1 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -976,7 +976,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) f_flags |= O_NONBLOCK; /* fsnotify_alloc_group takes a ref. Dropped in fanotify_release */ - group = fsnotify_alloc_group(&fanotify_fsnotify_ops); + group = fsnotify_alloc_user_group(&fanotify_fsnotify_ops); if (IS_ERR(group)) { free_uid(user); return PTR_ERR(group); diff --git a/fs/notify/group.c b/fs/notify/group.c index a4a4b1c64d32..ffd723ffe46d 100644 --- a/fs/notify/group.c +++ b/fs/notify/group.c @@ -111,14 +111,12 @@ void fsnotify_put_group(struct fsnotify_group *group) } EXPORT_SYMBOL_GPL(fsnotify_put_group); -/* - * Create a new fsnotify_group and hold a reference for the group returned. - */ -struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops) +static struct fsnotify_group *__fsnotify_alloc_group( + const struct fsnotify_ops *ops, gfp_t gfp) { struct fsnotify_group *group; - group = kzalloc(sizeof(struct fsnotify_group), GFP_KERNEL); + group = kzalloc(sizeof(struct fsnotify_group), gfp); if (!group) return ERR_PTR(-ENOMEM); @@ -139,8 +137,25 @@ struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops) return group; } + +/* + * Create a new fsnotify_group and hold a reference for the group returned. + */ +struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops) +{ + return __fsnotify_alloc_group(ops, GFP_KERNEL); +} EXPORT_SYMBOL_GPL(fsnotify_alloc_group); +/* + * Create a new fsnotify_group and hold a reference for the group returned. + */ +struct fsnotify_group *fsnotify_alloc_user_group(const struct fsnotify_ops *ops) +{ + return __fsnotify_alloc_group(ops, GFP_KERNEL_ACCOUNT); +} +EXPORT_SYMBOL_GPL(fsnotify_alloc_user_group); + int fsnotify_fasync(int fd, struct file *file, int on) { struct fsnotify_group *group = file->private_data; diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index 59c177011a0f..266d17e8ecb9 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -632,11 +632,11 @@ static struct fsnotify_group *inotify_new_group(unsigned int max_events) struct fsnotify_group *group; struct inotify_event_info *oevent; - group = fsnotify_alloc_group(&inotify_fsnotify_ops); + group = fsnotify_alloc_user_group(&inotify_fsnotify_ops); if (IS_ERR(group)) return group; - oevent = kmalloc(sizeof(struct inotify_event_info), GFP_KERNEL); + oevent = kmalloc(sizeof(struct inotify_event_info), GFP_KERNEL_ACCOUNT); if (unlikely(!oevent)) { fsnotify_destroy_group(group); return ERR_PTR(-ENOMEM); diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index a2e42d3cd87c..e5409b83e731 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -470,6 +470,7 @@ static inline void fsnotify_update_flags(struct dentry *dentry) /* create a new group */ extern struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops); +extern struct fsnotify_group *fsnotify_alloc_user_group(const struct fsnotify_ops *ops); /* get reference to a group */ extern void fsnotify_get_group(struct fsnotify_group *group); /* drop reference on a group from fsnotify_alloc_group */ -- cgit v1.2.3 From 8527efc59d45d7135460daac36054f2f213ac08a Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Tue, 5 Jan 2021 19:59:05 -0800 Subject: rpmsg: glink: Guard qcom_glink_ssr_notify() with correct config The qcom_glink_ssr_notify() function doesn't relate to the SMEM specific GLINK config, but the common RPMSG_QCOM_GLINK config. Update the guard to properly reflect this. Reviewed-by: Alex Elder Reported-by: kernel test robot Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20210106035905.4153692-1-bjorn.andersson@linaro.org Signed-off-by: Bjorn Andersson --- include/linux/rpmsg/qcom_glink.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/rpmsg/qcom_glink.h b/include/linux/rpmsg/qcom_glink.h index daded9fddf36..22fc3a69b683 100644 --- a/include/linux/rpmsg/qcom_glink.h +++ b/include/linux/rpmsg/qcom_glink.h @@ -7,12 +7,17 @@ struct qcom_glink; +#if IS_ENABLED(CONFIG_RPMSG_QCOM_GLINK) +void qcom_glink_ssr_notify(const char *ssr_name); +#else +static inline void qcom_glink_ssr_notify(const char *ssr_name) {} +#endif + #if IS_ENABLED(CONFIG_RPMSG_QCOM_GLINK_SMEM) struct qcom_glink *qcom_glink_smem_register(struct device *parent, struct device_node *node); void qcom_glink_smem_unregister(struct qcom_glink *glink); -void qcom_glink_ssr_notify(const char *ssr_name); #else @@ -24,7 +29,6 @@ qcom_glink_smem_register(struct device *parent, } static inline void qcom_glink_smem_unregister(struct qcom_glink *glink) {} -static inline void qcom_glink_ssr_notify(const char *ssr_name) {} #endif #endif -- cgit v1.2.3 From 0482a4e6de19bcfc3729dcc13b7b6dde03375bdb Mon Sep 17 00:00:00 2001 From: Samuel Holland Date: Sun, 3 Jan 2021 04:00:04 -0600 Subject: clk: sunxi-ng: h6-r: Add R_APB2_RSB clock and reset While no information about the H6 RSB controller is included in the datasheet or manual, the vendor BSP and power management blob both reference the RSB clock parent and register address. These values were verified by experimentation. Since this clock/reset are added late, the specifier is added at the end to maintain the existing DT binding. The code is kept in register order. Signed-off-by: Samuel Holland Acked-by: Maxime Ripard Signed-off-by: Chen-Yu Tsai --- drivers/clk/sunxi-ng/ccu-sun50i-h6-r.c | 5 +++++ drivers/clk/sunxi-ng/ccu-sun50i-h6-r.h | 2 +- include/dt-bindings/clock/sun50i-h6-r-ccu.h | 2 ++ include/dt-bindings/reset/sun50i-h6-r-ccu.h | 1 + 4 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/clk/sunxi-ng/ccu-sun50i-h6-r.c b/drivers/clk/sunxi-ng/ccu-sun50i-h6-r.c index 50f8d1bc7046..56e351b513f3 100644 --- a/drivers/clk/sunxi-ng/ccu-sun50i-h6-r.c +++ b/drivers/clk/sunxi-ng/ccu-sun50i-h6-r.c @@ -91,6 +91,8 @@ static SUNXI_CCU_GATE(r_apb2_uart_clk, "r-apb2-uart", "r-apb2", 0x18c, BIT(0), 0); static SUNXI_CCU_GATE(r_apb2_i2c_clk, "r-apb2-i2c", "r-apb2", 0x19c, BIT(0), 0); +static SUNXI_CCU_GATE(r_apb2_rsb_clk, "r-apb2-rsb", "r-apb2", + 0x1bc, BIT(0), 0); static SUNXI_CCU_GATE(r_apb1_ir_clk, "r-apb1-ir", "r-apb1", 0x1cc, BIT(0), 0); static SUNXI_CCU_GATE(r_apb1_w1_clk, "r-apb1-w1", "r-apb1", @@ -130,6 +132,7 @@ static struct ccu_common *sun50i_h6_r_ccu_clks[] = { &r_apb1_pwm_clk.common, &r_apb2_uart_clk.common, &r_apb2_i2c_clk.common, + &r_apb2_rsb_clk.common, &r_apb1_ir_clk.common, &r_apb1_w1_clk.common, &ir_clk.common, @@ -147,6 +150,7 @@ static struct clk_hw_onecell_data sun50i_h6_r_hw_clks = { [CLK_R_APB1_PWM] = &r_apb1_pwm_clk.common.hw, [CLK_R_APB2_UART] = &r_apb2_uart_clk.common.hw, [CLK_R_APB2_I2C] = &r_apb2_i2c_clk.common.hw, + [CLK_R_APB2_RSB] = &r_apb2_rsb_clk.common.hw, [CLK_R_APB1_IR] = &r_apb1_ir_clk.common.hw, [CLK_R_APB1_W1] = &r_apb1_w1_clk.common.hw, [CLK_IR] = &ir_clk.common.hw, @@ -161,6 +165,7 @@ static struct ccu_reset_map sun50i_h6_r_ccu_resets[] = { [RST_R_APB1_PWM] = { 0x13c, BIT(16) }, [RST_R_APB2_UART] = { 0x18c, BIT(16) }, [RST_R_APB2_I2C] = { 0x19c, BIT(16) }, + [RST_R_APB2_RSB] = { 0x1bc, BIT(16) }, [RST_R_APB1_IR] = { 0x1cc, BIT(16) }, [RST_R_APB1_W1] = { 0x1ec, BIT(16) }, }; diff --git a/drivers/clk/sunxi-ng/ccu-sun50i-h6-r.h b/drivers/clk/sunxi-ng/ccu-sun50i-h6-r.h index 782117dc0b28..7e290b840803 100644 --- a/drivers/clk/sunxi-ng/ccu-sun50i-h6-r.h +++ b/drivers/clk/sunxi-ng/ccu-sun50i-h6-r.h @@ -14,6 +14,6 @@ #define CLK_R_APB2 3 -#define CLK_NUMBER (CLK_W1 + 1) +#define CLK_NUMBER (CLK_R_APB2_RSB + 1) #endif /* _CCU_SUN50I_H6_R_H */ diff --git a/include/dt-bindings/clock/sun50i-h6-r-ccu.h b/include/dt-bindings/clock/sun50i-h6-r-ccu.h index 76136132a13e..890368d252c4 100644 --- a/include/dt-bindings/clock/sun50i-h6-r-ccu.h +++ b/include/dt-bindings/clock/sun50i-h6-r-ccu.h @@ -21,4 +21,6 @@ #define CLK_IR 11 #define CLK_W1 12 +#define CLK_R_APB2_RSB 13 + #endif /* _DT_BINDINGS_CLK_SUN50I_H6_R_CCU_H_ */ diff --git a/include/dt-bindings/reset/sun50i-h6-r-ccu.h b/include/dt-bindings/reset/sun50i-h6-r-ccu.h index 01c84dba49a4..7950e799c76d 100644 --- a/include/dt-bindings/reset/sun50i-h6-r-ccu.h +++ b/include/dt-bindings/reset/sun50i-h6-r-ccu.h @@ -13,5 +13,6 @@ #define RST_R_APB2_I2C 4 #define RST_R_APB1_IR 5 #define RST_R_APB1_W1 6 +#define RST_R_APB2_RSB 7 #endif /* _DT_BINDINGS_RST_SUN50I_H6_R_CCU_H_ */ -- cgit v1.2.3 From b499779761278d6f5339daa230938211d98861ef Mon Sep 17 00:00:00 2001 From: Sowjanya Komatineni Date: Mon, 21 Dec 2020 13:17:31 -0800 Subject: dt-bindings: clock: tegra: Add clock ID TEGRA210_CLK_QSPI_PM Tegra210 QSPI clock output has divider DIV2_SEL which will be enabled when using DDR interface mode. This patch adds clock ID for this to dt-binding. Acked-by: Rob Herring Signed-off-by: Sowjanya Komatineni Link: https://lore.kernel.org/r/1608585459-17250-2-git-send-email-skomatineni@nvidia.com Signed-off-by: Mark Brown --- include/dt-bindings/clock/tegra210-car.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/dt-bindings/clock/tegra210-car.h b/include/dt-bindings/clock/tegra210-car.h index ab8b8a737a0a..9cfcc3baa52c 100644 --- a/include/dt-bindings/clock/tegra210-car.h +++ b/include/dt-bindings/clock/tegra210-car.h @@ -307,7 +307,7 @@ #define TEGRA210_CLK_AUDIO4 275 #define TEGRA210_CLK_SPDIF 276 /* 277 */ -/* 278 */ +#define TEGRA210_CLK_QSPI_PM 278 /* 279 */ /* 280 */ #define TEGRA210_CLK_SOR0_LVDS 281 /* deprecated */ -- cgit v1.2.3 From 98621ed011c57ba6e52e01a5982b221c9943b6d9 Mon Sep 17 00:00:00 2001 From: Sowjanya Komatineni Date: Mon, 21 Dec 2020 13:17:35 -0800 Subject: spi: spi-mem: Mark dummy transfers by setting dummy_data bit This patch marks dummy transfer by setting dummy_data bit to 1. Controllers supporting dummy transfer by hardware use this bit field to skip software transfer of dummy bytes and use hardware dummy bytes transfer. Signed-off-by: Sowjanya Komatineni Link: https://lore.kernel.org/r/1608585459-17250-6-git-send-email-skomatineni@nvidia.com Signed-off-by: Mark Brown --- drivers/spi/spi-mem.c | 1 + include/linux/spi/spi.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include') diff --git a/drivers/spi/spi-mem.c b/drivers/spi/spi-mem.c index f3a3f196e628..c64371ce6c38 100644 --- a/drivers/spi/spi-mem.c +++ b/drivers/spi/spi-mem.c @@ -354,6 +354,7 @@ int spi_mem_exec_op(struct spi_mem *mem, const struct spi_mem_op *op) xfers[xferpos].tx_buf = tmpbuf + op->addr.nbytes + 1; xfers[xferpos].len = op->dummy.nbytes; xfers[xferpos].tx_nbits = op->dummy.buswidth; + xfers[xferpos].dummy_data = 1; spi_message_add_tail(&xfers[xferpos], &msg); xferpos++; totalxferlen += op->dummy.nbytes; diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 9bfdfaf286eb..797ef28fa7d5 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -825,6 +825,7 @@ extern void spi_res_release(struct spi_controller *ctlr, * transfer. If 0 the default (from @spi_device) is used. * @bits_per_word: select a bits_per_word other than the device default * for this transfer. If 0 the default (from @spi_device) is used. + * @dummy_data: indicates transfer is dummy bytes transfer. * @cs_change: affects chipselect after this transfer completes * @cs_change_delay: delay between cs deassert and assert when * @cs_change is set and @spi_transfer is not the last in @spi_message @@ -937,6 +938,7 @@ struct spi_transfer { struct sg_table tx_sg; struct sg_table rx_sg; + unsigned dummy_data:1; unsigned cs_change:1; unsigned tx_nbits:3; unsigned rx_nbits:3; -- cgit v1.2.3 From c167b9c7e3d6131b4a4865c112a3dbc86d2e997d Mon Sep 17 00:00:00 2001 From: Maximilian Luz Date: Mon, 21 Dec 2020 19:39:51 +0100 Subject: platform/surface: Add Surface Aggregator subsystem Add Surface System Aggregator Module core and Surface Serial Hub driver, required for the embedded controller found on Microsoft Surface devices. The Surface System Aggregator Module (SSAM, SAM or Surface Aggregator) is an embedded controller (EC) found on 4th and later generation Microsoft Surface devices, with the exception of the Surface Go series. This EC provides various functionality, depending on the device in question. This can include battery status and thermal reporting (5th and later generations), but also HID keyboard (6th+) and touchpad input (7th+) on Surface Laptop and Surface Book 3 series devices. This patch provides the basic necessities for communication with the SAM EC on 5th and later generation devices. On these devices, the EC provides an interface that acts as serial device, called the Surface Serial Hub (SSH). 4th generation devices, on which the EC interface is provided via an HID-over-I2C device, are not supported by this patch. Specifically, this patch adds a driver for the SSH device (device HID MSHW0084 in ACPI), as well as a controller structure and associated API. This represents the functional core of the Surface Aggregator kernel subsystem, introduced with this patch, and will be expanded upon in subsequent commits. The SSH driver acts as the main attachment point for this subsystem and sets-up and manages the controller structure. The controller in turn provides a basic communication interface, allowing to send requests from host to EC and receiving the corresponding responses, as well as managing and receiving events, sent from EC to host. It is structured into multiple layers, with the top layer presenting the API used by other kernel drivers and the lower layers modeled after the serial protocol used for communication. Said other drivers are then responsible for providing the (Surface model specific) functionality accessible through the EC (e.g. battery status reporting, thermal information, ...) via said controller structure and API, and will be added in future commits. Signed-off-by: Maximilian Luz Link: https://lore.kernel.org/r/20201221183959.1186143-2-luzmaximilian@gmail.com Signed-off-by: Hans de Goede --- MAINTAINERS | 8 + drivers/platform/surface/Kconfig | 2 + drivers/platform/surface/Makefile | 1 + drivers/platform/surface/aggregator/Kconfig | 42 + drivers/platform/surface/aggregator/Makefile | 10 + drivers/platform/surface/aggregator/controller.c | 2504 ++++++++++++++++++++ drivers/platform/surface/aggregator/controller.h | 276 +++ drivers/platform/surface/aggregator/core.c | 787 ++++++ drivers/platform/surface/aggregator/ssh_msgb.h | 205 ++ .../platform/surface/aggregator/ssh_packet_layer.c | 1710 +++++++++++++ .../platform/surface/aggregator/ssh_packet_layer.h | 187 ++ drivers/platform/surface/aggregator/ssh_parser.c | 228 ++ drivers/platform/surface/aggregator/ssh_parser.h | 154 ++ .../surface/aggregator/ssh_request_layer.c | 1211 ++++++++++ .../surface/aggregator/ssh_request_layer.h | 143 ++ include/linux/surface_aggregator/controller.h | 824 +++++++ include/linux/surface_aggregator/serial_hub.h | 672 ++++++ 17 files changed, 8964 insertions(+) create mode 100644 drivers/platform/surface/aggregator/Kconfig create mode 100644 drivers/platform/surface/aggregator/Makefile create mode 100644 drivers/platform/surface/aggregator/controller.c create mode 100644 drivers/platform/surface/aggregator/controller.h create mode 100644 drivers/platform/surface/aggregator/core.c create mode 100644 drivers/platform/surface/aggregator/ssh_msgb.h create mode 100644 drivers/platform/surface/aggregator/ssh_packet_layer.c create mode 100644 drivers/platform/surface/aggregator/ssh_packet_layer.h create mode 100644 drivers/platform/surface/aggregator/ssh_parser.c create mode 100644 drivers/platform/surface/aggregator/ssh_parser.h create mode 100644 drivers/platform/surface/aggregator/ssh_request_layer.c create mode 100644 drivers/platform/surface/aggregator/ssh_request_layer.h create mode 100644 include/linux/surface_aggregator/controller.h create mode 100644 include/linux/surface_aggregator/serial_hub.h (limited to 'include') diff --git a/MAINTAINERS b/MAINTAINERS index 546aa66428c9..845a245f562c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11813,6 +11813,14 @@ L: platform-driver-x86@vger.kernel.org S: Supported F: drivers/platform/surface/surfacepro3_button.c +MICROSOFT SURFACE SYSTEM AGGREGATOR SUBSYSTEM +M: Maximilian Luz +S: Maintained +W: https://github.com/linux-surface/surface-aggregator-module +C: irc://chat.freenode.net/##linux-surface +F: drivers/platform/surface/aggregator/ +F: include/linux/surface_aggregator/ + MICROTEK X6 SCANNER M: Oliver Neukum S: Maintained diff --git a/drivers/platform/surface/Kconfig b/drivers/platform/surface/Kconfig index 2c941cdac9ee..2916a47b130e 100644 --- a/drivers/platform/surface/Kconfig +++ b/drivers/platform/surface/Kconfig @@ -56,4 +56,6 @@ config SURFACE_PRO3_BUTTON help This driver handles the power/home/volume buttons on the Microsoft Surface Pro 3/4 tablet. +source "drivers/platform/surface/aggregator/Kconfig" + endif # SURFACE_PLATFORMS diff --git a/drivers/platform/surface/Makefile b/drivers/platform/surface/Makefile index cedfb027ded1..034134fe0264 100644 --- a/drivers/platform/surface/Makefile +++ b/drivers/platform/surface/Makefile @@ -7,5 +7,6 @@ obj-$(CONFIG_SURFACE3_WMI) += surface3-wmi.o obj-$(CONFIG_SURFACE_3_BUTTON) += surface3_button.o obj-$(CONFIG_SURFACE_3_POWER_OPREGION) += surface3_power.o +obj-$(CONFIG_SURFACE_AGGREGATOR) += aggregator/ obj-$(CONFIG_SURFACE_GPE) += surface_gpe.o obj-$(CONFIG_SURFACE_PRO3_BUTTON) += surfacepro3_button.o diff --git a/drivers/platform/surface/aggregator/Kconfig b/drivers/platform/surface/aggregator/Kconfig new file mode 100644 index 000000000000..e9f4ad96e40a --- /dev/null +++ b/drivers/platform/surface/aggregator/Kconfig @@ -0,0 +1,42 @@ +# SPDX-License-Identifier: GPL-2.0+ +# Copyright (C) 2019-2020 Maximilian Luz + +menuconfig SURFACE_AGGREGATOR + tristate "Microsoft Surface System Aggregator Module Subsystem and Drivers" + depends on SERIAL_DEV_BUS + select CRC_CCITT + help + The Surface System Aggregator Module (Surface SAM or SSAM) is an + embedded controller (EC) found on 5th- and later-generation Microsoft + Surface devices (i.e. Surface Pro 5, Surface Book 2, Surface Laptop, + and newer, with exception of Surface Go series devices). + + Depending on the device in question, this EC provides varying + functionality, including: + - EC access from ACPI via Surface ACPI Notify (5th- and 6th-generation) + - battery status information (all devices) + - thermal sensor access (all devices) + - performance mode / cooling mode control (all devices) + - clipboard detachment system control (Surface Book 2 and 3) + - HID / keyboard input (Surface Laptops, Surface Book 3) + + This option controls whether the Surface SAM subsystem core will be + built. This includes a driver for the Surface Serial Hub (SSH), which + is the device responsible for the communication with the EC, and a + basic kernel interface exposing the EC functionality to other client + drivers, i.e. allowing them to make requests to the EC and receive + events from it. Selecting this option alone will not provide any + client drivers and therefore no functionality beyond the in-kernel + interface. Said functionality is the responsibility of the respective + client drivers. + + Note: While 4th-generation Surface devices also make use of a SAM EC, + due to a difference in the communication interface of the controller, + only 5th and later generations are currently supported. Specifically, + devices using SAM-over-SSH are supported, whereas devices using + SAM-over-HID, which is used on the 4th generation, are currently not + supported. + + Choose m if you want to build the SAM subsystem core and SSH driver as + module, y if you want to build it into the kernel and n if you don't + want it at all. diff --git a/drivers/platform/surface/aggregator/Makefile b/drivers/platform/surface/aggregator/Makefile new file mode 100644 index 000000000000..faad18d4a7f2 --- /dev/null +++ b/drivers/platform/surface/aggregator/Makefile @@ -0,0 +1,10 @@ +# SPDX-License-Identifier: GPL-2.0+ +# Copyright (C) 2019-2020 Maximilian Luz + +obj-$(CONFIG_SURFACE_AGGREGATOR) += surface_aggregator.o + +surface_aggregator-objs := core.o +surface_aggregator-objs += ssh_parser.o +surface_aggregator-objs += ssh_packet_layer.o +surface_aggregator-objs += ssh_request_layer.o +surface_aggregator-objs += controller.o diff --git a/drivers/platform/surface/aggregator/controller.c b/drivers/platform/surface/aggregator/controller.c new file mode 100644 index 000000000000..488318cf2098 --- /dev/null +++ b/drivers/platform/surface/aggregator/controller.c @@ -0,0 +1,2504 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Main SSAM/SSH controller structure and functionality. + * + * Copyright (C) 2019-2020 Maximilian Luz + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#include "controller.h" +#include "ssh_msgb.h" +#include "ssh_request_layer.h" + + +/* -- Safe counters. -------------------------------------------------------- */ + +/** + * ssh_seq_reset() - Reset/initialize sequence ID counter. + * @c: The counter to reset. + */ +static void ssh_seq_reset(struct ssh_seq_counter *c) +{ + WRITE_ONCE(c->value, 0); +} + +/** + * ssh_seq_next() - Get next sequence ID. + * @c: The counter providing the sequence IDs. + * + * Return: Returns the next sequence ID of the counter. + */ +static u8 ssh_seq_next(struct ssh_seq_counter *c) +{ + u8 old = READ_ONCE(c->value); + u8 new = old + 1; + u8 ret; + + while (unlikely((ret = cmpxchg(&c->value, old, new)) != old)) { + old = ret; + new = old + 1; + } + + return old; +} + +/** + * ssh_rqid_reset() - Reset/initialize request ID counter. + * @c: The counter to reset. + */ +static void ssh_rqid_reset(struct ssh_rqid_counter *c) +{ + WRITE_ONCE(c->value, 0); +} + +/** + * ssh_rqid_next() - Get next request ID. + * @c: The counter providing the request IDs. + * + * Return: Returns the next request ID of the counter, skipping any reserved + * request IDs. + */ +static u16 ssh_rqid_next(struct ssh_rqid_counter *c) +{ + u16 old = READ_ONCE(c->value); + u16 new = ssh_rqid_next_valid(old); + u16 ret; + + while (unlikely((ret = cmpxchg(&c->value, old, new)) != old)) { + old = ret; + new = ssh_rqid_next_valid(old); + } + + return old; +} + + +/* -- Event notifier/callbacks. --------------------------------------------- */ +/* + * The notifier system is based on linux/notifier.h, specifically the SRCU + * implementation. The difference to that is, that some bits of the notifier + * call return value can be tracked across multiple calls. This is done so + * that handling of events can be tracked and a warning can be issued in case + * an event goes unhandled. The idea of that warning is that it should help + * discover and identify new/currently unimplemented features. + */ + +/** + * ssam_event_matches_notifier() - Test if an event matches a notifier. + * @n: The event notifier to test against. + * @event: The event to test. + * + * Return: Returns %true if the given event matches the given notifier + * according to the rules set in the notifier's event mask, %false otherwise. + */ +static bool ssam_event_matches_notifier(const struct ssam_event_notifier *n, + const struct ssam_event *event) +{ + bool match = n->event.id.target_category == event->target_category; + + if (n->event.mask & SSAM_EVENT_MASK_TARGET) + match &= n->event.reg.target_id == event->target_id; + + if (n->event.mask & SSAM_EVENT_MASK_INSTANCE) + match &= n->event.id.instance == event->instance_id; + + return match; +} + +/** + * ssam_nfblk_call_chain() - Call event notifier callbacks of the given chain. + * @nh: The notifier head for which the notifier callbacks should be called. + * @event: The event data provided to the callbacks. + * + * Call all registered notifier callbacks in order of their priority until + * either no notifier is left or a notifier returns a value with the + * %SSAM_NOTIF_STOP bit set. Note that this bit is automatically set via + * ssam_notifier_from_errno() on any non-zero error value. + * + * Return: Returns the notifier status value, which contains the notifier + * status bits (%SSAM_NOTIF_HANDLED and %SSAM_NOTIF_STOP) as well as a + * potential error value returned from the last executed notifier callback. + * Use ssam_notifier_to_errno() to convert this value to the original error + * value. + */ +static int ssam_nfblk_call_chain(struct ssam_nf_head *nh, struct ssam_event *event) +{ + struct ssam_event_notifier *nf; + int ret = 0, idx; + + idx = srcu_read_lock(&nh->srcu); + + list_for_each_entry_rcu(nf, &nh->head, base.node, + srcu_read_lock_held(&nh->srcu)) { + if (ssam_event_matches_notifier(nf, event)) { + ret = (ret & SSAM_NOTIF_STATE_MASK) | nf->base.fn(nf, event); + if (ret & SSAM_NOTIF_STOP) + break; + } + } + + srcu_read_unlock(&nh->srcu, idx); + return ret; +} + +/** + * ssam_nfblk_insert() - Insert a new notifier block into the given notifier + * list. + * @nh: The notifier head into which the block should be inserted. + * @nb: The notifier block to add. + * + * Note: This function must be synchronized by the caller with respect to other + * insert, find, and/or remove calls by holding ``struct ssam_nf.lock``. + * + * Return: Returns zero on success, %-EEXIST if the notifier block has already + * been registered. + */ +static int ssam_nfblk_insert(struct ssam_nf_head *nh, struct ssam_notifier_block *nb) +{ + struct ssam_notifier_block *p; + struct list_head *h; + + /* Runs under lock, no need for RCU variant. */ + list_for_each(h, &nh->head) { + p = list_entry(h, struct ssam_notifier_block, node); + + if (unlikely(p == nb)) { + WARN(1, "double register detected"); + return -EEXIST; + } + + if (nb->priority > p->priority) + break; + } + + list_add_tail_rcu(&nb->node, h); + return 0; +} + +/** + * ssam_nfblk_find() - Check if a notifier block is registered on the given + * notifier head. + * list. + * @nh: The notifier head on which to search. + * @nb: The notifier block to search for. + * + * Note: This function must be synchronized by the caller with respect to other + * insert, find, and/or remove calls by holding ``struct ssam_nf.lock``. + * + * Return: Returns true if the given notifier block is registered on the given + * notifier head, false otherwise. + */ +static bool ssam_nfblk_find(struct ssam_nf_head *nh, struct ssam_notifier_block *nb) +{ + struct ssam_notifier_block *p; + + /* Runs under lock, no need for RCU variant. */ + list_for_each_entry(p, &nh->head, node) { + if (p == nb) + return true; + } + + return false; +} + +/** + * ssam_nfblk_remove() - Remove a notifier block from its notifier list. + * @nb: The notifier block to be removed. + * + * Note: This function must be synchronized by the caller with respect to + * other insert, find, and/or remove calls by holding ``struct ssam_nf.lock``. + * Furthermore, the caller _must_ ensure SRCU synchronization by calling + * synchronize_srcu() with ``nh->srcu`` after leaving the critical section, to + * ensure that the removed notifier block is not in use any more. + */ +static void ssam_nfblk_remove(struct ssam_notifier_block *nb) +{ + list_del_rcu(&nb->node); +} + +/** + * ssam_nf_head_init() - Initialize the given notifier head. + * @nh: The notifier head to initialize. + */ +static int ssam_nf_head_init(struct ssam_nf_head *nh) +{ + int status; + + status = init_srcu_struct(&nh->srcu); + if (status) + return status; + + INIT_LIST_HEAD(&nh->head); + return 0; +} + +/** + * ssam_nf_head_destroy() - Deinitialize the given notifier head. + * @nh: The notifier head to deinitialize. + */ +static void ssam_nf_head_destroy(struct ssam_nf_head *nh) +{ + cleanup_srcu_struct(&nh->srcu); +} + + +/* -- Event/notification registry. ------------------------------------------ */ + +/** + * struct ssam_nf_refcount_key - Key used for event activation reference + * counting. + * @reg: The registry via which the event is enabled/disabled. + * @id: The ID uniquely describing the event. + */ +struct ssam_nf_refcount_key { + struct ssam_event_registry reg; + struct ssam_event_id id; +}; + +/** + * struct ssam_nf_refcount_entry - RB-tree entry for reference counting event + * activations. + * @node: The node of this entry in the rb-tree. + * @key: The key of the event. + * @refcount: The reference-count of the event. + * @flags: The flags used when enabling the event. + */ +struct ssam_nf_refcount_entry { + struct rb_node node; + struct ssam_nf_refcount_key key; + int refcount; + u8 flags; +}; + +/** + * ssam_nf_refcount_inc() - Increment reference-/activation-count of the given + * event. + * @nf: The notifier system reference. + * @reg: The registry used to enable/disable the event. + * @id: The event ID. + * + * Increments the reference-/activation-count associated with the specified + * event type/ID, allocating a new entry for this event ID if necessary. A + * newly allocated entry will have a refcount of one. + * + * Note: ``nf->lock`` must be held when calling this function. + * + * Return: Returns the refcount entry on success. Returns an error pointer + * with %-ENOSPC if there have already been %INT_MAX events of the specified + * ID and type registered, or %-ENOMEM if the entry could not be allocated. + */ +static struct ssam_nf_refcount_entry * +ssam_nf_refcount_inc(struct ssam_nf *nf, struct ssam_event_registry reg, + struct ssam_event_id id) +{ + struct ssam_nf_refcount_entry *entry; + struct ssam_nf_refcount_key key; + struct rb_node **link = &nf->refcount.rb_node; + struct rb_node *parent = NULL; + int cmp; + + lockdep_assert_held(&nf->lock); + + key.reg = reg; + key.id = id; + + while (*link) { + entry = rb_entry(*link, struct ssam_nf_refcount_entry, node); + parent = *link; + + cmp = memcmp(&key, &entry->key, sizeof(key)); + if (cmp < 0) { + link = &(*link)->rb_left; + } else if (cmp > 0) { + link = &(*link)->rb_right; + } else if (entry->refcount < INT_MAX) { + entry->refcount++; + return entry; + } else { + WARN_ON(1); + return ERR_PTR(-ENOSPC); + } + } + + entry = kzalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) + return ERR_PTR(-ENOMEM); + + entry->key = key; + entry->refcount = 1; + + rb_link_node(&entry->node, parent, link); + rb_insert_color(&entry->node, &nf->refcount); + + return entry; +} + +/** + * ssam_nf_refcount_dec() - Decrement reference-/activation-count of the given + * event. + * @nf: The notifier system reference. + * @reg: The registry used to enable/disable the event. + * @id: The event ID. + * + * Decrements the reference-/activation-count of the specified event, + * returning its entry. If the returned entry has a refcount of zero, the + * caller is responsible for freeing it using kfree(). + * + * Note: ``nf->lock`` must be held when calling this function. + * + * Return: Returns the refcount entry on success or %NULL if the entry has not + * been found. + */ +static struct ssam_nf_refcount_entry * +ssam_nf_refcount_dec(struct ssam_nf *nf, struct ssam_event_registry reg, + struct ssam_event_id id) +{ + struct ssam_nf_refcount_entry *entry; + struct ssam_nf_refcount_key key; + struct rb_node *node = nf->refcount.rb_node; + int cmp; + + lockdep_assert_held(&nf->lock); + + key.reg = reg; + key.id = id; + + while (node) { + entry = rb_entry(node, struct ssam_nf_refcount_entry, node); + + cmp = memcmp(&key, &entry->key, sizeof(key)); + if (cmp < 0) { + node = node->rb_left; + } else if (cmp > 0) { + node = node->rb_right; + } else { + entry->refcount--; + if (entry->refcount == 0) + rb_erase(&entry->node, &nf->refcount); + + return entry; + } + } + + return NULL; +} + +/** + * ssam_nf_refcount_empty() - Test if the notification system has any + * enabled/active events. + * @nf: The notification system. + */ +static bool ssam_nf_refcount_empty(struct ssam_nf *nf) +{ + return RB_EMPTY_ROOT(&nf->refcount); +} + +/** + * ssam_nf_call() - Call notification callbacks for the provided event. + * @nf: The notifier system + * @dev: The associated device, only used for logging. + * @rqid: The request ID of the event. + * @event: The event provided to the callbacks. + * + * Execute registered callbacks in order of their priority until either no + * callback is left or a callback returns a value with the %SSAM_NOTIF_STOP + * bit set. Note that this bit is set automatically when converting non-zero + * error values via ssam_notifier_from_errno() to notifier values. + * + * Also note that any callback that could handle an event should return a value + * with bit %SSAM_NOTIF_HANDLED set, indicating that the event does not go + * unhandled/ignored. In case no registered callback could handle an event, + * this function will emit a warning. + * + * In case a callback failed, this function will emit an error message. + */ +static void ssam_nf_call(struct ssam_nf *nf, struct device *dev, u16 rqid, + struct ssam_event *event) +{ + struct ssam_nf_head *nf_head; + int status, nf_ret; + + if (!ssh_rqid_is_event(rqid)) { + dev_warn(dev, "event: unsupported rqid: %#06x\n", rqid); + return; + } + + nf_head = &nf->head[ssh_rqid_to_event(rqid)]; + nf_ret = ssam_nfblk_call_chain(nf_head, event); + status = ssam_notifier_to_errno(nf_ret); + + if (status < 0) { + dev_err(dev, + "event: error handling event: %d (tc: %#04x, tid: %#04x, cid: %#04x, iid: %#04x)\n", + status, event->target_category, event->target_id, + event->command_id, event->instance_id); + } else if (!(nf_ret & SSAM_NOTIF_HANDLED)) { + dev_warn(dev, + "event: unhandled event (rqid: %#04x, tc: %#04x, tid: %#04x, cid: %#04x, iid: %#04x)\n", + rqid, event->target_category, event->target_id, + event->command_id, event->instance_id); + } +} + +/** + * ssam_nf_init() - Initialize the notifier system. + * @nf: The notifier system to initialize. + */ +static int ssam_nf_init(struct ssam_nf *nf) +{ + int i, status; + + for (i = 0; i < SSH_NUM_EVENTS; i++) { + status = ssam_nf_head_init(&nf->head[i]); + if (status) + break; + } + + if (status) { + while (i--) + ssam_nf_head_destroy(&nf->head[i]); + + return status; + } + + mutex_init(&nf->lock); + return 0; +} + +/** + * ssam_nf_destroy() - Deinitialize the notifier system. + * @nf: The notifier system to deinitialize. + */ +static void ssam_nf_destroy(struct ssam_nf *nf) +{ + int i; + + for (i = 0; i < SSH_NUM_EVENTS; i++) + ssam_nf_head_destroy(&nf->head[i]); + + mutex_destroy(&nf->lock); +} + + +/* -- Event/async request completion system. -------------------------------- */ + +#define SSAM_CPLT_WQ_NAME "ssam_cpltq" + +/* + * SSAM_CPLT_WQ_BATCH - Maximum number of event item completions executed per + * work execution. Used to prevent livelocking of the workqueue. Value chosen + * via educated guess, may be adjusted. + */ +#define SSAM_CPLT_WQ_BATCH 10 + +/** + * ssam_event_item_alloc() - Allocate an event item with the given payload size. + * @len: The event payload length. + * @flags: The flags used for allocation. + * + * Allocate an event item with the given payload size. Sets the item + * operations and payload length values. The item free callback (``ops.free``) + * should not be overwritten after this call. + * + * Return: Returns the newly allocated event item. + */ +static struct ssam_event_item *ssam_event_item_alloc(size_t len, gfp_t flags) +{ + struct ssam_event_item *item; + + item = kzalloc(struct_size(item, event.data, len), flags); + if (!item) + return NULL; + + item->event.length = len; + return item; +} + +/** + * ssam_event_queue_push() - Push an event item to the event queue. + * @q: The event queue. + * @item: The item to add. + */ +static void ssam_event_queue_push(struct ssam_event_queue *q, + struct ssam_event_item *item) +{ + spin_lock(&q->lock); + list_add_tail(&item->node, &q->head); + spin_unlock(&q->lock); +} + +/** + * ssam_event_queue_pop() - Pop the next event item from the event queue. + * @q: The event queue. + * + * Returns and removes the next event item from the queue. Returns %NULL If + * there is no event item left. + */ +static struct ssam_event_item *ssam_event_queue_pop(struct ssam_event_queue *q) +{ + struct ssam_event_item *item; + + spin_lock(&q->lock); + item = list_first_entry_or_null(&q->head, struct ssam_event_item, node); + if (item) + list_del(&item->node); + spin_unlock(&q->lock); + + return item; +} + +/** + * ssam_event_queue_is_empty() - Check if the event queue is empty. + * @q: The event queue. + */ +static bool ssam_event_queue_is_empty(struct ssam_event_queue *q) +{ + bool empty; + + spin_lock(&q->lock); + empty = list_empty(&q->head); + spin_unlock(&q->lock); + + return empty; +} + +/** + * ssam_cplt_get_event_queue() - Get the event queue for the given parameters. + * @cplt: The completion system on which to look for the queue. + * @tid: The target ID of the queue. + * @rqid: The request ID representing the event ID for which to get the queue. + * + * Return: Returns the event queue corresponding to the event type described + * by the given parameters. If the request ID does not represent an event, + * this function returns %NULL. If the target ID is not supported, this + * function will fall back to the default target ID (``tid = 1``). + */ +static +struct ssam_event_queue *ssam_cplt_get_event_queue(struct ssam_cplt *cplt, + u8 tid, u16 rqid) +{ + u16 event = ssh_rqid_to_event(rqid); + u16 tidx = ssh_tid_to_index(tid); + + if (!ssh_rqid_is_event(rqid)) { + dev_err(cplt->dev, "event: unsupported request ID: %#06x\n", rqid); + return NULL; + } + + if (!ssh_tid_is_valid(tid)) { + dev_warn(cplt->dev, "event: unsupported target ID: %u\n", tid); + tidx = 0; + } + + return &cplt->event.target[tidx].queue[event]; +} + +/** + * ssam_cplt_submit() - Submit a work item to the completion system workqueue. + * @cplt: The completion system. + * @work: The work item to submit. + */ +static bool ssam_cplt_submit(struct ssam_cplt *cplt, struct work_struct *work) +{ + return queue_work(cplt->wq, work); +} + +/** + * ssam_cplt_submit_event() - Submit an event to the completion system. + * @cplt: The completion system. + * @item: The event item to submit. + * + * Submits the event to the completion system by queuing it on the event item + * queue and queuing the respective event queue work item on the completion + * workqueue, which will eventually complete the event. + * + * Return: Returns zero on success, %-EINVAL if there is no event queue that + * can handle the given event item. + */ +static int ssam_cplt_submit_event(struct ssam_cplt *cplt, + struct ssam_event_item *item) +{ + struct ssam_event_queue *evq; + + evq = ssam_cplt_get_event_queue(cplt, item->event.target_id, item->rqid); + if (!evq) + return -EINVAL; + + ssam_event_queue_push(evq, item); + ssam_cplt_submit(cplt, &evq->work); + return 0; +} + +/** + * ssam_cplt_flush() - Flush the completion system. + * @cplt: The completion system. + * + * Flush the completion system by waiting until all currently submitted work + * items have been completed. + * + * Note: This function does not guarantee that all events will have been + * handled once this call terminates. In case of a larger number of + * to-be-completed events, the event queue work function may re-schedule its + * work item, which this flush operation will ignore. + * + * This operation is only intended to, during normal operation prior to + * shutdown, try to complete most events and requests to get them out of the + * system while the system is still fully operational. It does not aim to + * provide any guarantee that all of them have been handled. + */ +static void ssam_cplt_flush(struct ssam_cplt *cplt) +{ + flush_workqueue(cplt->wq); +} + +static void ssam_event_queue_work_fn(struct work_struct *work) +{ + struct ssam_event_queue *queue; + struct ssam_event_item *item; + struct ssam_nf *nf; + struct device *dev; + unsigned int iterations = SSAM_CPLT_WQ_BATCH; + + queue = container_of(work, struct ssam_event_queue, work); + nf = &queue->cplt->event.notif; + dev = queue->cplt->dev; + + /* Limit number of processed events to avoid livelocking. */ + do { + item = ssam_event_queue_pop(queue); + if (!item) + return; + + ssam_nf_call(nf, dev, item->rqid, &item->event); + kfree(item); + } while (--iterations); + + if (!ssam_event_queue_is_empty(queue)) + ssam_cplt_submit(queue->cplt, &queue->work); +} + +/** + * ssam_event_queue_init() - Initialize an event queue. + * @cplt: The completion system on which the queue resides. + * @evq: The event queue to initialize. + */ +static void ssam_event_queue_init(struct ssam_cplt *cplt, + struct ssam_event_queue *evq) +{ + evq->cplt = cplt; + spin_lock_init(&evq->lock); + INIT_LIST_HEAD(&evq->head); + INIT_WORK(&evq->work, ssam_event_queue_work_fn); +} + +/** + * ssam_cplt_init() - Initialize completion system. + * @cplt: The completion system to initialize. + * @dev: The device used for logging. + */ +static int ssam_cplt_init(struct ssam_cplt *cplt, struct device *dev) +{ + struct ssam_event_target *target; + int status, c, i; + + cplt->dev = dev; + + cplt->wq = create_workqueue(SSAM_CPLT_WQ_NAME); + if (!cplt->wq) + return -ENOMEM; + + for (c = 0; c < ARRAY_SIZE(cplt->event.target); c++) { + target = &cplt->event.target[c]; + + for (i = 0; i < ARRAY_SIZE(target->queue); i++) + ssam_event_queue_init(cplt, &target->queue[i]); + } + + status = ssam_nf_init(&cplt->event.notif); + if (status) + destroy_workqueue(cplt->wq); + + return status; +} + +/** + * ssam_cplt_destroy() - Deinitialize the completion system. + * @cplt: The completion system to deinitialize. + * + * Deinitialize the given completion system and ensure that all pending, i.e. + * yet-to-be-completed, event items and requests have been handled. + */ +static void ssam_cplt_destroy(struct ssam_cplt *cplt) +{ + /* + * Note: destroy_workqueue ensures that all currently queued work will + * be fully completed and the workqueue drained. This means that this + * call will inherently also free any queued ssam_event_items, thus we + * don't have to take care of that here explicitly. + */ + destroy_workqueue(cplt->wq); + ssam_nf_destroy(&cplt->event.notif); +} + + +/* -- Main SSAM device structures. ------------------------------------------ */ + +/** + * ssam_controller_device() - Get the &struct device associated with this + * controller. + * @c: The controller for which to get the device. + * + * Return: Returns the &struct device associated with this controller, + * providing its lower-level transport. + */ +struct device *ssam_controller_device(struct ssam_controller *c) +{ + return ssh_rtl_get_device(&c->rtl); +} +EXPORT_SYMBOL_GPL(ssam_controller_device); + +static void __ssam_controller_release(struct kref *kref) +{ + struct ssam_controller *ctrl = to_ssam_controller(kref, kref); + + /* + * The lock-call here is to satisfy lockdep. At this point we really + * expect this to be the last remaining reference to the controller. + * Anything else is a bug. + */ + ssam_controller_lock(ctrl); + ssam_controller_destroy(ctrl); + ssam_controller_unlock(ctrl); + + kfree(ctrl); +} + +/** + * ssam_controller_get() - Increment reference count of controller. + * @c: The controller. + * + * Return: Returns the controller provided as input. + */ +struct ssam_controller *ssam_controller_get(struct ssam_controller *c) +{ + if (c) + kref_get(&c->kref); + return c; +} +EXPORT_SYMBOL_GPL(ssam_controller_get); + +/** + * ssam_controller_put() - Decrement reference count of controller. + * @c: The controller. + */ +void ssam_controller_put(struct ssam_controller *c) +{ + if (c) + kref_put(&c->kref, __ssam_controller_release); +} +EXPORT_SYMBOL_GPL(ssam_controller_put); + +/** + * ssam_controller_statelock() - Lock the controller against state transitions. + * @c: The controller to lock. + * + * Lock the controller against state transitions. Holding this lock guarantees + * that the controller will not transition between states, i.e. if the + * controller is in state "started", when this lock has been acquired, it will + * remain in this state at least until the lock has been released. + * + * Multiple clients may concurrently hold this lock. In other words: The + * ``statelock`` functions represent the read-lock part of a r/w-semaphore. + * Actions causing state transitions of the controller must be executed while + * holding the write-part of this r/w-semaphore (see ssam_controller_lock() + * and ssam_controller_unlock() for that). + * + * See ssam_controller_stateunlock() for the corresponding unlock function. + */ +void ssam_controller_statelock(struct ssam_controller *c) +{ + down_read(&c->lock); +} +EXPORT_SYMBOL_GPL(ssam_controller_statelock); + +/** + * ssam_controller_stateunlock() - Unlock controller state transitions. + * @c: The controller to unlock. + * + * See ssam_controller_statelock() for the corresponding lock function. + */ +void ssam_controller_stateunlock(struct ssam_controller *c) +{ + up_read(&c->lock); +} +EXPORT_SYMBOL_GPL(ssam_controller_stateunlock); + +/** + * ssam_controller_lock() - Acquire the main controller lock. + * @c: The controller to lock. + * + * This lock must be held for any state transitions, including transition to + * suspend/resumed states and during shutdown. See ssam_controller_statelock() + * for more details on controller locking. + * + * See ssam_controller_unlock() for the corresponding unlock function. + */ +void ssam_controller_lock(struct ssam_controller *c) +{ + down_write(&c->lock); +} + +/* + * ssam_controller_unlock() - Release the main controller lock. + * @c: The controller to unlock. + * + * See ssam_controller_lock() for the corresponding lock function. + */ +void ssam_controller_unlock(struct ssam_controller *c) +{ + up_write(&c->lock); +} + +static void ssam_handle_event(struct ssh_rtl *rtl, + const struct ssh_command *cmd, + const struct ssam_span *data) +{ + struct ssam_controller *ctrl = to_ssam_controller(rtl, rtl); + struct ssam_event_item *item; + + item = ssam_event_item_alloc(data->len, GFP_KERNEL); + if (!item) + return; + + item->rqid = get_unaligned_le16(&cmd->rqid); + item->event.target_category = cmd->tc; + item->event.target_id = cmd->tid_in; + item->event.command_id = cmd->cid; + item->event.instance_id = cmd->iid; + memcpy(&item->event.data[0], data->ptr, data->len); + + if (WARN_ON(ssam_cplt_submit_event(&ctrl->cplt, item))) + kfree(item); +} + +static const struct ssh_rtl_ops ssam_rtl_ops = { + .handle_event = ssam_handle_event, +}; + +static bool ssam_notifier_is_empty(struct ssam_controller *ctrl); +static void ssam_notifier_unregister_all(struct ssam_controller *ctrl); + +#define SSAM_SSH_DSM_REVISION 0 + +/* d5e383e1-d892-4a76-89fc-f6aaae7ed5b5 */ +static const guid_t SSAM_SSH_DSM_GUID = + GUID_INIT(0xd5e383e1, 0xd892, 0x4a76, + 0x89, 0xfc, 0xf6, 0xaa, 0xae, 0x7e, 0xd5, 0xb5); + +enum ssh_dsm_fn { + SSH_DSM_FN_SSH_POWER_PROFILE = 0x05, + SSH_DSM_FN_SCREEN_ON_SLEEP_IDLE_TIMEOUT = 0x06, + SSH_DSM_FN_SCREEN_OFF_SLEEP_IDLE_TIMEOUT = 0x07, + SSH_DSM_FN_D3_CLOSES_HANDLE = 0x08, + SSH_DSM_FN_SSH_BUFFER_SIZE = 0x09, +}; + +static int ssam_dsm_get_functions(acpi_handle handle, u64 *funcs) +{ + union acpi_object *obj; + u64 mask = 0; + int i; + + *funcs = 0; + + /* + * The _DSM function is only present on newer models. It is not + * present on 5th and 6th generation devices (i.e. up to and including + * Surface Pro 6, Surface Laptop 2, Surface Book 2). + * + * If the _DSM is not present, indicate that no function is supported. + * This will result in default values being set. + */ + if (!acpi_has_method(handle, "_DSM")) + return 0; + + obj = acpi_evaluate_dsm_typed(handle, &SSAM_SSH_DSM_GUID, + SSAM_SSH_DSM_REVISION, 0, NULL, + ACPI_TYPE_BUFFER); + if (!obj) + return -EIO; + + for (i = 0; i < obj->buffer.length && i < 8; i++) + mask |= (((u64)obj->buffer.pointer[i]) << (i * 8)); + + if (mask & BIT(0)) + *funcs = mask; + + ACPI_FREE(obj); + return 0; +} + +static int ssam_dsm_load_u32(acpi_handle handle, u64 funcs, u64 func, u32 *ret) +{ + union acpi_object *obj; + u64 val; + + if (!(funcs & BIT(func))) + return 0; /* Not supported, leave *ret at its default value */ + + obj = acpi_evaluate_dsm_typed(handle, &SSAM_SSH_DSM_GUID, + SSAM_SSH_DSM_REVISION, func, NULL, + ACPI_TYPE_INTEGER); + if (!obj) + return -EIO; + + val = obj->integer.value; + ACPI_FREE(obj); + + if (val > U32_MAX) + return -ERANGE; + + *ret = val; + return 0; +} + +/** + * ssam_controller_caps_load_from_acpi() - Load controller capabilities from + * ACPI _DSM. + * @handle: The handle of the ACPI controller/SSH device. + * @caps: Where to store the capabilities in. + * + * Initializes the given controller capabilities with default values, then + * checks and, if the respective _DSM functions are available, loads the + * actual capabilities from the _DSM. + * + * Return: Returns zero on success, a negative error code on failure. + */ +static +int ssam_controller_caps_load_from_acpi(acpi_handle handle, + struct ssam_controller_caps *caps) +{ + u32 d3_closes_handle = false; + u64 funcs; + int status; + + /* Set defaults. */ + caps->ssh_power_profile = U32_MAX; + caps->screen_on_sleep_idle_timeout = U32_MAX; + caps->screen_off_sleep_idle_timeout = U32_MAX; + caps->d3_closes_handle = false; + caps->ssh_buffer_size = U32_MAX; + + /* Pre-load supported DSM functions. */ + status = ssam_dsm_get_functions(handle, &funcs); + if (status) + return status; + + /* Load actual values from ACPI, if present. */ + status = ssam_dsm_load_u32(handle, funcs, SSH_DSM_FN_SSH_POWER_PROFILE, + &caps->ssh_power_profile); + if (status) + return status; + + status = ssam_dsm_load_u32(handle, funcs, + SSH_DSM_FN_SCREEN_ON_SLEEP_IDLE_TIMEOUT, + &caps->screen_on_sleep_idle_timeout); + if (status) + return status; + + status = ssam_dsm_load_u32(handle, funcs, + SSH_DSM_FN_SCREEN_OFF_SLEEP_IDLE_TIMEOUT, + &caps->screen_off_sleep_idle_timeout); + if (status) + return status; + + status = ssam_dsm_load_u32(handle, funcs, SSH_DSM_FN_D3_CLOSES_HANDLE, + &d3_closes_handle); + if (status) + return status; + + caps->d3_closes_handle = !!d3_closes_handle; + + status = ssam_dsm_load_u32(handle, funcs, SSH_DSM_FN_SSH_BUFFER_SIZE, + &caps->ssh_buffer_size); + if (status) + return status; + + return 0; +} + +/** + * ssam_controller_init() - Initialize SSAM controller. + * @ctrl: The controller to initialize. + * @serdev: The serial device representing the underlying data transport. + * + * Initializes the given controller. Does neither start receiver nor + * transmitter threads. After this call, the controller has to be hooked up to + * the serdev core separately via &struct serdev_device_ops, relaying calls to + * ssam_controller_receive_buf() and ssam_controller_write_wakeup(). Once the + * controller has been hooked up, transmitter and receiver threads may be + * started via ssam_controller_start(). These setup steps need to be completed + * before controller can be used for requests. + */ +int ssam_controller_init(struct ssam_controller *ctrl, + struct serdev_device *serdev) +{ + acpi_handle handle = ACPI_HANDLE(&serdev->dev); + int status; + + init_rwsem(&ctrl->lock); + kref_init(&ctrl->kref); + + status = ssam_controller_caps_load_from_acpi(handle, &ctrl->caps); + if (status) + return status; + + dev_dbg(&serdev->dev, + "device capabilities:\n" + " ssh_power_profile: %u\n" + " ssh_buffer_size: %u\n" + " screen_on_sleep_idle_timeout: %u\n" + " screen_off_sleep_idle_timeout: %u\n" + " d3_closes_handle: %u\n", + ctrl->caps.ssh_power_profile, + ctrl->caps.ssh_buffer_size, + ctrl->caps.screen_on_sleep_idle_timeout, + ctrl->caps.screen_off_sleep_idle_timeout, + ctrl->caps.d3_closes_handle); + + ssh_seq_reset(&ctrl->counter.seq); + ssh_rqid_reset(&ctrl->counter.rqid); + + /* Initialize event/request completion system. */ + status = ssam_cplt_init(&ctrl->cplt, &serdev->dev); + if (status) + return status; + + /* Initialize request and packet transport layers. */ + status = ssh_rtl_init(&ctrl->rtl, serdev, &ssam_rtl_ops); + if (status) { + ssam_cplt_destroy(&ctrl->cplt); + return status; + } + + /* + * Set state via write_once even though we expect to be in an + * exclusive context, due to smoke-testing in + * ssam_request_sync_submit(). + */ + WRITE_ONCE(ctrl->state, SSAM_CONTROLLER_INITIALIZED); + return 0; +} + +/** + * ssam_controller_start() - Start the receiver and transmitter threads of the + * controller. + * @ctrl: The controller. + * + * Note: When this function is called, the controller should be properly + * hooked up to the serdev core via &struct serdev_device_ops. Please refer + * to ssam_controller_init() for more details on controller initialization. + * + * This function must be called with the main controller lock held (i.e. by + * calling ssam_controller_lock()). + */ +int ssam_controller_start(struct ssam_controller *ctrl) +{ + int status; + + lockdep_assert_held_write(&ctrl->lock); + + if (ctrl->state != SSAM_CONTROLLER_INITIALIZED) + return -EINVAL; + + status = ssh_rtl_start(&ctrl->rtl); + if (status) + return status; + + /* + * Set state via write_once even though we expect to be locked/in an + * exclusive context, due to smoke-testing in + * ssam_request_sync_submit(). + */ + WRITE_ONCE(ctrl->state, SSAM_CONTROLLER_STARTED); + return 0; +} + +/* + * SSAM_CTRL_SHUTDOWN_FLUSH_TIMEOUT - Timeout for flushing requests during + * shutdown. + * + * Chosen to be larger than one full request timeout, including packets timing + * out. This value should give ample time to complete any outstanding requests + * during normal operation and account for the odd package timeout. + */ +#define SSAM_CTRL_SHUTDOWN_FLUSH_TIMEOUT msecs_to_jiffies(5000) + +/** + * ssam_controller_shutdown() - Shut down the controller. + * @ctrl: The controller. + * + * Shuts down the controller by flushing all pending requests and stopping the + * transmitter and receiver threads. All requests submitted after this call + * will fail with %-ESHUTDOWN. While it is discouraged to do so, this function + * is safe to use in parallel with ongoing request submission. + * + * In the course of this shutdown procedure, all currently registered + * notifiers will be unregistered. It is, however, strongly recommended to not + * rely on this behavior, and instead the party registering the notifier + * should unregister it before the controller gets shut down, e.g. via the + * SSAM bus which guarantees client devices to be removed before a shutdown. + * + * Note that events may still be pending after this call, but, due to the + * notifiers being unregistered, these events will be dropped when the + * controller is subsequently destroyed via ssam_controller_destroy(). + * + * This function must be called with the main controller lock held (i.e. by + * calling ssam_controller_lock()). + */ +void ssam_controller_shutdown(struct ssam_controller *ctrl) +{ + enum ssam_controller_state s = ctrl->state; + int status; + + lockdep_assert_held_write(&ctrl->lock); + + if (s == SSAM_CONTROLLER_UNINITIALIZED || s == SSAM_CONTROLLER_STOPPED) + return; + + /* + * Try to flush pending events and requests while everything still + * works. Note: There may still be packets and/or requests in the + * system after this call (e.g. via control packets submitted by the + * packet transport layer or flush timeout / failure, ...). Those will + * be handled with the ssh_rtl_shutdown() call below. + */ + status = ssh_rtl_flush(&ctrl->rtl, SSAM_CTRL_SHUTDOWN_FLUSH_TIMEOUT); + if (status) { + ssam_err(ctrl, "failed to flush request transport layer: %d\n", + status); + } + + /* Try to flush all currently completing requests and events. */ + ssam_cplt_flush(&ctrl->cplt); + + /* + * We expect all notifiers to have been removed by the respective client + * driver that set them up at this point. If this warning occurs, some + * client driver has not done that... + */ + WARN_ON(!ssam_notifier_is_empty(ctrl)); + + /* + * Nevertheless, we should still take care of drivers that don't behave + * well. Thus disable all enabled events, unregister all notifiers. + */ + ssam_notifier_unregister_all(ctrl); + + /* + * Cancel remaining requests. Ensure no new ones can be queued and stop + * threads. + */ + ssh_rtl_shutdown(&ctrl->rtl); + + /* + * Set state via write_once even though we expect to be locked/in an + * exclusive context, due to smoke-testing in + * ssam_request_sync_submit(). + */ + WRITE_ONCE(ctrl->state, SSAM_CONTROLLER_STOPPED); + ctrl->rtl.ptl.serdev = NULL; +} + +/** + * ssam_controller_destroy() - Destroy the controller and free its resources. + * @ctrl: The controller. + * + * Ensures that all resources associated with the controller get freed. This + * function should only be called after the controller has been stopped via + * ssam_controller_shutdown(). In general, this function should not be called + * directly. The only valid place to call this function directly is during + * initialization, before the controller has been fully initialized and passed + * to other processes. This function is called automatically when the + * reference count of the controller reaches zero. + * + * This function must be called with the main controller lock held (i.e. by + * calling ssam_controller_lock()). + */ +void ssam_controller_destroy(struct ssam_controller *ctrl) +{ + lockdep_assert_held_write(&ctrl->lock); + + if (ctrl->state == SSAM_CONTROLLER_UNINITIALIZED) + return; + + WARN_ON(ctrl->state != SSAM_CONTROLLER_STOPPED); + + /* + * Note: New events could still have been received after the previous + * flush in ssam_controller_shutdown, before the request transport layer + * has been shut down. At this point, after the shutdown, we can be sure + * that no new events will be queued. The call to ssam_cplt_destroy will + * ensure that those remaining are being completed and freed. + */ + + /* Actually free resources. */ + ssam_cplt_destroy(&ctrl->cplt); + ssh_rtl_destroy(&ctrl->rtl); + + /* + * Set state via write_once even though we expect to be locked/in an + * exclusive context, due to smoke-testing in + * ssam_request_sync_submit(). + */ + WRITE_ONCE(ctrl->state, SSAM_CONTROLLER_UNINITIALIZED); +} + +/** + * ssam_controller_suspend() - Suspend the controller. + * @ctrl: The controller to suspend. + * + * Marks the controller as suspended. Note that display-off and D0-exit + * notifications have to be sent manually before transitioning the controller + * into the suspended state via this function. + * + * See ssam_controller_resume() for the corresponding resume function. + * + * Return: Returns %-EINVAL if the controller is currently not in the + * "started" state. + */ +int ssam_controller_suspend(struct ssam_controller *ctrl) +{ + ssam_controller_lock(ctrl); + + if (ctrl->state != SSAM_CONTROLLER_STARTED) { + ssam_controller_unlock(ctrl); + return -EINVAL; + } + + ssam_dbg(ctrl, "pm: suspending controller\n"); + + /* + * Set state via write_once even though we're locked, due to + * smoke-testing in ssam_request_sync_submit(). + */ + WRITE_ONCE(ctrl->state, SSAM_CONTROLLER_SUSPENDED); + + ssam_controller_unlock(ctrl); + return 0; +} + +/** + * ssam_controller_resume() - Resume the controller from suspend. + * @ctrl: The controller to resume. + * + * Resume the controller from the suspended state it was put into via + * ssam_controller_suspend(). This function does not issue display-on and + * D0-entry notifications. If required, those have to be sent manually after + * this call. + * + * Return: Returns %-EINVAL if the controller is currently not suspended. + */ +int ssam_controller_resume(struct ssam_controller *ctrl) +{ + ssam_controller_lock(ctrl); + + if (ctrl->state != SSAM_CONTROLLER_SUSPENDED) { + ssam_controller_unlock(ctrl); + return -EINVAL; + } + + ssam_dbg(ctrl, "pm: resuming controller\n"); + + /* + * Set state via write_once even though we're locked, due to + * smoke-testing in ssam_request_sync_submit(). + */ + WRITE_ONCE(ctrl->state, SSAM_CONTROLLER_STARTED); + + ssam_controller_unlock(ctrl); + return 0; +} + + +/* -- Top-level request interface ------------------------------------------- */ + +/** + * ssam_request_write_data() - Construct and write SAM request message to + * buffer. + * @buf: The buffer to write the data to. + * @ctrl: The controller via which the request will be sent. + * @spec: The request data and specification. + * + * Constructs a SAM/SSH request message and writes it to the provided buffer. + * The request and transport counters, specifically RQID and SEQ, will be set + * in this call. These counters are obtained from the controller. It is thus + * only valid to send the resulting message via the controller specified here. + * + * For calculation of the required buffer size, refer to the + * SSH_COMMAND_MESSAGE_LENGTH() macro. + * + * Return: Returns the number of bytes used in the buffer on success. Returns + * %-EINVAL if the payload length provided in the request specification is too + * large (larger than %SSH_COMMAND_MAX_PAYLOAD_SIZE) or if the provided buffer + * is too small. + */ +ssize_t ssam_request_write_data(struct ssam_span *buf, + struct ssam_controller *ctrl, + const struct ssam_request *spec) +{ + struct msgbuf msgb; + u16 rqid; + u8 seq; + + if (spec->length > SSH_COMMAND_MAX_PAYLOAD_SIZE) + return -EINVAL; + + if (SSH_COMMAND_MESSAGE_LENGTH(spec->length) > buf->len) + return -EINVAL; + + msgb_init(&msgb, buf->ptr, buf->len); + seq = ssh_seq_next(&ctrl->counter.seq); + rqid = ssh_rqid_next(&ctrl->counter.rqid); + msgb_push_cmd(&msgb, seq, rqid, spec); + + return msgb_bytes_used(&msgb); +} +EXPORT_SYMBOL_GPL(ssam_request_write_data); + +static void ssam_request_sync_complete(struct ssh_request *rqst, + const struct ssh_command *cmd, + const struct ssam_span *data, int status) +{ + struct ssh_rtl *rtl = ssh_request_rtl(rqst); + struct ssam_request_sync *r; + + r = container_of(rqst, struct ssam_request_sync, base); + r->status = status; + + if (r->resp) + r->resp->length = 0; + + if (status) { + rtl_dbg_cond(rtl, "rsp: request failed: %d\n", status); + return; + } + + if (!data) /* Handle requests without a response. */ + return; + + if (!r->resp || !r->resp->pointer) { + if (data->len) + rtl_warn(rtl, "rsp: no response buffer provided, dropping data\n"); + return; + } + + if (data->len > r->resp->capacity) { + rtl_err(rtl, + "rsp: response buffer too small, capacity: %zu bytes, got: %zu bytes\n", + r->resp->capacity, data->len); + r->status = -ENOSPC; + return; + } + + r->resp->length = data->len; + memcpy(r->resp->pointer, data->ptr, data->len); +} + +static void ssam_request_sync_release(struct ssh_request *rqst) +{ + complete_all(&container_of(rqst, struct ssam_request_sync, base)->comp); +} + +static const struct ssh_request_ops ssam_request_sync_ops = { + .release = ssam_request_sync_release, + .complete = ssam_request_sync_complete, +}; + +/** + * ssam_request_sync_alloc() - Allocate a synchronous request. + * @payload_len: The length of the request payload. + * @flags: Flags used for allocation. + * @rqst: Where to store the pointer to the allocated request. + * @buffer: Where to store the buffer descriptor for the message buffer of + * the request. + * + * Allocates a synchronous request with corresponding message buffer. The + * request still needs to be initialized ssam_request_sync_init() before + * it can be submitted, and the message buffer data must still be set to the + * returned buffer via ssam_request_sync_set_data() after it has been filled, + * if need be with adjusted message length. + * + * After use, the request and its corresponding message buffer should be freed + * via ssam_request_sync_free(). The buffer must not be freed separately. + * + * Return: Returns zero on success, %-ENOMEM if the request could not be + * allocated. + */ +int ssam_request_sync_alloc(size_t payload_len, gfp_t flags, + struct ssam_request_sync **rqst, + struct ssam_span *buffer) +{ + size_t msglen = SSH_COMMAND_MESSAGE_LENGTH(payload_len); + + *rqst = kzalloc(sizeof(**rqst) + msglen, flags); + if (!*rqst) + return -ENOMEM; + + buffer->ptr = (u8 *)(*rqst + 1); + buffer->len = msglen; + + return 0; +} +EXPORT_SYMBOL_GPL(ssam_request_sync_alloc); + +/** + * ssam_request_sync_free() - Free a synchronous request. + * @rqst: The request to be freed. + * + * Free a synchronous request and its corresponding buffer allocated with + * ssam_request_sync_alloc(). Do not use for requests allocated on the stack + * or via any other function. + * + * Warning: The caller must ensure that the request is not in use any more. + * I.e. the caller must ensure that it has the only reference to the request + * and the request is not currently pending. This means that the caller has + * either never submitted the request, request submission has failed, or the + * caller has waited until the submitted request has been completed via + * ssam_request_sync_wait(). + */ +void ssam_request_sync_free(struct ssam_request_sync *rqst) +{ + kfree(rqst); +} +EXPORT_SYMBOL_GPL(ssam_request_sync_free); + +/** + * ssam_request_sync_init() - Initialize a synchronous request struct. + * @rqst: The request to initialize. + * @flags: The request flags. + * + * Initializes the given request struct. Does not initialize the request + * message data. This has to be done explicitly after this call via + * ssam_request_sync_set_data() and the actual message data has to be written + * via ssam_request_write_data(). + * + * Return: Returns zero on success or %-EINVAL if the given flags are invalid. + */ +int ssam_request_sync_init(struct ssam_request_sync *rqst, + enum ssam_request_flags flags) +{ + int status; + + status = ssh_request_init(&rqst->base, flags, &ssam_request_sync_ops); + if (status) + return status; + + init_completion(&rqst->comp); + rqst->resp = NULL; + rqst->status = 0; + + return 0; +} +EXPORT_SYMBOL_GPL(ssam_request_sync_init); + +/** + * ssam_request_sync_submit() - Submit a synchronous request. + * @ctrl: The controller with which to submit the request. + * @rqst: The request to submit. + * + * Submit a synchronous request. The request has to be initialized and + * properly set up, including response buffer (may be %NULL if no response is + * expected) and command message data. This function does not wait for the + * request to be completed. + * + * If this function succeeds, ssam_request_sync_wait() must be used to ensure + * that the request has been completed before the response data can be + * accessed and/or the request can be freed. On failure, the request may + * immediately be freed. + * + * This function may only be used if the controller is active, i.e. has been + * initialized and not suspended. + */ +int ssam_request_sync_submit(struct ssam_controller *ctrl, + struct ssam_request_sync *rqst) +{ + int status; + + /* + * This is only a superficial check. In general, the caller needs to + * ensure that the controller is initialized and is not (and does not + * get) suspended during use, i.e. until the request has been completed + * (if _absolutely_ necessary, by use of ssam_controller_statelock/ + * ssam_controller_stateunlock, but something like ssam_client_link + * should be preferred as this needs to last until the request has been + * completed). + * + * Note that it is actually safe to use this function while the + * controller is in the process of being shut down (as ssh_rtl_submit + * is safe with regards to this), but it is generally discouraged to do + * so. + */ + if (WARN_ON(READ_ONCE(ctrl->state) != SSAM_CONTROLLER_STARTED)) { + ssh_request_put(&rqst->base); + return -ENODEV; + } + + status = ssh_rtl_submit(&ctrl->rtl, &rqst->base); + ssh_request_put(&rqst->base); + + return status; +} +EXPORT_SYMBOL_GPL(ssam_request_sync_submit); + +/** + * ssam_request_sync() - Execute a synchronous request. + * @ctrl: The controller via which the request will be submitted. + * @spec: The request specification and payload. + * @rsp: The response buffer. + * + * Allocates a synchronous request with its message data buffer on the heap + * via ssam_request_sync_alloc(), fully initializes it via the provided + * request specification, submits it, and finally waits for its completion + * before freeing it and returning its status. + * + * Return: Returns the status of the request or any failure during setup. + */ +int ssam_request_sync(struct ssam_controller *ctrl, + const struct ssam_request *spec, + struct ssam_response *rsp) +{ + struct ssam_request_sync *rqst; + struct ssam_span buf; + ssize_t len; + int status; + + status = ssam_request_sync_alloc(spec->length, GFP_KERNEL, &rqst, &buf); + if (status) + return status; + + status = ssam_request_sync_init(rqst, spec->flags); + if (status) + return status; + + ssam_request_sync_set_resp(rqst, rsp); + + len = ssam_request_write_data(&buf, ctrl, spec); + if (len < 0) { + ssam_request_sync_free(rqst); + return len; + } + + ssam_request_sync_set_data(rqst, buf.ptr, len); + + status = ssam_request_sync_submit(ctrl, rqst); + if (!status) + status = ssam_request_sync_wait(rqst); + + ssam_request_sync_free(rqst); + return status; +} +EXPORT_SYMBOL_GPL(ssam_request_sync); + +/** + * ssam_request_sync_with_buffer() - Execute a synchronous request with the + * provided buffer as back-end for the message buffer. + * @ctrl: The controller via which the request will be submitted. + * @spec: The request specification and payload. + * @rsp: The response buffer. + * @buf: The buffer for the request message data. + * + * Allocates a synchronous request struct on the stack, fully initializes it + * using the provided buffer as message data buffer, submits it, and then + * waits for its completion before returning its status. The + * SSH_COMMAND_MESSAGE_LENGTH() macro can be used to compute the required + * message buffer size. + * + * This function does essentially the same as ssam_request_sync(), but instead + * of dynamically allocating the request and message data buffer, it uses the + * provided message data buffer and stores the (small) request struct on the + * heap. + * + * Return: Returns the status of the request or any failure during setup. + */ +int ssam_request_sync_with_buffer(struct ssam_controller *ctrl, + const struct ssam_request *spec, + struct ssam_response *rsp, + struct ssam_span *buf) +{ + struct ssam_request_sync rqst; + ssize_t len; + int status; + + status = ssam_request_sync_init(&rqst, spec->flags); + if (status) + return status; + + ssam_request_sync_set_resp(&rqst, rsp); + + len = ssam_request_write_data(buf, ctrl, spec); + if (len < 0) + return len; + + ssam_request_sync_set_data(&rqst, buf->ptr, len); + + status = ssam_request_sync_submit(ctrl, &rqst); + if (!status) + status = ssam_request_sync_wait(&rqst); + + return status; +} +EXPORT_SYMBOL_GPL(ssam_request_sync_with_buffer); + + +/* -- Internal SAM requests. ------------------------------------------------ */ + +static SSAM_DEFINE_SYNC_REQUEST_R(ssam_ssh_get_firmware_version, __le32, { + .target_category = SSAM_SSH_TC_SAM, + .target_id = 0x01, + .command_id = 0x13, + .instance_id = 0x00, +}); + +static SSAM_DEFINE_SYNC_REQUEST_R(ssam_ssh_notif_display_off, u8, { + .target_category = SSAM_SSH_TC_SAM, + .target_id = 0x01, + .command_id = 0x15, + .instance_id = 0x00, +}); + +static SSAM_DEFINE_SYNC_REQUEST_R(ssam_ssh_notif_display_on, u8, { + .target_category = SSAM_SSH_TC_SAM, + .target_id = 0x01, + .command_id = 0x16, + .instance_id = 0x00, +}); + +static SSAM_DEFINE_SYNC_REQUEST_R(ssam_ssh_notif_d0_exit, u8, { + .target_category = SSAM_SSH_TC_SAM, + .target_id = 0x01, + .command_id = 0x33, + .instance_id = 0x00, +}); + +static SSAM_DEFINE_SYNC_REQUEST_R(ssam_ssh_notif_d0_entry, u8, { + .target_category = SSAM_SSH_TC_SAM, + .target_id = 0x01, + .command_id = 0x34, + .instance_id = 0x00, +}); + +/** + * struct ssh_notification_params - Command payload to enable/disable SSH + * notifications. + * @target_category: The target category for which notifications should be + * enabled/disabled. + * @flags: Flags determining how notifications are being sent. + * @request_id: The request ID that is used to send these notifications. + * @instance_id: The specific instance in the given target category for + * which notifications should be enabled. + */ +struct ssh_notification_params { + u8 target_category; + u8 flags; + __le16 request_id; + u8 instance_id; +} __packed; + +static_assert(sizeof(struct ssh_notification_params) == 5); + +static int __ssam_ssh_event_request(struct ssam_controller *ctrl, + struct ssam_event_registry reg, u8 cid, + struct ssam_event_id id, u8 flags) +{ + struct ssh_notification_params params; + struct ssam_request rqst; + struct ssam_response result; + int status; + + u16 rqid = ssh_tc_to_rqid(id.target_category); + u8 buf = 0; + + /* Only allow RQIDs that lie within the event spectrum. */ + if (!ssh_rqid_is_event(rqid)) + return -EINVAL; + + params.target_category = id.target_category; + params.instance_id = id.instance; + params.flags = flags; + put_unaligned_le16(rqid, ¶ms.request_id); + + rqst.target_category = reg.target_category; + rqst.target_id = reg.target_id; + rqst.command_id = cid; + rqst.instance_id = 0x00; + rqst.flags = SSAM_REQUEST_HAS_RESPONSE; + rqst.length = sizeof(params); + rqst.payload = (u8 *)¶ms; + + result.capacity = sizeof(buf); + result.length = 0; + result.pointer = &buf; + + status = ssam_retry(ssam_request_sync_onstack, ctrl, &rqst, &result, + sizeof(params)); + + return status < 0 ? status : buf; +} + +/** + * ssam_ssh_event_enable() - Enable SSH event. + * @ctrl: The controller for which to enable the event. + * @reg: The event registry describing what request to use for enabling and + * disabling the event. + * @id: The event identifier. + * @flags: The event flags. + * + * Enables the specified event on the EC. This function does not manage + * reference counting of enabled events and is basically only a wrapper for + * the raw EC request. If the specified event is already enabled, the EC will + * ignore this request. + * + * Return: Returns the status of the executed SAM request (zero on success and + * negative on direct failure) or %-EPROTO if the request response indicates a + * failure. + */ +static int ssam_ssh_event_enable(struct ssam_controller *ctrl, + struct ssam_event_registry reg, + struct ssam_event_id id, u8 flags) +{ + int status; + + status = __ssam_ssh_event_request(ctrl, reg, reg.cid_enable, id, flags); + + if (status < 0 && status != -EINVAL) { + ssam_err(ctrl, + "failed to enable event source (tc: %#04x, iid: %#04x, reg: %#04x)\n", + id.target_category, id.instance, reg.target_category); + } + + if (status > 0) { + ssam_err(ctrl, + "unexpected result while enabling event source: %#04x (tc: %#04x, iid: %#04x, reg: %#04x)\n", + status, id.target_category, id.instance, reg.target_category); + return -EPROTO; + } + + return status; +} + +/** + * ssam_ssh_event_disable() - Disable SSH event. + * @ctrl: The controller for which to disable the event. + * @reg: The event registry describing what request to use for enabling and + * disabling the event (must be same as used when enabling the event). + * @id: The event identifier. + * @flags: The event flags (likely ignored for disabling of events). + * + * Disables the specified event on the EC. This function does not manage + * reference counting of enabled events and is basically only a wrapper for + * the raw EC request. If the specified event is already disabled, the EC will + * ignore this request. + * + * Return: Returns the status of the executed SAM request (zero on success and + * negative on direct failure) or %-EPROTO if the request response indicates a + * failure. + */ +static int ssam_ssh_event_disable(struct ssam_controller *ctrl, + struct ssam_event_registry reg, + struct ssam_event_id id, u8 flags) +{ + int status; + + status = __ssam_ssh_event_request(ctrl, reg, reg.cid_enable, id, flags); + + if (status < 0 && status != -EINVAL) { + ssam_err(ctrl, + "failed to disable event source (tc: %#04x, iid: %#04x, reg: %#04x)\n", + id.target_category, id.instance, reg.target_category); + } + + if (status > 0) { + ssam_err(ctrl, + "unexpected result while disabling event source: %#04x (tc: %#04x, iid: %#04x, reg: %#04x)\n", + status, id.target_category, id.instance, reg.target_category); + return -EPROTO; + } + + return status; +} + + +/* -- Wrappers for internal SAM requests. ----------------------------------- */ + +/** + * ssam_get_firmware_version() - Get the SAM/EC firmware version. + * @ctrl: The controller. + * @version: Where to store the version number. + * + * Return: Returns zero on success or the status of the executed SAM request + * if that request failed. + */ +int ssam_get_firmware_version(struct ssam_controller *ctrl, u32 *version) +{ + __le32 __version; + int status; + + status = ssam_retry(ssam_ssh_get_firmware_version, ctrl, &__version); + if (status) + return status; + + *version = le32_to_cpu(__version); + return 0; +} + +/** + * ssam_ctrl_notif_display_off() - Notify EC that the display has been turned + * off. + * @ctrl: The controller. + * + * Notify the EC that the display has been turned off and the driver may enter + * a lower-power state. This will prevent events from being sent directly. + * Rather, the EC signals an event by pulling the wakeup GPIO high for as long + * as there are pending events. The events then need to be manually released, + * one by one, via the GPIO callback request. All pending events accumulated + * during this state can also be released by issuing the display-on + * notification, e.g. via ssam_ctrl_notif_display_on(), which will also reset + * the GPIO. + * + * On some devices, specifically ones with an integrated keyboard, the keyboard + * backlight will be turned off by this call. + * + * This function will only send the display-off notification command if + * display notifications are supported by the EC. Currently all known devices + * support these notifications. + * + * Use ssam_ctrl_notif_display_on() to reverse the effects of this function. + * + * Return: Returns zero on success or if no request has been executed, the + * status of the executed SAM request if that request failed, or %-EPROTO if + * an unexpected response has been received. + */ +int ssam_ctrl_notif_display_off(struct ssam_controller *ctrl) +{ + int status; + u8 response; + + ssam_dbg(ctrl, "pm: notifying display off\n"); + + status = ssam_retry(ssam_ssh_notif_display_off, ctrl, &response); + if (status) + return status; + + if (response != 0) { + ssam_err(ctrl, "unexpected response from display-off notification: %#04x\n", + response); + return -EPROTO; + } + + return 0; +} + +/** + * ssam_ctrl_notif_display_on() - Notify EC that the display has been turned on. + * @ctrl: The controller. + * + * Notify the EC that the display has been turned back on and the driver has + * exited its lower-power state. This notification is the counterpart to the + * display-off notification sent via ssam_ctrl_notif_display_off() and will + * reverse its effects, including resetting events to their default behavior. + * + * This function will only send the display-on notification command if display + * notifications are supported by the EC. Currently all known devices support + * these notifications. + * + * See ssam_ctrl_notif_display_off() for more details. + * + * Return: Returns zero on success or if no request has been executed, the + * status of the executed SAM request if that request failed, or %-EPROTO if + * an unexpected response has been received. + */ +int ssam_ctrl_notif_display_on(struct ssam_controller *ctrl) +{ + int status; + u8 response; + + ssam_dbg(ctrl, "pm: notifying display on\n"); + + status = ssam_retry(ssam_ssh_notif_display_on, ctrl, &response); + if (status) + return status; + + if (response != 0) { + ssam_err(ctrl, "unexpected response from display-on notification: %#04x\n", + response); + return -EPROTO; + } + + return 0; +} + +/** + * ssam_ctrl_notif_d0_exit() - Notify EC that the driver/device exits the D0 + * power state. + * @ctrl: The controller + * + * Notifies the EC that the driver prepares to exit the D0 power state in + * favor of a lower-power state. Exact effects of this function related to the + * EC are currently unknown. + * + * This function will only send the D0-exit notification command if D0-state + * notifications are supported by the EC. Only newer Surface generations + * support these notifications. + * + * Use ssam_ctrl_notif_d0_entry() to reverse the effects of this function. + * + * Return: Returns zero on success or if no request has been executed, the + * status of the executed SAM request if that request failed, or %-EPROTO if + * an unexpected response has been received. + */ +int ssam_ctrl_notif_d0_exit(struct ssam_controller *ctrl) +{ + int status; + u8 response; + + if (!ctrl->caps.d3_closes_handle) + return 0; + + ssam_dbg(ctrl, "pm: notifying D0 exit\n"); + + status = ssam_retry(ssam_ssh_notif_d0_exit, ctrl, &response); + if (status) + return status; + + if (response != 0) { + ssam_err(ctrl, "unexpected response from D0-exit notification: %#04x\n", + response); + return -EPROTO; + } + + return 0; +} + +/** + * ssam_ctrl_notif_d0_entry() - Notify EC that the driver/device enters the D0 + * power state. + * @ctrl: The controller + * + * Notifies the EC that the driver has exited a lower-power state and entered + * the D0 power state. Exact effects of this function related to the EC are + * currently unknown. + * + * This function will only send the D0-entry notification command if D0-state + * notifications are supported by the EC. Only newer Surface generations + * support these notifications. + * + * See ssam_ctrl_notif_d0_exit() for more details. + * + * Return: Returns zero on success or if no request has been executed, the + * status of the executed SAM request if that request failed, or %-EPROTO if + * an unexpected response has been received. + */ +int ssam_ctrl_notif_d0_entry(struct ssam_controller *ctrl) +{ + int status; + u8 response; + + if (!ctrl->caps.d3_closes_handle) + return 0; + + ssam_dbg(ctrl, "pm: notifying D0 entry\n"); + + status = ssam_retry(ssam_ssh_notif_d0_entry, ctrl, &response); + if (status) + return status; + + if (response != 0) { + ssam_err(ctrl, "unexpected response from D0-entry notification: %#04x\n", + response); + return -EPROTO; + } + + return 0; +} + + +/* -- Top-level event registry interface. ----------------------------------- */ + +/** + * ssam_notifier_register() - Register an event notifier. + * @ctrl: The controller to register the notifier on. + * @n: The event notifier to register. + * + * Register an event notifier and increment the usage counter of the + * associated SAM event. If the event was previously not enabled, it will be + * enabled during this call. + * + * Return: Returns zero on success, %-ENOSPC if there have already been + * %INT_MAX notifiers for the event ID/type associated with the notifier block + * registered, %-ENOMEM if the corresponding event entry could not be + * allocated. If this is the first time that a notifier block is registered + * for the specific associated event, returns the status of the event-enable + * EC-command. + */ +int ssam_notifier_register(struct ssam_controller *ctrl, + struct ssam_event_notifier *n) +{ + u16 rqid = ssh_tc_to_rqid(n->event.id.target_category); + struct ssam_nf_refcount_entry *entry; + struct ssam_nf_head *nf_head; + struct ssam_nf *nf; + int status; + + if (!ssh_rqid_is_event(rqid)) + return -EINVAL; + + nf = &ctrl->cplt.event.notif; + nf_head = &nf->head[ssh_rqid_to_event(rqid)]; + + mutex_lock(&nf->lock); + + entry = ssam_nf_refcount_inc(nf, n->event.reg, n->event.id); + if (IS_ERR(entry)) { + mutex_unlock(&nf->lock); + return PTR_ERR(entry); + } + + ssam_dbg(ctrl, "enabling event (reg: %#04x, tc: %#04x, iid: %#04x, rc: %d)\n", + n->event.reg.target_category, n->event.id.target_category, + n->event.id.instance, entry->refcount); + + status = ssam_nfblk_insert(nf_head, &n->base); + if (status) { + entry = ssam_nf_refcount_dec(nf, n->event.reg, n->event.id); + if (entry->refcount == 0) + kfree(entry); + + mutex_unlock(&nf->lock); + return status; + } + + if (entry->refcount == 1) { + status = ssam_ssh_event_enable(ctrl, n->event.reg, n->event.id, + n->event.flags); + if (status) { + ssam_nfblk_remove(&n->base); + kfree(ssam_nf_refcount_dec(nf, n->event.reg, n->event.id)); + mutex_unlock(&nf->lock); + synchronize_srcu(&nf_head->srcu); + return status; + } + + entry->flags = n->event.flags; + + } else if (entry->flags != n->event.flags) { + ssam_warn(ctrl, + "inconsistent flags when enabling event: got %#04x, expected %#04x (reg: %#04x, tc: %#04x, iid: %#04x)\n", + n->event.flags, entry->flags, n->event.reg.target_category, + n->event.id.target_category, n->event.id.instance); + } + + mutex_unlock(&nf->lock); + return 0; +} +EXPORT_SYMBOL_GPL(ssam_notifier_register); + +/** + * ssam_notifier_unregister() - Unregister an event notifier. + * @ctrl: The controller the notifier has been registered on. + * @n: The event notifier to unregister. + * + * Unregister an event notifier and decrement the usage counter of the + * associated SAM event. If the usage counter reaches zero, the event will be + * disabled. + * + * Return: Returns zero on success, %-ENOENT if the given notifier block has + * not been registered on the controller. If the given notifier block was the + * last one associated with its specific event, returns the status of the + * event-disable EC-command. + */ +int ssam_notifier_unregister(struct ssam_controller *ctrl, + struct ssam_event_notifier *n) +{ + u16 rqid = ssh_tc_to_rqid(n->event.id.target_category); + struct ssam_nf_refcount_entry *entry; + struct ssam_nf_head *nf_head; + struct ssam_nf *nf; + int status = 0; + + if (!ssh_rqid_is_event(rqid)) + return -EINVAL; + + nf = &ctrl->cplt.event.notif; + nf_head = &nf->head[ssh_rqid_to_event(rqid)]; + + mutex_lock(&nf->lock); + + if (!ssam_nfblk_find(nf_head, &n->base)) { + mutex_unlock(&nf->lock); + return -ENOENT; + } + + entry = ssam_nf_refcount_dec(nf, n->event.reg, n->event.id); + if (WARN_ON(!entry)) { + /* + * If this does not return an entry, there's a logic error + * somewhere: The notifier block is registered, but the event + * refcount entry is not there. Remove the notifier block + * anyways. + */ + status = -ENOENT; + goto remove; + } + + ssam_dbg(ctrl, "disabling event (reg: %#04x, tc: %#04x, iid: %#04x, rc: %d)\n", + n->event.reg.target_category, n->event.id.target_category, + n->event.id.instance, entry->refcount); + + if (entry->flags != n->event.flags) { + ssam_warn(ctrl, + "inconsistent flags when disabling event: got %#04x, expected %#04x (reg: %#04x, tc: %#04x, iid: %#04x)\n", + n->event.flags, entry->flags, n->event.reg.target_category, + n->event.id.target_category, n->event.id.instance); + } + + if (entry->refcount == 0) { + status = ssam_ssh_event_disable(ctrl, n->event.reg, n->event.id, + n->event.flags); + kfree(entry); + } + +remove: + ssam_nfblk_remove(&n->base); + mutex_unlock(&nf->lock); + synchronize_srcu(&nf_head->srcu); + + return status; +} +EXPORT_SYMBOL_GPL(ssam_notifier_unregister); + +/** + * ssam_notifier_disable_registered() - Disable events for all registered + * notifiers. + * @ctrl: The controller for which to disable the notifiers/events. + * + * Disables events for all currently registered notifiers. In case of an error + * (EC command failing), all previously disabled events will be restored and + * the error code returned. + * + * This function is intended to disable all events prior to hibernation entry. + * See ssam_notifier_restore_registered() to restore/re-enable all events + * disabled with this function. + * + * Note that this function will not disable events for notifiers registered + * after calling this function. It should thus be made sure that no new + * notifiers are going to be added after this call and before the corresponding + * call to ssam_notifier_restore_registered(). + * + * Return: Returns zero on success. In case of failure returns the error code + * returned by the failed EC command to disable an event. + */ +int ssam_notifier_disable_registered(struct ssam_controller *ctrl) +{ + struct ssam_nf *nf = &ctrl->cplt.event.notif; + struct rb_node *n; + int status; + + mutex_lock(&nf->lock); + for (n = rb_first(&nf->refcount); n; n = rb_next(n)) { + struct ssam_nf_refcount_entry *e; + + e = rb_entry(n, struct ssam_nf_refcount_entry, node); + status = ssam_ssh_event_disable(ctrl, e->key.reg, + e->key.id, e->flags); + if (status) + goto err; + } + mutex_unlock(&nf->lock); + + return 0; + +err: + for (n = rb_prev(n); n; n = rb_prev(n)) { + struct ssam_nf_refcount_entry *e; + + e = rb_entry(n, struct ssam_nf_refcount_entry, node); + ssam_ssh_event_enable(ctrl, e->key.reg, e->key.id, e->flags); + } + mutex_unlock(&nf->lock); + + return status; +} + +/** + * ssam_notifier_restore_registered() - Restore/re-enable events for all + * registered notifiers. + * @ctrl: The controller for which to restore the notifiers/events. + * + * Restores/re-enables all events for which notifiers have been registered on + * the given controller. In case of a failure, the error is logged and the + * function continues to try and enable the remaining events. + * + * This function is intended to restore/re-enable all registered events after + * hibernation. See ssam_notifier_disable_registered() for the counter part + * disabling the events and more details. + */ +void ssam_notifier_restore_registered(struct ssam_controller *ctrl) +{ + struct ssam_nf *nf = &ctrl->cplt.event.notif; + struct rb_node *n; + + mutex_lock(&nf->lock); + for (n = rb_first(&nf->refcount); n; n = rb_next(n)) { + struct ssam_nf_refcount_entry *e; + + e = rb_entry(n, struct ssam_nf_refcount_entry, node); + + /* Ignore errors, will get logged in call. */ + ssam_ssh_event_enable(ctrl, e->key.reg, e->key.id, e->flags); + } + mutex_unlock(&nf->lock); +} + +/** + * ssam_notifier_is_empty() - Check if there are any registered notifiers. + * @ctrl: The controller to check on. + * + * Return: Returns %true if there are currently no notifiers registered on the + * controller, %false otherwise. + */ +static bool ssam_notifier_is_empty(struct ssam_controller *ctrl) +{ + struct ssam_nf *nf = &ctrl->cplt.event.notif; + bool result; + + mutex_lock(&nf->lock); + result = ssam_nf_refcount_empty(nf); + mutex_unlock(&nf->lock); + + return result; +} + +/** + * ssam_notifier_unregister_all() - Unregister all currently registered + * notifiers. + * @ctrl: The controller to unregister the notifiers on. + * + * Unregisters all currently registered notifiers. This function is used to + * ensure that all notifiers will be unregistered and associated + * entries/resources freed when the controller is being shut down. + */ +static void ssam_notifier_unregister_all(struct ssam_controller *ctrl) +{ + struct ssam_nf *nf = &ctrl->cplt.event.notif; + struct ssam_nf_refcount_entry *e, *n; + + mutex_lock(&nf->lock); + rbtree_postorder_for_each_entry_safe(e, n, &nf->refcount, node) { + /* Ignore errors, will get logged in call. */ + ssam_ssh_event_disable(ctrl, e->key.reg, e->key.id, e->flags); + kfree(e); + } + nf->refcount = RB_ROOT; + mutex_unlock(&nf->lock); +} + + +/* -- Wakeup IRQ. ----------------------------------------------------------- */ + +static irqreturn_t ssam_irq_handle(int irq, void *dev_id) +{ + struct ssam_controller *ctrl = dev_id; + + ssam_dbg(ctrl, "pm: wake irq triggered\n"); + + /* + * Note: Proper wakeup detection is currently unimplemented. + * When the EC is in display-off or any other non-D0 state, it + * does not send events/notifications to the host. Instead it + * signals that there are events available via the wakeup IRQ. + * This driver is responsible for calling back to the EC to + * release these events one-by-one. + * + * This IRQ should not cause a full system resume by its own. + * Instead, events should be handled by their respective subsystem + * drivers, which in turn should signal whether a full system + * resume should be performed. + * + * TODO: Send GPIO callback command repeatedly to EC until callback + * returns 0x00. Return flag of callback is "has more events". + * Each time the command is sent, one event is "released". Once + * all events have been released (return = 0x00), the GPIO is + * re-armed. Detect wakeup events during this process, go back to + * sleep if no wakeup event has been received. + */ + + return IRQ_HANDLED; +} + +/** + * ssam_irq_setup() - Set up SAM EC wakeup-GPIO interrupt. + * @ctrl: The controller for which the IRQ should be set up. + * + * Set up an IRQ for the wakeup-GPIO pin of the SAM EC. This IRQ can be used + * to wake the device from a low power state. + * + * Note that this IRQ can only be triggered while the EC is in the display-off + * state. In this state, events are not sent to the host in the usual way. + * Instead the wakeup-GPIO gets pulled to "high" as long as there are pending + * events and these events need to be released one-by-one via the GPIO + * callback request, either until there are no events left and the GPIO is + * reset, or all at once by transitioning the EC out of the display-off state, + * which will also clear the GPIO. + * + * Not all events, however, should trigger a full system wakeup. Instead the + * driver should, if necessary, inspect and forward each event to the + * corresponding subsystem, which in turn should decide if the system needs to + * be woken up. This logic has not been implemented yet, thus wakeup by this + * IRQ should be disabled by default to avoid spurious wake-ups, caused, for + * example, by the remaining battery percentage changing. Refer to comments in + * this function and comments in the corresponding IRQ handler for more + * details on how this should be implemented. + * + * See also ssam_ctrl_notif_display_off() and ssam_ctrl_notif_display_off() + * for functions to transition the EC into and out of the display-off state as + * well as more details on it. + * + * The IRQ is disabled by default and has to be enabled before it can wake up + * the device from suspend via ssam_irq_arm_for_wakeup(). On teardown, the IRQ + * should be freed via ssam_irq_free(). + */ +int ssam_irq_setup(struct ssam_controller *ctrl) +{ + struct device *dev = ssam_controller_device(ctrl); + struct gpio_desc *gpiod; + int irq; + int status; + + /* + * The actual GPIO interrupt is declared in ACPI as TRIGGER_HIGH. + * However, the GPIO line only gets reset by sending the GPIO callback + * command to SAM (or alternatively the display-on notification). As + * proper handling for this interrupt is not implemented yet, leaving + * the IRQ at TRIGGER_HIGH would cause an IRQ storm (as the callback + * never gets sent and thus the line never gets reset). To avoid this, + * mark the IRQ as TRIGGER_RISING for now, only creating a single + * interrupt, and let the SAM resume callback during the controller + * resume process clear it. + */ + const int irqf = IRQF_SHARED | IRQF_ONESHOT | IRQF_TRIGGER_RISING; + + gpiod = gpiod_get(dev, "ssam_wakeup-int", GPIOD_ASIS); + if (IS_ERR(gpiod)) + return PTR_ERR(gpiod); + + irq = gpiod_to_irq(gpiod); + gpiod_put(gpiod); + + if (irq < 0) + return irq; + + status = request_threaded_irq(irq, NULL, ssam_irq_handle, irqf, + "ssam_wakeup", ctrl); + if (status) + return status; + + ctrl->irq.num = irq; + disable_irq(ctrl->irq.num); + return 0; +} + +/** + * ssam_irq_free() - Free SAM EC wakeup-GPIO interrupt. + * @ctrl: The controller for which the IRQ should be freed. + * + * Free the wakeup-GPIO IRQ previously set-up via ssam_irq_setup(). + */ +void ssam_irq_free(struct ssam_controller *ctrl) +{ + free_irq(ctrl->irq.num, ctrl); + ctrl->irq.num = -1; +} + +/** + * ssam_irq_arm_for_wakeup() - Arm the EC IRQ for wakeup, if enabled. + * @ctrl: The controller for which the IRQ should be armed. + * + * Sets up the IRQ so that it can be used to wake the device. Specifically, + * this function enables the irq and then, if the device is allowed to wake up + * the system, calls enable_irq_wake(). See ssam_irq_disarm_wakeup() for the + * corresponding function to disable the IRQ. + * + * This function is intended to arm the IRQ before entering S2idle suspend. + * + * Note: calls to ssam_irq_arm_for_wakeup() and ssam_irq_disarm_wakeup() must + * be balanced. + */ +int ssam_irq_arm_for_wakeup(struct ssam_controller *ctrl) +{ + struct device *dev = ssam_controller_device(ctrl); + int status; + + enable_irq(ctrl->irq.num); + if (device_may_wakeup(dev)) { + status = enable_irq_wake(ctrl->irq.num); + if (status) { + ssam_err(ctrl, "failed to enable wake IRQ: %d\n", status); + disable_irq(ctrl->irq.num); + return status; + } + + ctrl->irq.wakeup_enabled = true; + } else { + ctrl->irq.wakeup_enabled = false; + } + + return 0; +} + +/** + * ssam_irq_disarm_wakeup() - Disarm the wakeup IRQ. + * @ctrl: The controller for which the IRQ should be disarmed. + * + * Disarm the IRQ previously set up for wake via ssam_irq_arm_for_wakeup(). + * + * This function is intended to disarm the IRQ after exiting S2idle suspend. + * + * Note: calls to ssam_irq_arm_for_wakeup() and ssam_irq_disarm_wakeup() must + * be balanced. + */ +void ssam_irq_disarm_wakeup(struct ssam_controller *ctrl) +{ + int status; + + if (ctrl->irq.wakeup_enabled) { + status = disable_irq_wake(ctrl->irq.num); + if (status) + ssam_err(ctrl, "failed to disable wake IRQ: %d\n", status); + + ctrl->irq.wakeup_enabled = false; + } + disable_irq(ctrl->irq.num); +} diff --git a/drivers/platform/surface/aggregator/controller.h b/drivers/platform/surface/aggregator/controller.h new file mode 100644 index 000000000000..5ee9e966f1d7 --- /dev/null +++ b/drivers/platform/surface/aggregator/controller.h @@ -0,0 +1,276 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Main SSAM/SSH controller structure and functionality. + * + * Copyright (C) 2019-2020 Maximilian Luz + */ + +#ifndef _SURFACE_AGGREGATOR_CONTROLLER_H +#define _SURFACE_AGGREGATOR_CONTROLLER_H + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#include "ssh_request_layer.h" + + +/* -- Safe counters. -------------------------------------------------------- */ + +/** + * struct ssh_seq_counter - Safe counter for SSH sequence IDs. + * @value: The current counter value. + */ +struct ssh_seq_counter { + u8 value; +}; + +/** + * struct ssh_rqid_counter - Safe counter for SSH request IDs. + * @value: The current counter value. + */ +struct ssh_rqid_counter { + u16 value; +}; + + +/* -- Event/notification system. -------------------------------------------- */ + +/** + * struct ssam_nf_head - Notifier head for SSAM events. + * @srcu: The SRCU struct for synchronization. + * @head: List-head for notifier blocks registered under this head. + */ +struct ssam_nf_head { + struct srcu_struct srcu; + struct list_head head; +}; + +/** + * struct ssam_nf - Notifier callback- and activation-registry for SSAM events. + * @lock: Lock guarding (de-)registration of notifier blocks. Note: This + * lock does not need to be held for notifier calls, only + * registration and deregistration. + * @refcount: The root of the RB-tree used for reference-counting enabled + * events/notifications. + * @head: The list of notifier heads for event/notification callbacks. + */ +struct ssam_nf { + struct mutex lock; + struct rb_root refcount; + struct ssam_nf_head head[SSH_NUM_EVENTS]; +}; + + +/* -- Event/async request completion system. -------------------------------- */ + +struct ssam_cplt; + +/** + * struct ssam_event_item - Struct for event queuing and completion. + * @node: The node in the queue. + * @rqid: The request ID of the event. + * @event: Actual event data. + */ +struct ssam_event_item { + struct list_head node; + u16 rqid; + + struct ssam_event event; /* must be last */ +}; + +/** + * struct ssam_event_queue - Queue for completing received events. + * @cplt: Reference to the completion system on which this queue is active. + * @lock: The lock for any operation on the queue. + * @head: The list-head of the queue. + * @work: The &struct work_struct performing completion work for this queue. + */ +struct ssam_event_queue { + struct ssam_cplt *cplt; + + spinlock_t lock; + struct list_head head; + struct work_struct work; +}; + +/** + * struct ssam_event_target - Set of queues for a single SSH target ID. + * @queue: The array of queues, one queue per event ID. + */ +struct ssam_event_target { + struct ssam_event_queue queue[SSH_NUM_EVENTS]; +}; + +/** + * struct ssam_cplt - SSAM event/async request completion system. + * @dev: The device with which this system is associated. Only used + * for logging. + * @wq: The &struct workqueue_struct on which all completion work + * items are queued. + * @event: Event completion management. + * @event.target: Array of &struct ssam_event_target, one for each target. + * @event.notif: Notifier callbacks and event activation reference counting. + */ +struct ssam_cplt { + struct device *dev; + struct workqueue_struct *wq; + + struct { + struct ssam_event_target target[SSH_NUM_TARGETS]; + struct ssam_nf notif; + } event; +}; + + +/* -- Main SSAM device structures. ------------------------------------------ */ + +/** + * enum ssam_controller_state - State values for &struct ssam_controller. + * @SSAM_CONTROLLER_UNINITIALIZED: + * The controller has not been initialized yet or has been deinitialized. + * @SSAM_CONTROLLER_INITIALIZED: + * The controller is initialized, but has not been started yet. + * @SSAM_CONTROLLER_STARTED: + * The controller has been started and is ready to use. + * @SSAM_CONTROLLER_STOPPED: + * The controller has been stopped. + * @SSAM_CONTROLLER_SUSPENDED: + * The controller has been suspended. + */ +enum ssam_controller_state { + SSAM_CONTROLLER_UNINITIALIZED, + SSAM_CONTROLLER_INITIALIZED, + SSAM_CONTROLLER_STARTED, + SSAM_CONTROLLER_STOPPED, + SSAM_CONTROLLER_SUSPENDED, +}; + +/** + * struct ssam_controller_caps - Controller device capabilities. + * @ssh_power_profile: SSH power profile. + * @ssh_buffer_size: SSH driver UART buffer size. + * @screen_on_sleep_idle_timeout: SAM UART screen-on sleep idle timeout. + * @screen_off_sleep_idle_timeout: SAM UART screen-off sleep idle timeout. + * @d3_closes_handle: SAM closes UART handle in D3. + * + * Controller and SSH device capabilities found in ACPI. + */ +struct ssam_controller_caps { + u32 ssh_power_profile; + u32 ssh_buffer_size; + u32 screen_on_sleep_idle_timeout; + u32 screen_off_sleep_idle_timeout; + u32 d3_closes_handle:1; +}; + +/** + * struct ssam_controller - SSAM controller device. + * @kref: Reference count of the controller. + * @lock: Main lock for the controller, used to guard state changes. + * @state: Controller state. + * @rtl: Request transport layer for SSH I/O. + * @cplt: Completion system for SSH/SSAM events and asynchronous requests. + * @counter: Safe SSH message ID counters. + * @counter.seq: Sequence ID counter. + * @counter.rqid: Request ID counter. + * @irq: Wakeup IRQ resources. + * @irq.num: The wakeup IRQ number. + * @irq.wakeup_enabled: Whether wakeup by IRQ is enabled during suspend. + * @caps: The controller device capabilities. + */ +struct ssam_controller { + struct kref kref; + + struct rw_semaphore lock; + enum ssam_controller_state state; + + struct ssh_rtl rtl; + struct ssam_cplt cplt; + + struct { + struct ssh_seq_counter seq; + struct ssh_rqid_counter rqid; + } counter; + + struct { + int num; + bool wakeup_enabled; + } irq; + + struct ssam_controller_caps caps; +}; + +#define to_ssam_controller(ptr, member) \ + container_of(ptr, struct ssam_controller, member) + +#define ssam_dbg(ctrl, fmt, ...) rtl_dbg(&(ctrl)->rtl, fmt, ##__VA_ARGS__) +#define ssam_info(ctrl, fmt, ...) rtl_info(&(ctrl)->rtl, fmt, ##__VA_ARGS__) +#define ssam_warn(ctrl, fmt, ...) rtl_warn(&(ctrl)->rtl, fmt, ##__VA_ARGS__) +#define ssam_err(ctrl, fmt, ...) rtl_err(&(ctrl)->rtl, fmt, ##__VA_ARGS__) + +/** + * ssam_controller_receive_buf() - Provide input-data to the controller. + * @ctrl: The controller. + * @buf: The input buffer. + * @n: The number of bytes in the input buffer. + * + * Provide input data to be evaluated by the controller, which has been + * received via the lower-level transport. + * + * Return: Returns the number of bytes consumed, or, if the packet transport + * layer of the controller has been shut down, %-ESHUTDOWN. + */ +static inline +int ssam_controller_receive_buf(struct ssam_controller *ctrl, + const unsigned char *buf, size_t n) +{ + return ssh_ptl_rx_rcvbuf(&ctrl->rtl.ptl, buf, n); +} + +/** + * ssam_controller_write_wakeup() - Notify the controller that the underlying + * device has space available for data to be written. + * @ctrl: The controller. + */ +static inline void ssam_controller_write_wakeup(struct ssam_controller *ctrl) +{ + ssh_ptl_tx_wakeup_transfer(&ctrl->rtl.ptl); +} + +int ssam_controller_init(struct ssam_controller *ctrl, struct serdev_device *s); +int ssam_controller_start(struct ssam_controller *ctrl); +void ssam_controller_shutdown(struct ssam_controller *ctrl); +void ssam_controller_destroy(struct ssam_controller *ctrl); + +int ssam_notifier_disable_registered(struct ssam_controller *ctrl); +void ssam_notifier_restore_registered(struct ssam_controller *ctrl); + +int ssam_irq_setup(struct ssam_controller *ctrl); +void ssam_irq_free(struct ssam_controller *ctrl); +int ssam_irq_arm_for_wakeup(struct ssam_controller *ctrl); +void ssam_irq_disarm_wakeup(struct ssam_controller *ctrl); + +void ssam_controller_lock(struct ssam_controller *c); +void ssam_controller_unlock(struct ssam_controller *c); + +int ssam_get_firmware_version(struct ssam_controller *ctrl, u32 *version); +int ssam_ctrl_notif_display_off(struct ssam_controller *ctrl); +int ssam_ctrl_notif_display_on(struct ssam_controller *ctrl); +int ssam_ctrl_notif_d0_exit(struct ssam_controller *ctrl); +int ssam_ctrl_notif_d0_entry(struct ssam_controller *ctrl); + +int ssam_controller_suspend(struct ssam_controller *ctrl); +int ssam_controller_resume(struct ssam_controller *ctrl); + +#endif /* _SURFACE_AGGREGATOR_CONTROLLER_H */ diff --git a/drivers/platform/surface/aggregator/core.c b/drivers/platform/surface/aggregator/core.c new file mode 100644 index 000000000000..18e0e9e34e7b --- /dev/null +++ b/drivers/platform/surface/aggregator/core.c @@ -0,0 +1,787 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Surface Serial Hub (SSH) driver for communication with the Surface/System + * Aggregator Module (SSAM/SAM). + * + * Provides access to a SAM-over-SSH connected EC via a controller device. + * Handles communication via requests as well as enabling, disabling, and + * relaying of events. + * + * Copyright (C) 2019-2020 Maximilian Luz + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include "controller.h" + + +/* -- Static controller reference. ------------------------------------------ */ + +/* + * Main controller reference. The corresponding lock must be held while + * accessing (reading/writing) the reference. + */ +static struct ssam_controller *__ssam_controller; +static DEFINE_SPINLOCK(__ssam_controller_lock); + +/** + * ssam_get_controller() - Get reference to SSAM controller. + * + * Returns a reference to the SSAM controller of the system or %NULL if there + * is none, it hasn't been set up yet, or it has already been unregistered. + * This function automatically increments the reference count of the + * controller, thus the calling party must ensure that ssam_controller_put() + * is called when it doesn't need the controller any more. + */ +struct ssam_controller *ssam_get_controller(void) +{ + struct ssam_controller *ctrl; + + spin_lock(&__ssam_controller_lock); + + ctrl = __ssam_controller; + if (!ctrl) + goto out; + + if (WARN_ON(!kref_get_unless_zero(&ctrl->kref))) + ctrl = NULL; + +out: + spin_unlock(&__ssam_controller_lock); + return ctrl; +} +EXPORT_SYMBOL_GPL(ssam_get_controller); + +/** + * ssam_try_set_controller() - Try to set the main controller reference. + * @ctrl: The controller to which the reference should point. + * + * Set the main controller reference to the given pointer if the reference + * hasn't been set already. + * + * Return: Returns zero on success or %-EEXIST if the reference has already + * been set. + */ +static int ssam_try_set_controller(struct ssam_controller *ctrl) +{ + int status = 0; + + spin_lock(&__ssam_controller_lock); + if (!__ssam_controller) + __ssam_controller = ctrl; + else + status = -EEXIST; + spin_unlock(&__ssam_controller_lock); + + return status; +} + +/** + * ssam_clear_controller() - Remove/clear the main controller reference. + * + * Clears the main controller reference, i.e. sets it to %NULL. This function + * should be called before the controller is shut down. + */ +static void ssam_clear_controller(void) +{ + spin_lock(&__ssam_controller_lock); + __ssam_controller = NULL; + spin_unlock(&__ssam_controller_lock); +} + +/** + * ssam_client_link() - Link an arbitrary client device to the controller. + * @c: The controller to link to. + * @client: The client device. + * + * Link an arbitrary client device to the controller by creating a device link + * between it as consumer and the controller device as provider. This function + * can be used for non-SSAM devices (or SSAM devices not registered as child + * under the controller) to guarantee that the controller is valid for as long + * as the driver of the client device is bound, and that proper suspend and + * resume ordering is guaranteed. + * + * The device link does not have to be destructed manually. It is removed + * automatically once the driver of the client device unbinds. + * + * Return: Returns zero on success, %-ENODEV if the controller is not ready or + * going to be removed soon, or %-ENOMEM if the device link could not be + * created for other reasons. + */ +int ssam_client_link(struct ssam_controller *c, struct device *client) +{ + const u32 flags = DL_FLAG_PM_RUNTIME | DL_FLAG_AUTOREMOVE_CONSUMER; + struct device_link *link; + struct device *ctrldev; + + ssam_controller_statelock(c); + + if (c->state != SSAM_CONTROLLER_STARTED) { + ssam_controller_stateunlock(c); + return -ENODEV; + } + + ctrldev = ssam_controller_device(c); + if (!ctrldev) { + ssam_controller_stateunlock(c); + return -ENODEV; + } + + link = device_link_add(client, ctrldev, flags); + if (!link) { + ssam_controller_stateunlock(c); + return -ENOMEM; + } + + /* + * Return -ENODEV if supplier driver is on its way to be removed. In + * this case, the controller won't be around for much longer and the + * device link is not going to save us any more, as unbinding is + * already in progress. + */ + if (READ_ONCE(link->status) == DL_STATE_SUPPLIER_UNBIND) { + ssam_controller_stateunlock(c); + return -ENODEV; + } + + ssam_controller_stateunlock(c); + return 0; +} +EXPORT_SYMBOL_GPL(ssam_client_link); + +/** + * ssam_client_bind() - Bind an arbitrary client device to the controller. + * @client: The client device. + * + * Link an arbitrary client device to the controller by creating a device link + * between it as consumer and the main controller device as provider. This + * function can be used for non-SSAM devices to guarantee that the controller + * returned by this function is valid for as long as the driver of the client + * device is bound, and that proper suspend and resume ordering is guaranteed. + * + * This function does essentially the same as ssam_client_link(), except that + * it first fetches the main controller reference, then creates the link, and + * finally returns this reference. Note that this function does not increment + * the reference counter of the controller, as, due to the link, the + * controller lifetime is assured as long as the driver of the client device + * is bound. + * + * It is not valid to use the controller reference obtained by this method + * outside of the driver bound to the client device at the time of calling + * this function, without first incrementing the reference count of the + * controller via ssam_controller_get(). Even after doing this, care must be + * taken that requests are only submitted and notifiers are only + * (un-)registered when the controller is active and not suspended. In other + * words: The device link only lives as long as the client driver is bound and + * any guarantees enforced by this link (e.g. active controller state) can + * only be relied upon as long as this link exists and may need to be enforced + * in other ways afterwards. + * + * The created device link does not have to be destructed manually. It is + * removed automatically once the driver of the client device unbinds. + * + * Return: Returns the controller on success, an error pointer with %-ENODEV + * if the controller is not present, not ready or going to be removed soon, or + * %-ENOMEM if the device link could not be created for other reasons. + */ +struct ssam_controller *ssam_client_bind(struct device *client) +{ + struct ssam_controller *c; + int status; + + c = ssam_get_controller(); + if (!c) + return ERR_PTR(-ENODEV); + + status = ssam_client_link(c, client); + + /* + * Note that we can drop our controller reference in both success and + * failure cases: On success, we have bound the controller lifetime + * inherently to the client driver lifetime, i.e. it the controller is + * now guaranteed to outlive the client driver. On failure, we're not + * going to use the controller any more. + */ + ssam_controller_put(c); + + return status >= 0 ? c : ERR_PTR(status); +} +EXPORT_SYMBOL_GPL(ssam_client_bind); + + +/* -- Glue layer (serdev_device -> ssam_controller). ------------------------ */ + +static int ssam_receive_buf(struct serdev_device *dev, const unsigned char *buf, + size_t n) +{ + struct ssam_controller *ctrl; + + ctrl = serdev_device_get_drvdata(dev); + return ssam_controller_receive_buf(ctrl, buf, n); +} + +static void ssam_write_wakeup(struct serdev_device *dev) +{ + ssam_controller_write_wakeup(serdev_device_get_drvdata(dev)); +} + +static const struct serdev_device_ops ssam_serdev_ops = { + .receive_buf = ssam_receive_buf, + .write_wakeup = ssam_write_wakeup, +}; + + +/* -- SysFS and misc. ------------------------------------------------------- */ + +static int ssam_log_firmware_version(struct ssam_controller *ctrl) +{ + u32 version, a, b, c; + int status; + + status = ssam_get_firmware_version(ctrl, &version); + if (status) + return status; + + a = (version >> 24) & 0xff; + b = ((version >> 8) & 0xffff); + c = version & 0xff; + + ssam_info(ctrl, "SAM firmware version: %u.%u.%u\n", a, b, c); + return 0; +} + +static ssize_t firmware_version_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct ssam_controller *ctrl = dev_get_drvdata(dev); + u32 version, a, b, c; + int status; + + status = ssam_get_firmware_version(ctrl, &version); + if (status < 0) + return status; + + a = (version >> 24) & 0xff; + b = ((version >> 8) & 0xffff); + c = version & 0xff; + + return sysfs_emit(buf, "%u.%u.%u\n", a, b, c); +} +static DEVICE_ATTR_RO(firmware_version); + +static struct attribute *ssam_sam_attrs[] = { + &dev_attr_firmware_version.attr, + NULL +}; + +static const struct attribute_group ssam_sam_group = { + .name = "sam", + .attrs = ssam_sam_attrs, +}; + + +/* -- ACPI based device setup. ---------------------------------------------- */ + +static acpi_status ssam_serdev_setup_via_acpi_crs(struct acpi_resource *rsc, + void *ctx) +{ + struct serdev_device *serdev = ctx; + struct acpi_resource_common_serialbus *serial; + struct acpi_resource_uart_serialbus *uart; + bool flow_control; + int status = 0; + + if (rsc->type != ACPI_RESOURCE_TYPE_SERIAL_BUS) + return AE_OK; + + serial = &rsc->data.common_serial_bus; + if (serial->type != ACPI_RESOURCE_SERIAL_TYPE_UART) + return AE_OK; + + uart = &rsc->data.uart_serial_bus; + + /* Set up serdev device. */ + serdev_device_set_baudrate(serdev, uart->default_baud_rate); + + /* serdev currently only supports RTSCTS flow control. */ + if (uart->flow_control & (~((u8)ACPI_UART_FLOW_CONTROL_HW))) { + dev_warn(&serdev->dev, "setup: unsupported flow control (value: %#04x)\n", + uart->flow_control); + } + + /* Set RTSCTS flow control. */ + flow_control = uart->flow_control & ACPI_UART_FLOW_CONTROL_HW; + serdev_device_set_flow_control(serdev, flow_control); + + /* serdev currently only supports EVEN/ODD parity. */ + switch (uart->parity) { + case ACPI_UART_PARITY_NONE: + status = serdev_device_set_parity(serdev, SERDEV_PARITY_NONE); + break; + case ACPI_UART_PARITY_EVEN: + status = serdev_device_set_parity(serdev, SERDEV_PARITY_EVEN); + break; + case ACPI_UART_PARITY_ODD: + status = serdev_device_set_parity(serdev, SERDEV_PARITY_ODD); + break; + default: + dev_warn(&serdev->dev, "setup: unsupported parity (value: %#04x)\n", + uart->parity); + break; + } + + if (status) { + dev_err(&serdev->dev, "setup: failed to set parity (value: %#04x, error: %d)\n", + uart->parity, status); + return AE_ERROR; + } + + /* We've found the resource and are done. */ + return AE_CTRL_TERMINATE; +} + +static acpi_status ssam_serdev_setup_via_acpi(acpi_handle handle, + struct serdev_device *serdev) +{ + return acpi_walk_resources(handle, METHOD_NAME__CRS, + ssam_serdev_setup_via_acpi_crs, serdev); +} + + +/* -- Power management. ----------------------------------------------------- */ + +static void ssam_serial_hub_shutdown(struct device *dev) +{ + struct ssam_controller *c = dev_get_drvdata(dev); + int status; + + /* + * Try to disable notifiers, signal display-off and D0-exit, ignore any + * errors. + * + * Note: It has not been established yet if this is actually + * necessary/useful for shutdown. + */ + + status = ssam_notifier_disable_registered(c); + if (status) { + ssam_err(c, "pm: failed to disable notifiers for shutdown: %d\n", + status); + } + + status = ssam_ctrl_notif_display_off(c); + if (status) + ssam_err(c, "pm: display-off notification failed: %d\n", status); + + status = ssam_ctrl_notif_d0_exit(c); + if (status) + ssam_err(c, "pm: D0-exit notification failed: %d\n", status); +} + +#ifdef CONFIG_PM_SLEEP + +static int ssam_serial_hub_pm_prepare(struct device *dev) +{ + struct ssam_controller *c = dev_get_drvdata(dev); + int status; + + /* + * Try to signal display-off, This will quiesce events. + * + * Note: Signaling display-off/display-on should normally be done from + * some sort of display state notifier. As that is not available, + * signal it here. + */ + + status = ssam_ctrl_notif_display_off(c); + if (status) + ssam_err(c, "pm: display-off notification failed: %d\n", status); + + return status; +} + +static void ssam_serial_hub_pm_complete(struct device *dev) +{ + struct ssam_controller *c = dev_get_drvdata(dev); + int status; + + /* + * Try to signal display-on. This will restore events. + * + * Note: Signaling display-off/display-on should normally be done from + * some sort of display state notifier. As that is not available, + * signal it here. + */ + + status = ssam_ctrl_notif_display_on(c); + if (status) + ssam_err(c, "pm: display-on notification failed: %d\n", status); +} + +static int ssam_serial_hub_pm_suspend(struct device *dev) +{ + struct ssam_controller *c = dev_get_drvdata(dev); + int status; + + /* + * Try to signal D0-exit, enable IRQ wakeup if specified. Abort on + * error. + */ + + status = ssam_ctrl_notif_d0_exit(c); + if (status) { + ssam_err(c, "pm: D0-exit notification failed: %d\n", status); + goto err_notif; + } + + status = ssam_irq_arm_for_wakeup(c); + if (status) + goto err_irq; + + WARN_ON(ssam_controller_suspend(c)); + return 0; + +err_irq: + ssam_ctrl_notif_d0_entry(c); +err_notif: + ssam_ctrl_notif_display_on(c); + return status; +} + +static int ssam_serial_hub_pm_resume(struct device *dev) +{ + struct ssam_controller *c = dev_get_drvdata(dev); + int status; + + WARN_ON(ssam_controller_resume(c)); + + /* + * Try to disable IRQ wakeup (if specified) and signal D0-entry. In + * case of errors, log them and try to restore normal operation state + * as far as possible. + * + * Note: Signaling display-off/display-on should normally be done from + * some sort of display state notifier. As that is not available, + * signal it here. + */ + + ssam_irq_disarm_wakeup(c); + + status = ssam_ctrl_notif_d0_entry(c); + if (status) + ssam_err(c, "pm: D0-entry notification failed: %d\n", status); + + return 0; +} + +static int ssam_serial_hub_pm_freeze(struct device *dev) +{ + struct ssam_controller *c = dev_get_drvdata(dev); + int status; + + /* + * During hibernation image creation, we only have to ensure that the + * EC doesn't send us any events. This is done via the display-off + * and D0-exit notifications. Note that this sets up the wakeup IRQ + * on the EC side, however, we have disabled it by default on our side + * and won't enable it here. + * + * See ssam_serial_hub_poweroff() for more details on the hibernation + * process. + */ + + status = ssam_ctrl_notif_d0_exit(c); + if (status) { + ssam_err(c, "pm: D0-exit notification failed: %d\n", status); + ssam_ctrl_notif_display_on(c); + return status; + } + + WARN_ON(ssam_controller_suspend(c)); + return 0; +} + +static int ssam_serial_hub_pm_thaw(struct device *dev) +{ + struct ssam_controller *c = dev_get_drvdata(dev); + int status; + + WARN_ON(ssam_controller_resume(c)); + + status = ssam_ctrl_notif_d0_entry(c); + if (status) + ssam_err(c, "pm: D0-exit notification failed: %d\n", status); + + return status; +} + +static int ssam_serial_hub_pm_poweroff(struct device *dev) +{ + struct ssam_controller *c = dev_get_drvdata(dev); + int status; + + /* + * When entering hibernation and powering off the system, the EC, at + * least on some models, may disable events. Without us taking care of + * that, this leads to events not being enabled/restored when the + * system resumes from hibernation, resulting SAM-HID subsystem devices + * (i.e. keyboard, touchpad) not working, AC-plug/AC-unplug events being + * gone, etc. + * + * To avoid these issues, we disable all registered events here (this is + * likely not actually required) and restore them during the drivers PM + * restore callback. + * + * Wakeup from the EC interrupt is not supported during hibernation, + * so don't arm the IRQ here. + */ + + status = ssam_notifier_disable_registered(c); + if (status) { + ssam_err(c, "pm: failed to disable notifiers for hibernation: %d\n", + status); + return status; + } + + status = ssam_ctrl_notif_d0_exit(c); + if (status) { + ssam_err(c, "pm: D0-exit notification failed: %d\n", status); + ssam_notifier_restore_registered(c); + return status; + } + + WARN_ON(ssam_controller_suspend(c)); + return 0; +} + +static int ssam_serial_hub_pm_restore(struct device *dev) +{ + struct ssam_controller *c = dev_get_drvdata(dev); + int status; + + /* + * Ignore but log errors, try to restore state as much as possible in + * case of failures. See ssam_serial_hub_poweroff() for more details on + * the hibernation process. + */ + + WARN_ON(ssam_controller_resume(c)); + + status = ssam_ctrl_notif_d0_entry(c); + if (status) + ssam_err(c, "pm: D0-entry notification failed: %d\n", status); + + ssam_notifier_restore_registered(c); + return 0; +} + +static const struct dev_pm_ops ssam_serial_hub_pm_ops = { + .prepare = ssam_serial_hub_pm_prepare, + .complete = ssam_serial_hub_pm_complete, + .suspend = ssam_serial_hub_pm_suspend, + .resume = ssam_serial_hub_pm_resume, + .freeze = ssam_serial_hub_pm_freeze, + .thaw = ssam_serial_hub_pm_thaw, + .poweroff = ssam_serial_hub_pm_poweroff, + .restore = ssam_serial_hub_pm_restore, +}; + +#else /* CONFIG_PM_SLEEP */ + +static const struct dev_pm_ops ssam_serial_hub_pm_ops = { }; + +#endif /* CONFIG_PM_SLEEP */ + + +/* -- Device/driver setup. -------------------------------------------------- */ + +static const struct acpi_gpio_params gpio_ssam_wakeup_int = { 0, 0, false }; +static const struct acpi_gpio_params gpio_ssam_wakeup = { 1, 0, false }; + +static const struct acpi_gpio_mapping ssam_acpi_gpios[] = { + { "ssam_wakeup-int-gpio", &gpio_ssam_wakeup_int, 1 }, + { "ssam_wakeup-gpio", &gpio_ssam_wakeup, 1 }, + { }, +}; + +static int ssam_serial_hub_probe(struct serdev_device *serdev) +{ + struct ssam_controller *ctrl; + acpi_handle *ssh = ACPI_HANDLE(&serdev->dev); + acpi_status astatus; + int status; + + if (gpiod_count(&serdev->dev, NULL) < 0) + return -ENODEV; + + status = devm_acpi_dev_add_driver_gpios(&serdev->dev, ssam_acpi_gpios); + if (status) + return status; + + /* Allocate controller. */ + ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL); + if (!ctrl) + return -ENOMEM; + + /* Initialize controller. */ + status = ssam_controller_init(ctrl, serdev); + if (status) + goto err_ctrl_init; + + ssam_controller_lock(ctrl); + + /* Set up serdev device. */ + serdev_device_set_drvdata(serdev, ctrl); + serdev_device_set_client_ops(serdev, &ssam_serdev_ops); + status = serdev_device_open(serdev); + if (status) + goto err_devopen; + + astatus = ssam_serdev_setup_via_acpi(ssh, serdev); + if (ACPI_FAILURE(astatus)) { + status = -ENXIO; + goto err_devinit; + } + + /* Start controller. */ + status = ssam_controller_start(ctrl); + if (status) + goto err_devinit; + + ssam_controller_unlock(ctrl); + + /* + * Initial SAM requests: Log version and notify default/init power + * states. + */ + status = ssam_log_firmware_version(ctrl); + if (status) + goto err_initrq; + + status = ssam_ctrl_notif_d0_entry(ctrl); + if (status) + goto err_initrq; + + status = ssam_ctrl_notif_display_on(ctrl); + if (status) + goto err_initrq; + + status = sysfs_create_group(&serdev->dev.kobj, &ssam_sam_group); + if (status) + goto err_initrq; + + /* Set up IRQ. */ + status = ssam_irq_setup(ctrl); + if (status) + goto err_irq; + + /* Finally, set main controller reference. */ + status = ssam_try_set_controller(ctrl); + if (WARN_ON(status)) /* Currently, we're the only provider. */ + goto err_mainref; + + /* + * TODO: The EC can wake up the system via the associated GPIO interrupt + * in multiple situations. One of which is the remaining battery + * capacity falling below a certain threshold. Normally, we should + * use the device_init_wakeup function, however, the EC also seems + * to have other reasons for waking up the system and it seems + * that Windows has additional checks whether the system should be + * resumed. In short, this causes some spurious unwanted wake-ups. + * For now let's thus default power/wakeup to false. + */ + device_set_wakeup_capable(&serdev->dev, true); + acpi_walk_dep_device_list(ssh); + + return 0; + +err_mainref: + ssam_irq_free(ctrl); +err_irq: + sysfs_remove_group(&serdev->dev.kobj, &ssam_sam_group); +err_initrq: + ssam_controller_lock(ctrl); + ssam_controller_shutdown(ctrl); +err_devinit: + serdev_device_close(serdev); +err_devopen: + ssam_controller_destroy(ctrl); + ssam_controller_unlock(ctrl); +err_ctrl_init: + kfree(ctrl); + return status; +} + +static void ssam_serial_hub_remove(struct serdev_device *serdev) +{ + struct ssam_controller *ctrl = serdev_device_get_drvdata(serdev); + int status; + + /* Clear static reference so that no one else can get a new one. */ + ssam_clear_controller(); + + /* Disable and free IRQ. */ + ssam_irq_free(ctrl); + + sysfs_remove_group(&serdev->dev.kobj, &ssam_sam_group); + ssam_controller_lock(ctrl); + + /* Act as if suspending to silence events. */ + status = ssam_ctrl_notif_display_off(ctrl); + if (status) { + dev_err(&serdev->dev, "display-off notification failed: %d\n", + status); + } + + status = ssam_ctrl_notif_d0_exit(ctrl); + if (status) { + dev_err(&serdev->dev, "D0-exit notification failed: %d\n", + status); + } + + /* Shut down controller and remove serdev device reference from it. */ + ssam_controller_shutdown(ctrl); + + /* Shut down actual transport. */ + serdev_device_wait_until_sent(serdev, 0); + serdev_device_close(serdev); + + /* Drop our controller reference. */ + ssam_controller_unlock(ctrl); + ssam_controller_put(ctrl); + + device_set_wakeup_capable(&serdev->dev, false); +} + +static const struct acpi_device_id ssam_serial_hub_match[] = { + { "MSHW0084", 0 }, + { }, +}; +MODULE_DEVICE_TABLE(acpi, ssam_serial_hub_match); + +static struct serdev_device_driver ssam_serial_hub = { + .probe = ssam_serial_hub_probe, + .remove = ssam_serial_hub_remove, + .driver = { + .name = "surface_serial_hub", + .acpi_match_table = ssam_serial_hub_match, + .pm = &ssam_serial_hub_pm_ops, + .shutdown = ssam_serial_hub_shutdown, + .probe_type = PROBE_PREFER_ASYNCHRONOUS, + }, +}; +module_serdev_device_driver(ssam_serial_hub); + +MODULE_AUTHOR("Maximilian Luz "); +MODULE_DESCRIPTION("Subsystem and Surface Serial Hub driver for Surface System Aggregator Module"); +MODULE_LICENSE("GPL"); diff --git a/drivers/platform/surface/aggregator/ssh_msgb.h b/drivers/platform/surface/aggregator/ssh_msgb.h new file mode 100644 index 000000000000..1221f642dda1 --- /dev/null +++ b/drivers/platform/surface/aggregator/ssh_msgb.h @@ -0,0 +1,205 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * SSH message builder functions. + * + * Copyright (C) 2019-2020 Maximilian Luz + */ + +#ifndef _SURFACE_AGGREGATOR_SSH_MSGB_H +#define _SURFACE_AGGREGATOR_SSH_MSGB_H + +#include +#include + +#include +#include + +/** + * struct msgbuf - Buffer struct to construct SSH messages. + * @begin: Pointer to the beginning of the allocated buffer space. + * @end: Pointer to the end (one past last element) of the allocated buffer + * space. + * @ptr: Pointer to the first free element in the buffer. + */ +struct msgbuf { + u8 *begin; + u8 *end; + u8 *ptr; +}; + +/** + * msgb_init() - Initialize the given message buffer struct. + * @msgb: The buffer struct to initialize + * @ptr: Pointer to the underlying memory by which the buffer will be backed. + * @cap: Size of the underlying memory. + * + * Initialize the given message buffer struct using the provided memory as + * backing. + */ +static inline void msgb_init(struct msgbuf *msgb, u8 *ptr, size_t cap) +{ + msgb->begin = ptr; + msgb->end = ptr + cap; + msgb->ptr = ptr; +} + +/** + * msgb_bytes_used() - Return the current number of bytes used in the buffer. + * @msgb: The message buffer. + */ +static inline size_t msgb_bytes_used(const struct msgbuf *msgb) +{ + return msgb->ptr - msgb->begin; +} + +static inline void __msgb_push_u8(struct msgbuf *msgb, u8 value) +{ + *msgb->ptr = value; + msgb->ptr += sizeof(u8); +} + +static inline void __msgb_push_u16(struct msgbuf *msgb, u16 value) +{ + put_unaligned_le16(value, msgb->ptr); + msgb->ptr += sizeof(u16); +} + +/** + * msgb_push_u16() - Push a u16 value to the buffer. + * @msgb: The message buffer. + * @value: The value to push to the buffer. + */ +static inline void msgb_push_u16(struct msgbuf *msgb, u16 value) +{ + if (WARN_ON(msgb->ptr + sizeof(u16) > msgb->end)) + return; + + __msgb_push_u16(msgb, value); +} + +/** + * msgb_push_syn() - Push SSH SYN bytes to the buffer. + * @msgb: The message buffer. + */ +static inline void msgb_push_syn(struct msgbuf *msgb) +{ + msgb_push_u16(msgb, SSH_MSG_SYN); +} + +/** + * msgb_push_buf() - Push raw data to the buffer. + * @msgb: The message buffer. + * @buf: The data to push to the buffer. + * @len: The length of the data to push to the buffer. + */ +static inline void msgb_push_buf(struct msgbuf *msgb, const u8 *buf, size_t len) +{ + msgb->ptr = memcpy(msgb->ptr, buf, len) + len; +} + +/** + * msgb_push_crc() - Compute CRC and push it to the buffer. + * @msgb: The message buffer. + * @buf: The data for which the CRC should be computed. + * @len: The length of the data for which the CRC should be computed. + */ +static inline void msgb_push_crc(struct msgbuf *msgb, const u8 *buf, size_t len) +{ + msgb_push_u16(msgb, ssh_crc(buf, len)); +} + +/** + * msgb_push_frame() - Push a SSH message frame header to the buffer. + * @msgb: The message buffer + * @ty: The type of the frame. + * @len: The length of the payload of the frame. + * @seq: The sequence ID of the frame/packet. + */ +static inline void msgb_push_frame(struct msgbuf *msgb, u8 ty, u16 len, u8 seq) +{ + u8 *const begin = msgb->ptr; + + if (WARN_ON(msgb->ptr + sizeof(struct ssh_frame) > msgb->end)) + return; + + __msgb_push_u8(msgb, ty); /* Frame type. */ + __msgb_push_u16(msgb, len); /* Frame payload length. */ + __msgb_push_u8(msgb, seq); /* Frame sequence ID. */ + + msgb_push_crc(msgb, begin, msgb->ptr - begin); +} + +/** + * msgb_push_ack() - Push a SSH ACK frame to the buffer. + * @msgb: The message buffer + * @seq: The sequence ID of the frame/packet to be ACKed. + */ +static inline void msgb_push_ack(struct msgbuf *msgb, u8 seq) +{ + /* SYN. */ + msgb_push_syn(msgb); + + /* ACK-type frame + CRC. */ + msgb_push_frame(msgb, SSH_FRAME_TYPE_ACK, 0x00, seq); + + /* Payload CRC (ACK-type frames do not have a payload). */ + msgb_push_crc(msgb, msgb->ptr, 0); +} + +/** + * msgb_push_nak() - Push a SSH NAK frame to the buffer. + * @msgb: The message buffer + */ +static inline void msgb_push_nak(struct msgbuf *msgb) +{ + /* SYN. */ + msgb_push_syn(msgb); + + /* NAK-type frame + CRC. */ + msgb_push_frame(msgb, SSH_FRAME_TYPE_NAK, 0x00, 0x00); + + /* Payload CRC (ACK-type frames do not have a payload). */ + msgb_push_crc(msgb, msgb->ptr, 0); +} + +/** + * msgb_push_cmd() - Push a SSH command frame with payload to the buffer. + * @msgb: The message buffer. + * @seq: The sequence ID (SEQ) of the frame/packet. + * @rqid: The request ID (RQID) of the request contained in the frame. + * @rqst: The request to wrap in the frame. + */ +static inline void msgb_push_cmd(struct msgbuf *msgb, u8 seq, u16 rqid, + const struct ssam_request *rqst) +{ + const u8 type = SSH_FRAME_TYPE_DATA_SEQ; + u8 *cmd; + + /* SYN. */ + msgb_push_syn(msgb); + + /* Command frame + CRC. */ + msgb_push_frame(msgb, type, sizeof(struct ssh_command) + rqst->length, seq); + + /* Frame payload: Command struct + payload. */ + if (WARN_ON(msgb->ptr + sizeof(struct ssh_command) > msgb->end)) + return; + + cmd = msgb->ptr; + + __msgb_push_u8(msgb, SSH_PLD_TYPE_CMD); /* Payload type. */ + __msgb_push_u8(msgb, rqst->target_category); /* Target category. */ + __msgb_push_u8(msgb, rqst->target_id); /* Target ID (out). */ + __msgb_push_u8(msgb, 0x00); /* Target ID (in). */ + __msgb_push_u8(msgb, rqst->instance_id); /* Instance ID. */ + __msgb_push_u16(msgb, rqid); /* Request ID. */ + __msgb_push_u8(msgb, rqst->command_id); /* Command ID. */ + + /* Command payload. */ + msgb_push_buf(msgb, rqst->payload, rqst->length); + + /* CRC for command struct + payload. */ + msgb_push_crc(msgb, cmd, msgb->ptr - cmd); +} + +#endif /* _SURFACE_AGGREGATOR_SSH_MSGB_H */ diff --git a/drivers/platform/surface/aggregator/ssh_packet_layer.c b/drivers/platform/surface/aggregator/ssh_packet_layer.c new file mode 100644 index 000000000000..66e38fdc7963 --- /dev/null +++ b/drivers/platform/surface/aggregator/ssh_packet_layer.c @@ -0,0 +1,1710 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * SSH packet transport layer. + * + * Copyright (C) 2019-2020 Maximilian Luz + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "ssh_msgb.h" +#include "ssh_packet_layer.h" +#include "ssh_parser.h" + +/* + * To simplify reasoning about the code below, we define a few concepts. The + * system below is similar to a state-machine for packets, however, there are + * too many states to explicitly write them down. To (somewhat) manage the + * states and packets we rely on flags, reference counting, and some simple + * concepts. State transitions are triggered by actions. + * + * >> Actions << + * + * - submit + * - transmission start (process next item in queue) + * - transmission finished (guaranteed to never be parallel to transmission + * start) + * - ACK received + * - NAK received (this is equivalent to issuing re-submit for all pending + * packets) + * - timeout (this is equivalent to re-issuing a submit or canceling) + * - cancel (non-pending and pending) + * + * >> Data Structures, Packet Ownership, General Overview << + * + * The code below employs two main data structures: The packet queue, + * containing all packets scheduled for transmission, and the set of pending + * packets, containing all packets awaiting an ACK. + * + * Shared ownership of a packet is controlled via reference counting. Inside + * the transport system are a total of five packet owners: + * + * - the packet queue, + * - the pending set, + * - the transmitter thread, + * - the receiver thread (via ACKing), and + * - the timeout work item. + * + * Normal operation is as follows: The initial reference of the packet is + * obtained by submitting the packet and queuing it. The receiver thread takes + * packets from the queue. By doing this, it does not increment the refcount + * but takes over the reference (removing it from the queue). If the packet is + * sequenced (i.e. needs to be ACKed by the client), the transmitter thread + * sets-up the timeout and adds the packet to the pending set before starting + * to transmit it. As the timeout is handled by a reaper task, no additional + * reference for it is needed. After the transmit is done, the reference held + * by the transmitter thread is dropped. If the packet is unsequenced (i.e. + * does not need an ACK), the packet is completed by the transmitter thread + * before dropping that reference. + * + * On receival of an ACK, the receiver thread removes and obtains the + * reference to the packet from the pending set. The receiver thread will then + * complete the packet and drop its reference. + * + * On receival of a NAK, the receiver thread re-submits all currently pending + * packets. + * + * Packet timeouts are detected by the timeout reaper. This is a task, + * scheduled depending on the earliest packet timeout expiration date, + * checking all currently pending packets if their timeout has expired. If the + * timeout of a packet has expired, it is re-submitted and the number of tries + * of this packet is incremented. If this number reaches its limit, the packet + * will be completed with a failure. + * + * On transmission failure (such as repeated packet timeouts), the completion + * callback is immediately run by on thread on which the error was detected. + * + * To ensure that a packet eventually leaves the system it is marked as + * "locked" directly before it is going to be completed or when it is + * canceled. Marking a packet as "locked" has the effect that passing and + * creating new references of the packet is disallowed. This means that the + * packet cannot be added to the queue, the pending set, and the timeout, or + * be picked up by the transmitter thread or receiver thread. To remove a + * packet from the system it has to be marked as locked and subsequently all + * references from the data structures (queue, pending) have to be removed. + * References held by threads will eventually be dropped automatically as + * their execution progresses. + * + * Note that the packet completion callback is, in case of success and for a + * sequenced packet, guaranteed to run on the receiver thread, thus providing + * a way to reliably identify responses to the packet. The packet completion + * callback is only run once and it does not indicate that the packet has + * fully left the system (for this, one should rely on the release method, + * triggered when the reference count of the packet reaches zero). In case of + * re-submission (and with somewhat unlikely timing), it may be possible that + * the packet is being re-transmitted while the completion callback runs. + * Completion will occur both on success and internal error, as well as when + * the packet is canceled. + * + * >> Flags << + * + * Flags are used to indicate the state and progression of a packet. Some flags + * have stricter guarantees than other: + * + * - locked + * Indicates if the packet is locked. If the packet is locked, passing and/or + * creating additional references to the packet is forbidden. The packet thus + * may not be queued, dequeued, or removed or added to the pending set. Note + * that the packet state flags may still change (e.g. it may be marked as + * ACKed, transmitted, ...). + * + * - completed + * Indicates if the packet completion callback has been executed or is about + * to be executed. This flag is used to ensure that the packet completion + * callback is only run once. + * + * - queued + * Indicates if a packet is present in the submission queue or not. This flag + * must only be modified with the queue lock held, and must be coherent to the + * presence of the packet in the queue. + * + * - pending + * Indicates if a packet is present in the set of pending packets or not. + * This flag must only be modified with the pending lock held, and must be + * coherent to the presence of the packet in the pending set. + * + * - transmitting + * Indicates if the packet is currently transmitting. In case of + * re-transmissions, it is only safe to wait on the "transmitted" completion + * after this flag has been set. The completion will be set both in success + * and error case. + * + * - transmitted + * Indicates if the packet has been transmitted. This flag is not cleared by + * the system, thus it indicates the first transmission only. + * + * - acked + * Indicates if the packet has been acknowledged by the client. There are no + * other guarantees given. For example, the packet may still be canceled + * and/or the completion may be triggered an error even though this bit is + * set. Rely on the status provided to the completion callback instead. + * + * - canceled + * Indicates if the packet has been canceled from the outside. There are no + * other guarantees given. Specifically, the packet may be completed by + * another part of the system before the cancellation attempts to complete it. + * + * >> General Notes << + * + * - To avoid deadlocks, if both queue and pending locks are required, the + * pending lock must be acquired before the queue lock. + * + * - The packet priority must be accessed only while holding the queue lock. + * + * - The packet timestamp must be accessed only while holding the pending + * lock. + */ + +/* + * SSH_PTL_MAX_PACKET_TRIES - Maximum transmission attempts for packet. + * + * Maximum number of transmission attempts per sequenced packet in case of + * time-outs. Must be smaller than 16. If the packet times out after this + * amount of tries, the packet will be completed with %-ETIMEDOUT as status + * code. + */ +#define SSH_PTL_MAX_PACKET_TRIES 3 + +/* + * SSH_PTL_TX_TIMEOUT - Packet transmission timeout. + * + * Timeout in jiffies for packet transmission via the underlying serial + * device. If transmitting the packet takes longer than this timeout, the + * packet will be completed with -ETIMEDOUT. It will not be re-submitted. + */ +#define SSH_PTL_TX_TIMEOUT HZ + +/* + * SSH_PTL_PACKET_TIMEOUT - Packet response timeout. + * + * Timeout as ktime_t delta for ACKs. If we have not received an ACK in this + * time-frame after starting transmission, the packet will be re-submitted. + */ +#define SSH_PTL_PACKET_TIMEOUT ms_to_ktime(1000) + +/* + * SSH_PTL_PACKET_TIMEOUT_RESOLUTION - Packet timeout granularity. + * + * Time-resolution for timeouts. Should be larger than one jiffy to avoid + * direct re-scheduling of reaper work_struct. + */ +#define SSH_PTL_PACKET_TIMEOUT_RESOLUTION ms_to_ktime(max(2000 / HZ, 50)) + +/* + * SSH_PTL_MAX_PENDING - Maximum number of pending packets. + * + * Maximum number of sequenced packets concurrently waiting for an ACK. + * Packets marked as blocking will not be transmitted while this limit is + * reached. + */ +#define SSH_PTL_MAX_PENDING 1 + +/* + * SSH_PTL_RX_BUF_LEN - Evaluation-buffer size in bytes. + */ +#define SSH_PTL_RX_BUF_LEN 4096 + +/* + * SSH_PTL_RX_FIFO_LEN - Fifo input-buffer size in bytes. + */ +#define SSH_PTL_RX_FIFO_LEN 4096 + +static void __ssh_ptl_packet_release(struct kref *kref) +{ + struct ssh_packet *p = container_of(kref, struct ssh_packet, refcnt); + + ptl_dbg_cond(p->ptl, "ptl: releasing packet %p\n", p); + p->ops->release(p); +} + +/** + * ssh_packet_get() - Increment reference count of packet. + * @packet: The packet to increment the reference count of. + * + * Increments the reference count of the given packet. See ssh_packet_put() + * for the counter-part of this function. + * + * Return: Returns the packet provided as input. + */ +struct ssh_packet *ssh_packet_get(struct ssh_packet *packet) +{ + if (packet) + kref_get(&packet->refcnt); + return packet; +} +EXPORT_SYMBOL_GPL(ssh_packet_get); + +/** + * ssh_packet_put() - Decrement reference count of packet. + * @packet: The packet to decrement the reference count of. + * + * If the reference count reaches zero, the ``release`` callback specified in + * the packet's &struct ssh_packet_ops, i.e. ``packet->ops->release``, will be + * called. + * + * See ssh_packet_get() for the counter-part of this function. + */ +void ssh_packet_put(struct ssh_packet *packet) +{ + if (packet) + kref_put(&packet->refcnt, __ssh_ptl_packet_release); +} +EXPORT_SYMBOL_GPL(ssh_packet_put); + +static u8 ssh_packet_get_seq(struct ssh_packet *packet) +{ + return packet->data.ptr[SSH_MSGOFFSET_FRAME(seq)]; +} + +/** + * ssh_packet_init() - Initialize SSH packet. + * @packet: The packet to initialize. + * @type: Type-flags of the packet. + * @priority: Priority of the packet. See SSH_PACKET_PRIORITY() for details. + * @ops: Packet operations. + * + * Initializes the given SSH packet. Sets the transmission buffer pointer to + * %NULL and the transmission buffer length to zero. For data-type packets, + * this buffer has to be set separately via ssh_packet_set_data() before + * submission, and must contain a valid SSH message, i.e. frame with optional + * payload of any type. + */ +void ssh_packet_init(struct ssh_packet *packet, unsigned long type, + u8 priority, const struct ssh_packet_ops *ops) +{ + kref_init(&packet->refcnt); + + packet->ptl = NULL; + INIT_LIST_HEAD(&packet->queue_node); + INIT_LIST_HEAD(&packet->pending_node); + + packet->state = type & SSH_PACKET_FLAGS_TY_MASK; + packet->priority = priority; + packet->timestamp = KTIME_MAX; + + packet->data.ptr = NULL; + packet->data.len = 0; + + packet->ops = ops; +} + +/** + * ssh_ctrl_packet_alloc() - Allocate control packet. + * @packet: Where the pointer to the newly allocated packet should be stored. + * @buffer: The buffer corresponding to this packet. + * @flags: Flags used for allocation. + * + * Allocates a packet and corresponding transport buffer. Sets the packet's + * buffer reference to the allocated buffer. The packet must be freed via + * ssh_ctrl_packet_free(), which will also free the corresponding buffer. The + * corresponding buffer must not be freed separately. Intended to be used with + * %ssh_ptl_ctrl_packet_ops as packet operations. + * + * Return: Returns zero on success, %-ENOMEM if the allocation failed. + */ +static int ssh_ctrl_packet_alloc(struct ssh_packet **packet, + struct ssam_span *buffer, gfp_t flags) +{ + *packet = kzalloc(sizeof(**packet) + SSH_MSG_LEN_CTRL, flags); + if (!*packet) + return -ENOMEM; + + buffer->ptr = (u8 *)(*packet + 1); + buffer->len = SSH_MSG_LEN_CTRL; + + return 0; +} + +/** + * ssh_ctrl_packet_free() - Free control packet. + * @p: The packet to free. + */ +static void ssh_ctrl_packet_free(struct ssh_packet *p) +{ + kfree(p); +} + +static const struct ssh_packet_ops ssh_ptl_ctrl_packet_ops = { + .complete = NULL, + .release = ssh_ctrl_packet_free, +}; + +static void ssh_ptl_timeout_reaper_mod(struct ssh_ptl *ptl, ktime_t now, + ktime_t expires) +{ + unsigned long delta = msecs_to_jiffies(ktime_ms_delta(expires, now)); + ktime_t aexp = ktime_add(expires, SSH_PTL_PACKET_TIMEOUT_RESOLUTION); + + spin_lock(&ptl->rtx_timeout.lock); + + /* Re-adjust / schedule reaper only if it is above resolution delta. */ + if (ktime_before(aexp, ptl->rtx_timeout.expires)) { + ptl->rtx_timeout.expires = expires; + mod_delayed_work(system_wq, &ptl->rtx_timeout.reaper, delta); + } + + spin_unlock(&ptl->rtx_timeout.lock); +} + +/* Must be called with queue lock held. */ +static void ssh_packet_next_try(struct ssh_packet *p) +{ + u8 base = ssh_packet_priority_get_base(p->priority); + u8 try = ssh_packet_priority_get_try(p->priority); + + lockdep_assert_held(&p->ptl->queue.lock); + + p->priority = __SSH_PACKET_PRIORITY(base, try + 1); +} + +/* Must be called with queue lock held. */ +static struct list_head *__ssh_ptl_queue_find_entrypoint(struct ssh_packet *p) +{ + struct list_head *head; + struct ssh_packet *q; + + lockdep_assert_held(&p->ptl->queue.lock); + + /* + * We generally assume that there are less control (ACK/NAK) packets + * and re-submitted data packets as there are normal data packets (at + * least in situations in which many packets are queued; if there + * aren't many packets queued the decision on how to iterate should be + * basically irrelevant; the number of control/data packets is more or + * less limited via the maximum number of pending packets). Thus, when + * inserting a control or re-submitted data packet, (determined by + * their priority), we search from front to back. Normal data packets + * are, usually queued directly at the tail of the queue, so for those + * search from back to front. + */ + + if (p->priority > SSH_PACKET_PRIORITY(DATA, 0)) { + list_for_each(head, &p->ptl->queue.head) { + q = list_entry(head, struct ssh_packet, queue_node); + + if (q->priority < p->priority) + break; + } + } else { + list_for_each_prev(head, &p->ptl->queue.head) { + q = list_entry(head, struct ssh_packet, queue_node); + + if (q->priority >= p->priority) { + head = head->next; + break; + } + } + } + + return head; +} + +/* Must be called with queue lock held. */ +static int __ssh_ptl_queue_push(struct ssh_packet *packet) +{ + struct ssh_ptl *ptl = packet->ptl; + struct list_head *head; + + lockdep_assert_held(&ptl->queue.lock); + + if (test_bit(SSH_PTL_SF_SHUTDOWN_BIT, &ptl->state)) + return -ESHUTDOWN; + + /* Avoid further transitions when canceling/completing. */ + if (test_bit(SSH_PACKET_SF_LOCKED_BIT, &packet->state)) + return -EINVAL; + + /* If this packet has already been queued, do not add it. */ + if (test_and_set_bit(SSH_PACKET_SF_QUEUED_BIT, &packet->state)) + return -EALREADY; + + head = __ssh_ptl_queue_find_entrypoint(packet); + + list_add_tail(&ssh_packet_get(packet)->queue_node, head); + return 0; +} + +static int ssh_ptl_queue_push(struct ssh_packet *packet) +{ + int status; + + spin_lock(&packet->ptl->queue.lock); + status = __ssh_ptl_queue_push(packet); + spin_unlock(&packet->ptl->queue.lock); + + return status; +} + +static void ssh_ptl_queue_remove(struct ssh_packet *packet) +{ + struct ssh_ptl *ptl = packet->ptl; + + spin_lock(&ptl->queue.lock); + + if (!test_and_clear_bit(SSH_PACKET_SF_QUEUED_BIT, &packet->state)) { + spin_unlock(&ptl->queue.lock); + return; + } + + list_del(&packet->queue_node); + + spin_unlock(&ptl->queue.lock); + ssh_packet_put(packet); +} + +static void ssh_ptl_pending_push(struct ssh_packet *p) +{ + struct ssh_ptl *ptl = p->ptl; + const ktime_t timestamp = ktime_get_coarse_boottime(); + const ktime_t timeout = ptl->rtx_timeout.timeout; + + /* + * Note: We can get the time for the timestamp before acquiring the + * lock as this is the only place we're setting it and this function + * is called only from the transmitter thread. Thus it is not possible + * to overwrite the timestamp with an outdated value below. + */ + + spin_lock(&ptl->pending.lock); + + /* If we are canceling/completing this packet, do not add it. */ + if (test_bit(SSH_PACKET_SF_LOCKED_BIT, &p->state)) { + spin_unlock(&ptl->pending.lock); + return; + } + + /* + * On re-submission, the packet has already been added the pending + * set. We still need to update the timestamp as the packet timeout is + * reset for each (re-)submission. + */ + p->timestamp = timestamp; + + /* In case it is already pending (e.g. re-submission), do not add it. */ + if (!test_and_set_bit(SSH_PACKET_SF_PENDING_BIT, &p->state)) { + atomic_inc(&ptl->pending.count); + list_add_tail(&ssh_packet_get(p)->pending_node, &ptl->pending.head); + } + + spin_unlock(&ptl->pending.lock); + + /* Arm/update timeout reaper. */ + ssh_ptl_timeout_reaper_mod(ptl, timestamp, timestamp + timeout); +} + +static void ssh_ptl_pending_remove(struct ssh_packet *packet) +{ + struct ssh_ptl *ptl = packet->ptl; + + spin_lock(&ptl->pending.lock); + + if (!test_and_clear_bit(SSH_PACKET_SF_PENDING_BIT, &packet->state)) { + spin_unlock(&ptl->pending.lock); + return; + } + + list_del(&packet->pending_node); + atomic_dec(&ptl->pending.count); + + spin_unlock(&ptl->pending.lock); + + ssh_packet_put(packet); +} + +/* Warning: Does not check/set "completed" bit. */ +static void __ssh_ptl_complete(struct ssh_packet *p, int status) +{ + struct ssh_ptl *ptl = READ_ONCE(p->ptl); + + ptl_dbg_cond(ptl, "ptl: completing packet %p (status: %d)\n", p, status); + + if (p->ops->complete) + p->ops->complete(p, status); +} + +static void ssh_ptl_remove_and_complete(struct ssh_packet *p, int status) +{ + /* + * A call to this function should in general be preceded by + * set_bit(SSH_PACKET_SF_LOCKED_BIT, &p->flags) to avoid re-adding the + * packet to the structures it's going to be removed from. + * + * The set_bit call does not need explicit memory barriers as the + * implicit barrier of the test_and_set_bit() call below ensure that the + * flag is visible before we actually attempt to remove the packet. + */ + + if (test_and_set_bit(SSH_PACKET_SF_COMPLETED_BIT, &p->state)) + return; + + ssh_ptl_queue_remove(p); + ssh_ptl_pending_remove(p); + + __ssh_ptl_complete(p, status); +} + +static bool ssh_ptl_tx_can_process(struct ssh_packet *packet) +{ + struct ssh_ptl *ptl = packet->ptl; + + if (test_bit(SSH_PACKET_TY_FLUSH_BIT, &packet->state)) + return !atomic_read(&ptl->pending.count); + + /* We can always process non-blocking packets. */ + if (!test_bit(SSH_PACKET_TY_BLOCKING_BIT, &packet->state)) + return true; + + /* If we are already waiting for this packet, send it again. */ + if (test_bit(SSH_PACKET_SF_PENDING_BIT, &packet->state)) + return true; + + /* Otherwise: Check if we have the capacity to send. */ + return atomic_read(&ptl->pending.count) < SSH_PTL_MAX_PENDING; +} + +static struct ssh_packet *ssh_ptl_tx_pop(struct ssh_ptl *ptl) +{ + struct ssh_packet *packet = ERR_PTR(-ENOENT); + struct ssh_packet *p, *n; + + spin_lock(&ptl->queue.lock); + list_for_each_entry_safe(p, n, &ptl->queue.head, queue_node) { + /* + * If we are canceling or completing this packet, ignore it. + * It's going to be removed from this queue shortly. + */ + if (test_bit(SSH_PACKET_SF_LOCKED_BIT, &p->state)) + continue; + + /* + * Packets should be ordered non-blocking/to-be-resent first. + * If we cannot process this packet, assume that we can't + * process any following packet either and abort. + */ + if (!ssh_ptl_tx_can_process(p)) { + packet = ERR_PTR(-EBUSY); + break; + } + + /* + * We are allowed to change the state now. Remove it from the + * queue and mark it as being transmitted. + */ + + list_del(&p->queue_node); + + set_bit(SSH_PACKET_SF_TRANSMITTING_BIT, &p->state); + /* Ensure that state never gets zero. */ + smp_mb__before_atomic(); + clear_bit(SSH_PACKET_SF_QUEUED_BIT, &p->state); + + /* + * Update number of tries. This directly influences the + * priority in case the packet is re-submitted (e.g. via + * timeout/NAK). Note that all reads and writes to the + * priority after the first submission are guarded by the + * queue lock. + */ + ssh_packet_next_try(p); + + packet = p; + break; + } + spin_unlock(&ptl->queue.lock); + + return packet; +} + +static struct ssh_packet *ssh_ptl_tx_next(struct ssh_ptl *ptl) +{ + struct ssh_packet *p; + + p = ssh_ptl_tx_pop(ptl); + if (IS_ERR(p)) + return p; + + if (test_bit(SSH_PACKET_TY_SEQUENCED_BIT, &p->state)) { + ptl_dbg(ptl, "ptl: transmitting sequenced packet %p\n", p); + ssh_ptl_pending_push(p); + } else { + ptl_dbg(ptl, "ptl: transmitting non-sequenced packet %p\n", p); + } + + return p; +} + +static void ssh_ptl_tx_compl_success(struct ssh_packet *packet) +{ + struct ssh_ptl *ptl = packet->ptl; + + ptl_dbg(ptl, "ptl: successfully transmitted packet %p\n", packet); + + /* Transition state to "transmitted". */ + set_bit(SSH_PACKET_SF_TRANSMITTED_BIT, &packet->state); + /* Ensure that state never gets zero. */ + smp_mb__before_atomic(); + clear_bit(SSH_PACKET_SF_TRANSMITTING_BIT, &packet->state); + + /* If the packet is unsequenced, we're done: Lock and complete. */ + if (!test_bit(SSH_PACKET_TY_SEQUENCED_BIT, &packet->state)) { + set_bit(SSH_PACKET_SF_LOCKED_BIT, &packet->state); + ssh_ptl_remove_and_complete(packet, 0); + } + + /* + * Notify that a packet transmission has finished. In general we're only + * waiting for one packet (if any), so wake_up_all should be fine. + */ + wake_up_all(&ptl->tx.packet_wq); +} + +static void ssh_ptl_tx_compl_error(struct ssh_packet *packet, int status) +{ + /* Transmission failure: Lock the packet and try to complete it. */ + set_bit(SSH_PACKET_SF_LOCKED_BIT, &packet->state); + /* Ensure that state never gets zero. */ + smp_mb__before_atomic(); + clear_bit(SSH_PACKET_SF_TRANSMITTING_BIT, &packet->state); + + ptl_err(packet->ptl, "ptl: transmission error: %d\n", status); + ptl_dbg(packet->ptl, "ptl: failed to transmit packet: %p\n", packet); + + ssh_ptl_remove_and_complete(packet, status); + + /* + * Notify that a packet transmission has finished. In general we're only + * waiting for one packet (if any), so wake_up_all should be fine. + */ + wake_up_all(&packet->ptl->tx.packet_wq); +} + +static long ssh_ptl_tx_wait_packet(struct ssh_ptl *ptl) +{ + int status; + + status = wait_for_completion_interruptible(&ptl->tx.thread_cplt_pkt); + reinit_completion(&ptl->tx.thread_cplt_pkt); + + /* + * Ensure completion is cleared before continuing to avoid lost update + * problems. + */ + smp_mb__after_atomic(); + + return status; +} + +static long ssh_ptl_tx_wait_transfer(struct ssh_ptl *ptl, long timeout) +{ + long status; + + status = wait_for_completion_interruptible_timeout(&ptl->tx.thread_cplt_tx, + timeout); + reinit_completion(&ptl->tx.thread_cplt_tx); + + /* + * Ensure completion is cleared before continuing to avoid lost update + * problems. + */ + smp_mb__after_atomic(); + + return status; +} + +static int ssh_ptl_tx_packet(struct ssh_ptl *ptl, struct ssh_packet *packet) +{ + long timeout = SSH_PTL_TX_TIMEOUT; + size_t offset = 0; + + /* Note: Flush-packets don't have any data. */ + if (unlikely(!packet->data.ptr)) + return 0; + + ptl_dbg(ptl, "tx: sending data (length: %zu)\n", packet->data.len); + print_hex_dump_debug("tx: ", DUMP_PREFIX_OFFSET, 16, 1, + packet->data.ptr, packet->data.len, false); + + do { + ssize_t status, len; + u8 *buf; + + buf = packet->data.ptr + offset; + len = packet->data.len - offset; + + status = serdev_device_write_buf(ptl->serdev, buf, len); + if (status < 0) + return status; + + if (status == len) + return 0; + + offset += status; + + timeout = ssh_ptl_tx_wait_transfer(ptl, timeout); + if (kthread_should_stop() || !atomic_read(&ptl->tx.running)) + return -ESHUTDOWN; + + if (timeout < 0) + return -EINTR; + + if (timeout == 0) + return -ETIMEDOUT; + } while (true); +} + +static int ssh_ptl_tx_threadfn(void *data) +{ + struct ssh_ptl *ptl = data; + + while (!kthread_should_stop() && atomic_read(&ptl->tx.running)) { + struct ssh_packet *packet; + int status; + + /* Try to get the next packet. */ + packet = ssh_ptl_tx_next(ptl); + + /* If no packet can be processed, we are done. */ + if (IS_ERR(packet)) { + ssh_ptl_tx_wait_packet(ptl); + continue; + } + + /* Transfer and complete packet. */ + status = ssh_ptl_tx_packet(ptl, packet); + if (status) + ssh_ptl_tx_compl_error(packet, status); + else + ssh_ptl_tx_compl_success(packet); + + ssh_packet_put(packet); + } + + return 0; +} + +/** + * ssh_ptl_tx_wakeup_packet() - Wake up packet transmitter thread for new + * packet. + * @ptl: The packet transport layer. + * + * Wakes up the packet transmitter thread, notifying it that a new packet has + * arrived and is ready for transfer. If the packet transport layer has been + * shut down, calls to this function will be ignored. + */ +static void ssh_ptl_tx_wakeup_packet(struct ssh_ptl *ptl) +{ + if (test_bit(SSH_PTL_SF_SHUTDOWN_BIT, &ptl->state)) + return; + + complete(&ptl->tx.thread_cplt_pkt); +} + +/** + * ssh_ptl_tx_start() - Start packet transmitter thread. + * @ptl: The packet transport layer. + * + * Return: Returns zero on success, a negative error code on failure. + */ +int ssh_ptl_tx_start(struct ssh_ptl *ptl) +{ + atomic_set_release(&ptl->tx.running, 1); + + ptl->tx.thread = kthread_run(ssh_ptl_tx_threadfn, ptl, "ssam_serial_hub-tx"); + if (IS_ERR(ptl->tx.thread)) + return PTR_ERR(ptl->tx.thread); + + return 0; +} + +/** + * ssh_ptl_tx_stop() - Stop packet transmitter thread. + * @ptl: The packet transport layer. + * + * Return: Returns zero on success, a negative error code on failure. + */ +int ssh_ptl_tx_stop(struct ssh_ptl *ptl) +{ + int status = 0; + + if (!IS_ERR_OR_NULL(ptl->tx.thread)) { + /* Tell thread to stop. */ + atomic_set_release(&ptl->tx.running, 0); + + /* + * Wake up thread in case it is paused. Do not use wakeup + * helpers as this may be called when the shutdown bit has + * already been set. + */ + complete(&ptl->tx.thread_cplt_pkt); + complete(&ptl->tx.thread_cplt_tx); + + /* Finally, wait for thread to stop. */ + status = kthread_stop(ptl->tx.thread); + ptl->tx.thread = NULL; + } + + return status; +} + +static struct ssh_packet *ssh_ptl_ack_pop(struct ssh_ptl *ptl, u8 seq_id) +{ + struct ssh_packet *packet = ERR_PTR(-ENOENT); + struct ssh_packet *p, *n; + + spin_lock(&ptl->pending.lock); + list_for_each_entry_safe(p, n, &ptl->pending.head, pending_node) { + /* + * We generally expect packets to be in order, so first packet + * to be added to pending is first to be sent, is first to be + * ACKed. + */ + if (unlikely(ssh_packet_get_seq(p) != seq_id)) + continue; + + /* + * In case we receive an ACK while handling a transmission + * error completion. The packet will be removed shortly. + */ + if (unlikely(test_bit(SSH_PACKET_SF_LOCKED_BIT, &p->state))) { + packet = ERR_PTR(-EPERM); + break; + } + + /* + * Mark the packet as ACKed and remove it from pending by + * removing its node and decrementing the pending counter. + */ + set_bit(SSH_PACKET_SF_ACKED_BIT, &p->state); + /* Ensure that state never gets zero. */ + smp_mb__before_atomic(); + clear_bit(SSH_PACKET_SF_PENDING_BIT, &p->state); + + atomic_dec(&ptl->pending.count); + list_del(&p->pending_node); + packet = p; + + break; + } + spin_unlock(&ptl->pending.lock); + + return packet; +} + +static void ssh_ptl_wait_until_transmitted(struct ssh_packet *packet) +{ + wait_event(packet->ptl->tx.packet_wq, + test_bit(SSH_PACKET_SF_TRANSMITTED_BIT, &packet->state) || + test_bit(SSH_PACKET_SF_LOCKED_BIT, &packet->state)); +} + +static void ssh_ptl_acknowledge(struct ssh_ptl *ptl, u8 seq) +{ + struct ssh_packet *p; + + p = ssh_ptl_ack_pop(ptl, seq); + if (IS_ERR(p)) { + if (PTR_ERR(p) == -ENOENT) { + /* + * The packet has not been found in the set of pending + * packets. + */ + ptl_warn(ptl, "ptl: received ACK for non-pending packet\n"); + } else { + /* + * The packet is pending, but we are not allowed to take + * it because it has been locked. + */ + WARN_ON(PTR_ERR(p) != -EPERM); + } + return; + } + + ptl_dbg(ptl, "ptl: received ACK for packet %p\n", p); + + /* + * It is possible that the packet has been transmitted, but the state + * has not been updated from "transmitting" to "transmitted" yet. + * In that case, we need to wait for this transition to occur in order + * to determine between success or failure. + * + * On transmission failure, the packet will be locked after this call. + * On success, the transmitted bit will be set. + */ + ssh_ptl_wait_until_transmitted(p); + + /* + * The packet will already be locked in case of a transmission error or + * cancellation. Let the transmitter or cancellation issuer complete the + * packet. + */ + if (unlikely(test_and_set_bit(SSH_PACKET_SF_LOCKED_BIT, &p->state))) { + if (unlikely(!test_bit(SSH_PACKET_SF_TRANSMITTED_BIT, &p->state))) + ptl_err(ptl, "ptl: received ACK before packet had been fully transmitted\n"); + + ssh_packet_put(p); + return; + } + + ssh_ptl_remove_and_complete(p, 0); + ssh_packet_put(p); + + if (atomic_read(&ptl->pending.count) < SSH_PTL_MAX_PENDING) + ssh_ptl_tx_wakeup_packet(ptl); +} + +/** + * ssh_ptl_submit() - Submit a packet to the transport layer. + * @ptl: The packet transport layer to submit the packet to. + * @p: The packet to submit. + * + * Submits a new packet to the transport layer, queuing it to be sent. This + * function should not be used for re-submission. + * + * Return: Returns zero on success, %-EINVAL if a packet field is invalid or + * the packet has been canceled prior to submission, %-EALREADY if the packet + * has already been submitted, or %-ESHUTDOWN if the packet transport layer + * has been shut down. + */ +int ssh_ptl_submit(struct ssh_ptl *ptl, struct ssh_packet *p) +{ + struct ssh_ptl *ptl_old; + int status; + + /* Validate packet fields. */ + if (test_bit(SSH_PACKET_TY_FLUSH_BIT, &p->state)) { + if (p->data.ptr || test_bit(SSH_PACKET_TY_SEQUENCED_BIT, &p->state)) + return -EINVAL; + } else if (!p->data.ptr) { + return -EINVAL; + } + + /* + * The ptl reference only gets set on or before the first submission. + * After the first submission, it has to be read-only. + * + * Note that ptl may already be set from upper-layer request + * submission, thus we cannot expect it to be NULL. + */ + ptl_old = READ_ONCE(p->ptl); + if (!ptl_old) + WRITE_ONCE(p->ptl, ptl); + else if (WARN_ON(ptl_old != ptl)) + return -EALREADY; /* Submitted on different PTL. */ + + status = ssh_ptl_queue_push(p); + if (status) + return status; + + if (!test_bit(SSH_PACKET_TY_BLOCKING_BIT, &p->state) || + (atomic_read(&ptl->pending.count) < SSH_PTL_MAX_PENDING)) + ssh_ptl_tx_wakeup_packet(ptl); + + return 0; +} + +/* + * __ssh_ptl_resubmit() - Re-submit a packet to the transport layer. + * @packet: The packet to re-submit. + * + * Re-submits the given packet: Checks if it can be re-submitted and queues it + * if it can, resetting the packet timestamp in the process. Must be called + * with the pending lock held. + * + * Return: Returns %-ECANCELED if the packet has exceeded its number of tries, + * %-EINVAL if the packet has been locked, %-EALREADY if the packet is already + * on the queue, and %-ESHUTDOWN if the transmission layer has been shut down. + */ +static int __ssh_ptl_resubmit(struct ssh_packet *packet) +{ + int status; + u8 try; + + lockdep_assert_held(&packet->ptl->pending.lock); + + spin_lock(&packet->ptl->queue.lock); + + /* Check if the packet is out of tries. */ + try = ssh_packet_priority_get_try(packet->priority); + if (try >= SSH_PTL_MAX_PACKET_TRIES) { + spin_unlock(&packet->ptl->queue.lock); + return -ECANCELED; + } + + status = __ssh_ptl_queue_push(packet); + if (status) { + /* + * An error here indicates that the packet has either already + * been queued, been locked, or the transport layer is being + * shut down. In all cases: Ignore the error. + */ + spin_unlock(&packet->ptl->queue.lock); + return status; + } + + packet->timestamp = KTIME_MAX; + + spin_unlock(&packet->ptl->queue.lock); + return 0; +} + +static void ssh_ptl_resubmit_pending(struct ssh_ptl *ptl) +{ + struct ssh_packet *p; + bool resub = false; + + /* + * Note: We deliberately do not remove/attempt to cancel and complete + * packets that are out of tires in this function. The packet will be + * eventually canceled and completed by the timeout. Removing the packet + * here could lead to overly eager cancellation if the packet has not + * been re-transmitted yet but the tries-counter already updated (i.e + * ssh_ptl_tx_next() removed the packet from the queue and updated the + * counter, but re-transmission for the last try has not actually + * started yet). + */ + + spin_lock(&ptl->pending.lock); + + /* Re-queue all pending packets. */ + list_for_each_entry(p, &ptl->pending.head, pending_node) { + /* + * Re-submission fails if the packet is out of tries, has been + * locked, is already queued, or the layer is being shut down. + * No need to re-schedule tx-thread in those cases. + */ + if (!__ssh_ptl_resubmit(p)) + resub = true; + } + + spin_unlock(&ptl->pending.lock); + + if (resub) + ssh_ptl_tx_wakeup_packet(ptl); +} + +/** + * ssh_ptl_cancel() - Cancel a packet. + * @p: The packet to cancel. + * + * Cancels a packet. There are no guarantees on when completion and release + * callbacks will be called. This may occur during execution of this function + * or may occur at any point later. + * + * Note that it is not guaranteed that the packet will actually be canceled if + * the packet is concurrently completed by another process. The only guarantee + * of this function is that the packet will be completed (with success, + * failure, or cancellation) and released from the transport layer in a + * reasonable time-frame. + * + * May be called before the packet has been submitted, in which case any later + * packet submission fails. + */ +void ssh_ptl_cancel(struct ssh_packet *p) +{ + if (test_and_set_bit(SSH_PACKET_SF_CANCELED_BIT, &p->state)) + return; + + /* + * Lock packet and commit with memory barrier. If this packet has + * already been locked, it's going to be removed and completed by + * another party, which should have precedence. + */ + if (test_and_set_bit(SSH_PACKET_SF_LOCKED_BIT, &p->state)) + return; + + /* + * By marking the packet as locked and employing the implicit memory + * barrier of test_and_set_bit, we have guaranteed that, at this point, + * the packet cannot be added to the queue any more. + * + * In case the packet has never been submitted, packet->ptl is NULL. If + * the packet is currently being submitted, packet->ptl may be NULL or + * non-NULL. Due marking the packet as locked above and committing with + * the memory barrier, we have guaranteed that, if packet->ptl is NULL, + * the packet will never be added to the queue. If packet->ptl is + * non-NULL, we don't have any guarantees. + */ + + if (READ_ONCE(p->ptl)) { + ssh_ptl_remove_and_complete(p, -ECANCELED); + + if (atomic_read(&p->ptl->pending.count) < SSH_PTL_MAX_PENDING) + ssh_ptl_tx_wakeup_packet(p->ptl); + + } else if (!test_and_set_bit(SSH_PACKET_SF_COMPLETED_BIT, &p->state)) { + __ssh_ptl_complete(p, -ECANCELED); + } +} + +/* Must be called with pending lock held */ +static ktime_t ssh_packet_get_expiration(struct ssh_packet *p, ktime_t timeout) +{ + lockdep_assert_held(&p->ptl->pending.lock); + + if (p->timestamp != KTIME_MAX) + return ktime_add(p->timestamp, timeout); + else + return KTIME_MAX; +} + +static void ssh_ptl_timeout_reap(struct work_struct *work) +{ + struct ssh_ptl *ptl = to_ssh_ptl(work, rtx_timeout.reaper.work); + struct ssh_packet *p, *n; + LIST_HEAD(claimed); + ktime_t now = ktime_get_coarse_boottime(); + ktime_t timeout = ptl->rtx_timeout.timeout; + ktime_t next = KTIME_MAX; + bool resub = false; + int status; + + /* + * Mark reaper as "not pending". This is done before checking any + * packets to avoid lost-update type problems. + */ + spin_lock(&ptl->rtx_timeout.lock); + ptl->rtx_timeout.expires = KTIME_MAX; + spin_unlock(&ptl->rtx_timeout.lock); + + spin_lock(&ptl->pending.lock); + + list_for_each_entry_safe(p, n, &ptl->pending.head, pending_node) { + ktime_t expires = ssh_packet_get_expiration(p, timeout); + + /* + * Check if the timeout hasn't expired yet. Find out next + * expiration date to be handled after this run. + */ + if (ktime_after(expires, now)) { + next = ktime_before(expires, next) ? expires : next; + continue; + } + + status = __ssh_ptl_resubmit(p); + + /* + * Re-submission fails if the packet is out of tries, has been + * locked, is already queued, or the layer is being shut down. + * No need to re-schedule tx-thread in those cases. + */ + if (!status) + resub = true; + + /* Go to next packet if this packet is not out of tries. */ + if (status != -ECANCELED) + continue; + + /* No more tries left: Cancel the packet. */ + + /* + * If someone else has locked the packet already, don't use it + * and let the other party complete it. + */ + if (test_and_set_bit(SSH_PACKET_SF_LOCKED_BIT, &p->state)) + continue; + + /* + * We have now marked the packet as locked. Thus it cannot be + * added to the pending list again after we've removed it here. + * We can therefore re-use the pending_node of this packet + * temporarily. + */ + + clear_bit(SSH_PACKET_SF_PENDING_BIT, &p->state); + + atomic_dec(&ptl->pending.count); + list_del(&p->pending_node); + + list_add_tail(&p->pending_node, &claimed); + } + + spin_unlock(&ptl->pending.lock); + + /* Cancel and complete the packet. */ + list_for_each_entry_safe(p, n, &claimed, pending_node) { + if (!test_and_set_bit(SSH_PACKET_SF_COMPLETED_BIT, &p->state)) { + ssh_ptl_queue_remove(p); + __ssh_ptl_complete(p, -ETIMEDOUT); + } + + /* + * Drop the reference we've obtained by removing it from + * the pending set. + */ + list_del(&p->pending_node); + ssh_packet_put(p); + } + + /* Ensure that reaper doesn't run again immediately. */ + next = max(next, ktime_add(now, SSH_PTL_PACKET_TIMEOUT_RESOLUTION)); + if (next != KTIME_MAX) + ssh_ptl_timeout_reaper_mod(ptl, now, next); + + if (resub) + ssh_ptl_tx_wakeup_packet(ptl); +} + +static bool ssh_ptl_rx_retransmit_check(struct ssh_ptl *ptl, u8 seq) +{ + int i; + + /* + * Check if SEQ has been seen recently (i.e. packet was + * re-transmitted and we should ignore it). + */ + for (i = 0; i < ARRAY_SIZE(ptl->rx.blocked.seqs); i++) { + if (likely(ptl->rx.blocked.seqs[i] != seq)) + continue; + + ptl_dbg(ptl, "ptl: ignoring repeated data packet\n"); + return true; + } + + /* Update list of blocked sequence IDs. */ + ptl->rx.blocked.seqs[ptl->rx.blocked.offset] = seq; + ptl->rx.blocked.offset = (ptl->rx.blocked.offset + 1) + % ARRAY_SIZE(ptl->rx.blocked.seqs); + + return false; +} + +static void ssh_ptl_rx_dataframe(struct ssh_ptl *ptl, + const struct ssh_frame *frame, + const struct ssam_span *payload) +{ + if (ssh_ptl_rx_retransmit_check(ptl, frame->seq)) + return; + + ptl->ops.data_received(ptl, payload); +} + +static void ssh_ptl_send_ack(struct ssh_ptl *ptl, u8 seq) +{ + struct ssh_packet *packet; + struct ssam_span buf; + struct msgbuf msgb; + int status; + + status = ssh_ctrl_packet_alloc(&packet, &buf, GFP_KERNEL); + if (status) { + ptl_err(ptl, "ptl: failed to allocate ACK packet\n"); + return; + } + + ssh_packet_init(packet, 0, SSH_PACKET_PRIORITY(ACK, 0), + &ssh_ptl_ctrl_packet_ops); + + msgb_init(&msgb, buf.ptr, buf.len); + msgb_push_ack(&msgb, seq); + ssh_packet_set_data(packet, msgb.begin, msgb_bytes_used(&msgb)); + + ssh_ptl_submit(ptl, packet); + ssh_packet_put(packet); +} + +static void ssh_ptl_send_nak(struct ssh_ptl *ptl) +{ + struct ssh_packet *packet; + struct ssam_span buf; + struct msgbuf msgb; + int status; + + status = ssh_ctrl_packet_alloc(&packet, &buf, GFP_KERNEL); + if (status) { + ptl_err(ptl, "ptl: failed to allocate NAK packet\n"); + return; + } + + ssh_packet_init(packet, 0, SSH_PACKET_PRIORITY(NAK, 0), + &ssh_ptl_ctrl_packet_ops); + + msgb_init(&msgb, buf.ptr, buf.len); + msgb_push_nak(&msgb); + ssh_packet_set_data(packet, msgb.begin, msgb_bytes_used(&msgb)); + + ssh_ptl_submit(ptl, packet); + ssh_packet_put(packet); +} + +static size_t ssh_ptl_rx_eval(struct ssh_ptl *ptl, struct ssam_span *source) +{ + struct ssh_frame *frame; + struct ssam_span payload; + struct ssam_span aligned; + bool syn_found; + int status; + + /* Find SYN. */ + syn_found = sshp_find_syn(source, &aligned); + + if (unlikely(aligned.ptr - source->ptr) > 0) { + ptl_warn(ptl, "rx: parser: invalid start of frame, skipping\n"); + + /* + * Notes: + * - This might send multiple NAKs in case the communication + * starts with an invalid SYN and is broken down into multiple + * pieces. This should generally be handled fine, we just + * might receive duplicate data in this case, which is + * detected when handling data frames. + * - This path will also be executed on invalid CRCs: When an + * invalid CRC is encountered, the code below will skip data + * until directly after the SYN. This causes the search for + * the next SYN, which is generally not placed directly after + * the last one. + * + * Open question: Should we send this in case of invalid + * payload CRCs if the frame-type is non-sequential (current + * implementation) or should we drop that frame without + * telling the EC? + */ + ssh_ptl_send_nak(ptl); + } + + if (unlikely(!syn_found)) + return aligned.ptr - source->ptr; + + /* Parse and validate frame. */ + status = sshp_parse_frame(&ptl->serdev->dev, &aligned, &frame, &payload, + SSH_PTL_RX_BUF_LEN); + if (status) /* Invalid frame: skip to next SYN. */ + return aligned.ptr - source->ptr + sizeof(u16); + if (!frame) /* Not enough data. */ + return aligned.ptr - source->ptr; + + switch (frame->type) { + case SSH_FRAME_TYPE_ACK: + ssh_ptl_acknowledge(ptl, frame->seq); + break; + + case SSH_FRAME_TYPE_NAK: + ssh_ptl_resubmit_pending(ptl); + break; + + case SSH_FRAME_TYPE_DATA_SEQ: + ssh_ptl_send_ack(ptl, frame->seq); + fallthrough; + + case SSH_FRAME_TYPE_DATA_NSQ: + ssh_ptl_rx_dataframe(ptl, frame, &payload); + break; + + default: + ptl_warn(ptl, "ptl: received frame with unknown type %#04x\n", + frame->type); + break; + } + + return aligned.ptr - source->ptr + SSH_MESSAGE_LENGTH(frame->len); +} + +static int ssh_ptl_rx_threadfn(void *data) +{ + struct ssh_ptl *ptl = data; + + while (true) { + struct ssam_span span; + size_t offs = 0; + size_t n; + + wait_event_interruptible(ptl->rx.wq, + !kfifo_is_empty(&ptl->rx.fifo) || + kthread_should_stop()); + if (kthread_should_stop()) + break; + + /* Copy from fifo to evaluation buffer. */ + n = sshp_buf_read_from_fifo(&ptl->rx.buf, &ptl->rx.fifo); + + ptl_dbg(ptl, "rx: received data (size: %zu)\n", n); + print_hex_dump_debug("rx: ", DUMP_PREFIX_OFFSET, 16, 1, + ptl->rx.buf.ptr + ptl->rx.buf.len - n, + n, false); + + /* Parse until we need more bytes or buffer is empty. */ + while (offs < ptl->rx.buf.len) { + sshp_buf_span_from(&ptl->rx.buf, offs, &span); + n = ssh_ptl_rx_eval(ptl, &span); + if (n == 0) + break; /* Need more bytes. */ + + offs += n; + } + + /* Throw away the evaluated parts. */ + sshp_buf_drop(&ptl->rx.buf, offs); + } + + return 0; +} + +static void ssh_ptl_rx_wakeup(struct ssh_ptl *ptl) +{ + wake_up(&ptl->rx.wq); +} + +/** + * ssh_ptl_rx_start() - Start packet transport layer receiver thread. + * @ptl: The packet transport layer. + * + * Return: Returns zero on success, a negative error code on failure. + */ +int ssh_ptl_rx_start(struct ssh_ptl *ptl) +{ + if (ptl->rx.thread) + return 0; + + ptl->rx.thread = kthread_run(ssh_ptl_rx_threadfn, ptl, + "ssam_serial_hub-rx"); + if (IS_ERR(ptl->rx.thread)) + return PTR_ERR(ptl->rx.thread); + + return 0; +} + +/** + * ssh_ptl_rx_stop() - Stop packet transport layer receiver thread. + * @ptl: The packet transport layer. + * + * Return: Returns zero on success, a negative error code on failure. + */ +int ssh_ptl_rx_stop(struct ssh_ptl *ptl) +{ + int status = 0; + + if (ptl->rx.thread) { + status = kthread_stop(ptl->rx.thread); + ptl->rx.thread = NULL; + } + + return status; +} + +/** + * ssh_ptl_rx_rcvbuf() - Push data from lower-layer transport to the packet + * layer. + * @ptl: The packet transport layer. + * @buf: Pointer to the data to push to the layer. + * @n: Size of the data to push to the layer, in bytes. + * + * Pushes data from a lower-layer transport to the receiver fifo buffer of the + * packet layer and notifies the receiver thread. Calls to this function are + * ignored once the packet layer has been shut down. + * + * Return: Returns the number of bytes transferred (positive or zero) on + * success. Returns %-ESHUTDOWN if the packet layer has been shut down. + */ +int ssh_ptl_rx_rcvbuf(struct ssh_ptl *ptl, const u8 *buf, size_t n) +{ + int used; + + if (test_bit(SSH_PTL_SF_SHUTDOWN_BIT, &ptl->state)) + return -ESHUTDOWN; + + used = kfifo_in(&ptl->rx.fifo, buf, n); + if (used) + ssh_ptl_rx_wakeup(ptl); + + return used; +} + +/** + * ssh_ptl_shutdown() - Shut down the packet transport layer. + * @ptl: The packet transport layer. + * + * Shuts down the packet transport layer, removing and canceling all queued + * and pending packets. Packets canceled by this operation will be completed + * with %-ESHUTDOWN as status. Receiver and transmitter threads will be + * stopped. + * + * As a result of this function, the transport layer will be marked as shut + * down. Submission of packets after the transport layer has been shut down + * will fail with %-ESHUTDOWN. + */ +void ssh_ptl_shutdown(struct ssh_ptl *ptl) +{ + LIST_HEAD(complete_q); + LIST_HEAD(complete_p); + struct ssh_packet *p, *n; + int status; + + /* Ensure that no new packets (including ACK/NAK) can be submitted. */ + set_bit(SSH_PTL_SF_SHUTDOWN_BIT, &ptl->state); + /* + * Ensure that the layer gets marked as shut-down before actually + * stopping it. In combination with the check in ssh_ptl_queue_push(), + * this guarantees that no new packets can be added and all already + * queued packets are properly canceled. In combination with the check + * in ssh_ptl_rx_rcvbuf(), this guarantees that received data is + * properly cut off. + */ + smp_mb__after_atomic(); + + status = ssh_ptl_rx_stop(ptl); + if (status) + ptl_err(ptl, "ptl: failed to stop receiver thread\n"); + + status = ssh_ptl_tx_stop(ptl); + if (status) + ptl_err(ptl, "ptl: failed to stop transmitter thread\n"); + + cancel_delayed_work_sync(&ptl->rtx_timeout.reaper); + + /* + * At this point, all threads have been stopped. This means that the + * only references to packets from inside the system are in the queue + * and pending set. + * + * Note: We still need locks here because someone could still be + * canceling packets. + * + * Note 2: We can re-use queue_node (or pending_node) if we mark the + * packet as locked an then remove it from the queue (or pending set + * respectively). Marking the packet as locked avoids re-queuing + * (which should already be prevented by having stopped the treads...) + * and not setting QUEUED_BIT (or PENDING_BIT) prevents removal from a + * new list via other threads (e.g. cancellation). + * + * Note 3: There may be overlap between complete_p and complete_q. + * This is handled via test_and_set_bit() on the "completed" flag + * (also handles cancellation). + */ + + /* Mark queued packets as locked and move them to complete_q. */ + spin_lock(&ptl->queue.lock); + list_for_each_entry_safe(p, n, &ptl->queue.head, queue_node) { + set_bit(SSH_PACKET_SF_LOCKED_BIT, &p->state); + /* Ensure that state does not get zero. */ + smp_mb__before_atomic(); + clear_bit(SSH_PACKET_SF_QUEUED_BIT, &p->state); + + list_del(&p->queue_node); + list_add_tail(&p->queue_node, &complete_q); + } + spin_unlock(&ptl->queue.lock); + + /* Mark pending packets as locked and move them to complete_p. */ + spin_lock(&ptl->pending.lock); + list_for_each_entry_safe(p, n, &ptl->pending.head, pending_node) { + set_bit(SSH_PACKET_SF_LOCKED_BIT, &p->state); + /* Ensure that state does not get zero. */ + smp_mb__before_atomic(); + clear_bit(SSH_PACKET_SF_PENDING_BIT, &p->state); + + list_del(&p->pending_node); + list_add_tail(&p->pending_node, &complete_q); + } + atomic_set(&ptl->pending.count, 0); + spin_unlock(&ptl->pending.lock); + + /* Complete and drop packets on complete_q. */ + list_for_each_entry(p, &complete_q, queue_node) { + if (!test_and_set_bit(SSH_PACKET_SF_COMPLETED_BIT, &p->state)) + __ssh_ptl_complete(p, -ESHUTDOWN); + + ssh_packet_put(p); + } + + /* Complete and drop packets on complete_p. */ + list_for_each_entry(p, &complete_p, pending_node) { + if (!test_and_set_bit(SSH_PACKET_SF_COMPLETED_BIT, &p->state)) + __ssh_ptl_complete(p, -ESHUTDOWN); + + ssh_packet_put(p); + } + + /* + * At this point we have guaranteed that the system doesn't reference + * any packets any more. + */ +} + +/** + * ssh_ptl_init() - Initialize packet transport layer. + * @ptl: The packet transport layer to initialize. + * @serdev: The underlying serial device, i.e. the lower-level transport. + * @ops: Packet layer operations. + * + * Initializes the given packet transport layer. Transmitter and receiver + * threads must be started separately via ssh_ptl_tx_start() and + * ssh_ptl_rx_start(), after the packet-layer has been initialized and the + * lower-level transport layer has been set up. + * + * Return: Returns zero on success and a nonzero error code on failure. + */ +int ssh_ptl_init(struct ssh_ptl *ptl, struct serdev_device *serdev, + struct ssh_ptl_ops *ops) +{ + int i, status; + + ptl->serdev = serdev; + ptl->state = 0; + + spin_lock_init(&ptl->queue.lock); + INIT_LIST_HEAD(&ptl->queue.head); + + spin_lock_init(&ptl->pending.lock); + INIT_LIST_HEAD(&ptl->pending.head); + atomic_set_release(&ptl->pending.count, 0); + + ptl->tx.thread = NULL; + atomic_set(&ptl->tx.running, 0); + init_completion(&ptl->tx.thread_cplt_pkt); + init_completion(&ptl->tx.thread_cplt_tx); + init_waitqueue_head(&ptl->tx.packet_wq); + + ptl->rx.thread = NULL; + init_waitqueue_head(&ptl->rx.wq); + + spin_lock_init(&ptl->rtx_timeout.lock); + ptl->rtx_timeout.timeout = SSH_PTL_PACKET_TIMEOUT; + ptl->rtx_timeout.expires = KTIME_MAX; + INIT_DELAYED_WORK(&ptl->rtx_timeout.reaper, ssh_ptl_timeout_reap); + + ptl->ops = *ops; + + /* Initialize list of recent/blocked SEQs with invalid sequence IDs. */ + for (i = 0; i < ARRAY_SIZE(ptl->rx.blocked.seqs); i++) + ptl->rx.blocked.seqs[i] = U16_MAX; + ptl->rx.blocked.offset = 0; + + status = kfifo_alloc(&ptl->rx.fifo, SSH_PTL_RX_FIFO_LEN, GFP_KERNEL); + if (status) + return status; + + status = sshp_buf_alloc(&ptl->rx.buf, SSH_PTL_RX_BUF_LEN, GFP_KERNEL); + if (status) + kfifo_free(&ptl->rx.fifo); + + return status; +} + +/** + * ssh_ptl_destroy() - Deinitialize packet transport layer. + * @ptl: The packet transport layer to deinitialize. + * + * Deinitializes the given packet transport layer and frees resources + * associated with it. If receiver and/or transmitter threads have been + * started, the layer must first be shut down via ssh_ptl_shutdown() before + * this function can be called. + */ +void ssh_ptl_destroy(struct ssh_ptl *ptl) +{ + kfifo_free(&ptl->rx.fifo); + sshp_buf_free(&ptl->rx.buf); +} diff --git a/drivers/platform/surface/aggregator/ssh_packet_layer.h b/drivers/platform/surface/aggregator/ssh_packet_layer.h new file mode 100644 index 000000000000..058f111292ca --- /dev/null +++ b/drivers/platform/surface/aggregator/ssh_packet_layer.h @@ -0,0 +1,187 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * SSH packet transport layer. + * + * Copyright (C) 2019-2020 Maximilian Luz + */ + +#ifndef _SURFACE_AGGREGATOR_SSH_PACKET_LAYER_H +#define _SURFACE_AGGREGATOR_SSH_PACKET_LAYER_H + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include "ssh_parser.h" + +/** + * enum ssh_ptl_state_flags - State-flags for &struct ssh_ptl. + * + * @SSH_PTL_SF_SHUTDOWN_BIT: + * Indicates that the packet transport layer has been shut down or is + * being shut down and should not accept any new packets/data. + */ +enum ssh_ptl_state_flags { + SSH_PTL_SF_SHUTDOWN_BIT, +}; + +/** + * struct ssh_ptl_ops - Callback operations for packet transport layer. + * @data_received: Function called when a data-packet has been received. Both, + * the packet layer on which the packet has been received and + * the packet's payload data are provided to this function. + */ +struct ssh_ptl_ops { + void (*data_received)(struct ssh_ptl *p, const struct ssam_span *data); +}; + +/** + * struct ssh_ptl - SSH packet transport layer. + * @serdev: Serial device providing the underlying data transport. + * @state: State(-flags) of the transport layer. + * @queue: Packet submission queue. + * @queue.lock: Lock for modifying the packet submission queue. + * @queue.head: List-head of the packet submission queue. + * @pending: Set/list of pending packets. + * @pending.lock: Lock for modifying the pending set. + * @pending.head: List-head of the pending set/list. + * @pending.count: Number of currently pending packets. + * @tx: Transmitter subsystem. + * @tx.running: Flag indicating (desired) transmitter thread state. + * @tx.thread: Transmitter thread. + * @tx.thread_cplt_tx: Completion for transmitter thread waiting on transfer. + * @tx.thread_cplt_pkt: Completion for transmitter thread waiting on packets. + * @tx.packet_wq: Waitqueue-head for packet transmit completion. + * @rx: Receiver subsystem. + * @rx.thread: Receiver thread. + * @rx.wq: Waitqueue-head for receiver thread. + * @rx.fifo: Buffer for receiving data/pushing data to receiver thread. + * @rx.buf: Buffer for evaluating data on receiver thread. + * @rx.blocked: List of recent/blocked sequence IDs to detect retransmission. + * @rx.blocked.seqs: Array of blocked sequence IDs. + * @rx.blocked.offset: Offset indicating where a new ID should be inserted. + * @rtx_timeout: Retransmission timeout subsystem. + * @rtx_timeout.lock: Lock for modifying the retransmission timeout reaper. + * @rtx_timeout.timeout: Timeout interval for retransmission. + * @rtx_timeout.expires: Time specifying when the reaper work is next scheduled. + * @rtx_timeout.reaper: Work performing timeout checks and subsequent actions. + * @ops: Packet layer operations. + */ +struct ssh_ptl { + struct serdev_device *serdev; + unsigned long state; + + struct { + spinlock_t lock; + struct list_head head; + } queue; + + struct { + spinlock_t lock; + struct list_head head; + atomic_t count; + } pending; + + struct { + atomic_t running; + struct task_struct *thread; + struct completion thread_cplt_tx; + struct completion thread_cplt_pkt; + struct wait_queue_head packet_wq; + } tx; + + struct { + struct task_struct *thread; + struct wait_queue_head wq; + struct kfifo fifo; + struct sshp_buf buf; + + struct { + u16 seqs[8]; + u16 offset; + } blocked; + } rx; + + struct { + spinlock_t lock; + ktime_t timeout; + ktime_t expires; + struct delayed_work reaper; + } rtx_timeout; + + struct ssh_ptl_ops ops; +}; + +#define __ssam_prcond(func, p, fmt, ...) \ + do { \ + typeof(p) __p = (p); \ + \ + if (__p) \ + func(__p, fmt, ##__VA_ARGS__); \ + } while (0) + +#define ptl_dbg(p, fmt, ...) dev_dbg(&(p)->serdev->dev, fmt, ##__VA_ARGS__) +#define ptl_info(p, fmt, ...) dev_info(&(p)->serdev->dev, fmt, ##__VA_ARGS__) +#define ptl_warn(p, fmt, ...) dev_warn(&(p)->serdev->dev, fmt, ##__VA_ARGS__) +#define ptl_err(p, fmt, ...) dev_err(&(p)->serdev->dev, fmt, ##__VA_ARGS__) +#define ptl_dbg_cond(p, fmt, ...) __ssam_prcond(ptl_dbg, p, fmt, ##__VA_ARGS__) + +#define to_ssh_ptl(ptr, member) \ + container_of(ptr, struct ssh_ptl, member) + +int ssh_ptl_init(struct ssh_ptl *ptl, struct serdev_device *serdev, + struct ssh_ptl_ops *ops); + +void ssh_ptl_destroy(struct ssh_ptl *ptl); + +/** + * ssh_ptl_get_device() - Get device associated with packet transport layer. + * @ptl: The packet transport layer. + * + * Return: Returns the device on which the given packet transport layer builds + * upon. + */ +static inline struct device *ssh_ptl_get_device(struct ssh_ptl *ptl) +{ + return ptl->serdev ? &ptl->serdev->dev : NULL; +} + +int ssh_ptl_tx_start(struct ssh_ptl *ptl); +int ssh_ptl_tx_stop(struct ssh_ptl *ptl); +int ssh_ptl_rx_start(struct ssh_ptl *ptl); +int ssh_ptl_rx_stop(struct ssh_ptl *ptl); +void ssh_ptl_shutdown(struct ssh_ptl *ptl); + +int ssh_ptl_submit(struct ssh_ptl *ptl, struct ssh_packet *p); +void ssh_ptl_cancel(struct ssh_packet *p); + +int ssh_ptl_rx_rcvbuf(struct ssh_ptl *ptl, const u8 *buf, size_t n); + +/** + * ssh_ptl_tx_wakeup_transfer() - Wake up packet transmitter thread for + * transfer. + * @ptl: The packet transport layer. + * + * Wakes up the packet transmitter thread, notifying it that the underlying + * transport has more space for data to be transmitted. If the packet + * transport layer has been shut down, calls to this function will be ignored. + */ +static inline void ssh_ptl_tx_wakeup_transfer(struct ssh_ptl *ptl) +{ + if (test_bit(SSH_PTL_SF_SHUTDOWN_BIT, &ptl->state)) + return; + + complete(&ptl->tx.thread_cplt_tx); +} + +void ssh_packet_init(struct ssh_packet *packet, unsigned long type, + u8 priority, const struct ssh_packet_ops *ops); + +#endif /* _SURFACE_AGGREGATOR_SSH_PACKET_LAYER_H */ diff --git a/drivers/platform/surface/aggregator/ssh_parser.c b/drivers/platform/surface/aggregator/ssh_parser.c new file mode 100644 index 000000000000..e2dead8de94a --- /dev/null +++ b/drivers/platform/surface/aggregator/ssh_parser.c @@ -0,0 +1,228 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * SSH message parser. + * + * Copyright (C) 2019-2020 Maximilian Luz + */ + +#include +#include +#include +#include + +#include +#include "ssh_parser.h" + +/** + * sshp_validate_crc() - Validate a CRC in raw message data. + * @src: The span of data over which the CRC should be computed. + * @crc: The pointer to the expected u16 CRC value. + * + * Computes the CRC of the provided data span (@src), compares it to the CRC + * stored at the given address (@crc), and returns the result of this + * comparison, i.e. %true if equal. This function is intended to run on raw + * input/message data. + * + * Return: Returns %true if the computed CRC matches the stored CRC, %false + * otherwise. + */ +static bool sshp_validate_crc(const struct ssam_span *src, const u8 *crc) +{ + u16 actual = ssh_crc(src->ptr, src->len); + u16 expected = get_unaligned_le16(crc); + + return actual == expected; +} + +/** + * sshp_starts_with_syn() - Check if the given data starts with SSH SYN bytes. + * @src: The data span to check the start of. + */ +static bool sshp_starts_with_syn(const struct ssam_span *src) +{ + return src->len >= 2 && get_unaligned_le16(src->ptr) == SSH_MSG_SYN; +} + +/** + * sshp_find_syn() - Find SSH SYN bytes in the given data span. + * @src: The data span to search in. + * @rem: The span (output) indicating the remaining data, starting with SSH + * SYN bytes, if found. + * + * Search for SSH SYN bytes in the given source span. If found, set the @rem + * span to the remaining data, starting with the first SYN bytes and capped by + * the source span length, and return %true. This function does not copy any + * data, but rather only sets pointers to the respective start addresses and + * length values. + * + * If no SSH SYN bytes could be found, set the @rem span to the zero-length + * span at the end of the source span and return %false. + * + * If partial SSH SYN bytes could be found at the end of the source span, set + * the @rem span to cover these partial SYN bytes, capped by the end of the + * source span, and return %false. This function should then be re-run once + * more data is available. + * + * Return: Returns %true if a complete SSH SYN sequence could be found, + * %false otherwise. + */ +bool sshp_find_syn(const struct ssam_span *src, struct ssam_span *rem) +{ + size_t i; + + for (i = 0; i < src->len - 1; i++) { + if (likely(get_unaligned_le16(src->ptr + i) == SSH_MSG_SYN)) { + rem->ptr = src->ptr + i; + rem->len = src->len - i; + return true; + } + } + + if (unlikely(src->ptr[src->len - 1] == (SSH_MSG_SYN & 0xff))) { + rem->ptr = src->ptr + src->len - 1; + rem->len = 1; + return false; + } + + rem->ptr = src->ptr + src->len; + rem->len = 0; + return false; +} + +/** + * sshp_parse_frame() - Parse SSH frame. + * @dev: The device used for logging. + * @source: The source to parse from. + * @frame: The parsed frame (output). + * @payload: The parsed payload (output). + * @maxlen: The maximum supported message length. + * + * Parses and validates a SSH frame, including its payload, from the given + * source. Sets the provided @frame pointer to the start of the frame and + * writes the limits of the frame payload to the provided @payload span + * pointer. + * + * This function does not copy any data, but rather only validates the message + * data and sets pointers (and length values) to indicate the respective parts. + * + * If no complete SSH frame could be found, the frame pointer will be set to + * the %NULL pointer and the payload span will be set to the null span (start + * pointer %NULL, size zero). + * + * Return: Returns zero on success or if the frame is incomplete, %-ENOMSG if + * the start of the message is invalid, %-EBADMSG if any (frame-header or + * payload) CRC is invalid, or %-EMSGSIZE if the SSH message is bigger than + * the maximum message length specified in the @maxlen parameter. + */ +int sshp_parse_frame(const struct device *dev, const struct ssam_span *source, + struct ssh_frame **frame, struct ssam_span *payload, + size_t maxlen) +{ + struct ssam_span sf; + struct ssam_span sp; + + /* Initialize output. */ + *frame = NULL; + payload->ptr = NULL; + payload->len = 0; + + if (!sshp_starts_with_syn(source)) { + dev_warn(dev, "rx: parser: invalid start of frame\n"); + return -ENOMSG; + } + + /* Check for minimum packet length. */ + if (unlikely(source->len < SSH_MESSAGE_LENGTH(0))) { + dev_dbg(dev, "rx: parser: not enough data for frame\n"); + return 0; + } + + /* Pin down frame. */ + sf.ptr = source->ptr + sizeof(u16); + sf.len = sizeof(struct ssh_frame); + + /* Validate frame CRC. */ + if (unlikely(!sshp_validate_crc(&sf, sf.ptr + sf.len))) { + dev_warn(dev, "rx: parser: invalid frame CRC\n"); + return -EBADMSG; + } + + /* Ensure packet does not exceed maximum length. */ + sp.len = get_unaligned_le16(&((struct ssh_frame *)sf.ptr)->len); + if (unlikely(SSH_MESSAGE_LENGTH(sp.len) > maxlen)) { + dev_warn(dev, "rx: parser: frame too large: %llu bytes\n", + SSH_MESSAGE_LENGTH(sp.len)); + return -EMSGSIZE; + } + + /* Pin down payload. */ + sp.ptr = sf.ptr + sf.len + sizeof(u16); + + /* Check for frame + payload length. */ + if (source->len < SSH_MESSAGE_LENGTH(sp.len)) { + dev_dbg(dev, "rx: parser: not enough data for payload\n"); + return 0; + } + + /* Validate payload CRC. */ + if (unlikely(!sshp_validate_crc(&sp, sp.ptr + sp.len))) { + dev_warn(dev, "rx: parser: invalid payload CRC\n"); + return -EBADMSG; + } + + *frame = (struct ssh_frame *)sf.ptr; + *payload = sp; + + dev_dbg(dev, "rx: parser: valid frame found (type: %#04x, len: %u)\n", + (*frame)->type, (*frame)->len); + + return 0; +} + +/** + * sshp_parse_command() - Parse SSH command frame payload. + * @dev: The device used for logging. + * @source: The source to parse from. + * @command: The parsed command (output). + * @command_data: The parsed command data/payload (output). + * + * Parses and validates a SSH command frame payload. Sets the @command pointer + * to the command header and the @command_data span to the command data (i.e. + * payload of the command). This will result in a zero-length span if the + * command does not have any associated data/payload. This function does not + * check the frame-payload-type field, which should be checked by the caller + * before calling this function. + * + * The @source parameter should be the complete frame payload, e.g. returned + * by the sshp_parse_frame() command. + * + * This function does not copy any data, but rather only validates the frame + * payload data and sets pointers (and length values) to indicate the + * respective parts. + * + * Return: Returns zero on success or %-ENOMSG if @source does not represent a + * valid command-type frame payload, i.e. is too short. + */ +int sshp_parse_command(const struct device *dev, const struct ssam_span *source, + struct ssh_command **command, + struct ssam_span *command_data) +{ + /* Check for minimum length. */ + if (unlikely(source->len < sizeof(struct ssh_command))) { + *command = NULL; + command_data->ptr = NULL; + command_data->len = 0; + + dev_err(dev, "rx: parser: command payload is too short\n"); + return -ENOMSG; + } + + *command = (struct ssh_command *)source->ptr; + command_data->ptr = source->ptr + sizeof(struct ssh_command); + command_data->len = source->len - sizeof(struct ssh_command); + + dev_dbg(dev, "rx: parser: valid command found (tc: %#04x, cid: %#04x)\n", + (*command)->tc, (*command)->cid); + + return 0; +} diff --git a/drivers/platform/surface/aggregator/ssh_parser.h b/drivers/platform/surface/aggregator/ssh_parser.h new file mode 100644 index 000000000000..63c38d350988 --- /dev/null +++ b/drivers/platform/surface/aggregator/ssh_parser.h @@ -0,0 +1,154 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * SSH message parser. + * + * Copyright (C) 2019-2020 Maximilian Luz + */ + +#ifndef _SURFACE_AGGREGATOR_SSH_PARSER_H +#define _SURFACE_AGGREGATOR_SSH_PARSER_H + +#include +#include +#include +#include + +#include + +/** + * struct sshp_buf - Parser buffer for SSH messages. + * @ptr: Pointer to the beginning of the buffer. + * @len: Number of bytes used in the buffer. + * @cap: Maximum capacity of the buffer. + */ +struct sshp_buf { + u8 *ptr; + size_t len; + size_t cap; +}; + +/** + * sshp_buf_init() - Initialize a SSH parser buffer. + * @buf: The buffer to initialize. + * @ptr: The memory backing the buffer. + * @cap: The length of the memory backing the buffer, i.e. its capacity. + * + * Initializes the buffer with the given memory as backing and set its used + * length to zero. + */ +static inline void sshp_buf_init(struct sshp_buf *buf, u8 *ptr, size_t cap) +{ + buf->ptr = ptr; + buf->len = 0; + buf->cap = cap; +} + +/** + * sshp_buf_alloc() - Allocate and initialize a SSH parser buffer. + * @buf: The buffer to initialize/allocate to. + * @cap: The desired capacity of the buffer. + * @flags: The flags used for allocating the memory. + * + * Allocates @cap bytes and initializes the provided buffer struct with the + * allocated memory. + * + * Return: Returns zero on success and %-ENOMEM if allocation failed. + */ +static inline int sshp_buf_alloc(struct sshp_buf *buf, size_t cap, gfp_t flags) +{ + u8 *ptr; + + ptr = kzalloc(cap, flags); + if (!ptr) + return -ENOMEM; + + sshp_buf_init(buf, ptr, cap); + return 0; +} + +/** + * sshp_buf_free() - Free a SSH parser buffer. + * @buf: The buffer to free. + * + * Frees a SSH parser buffer by freeing the memory backing it and then + * resetting its pointer to %NULL and length and capacity to zero. Intended to + * free a buffer previously allocated with sshp_buf_alloc(). + */ +static inline void sshp_buf_free(struct sshp_buf *buf) +{ + kfree(buf->ptr); + buf->ptr = NULL; + buf->len = 0; + buf->cap = 0; +} + +/** + * sshp_buf_drop() - Drop data from the beginning of the buffer. + * @buf: The buffer to drop data from. + * @n: The number of bytes to drop. + * + * Drops the first @n bytes from the buffer. Re-aligns any remaining data to + * the beginning of the buffer. + */ +static inline void sshp_buf_drop(struct sshp_buf *buf, size_t n) +{ + memmove(buf->ptr, buf->ptr + n, buf->len - n); + buf->len -= n; +} + +/** + * sshp_buf_read_from_fifo() - Transfer data from a fifo to the buffer. + * @buf: The buffer to write the data into. + * @fifo: The fifo to read the data from. + * + * Transfers the data contained in the fifo to the buffer, removing it from + * the fifo. This function will try to transfer as much data as possible, + * limited either by the remaining space in the buffer or by the number of + * bytes available in the fifo. + * + * Return: Returns the number of bytes transferred. + */ +static inline size_t sshp_buf_read_from_fifo(struct sshp_buf *buf, + struct kfifo *fifo) +{ + size_t n; + + n = kfifo_out(fifo, buf->ptr + buf->len, buf->cap - buf->len); + buf->len += n; + + return n; +} + +/** + * sshp_buf_span_from() - Initialize a span from the given buffer and offset. + * @buf: The buffer to create the span from. + * @offset: The offset in the buffer at which the span should start. + * @span: The span to initialize (output). + * + * Initializes the provided span to point to the memory at the given offset in + * the buffer, with the length of the span being capped by the number of bytes + * used in the buffer after the offset (i.e. bytes remaining after the + * offset). + * + * Warning: This function does not validate that @offset is less than or equal + * to the number of bytes used in the buffer or the buffer capacity. This must + * be guaranteed by the caller. + */ +static inline void sshp_buf_span_from(struct sshp_buf *buf, size_t offset, + struct ssam_span *span) +{ + span->ptr = buf->ptr + offset; + span->len = buf->len - offset; +} + +bool sshp_find_syn(const struct ssam_span *src, struct ssam_span *rem); + +int sshp_parse_frame(const struct device *dev, const struct ssam_span *source, + struct ssh_frame **frame, struct ssam_span *payload, + size_t maxlen); + +int sshp_parse_command(const struct device *dev, const struct ssam_span *source, + struct ssh_command **command, + struct ssam_span *command_data); + +#endif /* _SURFACE_AGGREGATOR_SSH_PARSER_h */ diff --git a/drivers/platform/surface/aggregator/ssh_request_layer.c b/drivers/platform/surface/aggregator/ssh_request_layer.c new file mode 100644 index 000000000000..66c839a995f3 --- /dev/null +++ b/drivers/platform/surface/aggregator/ssh_request_layer.c @@ -0,0 +1,1211 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * SSH request transport layer. + * + * Copyright (C) 2019-2020 Maximilian Luz + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#include "ssh_packet_layer.h" +#include "ssh_request_layer.h" + +/* + * SSH_RTL_REQUEST_TIMEOUT - Request timeout. + * + * Timeout as ktime_t delta for request responses. If we have not received a + * response in this time-frame after finishing the underlying packet + * transmission, the request will be completed with %-ETIMEDOUT as status + * code. + */ +#define SSH_RTL_REQUEST_TIMEOUT ms_to_ktime(3000) + +/* + * SSH_RTL_REQUEST_TIMEOUT_RESOLUTION - Request timeout granularity. + * + * Time-resolution for timeouts. Should be larger than one jiffy to avoid + * direct re-scheduling of reaper work_struct. + */ +#define SSH_RTL_REQUEST_TIMEOUT_RESOLUTION ms_to_ktime(max(2000 / HZ, 50)) + +/* + * SSH_RTL_MAX_PENDING - Maximum number of pending requests. + * + * Maximum number of requests concurrently waiting to be completed (i.e. + * waiting for the corresponding packet transmission to finish if they don't + * have a response or waiting for a response if they have one). + */ +#define SSH_RTL_MAX_PENDING 3 + +/* + * SSH_RTL_TX_BATCH - Maximum number of requests processed per work execution. + * Used to prevent livelocking of the workqueue. Value chosen via educated + * guess, may be adjusted. + */ +#define SSH_RTL_TX_BATCH 10 + +static u16 ssh_request_get_rqid(struct ssh_request *rqst) +{ + return get_unaligned_le16(rqst->packet.data.ptr + + SSH_MSGOFFSET_COMMAND(rqid)); +} + +static u32 ssh_request_get_rqid_safe(struct ssh_request *rqst) +{ + if (!rqst->packet.data.ptr) + return U32_MAX; + + return ssh_request_get_rqid(rqst); +} + +static void ssh_rtl_queue_remove(struct ssh_request *rqst) +{ + struct ssh_rtl *rtl = ssh_request_rtl(rqst); + + spin_lock(&rtl->queue.lock); + + if (!test_and_clear_bit(SSH_REQUEST_SF_QUEUED_BIT, &rqst->state)) { + spin_unlock(&rtl->queue.lock); + return; + } + + list_del(&rqst->node); + + spin_unlock(&rtl->queue.lock); + ssh_request_put(rqst); +} + +static bool ssh_rtl_queue_empty(struct ssh_rtl *rtl) +{ + bool empty; + + spin_lock(&rtl->queue.lock); + empty = list_empty(&rtl->queue.head); + spin_unlock(&rtl->queue.lock); + + return empty; +} + +static void ssh_rtl_pending_remove(struct ssh_request *rqst) +{ + struct ssh_rtl *rtl = ssh_request_rtl(rqst); + + spin_lock(&rtl->pending.lock); + + if (!test_and_clear_bit(SSH_REQUEST_SF_PENDING_BIT, &rqst->state)) { + spin_unlock(&rtl->pending.lock); + return; + } + + atomic_dec(&rtl->pending.count); + list_del(&rqst->node); + + spin_unlock(&rtl->pending.lock); + + ssh_request_put(rqst); +} + +static int ssh_rtl_tx_pending_push(struct ssh_request *rqst) +{ + struct ssh_rtl *rtl = ssh_request_rtl(rqst); + + spin_lock(&rtl->pending.lock); + + if (test_bit(SSH_REQUEST_SF_LOCKED_BIT, &rqst->state)) { + spin_unlock(&rtl->pending.lock); + return -EINVAL; + } + + if (test_and_set_bit(SSH_REQUEST_SF_PENDING_BIT, &rqst->state)) { + spin_unlock(&rtl->pending.lock); + return -EALREADY; + } + + atomic_inc(&rtl->pending.count); + list_add_tail(&ssh_request_get(rqst)->node, &rtl->pending.head); + + spin_unlock(&rtl->pending.lock); + return 0; +} + +static void ssh_rtl_complete_with_status(struct ssh_request *rqst, int status) +{ + struct ssh_rtl *rtl = ssh_request_rtl(rqst); + + /* rtl/ptl may not be set if we're canceling before submitting. */ + rtl_dbg_cond(rtl, "rtl: completing request (rqid: %#06x, status: %d)\n", + ssh_request_get_rqid_safe(rqst), status); + + rqst->ops->complete(rqst, NULL, NULL, status); +} + +static void ssh_rtl_complete_with_rsp(struct ssh_request *rqst, + const struct ssh_command *cmd, + const struct ssam_span *data) +{ + struct ssh_rtl *rtl = ssh_request_rtl(rqst); + + rtl_dbg(rtl, "rtl: completing request with response (rqid: %#06x)\n", + ssh_request_get_rqid(rqst)); + + rqst->ops->complete(rqst, cmd, data, 0); +} + +static bool ssh_rtl_tx_can_process(struct ssh_request *rqst) +{ + struct ssh_rtl *rtl = ssh_request_rtl(rqst); + + if (test_bit(SSH_REQUEST_TY_FLUSH_BIT, &rqst->state)) + return !atomic_read(&rtl->pending.count); + + return atomic_read(&rtl->pending.count) < SSH_RTL_MAX_PENDING; +} + +static struct ssh_request *ssh_rtl_tx_next(struct ssh_rtl *rtl) +{ + struct ssh_request *rqst = ERR_PTR(-ENOENT); + struct ssh_request *p, *n; + + spin_lock(&rtl->queue.lock); + + /* Find first non-locked request and remove it. */ + list_for_each_entry_safe(p, n, &rtl->queue.head, node) { + if (unlikely(test_bit(SSH_REQUEST_SF_LOCKED_BIT, &p->state))) + continue; + + if (!ssh_rtl_tx_can_process(p)) { + rqst = ERR_PTR(-EBUSY); + break; + } + + /* Remove from queue and mark as transmitting. */ + set_bit(SSH_REQUEST_SF_TRANSMITTING_BIT, &p->state); + /* Ensure state never gets zero. */ + smp_mb__before_atomic(); + clear_bit(SSH_REQUEST_SF_QUEUED_BIT, &p->state); + + list_del(&p->node); + + rqst = p; + break; + } + + spin_unlock(&rtl->queue.lock); + return rqst; +} + +static int ssh_rtl_tx_try_process_one(struct ssh_rtl *rtl) +{ + struct ssh_request *rqst; + int status; + + /* Get and prepare next request for transmit. */ + rqst = ssh_rtl_tx_next(rtl); + if (IS_ERR(rqst)) + return PTR_ERR(rqst); + + /* Add it to/mark it as pending. */ + status = ssh_rtl_tx_pending_push(rqst); + if (status) { + ssh_request_put(rqst); + return -EAGAIN; + } + + /* Submit packet. */ + status = ssh_ptl_submit(&rtl->ptl, &rqst->packet); + if (status == -ESHUTDOWN) { + /* + * Packet has been refused due to the packet layer shutting + * down. Complete it here. + */ + set_bit(SSH_REQUEST_SF_LOCKED_BIT, &rqst->state); + /* + * Note: A barrier is not required here, as there are only two + * references in the system at this point: The one that we have, + * and the other one that belongs to the pending set. Due to the + * request being marked as "transmitting", our process is the + * only one allowed to remove the pending node and change the + * state. Normally, the task would fall to the packet callback, + * but as this is a path where submission failed, this callback + * will never be executed. + */ + + ssh_rtl_pending_remove(rqst); + ssh_rtl_complete_with_status(rqst, -ESHUTDOWN); + + ssh_request_put(rqst); + return -ESHUTDOWN; + + } else if (status) { + /* + * If submitting the packet failed and the packet layer isn't + * shutting down, the packet has either been submitted/queued + * before (-EALREADY, which cannot happen as we have + * guaranteed that requests cannot be re-submitted), or the + * packet was marked as locked (-EINVAL). To mark the packet + * locked at this stage, the request, and thus the packets + * itself, had to have been canceled. Simply drop the + * reference. Cancellation itself will remove it from the set + * of pending requests. + */ + + WARN_ON(status != -EINVAL); + + ssh_request_put(rqst); + return -EAGAIN; + } + + ssh_request_put(rqst); + return 0; +} + +static bool ssh_rtl_tx_schedule(struct ssh_rtl *rtl) +{ + if (atomic_read(&rtl->pending.count) >= SSH_RTL_MAX_PENDING) + return false; + + if (ssh_rtl_queue_empty(rtl)) + return false; + + return schedule_work(&rtl->tx.work); +} + +static void ssh_rtl_tx_work_fn(struct work_struct *work) +{ + struct ssh_rtl *rtl = to_ssh_rtl(work, tx.work); + unsigned int iterations = SSH_RTL_TX_BATCH; + int status; + + /* + * Try to be nice and not block/live-lock the workqueue: Run a maximum + * of 10 tries, then re-submit if necessary. This should not be + * necessary for normal execution, but guarantee it anyway. + */ + do { + status = ssh_rtl_tx_try_process_one(rtl); + if (status == -ENOENT || status == -EBUSY) + return; /* No more requests to process. */ + + if (status == -ESHUTDOWN) { + /* + * Packet system shutting down. No new packets can be + * transmitted. Return silently, the party initiating + * the shutdown should handle the rest. + */ + return; + } + + WARN_ON(status != 0 && status != -EAGAIN); + } while (--iterations); + + /* Out of tries, reschedule. */ + ssh_rtl_tx_schedule(rtl); +} + +/** + * ssh_rtl_submit() - Submit a request to the transport layer. + * @rtl: The request transport layer. + * @rqst: The request to submit. + * + * Submits a request to the transport layer. A single request may not be + * submitted multiple times without reinitializing it. + * + * Return: Returns zero on success, %-EINVAL if the request type is invalid or + * the request has been canceled prior to submission, %-EALREADY if the + * request has already been submitted, or %-ESHUTDOWN in case the request + * transport layer has been shut down. + */ +int ssh_rtl_submit(struct ssh_rtl *rtl, struct ssh_request *rqst) +{ + /* + * Ensure that requests expecting a response are sequenced. If this + * invariant ever changes, see the comment in ssh_rtl_complete() on what + * is required to be changed in the code. + */ + if (test_bit(SSH_REQUEST_TY_HAS_RESPONSE_BIT, &rqst->state)) + if (!test_bit(SSH_PACKET_TY_SEQUENCED_BIT, &rqst->packet.state)) + return -EINVAL; + + spin_lock(&rtl->queue.lock); + + /* + * Try to set ptl and check if this request has already been submitted. + * + * Must be inside lock as we might run into a lost update problem + * otherwise: If this were outside of the lock, cancellation in + * ssh_rtl_cancel_nonpending() may run after we've set the ptl + * reference but before we enter the lock. In that case, we'd detect + * that the request is being added to the queue and would try to remove + * it from that, but removal might fail because it hasn't actually been + * added yet. By putting this cmpxchg in the critical section, we + * ensure that the queuing detection only triggers when we are already + * in the critical section and the remove process will wait until the + * push operation has been completed (via lock) due to that. Only then, + * we can safely try to remove it. + */ + if (cmpxchg(&rqst->packet.ptl, NULL, &rtl->ptl)) { + spin_unlock(&rtl->queue.lock); + return -EALREADY; + } + + /* + * Ensure that we set ptl reference before we continue modifying state. + * This is required for non-pending cancellation. This barrier is paired + * with the one in ssh_rtl_cancel_nonpending(). + * + * By setting the ptl reference before we test for "locked", we can + * check if the "locked" test may have already run. See comments in + * ssh_rtl_cancel_nonpending() for more detail. + */ + smp_mb__after_atomic(); + + if (test_bit(SSH_RTL_SF_SHUTDOWN_BIT, &rtl->state)) { + spin_unlock(&rtl->queue.lock); + return -ESHUTDOWN; + } + + if (test_bit(SSH_REQUEST_SF_LOCKED_BIT, &rqst->state)) { + spin_unlock(&rtl->queue.lock); + return -EINVAL; + } + + set_bit(SSH_REQUEST_SF_QUEUED_BIT, &rqst->state); + list_add_tail(&ssh_request_get(rqst)->node, &rtl->queue.head); + + spin_unlock(&rtl->queue.lock); + + ssh_rtl_tx_schedule(rtl); + return 0; +} + +static void ssh_rtl_timeout_reaper_mod(struct ssh_rtl *rtl, ktime_t now, + ktime_t expires) +{ + unsigned long delta = msecs_to_jiffies(ktime_ms_delta(expires, now)); + ktime_t aexp = ktime_add(expires, SSH_RTL_REQUEST_TIMEOUT_RESOLUTION); + + spin_lock(&rtl->rtx_timeout.lock); + + /* Re-adjust / schedule reaper only if it is above resolution delta. */ + if (ktime_before(aexp, rtl->rtx_timeout.expires)) { + rtl->rtx_timeout.expires = expires; + mod_delayed_work(system_wq, &rtl->rtx_timeout.reaper, delta); + } + + spin_unlock(&rtl->rtx_timeout.lock); +} + +static void ssh_rtl_timeout_start(struct ssh_request *rqst) +{ + struct ssh_rtl *rtl = ssh_request_rtl(rqst); + ktime_t timestamp = ktime_get_coarse_boottime(); + ktime_t timeout = rtl->rtx_timeout.timeout; + + if (test_bit(SSH_REQUEST_SF_LOCKED_BIT, &rqst->state)) + return; + + /* + * Note: The timestamp gets set only once. This happens on the packet + * callback. All other access to it is read-only. + */ + WRITE_ONCE(rqst->timestamp, timestamp); + /* + * Ensure timestamp is set before starting the reaper. Paired with + * implicit barrier following check on ssh_request_get_expiration() in + * ssh_rtl_timeout_reap. + */ + smp_mb__after_atomic(); + + ssh_rtl_timeout_reaper_mod(rtl, timestamp, timestamp + timeout); +} + +static void ssh_rtl_complete(struct ssh_rtl *rtl, + const struct ssh_command *command, + const struct ssam_span *command_data) +{ + struct ssh_request *r = NULL; + struct ssh_request *p, *n; + u16 rqid = get_unaligned_le16(&command->rqid); + + /* + * Get request from pending based on request ID and mark it as response + * received and locked. + */ + spin_lock(&rtl->pending.lock); + list_for_each_entry_safe(p, n, &rtl->pending.head, node) { + /* We generally expect requests to be processed in order. */ + if (unlikely(ssh_request_get_rqid(p) != rqid)) + continue; + + /* + * Mark as "response received" and "locked" as we're going to + * complete it. + */ + set_bit(SSH_REQUEST_SF_LOCKED_BIT, &p->state); + set_bit(SSH_REQUEST_SF_RSPRCVD_BIT, &p->state); + /* Ensure state never gets zero. */ + smp_mb__before_atomic(); + clear_bit(SSH_REQUEST_SF_PENDING_BIT, &p->state); + + atomic_dec(&rtl->pending.count); + list_del(&p->node); + + r = p; + break; + } + spin_unlock(&rtl->pending.lock); + + if (!r) { + rtl_warn(rtl, "rtl: dropping unexpected command message (rqid = %#06x)\n", + rqid); + return; + } + + /* If the request hasn't been completed yet, we will do this now. */ + if (test_and_set_bit(SSH_REQUEST_SF_COMPLETED_BIT, &r->state)) { + ssh_request_put(r); + ssh_rtl_tx_schedule(rtl); + return; + } + + /* + * Make sure the request has been transmitted. In case of a sequenced + * request, we are guaranteed that the completion callback will run on + * the receiver thread directly when the ACK for the packet has been + * received. Similarly, this function is guaranteed to run on the + * receiver thread. Thus we are guaranteed that if the packet has been + * successfully transmitted and received an ACK, the transmitted flag + * has been set and is visible here. + * + * We are currently not handling unsequenced packets here, as those + * should never expect a response as ensured in ssh_rtl_submit. If this + * ever changes, one would have to test for + * + * (r->state & (transmitting | transmitted)) + * + * on unsequenced packets to determine if they could have been + * transmitted. There are no synchronization guarantees as in the + * sequenced case, since, in this case, the callback function will not + * run on the same thread. Thus an exact determination is impossible. + */ + if (!test_bit(SSH_REQUEST_SF_TRANSMITTED_BIT, &r->state)) { + rtl_err(rtl, "rtl: received response before ACK for request (rqid = %#06x)\n", + rqid); + + /* + * NB: Timeout has already been canceled, request already been + * removed from pending and marked as locked and completed. As + * we receive a "false" response, the packet might still be + * queued though. + */ + ssh_rtl_queue_remove(r); + + ssh_rtl_complete_with_status(r, -EREMOTEIO); + ssh_request_put(r); + + ssh_rtl_tx_schedule(rtl); + return; + } + + /* + * NB: Timeout has already been canceled, request already been + * removed from pending and marked as locked and completed. The request + * can also not be queued any more, as it has been marked as + * transmitting and later transmitted. Thus no need to remove it from + * anywhere. + */ + + ssh_rtl_complete_with_rsp(r, command, command_data); + ssh_request_put(r); + + ssh_rtl_tx_schedule(rtl); +} + +static bool ssh_rtl_cancel_nonpending(struct ssh_request *r) +{ + struct ssh_rtl *rtl; + unsigned long flags, fixed; + bool remove; + + /* + * Handle unsubmitted request: Try to mark the packet as locked, + * expecting the state to be zero (i.e. unsubmitted). Note that, if + * setting the state worked, we might still be adding the packet to the + * queue in a currently executing submit call. In that case, however, + * ptl reference must have been set previously, as locked is checked + * after setting ptl. Furthermore, when the ptl reference is set, the + * submission process is guaranteed to have entered the critical + * section. Thus only if we successfully locked this request and ptl is + * NULL, we have successfully removed the request, i.e. we are + * guaranteed that, due to the "locked" check in ssh_rtl_submit(), the + * packet will never be added. Otherwise, we need to try and grab it + * from the queue, where we are now guaranteed that the packet is or has + * been due to the critical section. + * + * Note that if the cmpxchg() fails, we are guaranteed that ptl has + * been set and is non-NULL, as states can only be nonzero after this + * has been set. Also note that we need to fetch the static (type) + * flags to ensure that they don't cause the cmpxchg() to fail. + */ + fixed = READ_ONCE(r->state) & SSH_REQUEST_FLAGS_TY_MASK; + flags = cmpxchg(&r->state, fixed, SSH_REQUEST_SF_LOCKED_BIT); + + /* + * Force correct ordering with regards to state and ptl reference access + * to safe-guard cancellation to concurrent submission against a + * lost-update problem. First try to exchange state, then also check + * ptl if that worked. This barrier is paired with the + * one in ssh_rtl_submit(). + */ + smp_mb__after_atomic(); + + if (flags == fixed && !READ_ONCE(r->packet.ptl)) { + if (test_and_set_bit(SSH_REQUEST_SF_COMPLETED_BIT, &r->state)) + return true; + + ssh_rtl_complete_with_status(r, -ECANCELED); + return true; + } + + rtl = ssh_request_rtl(r); + spin_lock(&rtl->queue.lock); + + /* + * Note: 1) Requests cannot be re-submitted. 2) If a request is + * queued, it cannot be "transmitting"/"pending" yet. Thus, if we + * successfully remove the request here, we have removed all its + * occurrences in the system. + */ + + remove = test_and_clear_bit(SSH_REQUEST_SF_QUEUED_BIT, &r->state); + if (!remove) { + spin_unlock(&rtl->queue.lock); + return false; + } + + set_bit(SSH_REQUEST_SF_LOCKED_BIT, &r->state); + list_del(&r->node); + + spin_unlock(&rtl->queue.lock); + + ssh_request_put(r); /* Drop reference obtained from queue. */ + + if (test_and_set_bit(SSH_REQUEST_SF_COMPLETED_BIT, &r->state)) + return true; + + ssh_rtl_complete_with_status(r, -ECANCELED); + return true; +} + +static bool ssh_rtl_cancel_pending(struct ssh_request *r) +{ + /* If the packet is already locked, it's going to be removed shortly. */ + if (test_and_set_bit(SSH_REQUEST_SF_LOCKED_BIT, &r->state)) + return true; + + /* + * Now that we have locked the packet, we have guaranteed that it can't + * be added to the system any more. If ptl is NULL, the locked + * check in ssh_rtl_submit() has not been run and any submission, + * currently in progress or called later, won't add the packet. Thus we + * can directly complete it. + * + * The implicit memory barrier of test_and_set_bit() should be enough + * to ensure that the correct order (first lock, then check ptl) is + * ensured. This is paired with the barrier in ssh_rtl_submit(). + */ + if (!READ_ONCE(r->packet.ptl)) { + if (test_and_set_bit(SSH_REQUEST_SF_COMPLETED_BIT, &r->state)) + return true; + + ssh_rtl_complete_with_status(r, -ECANCELED); + return true; + } + + /* + * Try to cancel the packet. If the packet has not been completed yet, + * this will subsequently (and synchronously) call the completion + * callback of the packet, which will complete the request. + */ + ssh_ptl_cancel(&r->packet); + + /* + * If the packet has been completed with success, i.e. has not been + * canceled by the above call, the request may not have been completed + * yet (may be waiting for a response). Check if we need to do this + * here. + */ + if (test_and_set_bit(SSH_REQUEST_SF_COMPLETED_BIT, &r->state)) + return true; + + ssh_rtl_queue_remove(r); + ssh_rtl_pending_remove(r); + ssh_rtl_complete_with_status(r, -ECANCELED); + + return true; +} + +/** + * ssh_rtl_cancel() - Cancel request. + * @rqst: The request to cancel. + * @pending: Whether to also cancel pending requests. + * + * Cancels the given request. If @pending is %false, this will not cancel + * pending requests, i.e. requests that have already been submitted to the + * packet layer but not been completed yet. If @pending is %true, this will + * cancel the given request regardless of the state it is in. + * + * If the request has been canceled by calling this function, both completion + * and release callbacks of the request will be executed in a reasonable + * time-frame. This may happen during execution of this function, however, + * there is no guarantee for this. For example, a request currently + * transmitting will be canceled/completed only after transmission has + * completed, and the respective callbacks will be executed on the transmitter + * thread, which may happen during, but also some time after execution of the + * cancel function. + * + * Return: Returns %true if the given request has been canceled or completed, + * either by this function or prior to calling this function, %false + * otherwise. If @pending is %true, this function will always return %true. + */ +bool ssh_rtl_cancel(struct ssh_request *rqst, bool pending) +{ + struct ssh_rtl *rtl; + bool canceled; + + if (test_and_set_bit(SSH_REQUEST_SF_CANCELED_BIT, &rqst->state)) + return true; + + if (pending) + canceled = ssh_rtl_cancel_pending(rqst); + else + canceled = ssh_rtl_cancel_nonpending(rqst); + + /* Note: rtl may be NULL if request has not been submitted yet. */ + rtl = ssh_request_rtl(rqst); + if (canceled && rtl) + ssh_rtl_tx_schedule(rtl); + + return canceled; +} + +static void ssh_rtl_packet_callback(struct ssh_packet *p, int status) +{ + struct ssh_request *r = to_ssh_request(p); + + if (unlikely(status)) { + set_bit(SSH_REQUEST_SF_LOCKED_BIT, &r->state); + + if (test_and_set_bit(SSH_REQUEST_SF_COMPLETED_BIT, &r->state)) + return; + + /* + * The packet may get canceled even though it has not been + * submitted yet. The request may still be queued. Check the + * queue and remove it if necessary. As the timeout would have + * been started in this function on success, there's no need + * to cancel it here. + */ + ssh_rtl_queue_remove(r); + ssh_rtl_pending_remove(r); + ssh_rtl_complete_with_status(r, status); + + ssh_rtl_tx_schedule(ssh_request_rtl(r)); + return; + } + + /* Update state: Mark as transmitted and clear transmitting. */ + set_bit(SSH_REQUEST_SF_TRANSMITTED_BIT, &r->state); + /* Ensure state never gets zero. */ + smp_mb__before_atomic(); + clear_bit(SSH_REQUEST_SF_TRANSMITTING_BIT, &r->state); + + /* If we expect a response, we just need to start the timeout. */ + if (test_bit(SSH_REQUEST_TY_HAS_RESPONSE_BIT, &r->state)) { + /* + * Note: This is the only place where the timestamp gets set, + * all other access to it is read-only. + */ + ssh_rtl_timeout_start(r); + return; + } + + /* + * If we don't expect a response, lock, remove, and complete the + * request. Note that, at this point, the request is guaranteed to have + * left the queue and no timeout has been started. Thus we only need to + * remove it from pending. If the request has already been completed (it + * may have been canceled) return. + */ + + set_bit(SSH_REQUEST_SF_LOCKED_BIT, &r->state); + if (test_and_set_bit(SSH_REQUEST_SF_COMPLETED_BIT, &r->state)) + return; + + ssh_rtl_pending_remove(r); + ssh_rtl_complete_with_status(r, 0); + + ssh_rtl_tx_schedule(ssh_request_rtl(r)); +} + +static ktime_t ssh_request_get_expiration(struct ssh_request *r, ktime_t timeout) +{ + ktime_t timestamp = READ_ONCE(r->timestamp); + + if (timestamp != KTIME_MAX) + return ktime_add(timestamp, timeout); + else + return KTIME_MAX; +} + +static void ssh_rtl_timeout_reap(struct work_struct *work) +{ + struct ssh_rtl *rtl = to_ssh_rtl(work, rtx_timeout.reaper.work); + struct ssh_request *r, *n; + LIST_HEAD(claimed); + ktime_t now = ktime_get_coarse_boottime(); + ktime_t timeout = rtl->rtx_timeout.timeout; + ktime_t next = KTIME_MAX; + + /* + * Mark reaper as "not pending". This is done before checking any + * requests to avoid lost-update type problems. + */ + spin_lock(&rtl->rtx_timeout.lock); + rtl->rtx_timeout.expires = KTIME_MAX; + spin_unlock(&rtl->rtx_timeout.lock); + + spin_lock(&rtl->pending.lock); + list_for_each_entry_safe(r, n, &rtl->pending.head, node) { + ktime_t expires = ssh_request_get_expiration(r, timeout); + + /* + * Check if the timeout hasn't expired yet. Find out next + * expiration date to be handled after this run. + */ + if (ktime_after(expires, now)) { + next = ktime_before(expires, next) ? expires : next; + continue; + } + + /* Avoid further transitions if locked. */ + if (test_and_set_bit(SSH_REQUEST_SF_LOCKED_BIT, &r->state)) + continue; + + /* + * We have now marked the packet as locked. Thus it cannot be + * added to the pending or queued lists again after we've + * removed it here. We can therefore re-use the node of this + * packet temporarily. + */ + + clear_bit(SSH_REQUEST_SF_PENDING_BIT, &r->state); + + atomic_dec(&rtl->pending.count); + list_del(&r->node); + + list_add_tail(&r->node, &claimed); + } + spin_unlock(&rtl->pending.lock); + + /* Cancel and complete the request. */ + list_for_each_entry_safe(r, n, &claimed, node) { + /* + * At this point we've removed the packet from pending. This + * means that we've obtained the last (only) reference of the + * system to it. Thus we can just complete it. + */ + if (!test_and_set_bit(SSH_REQUEST_SF_COMPLETED_BIT, &r->state)) + ssh_rtl_complete_with_status(r, -ETIMEDOUT); + + /* + * Drop the reference we've obtained by removing it from the + * pending set. + */ + list_del(&r->node); + ssh_request_put(r); + } + + /* Ensure that the reaper doesn't run again immediately. */ + next = max(next, ktime_add(now, SSH_RTL_REQUEST_TIMEOUT_RESOLUTION)); + if (next != KTIME_MAX) + ssh_rtl_timeout_reaper_mod(rtl, now, next); + + ssh_rtl_tx_schedule(rtl); +} + +static void ssh_rtl_rx_event(struct ssh_rtl *rtl, const struct ssh_command *cmd, + const struct ssam_span *data) +{ + rtl_dbg(rtl, "rtl: handling event (rqid: %#06x)\n", + get_unaligned_le16(&cmd->rqid)); + + rtl->ops.handle_event(rtl, cmd, data); +} + +static void ssh_rtl_rx_command(struct ssh_ptl *p, const struct ssam_span *data) +{ + struct ssh_rtl *rtl = to_ssh_rtl(p, ptl); + struct device *dev = &p->serdev->dev; + struct ssh_command *command; + struct ssam_span command_data; + + if (sshp_parse_command(dev, data, &command, &command_data)) + return; + + if (ssh_rqid_is_event(get_unaligned_le16(&command->rqid))) + ssh_rtl_rx_event(rtl, command, &command_data); + else + ssh_rtl_complete(rtl, command, &command_data); +} + +static void ssh_rtl_rx_data(struct ssh_ptl *p, const struct ssam_span *data) +{ + if (!data->len) { + ptl_err(p, "rtl: rx: no data frame payload\n"); + return; + } + + switch (data->ptr[0]) { + case SSH_PLD_TYPE_CMD: + ssh_rtl_rx_command(p, data); + break; + + default: + ptl_err(p, "rtl: rx: unknown frame payload type (type: %#04x)\n", + data->ptr[0]); + break; + } +} + +static void ssh_rtl_packet_release(struct ssh_packet *p) +{ + struct ssh_request *rqst; + + rqst = to_ssh_request(p); + rqst->ops->release(rqst); +} + +static const struct ssh_packet_ops ssh_rtl_packet_ops = { + .complete = ssh_rtl_packet_callback, + .release = ssh_rtl_packet_release, +}; + +/** + * ssh_request_init() - Initialize SSH request. + * @rqst: The request to initialize. + * @flags: Request flags, determining the type of the request. + * @ops: Request operations. + * + * Initializes the given SSH request and underlying packet. Sets the message + * buffer pointer to %NULL and the message buffer length to zero. This buffer + * has to be set separately via ssh_request_set_data() before submission and + * must contain a valid SSH request message. + * + * Return: Returns zero on success or %-EINVAL if the given flags are invalid. + */ +int ssh_request_init(struct ssh_request *rqst, enum ssam_request_flags flags, + const struct ssh_request_ops *ops) +{ + unsigned long type = BIT(SSH_PACKET_TY_BLOCKING_BIT); + + /* Unsequenced requests cannot have a response. */ + if (flags & SSAM_REQUEST_UNSEQUENCED && flags & SSAM_REQUEST_HAS_RESPONSE) + return -EINVAL; + + if (!(flags & SSAM_REQUEST_UNSEQUENCED)) + type |= BIT(SSH_PACKET_TY_SEQUENCED_BIT); + + ssh_packet_init(&rqst->packet, type, SSH_PACKET_PRIORITY(DATA, 0), + &ssh_rtl_packet_ops); + + INIT_LIST_HEAD(&rqst->node); + + rqst->state = 0; + if (flags & SSAM_REQUEST_HAS_RESPONSE) + rqst->state |= BIT(SSH_REQUEST_TY_HAS_RESPONSE_BIT); + + rqst->timestamp = KTIME_MAX; + rqst->ops = ops; + + return 0; +} + +/** + * ssh_rtl_init() - Initialize request transport layer. + * @rtl: The request transport layer to initialize. + * @serdev: The underlying serial device, i.e. the lower-level transport. + * @ops: Request transport layer operations. + * + * Initializes the given request transport layer and associated packet + * transport layer. Transmitter and receiver threads must be started + * separately via ssh_rtl_tx_start() and ssh_rtl_rx_start(), after the + * request-layer has been initialized and the lower-level serial device layer + * has been set up. + * + * Return: Returns zero on success and a nonzero error code on failure. + */ +int ssh_rtl_init(struct ssh_rtl *rtl, struct serdev_device *serdev, + const struct ssh_rtl_ops *ops) +{ + struct ssh_ptl_ops ptl_ops; + int status; + + ptl_ops.data_received = ssh_rtl_rx_data; + + status = ssh_ptl_init(&rtl->ptl, serdev, &ptl_ops); + if (status) + return status; + + spin_lock_init(&rtl->queue.lock); + INIT_LIST_HEAD(&rtl->queue.head); + + spin_lock_init(&rtl->pending.lock); + INIT_LIST_HEAD(&rtl->pending.head); + atomic_set_release(&rtl->pending.count, 0); + + INIT_WORK(&rtl->tx.work, ssh_rtl_tx_work_fn); + + spin_lock_init(&rtl->rtx_timeout.lock); + rtl->rtx_timeout.timeout = SSH_RTL_REQUEST_TIMEOUT; + rtl->rtx_timeout.expires = KTIME_MAX; + INIT_DELAYED_WORK(&rtl->rtx_timeout.reaper, ssh_rtl_timeout_reap); + + rtl->ops = *ops; + + return 0; +} + +/** + * ssh_rtl_destroy() - Deinitialize request transport layer. + * @rtl: The request transport layer to deinitialize. + * + * Deinitializes the given request transport layer and frees resources + * associated with it. If receiver and/or transmitter threads have been + * started, the layer must first be shut down via ssh_rtl_shutdown() before + * this function can be called. + */ +void ssh_rtl_destroy(struct ssh_rtl *rtl) +{ + ssh_ptl_destroy(&rtl->ptl); +} + +/** + * ssh_rtl_tx_start() - Start request transmitter and receiver. + * @rtl: The request transport layer. + * + * Return: Returns zero on success, a negative error code on failure. + */ +int ssh_rtl_start(struct ssh_rtl *rtl) +{ + int status; + + status = ssh_ptl_tx_start(&rtl->ptl); + if (status) + return status; + + ssh_rtl_tx_schedule(rtl); + + status = ssh_ptl_rx_start(&rtl->ptl); + if (status) { + ssh_rtl_flush(rtl, msecs_to_jiffies(5000)); + ssh_ptl_tx_stop(&rtl->ptl); + return status; + } + + return 0; +} + +struct ssh_flush_request { + struct ssh_request base; + struct completion completion; + int status; +}; + +static void ssh_rtl_flush_request_complete(struct ssh_request *r, + const struct ssh_command *cmd, + const struct ssam_span *data, + int status) +{ + struct ssh_flush_request *rqst; + + rqst = container_of(r, struct ssh_flush_request, base); + rqst->status = status; +} + +static void ssh_rtl_flush_request_release(struct ssh_request *r) +{ + struct ssh_flush_request *rqst; + + rqst = container_of(r, struct ssh_flush_request, base); + complete_all(&rqst->completion); +} + +static const struct ssh_request_ops ssh_rtl_flush_request_ops = { + .complete = ssh_rtl_flush_request_complete, + .release = ssh_rtl_flush_request_release, +}; + +/** + * ssh_rtl_flush() - Flush the request transport layer. + * @rtl: request transport layer + * @timeout: timeout for the flush operation in jiffies + * + * Queue a special flush request and wait for its completion. This request + * will be completed after all other currently queued and pending requests + * have been completed. Instead of a normal data packet, this request submits + * a special flush packet, meaning that upon completion, also the underlying + * packet transport layer has been flushed. + * + * Flushing the request layer guarantees that all previously submitted + * requests have been fully completed before this call returns. Additionally, + * flushing blocks execution of all later submitted requests until the flush + * has been completed. + * + * If the caller ensures that no new requests are submitted after a call to + * this function, the request transport layer is guaranteed to have no + * remaining requests when this call returns. The same guarantee does not hold + * for the packet layer, on which control packets may still be queued after + * this call. + * + * Return: Returns zero on success, %-ETIMEDOUT if the flush timed out and has + * been canceled as a result of the timeout, or %-ESHUTDOWN if the packet + * and/or request transport layer has been shut down before this call. May + * also return %-EINTR if the underlying packet transmission has been + * interrupted. + */ +int ssh_rtl_flush(struct ssh_rtl *rtl, unsigned long timeout) +{ + const unsigned int init_flags = SSAM_REQUEST_UNSEQUENCED; + struct ssh_flush_request rqst; + int status; + + ssh_request_init(&rqst.base, init_flags, &ssh_rtl_flush_request_ops); + rqst.base.packet.state |= BIT(SSH_PACKET_TY_FLUSH_BIT); + rqst.base.packet.priority = SSH_PACKET_PRIORITY(FLUSH, 0); + rqst.base.state |= BIT(SSH_REQUEST_TY_FLUSH_BIT); + + init_completion(&rqst.completion); + + status = ssh_rtl_submit(rtl, &rqst.base); + if (status) + return status; + + ssh_request_put(&rqst.base); + + if (!wait_for_completion_timeout(&rqst.completion, timeout)) { + ssh_rtl_cancel(&rqst.base, true); + wait_for_completion(&rqst.completion); + } + + WARN_ON(rqst.status != 0 && rqst.status != -ECANCELED && + rqst.status != -ESHUTDOWN && rqst.status != -EINTR); + + return rqst.status == -ECANCELED ? -ETIMEDOUT : rqst.status; +} + +/** + * ssh_rtl_shutdown() - Shut down request transport layer. + * @rtl: The request transport layer. + * + * Shuts down the request transport layer, removing and canceling all queued + * and pending requests. Requests canceled by this operation will be completed + * with %-ESHUTDOWN as status. Receiver and transmitter threads will be + * stopped, the lower-level packet layer will be shutdown. + * + * As a result of this function, the transport layer will be marked as shut + * down. Submission of requests after the transport layer has been shut down + * will fail with %-ESHUTDOWN. + */ +void ssh_rtl_shutdown(struct ssh_rtl *rtl) +{ + struct ssh_request *r, *n; + LIST_HEAD(claimed); + int pending; + + set_bit(SSH_RTL_SF_SHUTDOWN_BIT, &rtl->state); + /* + * Ensure that the layer gets marked as shut-down before actually + * stopping it. In combination with the check in ssh_rtl_submit(), + * this guarantees that no new requests can be added and all already + * queued requests are properly canceled. + */ + smp_mb__after_atomic(); + + /* Remove requests from queue. */ + spin_lock(&rtl->queue.lock); + list_for_each_entry_safe(r, n, &rtl->queue.head, node) { + set_bit(SSH_REQUEST_SF_LOCKED_BIT, &r->state); + /* Ensure state never gets zero. */ + smp_mb__before_atomic(); + clear_bit(SSH_REQUEST_SF_QUEUED_BIT, &r->state); + + list_del(&r->node); + list_add_tail(&r->node, &claimed); + } + spin_unlock(&rtl->queue.lock); + + /* + * We have now guaranteed that the queue is empty and no more new + * requests can be submitted (i.e. it will stay empty). This means that + * calling ssh_rtl_tx_schedule() will not schedule tx.work any more. So + * we can simply call cancel_work_sync() on tx.work here and when that + * returns, we've locked it down. This also means that after this call, + * we don't submit any more packets to the underlying packet layer, so + * we can also shut that down. + */ + + cancel_work_sync(&rtl->tx.work); + ssh_ptl_shutdown(&rtl->ptl); + cancel_delayed_work_sync(&rtl->rtx_timeout.reaper); + + /* + * Shutting down the packet layer should also have canceled all + * requests. Thus the pending set should be empty. Attempt to handle + * this gracefully anyways, even though this should be dead code. + */ + + pending = atomic_read(&rtl->pending.count); + if (WARN_ON(pending)) { + spin_lock(&rtl->pending.lock); + list_for_each_entry_safe(r, n, &rtl->pending.head, node) { + set_bit(SSH_REQUEST_SF_LOCKED_BIT, &r->state); + /* Ensure state never gets zero. */ + smp_mb__before_atomic(); + clear_bit(SSH_REQUEST_SF_PENDING_BIT, &r->state); + + list_del(&r->node); + list_add_tail(&r->node, &claimed); + } + spin_unlock(&rtl->pending.lock); + } + + /* Finally, cancel and complete the requests we claimed before. */ + list_for_each_entry_safe(r, n, &claimed, node) { + /* + * We need test_and_set() because we still might compete with + * cancellation. + */ + if (!test_and_set_bit(SSH_REQUEST_SF_COMPLETED_BIT, &r->state)) + ssh_rtl_complete_with_status(r, -ESHUTDOWN); + + /* + * Drop the reference we've obtained by removing it from the + * lists. + */ + list_del(&r->node); + ssh_request_put(r); + } +} diff --git a/drivers/platform/surface/aggregator/ssh_request_layer.h b/drivers/platform/surface/aggregator/ssh_request_layer.h new file mode 100644 index 000000000000..cb35815858d1 --- /dev/null +++ b/drivers/platform/surface/aggregator/ssh_request_layer.h @@ -0,0 +1,143 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * SSH request transport layer. + * + * Copyright (C) 2019-2020 Maximilian Luz + */ + +#ifndef _SURFACE_AGGREGATOR_SSH_REQUEST_LAYER_H +#define _SURFACE_AGGREGATOR_SSH_REQUEST_LAYER_H + +#include +#include +#include +#include +#include + +#include +#include + +#include "ssh_packet_layer.h" + +/** + * enum ssh_rtl_state_flags - State-flags for &struct ssh_rtl. + * + * @SSH_RTL_SF_SHUTDOWN_BIT: + * Indicates that the request transport layer has been shut down or is + * being shut down and should not accept any new requests. + */ +enum ssh_rtl_state_flags { + SSH_RTL_SF_SHUTDOWN_BIT, +}; + +/** + * struct ssh_rtl_ops - Callback operations for request transport layer. + * @handle_event: Function called when a SSH event has been received. The + * specified function takes the request layer, received command + * struct, and corresponding payload as arguments. If the event + * has no payload, the payload span is empty (not %NULL). + */ +struct ssh_rtl_ops { + void (*handle_event)(struct ssh_rtl *rtl, const struct ssh_command *cmd, + const struct ssam_span *data); +}; + +/** + * struct ssh_rtl - SSH request transport layer. + * @ptl: Underlying packet transport layer. + * @state: State(-flags) of the transport layer. + * @queue: Request submission queue. + * @queue.lock: Lock for modifying the request submission queue. + * @queue.head: List-head of the request submission queue. + * @pending: Set/list of pending requests. + * @pending.lock: Lock for modifying the request set. + * @pending.head: List-head of the pending set/list. + * @pending.count: Number of currently pending requests. + * @tx: Transmitter subsystem. + * @tx.work: Transmitter work item. + * @rtx_timeout: Retransmission timeout subsystem. + * @rtx_timeout.lock: Lock for modifying the retransmission timeout reaper. + * @rtx_timeout.timeout: Timeout interval for retransmission. + * @rtx_timeout.expires: Time specifying when the reaper work is next scheduled. + * @rtx_timeout.reaper: Work performing timeout checks and subsequent actions. + * @ops: Request layer operations. + */ +struct ssh_rtl { + struct ssh_ptl ptl; + unsigned long state; + + struct { + spinlock_t lock; + struct list_head head; + } queue; + + struct { + spinlock_t lock; + struct list_head head; + atomic_t count; + } pending; + + struct { + struct work_struct work; + } tx; + + struct { + spinlock_t lock; + ktime_t timeout; + ktime_t expires; + struct delayed_work reaper; + } rtx_timeout; + + struct ssh_rtl_ops ops; +}; + +#define rtl_dbg(r, fmt, ...) ptl_dbg(&(r)->ptl, fmt, ##__VA_ARGS__) +#define rtl_info(p, fmt, ...) ptl_info(&(p)->ptl, fmt, ##__VA_ARGS__) +#define rtl_warn(r, fmt, ...) ptl_warn(&(r)->ptl, fmt, ##__VA_ARGS__) +#define rtl_err(r, fmt, ...) ptl_err(&(r)->ptl, fmt, ##__VA_ARGS__) +#define rtl_dbg_cond(r, fmt, ...) __ssam_prcond(rtl_dbg, r, fmt, ##__VA_ARGS__) + +#define to_ssh_rtl(ptr, member) \ + container_of(ptr, struct ssh_rtl, member) + +/** + * ssh_rtl_get_device() - Get device associated with request transport layer. + * @rtl: The request transport layer. + * + * Return: Returns the device on which the given request transport layer + * builds upon. + */ +static inline struct device *ssh_rtl_get_device(struct ssh_rtl *rtl) +{ + return ssh_ptl_get_device(&rtl->ptl); +} + +/** + * ssh_request_rtl() - Get request transport layer associated with request. + * @rqst: The request to get the request transport layer reference for. + * + * Return: Returns the &struct ssh_rtl associated with the given SSH request. + */ +static inline struct ssh_rtl *ssh_request_rtl(struct ssh_request *rqst) +{ + struct ssh_ptl *ptl; + + ptl = READ_ONCE(rqst->packet.ptl); + return likely(ptl) ? to_ssh_rtl(ptl, ptl) : NULL; +} + +int ssh_rtl_submit(struct ssh_rtl *rtl, struct ssh_request *rqst); +bool ssh_rtl_cancel(struct ssh_request *rqst, bool pending); + +int ssh_rtl_init(struct ssh_rtl *rtl, struct serdev_device *serdev, + const struct ssh_rtl_ops *ops); + +int ssh_rtl_start(struct ssh_rtl *rtl); +int ssh_rtl_flush(struct ssh_rtl *rtl, unsigned long timeout); +void ssh_rtl_shutdown(struct ssh_rtl *rtl); +void ssh_rtl_destroy(struct ssh_rtl *rtl); + +int ssh_request_init(struct ssh_request *rqst, enum ssam_request_flags flags, + const struct ssh_request_ops *ops); + +#endif /* _SURFACE_AGGREGATOR_SSH_REQUEST_LAYER_H */ diff --git a/include/linux/surface_aggregator/controller.h b/include/linux/surface_aggregator/controller.h new file mode 100644 index 000000000000..f4b1ba887384 --- /dev/null +++ b/include/linux/surface_aggregator/controller.h @@ -0,0 +1,824 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Surface System Aggregator Module (SSAM) controller interface. + * + * Main communication interface for the SSAM EC. Provides a controller + * managing access and communication to and from the SSAM EC, as well as main + * communication structures and definitions. + * + * Copyright (C) 2019-2020 Maximilian Luz + */ + +#ifndef _LINUX_SURFACE_AGGREGATOR_CONTROLLER_H +#define _LINUX_SURFACE_AGGREGATOR_CONTROLLER_H + +#include +#include +#include + +#include + + +/* -- Main data types and definitions --------------------------------------- */ + +/** + * enum ssam_event_flags - Flags for enabling/disabling SAM events + * @SSAM_EVENT_SEQUENCED: The event will be sent via a sequenced data frame. + */ +enum ssam_event_flags { + SSAM_EVENT_SEQUENCED = BIT(0), +}; + +/** + * struct ssam_event - SAM event sent from the EC to the host. + * @target_category: Target category of the event source. See &enum ssam_ssh_tc. + * @target_id: Target ID of the event source. + * @command_id: Command ID of the event. + * @instance_id: Instance ID of the event source. + * @length: Length of the event payload in bytes. + * @data: Event payload data. + */ +struct ssam_event { + u8 target_category; + u8 target_id; + u8 command_id; + u8 instance_id; + u16 length; + u8 data[]; +}; + +/** + * enum ssam_request_flags - Flags for SAM requests. + * + * @SSAM_REQUEST_HAS_RESPONSE: + * Specifies that the request expects a response. If not set, the request + * will be directly completed after its underlying packet has been + * transmitted. If set, the request transport system waits for a response + * of the request. + * + * @SSAM_REQUEST_UNSEQUENCED: + * Specifies that the request should be transmitted via an unsequenced + * packet. If set, the request must not have a response, meaning that this + * flag and the %SSAM_REQUEST_HAS_RESPONSE flag are mutually exclusive. + */ +enum ssam_request_flags { + SSAM_REQUEST_HAS_RESPONSE = BIT(0), + SSAM_REQUEST_UNSEQUENCED = BIT(1), +}; + +/** + * struct ssam_request - SAM request description. + * @target_category: Category of the request's target. See &enum ssam_ssh_tc. + * @target_id: ID of the request's target. + * @command_id: Command ID of the request. + * @instance_id: Instance ID of the request's target. + * @flags: Flags for the request. See &enum ssam_request_flags. + * @length: Length of the request payload in bytes. + * @payload: Request payload data. + * + * This struct fully describes a SAM request with payload. It is intended to + * help set up the actual transport struct, e.g. &struct ssam_request_sync, + * and specifically its raw message data via ssam_request_write_data(). + */ +struct ssam_request { + u8 target_category; + u8 target_id; + u8 command_id; + u8 instance_id; + u16 flags; + u16 length; + const u8 *payload; +}; + +/** + * struct ssam_response - Response buffer for SAM request. + * @capacity: Capacity of the buffer, in bytes. + * @length: Length of the actual data stored in the memory pointed to by + * @pointer, in bytes. Set by the transport system. + * @pointer: Pointer to the buffer's memory, storing the response payload data. + */ +struct ssam_response { + size_t capacity; + size_t length; + u8 *pointer; +}; + +struct ssam_controller; + +struct ssam_controller *ssam_get_controller(void); +struct ssam_controller *ssam_client_bind(struct device *client); +int ssam_client_link(struct ssam_controller *ctrl, struct device *client); + +struct device *ssam_controller_device(struct ssam_controller *c); + +struct ssam_controller *ssam_controller_get(struct ssam_controller *c); +void ssam_controller_put(struct ssam_controller *c); + +void ssam_controller_statelock(struct ssam_controller *c); +void ssam_controller_stateunlock(struct ssam_controller *c); + +ssize_t ssam_request_write_data(struct ssam_span *buf, + struct ssam_controller *ctrl, + const struct ssam_request *spec); + + +/* -- Synchronous request interface. ---------------------------------------- */ + +/** + * struct ssam_request_sync - Synchronous SAM request struct. + * @base: Underlying SSH request. + * @comp: Completion used to signal full completion of the request. After the + * request has been submitted, this struct may only be modified or + * deallocated after the completion has been signaled. + * request has been submitted, + * @resp: Buffer to store the response. + * @status: Status of the request, set after the base request has been + * completed or has failed. + */ +struct ssam_request_sync { + struct ssh_request base; + struct completion comp; + struct ssam_response *resp; + int status; +}; + +int ssam_request_sync_alloc(size_t payload_len, gfp_t flags, + struct ssam_request_sync **rqst, + struct ssam_span *buffer); + +void ssam_request_sync_free(struct ssam_request_sync *rqst); + +int ssam_request_sync_init(struct ssam_request_sync *rqst, + enum ssam_request_flags flags); + +/** + * ssam_request_sync_set_data - Set message data of a synchronous request. + * @rqst: The request. + * @ptr: Pointer to the request message data. + * @len: Length of the request message data. + * + * Set the request message data of a synchronous request. The provided buffer + * needs to live until the request has been completed. + */ +static inline void ssam_request_sync_set_data(struct ssam_request_sync *rqst, + u8 *ptr, size_t len) +{ + ssh_request_set_data(&rqst->base, ptr, len); +} + +/** + * ssam_request_sync_set_resp - Set response buffer of a synchronous request. + * @rqst: The request. + * @resp: The response buffer. + * + * Sets the response buffer of a synchronous request. This buffer will store + * the response of the request after it has been completed. May be %NULL if no + * response is expected. + */ +static inline void ssam_request_sync_set_resp(struct ssam_request_sync *rqst, + struct ssam_response *resp) +{ + rqst->resp = resp; +} + +int ssam_request_sync_submit(struct ssam_controller *ctrl, + struct ssam_request_sync *rqst); + +/** + * ssam_request_sync_wait - Wait for completion of a synchronous request. + * @rqst: The request to wait for. + * + * Wait for completion and release of a synchronous request. After this + * function terminates, the request is guaranteed to have left the transport + * system. After successful submission of a request, this function must be + * called before accessing the response of the request, freeing the request, + * or freeing any of the buffers associated with the request. + * + * This function must not be called if the request has not been submitted yet + * and may lead to a deadlock/infinite wait if a subsequent request submission + * fails in that case, due to the completion never triggering. + * + * Return: Returns the status of the given request, which is set on completion + * of the packet. This value is zero on success and negative on failure. + */ +static inline int ssam_request_sync_wait(struct ssam_request_sync *rqst) +{ + wait_for_completion(&rqst->comp); + return rqst->status; +} + +int ssam_request_sync(struct ssam_controller *ctrl, + const struct ssam_request *spec, + struct ssam_response *rsp); + +int ssam_request_sync_with_buffer(struct ssam_controller *ctrl, + const struct ssam_request *spec, + struct ssam_response *rsp, + struct ssam_span *buf); + +/** + * ssam_request_sync_onstack - Execute a synchronous request on the stack. + * @ctrl: The controller via which the request is submitted. + * @rqst: The request specification. + * @rsp: The response buffer. + * @payload_len: The (maximum) request payload length. + * + * Allocates a synchronous request with specified payload length on the stack, + * fully initializes it via the provided request specification, submits it, + * and finally waits for its completion before returning its status. This + * helper macro essentially allocates the request message buffer on the stack + * and then calls ssam_request_sync_with_buffer(). + * + * Note: The @payload_len parameter specifies the maximum payload length, used + * for buffer allocation. The actual payload length may be smaller. + * + * Return: Returns the status of the request or any failure during setup, i.e. + * zero on success and a negative value on failure. + */ +#define ssam_request_sync_onstack(ctrl, rqst, rsp, payload_len) \ + ({ \ + u8 __data[SSH_COMMAND_MESSAGE_LENGTH(payload_len)]; \ + struct ssam_span __buf = { &__data[0], ARRAY_SIZE(__data) }; \ + \ + ssam_request_sync_with_buffer(ctrl, rqst, rsp, &__buf); \ + }) + +/** + * __ssam_retry - Retry request in case of I/O errors or timeouts. + * @request: The request function to execute. Must return an integer. + * @n: Number of tries. + * @args: Arguments for the request function. + * + * Executes the given request function, i.e. calls @request. In case the + * request returns %-EREMOTEIO (indicates I/O error) or %-ETIMEDOUT (request + * or underlying packet timed out), @request will be re-executed again, up to + * @n times in total. + * + * Return: Returns the return value of the last execution of @request. + */ +#define __ssam_retry(request, n, args...) \ + ({ \ + int __i, __s = 0; \ + \ + for (__i = (n); __i > 0; __i--) { \ + __s = request(args); \ + if (__s != -ETIMEDOUT && __s != -EREMOTEIO) \ + break; \ + } \ + __s; \ + }) + +/** + * ssam_retry - Retry request in case of I/O errors or timeouts up to three + * times in total. + * @request: The request function to execute. Must return an integer. + * @args: Arguments for the request function. + * + * Executes the given request function, i.e. calls @request. In case the + * request returns %-EREMOTEIO (indicates I/O error) or -%ETIMEDOUT (request + * or underlying packet timed out), @request will be re-executed again, up to + * three times in total. + * + * See __ssam_retry() for a more generic macro for this purpose. + * + * Return: Returns the return value of the last execution of @request. + */ +#define ssam_retry(request, args...) \ + __ssam_retry(request, 3, args) + +/** + * struct ssam_request_spec - Blue-print specification of SAM request. + * @target_category: Category of the request's target. See &enum ssam_ssh_tc. + * @target_id: ID of the request's target. + * @command_id: Command ID of the request. + * @instance_id: Instance ID of the request's target. + * @flags: Flags for the request. See &enum ssam_request_flags. + * + * Blue-print specification for a SAM request. This struct describes the + * unique static parameters of a request (i.e. type) without specifying any of + * its instance-specific data (e.g. payload). It is intended to be used as base + * for defining simple request functions via the + * ``SSAM_DEFINE_SYNC_REQUEST_x()`` family of macros. + */ +struct ssam_request_spec { + u8 target_category; + u8 target_id; + u8 command_id; + u8 instance_id; + u8 flags; +}; + +/** + * struct ssam_request_spec_md - Blue-print specification for multi-device SAM + * request. + * @target_category: Category of the request's target. See &enum ssam_ssh_tc. + * @command_id: Command ID of the request. + * @flags: Flags for the request. See &enum ssam_request_flags. + * + * Blue-print specification for a multi-device SAM request, i.e. a request + * that is applicable to multiple device instances, described by their + * individual target and instance IDs. This struct describes the unique static + * parameters of a request (i.e. type) without specifying any of its + * instance-specific data (e.g. payload) and without specifying any of its + * device specific IDs (i.e. target and instance ID). It is intended to be + * used as base for defining simple multi-device request functions via the + * ``SSAM_DEFINE_SYNC_REQUEST_MD_x()`` and ``SSAM_DEFINE_SYNC_REQUEST_CL_x()`` + * families of macros. + */ +struct ssam_request_spec_md { + u8 target_category; + u8 command_id; + u8 flags; +}; + +/** + * SSAM_DEFINE_SYNC_REQUEST_N() - Define synchronous SAM request function + * with neither argument nor return value. + * @name: Name of the generated function. + * @spec: Specification (&struct ssam_request_spec) defining the request. + * + * Defines a function executing the synchronous SAM request specified by + * @spec, with the request having neither argument nor return value. The + * generated function takes care of setting up the request struct and buffer + * allocation, as well as execution of the request itself, returning once the + * request has been fully completed. The required transport buffer will be + * allocated on the stack. + * + * The generated function is defined as ``int name(struct ssam_controller + * *ctrl)``, returning the status of the request, which is zero on success and + * negative on failure. The ``ctrl`` parameter is the controller via which the + * request is being sent. + * + * Refer to ssam_request_sync_onstack() for more details on the behavior of + * the generated function. + */ +#define SSAM_DEFINE_SYNC_REQUEST_N(name, spec...) \ + int name(struct ssam_controller *ctrl) \ + { \ + struct ssam_request_spec s = (struct ssam_request_spec)spec; \ + struct ssam_request rqst; \ + \ + rqst.target_category = s.target_category; \ + rqst.target_id = s.target_id; \ + rqst.command_id = s.command_id; \ + rqst.instance_id = s.instance_id; \ + rqst.flags = s.flags; \ + rqst.length = 0; \ + rqst.payload = NULL; \ + \ + return ssam_request_sync_onstack(ctrl, &rqst, NULL, 0); \ + } + +/** + * SSAM_DEFINE_SYNC_REQUEST_W() - Define synchronous SAM request function with + * argument. + * @name: Name of the generated function. + * @atype: Type of the request's argument. + * @spec: Specification (&struct ssam_request_spec) defining the request. + * + * Defines a function executing the synchronous SAM request specified by + * @spec, with the request taking an argument of type @atype and having no + * return value. The generated function takes care of setting up the request + * struct, buffer allocation, as well as execution of the request itself, + * returning once the request has been fully completed. The required transport + * buffer will be allocated on the stack. + * + * The generated function is defined as ``int name(struct ssam_controller + * *ctrl, const atype *arg)``, returning the status of the request, which is + * zero on success and negative on failure. The ``ctrl`` parameter is the + * controller via which the request is sent. The request argument is specified + * via the ``arg`` pointer. + * + * Refer to ssam_request_sync_onstack() for more details on the behavior of + * the generated function. + */ +#define SSAM_DEFINE_SYNC_REQUEST_W(name, atype, spec...) \ + int name(struct ssam_controller *ctrl, const atype *arg) \ + { \ + struct ssam_request_spec s = (struct ssam_request_spec)spec; \ + struct ssam_request rqst; \ + \ + rqst.target_category = s.target_category; \ + rqst.target_id = s.target_id; \ + rqst.command_id = s.command_id; \ + rqst.instance_id = s.instance_id; \ + rqst.flags = s.flags; \ + rqst.length = sizeof(atype); \ + rqst.payload = (u8 *)arg; \ + \ + return ssam_request_sync_onstack(ctrl, &rqst, NULL, \ + sizeof(atype)); \ + } + +/** + * SSAM_DEFINE_SYNC_REQUEST_R() - Define synchronous SAM request function with + * return value. + * @name: Name of the generated function. + * @rtype: Type of the request's return value. + * @spec: Specification (&struct ssam_request_spec) defining the request. + * + * Defines a function executing the synchronous SAM request specified by + * @spec, with the request taking no argument but having a return value of + * type @rtype. The generated function takes care of setting up the request + * and response structs, buffer allocation, as well as execution of the + * request itself, returning once the request has been fully completed. The + * required transport buffer will be allocated on the stack. + * + * The generated function is defined as ``int name(struct ssam_controller + * *ctrl, rtype *ret)``, returning the status of the request, which is zero on + * success and negative on failure. The ``ctrl`` parameter is the controller + * via which the request is sent. The request's return value is written to the + * memory pointed to by the ``ret`` parameter. + * + * Refer to ssam_request_sync_onstack() for more details on the behavior of + * the generated function. + */ +#define SSAM_DEFINE_SYNC_REQUEST_R(name, rtype, spec...) \ + int name(struct ssam_controller *ctrl, rtype *ret) \ + { \ + struct ssam_request_spec s = (struct ssam_request_spec)spec; \ + struct ssam_request rqst; \ + struct ssam_response rsp; \ + int status; \ + \ + rqst.target_category = s.target_category; \ + rqst.target_id = s.target_id; \ + rqst.command_id = s.command_id; \ + rqst.instance_id = s.instance_id; \ + rqst.flags = s.flags | SSAM_REQUEST_HAS_RESPONSE; \ + rqst.length = 0; \ + rqst.payload = NULL; \ + \ + rsp.capacity = sizeof(rtype); \ + rsp.length = 0; \ + rsp.pointer = (u8 *)ret; \ + \ + status = ssam_request_sync_onstack(ctrl, &rqst, &rsp, 0); \ + if (status) \ + return status; \ + \ + if (rsp.length != sizeof(rtype)) { \ + struct device *dev = ssam_controller_device(ctrl); \ + dev_err(dev, \ + "rqst: invalid response length, expected %zu, got %zu (tc: %#04x, cid: %#04x)", \ + sizeof(rtype), rsp.length, rqst.target_category,\ + rqst.command_id); \ + return -EIO; \ + } \ + \ + return 0; \ + } + +/** + * SSAM_DEFINE_SYNC_REQUEST_MD_N() - Define synchronous multi-device SAM + * request function with neither argument nor return value. + * @name: Name of the generated function. + * @spec: Specification (&struct ssam_request_spec_md) defining the request. + * + * Defines a function executing the synchronous SAM request specified by + * @spec, with the request having neither argument nor return value. Device + * specifying parameters are not hard-coded, but instead must be provided to + * the function. The generated function takes care of setting up the request + * struct, buffer allocation, as well as execution of the request itself, + * returning once the request has been fully completed. The required transport + * buffer will be allocated on the stack. + * + * The generated function is defined as ``int name(struct ssam_controller + * *ctrl, u8 tid, u8 iid)``, returning the status of the request, which is + * zero on success and negative on failure. The ``ctrl`` parameter is the + * controller via which the request is sent, ``tid`` the target ID for the + * request, and ``iid`` the instance ID. + * + * Refer to ssam_request_sync_onstack() for more details on the behavior of + * the generated function. + */ +#define SSAM_DEFINE_SYNC_REQUEST_MD_N(name, spec...) \ + int name(struct ssam_controller *ctrl, u8 tid, u8 iid) \ + { \ + struct ssam_request_spec_md s = (struct ssam_request_spec_md)spec; \ + struct ssam_request rqst; \ + \ + rqst.target_category = s.target_category; \ + rqst.target_id = tid; \ + rqst.command_id = s.command_id; \ + rqst.instance_id = iid; \ + rqst.flags = s.flags; \ + rqst.length = 0; \ + rqst.payload = NULL; \ + \ + return ssam_request_sync_onstack(ctrl, &rqst, NULL, 0); \ + } + +/** + * SSAM_DEFINE_SYNC_REQUEST_MD_W() - Define synchronous multi-device SAM + * request function with argument. + * @name: Name of the generated function. + * @atype: Type of the request's argument. + * @spec: Specification (&struct ssam_request_spec_md) defining the request. + * + * Defines a function executing the synchronous SAM request specified by + * @spec, with the request taking an argument of type @atype and having no + * return value. Device specifying parameters are not hard-coded, but instead + * must be provided to the function. The generated function takes care of + * setting up the request struct, buffer allocation, as well as execution of + * the request itself, returning once the request has been fully completed. + * The required transport buffer will be allocated on the stack. + * + * The generated function is defined as ``int name(struct ssam_controller + * *ctrl, u8 tid, u8 iid, const atype *arg)``, returning the status of the + * request, which is zero on success and negative on failure. The ``ctrl`` + * parameter is the controller via which the request is sent, ``tid`` the + * target ID for the request, and ``iid`` the instance ID. The request argument + * is specified via the ``arg`` pointer. + * + * Refer to ssam_request_sync_onstack() for more details on the behavior of + * the generated function. + */ +#define SSAM_DEFINE_SYNC_REQUEST_MD_W(name, atype, spec...) \ + int name(struct ssam_controller *ctrl, u8 tid, u8 iid, const atype *arg)\ + { \ + struct ssam_request_spec_md s = (struct ssam_request_spec_md)spec; \ + struct ssam_request rqst; \ + \ + rqst.target_category = s.target_category; \ + rqst.target_id = tid; \ + rqst.command_id = s.command_id; \ + rqst.instance_id = iid; \ + rqst.flags = s.flags; \ + rqst.length = sizeof(atype); \ + rqst.payload = (u8 *)arg; \ + \ + return ssam_request_sync_onstack(ctrl, &rqst, NULL, \ + sizeof(atype)); \ + } + +/** + * SSAM_DEFINE_SYNC_REQUEST_MD_R() - Define synchronous multi-device SAM + * request function with return value. + * @name: Name of the generated function. + * @rtype: Type of the request's return value. + * @spec: Specification (&struct ssam_request_spec_md) defining the request. + * + * Defines a function executing the synchronous SAM request specified by + * @spec, with the request taking no argument but having a return value of + * type @rtype. Device specifying parameters are not hard-coded, but instead + * must be provided to the function. The generated function takes care of + * setting up the request and response structs, buffer allocation, as well as + * execution of the request itself, returning once the request has been fully + * completed. The required transport buffer will be allocated on the stack. + * + * The generated function is defined as ``int name(struct ssam_controller + * *ctrl, u8 tid, u8 iid, rtype *ret)``, returning the status of the request, + * which is zero on success and negative on failure. The ``ctrl`` parameter is + * the controller via which the request is sent, ``tid`` the target ID for the + * request, and ``iid`` the instance ID. The request's return value is written + * to the memory pointed to by the ``ret`` parameter. + * + * Refer to ssam_request_sync_onstack() for more details on the behavior of + * the generated function. + */ +#define SSAM_DEFINE_SYNC_REQUEST_MD_R(name, rtype, spec...) \ + int name(struct ssam_controller *ctrl, u8 tid, u8 iid, rtype *ret) \ + { \ + struct ssam_request_spec_md s = (struct ssam_request_spec_md)spec; \ + struct ssam_request rqst; \ + struct ssam_response rsp; \ + int status; \ + \ + rqst.target_category = s.target_category; \ + rqst.target_id = tid; \ + rqst.command_id = s.command_id; \ + rqst.instance_id = iid; \ + rqst.flags = s.flags | SSAM_REQUEST_HAS_RESPONSE; \ + rqst.length = 0; \ + rqst.payload = NULL; \ + \ + rsp.capacity = sizeof(rtype); \ + rsp.length = 0; \ + rsp.pointer = (u8 *)ret; \ + \ + status = ssam_request_sync_onstack(ctrl, &rqst, &rsp, 0); \ + if (status) \ + return status; \ + \ + if (rsp.length != sizeof(rtype)) { \ + struct device *dev = ssam_controller_device(ctrl); \ + dev_err(dev, \ + "rqst: invalid response length, expected %zu, got %zu (tc: %#04x, cid: %#04x)", \ + sizeof(rtype), rsp.length, rqst.target_category,\ + rqst.command_id); \ + return -EIO; \ + } \ + \ + return 0; \ + } + + +/* -- Event notifier/callbacks. --------------------------------------------- */ + +#define SSAM_NOTIF_STATE_SHIFT 2 +#define SSAM_NOTIF_STATE_MASK ((1 << SSAM_NOTIF_STATE_SHIFT) - 1) + +/** + * enum ssam_notif_flags - Flags used in return values from SSAM notifier + * callback functions. + * + * @SSAM_NOTIF_HANDLED: + * Indicates that the notification has been handled. This flag should be + * set by the handler if the handler can act/has acted upon the event + * provided to it. This flag should not be set if the handler is not a + * primary handler intended for the provided event. + * + * If this flag has not been set by any handler after the notifier chain + * has been traversed, a warning will be emitted, stating that the event + * has not been handled. + * + * @SSAM_NOTIF_STOP: + * Indicates that the notifier traversal should stop. If this flag is + * returned from a notifier callback, notifier chain traversal will + * immediately stop and any remaining notifiers will not be called. This + * flag is automatically set when ssam_notifier_from_errno() is called + * with a negative error value. + */ +enum ssam_notif_flags { + SSAM_NOTIF_HANDLED = BIT(0), + SSAM_NOTIF_STOP = BIT(1), +}; + +struct ssam_event_notifier; + +typedef u32 (*ssam_notifier_fn_t)(struct ssam_event_notifier *nf, + const struct ssam_event *event); + +/** + * struct ssam_notifier_block - Base notifier block for SSAM event + * notifications. + * @node: The node for the list of notifiers. + * @fn: The callback function of this notifier. This function takes the + * respective notifier block and event as input and should return + * a notifier value, which can either be obtained from the flags + * provided in &enum ssam_notif_flags, converted from a standard + * error value via ssam_notifier_from_errno(), or a combination of + * both (e.g. ``ssam_notifier_from_errno(e) | SSAM_NOTIF_HANDLED``). + * @priority: Priority value determining the order in which notifier callbacks + * will be called. A higher value means higher priority, i.e. the + * associated callback will be executed earlier than other (lower + * priority) callbacks. + */ +struct ssam_notifier_block { + struct list_head node; + ssam_notifier_fn_t fn; + int priority; +}; + +/** + * ssam_notifier_from_errno() - Convert standard error value to notifier + * return code. + * @err: The error code to convert, must be negative (in case of failure) or + * zero (in case of success). + * + * Return: Returns the notifier return value obtained by converting the + * specified @err value. In case @err is negative, the %SSAM_NOTIF_STOP flag + * will be set, causing notifier call chain traversal to abort. + */ +static inline u32 ssam_notifier_from_errno(int err) +{ + if (WARN_ON(err > 0) || err == 0) + return 0; + else + return ((-err) << SSAM_NOTIF_STATE_SHIFT) | SSAM_NOTIF_STOP; +} + +/** + * ssam_notifier_to_errno() - Convert notifier return code to standard error + * value. + * @ret: The notifier return value to convert. + * + * Return: Returns the negative error value encoded in @ret or zero if @ret + * indicates success. + */ +static inline int ssam_notifier_to_errno(u32 ret) +{ + return -(ret >> SSAM_NOTIF_STATE_SHIFT); +} + + +/* -- Event/notification registry. ------------------------------------------ */ + +/** + * struct ssam_event_registry - Registry specification used for enabling events. + * @target_category: Target category for the event registry requests. + * @target_id: Target ID for the event registry requests. + * @cid_enable: Command ID for the event-enable request. + * @cid_disable: Command ID for the event-disable request. + * + * This struct describes a SAM event registry via the minimal collection of + * SAM IDs specifying the requests to use for enabling and disabling an event. + * The individual event to be enabled/disabled itself is specified via &struct + * ssam_event_id. + */ +struct ssam_event_registry { + u8 target_category; + u8 target_id; + u8 cid_enable; + u8 cid_disable; +}; + +/** + * struct ssam_event_id - Unique event ID used for enabling events. + * @target_category: Target category of the event source. + * @instance: Instance ID of the event source. + * + * This struct specifies the event to be enabled/disabled via an externally + * provided registry. It does not specify the registry to be used itself, this + * is done via &struct ssam_event_registry. + */ +struct ssam_event_id { + u8 target_category; + u8 instance; +}; + +/** + * enum ssam_event_mask - Flags specifying how events are matched to notifiers. + * + * @SSAM_EVENT_MASK_NONE: + * Run the callback for any event with matching target category. Do not + * do any additional filtering. + * + * @SSAM_EVENT_MASK_TARGET: + * In addition to filtering by target category, only execute the notifier + * callback for events with a target ID matching to the one of the + * registry used for enabling/disabling the event. + * + * @SSAM_EVENT_MASK_INSTANCE: + * In addition to filtering by target category, only execute the notifier + * callback for events with an instance ID matching to the instance ID + * used when enabling the event. + * + * @SSAM_EVENT_MASK_STRICT: + * Do all the filtering above. + */ +enum ssam_event_mask { + SSAM_EVENT_MASK_TARGET = BIT(0), + SSAM_EVENT_MASK_INSTANCE = BIT(1), + + SSAM_EVENT_MASK_NONE = 0, + SSAM_EVENT_MASK_STRICT = + SSAM_EVENT_MASK_TARGET + | SSAM_EVENT_MASK_INSTANCE, +}; + +/** + * SSAM_EVENT_REGISTRY() - Define a new event registry. + * @tc: Target category for the event registry requests. + * @tid: Target ID for the event registry requests. + * @cid_en: Command ID for the event-enable request. + * @cid_dis: Command ID for the event-disable request. + * + * Return: Returns the &struct ssam_event_registry specified by the given + * parameters. + */ +#define SSAM_EVENT_REGISTRY(tc, tid, cid_en, cid_dis) \ + ((struct ssam_event_registry) { \ + .target_category = (tc), \ + .target_id = (tid), \ + .cid_enable = (cid_en), \ + .cid_disable = (cid_dis), \ + }) + +#define SSAM_EVENT_REGISTRY_SAM \ + SSAM_EVENT_REGISTRY(SSAM_SSH_TC_SAM, 0x01, 0x0b, 0x0c) + +#define SSAM_EVENT_REGISTRY_KIP \ + SSAM_EVENT_REGISTRY(SSAM_SSH_TC_KIP, 0x02, 0x27, 0x28) + +#define SSAM_EVENT_REGISTRY_REG \ + SSAM_EVENT_REGISTRY(SSAM_SSH_TC_REG, 0x02, 0x01, 0x02) + +/** + * struct ssam_event_notifier - Notifier block for SSAM events. + * @base: The base notifier block with callback function and priority. + * @event: The event for which this block will receive notifications. + * @event.reg: Registry via which the event will be enabled/disabled. + * @event.id: ID specifying the event. + * @event.mask: Flags determining how events are matched to the notifier. + * @event.flags: Flags used for enabling the event. + */ +struct ssam_event_notifier { + struct ssam_notifier_block base; + + struct { + struct ssam_event_registry reg; + struct ssam_event_id id; + enum ssam_event_mask mask; + u8 flags; + } event; +}; + +int ssam_notifier_register(struct ssam_controller *ctrl, + struct ssam_event_notifier *n); + +int ssam_notifier_unregister(struct ssam_controller *ctrl, + struct ssam_event_notifier *n); + +#endif /* _LINUX_SURFACE_AGGREGATOR_CONTROLLER_H */ diff --git a/include/linux/surface_aggregator/serial_hub.h b/include/linux/surface_aggregator/serial_hub.h new file mode 100644 index 000000000000..64276fbfa1d5 --- /dev/null +++ b/include/linux/surface_aggregator/serial_hub.h @@ -0,0 +1,672 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Surface Serial Hub (SSH) protocol and communication interface. + * + * Lower-level communication layers and SSH protocol definitions for the + * Surface System Aggregator Module (SSAM). Provides the interface for basic + * packet- and request-based communication with the SSAM EC via SSH. + * + * Copyright (C) 2019-2020 Maximilian Luz + */ + +#ifndef _LINUX_SURFACE_AGGREGATOR_SERIAL_HUB_H +#define _LINUX_SURFACE_AGGREGATOR_SERIAL_HUB_H + +#include +#include +#include +#include +#include + + +/* -- Data structures for SAM-over-SSH communication. ----------------------- */ + +/** + * enum ssh_frame_type - Frame types for SSH frames. + * + * @SSH_FRAME_TYPE_DATA_SEQ: + * Indicates a data frame, followed by a payload with the length specified + * in the ``struct ssh_frame.len`` field. This frame is sequenced, meaning + * that an ACK is required. + * + * @SSH_FRAME_TYPE_DATA_NSQ: + * Same as %SSH_FRAME_TYPE_DATA_SEQ, but unsequenced, meaning that the + * message does not have to be ACKed. + * + * @SSH_FRAME_TYPE_ACK: + * Indicates an ACK message. + * + * @SSH_FRAME_TYPE_NAK: + * Indicates an error response for previously sent frame. In general, this + * means that the frame and/or payload is malformed, e.g. a CRC is wrong. + * For command-type payloads, this can also mean that the command is + * invalid. + */ +enum ssh_frame_type { + SSH_FRAME_TYPE_DATA_SEQ = 0x80, + SSH_FRAME_TYPE_DATA_NSQ = 0x00, + SSH_FRAME_TYPE_ACK = 0x40, + SSH_FRAME_TYPE_NAK = 0x04, +}; + +/** + * struct ssh_frame - SSH communication frame. + * @type: The type of the frame. See &enum ssh_frame_type. + * @len: The length of the frame payload directly following the CRC for this + * frame. Does not include the final CRC for that payload. + * @seq: The sequence number for this message/exchange. + */ +struct ssh_frame { + u8 type; + __le16 len; + u8 seq; +} __packed; + +static_assert(sizeof(struct ssh_frame) == 4); + +/* + * SSH_FRAME_MAX_PAYLOAD_SIZE - Maximum SSH frame payload length in bytes. + * + * This is the physical maximum length of the protocol. Implementations may + * set a more constrained limit. + */ +#define SSH_FRAME_MAX_PAYLOAD_SIZE U16_MAX + +/** + * enum ssh_payload_type - Type indicator for the SSH payload. + * @SSH_PLD_TYPE_CMD: The payload is a command structure with optional command + * payload. + */ +enum ssh_payload_type { + SSH_PLD_TYPE_CMD = 0x80, +}; + +/** + * struct ssh_command - Payload of a command-type frame. + * @type: The type of the payload. See &enum ssh_payload_type. Should be + * SSH_PLD_TYPE_CMD for this struct. + * @tc: Command target category. + * @tid_out: Output target ID. Should be zero if this an incoming (EC to host) + * message. + * @tid_in: Input target ID. Should be zero if this is an outgoing (host to + * EC) message. + * @iid: Instance ID. + * @rqid: Request ID. Used to match requests with responses and differentiate + * between responses and events. + * @cid: Command ID. + */ +struct ssh_command { + u8 type; + u8 tc; + u8 tid_out; + u8 tid_in; + u8 iid; + __le16 rqid; + u8 cid; +} __packed; + +static_assert(sizeof(struct ssh_command) == 8); + +/* + * SSH_COMMAND_MAX_PAYLOAD_SIZE - Maximum SSH command payload length in bytes. + * + * This is the physical maximum length of the protocol. Implementations may + * set a more constrained limit. + */ +#define SSH_COMMAND_MAX_PAYLOAD_SIZE \ + (SSH_FRAME_MAX_PAYLOAD_SIZE - sizeof(struct ssh_command)) + +/* + * SSH_MSG_LEN_BASE - Base-length of a SSH message. + * + * This is the minimum number of bytes required to form a message. The actual + * message length is SSH_MSG_LEN_BASE plus the length of the frame payload. + */ +#define SSH_MSG_LEN_BASE (sizeof(struct ssh_frame) + 3ull * sizeof(u16)) + +/* + * SSH_MSG_LEN_CTRL - Length of a SSH control message. + * + * This is the length of a SSH control message, which is equal to a SSH + * message without any payload. + */ +#define SSH_MSG_LEN_CTRL SSH_MSG_LEN_BASE + +/** + * SSH_MESSAGE_LENGTH() - Compute length of SSH message. + * @payload_size: Length of the payload inside the SSH frame. + * + * Return: Returns the length of a SSH message with payload of specified size. + */ +#define SSH_MESSAGE_LENGTH(payload_size) (SSH_MSG_LEN_BASE + (payload_size)) + +/** + * SSH_COMMAND_MESSAGE_LENGTH() - Compute length of SSH command message. + * @payload_size: Length of the command payload. + * + * Return: Returns the length of a SSH command message with command payload of + * specified size. + */ +#define SSH_COMMAND_MESSAGE_LENGTH(payload_size) \ + SSH_MESSAGE_LENGTH(sizeof(struct ssh_command) + (payload_size)) + +/** + * SSH_MSGOFFSET_FRAME() - Compute offset in SSH message to specified field in + * frame. + * @field: The field for which the offset should be computed. + * + * Return: Returns the offset of the specified &struct ssh_frame field in the + * raw SSH message data as. Takes SYN bytes (u16) preceding the frame into + * account. + */ +#define SSH_MSGOFFSET_FRAME(field) \ + (sizeof(u16) + offsetof(struct ssh_frame, field)) + +/** + * SSH_MSGOFFSET_COMMAND() - Compute offset in SSH message to specified field + * in command. + * @field: The field for which the offset should be computed. + * + * Return: Returns the offset of the specified &struct ssh_command field in + * the raw SSH message data. Takes SYN bytes (u16) preceding the frame and the + * frame CRC (u16) between frame and command into account. + */ +#define SSH_MSGOFFSET_COMMAND(field) \ + (2ull * sizeof(u16) + sizeof(struct ssh_frame) \ + + offsetof(struct ssh_command, field)) + +/* + * SSH_MSG_SYN - SSH message synchronization (SYN) bytes as u16. + */ +#define SSH_MSG_SYN ((u16)0x55aa) + +/** + * ssh_crc() - Compute CRC for SSH messages. + * @buf: The pointer pointing to the data for which the CRC should be computed. + * @len: The length of the data for which the CRC should be computed. + * + * Return: Returns the CRC computed on the provided data, as used for SSH + * messages. + */ +static inline u16 ssh_crc(const u8 *buf, size_t len) +{ + return crc_ccitt_false(0xffff, buf, len); +} + +/* + * SSH_NUM_EVENTS - The number of reserved event IDs. + * + * The number of reserved event IDs, used for registering an SSH event + * handler. Valid event IDs are numbers below or equal to this value, with + * exception of zero, which is not an event ID. Thus, this is also the + * absolute maximum number of event handlers that can be registered. + */ +#define SSH_NUM_EVENTS 34 + +/* + * SSH_NUM_TARGETS - The number of communication targets used in the protocol. + */ +#define SSH_NUM_TARGETS 2 + +/** + * ssh_rqid_next_valid() - Return the next valid request ID. + * @rqid: The current request ID. + * + * Return: Returns the next valid request ID, following the current request ID + * provided to this function. This function skips any request IDs reserved for + * events. + */ +static inline u16 ssh_rqid_next_valid(u16 rqid) +{ + return rqid > 0 ? rqid + 1u : rqid + SSH_NUM_EVENTS + 1u; +} + +/** + * ssh_rqid_to_event() - Convert request ID to its corresponding event ID. + * @rqid: The request ID to convert. + */ +static inline u16 ssh_rqid_to_event(u16 rqid) +{ + return rqid - 1u; +} + +/** + * ssh_rqid_is_event() - Check if given request ID is a valid event ID. + * @rqid: The request ID to check. + */ +static inline bool ssh_rqid_is_event(u16 rqid) +{ + return ssh_rqid_to_event(rqid) < SSH_NUM_EVENTS; +} + +/** + * ssh_tc_to_rqid() - Convert target category to its corresponding request ID. + * @tc: The target category to convert. + */ +static inline u16 ssh_tc_to_rqid(u8 tc) +{ + return tc; +} + +/** + * ssh_tid_to_index() - Convert target ID to its corresponding target index. + * @tid: The target ID to convert. + */ +static inline u8 ssh_tid_to_index(u8 tid) +{ + return tid - 1u; +} + +/** + * ssh_tid_is_valid() - Check if target ID is valid/supported. + * @tid: The target ID to check. + */ +static inline bool ssh_tid_is_valid(u8 tid) +{ + return ssh_tid_to_index(tid) < SSH_NUM_TARGETS; +} + +/** + * struct ssam_span - Reference to a buffer region. + * @ptr: Pointer to the buffer region. + * @len: Length of the buffer region. + * + * A reference to a (non-owned) buffer segment, consisting of pointer and + * length. Use of this struct indicates non-owned data, i.e. data of which the + * life-time is managed (i.e. it is allocated/freed) via another pointer. + */ +struct ssam_span { + u8 *ptr; + size_t len; +}; + +/* + * Known SSH/EC target categories. + * + * List of currently known target category values; "Known" as in we know they + * exist and are valid on at least some device/model. Detailed functionality + * or the full category name is only known for some of these categories and + * is detailed in the respective comment below. + * + * These values and abbreviations have been extracted from strings inside the + * Windows driver. + */ +enum ssam_ssh_tc { + /* Category 0x00 is invalid for EC use. */ + SSAM_SSH_TC_SAM = 0x01, /* Generic system functionality, real-time clock. */ + SSAM_SSH_TC_BAT = 0x02, /* Battery/power subsystem. */ + SSAM_SSH_TC_TMP = 0x03, /* Thermal subsystem. */ + SSAM_SSH_TC_PMC = 0x04, + SSAM_SSH_TC_FAN = 0x05, + SSAM_SSH_TC_PoM = 0x06, + SSAM_SSH_TC_DBG = 0x07, + SSAM_SSH_TC_KBD = 0x08, /* Legacy keyboard (Laptop 1/2). */ + SSAM_SSH_TC_FWU = 0x09, + SSAM_SSH_TC_UNI = 0x0a, + SSAM_SSH_TC_LPC = 0x0b, + SSAM_SSH_TC_TCL = 0x0c, + SSAM_SSH_TC_SFL = 0x0d, + SSAM_SSH_TC_KIP = 0x0e, + SSAM_SSH_TC_EXT = 0x0f, + SSAM_SSH_TC_BLD = 0x10, + SSAM_SSH_TC_BAS = 0x11, /* Detachment system (Surface Book 2/3). */ + SSAM_SSH_TC_SEN = 0x12, + SSAM_SSH_TC_SRQ = 0x13, + SSAM_SSH_TC_MCU = 0x14, + SSAM_SSH_TC_HID = 0x15, /* Generic HID input subsystem. */ + SSAM_SSH_TC_TCH = 0x16, + SSAM_SSH_TC_BKL = 0x17, + SSAM_SSH_TC_TAM = 0x18, + SSAM_SSH_TC_ACC = 0x19, + SSAM_SSH_TC_UFI = 0x1a, + SSAM_SSH_TC_USC = 0x1b, + SSAM_SSH_TC_PEN = 0x1c, + SSAM_SSH_TC_VID = 0x1d, + SSAM_SSH_TC_AUD = 0x1e, + SSAM_SSH_TC_SMC = 0x1f, + SSAM_SSH_TC_KPD = 0x20, + SSAM_SSH_TC_REG = 0x21, /* Extended event registry. */ +}; + + +/* -- Packet transport layer (ptl). ----------------------------------------- */ + +/** + * enum ssh_packet_base_priority - Base priorities for &struct ssh_packet. + * @SSH_PACKET_PRIORITY_FLUSH: Base priority for flush packets. + * @SSH_PACKET_PRIORITY_DATA: Base priority for normal data packets. + * @SSH_PACKET_PRIORITY_NAK: Base priority for NAK packets. + * @SSH_PACKET_PRIORITY_ACK: Base priority for ACK packets. + */ +enum ssh_packet_base_priority { + SSH_PACKET_PRIORITY_FLUSH = 0, /* same as DATA to sequence flush */ + SSH_PACKET_PRIORITY_DATA = 0, + SSH_PACKET_PRIORITY_NAK = 1, + SSH_PACKET_PRIORITY_ACK = 2, +}; + +/* + * Same as SSH_PACKET_PRIORITY() below, only with actual values. + */ +#define __SSH_PACKET_PRIORITY(base, try) \ + (((base) << 4) | ((try) & 0x0f)) + +/** + * SSH_PACKET_PRIORITY() - Compute packet priority from base priority and + * number of tries. + * @base: The base priority as suffix of &enum ssh_packet_base_priority, e.g. + * ``FLUSH``, ``DATA``, ``ACK``, or ``NAK``. + * @try: The number of tries (must be less than 16). + * + * Compute the combined packet priority. The combined priority is dominated by + * the base priority, whereas the number of (re-)tries decides the precedence + * of packets with the same base priority, giving higher priority to packets + * that already have more tries. + * + * Return: Returns the computed priority as value fitting inside a &u8. A + * higher number means a higher priority. + */ +#define SSH_PACKET_PRIORITY(base, try) \ + __SSH_PACKET_PRIORITY(SSH_PACKET_PRIORITY_##base, (try)) + +/** + * ssh_packet_priority_get_try() - Get number of tries from packet priority. + * @priority: The packet priority. + * + * Return: Returns the number of tries encoded in the specified packet + * priority. + */ +static inline u8 ssh_packet_priority_get_try(u8 priority) +{ + return priority & 0x0f; +} + +/** + * ssh_packet_priority_get_base - Get base priority from packet priority. + * @priority: The packet priority. + * + * Return: Returns the base priority encoded in the given packet priority. + */ +static inline u8 ssh_packet_priority_get_base(u8 priority) +{ + return (priority & 0xf0) >> 4; +} + +enum ssh_packet_flags { + /* state flags */ + SSH_PACKET_SF_LOCKED_BIT, + SSH_PACKET_SF_QUEUED_BIT, + SSH_PACKET_SF_PENDING_BIT, + SSH_PACKET_SF_TRANSMITTING_BIT, + SSH_PACKET_SF_TRANSMITTED_BIT, + SSH_PACKET_SF_ACKED_BIT, + SSH_PACKET_SF_CANCELED_BIT, + SSH_PACKET_SF_COMPLETED_BIT, + + /* type flags */ + SSH_PACKET_TY_FLUSH_BIT, + SSH_PACKET_TY_SEQUENCED_BIT, + SSH_PACKET_TY_BLOCKING_BIT, + + /* mask for state flags */ + SSH_PACKET_FLAGS_SF_MASK = + BIT(SSH_PACKET_SF_LOCKED_BIT) + | BIT(SSH_PACKET_SF_QUEUED_BIT) + | BIT(SSH_PACKET_SF_PENDING_BIT) + | BIT(SSH_PACKET_SF_TRANSMITTING_BIT) + | BIT(SSH_PACKET_SF_TRANSMITTED_BIT) + | BIT(SSH_PACKET_SF_ACKED_BIT) + | BIT(SSH_PACKET_SF_CANCELED_BIT) + | BIT(SSH_PACKET_SF_COMPLETED_BIT), + + /* mask for type flags */ + SSH_PACKET_FLAGS_TY_MASK = + BIT(SSH_PACKET_TY_FLUSH_BIT) + | BIT(SSH_PACKET_TY_SEQUENCED_BIT) + | BIT(SSH_PACKET_TY_BLOCKING_BIT), +}; + +struct ssh_ptl; +struct ssh_packet; + +/** + * struct ssh_packet_ops - Callback operations for a SSH packet. + * @release: Function called when the packet reference count reaches zero. + * This callback must be relied upon to ensure that the packet has + * left the transport system(s). + * @complete: Function called when the packet is completed, either with + * success or failure. In case of failure, the reason for the + * failure is indicated by the value of the provided status code + * argument. This value will be zero in case of success. Note that + * a call to this callback does not guarantee that the packet is + * not in use by the transport system any more. + */ +struct ssh_packet_ops { + void (*release)(struct ssh_packet *p); + void (*complete)(struct ssh_packet *p, int status); +}; + +/** + * struct ssh_packet - SSH transport packet. + * @ptl: Pointer to the packet transport layer. May be %NULL if the packet + * (or enclosing request) has not been submitted yet. + * @refcnt: Reference count of the packet. + * @priority: Priority of the packet. Must be computed via + * SSH_PACKET_PRIORITY(). Must only be accessed while holding the + * queue lock after first submission. + * @data: Raw message data. + * @data.len: Length of the raw message data. + * @data.ptr: Pointer to the raw message data buffer. + * @state: State and type flags describing current packet state (dynamic) + * and type (static). See &enum ssh_packet_flags for possible + * options. + * @timestamp: Timestamp specifying when the latest transmission of a + * currently pending packet has been started. May be %KTIME_MAX + * before or in-between transmission attempts. Used for the packet + * timeout implementation. Must only be accessed while holding the + * pending lock after first submission. + * @queue_node: The list node for the packet queue. + * @pending_node: The list node for the set of pending packets. + * @ops: Packet operations. + */ +struct ssh_packet { + struct ssh_ptl *ptl; + struct kref refcnt; + + u8 priority; + + struct { + size_t len; + u8 *ptr; + } data; + + unsigned long state; + ktime_t timestamp; + + struct list_head queue_node; + struct list_head pending_node; + + const struct ssh_packet_ops *ops; +}; + +struct ssh_packet *ssh_packet_get(struct ssh_packet *p); +void ssh_packet_put(struct ssh_packet *p); + +/** + * ssh_packet_set_data() - Set raw message data of packet. + * @p: The packet for which the message data should be set. + * @ptr: Pointer to the memory holding the message data. + * @len: Length of the message data. + * + * Sets the raw message data buffer of the packet to the provided memory. The + * memory is not copied. Instead, the caller is responsible for management + * (i.e. allocation and deallocation) of the memory. The caller must ensure + * that the provided memory is valid and contains a valid SSH message, + * starting from the time of submission of the packet until the ``release`` + * callback has been called. During this time, the memory may not be altered + * in any way. + */ +static inline void ssh_packet_set_data(struct ssh_packet *p, u8 *ptr, size_t len) +{ + p->data.ptr = ptr; + p->data.len = len; +} + + +/* -- Request transport layer (rtl). ---------------------------------------- */ + +enum ssh_request_flags { + /* state flags */ + SSH_REQUEST_SF_LOCKED_BIT, + SSH_REQUEST_SF_QUEUED_BIT, + SSH_REQUEST_SF_PENDING_BIT, + SSH_REQUEST_SF_TRANSMITTING_BIT, + SSH_REQUEST_SF_TRANSMITTED_BIT, + SSH_REQUEST_SF_RSPRCVD_BIT, + SSH_REQUEST_SF_CANCELED_BIT, + SSH_REQUEST_SF_COMPLETED_BIT, + + /* type flags */ + SSH_REQUEST_TY_FLUSH_BIT, + SSH_REQUEST_TY_HAS_RESPONSE_BIT, + + /* mask for state flags */ + SSH_REQUEST_FLAGS_SF_MASK = + BIT(SSH_REQUEST_SF_LOCKED_BIT) + | BIT(SSH_REQUEST_SF_QUEUED_BIT) + | BIT(SSH_REQUEST_SF_PENDING_BIT) + | BIT(SSH_REQUEST_SF_TRANSMITTING_BIT) + | BIT(SSH_REQUEST_SF_TRANSMITTED_BIT) + | BIT(SSH_REQUEST_SF_RSPRCVD_BIT) + | BIT(SSH_REQUEST_SF_CANCELED_BIT) + | BIT(SSH_REQUEST_SF_COMPLETED_BIT), + + /* mask for type flags */ + SSH_REQUEST_FLAGS_TY_MASK = + BIT(SSH_REQUEST_TY_FLUSH_BIT) + | BIT(SSH_REQUEST_TY_HAS_RESPONSE_BIT), +}; + +struct ssh_rtl; +struct ssh_request; + +/** + * struct ssh_request_ops - Callback operations for a SSH request. + * @release: Function called when the request's reference count reaches zero. + * This callback must be relied upon to ensure that the request has + * left the transport systems (both, packet an request systems). + * @complete: Function called when the request is completed, either with + * success or failure. The command data for the request response + * is provided via the &struct ssh_command parameter (``cmd``), + * the command payload of the request response via the &struct + * ssh_span parameter (``data``). + * + * If the request does not have any response or has not been + * completed with success, both ``cmd`` and ``data`` parameters will + * be NULL. If the request response does not have any command + * payload, the ``data`` span will be an empty (zero-length) span. + * + * In case of failure, the reason for the failure is indicated by + * the value of the provided status code argument (``status``). This + * value will be zero in case of success and a regular errno + * otherwise. + * + * Note that a call to this callback does not guarantee that the + * request is not in use by the transport systems any more. + */ +struct ssh_request_ops { + void (*release)(struct ssh_request *rqst); + void (*complete)(struct ssh_request *rqst, + const struct ssh_command *cmd, + const struct ssam_span *data, int status); +}; + +/** + * struct ssh_request - SSH transport request. + * @packet: The underlying SSH transport packet. + * @node: List node for the request queue and pending set. + * @state: State and type flags describing current request state (dynamic) + * and type (static). See &enum ssh_request_flags for possible + * options. + * @timestamp: Timestamp specifying when we start waiting on the response of + * the request. This is set once the underlying packet has been + * completed and may be %KTIME_MAX before that, or when the request + * does not expect a response. Used for the request timeout + * implementation. + * @ops: Request Operations. + */ +struct ssh_request { + struct ssh_packet packet; + struct list_head node; + + unsigned long state; + ktime_t timestamp; + + const struct ssh_request_ops *ops; +}; + +/** + * to_ssh_request() - Cast a SSH packet to its enclosing SSH request. + * @p: The packet to cast. + * + * Casts the given &struct ssh_packet to its enclosing &struct ssh_request. + * The caller is responsible for making sure that the packet is actually + * wrapped in a &struct ssh_request. + * + * Return: Returns the &struct ssh_request wrapping the provided packet. + */ +static inline struct ssh_request *to_ssh_request(struct ssh_packet *p) +{ + return container_of(p, struct ssh_request, packet); +} + +/** + * ssh_request_get() - Increment reference count of request. + * @r: The request to increment the reference count of. + * + * Increments the reference count of the given request by incrementing the + * reference count of the underlying &struct ssh_packet, enclosed in it. + * + * See also ssh_request_put(), ssh_packet_get(). + * + * Return: Returns the request provided as input. + */ +static inline struct ssh_request *ssh_request_get(struct ssh_request *r) +{ + return r ? to_ssh_request(ssh_packet_get(&r->packet)) : NULL; +} + +/** + * ssh_request_put() - Decrement reference count of request. + * @r: The request to decrement the reference count of. + * + * Decrements the reference count of the given request by decrementing the + * reference count of the underlying &struct ssh_packet, enclosed in it. If + * the reference count reaches zero, the ``release`` callback specified in the + * request's &struct ssh_request_ops, i.e. ``r->ops->release``, will be + * called. + * + * See also ssh_request_get(), ssh_packet_put(). + */ +static inline void ssh_request_put(struct ssh_request *r) +{ + if (r) + ssh_packet_put(&r->packet); +} + +/** + * ssh_request_set_data() - Set raw message data of request. + * @r: The request for which the message data should be set. + * @ptr: Pointer to the memory holding the message data. + * @len: Length of the message data. + * + * Sets the raw message data buffer of the underlying packet to the specified + * buffer. Does not copy the actual message data, just sets the buffer pointer + * and length. Refer to ssh_packet_set_data() for more details. + */ +static inline void ssh_request_set_data(struct ssh_request *r, u8 *ptr, size_t len) +{ + ssh_packet_set_data(&r->packet, ptr, len); +} + +#endif /* _LINUX_SURFACE_AGGREGATOR_SERIAL_HUB_H */ -- cgit v1.2.3 From eb0e90a82098d4a48308abb87d2087578a83987f Mon Sep 17 00:00:00 2001 From: Maximilian Luz Date: Mon, 21 Dec 2020 19:39:56 +0100 Subject: platform/surface: aggregator: Add dedicated bus and device type The Surface Aggregator EC provides varying functionality, depending on the Surface device. To manage this functionality, we use dedicated client devices for each subsystem or virtual device of the EC. While some of these clients are described as standard devices in ACPI and the corresponding client drivers can be implemented as platform drivers in the kernel (making use of the controller API already present), many devices, especially on newer Surface models, cannot be found there. To simplify management of these devices, we introduce a new bus and client device type for the Surface Aggregator subsystem. The new device type takes care of managing the controller reference, essentially guaranteeing its validity for as long as the client device exists, thus alleviating the need to manually establish device links for that purpose in the client driver (as has to be done with the platform devices). Signed-off-by: Maximilian Luz Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20201221183959.1186143-7-luzmaximilian@gmail.com Signed-off-by: Hans de Goede --- drivers/platform/surface/aggregator/Kconfig | 12 + drivers/platform/surface/aggregator/Makefile | 4 + drivers/platform/surface/aggregator/bus.c | 415 ++++++++++++++++++++++++++ drivers/platform/surface/aggregator/bus.h | 27 ++ drivers/platform/surface/aggregator/core.c | 12 + include/linux/mod_devicetable.h | 18 ++ include/linux/surface_aggregator/device.h | 423 +++++++++++++++++++++++++++ scripts/mod/devicetable-offsets.c | 8 + scripts/mod/file2alias.c | 23 ++ 9 files changed, 942 insertions(+) create mode 100644 drivers/platform/surface/aggregator/bus.c create mode 100644 drivers/platform/surface/aggregator/bus.h create mode 100644 include/linux/surface_aggregator/device.h (limited to 'include') diff --git a/drivers/platform/surface/aggregator/Kconfig b/drivers/platform/surface/aggregator/Kconfig index e417bac67088..3aaeea9f0433 100644 --- a/drivers/platform/surface/aggregator/Kconfig +++ b/drivers/platform/surface/aggregator/Kconfig @@ -41,6 +41,18 @@ menuconfig SURFACE_AGGREGATOR module, y if you want to build it into the kernel and n if you don't want it at all. +config SURFACE_AGGREGATOR_BUS + bool "Surface System Aggregator Module Bus" + depends on SURFACE_AGGREGATOR + default y + help + Expands the Surface System Aggregator Module (SSAM) core driver by + providing a dedicated bus and client-device type. + + This bus and device type are intended to provide and simplify support + for non-platform and non-ACPI SSAM devices, i.e. SSAM devices that are + not auto-detectable via the conventional means (e.g. ACPI). + config SURFACE_AGGREGATOR_ERROR_INJECTION bool "Surface System Aggregator Module Error Injection Capabilities" depends on SURFACE_AGGREGATOR diff --git a/drivers/platform/surface/aggregator/Makefile b/drivers/platform/surface/aggregator/Makefile index b8b24c8ec310..c112e2c7112b 100644 --- a/drivers/platform/surface/aggregator/Makefile +++ b/drivers/platform/surface/aggregator/Makefile @@ -11,3 +11,7 @@ surface_aggregator-objs += ssh_parser.o surface_aggregator-objs += ssh_packet_layer.o surface_aggregator-objs += ssh_request_layer.o surface_aggregator-objs += controller.o + +ifeq ($(CONFIG_SURFACE_AGGREGATOR_BUS),y) +surface_aggregator-objs += bus.o +endif diff --git a/drivers/platform/surface/aggregator/bus.c b/drivers/platform/surface/aggregator/bus.c new file mode 100644 index 000000000000..a9b660af0917 --- /dev/null +++ b/drivers/platform/surface/aggregator/bus.c @@ -0,0 +1,415 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Surface System Aggregator Module bus and device integration. + * + * Copyright (C) 2019-2020 Maximilian Luz + */ + +#include +#include + +#include +#include + +#include "bus.h" +#include "controller.h" + +static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct ssam_device *sdev = to_ssam_device(dev); + + return sysfs_emit(buf, "ssam:d%02Xc%02Xt%02Xi%02Xf%02X\n", + sdev->uid.domain, sdev->uid.category, sdev->uid.target, + sdev->uid.instance, sdev->uid.function); +} +static DEVICE_ATTR_RO(modalias); + +static struct attribute *ssam_device_attrs[] = { + &dev_attr_modalias.attr, + NULL, +}; +ATTRIBUTE_GROUPS(ssam_device); + +static int ssam_device_uevent(struct device *dev, struct kobj_uevent_env *env) +{ + struct ssam_device *sdev = to_ssam_device(dev); + + return add_uevent_var(env, "MODALIAS=ssam:d%02Xc%02Xt%02Xi%02Xf%02X", + sdev->uid.domain, sdev->uid.category, + sdev->uid.target, sdev->uid.instance, + sdev->uid.function); +} + +static void ssam_device_release(struct device *dev) +{ + struct ssam_device *sdev = to_ssam_device(dev); + + ssam_controller_put(sdev->ctrl); + kfree(sdev); +} + +const struct device_type ssam_device_type = { + .name = "surface_aggregator_device", + .groups = ssam_device_groups, + .uevent = ssam_device_uevent, + .release = ssam_device_release, +}; +EXPORT_SYMBOL_GPL(ssam_device_type); + +/** + * ssam_device_alloc() - Allocate and initialize a SSAM client device. + * @ctrl: The controller under which the device should be added. + * @uid: The UID of the device to be added. + * + * Allocates and initializes a new client device. The parent of the device + * will be set to the controller device and the name will be set based on the + * UID. Note that the device still has to be added via ssam_device_add(). + * Refer to that function for more details. + * + * Return: Returns the newly allocated and initialized SSAM client device, or + * %NULL if it could not be allocated. + */ +struct ssam_device *ssam_device_alloc(struct ssam_controller *ctrl, + struct ssam_device_uid uid) +{ + struct ssam_device *sdev; + + sdev = kzalloc(sizeof(*sdev), GFP_KERNEL); + if (!sdev) + return NULL; + + device_initialize(&sdev->dev); + sdev->dev.bus = &ssam_bus_type; + sdev->dev.type = &ssam_device_type; + sdev->dev.parent = ssam_controller_device(ctrl); + sdev->ctrl = ssam_controller_get(ctrl); + sdev->uid = uid; + + dev_set_name(&sdev->dev, "%02x:%02x:%02x:%02x:%02x", + sdev->uid.domain, sdev->uid.category, sdev->uid.target, + sdev->uid.instance, sdev->uid.function); + + return sdev; +} +EXPORT_SYMBOL_GPL(ssam_device_alloc); + +/** + * ssam_device_add() - Add a SSAM client device. + * @sdev: The SSAM client device to be added. + * + * Added client devices must be guaranteed to always have a valid and active + * controller. Thus, this function will fail with %-ENODEV if the controller + * of the device has not been initialized yet, has been suspended, or has been + * shut down. + * + * The caller of this function should ensure that the corresponding call to + * ssam_device_remove() is issued before the controller is shut down. If the + * added device is a direct child of the controller device (default), it will + * be automatically removed when the controller is shut down. + * + * By default, the controller device will become the parent of the newly + * created client device. The parent may be changed before ssam_device_add is + * called, but care must be taken that a) the correct suspend/resume ordering + * is guaranteed and b) the client device does not outlive the controller, + * i.e. that the device is removed before the controller is being shut down. + * In case these guarantees have to be manually enforced, please refer to the + * ssam_client_link() and ssam_client_bind() functions, which are intended to + * set up device-links for this purpose. + * + * Return: Returns zero on success, a negative error code on failure. + */ +int ssam_device_add(struct ssam_device *sdev) +{ + int status; + + /* + * Ensure that we can only add new devices to a controller if it has + * been started and is not going away soon. This works in combination + * with ssam_controller_remove_clients to ensure driver presence for the + * controller device, i.e. it ensures that the controller (sdev->ctrl) + * is always valid and can be used for requests as long as the client + * device we add here is registered as child under it. This essentially + * guarantees that the client driver can always expect the preconditions + * for functions like ssam_request_sync (controller has to be started + * and is not suspended) to hold and thus does not have to check for + * them. + * + * Note that for this to work, the controller has to be a parent device. + * If it is not a direct parent, care has to be taken that the device is + * removed via ssam_device_remove(), as device_unregister does not + * remove child devices recursively. + */ + ssam_controller_statelock(sdev->ctrl); + + if (sdev->ctrl->state != SSAM_CONTROLLER_STARTED) { + ssam_controller_stateunlock(sdev->ctrl); + return -ENODEV; + } + + status = device_add(&sdev->dev); + + ssam_controller_stateunlock(sdev->ctrl); + return status; +} +EXPORT_SYMBOL_GPL(ssam_device_add); + +/** + * ssam_device_remove() - Remove a SSAM client device. + * @sdev: The device to remove. + * + * Removes and unregisters the provided SSAM client device. + */ +void ssam_device_remove(struct ssam_device *sdev) +{ + device_unregister(&sdev->dev); +} +EXPORT_SYMBOL_GPL(ssam_device_remove); + +/** + * ssam_device_id_compatible() - Check if a device ID matches a UID. + * @id: The device ID as potential match. + * @uid: The device UID matching against. + * + * Check if the given ID is a match for the given UID, i.e. if a device with + * the provided UID is compatible to the given ID following the match rules + * described in its &ssam_device_id.match_flags member. + * + * Return: Returns %true if the given UID is compatible to the match rule + * described by the given ID, %false otherwise. + */ +static bool ssam_device_id_compatible(const struct ssam_device_id *id, + struct ssam_device_uid uid) +{ + if (id->domain != uid.domain || id->category != uid.category) + return false; + + if ((id->match_flags & SSAM_MATCH_TARGET) && id->target != uid.target) + return false; + + if ((id->match_flags & SSAM_MATCH_INSTANCE) && id->instance != uid.instance) + return false; + + if ((id->match_flags & SSAM_MATCH_FUNCTION) && id->function != uid.function) + return false; + + return true; +} + +/** + * ssam_device_id_is_null() - Check if a device ID is null. + * @id: The device ID to check. + * + * Check if a given device ID is null, i.e. all zeros. Used to check for the + * end of ``MODULE_DEVICE_TABLE(ssam, ...)`` or similar lists. + * + * Return: Returns %true if the given ID represents a null ID, %false + * otherwise. + */ +static bool ssam_device_id_is_null(const struct ssam_device_id *id) +{ + return id->match_flags == 0 && + id->domain == 0 && + id->category == 0 && + id->target == 0 && + id->instance == 0 && + id->function == 0 && + id->driver_data == 0; +} + +/** + * ssam_device_id_match() - Find the matching ID table entry for the given UID. + * @table: The table to search in. + * @uid: The UID to matched against the individual table entries. + * + * Find the first match for the provided device UID in the provided ID table + * and return it. Returns %NULL if no match could be found. + */ +const struct ssam_device_id *ssam_device_id_match(const struct ssam_device_id *table, + const struct ssam_device_uid uid) +{ + const struct ssam_device_id *id; + + for (id = table; !ssam_device_id_is_null(id); ++id) + if (ssam_device_id_compatible(id, uid)) + return id; + + return NULL; +} +EXPORT_SYMBOL_GPL(ssam_device_id_match); + +/** + * ssam_device_get_match() - Find and return the ID matching the device in the + * ID table of the bound driver. + * @dev: The device for which to get the matching ID table entry. + * + * Find the fist match for the UID of the device in the ID table of the + * currently bound driver and return it. Returns %NULL if the device does not + * have a driver bound to it, the driver does not have match_table (i.e. it is + * %NULL), or there is no match in the driver's match_table. + * + * This function essentially calls ssam_device_id_match() with the ID table of + * the bound device driver and the UID of the device. + * + * Return: Returns the first match for the UID of the device in the device + * driver's match table, or %NULL if no such match could be found. + */ +const struct ssam_device_id *ssam_device_get_match(const struct ssam_device *dev) +{ + const struct ssam_device_driver *sdrv; + + sdrv = to_ssam_device_driver(dev->dev.driver); + if (!sdrv) + return NULL; + + if (!sdrv->match_table) + return NULL; + + return ssam_device_id_match(sdrv->match_table, dev->uid); +} +EXPORT_SYMBOL_GPL(ssam_device_get_match); + +/** + * ssam_device_get_match_data() - Find the ID matching the device in the + * ID table of the bound driver and return its ``driver_data`` member. + * @dev: The device for which to get the match data. + * + * Find the fist match for the UID of the device in the ID table of the + * corresponding driver and return its driver_data. Returns %NULL if the + * device does not have a driver bound to it, the driver does not have + * match_table (i.e. it is %NULL), there is no match in the driver's + * match_table, or the match does not have any driver_data. + * + * This function essentially calls ssam_device_get_match() and, if any match + * could be found, returns its ``struct ssam_device_id.driver_data`` member. + * + * Return: Returns the driver data associated with the first match for the UID + * of the device in the device driver's match table, or %NULL if no such match + * could be found. + */ +const void *ssam_device_get_match_data(const struct ssam_device *dev) +{ + const struct ssam_device_id *id; + + id = ssam_device_get_match(dev); + if (!id) + return NULL; + + return (const void *)id->driver_data; +} +EXPORT_SYMBOL_GPL(ssam_device_get_match_data); + +static int ssam_bus_match(struct device *dev, struct device_driver *drv) +{ + struct ssam_device_driver *sdrv = to_ssam_device_driver(drv); + struct ssam_device *sdev = to_ssam_device(dev); + + if (!is_ssam_device(dev)) + return 0; + + return !!ssam_device_id_match(sdrv->match_table, sdev->uid); +} + +static int ssam_bus_probe(struct device *dev) +{ + return to_ssam_device_driver(dev->driver) + ->probe(to_ssam_device(dev)); +} + +static int ssam_bus_remove(struct device *dev) +{ + struct ssam_device_driver *sdrv = to_ssam_device_driver(dev->driver); + + if (sdrv->remove) + sdrv->remove(to_ssam_device(dev)); + + return 0; +} + +struct bus_type ssam_bus_type = { + .name = "surface_aggregator", + .match = ssam_bus_match, + .probe = ssam_bus_probe, + .remove = ssam_bus_remove, +}; +EXPORT_SYMBOL_GPL(ssam_bus_type); + +/** + * __ssam_device_driver_register() - Register a SSAM client device driver. + * @sdrv: The driver to register. + * @owner: The module owning the provided driver. + * + * Please refer to the ssam_device_driver_register() macro for the normal way + * to register a driver from inside its owning module. + */ +int __ssam_device_driver_register(struct ssam_device_driver *sdrv, + struct module *owner) +{ + sdrv->driver.owner = owner; + sdrv->driver.bus = &ssam_bus_type; + + /* force drivers to async probe so I/O is possible in probe */ + sdrv->driver.probe_type = PROBE_PREFER_ASYNCHRONOUS; + + return driver_register(&sdrv->driver); +} +EXPORT_SYMBOL_GPL(__ssam_device_driver_register); + +/** + * ssam_device_driver_unregister - Unregister a SSAM device driver. + * @sdrv: The driver to unregister. + */ +void ssam_device_driver_unregister(struct ssam_device_driver *sdrv) +{ + driver_unregister(&sdrv->driver); +} +EXPORT_SYMBOL_GPL(ssam_device_driver_unregister); + +static int ssam_remove_device(struct device *dev, void *_data) +{ + struct ssam_device *sdev = to_ssam_device(dev); + + if (is_ssam_device(dev)) + ssam_device_remove(sdev); + + return 0; +} + +/** + * ssam_controller_remove_clients() - Remove SSAM client devices registered as + * direct children under the given controller. + * @ctrl: The controller to remove all direct clients for. + * + * Remove all SSAM client devices registered as direct children under the + * given controller. Note that this only accounts for direct children of the + * controller device. This does not take care of any client devices where the + * parent device has been manually set before calling ssam_device_add. Refer + * to ssam_device_add()/ssam_device_remove() for more details on those cases. + * + * To avoid new devices being added in parallel to this call, the main + * controller lock (not statelock) must be held during this (and if + * necessary, any subsequent deinitialization) call. + */ +void ssam_controller_remove_clients(struct ssam_controller *ctrl) +{ + struct device *dev; + + dev = ssam_controller_device(ctrl); + device_for_each_child_reverse(dev, NULL, ssam_remove_device); +} + +/** + * ssam_bus_register() - Register and set-up the SSAM client device bus. + */ +int ssam_bus_register(void) +{ + return bus_register(&ssam_bus_type); +} + +/** + * ssam_bus_unregister() - Unregister the SSAM client device bus. + */ +void ssam_bus_unregister(void) +{ + return bus_unregister(&ssam_bus_type); +} diff --git a/drivers/platform/surface/aggregator/bus.h b/drivers/platform/surface/aggregator/bus.h new file mode 100644 index 000000000000..7712baaed6a5 --- /dev/null +++ b/drivers/platform/surface/aggregator/bus.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Surface System Aggregator Module bus and device integration. + * + * Copyright (C) 2019-2020 Maximilian Luz + */ + +#ifndef _SURFACE_AGGREGATOR_BUS_H +#define _SURFACE_AGGREGATOR_BUS_H + +#include + +#ifdef CONFIG_SURFACE_AGGREGATOR_BUS + +void ssam_controller_remove_clients(struct ssam_controller *ctrl); + +int ssam_bus_register(void); +void ssam_bus_unregister(void); + +#else /* CONFIG_SURFACE_AGGREGATOR_BUS */ + +static inline void ssam_controller_remove_clients(struct ssam_controller *ctrl) {} +static inline int ssam_bus_register(void) { return 0; } +static inline void ssam_bus_unregister(void) {} + +#endif /* CONFIG_SURFACE_AGGREGATOR_BUS */ +#endif /* _SURFACE_AGGREGATOR_BUS_H */ diff --git a/drivers/platform/surface/aggregator/core.c b/drivers/platform/surface/aggregator/core.c index b6a9dea53592..8dc2c267bcd6 100644 --- a/drivers/platform/surface/aggregator/core.c +++ b/drivers/platform/surface/aggregator/core.c @@ -22,6 +22,8 @@ #include #include + +#include "bus.h" #include "controller.h" #define CREATE_TRACE_POINTS @@ -739,6 +741,9 @@ static void ssam_serial_hub_remove(struct serdev_device *serdev) sysfs_remove_group(&serdev->dev.kobj, &ssam_sam_group); ssam_controller_lock(ctrl); + /* Remove all client devices. */ + ssam_controller_remove_clients(ctrl); + /* Act as if suspending to silence events. */ status = ssam_ctrl_notif_display_off(ctrl); if (status) { @@ -791,6 +796,10 @@ static int __init ssam_core_init(void) { int status; + status = ssam_bus_register(); + if (status) + goto err_bus; + status = ssh_ctrl_packet_cache_init(); if (status) goto err_cpkg; @@ -810,6 +819,8 @@ err_register: err_evitem: ssh_ctrl_packet_cache_destroy(); err_cpkg: + ssam_bus_unregister(); +err_bus: return status; } module_init(ssam_core_init); @@ -819,6 +830,7 @@ static void __exit ssam_core_exit(void) serdev_device_driver_unregister(&ssam_serial_hub); ssam_event_item_cache_destroy(); ssh_ctrl_packet_cache_destroy(); + ssam_bus_unregister(); } module_exit(ssam_core_exit); diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index c425290b21e2..935060955152 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -846,4 +846,22 @@ struct auxiliary_device_id { kernel_ulong_t driver_data; }; +/* Surface System Aggregator Module */ + +#define SSAM_MATCH_TARGET 0x1 +#define SSAM_MATCH_INSTANCE 0x2 +#define SSAM_MATCH_FUNCTION 0x4 + +struct ssam_device_id { + __u8 match_flags; + + __u8 domain; + __u8 category; + __u8 target; + __u8 instance; + __u8 function; + + kernel_ulong_t driver_data; +}; + #endif /* LINUX_MOD_DEVICETABLE_H */ diff --git a/include/linux/surface_aggregator/device.h b/include/linux/surface_aggregator/device.h new file mode 100644 index 000000000000..02f3e06c0a60 --- /dev/null +++ b/include/linux/surface_aggregator/device.h @@ -0,0 +1,423 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Surface System Aggregator Module (SSAM) bus and client-device subsystem. + * + * Main interface for the surface-aggregator bus, surface-aggregator client + * devices, and respective drivers building on top of the SSAM controller. + * Provides support for non-platform/non-ACPI SSAM clients via dedicated + * subsystem. + * + * Copyright (C) 2019-2020 Maximilian Luz + */ + +#ifndef _LINUX_SURFACE_AGGREGATOR_DEVICE_H +#define _LINUX_SURFACE_AGGREGATOR_DEVICE_H + +#include +#include +#include + +#include + + +/* -- Surface System Aggregator Module bus. --------------------------------- */ + +/** + * enum ssam_device_domain - SAM device domain. + * @SSAM_DOMAIN_VIRTUAL: Virtual device. + * @SSAM_DOMAIN_SERIALHUB: Physical device connected via Surface Serial Hub. + */ +enum ssam_device_domain { + SSAM_DOMAIN_VIRTUAL = 0x00, + SSAM_DOMAIN_SERIALHUB = 0x01, +}; + +/** + * enum ssam_virtual_tc - Target categories for the virtual SAM domain. + * @SSAM_VIRTUAL_TC_HUB: Device hub category. + */ +enum ssam_virtual_tc { + SSAM_VIRTUAL_TC_HUB = 0x00, +}; + +/** + * struct ssam_device_uid - Unique identifier for SSAM device. + * @domain: Domain of the device. + * @category: Target category of the device. + * @target: Target ID of the device. + * @instance: Instance ID of the device. + * @function: Sub-function of the device. This field can be used to split a + * single SAM device into multiple virtual subdevices to separate + * different functionality of that device and allow one driver per + * such functionality. + */ +struct ssam_device_uid { + u8 domain; + u8 category; + u8 target; + u8 instance; + u8 function; +}; + +/* + * Special values for device matching. + * + * These values are intended to be used with SSAM_DEVICE(), SSAM_VDEV(), and + * SSAM_SDEV() exclusively. Specifically, they are used to initialize the + * match_flags member of the device ID structure. Do not use them directly + * with struct ssam_device_id or struct ssam_device_uid. + */ +#define SSAM_ANY_TID 0xffff +#define SSAM_ANY_IID 0xffff +#define SSAM_ANY_FUN 0xffff + +/** + * SSAM_DEVICE() - Initialize a &struct ssam_device_id with the given + * parameters. + * @d: Domain of the device. + * @cat: Target category of the device. + * @tid: Target ID of the device. + * @iid: Instance ID of the device. + * @fun: Sub-function of the device. + * + * Initializes a &struct ssam_device_id with the given parameters. See &struct + * ssam_device_uid for details regarding the parameters. The special values + * %SSAM_ANY_TID, %SSAM_ANY_IID, and %SSAM_ANY_FUN can be used to specify that + * matching should ignore target ID, instance ID, and/or sub-function, + * respectively. This macro initializes the ``match_flags`` field based on the + * given parameters. + * + * Note: The parameters @d and @cat must be valid &u8 values, the parameters + * @tid, @iid, and @fun must be either valid &u8 values or %SSAM_ANY_TID, + * %SSAM_ANY_IID, or %SSAM_ANY_FUN, respectively. Other non-&u8 values are not + * allowed. + */ +#define SSAM_DEVICE(d, cat, tid, iid, fun) \ + .match_flags = (((tid) != SSAM_ANY_TID) ? SSAM_MATCH_TARGET : 0) \ + | (((iid) != SSAM_ANY_IID) ? SSAM_MATCH_INSTANCE : 0) \ + | (((fun) != SSAM_ANY_FUN) ? SSAM_MATCH_FUNCTION : 0), \ + .domain = d, \ + .category = cat, \ + .target = ((tid) != SSAM_ANY_TID) ? (tid) : 0, \ + .instance = ((iid) != SSAM_ANY_IID) ? (iid) : 0, \ + .function = ((fun) != SSAM_ANY_FUN) ? (fun) : 0 \ + +/** + * SSAM_VDEV() - Initialize a &struct ssam_device_id as virtual device with + * the given parameters. + * @cat: Target category of the device. + * @tid: Target ID of the device. + * @iid: Instance ID of the device. + * @fun: Sub-function of the device. + * + * Initializes a &struct ssam_device_id with the given parameters in the + * virtual domain. See &struct ssam_device_uid for details regarding the + * parameters. The special values %SSAM_ANY_TID, %SSAM_ANY_IID, and + * %SSAM_ANY_FUN can be used to specify that matching should ignore target ID, + * instance ID, and/or sub-function, respectively. This macro initializes the + * ``match_flags`` field based on the given parameters. + * + * Note: The parameter @cat must be a valid &u8 value, the parameters @tid, + * @iid, and @fun must be either valid &u8 values or %SSAM_ANY_TID, + * %SSAM_ANY_IID, or %SSAM_ANY_FUN, respectively. Other non-&u8 values are not + * allowed. + */ +#define SSAM_VDEV(cat, tid, iid, fun) \ + SSAM_DEVICE(SSAM_DOMAIN_VIRTUAL, SSAM_VIRTUAL_TC_##cat, tid, iid, fun) + +/** + * SSAM_SDEV() - Initialize a &struct ssam_device_id as physical SSH device + * with the given parameters. + * @cat: Target category of the device. + * @tid: Target ID of the device. + * @iid: Instance ID of the device. + * @fun: Sub-function of the device. + * + * Initializes a &struct ssam_device_id with the given parameters in the SSH + * domain. See &struct ssam_device_uid for details regarding the parameters. + * The special values %SSAM_ANY_TID, %SSAM_ANY_IID, and %SSAM_ANY_FUN can be + * used to specify that matching should ignore target ID, instance ID, and/or + * sub-function, respectively. This macro initializes the ``match_flags`` + * field based on the given parameters. + * + * Note: The parameter @cat must be a valid &u8 value, the parameters @tid, + * @iid, and @fun must be either valid &u8 values or %SSAM_ANY_TID, + * %SSAM_ANY_IID, or %SSAM_ANY_FUN, respectively. Other non-&u8 values are not + * allowed. + */ +#define SSAM_SDEV(cat, tid, iid, fun) \ + SSAM_DEVICE(SSAM_DOMAIN_SERIALHUB, SSAM_SSH_TC_##cat, tid, iid, fun) + +/** + * struct ssam_device - SSAM client device. + * @dev: Driver model representation of the device. + * @ctrl: SSAM controller managing this device. + * @uid: UID identifying the device. + */ +struct ssam_device { + struct device dev; + struct ssam_controller *ctrl; + + struct ssam_device_uid uid; +}; + +/** + * struct ssam_device_driver - SSAM client device driver. + * @driver: Base driver model structure. + * @match_table: Match table specifying which devices the driver should bind to. + * @probe: Called when the driver is being bound to a device. + * @remove: Called when the driver is being unbound from the device. + */ +struct ssam_device_driver { + struct device_driver driver; + + const struct ssam_device_id *match_table; + + int (*probe)(struct ssam_device *sdev); + void (*remove)(struct ssam_device *sdev); +}; + +extern struct bus_type ssam_bus_type; +extern const struct device_type ssam_device_type; + +/** + * is_ssam_device() - Check if the given device is a SSAM client device. + * @d: The device to test the type of. + * + * Return: Returns %true if the specified device is of type &struct + * ssam_device, i.e. the device type points to %ssam_device_type, and %false + * otherwise. + */ +static inline bool is_ssam_device(struct device *d) +{ + return d->type == &ssam_device_type; +} + +/** + * to_ssam_device() - Casts the given device to a SSAM client device. + * @d: The device to cast. + * + * Casts the given &struct device to a &struct ssam_device. The caller has to + * ensure that the given device is actually enclosed in a &struct ssam_device, + * e.g. by calling is_ssam_device(). + * + * Return: Returns a pointer to the &struct ssam_device wrapping the given + * device @d. + */ +static inline struct ssam_device *to_ssam_device(struct device *d) +{ + return container_of(d, struct ssam_device, dev); +} + +/** + * to_ssam_device_driver() - Casts the given device driver to a SSAM client + * device driver. + * @d: The driver to cast. + * + * Casts the given &struct device_driver to a &struct ssam_device_driver. The + * caller has to ensure that the given driver is actually enclosed in a + * &struct ssam_device_driver. + * + * Return: Returns the pointer to the &struct ssam_device_driver wrapping the + * given device driver @d. + */ +static inline +struct ssam_device_driver *to_ssam_device_driver(struct device_driver *d) +{ + return container_of(d, struct ssam_device_driver, driver); +} + +const struct ssam_device_id *ssam_device_id_match(const struct ssam_device_id *table, + const struct ssam_device_uid uid); + +const struct ssam_device_id *ssam_device_get_match(const struct ssam_device *dev); + +const void *ssam_device_get_match_data(const struct ssam_device *dev); + +struct ssam_device *ssam_device_alloc(struct ssam_controller *ctrl, + struct ssam_device_uid uid); + +int ssam_device_add(struct ssam_device *sdev); +void ssam_device_remove(struct ssam_device *sdev); + +/** + * ssam_device_get() - Increment reference count of SSAM client device. + * @sdev: The device to increment the reference count of. + * + * Increments the reference count of the given SSAM client device by + * incrementing the reference count of the enclosed &struct device via + * get_device(). + * + * See ssam_device_put() for the counter-part of this function. + * + * Return: Returns the device provided as input. + */ +static inline struct ssam_device *ssam_device_get(struct ssam_device *sdev) +{ + return sdev ? to_ssam_device(get_device(&sdev->dev)) : NULL; +} + +/** + * ssam_device_put() - Decrement reference count of SSAM client device. + * @sdev: The device to decrement the reference count of. + * + * Decrements the reference count of the given SSAM client device by + * decrementing the reference count of the enclosed &struct device via + * put_device(). + * + * See ssam_device_get() for the counter-part of this function. + */ +static inline void ssam_device_put(struct ssam_device *sdev) +{ + if (sdev) + put_device(&sdev->dev); +} + +/** + * ssam_device_get_drvdata() - Get driver-data of SSAM client device. + * @sdev: The device to get the driver-data from. + * + * Return: Returns the driver-data of the given device, previously set via + * ssam_device_set_drvdata(). + */ +static inline void *ssam_device_get_drvdata(struct ssam_device *sdev) +{ + return dev_get_drvdata(&sdev->dev); +} + +/** + * ssam_device_set_drvdata() - Set driver-data of SSAM client device. + * @sdev: The device to set the driver-data of. + * @data: The data to set the device's driver-data pointer to. + */ +static inline void ssam_device_set_drvdata(struct ssam_device *sdev, void *data) +{ + dev_set_drvdata(&sdev->dev, data); +} + +int __ssam_device_driver_register(struct ssam_device_driver *d, struct module *o); +void ssam_device_driver_unregister(struct ssam_device_driver *d); + +/** + * ssam_device_driver_register() - Register a SSAM client device driver. + * @drv: The driver to register. + */ +#define ssam_device_driver_register(drv) \ + __ssam_device_driver_register(drv, THIS_MODULE) + +/** + * module_ssam_device_driver() - Helper macro for SSAM device driver + * registration. + * @drv: The driver managed by this module. + * + * Helper macro to register a SSAM device driver via module_init() and + * module_exit(). This macro may only be used once per module and replaces the + * aforementioned definitions. + */ +#define module_ssam_device_driver(drv) \ + module_driver(drv, ssam_device_driver_register, \ + ssam_device_driver_unregister) + + +/* -- Helpers for client-device requests. ----------------------------------- */ + +/** + * SSAM_DEFINE_SYNC_REQUEST_CL_N() - Define synchronous client-device SAM + * request function with neither argument nor return value. + * @name: Name of the generated function. + * @spec: Specification (&struct ssam_request_spec_md) defining the request. + * + * Defines a function executing the synchronous SAM request specified by + * @spec, with the request having neither argument nor return value. Device + * specifying parameters are not hard-coded, but instead are provided via the + * client device, specifically its UID, supplied when calling this function. + * The generated function takes care of setting up the request struct, buffer + * allocation, as well as execution of the request itself, returning once the + * request has been fully completed. The required transport buffer will be + * allocated on the stack. + * + * The generated function is defined as ``int name(struct ssam_device *sdev)``, + * returning the status of the request, which is zero on success and negative + * on failure. The ``sdev`` parameter specifies both the target device of the + * request and by association the controller via which the request is sent. + * + * Refer to ssam_request_sync_onstack() for more details on the behavior of + * the generated function. + */ +#define SSAM_DEFINE_SYNC_REQUEST_CL_N(name, spec...) \ + SSAM_DEFINE_SYNC_REQUEST_MD_N(__raw_##name, spec) \ + int name(struct ssam_device *sdev) \ + { \ + return __raw_##name(sdev->ctrl, sdev->uid.target, \ + sdev->uid.instance); \ + } + +/** + * SSAM_DEFINE_SYNC_REQUEST_CL_W() - Define synchronous client-device SAM + * request function with argument. + * @name: Name of the generated function. + * @atype: Type of the request's argument. + * @spec: Specification (&struct ssam_request_spec_md) defining the request. + * + * Defines a function executing the synchronous SAM request specified by + * @spec, with the request taking an argument of type @atype and having no + * return value. Device specifying parameters are not hard-coded, but instead + * are provided via the client device, specifically its UID, supplied when + * calling this function. The generated function takes care of setting up the + * request struct, buffer allocation, as well as execution of the request + * itself, returning once the request has been fully completed. The required + * transport buffer will be allocated on the stack. + * + * The generated function is defined as ``int name(struct ssam_device *sdev, + * const atype *arg)``, returning the status of the request, which is zero on + * success and negative on failure. The ``sdev`` parameter specifies both the + * target device of the request and by association the controller via which + * the request is sent. The request's argument is specified via the ``arg`` + * pointer. + * + * Refer to ssam_request_sync_onstack() for more details on the behavior of + * the generated function. + */ +#define SSAM_DEFINE_SYNC_REQUEST_CL_W(name, atype, spec...) \ + SSAM_DEFINE_SYNC_REQUEST_MD_W(__raw_##name, atype, spec) \ + int name(struct ssam_device *sdev, const atype *arg) \ + { \ + return __raw_##name(sdev->ctrl, sdev->uid.target, \ + sdev->uid.instance, arg); \ + } + +/** + * SSAM_DEFINE_SYNC_REQUEST_CL_R() - Define synchronous client-device SAM + * request function with return value. + * @name: Name of the generated function. + * @rtype: Type of the request's return value. + * @spec: Specification (&struct ssam_request_spec_md) defining the request. + * + * Defines a function executing the synchronous SAM request specified by + * @spec, with the request taking no argument but having a return value of + * type @rtype. Device specifying parameters are not hard-coded, but instead + * are provided via the client device, specifically its UID, supplied when + * calling this function. The generated function takes care of setting up the + * request struct, buffer allocation, as well as execution of the request + * itself, returning once the request has been fully completed. The required + * transport buffer will be allocated on the stack. + * + * The generated function is defined as ``int name(struct ssam_device *sdev, + * rtype *ret)``, returning the status of the request, which is zero on + * success and negative on failure. The ``sdev`` parameter specifies both the + * target device of the request and by association the controller via which + * the request is sent. The request's return value is written to the memory + * pointed to by the ``ret`` parameter. + * + * Refer to ssam_request_sync_onstack() for more details on the behavior of + * the generated function. + */ +#define SSAM_DEFINE_SYNC_REQUEST_CL_R(name, rtype, spec...) \ + SSAM_DEFINE_SYNC_REQUEST_MD_R(__raw_##name, rtype, spec) \ + int name(struct ssam_device *sdev, rtype *ret) \ + { \ + return __raw_##name(sdev->ctrl, sdev->uid.target, \ + sdev->uid.instance, ret); \ + } + +#endif /* _LINUX_SURFACE_AGGREGATOR_DEVICE_H */ diff --git a/scripts/mod/devicetable-offsets.c b/scripts/mod/devicetable-offsets.c index e377f52dbfa3..f078eeb0a961 100644 --- a/scripts/mod/devicetable-offsets.c +++ b/scripts/mod/devicetable-offsets.c @@ -246,5 +246,13 @@ int main(void) DEVID(auxiliary_device_id); DEVID_FIELD(auxiliary_device_id, name); + DEVID(ssam_device_id); + DEVID_FIELD(ssam_device_id, match_flags); + DEVID_FIELD(ssam_device_id, domain); + DEVID_FIELD(ssam_device_id, category); + DEVID_FIELD(ssam_device_id, target); + DEVID_FIELD(ssam_device_id, instance); + DEVID_FIELD(ssam_device_id, function); + return 0; } diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c index fb4827027536..d21d2871387b 100644 --- a/scripts/mod/file2alias.c +++ b/scripts/mod/file2alias.c @@ -1375,6 +1375,28 @@ static int do_auxiliary_entry(const char *filename, void *symval, char *alias) return 1; } +/* + * Looks like: ssam:dNcNtNiNfN + * + * N is exactly 2 digits, where each is an upper-case hex digit. + */ +static int do_ssam_entry(const char *filename, void *symval, char *alias) +{ + DEF_FIELD(symval, ssam_device_id, match_flags); + DEF_FIELD(symval, ssam_device_id, domain); + DEF_FIELD(symval, ssam_device_id, category); + DEF_FIELD(symval, ssam_device_id, target); + DEF_FIELD(symval, ssam_device_id, instance); + DEF_FIELD(symval, ssam_device_id, function); + + sprintf(alias, "ssam:d%02Xc%02X", domain, category); + ADD(alias, "t", match_flags & SSAM_MATCH_TARGET, target); + ADD(alias, "i", match_flags & SSAM_MATCH_INSTANCE, instance); + ADD(alias, "f", match_flags & SSAM_MATCH_FUNCTION, function); + + return 1; +} + /* Does namelen bytes of name exactly match the symbol? */ static bool sym_is(const char *name, unsigned namelen, const char *symbol) { @@ -1450,6 +1472,7 @@ static const struct devtable devtable[] = { {"wmi", SIZE_wmi_device_id, do_wmi_entry}, {"mhi", SIZE_mhi_device_id, do_mhi_entry}, {"auxiliary", SIZE_auxiliary_device_id, do_auxiliary_entry}, + {"ssam", SIZE_ssam_device_id, do_ssam_entry}, }; /* Create MODULE_ALIAS() statements. -- cgit v1.2.3 From 178f6ab77e617c984d6520b92e747075a12676ff Mon Sep 17 00:00:00 2001 From: Maximilian Luz Date: Mon, 21 Dec 2020 19:39:58 +0100 Subject: platform/surface: Add Surface Aggregator user-space interface Add a misc-device providing user-space access to the Surface Aggregator EC, mainly intended for debugging, testing, and reverse-engineering. This interface gives user-space applications the ability to send requests to the EC and receive the corresponding responses. The device-file is managed by a pseudo platform-device and corresponding driver to avoid dependence on the dedicated bus, allowing it to be loaded in a minimal configuration. A python library and scripts to access this device can be found at [1]. [1]: https://github.com/linux-surface/surface-aggregator-module/tree/master/scripts/ssam Signed-off-by: Maximilian Luz Link: https://lore.kernel.org/r/20201221183959.1186143-9-luzmaximilian@gmail.com Signed-off-by: Hans de Goede --- .../driver-api/surface_aggregator/clients/cdev.rst | 87 ++++++ .../surface_aggregator/clients/index.rst | 12 +- Documentation/userspace-api/ioctl/ioctl-number.rst | 2 + MAINTAINERS | 2 + drivers/platform/surface/Kconfig | 17 ++ drivers/platform/surface/Makefile | 1 + drivers/platform/surface/surface_aggregator_cdev.c | 303 +++++++++++++++++++++ include/uapi/linux/surface_aggregator/cdev.h | 78 ++++++ 8 files changed, 501 insertions(+), 1 deletion(-) create mode 100644 Documentation/driver-api/surface_aggregator/clients/cdev.rst create mode 100644 drivers/platform/surface/surface_aggregator_cdev.c create mode 100644 include/uapi/linux/surface_aggregator/cdev.h (limited to 'include') diff --git a/Documentation/driver-api/surface_aggregator/clients/cdev.rst b/Documentation/driver-api/surface_aggregator/clients/cdev.rst new file mode 100644 index 000000000000..248c1372d879 --- /dev/null +++ b/Documentation/driver-api/surface_aggregator/clients/cdev.rst @@ -0,0 +1,87 @@ +.. SPDX-License-Identifier: GPL-2.0+ + +.. |u8| replace:: :c:type:`u8 ` +.. |u16| replace:: :c:type:`u16 ` +.. |ssam_cdev_request| replace:: :c:type:`struct ssam_cdev_request ` +.. |ssam_cdev_request_flags| replace:: :c:type:`enum ssam_cdev_request_flags ` + +============================== +User-Space EC Interface (cdev) +============================== + +The ``surface_aggregator_cdev`` module provides a misc-device for the SSAM +controller to allow for a (more or less) direct connection from user-space to +the SAM EC. It is intended to be used for development and debugging, and +therefore should not be used or relied upon in any other way. Note that this +module is not loaded automatically, but instead must be loaded manually. + +The provided interface is accessible through the ``/dev/surface/aggregator`` +device-file. All functionality of this interface is provided via IOCTLs. +These IOCTLs and their respective input/output parameter structs are defined in +``include/uapi/linux/surface_aggregator/cdev.h``. + +A small python library and scripts for accessing this interface can be found +at https://github.com/linux-surface/surface-aggregator-module/tree/master/scripts/ssam. + + +Controller IOCTLs +================= + +The following IOCTLs are provided: + +.. flat-table:: Controller IOCTLs + :widths: 1 1 1 1 4 + :header-rows: 1 + + * - Type + - Number + - Direction + - Name + - Description + + * - ``0xA5`` + - ``1`` + - ``WR`` + - ``REQUEST`` + - Perform synchronous SAM request. + + +``REQUEST`` +----------- + +Defined as ``_IOWR(0xA5, 1, struct ssam_cdev_request)``. + +Executes a synchronous SAM request. The request specification is passed in +as argument of type |ssam_cdev_request|, which is then written to/modified +by the IOCTL to return status and result of the request. + +Request payload data must be allocated separately and is passed in via the +``payload.data`` and ``payload.length`` members. If a response is required, +the response buffer must be allocated by the caller and passed in via the +``response.data`` member. The ``response.length`` member must be set to the +capacity of this buffer, or if no response is required, zero. Upon +completion of the request, the call will write the response to the response +buffer (if its capacity allows it) and overwrite the length field with the +actual size of the response, in bytes. + +Additionally, if the request has a response, this must be indicated via the +request flags, as is done with in-kernel requests. Request flags can be set +via the ``flags`` member and the values correspond to the values found in +|ssam_cdev_request_flags|. + +Finally, the status of the request itself is returned in the ``status`` +member (a negative errno value indicating failure). Note that failure +indication of the IOCTL is separated from failure indication of the request: +The IOCTL returns a negative status code if anything failed during setup of +the request (``-EFAULT``) or if the provided argument or any of its fields +are invalid (``-EINVAL``). In this case, the status value of the request +argument may be set, providing more detail on what went wrong (e.g. +``-ENOMEM`` for out-of-memory), but this value may also be zero. The IOCTL +will return with a zero status code in case the request has been set up, +submitted, and completed (i.e. handed back to user-space) successfully from +inside the IOCTL, but the request ``status`` member may still be negative in +case the actual execution of the request failed after it has been submitted. + +A full definition of the argument struct is provided below: + +.. kernel-doc:: include/uapi/linux/surface_aggregator/cdev.h diff --git a/Documentation/driver-api/surface_aggregator/clients/index.rst b/Documentation/driver-api/surface_aggregator/clients/index.rst index 31e026d96102..ab260ec82cfb 100644 --- a/Documentation/driver-api/surface_aggregator/clients/index.rst +++ b/Documentation/driver-api/surface_aggregator/clients/index.rst @@ -7,4 +7,14 @@ Client Driver Documentation This is the documentation for client drivers themselves. Refer to :doc:`../client` for documentation on how to write client drivers. -.. Place documentation for individual client drivers here. +.. toctree:: + :maxdepth: 1 + + cdev + +.. only:: subproject and html + + Indices + ======= + + * :ref:`genindex` diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst index a4c75a28c839..b5231d7f9200 100644 --- a/Documentation/userspace-api/ioctl/ioctl-number.rst +++ b/Documentation/userspace-api/ioctl/ioctl-number.rst @@ -324,6 +324,8 @@ Code Seq# Include File Comments 0xA3 90-9F linux/dtlk.h 0xA4 00-1F uapi/linux/tee.h Generic TEE subsystem 0xA4 00-1F uapi/asm/sgx.h +0xA5 01 linux/surface_aggregator/cdev.h Microsoft Surface Platform System Aggregator + 0xAA 00-3F linux/uapi/linux/userfaultfd.h 0xAB 00-1F linux/nbd.h 0xAC 00-1F linux/raw.h diff --git a/MAINTAINERS b/MAINTAINERS index 41f082551942..9bd55c842898 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11820,7 +11820,9 @@ W: https://github.com/linux-surface/surface-aggregator-module C: irc://chat.freenode.net/##linux-surface F: Documentation/driver-api/surface_aggregator/ F: drivers/platform/surface/aggregator/ +F: drivers/platform/surface/surface_aggregator_cdev.c F: include/linux/surface_aggregator/ +F: include/uapi/linux/surface_aggregator/ MICROTEK X6 SCANNER M: Oliver Neukum diff --git a/drivers/platform/surface/Kconfig b/drivers/platform/surface/Kconfig index 2916a47b130e..988b2de6b500 100644 --- a/drivers/platform/surface/Kconfig +++ b/drivers/platform/surface/Kconfig @@ -41,6 +41,23 @@ config SURFACE_3_POWER_OPREGION This driver provides support for ACPI operation region of the Surface 3 battery platform driver. +config SURFACE_AGGREGATOR_CDEV + tristate "Surface System Aggregator Module User-Space Interface" + depends on SURFACE_AGGREGATOR + help + Provides a misc-device interface to the Surface System Aggregator + Module (SSAM) controller. + + This option provides a module (called surface_aggregator_cdev), that, + when loaded, will add a client device (and its respective driver) to + the SSAM controller. Said client device manages a misc-device + interface (/dev/surface/aggregator), which can be used by user-space + tools to directly communicate with the SSAM EC by sending requests and + receiving the corresponding responses. + + The provided interface is intended for debugging and development only, + and should not be used otherwise. + config SURFACE_GPE tristate "Surface GPE/Lid Support Driver" depends on DMI diff --git a/drivers/platform/surface/Makefile b/drivers/platform/surface/Makefile index 034134fe0264..161f0ad05795 100644 --- a/drivers/platform/surface/Makefile +++ b/drivers/platform/surface/Makefile @@ -8,5 +8,6 @@ obj-$(CONFIG_SURFACE3_WMI) += surface3-wmi.o obj-$(CONFIG_SURFACE_3_BUTTON) += surface3_button.o obj-$(CONFIG_SURFACE_3_POWER_OPREGION) += surface3_power.o obj-$(CONFIG_SURFACE_AGGREGATOR) += aggregator/ +obj-$(CONFIG_SURFACE_AGGREGATOR_CDEV) += surface_aggregator_cdev.o obj-$(CONFIG_SURFACE_GPE) += surface_gpe.o obj-$(CONFIG_SURFACE_PRO3_BUTTON) += surfacepro3_button.o diff --git a/drivers/platform/surface/surface_aggregator_cdev.c b/drivers/platform/surface/surface_aggregator_cdev.c new file mode 100644 index 000000000000..340d15b148b9 --- /dev/null +++ b/drivers/platform/surface/surface_aggregator_cdev.c @@ -0,0 +1,303 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Provides user-space access to the SSAM EC via the /dev/surface/aggregator + * misc device. Intended for debugging and development. + * + * Copyright (C) 2020 Maximilian Luz + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#define SSAM_CDEV_DEVICE_NAME "surface_aggregator_cdev" + +struct ssam_cdev { + struct kref kref; + struct rw_semaphore lock; + struct ssam_controller *ctrl; + struct miscdevice mdev; +}; + +static void __ssam_cdev_release(struct kref *kref) +{ + kfree(container_of(kref, struct ssam_cdev, kref)); +} + +static struct ssam_cdev *ssam_cdev_get(struct ssam_cdev *cdev) +{ + if (cdev) + kref_get(&cdev->kref); + + return cdev; +} + +static void ssam_cdev_put(struct ssam_cdev *cdev) +{ + if (cdev) + kref_put(&cdev->kref, __ssam_cdev_release); +} + +static int ssam_cdev_device_open(struct inode *inode, struct file *filp) +{ + struct miscdevice *mdev = filp->private_data; + struct ssam_cdev *cdev = container_of(mdev, struct ssam_cdev, mdev); + + filp->private_data = ssam_cdev_get(cdev); + return stream_open(inode, filp); +} + +static int ssam_cdev_device_release(struct inode *inode, struct file *filp) +{ + ssam_cdev_put(filp->private_data); + return 0; +} + +static long ssam_cdev_request(struct ssam_cdev *cdev, unsigned long arg) +{ + struct ssam_cdev_request __user *r; + struct ssam_cdev_request rqst; + struct ssam_request spec; + struct ssam_response rsp; + const void __user *plddata; + void __user *rspdata; + int status = 0, ret = 0, tmp; + + r = (struct ssam_cdev_request __user *)arg; + ret = copy_struct_from_user(&rqst, sizeof(rqst), r, sizeof(*r)); + if (ret) + goto out; + + plddata = u64_to_user_ptr(rqst.payload.data); + rspdata = u64_to_user_ptr(rqst.response.data); + + /* Setup basic request fields. */ + spec.target_category = rqst.target_category; + spec.target_id = rqst.target_id; + spec.command_id = rqst.command_id; + spec.instance_id = rqst.instance_id; + spec.flags = 0; + spec.length = rqst.payload.length; + spec.payload = NULL; + + if (rqst.flags & SSAM_CDEV_REQUEST_HAS_RESPONSE) + spec.flags |= SSAM_REQUEST_HAS_RESPONSE; + + if (rqst.flags & SSAM_CDEV_REQUEST_UNSEQUENCED) + spec.flags |= SSAM_REQUEST_UNSEQUENCED; + + rsp.capacity = rqst.response.length; + rsp.length = 0; + rsp.pointer = NULL; + + /* Get request payload from user-space. */ + if (spec.length) { + if (!plddata) { + ret = -EINVAL; + goto out; + } + + spec.payload = kzalloc(spec.length, GFP_KERNEL); + if (!spec.payload) { + ret = -ENOMEM; + goto out; + } + + if (copy_from_user((void *)spec.payload, plddata, spec.length)) { + ret = -EFAULT; + goto out; + } + } + + /* Allocate response buffer. */ + if (rsp.capacity) { + if (!rspdata) { + ret = -EINVAL; + goto out; + } + + rsp.pointer = kzalloc(rsp.capacity, GFP_KERNEL); + if (!rsp.pointer) { + ret = -ENOMEM; + goto out; + } + } + + /* Perform request. */ + status = ssam_request_sync(cdev->ctrl, &spec, &rsp); + if (status) + goto out; + + /* Copy response to user-space. */ + if (rsp.length && copy_to_user(rspdata, rsp.pointer, rsp.length)) + ret = -EFAULT; + +out: + /* Always try to set response-length and status. */ + tmp = put_user(rsp.length, &r->response.length); + if (tmp) + ret = tmp; + + tmp = put_user(status, &r->status); + if (tmp) + ret = tmp; + + /* Cleanup. */ + kfree(spec.payload); + kfree(rsp.pointer); + + return ret; +} + +static long __ssam_cdev_device_ioctl(struct ssam_cdev *cdev, unsigned int cmd, + unsigned long arg) +{ + switch (cmd) { + case SSAM_CDEV_REQUEST: + return ssam_cdev_request(cdev, arg); + + default: + return -ENOTTY; + } +} + +static long ssam_cdev_device_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + struct ssam_cdev *cdev = file->private_data; + long status; + + /* Ensure that controller is valid for as long as we need it. */ + if (down_read_killable(&cdev->lock)) + return -ERESTARTSYS; + + if (!cdev->ctrl) { + up_read(&cdev->lock); + return -ENODEV; + } + + status = __ssam_cdev_device_ioctl(cdev, cmd, arg); + + up_read(&cdev->lock); + return status; +} + +static const struct file_operations ssam_controller_fops = { + .owner = THIS_MODULE, + .open = ssam_cdev_device_open, + .release = ssam_cdev_device_release, + .unlocked_ioctl = ssam_cdev_device_ioctl, + .compat_ioctl = ssam_cdev_device_ioctl, + .llseek = noop_llseek, +}; + +static int ssam_dbg_device_probe(struct platform_device *pdev) +{ + struct ssam_controller *ctrl; + struct ssam_cdev *cdev; + int status; + + ctrl = ssam_client_bind(&pdev->dev); + if (IS_ERR(ctrl)) + return PTR_ERR(ctrl) == -ENODEV ? -EPROBE_DEFER : PTR_ERR(ctrl); + + cdev = kzalloc(sizeof(*cdev), GFP_KERNEL); + if (!cdev) + return -ENOMEM; + + kref_init(&cdev->kref); + init_rwsem(&cdev->lock); + cdev->ctrl = ctrl; + + cdev->mdev.parent = &pdev->dev; + cdev->mdev.minor = MISC_DYNAMIC_MINOR; + cdev->mdev.name = "surface_aggregator"; + cdev->mdev.nodename = "surface/aggregator"; + cdev->mdev.fops = &ssam_controller_fops; + + status = misc_register(&cdev->mdev); + if (status) { + kfree(cdev); + return status; + } + + platform_set_drvdata(pdev, cdev); + return 0; +} + +static int ssam_dbg_device_remove(struct platform_device *pdev) +{ + struct ssam_cdev *cdev = platform_get_drvdata(pdev); + + misc_deregister(&cdev->mdev); + + /* + * The controller is only guaranteed to be valid for as long as the + * driver is bound. Remove controller so that any lingering open files + * cannot access it any more after we're gone. + */ + down_write(&cdev->lock); + cdev->ctrl = NULL; + up_write(&cdev->lock); + + ssam_cdev_put(cdev); + return 0; +} + +static struct platform_device *ssam_cdev_device; + +static struct platform_driver ssam_cdev_driver = { + .probe = ssam_dbg_device_probe, + .remove = ssam_dbg_device_remove, + .driver = { + .name = SSAM_CDEV_DEVICE_NAME, + .probe_type = PROBE_PREFER_ASYNCHRONOUS, + }, +}; + +static int __init ssam_debug_init(void) +{ + int status; + + ssam_cdev_device = platform_device_alloc(SSAM_CDEV_DEVICE_NAME, + PLATFORM_DEVID_NONE); + if (!ssam_cdev_device) + return -ENOMEM; + + status = platform_device_add(ssam_cdev_device); + if (status) + goto err_device; + + status = platform_driver_register(&ssam_cdev_driver); + if (status) + goto err_driver; + + return 0; + +err_driver: + platform_device_del(ssam_cdev_device); +err_device: + platform_device_put(ssam_cdev_device); + return status; +} +module_init(ssam_debug_init); + +static void __exit ssam_debug_exit(void) +{ + platform_driver_unregister(&ssam_cdev_driver); + platform_device_unregister(ssam_cdev_device); +} +module_exit(ssam_debug_exit); + +MODULE_AUTHOR("Maximilian Luz "); +MODULE_DESCRIPTION("User-space interface for Surface System Aggregator Module"); +MODULE_LICENSE("GPL"); diff --git a/include/uapi/linux/surface_aggregator/cdev.h b/include/uapi/linux/surface_aggregator/cdev.h new file mode 100644 index 000000000000..fbcce04abfe9 --- /dev/null +++ b/include/uapi/linux/surface_aggregator/cdev.h @@ -0,0 +1,78 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +/* + * Surface System Aggregator Module (SSAM) user-space EC interface. + * + * Definitions, structs, and IOCTLs for the /dev/surface/aggregator misc + * device. This device provides direct user-space access to the SSAM EC. + * Intended for debugging and development. + * + * Copyright (C) 2020 Maximilian Luz + */ + +#ifndef _UAPI_LINUX_SURFACE_AGGREGATOR_CDEV_H +#define _UAPI_LINUX_SURFACE_AGGREGATOR_CDEV_H + +#include +#include + +/** + * enum ssam_cdev_request_flags - Request flags for SSAM cdev request IOCTL. + * + * @SSAM_CDEV_REQUEST_HAS_RESPONSE: + * Specifies that the request expects a response. If not set, the request + * will be directly completed after its underlying packet has been + * transmitted. If set, the request transport system waits for a response + * of the request. + * + * @SSAM_CDEV_REQUEST_UNSEQUENCED: + * Specifies that the request should be transmitted via an unsequenced + * packet. If set, the request must not have a response, meaning that this + * flag and the %SSAM_CDEV_REQUEST_HAS_RESPONSE flag are mutually + * exclusive. + */ +enum ssam_cdev_request_flags { + SSAM_CDEV_REQUEST_HAS_RESPONSE = 0x01, + SSAM_CDEV_REQUEST_UNSEQUENCED = 0x02, +}; + +/** + * struct ssam_cdev_request - Controller request IOCTL argument. + * @target_category: Target category of the SAM request. + * @target_id: Target ID of the SAM request. + * @command_id: Command ID of the SAM request. + * @instance_id: Instance ID of the SAM request. + * @flags: Request flags (see &enum ssam_cdev_request_flags). + * @status: Request status (output). + * @payload: Request payload (input data). + * @payload.data: Pointer to request payload data. + * @payload.length: Length of request payload data (in bytes). + * @response: Request response (output data). + * @response.data: Pointer to response buffer. + * @response.length: On input: Capacity of response buffer (in bytes). + * On output: Length of request response (number of bytes + * in the buffer that are actually used). + */ +struct ssam_cdev_request { + __u8 target_category; + __u8 target_id; + __u8 command_id; + __u8 instance_id; + __u16 flags; + __s16 status; + + struct { + __u64 data; + __u16 length; + __u8 __pad[6]; + } payload; + + struct { + __u64 data; + __u16 length; + __u8 __pad[6]; + } response; +} __attribute__((__packed__)); + +#define SSAM_CDEV_REQUEST _IOWR(0xA5, 1, struct ssam_cdev_request) + +#endif /* _UAPI_LINUX_SURFACE_AGGREGATOR_CDEV_H */ -- cgit v1.2.3 From fc00bc8ac1dada4085f9308f85f2d6359da0faa8 Mon Sep 17 00:00:00 2001 From: Maximilian Luz Date: Mon, 21 Dec 2020 19:39:59 +0100 Subject: platform/surface: Add Surface ACPI Notify driver The Surface ACPI Notify (SAN) device provides an ACPI interface to the Surface Aggregator EC, specifically the Surface Serial Hub interface. This interface allows EC requests to be made from ACPI code and can convert a subset of EC events back to ACPI notifications. Specifically, this interface provides a GenericSerialBus operation region ACPI code can execute a request by writing the request command data and payload to this operation region and reading back the corresponding response via a write-then-read operation. Furthermore, this interface provides a _DSM method to be called when certain events from the EC have been received, essentially turning them into ACPI notifications. The driver provided in this commit essentially takes care of translating the request data written to the operation region, executing the request, waiting for it to finish, and finally writing and translating back the response (if the request has one). Furthermore, this driver takes care of enabling the events handled via ACPI _DSM calls. Lastly, this driver also exposes an interface providing discrete GPU (dGPU) power-on notifications on the Surface Book 2, which are also received via the operation region interface (but not handled by the SAN driver directly), making them accessible to other drivers (such as a dGPU hot-plug driver that may be added later on). On 5th and 6th generation Surface devices (Surface Pro 5/2017, Pro 6, Book 2, Laptop 1 and 2), the SAN interface provides full battery and thermal subsystem access, as well as other EC based functionality. On those models, battery and thermal sensor devices are implemented as standard ACPI devices of that type, however, forward ACPI calls to the corresponding Surface Aggregator EC request via the SAN interface and receive corresponding notifications (e.g. battery information change) from it. This interface is therefore required to provide said functionality on those devices. Signed-off-by: Maximilian Luz Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20201221183959.1186143-10-luzmaximilian@gmail.com Signed-off-by: Hans de Goede --- .../surface_aggregator/clients/index.rst | 1 + .../driver-api/surface_aggregator/clients/san.rst | 44 + MAINTAINERS | 2 + drivers/platform/surface/Kconfig | 19 + drivers/platform/surface/Makefile | 1 + drivers/platform/surface/surface_acpi_notify.c | 886 +++++++++++++++++++++ include/linux/surface_acpi_notify.h | 39 + 7 files changed, 992 insertions(+) create mode 100644 Documentation/driver-api/surface_aggregator/clients/san.rst create mode 100644 drivers/platform/surface/surface_acpi_notify.c create mode 100644 include/linux/surface_acpi_notify.h (limited to 'include') diff --git a/Documentation/driver-api/surface_aggregator/clients/index.rst b/Documentation/driver-api/surface_aggregator/clients/index.rst index ab260ec82cfb..3ccabce23271 100644 --- a/Documentation/driver-api/surface_aggregator/clients/index.rst +++ b/Documentation/driver-api/surface_aggregator/clients/index.rst @@ -11,6 +11,7 @@ This is the documentation for client drivers themselves. Refer to :maxdepth: 1 cdev + san .. only:: subproject and html diff --git a/Documentation/driver-api/surface_aggregator/clients/san.rst b/Documentation/driver-api/surface_aggregator/clients/san.rst new file mode 100644 index 000000000000..38c2580e7758 --- /dev/null +++ b/Documentation/driver-api/surface_aggregator/clients/san.rst @@ -0,0 +1,44 @@ +.. SPDX-License-Identifier: GPL-2.0+ + +.. |san_client_link| replace:: :c:func:`san_client_link` +.. |san_dgpu_notifier_register| replace:: :c:func:`san_dgpu_notifier_register` +.. |san_dgpu_notifier_unregister| replace:: :c:func:`san_dgpu_notifier_unregister` + +=================== +Surface ACPI Notify +=================== + +The Surface ACPI Notify (SAN) device provides the bridge between ACPI and +SAM controller. Specifically, ACPI code can execute requests and handle +battery and thermal events via this interface. In addition to this, events +relating to the discrete GPU (dGPU) of the Surface Book 2 can be sent from +ACPI code (note: the Surface Book 3 uses a different method for this). The +only currently known event sent via this interface is a dGPU power-on +notification. While this driver handles the former part internally, it only +relays the dGPU events to any other driver interested via its public API and +does not handle them. + +The public interface of this driver is split into two parts: Client +registration and notifier-block registration. + +A client to the SAN interface can be linked as consumer to the SAN device +via |san_client_link|. This can be used to ensure that the a client +receiving dGPU events does not miss any events due to the SAN interface not +being set up as this forces the client driver to unbind once the SAN driver +is unbound. + +Notifier-blocks can be registered by any device for as long as the module is +loaded, regardless of being linked as client or not. Registration is done +with |san_dgpu_notifier_register|. If the notifier is not needed any more, it +should be unregistered via |san_dgpu_notifier_unregister|. + +Consult the API documentation below for more details. + + +API Documentation +================= + +.. kernel-doc:: include/linux/surface_acpi_notify.h + +.. kernel-doc:: drivers/platform/surface/surface_acpi_notify.c + :export: diff --git a/MAINTAINERS b/MAINTAINERS index 9bd55c842898..cf250c1365b0 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11820,7 +11820,9 @@ W: https://github.com/linux-surface/surface-aggregator-module C: irc://chat.freenode.net/##linux-surface F: Documentation/driver-api/surface_aggregator/ F: drivers/platform/surface/aggregator/ +F: drivers/platform/surface/surface_acpi_notify.c F: drivers/platform/surface/surface_aggregator_cdev.c +F: include/linux/surface_acpi_notify.h F: include/linux/surface_aggregator/ F: include/uapi/linux/surface_aggregator/ diff --git a/drivers/platform/surface/Kconfig b/drivers/platform/surface/Kconfig index 988b2de6b500..83b0a4c7b352 100644 --- a/drivers/platform/surface/Kconfig +++ b/drivers/platform/surface/Kconfig @@ -41,6 +41,25 @@ config SURFACE_3_POWER_OPREGION This driver provides support for ACPI operation region of the Surface 3 battery platform driver. +config SURFACE_ACPI_NOTIFY + tristate "Surface ACPI Notify Driver" + depends on SURFACE_AGGREGATOR + help + Surface ACPI Notify (SAN) driver for Microsoft Surface devices. + + This driver provides support for the ACPI interface (called SAN) of + the Surface System Aggregator Module (SSAM) EC. This interface is used + on 5th- and 6th-generation Microsoft Surface devices (including + Surface Pro 5 and 6, Surface Book 2, Surface Laptops 1 and 2, and in + reduced functionality on the Surface Laptop 3) to execute SSAM + requests directly from ACPI code, as well as receive SSAM events and + turn them into ACPI notifications. It essentially acts as a + translation layer between the SSAM controller and ACPI. + + Specifically, this driver may be needed for battery status reporting, + thermal sensor access, and real-time clock information, depending on + the Surface device in question. + config SURFACE_AGGREGATOR_CDEV tristate "Surface System Aggregator Module User-Space Interface" depends on SURFACE_AGGREGATOR diff --git a/drivers/platform/surface/Makefile b/drivers/platform/surface/Makefile index 161f0ad05795..3eb971006877 100644 --- a/drivers/platform/surface/Makefile +++ b/drivers/platform/surface/Makefile @@ -7,6 +7,7 @@ obj-$(CONFIG_SURFACE3_WMI) += surface3-wmi.o obj-$(CONFIG_SURFACE_3_BUTTON) += surface3_button.o obj-$(CONFIG_SURFACE_3_POWER_OPREGION) += surface3_power.o +obj-$(CONFIG_SURFACE_ACPI_NOTIFY) += surface_acpi_notify.o obj-$(CONFIG_SURFACE_AGGREGATOR) += aggregator/ obj-$(CONFIG_SURFACE_AGGREGATOR_CDEV) += surface_aggregator_cdev.o obj-$(CONFIG_SURFACE_GPE) += surface_gpe.o diff --git a/drivers/platform/surface/surface_acpi_notify.c b/drivers/platform/surface/surface_acpi_notify.c new file mode 100644 index 000000000000..8cd67a669c86 --- /dev/null +++ b/drivers/platform/surface/surface_acpi_notify.c @@ -0,0 +1,886 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Driver for the Surface ACPI Notify (SAN) interface/shim. + * + * Translates communication from ACPI to Surface System Aggregator Module + * (SSAM/SAM) requests and back, specifically SAM-over-SSH. Translates SSAM + * events back to ACPI notifications. Allows handling of discrete GPU + * notifications sent from ACPI via the SAN interface by providing them to any + * registered external driver. + * + * Copyright (C) 2019-2020 Maximilian Luz + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +struct san_data { + struct device *dev; + struct ssam_controller *ctrl; + + struct acpi_connection_info info; + + struct ssam_event_notifier nf_bat; + struct ssam_event_notifier nf_tmp; +}; + +#define to_san_data(ptr, member) \ + container_of(ptr, struct san_data, member) + + +/* -- dGPU notifier interface. ---------------------------------------------- */ + +struct san_rqsg_if { + struct rw_semaphore lock; + struct device *dev; + struct blocking_notifier_head nh; +}; + +static struct san_rqsg_if san_rqsg_if = { + .lock = __RWSEM_INITIALIZER(san_rqsg_if.lock), + .dev = NULL, + .nh = BLOCKING_NOTIFIER_INIT(san_rqsg_if.nh), +}; + +static int san_set_rqsg_interface_device(struct device *dev) +{ + int status = 0; + + down_write(&san_rqsg_if.lock); + if (!san_rqsg_if.dev && dev) + san_rqsg_if.dev = dev; + else + status = -EBUSY; + up_write(&san_rqsg_if.lock); + + return status; +} + +/** + * san_client_link() - Link client as consumer to SAN device. + * @client: The client to link. + * + * Sets up a device link between the provided client device as consumer and + * the SAN device as provider. This function can be used to ensure that the + * SAN interface has been set up and will be set up for as long as the driver + * of the client device is bound. This guarantees that, during that time, all + * dGPU events will be received by any registered notifier. + * + * The link will be automatically removed once the client device's driver is + * unbound. + * + * Return: Returns zero on success, %-ENXIO if the SAN interface has not been + * set up yet, and %-ENOMEM if device link creation failed. + */ +int san_client_link(struct device *client) +{ + const u32 flags = DL_FLAG_PM_RUNTIME | DL_FLAG_AUTOREMOVE_CONSUMER; + struct device_link *link; + + down_read(&san_rqsg_if.lock); + + if (!san_rqsg_if.dev) { + up_read(&san_rqsg_if.lock); + return -ENXIO; + } + + link = device_link_add(client, san_rqsg_if.dev, flags); + if (!link) { + up_read(&san_rqsg_if.lock); + return -ENOMEM; + } + + if (READ_ONCE(link->status) == DL_STATE_SUPPLIER_UNBIND) { + up_read(&san_rqsg_if.lock); + return -ENXIO; + } + + up_read(&san_rqsg_if.lock); + return 0; +} +EXPORT_SYMBOL_GPL(san_client_link); + +/** + * san_dgpu_notifier_register() - Register a SAN dGPU notifier. + * @nb: The notifier-block to register. + * + * Registers a SAN dGPU notifier, receiving any new SAN dGPU events sent from + * ACPI. The registered notifier will be called with &struct san_dgpu_event + * as notifier data and the command ID of that event as notifier action. + */ +int san_dgpu_notifier_register(struct notifier_block *nb) +{ + return blocking_notifier_chain_register(&san_rqsg_if.nh, nb); +} +EXPORT_SYMBOL_GPL(san_dgpu_notifier_register); + +/** + * san_dgpu_notifier_unregister() - Unregister a SAN dGPU notifier. + * @nb: The notifier-block to unregister. + */ +int san_dgpu_notifier_unregister(struct notifier_block *nb) +{ + return blocking_notifier_chain_unregister(&san_rqsg_if.nh, nb); +} +EXPORT_SYMBOL_GPL(san_dgpu_notifier_unregister); + +static int san_dgpu_notifier_call(struct san_dgpu_event *evt) +{ + int ret; + + ret = blocking_notifier_call_chain(&san_rqsg_if.nh, evt->command, evt); + return notifier_to_errno(ret); +} + + +/* -- ACPI _DSM event relay. ------------------------------------------------ */ + +#define SAN_DSM_REVISION 0 + +/* 93b666c5-70c6-469f-a215-3d487c91ab3c */ +static const guid_t SAN_DSM_UUID = + GUID_INIT(0x93b666c5, 0x70c6, 0x469f, 0xa2, 0x15, 0x3d, + 0x48, 0x7c, 0x91, 0xab, 0x3c); + +enum san_dsm_event_fn { + SAN_DSM_EVENT_FN_BAT1_STAT = 0x03, + SAN_DSM_EVENT_FN_BAT1_INFO = 0x04, + SAN_DSM_EVENT_FN_ADP1_STAT = 0x05, + SAN_DSM_EVENT_FN_ADP1_INFO = 0x06, + SAN_DSM_EVENT_FN_BAT2_STAT = 0x07, + SAN_DSM_EVENT_FN_BAT2_INFO = 0x08, + SAN_DSM_EVENT_FN_THERMAL = 0x09, + SAN_DSM_EVENT_FN_DPTF = 0x0a, +}; + +enum sam_event_cid_bat { + SAM_EVENT_CID_BAT_BIX = 0x15, + SAM_EVENT_CID_BAT_BST = 0x16, + SAM_EVENT_CID_BAT_ADP = 0x17, + SAM_EVENT_CID_BAT_PROT = 0x18, + SAM_EVENT_CID_BAT_DPTF = 0x4f, +}; + +enum sam_event_cid_tmp { + SAM_EVENT_CID_TMP_TRIP = 0x0b, +}; + +struct san_event_work { + struct delayed_work work; + struct device *dev; + struct ssam_event event; /* must be last */ +}; + +static int san_acpi_notify_event(struct device *dev, u64 func, + union acpi_object *param) +{ + acpi_handle san = ACPI_HANDLE(dev); + union acpi_object *obj; + int status = 0; + + if (!acpi_check_dsm(san, &SAN_DSM_UUID, SAN_DSM_REVISION, 1 << func)) + return 0; + + dev_dbg(dev, "notify event %#04llx\n", func); + + obj = acpi_evaluate_dsm_typed(san, &SAN_DSM_UUID, SAN_DSM_REVISION, + func, param, ACPI_TYPE_BUFFER); + if (!obj) + return -EFAULT; + + if (obj->buffer.length != 1 || obj->buffer.pointer[0] != 0) { + dev_err(dev, "got unexpected result from _DSM\n"); + status = -EPROTO; + } + + ACPI_FREE(obj); + return status; +} + +static int san_evt_bat_adp(struct device *dev, const struct ssam_event *event) +{ + int status; + + status = san_acpi_notify_event(dev, SAN_DSM_EVENT_FN_ADP1_STAT, NULL); + if (status) + return status; + + /* + * Ensure that the battery states get updated correctly. When the + * battery is fully charged and an adapter is plugged in, it sometimes + * is not updated correctly, instead showing it as charging. + * Explicitly trigger battery updates to fix this. + */ + + status = san_acpi_notify_event(dev, SAN_DSM_EVENT_FN_BAT1_STAT, NULL); + if (status) + return status; + + return san_acpi_notify_event(dev, SAN_DSM_EVENT_FN_BAT2_STAT, NULL); +} + +static int san_evt_bat_bix(struct device *dev, const struct ssam_event *event) +{ + enum san_dsm_event_fn fn; + + if (event->instance_id == 0x02) + fn = SAN_DSM_EVENT_FN_BAT2_INFO; + else + fn = SAN_DSM_EVENT_FN_BAT1_INFO; + + return san_acpi_notify_event(dev, fn, NULL); +} + +static int san_evt_bat_bst(struct device *dev, const struct ssam_event *event) +{ + enum san_dsm_event_fn fn; + + if (event->instance_id == 0x02) + fn = SAN_DSM_EVENT_FN_BAT2_STAT; + else + fn = SAN_DSM_EVENT_FN_BAT1_STAT; + + return san_acpi_notify_event(dev, fn, NULL); +} + +static int san_evt_bat_dptf(struct device *dev, const struct ssam_event *event) +{ + union acpi_object payload; + + /* + * The Surface ACPI expects a buffer and not a package. It specifically + * checks for ObjectType (Arg3) == 0x03. This will cause a warning in + * acpica/nsarguments.c, but that warning can be safely ignored. + */ + payload.type = ACPI_TYPE_BUFFER; + payload.buffer.length = event->length; + payload.buffer.pointer = (u8 *)&event->data[0]; + + return san_acpi_notify_event(dev, SAN_DSM_EVENT_FN_DPTF, &payload); +} + +static unsigned long san_evt_bat_delay(u8 cid) +{ + switch (cid) { + case SAM_EVENT_CID_BAT_ADP: + /* + * Wait for battery state to update before signaling adapter + * change. + */ + return msecs_to_jiffies(5000); + + case SAM_EVENT_CID_BAT_BST: + /* Ensure we do not miss anything important due to caching. */ + return msecs_to_jiffies(2000); + + default: + return 0; + } +} + +static bool san_evt_bat(const struct ssam_event *event, struct device *dev) +{ + int status; + + switch (event->command_id) { + case SAM_EVENT_CID_BAT_BIX: + status = san_evt_bat_bix(dev, event); + break; + + case SAM_EVENT_CID_BAT_BST: + status = san_evt_bat_bst(dev, event); + break; + + case SAM_EVENT_CID_BAT_ADP: + status = san_evt_bat_adp(dev, event); + break; + + case SAM_EVENT_CID_BAT_PROT: + /* + * TODO: Implement support for battery protection status change + * event. + */ + return true; + + case SAM_EVENT_CID_BAT_DPTF: + status = san_evt_bat_dptf(dev, event); + break; + + default: + return false; + } + + if (status) { + dev_err(dev, "error handling power event (cid = %#04x)\n", + event->command_id); + } + + return true; +} + +static void san_evt_bat_workfn(struct work_struct *work) +{ + struct san_event_work *ev; + + ev = container_of(work, struct san_event_work, work.work); + san_evt_bat(&ev->event, ev->dev); + kfree(ev); +} + +static u32 san_evt_bat_nf(struct ssam_event_notifier *nf, + const struct ssam_event *event) +{ + struct san_data *d = to_san_data(nf, nf_bat); + struct san_event_work *work; + unsigned long delay = san_evt_bat_delay(event->command_id); + + if (delay == 0) + return san_evt_bat(event, d->dev) ? SSAM_NOTIF_HANDLED : 0; + + work = kzalloc(sizeof(*work) + event->length, GFP_KERNEL); + if (!work) + return ssam_notifier_from_errno(-ENOMEM); + + INIT_DELAYED_WORK(&work->work, san_evt_bat_workfn); + work->dev = d->dev; + + memcpy(&work->event, event, sizeof(struct ssam_event) + event->length); + + schedule_delayed_work(&work->work, delay); + return SSAM_NOTIF_HANDLED; +} + +static int san_evt_tmp_trip(struct device *dev, const struct ssam_event *event) +{ + union acpi_object param; + + /* + * The Surface ACPI expects an integer and not a package. This will + * cause a warning in acpica/nsarguments.c, but that warning can be + * safely ignored. + */ + param.type = ACPI_TYPE_INTEGER; + param.integer.value = event->instance_id; + + return san_acpi_notify_event(dev, SAN_DSM_EVENT_FN_THERMAL, ¶m); +} + +static bool san_evt_tmp(const struct ssam_event *event, struct device *dev) +{ + int status; + + switch (event->command_id) { + case SAM_EVENT_CID_TMP_TRIP: + status = san_evt_tmp_trip(dev, event); + break; + + default: + return false; + } + + if (status) { + dev_err(dev, "error handling thermal event (cid = %#04x)\n", + event->command_id); + } + + return true; +} + +static u32 san_evt_tmp_nf(struct ssam_event_notifier *nf, + const struct ssam_event *event) +{ + struct san_data *d = to_san_data(nf, nf_tmp); + + return san_evt_tmp(event, d->dev) ? SSAM_NOTIF_HANDLED : 0; +} + + +/* -- ACPI GSB OperationRegion handler -------------------------------------- */ + +struct gsb_data_in { + u8 cv; +} __packed; + +struct gsb_data_rqsx { + u8 cv; /* Command value (san_gsb_request_cv). */ + u8 tc; /* Target category. */ + u8 tid; /* Target ID. */ + u8 iid; /* Instance ID. */ + u8 snc; /* Expect-response-flag. */ + u8 cid; /* Command ID. */ + u16 cdl; /* Payload length. */ + u8 pld[]; /* Payload. */ +} __packed; + +struct gsb_data_etwl { + u8 cv; /* Command value (should be 0x02). */ + u8 etw3; /* Unknown. */ + u8 etw4; /* Unknown. */ + u8 msg[]; /* Error message (ASCIIZ). */ +} __packed; + +struct gsb_data_out { + u8 status; /* _SSH communication status. */ + u8 len; /* _SSH payload length. */ + u8 pld[]; /* _SSH payload. */ +} __packed; + +union gsb_buffer_data { + struct gsb_data_in in; /* Common input. */ + struct gsb_data_rqsx rqsx; /* RQSX input. */ + struct gsb_data_etwl etwl; /* ETWL input. */ + struct gsb_data_out out; /* Output. */ +}; + +struct gsb_buffer { + u8 status; /* GSB AttribRawProcess status. */ + u8 len; /* GSB AttribRawProcess length. */ + union gsb_buffer_data data; +} __packed; + +#define SAN_GSB_MAX_RQSX_PAYLOAD (U8_MAX - 2 - sizeof(struct gsb_data_rqsx)) +#define SAN_GSB_MAX_RESPONSE (U8_MAX - 2 - sizeof(struct gsb_data_out)) + +#define SAN_GSB_COMMAND 0 + +enum san_gsb_request_cv { + SAN_GSB_REQUEST_CV_RQST = 0x01, + SAN_GSB_REQUEST_CV_ETWL = 0x02, + SAN_GSB_REQUEST_CV_RQSG = 0x03, +}; + +#define SAN_REQUEST_NUM_TRIES 5 + +static acpi_status san_etwl(struct san_data *d, struct gsb_buffer *b) +{ + struct gsb_data_etwl *etwl = &b->data.etwl; + + if (b->len < sizeof(struct gsb_data_etwl)) { + dev_err(d->dev, "invalid ETWL package (len = %d)\n", b->len); + return AE_OK; + } + + dev_err(d->dev, "ETWL(%#04x, %#04x): %.*s\n", etwl->etw3, etwl->etw4, + (unsigned int)(b->len - sizeof(struct gsb_data_etwl)), + (char *)etwl->msg); + + /* Indicate success. */ + b->status = 0x00; + b->len = 0x00; + + return AE_OK; +} + +static +struct gsb_data_rqsx *san_validate_rqsx(struct device *dev, const char *type, + struct gsb_buffer *b) +{ + struct gsb_data_rqsx *rqsx = &b->data.rqsx; + + if (b->len < sizeof(struct gsb_data_rqsx)) { + dev_err(dev, "invalid %s package (len = %d)\n", type, b->len); + return NULL; + } + + if (get_unaligned(&rqsx->cdl) != b->len - sizeof(struct gsb_data_rqsx)) { + dev_err(dev, "bogus %s package (len = %d, cdl = %d)\n", + type, b->len, get_unaligned(&rqsx->cdl)); + return NULL; + } + + if (get_unaligned(&rqsx->cdl) > SAN_GSB_MAX_RQSX_PAYLOAD) { + dev_err(dev, "payload for %s package too large (cdl = %d)\n", + type, get_unaligned(&rqsx->cdl)); + return NULL; + } + + return rqsx; +} + +static void gsb_rqsx_response_error(struct gsb_buffer *gsb, int status) +{ + gsb->status = 0x00; + gsb->len = 0x02; + gsb->data.out.status = (u8)(-status); + gsb->data.out.len = 0x00; +} + +static void gsb_rqsx_response_success(struct gsb_buffer *gsb, u8 *ptr, size_t len) +{ + gsb->status = 0x00; + gsb->len = len + 2; + gsb->data.out.status = 0x00; + gsb->data.out.len = len; + + if (len) + memcpy(&gsb->data.out.pld[0], ptr, len); +} + +static acpi_status san_rqst_fixup_suspended(struct san_data *d, + struct ssam_request *rqst, + struct gsb_buffer *gsb) +{ + if (rqst->target_category == SSAM_SSH_TC_BAS && rqst->command_id == 0x0D) { + u8 base_state = 1; + + /* Base state quirk: + * The base state may be queried from ACPI when the EC is still + * suspended. In this case it will return '-EPERM'. This query + * will only be triggered from the ACPI lid GPE interrupt, thus + * we are either in laptop or studio mode (base status 0x01 or + * 0x02). Furthermore, we will only get here if the device (and + * EC) have been suspended. + * + * We now assume that the device is in laptop mode (0x01). This + * has the drawback that it will wake the device when unfolding + * it in studio mode, but it also allows us to avoid actively + * waiting for the EC to wake up, which may incur a notable + * delay. + */ + + dev_dbg(d->dev, "rqst: fixup: base-state quirk\n"); + + gsb_rqsx_response_success(gsb, &base_state, sizeof(base_state)); + return AE_OK; + } + + gsb_rqsx_response_error(gsb, -ENXIO); + return AE_OK; +} + +static acpi_status san_rqst(struct san_data *d, struct gsb_buffer *buffer) +{ + u8 rspbuf[SAN_GSB_MAX_RESPONSE]; + struct gsb_data_rqsx *gsb_rqst; + struct ssam_request rqst; + struct ssam_response rsp; + int status = 0; + + gsb_rqst = san_validate_rqsx(d->dev, "RQST", buffer); + if (!gsb_rqst) + return AE_OK; + + rqst.target_category = gsb_rqst->tc; + rqst.target_id = gsb_rqst->tid; + rqst.command_id = gsb_rqst->cid; + rqst.instance_id = gsb_rqst->iid; + rqst.flags = gsb_rqst->snc ? SSAM_REQUEST_HAS_RESPONSE : 0; + rqst.length = get_unaligned(&gsb_rqst->cdl); + rqst.payload = &gsb_rqst->pld[0]; + + rsp.capacity = ARRAY_SIZE(rspbuf); + rsp.length = 0; + rsp.pointer = &rspbuf[0]; + + /* Handle suspended device. */ + if (d->dev->power.is_suspended) { + dev_warn(d->dev, "rqst: device is suspended, not executing\n"); + return san_rqst_fixup_suspended(d, &rqst, buffer); + } + + status = __ssam_retry(ssam_request_sync_onstack, SAN_REQUEST_NUM_TRIES, + d->ctrl, &rqst, &rsp, SAN_GSB_MAX_RQSX_PAYLOAD); + + if (!status) { + gsb_rqsx_response_success(buffer, rsp.pointer, rsp.length); + } else { + dev_err(d->dev, "rqst: failed with error %d\n", status); + gsb_rqsx_response_error(buffer, status); + } + + return AE_OK; +} + +static acpi_status san_rqsg(struct san_data *d, struct gsb_buffer *buffer) +{ + struct gsb_data_rqsx *gsb_rqsg; + struct san_dgpu_event evt; + int status; + + gsb_rqsg = san_validate_rqsx(d->dev, "RQSG", buffer); + if (!gsb_rqsg) + return AE_OK; + + evt.category = gsb_rqsg->tc; + evt.target = gsb_rqsg->tid; + evt.command = gsb_rqsg->cid; + evt.instance = gsb_rqsg->iid; + evt.length = get_unaligned(&gsb_rqsg->cdl); + evt.payload = &gsb_rqsg->pld[0]; + + status = san_dgpu_notifier_call(&evt); + if (!status) { + gsb_rqsx_response_success(buffer, NULL, 0); + } else { + dev_err(d->dev, "rqsg: failed with error %d\n", status); + gsb_rqsx_response_error(buffer, status); + } + + return AE_OK; +} + +static acpi_status san_opreg_handler(u32 function, acpi_physical_address command, + u32 bits, u64 *value64, void *opreg_context, + void *region_context) +{ + struct san_data *d = to_san_data(opreg_context, info); + struct gsb_buffer *buffer = (struct gsb_buffer *)value64; + int accessor_type = (function & 0xFFFF0000) >> 16; + + if (command != SAN_GSB_COMMAND) { + dev_warn(d->dev, "unsupported command: %#04llx\n", command); + return AE_OK; + } + + if (accessor_type != ACPI_GSB_ACCESS_ATTRIB_RAW_PROCESS) { + dev_err(d->dev, "invalid access type: %#04x\n", accessor_type); + return AE_OK; + } + + /* Buffer must have at least contain the command-value. */ + if (buffer->len == 0) { + dev_err(d->dev, "request-package too small\n"); + return AE_OK; + } + + switch (buffer->data.in.cv) { + case SAN_GSB_REQUEST_CV_RQST: + return san_rqst(d, buffer); + + case SAN_GSB_REQUEST_CV_ETWL: + return san_etwl(d, buffer); + + case SAN_GSB_REQUEST_CV_RQSG: + return san_rqsg(d, buffer); + + default: + dev_warn(d->dev, "unsupported SAN0 request (cv: %#04x)\n", + buffer->data.in.cv); + return AE_OK; + } +} + + +/* -- Driver setup. --------------------------------------------------------- */ + +static int san_events_register(struct platform_device *pdev) +{ + struct san_data *d = platform_get_drvdata(pdev); + int status; + + d->nf_bat.base.priority = 1; + d->nf_bat.base.fn = san_evt_bat_nf; + d->nf_bat.event.reg = SSAM_EVENT_REGISTRY_SAM; + d->nf_bat.event.id.target_category = SSAM_SSH_TC_BAT; + d->nf_bat.event.id.instance = 0; + d->nf_bat.event.mask = SSAM_EVENT_MASK_TARGET; + d->nf_bat.event.flags = SSAM_EVENT_SEQUENCED; + + d->nf_tmp.base.priority = 1; + d->nf_tmp.base.fn = san_evt_tmp_nf; + d->nf_tmp.event.reg = SSAM_EVENT_REGISTRY_SAM; + d->nf_tmp.event.id.target_category = SSAM_SSH_TC_TMP; + d->nf_tmp.event.id.instance = 0; + d->nf_tmp.event.mask = SSAM_EVENT_MASK_TARGET; + d->nf_tmp.event.flags = SSAM_EVENT_SEQUENCED; + + status = ssam_notifier_register(d->ctrl, &d->nf_bat); + if (status) + return status; + + status = ssam_notifier_register(d->ctrl, &d->nf_tmp); + if (status) + ssam_notifier_unregister(d->ctrl, &d->nf_bat); + + return status; +} + +static void san_events_unregister(struct platform_device *pdev) +{ + struct san_data *d = platform_get_drvdata(pdev); + + ssam_notifier_unregister(d->ctrl, &d->nf_bat); + ssam_notifier_unregister(d->ctrl, &d->nf_tmp); +} + +#define san_consumer_printk(level, dev, handle, fmt, ...) \ +do { \ + char *path = ""; \ + struct acpi_buffer buffer = { \ + .length = ACPI_ALLOCATE_BUFFER, \ + .pointer = NULL, \ + }; \ + \ + if (ACPI_SUCCESS(acpi_get_name(handle, ACPI_FULL_PATHNAME, &buffer))) \ + path = buffer.pointer; \ + \ + dev_##level(dev, "[%s]: " fmt, path, ##__VA_ARGS__); \ + kfree(buffer.pointer); \ +} while (0) + +#define san_consumer_dbg(dev, handle, fmt, ...) \ + san_consumer_printk(dbg, dev, handle, fmt, ##__VA_ARGS__) + +#define san_consumer_warn(dev, handle, fmt, ...) \ + san_consumer_printk(warn, dev, handle, fmt, ##__VA_ARGS__) + +static bool is_san_consumer(struct platform_device *pdev, acpi_handle handle) +{ + struct acpi_handle_list dep_devices; + acpi_handle supplier = ACPI_HANDLE(&pdev->dev); + acpi_status status; + int i; + + if (!acpi_has_method(handle, "_DEP")) + return false; + + status = acpi_evaluate_reference(handle, "_DEP", NULL, &dep_devices); + if (ACPI_FAILURE(status)) { + san_consumer_dbg(&pdev->dev, handle, "failed to evaluate _DEP\n"); + return false; + } + + for (i = 0; i < dep_devices.count; i++) { + if (dep_devices.handles[i] == supplier) + return true; + } + + return false; +} + +static acpi_status san_consumer_setup(acpi_handle handle, u32 lvl, + void *context, void **rv) +{ + const u32 flags = DL_FLAG_PM_RUNTIME | DL_FLAG_AUTOREMOVE_SUPPLIER; + struct platform_device *pdev = context; + struct acpi_device *adev; + struct device_link *link; + + if (!is_san_consumer(pdev, handle)) + return AE_OK; + + /* Ignore ACPI devices that are not present. */ + if (acpi_bus_get_device(handle, &adev) != 0) + return AE_OK; + + san_consumer_dbg(&pdev->dev, handle, "creating device link\n"); + + /* Try to set up device links, ignore but log errors. */ + link = device_link_add(&adev->dev, &pdev->dev, flags); + if (!link) { + san_consumer_warn(&pdev->dev, handle, "failed to create device link\n"); + return AE_OK; + } + + return AE_OK; +} + +static int san_consumer_links_setup(struct platform_device *pdev) +{ + acpi_status status; + + status = acpi_walk_namespace(ACPI_TYPE_DEVICE, ACPI_ROOT_OBJECT, + ACPI_UINT32_MAX, san_consumer_setup, NULL, + pdev, NULL); + + return status ? -EFAULT : 0; +} + +static int san_probe(struct platform_device *pdev) +{ + acpi_handle san = ACPI_HANDLE(&pdev->dev); + struct ssam_controller *ctrl; + struct san_data *data; + acpi_status astatus; + int status; + + ctrl = ssam_client_bind(&pdev->dev); + if (IS_ERR(ctrl)) + return PTR_ERR(ctrl) == -ENODEV ? -EPROBE_DEFER : PTR_ERR(ctrl); + + status = san_consumer_links_setup(pdev); + if (status) + return status; + + data = devm_kzalloc(&pdev->dev, sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + data->dev = &pdev->dev; + data->ctrl = ctrl; + + platform_set_drvdata(pdev, data); + + astatus = acpi_install_address_space_handler(san, ACPI_ADR_SPACE_GSBUS, + &san_opreg_handler, NULL, + &data->info); + if (ACPI_FAILURE(astatus)) + return -ENXIO; + + status = san_events_register(pdev); + if (status) + goto err_enable_events; + + status = san_set_rqsg_interface_device(&pdev->dev); + if (status) + goto err_install_dev; + + acpi_walk_dep_device_list(san); + return 0; + +err_install_dev: + san_events_unregister(pdev); +err_enable_events: + acpi_remove_address_space_handler(san, ACPI_ADR_SPACE_GSBUS, + &san_opreg_handler); + return status; +} + +static int san_remove(struct platform_device *pdev) +{ + acpi_handle san = ACPI_HANDLE(&pdev->dev); + + san_set_rqsg_interface_device(NULL); + acpi_remove_address_space_handler(san, ACPI_ADR_SPACE_GSBUS, + &san_opreg_handler); + san_events_unregister(pdev); + + /* + * We have unregistered our event sources. Now we need to ensure that + * all delayed works they may have spawned are run to completion. + */ + flush_scheduled_work(); + + return 0; +} + +static const struct acpi_device_id san_match[] = { + { "MSHW0091" }, + { }, +}; +MODULE_DEVICE_TABLE(acpi, san_match); + +static struct platform_driver surface_acpi_notify = { + .probe = san_probe, + .remove = san_remove, + .driver = { + .name = "surface_acpi_notify", + .acpi_match_table = san_match, + .probe_type = PROBE_PREFER_ASYNCHRONOUS, + }, +}; +module_platform_driver(surface_acpi_notify); + +MODULE_AUTHOR("Maximilian Luz "); +MODULE_DESCRIPTION("Surface ACPI Notify driver for Surface System Aggregator Module"); +MODULE_LICENSE("GPL"); diff --git a/include/linux/surface_acpi_notify.h b/include/linux/surface_acpi_notify.h new file mode 100644 index 000000000000..8e3e86c7d78c --- /dev/null +++ b/include/linux/surface_acpi_notify.h @@ -0,0 +1,39 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Interface for Surface ACPI Notify (SAN) driver. + * + * Provides access to discrete GPU notifications sent from ACPI via the SAN + * driver, which are not handled by this driver directly. + * + * Copyright (C) 2019-2020 Maximilian Luz + */ + +#ifndef _LINUX_SURFACE_ACPI_NOTIFY_H +#define _LINUX_SURFACE_ACPI_NOTIFY_H + +#include +#include + +/** + * struct san_dgpu_event - Discrete GPU ACPI event. + * @category: Category of the event. + * @target: Target ID of the event source. + * @command: Command ID of the event. + * @instance: Instance ID of the event source. + * @length: Length of the event's payload data (in bytes). + * @payload: Pointer to the event's payload data. + */ +struct san_dgpu_event { + u8 category; + u8 target; + u8 command; + u8 instance; + u16 length; + u8 *payload; +}; + +int san_client_link(struct device *client); +int san_dgpu_notifier_register(struct notifier_block *nb); +int san_dgpu_notifier_unregister(struct notifier_block *nb); + +#endif /* _LINUX_SURFACE_ACPI_NOTIFY_H */ -- cgit v1.2.3 From 9326eecd9365a5b82220a4011592f7c0209566fc Mon Sep 17 00:00:00 2001 From: Xu Yilun Date: Wed, 6 Jan 2021 20:37:10 -0800 Subject: fpga: dfl: move dfl_device_id to mod_devicetable.h In order to support MODULE_DEVICE_TABLE() for dfl device driver, this patch moves struct dfl_device_id to mod_devicetable.h Some brief description for DFL (Device Feature List) is added to make the DFL known to the whole kernel. Reviewed-by: Tom Rix Acked-by: Wu Hao Signed-off-by: Xu Yilun Signed-off-by: Wu Hao Signed-off-by: Matthew Gerlach Signed-off-by: Russ Weight Signed-off-by: Moritz Fischer Link: https://lore.kernel.org/r/20210107043714.991646-5-mdf@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/fpga/dfl.h | 13 +------------ include/linux/mod_devicetable.h | 24 ++++++++++++++++++++++++ 2 files changed, 25 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/drivers/fpga/dfl.h b/drivers/fpga/dfl.h index ac373b1fcff9..549c7900dcfd 100644 --- a/drivers/fpga/dfl.h +++ b/drivers/fpga/dfl.h @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include @@ -525,18 +526,6 @@ enum dfl_id_type { DFL_ID_MAX, }; -/** - * struct dfl_device_id - dfl device identifier - * @type: DFL FIU type of the device. See enum dfl_id_type. - * @feature_id: feature identifier local to its DFL FIU type. - * @driver_data: driver specific data. - */ -struct dfl_device_id { - u16 type; - u16 feature_id; - unsigned long driver_data; -}; - /** * struct dfl_device - represent an dfl device on dfl bus * diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index c425290b21e2..b8dae34eca10 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -846,4 +846,28 @@ struct auxiliary_device_id { kernel_ulong_t driver_data; }; +/* + * DFL (Device Feature List) + * + * DFL defines a linked list of feature headers within the device MMIO space to + * provide an extensible way of adding features. Software can walk through these + * predefined data structures to enumerate features. It is now used in the FPGA. + * See Documentation/fpga/dfl.rst for more information. + * + * The dfl bus type is introduced to match the individual feature devices (dfl + * devices) for specific dfl drivers. + */ + +/** + * struct dfl_device_id - dfl device identifier + * @type: DFL FIU type of the device. See enum dfl_id_type. + * @feature_id: feature identifier local to its DFL FIU type. + * @driver_data: driver specific data. + */ +struct dfl_device_id { + __u16 type; + __u16 feature_id; + kernel_ulong_t driver_data; +}; + #endif /* LINUX_MOD_DEVICETABLE_H */ -- cgit v1.2.3 From ecc1641aca658ed4140751748f84985ffb6cce28 Mon Sep 17 00:00:00 2001 From: Xu Yilun Date: Wed, 6 Jan 2021 20:37:12 -0800 Subject: fpga: dfl: move dfl bus related APIs to include/linux/dfl.h Now the dfl drivers could be made as independent modules and put in different folders according to their functionalities. In order for scattered dfl device drivers to include dfl bus APIs, move the dfl bus APIs to a new header file in the public folder. [mdf@kernel.org: Fixed up header guards to match filename] Reviewed-by: Tom Rix Acked-by: Wu Hao Signed-off-by: Xu Yilun Signed-off-by: Moritz Fischer Link: https://lore.kernel.org/r/20210107043714.991646-7-mdf@kernel.org Signed-off-by: Greg Kroah-Hartman --- MAINTAINERS | 1 + drivers/fpga/dfl.c | 1 + drivers/fpga/dfl.h | 72 -------------------------------------------- include/linux/dfl.h | 86 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 88 insertions(+), 72 deletions(-) create mode 100644 include/linux/dfl.h (limited to 'include') diff --git a/MAINTAINERS b/MAINTAINERS index 546aa66428c9..a044b58eb9ac 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6957,6 +6957,7 @@ S: Maintained F: Documentation/ABI/testing/sysfs-bus-dfl F: Documentation/fpga/dfl.rst F: drivers/fpga/dfl* +F: include/linux/dfl.h F: include/uapi/linux/fpga-dfl.h FPGA MANAGER FRAMEWORK diff --git a/drivers/fpga/dfl.c b/drivers/fpga/dfl.c index 5a6ba3b2fa05..511b20ff35a3 100644 --- a/drivers/fpga/dfl.c +++ b/drivers/fpga/dfl.c @@ -10,6 +10,7 @@ * Wu Hao * Xiao Guangrong */ +#include #include #include #include diff --git a/drivers/fpga/dfl.h b/drivers/fpga/dfl.h index 549c7900dcfd..2b82c96ba56c 100644 --- a/drivers/fpga/dfl.h +++ b/drivers/fpga/dfl.h @@ -517,76 +517,4 @@ long dfl_feature_ioctl_set_irq(struct platform_device *pdev, struct dfl_feature *feature, unsigned long arg); -/** - * enum dfl_id_type - define the DFL FIU types - */ -enum dfl_id_type { - FME_ID = 0, - PORT_ID = 1, - DFL_ID_MAX, -}; - -/** - * struct dfl_device - represent an dfl device on dfl bus - * - * @dev: generic device interface. - * @id: id of the dfl device. - * @type: type of DFL FIU of the device. See enum dfl_id_type. - * @feature_id: feature identifier local to its DFL FIU type. - * @mmio_res: mmio resource of this dfl device. - * @irqs: list of Linux IRQ numbers of this dfl device. - * @num_irqs: number of IRQs supported by this dfl device. - * @cdev: pointer to DFL FPGA container device this dfl device belongs to. - * @id_entry: matched id entry in dfl driver's id table. - */ -struct dfl_device { - struct device dev; - int id; - u16 type; - u16 feature_id; - struct resource mmio_res; - int *irqs; - unsigned int num_irqs; - struct dfl_fpga_cdev *cdev; - const struct dfl_device_id *id_entry; -}; - -/** - * struct dfl_driver - represent an dfl device driver - * - * @drv: driver model structure. - * @id_table: pointer to table of device IDs the driver is interested in. - * { } member terminated. - * @probe: mandatory callback for device binding. - * @remove: callback for device unbinding. - */ -struct dfl_driver { - struct device_driver drv; - const struct dfl_device_id *id_table; - - int (*probe)(struct dfl_device *dfl_dev); - void (*remove)(struct dfl_device *dfl_dev); -}; - -#define to_dfl_dev(d) container_of(d, struct dfl_device, dev) -#define to_dfl_drv(d) container_of(d, struct dfl_driver, drv) - -/* - * use a macro to avoid include chaining to get THIS_MODULE. - */ -#define dfl_driver_register(drv) \ - __dfl_driver_register(drv, THIS_MODULE) -int __dfl_driver_register(struct dfl_driver *dfl_drv, struct module *owner); -void dfl_driver_unregister(struct dfl_driver *dfl_drv); - -/* - * module_dfl_driver() - Helper macro for drivers that don't do - * anything special in module init/exit. This eliminates a lot of - * boilerplate. Each module may only use this macro once, and - * calling it replaces module_init() and module_exit(). - */ -#define module_dfl_driver(__dfl_driver) \ - module_driver(__dfl_driver, dfl_driver_register, \ - dfl_driver_unregister) - #endif /* __FPGA_DFL_H */ diff --git a/include/linux/dfl.h b/include/linux/dfl.h new file mode 100644 index 000000000000..6cc10982351a --- /dev/null +++ b/include/linux/dfl.h @@ -0,0 +1,86 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Header file for DFL driver and device API + * + * Copyright (C) 2020 Intel Corporation, Inc. + */ + +#ifndef __LINUX_DFL_H +#define __LINUX_DFL_H + +#include +#include + +/** + * enum dfl_id_type - define the DFL FIU types + */ +enum dfl_id_type { + FME_ID = 0, + PORT_ID = 1, + DFL_ID_MAX, +}; + +/** + * struct dfl_device - represent an dfl device on dfl bus + * + * @dev: generic device interface. + * @id: id of the dfl device. + * @type: type of DFL FIU of the device. See enum dfl_id_type. + * @feature_id: feature identifier local to its DFL FIU type. + * @mmio_res: mmio resource of this dfl device. + * @irqs: list of Linux IRQ numbers of this dfl device. + * @num_irqs: number of IRQs supported by this dfl device. + * @cdev: pointer to DFL FPGA container device this dfl device belongs to. + * @id_entry: matched id entry in dfl driver's id table. + */ +struct dfl_device { + struct device dev; + int id; + u16 type; + u16 feature_id; + struct resource mmio_res; + int *irqs; + unsigned int num_irqs; + struct dfl_fpga_cdev *cdev; + const struct dfl_device_id *id_entry; +}; + +/** + * struct dfl_driver - represent an dfl device driver + * + * @drv: driver model structure. + * @id_table: pointer to table of device IDs the driver is interested in. + * { } member terminated. + * @probe: mandatory callback for device binding. + * @remove: callback for device unbinding. + */ +struct dfl_driver { + struct device_driver drv; + const struct dfl_device_id *id_table; + + int (*probe)(struct dfl_device *dfl_dev); + void (*remove)(struct dfl_device *dfl_dev); +}; + +#define to_dfl_dev(d) container_of(d, struct dfl_device, dev) +#define to_dfl_drv(d) container_of(d, struct dfl_driver, drv) + +/* + * use a macro to avoid include chaining to get THIS_MODULE. + */ +#define dfl_driver_register(drv) \ + __dfl_driver_register(drv, THIS_MODULE) +int __dfl_driver_register(struct dfl_driver *dfl_drv, struct module *owner); +void dfl_driver_unregister(struct dfl_driver *dfl_drv); + +/* + * module_dfl_driver() - Helper macro for drivers that don't do + * anything special in module init/exit. This eliminates a lot of + * boilerplate. Each module may only use this macro once, and + * calling it replaces module_init() and module_exit(). + */ +#define module_dfl_driver(__dfl_driver) \ + module_driver(__dfl_driver, dfl_driver_register, \ + dfl_driver_unregister) + +#endif /* __LINUX_DFL_H */ -- cgit v1.2.3 From 04f111130e9afa41c10d7bcec14e00e3be8b6977 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Thu, 10 Dec 2020 13:15:14 +0100 Subject: thermal/core: Remove notify ops With the removal of the notifys user in a previous patches, the ops is no longer needed, remove it. Signed-off-by: Daniel Lezcano Reviewed-by: Lukasz Luba Link: https://lore.kernel.org/r/20201210121514.25760-5-daniel.lezcano@linaro.org --- drivers/thermal/thermal_core.c | 3 --- include/linux/thermal.h | 2 -- 2 files changed, 5 deletions(-) (limited to 'include') diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index 4a291d205d5c..567bc6f254c0 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -412,9 +412,6 @@ static void handle_critical_trips(struct thermal_zone_device *tz, trace_thermal_zone_trip(tz, trip, trip_type); - if (tz->ops->notify) - tz->ops->notify(tz, trip, trip_type); - if (trip_type == THERMAL_TRIP_HOT && tz->ops->hot) tz->ops->hot(tz); else if (trip_type == THERMAL_TRIP_CRITICAL) diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 31b84404f047..c80032322158 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -77,8 +77,6 @@ struct thermal_zone_device_ops { int (*set_emul_temp) (struct thermal_zone_device *, int); int (*get_trend) (struct thermal_zone_device *, int, enum thermal_trend *); - int (*notify) (struct thermal_zone_device *, int, - enum thermal_trip_type); void (*hot)(struct thermal_zone_device *); void (*critical)(struct thermal_zone_device *); }; -- cgit v1.2.3 From 4b9bbb29baf6c948d24eaeff892815b8a403b64c Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Thu, 17 Dec 2020 19:17:00 -0800 Subject: driver core: Add device link support for INFERRED flag This flag can never be added to a device link that already exists and doesn't have the flag set. It can only be added when a device link is created for the first time or it can be maintained if the device link already has the it set. This flag will be used for marking device links created ONLY by inferring dependencies from data and NOT from explicit action by device drivers/frameworks. This will be useful in the future when we need to deal with cycles in dependencies inferred from firmware. Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20201218031703.3053753-3-saravanak@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 15 +++++++++++---- include/linux/device.h | 2 ++ 2 files changed, 13 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/base/core.c b/drivers/base/core.c index fe8601197b84..5827dbff7f21 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -229,7 +229,8 @@ int device_is_dependent(struct device *dev, void *target) return ret; list_for_each_entry(link, &dev->links.consumers, s_node) { - if (link->flags == (DL_FLAG_SYNC_STATE_ONLY | DL_FLAG_MANAGED)) + if ((link->flags & ~DL_FLAG_INFERRED) == + (DL_FLAG_SYNC_STATE_ONLY | DL_FLAG_MANAGED)) continue; if (link->consumer == target) @@ -302,7 +303,8 @@ static int device_reorder_to_tail(struct device *dev, void *not_used) device_for_each_child(dev, NULL, device_reorder_to_tail); list_for_each_entry(link, &dev->links.consumers, s_node) { - if (link->flags == (DL_FLAG_SYNC_STATE_ONLY | DL_FLAG_MANAGED)) + if ((link->flags & ~DL_FLAG_INFERRED) == + (DL_FLAG_SYNC_STATE_ONLY | DL_FLAG_MANAGED)) continue; device_reorder_to_tail(link->consumer, NULL); } @@ -546,7 +548,8 @@ postcore_initcall(devlink_class_init); #define DL_MANAGED_LINK_FLAGS (DL_FLAG_AUTOREMOVE_CONSUMER | \ DL_FLAG_AUTOREMOVE_SUPPLIER | \ DL_FLAG_AUTOPROBE_CONSUMER | \ - DL_FLAG_SYNC_STATE_ONLY) + DL_FLAG_SYNC_STATE_ONLY | \ + DL_FLAG_INFERRED) #define DL_ADD_VALID_FLAGS (DL_MANAGED_LINK_FLAGS | DL_FLAG_STATELESS | \ DL_FLAG_PM_RUNTIME | DL_FLAG_RPM_ACTIVE) @@ -615,7 +618,7 @@ struct device_link *device_link_add(struct device *consumer, if (!consumer || !supplier || flags & ~DL_ADD_VALID_FLAGS || (flags & DL_FLAG_STATELESS && flags & DL_MANAGED_LINK_FLAGS) || (flags & DL_FLAG_SYNC_STATE_ONLY && - flags != DL_FLAG_SYNC_STATE_ONLY) || + (flags & ~DL_FLAG_INFERRED) != DL_FLAG_SYNC_STATE_ONLY) || (flags & DL_FLAG_AUTOPROBE_CONSUMER && flags & (DL_FLAG_AUTOREMOVE_CONSUMER | DL_FLAG_AUTOREMOVE_SUPPLIER))) @@ -671,6 +674,10 @@ struct device_link *device_link_add(struct device *consumer, if (link->consumer != consumer) continue; + if (link->flags & DL_FLAG_INFERRED && + !(flags & DL_FLAG_INFERRED)) + link->flags &= ~DL_FLAG_INFERRED; + if (flags & DL_FLAG_PM_RUNTIME) { if (!(link->flags & DL_FLAG_PM_RUNTIME)) { pm_runtime_new_link(consumer); diff --git a/include/linux/device.h b/include/linux/device.h index 89bb8b84173e..cb5eb2e58c25 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -323,6 +323,7 @@ enum device_link_state { * AUTOPROBE_CONSUMER: Probe consumer driver automatically after supplier binds. * MANAGED: The core tracks presence of supplier/consumer drivers (internal). * SYNC_STATE_ONLY: Link only affects sync_state() behavior. + * INFERRED: Inferred from data (eg: firmware) and not from driver actions. */ #define DL_FLAG_STATELESS BIT(0) #define DL_FLAG_AUTOREMOVE_CONSUMER BIT(1) @@ -332,6 +333,7 @@ enum device_link_state { #define DL_FLAG_AUTOPROBE_CONSUMER BIT(5) #define DL_FLAG_MANAGED BIT(6) #define DL_FLAG_SYNC_STATE_ONLY BIT(7) +#define DL_FLAG_INFERRED BIT(8) /** * enum dl_dev_state - Device driver presence tracking information. -- cgit v1.2.3 From c7c730ac6a88abbbc961f8838d28da85662389d0 Mon Sep 17 00:00:00 2001 From: Bean Huo Date: Tue, 5 Jan 2021 12:34:41 +0100 Subject: scsi: ufs: Remove stringize operator '#' restriction Current EM macro definition, we use stringize operator '#', which turns the argument it precedes into a quoted string. Thus requires the symbol of __print_symbolic() should be the string corresponding to the name of the enum. However, we have other cases, the symbol and enum name are not the same, we can redefine EM/EMe, but there will introduce some redundant codes. This patch is to remove this restriction, let others reuse the current EM/EMe definition. Link: https://lore.kernel.org/r/20210105113446.16027-2-huobean@gmail.com Acked-by: Steven Rostedt (VMware) Signed-off-by: Bean Huo Signed-off-by: Martin K. Petersen --- include/trace/events/ufs.h | 40 ++++++++++++++++++++-------------------- 1 file changed, 20 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/include/trace/events/ufs.h b/include/trace/events/ufs.h index 0bd54a184391..fa755394bc0f 100644 --- a/include/trace/events/ufs.h +++ b/include/trace/events/ufs.h @@ -20,28 +20,28 @@ { SYNCHRONIZE_CACHE, "SYNC" }, \ { UNMAP, "UNMAP" }) -#define UFS_LINK_STATES \ - EM(UIC_LINK_OFF_STATE) \ - EM(UIC_LINK_ACTIVE_STATE) \ - EMe(UIC_LINK_HIBERN8_STATE) - -#define UFS_PWR_MODES \ - EM(UFS_ACTIVE_PWR_MODE) \ - EM(UFS_SLEEP_PWR_MODE) \ - EM(UFS_POWERDOWN_PWR_MODE) \ - EMe(UFS_DEEPSLEEP_PWR_MODE) - -#define UFSCHD_CLK_GATING_STATES \ - EM(CLKS_OFF) \ - EM(CLKS_ON) \ - EM(REQ_CLKS_OFF) \ - EMe(REQ_CLKS_ON) +#define UFS_LINK_STATES \ + EM(UIC_LINK_OFF_STATE, "UIC_LINK_OFF_STATE") \ + EM(UIC_LINK_ACTIVE_STATE, "UIC_LINK_ACTIVE_STATE") \ + EMe(UIC_LINK_HIBERN8_STATE, "UIC_LINK_HIBERN8_STATE") + +#define UFS_PWR_MODES \ + EM(UFS_ACTIVE_PWR_MODE, "UFS_ACTIVE_PWR_MODE") \ + EM(UFS_SLEEP_PWR_MODE, "UFS_SLEEP_PWR_MODE") \ + EM(UFS_POWERDOWN_PWR_MODE, "UFS_POWERDOWN_PWR_MODE") \ + EMe(UFS_DEEPSLEEP_PWR_MODE, "UFS_DEEPSLEEP_PWR_MODE") + +#define UFSCHD_CLK_GATING_STATES \ + EM(CLKS_OFF, "CLKS_OFF") \ + EM(CLKS_ON, "CLKS_ON") \ + EM(REQ_CLKS_OFF, "REQ_CLKS_OFF") \ + EMe(REQ_CLKS_ON, "REQ_CLKS_ON") /* Enums require being exported to userspace, for user tool parsing */ #undef EM #undef EMe -#define EM(a) TRACE_DEFINE_ENUM(a); -#define EMe(a) TRACE_DEFINE_ENUM(a); +#define EM(a, b) TRACE_DEFINE_ENUM(a); +#define EMe(a, b) TRACE_DEFINE_ENUM(a); UFS_LINK_STATES; UFS_PWR_MODES; @@ -53,8 +53,8 @@ UFSCHD_CLK_GATING_STATES; */ #undef EM #undef EMe -#define EM(a) { a, #a }, -#define EMe(a) { a, #a } +#define EM(a, b) {a, b}, +#define EMe(a, b) {a, b} TRACE_EVENT(ufshcd_clk_gating, -- cgit v1.2.3 From 28fa68fc557a7eba02615aa7d97a7cbcfa94559d Mon Sep 17 00:00:00 2001 From: Bean Huo Date: Tue, 5 Jan 2021 12:34:42 +0100 Subject: scsi: ufs: Use __print_symbolic() for UFS trace string print __print_symbolic() is designed for exporting the print formatting table to userspace and allows parsing tool, such as trace-cmd and perf, to analyze trace log according to this print formatting table, meanwhile, by using __print_symbolic()s, save space in the trace ring buffer. original print format: print fmt: "%s: %s: HDR:%s, CDB:%s", __get_str(str), __get_str(dev_name), __print_hex(REC->hdr, sizeof(REC->hdr)), __print_hex(REC->tsf, sizeof(REC->tsf)) after this change: print fmt: "%s: %s: HDR:%s, CDB:%s", print_symbolic(REC->str_t, {0, "send"}, {1, "complete"}, {2, "dev_complete"}, {3, "query_send"}, {4, "query_complete"}, {5, "query_complete_err"}, {6, "tm_send"}, {7, "tm_complete"}, {8, "tm_complete_err"}), __get_str(dev_name), __print_hex(REC->hdr, sizeof(REC->hdr)), __print_hex(REC->tsf, sizeof(REC->tsf)) Note: This patch just converts current __get_str(str) to __print_symbolic(), the original tracing log will not be affected by this change, so it doesn't break what current parsers expect. Link: https://lore.kernel.org/r/20210105113446.16027-3-huobean@gmail.com Acked-by: Steven Rostedt (VMware) Signed-off-by: Bean Huo Signed-off-by: Martin K. Petersen --- drivers/scsi/ufs/ufs.h | 10 +++++++++ drivers/scsi/ufs/ufshcd.c | 48 ++++++++++++++++++++--------------------- include/trace/events/ufs.h | 54 ++++++++++++++++++++++++++++++---------------- 3 files changed, 69 insertions(+), 43 deletions(-) (limited to 'include') diff --git a/drivers/scsi/ufs/ufs.h b/drivers/scsi/ufs/ufs.h index 14dfda735adf..ba24b504f85a 100644 --- a/drivers/scsi/ufs/ufs.h +++ b/drivers/scsi/ufs/ufs.h @@ -545,6 +545,16 @@ struct ufs_dev_info { u8 b_presrv_uspc_en; }; +/* + * This enum is used in string mapping in include/trace/events/ufs.h. + */ +enum ufs_trace_str_t { + UFS_CMD_SEND, UFS_CMD_COMP, UFS_DEV_COMP, + UFS_QUERY_SEND, UFS_QUERY_COMP, UFS_QUERY_ERR, + UFS_TM_SEND, UFS_TM_COMP, UFS_TM_ERR +}; + + /** * ufs_is_valid_unit_desc_lun - checks if the given LUN has a unit descriptor * @dev_info: pointer of instance of struct ufs_dev_info diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index ab657834f118..238db7d5746a 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -305,53 +305,53 @@ static void ufshcd_scsi_block_requests(struct ufs_hba *hba) } static void ufshcd_add_cmd_upiu_trace(struct ufs_hba *hba, unsigned int tag, - const char *str) + enum ufs_trace_str_t str_t) { struct utp_upiu_req *rq = hba->lrb[tag].ucd_req_ptr; - trace_ufshcd_upiu(dev_name(hba->dev), str, &rq->header, &rq->sc.cdb); + trace_ufshcd_upiu(dev_name(hba->dev), str_t, &rq->header, &rq->sc.cdb); } static void ufshcd_add_query_upiu_trace(struct ufs_hba *hba, unsigned int tag, - const char *str) + enum ufs_trace_str_t str_t) { struct utp_upiu_req *rq = hba->lrb[tag].ucd_req_ptr; - trace_ufshcd_upiu(dev_name(hba->dev), str, &rq->header, &rq->qr); + trace_ufshcd_upiu(dev_name(hba->dev), str_t, &rq->header, &rq->qr); } static void ufshcd_add_tm_upiu_trace(struct ufs_hba *hba, unsigned int tag, - const char *str) + enum ufs_trace_str_t str_t) { int off = (int)tag - hba->nutrs; struct utp_task_req_desc *descp = &hba->utmrdl_base_addr[off]; - trace_ufshcd_upiu(dev_name(hba->dev), str, &descp->req_header, + trace_ufshcd_upiu(dev_name(hba->dev), str_t, &descp->req_header, &descp->input_param1); } static void ufshcd_add_uic_command_trace(struct ufs_hba *hba, struct uic_command *ucmd, - const char *str) + enum ufs_trace_str_t str_t) { u32 cmd; if (!trace_ufshcd_uic_command_enabled()) return; - if (!strcmp(str, "send")) + if (str_t == UFS_CMD_SEND) cmd = ucmd->command; else cmd = ufshcd_readl(hba, REG_UIC_COMMAND); - trace_ufshcd_uic_command(dev_name(hba->dev), str, cmd, + trace_ufshcd_uic_command(dev_name(hba->dev), str_t, cmd, ufshcd_readl(hba, REG_UIC_COMMAND_ARG_1), ufshcd_readl(hba, REG_UIC_COMMAND_ARG_2), ufshcd_readl(hba, REG_UIC_COMMAND_ARG_3)); } -static void ufshcd_add_command_trace(struct ufs_hba *hba, - unsigned int tag, const char *str) +static void ufshcd_add_command_trace(struct ufs_hba *hba, unsigned int tag, + enum ufs_trace_str_t str_t) { sector_t lba = -1; u8 opcode = 0, group_id = 0; @@ -363,13 +363,13 @@ static void ufshcd_add_command_trace(struct ufs_hba *hba, if (!trace_ufshcd_command_enabled()) { /* trace UPIU W/O tracing command */ if (cmd) - ufshcd_add_cmd_upiu_trace(hba, tag, str); + ufshcd_add_cmd_upiu_trace(hba, tag, str_t); return; } if (cmd) { /* data phase exists */ /* trace UPIU also */ - ufshcd_add_cmd_upiu_trace(hba, tag, str); + ufshcd_add_cmd_upiu_trace(hba, tag, str_t); opcode = cmd->cmnd[0]; if ((opcode == READ_10) || (opcode == WRITE_10)) { /* @@ -392,7 +392,7 @@ static void ufshcd_add_command_trace(struct ufs_hba *hba, intr = ufshcd_readl(hba, REG_INTERRUPT_STATUS); doorbell = ufshcd_readl(hba, REG_UTP_TRANSFER_REQ_DOOR_BELL); - trace_ufshcd_command(dev_name(hba->dev), str, tag, + trace_ufshcd_command(dev_name(hba->dev), str_t, tag, doorbell, transfer_len, intr, lba, opcode, group_id); } @@ -2001,7 +2001,7 @@ void ufshcd_send_command(struct ufs_hba *hba, unsigned int task_tag) lrbp->issue_time_stamp = ktime_get(); lrbp->compl_time_stamp = ktime_set(0, 0); ufshcd_vops_setup_xfer_req(hba, task_tag, (lrbp->cmd ? true : false)); - ufshcd_add_command_trace(hba, task_tag, "send"); + ufshcd_add_command_trace(hba, task_tag, UFS_CMD_SEND); ufshcd_clk_scaling_start_busy(hba); __set_bit(task_tag, &hba->outstanding_reqs); ufshcd_writel(hba, 1 << task_tag, REG_UTP_TRANSFER_REQ_DOOR_BELL); @@ -2137,7 +2137,7 @@ ufshcd_dispatch_uic_cmd(struct ufs_hba *hba, struct uic_command *uic_cmd) ufshcd_writel(hba, uic_cmd->argument2, REG_UIC_COMMAND_ARG_2); ufshcd_writel(hba, uic_cmd->argument3, REG_UIC_COMMAND_ARG_3); - ufshcd_add_uic_command_trace(hba, uic_cmd, "send"); + ufshcd_add_uic_command_trace(hba, uic_cmd, UFS_CMD_SEND); /* Write UIC Cmd */ ufshcd_writel(hba, uic_cmd->command & COMMAND_OPCODE_MASK, @@ -2856,7 +2856,7 @@ static int ufshcd_exec_dev_cmd(struct ufs_hba *hba, hba->dev_cmd.complete = &wait; - ufshcd_add_query_upiu_trace(hba, tag, "query_send"); + ufshcd_add_query_upiu_trace(hba, tag, UFS_QUERY_SEND); /* Make sure descriptors are ready before ringing the doorbell */ wmb(); spin_lock_irqsave(hba->host->host_lock, flags); @@ -2867,7 +2867,7 @@ static int ufshcd_exec_dev_cmd(struct ufs_hba *hba, out: ufshcd_add_query_upiu_trace(hba, tag, - err ? "query_complete_err" : "query_complete"); + err ? UFS_QUERY_ERR : UFS_QUERY_COMP); out_put_tag: blk_put_request(req); @@ -5030,7 +5030,7 @@ static irqreturn_t ufshcd_uic_cmd_compl(struct ufs_hba *hba, u32 intr_status) if (retval == IRQ_HANDLED) ufshcd_add_uic_command_trace(hba, hba->active_uic_cmd, - "complete"); + UFS_CMD_COMP); return retval; } @@ -5054,7 +5054,7 @@ static void __ufshcd_transfer_req_compl(struct ufs_hba *hba, lrbp->compl_time_stamp = ktime_get(); cmd = lrbp->cmd; if (cmd) { - ufshcd_add_command_trace(hba, index, "complete"); + ufshcd_add_command_trace(hba, index, UFS_CMD_COMP); result = ufshcd_transfer_rsp_status(hba, lrbp); scsi_dma_unmap(cmd); cmd->result = result; @@ -5068,7 +5068,7 @@ static void __ufshcd_transfer_req_compl(struct ufs_hba *hba, lrbp->command_type == UTP_CMD_TYPE_UFS_STORAGE) { if (hba->dev_cmd.complete) { ufshcd_add_command_trace(hba, index, - "dev_complete"); + UFS_DEV_COMP); complete(hba->dev_cmd.complete); update_scaling = true; } @@ -6371,7 +6371,7 @@ static int __ufshcd_issue_tm_cmd(struct ufs_hba *hba, spin_unlock_irqrestore(host->host_lock, flags); - ufshcd_add_tm_upiu_trace(hba, task_tag, "tm_send"); + ufshcd_add_tm_upiu_trace(hba, task_tag, UFS_TM_SEND); /* wait until the task management command is completed */ err = wait_for_completion_io_timeout(&wait, @@ -6382,7 +6382,7 @@ static int __ufshcd_issue_tm_cmd(struct ufs_hba *hba, * use-after-free. */ req->end_io_data = NULL; - ufshcd_add_tm_upiu_trace(hba, task_tag, "tm_complete_err"); + ufshcd_add_tm_upiu_trace(hba, task_tag, UFS_TM_ERR); dev_err(hba->dev, "%s: task management cmd 0x%.2x timed-out\n", __func__, tm_function); if (ufshcd_clear_tm_cmd(hba, free_slot)) @@ -6393,7 +6393,7 @@ static int __ufshcd_issue_tm_cmd(struct ufs_hba *hba, err = 0; memcpy(treq, hba->utmrdl_base_addr + free_slot, sizeof(*treq)); - ufshcd_add_tm_upiu_trace(hba, task_tag, "tm_complete"); + ufshcd_add_tm_upiu_trace(hba, task_tag, UFS_TM_COMP); } spin_lock_irqsave(hba->host->host_lock, flags); diff --git a/include/trace/events/ufs.h b/include/trace/events/ufs.h index fa755394bc0f..7613a5cd14de 100644 --- a/include/trace/events/ufs.h +++ b/include/trace/events/ufs.h @@ -37,6 +37,17 @@ EM(REQ_CLKS_OFF, "REQ_CLKS_OFF") \ EMe(REQ_CLKS_ON, "REQ_CLKS_ON") +#define UFS_CMD_TRACE_STRINGS \ + EM(UFS_CMD_SEND, "send_req") \ + EM(UFS_CMD_COMP, "complete_rsp") \ + EM(UFS_DEV_COMP, "dev_complete") \ + EM(UFS_QUERY_SEND, "query_send") \ + EM(UFS_QUERY_COMP, "query_complete") \ + EM(UFS_QUERY_ERR, "query_complete_err") \ + EM(UFS_TM_SEND, "tm_send") \ + EM(UFS_TM_COMP, "tm_complete") \ + EMe(UFS_TM_ERR, "tm_complete_err") + /* Enums require being exported to userspace, for user tool parsing */ #undef EM #undef EMe @@ -46,6 +57,7 @@ UFS_LINK_STATES; UFS_PWR_MODES; UFSCHD_CLK_GATING_STATES; +UFS_CMD_TRACE_STRINGS /* * Now redefine the EM() and EMe() macros to map the enums to the strings @@ -56,6 +68,9 @@ UFSCHD_CLK_GATING_STATES; #define EM(a, b) {a, b}, #define EMe(a, b) {a, b} +#define show_ufs_cmd_trace_str(str_t) \ + __print_symbolic(str_t, UFS_CMD_TRACE_STRINGS) + TRACE_EVENT(ufshcd_clk_gating, TP_PROTO(const char *dev_name, int state), @@ -223,16 +238,16 @@ DEFINE_EVENT(ufshcd_template, ufshcd_init, TP_ARGS(dev_name, err, usecs, dev_state, link_state)); TRACE_EVENT(ufshcd_command, - TP_PROTO(const char *dev_name, const char *str, unsigned int tag, - u32 doorbell, int transfer_len, u32 intr, u64 lba, - u8 opcode, u8 group_id), + TP_PROTO(const char *dev_name, enum ufs_trace_str_t str_t, + unsigned int tag, u32 doorbell, int transfer_len, u32 intr, + u64 lba, u8 opcode, u8 group_id), - TP_ARGS(dev_name, str, tag, doorbell, transfer_len, + TP_ARGS(dev_name, str_t, tag, doorbell, transfer_len, intr, lba, opcode, group_id), TP_STRUCT__entry( __string(dev_name, dev_name) - __string(str, str) + __field(enum ufs_trace_str_t, str_t) __field(unsigned int, tag) __field(u32, doorbell) __field(int, transfer_len) @@ -244,7 +259,7 @@ TRACE_EVENT(ufshcd_command, TP_fast_assign( __assign_str(dev_name, dev_name); - __assign_str(str, str); + __entry->str_t = str_t; __entry->tag = tag; __entry->doorbell = doorbell; __entry->transfer_len = transfer_len; @@ -256,22 +271,22 @@ TRACE_EVENT(ufshcd_command, TP_printk( "%s: %s: tag: %u, DB: 0x%x, size: %d, IS: %u, LBA: %llu, opcode: 0x%x (%s), group_id: 0x%x", - __get_str(str), __get_str(dev_name), __entry->tag, - __entry->doorbell, __entry->transfer_len, + show_ufs_cmd_trace_str(__entry->str_t), __get_str(dev_name), + __entry->tag, __entry->doorbell, __entry->transfer_len, __entry->intr, __entry->lba, (u32)__entry->opcode, str_opcode(__entry->opcode), (u32)__entry->group_id ) ); TRACE_EVENT(ufshcd_uic_command, - TP_PROTO(const char *dev_name, const char *str, u32 cmd, + TP_PROTO(const char *dev_name, enum ufs_trace_str_t str_t, u32 cmd, u32 arg1, u32 arg2, u32 arg3), - TP_ARGS(dev_name, str, cmd, arg1, arg2, arg3), + TP_ARGS(dev_name, str_t, cmd, arg1, arg2, arg3), TP_STRUCT__entry( __string(dev_name, dev_name) - __string(str, str) + __field(enum ufs_trace_str_t, str_t) __field(u32, cmd) __field(u32, arg1) __field(u32, arg2) @@ -280,7 +295,7 @@ TRACE_EVENT(ufshcd_uic_command, TP_fast_assign( __assign_str(dev_name, dev_name); - __assign_str(str, str); + __entry->str_t = str_t; __entry->cmd = cmd; __entry->arg1 = arg1; __entry->arg2 = arg2; @@ -289,33 +304,34 @@ TRACE_EVENT(ufshcd_uic_command, TP_printk( "%s: %s: cmd: 0x%x, arg1: 0x%x, arg2: 0x%x, arg3: 0x%x", - __get_str(str), __get_str(dev_name), __entry->cmd, - __entry->arg1, __entry->arg2, __entry->arg3 + show_ufs_cmd_trace_str(__entry->str_t), __get_str(dev_name), + __entry->cmd, __entry->arg1, __entry->arg2, __entry->arg3 ) ); TRACE_EVENT(ufshcd_upiu, - TP_PROTO(const char *dev_name, const char *str, void *hdr, void *tsf), + TP_PROTO(const char *dev_name, enum ufs_trace_str_t str_t, void *hdr, + void *tsf), - TP_ARGS(dev_name, str, hdr, tsf), + TP_ARGS(dev_name, str_t, hdr, tsf), TP_STRUCT__entry( __string(dev_name, dev_name) - __string(str, str) + __field(enum ufs_trace_str_t, str_t) __array(unsigned char, hdr, 12) __array(unsigned char, tsf, 16) ), TP_fast_assign( __assign_str(dev_name, dev_name); - __assign_str(str, str); + __entry->str_t = str_t; memcpy(__entry->hdr, hdr, sizeof(__entry->hdr)); memcpy(__entry->tsf, tsf, sizeof(__entry->tsf)); ), TP_printk( "%s: %s: HDR:%s, CDB:%s", - __get_str(str), __get_str(dev_name), + show_ufs_cmd_trace_str(__entry->str_t), __get_str(dev_name), __print_hex(__entry->hdr, sizeof(__entry->hdr)), __print_hex(__entry->tsf, sizeof(__entry->tsf)) ) -- cgit v1.2.3 From 867fdc2d6e34635b2708cfa5d7e1100b3f298337 Mon Sep 17 00:00:00 2001 From: Bean Huo Date: Tue, 5 Jan 2021 12:34:46 +0100 Subject: scsi: ufs: Make UPIU trace easier differentiate among CDB, OSF, and TM Transaction Specific Fields (TSF) in the UPIU package could be CDB (SCSI/UFS Command Descriptor Block), OSF (Opcode Specific Field), and TM I/O parameter (Task Management Input/Output Parameter). But, currently, we take all of these as CDB in the UPIU trace. Thus makes user confuse among CDB, OSF, and TM message. So fix it with this patch. Link: https://lore.kernel.org/r/20210105113446.16027-7-huobean@gmail.com Acked-by: Steven Rostedt (VMware) Signed-off-by: Bean Huo Signed-off-by: Martin K. Petersen --- drivers/scsi/ufs/ufs.h | 7 +++++++ drivers/scsi/ufs/ufshcd.c | 9 +++++---- include/trace/events/ufs.h | 18 +++++++++++++++--- 3 files changed, 27 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/drivers/scsi/ufs/ufs.h b/drivers/scsi/ufs/ufs.h index ba24b504f85a..50f46f3bc8a2 100644 --- a/drivers/scsi/ufs/ufs.h +++ b/drivers/scsi/ufs/ufs.h @@ -554,6 +554,13 @@ enum ufs_trace_str_t { UFS_TM_SEND, UFS_TM_COMP, UFS_TM_ERR }; +/* + * Transaction Specific Fields (TSF) type in the UPIU package, this enum is + * used in include/trace/events/ufs.h for UFS command trace. + */ +enum ufs_trace_tsf_t { + UFS_TSF_CDB, UFS_TSF_OSF, UFS_TSF_TM_INPUT, UFS_TSF_TM_OUTPUT +}; /** * ufs_is_valid_unit_desc_lun - checks if the given LUN has a unit descriptor diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index 9879b79e62f0..53fd59ce50b2 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -312,7 +312,8 @@ static void ufshcd_add_cmd_upiu_trace(struct ufs_hba *hba, unsigned int tag, if (!trace_ufshcd_upiu_enabled()) return; - trace_ufshcd_upiu(dev_name(hba->dev), str_t, &rq->header, &rq->sc.cdb); + trace_ufshcd_upiu(dev_name(hba->dev), str_t, &rq->header, &rq->sc.cdb, + UFS_TSF_CDB); } static void ufshcd_add_query_upiu_trace(struct ufs_hba *hba, unsigned int tag, @@ -329,7 +330,7 @@ static void ufshcd_add_query_upiu_trace(struct ufs_hba *hba, unsigned int tag, rq_rsp = (struct utp_upiu_req *)hba->lrb[tag].ucd_rsp_ptr; trace_ufshcd_upiu(dev_name(hba->dev), str_t, &rq_rsp->header, - &rq_rsp->qr); + &rq_rsp->qr, UFS_TSF_OSF); } static void ufshcd_add_tm_upiu_trace(struct ufs_hba *hba, unsigned int tag, @@ -343,10 +344,10 @@ static void ufshcd_add_tm_upiu_trace(struct ufs_hba *hba, unsigned int tag, if (str_t == UFS_TM_SEND) trace_ufshcd_upiu(dev_name(hba->dev), str_t, &descp->req_header, - &descp->input_param1); + &descp->input_param1, UFS_TSF_TM_INPUT); else trace_ufshcd_upiu(dev_name(hba->dev), str_t, &descp->rsp_header, - &descp->output_param1); + &descp->output_param1, UFS_TSF_TM_OUTPUT); } static void ufshcd_add_uic_command_trace(struct ufs_hba *hba, diff --git a/include/trace/events/ufs.h b/include/trace/events/ufs.h index 7613a5cd14de..e151477d645c 100644 --- a/include/trace/events/ufs.h +++ b/include/trace/events/ufs.h @@ -48,6 +48,12 @@ EM(UFS_TM_COMP, "tm_complete") \ EMe(UFS_TM_ERR, "tm_complete_err") +#define UFS_CMD_TRACE_TSF_TYPES \ + EM(UFS_TSF_CDB, "CDB") \ + EM(UFS_TSF_OSF, "OSF") \ + EM(UFS_TSF_TM_INPUT, "TM_INPUT") \ + EMe(UFS_TSF_TM_OUTPUT, "TM_OUTPUT") + /* Enums require being exported to userspace, for user tool parsing */ #undef EM #undef EMe @@ -58,6 +64,7 @@ UFS_LINK_STATES; UFS_PWR_MODES; UFSCHD_CLK_GATING_STATES; UFS_CMD_TRACE_STRINGS +UFS_CMD_TRACE_TSF_TYPES /* * Now redefine the EM() and EMe() macros to map the enums to the strings @@ -70,6 +77,8 @@ UFS_CMD_TRACE_STRINGS #define show_ufs_cmd_trace_str(str_t) \ __print_symbolic(str_t, UFS_CMD_TRACE_STRINGS) +#define show_ufs_cmd_trace_tsf(tsf) \ + __print_symbolic(tsf, UFS_CMD_TRACE_TSF_TYPES) TRACE_EVENT(ufshcd_clk_gating, @@ -311,15 +320,16 @@ TRACE_EVENT(ufshcd_uic_command, TRACE_EVENT(ufshcd_upiu, TP_PROTO(const char *dev_name, enum ufs_trace_str_t str_t, void *hdr, - void *tsf), + void *tsf, enum ufs_trace_tsf_t tsf_t), - TP_ARGS(dev_name, str_t, hdr, tsf), + TP_ARGS(dev_name, str_t, hdr, tsf, tsf_t), TP_STRUCT__entry( __string(dev_name, dev_name) __field(enum ufs_trace_str_t, str_t) __array(unsigned char, hdr, 12) __array(unsigned char, tsf, 16) + __field(enum ufs_trace_tsf_t, tsf_t) ), TP_fast_assign( @@ -327,12 +337,14 @@ TRACE_EVENT(ufshcd_upiu, __entry->str_t = str_t; memcpy(__entry->hdr, hdr, sizeof(__entry->hdr)); memcpy(__entry->tsf, tsf, sizeof(__entry->tsf)); + __entry->tsf_t = tsf_t; ), TP_printk( - "%s: %s: HDR:%s, CDB:%s", + "%s: %s: HDR:%s, %s:%s", show_ufs_cmd_trace_str(__entry->str_t), __get_str(dev_name), __print_hex(__entry->hdr, sizeof(__entry->hdr)), + show_ufs_cmd_trace_tsf(__entry->tsf_t), __print_hex(__entry->tsf, sizeof(__entry->tsf)) ) ); -- cgit v1.2.3 From 33cb6d1ed311af2c1dfd107fa334cfb51113ef35 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Mon, 28 Dec 2020 21:30:21 +0100 Subject: dmaengine: at_hdmac: remove platform data header linux/platform_data/dma-atmel.h is only used by the at_hdmac driver. Move the CFG bits definitions back in at_hdmac_regs.h and the remaining definitions in the driver. Signed-off-by: Alexandre Belloni Link: https://lore.kernel.org/r/20201228203022.2674133-1-alexandre.belloni@bootlin.com Signed-off-by: Vinod Koul --- MAINTAINERS | 1 - drivers/dma/at_hdmac.c | 19 ++++++++++ drivers/dma/at_hdmac_regs.h | 28 +++++++++++++-- include/linux/platform_data/dma-atmel.h | 61 --------------------------------- 4 files changed, 44 insertions(+), 65 deletions(-) delete mode 100644 include/linux/platform_data/dma-atmel.h (limited to 'include') diff --git a/MAINTAINERS b/MAINTAINERS index 546aa66428c9..0d62310a31f8 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11604,7 +11604,6 @@ F: drivers/dma/at_hdmac.c F: drivers/dma/at_hdmac_regs.h F: drivers/dma/at_xdmac.c F: include/dt-bindings/dma/at91.h -F: include/linux/platform_data/dma-atmel.h MICROCHIP AT91 SERIAL DRIVER M: Richard Genoud diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c index 7eaee5b705b1..30ae36124b1d 100644 --- a/drivers/dma/at_hdmac.c +++ b/drivers/dma/at_hdmac.c @@ -54,6 +54,25 @@ module_param(init_nr_desc_per_channel, uint, 0644); MODULE_PARM_DESC(init_nr_desc_per_channel, "initial descriptors per channel (default: 64)"); +/** + * struct at_dma_platform_data - Controller configuration parameters + * @nr_channels: Number of channels supported by hardware (max 8) + * @cap_mask: dma_capability flags supported by the platform + */ +struct at_dma_platform_data { + unsigned int nr_channels; + dma_cap_mask_t cap_mask; +}; + +/** + * struct at_dma_slave - Controller-specific information about a slave + * @dma_dev: required DMA master device + * @cfg: Platform-specific initializer for the CFG register + */ +struct at_dma_slave { + struct device *dma_dev; + u32 cfg; +}; /* prototypes */ static dma_cookie_t atc_tx_submit(struct dma_async_tx_descriptor *tx); diff --git a/drivers/dma/at_hdmac_regs.h b/drivers/dma/at_hdmac_regs.h index 80fc2fe8c77e..4d1ebc040031 100644 --- a/drivers/dma/at_hdmac_regs.h +++ b/drivers/dma/at_hdmac_regs.h @@ -7,8 +7,6 @@ #ifndef AT_HDMAC_REGS_H #define AT_HDMAC_REGS_H -#include - #define AT_DMA_MAX_NR_CHANNELS 8 @@ -148,7 +146,31 @@ #define ATC_AUTO (0x1 << 31) /* Auto multiple buffer tx enable */ /* Bitfields in CFG */ -/* are in at_hdmac.h */ +#define ATC_PER_MSB(h) ((0x30U & (h)) >> 4) /* Extract most significant bits of a handshaking identifier */ + +#define ATC_SRC_PER(h) (0xFU & (h)) /* Channel src rq associated with periph handshaking ifc h */ +#define ATC_DST_PER(h) ((0xFU & (h)) << 4) /* Channel dst rq associated with periph handshaking ifc h */ +#define ATC_SRC_REP (0x1 << 8) /* Source Replay Mod */ +#define ATC_SRC_H2SEL (0x1 << 9) /* Source Handshaking Mod */ +#define ATC_SRC_H2SEL_SW (0x0 << 9) +#define ATC_SRC_H2SEL_HW (0x1 << 9) +#define ATC_SRC_PER_MSB(h) (ATC_PER_MSB(h) << 10) /* Channel src rq (most significant bits) */ +#define ATC_DST_REP (0x1 << 12) /* Destination Replay Mod */ +#define ATC_DST_H2SEL (0x1 << 13) /* Destination Handshaking Mod */ +#define ATC_DST_H2SEL_SW (0x0 << 13) +#define ATC_DST_H2SEL_HW (0x1 << 13) +#define ATC_DST_PER_MSB(h) (ATC_PER_MSB(h) << 14) /* Channel dst rq (most significant bits) */ +#define ATC_SOD (0x1 << 16) /* Stop On Done */ +#define ATC_LOCK_IF (0x1 << 20) /* Interface Lock */ +#define ATC_LOCK_B (0x1 << 21) /* AHB Bus Lock */ +#define ATC_LOCK_IF_L (0x1 << 22) /* Master Interface Arbiter Lock */ +#define ATC_LOCK_IF_L_CHUNK (0x0 << 22) +#define ATC_LOCK_IF_L_BUFFER (0x1 << 22) +#define ATC_AHB_PROT_MASK (0x7 << 24) /* AHB Protection */ +#define ATC_FIFOCFG_MASK (0x3 << 28) /* FIFO Request Configuration */ +#define ATC_FIFOCFG_LARGESTBURST (0x0 << 28) +#define ATC_FIFOCFG_HALFFIFO (0x1 << 28) +#define ATC_FIFOCFG_ENOUGHSPACE (0x2 << 28) /* Bitfields in SPIP */ #define ATC_SPIP_HOLE(x) (0xFFFFU & (x)) diff --git a/include/linux/platform_data/dma-atmel.h b/include/linux/platform_data/dma-atmel.h deleted file mode 100644 index 069637e6004f..000000000000 --- a/include/linux/platform_data/dma-atmel.h +++ /dev/null @@ -1,61 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Header file for the Atmel AHB DMA Controller driver - * - * Copyright (C) 2008 Atmel Corporation - */ -#ifndef AT_HDMAC_H -#define AT_HDMAC_H - -#include - -/** - * struct at_dma_platform_data - Controller configuration parameters - * @nr_channels: Number of channels supported by hardware (max 8) - * @cap_mask: dma_capability flags supported by the platform - */ -struct at_dma_platform_data { - unsigned int nr_channels; - dma_cap_mask_t cap_mask; -}; - -/** - * struct at_dma_slave - Controller-specific information about a slave - * @dma_dev: required DMA master device - * @cfg: Platform-specific initializer for the CFG register - */ -struct at_dma_slave { - struct device *dma_dev; - u32 cfg; -}; - - -/* Platform-configurable bits in CFG */ -#define ATC_PER_MSB(h) ((0x30U & (h)) >> 4) /* Extract most significant bits of a handshaking identifier */ - -#define ATC_SRC_PER(h) (0xFU & (h)) /* Channel src rq associated with periph handshaking ifc h */ -#define ATC_DST_PER(h) ((0xFU & (h)) << 4) /* Channel dst rq associated with periph handshaking ifc h */ -#define ATC_SRC_REP (0x1 << 8) /* Source Replay Mod */ -#define ATC_SRC_H2SEL (0x1 << 9) /* Source Handshaking Mod */ -#define ATC_SRC_H2SEL_SW (0x0 << 9) -#define ATC_SRC_H2SEL_HW (0x1 << 9) -#define ATC_SRC_PER_MSB(h) (ATC_PER_MSB(h) << 10) /* Channel src rq (most significant bits) */ -#define ATC_DST_REP (0x1 << 12) /* Destination Replay Mod */ -#define ATC_DST_H2SEL (0x1 << 13) /* Destination Handshaking Mod */ -#define ATC_DST_H2SEL_SW (0x0 << 13) -#define ATC_DST_H2SEL_HW (0x1 << 13) -#define ATC_DST_PER_MSB(h) (ATC_PER_MSB(h) << 14) /* Channel dst rq (most significant bits) */ -#define ATC_SOD (0x1 << 16) /* Stop On Done */ -#define ATC_LOCK_IF (0x1 << 20) /* Interface Lock */ -#define ATC_LOCK_B (0x1 << 21) /* AHB Bus Lock */ -#define ATC_LOCK_IF_L (0x1 << 22) /* Master Interface Arbiter Lock */ -#define ATC_LOCK_IF_L_CHUNK (0x0 << 22) -#define ATC_LOCK_IF_L_BUFFER (0x1 << 22) -#define ATC_AHB_PROT_MASK (0x7 << 24) /* AHB Protection */ -#define ATC_FIFOCFG_MASK (0x3 << 28) /* FIFO Request Configuration */ -#define ATC_FIFOCFG_LARGESTBURST (0x0 << 28) -#define ATC_FIFOCFG_HALFFIFO (0x1 << 28) -#define ATC_FIFOCFG_ENOUGHSPACE (0x2 << 28) - - -#endif /* AT_HDMAC_H */ -- cgit v1.2.3 From 2b405ec0e1c4b4c490b95da7ac3c9934c7675da6 Mon Sep 17 00:00:00 2001 From: Jonathan Neuschäfer Date: Fri, 1 Jan 2021 22:18:17 +0100 Subject: drm/mipi-dbi: Switch to new kerneldoc syntax for named variable macro argument MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The syntax without dots is available since commit 43756e347f21 ("scripts/kernel-doc: Add support for named variable macro arguments"). The same HTML output is produced with and without this patch. Signed-off-by: Jonathan Neuschäfer Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210101211818.1023919-1-j.neuschaefer@gmx.net --- include/drm/drm_mipi_dbi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/drm_mipi_dbi.h b/include/drm/drm_mipi_dbi.h index c2827ceaba0d..f543d6e3e822 100644 --- a/include/drm/drm_mipi_dbi.h +++ b/include/drm/drm_mipi_dbi.h @@ -172,7 +172,7 @@ int mipi_dbi_buf_copy(void *dst, struct drm_framebuffer *fb, * mipi_dbi_command - MIPI DCS command with optional parameter(s) * @dbi: MIPI DBI structure * @cmd: Command - * @seq...: Optional parameter(s) + * @seq: Optional parameter(s) * * Send MIPI DCS command to the controller. Use mipi_dbi_command_read() for * get/read. -- cgit v1.2.3 From 82581fcf070b68a91fb3a3ade08d9a76380a4789 Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Fri, 8 Jan 2021 10:53:06 +0100 Subject: drm/modes: add non-OF stub for of_get_drm_display_mode If CONFIG_OF is disabled, of_get_drm_display_mode is not compiled in, and drivers using it fail to build: ld: drivers/gpu/drm/imx/parallel-display.o: in function `imx_pd_connector_get_modes': parallel-display.c:(.text+0x8d): undefined reference to `of_get_drm_display_mode' Add an inline stub so they can be build-tested with non-OF configurations. Reported-by: Randy Dunlap Reviewed-by: Daniel Vetter Acked-by: Randy Dunlap Signed-off-by: Philipp Zabel --- include/drm/drm_modes.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/drm/drm_modes.h b/include/drm/drm_modes.h index a0d79d1c51e2..29ba4adf0c53 100644 --- a/include/drm/drm_modes.h +++ b/include/drm/drm_modes.h @@ -461,9 +461,19 @@ void drm_display_mode_from_videomode(const struct videomode *vm, void drm_display_mode_to_videomode(const struct drm_display_mode *dmode, struct videomode *vm); void drm_bus_flags_from_videomode(const struct videomode *vm, u32 *bus_flags); + +#if defined(CONFIG_OF) int of_get_drm_display_mode(struct device_node *np, struct drm_display_mode *dmode, u32 *bus_flags, int index); +#else +static inline int of_get_drm_display_mode(struct device_node *np, + struct drm_display_mode *dmode, + u32 *bus_flags, int index) +{ + return -EINVAL; +} +#endif void drm_mode_set_name(struct drm_display_mode *mode); int drm_mode_vrefresh(const struct drm_display_mode *mode); -- cgit v1.2.3 From 8fbdbb66f8c10bb359ad20fff95628e5deac88f4 Mon Sep 17 00:00:00 2001 From: Darren Salt Date: Tue, 5 Jan 2021 14:44:01 +0100 Subject: PCI: Export pci_rebar_get_possible_sizes() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Export pci_rebar_get_possible_sizes() for use by modular drivers. Signed-off-by: Darren Salt Signed-off-by: Nirmoy Das Signed-off-by: Christian König Acked-by: Bjorn Helgaas Link: https://patchwork.kernel.org/project/dri-devel/patch/20210107175017.15893-2-nirmoy.das@amd.com --- drivers/pci/pci.c | 1 + drivers/pci/pci.h | 1 - include/linux/pci.h | 1 + 3 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index b9fecc25d213..8d1aec39ecc8 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -3605,6 +3605,7 @@ u32 pci_rebar_get_possible_sizes(struct pci_dev *pdev, int bar) pci_read_config_dword(pdev, pos + PCI_REBAR_CAP, &cap); return (cap & PCI_REBAR_CAP_SIZES) >> 4; } +EXPORT_SYMBOL(pci_rebar_get_possible_sizes); /** * pci_rebar_get_current_size - get the current size of a BAR diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 5c59365092fa..8f130f9531b3 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -630,7 +630,6 @@ int acpi_get_rc_resources(struct device *dev, const char *hid, u16 segment, struct resource *res); #endif -u32 pci_rebar_get_possible_sizes(struct pci_dev *pdev, int bar); int pci_rebar_get_current_size(struct pci_dev *pdev, int bar); int pci_rebar_set_size(struct pci_dev *pdev, int bar, int size); static inline u64 pci_rebar_size_to_bytes(int size) diff --git a/include/linux/pci.h b/include/linux/pci.h index b32126d26997..5f25a0ec48c1 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1232,6 +1232,7 @@ void pci_update_resource(struct pci_dev *dev, int resno); int __must_check pci_assign_resource(struct pci_dev *dev, int i); int __must_check pci_reassign_resource(struct pci_dev *dev, int i, resource_size_t add_size, resource_size_t align); void pci_release_resource(struct pci_dev *dev, int resno); +u32 pci_rebar_get_possible_sizes(struct pci_dev *pdev, int bar); int __must_check pci_resize_resource(struct pci_dev *dev, int i, int size); int pci_select_bars(struct pci_dev *dev, unsigned long flags); bool pci_device_is_present(struct pci_dev *pdev); -- cgit v1.2.3 From 192f1bf7559e895d51f81c3976c5892c8b1e0601 Mon Sep 17 00:00:00 2001 From: Nirmoy Das Date: Thu, 7 Jan 2021 14:30:34 +0100 Subject: PCI: Add pci_rebar_bytes_to_size() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Users of pci_resize_resource() need a way to calculate BAR size from desired bytes. Add a helper function and export it so that modular drivers can use it. Signed-off-by: Darren Salt Signed-off-by: Christian König Signed-off-by: Nirmoy Das Acked-by: Bjorn Helgaas Link: https://patchwork.kernel.org/project/dri-devel/patch/20210107175017.15893-3-nirmoy.das@amd.com --- drivers/pci/pci.c | 2 +- include/linux/pci.h | 8 ++++++++ 2 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 8d1aec39ecc8..99ef2774b9d0 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1644,7 +1644,7 @@ static void pci_restore_rebar_state(struct pci_dev *pdev) pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl); bar_idx = ctrl & PCI_REBAR_CTRL_BAR_IDX; res = pdev->resource + bar_idx; - size = ilog2(resource_size(res)) - 20; + size = pci_rebar_bytes_to_size(resource_size(res)); ctrl &= ~PCI_REBAR_CTRL_BAR_SIZE; ctrl |= size << PCI_REBAR_CTRL_BAR_SHIFT; pci_write_config_dword(pdev, pos + PCI_REBAR_CTRL, ctrl); diff --git a/include/linux/pci.h b/include/linux/pci.h index 5f25a0ec48c1..53f4904ee83d 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1232,6 +1232,14 @@ void pci_update_resource(struct pci_dev *dev, int resno); int __must_check pci_assign_resource(struct pci_dev *dev, int i); int __must_check pci_reassign_resource(struct pci_dev *dev, int i, resource_size_t add_size, resource_size_t align); void pci_release_resource(struct pci_dev *dev, int resno); +static inline int pci_rebar_bytes_to_size(u64 bytes) +{ + bytes = roundup_pow_of_two(bytes); + + /* Return BAR size as defined in the resizable BAR specification */ + return max(ilog2(bytes), 20) - 20; +} + u32 pci_rebar_get_possible_sizes(struct pci_dev *pdev, int bar); int __must_check pci_resize_resource(struct pci_dev *dev, int i, int size); int pci_select_bars(struct pci_dev *dev, unsigned long flags); -- cgit v1.2.3 From 398cb92495cc1972014ffa81ff9cea1e5167b8df Mon Sep 17 00:00:00 2001 From: Guo Ren Date: Fri, 13 Nov 2020 09:48:27 +0000 Subject: csky: Fixup perf probe failed Current perf init will failed with: [ 1.452433] csky-pmu: probe of soc:pmu failed with error -16 This patch fix it up with adding CPUHP_AP_PERF_CSKY_ONLINE in cpuhotplug.h. Signed-off-by: Guo Ren Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Arnaldo Carvalho de Melo --- arch/csky/kernel/perf_event.c | 2 +- include/linux/cpuhotplug.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/arch/csky/kernel/perf_event.c b/arch/csky/kernel/perf_event.c index 1a29f1157449..55d5a5379483 100644 --- a/arch/csky/kernel/perf_event.c +++ b/arch/csky/kernel/perf_event.c @@ -1319,7 +1319,7 @@ int csky_pmu_device_probe(struct platform_device *pdev, pr_notice("[perf] PMU request irq fail!\n"); } - ret = cpuhp_setup_state(CPUHP_AP_PERF_ONLINE, "AP_PERF_ONLINE", + ret = cpuhp_setup_state(CPUHP_AP_PERF_CSKY_ONLINE, "AP_PERF_ONLINE", csky_pmu_starting_cpu, csky_pmu_dying_cpu); if (ret) { diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 0042ef362511..d3e26dc81494 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -185,6 +185,7 @@ enum cpuhp_state { CPUHP_AP_PERF_POWERPC_TRACE_IMC_ONLINE, CPUHP_AP_PERF_POWERPC_HV_24x7_ONLINE, CPUHP_AP_PERF_POWERPC_HV_GPCI_ONLINE, + CPUHP_AP_PERF_CSKY_ONLINE, CPUHP_AP_WATCHDOG_ONLINE, CPUHP_AP_WORKQUEUE_ONLINE, CPUHP_AP_RCUTREE_ONLINE, -- cgit v1.2.3 From 7e60bdeb91ef7914a667be266ac0a0e6ea335475 Mon Sep 17 00:00:00 2001 From: Zhaoge Zhang Date: Tue, 12 Jan 2021 09:54:39 +0800 Subject: drm: Fix macro name DRM_MODE_PROP_OBJECT in code comment Signed-off-by: Zhaoge Zhang Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/1610416479-32736-1-git-send-email-zhangzhaoge@loongson.cn --- include/drm/drm_property.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/drm_property.h b/include/drm/drm_property.h index 4a0a80d658c7..bbf5c1fdd7b0 100644 --- a/include/drm/drm_property.h +++ b/include/drm/drm_property.h @@ -114,7 +114,7 @@ struct drm_property { * by the property. Bitmask properties are created using * drm_property_create_bitmask(). * - * DRM_MODE_PROB_OBJECT + * DRM_MODE_PROP_OBJECT * Object properties are used to link modeset objects. This is used * extensively in the atomic support to create the display pipeline, * by linking &drm_framebuffer to &drm_plane, &drm_plane to -- cgit v1.2.3 From 04769cb1c45a919cd94b931e6494d2a9afc32914 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Fri, 27 Nov 2020 17:41:19 +0100 Subject: mm/frame-vector: Use FOLL_LONGTERM MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This is used by media/videbuf2 for persistent dma mappings, not just for a single dma operation and then freed again, so needs FOLL_LONGTERM. Unfortunately current pup_locked doesn't support FOLL_LONGTERM due to locking issues. Rework the code to pull the pup path out from the mmap_sem critical section as suggested by Jason. By relying entirely on the vma checks in pin_user_pages and follow_pfn (for vm_flags and vma_is_fsdax) we can also streamline the code a lot. Note that pin_user_pages_fast is a safe replacement despite the seeming lack of checking for vma->vm_flasg & (VM_IO | VM_PFNMAP). Such ptes are marked with pte_mkspecial (which pup_fast rejects in the fastpath), and only architectures supporting that support the pin_user_pages_fast fastpath. Signed-off-by: Daniel Vetter Cc: Christoph Hellwig Cc: Jason Gunthorpe Cc: Pawel Osciak Cc: Marek Szyprowski Cc: Kyungmin Park Cc: Tomasz Figa Cc: Mauro Carvalho Chehab Cc: Andrew Morton Cc: John Hubbard Cc: Jérôme Glisse Cc: Jan Kara Cc: Dan Williams Cc: linux-mm@kvack.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-samsung-soc@vger.kernel.org Cc: linux-media@vger.kernel.org Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20201127164131.2244124-6-daniel.vetter@ffwll.ch --- drivers/media/common/videobuf2/videobuf2-memops.c | 3 +- include/linux/mm.h | 2 +- mm/frame_vector.c | 53 ++++++++--------------- 3 files changed, 19 insertions(+), 39 deletions(-) (limited to 'include') diff --git a/drivers/media/common/videobuf2/videobuf2-memops.c b/drivers/media/common/videobuf2/videobuf2-memops.c index 6e9e05153f4e..9dd6c27162f4 100644 --- a/drivers/media/common/videobuf2/videobuf2-memops.c +++ b/drivers/media/common/videobuf2/videobuf2-memops.c @@ -40,7 +40,6 @@ struct frame_vector *vb2_create_framevec(unsigned long start, unsigned long first, last; unsigned long nr; struct frame_vector *vec; - unsigned int flags = FOLL_FORCE | FOLL_WRITE; first = start >> PAGE_SHIFT; last = (start + length - 1) >> PAGE_SHIFT; @@ -48,7 +47,7 @@ struct frame_vector *vb2_create_framevec(unsigned long start, vec = frame_vector_create(nr); if (!vec) return ERR_PTR(-ENOMEM); - ret = get_vaddr_frames(start & PAGE_MASK, nr, flags, vec); + ret = get_vaddr_frames(start & PAGE_MASK, nr, vec); if (ret < 0) goto out_destroy; /* We accept only complete set of PFNs */ diff --git a/include/linux/mm.h b/include/linux/mm.h index ecdf8a8cd6ae..2e7b1d048df9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1768,7 +1768,7 @@ struct frame_vector { struct frame_vector *frame_vector_create(unsigned int nr_frames); void frame_vector_destroy(struct frame_vector *vec); int get_vaddr_frames(unsigned long start, unsigned int nr_pfns, - unsigned int gup_flags, struct frame_vector *vec); + struct frame_vector *vec); void put_vaddr_frames(struct frame_vector *vec); int frame_vector_to_pages(struct frame_vector *vec); void frame_vector_to_pfns(struct frame_vector *vec); diff --git a/mm/frame_vector.c b/mm/frame_vector.c index 10f82d5643b6..f8c34b895c76 100644 --- a/mm/frame_vector.c +++ b/mm/frame_vector.c @@ -32,13 +32,12 @@ * This function takes care of grabbing mmap_lock as necessary. */ int get_vaddr_frames(unsigned long start, unsigned int nr_frames, - unsigned int gup_flags, struct frame_vector *vec) + struct frame_vector *vec) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; int ret = 0; int err; - int locked; if (nr_frames == 0) return 0; @@ -48,40 +47,26 @@ int get_vaddr_frames(unsigned long start, unsigned int nr_frames, start = untagged_addr(start); - mmap_read_lock(mm); - locked = 1; - vma = find_vma_intersection(mm, start, start + 1); - if (!vma) { - ret = -EFAULT; - goto out; - } - - /* - * While get_vaddr_frames() could be used for transient (kernel - * controlled lifetime) pinning of memory pages all current - * users establish long term (userspace controlled lifetime) - * page pinning. Treat get_vaddr_frames() like - * get_user_pages_longterm() and disallow it for filesystem-dax - * mappings. - */ - if (vma_is_fsdax(vma)) { - ret = -EOPNOTSUPP; - goto out; - } - - if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) { + ret = pin_user_pages_fast(start, nr_frames, + FOLL_FORCE | FOLL_WRITE | FOLL_LONGTERM, + (struct page **)(vec->ptrs)); + if (ret > 0) { vec->got_ref = true; vec->is_pfns = false; - ret = pin_user_pages_locked(start, nr_frames, - gup_flags, (struct page **)(vec->ptrs), &locked); - goto out; + goto out_unlocked; } + mmap_read_lock(mm); vec->got_ref = false; vec->is_pfns = true; + ret = 0; do { unsigned long *nums = frame_vector_pfns(vec); + vma = find_vma_intersection(mm, start, start + 1); + if (!vma) + break; + while (ret < nr_frames && start + PAGE_SIZE <= vma->vm_end) { err = follow_pfn(vma, start, &nums[ret]); if (err) { @@ -92,17 +77,13 @@ int get_vaddr_frames(unsigned long start, unsigned int nr_frames, start += PAGE_SIZE; ret++; } - /* - * We stop if we have enough pages or if VMA doesn't completely - * cover the tail page. - */ - if (ret >= nr_frames || start < vma->vm_end) + /* Bail out if VMA doesn't completely cover the tail page. */ + if (start < vma->vm_end) break; - vma = find_vma_intersection(mm, start, start + 1); - } while (vma && vma->vm_flags & (VM_IO | VM_PFNMAP)); + } while (ret < nr_frames); out: - if (locked) - mmap_read_unlock(mm); + mmap_read_unlock(mm); +out_unlocked: if (!ret) ret = -EFAULT; if (ret > 0) -- cgit v1.2.3 From eb83b8e3e6478845f8130622a2048ed4ec3b3be3 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Fri, 27 Nov 2020 17:41:20 +0100 Subject: media: videobuf2: Move frame_vector into media subsystem MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It's the only user. This also garbage collects the CONFIG_FRAME_VECTOR symbol from all over the tree (well just one place, somehow omap media driver still had this in its Kconfig, despite not using it). Reviewed-by: John Hubbard Acked-by: Hans Verkuil Acked-by: Mauro Carvalho Chehab Acked-by: Tomasz Figa Signed-off-by: Daniel Vetter Cc: Jason Gunthorpe Cc: Pawel Osciak Cc: Marek Szyprowski Cc: Kyungmin Park Cc: Tomasz Figa Cc: Mauro Carvalho Chehab Cc: Andrew Morton Cc: John Hubbard Cc: Jérôme Glisse Cc: Jan Kara Cc: Dan Williams Cc: linux-mm@kvack.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-samsung-soc@vger.kernel.org Cc: linux-media@vger.kernel.org Cc: Daniel Vetter Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20201127164131.2244124-7-daniel.vetter@ffwll.ch --- drivers/media/common/videobuf2/Kconfig | 1 - drivers/media/common/videobuf2/Makefile | 1 + drivers/media/common/videobuf2/frame_vector.c | 223 ++++++++++++++++++++++++++ drivers/media/platform/omap/Kconfig | 1 - include/linux/mm.h | 42 ----- include/media/frame_vector.h | 47 ++++++ include/media/videobuf2-core.h | 1 + mm/Kconfig | 3 - mm/Makefile | 1 - mm/frame_vector.c | 221 ------------------------- 10 files changed, 272 insertions(+), 269 deletions(-) create mode 100644 drivers/media/common/videobuf2/frame_vector.c create mode 100644 include/media/frame_vector.h delete mode 100644 mm/frame_vector.c (limited to 'include') diff --git a/drivers/media/common/videobuf2/Kconfig b/drivers/media/common/videobuf2/Kconfig index edbc99ebba87..d2223a12c95f 100644 --- a/drivers/media/common/videobuf2/Kconfig +++ b/drivers/media/common/videobuf2/Kconfig @@ -9,7 +9,6 @@ config VIDEOBUF2_V4L2 config VIDEOBUF2_MEMOPS tristate - select FRAME_VECTOR config VIDEOBUF2_DMA_CONTIG tristate diff --git a/drivers/media/common/videobuf2/Makefile b/drivers/media/common/videobuf2/Makefile index 77bebe8b202f..54306f8d096c 100644 --- a/drivers/media/common/videobuf2/Makefile +++ b/drivers/media/common/videobuf2/Makefile @@ -1,5 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 videobuf2-common-objs := videobuf2-core.o +videobuf2-common-objs += frame_vector.o ifeq ($(CONFIG_TRACEPOINTS),y) videobuf2-common-objs += vb2-trace.o diff --git a/drivers/media/common/videobuf2/frame_vector.c b/drivers/media/common/videobuf2/frame_vector.c new file mode 100644 index 000000000000..a0e65481a201 --- /dev/null +++ b/drivers/media/common/videobuf2/frame_vector.c @@ -0,0 +1,223 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +/** + * get_vaddr_frames() - map virtual addresses to pfns + * @start: starting user address + * @nr_frames: number of pages / pfns from start to map + * @gup_flags: flags modifying lookup behaviour + * @vec: structure which receives pages / pfns of the addresses mapped. + * It should have space for at least nr_frames entries. + * + * This function maps virtual addresses from @start and fills @vec structure + * with page frame numbers or page pointers to corresponding pages (choice + * depends on the type of the vma underlying the virtual address). If @start + * belongs to a normal vma, the function grabs reference to each of the pages + * to pin them in memory. If @start belongs to VM_IO | VM_PFNMAP vma, we don't + * touch page structures and the caller must make sure pfns aren't reused for + * anything else while he is using them. + * + * The function returns number of pages mapped which may be less than + * @nr_frames. In particular we stop mapping if there are more vmas of + * different type underlying the specified range of virtual addresses. + * When the function isn't able to map a single page, it returns error. + * + * This function takes care of grabbing mmap_lock as necessary. + */ +int get_vaddr_frames(unsigned long start, unsigned int nr_frames, + struct frame_vector *vec) +{ + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + int ret = 0; + int err; + + if (nr_frames == 0) + return 0; + + if (WARN_ON_ONCE(nr_frames > vec->nr_allocated)) + nr_frames = vec->nr_allocated; + + start = untagged_addr(start); + + ret = pin_user_pages_fast(start, nr_frames, + FOLL_FORCE | FOLL_WRITE | FOLL_LONGTERM, + (struct page **)(vec->ptrs)); + if (ret > 0) { + vec->got_ref = true; + vec->is_pfns = false; + goto out_unlocked; + } + + mmap_read_lock(mm); + vec->got_ref = false; + vec->is_pfns = true; + ret = 0; + do { + unsigned long *nums = frame_vector_pfns(vec); + + vma = find_vma_intersection(mm, start, start + 1); + if (!vma) + break; + + while (ret < nr_frames && start + PAGE_SIZE <= vma->vm_end) { + err = follow_pfn(vma, start, &nums[ret]); + if (err) { + if (ret == 0) + ret = err; + goto out; + } + start += PAGE_SIZE; + ret++; + } + /* Bail out if VMA doesn't completely cover the tail page. */ + if (start < vma->vm_end) + break; + } while (ret < nr_frames); +out: + mmap_read_unlock(mm); +out_unlocked: + if (!ret) + ret = -EFAULT; + if (ret > 0) + vec->nr_frames = ret; + return ret; +} +EXPORT_SYMBOL(get_vaddr_frames); + +/** + * put_vaddr_frames() - drop references to pages if get_vaddr_frames() acquired + * them + * @vec: frame vector to put + * + * Drop references to pages if get_vaddr_frames() acquired them. We also + * invalidate the frame vector so that it is prepared for the next call into + * get_vaddr_frames(). + */ +void put_vaddr_frames(struct frame_vector *vec) +{ + struct page **pages; + + if (!vec->got_ref) + goto out; + pages = frame_vector_pages(vec); + /* + * frame_vector_pages() might needed to do a conversion when + * get_vaddr_frames() got pages but vec was later converted to pfns. + * But it shouldn't really fail to convert pfns back... + */ + if (WARN_ON(IS_ERR(pages))) + goto out; + + unpin_user_pages(pages, vec->nr_frames); + vec->got_ref = false; +out: + vec->nr_frames = 0; +} +EXPORT_SYMBOL(put_vaddr_frames); + +/** + * frame_vector_to_pages - convert frame vector to contain page pointers + * @vec: frame vector to convert + * + * Convert @vec to contain array of page pointers. If the conversion is + * successful, return 0. Otherwise return an error. Note that we do not grab + * page references for the page structures. + */ +int frame_vector_to_pages(struct frame_vector *vec) +{ + int i; + unsigned long *nums; + struct page **pages; + + if (!vec->is_pfns) + return 0; + nums = frame_vector_pfns(vec); + for (i = 0; i < vec->nr_frames; i++) + if (!pfn_valid(nums[i])) + return -EINVAL; + pages = (struct page **)nums; + for (i = 0; i < vec->nr_frames; i++) + pages[i] = pfn_to_page(nums[i]); + vec->is_pfns = false; + return 0; +} +EXPORT_SYMBOL(frame_vector_to_pages); + +/** + * frame_vector_to_pfns - convert frame vector to contain pfns + * @vec: frame vector to convert + * + * Convert @vec to contain array of pfns. + */ +void frame_vector_to_pfns(struct frame_vector *vec) +{ + int i; + unsigned long *nums; + struct page **pages; + + if (vec->is_pfns) + return; + pages = (struct page **)(vec->ptrs); + nums = (unsigned long *)pages; + for (i = 0; i < vec->nr_frames; i++) + nums[i] = page_to_pfn(pages[i]); + vec->is_pfns = true; +} +EXPORT_SYMBOL(frame_vector_to_pfns); + +/** + * frame_vector_create() - allocate & initialize structure for pinned pfns + * @nr_frames: number of pfns slots we should reserve + * + * Allocate and initialize struct pinned_pfns to be able to hold @nr_pfns + * pfns. + */ +struct frame_vector *frame_vector_create(unsigned int nr_frames) +{ + struct frame_vector *vec; + int size = sizeof(struct frame_vector) + sizeof(void *) * nr_frames; + + if (WARN_ON_ONCE(nr_frames == 0)) + return NULL; + /* + * This is absurdly high. It's here just to avoid strange effects when + * arithmetics overflows. + */ + if (WARN_ON_ONCE(nr_frames > INT_MAX / sizeof(void *) / 2)) + return NULL; + /* + * Avoid higher order allocations, use vmalloc instead. It should + * be rare anyway. + */ + vec = kvmalloc(size, GFP_KERNEL); + if (!vec) + return NULL; + vec->nr_allocated = nr_frames; + vec->nr_frames = 0; + return vec; +} +EXPORT_SYMBOL(frame_vector_create); + +/** + * frame_vector_destroy() - free memory allocated to carry frame vector + * @vec: Frame vector to free + * + * Free structure allocated by frame_vector_create() to carry frames. + */ +void frame_vector_destroy(struct frame_vector *vec) +{ + /* Make sure put_vaddr_frames() got called properly... */ + VM_BUG_ON(vec->nr_frames > 0); + kvfree(vec); +} +EXPORT_SYMBOL(frame_vector_destroy); diff --git a/drivers/media/platform/omap/Kconfig b/drivers/media/platform/omap/Kconfig index f73b5893220d..de16de46c0f4 100644 --- a/drivers/media/platform/omap/Kconfig +++ b/drivers/media/platform/omap/Kconfig @@ -12,6 +12,5 @@ config VIDEO_OMAP2_VOUT depends on VIDEO_V4L2 select VIDEOBUF2_DMA_CONTIG select OMAP2_VRFB if ARCH_OMAP2 || ARCH_OMAP3 - select FRAME_VECTOR help V4L2 Display driver support for OMAP2/3 based boards. diff --git a/include/linux/mm.h b/include/linux/mm.h index 2e7b1d048df9..049439b65553 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1754,48 +1754,6 @@ int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc); int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc, struct task_struct *task, bool bypass_rlim); -/* Container for pinned pfns / pages */ -struct frame_vector { - unsigned int nr_allocated; /* Number of frames we have space for */ - unsigned int nr_frames; /* Number of frames stored in ptrs array */ - bool got_ref; /* Did we pin pages by getting page ref? */ - bool is_pfns; /* Does array contain pages or pfns? */ - void *ptrs[]; /* Array of pinned pfns / pages. Use - * pfns_vector_pages() or pfns_vector_pfns() - * for access */ -}; - -struct frame_vector *frame_vector_create(unsigned int nr_frames); -void frame_vector_destroy(struct frame_vector *vec); -int get_vaddr_frames(unsigned long start, unsigned int nr_pfns, - struct frame_vector *vec); -void put_vaddr_frames(struct frame_vector *vec); -int frame_vector_to_pages(struct frame_vector *vec); -void frame_vector_to_pfns(struct frame_vector *vec); - -static inline unsigned int frame_vector_count(struct frame_vector *vec) -{ - return vec->nr_frames; -} - -static inline struct page **frame_vector_pages(struct frame_vector *vec) -{ - if (vec->is_pfns) { - int err = frame_vector_to_pages(vec); - - if (err) - return ERR_PTR(err); - } - return (struct page **)(vec->ptrs); -} - -static inline unsigned long *frame_vector_pfns(struct frame_vector *vec) -{ - if (!vec->is_pfns) - frame_vector_to_pfns(vec); - return (unsigned long *)(vec->ptrs); -} - struct kvec; int get_kernel_pages(const struct kvec *iov, int nr_pages, int write, struct page **pages); diff --git a/include/media/frame_vector.h b/include/media/frame_vector.h new file mode 100644 index 000000000000..bfed1710dc24 --- /dev/null +++ b/include/media/frame_vector.h @@ -0,0 +1,47 @@ +// SPDX-License-Identifier: GPL-2.0 +#ifndef _MEDIA_FRAME_VECTOR_H +#define _MEDIA_FRAME_VECTOR_H + +/* Container for pinned pfns / pages in frame_vector.c */ +struct frame_vector { + unsigned int nr_allocated; /* Number of frames we have space for */ + unsigned int nr_frames; /* Number of frames stored in ptrs array */ + bool got_ref; /* Did we pin pages by getting page ref? */ + bool is_pfns; /* Does array contain pages or pfns? */ + void *ptrs[]; /* Array of pinned pfns / pages. Use + * pfns_vector_pages() or pfns_vector_pfns() + * for access */ +}; + +struct frame_vector *frame_vector_create(unsigned int nr_frames); +void frame_vector_destroy(struct frame_vector *vec); +int get_vaddr_frames(unsigned long start, unsigned int nr_pfns, + struct frame_vector *vec); +void put_vaddr_frames(struct frame_vector *vec); +int frame_vector_to_pages(struct frame_vector *vec); +void frame_vector_to_pfns(struct frame_vector *vec); + +static inline unsigned int frame_vector_count(struct frame_vector *vec) +{ + return vec->nr_frames; +} + +static inline struct page **frame_vector_pages(struct frame_vector *vec) +{ + if (vec->is_pfns) { + int err = frame_vector_to_pages(vec); + + if (err) + return ERR_PTR(err); + } + return (struct page **)(vec->ptrs); +} + +static inline unsigned long *frame_vector_pfns(struct frame_vector *vec) +{ + if (!vec->is_pfns) + frame_vector_to_pfns(vec); + return (unsigned long *)(vec->ptrs); +} + +#endif /* _MEDIA_FRAME_VECTOR_H */ diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h index 61969402a0e3..799ba61b5b6f 100644 --- a/include/media/videobuf2-core.h +++ b/include/media/videobuf2-core.h @@ -18,6 +18,7 @@ #include #include #include +#include #define VB2_MAX_FRAME (32) #define VB2_MAX_PLANES (8) diff --git a/mm/Kconfig b/mm/Kconfig index f730605b8dcf..24c045b24b95 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -804,9 +804,6 @@ config DEVICE_PRIVATE config VMAP_PFN bool -config FRAME_VECTOR - bool - config ARCH_USES_HIGH_VMA_FLAGS bool config ARCH_HAS_PKEYS diff --git a/mm/Makefile b/mm/Makefile index b6cd2fffa492..135bbb65511a 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -110,7 +110,6 @@ obj-$(CONFIG_PAGE_EXTENSION) += page_ext.o obj-$(CONFIG_CMA_DEBUGFS) += cma_debug.o obj-$(CONFIG_USERFAULTFD) += userfaultfd.o obj-$(CONFIG_IDLE_PAGE_TRACKING) += page_idle.o -obj-$(CONFIG_FRAME_VECTOR) += frame_vector.o obj-$(CONFIG_DEBUG_PAGE_REF) += debug_page_ref.o obj-$(CONFIG_HARDENED_USERCOPY) += usercopy.o obj-$(CONFIG_PERCPU_STATS) += percpu-stats.o diff --git a/mm/frame_vector.c b/mm/frame_vector.c deleted file mode 100644 index f8c34b895c76..000000000000 --- a/mm/frame_vector.c +++ /dev/null @@ -1,221 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include -#include -#include -#include -#include -#include -#include -#include - -/** - * get_vaddr_frames() - map virtual addresses to pfns - * @start: starting user address - * @nr_frames: number of pages / pfns from start to map - * @gup_flags: flags modifying lookup behaviour - * @vec: structure which receives pages / pfns of the addresses mapped. - * It should have space for at least nr_frames entries. - * - * This function maps virtual addresses from @start and fills @vec structure - * with page frame numbers or page pointers to corresponding pages (choice - * depends on the type of the vma underlying the virtual address). If @start - * belongs to a normal vma, the function grabs reference to each of the pages - * to pin them in memory. If @start belongs to VM_IO | VM_PFNMAP vma, we don't - * touch page structures and the caller must make sure pfns aren't reused for - * anything else while he is using them. - * - * The function returns number of pages mapped which may be less than - * @nr_frames. In particular we stop mapping if there are more vmas of - * different type underlying the specified range of virtual addresses. - * When the function isn't able to map a single page, it returns error. - * - * This function takes care of grabbing mmap_lock as necessary. - */ -int get_vaddr_frames(unsigned long start, unsigned int nr_frames, - struct frame_vector *vec) -{ - struct mm_struct *mm = current->mm; - struct vm_area_struct *vma; - int ret = 0; - int err; - - if (nr_frames == 0) - return 0; - - if (WARN_ON_ONCE(nr_frames > vec->nr_allocated)) - nr_frames = vec->nr_allocated; - - start = untagged_addr(start); - - ret = pin_user_pages_fast(start, nr_frames, - FOLL_FORCE | FOLL_WRITE | FOLL_LONGTERM, - (struct page **)(vec->ptrs)); - if (ret > 0) { - vec->got_ref = true; - vec->is_pfns = false; - goto out_unlocked; - } - - mmap_read_lock(mm); - vec->got_ref = false; - vec->is_pfns = true; - ret = 0; - do { - unsigned long *nums = frame_vector_pfns(vec); - - vma = find_vma_intersection(mm, start, start + 1); - if (!vma) - break; - - while (ret < nr_frames && start + PAGE_SIZE <= vma->vm_end) { - err = follow_pfn(vma, start, &nums[ret]); - if (err) { - if (ret == 0) - ret = err; - goto out; - } - start += PAGE_SIZE; - ret++; - } - /* Bail out if VMA doesn't completely cover the tail page. */ - if (start < vma->vm_end) - break; - } while (ret < nr_frames); -out: - mmap_read_unlock(mm); -out_unlocked: - if (!ret) - ret = -EFAULT; - if (ret > 0) - vec->nr_frames = ret; - return ret; -} -EXPORT_SYMBOL(get_vaddr_frames); - -/** - * put_vaddr_frames() - drop references to pages if get_vaddr_frames() acquired - * them - * @vec: frame vector to put - * - * Drop references to pages if get_vaddr_frames() acquired them. We also - * invalidate the frame vector so that it is prepared for the next call into - * get_vaddr_frames(). - */ -void put_vaddr_frames(struct frame_vector *vec) -{ - struct page **pages; - - if (!vec->got_ref) - goto out; - pages = frame_vector_pages(vec); - /* - * frame_vector_pages() might needed to do a conversion when - * get_vaddr_frames() got pages but vec was later converted to pfns. - * But it shouldn't really fail to convert pfns back... - */ - if (WARN_ON(IS_ERR(pages))) - goto out; - - unpin_user_pages(pages, vec->nr_frames); - vec->got_ref = false; -out: - vec->nr_frames = 0; -} -EXPORT_SYMBOL(put_vaddr_frames); - -/** - * frame_vector_to_pages - convert frame vector to contain page pointers - * @vec: frame vector to convert - * - * Convert @vec to contain array of page pointers. If the conversion is - * successful, return 0. Otherwise return an error. Note that we do not grab - * page references for the page structures. - */ -int frame_vector_to_pages(struct frame_vector *vec) -{ - int i; - unsigned long *nums; - struct page **pages; - - if (!vec->is_pfns) - return 0; - nums = frame_vector_pfns(vec); - for (i = 0; i < vec->nr_frames; i++) - if (!pfn_valid(nums[i])) - return -EINVAL; - pages = (struct page **)nums; - for (i = 0; i < vec->nr_frames; i++) - pages[i] = pfn_to_page(nums[i]); - vec->is_pfns = false; - return 0; -} -EXPORT_SYMBOL(frame_vector_to_pages); - -/** - * frame_vector_to_pfns - convert frame vector to contain pfns - * @vec: frame vector to convert - * - * Convert @vec to contain array of pfns. - */ -void frame_vector_to_pfns(struct frame_vector *vec) -{ - int i; - unsigned long *nums; - struct page **pages; - - if (vec->is_pfns) - return; - pages = (struct page **)(vec->ptrs); - nums = (unsigned long *)pages; - for (i = 0; i < vec->nr_frames; i++) - nums[i] = page_to_pfn(pages[i]); - vec->is_pfns = true; -} -EXPORT_SYMBOL(frame_vector_to_pfns); - -/** - * frame_vector_create() - allocate & initialize structure for pinned pfns - * @nr_frames: number of pfns slots we should reserve - * - * Allocate and initialize struct pinned_pfns to be able to hold @nr_pfns - * pfns. - */ -struct frame_vector *frame_vector_create(unsigned int nr_frames) -{ - struct frame_vector *vec; - int size = sizeof(struct frame_vector) + sizeof(void *) * nr_frames; - - if (WARN_ON_ONCE(nr_frames == 0)) - return NULL; - /* - * This is absurdly high. It's here just to avoid strange effects when - * arithmetics overflows. - */ - if (WARN_ON_ONCE(nr_frames > INT_MAX / sizeof(void *) / 2)) - return NULL; - /* - * Avoid higher order allocations, use vmalloc instead. It should - * be rare anyway. - */ - vec = kvmalloc(size, GFP_KERNEL); - if (!vec) - return NULL; - vec->nr_allocated = nr_frames; - vec->nr_frames = 0; - return vec; -} -EXPORT_SYMBOL(frame_vector_create); - -/** - * frame_vector_destroy() - free memory allocated to carry frame vector - * @vec: Frame vector to free - * - * Free structure allocated by frame_vector_create() to carry frames. - */ -void frame_vector_destroy(struct frame_vector *vec) -{ - /* Make sure put_vaddr_frames() got called properly... */ - VM_BUG_ON(vec->nr_frames > 0); - kvfree(vec); -} -EXPORT_SYMBOL(frame_vector_destroy); -- cgit v1.2.3 From 96667f8a4382db9ed042332ca6ee165ae9b91307 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Fri, 27 Nov 2020 17:41:21 +0100 Subject: mm: Close race in generic_access_phys MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Way back it was a reasonable assumptions that iomem mappings never change the pfn range they point at. But this has changed: - gpu drivers dynamically manage their memory nowadays, invalidating ptes with unmap_mapping_range when buffers get moved - contiguous dma allocations have moved from dedicated carvetouts to cma regions. This means if we miss the unmap the pfn might contain pagecache or anon memory (well anything allocated with GFP_MOVEABLE) - even /dev/mem now invalidates mappings when the kernel requests that iomem region when CONFIG_IO_STRICT_DEVMEM is set, see 3234ac664a87 ("/dev/mem: Revoke mappings when a driver claims the region") Accessing pfns obtained from ptes without holding all the locks is therefore no longer a good idea. Fix this. Since ioremap might need to manipulate pagetables too we need to drop the pt lock and have a retry loop if we raced. While at it, also add kerneldoc and improve the comment for the vma_ops->access function. It's for accessing, not for moving the memory from iomem to system memory, as the old comment seemed to suggest. References: 28b2ee20c7cb ("access_process_vm device memory infrastructure") Signed-off-by: Daniel Vetter Cc: Jason Gunthorpe Cc: Dan Williams Cc: Kees Cook Cc: Benjamin Herrensmidt Cc: Dave Airlie Cc: Andrew Morton Cc: John Hubbard Cc: Jérôme Glisse Cc: Jan Kara Cc: Dan Williams Cc: linux-mm@kvack.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-samsung-soc@vger.kernel.org Cc: linux-media@vger.kernel.org Cc: Chris Wilson Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20201127164131.2244124-8-daniel.vetter@ffwll.ch --- include/linux/mm.h | 3 ++- mm/memory.c | 46 +++++++++++++++++++++++++++++++++++++++++++--- 2 files changed, 45 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 049439b65553..c9900aedc195 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -590,7 +590,8 @@ struct vm_operations_struct { vm_fault_t (*pfn_mkwrite)(struct vm_fault *vmf); /* called by access_process_vm when get_user_pages() fails, typically - * for use by special VMAs that can switch between memory and hardware + * for use by special VMAs. See also generic_access_phys() for a generic + * implementation useful for any iomem mapping. */ int (*access)(struct vm_area_struct *vma, unsigned long addr, void *buf, int len, int write); diff --git a/mm/memory.c b/mm/memory.c index feff48e1465a..8079c181efff 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4834,28 +4834,68 @@ out: return ret; } +/** + * generic_access_phys - generic implementation for iomem mmap access + * @vma: the vma to access + * @addr: userspace addres, not relative offset within @vma + * @buf: buffer to read/write + * @len: length of transfer + * @write: set to FOLL_WRITE when writing, otherwise reading + * + * This is a generic implementation for &vm_operations_struct.access for an + * iomem mapping. This callback is used by access_process_vm() when the @vma is + * not page based. + */ int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, void *buf, int len, int write) { resource_size_t phys_addr; unsigned long prot = 0; void __iomem *maddr; - int offset = addr & (PAGE_SIZE-1); + pte_t *ptep, pte; + spinlock_t *ptl; + int offset = offset_in_page(addr); + int ret = -EINVAL; + + if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) + return -EINVAL; + +retry: + if (follow_pte(vma->vm_mm, addr, NULL, &ptep, NULL, &ptl)) + return -EINVAL; + pte = *ptep; + pte_unmap_unlock(ptep, ptl); - if (follow_phys(vma, addr, write, &prot, &phys_addr)) + prot = pgprot_val(pte_pgprot(pte)); + phys_addr = (resource_size_t)pte_pfn(pte) << PAGE_SHIFT; + + if ((write & FOLL_WRITE) && !pte_write(pte)) return -EINVAL; maddr = ioremap_prot(phys_addr, PAGE_ALIGN(len + offset), prot); if (!maddr) return -ENOMEM; + if (follow_pte(vma->vm_mm, addr, NULL, &ptep, NULL, &ptl)) + goto out_unmap; + + if (!pte_same(pte, *ptep)) { + pte_unmap_unlock(ptep, ptl); + iounmap(maddr); + + goto retry; + } + if (write) memcpy_toio(maddr + offset, buf, len); else memcpy_fromio(buf, maddr + offset, len); + ret = len; + pte_unmap_unlock(ptep, ptl); +out_unmap: iounmap(maddr); - return len; + return ret; } EXPORT_SYMBOL_GPL(generic_access_phys); #endif -- cgit v1.2.3 From 71a1d8ed900f8cf53151beff17e3e2ff8e9283a1 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Fri, 27 Nov 2020 17:41:24 +0100 Subject: resource: Move devmem revoke code to resource framework MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We want all iomem mmaps to consistently revoke ptes when the kernel takes over and CONFIG_IO_STRICT_DEVMEM is enabled. This includes the pci bar mmaps available through procfs and sysfs, which currently do not revoke mappings. To prepare for this, move the code from the /dev/kmem driver to kernel/resource.c. During review Jason spotted that barriers are used somewhat inconsistently. Fix that up while we shuffle this code, since it doesn't have an actual impact at runtime. Otherwise no semantic and behavioural changes intended, just code extraction and adjusting comments and names. Reviewed-by: Greg Kroah-Hartman Signed-off-by: Daniel Vetter Cc: Jason Gunthorpe Cc: Kees Cook Cc: Dan Williams Cc: Andrew Morton Cc: John Hubbard Cc: Jérôme Glisse Cc: Jan Kara Cc: Dan Williams Cc: linux-mm@kvack.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-samsung-soc@vger.kernel.org Cc: linux-media@vger.kernel.org Cc: Arnd Bergmann Cc: Greg Kroah-Hartman Cc: Daniel Vetter Cc: David Hildenbrand Cc: "Rafael J. Wysocki" Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20201127164131.2244124-11-daniel.vetter@ffwll.ch --- drivers/char/mem.c | 85 +------------------------------------------ include/linux/ioport.h | 6 +--- kernel/resource.c | 98 +++++++++++++++++++++++++++++++++++++++++++++++++- 3 files changed, 99 insertions(+), 90 deletions(-) (limited to 'include') diff --git a/drivers/char/mem.c b/drivers/char/mem.c index 7dcf9e4ea79d..43c871dc7477 100644 --- a/drivers/char/mem.c +++ b/drivers/char/mem.c @@ -31,9 +31,6 @@ #include #include #include -#include -#include -#include #ifdef CONFIG_IA64 # include @@ -836,42 +833,6 @@ static loff_t memory_lseek(struct file *file, loff_t offset, int orig) return ret; } -static struct inode *devmem_inode; - -#ifdef CONFIG_IO_STRICT_DEVMEM -void revoke_devmem(struct resource *res) -{ - /* pairs with smp_store_release() in devmem_init_inode() */ - struct inode *inode = smp_load_acquire(&devmem_inode); - - /* - * Check that the initialization has completed. Losing the race - * is ok because it means drivers are claiming resources before - * the fs_initcall level of init and prevent /dev/mem from - * establishing mappings. - */ - if (!inode) - return; - - /* - * The expectation is that the driver has successfully marked - * the resource busy by this point, so devmem_is_allowed() - * should start returning false, however for performance this - * does not iterate the entire resource range. - */ - if (devmem_is_allowed(PHYS_PFN(res->start)) && - devmem_is_allowed(PHYS_PFN(res->end))) { - /* - * *cringe* iomem=relaxed says "go ahead, what's the - * worst that can happen?" - */ - return; - } - - unmap_mapping_range(inode->i_mapping, res->start, resource_size(res), 1); -} -#endif - static int open_port(struct inode *inode, struct file *filp) { int rc; @@ -891,7 +852,7 @@ static int open_port(struct inode *inode, struct file *filp) * revocations when drivers want to take over a /dev/mem mapped * range. */ - filp->f_mapping = inode->i_mapping; + filp->f_mapping = iomem_get_mapping(); return 0; } @@ -1023,48 +984,6 @@ static char *mem_devnode(struct device *dev, umode_t *mode) static struct class *mem_class; -static int devmem_fs_init_fs_context(struct fs_context *fc) -{ - return init_pseudo(fc, DEVMEM_MAGIC) ? 0 : -ENOMEM; -} - -static struct file_system_type devmem_fs_type = { - .name = "devmem", - .owner = THIS_MODULE, - .init_fs_context = devmem_fs_init_fs_context, - .kill_sb = kill_anon_super, -}; - -static int devmem_init_inode(void) -{ - static struct vfsmount *devmem_vfs_mount; - static int devmem_fs_cnt; - struct inode *inode; - int rc; - - rc = simple_pin_fs(&devmem_fs_type, &devmem_vfs_mount, &devmem_fs_cnt); - if (rc < 0) { - pr_err("Cannot mount /dev/mem pseudo filesystem: %d\n", rc); - return rc; - } - - inode = alloc_anon_inode(devmem_vfs_mount->mnt_sb); - if (IS_ERR(inode)) { - rc = PTR_ERR(inode); - pr_err("Cannot allocate inode for /dev/mem: %d\n", rc); - simple_release_fs(&devmem_vfs_mount, &devmem_fs_cnt); - return rc; - } - - /* - * Publish /dev/mem initialized. - * Pairs with smp_load_acquire() in revoke_devmem(). - */ - smp_store_release(&devmem_inode, inode); - - return 0; -} - static int __init chr_dev_init(void) { int minor; @@ -1086,8 +1005,6 @@ static int __init chr_dev_init(void) */ if ((minor == DEVPORT_MINOR) && !arch_has_dev_port()) continue; - if ((minor == DEVMEM_MINOR) && devmem_init_inode() != 0) - continue; device_create(mem_class, NULL, MKDEV(MEM_MAJOR, minor), NULL, devlist[minor].name); diff --git a/include/linux/ioport.h b/include/linux/ioport.h index fe48b7840665..55de385c839c 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -334,11 +334,7 @@ static inline void irqresource_disabled(struct resource *res, u32 irq) res->flags = IORESOURCE_IRQ | IORESOURCE_DISABLED | IORESOURCE_UNSET; } -#ifdef CONFIG_IO_STRICT_DEVMEM -void revoke_devmem(struct resource *res); -#else -static inline void revoke_devmem(struct resource *res) { }; -#endif +extern struct address_space *iomem_get_mapping(void); #endif /* __ASSEMBLY__ */ #endif /* _LINUX_IOPORT_H */ diff --git a/kernel/resource.c b/kernel/resource.c index 833394f9c608..627e61b0c124 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -18,12 +18,15 @@ #include #include #include +#include #include #include #include #include #include +#include #include +#include #include @@ -1119,6 +1122,55 @@ resource_size_t resource_alignment(struct resource *res) static DECLARE_WAIT_QUEUE_HEAD(muxed_resource_wait); +static struct inode *iomem_inode; + +#ifdef CONFIG_IO_STRICT_DEVMEM +static void revoke_iomem(struct resource *res) +{ + /* pairs with smp_store_release() in iomem_init_inode() */ + struct inode *inode = smp_load_acquire(&iomem_inode); + + /* + * Check that the initialization has completed. Losing the race + * is ok because it means drivers are claiming resources before + * the fs_initcall level of init and prevent iomem_get_mapping users + * from establishing mappings. + */ + if (!inode) + return; + + /* + * The expectation is that the driver has successfully marked + * the resource busy by this point, so devmem_is_allowed() + * should start returning false, however for performance this + * does not iterate the entire resource range. + */ + if (devmem_is_allowed(PHYS_PFN(res->start)) && + devmem_is_allowed(PHYS_PFN(res->end))) { + /* + * *cringe* iomem=relaxed says "go ahead, what's the + * worst that can happen?" + */ + return; + } + + unmap_mapping_range(inode->i_mapping, res->start, resource_size(res), 1); +} +#else +static void revoke_iomem(struct resource *res) {} +#endif + +struct address_space *iomem_get_mapping(void) +{ + /* + * This function is only called from file open paths, hence guaranteed + * that fs_initcalls have completed and no need to check for NULL. But + * since revoke_iomem can be called before the initcall we still need + * the barrier to appease checkers. + */ + return smp_load_acquire(&iomem_inode)->i_mapping; +} + /** * __request_region - create a new busy resource region * @parent: parent resource descriptor @@ -1186,7 +1238,7 @@ struct resource * __request_region(struct resource *parent, write_unlock(&resource_lock); if (res && orig_parent == &iomem_resource) - revoke_devmem(res); + revoke_iomem(res); return res; } @@ -1786,4 +1838,48 @@ static int __init strict_iomem(char *str) return 1; } +static int iomem_fs_init_fs_context(struct fs_context *fc) +{ + return init_pseudo(fc, DEVMEM_MAGIC) ? 0 : -ENOMEM; +} + +static struct file_system_type iomem_fs_type = { + .name = "iomem", + .owner = THIS_MODULE, + .init_fs_context = iomem_fs_init_fs_context, + .kill_sb = kill_anon_super, +}; + +static int __init iomem_init_inode(void) +{ + static struct vfsmount *iomem_vfs_mount; + static int iomem_fs_cnt; + struct inode *inode; + int rc; + + rc = simple_pin_fs(&iomem_fs_type, &iomem_vfs_mount, &iomem_fs_cnt); + if (rc < 0) { + pr_err("Cannot mount iomem pseudo filesystem: %d\n", rc); + return rc; + } + + inode = alloc_anon_inode(iomem_vfs_mount->mnt_sb); + if (IS_ERR(inode)) { + rc = PTR_ERR(inode); + pr_err("Cannot allocate inode for iomem: %d\n", rc); + simple_release_fs(&iomem_vfs_mount, &iomem_fs_cnt); + return rc; + } + + /* + * Publish iomem revocation inode initialized. + * Pairs with smp_load_acquire() in revoke_iomem(). + */ + smp_store_release(&iomem_inode, inode); + + return 0; +} + +fs_initcall(iomem_init_inode); + __setup("iomem=", strict_iomem); -- cgit v1.2.3 From 74b30195395c406c787280a77ae55aed82dbbfc7 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Fri, 27 Nov 2020 17:41:25 +0100 Subject: sysfs: Support zapping of binary attr mmaps MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We want to be able to revoke pci mmaps so that the same access rules applies as for /dev/kmem. Revoke support for devmem was added in 3234ac664a87 ("/dev/mem: Revoke mappings when a driver claims the region"). The simplest way to achieve this is by having the same filp->f_mapping for all mappings, so that unmap_mapping_range can find them all, no matter through which file they've been created. Since this must be set at open time we need sysfs support for this. Add an optional mapping parameter bin_attr, which is only consulted when there's also an mmap callback, since without mmap support allowing to adjust the ->f_mapping makes no sense. Reviewed-by: Greg Kroah-Hartman Signed-off-by: Daniel Vetter Cc: Jason Gunthorpe Cc: Kees Cook Cc: Dan Williams Cc: Andrew Morton Cc: John Hubbard Cc: Jérôme Glisse Cc: Jan Kara Cc: Dan Williams Cc: linux-mm@kvack.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-samsung-soc@vger.kernel.org Cc: linux-media@vger.kernel.org Cc: Bjorn Helgaas Cc: linux-pci@vger.kernel.org Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Cc: Christian Brauner Cc: "David S. Miller" Cc: Michael Ellerman Cc: Sourabh Jain Cc: Daniel Vetter Cc: Mauro Carvalho Chehab Cc: Nayna Jain Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20201127164131.2244124-12-daniel.vetter@ffwll.ch --- fs/sysfs/file.c | 11 +++++++++++ include/linux/sysfs.h | 2 ++ 2 files changed, 13 insertions(+) (limited to 'include') diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 96d0da65e088..9aefa7779b29 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -170,6 +170,16 @@ static int sysfs_kf_bin_mmap(struct kernfs_open_file *of, return battr->mmap(of->file, kobj, battr, vma); } +static int sysfs_kf_bin_open(struct kernfs_open_file *of) +{ + struct bin_attribute *battr = of->kn->priv; + + if (battr->mapping) + of->file->f_mapping = battr->mapping; + + return 0; +} + void sysfs_notify(struct kobject *kobj, const char *dir, const char *attr) { struct kernfs_node *kn = kobj->sd, *tmp; @@ -241,6 +251,7 @@ static const struct kernfs_ops sysfs_bin_kfops_mmap = { .read = sysfs_kf_bin_read, .write = sysfs_kf_bin_write, .mmap = sysfs_kf_bin_mmap, + .open = sysfs_kf_bin_open, }; int sysfs_add_file_mode_ns(struct kernfs_node *parent, diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 2caa34c1ca1a..d76a1ddf83a3 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -164,11 +164,13 @@ __ATTRIBUTE_GROUPS(_name) struct file; struct vm_area_struct; +struct address_space; struct bin_attribute { struct attribute attr; size_t size; void *private; + struct address_space *mapping; ssize_t (*read)(struct file *, struct kobject *, struct bin_attribute *, char *, loff_t, size_t); ssize_t (*write)(struct file *, struct kobject *, struct bin_attribute *, -- cgit v1.2.3 From cc3283f8f41f741fbaef63d0503d8fb4a7919100 Mon Sep 17 00:00:00 2001 From: Simon Ser Date: Sun, 10 Jan 2021 13:51:03 +0100 Subject: drm/fourcc: fix Amlogic format modifier masks The comment says the layout and options use 8 bits, and the shift uses 8 bits. However the mask is 0xf, ie. 0b00001111 (4 bits). This could be surprising when introducing new layouts or options that take more than 4 bits, as this would silently drop the high bits. Make the masks consistent with the comment and the shift. Found when writing a drm_info patch [1]. [1]: https://github.com/ascent12/drm_info/pull/67 Signed-off-by: Simon Ser Fixes: d6528ec88309 ("drm/fourcc: Add modifier definitions for describing Amlogic Video Framebuffer Compression") Cc: Neil Armstrong Cc: Sam Ravnborg Cc: Kevin Hilman Cc: Daniel Vetter Acked-by: Neil Armstrong Link: https://patchwork.freedesktop.org/patch/msgid/20210110125103.15447-1-contact@emersion.fr --- include/uapi/drm/drm_fourcc.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h index 723c8e23ca87..5f42a14481bd 100644 --- a/include/uapi/drm/drm_fourcc.h +++ b/include/uapi/drm/drm_fourcc.h @@ -1036,9 +1036,9 @@ drm_fourcc_canonicalize_nvidia_format_mod(__u64 modifier) * Not all combinations are valid, and different SoCs may support different * combinations of layout and options. */ -#define __fourcc_mod_amlogic_layout_mask 0xf +#define __fourcc_mod_amlogic_layout_mask 0xff #define __fourcc_mod_amlogic_options_shift 8 -#define __fourcc_mod_amlogic_options_mask 0xf +#define __fourcc_mod_amlogic_options_mask 0xff #define DRM_FORMAT_MOD_AMLOGIC_FBC(__layout, __options) \ fourcc_mod_code(AMLOGIC, \ -- cgit v1.2.3 From b90f3726ea3811421f56757e866f01f6e2bb37d6 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 6 Jan 2021 18:33:04 -0800 Subject: linux/clk.h: use correct kernel-doc notation for 2 functions Fix kernel-doc notation for 2 functions so that the generated html is correct. Currently it skips all text between the ':' and the '-', so "[un]register a clock rate" is missing. Fixes: 86bcfa2e87c4 ("clk: add pr_debug & kerneldoc around clk notifiers") Signed-off-by: Randy Dunlap Cc: Mike Turquette Cc: Russell King Cc: linux-clk@vger.kernel.org Link: https://lore.kernel.org/r/20210107023304.24442-1-rdunlap@infradead.org Signed-off-by: Stephen Boyd --- include/linux/clk.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/clk.h b/include/linux/clk.h index 31ff1bf1b79f..45e698b74178 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -92,7 +92,7 @@ struct clk_bulk_data { #ifdef CONFIG_COMMON_CLK /** - * clk_notifier_register: register a clock rate-change notifier callback + * clk_notifier_register - register a clock rate-change notifier callback * @clk: clock whose rate we are interested in * @nb: notifier block with callback function pointer * @@ -103,7 +103,7 @@ struct clk_bulk_data { int clk_notifier_register(struct clk *clk, struct notifier_block *nb); /** - * clk_notifier_unregister: unregister a clock rate-change notifier callback + * clk_notifier_unregister - unregister a clock rate-change notifier callback * @clk: clock whose rate we are no longer interested in * @nb: notifier block which will be unregistered */ -- cgit v1.2.3 From 3188677d4901fbfb7a363ab2558e0a4bc76deecb Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Sun, 10 Jan 2021 15:01:59 +0100 Subject: power: supply: max8903: Absorb pdata header The platform data header is not included by any other file in the kernel but the driver itself. Decomission the stand-alone header and absorb it into the driver itself. Cc: Chris Lapa Cc: MyungJoo Ham Signed-off-by: Linus Walleij Signed-off-by: Sebastian Reichel --- drivers/power/supply/max8903_charger.c | 32 ++++++++++++++++++++++++- include/linux/power/max8903_charger.h | 43 ---------------------------------- 2 files changed, 31 insertions(+), 44 deletions(-) delete mode 100644 include/linux/power/max8903_charger.h (limited to 'include') diff --git a/drivers/power/supply/max8903_charger.c b/drivers/power/supply/max8903_charger.c index 0bd39b0cc257..ab1aa7df985e 100644 --- a/drivers/power/supply/max8903_charger.c +++ b/drivers/power/supply/max8903_charger.c @@ -15,7 +15,37 @@ #include #include #include -#include + +struct max8903_pdata { + /* + * GPIOs + * cen, chg, flt, dcm and usus are optional. + * dok and uok are not optional depending on the status of + * dc_valid and usb_valid. + */ + int cen; /* Charger Enable input */ + int dok; /* DC(Adapter) Power OK output */ + int uok; /* USB Power OK output */ + int chg; /* Charger status output */ + int flt; /* Fault output */ + int dcm; /* Current-Limit Mode input (1: DC, 2: USB) */ + int usus; /* USB Suspend Input (1: suspended) */ + + /* + * DC(Adapter/TA) is wired + * When dc_valid is true, + * dok should be valid. + * + * At least one of dc_valid or usb_valid should be true. + */ + bool dc_valid; + /* + * USB is wired + * When usb_valid is true, + * uok should be valid. + */ + bool usb_valid; +}; struct max8903_data { struct max8903_pdata *pdata; diff --git a/include/linux/power/max8903_charger.h b/include/linux/power/max8903_charger.h deleted file mode 100644 index 02f94a1b323b..000000000000 --- a/include/linux/power/max8903_charger.h +++ /dev/null @@ -1,43 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * max8903_charger.h - Maxim 8903 USB/Adapter Charger Driver - * - * Copyright (C) 2011 Samsung Electronics - * MyungJoo Ham - */ - -#ifndef __MAX8903_CHARGER_H__ -#define __MAX8903_CHARGER_H__ - -struct max8903_pdata { - /* - * GPIOs - * cen, chg, flt, dcm and usus are optional. - * dok and uok are not optional depending on the status of - * dc_valid and usb_valid. - */ - int cen; /* Charger Enable input */ - int dok; /* DC(Adapter) Power OK output */ - int uok; /* USB Power OK output */ - int chg; /* Charger status output */ - int flt; /* Fault output */ - int dcm; /* Current-Limit Mode input (1: DC, 2: USB) */ - int usus; /* USB Suspend Input (1: suspended) */ - - /* - * DC(Adapter/TA) is wired - * When dc_valid is true, - * dok should be valid. - * - * At least one of dc_valid or usb_valid should be true. - */ - bool dc_valid; - /* - * USB is wired - * When usb_valid is true, - * uok should be valid. - */ - bool usb_valid; -}; - -#endif /* __MAX8903_CHARGER_H__ */ -- cgit v1.2.3 From 90103622c30b13d97a1f5ae7d03cdd0fd79951c3 Mon Sep 17 00:00:00 2001 From: Anshuman Gupta Date: Mon, 11 Jan 2021 13:41:14 +0530 Subject: drm/hdcp: Max MST content streams Let's define Maximum MST content streams up to four generically which can be supported by modern display controllers. Cc: Sean Paul Cc: Ramalingam C Acked-by: Maarten Lankhorst Reviewed-by: Uma Shankar Reviewed-by: Ramalingam C Tested-by: Karthik B S Signed-off-by: Anshuman Gupta Link: https://patchwork.freedesktop.org/patch/msgid/20210111081120.28417-14-anshuman.gupta@intel.com --- include/drm/drm_hdcp.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/drm/drm_hdcp.h b/include/drm/drm_hdcp.h index fe58dbb46962..ac22c246542a 100644 --- a/include/drm/drm_hdcp.h +++ b/include/drm/drm_hdcp.h @@ -101,11 +101,11 @@ /* Following Macros take a byte at a time for bit(s) masking */ /* - * TODO: This has to be changed for DP MST, as multiple stream on - * same port is possible. - * For HDCP2.2 on HDMI and DP SST this value is always 1. + * TODO: HDCP_2_2_MAX_CONTENT_STREAMS_CNT is based upon actual + * H/W MST streams capacity. + * This required to be moved out to platform specific header. */ -#define HDCP_2_2_MAX_CONTENT_STREAMS_CNT 1 +#define HDCP_2_2_MAX_CONTENT_STREAMS_CNT 4 #define HDCP_2_2_TXCAP_MASK_LEN 2 #define HDCP_2_2_RXCAPS_LEN 3 #define HDCP_2_2_RX_REPEATER(x) ((x) & BIT(0)) -- cgit v1.2.3 From c512150b266b5d173c5ba841e9c09e4830ea4eca Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Sat, 5 Dec 2020 01:40:56 +0100 Subject: regulator: ab8500: Remove unused platform data The struct ab8500_regulator_platform_data was a leftover since the days before we probed all regulators from the device tree. The ab8500-ext regulator was the only used, defining platform data and register intialization that was never used for anything, a copy of a boardfile no longer in use. Delete the ab8500_regulator_platform_data and make the ab8500-ext regulator reference the regulator init data in the local file directly. We are 100% device tree these days. Cc: Lee Jones Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20201205004057.1712753-1-linus.walleij@linaro.org Signed-off-by: Mark Brown --- drivers/regulator/ab8500-ext.c | 417 +------------------------------------- include/linux/mfd/abx500/ab8500.h | 3 - include/linux/regulator/ab8500.h | 10 - 3 files changed, 2 insertions(+), 428 deletions(-) (limited to 'include') diff --git a/drivers/regulator/ab8500-ext.c b/drivers/regulator/ab8500-ext.c index 8bb43a671ded..05f9531bd108 100644 --- a/drivers/regulator/ab8500-ext.c +++ b/drivers/regulator/ab8500-ext.c @@ -24,403 +24,6 @@ #include #include -static struct regulator_consumer_supply ab8500_vaux1_consumers[] = { - /* Main display, u8500 R3 uib */ - REGULATOR_SUPPLY("vddi", "mcde_disp_sony_acx424akp.0"), - /* Main display, u8500 uib and ST uib */ - REGULATOR_SUPPLY("vdd1", "samsung_s6d16d0.0"), - /* Secondary display, ST uib */ - REGULATOR_SUPPLY("vdd1", "samsung_s6d16d0.1"), - /* SFH7741 proximity sensor */ - REGULATOR_SUPPLY("vcc", "gpio-keys.0"), - /* BH1780GLS ambient light sensor */ - REGULATOR_SUPPLY("vcc", "2-0029"), - /* lsm303dlh accelerometer */ - REGULATOR_SUPPLY("vdd", "2-0018"), - /* lsm303dlhc accelerometer */ - REGULATOR_SUPPLY("vdd", "2-0019"), - /* lsm303dlh magnetometer */ - REGULATOR_SUPPLY("vdd", "2-001e"), - /* Rohm BU21013 Touchscreen devices */ - REGULATOR_SUPPLY("avdd", "3-005c"), - REGULATOR_SUPPLY("avdd", "3-005d"), - /* Synaptics RMI4 Touchscreen device */ - REGULATOR_SUPPLY("vdd", "3-004b"), - /* L3G4200D Gyroscope device */ - REGULATOR_SUPPLY("vdd", "2-0068"), - /* Ambient light sensor device */ - REGULATOR_SUPPLY("vdd", "3-0029"), - /* Pressure sensor device */ - REGULATOR_SUPPLY("vdd", "2-005c"), - /* Cypress TrueTouch Touchscreen device */ - REGULATOR_SUPPLY("vcpin", "spi8.0"), - /* Camera device */ - REGULATOR_SUPPLY("vaux12v5", "mmio_camera"), -}; - -static struct regulator_consumer_supply ab8500_vaux2_consumers[] = { - /* On-board eMMC power */ - REGULATOR_SUPPLY("vmmc", "sdi4"), - /* AB8500 audio codec */ - REGULATOR_SUPPLY("vcc-N2158", "ab8500-codec.0"), - /* AB8500 accessory detect 1 */ - REGULATOR_SUPPLY("vcc-N2158", "ab8500-acc-det.0"), - /* AB8500 Tv-out device */ - REGULATOR_SUPPLY("vcc-N2158", "mcde_tv_ab8500.4"), - /* AV8100 HDMI device */ - REGULATOR_SUPPLY("vcc-N2158", "av8100_hdmi.3"), -}; - -static struct regulator_consumer_supply ab8500_vaux3_consumers[] = { - REGULATOR_SUPPLY("v-SD-STM", "stm"), - /* External MMC slot power */ - REGULATOR_SUPPLY("vmmc", "sdi0"), -}; - -static struct regulator_consumer_supply ab8500_vtvout_consumers[] = { - /* TV-out DENC supply */ - REGULATOR_SUPPLY("vtvout", "ab8500-denc.0"), - /* Internal general-purpose ADC */ - REGULATOR_SUPPLY("vddadc", "ab8500-gpadc.0"), - /* ADC for charger */ - REGULATOR_SUPPLY("vddadc", "ab8500-charger.0"), - /* AB8500 Tv-out device */ - REGULATOR_SUPPLY("vtvout", "mcde_tv_ab8500.4"), -}; - -static struct regulator_consumer_supply ab8500_vaud_consumers[] = { - /* AB8500 audio-codec main supply */ - REGULATOR_SUPPLY("vaud", "ab8500-codec.0"), -}; - -static struct regulator_consumer_supply ab8500_vamic1_consumers[] = { - /* AB8500 audio-codec Mic1 supply */ - REGULATOR_SUPPLY("vamic1", "ab8500-codec.0"), -}; - -static struct regulator_consumer_supply ab8500_vamic2_consumers[] = { - /* AB8500 audio-codec Mic2 supply */ - REGULATOR_SUPPLY("vamic2", "ab8500-codec.0"), -}; - -static struct regulator_consumer_supply ab8500_vdmic_consumers[] = { - /* AB8500 audio-codec DMic supply */ - REGULATOR_SUPPLY("vdmic", "ab8500-codec.0"), -}; - -static struct regulator_consumer_supply ab8500_vintcore_consumers[] = { - /* SoC core supply, no device */ - REGULATOR_SUPPLY("v-intcore", NULL), - /* USB Transceiver */ - REGULATOR_SUPPLY("vddulpivio18", "ab8500-usb.0"), - /* Handled by abx500 clk driver */ - REGULATOR_SUPPLY("v-intcore", "abx500-clk.0"), -}; - -static struct regulator_consumer_supply ab8500_vana_consumers[] = { - /* DB8500 DSI */ - REGULATOR_SUPPLY("vdddsi1v2", "mcde"), - REGULATOR_SUPPLY("vdddsi1v2", "b2r2_core"), - REGULATOR_SUPPLY("vdddsi1v2", "b2r2_1_core"), - REGULATOR_SUPPLY("vdddsi1v2", "dsilink.0"), - REGULATOR_SUPPLY("vdddsi1v2", "dsilink.1"), - REGULATOR_SUPPLY("vdddsi1v2", "dsilink.2"), - /* DB8500 CSI */ - REGULATOR_SUPPLY("vddcsi1v2", "mmio_camera"), -}; - -/* ab8500 regulator register initialization */ -static struct ab8500_regulator_reg_init ab8500_reg_init[] = { - /* - * VanaRequestCtrl = HP/LP depending on VxRequest - * VextSupply1RequestCtrl = HP/LP depending on VxRequest - */ - INIT_REGULATOR_REGISTER(AB8500_REGUREQUESTCTRL2, 0xf0, 0x00), - /* - * VextSupply2RequestCtrl = HP/LP depending on VxRequest - * VextSupply3RequestCtrl = HP/LP depending on VxRequest - * Vaux1RequestCtrl = HP/LP depending on VxRequest - * Vaux2RequestCtrl = HP/LP depending on VxRequest - */ - INIT_REGULATOR_REGISTER(AB8500_REGUREQUESTCTRL3, 0xff, 0x00), - /* - * Vaux3RequestCtrl = HP/LP depending on VxRequest - * SwHPReq = Control through SWValid disabled - */ - INIT_REGULATOR_REGISTER(AB8500_REGUREQUESTCTRL4, 0x07, 0x00), - /* - * VanaSysClkReq1HPValid = disabled - * Vaux1SysClkReq1HPValid = disabled - * Vaux2SysClkReq1HPValid = disabled - * Vaux3SysClkReq1HPValid = disabled - */ - INIT_REGULATOR_REGISTER(AB8500_REGUSYSCLKREQ1HPVALID1, 0xe8, 0x00), - /* - * VextSupply1SysClkReq1HPValid = disabled - * VextSupply2SysClkReq1HPValid = disabled - * VextSupply3SysClkReq1HPValid = SysClkReq1 controlled - */ - INIT_REGULATOR_REGISTER(AB8500_REGUSYSCLKREQ1HPVALID2, 0x70, 0x40), - /* - * VanaHwHPReq1Valid = disabled - * Vaux1HwHPreq1Valid = disabled - * Vaux2HwHPReq1Valid = disabled - * Vaux3HwHPReqValid = disabled - */ - INIT_REGULATOR_REGISTER(AB8500_REGUHWHPREQ1VALID1, 0xe8, 0x00), - /* - * VextSupply1HwHPReq1Valid = disabled - * VextSupply2HwHPReq1Valid = disabled - * VextSupply3HwHPReq1Valid = disabled - */ - INIT_REGULATOR_REGISTER(AB8500_REGUHWHPREQ1VALID2, 0x07, 0x00), - /* - * VanaHwHPReq2Valid = disabled - * Vaux1HwHPReq2Valid = disabled - * Vaux2HwHPReq2Valid = disabled - * Vaux3HwHPReq2Valid = disabled - */ - INIT_REGULATOR_REGISTER(AB8500_REGUHWHPREQ2VALID1, 0xe8, 0x00), - /* - * VextSupply1HwHPReq2Valid = disabled - * VextSupply2HwHPReq2Valid = disabled - * VextSupply3HwHPReq2Valid = HWReq2 controlled - */ - INIT_REGULATOR_REGISTER(AB8500_REGUHWHPREQ2VALID2, 0x07, 0x04), - /* - * VanaSwHPReqValid = disabled - * Vaux1SwHPReqValid = disabled - */ - INIT_REGULATOR_REGISTER(AB8500_REGUSWHPREQVALID1, 0xa0, 0x00), - /* - * Vaux2SwHPReqValid = disabled - * Vaux3SwHPReqValid = disabled - * VextSupply1SwHPReqValid = disabled - * VextSupply2SwHPReqValid = disabled - * VextSupply3SwHPReqValid = disabled - */ - INIT_REGULATOR_REGISTER(AB8500_REGUSWHPREQVALID2, 0x1f, 0x00), - /* - * SysClkReq2Valid1 = SysClkReq2 controlled - * SysClkReq3Valid1 = disabled - * SysClkReq4Valid1 = SysClkReq4 controlled - * SysClkReq5Valid1 = disabled - * SysClkReq6Valid1 = SysClkReq6 controlled - * SysClkReq7Valid1 = disabled - * SysClkReq8Valid1 = disabled - */ - INIT_REGULATOR_REGISTER(AB8500_REGUSYSCLKREQVALID1, 0xfe, 0x2a), - /* - * SysClkReq2Valid2 = disabled - * SysClkReq3Valid2 = disabled - * SysClkReq4Valid2 = disabled - * SysClkReq5Valid2 = disabled - * SysClkReq6Valid2 = SysClkReq6 controlled - * SysClkReq7Valid2 = disabled - * SysClkReq8Valid2 = disabled - */ - INIT_REGULATOR_REGISTER(AB8500_REGUSYSCLKREQVALID2, 0xfe, 0x20), - /* - * VTVoutEna = disabled - * Vintcore12Ena = disabled - * Vintcore12Sel = 1.25 V - * Vintcore12LP = inactive (HP) - * VTVoutLP = inactive (HP) - */ - INIT_REGULATOR_REGISTER(AB8500_REGUMISC1, 0xfe, 0x10), - /* - * VaudioEna = disabled - * VdmicEna = disabled - * Vamic1Ena = disabled - * Vamic2Ena = disabled - */ - INIT_REGULATOR_REGISTER(AB8500_VAUDIOSUPPLY, 0x1e, 0x00), - /* - * Vamic1_dzout = high-Z when Vamic1 is disabled - * Vamic2_dzout = high-Z when Vamic2 is disabled - */ - INIT_REGULATOR_REGISTER(AB8500_REGUCTRL1VAMIC, 0x03, 0x00), - /* - * VPll = Hw controlled (NOTE! PRCMU bits) - * VanaRegu = force off - */ - INIT_REGULATOR_REGISTER(AB8500_VPLLVANAREGU, 0x0f, 0x02), - /* - * VrefDDREna = disabled - * VrefDDRSleepMode = inactive (no pulldown) - */ - INIT_REGULATOR_REGISTER(AB8500_VREFDDR, 0x03, 0x00), - /* - * VextSupply1Regu = force LP - * VextSupply2Regu = force OFF - * VextSupply3Regu = force HP (-> STBB2=LP and TPS=LP) - * ExtSupply2Bypass = ExtSupply12LPn ball is 0 when Ena is 0 - * ExtSupply3Bypass = ExtSupply3LPn ball is 0 when Ena is 0 - */ - INIT_REGULATOR_REGISTER(AB8500_EXTSUPPLYREGU, 0xff, 0x13), - /* - * Vaux1Regu = force HP - * Vaux2Regu = force off - */ - INIT_REGULATOR_REGISTER(AB8500_VAUX12REGU, 0x0f, 0x01), - /* - * Vaux3Regu = force off - */ - INIT_REGULATOR_REGISTER(AB8500_VRF1VAUX3REGU, 0x03, 0x00), - /* - * Vaux1Sel = 2.8 V - */ - INIT_REGULATOR_REGISTER(AB8500_VAUX1SEL, 0x0f, 0x0C), - /* - * Vaux2Sel = 2.9 V - */ - INIT_REGULATOR_REGISTER(AB8500_VAUX2SEL, 0x0f, 0x0d), - /* - * Vaux3Sel = 2.91 V - */ - INIT_REGULATOR_REGISTER(AB8500_VRF1VAUX3SEL, 0x07, 0x07), - /* - * VextSupply12LP = disabled (no LP) - */ - INIT_REGULATOR_REGISTER(AB8500_REGUCTRL2SPARE, 0x01, 0x00), - /* - * Vaux1Disch = short discharge time - * Vaux2Disch = short discharge time - * Vaux3Disch = short discharge time - * Vintcore12Disch = short discharge time - * VTVoutDisch = short discharge time - * VaudioDisch = short discharge time - */ - INIT_REGULATOR_REGISTER(AB8500_REGUCTRLDISCH, 0xfc, 0x00), - /* - * VanaDisch = short discharge time - * VdmicPullDownEna = pulldown disabled when Vdmic is disabled - * VdmicDisch = short discharge time - */ - INIT_REGULATOR_REGISTER(AB8500_REGUCTRLDISCH2, 0x16, 0x00), -}; - -/* AB8500 regulators */ -static struct regulator_init_data ab8500_regulators[AB8500_NUM_REGULATORS] = { - /* supplies to the display/camera */ - [AB8500_LDO_AUX1] = { - .supply_regulator = "ab8500-ext-supply3", - .constraints = { - .name = "V-DISPLAY", - .min_uV = 2800000, - .max_uV = 3300000, - .valid_ops_mask = REGULATOR_CHANGE_VOLTAGE | - REGULATOR_CHANGE_STATUS, - .boot_on = 1, /* display is on at boot */ - }, - .num_consumer_supplies = ARRAY_SIZE(ab8500_vaux1_consumers), - .consumer_supplies = ab8500_vaux1_consumers, - }, - /* supplies to the on-board eMMC */ - [AB8500_LDO_AUX2] = { - .supply_regulator = "ab8500-ext-supply3", - .constraints = { - .name = "V-eMMC1", - .min_uV = 1100000, - .max_uV = 3300000, - .valid_ops_mask = REGULATOR_CHANGE_VOLTAGE | - REGULATOR_CHANGE_STATUS | - REGULATOR_CHANGE_MODE, - .valid_modes_mask = REGULATOR_MODE_NORMAL | - REGULATOR_MODE_IDLE, - }, - .num_consumer_supplies = ARRAY_SIZE(ab8500_vaux2_consumers), - .consumer_supplies = ab8500_vaux2_consumers, - }, - /* supply for VAUX3, supplies to SDcard slots */ - [AB8500_LDO_AUX3] = { - .supply_regulator = "ab8500-ext-supply3", - .constraints = { - .name = "V-MMC-SD", - .min_uV = 1100000, - .max_uV = 3300000, - .valid_ops_mask = REGULATOR_CHANGE_VOLTAGE | - REGULATOR_CHANGE_STATUS | - REGULATOR_CHANGE_MODE, - .valid_modes_mask = REGULATOR_MODE_NORMAL | - REGULATOR_MODE_IDLE, - }, - .num_consumer_supplies = ARRAY_SIZE(ab8500_vaux3_consumers), - .consumer_supplies = ab8500_vaux3_consumers, - }, - /* supply for tvout, gpadc, TVOUT LDO */ - [AB8500_LDO_TVOUT] = { - .constraints = { - .name = "V-TVOUT", - .valid_ops_mask = REGULATOR_CHANGE_STATUS, - }, - .num_consumer_supplies = ARRAY_SIZE(ab8500_vtvout_consumers), - .consumer_supplies = ab8500_vtvout_consumers, - }, - /* supply for ab8500-vaudio, VAUDIO LDO */ - [AB8500_LDO_AUDIO] = { - .constraints = { - .name = "V-AUD", - .valid_ops_mask = REGULATOR_CHANGE_STATUS, - }, - .num_consumer_supplies = ARRAY_SIZE(ab8500_vaud_consumers), - .consumer_supplies = ab8500_vaud_consumers, - }, - /* supply for v-anamic1 VAMic1-LDO */ - [AB8500_LDO_ANAMIC1] = { - .constraints = { - .name = "V-AMIC1", - .valid_ops_mask = REGULATOR_CHANGE_STATUS, - }, - .num_consumer_supplies = ARRAY_SIZE(ab8500_vamic1_consumers), - .consumer_supplies = ab8500_vamic1_consumers, - }, - /* supply for v-amic2, VAMIC2 LDO, reuse constants for AMIC1 */ - [AB8500_LDO_ANAMIC2] = { - .constraints = { - .name = "V-AMIC2", - .valid_ops_mask = REGULATOR_CHANGE_STATUS, - }, - .num_consumer_supplies = ARRAY_SIZE(ab8500_vamic2_consumers), - .consumer_supplies = ab8500_vamic2_consumers, - }, - /* supply for v-dmic, VDMIC LDO */ - [AB8500_LDO_DMIC] = { - .constraints = { - .name = "V-DMIC", - .valid_ops_mask = REGULATOR_CHANGE_STATUS, - }, - .num_consumer_supplies = ARRAY_SIZE(ab8500_vdmic_consumers), - .consumer_supplies = ab8500_vdmic_consumers, - }, - /* supply for v-intcore12, VINTCORE12 LDO */ - [AB8500_LDO_INTCORE] = { - .constraints = { - .name = "V-INTCORE", - .min_uV = 1250000, - .max_uV = 1350000, - .input_uV = 1800000, - .valid_ops_mask = REGULATOR_CHANGE_VOLTAGE | - REGULATOR_CHANGE_STATUS | - REGULATOR_CHANGE_MODE | - REGULATOR_CHANGE_DRMS, - .valid_modes_mask = REGULATOR_MODE_NORMAL | - REGULATOR_MODE_IDLE, - }, - .num_consumer_supplies = ARRAY_SIZE(ab8500_vintcore_consumers), - .consumer_supplies = ab8500_vintcore_consumers, - }, - /* supply for U8500 CSI-DSI, VANA LDO */ - [AB8500_LDO_ANA] = { - .constraints = { - .name = "V-CSI-DSI", - .valid_ops_mask = REGULATOR_CHANGE_STATUS, - }, - .num_consumer_supplies = ARRAY_SIZE(ab8500_vana_consumers), - .consumer_supplies = ab8500_vana_consumers, - }, -}; - /* supply for VextSupply3 */ static struct regulator_consumer_supply ab8500_ext_supply3_consumers[] = { /* SIM supply for 3 V SIM cards */ @@ -465,15 +68,6 @@ static struct regulator_init_data ab8500_ext_regulators[] = { }, }; -static struct ab8500_regulator_platform_data ab8500_regulator_plat_data = { - .reg_init = ab8500_reg_init, - .num_reg_init = ARRAY_SIZE(ab8500_reg_init), - .regulator = ab8500_regulators, - .num_regulator = ARRAY_SIZE(ab8500_regulators), - .ext_regulator = ab8500_ext_regulators, - .num_ext_regulator = ARRAY_SIZE(ab8500_ext_regulators), -}; - /** * struct ab8500_ext_regulator_info - ab8500 regulator information * @dev: device pointer @@ -788,7 +382,6 @@ static struct ab8500_ext_regulator_info static int ab8500_ext_regulator_probe(struct platform_device *pdev) { struct ab8500 *ab8500 = dev_get_drvdata(pdev->dev.parent); - struct ab8500_regulator_platform_data *pdata = &ab8500_regulator_plat_data; struct regulator_config config = { }; struct regulator_dev *rdev; int i; @@ -798,12 +391,6 @@ static int ab8500_ext_regulator_probe(struct platform_device *pdev) return -EINVAL; } - /* make sure the platform data has the correct size */ - if (pdata->num_ext_regulator != ARRAY_SIZE(ab8500_ext_regulator_info)) { - dev_err(&pdev->dev, "Configuration error: size mismatch.\n"); - return -EINVAL; - } - /* check for AB8500 2.x */ if (is_ab8500_2p0_or_earlier(ab8500)) { struct ab8500_ext_regulator_info *info; @@ -823,11 +410,11 @@ static int ab8500_ext_regulator_probe(struct platform_device *pdev) info = &ab8500_ext_regulator_info[i]; info->dev = &pdev->dev; info->cfg = (struct ab8500_ext_regulator_cfg *) - pdata->ext_regulator[i].driver_data; + ab8500_ext_regulators[i].driver_data; config.dev = &pdev->dev; config.driver_data = info; - config.init_data = &pdata->ext_regulator[i]; + config.init_data = &ab8500_ext_regulators[i]; /* register regulator with framework */ rdev = devm_regulator_register(&pdev->dev, &info->desc, diff --git a/include/linux/mfd/abx500/ab8500.h b/include/linux/mfd/abx500/ab8500.h index 524a7e4702c2..302a330c5c84 100644 --- a/include/linux/mfd/abx500/ab8500.h +++ b/include/linux/mfd/abx500/ab8500.h @@ -368,7 +368,6 @@ struct ab8500 { int it_latchhier_num; }; -struct ab8500_regulator_platform_data; struct ab8500_codec_platform_data; struct ab8500_sysctrl_platform_data; @@ -376,11 +375,9 @@ struct ab8500_sysctrl_platform_data; * struct ab8500_platform_data - AB8500 platform data * @irq_base: start of AB8500 IRQs, AB8500_NR_IRQS will be used * @init: board-specific initialization after detection of ab8500 - * @regulator: machine-specific constraints for regulators */ struct ab8500_platform_data { void (*init) (struct ab8500 *); - struct ab8500_regulator_platform_data *regulator; struct ab8500_codec_platform_data *codec; struct ab8500_sysctrl_platform_data *sysctrl; }; diff --git a/include/linux/regulator/ab8500.h b/include/linux/regulator/ab8500.h index 3ab1ddf151a2..ecf7b4713df9 100644 --- a/include/linux/regulator/ab8500.h +++ b/include/linux/regulator/ab8500.h @@ -153,14 +153,4 @@ enum ab8500_ext_regulator_id { AB8500_NUM_EXT_REGULATORS, }; -/* AB8500 regulator platform data */ -struct ab8500_regulator_platform_data { - int num_reg_init; - struct ab8500_regulator_reg_init *reg_init; - int num_regulator; - struct regulator_init_data *regulator; - int num_ext_regulator; - struct regulator_init_data *ext_regulator; -}; - #endif -- cgit v1.2.3 From 3acb64c07e95a75dc0af0bc958f2d09a44a9fd0d Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Sat, 5 Dec 2020 01:40:57 +0100 Subject: regulator: ab8500: Decomission platform data header The platform data header was only used to pass platform data from board files. We now populate the regulators exclusively from device tree, so the header contents can be moved into the regulator drivers. Cc: Lee Jones Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20201205004057.1712753-2-linus.walleij@linaro.org Signed-off-by: Mark Brown --- drivers/mfd/ab8500-core.c | 1 - drivers/regulator/ab8500-ext.c | 13 +++- drivers/regulator/ab8500.c | 116 ++++++++++++++++++++++++++++- include/linux/regulator/ab8500.h | 156 --------------------------------------- 4 files changed, 127 insertions(+), 159 deletions(-) delete mode 100644 include/linux/regulator/ab8500.h (limited to 'include') diff --git a/drivers/mfd/ab8500-core.c b/drivers/mfd/ab8500-core.c index a3bac9da8cbb..3b2276f04a98 100644 --- a/drivers/mfd/ab8500-core.c +++ b/drivers/mfd/ab8500-core.c @@ -21,7 +21,6 @@ #include #include #include -#include #include #include diff --git a/drivers/regulator/ab8500-ext.c b/drivers/regulator/ab8500-ext.c index 05f9531bd108..4f26952caa56 100644 --- a/drivers/regulator/ab8500-ext.c +++ b/drivers/regulator/ab8500-ext.c @@ -22,7 +22,18 @@ #include #include #include -#include + +/* AB8500 external regulators */ +enum ab8500_ext_regulator_id { + AB8500_EXT_SUPPLY1, + AB8500_EXT_SUPPLY2, + AB8500_EXT_SUPPLY3, + AB8500_NUM_EXT_REGULATORS, +}; + +struct ab8500_ext_regulator_cfg { + bool hwreq; /* requires hw mode or high power mode */ +}; /* supply for VextSupply3 */ static struct regulator_consumer_supply ab8500_ext_supply3_consumers[] = { diff --git a/drivers/regulator/ab8500.c b/drivers/regulator/ab8500.c index 47b8b6f7b571..23a401734a98 100644 --- a/drivers/regulator/ab8500.c +++ b/drivers/regulator/ab8500.c @@ -25,9 +25,123 @@ #include #include #include -#include #include +/* AB8500 regulators */ +enum ab8500_regulator_id { + AB8500_LDO_AUX1, + AB8500_LDO_AUX2, + AB8500_LDO_AUX3, + AB8500_LDO_INTCORE, + AB8500_LDO_TVOUT, + AB8500_LDO_AUDIO, + AB8500_LDO_ANAMIC1, + AB8500_LDO_ANAMIC2, + AB8500_LDO_DMIC, + AB8500_LDO_ANA, + AB8500_NUM_REGULATORS, +}; + +/* AB8505 regulators */ +enum ab8505_regulator_id { + AB8505_LDO_AUX1, + AB8505_LDO_AUX2, + AB8505_LDO_AUX3, + AB8505_LDO_AUX4, + AB8505_LDO_AUX5, + AB8505_LDO_AUX6, + AB8505_LDO_INTCORE, + AB8505_LDO_ADC, + AB8505_LDO_AUDIO, + AB8505_LDO_ANAMIC1, + AB8505_LDO_ANAMIC2, + AB8505_LDO_AUX8, + AB8505_LDO_ANA, + AB8505_NUM_REGULATORS, +}; + +/* AB8500 registers */ +enum ab8500_regulator_reg { + AB8500_REGUREQUESTCTRL2, + AB8500_REGUREQUESTCTRL3, + AB8500_REGUREQUESTCTRL4, + AB8500_REGUSYSCLKREQ1HPVALID1, + AB8500_REGUSYSCLKREQ1HPVALID2, + AB8500_REGUHWHPREQ1VALID1, + AB8500_REGUHWHPREQ1VALID2, + AB8500_REGUHWHPREQ2VALID1, + AB8500_REGUHWHPREQ2VALID2, + AB8500_REGUSWHPREQVALID1, + AB8500_REGUSWHPREQVALID2, + AB8500_REGUSYSCLKREQVALID1, + AB8500_REGUSYSCLKREQVALID2, + AB8500_REGUMISC1, + AB8500_VAUDIOSUPPLY, + AB8500_REGUCTRL1VAMIC, + AB8500_VPLLVANAREGU, + AB8500_VREFDDR, + AB8500_EXTSUPPLYREGU, + AB8500_VAUX12REGU, + AB8500_VRF1VAUX3REGU, + AB8500_VAUX1SEL, + AB8500_VAUX2SEL, + AB8500_VRF1VAUX3SEL, + AB8500_REGUCTRL2SPARE, + AB8500_REGUCTRLDISCH, + AB8500_REGUCTRLDISCH2, + AB8500_NUM_REGULATOR_REGISTERS, +}; + +/* AB8505 registers */ +enum ab8505_regulator_reg { + AB8505_REGUREQUESTCTRL1, + AB8505_REGUREQUESTCTRL2, + AB8505_REGUREQUESTCTRL3, + AB8505_REGUREQUESTCTRL4, + AB8505_REGUSYSCLKREQ1HPVALID1, + AB8505_REGUSYSCLKREQ1HPVALID2, + AB8505_REGUHWHPREQ1VALID1, + AB8505_REGUHWHPREQ1VALID2, + AB8505_REGUHWHPREQ2VALID1, + AB8505_REGUHWHPREQ2VALID2, + AB8505_REGUSWHPREQVALID1, + AB8505_REGUSWHPREQVALID2, + AB8505_REGUSYSCLKREQVALID1, + AB8505_REGUSYSCLKREQVALID2, + AB8505_REGUVAUX4REQVALID, + AB8505_REGUMISC1, + AB8505_VAUDIOSUPPLY, + AB8505_REGUCTRL1VAMIC, + AB8505_VSMPSAREGU, + AB8505_VSMPSBREGU, + AB8505_VSAFEREGU, /* NOTE! PRCMU register */ + AB8505_VPLLVANAREGU, + AB8505_EXTSUPPLYREGU, + AB8505_VAUX12REGU, + AB8505_VRF1VAUX3REGU, + AB8505_VSMPSASEL1, + AB8505_VSMPSASEL2, + AB8505_VSMPSASEL3, + AB8505_VSMPSBSEL1, + AB8505_VSMPSBSEL2, + AB8505_VSMPSBSEL3, + AB8505_VSAFESEL1, /* NOTE! PRCMU register */ + AB8505_VSAFESEL2, /* NOTE! PRCMU register */ + AB8505_VSAFESEL3, /* NOTE! PRCMU register */ + AB8505_VAUX1SEL, + AB8505_VAUX2SEL, + AB8505_VRF1VAUX3SEL, + AB8505_VAUX4REQCTRL, + AB8505_VAUX4REGU, + AB8505_VAUX4SEL, + AB8505_REGUCTRLDISCH, + AB8505_REGUCTRLDISCH2, + AB8505_REGUCTRLDISCH3, + AB8505_CTRLVAUX5, + AB8505_CTRLVAUX6, + AB8505_NUM_REGULATOR_REGISTERS, +}; + /** * struct ab8500_shared_mode - is used when mode is shared between * two regulators. diff --git a/include/linux/regulator/ab8500.h b/include/linux/regulator/ab8500.h deleted file mode 100644 index ecf7b4713df9..000000000000 --- a/include/linux/regulator/ab8500.h +++ /dev/null @@ -1,156 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) ST-Ericsson SA 2010 - * - * Authors: Sundar Iyer for ST-Ericsson - * Bengt Jonsson for ST-Ericsson - * Daniel Willerud for ST-Ericsson - */ - -#ifndef __LINUX_MFD_AB8500_REGULATOR_H -#define __LINUX_MFD_AB8500_REGULATOR_H - -#include - -/* AB8500 regulators */ -enum ab8500_regulator_id { - AB8500_LDO_AUX1, - AB8500_LDO_AUX2, - AB8500_LDO_AUX3, - AB8500_LDO_INTCORE, - AB8500_LDO_TVOUT, - AB8500_LDO_AUDIO, - AB8500_LDO_ANAMIC1, - AB8500_LDO_ANAMIC2, - AB8500_LDO_DMIC, - AB8500_LDO_ANA, - AB8500_NUM_REGULATORS, -}; - -/* AB8505 regulators */ -enum ab8505_regulator_id { - AB8505_LDO_AUX1, - AB8505_LDO_AUX2, - AB8505_LDO_AUX3, - AB8505_LDO_AUX4, - AB8505_LDO_AUX5, - AB8505_LDO_AUX6, - AB8505_LDO_INTCORE, - AB8505_LDO_ADC, - AB8505_LDO_AUDIO, - AB8505_LDO_ANAMIC1, - AB8505_LDO_ANAMIC2, - AB8505_LDO_AUX8, - AB8505_LDO_ANA, - AB8505_NUM_REGULATORS, -}; - -/* AB8500 and AB8505 register initialization */ -struct ab8500_regulator_reg_init { - int id; - u8 mask; - u8 value; -}; - -#define INIT_REGULATOR_REGISTER(_id, _mask, _value) \ - { \ - .id = _id, \ - .mask = _mask, \ - .value = _value, \ - } - -/* AB8500 registers */ -enum ab8500_regulator_reg { - AB8500_REGUREQUESTCTRL2, - AB8500_REGUREQUESTCTRL3, - AB8500_REGUREQUESTCTRL4, - AB8500_REGUSYSCLKREQ1HPVALID1, - AB8500_REGUSYSCLKREQ1HPVALID2, - AB8500_REGUHWHPREQ1VALID1, - AB8500_REGUHWHPREQ1VALID2, - AB8500_REGUHWHPREQ2VALID1, - AB8500_REGUHWHPREQ2VALID2, - AB8500_REGUSWHPREQVALID1, - AB8500_REGUSWHPREQVALID2, - AB8500_REGUSYSCLKREQVALID1, - AB8500_REGUSYSCLKREQVALID2, - AB8500_REGUMISC1, - AB8500_VAUDIOSUPPLY, - AB8500_REGUCTRL1VAMIC, - AB8500_VPLLVANAREGU, - AB8500_VREFDDR, - AB8500_EXTSUPPLYREGU, - AB8500_VAUX12REGU, - AB8500_VRF1VAUX3REGU, - AB8500_VAUX1SEL, - AB8500_VAUX2SEL, - AB8500_VRF1VAUX3SEL, - AB8500_REGUCTRL2SPARE, - AB8500_REGUCTRLDISCH, - AB8500_REGUCTRLDISCH2, - AB8500_NUM_REGULATOR_REGISTERS, -}; - -/* AB8505 registers */ -enum ab8505_regulator_reg { - AB8505_REGUREQUESTCTRL1, - AB8505_REGUREQUESTCTRL2, - AB8505_REGUREQUESTCTRL3, - AB8505_REGUREQUESTCTRL4, - AB8505_REGUSYSCLKREQ1HPVALID1, - AB8505_REGUSYSCLKREQ1HPVALID2, - AB8505_REGUHWHPREQ1VALID1, - AB8505_REGUHWHPREQ1VALID2, - AB8505_REGUHWHPREQ2VALID1, - AB8505_REGUHWHPREQ2VALID2, - AB8505_REGUSWHPREQVALID1, - AB8505_REGUSWHPREQVALID2, - AB8505_REGUSYSCLKREQVALID1, - AB8505_REGUSYSCLKREQVALID2, - AB8505_REGUVAUX4REQVALID, - AB8505_REGUMISC1, - AB8505_VAUDIOSUPPLY, - AB8505_REGUCTRL1VAMIC, - AB8505_VSMPSAREGU, - AB8505_VSMPSBREGU, - AB8505_VSAFEREGU, /* NOTE! PRCMU register */ - AB8505_VPLLVANAREGU, - AB8505_EXTSUPPLYREGU, - AB8505_VAUX12REGU, - AB8505_VRF1VAUX3REGU, - AB8505_VSMPSASEL1, - AB8505_VSMPSASEL2, - AB8505_VSMPSASEL3, - AB8505_VSMPSBSEL1, - AB8505_VSMPSBSEL2, - AB8505_VSMPSBSEL3, - AB8505_VSAFESEL1, /* NOTE! PRCMU register */ - AB8505_VSAFESEL2, /* NOTE! PRCMU register */ - AB8505_VSAFESEL3, /* NOTE! PRCMU register */ - AB8505_VAUX1SEL, - AB8505_VAUX2SEL, - AB8505_VRF1VAUX3SEL, - AB8505_VAUX4REQCTRL, - AB8505_VAUX4REGU, - AB8505_VAUX4SEL, - AB8505_REGUCTRLDISCH, - AB8505_REGUCTRLDISCH2, - AB8505_REGUCTRLDISCH3, - AB8505_CTRLVAUX5, - AB8505_CTRLVAUX6, - AB8505_NUM_REGULATOR_REGISTERS, -}; - -/* AB8500 external regulators */ -struct ab8500_ext_regulator_cfg { - bool hwreq; /* requires hw mode or high power mode */ -}; - -enum ab8500_ext_regulator_id { - AB8500_EXT_SUPPLY1, - AB8500_EXT_SUPPLY2, - AB8500_EXT_SUPPLY3, - AB8500_NUM_EXT_REGULATORS, -}; - -#endif -- cgit v1.2.3 From ff28a9f8d3b4e2e6d07e37e0f5e15119ee4aff55 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Tue, 12 Jan 2021 09:10:30 +0100 Subject: drm: Inline AGP wrappers into their only callers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The AGP wrapper functions serve no purpose. They used to handle builds that have CONFIG_AGP unset. But their callers are all in drm_agpsupport.c, which only gets build with CONFIG_AGP. v2: * clarify CONFIG_AGP in commit description (Daniel) Signed-off-by: Thomas Zimmermann Reviewed-by: Christian König Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210112081035.6882-2-tzimmermann@suse.de --- drivers/gpu/drm/drm_agpsupport.c | 12 ++++++------ drivers/gpu/drm/drm_memory.c | 18 ------------------ include/drm/drm_agpsupport.h | 18 ------------------ 3 files changed, 6 insertions(+), 42 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_agpsupport.c b/drivers/gpu/drm/drm_agpsupport.c index 4c7ad46fdd21..8b690ef306de 100644 --- a/drivers/gpu/drm/drm_agpsupport.c +++ b/drivers/gpu/drm/drm_agpsupport.c @@ -285,7 +285,7 @@ int drm_agp_unbind(struct drm_device *dev, struct drm_agp_binding *request) entry = drm_agp_lookup_entry(dev, request->handle); if (!entry || !entry->bound) return -EINVAL; - ret = drm_unbind_agp(entry->memory); + ret = agp_unbind_memory(entry->memory); if (ret == 0) entry->bound = 0; return ret; @@ -326,7 +326,7 @@ int drm_agp_bind(struct drm_device *dev, struct drm_agp_binding *request) if (!entry || entry->bound) return -EINVAL; page = DIV_ROUND_UP(request->offset, PAGE_SIZE); - retcode = drm_bind_agp(entry->memory, page); + retcode = agp_bind_memory(entry->memory, page); if (retcode) return retcode; entry->bound = dev->agp->base + (page << PAGE_SHIFT); @@ -369,11 +369,11 @@ int drm_agp_free(struct drm_device *dev, struct drm_agp_buffer *request) if (!entry) return -EINVAL; if (entry->bound) - drm_unbind_agp(entry->memory); + agp_unbind_memory(entry->memory); list_del(&entry->head); - drm_free_agp(entry->memory, entry->pages); + agp_free_memory(entry->memory); kfree(entry); return 0; } @@ -453,8 +453,8 @@ void drm_legacy_agp_clear(struct drm_device *dev) list_for_each_entry_safe(entry, tempe, &dev->agp->memory, head) { if (entry->bound) - drm_unbind_agp(entry->memory); - drm_free_agp(entry->memory, entry->pages); + agp_unbind_memory(entry->memory); + agp_free_memory(entry->memory); kfree(entry); } INIT_LIST_HEAD(&dev->agp->memory); diff --git a/drivers/gpu/drm/drm_memory.c b/drivers/gpu/drm/drm_memory.c index fbea69d6f909..f4f2bffdd5bd 100644 --- a/drivers/gpu/drm/drm_memory.c +++ b/drivers/gpu/drm/drm_memory.c @@ -100,24 +100,6 @@ static void *agp_remap(unsigned long offset, unsigned long size, return addr; } -/** Wrapper around agp_free_memory() */ -void drm_free_agp(struct agp_memory *handle, int pages) -{ - agp_free_memory(handle); -} - -/** Wrapper around agp_bind_memory() */ -int drm_bind_agp(struct agp_memory *handle, unsigned int start) -{ - return agp_bind_memory(handle, start); -} - -/** Wrapper around agp_unbind_memory() */ -int drm_unbind_agp(struct agp_memory *handle) -{ - return agp_unbind_memory(handle); -} - #else /* CONFIG_AGP */ static inline void *agp_remap(unsigned long offset, unsigned long size, struct drm_device *dev) diff --git a/include/drm/drm_agpsupport.h b/include/drm/drm_agpsupport.h index 664e120b93e6..f3136750c490 100644 --- a/include/drm/drm_agpsupport.h +++ b/include/drm/drm_agpsupport.h @@ -28,10 +28,6 @@ struct drm_agp_head { #if IS_ENABLED(CONFIG_AGP) -void drm_free_agp(struct agp_memory * handle, int pages); -int drm_bind_agp(struct agp_memory * handle, unsigned int start); -int drm_unbind_agp(struct agp_memory * handle); - struct drm_agp_head *drm_agp_init(struct drm_device *dev); void drm_legacy_agp_clear(struct drm_device *dev); int drm_agp_acquire(struct drm_device *dev); @@ -61,20 +57,6 @@ int drm_agp_bind_ioctl(struct drm_device *dev, void *data, #else /* CONFIG_AGP */ -static inline void drm_free_agp(struct agp_memory * handle, int pages) -{ -} - -static inline int drm_bind_agp(struct agp_memory * handle, unsigned int start) -{ - return -ENODEV; -} - -static inline int drm_unbind_agp(struct agp_memory * handle) -{ - return -ENODEV; -} - static inline struct drm_agp_head *drm_agp_init(struct drm_device *dev) { return NULL; -- cgit v1.2.3 From 14054f2afcd6fcef8270a32cbd7570b4992994c5 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Tue, 12 Jan 2021 09:10:35 +0100 Subject: drm: Move struct drm_device.hose to legacy section MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The field is only relevant for legacy DRM drivers. Its only non-legacy user in the DRM core is in drm_file.c. This code is now protected by CONFIG_DRM_LEGACY. Radeon, the only driver that used the field, has been changed to maintain it's own copy. Signed-off-by: Thomas Zimmermann Reviewed-by: Christian König Link: https://patchwork.freedesktop.org/patch/msgid/20210112081035.6882-7-tzimmermann@suse.de --- drivers/gpu/drm/drm_file.c | 2 ++ include/drm/drm_device.h | 9 +++++---- 2 files changed, 7 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c index 99403e49caf4..6b116bfd747c 100644 --- a/drivers/gpu/drm/drm_file.c +++ b/drivers/gpu/drm/drm_file.c @@ -367,6 +367,7 @@ static int drm_open_helper(struct file *filp, struct drm_minor *minor) list_add(&priv->lhead, &dev->filelist); mutex_unlock(&dev->filelist_mutex); +#ifdef CONFIG_DRM_LEGACY #ifdef __alpha__ /* * Default the hose @@ -386,6 +387,7 @@ static int drm_open_helper(struct file *filp, struct drm_minor *minor) dev->hose = b->sysdata; } } +#endif #endif return 0; diff --git a/include/drm/drm_device.h b/include/drm/drm_device.h index 939904ae88fc..d647223e8390 100644 --- a/include/drm/drm_device.h +++ b/include/drm/drm_device.h @@ -282,10 +282,6 @@ struct drm_device { /** @pdev: PCI device structure */ struct pci_dev *pdev; -#ifdef __alpha__ - /** @hose: PCI hose, only used on ALPHA platforms. */ - struct pci_controller *hose; -#endif /** @num_crtcs: Number of CRTCs on this device */ unsigned int num_crtcs; @@ -328,6 +324,11 @@ struct drm_device { /* List of devices per driver for stealth attach cleanup */ struct list_head legacy_dev_list; +#ifdef __alpha__ + /** @hose: PCI hose, only used on ALPHA platforms. */ + struct pci_controller *hose; +#endif + /* Context handle management - linked list of context handles */ struct list_head ctxlist; -- cgit v1.2.3 From 1e9d63331f8fa556f31e1406ab12f2a1e5cdb495 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Tue, 12 Jan 2021 11:02:44 -0800 Subject: fs: correctly document the inode dirty flags The documentation for I_DIRTY_SYNC and I_DIRTY_DATASYNC is a bit misleading, and I_DIRTY_TIME isn't documented at all. Fix this. Link: https://lore.kernel.org/r/20210112190253.64307-3-ebiggers@kernel.org Reviewed-by: Christoph Hellwig Reviewed-by: Jan Kara Signed-off-by: Eric Biggers Signed-off-by: Jan Kara --- include/linux/fs.h | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index fd47deea7c17..45a0303b2aeb 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2084,8 +2084,8 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, /* * Inode state bits. Protected by inode->i_lock * - * Three bits determine the dirty state of the inode, I_DIRTY_SYNC, - * I_DIRTY_DATASYNC and I_DIRTY_PAGES. + * Four bits determine the dirty state of the inode: I_DIRTY_SYNC, + * I_DIRTY_DATASYNC, I_DIRTY_PAGES, and I_DIRTY_TIME. * * Four bits define the lifetime of an inode. Initially, inodes are I_NEW, * until that flag is cleared. I_WILL_FREE, I_FREEING and I_CLEAR are set at @@ -2094,12 +2094,20 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, * Two bits are used for locking and completion notification, I_NEW and I_SYNC. * * I_DIRTY_SYNC Inode is dirty, but doesn't have to be written on - * fdatasync(). i_atime is the usual cause. - * I_DIRTY_DATASYNC Data-related inode changes pending. We keep track of + * fdatasync() (unless I_DIRTY_DATASYNC is also set). + * Timestamp updates are the usual cause. + * I_DIRTY_DATASYNC Data-related inode changes pending. We keep track of * these changes separately from I_DIRTY_SYNC so that we * don't have to write inode on fdatasync() when only - * mtime has changed in it. + * e.g. the timestamps have changed. * I_DIRTY_PAGES Inode has dirty pages. Inode itself may be clean. + * I_DIRTY_TIME The inode itself only has dirty timestamps, and the + * lazytime mount option is enabled. We keep track of this + * separately from I_DIRTY_SYNC in order to implement + * lazytime. This gets cleared if I_DIRTY_INODE + * (I_DIRTY_SYNC and/or I_DIRTY_DATASYNC) gets set. I.e. + * either I_DIRTY_TIME *or* I_DIRTY_INODE can be set in + * i_state, but not both. I_DIRTY_PAGES may still be set. * I_NEW Serves as both a mutex and completion notification. * New inodes set I_NEW. If two processes both create * the same inode, one of them will release its inode and -- cgit v1.2.3 From ed296c6c05b0ac52d7c6bf13a90f02b8b8222169 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Tue, 12 Jan 2021 11:02:53 -0800 Subject: ext4: simplify i_state checks in __ext4_update_other_inode_time() Since I_DIRTY_TIME and I_DIRTY_INODE are mutually exclusive in i_state, there's no need to check for I_DIRTY_TIME && !I_DIRTY_INODE. Just check for I_DIRTY_TIME. Also introduce a helper function in include/linux/fs.h to do this check. Link: https://lore.kernel.org/r/20210112190253.64307-12-ebiggers@kernel.org Reviewed-by: Christoph Hellwig Reviewed-by: Jan Kara Signed-off-by: Eric Biggers Signed-off-by: Jan Kara --- fs/ext4/inode.c | 8 ++------ include/linux/fs.h | 15 +++++++++++++++ 2 files changed, 17 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 4cc6c7834312..d809a06b6ef7 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4961,15 +4961,11 @@ static void __ext4_update_other_inode_time(struct super_block *sb, if (!inode) return; - if ((inode->i_state & (I_FREEING | I_WILL_FREE | I_NEW | - I_DIRTY_INODE)) || - ((inode->i_state & I_DIRTY_TIME) == 0)) + if (!inode_is_dirtytime_only(inode)) return; spin_lock(&inode->i_lock); - if (((inode->i_state & (I_FREEING | I_WILL_FREE | I_NEW | - I_DIRTY_INODE)) == 0) && - (inode->i_state & I_DIRTY_TIME)) { + if (inode_is_dirtytime_only(inode)) { struct ext4_inode_info *ei = EXT4_I(inode); inode->i_state &= ~I_DIRTY_TIME; diff --git a/include/linux/fs.h b/include/linux/fs.h index 45a0303b2aeb..de0c789104c2 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2194,6 +2194,21 @@ static inline void mark_inode_dirty_sync(struct inode *inode) __mark_inode_dirty(inode, I_DIRTY_SYNC); } +/* + * Returns true if the given inode itself only has dirty timestamps (its pages + * may still be dirty) and isn't currently being allocated or freed. + * Filesystems should call this if when writing an inode when lazytime is + * enabled, they want to opportunistically write the timestamps of other inodes + * located very nearby on-disk, e.g. in the same inode block. This returns true + * if the given inode is in need of such an opportunistic update. Requires + * i_lock, or at least later re-checking under i_lock. + */ +static inline bool inode_is_dirtytime_only(struct inode *inode) +{ + return (inode->i_state & (I_DIRTY_TIME | I_NEW | + I_FREEING | I_WILL_FREE)) == I_DIRTY_TIME; +} + extern void inc_nlink(struct inode *inode); extern void drop_nlink(struct inode *inode); extern void clear_nlink(struct inode *inode); -- cgit v1.2.3 From 660343d063f7b7151a8c679d91ebe13cf40ad866 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Wed, 13 Jan 2021 13:49:21 +0200 Subject: dmaengine: Extend the dmaengine_alignment for 128 and 256 bytes Some DMA device can benefit with higher order of alignment than the maximum of 64 bytes currently defined. Define 128 and 256 bytes alignment for these devices. Signed-off-by: Peter Ujfalusi Signed-off-by: Peter Ujfalusi Tested-by: Kishon Vijay Abraham I Link: https://lore.kernel.org/r/20210113114923.9231-2-peter.ujfalusi@gmail.com Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 68130f5f599e..004736b6a9c8 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -745,6 +745,8 @@ enum dmaengine_alignment { DMAENGINE_ALIGN_16_BYTES = 4, DMAENGINE_ALIGN_32_BYTES = 5, DMAENGINE_ALIGN_64_BYTES = 6, + DMAENGINE_ALIGN_128_BYTES = 7, + DMAENGINE_ALIGN_256_BYTES = 8, }; /** -- cgit v1.2.3 From a3b4388ea19b055ec482114e227c58d0184edfa5 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Sun, 10 Jan 2021 15:49:05 +0100 Subject: power: supply: z2_battery: Convert to GPIO descriptors This converts the Palm Z2 battery driver to use GPIO descriptors. Cc: Haojian Zhuang Cc: Robert Jarzmik Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Linus Walleij Reviewed-by: Daniel Mack Signed-off-by: Sebastian Reichel --- arch/arm/mach-pxa/z2.c | 12 +++++++++- drivers/power/supply/z2_battery.c | 46 ++++++++++++++++++--------------------- include/linux/z2_battery.h | 1 - 3 files changed, 32 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/arch/arm/mach-pxa/z2.c b/arch/arm/mach-pxa/z2.c index 21fd76bb09cd..a5dad8d08cac 100644 --- a/arch/arm/mach-pxa/z2.c +++ b/arch/arm/mach-pxa/z2.c @@ -488,7 +488,6 @@ static struct z2_battery_info batt_chip_info = { .batt_I2C_bus = 0, .batt_I2C_addr = 0x55, .batt_I2C_reg = 2, - .charge_gpio = GPIO0_ZIPITZ2_AC_DETECT, .min_voltage = 3475000, .max_voltage = 4190000, .batt_div = 59, @@ -497,9 +496,19 @@ static struct z2_battery_info batt_chip_info = { .batt_name = "Z2", }; +static struct gpiod_lookup_table z2_battery_gpio_table = { + .dev_id = "aer915", + .table = { + GPIO_LOOKUP("gpio-pxa", GPIO0_ZIPITZ2_AC_DETECT, + NULL, GPIO_ACTIVE_HIGH), + { }, + }, +}; + static struct i2c_board_info __initdata z2_i2c_board_info[] = { { I2C_BOARD_INFO("aer915", 0x55), + .dev_name = "aer915", .platform_data = &batt_chip_info, }, { I2C_BOARD_INFO("wm8750", 0x1b), @@ -510,6 +519,7 @@ static struct i2c_board_info __initdata z2_i2c_board_info[] = { static void __init z2_i2c_init(void) { pxa_set_i2c_info(NULL); + gpiod_add_lookup_table(&z2_battery_gpio_table); i2c_register_board_info(0, ARRAY_AND_SIZE(z2_i2c_board_info)); } #else diff --git a/drivers/power/supply/z2_battery.c b/drivers/power/supply/z2_battery.c index ebd2e42a4457..b1508fe70e5e 100644 --- a/drivers/power/supply/z2_battery.c +++ b/drivers/power/supply/z2_battery.c @@ -6,7 +6,7 @@ */ #include -#include +#include #include #include #include @@ -18,6 +18,7 @@ struct z2_charger { struct z2_battery_info *info; + struct gpio_desc *charge_gpiod; int bat_status; struct i2c_client *client; struct power_supply *batt_ps; @@ -95,8 +96,8 @@ static void z2_batt_update(struct z2_charger *charger) mutex_lock(&charger->work_lock); - charger->bat_status = (info->charge_gpio >= 0) ? - (gpio_get_value(info->charge_gpio) ? + charger->bat_status = charger->charge_gpiod ? + (gpiod_get_value(charger->charge_gpiod) ? POWER_SUPPLY_STATUS_CHARGING : POWER_SUPPLY_STATUS_DISCHARGING) : POWER_SUPPLY_STATUS_UNKNOWN; @@ -131,7 +132,7 @@ static int z2_batt_ps_init(struct z2_charger *charger, int props) enum power_supply_property *prop; struct z2_battery_info *info = charger->info; - if (info->charge_gpio >= 0) + if (charger->charge_gpiod) props++; /* POWER_SUPPLY_PROP_STATUS */ if (info->batt_tech >= 0) props++; /* POWER_SUPPLY_PROP_TECHNOLOGY */ @@ -147,7 +148,7 @@ static int z2_batt_ps_init(struct z2_charger *charger, int props) return -ENOMEM; prop[i++] = POWER_SUPPLY_PROP_PRESENT; - if (info->charge_gpio >= 0) + if (charger->charge_gpiod) prop[i++] = POWER_SUPPLY_PROP_STATUS; if (info->batt_tech >= 0) prop[i++] = POWER_SUPPLY_PROP_TECHNOLOGY; @@ -206,22 +207,23 @@ static int z2_batt_probe(struct i2c_client *client, mutex_init(&charger->work_lock); - if (info->charge_gpio >= 0 && gpio_is_valid(info->charge_gpio)) { - ret = gpio_request(info->charge_gpio, "BATT CHRG"); - if (ret) - goto err; + charger->charge_gpiod = devm_gpiod_get_optional(&client->dev, + NULL, GPIOD_IN); + if (IS_ERR(charger->charge_gpiod)) + return dev_err_probe(&client->dev, + PTR_ERR(charger->charge_gpiod), + "failed to get charge GPIO\n"); - ret = gpio_direction_input(info->charge_gpio); - if (ret) - goto err2; + if (charger->charge_gpiod) { + gpiod_set_consumer_name(charger->charge_gpiod, "BATT CHRG"); - irq_set_irq_type(gpio_to_irq(info->charge_gpio), + irq_set_irq_type(gpiod_to_irq(charger->charge_gpiod), IRQ_TYPE_EDGE_BOTH); - ret = request_irq(gpio_to_irq(info->charge_gpio), + ret = request_irq(gpiod_to_irq(charger->charge_gpiod), z2_charge_switch_irq, 0, "AC Detect", charger); if (ret) - goto err3; + goto err; } ret = z2_batt_ps_init(charger, props); @@ -245,11 +247,8 @@ static int z2_batt_probe(struct i2c_client *client, err4: kfree(charger->batt_ps_desc.properties); err3: - if (info->charge_gpio >= 0 && gpio_is_valid(info->charge_gpio)) - free_irq(gpio_to_irq(info->charge_gpio), charger); -err2: - if (info->charge_gpio >= 0 && gpio_is_valid(info->charge_gpio)) - gpio_free(info->charge_gpio); + if (charger->charge_gpiod) + free_irq(gpiod_to_irq(charger->charge_gpiod), charger); err: kfree(charger); return ret; @@ -258,16 +257,13 @@ err: static int z2_batt_remove(struct i2c_client *client) { struct z2_charger *charger = i2c_get_clientdata(client); - struct z2_battery_info *info = charger->info; cancel_work_sync(&charger->bat_work); power_supply_unregister(charger->batt_ps); kfree(charger->batt_ps_desc.properties); - if (info->charge_gpio >= 0 && gpio_is_valid(info->charge_gpio)) { - free_irq(gpio_to_irq(info->charge_gpio), charger); - gpio_free(info->charge_gpio); - } + if (charger->charge_gpiod) + free_irq(gpiod_to_irq(charger->charge_gpiod), charger); kfree(charger); diff --git a/include/linux/z2_battery.h b/include/linux/z2_battery.h index eaba53ff387c..9e8be7a7cd25 100644 --- a/include/linux/z2_battery.h +++ b/include/linux/z2_battery.h @@ -6,7 +6,6 @@ struct z2_battery_info { int batt_I2C_bus; int batt_I2C_addr; int batt_I2C_reg; - int charge_gpio; int min_voltage; int max_voltage; int batt_div; -- cgit v1.2.3 From cb6d6918c56ffd98e88164d5471f692d33dabf2b Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 11 Jan 2021 00:45:08 +0100 Subject: power: supply: wm97xx_battery: Convert to GPIO descriptor This converts the WM97xx driver to use a GPIO descriptor instead of passing a GPIO number thru platform data. Like everything else in the driver, use a simple local variable for the descriptor, it can only ever appear in one instance anyway so it should not hurt. After converting the driver I noticed that none of the boardfiles actually define a meaningful GPIO line for this, but hey, it is converted. Cc: Haojian Zhuang Cc: Robert Jarzmik Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Linus Walleij Reviewed-by: Daniel Mack Signed-off-by: Sebastian Reichel --- arch/arm/mach-pxa/mioa701.c | 1 - arch/arm/mach-pxa/palm27x.c | 1 - arch/arm/mach-pxa/palmte2.c | 1 - drivers/power/supply/wm97xx_battery.c | 45 +++++++++++++++-------------------- include/linux/wm97xx.h | 1 - 5 files changed, 19 insertions(+), 30 deletions(-) (limited to 'include') diff --git a/arch/arm/mach-pxa/mioa701.c b/arch/arm/mach-pxa/mioa701.c index d3af80317f2d..a79f296e81e0 100644 --- a/arch/arm/mach-pxa/mioa701.c +++ b/arch/arm/mach-pxa/mioa701.c @@ -577,7 +577,6 @@ static struct platform_device power_dev = { static struct wm97xx_batt_pdata mioa701_battery_data = { .batt_aux = WM97XX_AUX_ID1, .temp_aux = -1, - .charge_gpio = -1, .min_voltage = 0xc00, .max_voltage = 0xfc0, .batt_tech = POWER_SUPPLY_TECHNOLOGY_LION, diff --git a/arch/arm/mach-pxa/palm27x.c b/arch/arm/mach-pxa/palm27x.c index 0d246a1aebbc..6230381a7ca0 100644 --- a/arch/arm/mach-pxa/palm27x.c +++ b/arch/arm/mach-pxa/palm27x.c @@ -212,7 +212,6 @@ void __init palm27x_irda_init(int pwdn) static struct wm97xx_batt_pdata palm27x_batt_pdata = { .batt_aux = WM97XX_AUX_ID3, .temp_aux = WM97XX_AUX_ID2, - .charge_gpio = -1, .batt_mult = 1000, .batt_div = 414, .temp_mult = 1, diff --git a/arch/arm/mach-pxa/palmte2.c b/arch/arm/mach-pxa/palmte2.c index e3bcf58b4e63..a2b10db4aacc 100644 --- a/arch/arm/mach-pxa/palmte2.c +++ b/arch/arm/mach-pxa/palmte2.c @@ -273,7 +273,6 @@ static struct platform_device power_supply = { static struct wm97xx_batt_pdata palmte2_batt_pdata = { .batt_aux = WM97XX_AUX_ID3, .temp_aux = WM97XX_AUX_ID2, - .charge_gpio = -1, .max_voltage = PALMTE2_BAT_MAX_VOLTAGE, .min_voltage = PALMTE2_BAT_MIN_VOLTAGE, .batt_mult = 1000, diff --git a/drivers/power/supply/wm97xx_battery.c b/drivers/power/supply/wm97xx_battery.c index 58f01659daa5..a0e1eaa25d93 100644 --- a/drivers/power/supply/wm97xx_battery.c +++ b/drivers/power/supply/wm97xx_battery.c @@ -15,11 +15,12 @@ #include #include #include -#include +#include #include #include static struct work_struct bat_work; +static struct gpio_desc *charge_gpiod; static DEFINE_MUTEX(work_lock); static int bat_status = POWER_SUPPLY_STATUS_UNKNOWN; static enum power_supply_property *prop; @@ -96,12 +97,11 @@ static void wm97xx_bat_external_power_changed(struct power_supply *bat_ps) static void wm97xx_bat_update(struct power_supply *bat_ps) { int old_status = bat_status; - struct wm97xx_batt_pdata *pdata = power_supply_get_drvdata(bat_ps); mutex_lock(&work_lock); - bat_status = (pdata->charge_gpio >= 0) ? - (gpio_get_value(pdata->charge_gpio) ? + bat_status = (charge_gpiod) ? + (gpiod_get_value(charge_gpiod) ? POWER_SUPPLY_STATUS_DISCHARGING : POWER_SUPPLY_STATUS_CHARGING) : POWER_SUPPLY_STATUS_UNKNOWN; @@ -171,18 +171,19 @@ static int wm97xx_bat_probe(struct platform_device *dev) if (dev->id != -1) return -EINVAL; - if (gpio_is_valid(pdata->charge_gpio)) { - ret = gpio_request(pdata->charge_gpio, "BATT CHRG"); - if (ret) - goto err; - ret = gpio_direction_input(pdata->charge_gpio); - if (ret) - goto err2; - ret = request_irq(gpio_to_irq(pdata->charge_gpio), + charge_gpiod = devm_gpiod_get_optional(&dev->dev, NULL, GPIOD_IN); + if (IS_ERR(charge_gpiod)) + return dev_err_probe(&dev->dev, + PTR_ERR(charge_gpiod), + "failed to get charge GPIO\n"); + if (charge_gpiod) { + gpiod_set_consumer_name(charge_gpiod, "BATT CHRG"); + ret = request_irq(gpiod_to_irq(charge_gpiod), wm97xx_chrg_irq, 0, "AC Detect", dev); if (ret) - goto err2; + return dev_err_probe(&dev->dev, ret, + "failed to request GPIO irq\n"); props++; /* POWER_SUPPLY_PROP_STATUS */ } @@ -204,7 +205,7 @@ static int wm97xx_bat_probe(struct platform_device *dev) } prop[i++] = POWER_SUPPLY_PROP_PRESENT; - if (pdata->charge_gpio >= 0) + if (charge_gpiod) prop[i++] = POWER_SUPPLY_PROP_STATUS; if (pdata->batt_tech >= 0) prop[i++] = POWER_SUPPLY_PROP_TECHNOLOGY; @@ -242,23 +243,15 @@ static int wm97xx_bat_probe(struct platform_device *dev) err4: kfree(prop); err3: - if (gpio_is_valid(pdata->charge_gpio)) - free_irq(gpio_to_irq(pdata->charge_gpio), dev); -err2: - if (gpio_is_valid(pdata->charge_gpio)) - gpio_free(pdata->charge_gpio); -err: + if (charge_gpiod) + free_irq(gpiod_to_irq(charge_gpiod), dev); return ret; } static int wm97xx_bat_remove(struct platform_device *dev) { - struct wm97xx_batt_pdata *pdata = dev->dev.platform_data; - - if (pdata && gpio_is_valid(pdata->charge_gpio)) { - free_irq(gpio_to_irq(pdata->charge_gpio), dev); - gpio_free(pdata->charge_gpio); - } + if (charge_gpiod) + free_irq(gpiod_to_irq(charge_gpiod), dev); cancel_work_sync(&bat_work); power_supply_unregister(bat_psy); kfree(prop); diff --git a/include/linux/wm97xx.h b/include/linux/wm97xx.h index 58e082dadc68..462854f4f286 100644 --- a/include/linux/wm97xx.h +++ b/include/linux/wm97xx.h @@ -294,7 +294,6 @@ struct wm97xx { struct wm97xx_batt_pdata { int batt_aux; int temp_aux; - int charge_gpio; int min_voltage; int max_voltage; int batt_div; -- cgit v1.2.3 From 9d93a9e8aab3f82b6742dd034a6a81d4025cd82e Mon Sep 17 00:00:00 2001 From: Gabriel Somlo Date: Tue, 12 Jan 2021 12:31:40 -0500 Subject: drivers/soc/litex: move generic accessors to litex.h Move generic LiteX CSR (MMIO) register accessors to litex.h and declare them as "static inline", in preparation for supporting 32-bit CSR subregisters and 64-bit CPUs. NOTE: this is a non-functional change. Signed-off-by: Gabriel Somlo Signed-off-by: Stafford Horne --- drivers/soc/litex/litex_soc_ctrl.c | 73 ------------------------------------- include/linux/litex.h | 74 +++++++++++++++++++++++++++++++++++--- 2 files changed, 69 insertions(+), 78 deletions(-) (limited to 'include') diff --git a/drivers/soc/litex/litex_soc_ctrl.c b/drivers/soc/litex/litex_soc_ctrl.c index 1217cafdfd4d..65977526d68e 100644 --- a/drivers/soc/litex/litex_soc_ctrl.c +++ b/drivers/soc/litex/litex_soc_ctrl.c @@ -16,79 +16,6 @@ #include #include -/* - * LiteX SoC Generator, depending on the configuration, can split a single - * logical CSR (Control&Status Register) into a series of consecutive physical - * registers. - * - * For example, in the configuration with 8-bit CSR Bus, 32-bit aligned (the - * default one for 32-bit CPUs) a 32-bit logical CSR will be generated as four - * 32-bit physical registers, each one containing one byte of meaningful data. - * - * For details see: https://github.com/enjoy-digital/litex/wiki/CSR-Bus - * - * The purpose of `litex_set_reg`/`litex_get_reg` is to implement the logic - * of writing to/reading from the LiteX CSR in a single place that can be - * then reused by all LiteX drivers. - */ - -/** - * litex_set_reg() - Writes the value to the LiteX CSR (Control&Status Register) - * @reg: Address of the CSR - * @reg_size: The width of the CSR expressed in the number of bytes - * @val: Value to be written to the CSR - * - * In the currently supported LiteX configuration (8-bit CSR Bus, 32-bit aligned), - * a 32-bit LiteX CSR is generated as 4 consecutive 32-bit physical registers, - * each one containing one byte of meaningful data. - * - * This function splits a single possibly multi-byte write into a series of - * single-byte writes with a proper offset. - */ -void litex_set_reg(void __iomem *reg, unsigned long reg_size, - unsigned long val) -{ - unsigned long shifted_data, shift, i; - - for (i = 0; i < reg_size; ++i) { - shift = ((reg_size - i - 1) * LITEX_SUBREG_SIZE_BIT); - shifted_data = val >> shift; - - WRITE_LITEX_SUBREGISTER(shifted_data, reg, i); - } -} -EXPORT_SYMBOL_GPL(litex_set_reg); - -/** - * litex_get_reg() - Reads the value of the LiteX CSR (Control&Status Register) - * @reg: Address of the CSR - * @reg_size: The width of the CSR expressed in the number of bytes - * - * Return: Value read from the CSR - * - * In the currently supported LiteX configuration (8-bit CSR Bus, 32-bit aligned), - * a 32-bit LiteX CSR is generated as 4 consecutive 32-bit physical registers, - * each one containing one byte of meaningful data. - * - * This function generates a series of single-byte reads with a proper offset - * and joins their results into a single multi-byte value. - */ -unsigned long litex_get_reg(void __iomem *reg, unsigned long reg_size) -{ - unsigned long shifted_data, shift, i; - unsigned long result = 0; - - for (i = 0; i < reg_size; ++i) { - shifted_data = READ_LITEX_SUBREGISTER(reg, i); - - shift = ((reg_size - i - 1) * LITEX_SUBREG_SIZE_BIT); - result |= (shifted_data << shift); - } - - return result; -} -EXPORT_SYMBOL_GPL(litex_get_reg); - #define SCRATCH_REG_OFF 0x04 #define SCRATCH_REG_VALUE 0x12345678 #define SCRATCH_TEST_VALUE 0xdeadbeef diff --git a/include/linux/litex.h b/include/linux/litex.h index 40f5be503593..67c1a18a7425 100644 --- a/include/linux/litex.h +++ b/include/linux/litex.h @@ -3,9 +3,6 @@ * Common LiteX header providing * helper functions for accessing CSRs. * - * Implementation of the functions is provided by - * the LiteX SoC Controller driver. - * * Copyright (C) 2019-2020 Antmicro */ @@ -33,9 +30,76 @@ #define READ_LITEX_SUBREGISTER(base_offset, subreg_id) \ le32_to_cpu((__le32 __force)readl(base_offset + (LITEX_REG_SIZE * subreg_id))) -void litex_set_reg(void __iomem *reg, unsigned long reg_sz, unsigned long val); +/* + * LiteX SoC Generator, depending on the configuration, can split a single + * logical CSR (Control&Status Register) into a series of consecutive physical + * registers. + * + * For example, in the configuration with 8-bit CSR Bus, 32-bit aligned (the + * default one for 32-bit CPUs) a 32-bit logical CSR will be generated as four + * 32-bit physical registers, each one containing one byte of meaningful data. + * + * For details see: https://github.com/enjoy-digital/litex/wiki/CSR-Bus + * + * The purpose of `litex_set_reg`/`litex_get_reg` is to implement the logic + * of writing to/reading from the LiteX CSR in a single place that can be + * then reused by all LiteX drivers. + */ + +/** + * litex_set_reg() - Writes the value to the LiteX CSR (Control&Status Register) + * @reg: Address of the CSR + * @reg_size: The width of the CSR expressed in the number of bytes + * @val: Value to be written to the CSR + * + * In the currently supported LiteX configuration (8-bit CSR Bus, 32-bit aligned), + * a 32-bit LiteX CSR is generated as 4 consecutive 32-bit physical registers, + * each one containing one byte of meaningful data. + * + * This function splits a single possibly multi-byte write into a series of + * single-byte writes with a proper offset. + */ +static inline void litex_set_reg(void __iomem *reg, ulong reg_size, ulong val) +{ + ulong shifted_data, shift, i; + + for (i = 0; i < reg_size; ++i) { + shift = ((reg_size - i - 1) * LITEX_SUBREG_SIZE_BIT); + shifted_data = val >> shift; + + WRITE_LITEX_SUBREGISTER(shifted_data, reg, i); + } +} + +/** + * litex_get_reg() - Reads the value of the LiteX CSR (Control&Status Register) + * @reg: Address of the CSR + * @reg_size: The width of the CSR expressed in the number of bytes + * + * Return: Value read from the CSR + * + * In the currently supported LiteX configuration (8-bit CSR Bus, 32-bit aligned), + * a 32-bit LiteX CSR is generated as 4 consecutive 32-bit physical registers, + * each one containing one byte of meaningful data. + * + * This function generates a series of single-byte reads with a proper offset + * and joins their results into a single multi-byte value. + */ +static inline ulong litex_get_reg(void __iomem *reg, ulong reg_size) +{ + ulong shifted_data, shift, i; + ulong result = 0; + + for (i = 0; i < reg_size; ++i) { + shifted_data = READ_LITEX_SUBREGISTER(reg, i); + + shift = ((reg_size - i - 1) * LITEX_SUBREG_SIZE_BIT); + result |= (shifted_data << shift); + } + + return result; +} -unsigned long litex_get_reg(void __iomem *reg, unsigned long reg_sz); static inline void litex_write8(void __iomem *reg, u8 val) { -- cgit v1.2.3 From b5d3061ea2e691ab1fa6465fce3c59d9d10357de Mon Sep 17 00:00:00 2001 From: Gabriel Somlo Date: Tue, 12 Jan 2021 12:31:41 -0500 Subject: drivers/soc/litex: separate MMIO from subregister offset calculation Separate MMIO (read/write) access into _[read|write]_litex_subregister() static inline functions, leaving existing "READ|WRITE" macros to handle calculation of the subregister offset only. NOTE: this is a non-functional change. Signed-off-by: Gabriel Somlo Signed-off-by: Stafford Horne --- include/linux/litex.h | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/litex.h b/include/linux/litex.h index 67c1a18a7425..918bab45243c 100644 --- a/include/linux/litex.h +++ b/include/linux/litex.h @@ -24,11 +24,23 @@ #define LITEX_SUBREG_SIZE 0x1 #define LITEX_SUBREG_SIZE_BIT (LITEX_SUBREG_SIZE * 8) +static inline void _write_litex_subregister(u32 val, void __iomem *addr) +{ + writel((u32 __force)cpu_to_le32(val), addr); +} + +static inline u32 _read_litex_subregister(void __iomem *addr) +{ + return le32_to_cpu((__le32 __force)readl(addr)); +} + #define WRITE_LITEX_SUBREGISTER(val, base_offset, subreg_id) \ - writel((u32 __force)cpu_to_le32(val), base_offset + (LITEX_REG_SIZE * subreg_id)) + _write_litex_subregister(val, (base_offset) + \ + LITEX_REG_SIZE * (subreg_id)) #define READ_LITEX_SUBREGISTER(base_offset, subreg_id) \ - le32_to_cpu((__le32 __force)readl(base_offset + (LITEX_REG_SIZE * subreg_id))) + _read_litex_subregister((base_offset) + \ + LITEX_REG_SIZE * (subreg_id)) /* * LiteX SoC Generator, depending on the configuration, can split a single -- cgit v1.2.3 From ffa4ebc48971abffed722b75887ac1d8c9256b41 Mon Sep 17 00:00:00 2001 From: Gabriel Somlo Date: Tue, 12 Jan 2021 12:31:42 -0500 Subject: drivers/soc/litex: s/LITEX_REG_SIZE/LITEX_SUBREG_ALIGN/g The constant LITEX_REG_SIZE is renamed to the more descriptive LITEX_SUBREG_ALIGN (LiteX CSR subregisters are located at 32-bit aligned MMIO addresses). NOTE: this is a non-functional change. Signed-off-by: Gabriel Somlo Signed-off-by: Stafford Horne --- include/linux/litex.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/litex.h b/include/linux/litex.h index 918bab45243c..c63a7e1a337c 100644 --- a/include/linux/litex.h +++ b/include/linux/litex.h @@ -20,10 +20,12 @@ * Supporting other configurations will require extending the logic in this * header and in the LiteX SoC controller driver. */ -#define LITEX_REG_SIZE 0x4 #define LITEX_SUBREG_SIZE 0x1 #define LITEX_SUBREG_SIZE_BIT (LITEX_SUBREG_SIZE * 8) +/* LiteX subregisters of any width are always aligned on a 4-byte boundary */ +#define LITEX_SUBREG_ALIGN 0x4 + static inline void _write_litex_subregister(u32 val, void __iomem *addr) { writel((u32 __force)cpu_to_le32(val), addr); @@ -36,11 +38,11 @@ static inline u32 _read_litex_subregister(void __iomem *addr) #define WRITE_LITEX_SUBREGISTER(val, base_offset, subreg_id) \ _write_litex_subregister(val, (base_offset) + \ - LITEX_REG_SIZE * (subreg_id)) + LITEX_SUBREG_ALIGN * (subreg_id)) #define READ_LITEX_SUBREGISTER(base_offset, subreg_id) \ _read_litex_subregister((base_offset) + \ - LITEX_REG_SIZE * (subreg_id)) + LITEX_SUBREG_ALIGN * (subreg_id)) /* * LiteX SoC Generator, depending on the configuration, can split a single -- cgit v1.2.3 From 51f109228308a87c7f2583360e54acfc567203da Mon Sep 17 00:00:00 2001 From: Gabriel Somlo Date: Tue, 12 Jan 2021 12:31:43 -0500 Subject: drivers/soc/litex: support 32-bit subregisters, 64-bit CPUs Upstream LiteX now defaults to using 32-bit CSR subregisters (see https://github.com/enjoy-digital/litex/commit/a2b71fde). This patch expands on commit 22447a99c97e ("drivers/soc/litex: add LiteX SoC Controller driver"), adding support for handling both 8- and 32-bit LiteX CSR (MMIO) subregisters, as determined by the LITEX_SUBREG_SIZE Kconfig option. NOTE that while LITEX_SUBREG_SIZE could theoretically be a device tree property, defining it as a compile-time constant allows for much better optimization of the resulting code. This is further supported by the low expected usefulness of deploying the same kernel across LiteX SoCs built with different CSR-Bus data widths. Finally, the litex_[read|write][8|16|32|64]() accessors are redefined in terms of litex_[get|set]_reg(), which, after compiler optimization, will result in code as efficient as hardcoded shifts, but with the added benefit of automatically matching the appropriate LITEX_SUBREG_SIZE. NOTE that litex_[get|set]_reg() nominally operate on 64-bit data, but that will also be optimized by the compiler in situations where narrower data is used from a call site. Signed-off-by: Gabriel Somlo Signed-off-by: Stafford Horne --- drivers/soc/litex/Kconfig | 12 ++++ drivers/soc/litex/litex_soc_ctrl.c | 3 +- include/linux/litex.h | 137 +++++++++++++++---------------------- 3 files changed, 68 insertions(+), 84 deletions(-) (limited to 'include') diff --git a/drivers/soc/litex/Kconfig b/drivers/soc/litex/Kconfig index 7c6b009b6f6c..973f8d2fe1a7 100644 --- a/drivers/soc/litex/Kconfig +++ b/drivers/soc/litex/Kconfig @@ -16,4 +16,16 @@ config LITEX_SOC_CONTROLLER All drivers that use functions from litex.h must depend on LITEX. +config LITEX_SUBREG_SIZE + int "Size of a LiteX CSR subregister, in bytes" + depends on LITEX + range 1 4 + default 4 + help + LiteX MMIO registers (referred to as Configuration and Status + registers, or CSRs) are spread across adjacent 8- or 32-bit + subregisters, located at 32-bit aligned MMIO addresses. Use + this to select the appropriate size (1 or 4 bytes) matching + your particular LiteX build. + endmenu diff --git a/drivers/soc/litex/litex_soc_ctrl.c b/drivers/soc/litex/litex_soc_ctrl.c index 65977526d68e..da17ba56b795 100644 --- a/drivers/soc/litex/litex_soc_ctrl.c +++ b/drivers/soc/litex/litex_soc_ctrl.c @@ -58,7 +58,8 @@ static int litex_check_csr_access(void __iomem *reg_addr) /* restore original value of the SCRATCH register */ litex_write32(reg_addr + SCRATCH_REG_OFF, SCRATCH_REG_VALUE); - pr_info("LiteX SoC Controller driver initialized"); + pr_info("LiteX SoC Controller driver initialized: subreg:%d, align:%d", + LITEX_SUBREG_SIZE, LITEX_SUBREG_ALIGN); return 0; } diff --git a/include/linux/litex.h b/include/linux/litex.h index c63a7e1a337c..3456d527f644 100644 --- a/include/linux/litex.h +++ b/include/linux/litex.h @@ -10,17 +10,14 @@ #define _LINUX_LITEX_H #include -#include -#include -/* - * The parameters below are true for LiteX SoCs configured for 8-bit CSR Bus, - * 32-bit aligned. - * - * Supporting other configurations will require extending the logic in this - * header and in the LiteX SoC controller driver. - */ -#define LITEX_SUBREG_SIZE 0x1 +/* LiteX SoCs support 8- or 32-bit CSR Bus data width (i.e., subreg. size) */ +#if defined(CONFIG_LITEX_SUBREG_SIZE) && \ + (CONFIG_LITEX_SUBREG_SIZE == 1 || CONFIG_LITEX_SUBREG_SIZE == 4) +#define LITEX_SUBREG_SIZE CONFIG_LITEX_SUBREG_SIZE +#else +#error LiteX subregister size (LITEX_SUBREG_SIZE) must be 4 or 1! +#endif #define LITEX_SUBREG_SIZE_BIT (LITEX_SUBREG_SIZE * 8) /* LiteX subregisters of any width are always aligned on a 4-byte boundary */ @@ -36,25 +33,32 @@ static inline u32 _read_litex_subregister(void __iomem *addr) return le32_to_cpu((__le32 __force)readl(addr)); } -#define WRITE_LITEX_SUBREGISTER(val, base_offset, subreg_id) \ - _write_litex_subregister(val, (base_offset) + \ - LITEX_SUBREG_ALIGN * (subreg_id)) - -#define READ_LITEX_SUBREGISTER(base_offset, subreg_id) \ - _read_litex_subregister((base_offset) + \ - LITEX_SUBREG_ALIGN * (subreg_id)) - /* * LiteX SoC Generator, depending on the configuration, can split a single * logical CSR (Control&Status Register) into a series of consecutive physical * registers. * - * For example, in the configuration with 8-bit CSR Bus, 32-bit aligned (the - * default one for 32-bit CPUs) a 32-bit logical CSR will be generated as four - * 32-bit physical registers, each one containing one byte of meaningful data. + * For example, in the configuration with 8-bit CSR Bus, a 32-bit aligned, + * 32-bit wide logical CSR will be laid out as four 32-bit physical + * subregisters, each one containing one byte of meaningful data. * * For details see: https://github.com/enjoy-digital/litex/wiki/CSR-Bus - * + */ + +/* number of LiteX subregisters needed to store a register of given reg_size */ +#define _litex_num_subregs(reg_size) \ + (((reg_size) - 1) / LITEX_SUBREG_SIZE + 1) + +/* + * since the number of 4-byte aligned subregisters required to store a single + * LiteX CSR (MMIO) register varies with LITEX_SUBREG_SIZE, the offset of the + * next adjacent LiteX CSR register w.r.t. the offset of the current one also + * depends on how many subregisters the latter is spread across + */ +#define _next_reg_off(off, size) \ + ((off) + _litex_num_subregs(size) * LITEX_SUBREG_ALIGN) + +/* * The purpose of `litex_set_reg`/`litex_get_reg` is to implement the logic * of writing to/reading from the LiteX CSR in a single place that can be * then reused by all LiteX drivers. @@ -66,22 +70,17 @@ static inline u32 _read_litex_subregister(void __iomem *addr) * @reg_size: The width of the CSR expressed in the number of bytes * @val: Value to be written to the CSR * - * In the currently supported LiteX configuration (8-bit CSR Bus, 32-bit aligned), - * a 32-bit LiteX CSR is generated as 4 consecutive 32-bit physical registers, - * each one containing one byte of meaningful data. - * - * This function splits a single possibly multi-byte write into a series of - * single-byte writes with a proper offset. + * This function splits a single (possibly multi-byte) LiteX CSR write into + * a series of subregister writes with a proper offset. */ -static inline void litex_set_reg(void __iomem *reg, ulong reg_size, ulong val) +static inline void litex_set_reg(void __iomem *reg, size_t reg_size, u64 val) { - ulong shifted_data, shift, i; - - for (i = 0; i < reg_size; ++i) { - shift = ((reg_size - i - 1) * LITEX_SUBREG_SIZE_BIT); - shifted_data = val >> shift; + u8 shift = _litex_num_subregs(reg_size) * LITEX_SUBREG_SIZE_BIT; - WRITE_LITEX_SUBREGISTER(shifted_data, reg, i); + while (shift > 0) { + shift -= LITEX_SUBREG_SIZE_BIT; + _write_litex_subregister(val >> shift, reg); + reg += LITEX_SUBREG_ALIGN; } } @@ -92,89 +91,61 @@ static inline void litex_set_reg(void __iomem *reg, ulong reg_size, ulong val) * * Return: Value read from the CSR * - * In the currently supported LiteX configuration (8-bit CSR Bus, 32-bit aligned), - * a 32-bit LiteX CSR is generated as 4 consecutive 32-bit physical registers, - * each one containing one byte of meaningful data. - * - * This function generates a series of single-byte reads with a proper offset - * and joins their results into a single multi-byte value. + * This function generates a series of subregister reads with a proper offset + * and joins their results into a single (possibly multi-byte) LiteX CSR value. */ -static inline ulong litex_get_reg(void __iomem *reg, ulong reg_size) +static inline u64 litex_get_reg(void __iomem *reg, size_t reg_size) { - ulong shifted_data, shift, i; - ulong result = 0; - - for (i = 0; i < reg_size; ++i) { - shifted_data = READ_LITEX_SUBREGISTER(reg, i); - - shift = ((reg_size - i - 1) * LITEX_SUBREG_SIZE_BIT); - result |= (shifted_data << shift); + u64 r; + u8 i; + + r = _read_litex_subregister(reg); + for (i = 1; i < _litex_num_subregs(reg_size); i++) { + r <<= LITEX_SUBREG_SIZE_BIT; + reg += LITEX_SUBREG_ALIGN; + r |= _read_litex_subregister(reg); } - - return result; + return r; } - static inline void litex_write8(void __iomem *reg, u8 val) { - WRITE_LITEX_SUBREGISTER(val, reg, 0); + litex_set_reg(reg, sizeof(u8), val); } static inline void litex_write16(void __iomem *reg, u16 val) { - WRITE_LITEX_SUBREGISTER(val >> 8, reg, 0); - WRITE_LITEX_SUBREGISTER(val, reg, 1); + litex_set_reg(reg, sizeof(u16), val); } static inline void litex_write32(void __iomem *reg, u32 val) { - WRITE_LITEX_SUBREGISTER(val >> 24, reg, 0); - WRITE_LITEX_SUBREGISTER(val >> 16, reg, 1); - WRITE_LITEX_SUBREGISTER(val >> 8, reg, 2); - WRITE_LITEX_SUBREGISTER(val, reg, 3); + litex_set_reg(reg, sizeof(u32), val); } static inline void litex_write64(void __iomem *reg, u64 val) { - WRITE_LITEX_SUBREGISTER(val >> 56, reg, 0); - WRITE_LITEX_SUBREGISTER(val >> 48, reg, 1); - WRITE_LITEX_SUBREGISTER(val >> 40, reg, 2); - WRITE_LITEX_SUBREGISTER(val >> 32, reg, 3); - WRITE_LITEX_SUBREGISTER(val >> 24, reg, 4); - WRITE_LITEX_SUBREGISTER(val >> 16, reg, 5); - WRITE_LITEX_SUBREGISTER(val >> 8, reg, 6); - WRITE_LITEX_SUBREGISTER(val, reg, 7); + litex_set_reg(reg, sizeof(u64), val); } static inline u8 litex_read8(void __iomem *reg) { - return READ_LITEX_SUBREGISTER(reg, 0); + return litex_get_reg(reg, sizeof(u8)); } static inline u16 litex_read16(void __iomem *reg) { - return (READ_LITEX_SUBREGISTER(reg, 0) << 8) - | (READ_LITEX_SUBREGISTER(reg, 1)); + return litex_get_reg(reg, sizeof(u16)); } static inline u32 litex_read32(void __iomem *reg) { - return (READ_LITEX_SUBREGISTER(reg, 0) << 24) - | (READ_LITEX_SUBREGISTER(reg, 1) << 16) - | (READ_LITEX_SUBREGISTER(reg, 2) << 8) - | (READ_LITEX_SUBREGISTER(reg, 3)); + return litex_get_reg(reg, sizeof(u32)); } static inline u64 litex_read64(void __iomem *reg) { - return ((u64)READ_LITEX_SUBREGISTER(reg, 0) << 56) - | ((u64)READ_LITEX_SUBREGISTER(reg, 1) << 48) - | ((u64)READ_LITEX_SUBREGISTER(reg, 2) << 40) - | ((u64)READ_LITEX_SUBREGISTER(reg, 3) << 32) - | ((u64)READ_LITEX_SUBREGISTER(reg, 4) << 24) - | ((u64)READ_LITEX_SUBREGISTER(reg, 5) << 16) - | ((u64)READ_LITEX_SUBREGISTER(reg, 6) << 8) - | ((u64)READ_LITEX_SUBREGISTER(reg, 7)); + return litex_get_reg(reg, sizeof(u64)); } #endif /* _LINUX_LITEX_H */ -- cgit v1.2.3 From 4f70d150294b3ddfbe4be7130ca53898cd5b91be Mon Sep 17 00:00:00 2001 From: Gabriel Somlo Date: Tue, 12 Jan 2021 12:31:44 -0500 Subject: drivers/soc/litex: make 'litex_[set|get]_reg()' methods private The 'litex_[set|get]_reg()' methods use the 'reg_size' parameter to specify the width of the LiteX CSR (MMIO) register being accessed. Since 'u64' is the widest data being supported, the value of 'reg_size' MUST be between 1 and sizeof(u64), which SHOULD be checked at runtime if these methods are publicly available for use by other LiteX device drivers. At the same time, none of the existing (or foreseeable) LiteX device drivers have a need to access registers whose size is unknown during compilation. As such, all LiteX device drivers should use fixed-width accessor methods such as 'litex_[write|read][8|16|32|64]()'. This patch renames 'litex_[set|get]_reg()' to '_litex_[set|get]_reg()', indicating that they should NOT be directly called from outside of the 'include/linux/litex.h' header file. Signed-off-by: Gabriel Somlo Signed-off-by: Stafford Horne --- drivers/soc/litex/Kconfig | 2 +- include/linux/litex.h | 35 ++++++++++++++++++++--------------- 2 files changed, 21 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/drivers/soc/litex/Kconfig b/drivers/soc/litex/Kconfig index 973f8d2fe1a7..b9b3d51ea7df 100644 --- a/drivers/soc/litex/Kconfig +++ b/drivers/soc/litex/Kconfig @@ -11,7 +11,7 @@ config LITEX_SOC_CONTROLLER select LITEX help This option enables the SoC Controller Driver which verifies - LiteX CSR access and provides common litex_get_reg/litex_set_reg + LiteX CSR access and provides common litex_[read|write]* accessors. All drivers that use functions from litex.h must depend on LITEX. diff --git a/include/linux/litex.h b/include/linux/litex.h index 3456d527f644..5ea9ccf5cce4 100644 --- a/include/linux/litex.h +++ b/include/linux/litex.h @@ -59,21 +59,25 @@ static inline u32 _read_litex_subregister(void __iomem *addr) ((off) + _litex_num_subregs(size) * LITEX_SUBREG_ALIGN) /* - * The purpose of `litex_set_reg`/`litex_get_reg` is to implement the logic - * of writing to/reading from the LiteX CSR in a single place that can be - * then reused by all LiteX drivers. + * The purpose of `_litex_[set|get]_reg()` is to implement the logic of + * writing to/reading from the LiteX CSR in a single place that can be then + * reused by all LiteX drivers via the `litex_[write|read][8|16|32|64]()` + * accessors for the appropriate data width. + * NOTE: direct use of `_litex_[set|get]_reg()` by LiteX drivers is strongly + * discouraged, as they perform no error checking on the requested data width! */ /** - * litex_set_reg() - Writes the value to the LiteX CSR (Control&Status Register) + * _litex_set_reg() - Writes a value to the LiteX CSR (Control&Status Register) * @reg: Address of the CSR * @reg_size: The width of the CSR expressed in the number of bytes * @val: Value to be written to the CSR * * This function splits a single (possibly multi-byte) LiteX CSR write into * a series of subregister writes with a proper offset. + * NOTE: caller is responsible for ensuring (0 < reg_size <= sizeof(u64)). */ -static inline void litex_set_reg(void __iomem *reg, size_t reg_size, u64 val) +static inline void _litex_set_reg(void __iomem *reg, size_t reg_size, u64 val) { u8 shift = _litex_num_subregs(reg_size) * LITEX_SUBREG_SIZE_BIT; @@ -85,7 +89,7 @@ static inline void litex_set_reg(void __iomem *reg, size_t reg_size, u64 val) } /** - * litex_get_reg() - Reads the value of the LiteX CSR (Control&Status Register) + * _litex_get_reg() - Reads a value of the LiteX CSR (Control&Status Register) * @reg: Address of the CSR * @reg_size: The width of the CSR expressed in the number of bytes * @@ -93,8 +97,9 @@ static inline void litex_set_reg(void __iomem *reg, size_t reg_size, u64 val) * * This function generates a series of subregister reads with a proper offset * and joins their results into a single (possibly multi-byte) LiteX CSR value. + * NOTE: caller is responsible for ensuring (0 < reg_size <= sizeof(u64)). */ -static inline u64 litex_get_reg(void __iomem *reg, size_t reg_size) +static inline u64 _litex_get_reg(void __iomem *reg, size_t reg_size) { u64 r; u8 i; @@ -110,42 +115,42 @@ static inline u64 litex_get_reg(void __iomem *reg, size_t reg_size) static inline void litex_write8(void __iomem *reg, u8 val) { - litex_set_reg(reg, sizeof(u8), val); + _litex_set_reg(reg, sizeof(u8), val); } static inline void litex_write16(void __iomem *reg, u16 val) { - litex_set_reg(reg, sizeof(u16), val); + _litex_set_reg(reg, sizeof(u16), val); } static inline void litex_write32(void __iomem *reg, u32 val) { - litex_set_reg(reg, sizeof(u32), val); + _litex_set_reg(reg, sizeof(u32), val); } static inline void litex_write64(void __iomem *reg, u64 val) { - litex_set_reg(reg, sizeof(u64), val); + _litex_set_reg(reg, sizeof(u64), val); } static inline u8 litex_read8(void __iomem *reg) { - return litex_get_reg(reg, sizeof(u8)); + return _litex_get_reg(reg, sizeof(u8)); } static inline u16 litex_read16(void __iomem *reg) { - return litex_get_reg(reg, sizeof(u16)); + return _litex_get_reg(reg, sizeof(u16)); } static inline u32 litex_read32(void __iomem *reg) { - return litex_get_reg(reg, sizeof(u32)); + return _litex_get_reg(reg, sizeof(u32)); } static inline u64 litex_read64(void __iomem *reg) { - return litex_get_reg(reg, sizeof(u64)); + return _litex_get_reg(reg, sizeof(u64)); } #endif /* _LINUX_LITEX_H */ -- cgit v1.2.3 From 64ca771cd6bf48bd01f630ad1440ab151d1d19d5 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 5 Jan 2021 17:48:08 +0100 Subject: crypto: x86 - remove glue helper module All dependencies on the x86 glue helper module have been replaced by local instantiations of the new ECB/CBC preprocessor helper macros, so the glue helper module can be retired. Acked-by: Eric Biggers Signed-off-by: Ard Biesheuvel Signed-off-by: Herbert Xu --- arch/x86/crypto/Makefile | 2 - arch/x86/crypto/glue_helper.c | 155 ------------------------------ arch/x86/include/asm/crypto/glue_helper.h | 74 -------------- crypto/Kconfig | 5 - crypto/skcipher.c | 6 -- include/crypto/internal/skcipher.h | 1 - 6 files changed, 243 deletions(-) delete mode 100644 arch/x86/crypto/glue_helper.c delete mode 100644 arch/x86/include/asm/crypto/glue_helper.h (limited to 'include') diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile index a31de0c6ccde..b28e36b7c96b 100644 --- a/arch/x86/crypto/Makefile +++ b/arch/x86/crypto/Makefile @@ -4,8 +4,6 @@ OBJECT_FILES_NON_STANDARD := y -obj-$(CONFIG_CRYPTO_GLUE_HELPER_X86) += glue_helper.o - obj-$(CONFIG_CRYPTO_TWOFISH_586) += twofish-i586.o twofish-i586-y := twofish-i586-asm_32.o twofish_glue.o obj-$(CONFIG_CRYPTO_TWOFISH_X86_64) += twofish-x86_64.o diff --git a/arch/x86/crypto/glue_helper.c b/arch/x86/crypto/glue_helper.c deleted file mode 100644 index 895d34150c3f..000000000000 --- a/arch/x86/crypto/glue_helper.c +++ /dev/null @@ -1,155 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Shared glue code for 128bit block ciphers - * - * Copyright © 2012-2013 Jussi Kivilinna - * - * CBC & ECB parts based on code (crypto/cbc.c,ecb.c) by: - * Copyright (c) 2006 Herbert Xu - */ - -#include -#include -#include -#include -#include - -int glue_ecb_req_128bit(const struct common_glue_ctx *gctx, - struct skcipher_request *req) -{ - void *ctx = crypto_skcipher_ctx(crypto_skcipher_reqtfm(req)); - const unsigned int bsize = 128 / 8; - struct skcipher_walk walk; - bool fpu_enabled = false; - unsigned int nbytes; - int err; - - err = skcipher_walk_virt(&walk, req, false); - - while ((nbytes = walk.nbytes)) { - const u8 *src = walk.src.virt.addr; - u8 *dst = walk.dst.virt.addr; - unsigned int func_bytes; - unsigned int i; - - fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit, - &walk, fpu_enabled, nbytes); - for (i = 0; i < gctx->num_funcs; i++) { - func_bytes = bsize * gctx->funcs[i].num_blocks; - - if (nbytes < func_bytes) - continue; - - /* Process multi-block batch */ - do { - gctx->funcs[i].fn_u.ecb(ctx, dst, src); - src += func_bytes; - dst += func_bytes; - nbytes -= func_bytes; - } while (nbytes >= func_bytes); - - if (nbytes < bsize) - break; - } - err = skcipher_walk_done(&walk, nbytes); - } - - glue_fpu_end(fpu_enabled); - return err; -} -EXPORT_SYMBOL_GPL(glue_ecb_req_128bit); - -int glue_cbc_encrypt_req_128bit(const common_glue_func_t fn, - struct skcipher_request *req) -{ - void *ctx = crypto_skcipher_ctx(crypto_skcipher_reqtfm(req)); - const unsigned int bsize = 128 / 8; - struct skcipher_walk walk; - unsigned int nbytes; - int err; - - err = skcipher_walk_virt(&walk, req, false); - - while ((nbytes = walk.nbytes)) { - const u128 *src = (u128 *)walk.src.virt.addr; - u128 *dst = (u128 *)walk.dst.virt.addr; - u128 *iv = (u128 *)walk.iv; - - do { - u128_xor(dst, src, iv); - fn(ctx, (u8 *)dst, (u8 *)dst); - iv = dst; - src++; - dst++; - nbytes -= bsize; - } while (nbytes >= bsize); - - *(u128 *)walk.iv = *iv; - err = skcipher_walk_done(&walk, nbytes); - } - return err; -} -EXPORT_SYMBOL_GPL(glue_cbc_encrypt_req_128bit); - -int glue_cbc_decrypt_req_128bit(const struct common_glue_ctx *gctx, - struct skcipher_request *req) -{ - void *ctx = crypto_skcipher_ctx(crypto_skcipher_reqtfm(req)); - const unsigned int bsize = 128 / 8; - struct skcipher_walk walk; - bool fpu_enabled = false; - unsigned int nbytes; - int err; - - err = skcipher_walk_virt(&walk, req, false); - - while ((nbytes = walk.nbytes)) { - const u128 *src = walk.src.virt.addr; - u128 *dst = walk.dst.virt.addr; - unsigned int func_bytes, num_blocks; - unsigned int i; - u128 last_iv; - - fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit, - &walk, fpu_enabled, nbytes); - /* Start of the last block. */ - src += nbytes / bsize - 1; - dst += nbytes / bsize - 1; - - last_iv = *src; - - for (i = 0; i < gctx->num_funcs; i++) { - num_blocks = gctx->funcs[i].num_blocks; - func_bytes = bsize * num_blocks; - - if (nbytes < func_bytes) - continue; - - /* Process multi-block batch */ - do { - src -= num_blocks - 1; - dst -= num_blocks - 1; - - gctx->funcs[i].fn_u.cbc(ctx, (u8 *)dst, - (const u8 *)src); - - nbytes -= func_bytes; - if (nbytes < bsize) - goto done; - - u128_xor(dst, dst, --src); - dst--; - } while (nbytes >= func_bytes); - } -done: - u128_xor(dst, dst, (u128 *)walk.iv); - *(u128 *)walk.iv = last_iv; - err = skcipher_walk_done(&walk, nbytes); - } - - glue_fpu_end(fpu_enabled); - return err; -} -EXPORT_SYMBOL_GPL(glue_cbc_decrypt_req_128bit); - -MODULE_LICENSE("GPL"); diff --git a/arch/x86/include/asm/crypto/glue_helper.h b/arch/x86/include/asm/crypto/glue_helper.h deleted file mode 100644 index 23e09efd2aa6..000000000000 --- a/arch/x86/include/asm/crypto/glue_helper.h +++ /dev/null @@ -1,74 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Shared glue code for 128bit block ciphers - */ - -#ifndef _CRYPTO_GLUE_HELPER_H -#define _CRYPTO_GLUE_HELPER_H - -#include -#include -#include - -typedef void (*common_glue_func_t)(const void *ctx, u8 *dst, const u8 *src); -typedef void (*common_glue_cbc_func_t)(const void *ctx, u8 *dst, const u8 *src); - -struct common_glue_func_entry { - unsigned int num_blocks; /* number of blocks that @fn will process */ - union { - common_glue_func_t ecb; - common_glue_cbc_func_t cbc; - } fn_u; -}; - -struct common_glue_ctx { - unsigned int num_funcs; - int fpu_blocks_limit; /* -1 means fpu not needed at all */ - - /* - * First funcs entry must have largest num_blocks and last funcs entry - * must have num_blocks == 1! - */ - struct common_glue_func_entry funcs[]; -}; - -static inline bool glue_fpu_begin(unsigned int bsize, int fpu_blocks_limit, - struct skcipher_walk *walk, - bool fpu_enabled, unsigned int nbytes) -{ - if (likely(fpu_blocks_limit < 0)) - return false; - - if (fpu_enabled) - return true; - - /* - * Vector-registers are only used when chunk to be processed is large - * enough, so do not enable FPU until it is necessary. - */ - if (nbytes < bsize * (unsigned int)fpu_blocks_limit) - return false; - - /* prevent sleeping if FPU is in use */ - skcipher_walk_atomise(walk); - - kernel_fpu_begin(); - return true; -} - -static inline void glue_fpu_end(bool fpu_enabled) -{ - if (fpu_enabled) - kernel_fpu_end(); -} - -extern int glue_ecb_req_128bit(const struct common_glue_ctx *gctx, - struct skcipher_request *req); - -extern int glue_cbc_encrypt_req_128bit(const common_glue_func_t fn, - struct skcipher_request *req); - -extern int glue_cbc_decrypt_req_128bit(const struct common_glue_ctx *gctx, - struct skcipher_request *req); - -#endif /* _CRYPTO_GLUE_HELPER_H */ diff --git a/crypto/Kconfig b/crypto/Kconfig index b2182658c55e..94f0fde06b94 100644 --- a/crypto/Kconfig +++ b/crypto/Kconfig @@ -210,11 +210,6 @@ config CRYPTO_SIMD tristate select CRYPTO_CRYPTD -config CRYPTO_GLUE_HELPER_X86 - tristate - depends on X86 - select CRYPTO_SKCIPHER - config CRYPTO_ENGINE tristate diff --git a/crypto/skcipher.c b/crypto/skcipher.c index ff16d05644c7..a15376245416 100644 --- a/crypto/skcipher.c +++ b/crypto/skcipher.c @@ -491,12 +491,6 @@ int skcipher_walk_virt(struct skcipher_walk *walk, } EXPORT_SYMBOL_GPL(skcipher_walk_virt); -void skcipher_walk_atomise(struct skcipher_walk *walk) -{ - walk->flags &= ~SKCIPHER_WALK_SLEEP; -} -EXPORT_SYMBOL_GPL(skcipher_walk_atomise); - int skcipher_walk_async(struct skcipher_walk *walk, struct skcipher_request *req) { diff --git a/include/crypto/internal/skcipher.h b/include/crypto/internal/skcipher.h index 9dd6c0c17eb8..a2339f80a615 100644 --- a/include/crypto/internal/skcipher.h +++ b/include/crypto/internal/skcipher.h @@ -133,7 +133,6 @@ int skcipher_walk_done(struct skcipher_walk *walk, int err); int skcipher_walk_virt(struct skcipher_walk *walk, struct skcipher_request *req, bool atomic); -void skcipher_walk_atomise(struct skcipher_walk *walk); int skcipher_walk_async(struct skcipher_walk *walk, struct skcipher_request *req); int skcipher_walk_aead_encrypt(struct skcipher_walk *walk, -- cgit v1.2.3 From b0f87e8ac263e3b82ec314542cb7fb07a47fc8b7 Mon Sep 17 00:00:00 2001 From: Yoshihiro Shimoda Date: Tue, 12 Jan 2021 18:00:58 +0900 Subject: mfd: rohm-generic: Add BD9571 and BD9574 Add chip IDs for BD9571MWV and BD9574MWF. Signed-off-by: Yoshihiro Shimoda Reviewed-by: Matti Vaittinen Acked-for-MFD-by: Lee Jones Signed-off-by: Lee Jones --- include/linux/mfd/rohm-generic.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mfd/rohm-generic.h b/include/linux/mfd/rohm-generic.h index 4283b5b33e04..affacf8c6e91 100644 --- a/include/linux/mfd/rohm-generic.h +++ b/include/linux/mfd/rohm-generic.h @@ -12,6 +12,8 @@ enum rohm_chip_type { ROHM_CHIP_TYPE_BD71847, ROHM_CHIP_TYPE_BD70528, ROHM_CHIP_TYPE_BD71828, + ROHM_CHIP_TYPE_BD9571, + ROHM_CHIP_TYPE_BD9574, ROHM_CHIP_TYPE_AMOUNT }; -- cgit v1.2.3 From bfb26be7fe90186e5d9fe704cc124ab77bb7d127 Mon Sep 17 00:00:00 2001 From: Yoshihiro Shimoda Date: Tue, 12 Jan 2021 18:01:04 +0900 Subject: mfd: bd9571mwv: Use the SPDX license identifier Use the SPDX license identifier instead of a local description. Signed-off-by: Yoshihiro Shimoda Reviewed-by: Geert Uytterhoeven Acked-for-MFD-by: Lee Jones Signed-off-by: Lee Jones --- drivers/mfd/bd9571mwv.c | 10 +--------- include/linux/mfd/bd9571mwv.h | 10 +--------- 2 files changed, 2 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/drivers/mfd/bd9571mwv.c b/drivers/mfd/bd9571mwv.c index 19d57a45134c..e68c3fabf9fc 100644 --- a/drivers/mfd/bd9571mwv.c +++ b/drivers/mfd/bd9571mwv.c @@ -1,17 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * ROHM BD9571MWV-M MFD driver * * Copyright (C) 2017 Marek Vasut * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed "as is" WITHOUT ANY WARRANTY of any - * kind, whether expressed or implied; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License version 2 for more details. - * * Based on the TPS65086 driver */ diff --git a/include/linux/mfd/bd9571mwv.h b/include/linux/mfd/bd9571mwv.h index eb05569f752b..bcc709293b24 100644 --- a/include/linux/mfd/bd9571mwv.h +++ b/include/linux/mfd/bd9571mwv.h @@ -1,17 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * ROHM BD9571MWV-M driver * * Copyright (C) 2017 Marek Vasut * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed "as is" WITHOUT ANY WARRANTY of any - * kind, whether expressed or implied; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License version 2 for more details. - * * Based on the TPS65086 driver */ -- cgit v1.2.3 From f16e1fd197f85a943b5880009f4aefe05a17df0d Mon Sep 17 00:00:00 2001 From: Khiem Nguyen Date: Tue, 12 Jan 2021 18:01:06 +0900 Subject: mfd: bd9571mwv: Make the driver more generic Since the driver supports BD9571MWV PMIC only, this patch makes the functions and data structure become more generic so that it can support other PMIC variants as well. Also remove printing part name which Lee Jones suggested. Signed-off-by: Khiem Nguyen Co-developed-by: Yoshihiro Shimoda Signed-off-by: Yoshihiro Shimoda Reviewed-by: Matti Vaittinen Acked-for-MFD-by: Lee Jones Signed-off-by: Lee Jones --- drivers/mfd/bd9571mwv.c | 77 +++++++++++++++++++++++-------------------- include/linux/mfd/bd9571mwv.h | 18 ++-------- 2 files changed, 43 insertions(+), 52 deletions(-) (limited to 'include') diff --git a/drivers/mfd/bd9571mwv.c b/drivers/mfd/bd9571mwv.c index 49e968e20ddc..2c1fcbb6ff2b 100644 --- a/drivers/mfd/bd9571mwv.c +++ b/drivers/mfd/bd9571mwv.c @@ -3,6 +3,7 @@ * ROHM BD9571MWV-M MFD driver * * Copyright (C) 2017 Marek Vasut + * Copyright (C) 2020 Renesas Electronics Corporation * * Based on the TPS65086 driver */ @@ -102,13 +103,12 @@ static struct regmap_irq_chip bd9571mwv_irq_chip = { .num_irqs = ARRAY_SIZE(bd9571mwv_irqs), }; -static int bd9571mwv_identify(struct bd9571mwv *bd) +static int bd957x_identify(struct device *dev, struct regmap *regmap) { - struct device *dev = bd->dev; unsigned int value; int ret; - ret = regmap_read(bd->regmap, BD9571MWV_VENDOR_CODE, &value); + ret = regmap_read(regmap, BD9571MWV_VENDOR_CODE, &value); if (ret) { dev_err(dev, "Failed to read vendor code register (ret=%i)\n", ret); @@ -121,66 +121,71 @@ static int bd9571mwv_identify(struct bd9571mwv *bd) return -EINVAL; } - ret = regmap_read(bd->regmap, BD9571MWV_PRODUCT_CODE, &value); + ret = regmap_read(regmap, BD9571MWV_PRODUCT_CODE, &value); if (ret) { dev_err(dev, "Failed to read product code register (ret=%i)\n", ret); return ret; } - - if (value != BD9571MWV_PRODUCT_CODE_VAL) { - dev_err(dev, "Invalid product code ID %02x (expected %02x)\n", - value, BD9571MWV_PRODUCT_CODE_VAL); - return -EINVAL; - } - - ret = regmap_read(bd->regmap, BD9571MWV_PRODUCT_REVISION, &value); + ret = regmap_read(regmap, BD9571MWV_PRODUCT_REVISION, &value); if (ret) { dev_err(dev, "Failed to read revision register (ret=%i)\n", ret); return ret; } - dev_info(dev, "Device: BD9571MWV rev. %d\n", value & 0xff); - return 0; } static int bd9571mwv_probe(struct i2c_client *client, - const struct i2c_device_id *ids) + const struct i2c_device_id *ids) { - struct bd9571mwv *bd; - int ret; - - bd = devm_kzalloc(&client->dev, sizeof(*bd), GFP_KERNEL); - if (!bd) - return -ENOMEM; + const struct regmap_config *regmap_config; + const struct regmap_irq_chip *irq_chip; + const struct mfd_cell *cells; + struct device *dev = &client->dev; + struct regmap *regmap; + struct regmap_irq_chip_data *irq_data; + int ret, num_cells, irq = client->irq; + + /* Read the PMIC product code */ + ret = i2c_smbus_read_byte_data(client, BD9571MWV_PRODUCT_CODE); + if (ret < 0) { + dev_err(dev, "Failed to read product code\n"); + return ret; + } - i2c_set_clientdata(client, bd); - bd->dev = &client->dev; - bd->irq = client->irq; + switch (ret) { + case BD9571MWV_PRODUCT_CODE_BD9571MWV: + regmap_config = &bd9571mwv_regmap_config; + irq_chip = &bd9571mwv_irq_chip; + cells = bd9571mwv_cells; + num_cells = ARRAY_SIZE(bd9571mwv_cells); + break; + default: + dev_err(dev, "Unsupported device 0x%x\n", ret); + return -ENODEV; + } - bd->regmap = devm_regmap_init_i2c(client, &bd9571mwv_regmap_config); - if (IS_ERR(bd->regmap)) { - dev_err(bd->dev, "Failed to initialize register map\n"); - return PTR_ERR(bd->regmap); + regmap = devm_regmap_init_i2c(client, regmap_config); + if (IS_ERR(regmap)) { + dev_err(dev, "Failed to initialize register map\n"); + return PTR_ERR(regmap); } - ret = bd9571mwv_identify(bd); + ret = bd957x_identify(dev, regmap); if (ret) return ret; - ret = devm_regmap_add_irq_chip(bd->dev, bd->regmap, bd->irq, - IRQF_ONESHOT, 0, &bd9571mwv_irq_chip, - &bd->irq_data); + ret = devm_regmap_add_irq_chip(dev, regmap, irq, IRQF_ONESHOT, 0, + irq_chip, &irq_data); if (ret) { - dev_err(bd->dev, "Failed to register IRQ chip\n"); + dev_err(dev, "Failed to register IRQ chip\n"); return ret; } - return devm_mfd_add_devices(bd->dev, PLATFORM_DEVID_AUTO, - bd9571mwv_cells, ARRAY_SIZE(bd9571mwv_cells), - NULL, 0, regmap_irq_get_domain(bd->irq_data)); + return devm_mfd_add_devices(dev, PLATFORM_DEVID_AUTO, cells, num_cells, + NULL, 0, regmap_irq_get_domain(irq_data)); } static const struct of_device_id bd9571mwv_of_match_table[] = { diff --git a/include/linux/mfd/bd9571mwv.h b/include/linux/mfd/bd9571mwv.h index bcc709293b24..e1716eca6bb5 100644 --- a/include/linux/mfd/bd9571mwv.h +++ b/include/linux/mfd/bd9571mwv.h @@ -3,6 +3,7 @@ * ROHM BD9571MWV-M driver * * Copyright (C) 2017 Marek Vasut + * Copyright (C) 2020 Renesas Electronics Corporation * * Based on the TPS65086 driver */ @@ -17,7 +18,7 @@ #define BD9571MWV_VENDOR_CODE 0x00 #define BD9571MWV_VENDOR_CODE_VAL 0xdb #define BD9571MWV_PRODUCT_CODE 0x01 -#define BD9571MWV_PRODUCT_CODE_VAL 0x60 +#define BD9571MWV_PRODUCT_CODE_BD9571MWV 0x60 #define BD9571MWV_PRODUCT_REVISION 0x02 #define BD9571MWV_I2C_FUSA_MODE 0x10 @@ -94,19 +95,4 @@ enum bd9571mwv_irqs { BD9571MWV_IRQ_WDT_OF, BD9571MWV_IRQ_BKUP_TRG, }; - -/** - * struct bd9571mwv - state holder for the bd9571mwv driver - * - * Device data may be used to access the BD9571MWV chip - */ -struct bd9571mwv { - struct device *dev; - struct regmap *regmap; - - /* IRQ Data */ - int irq; - struct regmap_irq_chip_data *irq_data; -}; - #endif /* __LINUX_MFD_BD9571MWV_H */ -- cgit v1.2.3 From b2548da647bb04737196ffd945505d47a166239b Mon Sep 17 00:00:00 2001 From: Khiem Nguyen Date: Tue, 12 Jan 2021 18:01:07 +0900 Subject: mfd: bd9571mwv: Add support for BD9574MWF The new PMIC BD9574MWF inherits features from BD9571MWV. Add the support of new PMIC to existing bd9571mwv driver. Signed-off-by: Khiem Nguyen Co-developed-by: Yoshihiro Shimoda Signed-off-by: Yoshihiro Shimoda Reviewed-by: Matti Vaittinen Acked-for-MFD-by: Lee Jones Signed-off-by: Lee Jones --- drivers/mfd/bd9571mwv.c | 76 ++++++++++++++++++++++++++++++++++++++++++- include/linux/mfd/bd9571mwv.h | 17 ++++++++-- 2 files changed, 89 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/mfd/bd9571mwv.c b/drivers/mfd/bd9571mwv.c index 2c1fcbb6ff2b..e15b1acfb063 100644 --- a/drivers/mfd/bd9571mwv.c +++ b/drivers/mfd/bd9571mwv.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * ROHM BD9571MWV-M MFD driver + * ROHM BD9571MWV-M and BD9574MVF-M core driver * * Copyright (C) 2017 Marek Vasut * Copyright (C) 2020 Renesas Electronics Corporation @@ -11,6 +11,7 @@ #include #include #include +#include #include #include @@ -103,6 +104,72 @@ static struct regmap_irq_chip bd9571mwv_irq_chip = { .num_irqs = ARRAY_SIZE(bd9571mwv_irqs), }; +static const struct mfd_cell bd9574mwf_cells[] = { + { .name = "bd9574mwf-regulator", }, + { .name = "bd9574mwf-gpio", }, +}; + +static const struct regmap_range bd9574mwf_readable_yes_ranges[] = { + regmap_reg_range(BD9571MWV_VENDOR_CODE, BD9571MWV_PRODUCT_REVISION), + regmap_reg_range(BD9571MWV_BKUP_MODE_CNT, BD9571MWV_BKUP_MODE_CNT), + regmap_reg_range(BD9571MWV_DVFS_VINIT, BD9571MWV_DVFS_SETVMAX), + regmap_reg_range(BD9571MWV_DVFS_SETVID, BD9571MWV_DVFS_MONIVDAC), + regmap_reg_range(BD9571MWV_GPIO_IN, BD9571MWV_GPIO_IN), + regmap_reg_range(BD9571MWV_GPIO_INT, BD9571MWV_GPIO_INTMASK), + regmap_reg_range(BD9571MWV_INT_INTREQ, BD9571MWV_INT_INTMASK), +}; + +static const struct regmap_access_table bd9574mwf_readable_table = { + .yes_ranges = bd9574mwf_readable_yes_ranges, + .n_yes_ranges = ARRAY_SIZE(bd9574mwf_readable_yes_ranges), +}; + +static const struct regmap_range bd9574mwf_writable_yes_ranges[] = { + regmap_reg_range(BD9571MWV_BKUP_MODE_CNT, BD9571MWV_BKUP_MODE_CNT), + regmap_reg_range(BD9571MWV_DVFS_SETVID, BD9571MWV_DVFS_SETVID), + regmap_reg_range(BD9571MWV_GPIO_DIR, BD9571MWV_GPIO_OUT), + regmap_reg_range(BD9571MWV_GPIO_INT_SET, BD9571MWV_GPIO_INTMASK), + regmap_reg_range(BD9571MWV_INT_INTREQ, BD9571MWV_INT_INTMASK), +}; + +static const struct regmap_access_table bd9574mwf_writable_table = { + .yes_ranges = bd9574mwf_writable_yes_ranges, + .n_yes_ranges = ARRAY_SIZE(bd9574mwf_writable_yes_ranges), +}; + +static const struct regmap_range bd9574mwf_volatile_yes_ranges[] = { + regmap_reg_range(BD9571MWV_DVFS_MONIVDAC, BD9571MWV_DVFS_MONIVDAC), + regmap_reg_range(BD9571MWV_GPIO_IN, BD9571MWV_GPIO_IN), + regmap_reg_range(BD9571MWV_GPIO_INT, BD9571MWV_GPIO_INT), + regmap_reg_range(BD9571MWV_INT_INTREQ, BD9571MWV_INT_INTREQ), +}; + +static const struct regmap_access_table bd9574mwf_volatile_table = { + .yes_ranges = bd9574mwf_volatile_yes_ranges, + .n_yes_ranges = ARRAY_SIZE(bd9574mwf_volatile_yes_ranges), +}; + +static const struct regmap_config bd9574mwf_regmap_config = { + .reg_bits = 8, + .val_bits = 8, + .cache_type = REGCACHE_RBTREE, + .rd_table = &bd9574mwf_readable_table, + .wr_table = &bd9574mwf_writable_table, + .volatile_table = &bd9574mwf_volatile_table, + .max_register = 0xff, +}; + +static struct regmap_irq_chip bd9574mwf_irq_chip = { + .name = "bd9574mwf", + .status_base = BD9571MWV_INT_INTREQ, + .mask_base = BD9571MWV_INT_INTMASK, + .ack_base = BD9571MWV_INT_INTREQ, + .init_ack_masked = true, + .num_regs = 1, + .irqs = bd9571mwv_irqs, + .num_irqs = ARRAY_SIZE(bd9571mwv_irqs), +}; + static int bd957x_identify(struct device *dev, struct regmap *regmap) { unsigned int value; @@ -162,6 +229,12 @@ static int bd9571mwv_probe(struct i2c_client *client, cells = bd9571mwv_cells; num_cells = ARRAY_SIZE(bd9571mwv_cells); break; + case BD9571MWV_PRODUCT_CODE_BD9574MWF: + regmap_config = &bd9574mwf_regmap_config; + irq_chip = &bd9574mwf_irq_chip; + cells = bd9574mwf_cells; + num_cells = ARRAY_SIZE(bd9574mwf_cells); + break; default: dev_err(dev, "Unsupported device 0x%x\n", ret); return -ENODEV; @@ -190,6 +263,7 @@ static int bd9571mwv_probe(struct i2c_client *client, static const struct of_device_id bd9571mwv_of_match_table[] = { { .compatible = "rohm,bd9571mwv", }, + { .compatible = "rohm,bd9574mwf", }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, bd9571mwv_of_match_table); diff --git a/include/linux/mfd/bd9571mwv.h b/include/linux/mfd/bd9571mwv.h index e1716eca6bb5..8efd99d07c9e 100644 --- a/include/linux/mfd/bd9571mwv.h +++ b/include/linux/mfd/bd9571mwv.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * ROHM BD9571MWV-M driver + * ROHM BD9571MWV-M and BD9574MWF-M driver * * Copyright (C) 2017 Marek Vasut * Copyright (C) 2020 Renesas Electronics Corporation @@ -14,11 +14,12 @@ #include #include -/* List of registers for BD9571MWV */ +/* List of registers for BD9571MWV and BD9574MWF */ #define BD9571MWV_VENDOR_CODE 0x00 #define BD9571MWV_VENDOR_CODE_VAL 0xdb #define BD9571MWV_PRODUCT_CODE 0x01 #define BD9571MWV_PRODUCT_CODE_BD9571MWV 0x60 +#define BD9571MWV_PRODUCT_CODE_BD9574MWF 0x74 #define BD9571MWV_PRODUCT_REVISION 0x02 #define BD9571MWV_I2C_FUSA_MODE 0x10 @@ -48,6 +49,7 @@ #define BD9571MWV_VD33_VID 0x44 #define BD9571MWV_DVFS_VINIT 0x50 +#define BD9574MWF_VD09_VINIT 0x51 #define BD9571MWV_DVFS_SETVMAX 0x52 #define BD9571MWV_DVFS_BOOSTVID 0x53 #define BD9571MWV_DVFS_SETVID 0x54 @@ -61,6 +63,7 @@ #define BD9571MWV_GPIO_INT_SET 0x64 #define BD9571MWV_GPIO_INT 0x65 #define BD9571MWV_GPIO_INTMASK 0x66 +#define BD9574MWF_GPIO_MUX 0x67 #define BD9571MWV_REG_KEEP(n) (0x70 + (n)) @@ -70,6 +73,8 @@ #define BD9571MWV_PROT_ERROR_STATUS2 0x83 #define BD9571MWV_PROT_ERROR_STATUS3 0x84 #define BD9571MWV_PROT_ERROR_STATUS4 0x85 +#define BD9574MWF_PROT_ERROR_STATUS5 0x86 +#define BD9574MWF_SYSTEM_ERROR_STATUS 0x87 #define BD9571MWV_INT_INTREQ 0x90 #define BD9571MWV_INT_INTREQ_MD1_INT BIT(0) @@ -82,6 +87,12 @@ #define BD9571MWV_INT_INTREQ_BKUP_TRG_INT BIT(7) #define BD9571MWV_INT_INTMASK 0x91 +#define BD9574MWF_SSCG_CNT 0xA0 +#define BD9574MWF_POFFB_MRB 0xA1 +#define BD9574MWF_SMRB_WR_PROT 0xA2 +#define BD9574MWF_SMRB_ASSERT 0xA3 +#define BD9574MWF_SMRB_STATUS 0xA4 + #define BD9571MWV_ACCESS_KEY 0xff /* Define the BD9571MWV IRQ numbers */ @@ -91,7 +102,7 @@ enum bd9571mwv_irqs { BD9571MWV_IRQ_MD2_E2, BD9571MWV_IRQ_PROT_ERR, BD9571MWV_IRQ_GP, - BD9571MWV_IRQ_128H_OF, + BD9571MWV_IRQ_128H_OF, /* BKUP_HOLD on BD9574MWF */ BD9571MWV_IRQ_WDT_OF, BD9571MWV_IRQ_BKUP_TRG, }; -- cgit v1.2.3 From 097d43d8570457c1af9b09fab15412697b177f35 Mon Sep 17 00:00:00 2001 From: Daeseok Youn Date: Thu, 14 Jan 2021 16:08:17 +0900 Subject: mm: memblock: remove return value of memblock_free_all() No one checks the return value of memblock_free_all(). Make the return value void. memblock_free_all() is used on mem_init() for each architecture, and the total count of freed pages will be added to _totalram_pages variable by calling totalram_pages_add(). so do not need to return total count of freed pages. Signed-off-by: Daeseok Youn Reviewed-by: David Hildenbrand Signed-off-by: Mike Rapoport --- include/linux/memblock.h | 2 +- mm/memblock.c | 6 +----- 2 files changed, 2 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index b93c44b9121e..acf1e6a85066 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -117,7 +117,7 @@ int memblock_mark_mirror(phys_addr_t base, phys_addr_t size); int memblock_mark_nomap(phys_addr_t base, phys_addr_t size); int memblock_clear_nomap(phys_addr_t base, phys_addr_t size); -unsigned long memblock_free_all(void); +void memblock_free_all(void); void reset_node_managed_pages(pg_data_t *pgdat); void reset_all_zones_managed_pages(void); diff --git a/mm/memblock.c b/mm/memblock.c index d24bcfa88d2f..daf06f2847ed 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -2087,10 +2087,8 @@ void __init reset_all_zones_managed_pages(void) /** * memblock_free_all - release free pages to the buddy allocator - * - * Return: the number of pages actually released. */ -unsigned long __init memblock_free_all(void) +void __init memblock_free_all(void) { unsigned long pages; @@ -2099,8 +2097,6 @@ unsigned long __init memblock_free_all(void) pages = free_low_memory_core_early(); totalram_pages_add(pages); - - return pages; } #if defined(CONFIG_DEBUG_FS) && defined(CONFIG_ARCH_KEEP_MEMBLOCK) -- cgit v1.2.3 From 7569c6051fc44a54333c086be35347081b521025 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 14 Jan 2021 09:04:51 +0100 Subject: drm: drm_crc: fix a kernel-doc markup A function has a different name between their prototype and its kernel-doc markup: ../include/drm/drm_crtc.h:1257: warning: expecting prototype for drm_crtc_alloc_with_planes(). Prototype was for drmm_crtc_alloc_with_planes() instead Signed-off-by: Mauro Carvalho Chehab Acked-by: Simon Ser Signed-off-by: Simon Ser Link: https://patchwork.freedesktop.org/patch/msgid/2439fb6713e9b2aa27a81f3269a4b0e8e7dfcd36.1610610937.git.mchehab+huawei@kernel.org --- include/drm/drm_crtc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h index 540e2e43ec93..13eeba2a750a 100644 --- a/include/drm/drm_crtc.h +++ b/include/drm/drm_crtc.h @@ -1232,7 +1232,7 @@ void *__drmm_crtc_alloc_with_planes(struct drm_device *dev, const char *name, ...); /** - * drm_crtc_alloc_with_planes - Allocate and initialize a new CRTC object with + * drmm_crtc_alloc_with_planes - Allocate and initialize a new CRTC object with * specified primary and cursor planes. * @dev: DRM device * @type: the type of the struct which contains struct &drm_crtc -- cgit v1.2.3 From dc5723b02e523b2c4a68667f7e28c65018f7202f Mon Sep 17 00:00:00 2001 From: Sami Tolvanen Date: Fri, 11 Dec 2020 10:46:19 -0800 Subject: kbuild: add support for Clang LTO This change adds build system support for Clang's Link Time Optimization (LTO). With -flto, instead of ELF object files, Clang produces LLVM bitcode, which is compiled into native code at link time, allowing the final binary to be optimized globally. For more details, see: https://llvm.org/docs/LinkTimeOptimization.html The Kconfig option CONFIG_LTO_CLANG is implemented as a choice, which defaults to LTO being disabled. To use LTO, the architecture must select ARCH_SUPPORTS_LTO_CLANG and support: - compiling with Clang, - compiling all assembly code with Clang's integrated assembler, - and linking with LLD. While using CONFIG_LTO_CLANG_FULL results in the best runtime performance, the compilation is not scalable in time or memory. CONFIG_LTO_CLANG_THIN enables ThinLTO, which allows parallel optimization and faster incremental builds. ThinLTO is used by default if the architecture also selects ARCH_SUPPORTS_LTO_CLANG_THIN: https://clang.llvm.org/docs/ThinLTO.html To enable LTO, LLVM tools must be used to handle bitcode files, by passing LLVM=1 and LLVM_IAS=1 options to make: $ make LLVM=1 LLVM_IAS=1 defconfig $ scripts/config -e LTO_CLANG_THIN $ make LLVM=1 LLVM_IAS=1 To prepare for LTO support with other compilers, common parts are gated behind the CONFIG_LTO option, and LTO can be disabled for specific files by filtering out CC_FLAGS_LTO. Signed-off-by: Sami Tolvanen Reviewed-by: Kees Cook Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20201211184633.3213045-3-samitolvanen@google.com --- Makefile | 19 +++++++- arch/Kconfig | 91 +++++++++++++++++++++++++++++++++++++++ include/asm-generic/vmlinux.lds.h | 11 +++-- scripts/Makefile.build | 9 +++- scripts/Makefile.modfinal | 9 +++- scripts/Makefile.modpost | 21 ++++++++- scripts/link-vmlinux.sh | 32 ++++++++++---- 7 files changed, 174 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/Makefile b/Makefile index b434c342080b..2b9bcecd6ea1 100644 --- a/Makefile +++ b/Makefile @@ -893,6 +893,21 @@ KBUILD_CFLAGS += $(CC_FLAGS_SCS) export CC_FLAGS_SCS endif +ifdef CONFIG_LTO_CLANG +ifdef CONFIG_LTO_CLANG_THIN +CC_FLAGS_LTO += -flto=thin -fsplit-lto-unit +KBUILD_LDFLAGS += --thinlto-cache-dir=$(extmod-prefix).thinlto-cache +else +CC_FLAGS_LTO += -flto +endif +CC_FLAGS_LTO += -fvisibility=hidden +endif + +ifdef CONFIG_LTO +KBUILD_CFLAGS += $(CC_FLAGS_LTO) +export CC_FLAGS_LTO +endif + ifdef CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_32B KBUILD_CFLAGS += -falign-functions=32 endif @@ -1479,7 +1494,7 @@ MRPROPER_FILES += include/config include/generated \ *.spec # Directories & files removed with 'make distclean' -DISTCLEAN_FILES += tags TAGS cscope* GPATH GTAGS GRTAGS GSYMS +DISTCLEAN_FILES += tags TAGS cscope* GPATH GTAGS GRTAGS GSYMS .thinlto-cache # clean - Delete most, but leave enough to build external modules # @@ -1725,7 +1740,7 @@ PHONY += compile_commands.json clean-dirs := $(KBUILD_EXTMOD) clean: rm-files := $(KBUILD_EXTMOD)/Module.symvers $(KBUILD_EXTMOD)/modules.nsdeps \ - $(KBUILD_EXTMOD)/compile_commands.json + $(KBUILD_EXTMOD)/compile_commands.json $(KBUILD_EXTMOD)/.thinlto-cache PHONY += help help: diff --git a/arch/Kconfig b/arch/Kconfig index 78c6f05b10f9..9494e3931f4b 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -631,6 +631,97 @@ config SHADOW_CALL_STACK reading and writing arbitrary memory may be able to locate them and hijack control flow by modifying the stacks. +config LTO + bool + help + Selected if the kernel will be built using the compiler's LTO feature. + +config LTO_CLANG + bool + select LTO + help + Selected if the kernel will be built using Clang's LTO feature. + +config ARCH_SUPPORTS_LTO_CLANG + bool + help + An architecture should select this option if it supports: + - compiling with Clang, + - compiling inline assembly with Clang's integrated assembler, + - and linking with LLD. + +config ARCH_SUPPORTS_LTO_CLANG_THIN + bool + help + An architecture should select this option if it can support Clang's + ThinLTO mode. + +config HAS_LTO_CLANG + def_bool y + # Clang >= 11: https://github.com/ClangBuiltLinux/linux/issues/510 + depends on CC_IS_CLANG && CLANG_VERSION >= 110000 && LD_IS_LLD + depends on $(success,test $(LLVM) -eq 1) + depends on $(success,test $(LLVM_IAS) -eq 1) + depends on $(success,$(NM) --help | head -n 1 | grep -qi llvm) + depends on $(success,$(AR) --help | head -n 1 | grep -qi llvm) + depends on ARCH_SUPPORTS_LTO_CLANG + depends on !FTRACE_MCOUNT_USE_RECORDMCOUNT + depends on !KASAN + depends on !GCOV_KERNEL + depends on !MODVERSIONS + help + The compiler and Kconfig options support building with Clang's + LTO. + +choice + prompt "Link Time Optimization (LTO)" + default LTO_NONE + help + This option enables Link Time Optimization (LTO), which allows the + compiler to optimize binaries globally. + + If unsure, select LTO_NONE. Note that LTO is very resource-intensive + so it's disabled by default. + +config LTO_NONE + bool "None" + help + Build the kernel normally, without Link Time Optimization (LTO). + +config LTO_CLANG_FULL + bool "Clang Full LTO (EXPERIMENTAL)" + depends on HAS_LTO_CLANG + depends on !COMPILE_TEST + select LTO_CLANG + help + This option enables Clang's full Link Time Optimization (LTO), which + allows the compiler to optimize the kernel globally. If you enable + this option, the compiler generates LLVM bitcode instead of ELF + object files, and the actual compilation from bitcode happens at + the LTO link step, which may take several minutes depending on the + kernel configuration. More information can be found from LLVM's + documentation: + + https://llvm.org/docs/LinkTimeOptimization.html + + During link time, this option can use a large amount of RAM, and + may take much longer than the ThinLTO option. + +config LTO_CLANG_THIN + bool "Clang ThinLTO (EXPERIMENTAL)" + depends on HAS_LTO_CLANG && ARCH_SUPPORTS_LTO_CLANG_THIN + select LTO_CLANG + help + This option enables Clang's ThinLTO, which allows for parallel + optimization and faster incremental compiles compared to the + CONFIG_LTO_CLANG_FULL option. More information can be found + from Clang's documentation: + + https://clang.llvm.org/docs/ThinLTO.html + + If unsure, say Y. +endchoice + config HAVE_ARCH_WITHIN_STACK_FRAMES bool help diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index b2b3d81b1535..8988a2e445d8 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -90,15 +90,18 @@ * .data. We don't want to pull in .data..other sections, which Linux * has defined. Same for text and bss. * + * With LTO_CLANG, the linker also splits sections by default, so we need + * these macros to combine the sections during the final link. + * * RODATA_MAIN is not used because existing code already defines .rodata.x * sections to be brought in with rodata. */ -#ifdef CONFIG_LD_DEAD_CODE_DATA_ELIMINATION +#if defined(CONFIG_LD_DEAD_CODE_DATA_ELIMINATION) || defined(CONFIG_LTO_CLANG) #define TEXT_MAIN .text .text.[0-9a-zA-Z_]* -#define DATA_MAIN .data .data.[0-9a-zA-Z_]* .data..LPBX* +#define DATA_MAIN .data .data.[0-9a-zA-Z_]* .data..L* .data..compoundliteral* #define SDATA_MAIN .sdata .sdata.[0-9a-zA-Z_]* -#define RODATA_MAIN .rodata .rodata.[0-9a-zA-Z_]* -#define BSS_MAIN .bss .bss.[0-9a-zA-Z_]* +#define RODATA_MAIN .rodata .rodata.[0-9a-zA-Z_]* .rodata..L* +#define BSS_MAIN .bss .bss.[0-9a-zA-Z_]* .bss..compoundliteral* #define SBSS_MAIN .sbss .sbss.[0-9a-zA-Z_]* #else #define TEXT_MAIN .text diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 22654a463ad8..65d4bea937fa 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -111,7 +111,7 @@ endif # --------------------------------------------------------------------------- quiet_cmd_cc_s_c = CC $(quiet_modtag) $@ - cmd_cc_s_c = $(CC) $(filter-out $(DEBUG_CFLAGS), $(c_flags)) -fverbose-asm -S -o $@ $< + cmd_cc_s_c = $(CC) $(filter-out $(DEBUG_CFLAGS) $(CC_FLAGS_LTO), $(c_flags)) -fverbose-asm -S -o $@ $< $(obj)/%.s: $(src)/%.c FORCE $(call if_changed_dep,cc_s_c) @@ -421,8 +421,15 @@ $(obj)/lib.a: $(lib-y) FORCE # Do not replace $(filter %.o,^) with $(real-prereqs). When a single object # module is turned into a multi object module, $^ will contain header file # dependencies recorded in the .*.cmd file. +ifdef CONFIG_LTO_CLANG +quiet_cmd_link_multi-m = AR [M] $@ +cmd_link_multi-m = \ + rm -f $@; \ + $(AR) cDPrsT $@ $(filter %.o,$^) +else quiet_cmd_link_multi-m = LD [M] $@ cmd_link_multi-m = $(LD) $(ld_flags) -r -o $@ $(filter %.o,$^) +endif $(multi-used-m): FORCE $(call if_changed,link_multi-m) diff --git a/scripts/Makefile.modfinal b/scripts/Makefile.modfinal index d49ec001825d..6de2c35b64e8 100644 --- a/scripts/Makefile.modfinal +++ b/scripts/Makefile.modfinal @@ -30,6 +30,12 @@ quiet_cmd_cc_o_c = CC [M] $@ ARCH_POSTLINK := $(wildcard $(srctree)/arch/$(SRCARCH)/Makefile.postlink) +ifdef CONFIG_LTO_CLANG +# With CONFIG_LTO_CLANG, reuse the object file we compiled for modpost to +# avoid a second slow LTO link +prelink-ext := .lto +endif + quiet_cmd_ld_ko_o = LD [M] $@ cmd_ld_ko_o = \ $(LD) -r $(KBUILD_LDFLAGS) \ @@ -53,8 +59,9 @@ if_changed_except = $(if $(call newer_prereqs_except,$(2))$(cmd-check), \ $(cmd); \ printf '%s\n' 'cmd_$@ := $(make-cmd)' > $(dot-target).cmd, @:) + # Re-generate module BTFs if either module's .ko or vmlinux changed -$(modules): %.ko: %.o %.mod.o scripts/module.lds $(if $(KBUILD_BUILTIN),vmlinux) FORCE +$(modules): %.ko: %$(prelink-ext).o %.mod.o scripts/module.lds $(if $(KBUILD_BUILTIN),vmlinux) FORCE +$(call if_changed_except,ld_ko_o,vmlinux) ifdef CONFIG_DEBUG_INFO_BTF_MODULES +$(if $(newer-prereqs),$(call cmd,btf_ko)) diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost index f54b6ac37ac2..9ff8bfdb574d 100644 --- a/scripts/Makefile.modpost +++ b/scripts/Makefile.modpost @@ -43,6 +43,9 @@ __modpost: include include/config/auto.conf include scripts/Kbuild.include +# for ld_flags +include scripts/Makefile.lib + MODPOST = scripts/mod/modpost \ $(if $(CONFIG_MODVERSIONS),-m) \ $(if $(CONFIG_MODULE_SRCVERSION_ALL),-a) \ @@ -102,12 +105,26 @@ $(input-symdump): @echo >&2 'WARNING: Symbol version dump "$@" is missing.' @echo >&2 ' Modules may not have dependencies or modversions.' +ifdef CONFIG_LTO_CLANG +# With CONFIG_LTO_CLANG, .o files might be LLVM bitcode, so we need to run +# LTO to compile them into native code before running modpost +prelink-ext := .lto + +quiet_cmd_cc_lto_link_modules = LTO [M] $@ +cmd_cc_lto_link_modules = $(LD) $(ld_flags) -r -o $@ --whole-archive $^ + +%.lto.o: %.o + $(call if_changed,cc_lto_link_modules) +endif + +modules := $(sort $(shell cat $(MODORDER))) + # Read out modules.order to pass in modpost. # Otherwise, allmodconfig would fail with "Argument list too long". quiet_cmd_modpost = MODPOST $@ - cmd_modpost = sed 's/ko$$/o/' $< | $(MODPOST) -T - + cmd_modpost = sed 's/\.ko$$/$(prelink-ext)\.o/' $< | $(MODPOST) -T - -$(output-symdump): $(MODORDER) $(input-symdump) FORCE +$(output-symdump): $(MODORDER) $(input-symdump) $(modules:.ko=$(prelink-ext).o) FORCE $(call if_changed,modpost) targets += $(output-symdump) diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index 6eded325c837..596507573a48 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -56,6 +56,14 @@ modpost_link() ${KBUILD_VMLINUX_LIBS} \ --end-group" + if [ -n "${CONFIG_LTO_CLANG}" ]; then + # This might take a while, so indicate that we're doing + # an LTO link + info LTO ${1} + else + info LD ${1} + fi + ${LD} ${KBUILD_LDFLAGS} -r -o ${1} ${objects} } @@ -103,13 +111,22 @@ vmlinux_link() fi if [ "${SRCARCH}" != "um" ]; then - objects="--whole-archive \ - ${KBUILD_VMLINUX_OBJS} \ - --no-whole-archive \ - --start-group \ - ${KBUILD_VMLINUX_LIBS} \ - --end-group \ - ${@}" + if [ -n "${CONFIG_LTO_CLANG}" ]; then + # Use vmlinux.o instead of performing the slow LTO + # link again. + objects="--whole-archive \ + vmlinux.o \ + --no-whole-archive \ + ${@}" + else + objects="--whole-archive \ + ${KBUILD_VMLINUX_OBJS} \ + --no-whole-archive \ + --start-group \ + ${KBUILD_VMLINUX_LIBS} \ + --end-group \ + ${@}" + fi ${LD} ${KBUILD_LDFLAGS} ${LDFLAGS_vmlinux} \ ${strip_debug#-Wl,} \ @@ -274,7 +291,6 @@ fi; ${MAKE} -f "${srctree}/scripts/Makefile.build" obj=init need-builtin=1 #link vmlinux.o -info LD vmlinux.o modpost_link vmlinux.o objtool_link vmlinux.o -- cgit v1.2.3 From a8cccdd954732a558d481407ab7c3106b89c34ae Mon Sep 17 00:00:00 2001 From: Sami Tolvanen Date: Fri, 11 Dec 2020 10:46:24 -0800 Subject: init: lto: ensure initcall ordering With LTO, the compiler doesn't necessarily obey the link order for initcalls, and initcall variables need globally unique names to avoid collisions at link time. This change exports __KBUILD_MODNAME and adds the initcall_id() macro, which uses it together with __COUNTER__ and __LINE__ to help ensure these variables have unique names, and moves each variable to its own section when LTO is enabled, so the correct order can be specified using a linker script. The generate_initcall_ordering.pl script uses nm to find initcalls from the object files passed to the linker, and generates a linker script that specifies the same order for initcalls that we would have without LTO. With LTO enabled, the script is called in link-vmlinux.sh through jobserver-exec to limit the number of jobs spawned. Signed-off-by: Sami Tolvanen Reviewed-by: Kees Cook Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20201211184633.3213045-8-samitolvanen@google.com --- include/linux/init.h | 52 ++++++- scripts/Makefile.lib | 6 +- scripts/generate_initcall_order.pl | 270 +++++++++++++++++++++++++++++++++++++ scripts/link-vmlinux.sh | 15 +++ 4 files changed, 334 insertions(+), 9 deletions(-) create mode 100755 scripts/generate_initcall_order.pl (limited to 'include') diff --git a/include/linux/init.h b/include/linux/init.h index e668832ef66a..a57bf0dfd75f 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -184,19 +184,57 @@ extern bool initcall_debug; * as KEEP() in the linker script. */ +/* Format: ____ */ +#define __initcall_id(fn) \ + __PASTE(__KBUILD_MODNAME, \ + __PASTE(__, \ + __PASTE(__COUNTER__, \ + __PASTE(_, \ + __PASTE(__LINE__, \ + __PASTE(_, fn)))))) + +/* Format: ____ */ +#define __initcall_name(prefix, __iid, id) \ + __PASTE(__, \ + __PASTE(prefix, \ + __PASTE(__, \ + __PASTE(__iid, id)))) + +#ifdef CONFIG_LTO_CLANG +/* + * With LTO, the compiler doesn't necessarily obey link order for + * initcalls. In order to preserve the correct order, we add each + * variable into its own section and generate a linker script (in + * scripts/link-vmlinux.sh) to specify the order of the sections. + */ +#define __initcall_section(__sec, __iid) \ + #__sec ".init.." #__iid +#else +#define __initcall_section(__sec, __iid) \ + #__sec ".init" +#endif + #ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS -#define ___define_initcall(fn, id, __sec) \ +#define ____define_initcall(fn, __name, __sec) \ __ADDRESSABLE(fn) \ - asm(".section \"" #__sec ".init\", \"a\" \n" \ - "__initcall_" #fn #id ": \n" \ + asm(".section \"" __sec "\", \"a\" \n" \ + __stringify(__name) ": \n" \ ".long " #fn " - . \n" \ ".previous \n"); #else -#define ___define_initcall(fn, id, __sec) \ - static initcall_t __initcall_##fn##id __used \ - __attribute__((__section__(#__sec ".init"))) = fn; +#define ____define_initcall(fn, __name, __sec) \ + static initcall_t __name __used \ + __attribute__((__section__(__sec))) = fn; #endif +#define __unique_initcall(fn, id, __sec, __iid) \ + ____define_initcall(fn, \ + __initcall_name(initcall, __iid, id), \ + __initcall_section(__sec, __iid)) + +#define ___define_initcall(fn, id, __sec) \ + __unique_initcall(fn, id, __sec, __initcall_id(fn)) + #define __define_initcall(fn, id) ___define_initcall(fn, id, .initcall##id) /* @@ -236,7 +274,7 @@ extern bool initcall_debug; #define __exitcall(fn) \ static exitcall_t __exitcall_##fn __exit_call = fn -#define console_initcall(fn) ___define_initcall(fn,, .con_initcall) +#define console_initcall(fn) ___define_initcall(fn, con, .con_initcall) struct obs_kernel_param { const char *str; diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index 213677a5ed33..3ff3dbb3a830 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -117,9 +117,11 @@ target-stem = $(basename $(patsubst $(obj)/%,%,$@)) # These flags are needed for modversions and compiling, so we define them here # $(modname_flags) defines KBUILD_MODNAME as the name of the module it will # end up in (or would, if it gets compiled in) -name-fix = $(call stringify,$(subst $(comma),_,$(subst -,_,$1))) +name-fix-token = $(subst $(comma),_,$(subst -,_,$1)) +name-fix = $(call stringify,$(call name-fix-token,$1)) basename_flags = -DKBUILD_BASENAME=$(call name-fix,$(basetarget)) -modname_flags = -DKBUILD_MODNAME=$(call name-fix,$(modname)) +modname_flags = -DKBUILD_MODNAME=$(call name-fix,$(modname)) \ + -D__KBUILD_MODNAME=kmod_$(call name-fix-token,$(modname)) modfile_flags = -DKBUILD_MODFILE=$(call stringify,$(modfile)) _c_flags = $(filter-out $(CFLAGS_REMOVE_$(target-stem).o), \ diff --git a/scripts/generate_initcall_order.pl b/scripts/generate_initcall_order.pl new file mode 100755 index 000000000000..1a88d3f1b913 --- /dev/null +++ b/scripts/generate_initcall_order.pl @@ -0,0 +1,270 @@ +#!/usr/bin/env perl +# SPDX-License-Identifier: GPL-2.0 +# +# Generates a linker script that specifies the correct initcall order. +# +# Copyright (C) 2019 Google LLC + +use strict; +use warnings; +use IO::Handle; +use IO::Select; +use POSIX ":sys_wait_h"; + +my $nm = $ENV{'NM'} || die "$0: ERROR: NM not set?"; +my $objtree = $ENV{'objtree'} || '.'; + +## currently active child processes +my $jobs = {}; # child process pid -> file handle +## results from child processes +my $results = {}; # object index -> [ { level, secname }, ... ] + +## reads _NPROCESSORS_ONLN to determine the maximum number of processes to +## start +sub get_online_processors { + open(my $fh, "getconf _NPROCESSORS_ONLN 2>/dev/null |") + or die "$0: ERROR: failed to execute getconf: $!"; + my $procs = <$fh>; + close($fh); + + if (!($procs =~ /^\d+$/)) { + return 1; + } + + return int($procs); +} + +## writes results to the parent process +## format: +sub write_results { + my ($index, $initcalls) = @_; + + # sort by the counter value to ensure the order of initcalls within + # each object file is correct + foreach my $counter (sort { $a <=> $b } keys(%{$initcalls})) { + my $level = $initcalls->{$counter}->{'level'}; + + # section name for the initcall function + my $secname = $initcalls->{$counter}->{'module'} . '__' . + $counter . '_' . + $initcalls->{$counter}->{'line'} . '_' . + $initcalls->{$counter}->{'function'}; + + print "$index $level $secname\n"; + } +} + +## reads a result line from a child process and adds it to the $results array +sub read_results{ + my ($fh) = @_; + + # each child prints out a full line w/ autoflush and exits after the + # last line, so even if buffered I/O blocks here, it shouldn't block + # very long + my $data = <$fh>; + + if (!defined($data)) { + return 0; + } + + chomp($data); + + my ($index, $level, $secname) = $data =~ + /^(\d+)\ ([^\ ]+)\ (.*)$/; + + if (!defined($index) || + !defined($level) || + !defined($secname)) { + die "$0: ERROR: child process returned invalid data: $data\n"; + } + + $index = int($index); + + if (!exists($results->{$index})) { + $results->{$index} = []; + } + + push (@{$results->{$index}}, { + 'level' => $level, + 'secname' => $secname + }); + + return 1; +} + +## finds initcalls from an object file or all object files in an archive, and +## writes results back to the parent process +sub find_initcalls { + my ($index, $file) = @_; + + die "$0: ERROR: file $file doesn't exist?" if (! -f $file); + + open(my $fh, "\"$nm\" --defined-only \"$file\" 2>/dev/null |") + or die "$0: ERROR: failed to execute \"$nm\": $!"; + + my $initcalls = {}; + + while (<$fh>) { + chomp; + + # check for the start of a new object file (if processing an + # archive) + my ($path)= $_ =~ /^(.+)\:$/; + + if (defined($path)) { + write_results($index, $initcalls); + $initcalls = {}; + next; + } + + # look for an initcall + my ($module, $counter, $line, $symbol) = $_ =~ + /[a-z]\s+__initcall__(\S*)__(\d+)_(\d+)_(.*)$/; + + if (!defined($module)) { + $module = '' + } + + if (!defined($counter) || + !defined($line) || + !defined($symbol)) { + next; + } + + # parse initcall level + my ($function, $level) = $symbol =~ + /^(.*)((early|rootfs|con|[0-9])s?)$/; + + die "$0: ERROR: invalid initcall name $symbol in $file($path)" + if (!defined($function) || !defined($level)); + + $initcalls->{$counter} = { + 'module' => $module, + 'line' => $line, + 'function' => $function, + 'level' => $level, + }; + } + + close($fh); + write_results($index, $initcalls); +} + +## waits for any child process to complete, reads the results, and adds them to +## the $results array for later processing +sub wait_for_results { + my ($select) = @_; + + my $pid = 0; + do { + # unblock children that may have a full write buffer + foreach my $fh ($select->can_read(0)) { + read_results($fh); + } + + # check for children that have exited, read the remaining data + # from them, and clean up + $pid = waitpid(-1, WNOHANG); + if ($pid > 0) { + if (!exists($jobs->{$pid})) { + next; + } + + my $fh = $jobs->{$pid}; + $select->remove($fh); + + while (read_results($fh)) { + # until eof + } + + close($fh); + delete($jobs->{$pid}); + } + } while ($pid > 0); +} + +## forks a child to process each file passed in the command line and collects +## the results +sub process_files { + my $index = 0; + my $njobs = $ENV{'PARALLELISM'} || get_online_processors(); + my $select = IO::Select->new(); + + while (my $file = shift(@ARGV)) { + # fork a child process and read it's stdout + my $pid = open(my $fh, '-|'); + + if (!defined($pid)) { + die "$0: ERROR: failed to fork: $!"; + } elsif ($pid) { + # save the child process pid and the file handle + $select->add($fh); + $jobs->{$pid} = $fh; + } else { + # in the child process + STDOUT->autoflush(1); + find_initcalls($index, "$objtree/$file"); + exit; + } + + $index++; + + # limit the number of children to $njobs + if (scalar(keys(%{$jobs})) >= $njobs) { + wait_for_results($select); + } + } + + # wait for the remaining children to complete + while (scalar(keys(%{$jobs})) > 0) { + wait_for_results($select); + } +} + +sub generate_initcall_lds() { + process_files(); + + my $sections = {}; # level -> [ secname, ...] + + # sort results to retain link order and split to sections per + # initcall level + foreach my $index (sort { $a <=> $b } keys(%{$results})) { + foreach my $result (@{$results->{$index}}) { + my $level = $result->{'level'}; + + if (!exists($sections->{$level})) { + $sections->{$level} = []; + } + + push(@{$sections->{$level}}, $result->{'secname'}); + } + } + + die "$0: ERROR: no initcalls?" if (!keys(%{$sections})); + + # print out a linker script that defines the order of initcalls for + # each level + print "SECTIONS {\n"; + + foreach my $level (sort(keys(%{$sections}))) { + my $section; + + if ($level eq 'con') { + $section = '.con_initcall.init'; + } else { + $section = ".initcall${level}.init"; + } + + print "\t${section} : {\n"; + + foreach my $secname (@{$sections->{$level}}) { + print "\t\t*(${section}..${secname}) ;\n"; + } + + print "\t}\n"; + } + + print "}\n"; +} + +generate_initcall_lds(); diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index 78e55fe7210b..c5919d5a0b4f 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -43,6 +43,17 @@ info() fi } +# Generate a linker script to ensure correct ordering of initcalls. +gen_initcalls() +{ + info GEN .tmp_initcalls.lds + + ${PYTHON} ${srctree}/scripts/jobserver-exec \ + ${PERL} ${srctree}/scripts/generate_initcall_order.pl \ + ${KBUILD_VMLINUX_OBJS} ${KBUILD_VMLINUX_LIBS} \ + > .tmp_initcalls.lds +} + # If CONFIG_LTO_CLANG is selected, collect generated symbol versions into # .tmp_symversions.lds gen_symversions() @@ -72,6 +83,9 @@ modpost_link() --end-group" if [ -n "${CONFIG_LTO_CLANG}" ]; then + gen_initcalls + lds="-T .tmp_initcalls.lds" + if [ -n "${CONFIG_MODVERSIONS}" ]; then gen_symversions lds="${lds} -T .tmp_symversions.lds" @@ -262,6 +276,7 @@ cleanup() { rm -f .btf.* rm -f .tmp_System.map + rm -f .tmp_initcalls.lds rm -f .tmp_symversions.lds rm -f .tmp_vmlinux* rm -f System.map -- cgit v1.2.3 From 3578ad11f3fba07e64c26d8db68cfd3dde28c59e Mon Sep 17 00:00:00 2001 From: Sami Tolvanen Date: Fri, 11 Dec 2020 10:46:25 -0800 Subject: init: lto: fix PREL32 relocations With LTO, the compiler can rename static functions to avoid global naming collisions. As initcall functions are typically static, renaming can break references to them in inline assembly. This change adds a global stub with a stable name for each initcall to fix the issue when PREL32 relocations are used. Signed-off-by: Sami Tolvanen Reviewed-by: Kees Cook Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20201211184633.3213045-9-samitolvanen@google.com --- include/linux/init.h | 31 +++++++++++++++++++++++++++---- 1 file changed, 27 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/init.h b/include/linux/init.h index a57bf0dfd75f..a01f01c1a5c5 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -209,26 +209,49 @@ extern bool initcall_debug; */ #define __initcall_section(__sec, __iid) \ #__sec ".init.." #__iid + +/* + * With LTO, the compiler can rename static functions to avoid + * global naming collisions. We use a global stub function for + * initcalls to create a stable symbol name whose address can be + * taken in inline assembly when PREL32 relocations are used. + */ +#define __initcall_stub(fn, __iid, id) \ + __initcall_name(initstub, __iid, id) + +#define __define_initcall_stub(__stub, fn) \ + int __init __stub(void); \ + int __init __stub(void) \ + { \ + return fn(); \ + } \ + __ADDRESSABLE(__stub) #else #define __initcall_section(__sec, __iid) \ #__sec ".init" + +#define __initcall_stub(fn, __iid, id) fn + +#define __define_initcall_stub(__stub, fn) \ + __ADDRESSABLE(fn) #endif #ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS -#define ____define_initcall(fn, __name, __sec) \ - __ADDRESSABLE(fn) \ +#define ____define_initcall(fn, __stub, __name, __sec) \ + __define_initcall_stub(__stub, fn) \ asm(".section \"" __sec "\", \"a\" \n" \ __stringify(__name) ": \n" \ - ".long " #fn " - . \n" \ + ".long " __stringify(__stub) " - . \n" \ ".previous \n"); #else -#define ____define_initcall(fn, __name, __sec) \ +#define ____define_initcall(fn, __unused, __name, __sec) \ static initcall_t __name __used \ __attribute__((__section__(__sec))) = fn; #endif #define __unique_initcall(fn, id, __sec, __iid) \ ____define_initcall(fn, \ + __initcall_stub(fn, __iid, id), \ __initcall_name(initcall, __iid, id), \ __initcall_section(__sec, __iid)) -- cgit v1.2.3 From 09a4e4d9c52a3c5e39e4f409b2c083ab13c6afc2 Mon Sep 17 00:00:00 2001 From: Sami Tolvanen Date: Fri, 11 Dec 2020 10:46:26 -0800 Subject: PCI: Fix PREL32 relocations for LTO With Clang's Link Time Optimization (LTO), the compiler can rename static functions to avoid global naming collisions. As PCI fixup functions are typically static, renaming can break references to them in inline assembly. This change adds a global stub to DECLARE_PCI_FIXUP_SECTION to fix the issue when PREL32 relocations are used. Signed-off-by: Sami Tolvanen Acked-by: Bjorn Helgaas Reviewed-by: Kees Cook Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20201211184633.3213045-10-samitolvanen@google.com --- include/linux/pci.h | 27 +++++++++++++++++++++++++-- 1 file changed, 25 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/pci.h b/include/linux/pci.h index b32126d26997..2276e5d00192 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1917,7 +1917,7 @@ enum pci_fixup_pass { }; #ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS -#define __DECLARE_PCI_FIXUP_SECTION(sec, name, vendor, device, class, \ +#define ___DECLARE_PCI_FIXUP_SECTION(sec, name, vendor, device, class, \ class_shift, hook) \ __ADDRESSABLE(hook) \ asm(".section " #sec ", \"a\" \n" \ @@ -1926,10 +1926,33 @@ enum pci_fixup_pass { ".long " #class ", " #class_shift " \n" \ ".long " #hook " - . \n" \ ".previous \n"); + +/* + * Clang's LTO may rename static functions in C, but has no way to + * handle such renamings when referenced from inline asm. To work + * around this, create global C stubs for these cases. + */ +#ifdef CONFIG_LTO_CLANG +#define __DECLARE_PCI_FIXUP_SECTION(sec, name, vendor, device, class, \ + class_shift, hook, stub) \ + void stub(struct pci_dev *dev); \ + void stub(struct pci_dev *dev) \ + { \ + hook(dev); \ + } \ + ___DECLARE_PCI_FIXUP_SECTION(sec, name, vendor, device, class, \ + class_shift, stub) +#else +#define __DECLARE_PCI_FIXUP_SECTION(sec, name, vendor, device, class, \ + class_shift, hook, stub) \ + ___DECLARE_PCI_FIXUP_SECTION(sec, name, vendor, device, class, \ + class_shift, hook) +#endif + #define DECLARE_PCI_FIXUP_SECTION(sec, name, vendor, device, class, \ class_shift, hook) \ __DECLARE_PCI_FIXUP_SECTION(sec, name, vendor, device, class, \ - class_shift, hook) + class_shift, hook, __UNIQUE_ID(hook)) #else /* Anonymous variables would be nice... */ #define DECLARE_PCI_FIXUP_SECTION(section, name, vendor, device, class, \ -- cgit v1.2.3 From 215b674b84dd052098fe6389e32a5afaff8b4d56 Mon Sep 17 00:00:00 2001 From: Lokesh Gidra Date: Fri, 8 Jan 2021 14:22:20 -0800 Subject: security: add inode_init_security_anon() LSM hook This change adds a new LSM hook, inode_init_security_anon(), that will be used while creating secure anonymous inodes. The hook allows/denies its creation and assigns a security context to the inode. The new hook accepts an optional context_inode parameter that callers can use to provide additional contextual information to security modules for granting/denying permission to create an anon-inode of the same type. This context_inode's security_context can also be used to initialize the newly created anon-inode's security_context. Signed-off-by: Lokesh Gidra Reviewed-by: Eric Biggers Signed-off-by: Paul Moore --- include/linux/lsm_hook_defs.h | 2 ++ include/linux/lsm_hooks.h | 9 +++++++++ include/linux/security.h | 10 ++++++++++ security/security.c | 8 ++++++++ 4 files changed, 29 insertions(+) (limited to 'include') diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 7aaa753b8608..dfd261dcbcb0 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -113,6 +113,8 @@ LSM_HOOK(void, LSM_RET_VOID, inode_free_security, struct inode *inode) LSM_HOOK(int, 0, inode_init_security, struct inode *inode, struct inode *dir, const struct qstr *qstr, const char **name, void **value, size_t *len) +LSM_HOOK(int, 0, inode_init_security_anon, struct inode *inode, + const struct qstr *name, const struct inode *context_inode) LSM_HOOK(int, 0, inode_create, struct inode *dir, struct dentry *dentry, umode_t mode) LSM_HOOK(int, 0, inode_link, struct dentry *old_dentry, struct inode *dir, diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index a19adef1f088..bdfc8a76a4f7 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -233,6 +233,15 @@ * Returns 0 if @name and @value have been successfully set, * -EOPNOTSUPP if no security attribute is needed, or * -ENOMEM on memory allocation failure. + * @inode_init_security_anon: + * Set up the incore security field for the new anonymous inode + * and return whether the inode creation is permitted by the security + * module or not. + * @inode contains the inode structure + * @name name of the anonymous inode class + * @context_inode optional related inode + * Returns 0 on success, -EACCES if the security module denies the + * creation of this inode, or another -errno upon other errors. * @inode_create: * Check permission to create a regular file. * @dir contains inode structure of the parent of the new file. diff --git a/include/linux/security.h b/include/linux/security.h index c35ea0ffccd9..b0d14f04b16d 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -324,6 +324,9 @@ void security_inode_free(struct inode *inode); int security_inode_init_security(struct inode *inode, struct inode *dir, const struct qstr *qstr, initxattrs initxattrs, void *fs_data); +int security_inode_init_security_anon(struct inode *inode, + const struct qstr *name, + const struct inode *context_inode); int security_old_inode_init_security(struct inode *inode, struct inode *dir, const struct qstr *qstr, const char **name, void **value, size_t *len); @@ -738,6 +741,13 @@ static inline int security_inode_init_security(struct inode *inode, return 0; } +static inline int security_inode_init_security_anon(struct inode *inode, + const struct qstr *name, + const struct inode *context_inode) +{ + return 0; +} + static inline int security_old_inode_init_security(struct inode *inode, struct inode *dir, const struct qstr *qstr, diff --git a/security/security.c b/security/security.c index 7b09cfbae94f..401663b5b70e 100644 --- a/security/security.c +++ b/security/security.c @@ -1059,6 +1059,14 @@ out: } EXPORT_SYMBOL(security_inode_init_security); +int security_inode_init_security_anon(struct inode *inode, + const struct qstr *name, + const struct inode *context_inode) +{ + return call_int_hook(inode_init_security_anon, 0, inode, name, + context_inode); +} + int security_old_inode_init_security(struct inode *inode, struct inode *dir, const struct qstr *qstr, const char **name, void **value, size_t *len) -- cgit v1.2.3 From e7e832ce6fa769f800cd7eaebdb0459ad31e0416 Mon Sep 17 00:00:00 2001 From: Daniel Colascione Date: Fri, 8 Jan 2021 14:22:21 -0800 Subject: fs: add LSM-supporting anon-inode interface This change adds a new function, anon_inode_getfd_secure, that creates anonymous-node file with individual non-S_PRIVATE inode to which security modules can apply policy. Existing callers continue using the original singleton-inode kind of anonymous-inode file. We can transition anonymous inode users to the new kind of anonymous inode in individual patches for the sake of bisection and review. The new function accepts an optional context_inode parameter that callers can use to provide additional contextual information to security modules. For example, in case of userfaultfd, the created inode is a 'logical child' of the context_inode (userfaultfd inode of the parent process) in the sense that it provides the security context required during creation of the child process' userfaultfd inode. Signed-off-by: Daniel Colascione [LG: Delete obsolete comments to alloc_anon_inode()] [LG: Add context_inode description in comments to anon_inode_getfd_secure()] [LG: Remove definition of anon_inode_getfile_secure() as there are no callers] [LG: Make __anon_inode_getfile() static] [LG: Use correct error cast in __anon_inode_getfile()] [LG: Fix error handling in __anon_inode_getfile()] Signed-off-by: Lokesh Gidra Reviewed-by: Eric Biggers Signed-off-by: Paul Moore --- fs/anon_inodes.c | 150 ++++++++++++++++++++++++++++++++------------ fs/libfs.c | 5 -- include/linux/anon_inodes.h | 5 ++ 3 files changed, 115 insertions(+), 45 deletions(-) (limited to 'include') diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c index 89714308c25b..023337d65a03 100644 --- a/fs/anon_inodes.c +++ b/fs/anon_inodes.c @@ -55,61 +55,79 @@ static struct file_system_type anon_inode_fs_type = { .kill_sb = kill_anon_super, }; -/** - * anon_inode_getfile - creates a new file instance by hooking it up to an - * anonymous inode, and a dentry that describe the "class" - * of the file - * - * @name: [in] name of the "class" of the new file - * @fops: [in] file operations for the new file - * @priv: [in] private data for the new file (will be file's private_data) - * @flags: [in] flags - * - * Creates a new file by hooking it on a single inode. This is useful for files - * that do not need to have a full-fledged inode in order to operate correctly. - * All the files created with anon_inode_getfile() will share a single inode, - * hence saving memory and avoiding code duplication for the file/inode/dentry - * setup. Returns the newly created file* or an error pointer. - */ -struct file *anon_inode_getfile(const char *name, - const struct file_operations *fops, - void *priv, int flags) +static struct inode *anon_inode_make_secure_inode( + const char *name, + const struct inode *context_inode) { - struct file *file; + struct inode *inode; + const struct qstr qname = QSTR_INIT(name, strlen(name)); + int error; + + inode = alloc_anon_inode(anon_inode_mnt->mnt_sb); + if (IS_ERR(inode)) + return inode; + inode->i_flags &= ~S_PRIVATE; + error = security_inode_init_security_anon(inode, &qname, context_inode); + if (error) { + iput(inode); + return ERR_PTR(error); + } + return inode; +} - if (IS_ERR(anon_inode_inode)) - return ERR_PTR(-ENODEV); +static struct file *__anon_inode_getfile(const char *name, + const struct file_operations *fops, + void *priv, int flags, + const struct inode *context_inode, + bool secure) +{ + struct inode *inode; + struct file *file; if (fops->owner && !try_module_get(fops->owner)) return ERR_PTR(-ENOENT); - /* - * We know the anon_inode inode count is always greater than zero, - * so ihold() is safe. - */ - ihold(anon_inode_inode); - file = alloc_file_pseudo(anon_inode_inode, anon_inode_mnt, name, + if (secure) { + inode = anon_inode_make_secure_inode(name, context_inode); + if (IS_ERR(inode)) { + file = ERR_CAST(inode); + goto err; + } + } else { + inode = anon_inode_inode; + if (IS_ERR(inode)) { + file = ERR_PTR(-ENODEV); + goto err; + } + /* + * We know the anon_inode inode count is always + * greater than zero, so ihold() is safe. + */ + ihold(inode); + } + + file = alloc_file_pseudo(inode, anon_inode_mnt, name, flags & (O_ACCMODE | O_NONBLOCK), fops); if (IS_ERR(file)) - goto err; + goto err_iput; - file->f_mapping = anon_inode_inode->i_mapping; + file->f_mapping = inode->i_mapping; file->private_data = priv; return file; +err_iput: + iput(inode); err: - iput(anon_inode_inode); module_put(fops->owner); return file; } -EXPORT_SYMBOL_GPL(anon_inode_getfile); /** - * anon_inode_getfd - creates a new file instance by hooking it up to an - * anonymous inode, and a dentry that describe the "class" - * of the file + * anon_inode_getfile - creates a new file instance by hooking it up to an + * anonymous inode, and a dentry that describe the "class" + * of the file * * @name: [in] name of the "class" of the new file * @fops: [in] file operations for the new file @@ -118,12 +136,23 @@ EXPORT_SYMBOL_GPL(anon_inode_getfile); * * Creates a new file by hooking it on a single inode. This is useful for files * that do not need to have a full-fledged inode in order to operate correctly. - * All the files created with anon_inode_getfd() will share a single inode, + * All the files created with anon_inode_getfile() will share a single inode, * hence saving memory and avoiding code duplication for the file/inode/dentry - * setup. Returns new descriptor or an error code. + * setup. Returns the newly created file* or an error pointer. */ -int anon_inode_getfd(const char *name, const struct file_operations *fops, - void *priv, int flags) +struct file *anon_inode_getfile(const char *name, + const struct file_operations *fops, + void *priv, int flags) +{ + return __anon_inode_getfile(name, fops, priv, flags, NULL, false); +} +EXPORT_SYMBOL_GPL(anon_inode_getfile); + +static int __anon_inode_getfd(const char *name, + const struct file_operations *fops, + void *priv, int flags, + const struct inode *context_inode, + bool secure) { int error, fd; struct file *file; @@ -133,7 +162,8 @@ int anon_inode_getfd(const char *name, const struct file_operations *fops, return error; fd = error; - file = anon_inode_getfile(name, fops, priv, flags); + file = __anon_inode_getfile(name, fops, priv, flags, context_inode, + secure); if (IS_ERR(file)) { error = PTR_ERR(file); goto err_put_unused_fd; @@ -146,8 +176,48 @@ err_put_unused_fd: put_unused_fd(fd); return error; } + +/** + * anon_inode_getfd - creates a new file instance by hooking it up to + * an anonymous inode and a dentry that describe + * the "class" of the file + * + * @name: [in] name of the "class" of the new file + * @fops: [in] file operations for the new file + * @priv: [in] private data for the new file (will be file's private_data) + * @flags: [in] flags + * + * Creates a new file by hooking it on a single inode. This is + * useful for files that do not need to have a full-fledged inode in + * order to operate correctly. All the files created with + * anon_inode_getfd() will use the same singleton inode, reducing + * memory use and avoiding code duplication for the file/inode/dentry + * setup. Returns a newly created file descriptor or an error code. + */ +int anon_inode_getfd(const char *name, const struct file_operations *fops, + void *priv, int flags) +{ + return __anon_inode_getfd(name, fops, priv, flags, NULL, false); +} EXPORT_SYMBOL_GPL(anon_inode_getfd); +/** + * Like anon_inode_getfd(), but creates a new !S_PRIVATE anon inode rather than + * reuse the singleton anon inode, and calls the inode_init_security_anon() LSM + * hook. This allows the inode to have its own security context and for a LSM + * to reject creation of the inode. An optional @context_inode argument is + * also added to provide the logical relationship with the new inode. The LSM + * may use @context_inode in inode_init_security_anon(), but a reference to it + * is not held. + */ +int anon_inode_getfd_secure(const char *name, const struct file_operations *fops, + void *priv, int flags, + const struct inode *context_inode) +{ + return __anon_inode_getfd(name, fops, priv, flags, context_inode, true); +} +EXPORT_SYMBOL_GPL(anon_inode_getfd_secure); + static int __init anon_inode_init(void) { anon_inode_mnt = kern_mount(&anon_inode_fs_type); diff --git a/fs/libfs.c b/fs/libfs.c index d1c3bade9f30..e52818fb276a 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -1214,11 +1214,6 @@ static int anon_set_page_dirty(struct page *page) return 0; }; -/* - * A single inode exists for all anon_inode files. Contrary to pipes, - * anon_inode inodes have no associated per-instance data, so we need - * only allocate one of them. - */ struct inode *alloc_anon_inode(struct super_block *s) { static const struct address_space_operations anon_aops = { diff --git a/include/linux/anon_inodes.h b/include/linux/anon_inodes.h index d0d7d96261ad..71881a2b6f78 100644 --- a/include/linux/anon_inodes.h +++ b/include/linux/anon_inodes.h @@ -10,12 +10,17 @@ #define _LINUX_ANON_INODES_H struct file_operations; +struct inode; struct file *anon_inode_getfile(const char *name, const struct file_operations *fops, void *priv, int flags); int anon_inode_getfd(const char *name, const struct file_operations *fops, void *priv, int flags); +int anon_inode_getfd_secure(const char *name, + const struct file_operations *fops, + void *priv, int flags, + const struct inode *context_inode); #endif /* _LINUX_ANON_INODES_H */ -- cgit v1.2.3 From 802fee26d8afd073c630a74dbe1a996970f3fd90 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Sun, 13 Dec 2020 22:50:40 +0900 Subject: riscv: cleanup Canaan Kendryte K210 sysctl driver Introduce the header file include/soc/canaan/k210-sysctl.h to have a common definition of the Canaan Kendryte K210 SoC system controller registers. Simplify the k210 system controller driver code by removing unused register bits definition. The MAINTAINERS file is updated, adding the entry "CANAAN/KENDRYTE K210 SOC SYSTEM CONTROLLER DRIVER" with myself listed as maintainer for this driver. This is a preparatory patch for introducing the K210 clock driver. No functional changes are introduced. Signed-off-by: Damien Le Moal Signed-off-by: Palmer Dabbelt --- MAINTAINERS | 7 +++ drivers/soc/canaan/k210-sysctl.c | 93 +++++++++++----------------------------- include/soc/canaan/k210-sysctl.h | 41 ++++++++++++++++++ 3 files changed, 74 insertions(+), 67 deletions(-) create mode 100644 include/soc/canaan/k210-sysctl.h (limited to 'include') diff --git a/MAINTAINERS b/MAINTAINERS index 6eff4f720c72..4aaa7a17016b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3860,6 +3860,13 @@ W: https://github.com/Cascoda/ca8210-linux.git F: Documentation/devicetree/bindings/net/ieee802154/ca8210.txt F: drivers/net/ieee802154/ca8210.c +CANAAN/KENDRYTE K210 SOC SYSTEM CONTROLLER DRIVER +M: Damien Le Moal +L: linux-riscv@lists.infradead.org +S: Maintained +F: drivers/soc/canaan/ +F: include/soc/canaan/ + CACHEFILES: FS-CACHE BACKEND FOR CACHING ON MOUNTED FILESYSTEMS M: David Howells L: linux-cachefs@redhat.com (moderated for non-subscribers) diff --git a/drivers/soc/canaan/k210-sysctl.c b/drivers/soc/canaan/k210-sysctl.c index 4608fbca20e1..60b474c33d45 100644 --- a/drivers/soc/canaan/k210-sysctl.c +++ b/drivers/soc/canaan/k210-sysctl.c @@ -12,74 +12,33 @@ #include #include +#include + #define K210_SYSCTL_CLK0_FREQ 26000000UL /* Registers base address */ #define K210_SYSCTL_SYSCTL_BASE_ADDR 0x50440000ULL -/* Registers */ -#define K210_SYSCTL_PLL0 0x08 -#define K210_SYSCTL_PLL1 0x0c -/* clkr: 4bits, clkf1: 6bits, clkod: 4bits, bwadj: 4bits */ -#define PLL_RESET (1 << 20) -#define PLL_PWR (1 << 21) -#define PLL_INTFB (1 << 22) -#define PLL_BYPASS (1 << 23) -#define PLL_TEST (1 << 24) -#define PLL_OUT_EN (1 << 25) -#define PLL_TEST_EN (1 << 26) -#define K210_SYSCTL_PLL_LOCK 0x18 -#define PLL0_LOCK1 (1 << 0) -#define PLL0_LOCK2 (1 << 1) -#define PLL0_SLIP_CLEAR (1 << 2) -#define PLL0_TEST_CLK_OUT (1 << 3) -#define PLL1_LOCK1 (1 << 8) -#define PLL1_LOCK2 (1 << 9) -#define PLL1_SLIP_CLEAR (1 << 10) -#define PLL1_TEST_CLK_OUT (1 << 11) -#define PLL2_LOCK1 (1 << 16) -#define PLL2_LOCK2 (1 << 16) -#define PLL2_SLIP_CLEAR (1 << 18) -#define PLL2_TEST_CLK_OUT (1 << 19) -#define K210_SYSCTL_CLKSEL0 0x20 -#define CLKSEL_ACLK (1 << 0) -#define K210_SYSCTL_CLKEN_CENT 0x28 -#define CLKEN_CPU (1 << 0) -#define CLKEN_SRAM0 (1 << 1) -#define CLKEN_SRAM1 (1 << 2) -#define CLKEN_APB0 (1 << 3) -#define CLKEN_APB1 (1 << 4) -#define CLKEN_APB2 (1 << 5) -#define K210_SYSCTL_CLKEN_PERI 0x2c -#define CLKEN_ROM (1 << 0) -#define CLKEN_DMA (1 << 1) -#define CLKEN_AI (1 << 2) -#define CLKEN_DVP (1 << 3) -#define CLKEN_FFT (1 << 4) -#define CLKEN_GPIO (1 << 5) -#define CLKEN_SPI0 (1 << 6) -#define CLKEN_SPI1 (1 << 7) -#define CLKEN_SPI2 (1 << 8) -#define CLKEN_SPI3 (1 << 9) -#define CLKEN_I2S0 (1 << 10) -#define CLKEN_I2S1 (1 << 11) -#define CLKEN_I2S2 (1 << 12) -#define CLKEN_I2C0 (1 << 13) -#define CLKEN_I2C1 (1 << 14) -#define CLKEN_I2C2 (1 << 15) -#define CLKEN_UART1 (1 << 16) -#define CLKEN_UART2 (1 << 17) -#define CLKEN_UART3 (1 << 18) -#define CLKEN_AES (1 << 19) -#define CLKEN_FPIO (1 << 20) -#define CLKEN_TIMER0 (1 << 21) -#define CLKEN_TIMER1 (1 << 22) -#define CLKEN_TIMER2 (1 << 23) -#define CLKEN_WDT0 (1 << 24) -#define CLKEN_WDT1 (1 << 25) -#define CLKEN_SHA (1 << 26) -#define CLKEN_OTP (1 << 27) -#define CLKEN_RTC (1 << 29) +/* Register bits */ +/* K210_SYSCTL_PLL1: clkr: 4bits, clkf1: 6bits, clkod: 4bits, bwadj: 4bits */ +#define PLL_RESET (1 << 20) +#define PLL_PWR (1 << 21) +#define PLL_BYPASS (1 << 23) +#define PLL_OUT_EN (1 << 25) +/* K210_SYSCTL_PLL_LOCK */ +#define PLL1_LOCK1 (1 << 8) +#define PLL1_LOCK2 (1 << 9) +#define PLL1_SLIP_CLEAR (1 << 10) +/* K210_SYSCTL_SEL0 */ +#define CLKSEL_ACLK (1 << 0) +/* K210_SYSCTL_CLKEN_CENT */ +#define CLKEN_CPU (1 << 0) +#define CLKEN_SRAM0 (1 << 1) +#define CLKEN_SRAM1 (1 << 2) +/* K210_SYSCTL_EN_PERI */ +#define CLKEN_ROM (1 << 0) +#define CLKEN_TIMER0 (1 << 21) +#define CLKEN_RTC (1 << 29) struct k210_sysctl { void __iomem *regs; @@ -140,7 +99,7 @@ static unsigned long k210_sysctl_clk_recalc_rate(struct clk_hw *hw, * If the clock selector is not set, use the base frequency. * Otherwise, use PLL0 frequency with a frequency divisor. */ - clksel0 = readl(s->regs + K210_SYSCTL_CLKSEL0); + clksel0 = readl(s->regs + K210_SYSCTL_SEL0); if (!(clksel0 & CLKSEL_ACLK)) return K210_SYSCTL_CLK0_FREQ; @@ -237,11 +196,11 @@ static void __init k210_soc_early_init(const void *fdt) k210_set_bits(PLL_OUT_EN, regs + K210_SYSCTL_PLL0); k210_set_bits(CLKEN_CPU | CLKEN_SRAM0 | CLKEN_SRAM1, - regs + K210_SYSCTL_CLKEN_CENT); + regs + K210_SYSCTL_EN_CENT); k210_set_bits(CLKEN_ROM | CLKEN_TIMER0 | CLKEN_RTC, - regs + K210_SYSCTL_CLKEN_PERI); + regs + K210_SYSCTL_EN_PERI); - k210_set_bits(CLKSEL_ACLK, regs + K210_SYSCTL_CLKSEL0); + k210_set_bits(CLKSEL_ACLK, regs + K210_SYSCTL_SEL0); iounmap(regs); } diff --git a/include/soc/canaan/k210-sysctl.h b/include/soc/canaan/k210-sysctl.h new file mode 100644 index 000000000000..2e037db68f35 --- /dev/null +++ b/include/soc/canaan/k210-sysctl.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2019-20 Sean Anderson + * Copyright (c) 2020 Western Digital Corporation or its affiliates. + */ +#ifndef K210_SYSCTL_H +#define K210_SYSCTL_H + +/* + * Kendryte K210 SoC system controller registers offsets. + * Taken from Kendryte SDK (kendryte-standalone-sdk). + */ +#define K210_SYSCTL_GIT_ID 0x00 /* Git short commit id */ +#define K210_SYSCTL_UART_BAUD 0x04 /* Default UARTHS baud rate */ +#define K210_SYSCTL_PLL0 0x08 /* PLL0 controller */ +#define K210_SYSCTL_PLL1 0x0C /* PLL1 controller */ +#define K210_SYSCTL_PLL2 0x10 /* PLL2 controller */ +#define K210_SYSCTL_PLL_LOCK 0x18 /* PLL lock tester */ +#define K210_SYSCTL_ROM_ERROR 0x1C /* AXI ROM detector */ +#define K210_SYSCTL_SEL0 0x20 /* Clock select controller 0 */ +#define K210_SYSCTL_SEL1 0x24 /* Clock select controller 1 */ +#define K210_SYSCTL_EN_CENT 0x28 /* Central clock enable */ +#define K210_SYSCTL_EN_PERI 0x2C /* Peripheral clock enable */ +#define K210_SYSCTL_SOFT_RESET 0x30 /* Soft reset ctrl */ +#define K210_SYSCTL_PERI_RESET 0x34 /* Peripheral reset controller */ +#define K210_SYSCTL_THR0 0x38 /* Clock threshold controller 0 */ +#define K210_SYSCTL_THR1 0x3C /* Clock threshold controller 1 */ +#define K210_SYSCTL_THR2 0x40 /* Clock threshold controller 2 */ +#define K210_SYSCTL_THR3 0x44 /* Clock threshold controller 3 */ +#define K210_SYSCTL_THR4 0x48 /* Clock threshold controller 4 */ +#define K210_SYSCTL_THR5 0x4C /* Clock threshold controller 5 */ +#define K210_SYSCTL_THR6 0x50 /* Clock threshold controller 6 */ +#define K210_SYSCTL_MISC 0x54 /* Miscellaneous controller */ +#define K210_SYSCTL_PERI 0x58 /* Peripheral controller */ +#define K210_SYSCTL_SPI_SLEEP 0x5C /* SPI sleep controller */ +#define K210_SYSCTL_RESET_STAT 0x60 /* Reset source status */ +#define K210_SYSCTL_DMA_SEL0 0x64 /* DMA handshake selector 0 */ +#define K210_SYSCTL_DMA_SEL1 0x68 /* DMA handshake selector 1 */ +#define K210_SYSCTL_POWER_SEL 0x6C /* IO Power Mode Select controller */ + +#endif -- cgit v1.2.3 From 1d7c9d093ed58b8cf4ae23986cd01272667d412a Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Sun, 13 Dec 2020 22:50:43 +0900 Subject: dt-bindings: reset: Document canaan,k210-rst bindings Document the device tree bindings for the Canaan Kendryte K210 SoC reset controller driver in Documentation/devicetree/bindings/reset/canaan,k210-rst.yaml. The header file include/dt-bindings/reset/k210-rst.h is added to define all possible reset lines of the SoC. Signed-off-by: Damien Le Moal Reviewed-by: Rob Herring Signed-off-by: Palmer Dabbelt --- .../devicetree/bindings/reset/canaan,k210-rst.yaml | 40 +++++++++++++++++++++ include/dt-bindings/reset/k210-rst.h | 42 ++++++++++++++++++++++ 2 files changed, 82 insertions(+) create mode 100644 Documentation/devicetree/bindings/reset/canaan,k210-rst.yaml create mode 100644 include/dt-bindings/reset/k210-rst.h (limited to 'include') diff --git a/Documentation/devicetree/bindings/reset/canaan,k210-rst.yaml b/Documentation/devicetree/bindings/reset/canaan,k210-rst.yaml new file mode 100644 index 000000000000..53e4ede9c0bd --- /dev/null +++ b/Documentation/devicetree/bindings/reset/canaan,k210-rst.yaml @@ -0,0 +1,40 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/reset/canaan,k210-rst.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Canaan Kendryte K210 Reset Controller Device Tree Bindings + +maintainers: + - Damien Le Moal + +description: | + Canaan Kendryte K210 reset controller driver which supports the SoC + system controller supplied reset registers for the various peripherals + of the SoC. The K210 reset controller node must be defined as a child + node of the K210 system controller node. + + See also: + - dt-bindings/reset/k210-rst.h + +properties: + compatible: + const: canaan,k210-rst + + '#reset-cells': + const: 1 + +required: + - '#reset-cells' + - compatible + +additionalProperties: false + +examples: + - | + #include + sysrst: reset-controller { + compatible = "canaan,k210-rst"; + #reset-cells = <1>; + }; diff --git a/include/dt-bindings/reset/k210-rst.h b/include/dt-bindings/reset/k210-rst.h new file mode 100644 index 000000000000..883c1aed50e8 --- /dev/null +++ b/include/dt-bindings/reset/k210-rst.h @@ -0,0 +1,42 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Copyright (C) 2019 Sean Anderson + * Copyright (c) 2020 Western Digital Corporation or its affiliates. + */ +#ifndef RESET_K210_SYSCTL_H +#define RESET_K210_SYSCTL_H + +/* + * Kendryte K210 SoC system controller K210_SYSCTL_SOFT_RESET register bits. + * Taken from Kendryte SDK (kendryte-standalone-sdk). + */ +#define K210_RST_ROM 0 +#define K210_RST_DMA 1 +#define K210_RST_AI 2 +#define K210_RST_DVP 3 +#define K210_RST_FFT 4 +#define K210_RST_GPIO 5 +#define K210_RST_SPI0 6 +#define K210_RST_SPI1 7 +#define K210_RST_SPI2 8 +#define K210_RST_SPI3 9 +#define K210_RST_I2S0 10 +#define K210_RST_I2S1 11 +#define K210_RST_I2S2 12 +#define K210_RST_I2C0 13 +#define K210_RST_I2C1 14 +#define K210_RST_I2C2 15 +#define K210_RST_UART1 16 +#define K210_RST_UART2 17 +#define K210_RST_UART3 18 +#define K210_RST_AES 19 +#define K210_RST_FPIOA 20 +#define K210_RST_TIMER0 21 +#define K210_RST_TIMER1 22 +#define K210_RST_TIMER2 23 +#define K210_RST_WDT0 24 +#define K210_RST_WDT1 25 +#define K210_RST_SHA 26 +#define K210_RST_RTC 29 + +#endif /* RESET_K210_SYSCTL_H */ -- cgit v1.2.3 From ed3137edb31b86702511e7ad12b4abe8686b6805 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Sun, 13 Dec 2020 22:50:44 +0900 Subject: dt-bindings: pinctrl: Document canaan,k210-fpioa bindings Document the device tree bindings for the Canaan Kendryte K210 SoC Fully Programmable IO Array (FPIOA) pinctrl driver in Documentation/devicetree/bindings/pinctrl/canaan,k210-fpioa.yaml. The new header file include/dt-bindings/pinctrl/k210-fpioa.h is added to define all 256 possible pin functions of the SoC IO pins, as well as macros simplifying the definition of pin functions in a device tree. Signed-off-by: Damien Le Moal Reviewed-by: Rob Herring Signed-off-by: Palmer Dabbelt --- .../bindings/pinctrl/canaan,k210-fpioa.yaml | 171 +++++++++++++ include/dt-bindings/pinctrl/k210-fpioa.h | 276 +++++++++++++++++++++ 2 files changed, 447 insertions(+) create mode 100644 Documentation/devicetree/bindings/pinctrl/canaan,k210-fpioa.yaml create mode 100644 include/dt-bindings/pinctrl/k210-fpioa.h (limited to 'include') diff --git a/Documentation/devicetree/bindings/pinctrl/canaan,k210-fpioa.yaml b/Documentation/devicetree/bindings/pinctrl/canaan,k210-fpioa.yaml new file mode 100644 index 000000000000..46fbc73ab26b --- /dev/null +++ b/Documentation/devicetree/bindings/pinctrl/canaan,k210-fpioa.yaml @@ -0,0 +1,171 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/pinctrl/canaan,k210-fpioa.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Canaan Kendryte K210 FPIOA Device Tree Bindings + +maintainers: + - Damien Le Moal + +description: + The Canaan Kendryte K210 SoC Fully Programmable IO Array (FPIOA) + controller allows assiging any of 256 possible functions to any of + 48 IO pins of the SoC. Pin function configuration is performed on + a per-pin basis. + +properties: + compatible: + const: canaan,k210-fpioa + + reg: + maxItems: 1 + description: + Address and length of the register set for the FPIOA controller. + + clocks: + items: + - description: Controller reference clock source + - description: APB interface clock source + + clock-names: + items: + - const: ref + - const: pclk + + resets: + maxItems: 1 + + canaan,k210-sysctl-power: + $ref: /schemas/types.yaml#/definitions/phandle-array + description: | + phandle of the K210 system controller node and offset of its + power domain control register. + +patternProperties: + '-pinmux$': + type: object + $ref: /schemas/pinctrl/pinmux-node.yaml + description: + FPIOA client devices use sub-nodes to define the desired pin + configuration. Client device sub-nodes use the pinux property + below. + + properties: + pinmux: + description: + List of IO pins alternate functions. The values for each IO + pin is a combination of an IO pin number (0 to 47) with the + desired function for the IO pin. Functions are defined as + macros in include/dt-bindings/pinctrl/k210-fpioa.h. + The K210_FPIOA(IO pin, function) macro is provided to + facilitate the combination of IO pin numbers and functions. + + required: + - pinmux + + additionalProperties: false + + '-pins$': + type: object + $ref: /schemas/pinctrl/pincfg-node.yaml + description: + FPIOA client devices use sub-nodes to define the desired + configuration of pins. Client device sub-nodes use the + properties below. + + properties: + pins: + description: + List of IO pins affected by the properties specified in this + subnode. IO pins are identified using the pin names "IO_xx". + Pin configuration nodes can also define the power domain to + be used for the SoC pin groups A0 (IO pins 0-5), + A1 (IO pins 6-11), A2 (IO pins 12-17), B0 (IO pins 18-23), + B1 (IO pins 24-29), B2 (IO pins 30-35), B3 (IO pins 30-35), + C0 (IO pins 36-41) and C1 (IO pins 42-47) using the + power-source property. + items: + anyOf: + - pattern: "^(IO_([0-9]*))|(A[0-2])|(B[3-5])|(C[6-7])$" + - enum: [ IO_0, IO_1, IO_2, IO_3, IO_4, IO_5, IO_6, IO_7, + IO_8, IO_9, IO_10, IO_11, IO_12, IO_13, IO_14, + IO_15, IO_16, IO_17, IO_18, IO_19, IO_20, IO_21, + IO_22, IO_23, IO_24, IO_25, IO_26, IO_27, IO_28, + IO_29, IO_30, IO_31, IO_32, IO_33, IO_34, IO_35, + IO_36, IO_37, IO_38, IO_39, IO_40, IO_41, IO_42, + IO_43, IO_44, IO_45, IO_46, IO_47, + A0, A1, A2, B3, B4, B5, C6, C7 ] + bias-disable: true + + bias-pull-down: true + + bias-pull-up: true + + drive-strength: true + + drive-strength-microamp: true + + input-enable: true + + input-disable: true + + input-schmitt-enable: true + + input-schmitt-disable: true + + input-polarity-invert: + description: + Enable or disable pin input polarity inversion. + + output-enable: true + + output-disable: true + + output-high: true + + output-low: true + + output-polarity-invert: + description: + Enable or disable pin output polarity inversion. + + slew-rate: true + + power-source: true + + additionalProperties: false + +required: + - compatible + - reg + - clocks + - canaan,k210-sysctl-power + +additionalProperties: false + +examples: + - | + #include + #include + #include + + fpioa: pinmux@502B0000 { + compatible = "canaan,k210-fpioa"; + reg = <0x502B0000 0x100>; + clocks = <&sysclk K210_CLK_FPIOA>, + <&sysclk K210_CLK_APB0>; + clock-names = "ref", "pclk"; + resets = <&sysrst K210_RST_FPIOA>; + canaan,k210-sysctl-power = <&sysctl 108>; + pinctrl-0 = <&jtag_pinctrl>; + pinctrl-names = "default"; + + jtag_pinctrl: jtag-pinmux { + pinmux = , + , + , + ; + }; + }; diff --git a/include/dt-bindings/pinctrl/k210-fpioa.h b/include/dt-bindings/pinctrl/k210-fpioa.h new file mode 100644 index 000000000000..314285eab3a1 --- /dev/null +++ b/include/dt-bindings/pinctrl/k210-fpioa.h @@ -0,0 +1,276 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Copyright (C) 2020 Sean Anderson + * Copyright (c) 2020 Western Digital Corporation or its affiliates. + */ +#ifndef PINCTRL_K210_FPIOA_H +#define PINCTRL_K210_FPIOA_H + +/* + * Full list of FPIOA functions from + * kendryte-standalone-sdk/lib/drivers/include/fpioa.h + */ +#define K210_PCF_MASK GENMASK(7, 0) +#define K210_PCF_JTAG_TCLK 0 /* JTAG Test Clock */ +#define K210_PCF_JTAG_TDI 1 /* JTAG Test Data In */ +#define K210_PCF_JTAG_TMS 2 /* JTAG Test Mode Select */ +#define K210_PCF_JTAG_TDO 3 /* JTAG Test Data Out */ +#define K210_PCF_SPI0_D0 4 /* SPI0 Data 0 */ +#define K210_PCF_SPI0_D1 5 /* SPI0 Data 1 */ +#define K210_PCF_SPI0_D2 6 /* SPI0 Data 2 */ +#define K210_PCF_SPI0_D3 7 /* SPI0 Data 3 */ +#define K210_PCF_SPI0_D4 8 /* SPI0 Data 4 */ +#define K210_PCF_SPI0_D5 9 /* SPI0 Data 5 */ +#define K210_PCF_SPI0_D6 10 /* SPI0 Data 6 */ +#define K210_PCF_SPI0_D7 11 /* SPI0 Data 7 */ +#define K210_PCF_SPI0_SS0 12 /* SPI0 Chip Select 0 */ +#define K210_PCF_SPI0_SS1 13 /* SPI0 Chip Select 1 */ +#define K210_PCF_SPI0_SS2 14 /* SPI0 Chip Select 2 */ +#define K210_PCF_SPI0_SS3 15 /* SPI0 Chip Select 3 */ +#define K210_PCF_SPI0_ARB 16 /* SPI0 Arbitration */ +#define K210_PCF_SPI0_SCLK 17 /* SPI0 Serial Clock */ +#define K210_PCF_UARTHS_RX 18 /* UART High speed Receiver */ +#define K210_PCF_UARTHS_TX 19 /* UART High speed Transmitter */ +#define K210_PCF_RESV6 20 /* Reserved function */ +#define K210_PCF_RESV7 21 /* Reserved function */ +#define K210_PCF_CLK_SPI1 22 /* Clock SPI1 */ +#define K210_PCF_CLK_I2C1 23 /* Clock I2C1 */ +#define K210_PCF_GPIOHS0 24 /* GPIO High speed 0 */ +#define K210_PCF_GPIOHS1 25 /* GPIO High speed 1 */ +#define K210_PCF_GPIOHS2 26 /* GPIO High speed 2 */ +#define K210_PCF_GPIOHS3 27 /* GPIO High speed 3 */ +#define K210_PCF_GPIOHS4 28 /* GPIO High speed 4 */ +#define K210_PCF_GPIOHS5 29 /* GPIO High speed 5 */ +#define K210_PCF_GPIOHS6 30 /* GPIO High speed 6 */ +#define K210_PCF_GPIOHS7 31 /* GPIO High speed 7 */ +#define K210_PCF_GPIOHS8 32 /* GPIO High speed 8 */ +#define K210_PCF_GPIOHS9 33 /* GPIO High speed 9 */ +#define K210_PCF_GPIOHS10 34 /* GPIO High speed 10 */ +#define K210_PCF_GPIOHS11 35 /* GPIO High speed 11 */ +#define K210_PCF_GPIOHS12 36 /* GPIO High speed 12 */ +#define K210_PCF_GPIOHS13 37 /* GPIO High speed 13 */ +#define K210_PCF_GPIOHS14 38 /* GPIO High speed 14 */ +#define K210_PCF_GPIOHS15 39 /* GPIO High speed 15 */ +#define K210_PCF_GPIOHS16 40 /* GPIO High speed 16 */ +#define K210_PCF_GPIOHS17 41 /* GPIO High speed 17 */ +#define K210_PCF_GPIOHS18 42 /* GPIO High speed 18 */ +#define K210_PCF_GPIOHS19 43 /* GPIO High speed 19 */ +#define K210_PCF_GPIOHS20 44 /* GPIO High speed 20 */ +#define K210_PCF_GPIOHS21 45 /* GPIO High speed 21 */ +#define K210_PCF_GPIOHS22 46 /* GPIO High speed 22 */ +#define K210_PCF_GPIOHS23 47 /* GPIO High speed 23 */ +#define K210_PCF_GPIOHS24 48 /* GPIO High speed 24 */ +#define K210_PCF_GPIOHS25 49 /* GPIO High speed 25 */ +#define K210_PCF_GPIOHS26 50 /* GPIO High speed 26 */ +#define K210_PCF_GPIOHS27 51 /* GPIO High speed 27 */ +#define K210_PCF_GPIOHS28 52 /* GPIO High speed 28 */ +#define K210_PCF_GPIOHS29 53 /* GPIO High speed 29 */ +#define K210_PCF_GPIOHS30 54 /* GPIO High speed 30 */ +#define K210_PCF_GPIOHS31 55 /* GPIO High speed 31 */ +#define K210_PCF_GPIO0 56 /* GPIO pin 0 */ +#define K210_PCF_GPIO1 57 /* GPIO pin 1 */ +#define K210_PCF_GPIO2 58 /* GPIO pin 2 */ +#define K210_PCF_GPIO3 59 /* GPIO pin 3 */ +#define K210_PCF_GPIO4 60 /* GPIO pin 4 */ +#define K210_PCF_GPIO5 61 /* GPIO pin 5 */ +#define K210_PCF_GPIO6 62 /* GPIO pin 6 */ +#define K210_PCF_GPIO7 63 /* GPIO pin 7 */ +#define K210_PCF_UART1_RX 64 /* UART1 Receiver */ +#define K210_PCF_UART1_TX 65 /* UART1 Transmitter */ +#define K210_PCF_UART2_RX 66 /* UART2 Receiver */ +#define K210_PCF_UART2_TX 67 /* UART2 Transmitter */ +#define K210_PCF_UART3_RX 68 /* UART3 Receiver */ +#define K210_PCF_UART3_TX 69 /* UART3 Transmitter */ +#define K210_PCF_SPI1_D0 70 /* SPI1 Data 0 */ +#define K210_PCF_SPI1_D1 71 /* SPI1 Data 1 */ +#define K210_PCF_SPI1_D2 72 /* SPI1 Data 2 */ +#define K210_PCF_SPI1_D3 73 /* SPI1 Data 3 */ +#define K210_PCF_SPI1_D4 74 /* SPI1 Data 4 */ +#define K210_PCF_SPI1_D5 75 /* SPI1 Data 5 */ +#define K210_PCF_SPI1_D6 76 /* SPI1 Data 6 */ +#define K210_PCF_SPI1_D7 77 /* SPI1 Data 7 */ +#define K210_PCF_SPI1_SS0 78 /* SPI1 Chip Select 0 */ +#define K210_PCF_SPI1_SS1 79 /* SPI1 Chip Select 1 */ +#define K210_PCF_SPI1_SS2 80 /* SPI1 Chip Select 2 */ +#define K210_PCF_SPI1_SS3 81 /* SPI1 Chip Select 3 */ +#define K210_PCF_SPI1_ARB 82 /* SPI1 Arbitration */ +#define K210_PCF_SPI1_SCLK 83 /* SPI1 Serial Clock */ +#define K210_PCF_SPI2_D0 84 /* SPI2 Data 0 */ +#define K210_PCF_SPI2_SS 85 /* SPI2 Select */ +#define K210_PCF_SPI2_SCLK 86 /* SPI2 Serial Clock */ +#define K210_PCF_I2S0_MCLK 87 /* I2S0 Master Clock */ +#define K210_PCF_I2S0_SCLK 88 /* I2S0 Serial Clock(BCLK) */ +#define K210_PCF_I2S0_WS 89 /* I2S0 Word Select(LRCLK) */ +#define K210_PCF_I2S0_IN_D0 90 /* I2S0 Serial Data Input 0 */ +#define K210_PCF_I2S0_IN_D1 91 /* I2S0 Serial Data Input 1 */ +#define K210_PCF_I2S0_IN_D2 92 /* I2S0 Serial Data Input 2 */ +#define K210_PCF_I2S0_IN_D3 93 /* I2S0 Serial Data Input 3 */ +#define K210_PCF_I2S0_OUT_D0 94 /* I2S0 Serial Data Output 0 */ +#define K210_PCF_I2S0_OUT_D1 95 /* I2S0 Serial Data Output 1 */ +#define K210_PCF_I2S0_OUT_D2 96 /* I2S0 Serial Data Output 2 */ +#define K210_PCF_I2S0_OUT_D3 97 /* I2S0 Serial Data Output 3 */ +#define K210_PCF_I2S1_MCLK 98 /* I2S1 Master Clock */ +#define K210_PCF_I2S1_SCLK 99 /* I2S1 Serial Clock(BCLK) */ +#define K210_PCF_I2S1_WS 100 /* I2S1 Word Select(LRCLK) */ +#define K210_PCF_I2S1_IN_D0 101 /* I2S1 Serial Data Input 0 */ +#define K210_PCF_I2S1_IN_D1 102 /* I2S1 Serial Data Input 1 */ +#define K210_PCF_I2S1_IN_D2 103 /* I2S1 Serial Data Input 2 */ +#define K210_PCF_I2S1_IN_D3 104 /* I2S1 Serial Data Input 3 */ +#define K210_PCF_I2S1_OUT_D0 105 /* I2S1 Serial Data Output 0 */ +#define K210_PCF_I2S1_OUT_D1 106 /* I2S1 Serial Data Output 1 */ +#define K210_PCF_I2S1_OUT_D2 107 /* I2S1 Serial Data Output 2 */ +#define K210_PCF_I2S1_OUT_D3 108 /* I2S1 Serial Data Output 3 */ +#define K210_PCF_I2S2_MCLK 109 /* I2S2 Master Clock */ +#define K210_PCF_I2S2_SCLK 110 /* I2S2 Serial Clock(BCLK) */ +#define K210_PCF_I2S2_WS 111 /* I2S2 Word Select(LRCLK) */ +#define K210_PCF_I2S2_IN_D0 112 /* I2S2 Serial Data Input 0 */ +#define K210_PCF_I2S2_IN_D1 113 /* I2S2 Serial Data Input 1 */ +#define K210_PCF_I2S2_IN_D2 114 /* I2S2 Serial Data Input 2 */ +#define K210_PCF_I2S2_IN_D3 115 /* I2S2 Serial Data Input 3 */ +#define K210_PCF_I2S2_OUT_D0 116 /* I2S2 Serial Data Output 0 */ +#define K210_PCF_I2S2_OUT_D1 117 /* I2S2 Serial Data Output 1 */ +#define K210_PCF_I2S2_OUT_D2 118 /* I2S2 Serial Data Output 2 */ +#define K210_PCF_I2S2_OUT_D3 119 /* I2S2 Serial Data Output 3 */ +#define K210_PCF_RESV0 120 /* Reserved function */ +#define K210_PCF_RESV1 121 /* Reserved function */ +#define K210_PCF_RESV2 122 /* Reserved function */ +#define K210_PCF_RESV3 123 /* Reserved function */ +#define K210_PCF_RESV4 124 /* Reserved function */ +#define K210_PCF_RESV5 125 /* Reserved function */ +#define K210_PCF_I2C0_SCLK 126 /* I2C0 Serial Clock */ +#define K210_PCF_I2C0_SDA 127 /* I2C0 Serial Data */ +#define K210_PCF_I2C1_SCLK 128 /* I2C1 Serial Clock */ +#define K210_PCF_I2C1_SDA 129 /* I2C1 Serial Data */ +#define K210_PCF_I2C2_SCLK 130 /* I2C2 Serial Clock */ +#define K210_PCF_I2C2_SDA 131 /* I2C2 Serial Data */ +#define K210_PCF_DVP_XCLK 132 /* DVP System Clock */ +#define K210_PCF_DVP_RST 133 /* DVP System Reset */ +#define K210_PCF_DVP_PWDN 134 /* DVP Power Down Mode */ +#define K210_PCF_DVP_VSYNC 135 /* DVP Vertical Sync */ +#define K210_PCF_DVP_HSYNC 136 /* DVP Horizontal Sync */ +#define K210_PCF_DVP_PCLK 137 /* Pixel Clock */ +#define K210_PCF_DVP_D0 138 /* Data Bit 0 */ +#define K210_PCF_DVP_D1 139 /* Data Bit 1 */ +#define K210_PCF_DVP_D2 140 /* Data Bit 2 */ +#define K210_PCF_DVP_D3 141 /* Data Bit 3 */ +#define K210_PCF_DVP_D4 142 /* Data Bit 4 */ +#define K210_PCF_DVP_D5 143 /* Data Bit 5 */ +#define K210_PCF_DVP_D6 144 /* Data Bit 6 */ +#define K210_PCF_DVP_D7 145 /* Data Bit 7 */ +#define K210_PCF_SCCB_SCLK 146 /* Serial Camera Control Bus Clock */ +#define K210_PCF_SCCB_SDA 147 /* Serial Camera Control Bus Data */ +#define K210_PCF_UART1_CTS 148 /* UART1 Clear To Send */ +#define K210_PCF_UART1_DSR 149 /* UART1 Data Set Ready */ +#define K210_PCF_UART1_DCD 150 /* UART1 Data Carrier Detect */ +#define K210_PCF_UART1_RI 151 /* UART1 Ring Indicator */ +#define K210_PCF_UART1_SIR_IN 152 /* UART1 Serial Infrared Input */ +#define K210_PCF_UART1_DTR 153 /* UART1 Data Terminal Ready */ +#define K210_PCF_UART1_RTS 154 /* UART1 Request To Send */ +#define K210_PCF_UART1_OUT2 155 /* UART1 User-designated Output 2 */ +#define K210_PCF_UART1_OUT1 156 /* UART1 User-designated Output 1 */ +#define K210_PCF_UART1_SIR_OUT 157 /* UART1 Serial Infrared Output */ +#define K210_PCF_UART1_BAUD 158 /* UART1 Transmit Clock Output */ +#define K210_PCF_UART1_RE 159 /* UART1 Receiver Output Enable */ +#define K210_PCF_UART1_DE 160 /* UART1 Driver Output Enable */ +#define K210_PCF_UART1_RS485_EN 161 /* UART1 RS485 Enable */ +#define K210_PCF_UART2_CTS 162 /* UART2 Clear To Send */ +#define K210_PCF_UART2_DSR 163 /* UART2 Data Set Ready */ +#define K210_PCF_UART2_DCD 164 /* UART2 Data Carrier Detect */ +#define K210_PCF_UART2_RI 165 /* UART2 Ring Indicator */ +#define K210_PCF_UART2_SIR_IN 166 /* UART2 Serial Infrared Input */ +#define K210_PCF_UART2_DTR 167 /* UART2 Data Terminal Ready */ +#define K210_PCF_UART2_RTS 168 /* UART2 Request To Send */ +#define K210_PCF_UART2_OUT2 169 /* UART2 User-designated Output 2 */ +#define K210_PCF_UART2_OUT1 170 /* UART2 User-designated Output 1 */ +#define K210_PCF_UART2_SIR_OUT 171 /* UART2 Serial Infrared Output */ +#define K210_PCF_UART2_BAUD 172 /* UART2 Transmit Clock Output */ +#define K210_PCF_UART2_RE 173 /* UART2 Receiver Output Enable */ +#define K210_PCF_UART2_DE 174 /* UART2 Driver Output Enable */ +#define K210_PCF_UART2_RS485_EN 175 /* UART2 RS485 Enable */ +#define K210_PCF_UART3_CTS 176 /* UART3 Clear To Send */ +#define K210_PCF_UART3_DSR 177 /* UART3 Data Set Ready */ +#define K210_PCF_UART3_DCD 178 /* UART3 Data Carrier Detect */ +#define K210_PCF_UART3_RI 179 /* UART3 Ring Indicator */ +#define K210_PCF_UART3_SIR_IN 180 /* UART3 Serial Infrared Input */ +#define K210_PCF_UART3_DTR 181 /* UART3 Data Terminal Ready */ +#define K210_PCF_UART3_RTS 182 /* UART3 Request To Send */ +#define K210_PCF_UART3_OUT2 183 /* UART3 User-designated Output 2 */ +#define K210_PCF_UART3_OUT1 184 /* UART3 User-designated Output 1 */ +#define K210_PCF_UART3_SIR_OUT 185 /* UART3 Serial Infrared Output */ +#define K210_PCF_UART3_BAUD 186 /* UART3 Transmit Clock Output */ +#define K210_PCF_UART3_RE 187 /* UART3 Receiver Output Enable */ +#define K210_PCF_UART3_DE 188 /* UART3 Driver Output Enable */ +#define K210_PCF_UART3_RS485_EN 189 /* UART3 RS485 Enable */ +#define K210_PCF_TIMER0_TOGGLE1 190 /* TIMER0 Toggle Output 1 */ +#define K210_PCF_TIMER0_TOGGLE2 191 /* TIMER0 Toggle Output 2 */ +#define K210_PCF_TIMER0_TOGGLE3 192 /* TIMER0 Toggle Output 3 */ +#define K210_PCF_TIMER0_TOGGLE4 193 /* TIMER0 Toggle Output 4 */ +#define K210_PCF_TIMER1_TOGGLE1 194 /* TIMER1 Toggle Output 1 */ +#define K210_PCF_TIMER1_TOGGLE2 195 /* TIMER1 Toggle Output 2 */ +#define K210_PCF_TIMER1_TOGGLE3 196 /* TIMER1 Toggle Output 3 */ +#define K210_PCF_TIMER1_TOGGLE4 197 /* TIMER1 Toggle Output 4 */ +#define K210_PCF_TIMER2_TOGGLE1 198 /* TIMER2 Toggle Output 1 */ +#define K210_PCF_TIMER2_TOGGLE2 199 /* TIMER2 Toggle Output 2 */ +#define K210_PCF_TIMER2_TOGGLE3 200 /* TIMER2 Toggle Output 3 */ +#define K210_PCF_TIMER2_TOGGLE4 201 /* TIMER2 Toggle Output 4 */ +#define K210_PCF_CLK_SPI2 202 /* Clock SPI2 */ +#define K210_PCF_CLK_I2C2 203 /* Clock I2C2 */ +#define K210_PCF_INTERNAL0 204 /* Internal function signal 0 */ +#define K210_PCF_INTERNAL1 205 /* Internal function signal 1 */ +#define K210_PCF_INTERNAL2 206 /* Internal function signal 2 */ +#define K210_PCF_INTERNAL3 207 /* Internal function signal 3 */ +#define K210_PCF_INTERNAL4 208 /* Internal function signal 4 */ +#define K210_PCF_INTERNAL5 209 /* Internal function signal 5 */ +#define K210_PCF_INTERNAL6 210 /* Internal function signal 6 */ +#define K210_PCF_INTERNAL7 211 /* Internal function signal 7 */ +#define K210_PCF_INTERNAL8 212 /* Internal function signal 8 */ +#define K210_PCF_INTERNAL9 213 /* Internal function signal 9 */ +#define K210_PCF_INTERNAL10 214 /* Internal function signal 10 */ +#define K210_PCF_INTERNAL11 215 /* Internal function signal 11 */ +#define K210_PCF_INTERNAL12 216 /* Internal function signal 12 */ +#define K210_PCF_INTERNAL13 217 /* Internal function signal 13 */ +#define K210_PCF_INTERNAL14 218 /* Internal function signal 14 */ +#define K210_PCF_INTERNAL15 219 /* Internal function signal 15 */ +#define K210_PCF_INTERNAL16 220 /* Internal function signal 16 */ +#define K210_PCF_INTERNAL17 221 /* Internal function signal 17 */ +#define K210_PCF_CONSTANT 222 /* Constant function */ +#define K210_PCF_INTERNAL18 223 /* Internal function signal 18 */ +#define K210_PCF_DEBUG0 224 /* Debug function 0 */ +#define K210_PCF_DEBUG1 225 /* Debug function 1 */ +#define K210_PCF_DEBUG2 226 /* Debug function 2 */ +#define K210_PCF_DEBUG3 227 /* Debug function 3 */ +#define K210_PCF_DEBUG4 228 /* Debug function 4 */ +#define K210_PCF_DEBUG5 229 /* Debug function 5 */ +#define K210_PCF_DEBUG6 230 /* Debug function 6 */ +#define K210_PCF_DEBUG7 231 /* Debug function 7 */ +#define K210_PCF_DEBUG8 232 /* Debug function 8 */ +#define K210_PCF_DEBUG9 233 /* Debug function 9 */ +#define K210_PCF_DEBUG10 234 /* Debug function 10 */ +#define K210_PCF_DEBUG11 235 /* Debug function 11 */ +#define K210_PCF_DEBUG12 236 /* Debug function 12 */ +#define K210_PCF_DEBUG13 237 /* Debug function 13 */ +#define K210_PCF_DEBUG14 238 /* Debug function 14 */ +#define K210_PCF_DEBUG15 239 /* Debug function 15 */ +#define K210_PCF_DEBUG16 240 /* Debug function 16 */ +#define K210_PCF_DEBUG17 241 /* Debug function 17 */ +#define K210_PCF_DEBUG18 242 /* Debug function 18 */ +#define K210_PCF_DEBUG19 243 /* Debug function 19 */ +#define K210_PCF_DEBUG20 244 /* Debug function 20 */ +#define K210_PCF_DEBUG21 245 /* Debug function 21 */ +#define K210_PCF_DEBUG22 246 /* Debug function 22 */ +#define K210_PCF_DEBUG23 247 /* Debug function 23 */ +#define K210_PCF_DEBUG24 248 /* Debug function 24 */ +#define K210_PCF_DEBUG25 249 /* Debug function 25 */ +#define K210_PCF_DEBUG26 250 /* Debug function 26 */ +#define K210_PCF_DEBUG27 251 /* Debug function 27 */ +#define K210_PCF_DEBUG28 252 /* Debug function 28 */ +#define K210_PCF_DEBUG29 253 /* Debug function 29 */ +#define K210_PCF_DEBUG30 254 /* Debug function 30 */ +#define K210_PCF_DEBUG31 255 /* Debug function 31 */ + +#define K210_FPIOA(pin, func) (((pin) << 16) | (func)) + +#define K210_PC_POWER_3V3 0 +#define K210_PC_POWER_1V8 1 + +#endif /* PINCTRL_K210_FPIOA_H */ -- cgit v1.2.3 From ae3c107cd8bea82cb7cb427d9c5d305b8ce72216 Mon Sep 17 00:00:00 2001 From: Atish Patra Date: Wed, 18 Nov 2020 16:38:26 -0800 Subject: numa: Move numa implementation to common code ARM64 numa implementation is generic enough that RISC-V can reuse that implementation with very minor cosmetic changes. This will help both ARM64 and RISC-V in terms of maintanace and feature improvement Move the numa implementation code to common directory so that both ISAs can reuse this. This doesn't introduce any function changes for ARM64. Signed-off-by: Atish Patra Acked-by: Jonathan Cameron Tested-by: Jonathan Cameron Acked-by: Catalin Marinas Signed-off-by: Palmer Dabbelt --- arch/arm64/Kconfig | 1 + arch/arm64/include/asm/numa.h | 48 +---- arch/arm64/mm/Makefile | 1 - arch/arm64/mm/numa.c | 483 ------------------------------------------ drivers/base/Kconfig | 6 + drivers/base/Makefile | 1 + drivers/base/arch_numa.c | 483 ++++++++++++++++++++++++++++++++++++++++++ include/asm-generic/numa.h | 52 +++++ 8 files changed, 544 insertions(+), 531 deletions(-) delete mode 100644 arch/arm64/mm/numa.c create mode 100644 drivers/base/arch_numa.c create mode 100644 include/asm-generic/numa.h (limited to 'include') diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 05e17351e4f3..ff9f5c05cca3 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -995,6 +995,7 @@ config HOTPLUG_CPU # Common NUMA Features config NUMA bool "NUMA Memory Allocation and Scheduler Support" + select GENERIC_ARCH_NUMA select ACPI_NUMA if ACPI select OF_NUMA help diff --git a/arch/arm64/include/asm/numa.h b/arch/arm64/include/asm/numa.h index ffc1dcdf1871..8c8cf4297cc3 100644 --- a/arch/arm64/include/asm/numa.h +++ b/arch/arm64/include/asm/numa.h @@ -3,52 +3,6 @@ #define __ASM_NUMA_H #include - -#ifdef CONFIG_NUMA - -#define NR_NODE_MEMBLKS (MAX_NUMNODES * 2) - -int __node_distance(int from, int to); -#define node_distance(a, b) __node_distance(a, b) - -extern nodemask_t numa_nodes_parsed __initdata; - -extern bool numa_off; - -/* Mappings between node number and cpus on that node. */ -extern cpumask_var_t node_to_cpumask_map[MAX_NUMNODES]; -void numa_clear_node(unsigned int cpu); - -#ifdef CONFIG_DEBUG_PER_CPU_MAPS -const struct cpumask *cpumask_of_node(int node); -#else -/* Returns a pointer to the cpumask of CPUs on Node 'node'. */ -static inline const struct cpumask *cpumask_of_node(int node) -{ - if (node == NUMA_NO_NODE) - return cpu_all_mask; - - return node_to_cpumask_map[node]; -} -#endif - -void __init arch_numa_init(void); -int __init numa_add_memblk(int nodeid, u64 start, u64 end); -void __init numa_set_distance(int from, int to, int distance); -void __init numa_free_distance(void); -void __init early_map_cpu_to_node(unsigned int cpu, int nid); -void numa_store_cpu_info(unsigned int cpu); -void numa_add_cpu(unsigned int cpu); -void numa_remove_cpu(unsigned int cpu); - -#else /* CONFIG_NUMA */ - -static inline void numa_store_cpu_info(unsigned int cpu) { } -static inline void numa_add_cpu(unsigned int cpu) { } -static inline void numa_remove_cpu(unsigned int cpu) { } -static inline void arch_numa_init(void) { } -static inline void early_map_cpu_to_node(unsigned int cpu, int nid) { } - -#endif /* CONFIG_NUMA */ +#include #endif /* __ASM_NUMA_H */ diff --git a/arch/arm64/mm/Makefile b/arch/arm64/mm/Makefile index 5ead3c3de3b6..cd60e4fed78f 100644 --- a/arch/arm64/mm/Makefile +++ b/arch/arm64/mm/Makefile @@ -6,7 +6,6 @@ obj-y := dma-mapping.o extable.o fault.o init.o \ obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o obj-$(CONFIG_PTDUMP_CORE) += ptdump.o obj-$(CONFIG_PTDUMP_DEBUGFS) += ptdump_debugfs.o -obj-$(CONFIG_NUMA) += numa.o obj-$(CONFIG_DEBUG_VIRTUAL) += physaddr.o obj-$(CONFIG_ARM64_MTE) += mteswap.o KASAN_SANITIZE_physaddr.o += n diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c deleted file mode 100644 index 0dae54ce7d43..000000000000 --- a/arch/arm64/mm/numa.c +++ /dev/null @@ -1,483 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * NUMA support, based on the x86 implementation. - * - * Copyright (C) 2015 Cavium Inc. - * Author: Ganapatrao Kulkarni - */ - -#define pr_fmt(fmt) "NUMA: " fmt - -#include -#include -#include -#include - -#include - -struct pglist_data *node_data[MAX_NUMNODES] __read_mostly; -EXPORT_SYMBOL(node_data); -nodemask_t numa_nodes_parsed __initdata; -static int cpu_to_node_map[NR_CPUS] = { [0 ... NR_CPUS-1] = NUMA_NO_NODE }; - -static int numa_distance_cnt; -static u8 *numa_distance; -bool numa_off; - -static __init int numa_parse_early_param(char *opt) -{ - if (!opt) - return -EINVAL; - if (str_has_prefix(opt, "off")) - numa_off = true; - - return 0; -} -early_param("numa", numa_parse_early_param); - -cpumask_var_t node_to_cpumask_map[MAX_NUMNODES]; -EXPORT_SYMBOL(node_to_cpumask_map); - -#ifdef CONFIG_DEBUG_PER_CPU_MAPS - -/* - * Returns a pointer to the bitmask of CPUs on Node 'node'. - */ -const struct cpumask *cpumask_of_node(int node) -{ - - if (node == NUMA_NO_NODE) - return cpu_all_mask; - - if (WARN_ON(node < 0 || node >= nr_node_ids)) - return cpu_none_mask; - - if (WARN_ON(node_to_cpumask_map[node] == NULL)) - return cpu_online_mask; - - return node_to_cpumask_map[node]; -} -EXPORT_SYMBOL(cpumask_of_node); - -#endif - -static void numa_update_cpu(unsigned int cpu, bool remove) -{ - int nid = cpu_to_node(cpu); - - if (nid == NUMA_NO_NODE) - return; - - if (remove) - cpumask_clear_cpu(cpu, node_to_cpumask_map[nid]); - else - cpumask_set_cpu(cpu, node_to_cpumask_map[nid]); -} - -void numa_add_cpu(unsigned int cpu) -{ - numa_update_cpu(cpu, false); -} - -void numa_remove_cpu(unsigned int cpu) -{ - numa_update_cpu(cpu, true); -} - -void numa_clear_node(unsigned int cpu) -{ - numa_remove_cpu(cpu); - set_cpu_numa_node(cpu, NUMA_NO_NODE); -} - -/* - * Allocate node_to_cpumask_map based on number of available nodes - * Requires node_possible_map to be valid. - * - * Note: cpumask_of_node() is not valid until after this is done. - * (Use CONFIG_DEBUG_PER_CPU_MAPS to check this.) - */ -static void __init setup_node_to_cpumask_map(void) -{ - int node; - - /* setup nr_node_ids if not done yet */ - if (nr_node_ids == MAX_NUMNODES) - setup_nr_node_ids(); - - /* allocate and clear the mapping */ - for (node = 0; node < nr_node_ids; node++) { - alloc_bootmem_cpumask_var(&node_to_cpumask_map[node]); - cpumask_clear(node_to_cpumask_map[node]); - } - - /* cpumask_of_node() will now work */ - pr_debug("Node to cpumask map for %u nodes\n", nr_node_ids); -} - -/* - * Set the cpu to node and mem mapping - */ -void numa_store_cpu_info(unsigned int cpu) -{ - set_cpu_numa_node(cpu, cpu_to_node_map[cpu]); -} - -void __init early_map_cpu_to_node(unsigned int cpu, int nid) -{ - /* fallback to node 0 */ - if (nid < 0 || nid >= MAX_NUMNODES || numa_off) - nid = 0; - - cpu_to_node_map[cpu] = nid; - - /* - * We should set the numa node of cpu0 as soon as possible, because it - * has already been set up online before. cpu_to_node(0) will soon be - * called. - */ - if (!cpu) - set_cpu_numa_node(cpu, nid); -} - -#ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA -unsigned long __per_cpu_offset[NR_CPUS] __read_mostly; -EXPORT_SYMBOL(__per_cpu_offset); - -static int __init early_cpu_to_node(int cpu) -{ - return cpu_to_node_map[cpu]; -} - -static int __init pcpu_cpu_distance(unsigned int from, unsigned int to) -{ - return node_distance(early_cpu_to_node(from), early_cpu_to_node(to)); -} - -static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, - size_t align) -{ - int nid = early_cpu_to_node(cpu); - - return memblock_alloc_try_nid(size, align, - __pa(MAX_DMA_ADDRESS), MEMBLOCK_ALLOC_ACCESSIBLE, nid); -} - -static void __init pcpu_fc_free(void *ptr, size_t size) -{ - memblock_free_early(__pa(ptr), size); -} - -void __init setup_per_cpu_areas(void) -{ - unsigned long delta; - unsigned int cpu; - int rc; - - /* - * Always reserve area for module percpu variables. That's - * what the legacy allocator did. - */ - rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE, - PERCPU_DYNAMIC_RESERVE, PAGE_SIZE, - pcpu_cpu_distance, - pcpu_fc_alloc, pcpu_fc_free); - if (rc < 0) - panic("Failed to initialize percpu areas."); - - delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start; - for_each_possible_cpu(cpu) - __per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu]; -} -#endif - -/** - * numa_add_memblk() - Set node id to memblk - * @nid: NUMA node ID of the new memblk - * @start: Start address of the new memblk - * @end: End address of the new memblk - * - * RETURNS: - * 0 on success, -errno on failure. - */ -int __init numa_add_memblk(int nid, u64 start, u64 end) -{ - int ret; - - ret = memblock_set_node(start, (end - start), &memblock.memory, nid); - if (ret < 0) { - pr_err("memblock [0x%llx - 0x%llx] failed to add on node %d\n", - start, (end - 1), nid); - return ret; - } - - node_set(nid, numa_nodes_parsed); - return ret; -} - -/* - * Initialize NODE_DATA for a node on the local memory - */ -static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn) -{ - const size_t nd_size = roundup(sizeof(pg_data_t), SMP_CACHE_BYTES); - u64 nd_pa; - void *nd; - int tnid; - - if (start_pfn >= end_pfn) - pr_info("Initmem setup node %d []\n", nid); - - nd_pa = memblock_phys_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid); - if (!nd_pa) - panic("Cannot allocate %zu bytes for node %d data\n", - nd_size, nid); - - nd = __va(nd_pa); - - /* report and initialize */ - pr_info("NODE_DATA [mem %#010Lx-%#010Lx]\n", - nd_pa, nd_pa + nd_size - 1); - tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT); - if (tnid != nid) - pr_info("NODE_DATA(%d) on node %d\n", nid, tnid); - - node_data[nid] = nd; - memset(NODE_DATA(nid), 0, sizeof(pg_data_t)); - NODE_DATA(nid)->node_id = nid; - NODE_DATA(nid)->node_start_pfn = start_pfn; - NODE_DATA(nid)->node_spanned_pages = end_pfn - start_pfn; -} - -/* - * numa_free_distance - * - * The current table is freed. - */ -void __init numa_free_distance(void) -{ - size_t size; - - if (!numa_distance) - return; - - size = numa_distance_cnt * numa_distance_cnt * - sizeof(numa_distance[0]); - - memblock_free(__pa(numa_distance), size); - numa_distance_cnt = 0; - numa_distance = NULL; -} - -/* - * Create a new NUMA distance table. - */ -static int __init numa_alloc_distance(void) -{ - size_t size; - u64 phys; - int i, j; - - size = nr_node_ids * nr_node_ids * sizeof(numa_distance[0]); - phys = memblock_find_in_range(0, PFN_PHYS(max_pfn), - size, PAGE_SIZE); - if (WARN_ON(!phys)) - return -ENOMEM; - - memblock_reserve(phys, size); - - numa_distance = __va(phys); - numa_distance_cnt = nr_node_ids; - - /* fill with the default distances */ - for (i = 0; i < numa_distance_cnt; i++) - for (j = 0; j < numa_distance_cnt; j++) - numa_distance[i * numa_distance_cnt + j] = i == j ? - LOCAL_DISTANCE : REMOTE_DISTANCE; - - pr_debug("Initialized distance table, cnt=%d\n", numa_distance_cnt); - - return 0; -} - -/** - * numa_set_distance() - Set inter node NUMA distance from node to node. - * @from: the 'from' node to set distance - * @to: the 'to' node to set distance - * @distance: NUMA distance - * - * Set the distance from node @from to @to to @distance. - * If distance table doesn't exist, a warning is printed. - * - * If @from or @to is higher than the highest known node or lower than zero - * or @distance doesn't make sense, the call is ignored. - */ -void __init numa_set_distance(int from, int to, int distance) -{ - if (!numa_distance) { - pr_warn_once("Warning: distance table not allocated yet\n"); - return; - } - - if (from >= numa_distance_cnt || to >= numa_distance_cnt || - from < 0 || to < 0) { - pr_warn_once("Warning: node ids are out of bound, from=%d to=%d distance=%d\n", - from, to, distance); - return; - } - - if ((u8)distance != distance || - (from == to && distance != LOCAL_DISTANCE)) { - pr_warn_once("Warning: invalid distance parameter, from=%d to=%d distance=%d\n", - from, to, distance); - return; - } - - numa_distance[from * numa_distance_cnt + to] = distance; -} - -/* - * Return NUMA distance @from to @to - */ -int __node_distance(int from, int to) -{ - if (from >= numa_distance_cnt || to >= numa_distance_cnt) - return from == to ? LOCAL_DISTANCE : REMOTE_DISTANCE; - return numa_distance[from * numa_distance_cnt + to]; -} -EXPORT_SYMBOL(__node_distance); - -static int __init numa_register_nodes(void) -{ - int nid; - struct memblock_region *mblk; - - /* Check that valid nid is set to memblks */ - for_each_mem_region(mblk) { - int mblk_nid = memblock_get_region_node(mblk); - - if (mblk_nid == NUMA_NO_NODE || mblk_nid >= MAX_NUMNODES) { - pr_warn("Warning: invalid memblk node %d [mem %#010Lx-%#010Lx]\n", - mblk_nid, mblk->base, - mblk->base + mblk->size - 1); - return -EINVAL; - } - } - - /* Finally register nodes. */ - for_each_node_mask(nid, numa_nodes_parsed) { - unsigned long start_pfn, end_pfn; - - get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); - setup_node_data(nid, start_pfn, end_pfn); - node_set_online(nid); - } - - /* Setup online nodes to actual nodes*/ - node_possible_map = numa_nodes_parsed; - - return 0; -} - -static int __init numa_init(int (*init_func)(void)) -{ - int ret; - - nodes_clear(numa_nodes_parsed); - nodes_clear(node_possible_map); - nodes_clear(node_online_map); - - ret = numa_alloc_distance(); - if (ret < 0) - return ret; - - ret = init_func(); - if (ret < 0) - goto out_free_distance; - - if (nodes_empty(numa_nodes_parsed)) { - pr_info("No NUMA configuration found\n"); - ret = -EINVAL; - goto out_free_distance; - } - - ret = numa_register_nodes(); - if (ret < 0) - goto out_free_distance; - - setup_node_to_cpumask_map(); - - return 0; -out_free_distance: - numa_free_distance(); - return ret; -} - -/** - * dummy_numa_init() - Fallback dummy NUMA init - * - * Used if there's no underlying NUMA architecture, NUMA initialization - * fails, or NUMA is disabled on the command line. - * - * Must online at least one node (node 0) and add memory blocks that cover all - * allowed memory. It is unlikely that this function fails. - * - * Return: 0 on success, -errno on failure. - */ -static int __init dummy_numa_init(void) -{ - phys_addr_t start = memblock_start_of_DRAM(); - phys_addr_t end = memblock_end_of_DRAM(); - int ret; - - if (numa_off) - pr_info("NUMA disabled\n"); /* Forced off on command line. */ - pr_info("Faking a node at [mem %#018Lx-%#018Lx]\n", start, end - 1); - - ret = numa_add_memblk(0, start, end); - if (ret) { - pr_err("NUMA init failed\n"); - return ret; - } - - numa_off = true; - return 0; -} - -#ifdef CONFIG_ACPI_NUMA -static int __init arch_acpi_numa_init(void) -{ - int ret; - - ret = acpi_numa_init(); - if (ret) { - pr_info("Failed to initialise from firmware\n"); - return ret; - } - - return srat_disabled() ? -EINVAL : 0; -} -#else -static int __init arch_acpi_numa_init(void) -{ - return -EOPNOTSUPP; -} -#endif - -/** - * arch_numa_init() - Initialize NUMA - * - * Try each configured NUMA initialization method until one succeeds. The - * last fallback is dummy single node config encompassing whole memory. - */ -void __init arch_numa_init(void) -{ - if (!numa_off) { - if (!acpi_disabled && !numa_init(arch_acpi_numa_init)) - return; - if (acpi_disabled && !numa_init(of_numa_init)) - return; - } - - numa_init(dummy_numa_init); -} diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig index 040be48ce046..dbd88e2be88a 100644 --- a/drivers/base/Kconfig +++ b/drivers/base/Kconfig @@ -213,4 +213,10 @@ config GENERIC_ARCH_TOPOLOGY appropriate scaling, sysfs interface for reading capacity values at runtime. +config GENERIC_ARCH_NUMA + bool + help + Enable support for generic NUMA implementation. Currently, RISC-V + and ARM64 use it. + endmenu diff --git a/drivers/base/Makefile b/drivers/base/Makefile index 5e7bf9669a81..8b93a7f291ec 100644 --- a/drivers/base/Makefile +++ b/drivers/base/Makefile @@ -24,6 +24,7 @@ obj-$(CONFIG_PINCTRL) += pinctrl.o obj-$(CONFIG_DEV_COREDUMP) += devcoredump.o obj-$(CONFIG_GENERIC_MSI_IRQ_DOMAIN) += platform-msi.o obj-$(CONFIG_GENERIC_ARCH_TOPOLOGY) += arch_topology.o +obj-$(CONFIG_GENERIC_ARCH_NUMA) += arch_numa.o obj-y += test/ diff --git a/drivers/base/arch_numa.c b/drivers/base/arch_numa.c new file mode 100644 index 000000000000..0dae54ce7d43 --- /dev/null +++ b/drivers/base/arch_numa.c @@ -0,0 +1,483 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * NUMA support, based on the x86 implementation. + * + * Copyright (C) 2015 Cavium Inc. + * Author: Ganapatrao Kulkarni + */ + +#define pr_fmt(fmt) "NUMA: " fmt + +#include +#include +#include +#include + +#include + +struct pglist_data *node_data[MAX_NUMNODES] __read_mostly; +EXPORT_SYMBOL(node_data); +nodemask_t numa_nodes_parsed __initdata; +static int cpu_to_node_map[NR_CPUS] = { [0 ... NR_CPUS-1] = NUMA_NO_NODE }; + +static int numa_distance_cnt; +static u8 *numa_distance; +bool numa_off; + +static __init int numa_parse_early_param(char *opt) +{ + if (!opt) + return -EINVAL; + if (str_has_prefix(opt, "off")) + numa_off = true; + + return 0; +} +early_param("numa", numa_parse_early_param); + +cpumask_var_t node_to_cpumask_map[MAX_NUMNODES]; +EXPORT_SYMBOL(node_to_cpumask_map); + +#ifdef CONFIG_DEBUG_PER_CPU_MAPS + +/* + * Returns a pointer to the bitmask of CPUs on Node 'node'. + */ +const struct cpumask *cpumask_of_node(int node) +{ + + if (node == NUMA_NO_NODE) + return cpu_all_mask; + + if (WARN_ON(node < 0 || node >= nr_node_ids)) + return cpu_none_mask; + + if (WARN_ON(node_to_cpumask_map[node] == NULL)) + return cpu_online_mask; + + return node_to_cpumask_map[node]; +} +EXPORT_SYMBOL(cpumask_of_node); + +#endif + +static void numa_update_cpu(unsigned int cpu, bool remove) +{ + int nid = cpu_to_node(cpu); + + if (nid == NUMA_NO_NODE) + return; + + if (remove) + cpumask_clear_cpu(cpu, node_to_cpumask_map[nid]); + else + cpumask_set_cpu(cpu, node_to_cpumask_map[nid]); +} + +void numa_add_cpu(unsigned int cpu) +{ + numa_update_cpu(cpu, false); +} + +void numa_remove_cpu(unsigned int cpu) +{ + numa_update_cpu(cpu, true); +} + +void numa_clear_node(unsigned int cpu) +{ + numa_remove_cpu(cpu); + set_cpu_numa_node(cpu, NUMA_NO_NODE); +} + +/* + * Allocate node_to_cpumask_map based on number of available nodes + * Requires node_possible_map to be valid. + * + * Note: cpumask_of_node() is not valid until after this is done. + * (Use CONFIG_DEBUG_PER_CPU_MAPS to check this.) + */ +static void __init setup_node_to_cpumask_map(void) +{ + int node; + + /* setup nr_node_ids if not done yet */ + if (nr_node_ids == MAX_NUMNODES) + setup_nr_node_ids(); + + /* allocate and clear the mapping */ + for (node = 0; node < nr_node_ids; node++) { + alloc_bootmem_cpumask_var(&node_to_cpumask_map[node]); + cpumask_clear(node_to_cpumask_map[node]); + } + + /* cpumask_of_node() will now work */ + pr_debug("Node to cpumask map for %u nodes\n", nr_node_ids); +} + +/* + * Set the cpu to node and mem mapping + */ +void numa_store_cpu_info(unsigned int cpu) +{ + set_cpu_numa_node(cpu, cpu_to_node_map[cpu]); +} + +void __init early_map_cpu_to_node(unsigned int cpu, int nid) +{ + /* fallback to node 0 */ + if (nid < 0 || nid >= MAX_NUMNODES || numa_off) + nid = 0; + + cpu_to_node_map[cpu] = nid; + + /* + * We should set the numa node of cpu0 as soon as possible, because it + * has already been set up online before. cpu_to_node(0) will soon be + * called. + */ + if (!cpu) + set_cpu_numa_node(cpu, nid); +} + +#ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA +unsigned long __per_cpu_offset[NR_CPUS] __read_mostly; +EXPORT_SYMBOL(__per_cpu_offset); + +static int __init early_cpu_to_node(int cpu) +{ + return cpu_to_node_map[cpu]; +} + +static int __init pcpu_cpu_distance(unsigned int from, unsigned int to) +{ + return node_distance(early_cpu_to_node(from), early_cpu_to_node(to)); +} + +static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, + size_t align) +{ + int nid = early_cpu_to_node(cpu); + + return memblock_alloc_try_nid(size, align, + __pa(MAX_DMA_ADDRESS), MEMBLOCK_ALLOC_ACCESSIBLE, nid); +} + +static void __init pcpu_fc_free(void *ptr, size_t size) +{ + memblock_free_early(__pa(ptr), size); +} + +void __init setup_per_cpu_areas(void) +{ + unsigned long delta; + unsigned int cpu; + int rc; + + /* + * Always reserve area for module percpu variables. That's + * what the legacy allocator did. + */ + rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE, + PERCPU_DYNAMIC_RESERVE, PAGE_SIZE, + pcpu_cpu_distance, + pcpu_fc_alloc, pcpu_fc_free); + if (rc < 0) + panic("Failed to initialize percpu areas."); + + delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start; + for_each_possible_cpu(cpu) + __per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu]; +} +#endif + +/** + * numa_add_memblk() - Set node id to memblk + * @nid: NUMA node ID of the new memblk + * @start: Start address of the new memblk + * @end: End address of the new memblk + * + * RETURNS: + * 0 on success, -errno on failure. + */ +int __init numa_add_memblk(int nid, u64 start, u64 end) +{ + int ret; + + ret = memblock_set_node(start, (end - start), &memblock.memory, nid); + if (ret < 0) { + pr_err("memblock [0x%llx - 0x%llx] failed to add on node %d\n", + start, (end - 1), nid); + return ret; + } + + node_set(nid, numa_nodes_parsed); + return ret; +} + +/* + * Initialize NODE_DATA for a node on the local memory + */ +static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn) +{ + const size_t nd_size = roundup(sizeof(pg_data_t), SMP_CACHE_BYTES); + u64 nd_pa; + void *nd; + int tnid; + + if (start_pfn >= end_pfn) + pr_info("Initmem setup node %d []\n", nid); + + nd_pa = memblock_phys_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid); + if (!nd_pa) + panic("Cannot allocate %zu bytes for node %d data\n", + nd_size, nid); + + nd = __va(nd_pa); + + /* report and initialize */ + pr_info("NODE_DATA [mem %#010Lx-%#010Lx]\n", + nd_pa, nd_pa + nd_size - 1); + tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT); + if (tnid != nid) + pr_info("NODE_DATA(%d) on node %d\n", nid, tnid); + + node_data[nid] = nd; + memset(NODE_DATA(nid), 0, sizeof(pg_data_t)); + NODE_DATA(nid)->node_id = nid; + NODE_DATA(nid)->node_start_pfn = start_pfn; + NODE_DATA(nid)->node_spanned_pages = end_pfn - start_pfn; +} + +/* + * numa_free_distance + * + * The current table is freed. + */ +void __init numa_free_distance(void) +{ + size_t size; + + if (!numa_distance) + return; + + size = numa_distance_cnt * numa_distance_cnt * + sizeof(numa_distance[0]); + + memblock_free(__pa(numa_distance), size); + numa_distance_cnt = 0; + numa_distance = NULL; +} + +/* + * Create a new NUMA distance table. + */ +static int __init numa_alloc_distance(void) +{ + size_t size; + u64 phys; + int i, j; + + size = nr_node_ids * nr_node_ids * sizeof(numa_distance[0]); + phys = memblock_find_in_range(0, PFN_PHYS(max_pfn), + size, PAGE_SIZE); + if (WARN_ON(!phys)) + return -ENOMEM; + + memblock_reserve(phys, size); + + numa_distance = __va(phys); + numa_distance_cnt = nr_node_ids; + + /* fill with the default distances */ + for (i = 0; i < numa_distance_cnt; i++) + for (j = 0; j < numa_distance_cnt; j++) + numa_distance[i * numa_distance_cnt + j] = i == j ? + LOCAL_DISTANCE : REMOTE_DISTANCE; + + pr_debug("Initialized distance table, cnt=%d\n", numa_distance_cnt); + + return 0; +} + +/** + * numa_set_distance() - Set inter node NUMA distance from node to node. + * @from: the 'from' node to set distance + * @to: the 'to' node to set distance + * @distance: NUMA distance + * + * Set the distance from node @from to @to to @distance. + * If distance table doesn't exist, a warning is printed. + * + * If @from or @to is higher than the highest known node or lower than zero + * or @distance doesn't make sense, the call is ignored. + */ +void __init numa_set_distance(int from, int to, int distance) +{ + if (!numa_distance) { + pr_warn_once("Warning: distance table not allocated yet\n"); + return; + } + + if (from >= numa_distance_cnt || to >= numa_distance_cnt || + from < 0 || to < 0) { + pr_warn_once("Warning: node ids are out of bound, from=%d to=%d distance=%d\n", + from, to, distance); + return; + } + + if ((u8)distance != distance || + (from == to && distance != LOCAL_DISTANCE)) { + pr_warn_once("Warning: invalid distance parameter, from=%d to=%d distance=%d\n", + from, to, distance); + return; + } + + numa_distance[from * numa_distance_cnt + to] = distance; +} + +/* + * Return NUMA distance @from to @to + */ +int __node_distance(int from, int to) +{ + if (from >= numa_distance_cnt || to >= numa_distance_cnt) + return from == to ? LOCAL_DISTANCE : REMOTE_DISTANCE; + return numa_distance[from * numa_distance_cnt + to]; +} +EXPORT_SYMBOL(__node_distance); + +static int __init numa_register_nodes(void) +{ + int nid; + struct memblock_region *mblk; + + /* Check that valid nid is set to memblks */ + for_each_mem_region(mblk) { + int mblk_nid = memblock_get_region_node(mblk); + + if (mblk_nid == NUMA_NO_NODE || mblk_nid >= MAX_NUMNODES) { + pr_warn("Warning: invalid memblk node %d [mem %#010Lx-%#010Lx]\n", + mblk_nid, mblk->base, + mblk->base + mblk->size - 1); + return -EINVAL; + } + } + + /* Finally register nodes. */ + for_each_node_mask(nid, numa_nodes_parsed) { + unsigned long start_pfn, end_pfn; + + get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); + setup_node_data(nid, start_pfn, end_pfn); + node_set_online(nid); + } + + /* Setup online nodes to actual nodes*/ + node_possible_map = numa_nodes_parsed; + + return 0; +} + +static int __init numa_init(int (*init_func)(void)) +{ + int ret; + + nodes_clear(numa_nodes_parsed); + nodes_clear(node_possible_map); + nodes_clear(node_online_map); + + ret = numa_alloc_distance(); + if (ret < 0) + return ret; + + ret = init_func(); + if (ret < 0) + goto out_free_distance; + + if (nodes_empty(numa_nodes_parsed)) { + pr_info("No NUMA configuration found\n"); + ret = -EINVAL; + goto out_free_distance; + } + + ret = numa_register_nodes(); + if (ret < 0) + goto out_free_distance; + + setup_node_to_cpumask_map(); + + return 0; +out_free_distance: + numa_free_distance(); + return ret; +} + +/** + * dummy_numa_init() - Fallback dummy NUMA init + * + * Used if there's no underlying NUMA architecture, NUMA initialization + * fails, or NUMA is disabled on the command line. + * + * Must online at least one node (node 0) and add memory blocks that cover all + * allowed memory. It is unlikely that this function fails. + * + * Return: 0 on success, -errno on failure. + */ +static int __init dummy_numa_init(void) +{ + phys_addr_t start = memblock_start_of_DRAM(); + phys_addr_t end = memblock_end_of_DRAM(); + int ret; + + if (numa_off) + pr_info("NUMA disabled\n"); /* Forced off on command line. */ + pr_info("Faking a node at [mem %#018Lx-%#018Lx]\n", start, end - 1); + + ret = numa_add_memblk(0, start, end); + if (ret) { + pr_err("NUMA init failed\n"); + return ret; + } + + numa_off = true; + return 0; +} + +#ifdef CONFIG_ACPI_NUMA +static int __init arch_acpi_numa_init(void) +{ + int ret; + + ret = acpi_numa_init(); + if (ret) { + pr_info("Failed to initialise from firmware\n"); + return ret; + } + + return srat_disabled() ? -EINVAL : 0; +} +#else +static int __init arch_acpi_numa_init(void) +{ + return -EOPNOTSUPP; +} +#endif + +/** + * arch_numa_init() - Initialize NUMA + * + * Try each configured NUMA initialization method until one succeeds. The + * last fallback is dummy single node config encompassing whole memory. + */ +void __init arch_numa_init(void) +{ + if (!numa_off) { + if (!acpi_disabled && !numa_init(arch_acpi_numa_init)) + return; + if (acpi_disabled && !numa_init(of_numa_init)) + return; + } + + numa_init(dummy_numa_init); +} diff --git a/include/asm-generic/numa.h b/include/asm-generic/numa.h new file mode 100644 index 000000000000..1a3ad6d29833 --- /dev/null +++ b/include/asm-generic/numa.h @@ -0,0 +1,52 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_GENERIC_NUMA_H +#define __ASM_GENERIC_NUMA_H + +#ifdef CONFIG_NUMA + +#define NR_NODE_MEMBLKS (MAX_NUMNODES * 2) + +int __node_distance(int from, int to); +#define node_distance(a, b) __node_distance(a, b) + +extern nodemask_t numa_nodes_parsed __initdata; + +extern bool numa_off; + +/* Mappings between node number and cpus on that node. */ +extern cpumask_var_t node_to_cpumask_map[MAX_NUMNODES]; +void numa_clear_node(unsigned int cpu); + +#ifdef CONFIG_DEBUG_PER_CPU_MAPS +const struct cpumask *cpumask_of_node(int node); +#else +/* Returns a pointer to the cpumask of CPUs on Node 'node'. */ +static inline const struct cpumask *cpumask_of_node(int node) +{ + if (node == NUMA_NO_NODE) + return cpu_all_mask; + + return node_to_cpumask_map[node]; +} +#endif + +void __init arch_numa_init(void); +int __init numa_add_memblk(int nodeid, u64 start, u64 end); +void __init numa_set_distance(int from, int to, int distance); +void __init numa_free_distance(void); +void __init early_map_cpu_to_node(unsigned int cpu, int nid); +void numa_store_cpu_info(unsigned int cpu); +void numa_add_cpu(unsigned int cpu); +void numa_remove_cpu(unsigned int cpu); + +#else /* CONFIG_NUMA */ + +static inline void numa_store_cpu_info(unsigned int cpu) { } +static inline void numa_add_cpu(unsigned int cpu) { } +static inline void numa_remove_cpu(unsigned int cpu) { } +static inline void arch_numa_init(void) { } +static inline void early_map_cpu_to_node(unsigned int cpu, int nid) { } + +#endif /* CONFIG_NUMA */ + +#endif /* __ASM_GENERIC_NUMA_H */ -- cgit v1.2.3 From 962c8dcdd5fa680e2bd68320d54e797b6d8c17fe Mon Sep 17 00:00:00 2001 From: Muneendra Kumar Date: Thu, 7 Jan 2021 03:19:04 +0530 Subject: scsi: core: Add a new error code DID_TRANSPORT_MARGINAL in scsi.h Add code in scsi_result_to_blk_status to translate a new error DID_TRANSPORT_MARGINAL to the corresponding blk_status_t i.e BLK_STS_TRANSPORT. Add DID_TRANSPORT_MARGINAL case to scsi_decide_disposition(). Link: https://lore.kernel.org/r/1609969748-17684-2-git-send-email-muneendra.kumar@broadcom.com Reviewed-by: Himanshu Madhani Reviewed-by: Ewan D. Milne Reviewed-by: Hannes Reinecke Signed-off-by: Muneendra Kumar Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_error.c | 6 ++++++ drivers/scsi/scsi_lib.c | 1 + include/scsi/scsi.h | 1 + 3 files changed, 8 insertions(+) (limited to 'include') diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index f11f51e2465f..28056ee498b3 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -1861,6 +1861,12 @@ int scsi_decide_disposition(struct scsi_cmnd *scmd) * the fast io fail tmo fired), so send IO directly upwards. */ return SUCCESS; + case DID_TRANSPORT_MARGINAL: + /* + * caller has decided not to do retries on + * abort success, so send IO directly upwards + */ + return SUCCESS; case DID_ERROR: if (msg_byte(scmd->result) == COMMAND_COMPLETE && status_byte(scmd->result) == RESERVATION_CONFLICT) diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index b3f14f05340a..d0ae586565f8 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -630,6 +630,7 @@ static blk_status_t scsi_result_to_blk_status(struct scsi_cmnd *cmd, int result) return BLK_STS_OK; return BLK_STS_IOERR; case DID_TRANSPORT_FAILFAST: + case DID_TRANSPORT_MARGINAL: return BLK_STS_TRANSPORT; case DID_TARGET_FAILURE: set_host_byte(cmd, DID_OK); diff --git a/include/scsi/scsi.h b/include/scsi/scsi.h index 5339baadc082..5b287ad8b727 100644 --- a/include/scsi/scsi.h +++ b/include/scsi/scsi.h @@ -159,6 +159,7 @@ static inline int scsi_is_wlun(u64 lun) * paths might yield different results */ #define DID_ALLOC_FAILURE 0x12 /* Space allocation on the device failed */ #define DID_MEDIUM_ERROR 0x13 /* Medium error */ +#define DID_TRANSPORT_MARGINAL 0x14 /* Transport marginal errors */ #define DRIVER_OK 0x00 /* Driver status */ /* -- cgit v1.2.3 From 60bee27ba2dff82eb921c515e49236abfb6c54ab Mon Sep 17 00:00:00 2001 From: Muneendra Kumar Date: Thu, 7 Jan 2021 03:19:05 +0530 Subject: scsi: core: No retries on abort success Add a new optional routine, eh_should_retry_cmd(), in scsi_host_template that allows the transport to decide if a cmd is retryable. Return true if the transport is in a state the cmd should be retried on. Update scmd_eh_abort_handler() and scsi_eh_flush_done_q() to both call scsi_eh_should_retry_cmd() to check whether the command needs to be retried. The above changes were based on a patch by Mike Christie. Link: https://lore.kernel.org/r/1609969748-17684-3-git-send-email-muneendra.kumar@broadcom.com Reviewed-by: Himanshu Madhani Reviewed-by: Ewan D. Milne Reviewed-by: Hannes Reinecke Signed-off-by: Muneendra Kumar Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_error.c | 17 +++++++++++++++-- include/scsi/scsi_host.h | 6 ++++++ 2 files changed, 21 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 28056ee498b3..1cdfa5a8ca09 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -124,6 +124,17 @@ static bool scsi_cmd_retry_allowed(struct scsi_cmnd *cmd) return ++cmd->retries <= cmd->allowed; } +static bool scsi_eh_should_retry_cmd(struct scsi_cmnd *cmd) +{ + struct scsi_device *sdev = cmd->device; + struct Scsi_Host *host = sdev->host; + + if (host->hostt->eh_should_retry_cmd) + return host->hostt->eh_should_retry_cmd(cmd); + + return true; +} + /** * scmd_eh_abort_handler - Handle command aborts * @work: command to be aborted. @@ -159,7 +170,8 @@ scmd_eh_abort_handler(struct work_struct *work) "eh timeout, not retrying " "aborted command\n")); } else if (!scsi_noretry_cmd(scmd) && - scsi_cmd_retry_allowed(scmd)) { + scsi_cmd_retry_allowed(scmd) && + scsi_eh_should_retry_cmd(scmd)) { SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_WARNING, scmd, "retry aborted command\n")); @@ -2111,7 +2123,8 @@ void scsi_eh_flush_done_q(struct list_head *done_q) list_for_each_entry_safe(scmd, next, done_q, eh_entry) { list_del_init(&scmd->eh_entry); if (scsi_device_online(scmd->device) && - !scsi_noretry_cmd(scmd) && scsi_cmd_retry_allowed(scmd)) { + !scsi_noretry_cmd(scmd) && scsi_cmd_retry_allowed(scmd) && + scsi_eh_should_retry_cmd(scmd)) { SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_INFO, scmd, "%s: flush retry cmd\n", diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h index 701f178b20ae..e30fd963b97d 100644 --- a/include/scsi/scsi_host.h +++ b/include/scsi/scsi_host.h @@ -314,6 +314,12 @@ struct scsi_host_template { * Status: OPTIONAL */ enum blk_eh_timer_return (*eh_timed_out)(struct scsi_cmnd *); + /* + * Optional routine that allows the transport to decide if a cmd + * is retryable. Return true if the transport is in a state the + * cmd should be retried on. + */ + bool (*eh_should_retry_cmd)(struct scsi_cmnd *scmd); /* This is an optional routine that allows transport to initiate * LLD adapter or firmware reset using sysfs attribute. -- cgit v1.2.3 From 02c66326dc7e8b3a71b7ceb9a08ec1208e13ea84 Mon Sep 17 00:00:00 2001 From: Muneendra Kumar Date: Thu, 7 Jan 2021 03:19:06 +0530 Subject: scsi: scsi_transport_fc: Add a new rport state FC_PORTSTATE_MARGINAL Add a new interface, fc_eh_should_retry_cmd(), which checks if the cmd should be retried or not by checking the rport state. If the rport state is marginal it returns false to make sure there won't be any retries on the cmd. Make the fc_remote_port_delete(), fc_user_scan_tgt(), and fc_timeout_deleted_rport() functions handle the new rport state. Link: https://lore.kernel.org/r/1609969748-17684-4-git-send-email-muneendra.kumar@broadcom.com Reviewed-by: Himanshu Madhani Reviewed-by: Ewan D. Milne Reviewed-by: Hannes Reinecke Signed-off-by: Muneendra Kumar Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_transport_fc.c | 62 +++++++++++++++++++++++++++++----------- include/scsi/scsi_transport_fc.h | 4 ++- 2 files changed, 49 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/drivers/scsi/scsi_transport_fc.c b/drivers/scsi/scsi_transport_fc.c index a926e8f9e56e..ffd25195ae62 100644 --- a/drivers/scsi/scsi_transport_fc.c +++ b/drivers/scsi/scsi_transport_fc.c @@ -148,20 +148,23 @@ fc_enum_name_search(host_event_code, fc_host_event_code, static struct { enum fc_port_state value; char *name; + int matchlen; } fc_port_state_names[] = { - { FC_PORTSTATE_UNKNOWN, "Unknown" }, - { FC_PORTSTATE_NOTPRESENT, "Not Present" }, - { FC_PORTSTATE_ONLINE, "Online" }, - { FC_PORTSTATE_OFFLINE, "Offline" }, - { FC_PORTSTATE_BLOCKED, "Blocked" }, - { FC_PORTSTATE_BYPASSED, "Bypassed" }, - { FC_PORTSTATE_DIAGNOSTICS, "Diagnostics" }, - { FC_PORTSTATE_LINKDOWN, "Linkdown" }, - { FC_PORTSTATE_ERROR, "Error" }, - { FC_PORTSTATE_LOOPBACK, "Loopback" }, - { FC_PORTSTATE_DELETED, "Deleted" }, + { FC_PORTSTATE_UNKNOWN, "Unknown", 7}, + { FC_PORTSTATE_NOTPRESENT, "Not Present", 11 }, + { FC_PORTSTATE_ONLINE, "Online", 6 }, + { FC_PORTSTATE_OFFLINE, "Offline", 7 }, + { FC_PORTSTATE_BLOCKED, "Blocked", 7 }, + { FC_PORTSTATE_BYPASSED, "Bypassed", 8 }, + { FC_PORTSTATE_DIAGNOSTICS, "Diagnostics", 11 }, + { FC_PORTSTATE_LINKDOWN, "Linkdown", 8 }, + { FC_PORTSTATE_ERROR, "Error", 5 }, + { FC_PORTSTATE_LOOPBACK, "Loopback", 8 }, + { FC_PORTSTATE_DELETED, "Deleted", 7 }, + { FC_PORTSTATE_MARGINAL, "Marginal", 8 }, }; fc_enum_name_search(port_state, fc_port_state, fc_port_state_names) +fc_enum_name_match(port_state, fc_port_state, fc_port_state_names) #define FC_PORTSTATE_MAX_NAMELEN 20 @@ -2509,7 +2512,8 @@ fc_user_scan_tgt(struct Scsi_Host *shost, uint channel, uint id, u64 lun) if (rport->scsi_target_id == -1) continue; - if (rport->port_state != FC_PORTSTATE_ONLINE) + if ((rport->port_state != FC_PORTSTATE_ONLINE) && + (rport->port_state != FC_PORTSTATE_MARGINAL)) continue; if ((channel == rport->channel) && @@ -3373,7 +3377,8 @@ fc_remote_port_delete(struct fc_rport *rport) spin_lock_irqsave(shost->host_lock, flags); - if (rport->port_state != FC_PORTSTATE_ONLINE) { + if ((rport->port_state != FC_PORTSTATE_ONLINE) && + (rport->port_state != FC_PORTSTATE_MARGINAL)) { spin_unlock_irqrestore(shost->host_lock, flags); return; } @@ -3515,7 +3520,8 @@ fc_timeout_deleted_rport(struct work_struct *work) * target, validate it still is. If not, tear down the * scsi_target on it. */ - if ((rport->port_state == FC_PORTSTATE_ONLINE) && + if (((rport->port_state == FC_PORTSTATE_ONLINE) || + (rport->port_state == FC_PORTSTATE_MARGINAL)) && (rport->scsi_target_id != -1) && !(rport->roles & FC_PORT_ROLE_FCP_TARGET)) { dev_printk(KERN_ERR, &rport->dev, @@ -3658,7 +3664,8 @@ fc_scsi_scan_rport(struct work_struct *work) struct fc_internal *i = to_fc_internal(shost->transportt); unsigned long flags; - if ((rport->port_state == FC_PORTSTATE_ONLINE) && + if (((rport->port_state == FC_PORTSTATE_ONLINE) || + (rport->port_state == FC_PORTSTATE_MARGINAL)) && (rport->roles & FC_PORT_ROLE_FCP_TARGET) && !(i->f->disable_target_scan)) { scsi_scan_target(&rport->dev, rport->channel, @@ -3731,6 +3738,28 @@ int fc_block_scsi_eh(struct scsi_cmnd *cmnd) } EXPORT_SYMBOL(fc_block_scsi_eh); +/* + * fc_eh_should_retry_cmd - Checks if the cmd should be retried or not + * @scmd: The SCSI command to be checked + * + * This checks the rport state to decide if a cmd is + * retryable. + * + * Returns: true if the rport state is not in marginal state. + */ +bool fc_eh_should_retry_cmd(struct scsi_cmnd *scmd) +{ + struct fc_rport *rport = starget_to_rport(scsi_target(scmd->device)); + + if ((rport->port_state != FC_PORTSTATE_ONLINE) && + (scmd->request->cmd_flags & REQ_FAILFAST_TRANSPORT)) { + set_host_byte(scmd, DID_TRANSPORT_MARGINAL); + return false; + } + return true; +} +EXPORT_SYMBOL_GPL(fc_eh_should_retry_cmd); + /** * fc_vport_setup - allocates and creates a FC virtual port. * @shost: scsi host the virtual port is connected to. @@ -4162,7 +4191,8 @@ static blk_status_t fc_bsg_rport_prep(struct fc_rport *rport) !(rport->flags & FC_RPORT_FAST_FAIL_TIMEDOUT)) return BLK_STS_RESOURCE; - if (rport->port_state != FC_PORTSTATE_ONLINE) + if ((rport->port_state != FC_PORTSTATE_ONLINE) && + (rport->port_state != FC_PORTSTATE_MARGINAL)) return BLK_STS_IOERR; return BLK_STS_OK; diff --git a/include/scsi/scsi_transport_fc.h b/include/scsi/scsi_transport_fc.h index c759b29e46c7..14214ee121ad 100644 --- a/include/scsi/scsi_transport_fc.h +++ b/include/scsi/scsi_transport_fc.h @@ -67,6 +67,7 @@ enum fc_port_state { FC_PORTSTATE_ERROR, FC_PORTSTATE_LOOPBACK, FC_PORTSTATE_DELETED, + FC_PORTSTATE_MARGINAL, }; @@ -742,7 +743,6 @@ struct fc_function_template { unsigned long disable_target_scan:1; }; - /** * fc_remote_port_chkready - called to validate the remote port state * prior to initiating io to the port. @@ -758,6 +758,7 @@ fc_remote_port_chkready(struct fc_rport *rport) switch (rport->port_state) { case FC_PORTSTATE_ONLINE: + case FC_PORTSTATE_MARGINAL: if (rport->roles & FC_PORT_ROLE_FCP_TARGET) result = 0; else if (rport->flags & FC_RPORT_DEVLOSS_PENDING) @@ -839,6 +840,7 @@ int fc_vport_terminate(struct fc_vport *vport); int fc_block_rport(struct fc_rport *rport); int fc_block_scsi_eh(struct scsi_cmnd *cmnd); enum blk_eh_timer_return fc_eh_timed_out(struct scsi_cmnd *scmd); +bool fc_eh_should_retry_cmd(struct scsi_cmnd *scmd); static inline struct Scsi_Host *fc_bsg_to_shost(struct bsg_job *job) { -- cgit v1.2.3 From d6e645012d97164609260ac567b304681734c5e2 Mon Sep 17 00:00:00 2001 From: Tushar Sugandhi Date: Thu, 7 Jan 2021 20:07:03 -0800 Subject: IMA: define a hook to measure kernel integrity critical data IMA provides capabilities to measure file and buffer data. However, various data structures, policies, and states stored in kernel memory also impact the integrity of the system. Several kernel subsystems contain such integrity critical data. These kernel subsystems help protect the integrity of the system. Currently, IMA does not provide a generic function for measuring kernel integrity critical data. Define ima_measure_critical_data, a new IMA hook, to measure kernel integrity critical data. Signed-off-by: Tushar Sugandhi Reviewed-by: Tyler Hicks Signed-off-by: Mimi Zohar --- include/linux/ima.h | 7 +++++++ security/integrity/ima/ima.h | 1 + security/integrity/ima/ima_api.c | 2 +- security/integrity/ima/ima_main.c | 24 ++++++++++++++++++++++++ 4 files changed, 33 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ima.h b/include/linux/ima.h index 7db9cca1af34..59bd90ac3c35 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -31,6 +31,9 @@ extern void ima_post_path_mknod(struct dentry *dentry); extern int ima_file_hash(struct file *file, char *buf, size_t buf_size); extern int ima_inode_hash(struct inode *inode, char *buf, size_t buf_size); extern void ima_kexec_cmdline(int kernel_fd, const void *buf, int size); +extern void ima_measure_critical_data(const char *event_name, + const void *buf, size_t buf_len, + bool hash); #ifdef CONFIG_IMA_APPRAISE_BOOTPARAM extern void ima_appraise_parse_cmdline(void); @@ -128,6 +131,10 @@ static inline int ima_inode_hash(struct inode *inode, char *buf, size_t buf_size } static inline void ima_kexec_cmdline(int kernel_fd, const void *buf, int size) {} + +static inline void ima_measure_critical_data(const char *event_name, + const void *buf, size_t buf_len, + bool hash) {} #endif /* CONFIG_IMA */ #ifndef CONFIG_IMA_KEXEC diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h index 0b4634515839..aa312472c7c5 100644 --- a/security/integrity/ima/ima.h +++ b/security/integrity/ima/ima.h @@ -201,6 +201,7 @@ static inline unsigned int ima_hash_key(u8 *digest) hook(POLICY_CHECK, policy) \ hook(KEXEC_CMDLINE, kexec_cmdline) \ hook(KEY_CHECK, key) \ + hook(CRITICAL_DATA, critical_data) \ hook(MAX_CHECK, none) #define __ima_hook_enumify(ENUM, str) ENUM, diff --git a/security/integrity/ima/ima_api.c b/security/integrity/ima/ima_api.c index e76499b1ce78..1dd70dc68ffd 100644 --- a/security/integrity/ima/ima_api.c +++ b/security/integrity/ima/ima_api.c @@ -176,7 +176,7 @@ err_out: * subj=, obj=, type=, func=, mask=, fsmagic= * subj,obj, and type: are LSM specific. * func: FILE_CHECK | BPRM_CHECK | CREDS_CHECK | MMAP_CHECK | MODULE_CHECK - * | KEXEC_CMDLINE | KEY_CHECK + * | KEXEC_CMDLINE | KEY_CHECK | CRITICAL_DATA * mask: contains the permission mask * fsmagic: hex value * diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c index 250e52114230..251e7b4006f4 100644 --- a/security/integrity/ima/ima_main.c +++ b/security/integrity/ima/ima_main.c @@ -943,6 +943,30 @@ void ima_kexec_cmdline(int kernel_fd, const void *buf, int size) fdput(f); } +/** + * ima_measure_critical_data - measure kernel integrity critical data + * @event_name: event name for the record in the IMA measurement list + * @buf: pointer to buffer data + * @buf_len: length of buffer data (in bytes) + * @hash: measure buffer data hash + * + * Measure data critical to the integrity of the kernel into the IMA log + * and extend the pcr. Examples of critical data could be various data + * structures, policies, and states stored in kernel memory that can + * impact the integrity of the system. + */ +void ima_measure_critical_data(const char *event_name, + const void *buf, size_t buf_len, + bool hash) +{ + if (!event_name || !buf || !buf_len) + return; + + process_buffer_measurement(NULL, buf, buf_len, event_name, + CRITICAL_DATA, 0, NULL, + hash); +} + static int __init init_ima(void) { int error; -- cgit v1.2.3 From 9f5d7d23cc5ec61a92076b73665fcb9aaa5bb5a0 Mon Sep 17 00:00:00 2001 From: Tushar Sugandhi Date: Thu, 7 Jan 2021 20:07:06 -0800 Subject: IMA: extend critical data hook to limit the measurement based on a label The IMA hook ima_measure_critical_data() does not support a way to specify the source of the critical data provider. Thus, the data measurement cannot be constrained based on the data source label in the IMA policy. Extend the IMA hook ima_measure_critical_data() to support passing the data source label as an input parameter, so that the policy rule can be used to limit the measurements based on the label. Signed-off-by: Tushar Sugandhi Reviewed-by: Tyler Hicks Signed-off-by: Mimi Zohar --- include/linux/ima.h | 7 +++++-- security/integrity/ima/ima_main.c | 8 +++++--- 2 files changed, 10 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/ima.h b/include/linux/ima.h index 59bd90ac3c35..2ac834badbbe 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -31,7 +31,8 @@ extern void ima_post_path_mknod(struct dentry *dentry); extern int ima_file_hash(struct file *file, char *buf, size_t buf_size); extern int ima_inode_hash(struct inode *inode, char *buf, size_t buf_size); extern void ima_kexec_cmdline(int kernel_fd, const void *buf, int size); -extern void ima_measure_critical_data(const char *event_name, +extern void ima_measure_critical_data(const char *event_label, + const char *event_name, const void *buf, size_t buf_len, bool hash); @@ -132,9 +133,11 @@ static inline int ima_inode_hash(struct inode *inode, char *buf, size_t buf_size static inline void ima_kexec_cmdline(int kernel_fd, const void *buf, int size) {} -static inline void ima_measure_critical_data(const char *event_name, +static inline void ima_measure_critical_data(const char *event_label, + const char *event_name, const void *buf, size_t buf_len, bool hash) {} + #endif /* CONFIG_IMA */ #ifndef CONFIG_IMA_KEXEC diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c index 251e7b4006f4..6a429846f90a 100644 --- a/security/integrity/ima/ima_main.c +++ b/security/integrity/ima/ima_main.c @@ -945,6 +945,7 @@ void ima_kexec_cmdline(int kernel_fd, const void *buf, int size) /** * ima_measure_critical_data - measure kernel integrity critical data + * @event_label: unique event label for grouping and limiting critical data * @event_name: event name for the record in the IMA measurement list * @buf: pointer to buffer data * @buf_len: length of buffer data (in bytes) @@ -955,15 +956,16 @@ void ima_kexec_cmdline(int kernel_fd, const void *buf, int size) * structures, policies, and states stored in kernel memory that can * impact the integrity of the system. */ -void ima_measure_critical_data(const char *event_name, +void ima_measure_critical_data(const char *event_label, + const char *event_name, const void *buf, size_t buf_len, bool hash) { - if (!event_name || !buf || !buf_len) + if (!event_name || !event_label || !buf || !buf_len) return; process_buffer_measurement(NULL, buf, buf_len, event_name, - CRITICAL_DATA, 0, NULL, + CRITICAL_DATA, 0, event_label, hash); } -- cgit v1.2.3 From 0ba882ae2818193487b70ad39622973538711d9a Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Thu, 14 Jan 2021 16:16:27 +0100 Subject: spi: Drop unused efm32 bus driver MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Support for this machine was just removed, so drop the now unused spi bus driver, too. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20210114151630.128830-5-u.kleine-koenig@pengutronix.de Signed-off-by: Mark Brown --- drivers/spi/Kconfig | 7 - drivers/spi/Makefile | 1 - drivers/spi/spi-efm32.c | 462 -------------------------------- include/linux/platform_data/efm32-spi.h | 15 -- 4 files changed, 485 deletions(-) delete mode 100644 drivers/spi/spi-efm32.c delete mode 100644 include/linux/platform_data/efm32-spi.h (limited to 'include') diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig index aadaea052f51..d3375aa6e292 100644 --- a/drivers/spi/Kconfig +++ b/drivers/spi/Kconfig @@ -292,13 +292,6 @@ config SPI_DLN2 This driver can also be built as a module. If so, the module will be called spi-dln2. -config SPI_EFM32 - tristate "EFM32 SPI controller" - depends on OF && ARM && (ARCH_EFM32 || COMPILE_TEST) - select SPI_BITBANG - help - Driver for the spi controller found on Energy Micro's EFM32 SoCs. - config SPI_EP93XX tristate "Cirrus Logic EP93xx SPI controller" depends on ARCH_EP93XX || COMPILE_TEST diff --git a/drivers/spi/Makefile b/drivers/spi/Makefile index 6fea5821662e..5a21b5cc8015 100644 --- a/drivers/spi/Makefile +++ b/drivers/spi/Makefile @@ -42,7 +42,6 @@ spi-dw-$(CONFIG_SPI_DW_DMA) += spi-dw-dma.o obj-$(CONFIG_SPI_DW_BT1) += spi-dw-bt1.o obj-$(CONFIG_SPI_DW_MMIO) += spi-dw-mmio.o obj-$(CONFIG_SPI_DW_PCI) += spi-dw-pci.o -obj-$(CONFIG_SPI_EFM32) += spi-efm32.o obj-$(CONFIG_SPI_EP93XX) += spi-ep93xx.o obj-$(CONFIG_SPI_FALCON) += spi-falcon.o obj-$(CONFIG_SPI_FSI) += spi-fsi.o diff --git a/drivers/spi/spi-efm32.c b/drivers/spi/spi-efm32.c deleted file mode 100644 index ea6e4a7b3feb..000000000000 --- a/drivers/spi/spi-efm32.c +++ /dev/null @@ -1,462 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2012-2013 Uwe Kleine-Koenig for Pengutronix - */ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#define DRIVER_NAME "efm32-spi" - -#define MASK_VAL(mask, val) ((val << __ffs(mask)) & mask) - -#define REG_CTRL 0x00 -#define REG_CTRL_SYNC 0x0001 -#define REG_CTRL_CLKPOL 0x0100 -#define REG_CTRL_CLKPHA 0x0200 -#define REG_CTRL_MSBF 0x0400 -#define REG_CTRL_TXBIL 0x1000 - -#define REG_FRAME 0x04 -#define REG_FRAME_DATABITS__MASK 0x000f -#define REG_FRAME_DATABITS(n) ((n) - 3) - -#define REG_CMD 0x0c -#define REG_CMD_RXEN 0x0001 -#define REG_CMD_RXDIS 0x0002 -#define REG_CMD_TXEN 0x0004 -#define REG_CMD_TXDIS 0x0008 -#define REG_CMD_MASTEREN 0x0010 - -#define REG_STATUS 0x10 -#define REG_STATUS_TXENS 0x0002 -#define REG_STATUS_TXC 0x0020 -#define REG_STATUS_TXBL 0x0040 -#define REG_STATUS_RXDATAV 0x0080 - -#define REG_CLKDIV 0x14 - -#define REG_RXDATAX 0x18 -#define REG_RXDATAX_RXDATA__MASK 0x01ff -#define REG_RXDATAX_PERR 0x4000 -#define REG_RXDATAX_FERR 0x8000 - -#define REG_TXDATA 0x34 - -#define REG_IF 0x40 -#define REG_IF_TXBL 0x0002 -#define REG_IF_RXDATAV 0x0004 - -#define REG_IFS 0x44 -#define REG_IFC 0x48 -#define REG_IEN 0x4c - -#define REG_ROUTE 0x54 -#define REG_ROUTE_RXPEN 0x0001 -#define REG_ROUTE_TXPEN 0x0002 -#define REG_ROUTE_CLKPEN 0x0008 -#define REG_ROUTE_LOCATION__MASK 0x0700 -#define REG_ROUTE_LOCATION(n) MASK_VAL(REG_ROUTE_LOCATION__MASK, (n)) - -struct efm32_spi_ddata { - struct spi_bitbang bitbang; - - spinlock_t lock; - - struct clk *clk; - void __iomem *base; - unsigned int rxirq, txirq; - struct efm32_spi_pdata pdata; - - /* irq data */ - struct completion done; - const u8 *tx_buf; - u8 *rx_buf; - unsigned tx_len, rx_len; -}; - -#define ddata_to_dev(ddata) (&(ddata->bitbang.master->dev)) -#define efm32_spi_vdbg(ddata, format, arg...) \ - dev_vdbg(ddata_to_dev(ddata), format, ##arg) - -static void efm32_spi_write32(struct efm32_spi_ddata *ddata, - u32 value, unsigned offset) -{ - writel_relaxed(value, ddata->base + offset); -} - -static u32 efm32_spi_read32(struct efm32_spi_ddata *ddata, unsigned offset) -{ - return readl_relaxed(ddata->base + offset); -} - -static int efm32_spi_setup_transfer(struct spi_device *spi, - struct spi_transfer *t) -{ - struct efm32_spi_ddata *ddata = spi_master_get_devdata(spi->master); - - unsigned bpw = t->bits_per_word ?: spi->bits_per_word; - unsigned speed = t->speed_hz ?: spi->max_speed_hz; - unsigned long clkfreq = clk_get_rate(ddata->clk); - u32 clkdiv; - - efm32_spi_write32(ddata, REG_CTRL_SYNC | REG_CTRL_MSBF | - (spi->mode & SPI_CPHA ? REG_CTRL_CLKPHA : 0) | - (spi->mode & SPI_CPOL ? REG_CTRL_CLKPOL : 0), REG_CTRL); - - efm32_spi_write32(ddata, - REG_FRAME_DATABITS(bpw), REG_FRAME); - - if (2 * speed >= clkfreq) - clkdiv = 0; - else - clkdiv = 64 * (DIV_ROUND_UP(2 * clkfreq, speed) - 4); - - if (clkdiv > (1U << 21)) - return -EINVAL; - - efm32_spi_write32(ddata, clkdiv, REG_CLKDIV); - efm32_spi_write32(ddata, REG_CMD_MASTEREN, REG_CMD); - efm32_spi_write32(ddata, REG_CMD_RXEN | REG_CMD_TXEN, REG_CMD); - - return 0; -} - -static void efm32_spi_tx_u8(struct efm32_spi_ddata *ddata) -{ - u8 val = 0; - - if (ddata->tx_buf) { - val = *ddata->tx_buf; - ddata->tx_buf++; - } - - ddata->tx_len--; - efm32_spi_write32(ddata, val, REG_TXDATA); - efm32_spi_vdbg(ddata, "%s: tx 0x%x\n", __func__, val); -} - -static void efm32_spi_rx_u8(struct efm32_spi_ddata *ddata) -{ - u32 rxdata = efm32_spi_read32(ddata, REG_RXDATAX); - efm32_spi_vdbg(ddata, "%s: rx 0x%x\n", __func__, rxdata); - - if (ddata->rx_buf) { - *ddata->rx_buf = rxdata; - ddata->rx_buf++; - } - - ddata->rx_len--; -} - -static void efm32_spi_filltx(struct efm32_spi_ddata *ddata) -{ - while (ddata->tx_len && - ddata->tx_len + 2 > ddata->rx_len && - efm32_spi_read32(ddata, REG_STATUS) & REG_STATUS_TXBL) { - efm32_spi_tx_u8(ddata); - } -} - -static int efm32_spi_txrx_bufs(struct spi_device *spi, struct spi_transfer *t) -{ - struct efm32_spi_ddata *ddata = spi_master_get_devdata(spi->master); - int ret = -EBUSY; - - spin_lock_irq(&ddata->lock); - - if (ddata->tx_buf || ddata->rx_buf) - goto out_unlock; - - ddata->tx_buf = t->tx_buf; - ddata->rx_buf = t->rx_buf; - ddata->tx_len = ddata->rx_len = - t->len * DIV_ROUND_UP(t->bits_per_word, 8); - - efm32_spi_filltx(ddata); - - reinit_completion(&ddata->done); - - efm32_spi_write32(ddata, REG_IF_TXBL | REG_IF_RXDATAV, REG_IEN); - - spin_unlock_irq(&ddata->lock); - - wait_for_completion(&ddata->done); - - spin_lock_irq(&ddata->lock); - - ret = t->len - max(ddata->tx_len, ddata->rx_len); - - efm32_spi_write32(ddata, 0, REG_IEN); - ddata->tx_buf = ddata->rx_buf = NULL; - -out_unlock: - spin_unlock_irq(&ddata->lock); - - return ret; -} - -static irqreturn_t efm32_spi_rxirq(int irq, void *data) -{ - struct efm32_spi_ddata *ddata = data; - irqreturn_t ret = IRQ_NONE; - - spin_lock(&ddata->lock); - - while (ddata->rx_len > 0 && - efm32_spi_read32(ddata, REG_STATUS) & - REG_STATUS_RXDATAV) { - efm32_spi_rx_u8(ddata); - - ret = IRQ_HANDLED; - } - - if (!ddata->rx_len) { - u32 ien = efm32_spi_read32(ddata, REG_IEN); - - ien &= ~REG_IF_RXDATAV; - - efm32_spi_write32(ddata, ien, REG_IEN); - - complete(&ddata->done); - } - - spin_unlock(&ddata->lock); - - return ret; -} - -static irqreturn_t efm32_spi_txirq(int irq, void *data) -{ - struct efm32_spi_ddata *ddata = data; - - efm32_spi_vdbg(ddata, - "%s: txlen = %u, rxlen = %u, if=0x%08x, stat=0x%08x\n", - __func__, ddata->tx_len, ddata->rx_len, - efm32_spi_read32(ddata, REG_IF), - efm32_spi_read32(ddata, REG_STATUS)); - - spin_lock(&ddata->lock); - - efm32_spi_filltx(ddata); - - efm32_spi_vdbg(ddata, "%s: txlen = %u, rxlen = %u\n", - __func__, ddata->tx_len, ddata->rx_len); - - if (!ddata->tx_len) { - u32 ien = efm32_spi_read32(ddata, REG_IEN); - - ien &= ~REG_IF_TXBL; - - efm32_spi_write32(ddata, ien, REG_IEN); - efm32_spi_vdbg(ddata, "disable TXBL\n"); - } - - spin_unlock(&ddata->lock); - - return IRQ_HANDLED; -} - -static u32 efm32_spi_get_configured_location(struct efm32_spi_ddata *ddata) -{ - u32 reg = efm32_spi_read32(ddata, REG_ROUTE); - - return (reg & REG_ROUTE_LOCATION__MASK) >> __ffs(REG_ROUTE_LOCATION__MASK); -} - -static void efm32_spi_probe_dt(struct platform_device *pdev, - struct spi_master *master, struct efm32_spi_ddata *ddata) -{ - struct device_node *np = pdev->dev.of_node; - u32 location; - int ret; - - ret = of_property_read_u32(np, "energymicro,location", &location); - - if (ret) - /* fall back to wrongly namespaced property */ - ret = of_property_read_u32(np, "efm32,location", &location); - - if (ret) - /* fall back to old and (wrongly) generic property "location" */ - ret = of_property_read_u32(np, "location", &location); - - if (!ret) { - dev_dbg(&pdev->dev, "using location %u\n", location); - } else { - /* default to location configured in hardware */ - location = efm32_spi_get_configured_location(ddata); - - dev_info(&pdev->dev, "fall back to location %u\n", location); - } - - ddata->pdata.location = location; -} - -static int efm32_spi_probe(struct platform_device *pdev) -{ - struct efm32_spi_ddata *ddata; - struct resource *res; - int ret; - struct spi_master *master; - struct device_node *np = pdev->dev.of_node; - - if (!np) - return -EINVAL; - - master = spi_alloc_master(&pdev->dev, sizeof(*ddata)); - if (!master) { - dev_dbg(&pdev->dev, - "failed to allocate spi master controller\n"); - return -ENOMEM; - } - platform_set_drvdata(pdev, master); - - master->dev.of_node = pdev->dev.of_node; - - master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH; - master->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 16); - master->use_gpio_descriptors = true; - - ddata = spi_master_get_devdata(master); - - ddata->bitbang.master = master; - ddata->bitbang.setup_transfer = efm32_spi_setup_transfer; - ddata->bitbang.txrx_bufs = efm32_spi_txrx_bufs; - - spin_lock_init(&ddata->lock); - init_completion(&ddata->done); - - ddata->clk = devm_clk_get(&pdev->dev, NULL); - if (IS_ERR(ddata->clk)) { - ret = PTR_ERR(ddata->clk); - dev_err(&pdev->dev, "failed to get clock: %d\n", ret); - goto err; - } - - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!res) { - ret = -ENODEV; - dev_err(&pdev->dev, "failed to determine base address\n"); - goto err; - } - - if (resource_size(res) < 0x60) { - ret = -EINVAL; - dev_err(&pdev->dev, "memory resource too small\n"); - goto err; - } - - ddata->base = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(ddata->base)) { - ret = PTR_ERR(ddata->base); - goto err; - } - - ret = platform_get_irq(pdev, 0); - if (ret <= 0) - goto err; - - ddata->rxirq = ret; - - ret = platform_get_irq(pdev, 1); - if (ret <= 0) - ret = ddata->rxirq + 1; - - ddata->txirq = ret; - - ret = clk_prepare_enable(ddata->clk); - if (ret < 0) { - dev_err(&pdev->dev, "failed to enable clock (%d)\n", ret); - goto err; - } - - efm32_spi_probe_dt(pdev, master, ddata); - - efm32_spi_write32(ddata, 0, REG_IEN); - efm32_spi_write32(ddata, REG_ROUTE_TXPEN | REG_ROUTE_RXPEN | - REG_ROUTE_CLKPEN | - REG_ROUTE_LOCATION(ddata->pdata.location), REG_ROUTE); - - ret = request_irq(ddata->rxirq, efm32_spi_rxirq, - 0, DRIVER_NAME " rx", ddata); - if (ret) { - dev_err(&pdev->dev, "failed to register rxirq (%d)\n", ret); - goto err_disable_clk; - } - - ret = request_irq(ddata->txirq, efm32_spi_txirq, - 0, DRIVER_NAME " tx", ddata); - if (ret) { - dev_err(&pdev->dev, "failed to register txirq (%d)\n", ret); - goto err_free_rx_irq; - } - - ret = spi_bitbang_start(&ddata->bitbang); - if (ret) { - dev_err(&pdev->dev, "spi_bitbang_start failed (%d)\n", ret); - - free_irq(ddata->txirq, ddata); -err_free_rx_irq: - free_irq(ddata->rxirq, ddata); -err_disable_clk: - clk_disable_unprepare(ddata->clk); -err: - spi_master_put(master); - } - - return ret; -} - -static int efm32_spi_remove(struct platform_device *pdev) -{ - struct spi_master *master = platform_get_drvdata(pdev); - struct efm32_spi_ddata *ddata = spi_master_get_devdata(master); - - spi_bitbang_stop(&ddata->bitbang); - - efm32_spi_write32(ddata, 0, REG_IEN); - - free_irq(ddata->txirq, ddata); - free_irq(ddata->rxirq, ddata); - clk_disable_unprepare(ddata->clk); - spi_master_put(master); - - return 0; -} - -static const struct of_device_id efm32_spi_dt_ids[] = { - { - .compatible = "energymicro,efm32-spi", - }, { - /* doesn't follow the "vendor,device" scheme, don't use */ - .compatible = "efm32,spi", - }, { - /* sentinel */ - } -}; -MODULE_DEVICE_TABLE(of, efm32_spi_dt_ids); - -static struct platform_driver efm32_spi_driver = { - .probe = efm32_spi_probe, - .remove = efm32_spi_remove, - - .driver = { - .name = DRIVER_NAME, - .of_match_table = efm32_spi_dt_ids, - }, -}; -module_platform_driver(efm32_spi_driver); - -MODULE_AUTHOR("Uwe Kleine-Koenig "); -MODULE_DESCRIPTION("EFM32 SPI driver"); -MODULE_LICENSE("GPL v2"); -MODULE_ALIAS("platform:" DRIVER_NAME); diff --git a/include/linux/platform_data/efm32-spi.h b/include/linux/platform_data/efm32-spi.h deleted file mode 100644 index a2c56fcd0534..000000000000 --- a/include/linux/platform_data/efm32-spi.h +++ /dev/null @@ -1,15 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __LINUX_PLATFORM_DATA_EFM32_SPI_H__ -#define __LINUX_PLATFORM_DATA_EFM32_SPI_H__ - -#include - -/** - * struct efm32_spi_pdata - * @location: pinmux location for the I/O pins (to be written to the ROUTE - * register) - */ -struct efm32_spi_pdata { - u8 location; -}; -#endif /* ifndef __LINUX_PLATFORM_DATA_EFM32_SPI_H__ */ -- cgit v1.2.3 From bca585d24a1719d9314d5438b0d2804a33d9bbb6 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 5 Jan 2021 14:13:52 -0500 Subject: new helper: d_find_alias_rcu() similar to d_find_alias(inode), except that * the caller must be holding rcu_read_lock() * inode must not be freed until matching rcu_read_unlock() * result is *NOT* pinned and can only be dereferenced until the matching rcu_read_unlock(). Signed-off-by: Al Viro --- fs/dcache.c | 25 +++++++++++++++++++++++++ include/linux/dcache.h | 2 ++ 2 files changed, 27 insertions(+) (limited to 'include') diff --git a/fs/dcache.c b/fs/dcache.c index 97e81a844a96..843546633457 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -1042,6 +1042,31 @@ struct dentry *d_find_alias(struct inode *inode) } EXPORT_SYMBOL(d_find_alias); +/* + * Caller MUST be holding rcu_read_lock() and be guaranteed + * that inode won't get freed until rcu_read_unlock(). + */ +struct dentry *d_find_alias_rcu(struct inode *inode) +{ + struct hlist_head *l = &inode->i_dentry; + struct dentry *de = NULL; + + spin_lock(&inode->i_lock); + // ->i_dentry and ->i_rcu are colocated, but the latter won't be + // used without having I_FREEING set, which means no aliases left + if (likely(!(inode->i_state & I_FREEING) && !hlist_empty(l))) { + if (S_ISDIR(inode->i_mode)) { + de = hlist_entry(l->first, struct dentry, d_u.d_alias); + } else { + hlist_for_each_entry(de, l, d_u.d_alias) + if (!d_unhashed(de)) + break; + } + } + spin_unlock(&inode->i_lock); + return de; +} + /* * Try to kill dentries associated with this inode. * WARNING: you must own a reference to inode. diff --git a/include/linux/dcache.h b/include/linux/dcache.h index d7b369fc15d3..c1e48014106f 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -262,6 +262,8 @@ extern void d_tmpfile(struct dentry *, struct inode *); extern struct dentry *d_find_alias(struct inode *); extern void d_prune_aliases(struct inode *); +extern struct dentry *d_find_alias_rcu(struct inode *); + /* test whether we have any submounts in a subdir tree */ extern int path_has_submounts(const struct path *); -- cgit v1.2.3 From 7ae41220ef5831674f446baef19bfe1b31358260 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Mon, 11 Jan 2021 00:17:36 +0100 Subject: rtc: introduce features bitfield Introduce a bitfield to allow the drivers to announce the available features for an RTC. The main use case would be to better handle alarms, that could be present or not or have a minute resolution or may need a correct week day to be set. Use the newly introduced RTC_FEATURE_ALARM bit to then test whether alarms are available instead of relying on the presence of ops->set_alarm. Signed-off-by: Alexandre Belloni Link: https://lore.kernel.org/r/20210110231752.1418816-2-alexandre.belloni@bootlin.com --- drivers/rtc/class.c | 5 +++++ drivers/rtc/interface.c | 12 ++++++------ include/linux/rtc.h | 2 ++ include/uapi/linux/rtc.h | 5 +++++ 4 files changed, 18 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c index 7e470fbd5e4d..03abd0aa229a 100644 --- a/drivers/rtc/class.c +++ b/drivers/rtc/class.c @@ -231,6 +231,8 @@ static struct rtc_device *rtc_allocate_device(void) rtc->pie_timer.function = rtc_pie_update_irq; rtc->pie_enabled = 0; + set_bit(RTC_FEATURE_ALARM, rtc->features); + return rtc; } @@ -386,6 +388,9 @@ int __devm_rtc_register_device(struct module *owner, struct rtc_device *rtc) return -EINVAL; } + if (!rtc->ops->set_alarm) + clear_bit(RTC_FEATURE_ALARM, rtc->features); + rtc->owner = owner; rtc_device_get_offset(rtc); diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c index 794a4f036b99..dcb34c73319e 100644 --- a/drivers/rtc/interface.c +++ b/drivers/rtc/interface.c @@ -186,7 +186,7 @@ static int rtc_read_alarm_internal(struct rtc_device *rtc, if (!rtc->ops) { err = -ENODEV; - } else if (!rtc->ops->read_alarm) { + } else if (!test_bit(RTC_FEATURE_ALARM, rtc->features) || !rtc->ops->read_alarm) { err = -EINVAL; } else { alarm->enabled = 0; @@ -392,7 +392,7 @@ int rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm) return err; if (!rtc->ops) { err = -ENODEV; - } else if (!rtc->ops->read_alarm) { + } else if (!test_bit(RTC_FEATURE_ALARM, rtc->features) || !rtc->ops->read_alarm) { err = -EINVAL; } else { memset(alarm, 0, sizeof(struct rtc_wkalrm)); @@ -436,7 +436,7 @@ static int __rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm) if (!rtc->ops) err = -ENODEV; - else if (!rtc->ops->set_alarm) + else if (!test_bit(RTC_FEATURE_ALARM, rtc->features)) err = -EINVAL; else err = rtc->ops->set_alarm(rtc->dev.parent, alarm); @@ -451,7 +451,7 @@ int rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm) if (!rtc->ops) return -ENODEV; - else if (!rtc->ops->set_alarm) + else if (!test_bit(RTC_FEATURE_ALARM, rtc->features)) return -EINVAL; err = rtc_valid_tm(&alarm->time); @@ -531,7 +531,7 @@ int rtc_alarm_irq_enable(struct rtc_device *rtc, unsigned int enabled) /* nothing */; else if (!rtc->ops) err = -ENODEV; - else if (!rtc->ops->alarm_irq_enable) + else if (!test_bit(RTC_FEATURE_ALARM, rtc->features) || !rtc->ops->alarm_irq_enable) err = -EINVAL; else err = rtc->ops->alarm_irq_enable(rtc->dev.parent, enabled); @@ -843,7 +843,7 @@ static int rtc_timer_enqueue(struct rtc_device *rtc, struct rtc_timer *timer) static void rtc_alarm_disable(struct rtc_device *rtc) { - if (!rtc->ops || !rtc->ops->alarm_irq_enable) + if (!rtc->ops || !test_bit(RTC_FEATURE_ALARM, rtc->features) || !rtc->ops->alarm_irq_enable) return; rtc->ops->alarm_irq_enable(rtc->dev.parent, false); diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 568909449c13..bd611e26291d 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -141,6 +141,8 @@ struct rtc_device { */ unsigned long set_offset_nsec; + unsigned long features[BITS_TO_LONGS(RTC_FEATURE_CNT)]; + time64_t range_min; timeu64_t range_max; time64_t start_secs; diff --git a/include/uapi/linux/rtc.h b/include/uapi/linux/rtc.h index fa9aff91cbf2..f950bff75e97 100644 --- a/include/uapi/linux/rtc.h +++ b/include/uapi/linux/rtc.h @@ -110,6 +110,11 @@ struct rtc_pll_info { #define RTC_AF 0x20 /* Alarm interrupt */ #define RTC_UF 0x10 /* Update interrupt for 1Hz RTC */ +/* feature list */ +#define RTC_FEATURE_ALARM 0 +#define RTC_FEATURE_ALARM_RES_MINUTE 1 +#define RTC_FEATURE_NEED_WEEK_DAY 2 +#define RTC_FEATURE_CNT 3 #define RTC_MAX_FREQ 8192 -- cgit v1.2.3 From 61712a5f8271ebdbb9d34d28279b77a452db9d5c Mon Sep 17 00:00:00 2001 From: Yue Zou Date: Mon, 18 Jan 2021 01:03:55 +0000 Subject: vgaarb: Remove unneeded semicolons Remove superfluous semicolons after function definitions. Signed-off-by: Yue Zou Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210118010356.214491-1-zouyue3@huawei.com --- include/linux/vgaarb.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/vgaarb.h b/include/linux/vgaarb.h index 977caf96c8d2..fc6dfeba04a5 100644 --- a/include/linux/vgaarb.h +++ b/include/linux/vgaarb.h @@ -121,9 +121,9 @@ extern struct pci_dev *vga_default_device(void); extern void vga_set_default_device(struct pci_dev *pdev); extern int vga_remove_vgacon(struct pci_dev *pdev); #else -static inline struct pci_dev *vga_default_device(void) { return NULL; }; -static inline void vga_set_default_device(struct pci_dev *pdev) { }; -static inline int vga_remove_vgacon(struct pci_dev *pdev) { return 0; }; +static inline struct pci_dev *vga_default_device(void) { return NULL; } +static inline void vga_set_default_device(struct pci_dev *pdev) { } +static inline int vga_remove_vgacon(struct pci_dev *pdev) { return 0; } #endif /* -- cgit v1.2.3 From 72fec10c17d95bcb99371f5b29f6947e67d7493b Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Fri, 11 Dec 2020 17:29:42 +0100 Subject: drm/ttm: WARN_ON non-empty lru when disabling a resource manager MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit ttm_resource_manager->use_type is only used for runtime changes by vmwgfx. I think ideally we'd push this functionality into drivers - ttm itself does not provide any locking to guarantee this is safe, so the only way this can work at runtime is if the driver does provide additional guarantees. vwmgfx does that through the vmw_private->reservation_sem. Therefore supporting this feature in shared code feels a bit misplaced. As a first step add a WARN_ON to make sure the resource manager is empty. This is just to make sure I actually understand correctly what vmwgfx is doing, and to make sure an eventual subsequent refactor doesn't break anything. This check should also be useful for other drivers, to make sure they haven't leaked anything. Reviewed-by: Roland Scheidegger Reviewed-by: Christian König Signed-off-by: Daniel Vetter Cc: Christian Koenig Cc: Huang Rui Link: https://patchwork.freedesktop.org/patch/msgid/20201211162942.3399050-3-daniel.vetter@ffwll.ch --- include/drm/ttm/ttm_resource.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/drm/ttm/ttm_resource.h b/include/drm/ttm/ttm_resource.h index ad6da99770e9..da0ed7e8c915 100644 --- a/include/drm/ttm/ttm_resource.h +++ b/include/drm/ttm/ttm_resource.h @@ -190,6 +190,10 @@ struct ttm_resource { static inline void ttm_resource_manager_set_used(struct ttm_resource_manager *man, bool used) { + int i; + + for (i = 0; i < TTM_MAX_BO_PRIORITY; i++) + WARN_ON(!list_empty(&man->lru[i])); man->use_type = used; } -- cgit v1.2.3 From 84335675f2223cbd25d0de7d38ecc7d40b95bd4a Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Fri, 15 Jan 2021 17:47:39 +0100 Subject: dma-buf: Add debug option MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We have too many people abusing the struct page they can get at but really shouldn't in importers. Aside from that the backing page might simply not exist (for dynamic p2p mappings) looking at it and using it e.g. for mmap can also wreak the page handling of the exporter completely. Importers really must go through the proper interface like dma_buf_mmap for everything. I'm semi-tempted to enforce this for dynamic importers since those really have no excuse at all to break the rules. Unfortuantely we can't store the right pointers somewhere safe to make sure we oops on something recognizable, so best is to just wrangle them a bit by flipping all the bits. At least on x86 kernel addresses have all their high bits sets and the struct page array is fairly low in the kernel mapping, so flipping all the bits gives us a very high pointer in userspace and hence excellent chances for an invalid dereference. v2: Add a note to the @map_dma_buf hook that exporters shouldn't do fancy caching tricks, which would blow up with this address scrambling trick here (Chris) Enable by default when CONFIG_DMA_API_DEBUG is enabled. v3: Only one copy of the mangle/unmangle code (Christian) v4: #ifdef, not #if (0day) v5: sg_table can also be an ERR_PTR (Chris, Christian) Reviewed-by: Chris Wilson Reviewed-by: Christian König Signed-off-by: Daniel Vetter Cc: Chris Wilson Cc: Sumit Semwal Cc: "Christian König" Cc: David Stevens Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Link: https://patchwork.freedesktop.org/patch/msgid/20210115164739.3958206-1-daniel.vetter@ffwll.ch --- drivers/dma-buf/Kconfig | 8 ++++++++ drivers/dma-buf/dma-buf.c | 46 ++++++++++++++++++++++++++++++++++++++++++---- include/linux/dma-buf.h | 6 ++++++ 3 files changed, 56 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/dma-buf/Kconfig b/drivers/dma-buf/Kconfig index 4f8224a6ac95..4e16c71c24b7 100644 --- a/drivers/dma-buf/Kconfig +++ b/drivers/dma-buf/Kconfig @@ -50,6 +50,14 @@ config DMABUF_MOVE_NOTIFY This is marked experimental because we don't yet have a consistent execution context and memory management between drivers. +config DMABUF_DEBUG + bool "DMA-BUF debug checks" + default y if DMA_API_DEBUG + help + This option enables additional checks for DMA-BUF importers and + exporters. Specifically it validates that importers do not peek at the + underlying struct page when they import a buffer. + config DMABUF_SELFTESTS tristate "Selftests for the dma-buf interfaces" default n diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index b8465243eca2..3948b88aa123 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -653,6 +653,34 @@ void dma_buf_put(struct dma_buf *dmabuf) } EXPORT_SYMBOL_GPL(dma_buf_put); +static void mangle_sg_table(struct sg_table *sg_table) +{ +#ifdef CONFIG_DMABUF_DEBUG + int i; + struct scatterlist *sg; + + /* To catch abuse of the underlying struct page by importers mix + * up the bits, but take care to preserve the low SG_ bits to + * not corrupt the sgt. The mixing is undone in __unmap_dma_buf + * before passing the sgt back to the exporter. */ + for_each_sgtable_sg(sg_table, sg, i) + sg->page_link ^= ~0xffUL; +#endif + +} +static struct sg_table * __map_dma_buf(struct dma_buf_attachment *attach, + enum dma_data_direction direction) +{ + struct sg_table *sg_table; + + sg_table = attach->dmabuf->ops->map_dma_buf(attach, direction); + + if (!IS_ERR_OR_NULL(sg_table)) + mangle_sg_table(sg_table); + + return sg_table; +} + /** * dma_buf_dynamic_attach - Add the device to dma_buf's attachments list * @dmabuf: [in] buffer to attach device to. @@ -724,7 +752,7 @@ dma_buf_dynamic_attach(struct dma_buf *dmabuf, struct device *dev, goto err_unlock; } - sgt = dmabuf->ops->map_dma_buf(attach, DMA_BIDIRECTIONAL); + sgt = __map_dma_buf(attach, DMA_BIDIRECTIONAL); if (!sgt) sgt = ERR_PTR(-ENOMEM); if (IS_ERR(sgt)) { @@ -771,6 +799,16 @@ struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf, } EXPORT_SYMBOL_GPL(dma_buf_attach); +static void __unmap_dma_buf(struct dma_buf_attachment *attach, + struct sg_table *sg_table, + enum dma_data_direction direction) +{ + /* uses XOR, hence this unmangles */ + mangle_sg_table(sg_table); + + attach->dmabuf->ops->unmap_dma_buf(attach, sg_table, direction); +} + /** * dma_buf_detach - Remove the given attachment from dmabuf's attachments list * @dmabuf: [in] buffer to detach from. @@ -789,7 +827,7 @@ void dma_buf_detach(struct dma_buf *dmabuf, struct dma_buf_attachment *attach) if (dma_buf_is_dynamic(attach->dmabuf)) dma_resv_lock(attach->dmabuf->resv, NULL); - dmabuf->ops->unmap_dma_buf(attach, attach->sgt, attach->dir); + __unmap_dma_buf(attach, attach->sgt, attach->dir); if (dma_buf_is_dynamic(attach->dmabuf)) { dma_buf_unpin(attach); @@ -911,7 +949,7 @@ struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *attach, } } - sg_table = attach->dmabuf->ops->map_dma_buf(attach, direction); + sg_table = __map_dma_buf(attach, direction); if (!sg_table) sg_table = ERR_PTR(-ENOMEM); @@ -974,7 +1012,7 @@ void dma_buf_unmap_attachment(struct dma_buf_attachment *attach, if (dma_buf_is_dynamic(attach->dmabuf)) dma_resv_assert_held(attach->dmabuf->resv); - attach->dmabuf->ops->unmap_dma_buf(attach, sg_table, direction); + __unmap_dma_buf(attach, sg_table, direction); if (dma_buf_is_dynamic(attach->dmabuf) && !IS_ENABLED(CONFIG_DMABUF_MOVE_NOTIFY)) diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 628681bf6c99..efdc56b9d95f 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -154,6 +154,12 @@ struct dma_buf_ops { * On failure, returns a negative error value wrapped into a pointer. * May also return -EINTR when a signal was received while being * blocked. + * + * Note that exporters should not try to cache the scatter list, or + * return the same one for multiple calls. Caching is done either by the + * DMA-BUF code (for non-dynamic importers) or the importer. Ownership + * of the scatter list is transferred to the caller, and returned by + * @unmap_dma_buf. */ struct sg_table * (*map_dma_buf)(struct dma_buf_attachment *, enum dma_data_direction); -- cgit v1.2.3 From 1b399bb04837183cecdc1b32ef1cfc7fcfa75d32 Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Sun, 13 Dec 2020 23:54:46 +0000 Subject: kconfig.h: Add IF_ENABLED() macro IF_ENABLED(CONFIG_FOO, ptr) evaluates to (ptr) if CONFIG_FOO is set to 'y' or 'm', NULL otherwise. The (ptr) argument must be a pointer. The IF_ENABLED() macro can be very useful to help GCC drop dead code. For instance, consider the following: #ifdef CONFIG_FOO_SUSPEND static int foo_suspend(struct device *dev) { ... } #endif static struct pm_ops foo_ops = { #ifdef CONFIG_FOO_SUSPEND .suspend = foo_suspend, #endif }; While this works, the foo_suspend() macro is compiled conditionally, only when CONFIG_FOO_SUSPEND is set. This is problematic, as there could be a build bug in this function, we wouldn't have a way to know unless the config option is set. An alternative is to declare foo_suspend() always, but mark it as maybe unused: static int __maybe_unused foo_suspend(struct device *dev) { ... } static struct pm_ops foo_ops = { #ifdef CONFIG_FOO_SUSPEND .suspend = foo_suspend, #endif }; Again, this works, but the __maybe_unused attribute is required to instruct the compiler that the function may not be referenced anywhere, and is safe to remove without making a fuss about it. This makes the programmer responsible for tagging the functions that can be garbage-collected. With this patch, it is now possible to write the following: static int foo_suspend(struct device *dev) { ... } static struct pm_ops foo_ops = { .suspend = IF_ENABLED(CONFIG_FOO_SUSPEND, foo_suspend), }; The foo_suspend() function will now be automatically dropped by the compiler, and it does not require any specific attribute. Signed-off-by: Paul Cercueil Acked-by: Arnd Bergmann Link: https://lore.kernel.org/r/20201213235447.138271-1-paul@crapouillou.net Signed-off-by: Linus Walleij --- include/linux/kconfig.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/kconfig.h b/include/linux/kconfig.h index 9d12c970f18f..e78e17a76dc9 100644 --- a/include/linux/kconfig.h +++ b/include/linux/kconfig.h @@ -72,4 +72,10 @@ */ #define IS_ENABLED(option) __or(IS_BUILTIN(option), IS_MODULE(option)) +/* + * IF_ENABLED(CONFIG_FOO, ptr) evaluates to (ptr) if CONFIG_FOO is set to 'y' + * or 'm', NULL otherwise. + */ +#define IF_ENABLED(option, ptr) (IS_ENABLED(option) ? (ptr) : NULL) + #endif /* __LINUX_KCONFIG_H */ -- cgit v1.2.3 From b33752c300232d7f95dd9a4353947d0c9e6a0e52 Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Fri, 15 Jan 2021 09:06:37 -0800 Subject: HID: i2c-hid: Reorganize so ACPI and OF are separate modules This patch rejiggers the i2c-hid code so that the OF (Open Firmware aka Device Tree) and ACPI support is separated out a bit. The OF and ACPI drivers are now separate modules that wrap the core module. Essentially, what we're doing here: * Make "power up" and "power down" a function that can be (optionally) implemented by a given user of the i2c-hid core. * The OF and ACPI modules are drivers on their own, so they implement probe / remove / suspend / resume / shutdown. The core code provides implementations that OF and ACPI can call into. We'll organize this so that we now have 3 modules: the old i2c-hid module becomes the "core" module and two new modules will depend on it, handling probing the specific device. As part of this work, we'll remove the i2c-hid "platform data" concept since it's not needed. Signed-off-by: Douglas Anderson Reviewed-by: Hans de Goede Signed-off-by: Benjamin Tissoires --- drivers/hid/Makefile | 2 +- drivers/hid/i2c-hid/Kconfig | 32 ++++- drivers/hid/i2c-hid/Makefile | 5 +- drivers/hid/i2c-hid/i2c-hid-acpi.c | 143 +++++++++++++++++++ drivers/hid/i2c-hid/i2c-hid-core.c | 252 ++++++---------------------------- drivers/hid/i2c-hid/i2c-hid-of.c | 143 +++++++++++++++++++ drivers/hid/i2c-hid/i2c-hid.h | 22 +++ include/linux/platform_data/i2c-hid.h | 41 ------ 8 files changed, 379 insertions(+), 261 deletions(-) create mode 100644 drivers/hid/i2c-hid/i2c-hid-acpi.c create mode 100644 drivers/hid/i2c-hid/i2c-hid-of.c delete mode 100644 include/linux/platform_data/i2c-hid.h (limited to 'include') diff --git a/drivers/hid/Makefile b/drivers/hid/Makefile index 014d21fe7dac..a0621a4a65cd 100644 --- a/drivers/hid/Makefile +++ b/drivers/hid/Makefile @@ -138,7 +138,7 @@ obj-$(CONFIG_USB_HID) += usbhid/ obj-$(CONFIG_USB_MOUSE) += usbhid/ obj-$(CONFIG_USB_KBD) += usbhid/ -obj-$(CONFIG_I2C_HID) += i2c-hid/ +obj-$(CONFIG_I2C_HID_CORE) += i2c-hid/ obj-$(CONFIG_INTEL_ISH_HID) += intel-ish-hid/ obj-$(INTEL_ISH_FIRMWARE_DOWNLOADER) += intel-ish-hid/ diff --git a/drivers/hid/i2c-hid/Kconfig b/drivers/hid/i2c-hid/Kconfig index c4e5dfeab2bd..819b7521c182 100644 --- a/drivers/hid/i2c-hid/Kconfig +++ b/drivers/hid/i2c-hid/Kconfig @@ -2,18 +2,40 @@ menu "I2C HID support" depends on I2C -config I2C_HID - tristate "HID over I2C transport layer" +config I2C_HID_ACPI + tristate "HID over I2C transport layer ACPI driver" default n - depends on I2C && INPUT - select HID + depends on I2C && INPUT && ACPI + help + Say Y here if you use a keyboard, a touchpad, a touchscreen, or any + other HID based devices which is connected to your computer via I2C. + This driver supports ACPI-based systems. + + If unsure, say N. + + This support is also available as a module. If so, the module + will be called i2c-hid-acpi. It will also build/depend on the + module i2c-hid. + +config I2C_HID_OF + tristate "HID over I2C transport layer Open Firmware driver" + default n + depends on I2C && INPUT && OF help Say Y here if you use a keyboard, a touchpad, a touchscreen, or any other HID based devices which is connected to your computer via I2C. + This driver supports Open Firmware (Device Tree)-based systems. If unsure, say N. This support is also available as a module. If so, the module - will be called i2c-hid. + will be called i2c-hid-of. It will also build/depend on the + module i2c-hid. endmenu + +config I2C_HID_CORE + tristate + default y if I2C_HID_ACPI=y || I2C_HID_OF=y + default m if I2C_HID_ACPI=m || I2C_HID_OF=m + select HID diff --git a/drivers/hid/i2c-hid/Makefile b/drivers/hid/i2c-hid/Makefile index 681b3896898e..9b4a73446841 100644 --- a/drivers/hid/i2c-hid/Makefile +++ b/drivers/hid/i2c-hid/Makefile @@ -3,7 +3,10 @@ # Makefile for the I2C input drivers # -obj-$(CONFIG_I2C_HID) += i2c-hid.o +obj-$(CONFIG_I2C_HID_CORE) += i2c-hid.o i2c-hid-objs = i2c-hid-core.o i2c-hid-$(CONFIG_DMI) += i2c-hid-dmi-quirks.o + +obj-$(CONFIG_I2C_HID_ACPI) += i2c-hid-acpi.o +obj-$(CONFIG_I2C_HID_OF) += i2c-hid-of.o diff --git a/drivers/hid/i2c-hid/i2c-hid-acpi.c b/drivers/hid/i2c-hid/i2c-hid-acpi.c new file mode 100644 index 000000000000..bb8c00e6be78 --- /dev/null +++ b/drivers/hid/i2c-hid/i2c-hid-acpi.c @@ -0,0 +1,143 @@ +/* + * HID over I2C ACPI Subclass + * + * Copyright (c) 2012 Benjamin Tissoires + * Copyright (c) 2012 Ecole Nationale de l'Aviation Civile, France + * Copyright (c) 2012 Red Hat, Inc + * + * This code was forked out of the core code, which was partly based on + * "USB HID support for Linux": + * + * Copyright (c) 1999 Andreas Gal + * Copyright (c) 2000-2005 Vojtech Pavlik + * Copyright (c) 2005 Michael Haboustak for Concept2, Inc + * Copyright (c) 2007-2008 Oliver Neukum + * Copyright (c) 2006-2010 Jiri Kosina + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file COPYING in the main directory of this archive for + * more details. + */ + +#include +#include +#include +#include +#include +#include + +#include "i2c-hid.h" + +struct i2c_hid_acpi { + struct i2chid_ops ops; + struct i2c_client *client; +}; + +static const struct acpi_device_id i2c_hid_acpi_blacklist[] = { + /* + * The CHPN0001 ACPI device, which is used to describe the Chipone + * ICN8505 controller, has a _CID of PNP0C50 but is not HID compatible. + */ + {"CHPN0001", 0 }, + { }, +}; + +static int i2c_hid_acpi_get_descriptor(struct i2c_client *client) +{ + static guid_t i2c_hid_guid = + GUID_INIT(0x3CDFF6F7, 0x4267, 0x4555, + 0xAD, 0x05, 0xB3, 0x0A, 0x3D, 0x89, 0x38, 0xDE); + union acpi_object *obj; + struct acpi_device *adev; + acpi_handle handle; + u16 hid_descriptor_address; + + handle = ACPI_HANDLE(&client->dev); + if (!handle || acpi_bus_get_device(handle, &adev)) { + dev_err(&client->dev, "Error could not get ACPI device\n"); + return -ENODEV; + } + + if (acpi_match_device_ids(adev, i2c_hid_acpi_blacklist) == 0) + return -ENODEV; + + obj = acpi_evaluate_dsm_typed(handle, &i2c_hid_guid, 1, 1, NULL, + ACPI_TYPE_INTEGER); + if (!obj) { + dev_err(&client->dev, "Error _DSM call to get HID descriptor address failed\n"); + return -ENODEV; + } + + hid_descriptor_address = obj->integer.value; + ACPI_FREE(obj); + + return hid_descriptor_address; +} + +static void i2c_hid_acpi_shutdown_tail(struct i2chid_ops *ops) +{ + struct i2c_hid_acpi *ihid_acpi = + container_of(ops, struct i2c_hid_acpi, ops); + struct device *dev = &ihid_acpi->client->dev; + acpi_device_set_power(ACPI_COMPANION(dev), ACPI_STATE_D3_COLD); +} + +static int i2c_hid_acpi_probe(struct i2c_client *client, + const struct i2c_device_id *dev_id) +{ + struct device *dev = &client->dev; + struct i2c_hid_acpi *ihid_acpi; + struct acpi_device *adev; + u16 hid_descriptor_address; + int ret; + + ihid_acpi = devm_kzalloc(&client->dev, sizeof(*ihid_acpi), GFP_KERNEL); + if (!ihid_acpi) + return -ENOMEM; + + ihid_acpi->client = client; + ihid_acpi->ops.shutdown_tail = i2c_hid_acpi_shutdown_tail; + + ret = i2c_hid_acpi_get_descriptor(client); + if (ret < 0) + return ret; + hid_descriptor_address = ret; + + adev = ACPI_COMPANION(dev); + if (adev) + acpi_device_fix_up_power(adev); + + if (acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0) { + device_set_wakeup_capable(dev, true); + device_set_wakeup_enable(dev, false); + } + + return i2c_hid_core_probe(client, &ihid_acpi->ops, + hid_descriptor_address); +} + +static const struct acpi_device_id i2c_hid_acpi_match[] = { + {"ACPI0C50", 0 }, + {"PNP0C50", 0 }, + { }, +}; +MODULE_DEVICE_TABLE(acpi, i2c_hid_acpi_match); + +static struct i2c_driver i2c_hid_acpi_driver = { + .driver = { + .name = "i2c_hid_acpi", + .pm = &i2c_hid_core_pm, + .probe_type = PROBE_PREFER_ASYNCHRONOUS, + .acpi_match_table = ACPI_PTR(i2c_hid_acpi_match), + }, + + .probe = i2c_hid_acpi_probe, + .remove = i2c_hid_core_remove, + .shutdown = i2c_hid_core_shutdown, +}; + +module_i2c_driver(i2c_hid_acpi_driver); + +MODULE_DESCRIPTION("HID over I2C ACPI driver"); +MODULE_AUTHOR("Benjamin Tissoires "); +MODULE_LICENSE("GPL"); diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c index bfe716d7ea44..b64441db29a8 100644 --- a/drivers/hid/i2c-hid/i2c-hid-core.c +++ b/drivers/hid/i2c-hid/i2c-hid-core.c @@ -35,11 +35,6 @@ #include #include #include -#include -#include -#include - -#include #include "../hid-ids.h" #include "i2c-hid.h" @@ -156,10 +151,10 @@ struct i2c_hid { wait_queue_head_t wait; /* For waiting the interrupt */ - struct i2c_hid_platform_data pdata; - bool irq_wake_enabled; struct mutex reset_lock; + + struct i2chid_ops *ops; }; static const struct i2c_hid_quirks { @@ -884,144 +879,36 @@ static int i2c_hid_fetch_hid_descriptor(struct i2c_hid *ihid) return 0; } -#ifdef CONFIG_ACPI -static const struct acpi_device_id i2c_hid_acpi_blacklist[] = { - /* - * The CHPN0001 ACPI device, which is used to describe the Chipone - * ICN8505 controller, has a _CID of PNP0C50 but is not HID compatible. - */ - {"CHPN0001", 0 }, - { }, -}; - -static int i2c_hid_acpi_pdata(struct i2c_client *client, - struct i2c_hid_platform_data *pdata) -{ - static guid_t i2c_hid_guid = - GUID_INIT(0x3CDFF6F7, 0x4267, 0x4555, - 0xAD, 0x05, 0xB3, 0x0A, 0x3D, 0x89, 0x38, 0xDE); - union acpi_object *obj; - struct acpi_device *adev; - acpi_handle handle; - - handle = ACPI_HANDLE(&client->dev); - if (!handle || acpi_bus_get_device(handle, &adev)) { - dev_err(&client->dev, "Error could not get ACPI device\n"); - return -ENODEV; - } - - if (acpi_match_device_ids(adev, i2c_hid_acpi_blacklist) == 0) - return -ENODEV; - - obj = acpi_evaluate_dsm_typed(handle, &i2c_hid_guid, 1, 1, NULL, - ACPI_TYPE_INTEGER); - if (!obj) { - dev_err(&client->dev, "Error _DSM call to get HID descriptor address failed\n"); - return -ENODEV; - } - - pdata->hid_descriptor_address = obj->integer.value; - ACPI_FREE(obj); - - return 0; -} - -static void i2c_hid_acpi_fix_up_power(struct device *dev) -{ - struct acpi_device *adev; - - adev = ACPI_COMPANION(dev); - if (adev) - acpi_device_fix_up_power(adev); -} - -static void i2c_hid_acpi_enable_wakeup(struct device *dev) -{ - if (acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0) { - device_set_wakeup_capable(dev, true); - device_set_wakeup_enable(dev, false); - } -} - -static void i2c_hid_acpi_shutdown(struct device *dev) +static int i2c_hid_core_power_up(struct i2c_hid *ihid) { - acpi_device_set_power(ACPI_COMPANION(dev), ACPI_STATE_D3_COLD); -} + if (!ihid->ops->power_up) + return 0; -static const struct acpi_device_id i2c_hid_acpi_match[] = { - {"ACPI0C50", 0 }, - {"PNP0C50", 0 }, - { }, -}; -MODULE_DEVICE_TABLE(acpi, i2c_hid_acpi_match); -#else -static inline int i2c_hid_acpi_pdata(struct i2c_client *client, - struct i2c_hid_platform_data *pdata) -{ - return -ENODEV; + return ihid->ops->power_up(ihid->ops); } -static inline void i2c_hid_acpi_fix_up_power(struct device *dev) {} - -static inline void i2c_hid_acpi_enable_wakeup(struct device *dev) {} - -static inline void i2c_hid_acpi_shutdown(struct device *dev) {} -#endif - -#ifdef CONFIG_OF -static int i2c_hid_of_probe(struct i2c_client *client, - struct i2c_hid_platform_data *pdata) +static void i2c_hid_core_power_down(struct i2c_hid *ihid) { - struct device *dev = &client->dev; - u32 val; - int ret; - - ret = of_property_read_u32(dev->of_node, "hid-descr-addr", &val); - if (ret) { - dev_err(&client->dev, "HID register address not provided\n"); - return -ENODEV; - } - if (val >> 16) { - dev_err(&client->dev, "Bad HID register address: 0x%08x\n", - val); - return -EINVAL; - } - pdata->hid_descriptor_address = val; - - return 0; -} + if (!ihid->ops->power_down) + return; -static const struct of_device_id i2c_hid_of_match[] = { - { .compatible = "hid-over-i2c" }, - {}, -}; -MODULE_DEVICE_TABLE(of, i2c_hid_of_match); -#else -static inline int i2c_hid_of_probe(struct i2c_client *client, - struct i2c_hid_platform_data *pdata) -{ - return -ENODEV; + ihid->ops->power_down(ihid->ops); } -#endif -static void i2c_hid_fwnode_probe(struct i2c_client *client, - struct i2c_hid_platform_data *pdata) +static void i2c_hid_core_shutdown_tail(struct i2c_hid *ihid) { - u32 val; + if (!ihid->ops->shutdown_tail) + return; - if (!device_property_read_u32(&client->dev, "post-power-on-delay-ms", - &val)) - pdata->post_power_delay_ms = val; + ihid->ops->shutdown_tail(ihid->ops); } -static int i2c_hid_probe(struct i2c_client *client, - const struct i2c_device_id *dev_id) +int i2c_hid_core_probe(struct i2c_client *client, struct i2chid_ops *ops, + u16 hid_descriptor_address) { int ret; struct i2c_hid *ihid; struct hid_device *hid; - __u16 hidRegister; - struct i2c_hid_platform_data *platform_data = client->dev.platform_data; dbg_hid("HID probe called for i2c 0x%02x\n", client->addr); @@ -1042,44 +929,17 @@ static int i2c_hid_probe(struct i2c_client *client, if (!ihid) return -ENOMEM; - if (client->dev.of_node) { - ret = i2c_hid_of_probe(client, &ihid->pdata); - if (ret) - return ret; - } else if (!platform_data) { - ret = i2c_hid_acpi_pdata(client, &ihid->pdata); - if (ret) - return ret; - } else { - ihid->pdata = *platform_data; - } - - /* Parse platform agnostic common properties from ACPI / device tree */ - i2c_hid_fwnode_probe(client, &ihid->pdata); - - ihid->pdata.supplies[0].supply = "vdd"; - ihid->pdata.supplies[1].supply = "vddl"; + ihid->ops = ops; - ret = devm_regulator_bulk_get(&client->dev, - ARRAY_SIZE(ihid->pdata.supplies), - ihid->pdata.supplies); + ret = i2c_hid_core_power_up(ihid); if (ret) return ret; - ret = regulator_bulk_enable(ARRAY_SIZE(ihid->pdata.supplies), - ihid->pdata.supplies); - if (ret < 0) - return ret; - - if (ihid->pdata.post_power_delay_ms) - msleep(ihid->pdata.post_power_delay_ms); - i2c_set_clientdata(client, ihid); ihid->client = client; - hidRegister = ihid->pdata.hid_descriptor_address; - ihid->wHIDDescRegister = cpu_to_le16(hidRegister); + ihid->wHIDDescRegister = cpu_to_le16(hid_descriptor_address); init_waitqueue_head(&ihid->wait); mutex_init(&ihid->reset_lock); @@ -1089,11 +949,7 @@ static int i2c_hid_probe(struct i2c_client *client, * real computation later. */ ret = i2c_hid_alloc_buffers(ihid, HID_MIN_BUFFER_SIZE); if (ret < 0) - goto err_regulator; - - i2c_hid_acpi_fix_up_power(&client->dev); - - i2c_hid_acpi_enable_wakeup(&client->dev); + goto err_powered; device_enable_async_suspend(&client->dev); @@ -1102,19 +958,19 @@ static int i2c_hid_probe(struct i2c_client *client, if (ret < 0) { dev_dbg(&client->dev, "nothing at this address: %d\n", ret); ret = -ENXIO; - goto err_regulator; + goto err_powered; } ret = i2c_hid_fetch_hid_descriptor(ihid); if (ret < 0) { dev_err(&client->dev, "Failed to fetch the HID Descriptor\n"); - goto err_regulator; + goto err_powered; } ret = i2c_hid_init_irq(client); if (ret < 0) - goto err_regulator; + goto err_powered; hid = hid_allocate_device(); if (IS_ERR(hid)) { @@ -1153,14 +1009,14 @@ err_mem_free: err_irq: free_irq(client->irq, ihid); -err_regulator: - regulator_bulk_disable(ARRAY_SIZE(ihid->pdata.supplies), - ihid->pdata.supplies); +err_powered: + i2c_hid_core_power_down(ihid); i2c_hid_free_buffers(ihid); return ret; } +EXPORT_SYMBOL_GPL(i2c_hid_core_probe); -static int i2c_hid_remove(struct i2c_client *client) +int i2c_hid_core_remove(struct i2c_client *client) { struct i2c_hid *ihid = i2c_get_clientdata(client); struct hid_device *hid; @@ -1173,24 +1029,25 @@ static int i2c_hid_remove(struct i2c_client *client) if (ihid->bufsize) i2c_hid_free_buffers(ihid); - regulator_bulk_disable(ARRAY_SIZE(ihid->pdata.supplies), - ihid->pdata.supplies); + i2c_hid_core_power_down(ihid); return 0; } +EXPORT_SYMBOL_GPL(i2c_hid_core_remove); -static void i2c_hid_shutdown(struct i2c_client *client) +void i2c_hid_core_shutdown(struct i2c_client *client) { struct i2c_hid *ihid = i2c_get_clientdata(client); i2c_hid_set_power(client, I2C_HID_PWR_SLEEP); free_irq(client->irq, ihid); - i2c_hid_acpi_shutdown(&client->dev); + i2c_hid_core_shutdown_tail(ihid); } +EXPORT_SYMBOL_GPL(i2c_hid_core_shutdown); #ifdef CONFIG_PM_SLEEP -static int i2c_hid_suspend(struct device *dev) +static int i2c_hid_core_suspend(struct device *dev) { struct i2c_client *client = to_i2c_client(dev); struct i2c_hid *ihid = i2c_get_clientdata(client); @@ -1217,14 +1074,13 @@ static int i2c_hid_suspend(struct device *dev) hid_warn(hid, "Failed to enable irq wake: %d\n", wake_status); } else { - regulator_bulk_disable(ARRAY_SIZE(ihid->pdata.supplies), - ihid->pdata.supplies); + i2c_hid_core_power_down(ihid); } return 0; } -static int i2c_hid_resume(struct device *dev) +static int i2c_hid_core_resume(struct device *dev) { int ret; struct i2c_client *client = to_i2c_client(dev); @@ -1233,13 +1089,7 @@ static int i2c_hid_resume(struct device *dev) int wake_status; if (!device_may_wakeup(&client->dev)) { - ret = regulator_bulk_enable(ARRAY_SIZE(ihid->pdata.supplies), - ihid->pdata.supplies); - if (ret) - hid_warn(hid, "Failed to enable supplies: %d\n", ret); - - if (ihid->pdata.post_power_delay_ms) - msleep(ihid->pdata.post_power_delay_ms); + i2c_hid_core_power_up(ihid); } else if (ihid->irq_wake_enabled) { wake_status = disable_irq_wake(client->irq); if (!wake_status) @@ -1276,34 +1126,10 @@ static int i2c_hid_resume(struct device *dev) } #endif -static const struct dev_pm_ops i2c_hid_pm = { - SET_SYSTEM_SLEEP_PM_OPS(i2c_hid_suspend, i2c_hid_resume) +const struct dev_pm_ops i2c_hid_core_pm = { + SET_SYSTEM_SLEEP_PM_OPS(i2c_hid_core_suspend, i2c_hid_core_resume) }; - -static const struct i2c_device_id i2c_hid_id_table[] = { - { "hid", 0 }, - { "hid-over-i2c", 0 }, - { }, -}; -MODULE_DEVICE_TABLE(i2c, i2c_hid_id_table); - - -static struct i2c_driver i2c_hid_driver = { - .driver = { - .name = "i2c_hid", - .pm = &i2c_hid_pm, - .probe_type = PROBE_PREFER_ASYNCHRONOUS, - .acpi_match_table = ACPI_PTR(i2c_hid_acpi_match), - .of_match_table = of_match_ptr(i2c_hid_of_match), - }, - - .probe = i2c_hid_probe, - .remove = i2c_hid_remove, - .shutdown = i2c_hid_shutdown, - .id_table = i2c_hid_id_table, -}; - -module_i2c_driver(i2c_hid_driver); +EXPORT_SYMBOL_GPL(i2c_hid_core_pm); MODULE_DESCRIPTION("HID over I2C core driver"); MODULE_AUTHOR("Benjamin Tissoires "); diff --git a/drivers/hid/i2c-hid/i2c-hid-of.c b/drivers/hid/i2c-hid/i2c-hid-of.c new file mode 100644 index 000000000000..4bf7cea92637 --- /dev/null +++ b/drivers/hid/i2c-hid/i2c-hid-of.c @@ -0,0 +1,143 @@ +/* + * HID over I2C Open Firmware Subclass + * + * Copyright (c) 2012 Benjamin Tissoires + * Copyright (c) 2012 Ecole Nationale de l'Aviation Civile, France + * Copyright (c) 2012 Red Hat, Inc + * + * This code was forked out of the core code, which was partly based on + * "USB HID support for Linux": + * + * Copyright (c) 1999 Andreas Gal + * Copyright (c) 2000-2005 Vojtech Pavlik + * Copyright (c) 2005 Michael Haboustak for Concept2, Inc + * Copyright (c) 2007-2008 Oliver Neukum + * Copyright (c) 2006-2010 Jiri Kosina + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file COPYING in the main directory of this archive for + * more details. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include "i2c-hid.h" + +struct i2c_hid_of { + struct i2chid_ops ops; + + struct i2c_client *client; + struct regulator_bulk_data supplies[2]; + int post_power_delay_ms; +}; + +static int i2c_hid_of_power_up(struct i2chid_ops *ops) +{ + struct i2c_hid_of *ihid_of = container_of(ops, struct i2c_hid_of, ops); + struct device *dev = &ihid_of->client->dev; + int ret; + + ret = regulator_bulk_enable(ARRAY_SIZE(ihid_of->supplies), + ihid_of->supplies); + if (ret) { + dev_warn(dev, "Failed to enable supplies: %d\n", ret); + return ret; + } + + if (ihid_of->post_power_delay_ms) + msleep(ihid_of->post_power_delay_ms); + + return 0; +} + +static void i2c_hid_of_power_down(struct i2chid_ops *ops) +{ + struct i2c_hid_of *ihid_of = container_of(ops, struct i2c_hid_of, ops); + + regulator_bulk_disable(ARRAY_SIZE(ihid_of->supplies), + ihid_of->supplies); +} + +static int i2c_hid_of_probe(struct i2c_client *client, + const struct i2c_device_id *dev_id) +{ + struct device *dev = &client->dev; + struct i2c_hid_of *ihid_of; + u16 hid_descriptor_address; + int ret; + u32 val; + + ihid_of = devm_kzalloc(&client->dev, sizeof(*ihid_of), GFP_KERNEL); + if (!ihid_of) + return -ENOMEM; + + ihid_of->ops.power_up = i2c_hid_of_power_up; + ihid_of->ops.power_down = i2c_hid_of_power_down; + + ret = of_property_read_u32(dev->of_node, "hid-descr-addr", &val); + if (ret) { + dev_err(&client->dev, "HID register address not provided\n"); + return -ENODEV; + } + if (val >> 16) { + dev_err(&client->dev, "Bad HID register address: 0x%08x\n", + val); + return -EINVAL; + } + hid_descriptor_address = val; + + if (!device_property_read_u32(&client->dev, "post-power-on-delay-ms", + &val)) + ihid_of->post_power_delay_ms = val; + + ihid_of->supplies[0].supply = "vdd"; + ihid_of->supplies[1].supply = "vddl"; + ret = devm_regulator_bulk_get(&client->dev, + ARRAY_SIZE(ihid_of->supplies), + ihid_of->supplies); + if (ret) + return ret; + + return i2c_hid_core_probe(client, &ihid_of->ops, + hid_descriptor_address); +} + +static const struct of_device_id i2c_hid_of_match[] = { + { .compatible = "hid-over-i2c" }, + {}, +}; +MODULE_DEVICE_TABLE(of, i2c_hid_of_match); + +static const struct i2c_device_id i2c_hid_of_id_table[] = { + { "hid", 0 }, + { "hid-over-i2c", 0 }, + { }, +}; +MODULE_DEVICE_TABLE(i2c, i2c_hid_of_id_table); + +static struct i2c_driver i2c_hid_of_driver = { + .driver = { + .name = "i2c_hid_of", + .pm = &i2c_hid_core_pm, + .probe_type = PROBE_PREFER_ASYNCHRONOUS, + .of_match_table = of_match_ptr(i2c_hid_of_match), + }, + + .probe = i2c_hid_of_probe, + .remove = i2c_hid_core_remove, + .shutdown = i2c_hid_core_shutdown, + .id_table = i2c_hid_of_id_table, +}; + +module_i2c_driver(i2c_hid_of_driver); + +MODULE_DESCRIPTION("HID over I2C OF driver"); +MODULE_AUTHOR("Benjamin Tissoires "); +MODULE_LICENSE("GPL"); diff --git a/drivers/hid/i2c-hid/i2c-hid.h b/drivers/hid/i2c-hid/i2c-hid.h index a8c19aef5824..05a7827d211a 100644 --- a/drivers/hid/i2c-hid/i2c-hid.h +++ b/drivers/hid/i2c-hid/i2c-hid.h @@ -3,6 +3,7 @@ #ifndef I2C_HID_H #define I2C_HID_H +#include #ifdef CONFIG_DMI struct i2c_hid_desc *i2c_hid_get_dmi_i2c_hid_desc_override(uint8_t *i2c_name); @@ -17,4 +18,25 @@ static inline char *i2c_hid_get_dmi_hid_report_desc_override(uint8_t *i2c_name, { return NULL; } #endif +/** + * struct i2chid_ops - Ops provided to the core. + * + * @power_up: do sequencing to power up the device. + * @power_down: do sequencing to power down the device. + * @shutdown_tail: called at the end of shutdown. + */ +struct i2chid_ops { + int (*power_up)(struct i2chid_ops *ops); + void (*power_down)(struct i2chid_ops *ops); + void (*shutdown_tail)(struct i2chid_ops *ops); +}; + +int i2c_hid_core_probe(struct i2c_client *client, struct i2chid_ops *ops, + u16 hid_descriptor_address); +int i2c_hid_core_remove(struct i2c_client *client); + +void i2c_hid_core_shutdown(struct i2c_client *client); + +extern const struct dev_pm_ops i2c_hid_core_pm; + #endif diff --git a/include/linux/platform_data/i2c-hid.h b/include/linux/platform_data/i2c-hid.h deleted file mode 100644 index c628bb5e1061..000000000000 --- a/include/linux/platform_data/i2c-hid.h +++ /dev/null @@ -1,41 +0,0 @@ -/* - * HID over I2C protocol implementation - * - * Copyright (c) 2012 Benjamin Tissoires - * Copyright (c) 2012 Ecole Nationale de l'Aviation Civile, France - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file COPYING in the main directory of this archive for - * more details. - */ - -#ifndef __LINUX_I2C_HID_H -#define __LINUX_I2C_HID_H - -#include -#include - -/** - * struct i2chid_platform_data - used by hid over i2c implementation. - * @hid_descriptor_address: i2c register where the HID descriptor is stored. - * @supplies: regulators for powering on the device. - * @post_power_delay_ms: delay after powering on before device is usable. - * - * Note that it is the responsibility of the platform driver (or the acpi 5.0 - * driver, or the flattened device tree) to setup the irq related to the gpio in - * the struct i2c_board_info. - * The platform driver should also setup the gpio according to the device: - * - * A typical example is the following: - * irq = gpio_to_irq(intr_gpio); - * hkdk4412_i2c_devs5[0].irq = irq; // store the irq in i2c_board_info - * gpio_request(intr_gpio, "elan-irq"); - * s3c_gpio_setpull(intr_gpio, S3C_GPIO_PULL_UP); - */ -struct i2c_hid_platform_data { - u16 hid_descriptor_address; - struct regulator_bulk_data supplies[2]; - int post_power_delay_ms; -}; - -#endif /* __LINUX_I2C_HID_H */ -- cgit v1.2.3 From 33eb12f2966ef9c529ce7138711a9c150a17931e Mon Sep 17 00:00:00 2001 From: Patrisious Haddad Date: Wed, 30 Dec 2020 15:02:40 +0200 Subject: RDMA/nldev: Return an error message on failure to turn auto mode The bounded counter can't be reconfigured to be in auto mode, in attempt to do it, the user will get an error, but without any hint why. Update nldev interface to return an error message through extack mechanism. Link: https://lore.kernel.org/r/20201230130240.180737-1-leon@kernel.org Signed-off-by: Patrisious Haddad Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/counters.c | 62 ++++++++++++++++++++------------------ drivers/infiniband/core/nldev.c | 4 +-- include/rdma/rdma_counter.h | 3 +- 3 files changed, 36 insertions(+), 33 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/core/counters.c b/drivers/infiniband/core/counters.c index 92745522250e..2b9a1ee7a160 100644 --- a/drivers/infiniband/core/counters.c +++ b/drivers/infiniband/core/counters.c @@ -10,30 +10,35 @@ #define ALL_AUTO_MODE_MASKS (RDMA_COUNTER_MASK_QP_TYPE | RDMA_COUNTER_MASK_PID) -static int __counter_set_mode(struct rdma_counter_mode *curr, +static int __counter_set_mode(struct rdma_port_counter *port_counter, enum rdma_nl_counter_mode new_mode, enum rdma_nl_counter_mask new_mask) { - if ((new_mode == RDMA_COUNTER_MODE_AUTO) && - ((new_mask & (~ALL_AUTO_MODE_MASKS)) || - (curr->mode != RDMA_COUNTER_MODE_NONE))) - return -EINVAL; + if (new_mode == RDMA_COUNTER_MODE_AUTO && port_counter->num_counters) + if (new_mask & ~ALL_AUTO_MODE_MASKS || + port_counter->mode.mode != RDMA_COUNTER_MODE_NONE) + return -EINVAL; - curr->mode = new_mode; - curr->mask = new_mask; + port_counter->mode.mode = new_mode; + port_counter->mode.mask = new_mask; return 0; } /** * rdma_counter_set_auto_mode() - Turn on/off per-port auto mode * - * When @on is true, the @mask must be set; When @on is false, it goes - * into manual mode if there's any counter, so that the user is able to - * manually access them. + * @dev: Device to operate + * @port: Port to use + * @mask: Mask to configure + * @extack: Message to the user + * + * Return 0 on success. */ int rdma_counter_set_auto_mode(struct ib_device *dev, u8 port, - bool on, enum rdma_nl_counter_mask mask) + enum rdma_nl_counter_mask mask, + struct netlink_ext_ack *extack) { + enum rdma_nl_counter_mode mode = RDMA_COUNTER_MODE_AUTO; struct rdma_port_counter *port_counter; int ret; @@ -42,23 +47,23 @@ int rdma_counter_set_auto_mode(struct ib_device *dev, u8 port, return -EOPNOTSUPP; mutex_lock(&port_counter->lock); - if (on) { - ret = __counter_set_mode(&port_counter->mode, - RDMA_COUNTER_MODE_AUTO, mask); - } else { - if (port_counter->mode.mode != RDMA_COUNTER_MODE_AUTO) { - ret = -EINVAL; - goto out; - } + if (mask) { + ret = __counter_set_mode(port_counter, mode, mask); + if (ret) + NL_SET_ERR_MSG( + extack, + "Turning on auto mode is not allowed when there is bound QP"); + goto out; + } - if (port_counter->num_counters) - ret = __counter_set_mode(&port_counter->mode, - RDMA_COUNTER_MODE_MANUAL, 0); - else - ret = __counter_set_mode(&port_counter->mode, - RDMA_COUNTER_MODE_NONE, 0); + if (port_counter->mode.mode != RDMA_COUNTER_MODE_AUTO) { + ret = -EINVAL; + goto out; } + mode = (port_counter->num_counters) ? RDMA_COUNTER_MODE_MANUAL : + RDMA_COUNTER_MODE_NONE; + ret = __counter_set_mode(port_counter, mode, 0); out: mutex_unlock(&port_counter->lock); return ret; @@ -122,8 +127,8 @@ static struct rdma_counter *alloc_and_bind(struct ib_device *dev, u8 port, mutex_lock(&port_counter->lock); switch (mode) { case RDMA_COUNTER_MODE_MANUAL: - ret = __counter_set_mode(&port_counter->mode, - RDMA_COUNTER_MODE_MANUAL, 0); + ret = __counter_set_mode(port_counter, RDMA_COUNTER_MODE_MANUAL, + 0); if (ret) { mutex_unlock(&port_counter->lock); goto err_mode; @@ -170,8 +175,7 @@ static void rdma_counter_free(struct rdma_counter *counter) port_counter->num_counters--; if (!port_counter->num_counters && (port_counter->mode.mode == RDMA_COUNTER_MODE_MANUAL)) - __counter_set_mode(&port_counter->mode, RDMA_COUNTER_MODE_NONE, - 0); + __counter_set_mode(port_counter, RDMA_COUNTER_MODE_NONE, 0); mutex_unlock(&port_counter->lock); diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c index 08366e254b1d..d306049c22a2 100644 --- a/drivers/infiniband/core/nldev.c +++ b/drivers/infiniband/core/nldev.c @@ -1768,9 +1768,7 @@ static int nldev_stat_set_doit(struct sk_buff *skb, struct nlmsghdr *nlh, if (tb[RDMA_NLDEV_ATTR_STAT_AUTO_MODE_MASK]) mask = nla_get_u32( tb[RDMA_NLDEV_ATTR_STAT_AUTO_MODE_MASK]); - - ret = rdma_counter_set_auto_mode(device, port, - mask ? true : false, mask); + ret = rdma_counter_set_auto_mode(device, port, mask, extack); if (ret) goto err_msg; } else { diff --git a/include/rdma/rdma_counter.h b/include/rdma/rdma_counter.h index eb99856e8b30..e75cf9742e04 100644 --- a/include/rdma/rdma_counter.h +++ b/include/rdma/rdma_counter.h @@ -46,7 +46,8 @@ struct rdma_counter { void rdma_counter_init(struct ib_device *dev); void rdma_counter_release(struct ib_device *dev); int rdma_counter_set_auto_mode(struct ib_device *dev, u8 port, - bool on, enum rdma_nl_counter_mask mask); + enum rdma_nl_counter_mask mask, + struct netlink_ext_ack *extack); int rdma_counter_bind_qp_auto(struct ib_qp *qp, u8 port); int rdma_counter_unbind_qp(struct ib_qp *qp, bool force); -- cgit v1.2.3 From 0627cc334d408953c0ff9ef8731325c2d02572ed Mon Sep 17 00:00:00 2001 From: Yue Zou Date: Mon, 18 Jan 2021 01:01:37 +0000 Subject: sony-laptop: Remove unneeded semicolon Remove a superfluous semicolon after function definition. Signed-off-by: Yue Zou Link: https://lore.kernel.org/r/20210118010137.214378-1-zouyue3@huawei.com Signed-off-by: Hans de Goede --- include/linux/sony-laptop.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sony-laptop.h b/include/linux/sony-laptop.h index 374d0fdb0743..1e3c92feea6e 100644 --- a/include/linux/sony-laptop.h +++ b/include/linux/sony-laptop.h @@ -31,7 +31,7 @@ #if IS_ENABLED(CONFIG_SONY_LAPTOP) int sony_pic_camera_command(int command, u8 value); #else -static inline int sony_pic_camera_command(int command, u8 value) { return 0; }; +static inline int sony_pic_camera_command(int command, u8 value) { return 0; } #endif #endif /* __KERNEL__ */ -- cgit v1.2.3 From 93e86295f5e9238779096fa599c3804a08e25bd1 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Mon, 18 Jan 2021 00:04:55 -0800 Subject: workqueue: fix annotation for WQ_SYSFS 'wq_sysfs_register()' in annotation for 'WQ_SYSFS' is unavailable, change it to 'workqueue_sysfs_register()'. Signed-off-by: Menglong Dong Reviewed-by: Lai Jiangshan Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 26de0cae2a0a..d15a7730ee18 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -311,7 +311,7 @@ enum { WQ_MEM_RECLAIM = 1 << 3, /* may be used for memory reclaim */ WQ_HIGHPRI = 1 << 4, /* high priority */ WQ_CPU_INTENSIVE = 1 << 5, /* cpu intensive workqueue */ - WQ_SYSFS = 1 << 6, /* visible in sysfs, see wq_sysfs_register() */ + WQ_SYSFS = 1 << 6, /* visible in sysfs, see workqueue_sysfs_register() */ /* * Per-cpu workqueues are generally preferred because they tend to -- cgit v1.2.3 From 7bf9c4a88e3e33cf593b2452776361c6db0f28b0 Mon Sep 17 00:00:00 2001 From: Zqiang Date: Mon, 4 Jan 2021 20:43:06 +0800 Subject: workqueue: tracing the name of the workqueue instead of it's address This patch tracing workqueue name instead of it's address, the new format is as follows. workqueue_queue_work: work struct=0000000084e3df56 function= drm_fb_helper_dirty_work workqueue=events req_cpu=256 cpu=1 This tell us to know which workqueue our work is queued. Signed-off-by: Zqiang Signed-off-by: Tejun Heo --- include/trace/events/workqueue.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/trace/events/workqueue.h b/include/trace/events/workqueue.h index 9b8ae961acc5..970cc2ea2850 100644 --- a/include/trace/events/workqueue.h +++ b/include/trace/events/workqueue.h @@ -30,7 +30,7 @@ TRACE_EVENT(workqueue_queue_work, TP_STRUCT__entry( __field( void *, work ) __field( void *, function) - __field( void *, workqueue) + __field( const char *, workqueue) __field( unsigned int, req_cpu ) __field( unsigned int, cpu ) ), @@ -38,12 +38,12 @@ TRACE_EVENT(workqueue_queue_work, TP_fast_assign( __entry->work = work; __entry->function = work->func; - __entry->workqueue = pwq->wq; + __entry->workqueue = pwq->wq->name; __entry->req_cpu = req_cpu; __entry->cpu = pwq->pool->cpu; ), - TP_printk("work struct=%p function=%ps workqueue=%p req_cpu=%u cpu=%u", + TP_printk("work struct=%p function=%ps workqueue=%s req_cpu=%u cpu=%u", __entry->work, __entry->function, __entry->workqueue, __entry->req_cpu, __entry->cpu) ); -- cgit v1.2.3 From 7c553f8b5a7dcf45f7a06da23b45e431aafbbdba Mon Sep 17 00:00:00 2001 From: Lyude Paul Date: Tue, 15 Sep 2020 12:49:13 -0400 Subject: drm/dp: Revert "drm/dp: Introduce EDID-based quirks" This reverts commit 0883ce8146ed6074c76399f4e70dbed788582e12. Originally these quirks were added because of the issues with using the eDP backlight interfaces on certain laptop panels, which made it impossible to properly probe for DPCD backlight support without having a whitelist for panels that we know have working VESA backlight control interfaces over DPCD. As well, it should be noted it was impossible to use the normal sink OUI for recognizing these panels as none of them actually filled out their OUIs, hence needing to resort to checking EDIDs. At the time we weren't really sure why certain panels had issues with DPCD backlight controls, but we eventually figured out that there was a second interface that these problematic laptop panels actually did work with and advertise properly: Intel's proprietary backlight interface for HDR panels. So far the testing we've done hasn't brought any panels to light that advertise this interface and don't support it properly, which means we finally have a real solution to this problem. As a result, we now have no need for the force DPCD backlight quirk, and furthermore this also removes the need for any kind of EDID quirk checking in DRM. So, let's just revert it for now since we were the only driver using this. v3: * Rebase v2: * Fix indenting error picked up by checkpatch in intel_edp_init_connector() Signed-off-by: Lyude Paul Acked-by: Jani Nikula Cc: thaytan@noraisin.net Cc: Vasily Khoruzhick Link: https://patchwork.freedesktop.org/patch/msgid/20210114221709.2261452-6-lyude@redhat.com --- drivers/gpu/drm/drm_dp_helper.c | 83 +--------------------- drivers/gpu/drm/drm_dp_mst_topology.c | 3 +- drivers/gpu/drm/i915/display/intel_display_types.h | 1 - drivers/gpu/drm/i915/display/intel_dp.c | 9 +-- drivers/gpu/drm/i915/display/intel_dp_mst.c | 3 +- drivers/gpu/drm/i915/display/intel_psr.c | 2 +- include/drm/drm_dp_helper.h | 21 +----- 7 files changed, 9 insertions(+), 113 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c index 3ecde451f523..19dbdeb581cb 100644 --- a/drivers/gpu/drm/drm_dp_helper.c +++ b/drivers/gpu/drm/drm_dp_helper.c @@ -1236,7 +1236,7 @@ bool drm_dp_read_sink_count_cap(struct drm_connector *connector, return connector->connector_type != DRM_MODE_CONNECTOR_eDP && dpcd[DP_DPCD_REV] >= DP_DPCD_REV_11 && dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DWN_STRM_PORT_PRESENT && - !drm_dp_has_quirk(desc, 0, DP_DPCD_QUIRK_NO_SINK_COUNT); + !drm_dp_has_quirk(desc, DP_DPCD_QUIRK_NO_SINK_COUNT); } EXPORT_SYMBOL(drm_dp_read_sink_count_cap); @@ -1957,87 +1957,6 @@ drm_dp_get_quirks(const struct drm_dp_dpcd_ident *ident, bool is_branch) #undef DEVICE_ID_ANY #undef DEVICE_ID -struct edid_quirk { - u8 mfg_id[2]; - u8 prod_id[2]; - u32 quirks; -}; - -#define MFG(first, second) { (first), (second) } -#define PROD_ID(first, second) { (first), (second) } - -/* - * Some devices have unreliable OUIDs where they don't set the device ID - * correctly, and as a result we need to use the EDID for finding additional - * DP quirks in such cases. - */ -static const struct edid_quirk edid_quirk_list[] = { - /* Optional 4K AMOLED panel in the ThinkPad X1 Extreme 2nd Generation - * only supports DPCD backlight controls - */ - { MFG(0x4c, 0x83), PROD_ID(0x41, 0x41), BIT(DP_QUIRK_FORCE_DPCD_BACKLIGHT) }, - /* - * Some Dell CML 2020 systems have panels support both AUX and PWM - * backlight control, and some only support AUX backlight control. All - * said panels start up in AUX mode by default, and we don't have any - * support for disabling HDR mode on these panels which would be - * required to switch to PWM backlight control mode (plus, I'm not - * even sure we want PWM backlight controls over DPCD backlight - * controls anyway...). Until we have a better way of detecting these, - * force DPCD backlight mode on all of them. - */ - { MFG(0x06, 0xaf), PROD_ID(0x9b, 0x32), BIT(DP_QUIRK_FORCE_DPCD_BACKLIGHT) }, - { MFG(0x06, 0xaf), PROD_ID(0xeb, 0x41), BIT(DP_QUIRK_FORCE_DPCD_BACKLIGHT) }, - { MFG(0x4d, 0x10), PROD_ID(0xc7, 0x14), BIT(DP_QUIRK_FORCE_DPCD_BACKLIGHT) }, - { MFG(0x4d, 0x10), PROD_ID(0xe6, 0x14), BIT(DP_QUIRK_FORCE_DPCD_BACKLIGHT) }, - { MFG(0x4c, 0x83), PROD_ID(0x47, 0x41), BIT(DP_QUIRK_FORCE_DPCD_BACKLIGHT) }, - { MFG(0x09, 0xe5), PROD_ID(0xde, 0x08), BIT(DP_QUIRK_FORCE_DPCD_BACKLIGHT) }, -}; - -#undef MFG -#undef PROD_ID - -/** - * drm_dp_get_edid_quirks() - Check the EDID of a DP device to find additional - * DP-specific quirks - * @edid: The EDID to check - * - * While OUIDs are meant to be used to recognize a DisplayPort device, a lot - * of manufacturers don't seem to like following standards and neglect to fill - * the dev-ID in, making it impossible to only use OUIDs for determining - * quirks in some cases. This function can be used to check the EDID and look - * up any additional DP quirks. The bits returned by this function correspond - * to the quirk bits in &drm_dp_quirk. - * - * Returns: a bitmask of quirks, if any. The driver can check this using - * drm_dp_has_quirk(). - */ -u32 drm_dp_get_edid_quirks(const struct edid *edid) -{ - const struct edid_quirk *quirk; - u32 quirks = 0; - int i; - - if (!edid) - return 0; - - for (i = 0; i < ARRAY_SIZE(edid_quirk_list); i++) { - quirk = &edid_quirk_list[i]; - if (memcmp(quirk->mfg_id, edid->mfg_id, - sizeof(edid->mfg_id)) == 0 && - memcmp(quirk->prod_id, edid->prod_code, - sizeof(edid->prod_code)) == 0) - quirks |= quirk->quirks; - } - - DRM_DEBUG_KMS("DP sink: EDID mfg %*phD prod-ID %*phD quirks: 0x%04x\n", - (int)sizeof(edid->mfg_id), edid->mfg_id, - (int)sizeof(edid->prod_code), edid->prod_code, quirks); - - return quirks; -} -EXPORT_SYMBOL(drm_dp_get_edid_quirks); - /** * drm_dp_read_desc - read sink/branch descriptor from DPCD * @aux: DisplayPort AUX channel diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index 0401b2f47500..a2e692a0c6c2 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -5824,8 +5824,7 @@ struct drm_dp_aux *drm_dp_mst_dsc_aux_for_port(struct drm_dp_mst_port *port) if (drm_dp_read_desc(port->mgr->aux, &desc, true)) return NULL; - if (drm_dp_has_quirk(&desc, 0, - DP_DPCD_QUIRK_DSC_WITHOUT_VIRTUAL_DPCD) && + if (drm_dp_has_quirk(&desc, DP_DPCD_QUIRK_DSC_WITHOUT_VIRTUAL_DPCD) && port->mgr->dpcd[DP_DPCD_REV] >= DP_DPCD_REV_14 && port->parent == port->mgr->mst_primary) { u8 downstreamport; diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h index d03b030f8797..b601e804f854 100644 --- a/drivers/gpu/drm/i915/display/intel_display_types.h +++ b/drivers/gpu/drm/i915/display/intel_display_types.h @@ -1405,7 +1405,6 @@ struct intel_dp { int max_link_rate; /* sink or branch descriptor */ struct drm_dp_desc desc; - u32 edid_quirks; struct drm_dp_aux aux; u32 aux_busy_last_status; u8 train_set[4]; diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index 66aae1ad28ae..8b9c20555f0e 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -162,8 +162,7 @@ static void intel_dp_set_sink_rates(struct intel_dp *intel_dp) int i, max_rate; int max_lttpr_rate; - if (drm_dp_has_quirk(&intel_dp->desc, 0, - DP_DPCD_QUIRK_CAN_DO_MAX_LINK_RATE_3_24_GBPS)) { + if (drm_dp_has_quirk(&intel_dp->desc, DP_DPCD_QUIRK_CAN_DO_MAX_LINK_RATE_3_24_GBPS)) { /* Needed, e.g., for Apple MBP 2017, 15 inch eDP Retina panel */ static const int quirk_rates[] = { 162000, 270000, 324000 }; @@ -2435,8 +2434,7 @@ intel_dp_compute_config(struct intel_encoder *encoder, struct intel_connector *intel_connector = intel_dp->attached_connector; struct intel_digital_connector_state *intel_conn_state = to_intel_digital_connector_state(conn_state); - bool constant_n = drm_dp_has_quirk(&intel_dp->desc, 0, - DP_DPCD_QUIRK_CONSTANT_N); + bool constant_n = drm_dp_has_quirk(&intel_dp->desc, DP_DPCD_QUIRK_CONSTANT_N); int ret = 0, output_bpp; if (HAS_PCH_SPLIT(dev_priv) && !HAS_DDI(dev_priv) && port != PORT_A) @@ -6048,7 +6046,6 @@ intel_dp_set_edid(struct intel_dp *intel_dp) } drm_dp_cec_set_edid(&intel_dp->aux, edid); - intel_dp->edid_quirks = drm_dp_get_edid_quirks(edid); } static void @@ -6062,7 +6059,6 @@ intel_dp_unset_edid(struct intel_dp *intel_dp) intel_dp->has_hdmi_sink = false; intel_dp->has_audio = false; - intel_dp->edid_quirks = 0; intel_dp->dfp.max_bpc = 0; intel_dp->dfp.max_dotclock = 0; @@ -7116,7 +7112,6 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp, if (edid) { if (drm_add_edid_modes(connector, edid)) { drm_connector_update_edid_property(connector, edid); - intel_dp->edid_quirks = drm_dp_get_edid_quirks(edid); } else { kfree(edid); edid = ERR_PTR(-EINVAL); diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c index f76e2c2a83b8..d6a1b961a0e8 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c @@ -53,8 +53,7 @@ static int intel_dp_mst_compute_link_config(struct intel_encoder *encoder, struct drm_i915_private *i915 = to_i915(connector->base.dev); const struct drm_display_mode *adjusted_mode = &crtc_state->hw.adjusted_mode; - bool constant_n = drm_dp_has_quirk(&intel_dp->desc, 0, - DP_DPCD_QUIRK_CONSTANT_N); + bool constant_n = drm_dp_has_quirk(&intel_dp->desc, DP_DPCD_QUIRK_CONSTANT_N); int bpp, slots = -EINVAL; crtc_state->lane_count = limits->max_lane_count; diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c index c24ae69426cf..1e6c1fa59d4a 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.c +++ b/drivers/gpu/drm/i915/display/intel_psr.c @@ -305,7 +305,7 @@ void intel_psr_init_dpcd(struct intel_dp *intel_dp) drm_dbg_kms(&dev_priv->drm, "eDP panel supports PSR version %x\n", intel_dp->psr_dpcd[0]); - if (drm_dp_has_quirk(&intel_dp->desc, 0, DP_DPCD_QUIRK_NO_PSR)) { + if (drm_dp_has_quirk(&intel_dp->desc, DP_DPCD_QUIRK_NO_PSR)) { drm_dbg_kms(&dev_priv->drm, "PSR support not currently available for this panel\n"); return; diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h index 6236f212da61..edffd1dcca3e 100644 --- a/include/drm/drm_dp_helper.h +++ b/include/drm/drm_dp_helper.h @@ -2029,16 +2029,13 @@ struct drm_dp_desc { int drm_dp_read_desc(struct drm_dp_aux *aux, struct drm_dp_desc *desc, bool is_branch); -u32 drm_dp_get_edid_quirks(const struct edid *edid); /** * enum drm_dp_quirk - Display Port sink/branch device specific quirks * * Display Port sink and branch devices in the wild have a variety of bugs, try * to collect them here. The quirks are shared, but it's up to the drivers to - * implement workarounds for them. Note that because some devices have - * unreliable OUIDs, the EDID of sinks should also be checked for quirks using - * drm_dp_get_edid_quirks(). + * implement workarounds for them. */ enum drm_dp_quirk { /** @@ -2070,16 +2067,6 @@ enum drm_dp_quirk { * The DSC caps can be read from the physical aux instead. */ DP_DPCD_QUIRK_DSC_WITHOUT_VIRTUAL_DPCD, - /** - * @DP_QUIRK_FORCE_DPCD_BACKLIGHT: - * - * The device is telling the truth when it says that it uses DPCD - * backlight controls, even if the system's firmware disagrees. This - * quirk should be checked against both the ident and panel EDID. - * When present, the driver should honor the DPCD backlight - * capabilities advertised. - */ - DP_QUIRK_FORCE_DPCD_BACKLIGHT, /** * @DP_DPCD_QUIRK_CAN_DO_MAX_LINK_RATE_3_24_GBPS: * @@ -2092,16 +2079,14 @@ enum drm_dp_quirk { /** * drm_dp_has_quirk() - does the DP device have a specific quirk * @desc: Device descriptor filled by drm_dp_read_desc() - * @edid_quirks: Optional quirk bitmask filled by drm_dp_get_edid_quirks() * @quirk: Quirk to query for * * Return true if DP device identified by @desc has @quirk. */ static inline bool -drm_dp_has_quirk(const struct drm_dp_desc *desc, u32 edid_quirks, - enum drm_dp_quirk quirk) +drm_dp_has_quirk(const struct drm_dp_desc *desc, enum drm_dp_quirk quirk) { - return (desc->quirks | edid_quirks) & BIT(quirk); + return desc->quirks & BIT(quirk); } #ifdef CONFIG_DRM_DP_CEC -- cgit v1.2.3 From a7d6ba14efb778fc8c65c627a057d5dd29debd04 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Tue, 15 Dec 2020 00:38:04 +0100 Subject: thermal/core: Remove the 'forced_passive' option The code was reorganized in 2012 with the commit 0c01ebbfd3caf1. The main change is a loop on the trip points array and a unconditional call to the throttle() ops of the governors for each of them even if the trip temperature is not reached yet. With this change, the 'forced_passive' is no longer checked in the thermal_zone_device_update() function but in the step wise governor's throttle() callback. As the force_passive does no belong to the trip point array, the thermal_zone_device_update() can not compare with the specified passive temperature, thus does not detect the passive limit has been crossed. Consequently, throttle() is never called and the 'forced_passive' branch is unreached. In addition, the default processor cooling device is not automatically bound to the thermal zone if there is not passive trip point, thus the 'forced_passive' can not operate. If there is an active trip point, then the throttle function will be called to mitigate at this temperature and the 'forced_passive' will override the mitigation of the active trip point in this case but with the default cooling device bound to the thermal zone, so usually a fan, and that is not a passive cooling effect. Given the regression exists since more than 8 years, nobody complained and at the best of my knowledge there is no bug open in https://bugzilla.kernel.org, it is reasonable to say it is unused. Remove the 'forced_passive' related code. Signed-off-by: Daniel Lezcano Reviewed-by: Thara Gopinath Link: https://lore.kernel.org/r/20201214233811.485669-1-daniel.lezcano@linaro.org --- Documentation/driver-api/thermal/sysfs-api.rst | 13 ----- drivers/thermal/gov_step_wise.c | 14 +---- drivers/thermal/thermal_sysfs.c | 80 -------------------------- include/linux/thermal.h | 4 -- 4 files changed, 3 insertions(+), 108 deletions(-) (limited to 'include') diff --git a/Documentation/driver-api/thermal/sysfs-api.rst b/Documentation/driver-api/thermal/sysfs-api.rst index e7520cb439ac..a4969c474cc3 100644 --- a/Documentation/driver-api/thermal/sysfs-api.rst +++ b/Documentation/driver-api/thermal/sysfs-api.rst @@ -520,19 +520,6 @@ available_policies RW, Optional -passive - Attribute is only present for zones in which the passive cooling - policy is not supported by native thermal driver. Default is zero - and can be set to a temperature (in millidegrees) to enable a - passive trip point for the zone. Activation is done by polling with - an interval of 1 second. - - Unit: millidegrees Celsius - - Valid values: 0 (disabled) or greater than 1000 - - RW, Optional - emul_temp Interface to set the emulated temperature method in thermal zone (sensor). After setting this temperature, the thermal zone may pass diff --git a/drivers/thermal/gov_step_wise.c b/drivers/thermal/gov_step_wise.c index 2ae7198d3067..12acb12aac50 100644 --- a/drivers/thermal/gov_step_wise.c +++ b/drivers/thermal/gov_step_wise.c @@ -109,7 +109,7 @@ static void update_passive_instance(struct thermal_zone_device *tz, * If value is +1, activate a passive instance. * If value is -1, deactivate a passive instance. */ - if (type == THERMAL_TRIP_PASSIVE || type == THERMAL_TRIPS_NONE) + if (type == THERMAL_TRIP_PASSIVE) tz->passive += value; } @@ -122,13 +122,8 @@ static void thermal_zone_trip_update(struct thermal_zone_device *tz, int trip) bool throttle = false; int old_target; - if (trip == THERMAL_TRIPS_NONE) { - trip_temp = tz->forced_passive; - trip_type = THERMAL_TRIPS_NONE; - } else { - tz->ops->get_trip_temp(tz, trip, &trip_temp); - tz->ops->get_trip_type(tz, trip, &trip_type); - } + tz->ops->get_trip_temp(tz, trip, &trip_temp); + tz->ops->get_trip_type(tz, trip, &trip_type); trend = get_tz_trend(tz, trip); @@ -189,9 +184,6 @@ static int step_wise_throttle(struct thermal_zone_device *tz, int trip) thermal_zone_trip_update(tz, trip); - if (tz->forced_passive) - thermal_zone_trip_update(tz, THERMAL_TRIPS_NONE); - mutex_lock(&tz->lock); list_for_each_entry(instance, &tz->thermal_instances, tz_node) diff --git a/drivers/thermal/thermal_sysfs.c b/drivers/thermal/thermal_sysfs.c index 0866e949339b..4e7f9e880d76 100644 --- a/drivers/thermal/thermal_sysfs.c +++ b/drivers/thermal/thermal_sysfs.c @@ -216,49 +216,6 @@ trip_point_hyst_show(struct device *dev, struct device_attribute *attr, return ret ? ret : sprintf(buf, "%d\n", temperature); } -static ssize_t -passive_store(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) -{ - struct thermal_zone_device *tz = to_thermal_zone(dev); - int state; - - if (sscanf(buf, "%d\n", &state) != 1) - return -EINVAL; - - /* sanity check: values below 1000 millicelcius don't make sense - * and can cause the system to go into a thermal heart attack - */ - if (state && state < 1000) - return -EINVAL; - - if (state && !tz->forced_passive) { - if (!tz->passive_delay) - tz->passive_delay = 1000; - thermal_zone_device_rebind_exception(tz, "Processor", - sizeof("Processor")); - } else if (!state && tz->forced_passive) { - tz->passive_delay = 0; - thermal_zone_device_unbind_exception(tz, "Processor", - sizeof("Processor")); - } - - tz->forced_passive = state; - - thermal_zone_device_update(tz, THERMAL_EVENT_UNSPECIFIED); - - return count; -} - -static ssize_t -passive_show(struct device *dev, struct device_attribute *attr, - char *buf) -{ - struct thermal_zone_device *tz = to_thermal_zone(dev); - - return sprintf(buf, "%d\n", tz->forced_passive); -} - static ssize_t policy_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) @@ -403,7 +360,6 @@ static DEVICE_ATTR_RW(sustainable_power); /* These thermal zone device attributes are created based on conditions */ static DEVICE_ATTR_RW(mode); -static DEVICE_ATTR_RW(passive); /* These attributes are unconditionally added to a thermal zone */ static struct attribute *thermal_zone_dev_attrs[] = { @@ -438,45 +394,9 @@ static const struct attribute_group thermal_zone_mode_attribute_group = { .attrs = thermal_zone_mode_attrs, }; -/* We expose passive only if passive trips are present */ -static struct attribute *thermal_zone_passive_attrs[] = { - &dev_attr_passive.attr, - NULL, -}; - -static umode_t thermal_zone_passive_is_visible(struct kobject *kobj, - struct attribute *attr, - int attrno) -{ - struct device *dev = kobj_to_dev(kobj); - struct thermal_zone_device *tz; - enum thermal_trip_type trip_type; - int count, passive = 0; - - tz = container_of(dev, struct thermal_zone_device, device); - - for (count = 0; count < tz->trips && !passive; count++) { - tz->ops->get_trip_type(tz, count, &trip_type); - - if (trip_type == THERMAL_TRIP_PASSIVE) - passive = 1; - } - - if (!passive) - return attr->mode; - - return 0; -} - -static const struct attribute_group thermal_zone_passive_attribute_group = { - .attrs = thermal_zone_passive_attrs, - .is_visible = thermal_zone_passive_is_visible, -}; - static const struct attribute_group *thermal_zone_attribute_groups[] = { &thermal_zone_attribute_group, &thermal_zone_mode_attribute_group, - &thermal_zone_passive_attribute_group, /* This is not NULL terminated as we create the group dynamically */ }; diff --git a/include/linux/thermal.h b/include/linux/thermal.h index c80032322158..a57232a9a6f9 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -131,9 +131,6 @@ struct thermal_cooling_device { trip point. * @prev_high_trip: the above current temperature if you've crossed a passive trip point. - * @forced_passive: If > 0, temperature at which to switch on all ACPI - * processor cooling devices. Currently only used by the - * step-wise governor. * @need_update: if equals 1, thermal_zone_device_update needs to be invoked. * @ops: operations this &thermal_zone_device supports * @tzp: thermal zone parameters @@ -167,7 +164,6 @@ struct thermal_zone_device { int passive; int prev_low_trip; int prev_high_trip; - unsigned int forced_passive; atomic_t need_update; struct thermal_zone_device_ops *ops; struct thermal_zone_params *tzp; -- cgit v1.2.3 From 2121496fdc5f2d93eda9743c4b487469f0042e3c Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Tue, 15 Dec 2020 00:38:09 +0100 Subject: thermal/core: Remove unused macro THERMAL_TRIPS_NONE The macro THERMAL_TRIPS_NONE is no longer used, remove it. Signed-off-by: Daniel Lezcano Reviewed-by: Thara Gopinath Link: https://lore.kernel.org/r/20201214233811.485669-6-daniel.lezcano@linaro.org --- include/linux/thermal.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index a57232a9a6f9..060a2160add4 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -17,7 +17,6 @@ #include #include -#define THERMAL_TRIPS_NONE -1 #define THERMAL_MAX_TRIPS 12 /* invalid cooling state */ -- cgit v1.2.3 From 17d399cd9c8936909bc8936a5837b6da9af9c29e Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Wed, 16 Dec 2020 23:03:35 +0100 Subject: thermal/core: Precompute the delays from msecs to jiffies The delays are stored in ms units and when the polling function is called this delay is converted into jiffies at each call. Instead of doing the conversion again and again, compute the jiffies at init time and use the value directly when setting the polling. Cc: Thara Gopinath Signed-off-by: Daniel Lezcano Reviewed-by: Lukasz Luba Reviewed-by: Thara Gopinath Link: https://lore.kernel.org/r/20201216220337.839878-1-daniel.lezcano@linaro.org --- drivers/thermal/thermal_core.c | 3 +++ drivers/thermal/thermal_core.h | 1 + drivers/thermal/thermal_helpers.c | 7 +++++++ include/linux/thermal.h | 7 +++++++ 4 files changed, 18 insertions(+) (limited to 'include') diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index bcc2ea4f5482..2c41d4a0923f 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -1315,6 +1315,9 @@ thermal_zone_device_register(const char *type, int trips, int mask, tz->passive_delay = passive_delay; tz->polling_delay = polling_delay; + thermal_set_delay_jiffies(&tz->passive_delay_jiffies, passive_delay); + thermal_set_delay_jiffies(&tz->polling_delay_jiffies, polling_delay); + /* sys I/F */ /* Add nodes that are always present via .groups */ result = thermal_zone_create_device_groups(tz, mask); diff --git a/drivers/thermal/thermal_core.h b/drivers/thermal/thermal_core.h index e50c6b2909fe..90f9a80c8b23 100644 --- a/drivers/thermal/thermal_core.h +++ b/drivers/thermal/thermal_core.h @@ -123,6 +123,7 @@ int thermal_build_list_of_policies(char *buf); /* Helpers */ void thermal_zone_set_trips(struct thermal_zone_device *tz); +void thermal_set_delay_jiffies(unsigned long *delay_jiffies, int delay_ms); /* sysfs I/F */ int thermal_zone_create_device_groups(struct thermal_zone_device *, int); diff --git a/drivers/thermal/thermal_helpers.c b/drivers/thermal/thermal_helpers.c index c94bc824e5d3..7f50f412e02a 100644 --- a/drivers/thermal/thermal_helpers.c +++ b/drivers/thermal/thermal_helpers.c @@ -175,6 +175,13 @@ exit: mutex_unlock(&tz->lock); } +void thermal_set_delay_jiffies(unsigned long *delay_jiffies, int delay_ms) +{ + *delay_jiffies = msecs_to_jiffies(delay_ms); + if (delay_ms > 1000) + *delay_jiffies = round_jiffies(*delay_jiffies); +} + static void thermal_cdev_set_cur_state(struct thermal_cooling_device *cdev, int target) { diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 060a2160add4..d1b82c70de69 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -117,9 +117,14 @@ struct thermal_cooling_device { * @trips_disabled; bitmap for disabled trips * @passive_delay: number of milliseconds to wait between polls when * performing passive cooling. + * @passive_delay_jiffies: number of jiffies to wait between polls when + * performing passive cooling. * @polling_delay: number of milliseconds to wait between polls when * checking whether trip points have been crossed (0 for * interrupt driven systems) + * @polling_delay_jiffies: number of jiffies to wait between polls when + * checking whether trip points have been crossed (0 for + * interrupt driven systems) * @temperature: current temperature. This is only for core code, * drivers should use thermal_zone_get_temp() to get the * current temperature @@ -155,6 +160,8 @@ struct thermal_zone_device { void *devdata; int trips; unsigned long trips_disabled; /* bitmap for disabled trips */ + unsigned long passive_delay_jiffies; + unsigned long polling_delay_jiffies; int passive_delay; int polling_delay; int temperature; -- cgit v1.2.3 From b39d2dd5b5ed08d15711aefd5afd72bd87387c64 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Wed, 16 Dec 2020 23:03:37 +0100 Subject: thermal/core: Remove ms based delay fields MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The code does no longer use the ms unit based fields to set the delays as they are replaced by the jiffies. Remove them and replace their user to use the jiffies version instead. Cc: Thara Gopinath Signed-off-by: Daniel Lezcano Reviewed-by: Lukasz Luba Reviewed-by: Peter Kästle Acked-by: Hans de Goede Link: https://lore.kernel.org/r/20201216220337.839878-3-daniel.lezcano@linaro.org --- drivers/platform/x86/acerhdf.c | 3 ++- drivers/thermal/da9062-thermal.c | 4 ++-- drivers/thermal/gov_power_allocator.c | 2 +- drivers/thermal/thermal_core.c | 4 +--- drivers/thermal/ti-soc-thermal/ti-thermal-common.c | 6 ++++-- include/linux/thermal.h | 7 ------- 6 files changed, 10 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/drivers/platform/x86/acerhdf.c b/drivers/platform/x86/acerhdf.c index b6aa6e5514f4..6b8b3ab8db48 100644 --- a/drivers/platform/x86/acerhdf.c +++ b/drivers/platform/x86/acerhdf.c @@ -336,7 +336,8 @@ static void acerhdf_check_param(struct thermal_zone_device *thermal) pr_notice("interval changed to: %d\n", interval); if (thermal) - thermal->polling_delay = interval*1000; + thermal->polling_delay_jiffies = + round_jiffies(msecs_to_jiffies(interval * 1000)); prev_interval = interval; } diff --git a/drivers/thermal/da9062-thermal.c b/drivers/thermal/da9062-thermal.c index 4d74994f160a..180edec34e07 100644 --- a/drivers/thermal/da9062-thermal.c +++ b/drivers/thermal/da9062-thermal.c @@ -95,7 +95,7 @@ static void da9062_thermal_poll_on(struct work_struct *work) thermal_zone_device_update(thermal->zone, THERMAL_EVENT_UNSPECIFIED); - delay = msecs_to_jiffies(thermal->zone->passive_delay); + delay = thermal->zone->passive_delay_jiffies; queue_delayed_work(system_freezable_wq, &thermal->work, delay); return; } @@ -245,7 +245,7 @@ static int da9062_thermal_probe(struct platform_device *pdev) dev_dbg(&pdev->dev, "TJUNC temperature polling period set at %d ms\n", - thermal->zone->passive_delay); + jiffies_to_msecs(thermal->zone->passive_delay_jiffies)); ret = platform_get_irq_byname(pdev, "THERMAL"); if (ret < 0) { diff --git a/drivers/thermal/gov_power_allocator.c b/drivers/thermal/gov_power_allocator.c index 7a4170a0b51f..f8c3d1e40b86 100644 --- a/drivers/thermal/gov_power_allocator.c +++ b/drivers/thermal/gov_power_allocator.c @@ -258,7 +258,7 @@ static u32 pid_controller(struct thermal_zone_device *tz, * power being applied, slowing down the controller) */ d = mul_frac(tz->tzp->k_d, err - params->prev_err); - d = div_frac(d, tz->passive_delay); + d = div_frac(d, jiffies_to_msecs(tz->passive_delay_jiffies)); params->prev_err = err; power_range = p + i + d; diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index d96c515af3cb..b2615449b18f 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -313,7 +313,7 @@ static void monitor_thermal_zone(struct thermal_zone_device *tz) if (!stop && tz->passive) thermal_zone_device_set_polling(tz, tz->passive_delay_jiffies); - else if (!stop && tz->polling_delay) + else if (!stop && tz->polling_delay_jiffies) thermal_zone_device_set_polling(tz, tz->polling_delay_jiffies); else thermal_zone_device_set_polling(tz, 0); @@ -1307,8 +1307,6 @@ thermal_zone_device_register(const char *type, int trips, int mask, tz->device.class = &thermal_class; tz->devdata = devdata; tz->trips = trips; - tz->passive_delay = passive_delay; - tz->polling_delay = polling_delay; thermal_set_delay_jiffies(&tz->passive_delay_jiffies, passive_delay); thermal_set_delay_jiffies(&tz->polling_delay_jiffies, polling_delay); diff --git a/drivers/thermal/ti-soc-thermal/ti-thermal-common.c b/drivers/thermal/ti-soc-thermal/ti-thermal-common.c index 2ce4b19f312a..f84375865c97 100644 --- a/drivers/thermal/ti-soc-thermal/ti-thermal-common.c +++ b/drivers/thermal/ti-soc-thermal/ti-thermal-common.c @@ -166,6 +166,7 @@ int ti_thermal_expose_sensor(struct ti_bandgap *bgp, int id, char *domain) { struct ti_thermal_data *data; + int interval; data = ti_bandgap_get_sensor_data(bgp, id); @@ -183,9 +184,10 @@ int ti_thermal_expose_sensor(struct ti_bandgap *bgp, int id, return PTR_ERR(data->ti_thermal); } + interval = jiffies_to_msecs(data->ti_thermal->polling_delay_jiffies); + ti_bandgap_set_sensor_data(bgp, id, data); - ti_bandgap_write_update_interval(bgp, data->sensor_id, - data->ti_thermal->polling_delay); + ti_bandgap_write_update_interval(bgp, data->sensor_id, interval); return 0; } diff --git a/include/linux/thermal.h b/include/linux/thermal.h index d1b82c70de69..1e686404951b 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -115,13 +115,8 @@ struct thermal_cooling_device { * @devdata: private pointer for device private data * @trips: number of trip points the thermal zone supports * @trips_disabled; bitmap for disabled trips - * @passive_delay: number of milliseconds to wait between polls when - * performing passive cooling. * @passive_delay_jiffies: number of jiffies to wait between polls when * performing passive cooling. - * @polling_delay: number of milliseconds to wait between polls when - * checking whether trip points have been crossed (0 for - * interrupt driven systems) * @polling_delay_jiffies: number of jiffies to wait between polls when * checking whether trip points have been crossed (0 for * interrupt driven systems) @@ -162,8 +157,6 @@ struct thermal_zone_device { unsigned long trips_disabled; /* bitmap for disabled trips */ unsigned long passive_delay_jiffies; unsigned long polling_delay_jiffies; - int passive_delay; - int polling_delay; int temperature; int last_temperature; int emul_temperature; -- cgit v1.2.3 From 23ff8529ee207c634ce2e170c353938db7aa98a9 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Mon, 18 Jan 2021 18:38:24 +0100 Subject: thermal/core: Make cooling device state change private The change of the cooling device state should be used by the governor or at least by the core code, not by the drivers themselves. Remove the API usage and move the function declaration to the internal headers. Signed-off-by: Daniel Lezcano Acked-by: Guenter Roeck Acked-by: Zhang Rui Link: https://lore.kernel.org/r/20210118173824.9970-1-daniel.lezcano@linaro.org --- drivers/hwmon/pwm-fan.c | 1 - drivers/thermal/khadas_mcu_fan.c | 1 - drivers/thermal/thermal_core.h | 2 ++ include/linux/thermal.h | 3 --- 4 files changed, 2 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/hwmon/pwm-fan.c b/drivers/hwmon/pwm-fan.c index 777439f48c14..c8a15971d704 100644 --- a/drivers/hwmon/pwm-fan.c +++ b/drivers/hwmon/pwm-fan.c @@ -422,7 +422,6 @@ static int pwm_fan_probe(struct platform_device *pdev) return ret; } ctx->cdev = cdev; - thermal_cdev_update(cdev); } return 0; diff --git a/drivers/thermal/khadas_mcu_fan.c b/drivers/thermal/khadas_mcu_fan.c index 9eadd2d6413e..d35e5313bea4 100644 --- a/drivers/thermal/khadas_mcu_fan.c +++ b/drivers/thermal/khadas_mcu_fan.c @@ -100,7 +100,6 @@ static int khadas_mcu_fan_probe(struct platform_device *pdev) return ret; } ctx->cdev = cdev; - thermal_cdev_update(cdev); return 0; } diff --git a/drivers/thermal/thermal_core.h b/drivers/thermal/thermal_core.h index 90f9a80c8b23..86b8cef7310e 100644 --- a/drivers/thermal/thermal_core.h +++ b/drivers/thermal/thermal_core.h @@ -65,6 +65,8 @@ static inline bool cdev_is_power_actor(struct thermal_cooling_device *cdev) cdev->ops->power2state; } +void thermal_cdev_update(struct thermal_cooling_device *); + /** * struct thermal_trip - representation of a point in temperature domain * @np: pointer to struct device_node that this trip point was created from diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 1e686404951b..6ac7bb1d2b1f 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -390,7 +390,6 @@ int thermal_zone_get_temp(struct thermal_zone_device *tz, int *temp); int thermal_zone_get_slope(struct thermal_zone_device *tz); int thermal_zone_get_offset(struct thermal_zone_device *tz); -void thermal_cdev_update(struct thermal_cooling_device *); void thermal_notify_framework(struct thermal_zone_device *, int); int thermal_zone_device_enable(struct thermal_zone_device *tz); int thermal_zone_device_disable(struct thermal_zone_device *tz); @@ -437,8 +436,6 @@ static inline int thermal_zone_get_offset( struct thermal_zone_device *tz) { return -ENODEV; } -static inline void thermal_cdev_update(struct thermal_cooling_device *cdev) -{ } static inline void thermal_notify_framework(struct thermal_zone_device *tz, int trip) { } -- cgit v1.2.3 From 93cc26fa8f37fbd320f36525bfedd4b3e2b3e2ba Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 18 Jan 2021 14:23:22 +0100 Subject: backlight: lms283gf05: Convert to GPIO descriptors This converts the lms283gf05 backlight driver to use GPIO descriptors and switches the single PXA Palm Z2 device over to defining these. Since the platform data was only used to convey GPIO information we can delete the platform data header. Notice that we define the proper active low semantics in the board file GPIO descriptor table (active low) and assert the reset line by bringing it to "1" (asserted). Cc: Marek Vasut Cc: Haojian Zhuang Cc: Robert Jarzmik Signed-off-by: Linus Walleij Reviewed-by: Daniel Mack Acked-by: Mark Brown Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones --- arch/arm/mach-pxa/z2.c | 12 ++++++---- drivers/video/backlight/lms283gf05.c | 43 ++++++++++++++---------------------- include/linux/spi/lms283gf05.h | 16 -------------- 3 files changed, 25 insertions(+), 46 deletions(-) delete mode 100644 include/linux/spi/lms283gf05.h (limited to 'include') diff --git a/arch/arm/mach-pxa/z2.c b/arch/arm/mach-pxa/z2.c index 21fd76bb09cd..89eb5243c85f 100644 --- a/arch/arm/mach-pxa/z2.c +++ b/arch/arm/mach-pxa/z2.c @@ -20,7 +20,6 @@ #include #include #include -#include #include #include #include @@ -578,8 +577,13 @@ static struct pxa2xx_spi_chip lms283_chip_info = { .gpio_cs = GPIO88_ZIPITZ2_LCD_CS, }; -static const struct lms283gf05_pdata lms283_pdata = { - .reset_gpio = GPIO19_ZIPITZ2_LCD_RESET, +static struct gpiod_lookup_table lms283_gpio_table = { + .dev_id = "spi2.0", /* SPI bus 2 chip select 0 */ + .table = { + GPIO_LOOKUP("gpio-pxa", GPIO19_ZIPITZ2_LCD_RESET, + "reset", GPIO_ACTIVE_LOW), + { }, + }, }; static struct spi_board_info spi_board_info[] __initdata = { @@ -595,7 +599,6 @@ static struct spi_board_info spi_board_info[] __initdata = { { .modalias = "lms283gf05", .controller_data = &lms283_chip_info, - .platform_data = &lms283_pdata, .max_speed_hz = 400000, .bus_num = 2, .chip_select = 0, @@ -615,6 +618,7 @@ static void __init z2_spi_init(void) { pxa2xx_set_spi_info(1, &pxa_ssp1_master_info); pxa2xx_set_spi_info(2, &pxa_ssp2_master_info); + gpiod_add_lookup_table(&lms283_gpio_table); spi_register_board_info(spi_board_info, ARRAY_SIZE(spi_board_info)); } #else diff --git a/drivers/video/backlight/lms283gf05.c b/drivers/video/backlight/lms283gf05.c index 0e45685bcc1c..36856962ed83 100644 --- a/drivers/video/backlight/lms283gf05.c +++ b/drivers/video/backlight/lms283gf05.c @@ -9,16 +9,16 @@ #include #include #include -#include +#include #include #include -#include #include struct lms283gf05_state { struct spi_device *spi; struct lcd_device *ld; + struct gpio_desc *reset; }; struct lms283gf05_seq { @@ -90,13 +90,13 @@ static const struct lms283gf05_seq disp_pdwnseq[] = { }; -static void lms283gf05_reset(unsigned long gpio, bool inverted) +static void lms283gf05_reset(struct gpio_desc *gpiod) { - gpio_set_value(gpio, !inverted); + gpiod_set_value(gpiod, 0); /* De-asserted */ mdelay(100); - gpio_set_value(gpio, inverted); + gpiod_set_value(gpiod, 1); /* Asserted */ mdelay(20); - gpio_set_value(gpio, !inverted); + gpiod_set_value(gpiod, 0); /* De-asserted */ mdelay(20); } @@ -125,18 +125,15 @@ static int lms283gf05_power_set(struct lcd_device *ld, int power) { struct lms283gf05_state *st = lcd_get_data(ld); struct spi_device *spi = st->spi; - struct lms283gf05_pdata *pdata = dev_get_platdata(&spi->dev); if (power <= FB_BLANK_NORMAL) { - if (pdata) - lms283gf05_reset(pdata->reset_gpio, - pdata->reset_inverted); + if (st->reset) + lms283gf05_reset(st->reset); lms283gf05_toggle(spi, disp_initseq, ARRAY_SIZE(disp_initseq)); } else { lms283gf05_toggle(spi, disp_pdwnseq, ARRAY_SIZE(disp_pdwnseq)); - if (pdata) - gpio_set_value(pdata->reset_gpio, - pdata->reset_inverted); + if (st->reset) + gpiod_set_value(st->reset, 1); /* Asserted */ } return 0; @@ -150,24 +147,18 @@ static struct lcd_ops lms_ops = { static int lms283gf05_probe(struct spi_device *spi) { struct lms283gf05_state *st; - struct lms283gf05_pdata *pdata = dev_get_platdata(&spi->dev); struct lcd_device *ld; - int ret = 0; - - if (pdata != NULL) { - ret = devm_gpio_request_one(&spi->dev, pdata->reset_gpio, - GPIOF_DIR_OUT | (!pdata->reset_inverted ? - GPIOF_INIT_HIGH : GPIOF_INIT_LOW), - "LMS283GF05 RESET"); - if (ret) - return ret; - } st = devm_kzalloc(&spi->dev, sizeof(struct lms283gf05_state), GFP_KERNEL); if (st == NULL) return -ENOMEM; + st->reset = gpiod_get_optional(&spi->dev, "reset", GPIOD_OUT_LOW); + if (IS_ERR(st->reset)) + return PTR_ERR(st->reset); + gpiod_set_consumer_name(st->reset, "LMS283GF05 RESET"); + ld = devm_lcd_device_register(&spi->dev, "lms283gf05", &spi->dev, st, &lms_ops); if (IS_ERR(ld)) @@ -179,8 +170,8 @@ static int lms283gf05_probe(struct spi_device *spi) spi_set_drvdata(spi, st); /* kick in the LCD */ - if (pdata) - lms283gf05_reset(pdata->reset_gpio, pdata->reset_inverted); + if (st->reset) + lms283gf05_reset(st->reset); lms283gf05_toggle(spi, disp_initseq, ARRAY_SIZE(disp_initseq)); return 0; diff --git a/include/linux/spi/lms283gf05.h b/include/linux/spi/lms283gf05.h deleted file mode 100644 index f237b2d062e9..000000000000 --- a/include/linux/spi/lms283gf05.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * lms283gf05.h - Platform glue for Samsung LMS283GF05 LCD - * - * Copyright (C) 2009 Marek Vasut -*/ - -#ifndef _INCLUDE_LINUX_SPI_LMS283GF05_H_ -#define _INCLUDE_LINUX_SPI_LMS283GF05_H_ - -struct lms283gf05_pdata { - unsigned long reset_gpio; - bool reset_inverted; -}; - -#endif /* _INCLUDE_LINUX_SPI_LMS283GF05_H_ */ -- cgit v1.2.3 From 9f77c58d65ff216d71f5ab829b6f39afefbde10c Mon Sep 17 00:00:00 2001 From: Pi-Hsun Shih Date: Mon, 21 Dec 2020 12:12:23 +0800 Subject: platform/chrome: cros_ec_commands: Add host command to keep AP off after EC reset. Add command to EC_CMD_REBOOT_EC to reset EC but don't boot AP. Signed-off-by: Pi-Hsun Shih Signed-off-by: Enric Balletbo i Serra Link: https://lore.kernel.org/r/20201221041231.14516-1-pihsun@chromium.org --- include/linux/platform_data/cros_ec_commands.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h index 9787715540c7..d3c40220b281 100644 --- a/include/linux/platform_data/cros_ec_commands.h +++ b/include/linux/platform_data/cros_ec_commands.h @@ -4741,6 +4741,7 @@ enum ec_reboot_cmd { EC_REBOOT_DISABLE_JUMP = 5, /* Disable jump until next reboot */ EC_REBOOT_HIBERNATE = 6, /* Hibernate EC */ EC_REBOOT_HIBERNATE_CLEAR_AP_OFF = 7, /* and clears AP_OFF flag */ + EC_REBOOT_COLD_AP_OFF = 8, /* Cold-reboot and don't boot AP */ }; /* Flags for ec_params_reboot_ec.reboot_flags */ -- cgit v1.2.3 From f6f1f8e6e3eea25f539105d48166e91f0ab46dd1 Mon Sep 17 00:00:00 2001 From: Aswath Govindraju Date: Tue, 5 Jan 2021 16:28:12 +0530 Subject: misc: eeprom_93xx46: Add quirk to support Microchip 93LC46B eeprom A dummy zero bit is sent preceding the data during a read transfer by the Microchip 93LC46B eeprom (section 2.7 of[1]). This results in right shift of data during a read. In order to ignore this bit a quirk can be added to send an extra zero bit after the read address. Add a quirk to ignore the zero bit sent before data by adding a zero bit after the read address. [1] - https://www.mouser.com/datasheet/2/268/20001749K-277859.pdf Signed-off-by: Aswath Govindraju Link: https://lore.kernel.org/r/20210105105817.17644-3-a-govindraju@ti.com Signed-off-by: Greg Kroah-Hartman --- drivers/misc/eeprom/eeprom_93xx46.c | 15 +++++++++++++++ include/linux/eeprom_93xx46.h | 2 ++ 2 files changed, 17 insertions(+) (limited to 'include') diff --git a/drivers/misc/eeprom/eeprom_93xx46.c b/drivers/misc/eeprom/eeprom_93xx46.c index e130a0d858e9..80114f4c80ad 100644 --- a/drivers/misc/eeprom/eeprom_93xx46.c +++ b/drivers/misc/eeprom/eeprom_93xx46.c @@ -35,6 +35,10 @@ static const struct eeprom_93xx46_devtype_data atmel_at93c46d_data = { EEPROM_93XX46_QUIRK_INSTRUCTION_LENGTH, }; +static const struct eeprom_93xx46_devtype_data microchip_93lc46b_data = { + .quirks = EEPROM_93XX46_QUIRK_EXTRA_READ_CYCLE, +}; + struct eeprom_93xx46_dev { struct spi_device *spi; struct eeprom_93xx46_platform_data *pdata; @@ -55,6 +59,11 @@ static inline bool has_quirk_instruction_length(struct eeprom_93xx46_dev *edev) return edev->pdata->quirks & EEPROM_93XX46_QUIRK_INSTRUCTION_LENGTH; } +static inline bool has_quirk_extra_read_cycle(struct eeprom_93xx46_dev *edev) +{ + return edev->pdata->quirks & EEPROM_93XX46_QUIRK_EXTRA_READ_CYCLE; +} + static int eeprom_93xx46_read(void *priv, unsigned int off, void *val, size_t count) { @@ -96,6 +105,11 @@ static int eeprom_93xx46_read(void *priv, unsigned int off, dev_dbg(&edev->spi->dev, "read cmd 0x%x, %d Hz\n", cmd_addr, edev->spi->max_speed_hz); + if (has_quirk_extra_read_cycle(edev)) { + cmd_addr <<= 1; + bits += 1; + } + spi_message_init(&m); t[0].tx_buf = (char *)&cmd_addr; @@ -363,6 +377,7 @@ static void select_deassert(void *context) static const struct of_device_id eeprom_93xx46_of_table[] = { { .compatible = "eeprom-93xx46", }, { .compatible = "atmel,at93c46d", .data = &atmel_at93c46d_data, }, + { .compatible = "microchip,93lc46b", .data = µchip_93lc46b_data, }, {} }; MODULE_DEVICE_TABLE(of, eeprom_93xx46_of_table); diff --git a/include/linux/eeprom_93xx46.h b/include/linux/eeprom_93xx46.h index eec7928ff8fe..99580c22f91a 100644 --- a/include/linux/eeprom_93xx46.h +++ b/include/linux/eeprom_93xx46.h @@ -16,6 +16,8 @@ struct eeprom_93xx46_platform_data { #define EEPROM_93XX46_QUIRK_SINGLE_WORD_READ (1 << 0) /* Instructions such as EWEN are (addrlen + 2) in length. */ #define EEPROM_93XX46_QUIRK_INSTRUCTION_LENGTH (1 << 1) +/* Add extra cycle after address during a read */ +#define EEPROM_93XX46_QUIRK_EXTRA_READ_CYCLE BIT(2) /* * optional hooks to control additional logic -- cgit v1.2.3 From 368c0159d492d7fbdb5791b40c9263ec4e97a10f Mon Sep 17 00:00:00 2001 From: Jianxin Xiong Date: Tue, 15 Dec 2020 13:27:13 -0800 Subject: RDMA/umem: Support importing dma-buf as user memory region Dma-buf is a standard cross-driver buffer sharing mechanism that can be used to support peer-to-peer access from RDMA devices. Device memory exported via dma-buf is associated with a file descriptor. This is passed to the user space as a property associated with the buffer allocation. When the buffer is registered as a memory region, the file descriptor is passed to the RDMA driver along with other parameters. Implement the common code for importing dma-buf object and mapping dma-buf pages. Link: https://lore.kernel.org/r/1608067636-98073-2-git-send-email-jianxin.xiong@intel.com Signed-off-by: Jianxin Xiong Reviewed-by: Sean Hefty Acked-by: Michael J. Ruhl Acked-by: Christian Koenig Acked-by: Daniel Vetter Signed-off-by: Jason Gunthorpe --- drivers/infiniband/Kconfig | 1 + drivers/infiniband/core/Makefile | 2 +- drivers/infiniband/core/umem.c | 3 + drivers/infiniband/core/umem_dmabuf.c | 174 ++++++++++++++++++++++++++++++++++ include/rdma/ib_umem.h | 48 +++++++++- 5 files changed, 224 insertions(+), 4 deletions(-) create mode 100644 drivers/infiniband/core/umem_dmabuf.c (limited to 'include') diff --git a/drivers/infiniband/Kconfig b/drivers/infiniband/Kconfig index 9325e189a215..04a78d9f8fe3 100644 --- a/drivers/infiniband/Kconfig +++ b/drivers/infiniband/Kconfig @@ -41,6 +41,7 @@ config INFINIBAND_USER_MEM bool depends on INFINIBAND_USER_ACCESS != n depends on MMU + select DMA_SHARED_BUFFER default y config INFINIBAND_ON_DEMAND_PAGING diff --git a/drivers/infiniband/core/Makefile b/drivers/infiniband/core/Makefile index ccf2670ef45e..8ab4eea5a0a5 100644 --- a/drivers/infiniband/core/Makefile +++ b/drivers/infiniband/core/Makefile @@ -40,5 +40,5 @@ ib_uverbs-y := uverbs_main.o uverbs_cmd.o uverbs_marshall.o \ uverbs_std_types_srq.o \ uverbs_std_types_wq.o \ uverbs_std_types_qp.o -ib_uverbs-$(CONFIG_INFINIBAND_USER_MEM) += umem.o +ib_uverbs-$(CONFIG_INFINIBAND_USER_MEM) += umem.o umem_dmabuf.o ib_uverbs-$(CONFIG_INFINIBAND_ON_DEMAND_PAGING) += umem_odp.o diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c index 917338db7ac1..2dde99a9ba07 100644 --- a/drivers/infiniband/core/umem.c +++ b/drivers/infiniband/core/umem.c @@ -2,6 +2,7 @@ * Copyright (c) 2005 Topspin Communications. All rights reserved. * Copyright (c) 2005 Cisco Systems. All rights reserved. * Copyright (c) 2005 Mellanox Technologies. All rights reserved. + * Copyright (c) 2020 Intel Corporation. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU @@ -278,6 +279,8 @@ void ib_umem_release(struct ib_umem *umem) { if (!umem) return; + if (umem->is_dmabuf) + return ib_umem_dmabuf_release(to_ib_umem_dmabuf(umem)); if (umem->is_odp) return ib_umem_odp_release(to_ib_umem_odp(umem)); diff --git a/drivers/infiniband/core/umem_dmabuf.c b/drivers/infiniband/core/umem_dmabuf.c new file mode 100644 index 000000000000..f9b5162d9260 --- /dev/null +++ b/drivers/infiniband/core/umem_dmabuf.c @@ -0,0 +1,174 @@ +// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) +/* + * Copyright (c) 2020 Intel Corporation. All rights reserved. + */ + +#include +#include +#include + +#include "uverbs.h" + +int ib_umem_dmabuf_map_pages(struct ib_umem_dmabuf *umem_dmabuf) +{ + struct sg_table *sgt; + struct scatterlist *sg; + struct dma_fence *fence; + unsigned long start, end, cur = 0; + unsigned int nmap = 0; + int i; + + dma_resv_assert_held(umem_dmabuf->attach->dmabuf->resv); + + if (umem_dmabuf->sgt) + goto wait_fence; + + sgt = dma_buf_map_attachment(umem_dmabuf->attach, DMA_BIDIRECTIONAL); + if (IS_ERR(sgt)) + return PTR_ERR(sgt); + + /* modify the sg list in-place to match umem address and length */ + + start = ALIGN_DOWN(umem_dmabuf->umem.address, PAGE_SIZE); + end = ALIGN(umem_dmabuf->umem.address + umem_dmabuf->umem.length, + PAGE_SIZE); + for_each_sgtable_dma_sg(sgt, sg, i) { + if (start < cur + sg_dma_len(sg) && cur < end) + nmap++; + if (cur <= start && start < cur + sg_dma_len(sg)) { + unsigned long offset = start - cur; + + umem_dmabuf->first_sg = sg; + umem_dmabuf->first_sg_offset = offset; + sg_dma_address(sg) += offset; + sg_dma_len(sg) -= offset; + cur += offset; + } + if (cur < end && end <= cur + sg_dma_len(sg)) { + unsigned long trim = cur + sg_dma_len(sg) - end; + + umem_dmabuf->last_sg = sg; + umem_dmabuf->last_sg_trim = trim; + sg_dma_len(sg) -= trim; + break; + } + cur += sg_dma_len(sg); + } + + umem_dmabuf->umem.sg_head.sgl = umem_dmabuf->first_sg; + umem_dmabuf->umem.sg_head.nents = nmap; + umem_dmabuf->umem.nmap = nmap; + umem_dmabuf->sgt = sgt; + +wait_fence: + /* + * Although the sg list is valid now, the content of the pages + * may be not up-to-date. Wait for the exporter to finish + * the migration. + */ + fence = dma_resv_get_excl(umem_dmabuf->attach->dmabuf->resv); + if (fence) + return dma_fence_wait(fence, false); + + return 0; +} +EXPORT_SYMBOL(ib_umem_dmabuf_map_pages); + +void ib_umem_dmabuf_unmap_pages(struct ib_umem_dmabuf *umem_dmabuf) +{ + dma_resv_assert_held(umem_dmabuf->attach->dmabuf->resv); + + if (!umem_dmabuf->sgt) + return; + + /* retore the original sg list */ + if (umem_dmabuf->first_sg) { + sg_dma_address(umem_dmabuf->first_sg) -= + umem_dmabuf->first_sg_offset; + sg_dma_len(umem_dmabuf->first_sg) += + umem_dmabuf->first_sg_offset; + umem_dmabuf->first_sg = NULL; + umem_dmabuf->first_sg_offset = 0; + } + if (umem_dmabuf->last_sg) { + sg_dma_len(umem_dmabuf->last_sg) += + umem_dmabuf->last_sg_trim; + umem_dmabuf->last_sg = NULL; + umem_dmabuf->last_sg_trim = 0; + } + + dma_buf_unmap_attachment(umem_dmabuf->attach, umem_dmabuf->sgt, + DMA_BIDIRECTIONAL); + + umem_dmabuf->sgt = NULL; +} +EXPORT_SYMBOL(ib_umem_dmabuf_unmap_pages); + +struct ib_umem_dmabuf *ib_umem_dmabuf_get(struct ib_device *device, + unsigned long offset, size_t size, + int fd, int access, + const struct dma_buf_attach_ops *ops) +{ + struct dma_buf *dmabuf; + struct ib_umem_dmabuf *umem_dmabuf; + struct ib_umem *umem; + unsigned long end; + struct ib_umem_dmabuf *ret = ERR_PTR(-EINVAL); + + if (check_add_overflow(offset, (unsigned long)size, &end)) + return ret; + + if (unlikely(!ops || !ops->move_notify)) + return ret; + + dmabuf = dma_buf_get(fd); + if (IS_ERR(dmabuf)) + return ERR_CAST(dmabuf); + + if (dmabuf->size < end) + goto out_release_dmabuf; + + umem_dmabuf = kzalloc(sizeof(*umem_dmabuf), GFP_KERNEL); + if (!umem_dmabuf) { + ret = ERR_PTR(-ENOMEM); + goto out_release_dmabuf; + } + + umem = &umem_dmabuf->umem; + umem->ibdev = device; + umem->length = size; + umem->address = offset; + umem->writable = ib_access_writable(access); + umem->is_dmabuf = 1; + + if (!ib_umem_num_pages(umem)) + goto out_free_umem; + + umem_dmabuf->attach = dma_buf_dynamic_attach( + dmabuf, + device->dma_device, + ops, + umem_dmabuf); + if (IS_ERR(umem_dmabuf->attach)) { + ret = ERR_CAST(umem_dmabuf->attach); + goto out_free_umem; + } + return umem_dmabuf; + +out_free_umem: + kfree(umem_dmabuf); + +out_release_dmabuf: + dma_buf_put(dmabuf); + return ret; +} +EXPORT_SYMBOL(ib_umem_dmabuf_get); + +void ib_umem_dmabuf_release(struct ib_umem_dmabuf *umem_dmabuf) +{ + struct dma_buf *dmabuf = umem_dmabuf->attach->dmabuf; + + dma_buf_detach(dmabuf, umem_dmabuf->attach); + dma_buf_put(dmabuf); + kfree(umem_dmabuf); +} diff --git a/include/rdma/ib_umem.h b/include/rdma/ib_umem.h index 7752211c9638..676c57f5ca80 100644 --- a/include/rdma/ib_umem.h +++ b/include/rdma/ib_umem.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ /* * Copyright (c) 2007 Cisco Systems. All rights reserved. + * Copyright (c) 2020 Intel Corporation. All rights reserved. */ #ifndef IB_UMEM_H @@ -13,6 +14,7 @@ struct ib_ucontext; struct ib_umem_odp; +struct dma_buf_attach_ops; struct ib_umem { struct ib_device *ibdev; @@ -22,12 +24,29 @@ struct ib_umem { unsigned long address; u32 writable : 1; u32 is_odp : 1; + u32 is_dmabuf : 1; struct work_struct work; struct sg_table sg_head; int nmap; unsigned int sg_nents; }; +struct ib_umem_dmabuf { + struct ib_umem umem; + struct dma_buf_attachment *attach; + struct sg_table *sgt; + struct scatterlist *first_sg; + struct scatterlist *last_sg; + unsigned long first_sg_offset; + unsigned long last_sg_trim; + void *private; +}; + +static inline struct ib_umem_dmabuf *to_ib_umem_dmabuf(struct ib_umem *umem) +{ + return container_of(umem, struct ib_umem_dmabuf, umem); +} + /* Returns the offset of the umem start relative to the first page. */ static inline int ib_umem_offset(struct ib_umem *umem) { @@ -86,6 +105,7 @@ int ib_umem_copy_from(void *dst, struct ib_umem *umem, size_t offset, unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem, unsigned long pgsz_bitmap, unsigned long virt); + /** * ib_umem_find_best_pgoff - Find best HW page size * @@ -116,6 +136,14 @@ static inline unsigned long ib_umem_find_best_pgoff(struct ib_umem *umem, dma_addr & pgoff_bitmask); } +struct ib_umem_dmabuf *ib_umem_dmabuf_get(struct ib_device *device, + unsigned long offset, size_t size, + int fd, int access, + const struct dma_buf_attach_ops *ops); +int ib_umem_dmabuf_map_pages(struct ib_umem_dmabuf *umem_dmabuf); +void ib_umem_dmabuf_unmap_pages(struct ib_umem_dmabuf *umem_dmabuf); +void ib_umem_dmabuf_release(struct ib_umem_dmabuf *umem_dmabuf); + #else /* CONFIG_INFINIBAND_USER_MEM */ #include @@ -124,12 +152,12 @@ static inline struct ib_umem *ib_umem_get(struct ib_device *device, unsigned long addr, size_t size, int access) { - return ERR_PTR(-EINVAL); + return ERR_PTR(-EOPNOTSUPP); } static inline void ib_umem_release(struct ib_umem *umem) { } static inline int ib_umem_copy_from(void *dst, struct ib_umem *umem, size_t offset, size_t length) { - return -EINVAL; + return -EOPNOTSUPP; } static inline unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem, unsigned long pgsz_bitmap, @@ -143,7 +171,21 @@ static inline unsigned long ib_umem_find_best_pgoff(struct ib_umem *umem, { return 0; } +static inline +struct ib_umem_dmabuf *ib_umem_dmabuf_get(struct ib_device *device, + unsigned long offset, + size_t size, int fd, + int access, + struct dma_buf_attach_ops *ops) +{ + return ERR_PTR(-EOPNOTSUPP); +} +static inline int ib_umem_dmabuf_map_pages(struct ib_umem_dmabuf *umem_dmabuf) +{ + return -EOPNOTSUPP; +} +static inline void ib_umem_dmabuf_unmap_pages(struct ib_umem_dmabuf *umem_dmabuf) { } +static inline void ib_umem_dmabuf_release(struct ib_umem_dmabuf *umem_dmabuf) { } #endif /* CONFIG_INFINIBAND_USER_MEM */ - #endif /* IB_UMEM_H */ -- cgit v1.2.3 From 3bc489e8827a93b14d27211ae0576b3c1de85000 Mon Sep 17 00:00:00 2001 From: Jianxin Xiong Date: Tue, 15 Dec 2020 13:27:14 -0800 Subject: RDMA/core: Add device method for registering dma-buf based memory region Dma-buf based memory region requires one extra parameter and is processed quite differently. Adding a separate method allows clean separation from regular memory regions. Link: https://lore.kernel.org/r/1608067636-98073-3-git-send-email-jianxin.xiong@intel.com Signed-off-by: Jianxin Xiong Reviewed-by: Sean Hefty Acked-by: Michael J. Ruhl Acked-by: Christian Koenig Acked-by: Daniel Vetter Reviewed-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/device.c | 1 + include/rdma/ib_verbs.h | 6 +++++- 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index 3d08373c7797..c895d7bfa512 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -2681,6 +2681,7 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops) SET_DEVICE_OP(dev_ops, read_counters); SET_DEVICE_OP(dev_ops, reg_dm_mr); SET_DEVICE_OP(dev_ops, reg_user_mr); + SET_DEVICE_OP(dev_ops, reg_user_mr_dmabuf); SET_DEVICE_OP(dev_ops, req_ncomp_notif); SET_DEVICE_OP(dev_ops, req_notify_cq); SET_DEVICE_OP(dev_ops, rereg_user_mr); diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 9fed65bf9279..62e574c50555 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -2,7 +2,7 @@ /* * Copyright (c) 2004 Mellanox Technologies Ltd. All rights reserved. * Copyright (c) 2004 Infinicon Corporation. All rights reserved. - * Copyright (c) 2004 Intel Corporation. All rights reserved. + * Copyright (c) 2004, 2020 Intel Corporation. All rights reserved. * Copyright (c) 2004 Topspin Corporation. All rights reserved. * Copyright (c) 2004 Voltaire Corporation. All rights reserved. * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved. @@ -2434,6 +2434,10 @@ struct ib_device_ops { struct ib_mr *(*reg_user_mr)(struct ib_pd *pd, u64 start, u64 length, u64 virt_addr, int mr_access_flags, struct ib_udata *udata); + struct ib_mr *(*reg_user_mr_dmabuf)(struct ib_pd *pd, u64 offset, + u64 length, u64 virt_addr, int fd, + int mr_access_flags, + struct ib_udata *udata); struct ib_mr *(*rereg_user_mr)(struct ib_mr *mr, int flags, u64 start, u64 length, u64 virt_addr, int mr_access_flags, struct ib_pd *pd, -- cgit v1.2.3 From bfe0cc6eb2491aeae2bba02a305fcce13cd90624 Mon Sep 17 00:00:00 2001 From: Jianxin Xiong Date: Tue, 15 Dec 2020 13:27:15 -0800 Subject: RDMA/uverbs: Add uverbs command for dma-buf based MR registration Implement a new uverbs ioctl method for memory registration with file descriptor as an extra parameter. Link: https://lore.kernel.org/r/1608067636-98073-4-git-send-email-jianxin.xiong@intel.com Signed-off-by: Jianxin Xiong Reviewed-by: Sean Hefty Acked-by: Michael J. Ruhl Acked-by: Christian Koenig Acked-by: Daniel Vetter Reviewed-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/uverbs_std_types_mr.c | 117 +++++++++++++++++++++++++- include/uapi/rdma/ib_user_ioctl_cmds.h | 14 +++ 2 files changed, 129 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/core/uverbs_std_types_mr.c b/drivers/infiniband/core/uverbs_std_types_mr.c index dd4e76b26c74..f782d5e1aa25 100644 --- a/drivers/infiniband/core/uverbs_std_types_mr.c +++ b/drivers/infiniband/core/uverbs_std_types_mr.c @@ -1,5 +1,6 @@ /* * Copyright (c) 2018, Mellanox Technologies inc. All rights reserved. + * Copyright (c) 2020, Intel Corporation. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU @@ -182,6 +183,86 @@ static int UVERBS_HANDLER(UVERBS_METHOD_QUERY_MR)( return IS_UVERBS_COPY_ERR(ret) ? ret : 0; } +static int UVERBS_HANDLER(UVERBS_METHOD_REG_DMABUF_MR)( + struct uverbs_attr_bundle *attrs) +{ + struct ib_uobject *uobj = + uverbs_attr_get_uobject(attrs, UVERBS_ATTR_REG_DMABUF_MR_HANDLE); + struct ib_pd *pd = + uverbs_attr_get_obj(attrs, UVERBS_ATTR_REG_DMABUF_MR_PD_HANDLE); + struct ib_device *ib_dev = pd->device; + + u64 offset, length, iova; + u32 fd, access_flags; + struct ib_mr *mr; + int ret; + + if (!ib_dev->ops.reg_user_mr_dmabuf) + return -EOPNOTSUPP; + + ret = uverbs_copy_from(&offset, attrs, + UVERBS_ATTR_REG_DMABUF_MR_OFFSET); + if (ret) + return ret; + + ret = uverbs_copy_from(&length, attrs, + UVERBS_ATTR_REG_DMABUF_MR_LENGTH); + if (ret) + return ret; + + ret = uverbs_copy_from(&iova, attrs, + UVERBS_ATTR_REG_DMABUF_MR_IOVA); + if (ret) + return ret; + + if ((offset & ~PAGE_MASK) != (iova & ~PAGE_MASK)) + return -EINVAL; + + ret = uverbs_copy_from(&fd, attrs, + UVERBS_ATTR_REG_DMABUF_MR_FD); + if (ret) + return ret; + + ret = uverbs_get_flags32(&access_flags, attrs, + UVERBS_ATTR_REG_DMABUF_MR_ACCESS_FLAGS, + IB_ACCESS_LOCAL_WRITE | + IB_ACCESS_REMOTE_READ | + IB_ACCESS_REMOTE_WRITE | + IB_ACCESS_REMOTE_ATOMIC | + IB_ACCESS_RELAXED_ORDERING); + if (ret) + return ret; + + ret = ib_check_mr_access(ib_dev, access_flags); + if (ret) + return ret; + + mr = pd->device->ops.reg_user_mr_dmabuf(pd, offset, length, iova, fd, + access_flags, + &attrs->driver_udata); + if (IS_ERR(mr)) + return PTR_ERR(mr); + + mr->device = pd->device; + mr->pd = pd; + mr->type = IB_MR_TYPE_USER; + mr->uobject = uobj; + atomic_inc(&pd->usecnt); + + uobj->object = mr; + + uverbs_finalize_uobj_create(attrs, UVERBS_ATTR_REG_DMABUF_MR_HANDLE); + + ret = uverbs_copy_to(attrs, UVERBS_ATTR_REG_DMABUF_MR_RESP_LKEY, + &mr->lkey, sizeof(mr->lkey)); + if (ret) + return ret; + + ret = uverbs_copy_to(attrs, UVERBS_ATTR_REG_DMABUF_MR_RESP_RKEY, + &mr->rkey, sizeof(mr->rkey)); + return ret; +} + DECLARE_UVERBS_NAMED_METHOD( UVERBS_METHOD_ADVISE_MR, UVERBS_ATTR_IDR(UVERBS_ATTR_ADVISE_MR_PD_HANDLE, @@ -247,6 +328,37 @@ DECLARE_UVERBS_NAMED_METHOD( UVERBS_ATTR_TYPE(u32), UA_MANDATORY)); +DECLARE_UVERBS_NAMED_METHOD( + UVERBS_METHOD_REG_DMABUF_MR, + UVERBS_ATTR_IDR(UVERBS_ATTR_REG_DMABUF_MR_HANDLE, + UVERBS_OBJECT_MR, + UVERBS_ACCESS_NEW, + UA_MANDATORY), + UVERBS_ATTR_IDR(UVERBS_ATTR_REG_DMABUF_MR_PD_HANDLE, + UVERBS_OBJECT_PD, + UVERBS_ACCESS_READ, + UA_MANDATORY), + UVERBS_ATTR_PTR_IN(UVERBS_ATTR_REG_DMABUF_MR_OFFSET, + UVERBS_ATTR_TYPE(u64), + UA_MANDATORY), + UVERBS_ATTR_PTR_IN(UVERBS_ATTR_REG_DMABUF_MR_LENGTH, + UVERBS_ATTR_TYPE(u64), + UA_MANDATORY), + UVERBS_ATTR_PTR_IN(UVERBS_ATTR_REG_DMABUF_MR_IOVA, + UVERBS_ATTR_TYPE(u64), + UA_MANDATORY), + UVERBS_ATTR_PTR_IN(UVERBS_ATTR_REG_DMABUF_MR_FD, + UVERBS_ATTR_TYPE(u32), + UA_MANDATORY), + UVERBS_ATTR_FLAGS_IN(UVERBS_ATTR_REG_DMABUF_MR_ACCESS_FLAGS, + enum ib_access_flags), + UVERBS_ATTR_PTR_OUT(UVERBS_ATTR_REG_DMABUF_MR_RESP_LKEY, + UVERBS_ATTR_TYPE(u32), + UA_MANDATORY), + UVERBS_ATTR_PTR_OUT(UVERBS_ATTR_REG_DMABUF_MR_RESP_RKEY, + UVERBS_ATTR_TYPE(u32), + UA_MANDATORY)); + DECLARE_UVERBS_NAMED_METHOD_DESTROY( UVERBS_METHOD_MR_DESTROY, UVERBS_ATTR_IDR(UVERBS_ATTR_DESTROY_MR_HANDLE, @@ -257,10 +369,11 @@ DECLARE_UVERBS_NAMED_METHOD_DESTROY( DECLARE_UVERBS_NAMED_OBJECT( UVERBS_OBJECT_MR, UVERBS_TYPE_ALLOC_IDR(uverbs_free_mr), + &UVERBS_METHOD(UVERBS_METHOD_ADVISE_MR), &UVERBS_METHOD(UVERBS_METHOD_DM_MR_REG), &UVERBS_METHOD(UVERBS_METHOD_MR_DESTROY), - &UVERBS_METHOD(UVERBS_METHOD_ADVISE_MR), - &UVERBS_METHOD(UVERBS_METHOD_QUERY_MR)); + &UVERBS_METHOD(UVERBS_METHOD_QUERY_MR), + &UVERBS_METHOD(UVERBS_METHOD_REG_DMABUF_MR)); const struct uapi_definition uverbs_def_obj_mr[] = { UAPI_DEF_CHAIN_OBJ_TREE_NAMED(UVERBS_OBJECT_MR, diff --git a/include/uapi/rdma/ib_user_ioctl_cmds.h b/include/uapi/rdma/ib_user_ioctl_cmds.h index 7968a1845355..dafc7ebe545b 100644 --- a/include/uapi/rdma/ib_user_ioctl_cmds.h +++ b/include/uapi/rdma/ib_user_ioctl_cmds.h @@ -1,5 +1,6 @@ /* * Copyright (c) 2018, Mellanox Technologies inc. All rights reserved. + * Copyright (c) 2020, Intel Corporation. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU @@ -251,6 +252,7 @@ enum uverbs_methods_mr { UVERBS_METHOD_MR_DESTROY, UVERBS_METHOD_ADVISE_MR, UVERBS_METHOD_QUERY_MR, + UVERBS_METHOD_REG_DMABUF_MR, }; enum uverbs_attrs_mr_destroy_ids { @@ -272,6 +274,18 @@ enum uverbs_attrs_query_mr_cmd_attr_ids { UVERBS_ATTR_QUERY_MR_RESP_IOVA, }; +enum uverbs_attrs_reg_dmabuf_mr_cmd_attr_ids { + UVERBS_ATTR_REG_DMABUF_MR_HANDLE, + UVERBS_ATTR_REG_DMABUF_MR_PD_HANDLE, + UVERBS_ATTR_REG_DMABUF_MR_OFFSET, + UVERBS_ATTR_REG_DMABUF_MR_LENGTH, + UVERBS_ATTR_REG_DMABUF_MR_IOVA, + UVERBS_ATTR_REG_DMABUF_MR_FD, + UVERBS_ATTR_REG_DMABUF_MR_ACCESS_FLAGS, + UVERBS_ATTR_REG_DMABUF_MR_RESP_LKEY, + UVERBS_ATTR_REG_DMABUF_MR_RESP_RKEY, +}; + enum uverbs_attrs_create_counters_cmd_attr_ids { UVERBS_ATTR_CREATE_COUNTERS_HANDLE, }; -- cgit v1.2.3 From fcba4b2047a31a55e1cef73849363a3cf7c2736d Mon Sep 17 00:00:00 2001 From: Loic Poulain Date: Tue, 5 Jan 2021 17:44:35 +0100 Subject: mhi: unconstify mhi_event_config Some parameters may have to be determined at runtime. It is the case for the event ring MSI vector. Signed-off-by: Loic Poulain Reviewed-by: Manivannan Sadhasivam Signed-off-by: Manivannan Sadhasivam --- include/linux/mhi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mhi.h b/include/linux/mhi.h index 54afcae1709a..48f5c9168ae0 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -279,7 +279,7 @@ struct mhi_controller_config { u32 num_channels; const struct mhi_channel_config *ch_cfg; u32 num_events; - const struct mhi_event_config *event_cfg; + struct mhi_event_config *event_cfg; bool use_bounce_buf; bool m2_no_db; }; -- cgit v1.2.3 From 6ffcc18d9c0b4522c95aab71ff3ff5a56e699945 Mon Sep 17 00:00:00 2001 From: Carl Huang Date: Mon, 4 Jan 2021 18:11:28 +0800 Subject: mhi: use irq_flags if controller driver configures it If controller driver has specified the irq_flags, mhi uses this specified irq_flags. Otherwise, mhi uses default irq_flags. The purpose of this change is to support one MSI vector for QCA6390. MHI will use one same MSI vector too in this scenario. In case of one MSI vector, IRQ_NO_BALANCING is needed when irq handler is requested. The reason is if irq migration happens, the msi_data may change too. However, the msi_data is already programmed to QCA6390 hardware during initialization phase. This msi_data inconsistence will result in crash in kernel. Another issue is in case of one MSI vector, IRQF_NO_SUSPEND will trigger WARNINGS because QCA6390 wants to disable the IRQ during the suspend. To avoid above two issues, QCA6390 driver specifies the irq_flags in case of one MSI vector when mhi_register_controller is called. Signed-off-by: Carl Huang Reviewed-by: Manivannan Sadhasivam Signed-off-by: Manivannan Sadhasivam --- drivers/bus/mhi/core/init.c | 9 +++++++-- include/linux/mhi.h | 2 ++ 2 files changed, 9 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/bus/mhi/core/init.c b/drivers/bus/mhi/core/init.c index f0697f433c2f..aa575d3fb3ae 100644 --- a/drivers/bus/mhi/core/init.c +++ b/drivers/bus/mhi/core/init.c @@ -151,12 +151,17 @@ int mhi_init_irq_setup(struct mhi_controller *mhi_cntrl) { struct mhi_event *mhi_event = mhi_cntrl->mhi_event; struct device *dev = &mhi_cntrl->mhi_dev->dev; + unsigned long irq_flags = IRQF_SHARED | IRQF_NO_SUSPEND; int i, ret; + /* if controller driver has set irq_flags, use it */ + if (mhi_cntrl->irq_flags) + irq_flags = mhi_cntrl->irq_flags; + /* Setup BHI_INTVEC IRQ */ ret = request_threaded_irq(mhi_cntrl->irq[0], mhi_intvec_handler, mhi_intvec_threaded_handler, - IRQF_SHARED | IRQF_NO_SUSPEND, + irq_flags, "bhi", mhi_cntrl); if (ret) return ret; @@ -174,7 +179,7 @@ int mhi_init_irq_setup(struct mhi_controller *mhi_cntrl) ret = request_irq(mhi_cntrl->irq[mhi_event->irq], mhi_irq_handler, - IRQF_SHARED | IRQF_NO_SUSPEND, + irq_flags, "mhi", mhi_event); if (ret) { dev_err(dev, "Error requesting irq:%d for ev:%d\n", diff --git a/include/linux/mhi.h b/include/linux/mhi.h index 562862ff819c..b7138127664f 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -353,6 +353,7 @@ struct mhi_controller_config { * @fbc_download: MHI host needs to do complete image transfer (optional) * @pre_init: MHI host needs to do pre-initialization before power up * @wake_set: Device wakeup set flag + * @irq_flags: irq flags passed to request_irq (optional) * * Fields marked as (required) need to be populated by the controller driver * before calling mhi_register_controller(). For the fields marked as (optional) @@ -444,6 +445,7 @@ struct mhi_controller { bool fbc_download; bool pre_init; bool wake_set; + unsigned long irq_flags; }; /** -- cgit v1.2.3 From c52b7c807b0a6ae26582208a0b07c2a6a796b50f Mon Sep 17 00:00:00 2001 From: "Alexander A. Klimov" Date: Thu, 16 Jul 2020 21:52:27 +0200 Subject: encrypted-keys: Replace HTTP links with HTTPS ones Rationale: Reduces attack surface on kernel devs opening the links for MITM as HTTPS traffic is much harder to manipulate. Deterministic algorithm: For each file: If not .svg: For each line: If doesn't contain `\bxmlns\b`: For each link, `\bhttp://[^# \t\r\n]*(?:\w|/)`: If neither `\bgnu\.org/license`, nor `\bmozilla\.org/MPL\b`: If both the HTTP and HTTPS versions return 200 OK and serve the same content: Replace HTTP with HTTPS. Signed-off-by: Alexander A. Klimov Signed-off-by: David Howells Reviewed-by: Ben Boeckel --- include/keys/encrypted-type.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/keys/encrypted-type.h b/include/keys/encrypted-type.h index 38afb341c3f2..abfcbe02001a 100644 --- a/include/keys/encrypted-type.h +++ b/include/keys/encrypted-type.h @@ -2,7 +2,7 @@ /* * Copyright (C) 2010 IBM Corporation * Copyright (C) 2010 Politecnico di Torino, Italy - * TORSEC group -- http://security.polito.it + * TORSEC group -- https://security.polito.it * * Authors: * Mimi Zohar -- cgit v1.2.3 From 464e96aeb16ab4e071d353f69ebbddfa08c8d731 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Fri, 27 Nov 2020 11:15:43 -0800 Subject: keys: remove trailing semicolon in macro definition The macro use will already have a semicolon. Signed-off-by: Tom Rix Signed-off-by: David Howells Acked-by: Jarkko Sakkinen Reviewed-by: Ben Boeckel --- include/linux/key.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/key.h b/include/linux/key.h index 0f2e24f13c2b..1b0837c975b9 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -360,7 +360,7 @@ static inline struct key *request_key(struct key_type *type, * completion of keys undergoing construction with a non-interruptible wait. */ #define request_key_net(type, description, net, callout_info) \ - request_key_tag(type, description, net->key_domain, callout_info); + request_key_tag(type, description, net->key_domain, callout_info) /** * request_key_net_rcu - Request a key for a net namespace under RCU conditions @@ -372,7 +372,7 @@ static inline struct key *request_key(struct key_type *type, * network namespace are used. */ #define request_key_net_rcu(type, description, net) \ - request_key_rcu(type, description, net->key_domain); + request_key_rcu(type, description, net->key_domain) #endif /* CONFIG_NET */ extern int wait_for_key_construction(struct key *key, bool intr); -- cgit v1.2.3 From 09315b2d0d6944b9e249003c04abb88b5594a683 Mon Sep 17 00:00:00 2001 From: Tianjia Zhang Date: Wed, 18 Nov 2020 20:30:31 +0800 Subject: crypto: public_key: Remove redundant header file from public_key.h The akcipher.h header file was originally introduced in SM2, and then the definition of SM2 was moved to the existing code. This header file is left and should be removed. Signed-off-by: Tianjia Zhang Signed-off-by: David Howells Reviewed-by: Ben Boeckel --- include/crypto/public_key.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/crypto/public_key.h b/include/crypto/public_key.h index 948c5203ca9c..47accec68cb0 100644 --- a/include/crypto/public_key.h +++ b/include/crypto/public_key.h @@ -12,7 +12,6 @@ #include #include -#include /* * Cryptographic data for the public-key subtype of the asymmetric key type. -- cgit v1.2.3 From f14602caf4faef18999985bc87a414b552844ad2 Mon Sep 17 00:00:00 2001 From: Mickaël Salaün Date: Fri, 20 Nov 2020 19:04:22 +0100 Subject: PKCS#7: Fix missing include MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add missing linux/types.h for size_t. [DH: Changed from stddef.h] Signed-off-by: Mickaël Salaün Signed-off-by: David Howells Reviewed-by: Ben Boeckel --- include/linux/verification.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/verification.h b/include/linux/verification.h index 911ab7c2b1ab..a655923335ae 100644 --- a/include/linux/verification.h +++ b/include/linux/verification.h @@ -8,6 +8,8 @@ #ifndef _LINUX_VERIFICATION_H #define _LINUX_VERIFICATION_H +#include + /* * Indicate that both builtin trusted keys and secondary trusted keys * should be used. -- cgit v1.2.3 From 4993e1f9479a4161fd7d93e2b8b30b438f00cb0f Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 20 Nov 2020 19:04:23 +0100 Subject: certs: Fix blacklist flag type confusion MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit KEY_FLAG_KEEP is not meant to be passed to keyring_alloc() or key_alloc(), as these only take KEY_ALLOC_* flags. KEY_FLAG_KEEP has the same value as KEY_ALLOC_BYPASS_RESTRICTION, but fortunately only key_create_or_update() uses it. LSMs using the key_alloc hook don't check that flag. KEY_FLAG_KEEP is then ignored but fortunately (again) the root user cannot write to the blacklist keyring, so it is not possible to remove a key/hash from it. Fix this by adding a KEY_ALLOC_SET_KEEP flag that tells key_alloc() to set KEY_FLAG_KEEP on the new key. blacklist_init() can then, correctly, pass this to keyring_alloc(). We can also use this in ima_mok_init() rather than setting the flag manually. Note that this doesn't fix an observable bug with the current implementation but it is required to allow addition of new hashes to the blacklist in the future without making it possible for them to be removed. Fixes: 734114f8782f ("KEYS: Add a system blacklist keyring") Reported-by: Mickaël Salaün Signed-off-by: David Howells cc: Mickaël Salaün cc: Mimi Zohar Cc: David Woodhouse --- certs/blacklist.c | 2 +- include/linux/key.h | 1 + security/integrity/ima/ima_mok.c | 5 ++--- security/keys/key.c | 2 ++ 4 files changed, 6 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/certs/blacklist.c b/certs/blacklist.c index a888b934a1cd..029471947838 100644 --- a/certs/blacklist.c +++ b/certs/blacklist.c @@ -162,7 +162,7 @@ static int __init blacklist_init(void) KEY_USR_VIEW | KEY_USR_READ | KEY_USR_SEARCH, KEY_ALLOC_NOT_IN_QUOTA | - KEY_FLAG_KEEP, + KEY_ALLOC_SET_KEEP, NULL, NULL); if (IS_ERR(blacklist_keyring)) panic("Can't allocate system blacklist keyring\n"); diff --git a/include/linux/key.h b/include/linux/key.h index 1b0837c975b9..7febc4881363 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -289,6 +289,7 @@ extern struct key *key_alloc(struct key_type *type, #define KEY_ALLOC_BUILT_IN 0x0004 /* Key is built into kernel */ #define KEY_ALLOC_BYPASS_RESTRICTION 0x0008 /* Override the check on restricted keyrings */ #define KEY_ALLOC_UID_KEYRING 0x0010 /* allocating a user or user session keyring */ +#define KEY_ALLOC_SET_KEEP 0x0020 /* Set the KEEP flag on the key/keyring */ extern void key_revoke(struct key *key); extern void key_invalidate(struct key *key); diff --git a/security/integrity/ima/ima_mok.c b/security/integrity/ima/ima_mok.c index 36cadadbfba4..1e5c01916173 100644 --- a/security/integrity/ima/ima_mok.c +++ b/security/integrity/ima/ima_mok.c @@ -38,13 +38,12 @@ __init int ima_mok_init(void) (KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_VIEW | KEY_USR_READ | KEY_USR_WRITE | KEY_USR_SEARCH, - KEY_ALLOC_NOT_IN_QUOTA, + KEY_ALLOC_NOT_IN_QUOTA | + KEY_ALLOC_SET_KEEP, restriction, NULL); if (IS_ERR(ima_blacklist_keyring)) panic("Can't allocate IMA blacklist keyring."); - - set_bit(KEY_FLAG_KEEP, &ima_blacklist_keyring->flags); return 0; } device_initcall(ima_mok_init); diff --git a/security/keys/key.c b/security/keys/key.c index ebe752b137aa..c45afdd1dfbb 100644 --- a/security/keys/key.c +++ b/security/keys/key.c @@ -303,6 +303,8 @@ struct key *key_alloc(struct key_type *type, const char *desc, key->flags |= 1 << KEY_FLAG_BUILTIN; if (flags & KEY_ALLOC_UID_KEYRING) key->flags |= 1 << KEY_FLAG_UID_KEYRING; + if (flags & KEY_ALLOC_SET_KEEP) + key->flags |= 1 << KEY_FLAG_KEEP; #ifdef KEY_DEBUGGING key->magic = KEY_DEBUG_MAGIC; -- cgit v1.2.3 From 4c9a3a6c9c5478ce6b4b9db6c964244474676bcb Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 14 Jan 2021 09:04:37 +0100 Subject: parport: fix a kernel-doc markup The kernel-doc markup inside share.c is actually for __parport_register_driver. The actual goal seems to be to document parport_register_driver(). So, fix the existing markup and add a new one. Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/dc0778af8c466cc667409ead05876a5cfd3cbece.1610610937.git.mchehab+huawei@kernel.org Signed-off-by: Jonathan Corbet --- drivers/parport/share.c | 2 +- include/linux/parport.h | 31 +++++++++++++++++++++++++++++++ 2 files changed, 32 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/parport/share.c b/drivers/parport/share.c index 7fec4fefe151..62f8407923d4 100644 --- a/drivers/parport/share.c +++ b/drivers/parport/share.c @@ -243,7 +243,7 @@ static int port_detect(struct device *dev, void *dev_drv) } /** - * parport_register_driver - register a parallel port device driver + * __parport_register_driver - register a parallel port device driver * @drv: structure describing the driver * @owner: owner module of drv * @mod_name: module name string diff --git a/include/linux/parport.h b/include/linux/parport.h index 1fb508c19e83..f981f794c850 100644 --- a/include/linux/parport.h +++ b/include/linux/parport.h @@ -297,6 +297,37 @@ int __must_check __parport_register_driver(struct parport_driver *, * parport_register_driver must be a macro so that KBUILD_MODNAME can * be expanded */ + +/** + * parport_register_driver - register a parallel port device driver + * @driver: structure describing the driver + * + * This can be called by a parallel port device driver in order + * to receive notifications about ports being found in the + * system, as well as ports no longer available. + * + * If devmodel is true then the new device model is used + * for registration. + * + * The @driver structure is allocated by the caller and must not be + * deallocated until after calling parport_unregister_driver(). + * + * If using the non device model: + * The driver's attach() function may block. The port that + * attach() is given will be valid for the duration of the + * callback, but if the driver wants to take a copy of the + * pointer it must call parport_get_port() to do so. Calling + * parport_register_device() on that port will do this for you. + * + * The driver's detach() function may block. The port that + * detach() is given will be valid for the duration of the + * callback, but if the driver wants to take a copy of the + * pointer it must call parport_get_port() to do so. + * + * + * Returns 0 on success. The non device model will always succeeds. + * but the new device model can fail and will return the error code. + **/ #define parport_register_driver(driver) \ __parport_register_driver(driver, THIS_MODULE, KBUILD_MODNAME) -- cgit v1.2.3 From e23bd83368af41ce420bd0eacb32817ccf7d3ca2 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 14 Jan 2021 09:04:41 +0100 Subject: firmware: stratix10-svc: fix kernel-doc markups There are some common comments marked, instead, with kernel-doc notation, which won't work. While here, rename an identifier, in order to match the function prototype below kernel-doc markup. Acked-by: Richard Gong Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/02a1eb47767e01e875d8840805b8b2d4f3c6bdee.1610610937.git.mchehab+huawei@kernel.org Signed-off-by: Jonathan Corbet --- include/linux/firmware/intel/stratix10-svc-client.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/firmware/intel/stratix10-svc-client.h b/include/linux/firmware/intel/stratix10-svc-client.h index a93d85932eb9..ebc295647581 100644 --- a/include/linux/firmware/intel/stratix10-svc-client.h +++ b/include/linux/firmware/intel/stratix10-svc-client.h @@ -6,7 +6,7 @@ #ifndef __STRATIX10_SVC_CLIENT_H #define __STRATIX10_SVC_CLIENT_H -/** +/* * Service layer driver supports client names * * fpga: for FPGA configuration @@ -15,7 +15,7 @@ #define SVC_CLIENT_FPGA "fpga" #define SVC_CLIENT_RSU "rsu" -/** +/* * Status of the sent command, in bit number * * SVC_STATUS_OK: @@ -50,7 +50,7 @@ #define SVC_STATUS_ERROR 5 #define SVC_STATUS_NO_SUPPORT 6 -/** +/* * Flag bit for COMMAND_RECONFIG * * COMMAND_RECONFIG_FLAG_PARTIAL: @@ -58,7 +58,7 @@ */ #define COMMAND_RECONFIG_FLAG_PARTIAL 1 -/** +/* * Timeout settings for service clients: * timeout value used in Stratix10 FPGA manager driver. * timeout value used in RSU driver @@ -218,7 +218,7 @@ void stratix10_svc_free_memory(struct stratix10_svc_chan *chan, void *kaddr); int stratix10_svc_send(struct stratix10_svc_chan *chan, void *msg); /** - * intel_svc_done() - complete service request + * stratix10_svc_done() - complete service request * @chan: service channel assigned to the client * * This function is used by service client to inform service layer that -- cgit v1.2.3 From 3aa1141f9916af3258e2bc69e294e2cc07d2ddf1 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 14 Jan 2021 09:04:42 +0100 Subject: connector: fix a kernel-doc markup A function has a different name between their prototype and its kernel-doc markup. Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/889cfb141a98ae06d5bc79b744786ec2e8f92d93.1610610937.git.mchehab+huawei@kernel.org Signed-off-by: Jonathan Corbet --- include/linux/connector.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/connector.h b/include/linux/connector.h index 8ea860efea37..487350bb19c3 100644 --- a/include/linux/connector.h +++ b/include/linux/connector.h @@ -99,7 +99,7 @@ void cn_del_callback(const struct cb_id *id); int cn_netlink_send_mult(struct cn_msg *msg, u16 len, u32 portid, u32 group, gfp_t gfp_mask); /** - * cn_netlink_send_mult - Sends message to the specified groups. + * cn_netlink_send - Sends message to the specified groups. * * @msg: message header(with attached data). * @portid: destination port. -- cgit v1.2.3 From 909782ad0a36e4e5f875a431e280cba7b9b046fa Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 14 Jan 2021 09:04:44 +0100 Subject: memblock: fix kernel-doc markups Some identifiers have different names between their prototypes and the kernel-doc markup. Acked-by: Mike Rapoport Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/f3c65f61367993a607f9daf9dc1a3bdab1f0a040.1610610937.git.mchehab+huawei@kernel.org Signed-off-by: Jonathan Corbet --- include/linux/memblock.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index b93c44b9121e..9cc6da7b513e 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -272,7 +272,7 @@ void __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone, unsigned long *out_spfn, unsigned long *out_epfn); /** - * for_each_free_mem_range_in_zone - iterate through zone specific free + * for_each_free_mem_pfn_range_in_zone - iterate through zone specific free * memblock areas * @i: u64 used as loop variable * @zone: zone in which all of the memory blocks reside @@ -292,7 +292,7 @@ void __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone, __next_mem_pfn_range_in_zone(&i, zone, p_start, p_end)) /** - * for_each_free_mem_range_in_zone_from - iterate through zone specific + * for_each_free_mem_pfn_range_in_zone_from - iterate through zone specific * free memblock areas from a given point * @i: u64 used as loop variable * @zone: zone in which all of the memory blocks reside -- cgit v1.2.3 From 484cac791015e786f857c1cd98b7696aaf1e8a7a Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 14 Jan 2021 09:04:45 +0100 Subject: w1: fix a kernel-doc markup A function has a different name between their prototype and its kernel-doc markup. Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/2dc136ff6290d7c8919599d21bee244f31647c8c.1610610937.git.mchehab+huawei@kernel.org Signed-off-by: Jonathan Corbet --- include/linux/w1.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/w1.h b/include/linux/w1.h index 949d3b10e531..9a2a0ef39018 100644 --- a/include/linux/w1.h +++ b/include/linux/w1.h @@ -280,7 +280,7 @@ int w1_register_family(struct w1_family *family); void w1_unregister_family(struct w1_family *family); /** - * module_w1_driver() - Helper macro for registering a 1-Wire families + * module_w1_family() - Helper macro for registering a 1-Wire families * @__w1_family: w1_family struct * * Helper macro for 1-Wire families which do not do anything special in module -- cgit v1.2.3 From 660d2062190db131d2feaf19914e90f868fe285c Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 13 Jan 2021 10:11:35 +0100 Subject: crypto - shash: reduce minimum alignment of shash_desc structure Unlike many other structure types defined in the crypto API, the 'shash_desc' structure is permitted to live on the stack, which implies its contents may not be accessed by DMA masters. (This is due to the fact that the stack may be located in the vmalloc area, which requires a different virtual-to-physical translation than the one implemented by the DMA subsystem) Our definition of CRYPTO_MINALIGN_ATTR is based on ARCH_KMALLOC_MINALIGN, which may take DMA constraints into account on architectures that support non-cache coherent DMA such as ARM and arm64. In this case, the value is chosen to reflect the largest cacheline size in the system, in order to ensure that explicit cache maintenance as required by non-coherent DMA masters does not affect adjacent, unrelated slab allocations. On arm64, this value is currently set at 128 bytes. This means that applying CRYPTO_MINALIGN_ATTR to struct shash_desc is both unnecessary (as it is never used for DMA), and undesirable, given that it wastes stack space (on arm64, performing the alignment costs 112 bytes in the worst case, and the hole between the 'tfm' and '__ctx' members takes up another 120 bytes, resulting in an increased stack footprint of up to 232 bytes.) So instead, let's switch to the minimum SLAB alignment, which does not take DMA constraints into account. Note that this is a no-op for x86. Signed-off-by: Ard Biesheuvel Signed-off-by: Herbert Xu --- include/crypto/hash.h | 8 ++++---- include/linux/crypto.h | 9 ++++++--- 2 files changed, 10 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/crypto/hash.h b/include/crypto/hash.h index af2ff31ff619..13f8a6a54ca8 100644 --- a/include/crypto/hash.h +++ b/include/crypto/hash.h @@ -149,7 +149,7 @@ struct ahash_alg { struct shash_desc { struct crypto_shash *tfm; - void *__ctx[] CRYPTO_MINALIGN_ATTR; + void *__ctx[] __aligned(ARCH_SLAB_MINALIGN); }; #define HASH_MAX_DIGESTSIZE 64 @@ -162,9 +162,9 @@ struct shash_desc { #define HASH_MAX_STATESIZE 512 -#define SHASH_DESC_ON_STACK(shash, ctx) \ - char __##shash##_desc[sizeof(struct shash_desc) + \ - HASH_MAX_DESCSIZE] CRYPTO_MINALIGN_ATTR; \ +#define SHASH_DESC_ON_STACK(shash, ctx) \ + char __##shash##_desc[sizeof(struct shash_desc) + HASH_MAX_DESCSIZE] \ + __aligned(__alignof__(struct shash_desc)); \ struct shash_desc *shash = (struct shash_desc *)__##shash##_desc /** diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 9b55cd6b1f1b..da5e0d74bb2f 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -151,9 +151,12 @@ * The macro CRYPTO_MINALIGN_ATTR (along with the void * type in the actual * declaration) is used to ensure that the crypto_tfm context structure is * aligned correctly for the given architecture so that there are no alignment - * faults for C data types. In particular, this is required on platforms such - * as arm where pointers are 32-bit aligned but there are data types such as - * u64 which require 64-bit alignment. + * faults for C data types. On architectures that support non-cache coherent + * DMA, such as ARM or arm64, it also takes into account the minimal alignment + * that is required to ensure that the context struct member does not share any + * cachelines with the rest of the struct. This is needed to ensure that cache + * maintenance for non-coherent DMA (cache invalidation in particular) does not + * affect data that may be accessed by the CPU concurrently. */ #define CRYPTO_MINALIGN ARCH_KMALLOC_MINALIGN -- cgit v1.2.3 From bfb3939c51d51c0de794da14f33c13e36d2e4f3d Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Sat, 9 Jan 2021 13:43:05 +0100 Subject: i2c: refactor documentation of struct i2c_msg The information about 'i2c_msg' was spread between kdoc and comments. Move all the explanations to kdoc and duplicate only the requirements for the flags in the comments. Also, add some redundancy and fix some typos while here. Signed-off-by: Wolfram Sang Signed-off-by: Wolfram Sang --- include/uapi/linux/i2c.h | 91 +++++++++++++++++++++++++++++------------------- 1 file changed, 55 insertions(+), 36 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/i2c.h b/include/uapi/linux/i2c.h index f71a1751cacf..8d2f59f53324 100644 --- a/include/uapi/linux/i2c.h +++ b/include/uapi/linux/i2c.h @@ -32,18 +32,41 @@ /** * struct i2c_msg - an I2C transaction segment beginning with START - * @addr: Slave address, either seven or ten bits. When this is a ten - * bit address, I2C_M_TEN must be set in @flags and the adapter - * must support I2C_FUNC_10BIT_ADDR. - * @flags: I2C_M_RD is handled by all adapters. No other flags may be - * provided unless the adapter exported the relevant I2C_FUNC_* - * flags through i2c_check_functionality(). - * @len: Number of data bytes in @buf being read from or written to the - * I2C slave address. For read transactions where I2C_M_RECV_LEN - * is set, the caller guarantees that this buffer can hold up to - * 32 bytes in addition to the initial length byte sent by the - * slave (plus, if used, the SMBus PEC); and this value will be - * incremented by the number of block data bytes received. + * + * @addr: Slave address, either 7 or 10 bits. When this is a 10 bit address, + * %I2C_M_TEN must be set in @flags and the adapter must support + * %I2C_FUNC_10BIT_ADDR. + * + * @flags: + * Supported by all adapters: + * %I2C_M_RD: read data (from slave to master). Guaranteed to be 0x0001! + * + * Optional: + * %I2C_M_DMA_SAFE: the buffer of this message is DMA safe. Makes only sense + * in kernelspace, because userspace buffers are copied anyway + * + * Only if I2C_FUNC_10BIT_ADDR is set: + * %I2C_M_TEN: this is a 10 bit chip address + * + * Only if I2C_FUNC_SMBUS_READ_BLOCK_DATA is set: + * %I2C_M_RECV_LEN: message length will be first received byte + * + * Only if I2C_FUNC_NOSTART is set: + * %I2C_M_NOSTART: skip repeated start sequence + + * Only if I2C_FUNC_PROTOCOL_MANGLING is set: + * %I2C_M_NO_RD_ACK: in a read message, master ACK/NACK bit is skipped + * %I2C_M_IGNORE_NAK: treat NACK from client as ACK + * %I2C_M_REV_DIR_ADDR: toggles the Rd/Wr bit + * %I2C_M_STOP: force a STOP condition after the message + * + * @len: Number of data bytes in @buf being read from or written to the I2C + * slave address. For read transactions where %I2C_M_RECV_LEN is set, the + * caller guarantees that this buffer can hold up to %I2C_SMBUS_BLOCK_MAX + * bytes in addition to the initial length byte sent by the slave (plus, + * if used, the SMBus PEC); and this value will be incremented by the number + * of block data bytes received. + * * @buf: The buffer into which data is read, or from which it's written. * * An i2c_msg is the low level representation of one segment of an I2C @@ -60,40 +83,36 @@ * group, it is followed by a STOP. Otherwise it is followed by the next * @i2c_msg transaction segment, beginning with a (repeated) START. * - * Alternatively, when the adapter supports I2C_FUNC_PROTOCOL_MANGLING then + * Alternatively, when the adapter supports %I2C_FUNC_PROTOCOL_MANGLING then * passing certain @flags may have changed those standard protocol behaviors. * Those flags are only for use with broken/nonconforming slaves, and with - * adapters which are known to support the specific mangling options they - * need (one or more of IGNORE_NAK, NO_RD_ACK, NOSTART, and REV_DIR_ADDR). + * adapters which are known to support the specific mangling options they need. */ struct i2c_msg { - __u16 addr; /* slave address */ + __u16 addr; __u16 flags; -#define I2C_M_RD 0x0001 /* read data, from slave to master */ - /* I2C_M_RD is guaranteed to be 0x0001! */ -#define I2C_M_TEN 0x0010 /* this is a ten bit chip address */ -#define I2C_M_DMA_SAFE 0x0200 /* the buffer of this message is DMA safe */ - /* makes only sense in kernelspace */ - /* userspace buffers are copied anyway */ -#define I2C_M_RECV_LEN 0x0400 /* length will be first received byte */ -#define I2C_M_NO_RD_ACK 0x0800 /* if I2C_FUNC_PROTOCOL_MANGLING */ -#define I2C_M_IGNORE_NAK 0x1000 /* if I2C_FUNC_PROTOCOL_MANGLING */ -#define I2C_M_REV_DIR_ADDR 0x2000 /* if I2C_FUNC_PROTOCOL_MANGLING */ -#define I2C_M_NOSTART 0x4000 /* if I2C_FUNC_NOSTART */ -#define I2C_M_STOP 0x8000 /* if I2C_FUNC_PROTOCOL_MANGLING */ - __u16 len; /* msg length */ - __u8 *buf; /* pointer to msg data */ +#define I2C_M_RD 0x0001 /* guaranteed to be 0x0001! */ +#define I2C_M_TEN 0x0010 /* use only if I2C_FUNC_10BIT_ADDR */ +#define I2C_M_DMA_SAFE 0x0200 /* use only in kernel space */ +#define I2C_M_RECV_LEN 0x0400 /* use only if I2C_FUNC_SMBUS_READ_BLOCK_DATA */ +#define I2C_M_NO_RD_ACK 0x0800 /* use only if I2C_FUNC_PROTOCOL_MANGLING */ +#define I2C_M_IGNORE_NAK 0x1000 /* use only if I2C_FUNC_PROTOCOL_MANGLING */ +#define I2C_M_REV_DIR_ADDR 0x2000 /* use only if I2C_FUNC_PROTOCOL_MANGLING */ +#define I2C_M_NOSTART 0x4000 /* use only if I2C_FUNC_NOSTART */ +#define I2C_M_STOP 0x8000 /* use only if I2C_FUNC_PROTOCOL_MANGLING */ + __u16 len; + __u8 *buf; }; /* To determine what functionality is present */ #define I2C_FUNC_I2C 0x00000001 -#define I2C_FUNC_10BIT_ADDR 0x00000002 -#define I2C_FUNC_PROTOCOL_MANGLING 0x00000004 /* I2C_M_IGNORE_NAK etc. */ +#define I2C_FUNC_10BIT_ADDR 0x00000002 /* required for I2C_M_TEN */ +#define I2C_FUNC_PROTOCOL_MANGLING 0x00000004 /* required for I2C_M_IGNORE_NAK etc. */ #define I2C_FUNC_SMBUS_PEC 0x00000008 -#define I2C_FUNC_NOSTART 0x00000010 /* I2C_M_NOSTART */ +#define I2C_FUNC_NOSTART 0x00000010 /* required for I2C_M_NOSTART */ #define I2C_FUNC_SLAVE 0x00000020 -#define I2C_FUNC_SMBUS_BLOCK_PROC_CALL 0x00008000 /* SMBus 2.0 */ +#define I2C_FUNC_SMBUS_BLOCK_PROC_CALL 0x00008000 /* SMBus 2.0 or later */ #define I2C_FUNC_SMBUS_QUICK 0x00010000 #define I2C_FUNC_SMBUS_READ_BYTE 0x00020000 #define I2C_FUNC_SMBUS_WRITE_BYTE 0x00040000 @@ -102,11 +121,11 @@ struct i2c_msg { #define I2C_FUNC_SMBUS_READ_WORD_DATA 0x00200000 #define I2C_FUNC_SMBUS_WRITE_WORD_DATA 0x00400000 #define I2C_FUNC_SMBUS_PROC_CALL 0x00800000 -#define I2C_FUNC_SMBUS_READ_BLOCK_DATA 0x01000000 +#define I2C_FUNC_SMBUS_READ_BLOCK_DATA 0x01000000 /* required for I2C_M_RECV_LEN */ #define I2C_FUNC_SMBUS_WRITE_BLOCK_DATA 0x02000000 #define I2C_FUNC_SMBUS_READ_I2C_BLOCK 0x04000000 /* I2C-like block xfer */ #define I2C_FUNC_SMBUS_WRITE_I2C_BLOCK 0x08000000 /* w/ 1-byte reg. addr. */ -#define I2C_FUNC_SMBUS_HOST_NOTIFY 0x10000000 +#define I2C_FUNC_SMBUS_HOST_NOTIFY 0x10000000 /* SMBus 2.0 or later */ #define I2C_FUNC_SMBUS_BYTE (I2C_FUNC_SMBUS_READ_BYTE | \ I2C_FUNC_SMBUS_WRITE_BYTE) -- cgit v1.2.3 From deb0d3351b0cb7233206317ca1774bda312de28e Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Sat, 9 Jan 2021 13:43:06 +0100 Subject: i2c: remove licence boilerplate from main UAPI header Remove boilerplate because we now have the SPDX header. Signed-off-by: Wolfram Sang Signed-off-by: Wolfram Sang --- include/uapi/linux/i2c.h | 32 +++++++------------------------- 1 file changed, 7 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/i2c.h b/include/uapi/linux/i2c.h index 8d2f59f53324..7786551eb177 100644 --- a/include/uapi/linux/i2c.h +++ b/include/uapi/linux/i2c.h @@ -1,29 +1,11 @@ /* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ -/* ------------------------------------------------------------------------- */ -/* */ -/* i2c.h - definitions for the i2c-bus interface */ -/* */ -/* ------------------------------------------------------------------------- */ -/* Copyright (C) 1995-2000 Simon G. Vogl - - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License as published by - the Free Software Foundation; either version 2 of the License, or - (at your option) any later version. - - This program is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - GNU General Public License for more details. - - You should have received a copy of the GNU General Public License - along with this program; if not, write to the Free Software - Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, - MA 02110-1301 USA. */ -/* ------------------------------------------------------------------------- */ - -/* With some changes from Kyösti Mälkki and - Frodo Looijaard */ +/* + * i2c.h - definitions for the I2C bus interface + * + * Copyright (C) 1995-2000 Simon G. Vogl + * With some changes from Kyösti Mälkki and + * Frodo Looijaard + */ #ifndef _UAPI_LINUX_I2C_H #define _UAPI_LINUX_I2C_H -- cgit v1.2.3 From 1713d66cae8acdf3d34bafe09598fec9d1fb4793 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Sat, 9 Jan 2021 13:43:07 +0100 Subject: i2c: remove licence boilerplate from i2c-dev UAPI header Remove boilerplate because we now have the SPDX header. Signed-off-by: Wolfram Sang Signed-off-by: Wolfram Sang --- include/uapi/linux/i2c-dev.h | 25 +++++-------------------- 1 file changed, 5 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/i2c-dev.h b/include/uapi/linux/i2c-dev.h index 85f8047afcf2..1c4cec4ddd84 100644 --- a/include/uapi/linux/i2c-dev.h +++ b/include/uapi/linux/i2c-dev.h @@ -1,25 +1,10 @@ /* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* - i2c-dev.h - i2c-bus driver, char device interface - - Copyright (C) 1995-97 Simon G. Vogl - Copyright (C) 1998-99 Frodo Looijaard - - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License as published by - the Free Software Foundation; either version 2 of the License, or - (at your option) any later version. - - This program is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - GNU General Public License for more details. - - You should have received a copy of the GNU General Public License - along with this program; if not, write to the Free Software - Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, - MA 02110-1301 USA. -*/ + * i2c-dev.h - I2C bus char device interface + * + * Copyright (C) 1995-97 Simon G. Vogl + * Copyright (C) 1998-99 Frodo Looijaard + */ #ifndef _UAPI_LINUX_I2C_DEV_H #define _UAPI_LINUX_I2C_DEV_H -- cgit v1.2.3 From 21500aa84024b3fc541197b2041d80538539740d Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Sat, 9 Jan 2021 13:43:09 +0100 Subject: i2c: uapi: add macro to describe support for all SMBus transfers Some I2C bus master drivers which support I2C_M_RECV_LEN do not set the functionality bits of the now supported SMBus transfers. Add a convenience macro to make this very simple. Signed-off-by: Wolfram Sang Signed-off-by: Wolfram Sang --- include/uapi/linux/i2c.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/i2c.h b/include/uapi/linux/i2c.h index 7786551eb177..92326ebde350 100644 --- a/include/uapi/linux/i2c.h +++ b/include/uapi/linux/i2c.h @@ -129,6 +129,11 @@ struct i2c_msg { I2C_FUNC_SMBUS_I2C_BLOCK | \ I2C_FUNC_SMBUS_PEC) +/* if I2C_M_RECV_LEN is also supported */ +#define I2C_FUNC_SMBUS_EMUL_ALL (I2C_FUNC_SMBUS_EMUL | \ + I2C_FUNC_SMBUS_READ_BLOCK_DATA | \ + I2C_FUNC_SMBUS_BLOCK_PROC_CALL) + /* * Data for SMBus Messages */ -- cgit v1.2.3 From 87199e4c2490ab4ba0483a5ae5690c19b5c3d45b Mon Sep 17 00:00:00 2001 From: Radhakrishna Sripada Date: Thu, 14 Jan 2021 22:13:12 +0200 Subject: drm/framebuffer: Format modifier for Intel Gen 12 render compression with Clear Color Gen12 display can decompress surfaces compressed by render engine with Clear Color, add a new modifier as the driver needs to know the surface was compressed by render engine. V2: Description changes as suggested by Rafael. V3: Mention the Clear Color size of 64 bits in the comments(DK) v4: Fix trailing whitespaces v5: Explain Clear Color in the documentation. v6: Documentation Nitpicks(Nanley) Cc: Ville Syrjala Cc: Dhinakaran Pandiyan Cc: Kalyan Kondapally Cc: Rafael Antognolli Cc: Nanley Chery Signed-off-by: Radhakrishna Sripada Signed-off-by: Imre Deak Acked-by: Daniel Vetter Acked-by: Jani Nikula Acked-by: Nanley Chery Reviewed-by: Mika Kahola Link: https://patchwork.freedesktop.org/patch/msgid/20210114201314.783648-2-imre.deak@intel.com --- include/uapi/drm/drm_fourcc.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include') diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h index 723c8e23ca87..8782a7260c6f 100644 --- a/include/uapi/drm/drm_fourcc.h +++ b/include/uapi/drm/drm_fourcc.h @@ -527,6 +527,25 @@ extern "C" { */ #define I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS fourcc_mod_code(INTEL, 7) +/* + * Intel Color Control Surface with Clear Color (CCS) for Gen-12 render + * compression. + * + * The main surface is Y-tiled and is at plane index 0 whereas CCS is linear + * and at index 1. The clear color is stored at index 2, and the pitch should + * be ignored. The clear color structure is 256 bits. The first 128 bits + * represents Raw Clear Color Red, Green, Blue and Alpha color each represented + * by 32 bits. The raw clear color is consumed by the 3d engine and generates + * the converted clear color of size 64 bits. The first 32 bits store the Lower + * Converted Clear Color value and the next 32 bits store the Higher Converted + * Clear Color value when applicable. The Converted Clear Color values are + * consumed by the DE. The last 64 bits are used to store Color Discard Enable + * and Depth Clear Value Valid which are ignored by the DE. A CCS cache line + * corresponds to an area of 4x1 tiles in the main surface. The main surface + * pitch is required to be a multiple of 4 tile widths. + */ +#define I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC fourcc_mod_code(INTEL, 8) + /* * Tiled, NV12MT, grouped in 64 (pixels) x 32 (lines) -sized macroblocks * -- cgit v1.2.3 From d8cd784ff7b3439c21cbad94b5b1f1f8cf7c36e4 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Wed, 13 Jan 2021 10:04:44 +0100 Subject: scsi: aic7xxx: aic79xx: Drop internal SCSI message definition Use the standard SCSI message definitions instead of the driver-internal ones. Link: https://lore.kernel.org/r/20210113090500.129644-20-hare@suse.de Reviewed-by: Christoph Hellwig Signed-off-by: Hannes Reinecke Signed-off-by: Martin K. Petersen --- drivers/scsi/aic7xxx/aic79xx_core.c | 138 ++++++++++++++++++------------------ drivers/scsi/aic7xxx/aic79xx_osm.c | 4 +- drivers/scsi/aic7xxx/aic7xxx_core.c | 126 ++++++++++++++++---------------- drivers/scsi/aic7xxx/aic7xxx_osm.c | 5 +- drivers/scsi/aic7xxx/scsi_message.h | 41 ----------- include/scsi/scsi.h | 1 + 6 files changed, 138 insertions(+), 177 deletions(-) (limited to 'include') diff --git a/drivers/scsi/aic7xxx/aic79xx_core.c b/drivers/scsi/aic7xxx/aic79xx_core.c index f179e05fb8c3..3e3100dbfda3 100644 --- a/drivers/scsi/aic7xxx/aic79xx_core.c +++ b/drivers/scsi/aic7xxx/aic79xx_core.c @@ -73,16 +73,16 @@ static const u_int num_errors = ARRAY_SIZE(ahd_hard_errors); static const struct ahd_phase_table_entry ahd_phase_table[] = { - { P_DATAOUT, MSG_NOOP, "in Data-out phase" }, - { P_DATAIN, MSG_INITIATOR_DET_ERR, "in Data-in phase" }, - { P_DATAOUT_DT, MSG_NOOP, "in DT Data-out phase" }, - { P_DATAIN_DT, MSG_INITIATOR_DET_ERR, "in DT Data-in phase" }, - { P_COMMAND, MSG_NOOP, "in Command phase" }, - { P_MESGOUT, MSG_NOOP, "in Message-out phase" }, - { P_STATUS, MSG_INITIATOR_DET_ERR, "in Status phase" }, + { P_DATAOUT, NOP, "in Data-out phase" }, + { P_DATAIN, INITIATOR_ERROR, "in Data-in phase" }, + { P_DATAOUT_DT, NOP, "in DT Data-out phase" }, + { P_DATAIN_DT, INITIATOR_ERROR, "in DT Data-in phase" }, + { P_COMMAND, NOP, "in Command phase" }, + { P_MESGOUT, NOP, "in Message-out phase" }, + { P_STATUS, INITIATOR_ERROR, "in Status phase" }, { P_MESGIN, MSG_PARITY_ERROR, "in Message-in phase" }, - { P_BUSFREE, MSG_NOOP, "while idle" }, - { 0, MSG_NOOP, "in unknown phase" } + { P_BUSFREE, NOP, "while idle" }, + { 0, NOP, "in unknown phase" } }; /* @@ -1126,7 +1126,7 @@ ahd_restart(struct ahd_softc *ahd) /* No more pending messages */ ahd_clear_msg_state(ahd); ahd_outb(ahd, SCSISIGO, 0); /* De-assert BSY */ - ahd_outb(ahd, MSG_OUT, MSG_NOOP); /* No message to send */ + ahd_outb(ahd, MSG_OUT, NOP); /* No message to send */ ahd_outb(ahd, SXFRCTL1, ahd_inb(ahd, SXFRCTL1) & ~BITBUCKET); ahd_outb(ahd, SEQINTCTL, 0); ahd_outb(ahd, LASTPHASE, P_BUSFREE); @@ -2007,7 +2007,7 @@ ahd_handle_seqint(struct ahd_softc *ahd, u_int intstat) */ ahd_assert_atn(ahd); ahd_outb(ahd, MSG_OUT, HOST_MSG); - ahd->msgout_buf[0] = MSG_ABORT_TASK; + ahd->msgout_buf[0] = ABORT_TASK; ahd->msgout_len = 1; ahd->msgout_index = 0; ahd->msg_type = MSG_TYPE_INITIATOR_MSGOUT; @@ -2135,7 +2135,7 @@ ahd_handle_seqint(struct ahd_softc *ahd, u_int intstat) printk("SXFRCTL0 == 0x%x\n", ahd_inb(ahd, SXFRCTL0)); printk("SEQCTL0 == 0x%x\n", ahd_inb(ahd, SEQCTL0)); ahd_dump_card_state(ahd); - ahd->msgout_buf[0] = MSG_BUS_DEV_RESET; + ahd->msgout_buf[0] = TARGET_RESET; ahd->msgout_len = 1; ahd->msgout_index = 0; ahd->msg_type = MSG_TYPE_INITIATOR_MSGOUT; @@ -2691,7 +2691,7 @@ ahd_handle_transmission_error(struct ahd_softc *ahd) lastphase = ahd_inb(ahd, LASTPHASE); curphase = ahd_inb(ahd, SCSISIGI) & PHASE_MASK; perrdiag = ahd_inb(ahd, PERRDIAG); - msg_out = MSG_INITIATOR_DET_ERR; + msg_out = INITIATOR_ERROR; ahd_outb(ahd, CLRSINT1, CLRSCSIPERR); /* @@ -2823,14 +2823,14 @@ ahd_handle_transmission_error(struct ahd_softc *ahd) } /* - * We've set the hardware to assert ATN if we + * We've set the hardware to assert ATN if we * get a parity error on "in" phases, so all we * need to do is stuff the message buffer with * the appropriate message. "In" phases have set - * mesg_out to something other than MSG_NOP. + * mesg_out to something other than NOP. */ ahd->send_msg_perror = msg_out; - if (scb != NULL && msg_out == MSG_INITIATOR_DET_ERR) + if (scb != NULL && msg_out == INITIATOR_ERROR) scb->flags |= SCB_TRANSMISSION_ERROR; ahd_outb(ahd, MSG_OUT, HOST_MSG); ahd_outb(ahd, CLRINT, CLRSCSIINT); @@ -3050,8 +3050,8 @@ ahd_handle_nonpkt_busfree(struct ahd_softc *ahd) u_int tag; tag = SCB_LIST_NULL; - if (ahd_sent_msg(ahd, AHDMSG_1B, MSG_ABORT_TAG, TRUE) - || ahd_sent_msg(ahd, AHDMSG_1B, MSG_ABORT, TRUE)) { + if (ahd_sent_msg(ahd, AHDMSG_1B, ABORT_TASK, TRUE) + || ahd_sent_msg(ahd, AHDMSG_1B, ABORT_TASK_SET, TRUE)) { int found; int sent_msg; @@ -3066,9 +3066,9 @@ ahd_handle_nonpkt_busfree(struct ahd_softc *ahd) ahd_print_path(ahd, scb); printk("SCB %d - Abort%s Completed.\n", SCB_GET_TAG(scb), - sent_msg == MSG_ABORT_TAG ? "" : " Tag"); + sent_msg == ABORT_TASK ? "" : " Tag"); - if (sent_msg == MSG_ABORT_TAG) + if (sent_msg == ABORT_TASK) tag = SCB_GET_TAG(scb); if ((scb->flags & SCB_EXTERNAL_RESET) != 0) { @@ -3093,12 +3093,12 @@ ahd_handle_nonpkt_busfree(struct ahd_softc *ahd) printk("found == 0x%x\n", found); printerror = 0; } else if (ahd_sent_msg(ahd, AHDMSG_1B, - MSG_BUS_DEV_RESET, TRUE)) { + TARGET_RESET, TRUE)) { ahd_handle_devreset(ahd, &devinfo, CAM_LUN_WILDCARD, CAM_BDR_SENT, "Bus Device Reset", /*verbose_level*/0); printerror = 0; - } else if (ahd_sent_msg(ahd, AHDMSG_EXT, MSG_EXT_PPR, FALSE) + } else if (ahd_sent_msg(ahd, AHDMSG_EXT, EXTENDED_PPR, FALSE) && ppr_busfree == 0) { struct ahd_initiator_tinfo *tinfo; struct ahd_tmode_tstate *tstate; @@ -3151,7 +3151,7 @@ ahd_handle_nonpkt_busfree(struct ahd_softc *ahd) } printerror = 0; } - } else if (ahd_sent_msg(ahd, AHDMSG_EXT, MSG_EXT_WDTR, FALSE) + } else if (ahd_sent_msg(ahd, AHDMSG_EXT, EXTENDED_WDTR, FALSE) && ppr_busfree == 0) { /* * Negotiation Rejected. Go-narrow and @@ -3176,7 +3176,7 @@ ahd_handle_nonpkt_busfree(struct ahd_softc *ahd) ahd_qinfifo_requeue_tail(ahd, scb); } printerror = 0; - } else if (ahd_sent_msg(ahd, AHDMSG_EXT, MSG_EXT_SDTR, FALSE) + } else if (ahd_sent_msg(ahd, AHDMSG_EXT, EXTENDED_SDTR, FALSE) && ppr_busfree == 0) { /* * Negotiation Rejected. Go-async and @@ -3204,7 +3204,7 @@ ahd_handle_nonpkt_busfree(struct ahd_softc *ahd) printerror = 0; } else if ((ahd->msg_flags & MSG_FLAG_EXPECT_IDE_BUSFREE) != 0 && ahd_sent_msg(ahd, AHDMSG_1B, - MSG_INITIATOR_DET_ERR, TRUE)) { + INITIATOR_ERROR, TRUE)) { #ifdef AHD_DEBUG if ((ahd_debug & AHD_SHOW_MESSAGES) != 0) @@ -3213,7 +3213,7 @@ ahd_handle_nonpkt_busfree(struct ahd_softc *ahd) printerror = 0; } else if ((ahd->msg_flags & MSG_FLAG_EXPECT_QASREJ_BUSFREE) && ahd_sent_msg(ahd, AHDMSG_1B, - MSG_MESSAGE_REJECT, TRUE)) { + MESSAGE_REJECT, TRUE)) { #ifdef AHD_DEBUG if ((ahd_debug & AHD_SHOW_MESSAGES) != 0) @@ -3367,7 +3367,7 @@ proto_violation_reset: ahd_outb(ahd, MSG_OUT, HOST_MSG); if (scb == NULL) { ahd_print_devinfo(ahd, &devinfo); - ahd->msgout_buf[0] = MSG_ABORT_TASK; + ahd->msgout_buf[0] = ABORT_TASK; ahd->msgout_len = 1; ahd->msgout_index = 0; ahd->msg_type = MSG_TYPE_INITIATOR_MSGOUT; @@ -4389,7 +4389,7 @@ ahd_setup_initiator_msgout(struct ahd_softc *ahd, struct ahd_devinfo *devinfo, } else if (scb == NULL) { printk("%s: WARNING. No pending message for " "I_T msgin. Issuing NO-OP\n", ahd_name(ahd)); - ahd->msgout_buf[ahd->msgout_index++] = MSG_NOOP; + ahd->msgout_buf[ahd->msgout_index++] = NOP; ahd->msgout_len++; ahd->msg_type = MSG_TYPE_INITIATOR_MSGOUT; return; @@ -4415,7 +4415,7 @@ ahd_setup_initiator_msgout(struct ahd_softc *ahd, struct ahd_devinfo *devinfo, } if (scb->flags & SCB_DEVICE_RESET) { - ahd->msgout_buf[ahd->msgout_index++] = MSG_BUS_DEV_RESET; + ahd->msgout_buf[ahd->msgout_index++] = TARGET_RESET; ahd->msgout_len++; ahd_print_path(ahd, scb); printk("Bus Device Reset Message Sent\n"); @@ -4430,9 +4430,9 @@ ahd_setup_initiator_msgout(struct ahd_softc *ahd, struct ahd_devinfo *devinfo, } else if ((scb->flags & SCB_ABORT) != 0) { if ((scb->hscb->control & TAG_ENB) != 0) { - ahd->msgout_buf[ahd->msgout_index++] = MSG_ABORT_TAG; + ahd->msgout_buf[ahd->msgout_index++] = ABORT_TASK; } else { - ahd->msgout_buf[ahd->msgout_index++] = MSG_ABORT; + ahd->msgout_buf[ahd->msgout_index++] = ABORT_TASK_SET; } ahd->msgout_len++; ahd_print_path(ahd, scb); @@ -4664,7 +4664,7 @@ ahd_clear_msg_state(struct ahd_softc *ahd) */ ahd_outb(ahd, CLRSINT1, CLRATNO); } - ahd_outb(ahd, MSG_OUT, MSG_NOOP); + ahd_outb(ahd, MSG_OUT, NOP); ahd_outb(ahd, SEQ_FLAGS2, ahd_inb(ahd, SEQ_FLAGS2) & ~TARGET_MSG_PENDING); ahd_restore_modes(ahd, saved_modes); @@ -4745,7 +4745,7 @@ reswitch: * with a busfree. */ if ((ahd->msg_flags & MSG_FLAG_PACKETIZED) != 0 - && ahd->send_msg_perror == MSG_INITIATOR_DET_ERR) + && ahd->send_msg_perror == INITIATOR_ERROR) ahd->msg_flags |= MSG_FLAG_EXPECT_IDE_BUSFREE; ahd_outb(ahd, RETURN_2, ahd->send_msg_perror); @@ -5023,7 +5023,7 @@ ahd_sent_msg(struct ahd_softc *ahd, ahd_msgtype type, u_int msgval, int full) index = 0; while (index < ahd->msgout_len) { - if (ahd->msgout_buf[index] == MSG_EXTENDED) { + if (ahd->msgout_buf[index] == EXTENDED_MESSAGE) { u_int end_index; end_index = index + 1 + ahd->msgout_buf[index + 1]; @@ -5037,8 +5037,8 @@ ahd_sent_msg(struct ahd_softc *ahd, ahd_msgtype type, u_int msgval, int full) found = TRUE; } index = end_index; - } else if (ahd->msgout_buf[index] >= MSG_SIMPLE_TASK - && ahd->msgout_buf[index] <= MSG_IGN_WIDE_RESIDUE) { + } else if (ahd->msgout_buf[index] >= SIMPLE_QUEUE_TAG + && ahd->msgout_buf[index] <= IGNORE_WIDE_RESIDUE) { /* Skip tag type and tag id or residue param*/ index += 2; @@ -5089,30 +5089,30 @@ ahd_parse_msg(struct ahd_softc *ahd, struct ahd_devinfo *devinfo) * extended message type. */ switch (ahd->msgin_buf[0]) { - case MSG_DISCONNECT: - case MSG_SAVEDATAPOINTER: - case MSG_CMDCOMPLETE: - case MSG_RESTOREPOINTERS: - case MSG_IGN_WIDE_RESIDUE: + case DISCONNECT: + case SAVE_POINTERS: + case COMMAND_COMPLETE: + case RESTORE_POINTERS: + case IGNORE_WIDE_RESIDUE: /* * End our message loop as these are messages * the sequencer handles on its own. */ done = MSGLOOP_TERMINATED; break; - case MSG_MESSAGE_REJECT: + case MESSAGE_REJECT: response = ahd_handle_msg_reject(ahd, devinfo); fallthrough; - case MSG_NOOP: + case NOP: done = MSGLOOP_MSGCOMPLETE; break; - case MSG_EXTENDED: + case EXTENDED_MESSAGE: { /* Wait for enough of the message to begin validation */ if (ahd->msgin_index < 2) break; switch (ahd->msgin_buf[2]) { - case MSG_EXT_SDTR: + case EXTENDED_SDTR: { u_int period; u_int ppr_options; @@ -5160,7 +5160,7 @@ ahd_parse_msg(struct ahd_softc *ahd, struct ahd_devinfo *devinfo) * and didn't have to fall down to async * transfers. */ - if (ahd_sent_msg(ahd, AHDMSG_EXT, MSG_EXT_SDTR, TRUE)) { + if (ahd_sent_msg(ahd, AHDMSG_EXT, EXTENDED_SDTR, TRUE)) { /* We started it */ if (saved_offset != offset) { /* Went too low - force async */ @@ -5187,7 +5187,7 @@ ahd_parse_msg(struct ahd_softc *ahd, struct ahd_devinfo *devinfo) done = MSGLOOP_MSGCOMPLETE; break; } - case MSG_EXT_WDTR: + case EXTENDED_WDTR: { u_int bus_width; u_int saved_width; @@ -5221,7 +5221,7 @@ ahd_parse_msg(struct ahd_softc *ahd, struct ahd_devinfo *devinfo) saved_width, bus_width); } - if (ahd_sent_msg(ahd, AHDMSG_EXT, MSG_EXT_WDTR, TRUE)) { + if (ahd_sent_msg(ahd, AHDMSG_EXT, EXTENDED_WDTR, TRUE)) { /* * Don't send a WDTR back to the * target, since we asked first. @@ -5283,7 +5283,7 @@ ahd_parse_msg(struct ahd_softc *ahd, struct ahd_devinfo *devinfo) done = MSGLOOP_MSGCOMPLETE; break; } - case MSG_EXT_PPR: + case EXTENDED_PPR: { u_int period; u_int offset; @@ -5338,7 +5338,7 @@ ahd_parse_msg(struct ahd_softc *ahd, struct ahd_devinfo *devinfo) ahd_validate_offset(ahd, tinfo, period, &offset, bus_width, devinfo->role); - if (ahd_sent_msg(ahd, AHDMSG_EXT, MSG_EXT_PPR, TRUE)) { + if (ahd_sent_msg(ahd, AHDMSG_EXT, EXTENDED_PPR, TRUE)) { /* * If we are unable to do any of the * requested options (we went too low), @@ -5401,7 +5401,7 @@ ahd_parse_msg(struct ahd_softc *ahd, struct ahd_devinfo *devinfo) break; } #ifdef AHD_TARGET_MODE - case MSG_BUS_DEV_RESET: + case TARGET_RESET: ahd_handle_devreset(ahd, devinfo, CAM_LUN_WILDCARD, CAM_BDR_SENT, "Bus Device Reset Received", @@ -5409,9 +5409,9 @@ ahd_parse_msg(struct ahd_softc *ahd, struct ahd_devinfo *devinfo) ahd_restart(ahd); done = MSGLOOP_TERMINATED; break; - case MSG_ABORT_TAG: - case MSG_ABORT: - case MSG_CLEAR_QUEUE: + case ABORT_TASK: + case ABORT_TASK_SET: + case CLEAR_TASK_SET: { int tag; @@ -5421,7 +5421,7 @@ ahd_parse_msg(struct ahd_softc *ahd, struct ahd_devinfo *devinfo) break; } tag = SCB_LIST_NULL; - if (ahd->msgin_buf[0] == MSG_ABORT_TAG) + if (ahd->msgin_buf[0] == ABORT_TASK) tag = ahd_inb(ahd, INITIATOR_TAG); ahd_abort_scbs(ahd, devinfo->target, devinfo->channel, devinfo->lun, tag, ROLE_TARGET, @@ -5445,7 +5445,7 @@ ahd_parse_msg(struct ahd_softc *ahd, struct ahd_devinfo *devinfo) break; } #endif - case MSG_QAS_REQUEST: + case QAS_REQUEST: #ifdef AHD_DEBUG if ((ahd_debug & AHD_SHOW_MESSAGES) != 0) printk("%s: QAS request. SCSISIGI == 0x%x\n", @@ -5453,7 +5453,7 @@ ahd_parse_msg(struct ahd_softc *ahd, struct ahd_devinfo *devinfo) #endif ahd->msg_flags |= MSG_FLAG_EXPECT_QASREJ_BUSFREE; fallthrough; - case MSG_TERM_IO_PROC: + case TERMINATE_IO_PROC: default: reject = TRUE; break; @@ -5465,7 +5465,7 @@ ahd_parse_msg(struct ahd_softc *ahd, struct ahd_devinfo *devinfo) */ ahd->msgout_index = 0; ahd->msgout_len = 1; - ahd->msgout_buf[0] = MSG_MESSAGE_REJECT; + ahd->msgout_buf[0] = MESSAGE_REJECT; done = MSGLOOP_MSGCOMPLETE; response = TRUE; } @@ -5504,8 +5504,8 @@ ahd_handle_msg_reject(struct ahd_softc *ahd, struct ahd_devinfo *devinfo) /* Might be necessary */ last_msg = ahd_inb(ahd, LAST_MSG); - if (ahd_sent_msg(ahd, AHDMSG_EXT, MSG_EXT_PPR, /*full*/FALSE)) { - if (ahd_sent_msg(ahd, AHDMSG_EXT, MSG_EXT_PPR, /*full*/TRUE) + if (ahd_sent_msg(ahd, AHDMSG_EXT, EXTENDED_PPR, /*full*/FALSE)) { + if (ahd_sent_msg(ahd, AHDMSG_EXT, EXTENDED_PPR, /*full*/TRUE) && tinfo->goal.period <= AHD_SYNCRATE_PACED) { /* * Target may not like our SPI-4 PPR Options. @@ -5542,7 +5542,7 @@ ahd_handle_msg_reject(struct ahd_softc *ahd, struct ahd_devinfo *devinfo) ahd_build_transfer_msg(ahd, devinfo); ahd->msgout_index = 0; response = 1; - } else if (ahd_sent_msg(ahd, AHDMSG_EXT, MSG_EXT_WDTR, /*full*/FALSE)) { + } else if (ahd_sent_msg(ahd, AHDMSG_EXT, EXTENDED_WDTR, /*full*/FALSE)) { /* note 8bit xfers */ printk("(%s:%c:%d:%d): refuses WIDE negotiation. Using " @@ -5567,7 +5567,7 @@ ahd_handle_msg_reject(struct ahd_softc *ahd, struct ahd_devinfo *devinfo) ahd->msgout_index = 0; response = 1; } - } else if (ahd_sent_msg(ahd, AHDMSG_EXT, MSG_EXT_SDTR, /*full*/FALSE)) { + } else if (ahd_sent_msg(ahd, AHDMSG_EXT, EXTENDED_SDTR, /*full*/FALSE)) { /* note asynch xfers and clear flag */ ahd_set_syncrate(ahd, devinfo, /*period*/0, /*offset*/0, /*ppr_options*/0, @@ -5577,13 +5577,13 @@ ahd_handle_msg_reject(struct ahd_softc *ahd, struct ahd_devinfo *devinfo) "Using asynchronous transfers\n", ahd_name(ahd), devinfo->channel, devinfo->target, devinfo->lun); - } else if ((scb->hscb->control & MSG_SIMPLE_TASK) != 0) { + } else if ((scb->hscb->control & SIMPLE_QUEUE_TAG) != 0) { int tag_type; int mask; - tag_type = (scb->hscb->control & MSG_SIMPLE_TASK); + tag_type = (scb->hscb->control & SIMPLE_QUEUE_TAG); - if (tag_type == MSG_SIMPLE_TASK) { + if (tag_type == SIMPLE_QUEUE_TAG) { printk("(%s:%c:%d:%d): refuses tagged commands. " "Performing non-tagged I/O\n", ahd_name(ahd), devinfo->channel, devinfo->target, devinfo->lun); @@ -5593,7 +5593,7 @@ ahd_handle_msg_reject(struct ahd_softc *ahd, struct ahd_devinfo *devinfo) printk("(%s:%c:%d:%d): refuses %s tagged commands. " "Performing simple queue tagged I/O only\n", ahd_name(ahd), devinfo->channel, devinfo->target, - devinfo->lun, tag_type == MSG_ORDERED_TASK + devinfo->lun, tag_type == ORDERED_QUEUE_TAG ? "ordered" : "head of queue"); ahd_set_tags(ahd, scb->io_ctx, devinfo, AHD_QUEUE_BASIC); mask = ~0x03; @@ -5607,7 +5607,7 @@ ahd_handle_msg_reject(struct ahd_softc *ahd, struct ahd_devinfo *devinfo) ahd_inb_scbram(ahd, SCB_CONTROL) & mask); scb->hscb->control &= mask; ahd_set_transaction_tag(scb, /*enabled*/FALSE, - /*type*/MSG_SIMPLE_TASK); + /*type*/SIMPLE_QUEUE_TAG); ahd_outb(ahd, MSG_OUT, MSG_IDENTIFYFLAG); ahd_assert_atn(ahd); ahd_busy_tcl(ahd, BUILD_TCL(scb->hscb->scsiid, devinfo->lun), @@ -5922,7 +5922,7 @@ ahd_handle_devreset(struct ahd_softc *ahd, struct ahd_devinfo *devinfo, continue; ahd_queue_lstate_event(ahd, lstate, devinfo->our_scsiid, - MSG_BUS_DEV_RESET, /*arg*/0); + TARGET_RESET, /*arg*/0); ahd_send_lstate_events(ahd, lstate); } } @@ -9158,7 +9158,7 @@ ahd_queue_lstate_event(struct ahd_softc *ahd, struct ahd_tmode_lstate *lstate, - (lstate->event_r_idx - lstate->event_w_idx); if (event_type == EVENT_TYPE_BUS_RESET - || event_type == MSG_BUS_DEV_RESET) { + || event_type == TARGET_RESET) { /* * Any earlier events are irrelevant, so reset our buffer. * This has the effect of allowing us to deal with reset diff --git a/drivers/scsi/aic7xxx/aic79xx_osm.c b/drivers/scsi/aic7xxx/aic79xx_osm.c index 4a91385fdfea..4f7102f8eeb0 100644 --- a/drivers/scsi/aic7xxx/aic79xx_osm.c +++ b/drivers/scsi/aic7xxx/aic79xx_osm.c @@ -1602,10 +1602,10 @@ ahd_linux_run_command(struct ahd_softc *ahd, struct ahd_linux_device *dev, if ((dev->flags & (AHD_DEV_Q_TAGGED|AHD_DEV_Q_BASIC)) != 0) { if (dev->commands_since_idle_or_otag == AHD_OTAG_THRESH && (dev->flags & AHD_DEV_Q_TAGGED) != 0) { - hscb->control |= MSG_ORDERED_TASK; + hscb->control |= ORDERED_QUEUE_TAG; dev->commands_since_idle_or_otag = 0; } else { - hscb->control |= MSG_SIMPLE_TASK; + hscb->control |= SIMPLE_QUEUE_TAG; } } diff --git a/drivers/scsi/aic7xxx/aic7xxx_core.c b/drivers/scsi/aic7xxx/aic7xxx_core.c index 43da21a26e1a..4b04ab8908f8 100644 --- a/drivers/scsi/aic7xxx/aic7xxx_core.c +++ b/drivers/scsi/aic7xxx/aic7xxx_core.c @@ -84,16 +84,16 @@ static const u_int num_errors = ARRAY_SIZE(ahc_hard_errors); static const struct ahc_phase_table_entry ahc_phase_table[] = { - { P_DATAOUT, MSG_NOOP, "in Data-out phase" }, - { P_DATAIN, MSG_INITIATOR_DET_ERR, "in Data-in phase" }, - { P_DATAOUT_DT, MSG_NOOP, "in DT Data-out phase" }, - { P_DATAIN_DT, MSG_INITIATOR_DET_ERR, "in DT Data-in phase" }, - { P_COMMAND, MSG_NOOP, "in Command phase" }, - { P_MESGOUT, MSG_NOOP, "in Message-out phase" }, - { P_STATUS, MSG_INITIATOR_DET_ERR, "in Status phase" }, + { P_DATAOUT, NOP, "in Data-out phase" }, + { P_DATAIN, INITIATOR_ERROR, "in Data-in phase" }, + { P_DATAOUT_DT, NOP, "in DT Data-out phase" }, + { P_DATAIN_DT, INITIATOR_ERROR, "in DT Data-in phase" }, + { P_COMMAND, NOP, "in Command phase" }, + { P_MESGOUT, NOP, "in Message-out phase" }, + { P_STATUS, INITIATOR_ERROR, "in Status phase" }, { P_MESGIN, MSG_PARITY_ERROR, "in Message-in phase" }, - { P_BUSFREE, MSG_NOOP, "while idle" }, - { 0, MSG_NOOP, "in unknown phase" } + { P_BUSFREE, NOP, "while idle" }, + { 0, NOP, "in unknown phase" } }; /* @@ -815,7 +815,7 @@ ahc_restart(struct ahc_softc *ahc) ahc_clear_msg_state(ahc); ahc_outb(ahc, SCSISIGO, 0); /* De-assert BSY */ - ahc_outb(ahc, MSG_OUT, MSG_NOOP); /* No message to send */ + ahc_outb(ahc, MSG_OUT, NOP); /* No message to send */ ahc_outb(ahc, SXFRCTL1, ahc_inb(ahc, SXFRCTL1) & ~BITBUCKET); ahc_outb(ahc, LASTPHASE, P_BUSFREE); ahc_outb(ahc, SAVED_SCSIID, 0xFF); @@ -1179,7 +1179,7 @@ ahc_handle_seqint(struct ahc_softc *ahc, u_int intstat) printk("SXFRCTL0 == 0x%x\n", ahc_inb(ahc, SXFRCTL0)); printk("SEQCTL == 0x%x\n", ahc_inb(ahc, SEQCTL)); ahc_dump_card_state(ahc); - ahc->msgout_buf[0] = MSG_BUS_DEV_RESET; + ahc->msgout_buf[0] = TARGET_RESET; ahc->msgout_len = 1; ahc->msgout_index = 0; ahc->msg_type = MSG_TYPE_INITIATOR_MSGOUT; @@ -1683,7 +1683,7 @@ ahc_handle_scsiint(struct ahc_softc *ahc, u_int intstat) * data direction, so ignore the value * in the phase table. */ - mesg_out = MSG_INITIATOR_DET_ERR; + mesg_out = INITIATOR_ERROR; } /* @@ -1693,7 +1693,7 @@ ahc_handle_scsiint(struct ahc_softc *ahc, u_int intstat) * the appropriate message. "In" phases have set * mesg_out to something other than MSG_NOP. */ - if (mesg_out != MSG_NOOP) { + if (mesg_out != NOP) { if (ahc->msg_type != MSG_TYPE_NONE) ahc->send_msg_perror = TRUE; else @@ -1817,10 +1817,10 @@ ahc_handle_scsiint(struct ahc_softc *ahc, u_int intstat) u_int tag; tag = SCB_LIST_NULL; - if (ahc_sent_msg(ahc, AHCMSG_1B, MSG_ABORT_TAG, TRUE) - || ahc_sent_msg(ahc, AHCMSG_1B, MSG_ABORT, TRUE)) { + if (ahc_sent_msg(ahc, AHCMSG_1B, ABORT_TASK, TRUE) + || ahc_sent_msg(ahc, AHCMSG_1B, ABORT_TASK_SET, TRUE)) { if (ahc->msgout_buf[ahc->msgout_index - 1] - == MSG_ABORT_TAG) + == ABORT_TASK) tag = scb->hscb->tag; ahc_print_path(ahc, scb); printk("SCB %d - Abort%s Completed.\n", @@ -1832,7 +1832,7 @@ ahc_handle_scsiint(struct ahc_softc *ahc, u_int intstat) CAM_REQ_ABORTED); printerror = 0; } else if (ahc_sent_msg(ahc, AHCMSG_1B, - MSG_BUS_DEV_RESET, TRUE)) { + TARGET_RESET, TRUE)) { ahc_compile_devinfo(&devinfo, initiator_role_id, target, @@ -1845,7 +1845,7 @@ ahc_handle_scsiint(struct ahc_softc *ahc, u_int intstat) /*verbose_level*/0); printerror = 0; } else if (ahc_sent_msg(ahc, AHCMSG_EXT, - MSG_EXT_PPR, FALSE)) { + EXTENDED_PPR, FALSE)) { struct ahc_initiator_tinfo *tinfo; struct ahc_tmode_tstate *tstate; @@ -1864,7 +1864,7 @@ ahc_handle_scsiint(struct ahc_softc *ahc, u_int intstat) ahc_qinfifo_requeue_tail(ahc, scb); printerror = 0; } else if (ahc_sent_msg(ahc, AHCMSG_EXT, - MSG_EXT_WDTR, FALSE)) { + EXTENDED_WDTR, FALSE)) { /* * Negotiation Rejected. Go-narrow and * retry command. @@ -1876,7 +1876,7 @@ ahc_handle_scsiint(struct ahc_softc *ahc, u_int intstat) ahc_qinfifo_requeue_tail(ahc, scb); printerror = 0; } else if (ahc_sent_msg(ahc, AHCMSG_EXT, - MSG_EXT_SDTR, FALSE)) { + EXTENDED_SDTR, FALSE)) { /* * Negotiation Rejected. Go-async and * retry command. @@ -2878,7 +2878,7 @@ ahc_setup_initiator_msgout(struct ahc_softc *ahc, struct ahc_devinfo *devinfo, } if (scb->flags & SCB_DEVICE_RESET) { - ahc->msgout_buf[ahc->msgout_index++] = MSG_BUS_DEV_RESET; + ahc->msgout_buf[ahc->msgout_index++] = TARGET_RESET; ahc->msgout_len++; ahc_print_path(ahc, scb); printk("Bus Device Reset Message Sent\n"); @@ -2892,9 +2892,9 @@ ahc_setup_initiator_msgout(struct ahc_softc *ahc, struct ahc_devinfo *devinfo, ahc_outb(ahc, SCSISEQ, (ahc_inb(ahc, SCSISEQ) & ~ENSELO)); } else if ((scb->flags & SCB_ABORT) != 0) { if ((scb->hscb->control & TAG_ENB) != 0) - ahc->msgout_buf[ahc->msgout_index++] = MSG_ABORT_TAG; + ahc->msgout_buf[ahc->msgout_index++] = ABORT_TASK; else - ahc->msgout_buf[ahc->msgout_index++] = MSG_ABORT; + ahc->msgout_buf[ahc->msgout_index++] = ABORT_TASK_SET; ahc->msgout_len++; ahc_print_path(ahc, scb); printk("Abort%s Message Sent\n", @@ -3104,7 +3104,7 @@ ahc_clear_msg_state(struct ahc_softc *ahc) */ ahc_outb(ahc, CLRSINT1, CLRATNO); } - ahc_outb(ahc, MSG_OUT, MSG_NOOP); + ahc_outb(ahc, MSG_OUT, NOP); ahc_outb(ahc, SEQ_FLAGS2, ahc_inb(ahc, SEQ_FLAGS2) & ~TARGET_MSG_PENDING); } @@ -3190,7 +3190,7 @@ proto_violation_reset: ahc_outb(ahc, MSG_OUT, HOST_MSG); if (scb == NULL) { ahc_print_devinfo(ahc, &devinfo); - ahc->msgout_buf[0] = MSG_ABORT_TASK; + ahc->msgout_buf[0] = ABORT_TASK; ahc->msgout_len = 1; ahc->msgout_index = 0; ahc->msg_type = MSG_TYPE_INITIATOR_MSGOUT; @@ -3518,7 +3518,7 @@ ahc_sent_msg(struct ahc_softc *ahc, ahc_msgtype type, u_int msgval, int full) index = 0; while (index < ahc->msgout_len) { - if (ahc->msgout_buf[index] == MSG_EXTENDED) { + if (ahc->msgout_buf[index] == EXTENDED_MESSAGE) { u_int end_index; end_index = index + 1 + ahc->msgout_buf[index + 1]; @@ -3532,8 +3532,8 @@ ahc_sent_msg(struct ahc_softc *ahc, ahc_msgtype type, u_int msgval, int full) found = TRUE; } index = end_index; - } else if (ahc->msgout_buf[index] >= MSG_SIMPLE_TASK - && ahc->msgout_buf[index] <= MSG_IGN_WIDE_RESIDUE) { + } else if (ahc->msgout_buf[index] >= SIMPLE_QUEUE_TAG + && ahc->msgout_buf[index] <= IGNORE_WIDE_RESIDUE) { /* Skip tag type and tag id or residue param*/ index += 2; @@ -3584,37 +3584,37 @@ ahc_parse_msg(struct ahc_softc *ahc, struct ahc_devinfo *devinfo) * extended message type. */ switch (ahc->msgin_buf[0]) { - case MSG_DISCONNECT: - case MSG_SAVEDATAPOINTER: - case MSG_CMDCOMPLETE: - case MSG_RESTOREPOINTERS: - case MSG_IGN_WIDE_RESIDUE: + case DISCONNECT: + case SAVE_POINTERS: + case COMMAND_COMPLETE: + case RESTORE_POINTERS: + case IGNORE_WIDE_RESIDUE: /* * End our message loop as these are messages * the sequencer handles on its own. */ done = MSGLOOP_TERMINATED; break; - case MSG_MESSAGE_REJECT: + case MESSAGE_REJECT: response = ahc_handle_msg_reject(ahc, devinfo); fallthrough; - case MSG_NOOP: + case NOP: done = MSGLOOP_MSGCOMPLETE; break; - case MSG_EXTENDED: + case EXTENDED_MESSAGE: { /* Wait for enough of the message to begin validation */ if (ahc->msgin_index < 2) break; switch (ahc->msgin_buf[2]) { - case MSG_EXT_SDTR: + case EXTENDED_SDTR: { const struct ahc_syncrate *syncrate; u_int period; u_int ppr_options; u_int offset; u_int saved_offset; - + if (ahc->msgin_buf[1] != MSG_EXT_SDTR_LEN) { reject = TRUE; break; @@ -3648,7 +3648,7 @@ ahc_parse_msg(struct ahc_softc *ahc, struct ahc_devinfo *devinfo) ahc->msgin_buf[3], saved_offset, period, offset); } - ahc_set_syncrate(ahc, devinfo, + ahc_set_syncrate(ahc, devinfo, syncrate, period, offset, ppr_options, AHC_TRANS_ACTIVE|AHC_TRANS_GOAL, @@ -3659,7 +3659,7 @@ ahc_parse_msg(struct ahc_softc *ahc, struct ahc_devinfo *devinfo) * and didn't have to fall down to async * transfers. */ - if (ahc_sent_msg(ahc, AHCMSG_EXT, MSG_EXT_SDTR, TRUE)) { + if (ahc_sent_msg(ahc, AHCMSG_EXT, EXTENDED_SDTR, TRUE)) { /* We started it */ if (saved_offset != offset) { /* Went too low - force async */ @@ -3686,7 +3686,7 @@ ahc_parse_msg(struct ahc_softc *ahc, struct ahc_devinfo *devinfo) done = MSGLOOP_MSGCOMPLETE; break; } - case MSG_EXT_WDTR: + case EXTENDED_WDTR: { u_int bus_width; u_int saved_width; @@ -3720,7 +3720,7 @@ ahc_parse_msg(struct ahc_softc *ahc, struct ahc_devinfo *devinfo) saved_width, bus_width); } - if (ahc_sent_msg(ahc, AHCMSG_EXT, MSG_EXT_WDTR, TRUE)) { + if (ahc_sent_msg(ahc, AHCMSG_EXT, EXTENDED_WDTR, TRUE)) { /* * Don't send a WDTR back to the * target, since we asked first. @@ -3782,7 +3782,7 @@ ahc_parse_msg(struct ahc_softc *ahc, struct ahc_devinfo *devinfo) done = MSGLOOP_MSGCOMPLETE; break; } - case MSG_EXT_PPR: + case EXTENDED_PPR: { const struct ahc_syncrate *syncrate; u_int period; @@ -3842,7 +3842,7 @@ ahc_parse_msg(struct ahc_softc *ahc, struct ahc_devinfo *devinfo) &offset, bus_width, devinfo->role); - if (ahc_sent_msg(ahc, AHCMSG_EXT, MSG_EXT_PPR, TRUE)) { + if (ahc_sent_msg(ahc, AHCMSG_EXT, EXTENDED_PPR, TRUE)) { /* * If we are unable to do any of the * requested options (we went too low), @@ -3906,7 +3906,7 @@ ahc_parse_msg(struct ahc_softc *ahc, struct ahc_devinfo *devinfo) break; } #ifdef AHC_TARGET_MODE - case MSG_BUS_DEV_RESET: + case TARGET_RESET: ahc_handle_devreset(ahc, devinfo, CAM_BDR_SENT, "Bus Device Reset Received", @@ -3914,9 +3914,9 @@ ahc_parse_msg(struct ahc_softc *ahc, struct ahc_devinfo *devinfo) ahc_restart(ahc); done = MSGLOOP_TERMINATED; break; - case MSG_ABORT_TAG: - case MSG_ABORT: - case MSG_CLEAR_QUEUE: + case ABORT_TASK: + case ABORT_TASK_SET: + case CLEAR_QUEUE_TASK_SET: { int tag; @@ -3926,7 +3926,7 @@ ahc_parse_msg(struct ahc_softc *ahc, struct ahc_devinfo *devinfo) break; } tag = SCB_LIST_NULL; - if (ahc->msgin_buf[0] == MSG_ABORT_TAG) + if (ahc->msgin_buf[0] == ABORT_TASK) tag = ahc_inb(ahc, INITIATOR_TAG); ahc_abort_scbs(ahc, devinfo->target, devinfo->channel, devinfo->lun, tag, ROLE_TARGET, @@ -3950,7 +3950,7 @@ ahc_parse_msg(struct ahc_softc *ahc, struct ahc_devinfo *devinfo) break; } #endif - case MSG_TERM_IO_PROC: + case TERMINATE_IO_PROC: default: reject = TRUE; break; @@ -3962,7 +3962,7 @@ ahc_parse_msg(struct ahc_softc *ahc, struct ahc_devinfo *devinfo) */ ahc->msgout_index = 0; ahc->msgout_len = 1; - ahc->msgout_buf[0] = MSG_MESSAGE_REJECT; + ahc->msgout_buf[0] = MESSAGE_REJECT; done = MSGLOOP_MSGCOMPLETE; response = TRUE; } @@ -4001,7 +4001,7 @@ ahc_handle_msg_reject(struct ahc_softc *ahc, struct ahc_devinfo *devinfo) /* Might be necessary */ last_msg = ahc_inb(ahc, LAST_MSG); - if (ahc_sent_msg(ahc, AHCMSG_EXT, MSG_EXT_PPR, /*full*/FALSE)) { + if (ahc_sent_msg(ahc, AHCMSG_EXT, EXTENDED_PPR, /*full*/FALSE)) { /* * Target does not support the PPR message. * Attempt to negotiate SPI-2 style. @@ -4020,7 +4020,7 @@ ahc_handle_msg_reject(struct ahc_softc *ahc, struct ahc_devinfo *devinfo) ahc_build_transfer_msg(ahc, devinfo); ahc->msgout_index = 0; response = 1; - } else if (ahc_sent_msg(ahc, AHCMSG_EXT, MSG_EXT_WDTR, /*full*/FALSE)) { + } else if (ahc_sent_msg(ahc, AHCMSG_EXT, EXTENDED_WDTR, /*full*/FALSE)) { /* note 8bit xfers */ printk("(%s:%c:%d:%d): refuses WIDE negotiation. Using " @@ -4045,7 +4045,7 @@ ahc_handle_msg_reject(struct ahc_softc *ahc, struct ahc_devinfo *devinfo) ahc->msgout_index = 0; response = 1; } - } else if (ahc_sent_msg(ahc, AHCMSG_EXT, MSG_EXT_SDTR, /*full*/FALSE)) { + } else if (ahc_sent_msg(ahc, AHCMSG_EXT, EXTENDED_SDTR, /*full*/FALSE)) { /* note asynch xfers and clear flag */ ahc_set_syncrate(ahc, devinfo, /*syncrate*/NULL, /*period*/0, /*offset*/0, /*ppr_options*/0, @@ -4055,13 +4055,13 @@ ahc_handle_msg_reject(struct ahc_softc *ahc, struct ahc_devinfo *devinfo) "Using asynchronous transfers\n", ahc_name(ahc), devinfo->channel, devinfo->target, devinfo->lun); - } else if ((scb->hscb->control & MSG_SIMPLE_TASK) != 0) { + } else if ((scb->hscb->control & SIMPLE_QUEUE_TAG) != 0) { int tag_type; int mask; - tag_type = (scb->hscb->control & MSG_SIMPLE_TASK); + tag_type = (scb->hscb->control & SIMPLE_QUEUE_TAG); - if (tag_type == MSG_SIMPLE_TASK) { + if (tag_type == SIMPLE_QUEUE_TAG) { printk("(%s:%c:%d:%d): refuses tagged commands. " "Performing non-tagged I/O\n", ahc_name(ahc), devinfo->channel, devinfo->target, devinfo->lun); @@ -4071,7 +4071,7 @@ ahc_handle_msg_reject(struct ahc_softc *ahc, struct ahc_devinfo *devinfo) printk("(%s:%c:%d:%d): refuses %s tagged commands. " "Performing simple queue tagged I/O only\n", ahc_name(ahc), devinfo->channel, devinfo->target, - devinfo->lun, tag_type == MSG_ORDERED_TASK + devinfo->lun, tag_type == ORDERED_QUEUE_TAG ? "ordered" : "head of queue"); ahc_set_tags(ahc, scb->io_ctx, devinfo, AHC_QUEUE_BASIC); mask = ~0x03; @@ -4083,9 +4083,9 @@ ahc_handle_msg_reject(struct ahc_softc *ahc, struct ahc_devinfo *devinfo) */ ahc_outb(ahc, SCB_CONTROL, ahc_inb(ahc, SCB_CONTROL) & mask); - scb->hscb->control &= mask; + scb->hscb->control &= mask; ahc_set_transaction_tag(scb, /*enabled*/FALSE, - /*type*/MSG_SIMPLE_TASK); + /*type*/SIMPLE_QUEUE_TAG); ahc_outb(ahc, MSG_OUT, MSG_IDENTIFYFLAG); ahc_assert_atn(ahc); @@ -4322,7 +4322,7 @@ ahc_handle_devreset(struct ahc_softc *ahc, struct ahc_devinfo *devinfo, continue; ahc_queue_lstate_event(ahc, lstate, devinfo->our_scsiid, - MSG_BUS_DEV_RESET, /*arg*/0); + TARGET_RESET, /*arg*/0); ahc_send_lstate_events(ahc, lstate); } } @@ -5168,7 +5168,7 @@ ahc_chip_init(struct ahc_softc *ahc) ahc_outb(ahc, DISCONNECTED_SCBH, SCB_LIST_NULL); /* Message out buffer starts empty */ - ahc_outb(ahc, MSG_OUT, MSG_NOOP); + ahc_outb(ahc, MSG_OUT, NOP); /* * Setup the allowed SCSI Sequences based on operational mode. @@ -6687,7 +6687,7 @@ ahc_queue_lstate_event(struct ahc_softc *ahc, struct ahc_tmode_lstate *lstate, - (lstate->event_r_idx - lstate->event_w_idx); if (event_type == EVENT_TYPE_BUS_RESET - || event_type == MSG_BUS_DEV_RESET) { + || event_type == TARGET_RESET) { /* * Any earlier events are irrelevant, so reset our buffer. * This has the effect of allowing us to deal with reset diff --git a/drivers/scsi/aic7xxx/aic7xxx_osm.c b/drivers/scsi/aic7xxx/aic7xxx_osm.c index 2c7d9d38a577..d33f5a00bf0b 100644 --- a/drivers/scsi/aic7xxx/aic7xxx_osm.c +++ b/drivers/scsi/aic7xxx/aic7xxx_osm.c @@ -1,3 +1,4 @@ + /* * Adaptec AIC7xxx device driver for Linux. * @@ -1480,10 +1481,10 @@ ahc_linux_run_command(struct ahc_softc *ahc, struct ahc_linux_device *dev, if ((dev->flags & (AHC_DEV_Q_TAGGED|AHC_DEV_Q_BASIC)) != 0) { if (dev->commands_since_idle_or_otag == AHC_OTAG_THRESH && (dev->flags & AHC_DEV_Q_TAGGED) != 0) { - hscb->control |= MSG_ORDERED_TASK; + hscb->control |= ORDERED_QUEUE_TAG; dev->commands_since_idle_or_otag = 0; } else { - hscb->control |= MSG_SIMPLE_TASK; + hscb->control |= SIMPLE_QUEUE_TAG; } } diff --git a/drivers/scsi/aic7xxx/scsi_message.h b/drivers/scsi/aic7xxx/scsi_message.h index 75811e245ec7..a7515c3039ed 100644 --- a/drivers/scsi/aic7xxx/scsi_message.h +++ b/drivers/scsi/aic7xxx/scsi_message.h @@ -3,44 +3,6 @@ * $FreeBSD: src/sys/cam/scsi/scsi_message.h,v 1.2 2000/05/01 20:21:29 peter Exp $ */ -/* Messages (1 byte) */ /* I/T (M)andatory or (O)ptional */ -#define MSG_CMDCOMPLETE 0x00 /* M/M */ -#define MSG_TASK_COMPLETE 0x00 /* M/M */ /* SPI3 Terminology */ -#define MSG_EXTENDED 0x01 /* O/O */ -#define MSG_SAVEDATAPOINTER 0x02 /* O/O */ -#define MSG_RESTOREPOINTERS 0x03 /* O/O */ -#define MSG_DISCONNECT 0x04 /* O/O */ -#define MSG_INITIATOR_DET_ERR 0x05 /* M/M */ -#define MSG_ABORT 0x06 /* O/M */ -#define MSG_ABORT_TASK_SET 0x06 /* O/M */ /* SPI3 Terminology */ -#define MSG_MESSAGE_REJECT 0x07 /* M/M */ -#define MSG_NOOP 0x08 /* M/M */ -#define MSG_PARITY_ERROR 0x09 /* M/M */ -#define MSG_LINK_CMD_COMPLETE 0x0a /* O/O */ -#define MSG_LINK_CMD_COMPLETEF 0x0b /* O/O */ -#define MSG_BUS_DEV_RESET 0x0c /* O/M */ -#define MSG_TARGET_RESET 0x0c /* O/M */ /* SPI3 Terminology */ -#define MSG_ABORT_TAG 0x0d /* O/O */ -#define MSG_ABORT_TASK 0x0d /* O/O */ /* SPI3 Terminology */ -#define MSG_CLEAR_QUEUE 0x0e /* O/O */ -#define MSG_CLEAR_TASK_SET 0x0e /* O/O */ /* SPI3 Terminology */ -#define MSG_INIT_RECOVERY 0x0f /* O/O */ /* Deprecated in SPI3 */ -#define MSG_REL_RECOVERY 0x10 /* O/O */ /* Deprecated in SPI3 */ -#define MSG_TERM_IO_PROC 0x11 /* O/O */ /* Deprecated in SPI3 */ -#define MSG_CLEAR_ACA 0x16 /* O/O */ /* SPI3 */ -#define MSG_LOGICAL_UNIT_RESET 0x17 /* O/O */ /* SPI3 */ -#define MSG_QAS_REQUEST 0x55 /* O/O */ /* SPI3 */ - -/* Messages (2 byte) */ -#define MSG_SIMPLE_Q_TAG 0x20 /* O/O */ -#define MSG_SIMPLE_TASK 0x20 /* O/O */ /* SPI3 Terminology */ -#define MSG_HEAD_OF_Q_TAG 0x21 /* O/O */ -#define MSG_HEAD_OF_QUEUE_TASK 0x21 /* O/O */ /* SPI3 Terminology */ -#define MSG_ORDERED_Q_TAG 0x22 /* O/O */ -#define MSG_ORDERED_TASK 0x22 /* O/O */ /* SPI3 Terminology */ -#define MSG_IGN_WIDE_RESIDUE 0x23 /* O/O */ -#define MSG_ACA_TASK 0x24 /* 0/0 */ /* SPI3 */ - /* Identify message */ /* M/M */ #define MSG_IDENTIFYFLAG 0x80 #define MSG_IDENTIFY_DISCFLAG 0x40 @@ -49,16 +11,13 @@ #define MSG_IDENTIFY_LUNMASK 0x3F /* Extended messages (opcode and length) */ -#define MSG_EXT_SDTR 0x01 #define MSG_EXT_SDTR_LEN 0x03 -#define MSG_EXT_WDTR 0x03 #define MSG_EXT_WDTR_LEN 0x02 #define MSG_EXT_WDTR_BUS_8_BIT 0x00 #define MSG_EXT_WDTR_BUS_16_BIT 0x01 #define MSG_EXT_WDTR_BUS_32_BIT 0x02 /* Deprecated in SPI3 */ -#define MSG_EXT_PPR 0x04 /* SPI3 */ #define MSG_EXT_PPR_LEN 0x06 #define MSG_EXT_PPR_PCOMP_EN 0x80 #define MSG_EXT_PPR_RTI 0x40 diff --git a/include/scsi/scsi.h b/include/scsi/scsi.h index 5b287ad8b727..e75cca25338a 100644 --- a/include/scsi/scsi.h +++ b/include/scsi/scsi.h @@ -116,6 +116,7 @@ static inline int scsi_is_wlun(u64 lun) #define CLEAR_TASK_SET 0x0e #define INITIATE_RECOVERY 0x0f /* SCSI-II only */ #define RELEASE_RECOVERY 0x10 /* SCSI-II only */ +#define TERMINATE_IO_PROC 0x11 /* SCSI-II only */ #define CLEAR_ACA 0x16 #define LOGICAL_UNIT_RESET 0x17 #define SIMPLE_QUEUE_TAG 0x20 -- cgit v1.2.3 From d37932a91600ec47738c4ea98c3a6345b43f6794 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Wed, 13 Jan 2021 10:04:52 +0100 Subject: scsi: core: Add 'set_status_byte()' accessor Add the missing 'set_status_byte()' accessor function. Link: https://lore.kernel.org/r/20210113090500.129644-28-hare@suse.de Reviewed-by: Benjamin Block Signed-off-by: Hannes Reinecke Signed-off-by: Martin K. Petersen --- include/scsi/scsi_cmnd.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h index 69ade4fb71aa..ace15b5dc956 100644 --- a/include/scsi/scsi_cmnd.h +++ b/include/scsi/scsi_cmnd.h @@ -308,6 +308,11 @@ static inline struct scsi_data_buffer *scsi_prot(struct scsi_cmnd *cmd) #define scsi_for_each_prot_sg(cmd, sg, nseg, __i) \ for_each_sg(scsi_prot_sglist(cmd), sg, nseg, __i) +static inline void set_status_byte(struct scsi_cmnd *cmd, char status) +{ + cmd->result = (cmd->result & 0xffffff00) | status; +} + static inline void set_msg_byte(struct scsi_cmnd *cmd, char status) { cmd->result = (cmd->result & 0xffff00ff) | (status << 8); -- cgit v1.2.3 From 121181f3f839c29d8dd9fdc3cc9babbdc74227f8 Mon Sep 17 00:00:00 2001 From: John Garry Date: Mon, 18 Jan 2021 11:09:38 +0100 Subject: scsi: libsas: Remove notifier indirection LLDDs report events to libsas with .notify_port_event and .notify_phy_event callbacks. These callbacks are fixed and so there is no reason why the functions cannot be called directly, so do that. This neatens the code slightly, makes it more obvious, and reduces function pointer usage, which is generally a good thing. Downside is that there are 2x more symbol exports. [a.darwish@linutronix.de: Remove the now unused "sas_ha" local variables] Link: https://lore.kernel.org/r/20210118100955.1761652-3-a.darwish@linutronix.de Reviewed-by: Christoph Hellwig Reviewed-by: Jack Wang Signed-off-by: John Garry Signed-off-by: Ahmed S. Darwish Signed-off-by: Martin K. Petersen --- Documentation/scsi/libsas.rst | 8 ++----- drivers/scsi/aic94xx/aic94xx_scb.c | 20 ++++++++--------- drivers/scsi/hisi_sas/hisi_sas_main.c | 12 ++++------ drivers/scsi/hisi_sas/hisi_sas_v1_hw.c | 3 +-- drivers/scsi/hisi_sas/hisi_sas_v2_hw.c | 3 +-- drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 3 +-- drivers/scsi/isci/port.c | 7 +++--- drivers/scsi/libsas/sas_event.c | 13 ++++------- drivers/scsi/libsas/sas_init.c | 6 ----- drivers/scsi/libsas/sas_internal.h | 1 - drivers/scsi/mvsas/mv_sas.c | 14 +++++------- drivers/scsi/pm8001/pm8001_hwi.c | 40 ++++++++++++++++------------------ drivers/scsi/pm8001/pm8001_sas.c | 7 ++---- drivers/scsi/pm8001/pm80xx_hwi.c | 35 +++++++++++++---------------- include/scsi/libsas.h | 7 +++--- 15 files changed, 69 insertions(+), 110 deletions(-) (limited to 'include') diff --git a/Documentation/scsi/libsas.rst b/Documentation/scsi/libsas.rst index f9b77c7879db..6722e352444b 100644 --- a/Documentation/scsi/libsas.rst +++ b/Documentation/scsi/libsas.rst @@ -189,12 +189,8 @@ num_phys The event interface:: /* LLDD calls these to notify the class of an event. */ - void (*notify_port_event)(struct sas_phy *, enum port_event); - void (*notify_phy_event)(struct sas_phy *, enum phy_event); - -When sas_register_ha() returns, those are set and can be -called by the LLDD to notify the SAS layer of such events -the SAS layer. + void sas_notify_port_event(struct sas_phy *, enum port_event); + void sas_notify_phy_event(struct sas_phy *, enum phy_event); The port notification:: diff --git a/drivers/scsi/aic94xx/aic94xx_scb.c b/drivers/scsi/aic94xx/aic94xx_scb.c index 13677973da5c..770546177ca4 100644 --- a/drivers/scsi/aic94xx/aic94xx_scb.c +++ b/drivers/scsi/aic94xx/aic94xx_scb.c @@ -68,7 +68,6 @@ static void asd_phy_event_tasklet(struct asd_ascb *ascb, struct done_list_struct *dl) { struct asd_ha_struct *asd_ha = ascb->ha; - struct sas_ha_struct *sas_ha = &asd_ha->sas_ha; int phy_id = dl->status_block[0] & DL_PHY_MASK; struct asd_phy *phy = &asd_ha->phys[phy_id]; @@ -81,7 +80,7 @@ static void asd_phy_event_tasklet(struct asd_ascb *ascb, ASD_DPRINTK("phy%d: device unplugged\n", phy_id); asd_turn_led(asd_ha, phy_id, 0); sas_phy_disconnected(&phy->sas_phy); - sas_ha->notify_phy_event(&phy->sas_phy, PHYE_LOSS_OF_SIGNAL); + sas_notify_phy_event(&phy->sas_phy, PHYE_LOSS_OF_SIGNAL); break; case CURRENT_OOB_DONE: /* hot plugged device */ @@ -89,12 +88,12 @@ static void asd_phy_event_tasklet(struct asd_ascb *ascb, get_lrate_mode(phy, oob_mode); ASD_DPRINTK("phy%d device plugged: lrate:0x%x, proto:0x%x\n", phy_id, phy->sas_phy.linkrate, phy->sas_phy.iproto); - sas_ha->notify_phy_event(&phy->sas_phy, PHYE_OOB_DONE); + sas_notify_phy_event(&phy->sas_phy, PHYE_OOB_DONE); break; case CURRENT_SPINUP_HOLD: /* hot plug SATA, no COMWAKE sent */ asd_turn_led(asd_ha, phy_id, 1); - sas_ha->notify_phy_event(&phy->sas_phy, PHYE_SPINUP_HOLD); + sas_notify_phy_event(&phy->sas_phy, PHYE_SPINUP_HOLD); break; case CURRENT_GTO_TIMEOUT: case CURRENT_OOB_ERROR: @@ -102,7 +101,7 @@ static void asd_phy_event_tasklet(struct asd_ascb *ascb, dl->status_block[1]); asd_turn_led(asd_ha, phy_id, 0); sas_phy_disconnected(&phy->sas_phy); - sas_ha->notify_phy_event(&phy->sas_phy, PHYE_OOB_ERROR); + sas_notify_phy_event(&phy->sas_phy, PHYE_OOB_ERROR); break; } } @@ -222,7 +221,6 @@ static void asd_bytes_dmaed_tasklet(struct asd_ascb *ascb, int edb_el = edb_id + ascb->edb_index; struct asd_dma_tok *edb = ascb->ha->seq.edb_arr[edb_el]; struct asd_phy *phy = &ascb->ha->phys[phy_id]; - struct sas_ha_struct *sas_ha = phy->sas_phy.ha; u16 size = ((dl->status_block[3] & 7) << 8) | dl->status_block[2]; size = min(size, (u16) sizeof(phy->frame_rcvd)); @@ -234,7 +232,7 @@ static void asd_bytes_dmaed_tasklet(struct asd_ascb *ascb, spin_unlock_irqrestore(&phy->sas_phy.frame_rcvd_lock, flags); asd_dump_frame_rcvd(phy, dl); asd_form_port(ascb->ha, phy); - sas_ha->notify_port_event(&phy->sas_phy, PORTE_BYTES_DMAED); + sas_notify_port_event(&phy->sas_phy, PORTE_BYTES_DMAED); } static void asd_link_reset_err_tasklet(struct asd_ascb *ascb, @@ -270,7 +268,7 @@ static void asd_link_reset_err_tasklet(struct asd_ascb *ascb, asd_turn_led(asd_ha, phy_id, 0); sas_phy_disconnected(sas_phy); asd_deform_port(asd_ha, phy); - sas_ha->notify_port_event(sas_phy, PORTE_LINK_RESET_ERR); + sas_notify_port_event(sas_phy, PORTE_LINK_RESET_ERR); if (retries_left == 0) { int num = 1; @@ -315,7 +313,7 @@ static void asd_primitive_rcvd_tasklet(struct asd_ascb *ascb, spin_lock_irqsave(&sas_phy->sas_prim_lock, flags); sas_phy->sas_prim = ffs(cont); spin_unlock_irqrestore(&sas_phy->sas_prim_lock, flags); - sas_ha->notify_port_event(sas_phy,PORTE_BROADCAST_RCVD); + sas_notify_port_event(sas_phy, PORTE_BROADCAST_RCVD); break; case LmUNKNOWNP: @@ -336,7 +334,7 @@ static void asd_primitive_rcvd_tasklet(struct asd_ascb *ascb, /* The sequencer disables all phys on that port. * We have to re-enable the phys ourselves. */ asd_deform_port(asd_ha, phy); - sas_ha->notify_port_event(sas_phy, PORTE_HARD_RESET); + sas_notify_port_event(sas_phy, PORTE_HARD_RESET); break; default: @@ -567,7 +565,7 @@ static void escb_tasklet_complete(struct asd_ascb *ascb, /* the device is gone */ sas_phy_disconnected(sas_phy); asd_deform_port(asd_ha, phy); - sas_ha->notify_port_event(sas_phy, PORTE_TIMER_EVENT); + sas_notify_port_event(sas_phy, PORTE_TIMER_EVENT); break; default: ASD_DPRINTK("%s: phy%d: unknown event:0x%x\n", __func__, diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c index cf0bfac920a8..76f8fc3fad59 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_main.c +++ b/drivers/scsi/hisi_sas/hisi_sas_main.c @@ -616,7 +616,6 @@ static void hisi_sas_bytes_dmaed(struct hisi_hba *hisi_hba, int phy_no) { struct hisi_sas_phy *phy = &hisi_hba->phy[phy_no]; struct asd_sas_phy *sas_phy = &phy->sas_phy; - struct sas_ha_struct *sas_ha; if (!phy->phy_attached) return; @@ -627,8 +626,7 @@ static void hisi_sas_bytes_dmaed(struct hisi_hba *hisi_hba, int phy_no) return; } - sas_ha = &hisi_hba->sha; - sas_ha->notify_phy_event(sas_phy, PHYE_OOB_DONE); + sas_notify_phy_event(sas_phy, PHYE_OOB_DONE); if (sas_phy->phy) { struct sas_phy *sphy = sas_phy->phy; @@ -656,7 +654,7 @@ static void hisi_sas_bytes_dmaed(struct hisi_hba *hisi_hba, int phy_no) } sas_phy->frame_rcvd_size = phy->frame_rcvd_size; - sas_ha->notify_port_event(sas_phy, PORTE_BYTES_DMAED); + sas_notify_port_event(sas_phy, PORTE_BYTES_DMAED); } static struct hisi_sas_device *hisi_sas_alloc_dev(struct domain_device *device) @@ -1411,7 +1409,6 @@ static void hisi_sas_refresh_port_id(struct hisi_hba *hisi_hba) static void hisi_sas_rescan_topology(struct hisi_hba *hisi_hba, u32 state) { - struct sas_ha_struct *sas_ha = &hisi_hba->sha; struct asd_sas_port *_sas_port = NULL; int phy_no; @@ -1432,7 +1429,7 @@ static void hisi_sas_rescan_topology(struct hisi_hba *hisi_hba, u32 state) _sas_port = sas_port; if (dev_is_expander(dev->dev_type)) - sas_ha->notify_port_event(sas_phy, + sas_notify_port_event(sas_phy, PORTE_BROADCAST_RCVD); } } else { @@ -2194,7 +2191,6 @@ void hisi_sas_phy_down(struct hisi_hba *hisi_hba, int phy_no, int rdy) { struct hisi_sas_phy *phy = &hisi_hba->phy[phy_no]; struct asd_sas_phy *sas_phy = &phy->sas_phy; - struct sas_ha_struct *sas_ha = &hisi_hba->sha; struct device *dev = hisi_hba->dev; if (rdy) { @@ -2210,7 +2206,7 @@ void hisi_sas_phy_down(struct hisi_hba *hisi_hba, int phy_no, int rdy) return; } /* Phy down and not ready */ - sas_ha->notify_phy_event(sas_phy, PHYE_LOSS_OF_SIGNAL); + sas_notify_phy_event(sas_phy, PHYE_LOSS_OF_SIGNAL); sas_phy_disconnected(sas_phy); if (port) { diff --git a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c index 45e866cb9164..22eecc89d41b 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c @@ -1408,7 +1408,6 @@ static irqreturn_t int_bcast_v1_hw(int irq, void *p) struct hisi_sas_phy *phy = p; struct hisi_hba *hisi_hba = phy->hisi_hba; struct asd_sas_phy *sas_phy = &phy->sas_phy; - struct sas_ha_struct *sha = &hisi_hba->sha; struct device *dev = hisi_hba->dev; int phy_no = sas_phy->id; u32 irq_value; @@ -1424,7 +1423,7 @@ static irqreturn_t int_bcast_v1_hw(int irq, void *p) } if (!test_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags)) - sha->notify_port_event(sas_phy, PORTE_BROADCAST_RCVD); + sas_notify_port_event(sas_phy, PORTE_BROADCAST_RCVD); end: hisi_sas_phy_write32(hisi_hba, phy_no, CHL_INT2, diff --git a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c index 9adfdefef9ca..10ba0680da04 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c @@ -2818,14 +2818,13 @@ static void phy_bcast_v2_hw(int phy_no, struct hisi_hba *hisi_hba) { struct hisi_sas_phy *phy = &hisi_hba->phy[phy_no]; struct asd_sas_phy *sas_phy = &phy->sas_phy; - struct sas_ha_struct *sas_ha = &hisi_hba->sha; u32 bcast_status; hisi_sas_phy_write32(hisi_hba, phy_no, SL_RX_BCAST_CHK_MSK, 1); bcast_status = hisi_sas_phy_read32(hisi_hba, phy_no, RX_PRIMS_STATUS); if ((bcast_status & RX_BCAST_CHG_MSK) && !test_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags)) - sas_ha->notify_port_event(sas_phy, PORTE_BROADCAST_RCVD); + sas_notify_port_event(sas_phy, PORTE_BROADCAST_RCVD); hisi_sas_phy_write32(hisi_hba, phy_no, CHL_INT0, CHL_INT0_SL_RX_BCST_ACK_MSK); hisi_sas_phy_write32(hisi_hba, phy_no, SL_RX_BCAST_CHK_MSK, 0); diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c index 91a7286e8102..fcf427f46423 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c @@ -1595,14 +1595,13 @@ static irqreturn_t phy_bcast_v3_hw(int phy_no, struct hisi_hba *hisi_hba) { struct hisi_sas_phy *phy = &hisi_hba->phy[phy_no]; struct asd_sas_phy *sas_phy = &phy->sas_phy; - struct sas_ha_struct *sas_ha = &hisi_hba->sha; u32 bcast_status; hisi_sas_phy_write32(hisi_hba, phy_no, SL_RX_BCAST_CHK_MSK, 1); bcast_status = hisi_sas_phy_read32(hisi_hba, phy_no, RX_PRIMS_STATUS); if ((bcast_status & RX_BCAST_CHG_MSK) && !test_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags)) - sas_ha->notify_port_event(sas_phy, PORTE_BROADCAST_RCVD); + sas_notify_port_event(sas_phy, PORTE_BROADCAST_RCVD); hisi_sas_phy_write32(hisi_hba, phy_no, CHL_INT0, CHL_INT0_SL_RX_BCST_ACK_MSK); hisi_sas_phy_write32(hisi_hba, phy_no, SL_RX_BCAST_CHK_MSK, 0); diff --git a/drivers/scsi/isci/port.c b/drivers/scsi/isci/port.c index 1df45f028ea7..8d9349738067 100644 --- a/drivers/scsi/isci/port.c +++ b/drivers/scsi/isci/port.c @@ -164,7 +164,7 @@ static void isci_port_bc_change_received(struct isci_host *ihost, "%s: isci_phy = %p, sas_phy = %p\n", __func__, iphy, &iphy->sas_phy); - ihost->sas_ha.notify_port_event(&iphy->sas_phy, PORTE_BROADCAST_RCVD); + sas_notify_port_event(&iphy->sas_phy, PORTE_BROADCAST_RCVD); sci_port_bcn_enable(iport); } @@ -223,8 +223,7 @@ static void isci_port_link_up(struct isci_host *isci_host, /* Notify libsas that we have an address frame, if indeed * we've found an SSP, SMP, or STP target */ if (success) - isci_host->sas_ha.notify_port_event(&iphy->sas_phy, - PORTE_BYTES_DMAED); + sas_notify_port_event(&iphy->sas_phy, PORTE_BYTES_DMAED); } @@ -270,7 +269,7 @@ static void isci_port_link_down(struct isci_host *isci_host, * isci_port_deformed and isci_dev_gone functions. */ sas_phy_disconnected(&isci_phy->sas_phy); - isci_host->sas_ha.notify_phy_event(&isci_phy->sas_phy, + sas_notify_phy_event(&isci_phy->sas_phy, PHYE_LOSS_OF_SIGNAL); dev_dbg(&isci_host->pdev->dev, diff --git a/drivers/scsi/libsas/sas_event.c b/drivers/scsi/libsas/sas_event.c index a1852f6c042b..112a1b76f63b 100644 --- a/drivers/scsi/libsas/sas_event.c +++ b/drivers/scsi/libsas/sas_event.c @@ -109,7 +109,7 @@ void sas_enable_revalidation(struct sas_ha_struct *ha) sas_phy = container_of(port->phy_list.next, struct asd_sas_phy, port_phy_el); - ha->notify_port_event(sas_phy, PORTE_BROADCAST_RCVD); + sas_notify_port_event(sas_phy, PORTE_BROADCAST_RCVD); } mutex_unlock(&ha->disco_mutex); } @@ -131,7 +131,7 @@ static void sas_phy_event_worker(struct work_struct *work) sas_free_event(ev); } -static int sas_notify_port_event(struct asd_sas_phy *phy, enum port_event event) +int sas_notify_port_event(struct asd_sas_phy *phy, enum port_event event) { struct asd_sas_event *ev; struct sas_ha_struct *ha = phy->ha; @@ -151,6 +151,7 @@ static int sas_notify_port_event(struct asd_sas_phy *phy, enum port_event event) return ret; } +EXPORT_SYMBOL_GPL(sas_notify_port_event); int sas_notify_phy_event(struct asd_sas_phy *phy, enum phy_event event) { @@ -172,11 +173,5 @@ int sas_notify_phy_event(struct asd_sas_phy *phy, enum phy_event event) return ret; } +EXPORT_SYMBOL_GPL(sas_notify_phy_event); -int sas_init_events(struct sas_ha_struct *sas_ha) -{ - sas_ha->notify_port_event = sas_notify_port_event; - sas_ha->notify_phy_event = sas_notify_phy_event; - - return 0; -} diff --git a/drivers/scsi/libsas/sas_init.c b/drivers/scsi/libsas/sas_init.c index 21c43b18d5d5..6dc2505d36af 100644 --- a/drivers/scsi/libsas/sas_init.c +++ b/drivers/scsi/libsas/sas_init.c @@ -123,12 +123,6 @@ int sas_register_ha(struct sas_ha_struct *sas_ha) goto Undo_phys; } - error = sas_init_events(sas_ha); - if (error) { - pr_notice("couldn't start event thread:%d\n", error); - goto Undo_ports; - } - error = -ENOMEM; snprintf(name, sizeof(name), "%s_event_q", dev_name(sas_ha->dev)); sas_ha->event_q = create_singlethread_workqueue(name); diff --git a/drivers/scsi/libsas/sas_internal.h b/drivers/scsi/libsas/sas_internal.h index 1f1d01901978..53ea32ed17a7 100644 --- a/drivers/scsi/libsas/sas_internal.h +++ b/drivers/scsi/libsas/sas_internal.h @@ -54,7 +54,6 @@ void sas_free_event(struct asd_sas_event *event); int sas_register_ports(struct sas_ha_struct *sas_ha); void sas_unregister_ports(struct sas_ha_struct *sas_ha); -int sas_init_events(struct sas_ha_struct *sas_ha); void sas_disable_revalidation(struct sas_ha_struct *ha); void sas_enable_revalidation(struct sas_ha_struct *ha); void __sas_drain_work(struct sas_ha_struct *ha); diff --git a/drivers/scsi/mvsas/mv_sas.c b/drivers/scsi/mvsas/mv_sas.c index a920eced92ec..e5e3e95f78b0 100644 --- a/drivers/scsi/mvsas/mv_sas.c +++ b/drivers/scsi/mvsas/mv_sas.c @@ -220,7 +220,7 @@ static void mvs_bytes_dmaed(struct mvs_info *mvi, int i) { struct mvs_phy *phy = &mvi->phy[i]; struct asd_sas_phy *sas_phy = &phy->sas_phy; - struct sas_ha_struct *sas_ha; + if (!phy->phy_attached) return; @@ -229,8 +229,7 @@ static void mvs_bytes_dmaed(struct mvs_info *mvi, int i) return; } - sas_ha = mvi->sas; - sas_ha->notify_phy_event(sas_phy, PHYE_OOB_DONE); + sas_notify_phy_event(sas_phy, PHYE_OOB_DONE); if (sas_phy->phy) { struct sas_phy *sphy = sas_phy->phy; @@ -262,8 +261,7 @@ static void mvs_bytes_dmaed(struct mvs_info *mvi, int i) sas_phy->frame_rcvd_size = phy->frame_rcvd_size; - mvi->sas->notify_port_event(sas_phy, - PORTE_BYTES_DMAED); + sas_notify_port_event(sas_phy, PORTE_BYTES_DMAED); } void mvs_scan_start(struct Scsi_Host *shost) @@ -1880,7 +1878,6 @@ static void mvs_work_queue(struct work_struct *work) struct mvs_info *mvi = mwq->mvi; unsigned long flags; u32 phy_no = (unsigned long) mwq->data; - struct sas_ha_struct *sas_ha = mvi->sas; struct mvs_phy *phy = &mvi->phy[phy_no]; struct asd_sas_phy *sas_phy = &phy->sas_phy; @@ -1895,7 +1892,7 @@ static void mvs_work_queue(struct work_struct *work) if (!(tmp & PHY_READY_MASK)) { sas_phy_disconnected(sas_phy); mvs_phy_disconnected(phy); - sas_ha->notify_phy_event(sas_phy, + sas_notify_phy_event(sas_phy, PHYE_LOSS_OF_SIGNAL); mv_dprintk("phy%d Removed Device\n", phy_no); } else { @@ -1908,8 +1905,7 @@ static void mvs_work_queue(struct work_struct *work) } } else if (mwq->handler & EXP_BRCT_CHG) { phy->phy_event &= ~EXP_BRCT_CHG; - sas_ha->notify_port_event(sas_phy, - PORTE_BROADCAST_RCVD); + sas_notify_port_event(sas_phy, PORTE_BROADCAST_RCVD); mv_dprintk("phy%d Got Broadcast Change\n", phy_no); } list_del(&mwq->entry); diff --git a/drivers/scsi/pm8001/pm8001_hwi.c b/drivers/scsi/pm8001/pm8001_hwi.c index 4bc11533fc91..f2c2c73fc9a5 100644 --- a/drivers/scsi/pm8001/pm8001_hwi.c +++ b/drivers/scsi/pm8001/pm8001_hwi.c @@ -3185,7 +3185,7 @@ void pm8001_bytes_dmaed(struct pm8001_hba_info *pm8001_ha, int i) pm8001_dbg(pm8001_ha, MSG, "phy %d byte dmaded.\n", i); sas_phy->frame_rcvd_size = phy->frame_rcvd_size; - pm8001_ha->sas->notify_port_event(sas_phy, PORTE_BYTES_DMAED); + sas_notify_port_event(sas_phy, PORTE_BYTES_DMAED); } /* Get the link rate speed */ @@ -3299,7 +3299,6 @@ hw_event_sas_phy_up(struct pm8001_hba_info *pm8001_ha, void *piomb) u32 npip_portstate = le32_to_cpu(pPayload->npip_portstate); u8 portstate = (u8)(npip_portstate & 0x0000000F); struct pm8001_port *port = &pm8001_ha->port[port_id]; - struct sas_ha_struct *sas_ha = pm8001_ha->sas; struct pm8001_phy *phy = &pm8001_ha->phy[phy_id]; unsigned long flags; u8 deviceType = pPayload->sas_identify.dev_type; @@ -3343,7 +3342,7 @@ hw_event_sas_phy_up(struct pm8001_hba_info *pm8001_ha, void *piomb) else if (phy->identify.device_type != SAS_PHY_UNUSED) phy->identify.target_port_protocols = SAS_PROTOCOL_SMP; phy->sas_phy.oob_mode = SAS_OOB_MODE; - sas_ha->notify_phy_event(&phy->sas_phy, PHYE_OOB_DONE); + sas_notify_phy_event(&phy->sas_phy, PHYE_OOB_DONE); spin_lock_irqsave(&phy->sas_phy.frame_rcvd_lock, flags); memcpy(phy->frame_rcvd, &pPayload->sas_identify, sizeof(struct sas_identify_frame)-4); @@ -3375,7 +3374,6 @@ hw_event_sata_phy_up(struct pm8001_hba_info *pm8001_ha, void *piomb) u32 npip_portstate = le32_to_cpu(pPayload->npip_portstate); u8 portstate = (u8)(npip_portstate & 0x0000000F); struct pm8001_port *port = &pm8001_ha->port[port_id]; - struct sas_ha_struct *sas_ha = pm8001_ha->sas; struct pm8001_phy *phy = &pm8001_ha->phy[phy_id]; unsigned long flags; pm8001_dbg(pm8001_ha, DEVIO, "HW_EVENT_SATA_PHY_UP port id = %d, phy id = %d\n", @@ -3387,7 +3385,7 @@ hw_event_sata_phy_up(struct pm8001_hba_info *pm8001_ha, void *piomb) phy->phy_type |= PORT_TYPE_SATA; phy->phy_attached = 1; phy->sas_phy.oob_mode = SATA_OOB_MODE; - sas_ha->notify_phy_event(&phy->sas_phy, PHYE_OOB_DONE); + sas_notify_phy_event(&phy->sas_phy, PHYE_OOB_DONE); spin_lock_irqsave(&phy->sas_phy.frame_rcvd_lock, flags); memcpy(phy->frame_rcvd, ((u8 *)&pPayload->sata_fis - 4), sizeof(struct dev_to_host_fis)); @@ -3734,11 +3732,11 @@ static int mpi_hw_event(struct pm8001_hba_info *pm8001_ha, void* piomb) break; case HW_EVENT_SATA_SPINUP_HOLD: pm8001_dbg(pm8001_ha, MSG, "HW_EVENT_SATA_SPINUP_HOLD\n"); - sas_ha->notify_phy_event(&phy->sas_phy, PHYE_SPINUP_HOLD); + sas_notify_phy_event(&phy->sas_phy, PHYE_SPINUP_HOLD); break; case HW_EVENT_PHY_DOWN: pm8001_dbg(pm8001_ha, MSG, "HW_EVENT_PHY_DOWN\n"); - sas_ha->notify_phy_event(&phy->sas_phy, PHYE_LOSS_OF_SIGNAL); + sas_notify_phy_event(&phy->sas_phy, PHYE_LOSS_OF_SIGNAL); phy->phy_attached = 0; phy->phy_state = 0; hw_event_phy_down(pm8001_ha, piomb); @@ -3747,7 +3745,7 @@ static int mpi_hw_event(struct pm8001_hba_info *pm8001_ha, void* piomb) pm8001_dbg(pm8001_ha, MSG, "HW_EVENT_PORT_INVALID\n"); sas_phy_disconnected(sas_phy); phy->phy_attached = 0; - sas_ha->notify_port_event(sas_phy, PORTE_LINK_RESET_ERR); + sas_notify_port_event(sas_phy, PORTE_LINK_RESET_ERR); break; /* the broadcast change primitive received, tell the LIBSAS this event to revalidate the sas domain*/ @@ -3758,20 +3756,20 @@ static int mpi_hw_event(struct pm8001_hba_info *pm8001_ha, void* piomb) spin_lock_irqsave(&sas_phy->sas_prim_lock, flags); sas_phy->sas_prim = HW_EVENT_BROADCAST_CHANGE; spin_unlock_irqrestore(&sas_phy->sas_prim_lock, flags); - sas_ha->notify_port_event(sas_phy, PORTE_BROADCAST_RCVD); + sas_notify_port_event(sas_phy, PORTE_BROADCAST_RCVD); break; case HW_EVENT_PHY_ERROR: pm8001_dbg(pm8001_ha, MSG, "HW_EVENT_PHY_ERROR\n"); sas_phy_disconnected(&phy->sas_phy); phy->phy_attached = 0; - sas_ha->notify_phy_event(&phy->sas_phy, PHYE_OOB_ERROR); + sas_notify_phy_event(&phy->sas_phy, PHYE_OOB_ERROR); break; case HW_EVENT_BROADCAST_EXP: pm8001_dbg(pm8001_ha, MSG, "HW_EVENT_BROADCAST_EXP\n"); spin_lock_irqsave(&sas_phy->sas_prim_lock, flags); sas_phy->sas_prim = HW_EVENT_BROADCAST_EXP; spin_unlock_irqrestore(&sas_phy->sas_prim_lock, flags); - sas_ha->notify_port_event(sas_phy, PORTE_BROADCAST_RCVD); + sas_notify_port_event(sas_phy, PORTE_BROADCAST_RCVD); break; case HW_EVENT_LINK_ERR_INVALID_DWORD: pm8001_dbg(pm8001_ha, MSG, @@ -3780,7 +3778,7 @@ static int mpi_hw_event(struct pm8001_hba_info *pm8001_ha, void* piomb) HW_EVENT_LINK_ERR_INVALID_DWORD, port_id, phy_id, 0, 0); sas_phy_disconnected(sas_phy); phy->phy_attached = 0; - sas_ha->notify_port_event(sas_phy, PORTE_LINK_RESET_ERR); + sas_notify_port_event(sas_phy, PORTE_LINK_RESET_ERR); break; case HW_EVENT_LINK_ERR_DISPARITY_ERROR: pm8001_dbg(pm8001_ha, MSG, @@ -3790,7 +3788,7 @@ static int mpi_hw_event(struct pm8001_hba_info *pm8001_ha, void* piomb) port_id, phy_id, 0, 0); sas_phy_disconnected(sas_phy); phy->phy_attached = 0; - sas_ha->notify_port_event(sas_phy, PORTE_LINK_RESET_ERR); + sas_notify_port_event(sas_phy, PORTE_LINK_RESET_ERR); break; case HW_EVENT_LINK_ERR_CODE_VIOLATION: pm8001_dbg(pm8001_ha, MSG, @@ -3800,7 +3798,7 @@ static int mpi_hw_event(struct pm8001_hba_info *pm8001_ha, void* piomb) port_id, phy_id, 0, 0); sas_phy_disconnected(sas_phy); phy->phy_attached = 0; - sas_ha->notify_port_event(sas_phy, PORTE_LINK_RESET_ERR); + sas_notify_port_event(sas_phy, PORTE_LINK_RESET_ERR); break; case HW_EVENT_LINK_ERR_LOSS_OF_DWORD_SYNCH: pm8001_dbg(pm8001_ha, MSG, @@ -3810,7 +3808,7 @@ static int mpi_hw_event(struct pm8001_hba_info *pm8001_ha, void* piomb) port_id, phy_id, 0, 0); sas_phy_disconnected(sas_phy); phy->phy_attached = 0; - sas_ha->notify_port_event(sas_phy, PORTE_LINK_RESET_ERR); + sas_notify_port_event(sas_phy, PORTE_LINK_RESET_ERR); break; case HW_EVENT_MALFUNCTION: pm8001_dbg(pm8001_ha, MSG, "HW_EVENT_MALFUNCTION\n"); @@ -3820,7 +3818,7 @@ static int mpi_hw_event(struct pm8001_hba_info *pm8001_ha, void* piomb) spin_lock_irqsave(&sas_phy->sas_prim_lock, flags); sas_phy->sas_prim = HW_EVENT_BROADCAST_SES; spin_unlock_irqrestore(&sas_phy->sas_prim_lock, flags); - sas_ha->notify_port_event(sas_phy, PORTE_BROADCAST_RCVD); + sas_notify_port_event(sas_phy, PORTE_BROADCAST_RCVD); break; case HW_EVENT_INBOUND_CRC_ERROR: pm8001_dbg(pm8001_ha, MSG, "HW_EVENT_INBOUND_CRC_ERROR\n"); @@ -3830,13 +3828,13 @@ static int mpi_hw_event(struct pm8001_hba_info *pm8001_ha, void* piomb) break; case HW_EVENT_HARD_RESET_RECEIVED: pm8001_dbg(pm8001_ha, MSG, "HW_EVENT_HARD_RESET_RECEIVED\n"); - sas_ha->notify_port_event(sas_phy, PORTE_HARD_RESET); + sas_notify_port_event(sas_phy, PORTE_HARD_RESET); break; case HW_EVENT_ID_FRAME_TIMEOUT: pm8001_dbg(pm8001_ha, MSG, "HW_EVENT_ID_FRAME_TIMEOUT\n"); sas_phy_disconnected(sas_phy); phy->phy_attached = 0; - sas_ha->notify_port_event(sas_phy, PORTE_LINK_RESET_ERR); + sas_notify_port_event(sas_phy, PORTE_LINK_RESET_ERR); break; case HW_EVENT_LINK_ERR_PHY_RESET_FAILED: pm8001_dbg(pm8001_ha, MSG, @@ -3846,20 +3844,20 @@ static int mpi_hw_event(struct pm8001_hba_info *pm8001_ha, void* piomb) port_id, phy_id, 0, 0); sas_phy_disconnected(sas_phy); phy->phy_attached = 0; - sas_ha->notify_port_event(sas_phy, PORTE_LINK_RESET_ERR); + sas_notify_port_event(sas_phy, PORTE_LINK_RESET_ERR); break; case HW_EVENT_PORT_RESET_TIMER_TMO: pm8001_dbg(pm8001_ha, MSG, "HW_EVENT_PORT_RESET_TIMER_TMO\n"); sas_phy_disconnected(sas_phy); phy->phy_attached = 0; - sas_ha->notify_port_event(sas_phy, PORTE_LINK_RESET_ERR); + sas_notify_port_event(sas_phy, PORTE_LINK_RESET_ERR); break; case HW_EVENT_PORT_RECOVERY_TIMER_TMO: pm8001_dbg(pm8001_ha, MSG, "HW_EVENT_PORT_RECOVERY_TIMER_TMO\n"); sas_phy_disconnected(sas_phy); phy->phy_attached = 0; - sas_ha->notify_port_event(sas_phy, PORTE_LINK_RESET_ERR); + sas_notify_port_event(sas_phy, PORTE_LINK_RESET_ERR); break; case HW_EVENT_PORT_RECOVER: pm8001_dbg(pm8001_ha, MSG, "HW_EVENT_PORT_RECOVER\n"); diff --git a/drivers/scsi/pm8001/pm8001_sas.c b/drivers/scsi/pm8001/pm8001_sas.c index f8d142f9b9ad..6af561a77c76 100644 --- a/drivers/scsi/pm8001/pm8001_sas.c +++ b/drivers/scsi/pm8001/pm8001_sas.c @@ -158,7 +158,6 @@ int pm8001_phy_control(struct asd_sas_phy *sas_phy, enum phy_func func, int rc = 0, phy_id = sas_phy->id; struct pm8001_hba_info *pm8001_ha = NULL; struct sas_phy_linkrates *rates; - struct sas_ha_struct *sas_ha; struct pm8001_phy *phy; DECLARE_COMPLETION_ONSTACK(completion); unsigned long flags; @@ -207,18 +206,16 @@ int pm8001_phy_control(struct asd_sas_phy *sas_phy, enum phy_func func, if (pm8001_ha->chip_id != chip_8001) { if (pm8001_ha->phy[phy_id].phy_state == PHY_STATE_LINK_UP_SPCV) { - sas_ha = pm8001_ha->sas; sas_phy_disconnected(&phy->sas_phy); - sas_ha->notify_phy_event(&phy->sas_phy, + sas_notify_phy_event(&phy->sas_phy, PHYE_LOSS_OF_SIGNAL); phy->phy_attached = 0; } } else { if (pm8001_ha->phy[phy_id].phy_state == PHY_STATE_LINK_UP_SPC) { - sas_ha = pm8001_ha->sas; sas_phy_disconnected(&phy->sas_phy); - sas_ha->notify_phy_event(&phy->sas_phy, + sas_notify_phy_event(&phy->sas_phy, PHYE_LOSS_OF_SIGNAL); phy->phy_attached = 0; } diff --git a/drivers/scsi/pm8001/pm80xx_hwi.c b/drivers/scsi/pm8001/pm80xx_hwi.c index 6fd206abc9fc..2cae479d0383 100644 --- a/drivers/scsi/pm8001/pm80xx_hwi.c +++ b/drivers/scsi/pm8001/pm80xx_hwi.c @@ -3294,7 +3294,6 @@ hw_event_sas_phy_up(struct pm8001_hba_info *pm8001_ha, void *piomb) u8 portstate = (u8)(phyid_npip_portstate & 0x0000000F); struct pm8001_port *port = &pm8001_ha->port[port_id]; - struct sas_ha_struct *sas_ha = pm8001_ha->sas; struct pm8001_phy *phy = &pm8001_ha->phy[phy_id]; unsigned long flags; u8 deviceType = pPayload->sas_identify.dev_type; @@ -3339,7 +3338,7 @@ hw_event_sas_phy_up(struct pm8001_hba_info *pm8001_ha, void *piomb) else if (phy->identify.device_type != SAS_PHY_UNUSED) phy->identify.target_port_protocols = SAS_PROTOCOL_SMP; phy->sas_phy.oob_mode = SAS_OOB_MODE; - sas_ha->notify_phy_event(&phy->sas_phy, PHYE_OOB_DONE); + sas_notify_phy_event(&phy->sas_phy, PHYE_OOB_DONE); spin_lock_irqsave(&phy->sas_phy.frame_rcvd_lock, flags); memcpy(phy->frame_rcvd, &pPayload->sas_identify, sizeof(struct sas_identify_frame)-4); @@ -3373,7 +3372,6 @@ hw_event_sata_phy_up(struct pm8001_hba_info *pm8001_ha, void *piomb) u8 portstate = (u8)(phyid_npip_portstate & 0x0000000F); struct pm8001_port *port = &pm8001_ha->port[port_id]; - struct sas_ha_struct *sas_ha = pm8001_ha->sas; struct pm8001_phy *phy = &pm8001_ha->phy[phy_id]; unsigned long flags; pm8001_dbg(pm8001_ha, DEVIO, @@ -3387,7 +3385,7 @@ hw_event_sata_phy_up(struct pm8001_hba_info *pm8001_ha, void *piomb) phy->phy_type |= PORT_TYPE_SATA; phy->phy_attached = 1; phy->sas_phy.oob_mode = SATA_OOB_MODE; - sas_ha->notify_phy_event(&phy->sas_phy, PHYE_OOB_DONE); + sas_notify_phy_event(&phy->sas_phy, PHYE_OOB_DONE); spin_lock_irqsave(&phy->sas_phy.frame_rcvd_lock, flags); memcpy(phy->frame_rcvd, ((u8 *)&pPayload->sata_fis - 4), sizeof(struct dev_to_host_fis)); @@ -3469,11 +3467,8 @@ hw_event_phy_down(struct pm8001_hba_info *pm8001_ha, void *piomb) break; } - if (port_sata && (portstate != PORT_IN_RESET)) { - struct sas_ha_struct *sas_ha = pm8001_ha->sas; - - sas_ha->notify_phy_event(&phy->sas_phy, PHYE_LOSS_OF_SIGNAL); - } + if (port_sata && (portstate != PORT_IN_RESET)) + sas_notify_phy_event(&phy->sas_phy, PHYE_LOSS_OF_SIGNAL); } static int mpi_phy_start_resp(struct pm8001_hba_info *pm8001_ha, void *piomb) @@ -3571,7 +3566,7 @@ static int mpi_hw_event(struct pm8001_hba_info *pm8001_ha, void *piomb) break; case HW_EVENT_SATA_SPINUP_HOLD: pm8001_dbg(pm8001_ha, MSG, "HW_EVENT_SATA_SPINUP_HOLD\n"); - sas_ha->notify_phy_event(&phy->sas_phy, PHYE_SPINUP_HOLD); + sas_notify_phy_event(&phy->sas_phy, PHYE_SPINUP_HOLD); break; case HW_EVENT_PHY_DOWN: pm8001_dbg(pm8001_ha, MSG, "HW_EVENT_PHY_DOWN\n"); @@ -3587,7 +3582,7 @@ static int mpi_hw_event(struct pm8001_hba_info *pm8001_ha, void *piomb) pm8001_dbg(pm8001_ha, MSG, "HW_EVENT_PORT_INVALID\n"); sas_phy_disconnected(sas_phy); phy->phy_attached = 0; - sas_ha->notify_port_event(sas_phy, PORTE_LINK_RESET_ERR); + sas_notify_port_event(sas_phy, PORTE_LINK_RESET_ERR); break; /* the broadcast change primitive received, tell the LIBSAS this event to revalidate the sas domain*/ @@ -3598,20 +3593,20 @@ static int mpi_hw_event(struct pm8001_hba_info *pm8001_ha, void *piomb) spin_lock_irqsave(&sas_phy->sas_prim_lock, flags); sas_phy->sas_prim = HW_EVENT_BROADCAST_CHANGE; spin_unlock_irqrestore(&sas_phy->sas_prim_lock, flags); - sas_ha->notify_port_event(sas_phy, PORTE_BROADCAST_RCVD); + sas_notify_port_event(sas_phy, PORTE_BROADCAST_RCVD); break; case HW_EVENT_PHY_ERROR: pm8001_dbg(pm8001_ha, MSG, "HW_EVENT_PHY_ERROR\n"); sas_phy_disconnected(&phy->sas_phy); phy->phy_attached = 0; - sas_ha->notify_phy_event(&phy->sas_phy, PHYE_OOB_ERROR); + sas_notify_phy_event(&phy->sas_phy, PHYE_OOB_ERROR); break; case HW_EVENT_BROADCAST_EXP: pm8001_dbg(pm8001_ha, MSG, "HW_EVENT_BROADCAST_EXP\n"); spin_lock_irqsave(&sas_phy->sas_prim_lock, flags); sas_phy->sas_prim = HW_EVENT_BROADCAST_EXP; spin_unlock_irqrestore(&sas_phy->sas_prim_lock, flags); - sas_ha->notify_port_event(sas_phy, PORTE_BROADCAST_RCVD); + sas_notify_port_event(sas_phy, PORTE_BROADCAST_RCVD); break; case HW_EVENT_LINK_ERR_INVALID_DWORD: pm8001_dbg(pm8001_ha, MSG, @@ -3648,7 +3643,7 @@ static int mpi_hw_event(struct pm8001_hba_info *pm8001_ha, void *piomb) spin_lock_irqsave(&sas_phy->sas_prim_lock, flags); sas_phy->sas_prim = HW_EVENT_BROADCAST_SES; spin_unlock_irqrestore(&sas_phy->sas_prim_lock, flags); - sas_ha->notify_port_event(sas_phy, PORTE_BROADCAST_RCVD); + sas_notify_port_event(sas_phy, PORTE_BROADCAST_RCVD); break; case HW_EVENT_INBOUND_CRC_ERROR: pm8001_dbg(pm8001_ha, MSG, "HW_EVENT_INBOUND_CRC_ERROR\n"); @@ -3658,13 +3653,13 @@ static int mpi_hw_event(struct pm8001_hba_info *pm8001_ha, void *piomb) break; case HW_EVENT_HARD_RESET_RECEIVED: pm8001_dbg(pm8001_ha, MSG, "HW_EVENT_HARD_RESET_RECEIVED\n"); - sas_ha->notify_port_event(sas_phy, PORTE_HARD_RESET); + sas_notify_port_event(sas_phy, PORTE_HARD_RESET); break; case HW_EVENT_ID_FRAME_TIMEOUT: pm8001_dbg(pm8001_ha, MSG, "HW_EVENT_ID_FRAME_TIMEOUT\n"); sas_phy_disconnected(sas_phy); phy->phy_attached = 0; - sas_ha->notify_port_event(sas_phy, PORTE_LINK_RESET_ERR); + sas_notify_port_event(sas_phy, PORTE_LINK_RESET_ERR); break; case HW_EVENT_LINK_ERR_PHY_RESET_FAILED: pm8001_dbg(pm8001_ha, MSG, @@ -3674,7 +3669,7 @@ static int mpi_hw_event(struct pm8001_hba_info *pm8001_ha, void *piomb) port_id, phy_id, 0, 0); sas_phy_disconnected(sas_phy); phy->phy_attached = 0; - sas_ha->notify_port_event(sas_phy, PORTE_LINK_RESET_ERR); + sas_notify_port_event(sas_phy, PORTE_LINK_RESET_ERR); break; case HW_EVENT_PORT_RESET_TIMER_TMO: pm8001_dbg(pm8001_ha, MSG, "HW_EVENT_PORT_RESET_TIMER_TMO\n"); @@ -3682,7 +3677,7 @@ static int mpi_hw_event(struct pm8001_hba_info *pm8001_ha, void *piomb) port_id, phy_id, 0, 0); sas_phy_disconnected(sas_phy); phy->phy_attached = 0; - sas_ha->notify_port_event(sas_phy, PORTE_LINK_RESET_ERR); + sas_notify_port_event(sas_phy, PORTE_LINK_RESET_ERR); if (pm8001_ha->phy[phy_id].reset_completion) { pm8001_ha->phy[phy_id].port_reset_status = PORT_RESET_TMO; @@ -3699,7 +3694,7 @@ static int mpi_hw_event(struct pm8001_hba_info *pm8001_ha, void *piomb) for (i = 0; i < pm8001_ha->chip->n_phy; i++) { if (port->wide_port_phymap & (1 << i)) { phy = &pm8001_ha->phy[i]; - sas_ha->notify_phy_event(&phy->sas_phy, + sas_notify_phy_event(&phy->sas_phy, PHYE_LOSS_OF_SIGNAL); port->wide_port_phymap &= ~(1 << i); } diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h index 4e2d61e8fb1e..3387149502e9 100644 --- a/include/scsi/libsas.h +++ b/include/scsi/libsas.h @@ -391,10 +391,6 @@ struct sas_ha_struct { int strict_wide_ports; /* both sas_addr and attached_sas_addr must match * their siblings when forming wide ports */ - /* LLDD calls these to notify the class of an event. */ - int (*notify_port_event)(struct asd_sas_phy *, enum port_event); - int (*notify_phy_event)(struct asd_sas_phy *, enum phy_event); - void *lldd_ha; /* not touched by sas class code */ struct list_head eh_done_q; /* complete via scsi_eh_flush_done_q */ @@ -706,4 +702,7 @@ struct sas_phy *sas_get_local_phy(struct domain_device *dev); int sas_request_addr(struct Scsi_Host *shost, u8 *addr); +int sas_notify_port_event(struct asd_sas_phy *phy, enum port_event event); +int sas_notify_phy_event(struct asd_sas_phy *phy, enum phy_event event); + #endif /* _SASLIB_H_ */ -- cgit v1.2.3 From c2d0f1a65ab9fbabebb463bf36f50ea8f4633386 Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Mon, 18 Jan 2021 11:09:39 +0100 Subject: scsi: libsas: Introduce a _gfp() variant of event notifiers sas_alloc_event() uses in_interrupt() to decide which allocation should be used. The usage of in_interrupt() in drivers is phased out and Linus clearly requested that code which changes behaviour depending on context should either be separated or the context be conveyed in an argument passed by the caller, which usually knows the context. The in_interrupt() check is also only partially correct, because it fails to choose the correct code path when just preemption or interrupts are disabled. For example, as in the following call chain: mvsas/mv_sas.c: mvs_work_queue() [process context] spin_lock_irqsave(mvs_info::lock, ) -> libsas/sas_event.c: sas_notify_phy_event() -> sas_alloc_event() -> in_interrupt() = false -> invalid GFP_KERNEL allocation -> libsas/sas_event.c: sas_notify_port_event() -> sas_alloc_event() -> in_interrupt() = false -> invalid GFP_KERNEL allocation Introduce sas_alloc_event_gfp(), sas_notify_port_event_gfp(), and sas_notify_phy_event_gfp(), which all behave like the non _gfp() variants but use a caller-passed GFP mask for allocations. For bisectability, all callers will be modified first to pass GFP context, then the non _gfp() libsas API variants will be modified to take a gfp_t by default. Link: https://lore.kernel.org/r/20210118100955.1761652-4-a.darwish@linutronix.de Fixes: 1c393b970e0f ("scsi: libsas: Use dynamic alloced work to avoid sas event lost") Cc: Jason Yan Reviewed-by: John Garry Signed-off-by: Ahmed S. Darwish Signed-off-by: Martin K. Petersen --- Documentation/scsi/libsas.rst | 2 ++ drivers/scsi/libsas/sas_event.c | 65 +++++++++++++++++++++++++++++++------- drivers/scsi/libsas/sas_init.c | 21 +++++++++--- drivers/scsi/libsas/sas_internal.h | 4 +++ include/scsi/libsas.h | 4 +++ 5 files changed, 79 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/Documentation/scsi/libsas.rst b/Documentation/scsi/libsas.rst index 6722e352444b..ea63ab3a9216 100644 --- a/Documentation/scsi/libsas.rst +++ b/Documentation/scsi/libsas.rst @@ -191,6 +191,8 @@ The event interface:: /* LLDD calls these to notify the class of an event. */ void sas_notify_port_event(struct sas_phy *, enum port_event); void sas_notify_phy_event(struct sas_phy *, enum phy_event); + void sas_notify_port_event_gfp(struct sas_phy *, enum port_event, gfp_t); + void sas_notify_phy_event_gfp(struct sas_phy *, enum phy_event, gfp_t); The port notification:: diff --git a/drivers/scsi/libsas/sas_event.c b/drivers/scsi/libsas/sas_event.c index 112a1b76f63b..ba266a17250a 100644 --- a/drivers/scsi/libsas/sas_event.c +++ b/drivers/scsi/libsas/sas_event.c @@ -131,18 +131,15 @@ static void sas_phy_event_worker(struct work_struct *work) sas_free_event(ev); } -int sas_notify_port_event(struct asd_sas_phy *phy, enum port_event event) +static int __sas_notify_port_event(struct asd_sas_phy *phy, + enum port_event event, + struct asd_sas_event *ev) { - struct asd_sas_event *ev; struct sas_ha_struct *ha = phy->ha; int ret; BUG_ON(event >= PORT_NUM_EVENTS); - ev = sas_alloc_event(phy); - if (!ev) - return -ENOMEM; - INIT_SAS_EVENT(ev, sas_port_event_worker, phy, event); ret = sas_queue_event(event, &ev->work, ha); @@ -151,20 +148,41 @@ int sas_notify_port_event(struct asd_sas_phy *phy, enum port_event event) return ret; } -EXPORT_SYMBOL_GPL(sas_notify_port_event); -int sas_notify_phy_event(struct asd_sas_phy *phy, enum phy_event event) +int sas_notify_port_event_gfp(struct asd_sas_phy *phy, enum port_event event, + gfp_t gfp_flags) { struct asd_sas_event *ev; - struct sas_ha_struct *ha = phy->ha; - int ret; - BUG_ON(event >= PHY_NUM_EVENTS); + ev = sas_alloc_event_gfp(phy, gfp_flags); + if (!ev) + return -ENOMEM; + + return __sas_notify_port_event(phy, event, ev); +} +EXPORT_SYMBOL_GPL(sas_notify_port_event_gfp); + +int sas_notify_port_event(struct asd_sas_phy *phy, enum port_event event) +{ + struct asd_sas_event *ev; ev = sas_alloc_event(phy); if (!ev) return -ENOMEM; + return __sas_notify_port_event(phy, event, ev); +} +EXPORT_SYMBOL_GPL(sas_notify_port_event); + +static inline int __sas_notify_phy_event(struct asd_sas_phy *phy, + enum phy_event event, + struct asd_sas_event *ev) +{ + struct sas_ha_struct *ha = phy->ha; + int ret; + + BUG_ON(event >= PHY_NUM_EVENTS); + INIT_SAS_EVENT(ev, sas_phy_event_worker, phy, event); ret = sas_queue_event(event, &ev->work, ha); @@ -173,5 +191,28 @@ int sas_notify_phy_event(struct asd_sas_phy *phy, enum phy_event event) return ret; } -EXPORT_SYMBOL_GPL(sas_notify_phy_event); +int sas_notify_phy_event_gfp(struct asd_sas_phy *phy, enum phy_event event, + gfp_t gfp_flags) +{ + struct asd_sas_event *ev; + + ev = sas_alloc_event_gfp(phy, gfp_flags); + if (!ev) + return -ENOMEM; + + return __sas_notify_phy_event(phy, event, ev); +} +EXPORT_SYMBOL_GPL(sas_notify_phy_event_gfp); + +int sas_notify_phy_event(struct asd_sas_phy *phy, enum phy_event event) +{ + struct asd_sas_event *ev; + + ev = sas_alloc_event(phy); + if (!ev) + return -ENOMEM; + + return __sas_notify_phy_event(phy, event, ev); +} +EXPORT_SYMBOL_GPL(sas_notify_phy_event); diff --git a/drivers/scsi/libsas/sas_init.c b/drivers/scsi/libsas/sas_init.c index 6dc2505d36af..f8ae1f0f17d3 100644 --- a/drivers/scsi/libsas/sas_init.c +++ b/drivers/scsi/libsas/sas_init.c @@ -584,16 +584,15 @@ sas_domain_attach_transport(struct sas_domain_function_template *dft) } EXPORT_SYMBOL_GPL(sas_domain_attach_transport); - -struct asd_sas_event *sas_alloc_event(struct asd_sas_phy *phy) +static struct asd_sas_event *__sas_alloc_event(struct asd_sas_phy *phy, + gfp_t gfp_flags) { struct asd_sas_event *event; - gfp_t flags = in_interrupt() ? GFP_ATOMIC : GFP_KERNEL; struct sas_ha_struct *sas_ha = phy->ha; struct sas_internal *i = to_sas_internal(sas_ha->core.shost->transportt); - event = kmem_cache_zalloc(sas_event_cache, flags); + event = kmem_cache_zalloc(sas_event_cache, gfp_flags); if (!event) return NULL; @@ -604,7 +603,8 @@ struct asd_sas_event *sas_alloc_event(struct asd_sas_phy *phy) if (cmpxchg(&phy->in_shutdown, 0, 1) == 0) { pr_notice("The phy%d bursting events, shut it down.\n", phy->id); - sas_notify_phy_event(phy, PHYE_SHUTDOWN); + sas_notify_phy_event_gfp(phy, PHYE_SHUTDOWN, + gfp_flags); } } else { /* Do not support PHY control, stop allocating events */ @@ -618,6 +618,17 @@ struct asd_sas_event *sas_alloc_event(struct asd_sas_phy *phy) return event; } +struct asd_sas_event *sas_alloc_event(struct asd_sas_phy *phy) +{ + return __sas_alloc_event(phy, in_interrupt() ? GFP_ATOMIC : GFP_KERNEL); +} + +struct asd_sas_event *sas_alloc_event_gfp(struct asd_sas_phy *phy, + gfp_t gfp_flags) +{ + return __sas_alloc_event(phy, gfp_flags); +} + void sas_free_event(struct asd_sas_event *event) { struct asd_sas_phy *phy = event->phy; diff --git a/drivers/scsi/libsas/sas_internal.h b/drivers/scsi/libsas/sas_internal.h index 53ea32ed17a7..52e09c3e2b50 100644 --- a/drivers/scsi/libsas/sas_internal.h +++ b/drivers/scsi/libsas/sas_internal.h @@ -49,6 +49,8 @@ int sas_register_phys(struct sas_ha_struct *sas_ha); void sas_unregister_phys(struct sas_ha_struct *sas_ha); struct asd_sas_event *sas_alloc_event(struct asd_sas_phy *phy); +struct asd_sas_event *sas_alloc_event_gfp(struct asd_sas_phy *phy, + gfp_t gfp_flags); void sas_free_event(struct asd_sas_event *event); int sas_register_ports(struct sas_ha_struct *sas_ha); @@ -77,6 +79,8 @@ int sas_smp_phy_control(struct domain_device *dev, int phy_id, int sas_smp_get_phy_events(struct sas_phy *phy); int sas_notify_phy_event(struct asd_sas_phy *phy, enum phy_event event); +int sas_notify_phy_event_gfp(struct asd_sas_phy *phy, enum phy_event event, + gfp_t flags); void sas_device_set_phy(struct domain_device *dev, struct sas_port *port); struct domain_device *sas_find_dev_by_rphy(struct sas_rphy *rphy); struct domain_device *sas_ex_to_ata(struct domain_device *ex_dev, int phy_id); diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h index 3387149502e9..e6a43163ab5b 100644 --- a/include/scsi/libsas.h +++ b/include/scsi/libsas.h @@ -704,5 +704,9 @@ int sas_request_addr(struct Scsi_Host *shost, u8 *addr); int sas_notify_port_event(struct asd_sas_phy *phy, enum port_event event); int sas_notify_phy_event(struct asd_sas_phy *phy, enum phy_event event); +int sas_notify_port_event_gfp(struct asd_sas_phy *phy, enum port_event event, + gfp_t gfp_flags); +int sas_notify_phy_event_gfp(struct asd_sas_phy *phy, enum phy_event event, + gfp_t gfp_flags); #endif /* _SASLIB_H_ */ -- cgit v1.2.3 From 5d6a75a1edf63ff243d937253ced62d8edea30b5 Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Mon, 18 Jan 2021 11:09:48 +0100 Subject: scsi: libsas: Add gfp_t flags parameter to event notifications All call-sites of below libsas APIs: - sas_alloc_event() - sas_notify_port_event() - sas_notify_phy_event() have been converted to use the _gfp()-suffixed version. Modify the original APIs above to take a gfp_t flags parameter by default. For bisectability, call-sites will be modified again to use the original libsas APIs (while passing gfp_t). The temporary _gfp()-suffixed versions can then be removed. Link: https://lore.kernel.org/r/20210118100955.1761652-13-a.darwish@linutronix.de Cc: Jason Yan Reviewed-by: John Garry Signed-off-by: Ahmed S. Darwish Signed-off-by: Martin K. Petersen --- Documentation/scsi/libsas.rst | 4 +-- drivers/scsi/libsas/sas_event.c | 62 +++++++++++--------------------------- drivers/scsi/libsas/sas_init.c | 12 +++----- drivers/scsi/libsas/sas_internal.h | 5 +-- include/scsi/libsas.h | 6 ++-- 5 files changed, 31 insertions(+), 58 deletions(-) (limited to 'include') diff --git a/Documentation/scsi/libsas.rst b/Documentation/scsi/libsas.rst index ea63ab3a9216..c65086470a15 100644 --- a/Documentation/scsi/libsas.rst +++ b/Documentation/scsi/libsas.rst @@ -189,8 +189,8 @@ num_phys The event interface:: /* LLDD calls these to notify the class of an event. */ - void sas_notify_port_event(struct sas_phy *, enum port_event); - void sas_notify_phy_event(struct sas_phy *, enum phy_event); + void sas_notify_port_event(struct sas_phy *, enum port_event, gfp_t); + void sas_notify_phy_event(struct sas_phy *, enum phy_event, gfp_t); void sas_notify_port_event_gfp(struct sas_phy *, enum port_event, gfp_t); void sas_notify_phy_event_gfp(struct sas_phy *, enum phy_event, gfp_t); diff --git a/drivers/scsi/libsas/sas_event.c b/drivers/scsi/libsas/sas_event.c index 25f3aaea8142..3d0cc407b33f 100644 --- a/drivers/scsi/libsas/sas_event.c +++ b/drivers/scsi/libsas/sas_event.c @@ -132,15 +132,19 @@ static void sas_phy_event_worker(struct work_struct *work) sas_free_event(ev); } -static int __sas_notify_port_event(struct asd_sas_phy *phy, - enum port_event event, - struct asd_sas_event *ev) +int sas_notify_port_event(struct asd_sas_phy *phy, enum port_event event, + gfp_t gfp_flags) { struct sas_ha_struct *ha = phy->ha; + struct asd_sas_event *ev; int ret; BUG_ON(event >= PORT_NUM_EVENTS); + ev = sas_alloc_event_gfp(phy, gfp_flags); + if (!ev) + return -ENOMEM; + INIT_SAS_EVENT(ev, sas_port_event_worker, phy, event); ret = sas_queue_event(event, &ev->work, ha); @@ -149,41 +153,28 @@ static int __sas_notify_port_event(struct asd_sas_phy *phy, return ret; } +EXPORT_SYMBOL_GPL(sas_notify_port_event); int sas_notify_port_event_gfp(struct asd_sas_phy *phy, enum port_event event, gfp_t gfp_flags) { - struct asd_sas_event *ev; - - ev = sas_alloc_event_gfp(phy, gfp_flags); - if (!ev) - return -ENOMEM; - - return __sas_notify_port_event(phy, event, ev); + return sas_notify_port_event(phy, event, gfp_flags); } EXPORT_SYMBOL_GPL(sas_notify_port_event_gfp); -int sas_notify_port_event(struct asd_sas_phy *phy, enum port_event event) -{ - struct asd_sas_event *ev; - - ev = sas_alloc_event(phy); - if (!ev) - return -ENOMEM; - - return __sas_notify_port_event(phy, event, ev); -} -EXPORT_SYMBOL_GPL(sas_notify_port_event); - -static inline int __sas_notify_phy_event(struct asd_sas_phy *phy, - enum phy_event event, - struct asd_sas_event *ev) +int sas_notify_phy_event(struct asd_sas_phy *phy, enum phy_event event, + gfp_t gfp_flags) { struct sas_ha_struct *ha = phy->ha; + struct asd_sas_event *ev; int ret; BUG_ON(event >= PHY_NUM_EVENTS); + ev = sas_alloc_event_gfp(phy, gfp_flags); + if (!ev) + return -ENOMEM; + INIT_SAS_EVENT(ev, sas_phy_event_worker, phy, event); ret = sas_queue_event(event, &ev->work, ha); @@ -192,28 +183,11 @@ static inline int __sas_notify_phy_event(struct asd_sas_phy *phy, return ret; } +EXPORT_SYMBOL_GPL(sas_notify_phy_event); int sas_notify_phy_event_gfp(struct asd_sas_phy *phy, enum phy_event event, gfp_t gfp_flags) { - struct asd_sas_event *ev; - - ev = sas_alloc_event_gfp(phy, gfp_flags); - if (!ev) - return -ENOMEM; - - return __sas_notify_phy_event(phy, event, ev); + return sas_notify_phy_event(phy, event, gfp_flags); } EXPORT_SYMBOL_GPL(sas_notify_phy_event_gfp); - -int sas_notify_phy_event(struct asd_sas_phy *phy, enum phy_event event) -{ - struct asd_sas_event *ev; - - ev = sas_alloc_event(phy); - if (!ev) - return -ENOMEM; - - return __sas_notify_phy_event(phy, event, ev); -} -EXPORT_SYMBOL_GPL(sas_notify_phy_event); diff --git a/drivers/scsi/libsas/sas_init.c b/drivers/scsi/libsas/sas_init.c index 9ce0cd214eb9..f06b83211e3b 100644 --- a/drivers/scsi/libsas/sas_init.c +++ b/drivers/scsi/libsas/sas_init.c @@ -585,8 +585,8 @@ sas_domain_attach_transport(struct sas_domain_function_template *dft) } EXPORT_SYMBOL_GPL(sas_domain_attach_transport); -static struct asd_sas_event *__sas_alloc_event(struct asd_sas_phy *phy, - gfp_t gfp_flags) +struct asd_sas_event *sas_alloc_event(struct asd_sas_phy *phy, + gfp_t gfp_flags) { struct asd_sas_event *event; struct sas_ha_struct *sas_ha = phy->ha; @@ -619,15 +619,11 @@ static struct asd_sas_event *__sas_alloc_event(struct asd_sas_phy *phy, return event; } -struct asd_sas_event *sas_alloc_event(struct asd_sas_phy *phy) -{ - return __sas_alloc_event(phy, in_interrupt() ? GFP_ATOMIC : GFP_KERNEL); -} - struct asd_sas_event *sas_alloc_event_gfp(struct asd_sas_phy *phy, gfp_t gfp_flags) { - return __sas_alloc_event(phy, gfp_flags); + + return sas_alloc_event(phy, gfp_flags); } void sas_free_event(struct asd_sas_event *event) diff --git a/drivers/scsi/libsas/sas_internal.h b/drivers/scsi/libsas/sas_internal.h index 52e09c3e2b50..294cdcb4ce42 100644 --- a/drivers/scsi/libsas/sas_internal.h +++ b/drivers/scsi/libsas/sas_internal.h @@ -48,7 +48,7 @@ int sas_show_oob_mode(enum sas_oob_mode oob_mode, char *buf); int sas_register_phys(struct sas_ha_struct *sas_ha); void sas_unregister_phys(struct sas_ha_struct *sas_ha); -struct asd_sas_event *sas_alloc_event(struct asd_sas_phy *phy); +struct asd_sas_event *sas_alloc_event(struct asd_sas_phy *phy, gfp_t gfp_flags); struct asd_sas_event *sas_alloc_event_gfp(struct asd_sas_phy *phy, gfp_t gfp_flags); void sas_free_event(struct asd_sas_event *event); @@ -78,7 +78,8 @@ int sas_smp_phy_control(struct domain_device *dev, int phy_id, enum phy_func phy_func, struct sas_phy_linkrates *); int sas_smp_get_phy_events(struct sas_phy *phy); -int sas_notify_phy_event(struct asd_sas_phy *phy, enum phy_event event); +int sas_notify_phy_event(struct asd_sas_phy *phy, enum phy_event event, + gfp_t flags); int sas_notify_phy_event_gfp(struct asd_sas_phy *phy, enum phy_event event, gfp_t flags); void sas_device_set_phy(struct domain_device *dev, struct sas_port *port); diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h index e6a43163ab5b..fda56e151695 100644 --- a/include/scsi/libsas.h +++ b/include/scsi/libsas.h @@ -702,8 +702,10 @@ struct sas_phy *sas_get_local_phy(struct domain_device *dev); int sas_request_addr(struct Scsi_Host *shost, u8 *addr); -int sas_notify_port_event(struct asd_sas_phy *phy, enum port_event event); -int sas_notify_phy_event(struct asd_sas_phy *phy, enum phy_event event); +int sas_notify_port_event(struct asd_sas_phy *phy, enum port_event event, + gfp_t gfp_flags); +int sas_notify_phy_event(struct asd_sas_phy *phy, enum phy_event event, + gfp_t gfp_flags); int sas_notify_port_event_gfp(struct asd_sas_phy *phy, enum port_event event, gfp_t gfp_flags); int sas_notify_phy_event_gfp(struct asd_sas_phy *phy, enum phy_event event, -- cgit v1.2.3 From 65f7cfba6196baf2fc06ac0ab0be764377f3206a Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Mon, 18 Jan 2021 11:09:55 +0100 Subject: scsi: libsas: Remove temporarily-added _gfp() API variants These variants were added for bisectability. Remove them, as all call sites have now been convertd to use the original API. Link: https://lore.kernel.org/r/20210118100955.1761652-20-a.darwish@linutronix.de Cc: Jason Yan Reviewed-by: John Garry Signed-off-by: Ahmed S. Darwish Signed-off-by: Martin K. Petersen --- Documentation/scsi/libsas.rst | 2 -- drivers/scsi/libsas/sas_event.c | 14 -------------- drivers/scsi/libsas/sas_init.c | 7 ------- drivers/scsi/libsas/sas_internal.h | 4 ---- include/scsi/libsas.h | 4 ---- 5 files changed, 31 deletions(-) (limited to 'include') diff --git a/Documentation/scsi/libsas.rst b/Documentation/scsi/libsas.rst index c65086470a15..6589dfefbc02 100644 --- a/Documentation/scsi/libsas.rst +++ b/Documentation/scsi/libsas.rst @@ -191,8 +191,6 @@ The event interface:: /* LLDD calls these to notify the class of an event. */ void sas_notify_port_event(struct sas_phy *, enum port_event, gfp_t); void sas_notify_phy_event(struct sas_phy *, enum phy_event, gfp_t); - void sas_notify_port_event_gfp(struct sas_phy *, enum port_event, gfp_t); - void sas_notify_phy_event_gfp(struct sas_phy *, enum phy_event, gfp_t); The port notification:: diff --git a/drivers/scsi/libsas/sas_event.c b/drivers/scsi/libsas/sas_event.c index 542831887769..f703115e7a25 100644 --- a/drivers/scsi/libsas/sas_event.c +++ b/drivers/scsi/libsas/sas_event.c @@ -155,13 +155,6 @@ int sas_notify_port_event(struct asd_sas_phy *phy, enum port_event event, } EXPORT_SYMBOL_GPL(sas_notify_port_event); -int sas_notify_port_event_gfp(struct asd_sas_phy *phy, enum port_event event, - gfp_t gfp_flags) -{ - return sas_notify_port_event(phy, event, gfp_flags); -} -EXPORT_SYMBOL_GPL(sas_notify_port_event_gfp); - int sas_notify_phy_event(struct asd_sas_phy *phy, enum phy_event event, gfp_t gfp_flags) { @@ -184,10 +177,3 @@ int sas_notify_phy_event(struct asd_sas_phy *phy, enum phy_event event, return ret; } EXPORT_SYMBOL_GPL(sas_notify_phy_event); - -int sas_notify_phy_event_gfp(struct asd_sas_phy *phy, enum phy_event event, - gfp_t gfp_flags) -{ - return sas_notify_phy_event(phy, event, gfp_flags); -} -EXPORT_SYMBOL_GPL(sas_notify_phy_event_gfp); diff --git a/drivers/scsi/libsas/sas_init.c b/drivers/scsi/libsas/sas_init.c index 62260e84ca2d..2b0f98ca6ec3 100644 --- a/drivers/scsi/libsas/sas_init.c +++ b/drivers/scsi/libsas/sas_init.c @@ -619,13 +619,6 @@ struct asd_sas_event *sas_alloc_event(struct asd_sas_phy *phy, return event; } -struct asd_sas_event *sas_alloc_event_gfp(struct asd_sas_phy *phy, - gfp_t gfp_flags) -{ - - return sas_alloc_event(phy, gfp_flags); -} - void sas_free_event(struct asd_sas_event *event) { struct asd_sas_phy *phy = event->phy; diff --git a/drivers/scsi/libsas/sas_internal.h b/drivers/scsi/libsas/sas_internal.h index 294cdcb4ce42..d7a1fb5c10c6 100644 --- a/drivers/scsi/libsas/sas_internal.h +++ b/drivers/scsi/libsas/sas_internal.h @@ -49,8 +49,6 @@ int sas_register_phys(struct sas_ha_struct *sas_ha); void sas_unregister_phys(struct sas_ha_struct *sas_ha); struct asd_sas_event *sas_alloc_event(struct asd_sas_phy *phy, gfp_t gfp_flags); -struct asd_sas_event *sas_alloc_event_gfp(struct asd_sas_phy *phy, - gfp_t gfp_flags); void sas_free_event(struct asd_sas_event *event); int sas_register_ports(struct sas_ha_struct *sas_ha); @@ -80,8 +78,6 @@ int sas_smp_get_phy_events(struct sas_phy *phy); int sas_notify_phy_event(struct asd_sas_phy *phy, enum phy_event event, gfp_t flags); -int sas_notify_phy_event_gfp(struct asd_sas_phy *phy, enum phy_event event, - gfp_t flags); void sas_device_set_phy(struct domain_device *dev, struct sas_port *port); struct domain_device *sas_find_dev_by_rphy(struct sas_rphy *rphy); struct domain_device *sas_ex_to_ata(struct domain_device *ex_dev, int phy_id); diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h index fda56e151695..9271d7a49b90 100644 --- a/include/scsi/libsas.h +++ b/include/scsi/libsas.h @@ -706,9 +706,5 @@ int sas_notify_port_event(struct asd_sas_phy *phy, enum port_event event, gfp_t gfp_flags); int sas_notify_phy_event(struct asd_sas_phy *phy, enum phy_event event, gfp_t gfp_flags); -int sas_notify_port_event_gfp(struct asd_sas_phy *phy, enum port_event event, - gfp_t gfp_flags); -int sas_notify_phy_event_gfp(struct asd_sas_phy *phy, enum phy_event event, - gfp_t gfp_flags); #endif /* _SASLIB_H_ */ -- cgit v1.2.3 From 9d0735519f99948c5b5c22426b682ced7f7af9be Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 20 Jan 2021 16:41:56 +0100 Subject: rtc: remove sirfsoc driver The CSR SiRF prima2/atlas platforms are getting removed, so this driver is no longer needed. Cc: Barry Song Signed-off-by: Arnd Bergmann Acked-by: Barry Song Signed-off-by: Alexandre Belloni Link: https://lore.kernel.org/r/20210120154158.1860736-2-arnd@kernel.org --- .../devicetree/bindings/rtc/sirf,prima2-sysrtc.txt | 13 - drivers/rtc/Kconfig | 7 - drivers/rtc/Makefile | 1 - drivers/rtc/rtc-sirfsoc.c | 446 --------------------- include/linux/rtc/sirfsoc_rtciobrg.h | 21 - 5 files changed, 488 deletions(-) delete mode 100644 Documentation/devicetree/bindings/rtc/sirf,prima2-sysrtc.txt delete mode 100644 drivers/rtc/rtc-sirfsoc.c delete mode 100644 include/linux/rtc/sirfsoc_rtciobrg.h (limited to 'include') diff --git a/Documentation/devicetree/bindings/rtc/sirf,prima2-sysrtc.txt b/Documentation/devicetree/bindings/rtc/sirf,prima2-sysrtc.txt deleted file mode 100644 index 58885b55da21..000000000000 --- a/Documentation/devicetree/bindings/rtc/sirf,prima2-sysrtc.txt +++ /dev/null @@ -1,13 +0,0 @@ -SiRFSoC Real Time Clock - -Required properties: -- compatible: must be "sirf,prima2-sysrtc" -- reg: address range of rtc register set. -- interrupts: rtc alarm interrupts. - -Example: - rtc@2000 { - compatible = "sirf,prima2-sysrtc"; - reg = <0x2000 0x1000>; - interrupts = <52 53 54>; - }; diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig index fe4fdb75a4c5..12907352f697 100644 --- a/drivers/rtc/Kconfig +++ b/drivers/rtc/Kconfig @@ -1793,13 +1793,6 @@ config RTC_DRV_IMX_SC If you say yes here you get support for the NXP i.MX System Controller RTC module. -config RTC_DRV_SIRFSOC - tristate "SiRFSOC RTC" - depends on ARCH_SIRF - help - Say "yes" here to support the real time clock on SiRF SOC chips. - This driver can also be built as a module called rtc-sirfsoc. - config RTC_DRV_ST_LPC tristate "STMicroelectronics LPC RTC" depends on ARCH_STI diff --git a/drivers/rtc/Makefile b/drivers/rtc/Makefile index a020adde4bbd..821643b3b699 100644 --- a/drivers/rtc/Makefile +++ b/drivers/rtc/Makefile @@ -154,7 +154,6 @@ obj-$(CONFIG_RTC_DRV_SA1100) += rtc-sa1100.o obj-$(CONFIG_RTC_DRV_SC27XX) += rtc-sc27xx.o obj-$(CONFIG_RTC_DRV_SD3078) += rtc-sd3078.o obj-$(CONFIG_RTC_DRV_SH) += rtc-sh.o -obj-$(CONFIG_RTC_DRV_SIRFSOC) += rtc-sirfsoc.o obj-$(CONFIG_RTC_DRV_SNVS) += rtc-snvs.o obj-$(CONFIG_RTC_DRV_SPEAR) += rtc-spear.o obj-$(CONFIG_RTC_DRV_STARFIRE) += rtc-starfire.o diff --git a/drivers/rtc/rtc-sirfsoc.c b/drivers/rtc/rtc-sirfsoc.c deleted file mode 100644 index 03a6cca23201..000000000000 --- a/drivers/rtc/rtc-sirfsoc.c +++ /dev/null @@ -1,446 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * SiRFSoC Real Time Clock interface for Linux - * - * Copyright (c) 2013 Cambridge Silicon Radio Limited, a CSR plc group company. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include - - -#define RTC_CN 0x00 -#define RTC_ALARM0 0x04 -#define RTC_ALARM1 0x18 -#define RTC_STATUS 0x08 -#define RTC_SW_VALUE 0x40 -#define SIRFSOC_RTC_AL1E (1<<6) -#define SIRFSOC_RTC_AL1 (1<<4) -#define SIRFSOC_RTC_HZE (1<<3) -#define SIRFSOC_RTC_AL0E (1<<2) -#define SIRFSOC_RTC_HZ (1<<1) -#define SIRFSOC_RTC_AL0 (1<<0) -#define RTC_DIV 0x0c -#define RTC_DEEP_CTRL 0x14 -#define RTC_CLOCK_SWITCH 0x1c -#define SIRFSOC_RTC_CLK 0x03 /* others are reserved */ - -/* Refer to RTC DIV switch */ -#define RTC_HZ 16 - -/* This macro is also defined in arch/arm/plat-sirfsoc/cpu.c */ -#define RTC_SHIFT 4 - -#define INTR_SYSRTC_CN 0x48 - -struct sirfsoc_rtc_drv { - struct rtc_device *rtc; - u32 rtc_base; - u32 irq; - unsigned irq_wake; - /* Overflow for every 8 years extra time */ - u32 overflow_rtc; - spinlock_t lock; - struct regmap *regmap; -#ifdef CONFIG_PM - u32 saved_counter; - u32 saved_overflow_rtc; -#endif -}; - -static u32 sirfsoc_rtc_readl(struct sirfsoc_rtc_drv *rtcdrv, u32 offset) -{ - u32 val; - - regmap_read(rtcdrv->regmap, rtcdrv->rtc_base + offset, &val); - return val; -} - -static void sirfsoc_rtc_writel(struct sirfsoc_rtc_drv *rtcdrv, - u32 offset, u32 val) -{ - regmap_write(rtcdrv->regmap, rtcdrv->rtc_base + offset, val); -} - -static int sirfsoc_rtc_read_alarm(struct device *dev, - struct rtc_wkalrm *alrm) -{ - unsigned long rtc_alarm, rtc_count; - struct sirfsoc_rtc_drv *rtcdrv; - - rtcdrv = dev_get_drvdata(dev); - - spin_lock_irq(&rtcdrv->lock); - - rtc_count = sirfsoc_rtc_readl(rtcdrv, RTC_CN); - - rtc_alarm = sirfsoc_rtc_readl(rtcdrv, RTC_ALARM0); - memset(alrm, 0, sizeof(struct rtc_wkalrm)); - - /* - * assume alarm interval not beyond one round counter overflow_rtc: - * 0->0xffffffff - */ - /* if alarm is in next overflow cycle */ - if (rtc_count > rtc_alarm) - rtc_time64_to_tm((rtcdrv->overflow_rtc + 1) - << (BITS_PER_LONG - RTC_SHIFT) - | rtc_alarm >> RTC_SHIFT, &alrm->time); - else - rtc_time64_to_tm(rtcdrv->overflow_rtc - << (BITS_PER_LONG - RTC_SHIFT) - | rtc_alarm >> RTC_SHIFT, &alrm->time); - if (sirfsoc_rtc_readl(rtcdrv, RTC_STATUS) & SIRFSOC_RTC_AL0E) - alrm->enabled = 1; - - spin_unlock_irq(&rtcdrv->lock); - - return 0; -} - -static int sirfsoc_rtc_set_alarm(struct device *dev, - struct rtc_wkalrm *alrm) -{ - unsigned long rtc_status_reg, rtc_alarm; - struct sirfsoc_rtc_drv *rtcdrv; - rtcdrv = dev_get_drvdata(dev); - - if (alrm->enabled) { - rtc_alarm = rtc_tm_to_time64(&alrm->time); - - spin_lock_irq(&rtcdrv->lock); - - rtc_status_reg = sirfsoc_rtc_readl(rtcdrv, RTC_STATUS); - if (rtc_status_reg & SIRFSOC_RTC_AL0E) { - /* - * An ongoing alarm in progress - ingore it and not - * to return EBUSY - */ - dev_info(dev, "An old alarm was set, will be replaced by a new one\n"); - } - - sirfsoc_rtc_writel(rtcdrv, RTC_ALARM0, rtc_alarm << RTC_SHIFT); - rtc_status_reg &= ~0x07; /* mask out the lower status bits */ - /* - * This bit RTC_AL sets it as a wake-up source for Sleep Mode - * Writing 1 into this bit will clear it - */ - rtc_status_reg |= SIRFSOC_RTC_AL0; - /* enable the RTC alarm interrupt */ - rtc_status_reg |= SIRFSOC_RTC_AL0E; - sirfsoc_rtc_writel(rtcdrv, RTC_STATUS, rtc_status_reg); - - spin_unlock_irq(&rtcdrv->lock); - } else { - /* - * if this function was called with enabled=0 - * then it could mean that the application is - * trying to cancel an ongoing alarm - */ - spin_lock_irq(&rtcdrv->lock); - - rtc_status_reg = sirfsoc_rtc_readl(rtcdrv, RTC_STATUS); - if (rtc_status_reg & SIRFSOC_RTC_AL0E) { - /* clear the RTC status register's alarm bit */ - rtc_status_reg &= ~0x07; - /* write 1 into SIRFSOC_RTC_AL0 to force a clear */ - rtc_status_reg |= (SIRFSOC_RTC_AL0); - /* Clear the Alarm enable bit */ - rtc_status_reg &= ~(SIRFSOC_RTC_AL0E); - - sirfsoc_rtc_writel(rtcdrv, RTC_STATUS, - rtc_status_reg); - } - - spin_unlock_irq(&rtcdrv->lock); - } - - return 0; -} - -static int sirfsoc_rtc_read_time(struct device *dev, - struct rtc_time *tm) -{ - unsigned long tmp_rtc = 0; - struct sirfsoc_rtc_drv *rtcdrv; - rtcdrv = dev_get_drvdata(dev); - /* - * This patch is taken from WinCE - Need to validate this for - * correctness. To work around sirfsoc RTC counter double sync logic - * fail, read several times to make sure get stable value. - */ - do { - tmp_rtc = sirfsoc_rtc_readl(rtcdrv, RTC_CN); - cpu_relax(); - } while (tmp_rtc != sirfsoc_rtc_readl(rtcdrv, RTC_CN)); - - rtc_time64_to_tm(rtcdrv->overflow_rtc << (BITS_PER_LONG - RTC_SHIFT) - | tmp_rtc >> RTC_SHIFT, tm); - return 0; -} - -static int sirfsoc_rtc_set_time(struct device *dev, - struct rtc_time *tm) -{ - unsigned long rtc_time; - struct sirfsoc_rtc_drv *rtcdrv; - rtcdrv = dev_get_drvdata(dev); - - rtc_time = rtc_tm_to_time64(tm); - - rtcdrv->overflow_rtc = rtc_time >> (BITS_PER_LONG - RTC_SHIFT); - - sirfsoc_rtc_writel(rtcdrv, RTC_SW_VALUE, rtcdrv->overflow_rtc); - sirfsoc_rtc_writel(rtcdrv, RTC_CN, rtc_time << RTC_SHIFT); - - return 0; -} - -static int sirfsoc_rtc_alarm_irq_enable(struct device *dev, - unsigned int enabled) -{ - unsigned long rtc_status_reg = 0x0; - struct sirfsoc_rtc_drv *rtcdrv; - - rtcdrv = dev_get_drvdata(dev); - - spin_lock_irq(&rtcdrv->lock); - - rtc_status_reg = sirfsoc_rtc_readl(rtcdrv, RTC_STATUS); - if (enabled) - rtc_status_reg |= SIRFSOC_RTC_AL0E; - else - rtc_status_reg &= ~SIRFSOC_RTC_AL0E; - - sirfsoc_rtc_writel(rtcdrv, RTC_STATUS, rtc_status_reg); - - spin_unlock_irq(&rtcdrv->lock); - - return 0; - -} - -static const struct rtc_class_ops sirfsoc_rtc_ops = { - .read_time = sirfsoc_rtc_read_time, - .set_time = sirfsoc_rtc_set_time, - .read_alarm = sirfsoc_rtc_read_alarm, - .set_alarm = sirfsoc_rtc_set_alarm, - .alarm_irq_enable = sirfsoc_rtc_alarm_irq_enable -}; - -static irqreturn_t sirfsoc_rtc_irq_handler(int irq, void *pdata) -{ - struct sirfsoc_rtc_drv *rtcdrv = pdata; - unsigned long rtc_status_reg = 0x0; - unsigned long events = 0x0; - - spin_lock(&rtcdrv->lock); - - rtc_status_reg = sirfsoc_rtc_readl(rtcdrv, RTC_STATUS); - /* this bit will be set ONLY if an alarm was active - * and it expired NOW - * So this is being used as an ASSERT - */ - if (rtc_status_reg & SIRFSOC_RTC_AL0) { - /* - * clear the RTC status register's alarm bit - * mask out the lower status bits - */ - rtc_status_reg &= ~0x07; - /* write 1 into SIRFSOC_RTC_AL0 to ACK the alarm interrupt */ - rtc_status_reg |= (SIRFSOC_RTC_AL0); - /* Clear the Alarm enable bit */ - rtc_status_reg &= ~(SIRFSOC_RTC_AL0E); - } - - sirfsoc_rtc_writel(rtcdrv, RTC_STATUS, rtc_status_reg); - - spin_unlock(&rtcdrv->lock); - - /* this should wake up any apps polling/waiting on the read - * after setting the alarm - */ - events |= RTC_IRQF | RTC_AF; - rtc_update_irq(rtcdrv->rtc, 1, events); - - return IRQ_HANDLED; -} - -static const struct of_device_id sirfsoc_rtc_of_match[] = { - { .compatible = "sirf,prima2-sysrtc"}, - {}, -}; - -static const struct regmap_config sysrtc_regmap_config = { - .reg_bits = 32, - .val_bits = 32, - .fast_io = true, -}; - -MODULE_DEVICE_TABLE(of, sirfsoc_rtc_of_match); - -static int sirfsoc_rtc_probe(struct platform_device *pdev) -{ - int err; - unsigned long rtc_div; - struct sirfsoc_rtc_drv *rtcdrv; - struct device_node *np = pdev->dev.of_node; - - rtcdrv = devm_kzalloc(&pdev->dev, - sizeof(struct sirfsoc_rtc_drv), GFP_KERNEL); - if (rtcdrv == NULL) - return -ENOMEM; - - spin_lock_init(&rtcdrv->lock); - - err = of_property_read_u32(np, "reg", &rtcdrv->rtc_base); - if (err) { - dev_err(&pdev->dev, "unable to find base address of rtc node in dtb\n"); - return err; - } - - platform_set_drvdata(pdev, rtcdrv); - - /* Register rtc alarm as a wakeup source */ - device_init_wakeup(&pdev->dev, 1); - - rtcdrv->regmap = devm_regmap_init_iobg(&pdev->dev, - &sysrtc_regmap_config); - if (IS_ERR(rtcdrv->regmap)) { - err = PTR_ERR(rtcdrv->regmap); - dev_err(&pdev->dev, "Failed to allocate register map: %d\n", - err); - return err; - } - - /* - * Set SYS_RTC counter in RTC_HZ HZ Units - * We are using 32K RTC crystal (32768 / RTC_HZ / 2) -1 - * If 16HZ, therefore RTC_DIV = 1023; - */ - rtc_div = ((32768 / RTC_HZ) / 2) - 1; - sirfsoc_rtc_writel(rtcdrv, RTC_DIV, rtc_div); - - /* 0x3 -> RTC_CLK */ - sirfsoc_rtc_writel(rtcdrv, RTC_CLOCK_SWITCH, SIRFSOC_RTC_CLK); - - /* reset SYS RTC ALARM0 */ - sirfsoc_rtc_writel(rtcdrv, RTC_ALARM0, 0x0); - - /* reset SYS RTC ALARM1 */ - sirfsoc_rtc_writel(rtcdrv, RTC_ALARM1, 0x0); - - /* Restore RTC Overflow From Register After Command Reboot */ - rtcdrv->overflow_rtc = - sirfsoc_rtc_readl(rtcdrv, RTC_SW_VALUE); - - rtcdrv->rtc = devm_rtc_allocate_device(&pdev->dev); - if (IS_ERR(rtcdrv->rtc)) - return PTR_ERR(rtcdrv->rtc); - - rtcdrv->rtc->ops = &sirfsoc_rtc_ops; - rtcdrv->rtc->range_max = (1ULL << 60) - 1; - - rtcdrv->irq = platform_get_irq(pdev, 0); - err = devm_request_irq(&pdev->dev, rtcdrv->irq, sirfsoc_rtc_irq_handler, - IRQF_SHARED, pdev->name, rtcdrv); - if (err) { - dev_err(&pdev->dev, "Unable to register for the SiRF SOC RTC IRQ\n"); - return err; - } - - return devm_rtc_register_device(rtcdrv->rtc); -} - -#ifdef CONFIG_PM_SLEEP -static int sirfsoc_rtc_suspend(struct device *dev) -{ - struct sirfsoc_rtc_drv *rtcdrv = dev_get_drvdata(dev); - rtcdrv->overflow_rtc = - sirfsoc_rtc_readl(rtcdrv, RTC_SW_VALUE); - - rtcdrv->saved_counter = - sirfsoc_rtc_readl(rtcdrv, RTC_CN); - rtcdrv->saved_overflow_rtc = rtcdrv->overflow_rtc; - if (device_may_wakeup(dev) && !enable_irq_wake(rtcdrv->irq)) - rtcdrv->irq_wake = 1; - - return 0; -} - -static int sirfsoc_rtc_resume(struct device *dev) -{ - u32 tmp; - struct sirfsoc_rtc_drv *rtcdrv = dev_get_drvdata(dev); - - /* - * if resume from snapshot and the rtc power is lost, - * restroe the rtc settings - */ - if (SIRFSOC_RTC_CLK != sirfsoc_rtc_readl(rtcdrv, RTC_CLOCK_SWITCH)) { - u32 rtc_div; - /* 0x3 -> RTC_CLK */ - sirfsoc_rtc_writel(rtcdrv, RTC_CLOCK_SWITCH, SIRFSOC_RTC_CLK); - /* - * Set SYS_RTC counter in RTC_HZ HZ Units - * We are using 32K RTC crystal (32768 / RTC_HZ / 2) -1 - * If 16HZ, therefore RTC_DIV = 1023; - */ - rtc_div = ((32768 / RTC_HZ) / 2) - 1; - - sirfsoc_rtc_writel(rtcdrv, RTC_DIV, rtc_div); - - /* reset SYS RTC ALARM0 */ - sirfsoc_rtc_writel(rtcdrv, RTC_ALARM0, 0x0); - - /* reset SYS RTC ALARM1 */ - sirfsoc_rtc_writel(rtcdrv, RTC_ALARM1, 0x0); - } - rtcdrv->overflow_rtc = rtcdrv->saved_overflow_rtc; - - /* - * if current counter is small than previous, - * it means overflow in sleep - */ - tmp = sirfsoc_rtc_readl(rtcdrv, RTC_CN); - if (tmp <= rtcdrv->saved_counter) - rtcdrv->overflow_rtc++; - /* - *PWRC Value Be Changed When Suspend, Restore Overflow - * In Memory To Register - */ - sirfsoc_rtc_writel(rtcdrv, RTC_SW_VALUE, rtcdrv->overflow_rtc); - - if (device_may_wakeup(dev) && rtcdrv->irq_wake) { - disable_irq_wake(rtcdrv->irq); - rtcdrv->irq_wake = 0; - } - - return 0; -} -#endif - -static SIMPLE_DEV_PM_OPS(sirfsoc_rtc_pm_ops, - sirfsoc_rtc_suspend, sirfsoc_rtc_resume); - -static struct platform_driver sirfsoc_rtc_driver = { - .driver = { - .name = "sirfsoc-rtc", - .pm = &sirfsoc_rtc_pm_ops, - .of_match_table = sirfsoc_rtc_of_match, - }, - .probe = sirfsoc_rtc_probe, -}; -module_platform_driver(sirfsoc_rtc_driver); - -MODULE_DESCRIPTION("SiRF SoC rtc driver"); -MODULE_AUTHOR("Xianglong Du "); -MODULE_LICENSE("GPL v2"); -MODULE_ALIAS("platform:sirfsoc-rtc"); diff --git a/include/linux/rtc/sirfsoc_rtciobrg.h b/include/linux/rtc/sirfsoc_rtciobrg.h deleted file mode 100644 index b31f2856733d..000000000000 --- a/include/linux/rtc/sirfsoc_rtciobrg.h +++ /dev/null @@ -1,21 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * RTC I/O Bridge interfaces for CSR SiRFprimaII - * ARM access the registers of SYSRTC, GPSRTC and PWRC through this module - * - * Copyright (c) 2011 Cambridge Silicon Radio Limited, a CSR plc group company. - */ -#ifndef _SIRFSOC_RTC_IOBRG_H_ -#define _SIRFSOC_RTC_IOBRG_H_ - -struct regmap_config; - -extern void sirfsoc_rtc_iobrg_besyncing(void); - -extern u32 sirfsoc_rtc_iobrg_readl(u32 addr); - -extern void sirfsoc_rtc_iobrg_writel(u32 val, u32 addr); -struct regmap *devm_regmap_init_iobg(struct device *dev, - const struct regmap_config *config); - -#endif -- cgit v1.2.3 From a6435940b62f81a1718bf2bd46a051379fc89b9d Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 21 Jan 2021 14:19:20 +0100 Subject: mount: attach mappings to mounts In order to support per-mount idmappings vfsmounts are marked with user namespaces. The idmapping of the user namespace will be used to map the ids of vfs objects when they are accessed through that mount. By default all vfsmounts are marked with the initial user namespace. The initial user namespace is used to indicate that a mount is not idmapped. All operations behave as before. Based on prior discussions we want to attach the whole user namespace and not just a dedicated idmapping struct. This allows us to reuse all the helpers that already exist for dealing with idmappings instead of introducing a whole new range of helpers. In addition, if we decide in the future that we are confident enough to enable unprivileged users to setup idmapped mounts the permission checking can take into account whether the caller is privileged in the user namespace the mount is currently marked with. Later patches enforce that once a mount has been idmapped it can't be remapped. This keeps permission checking and life-cycle management simple. Users wanting to change the idmapped can always create a new detached mount with a different idmapping. Add a new mnt_userns member to vfsmount and two simple helpers to retrieve the mnt_userns from vfsmounts and files. The idea to attach user namespaces to vfsmounts has been floated around in various forms at Linux Plumbers in ~2018 with the original idea tracing back to a discussion in 2017 at a conference in St. Petersburg between Christoph, Tycho, and myself. Link: https://lore.kernel.org/r/20210121131959.646623-2-christian.brauner@ubuntu.com Cc: Christoph Hellwig Cc: David Howells Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig Signed-off-by: Christian Brauner --- fs/namespace.c | 9 +++++++++ include/linux/fs.h | 6 ++++++ include/linux/mount.h | 6 ++++++ 3 files changed, 21 insertions(+) (limited to 'include') diff --git a/fs/namespace.c b/fs/namespace.c index 9d33909d0f9e..ecdc63ef881c 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -210,6 +210,7 @@ static struct mount *alloc_vfsmnt(const char *name) INIT_HLIST_NODE(&mnt->mnt_mp_list); INIT_LIST_HEAD(&mnt->mnt_umounting); INIT_HLIST_HEAD(&mnt->mnt_stuck_children); + mnt->mnt.mnt_userns = &init_user_ns; } return mnt; @@ -547,6 +548,11 @@ int sb_prepare_remount_readonly(struct super_block *sb) static void free_vfsmnt(struct mount *mnt) { + struct user_namespace *mnt_userns; + + mnt_userns = mnt_user_ns(&mnt->mnt); + if (mnt_userns != &init_user_ns) + put_user_ns(mnt_userns); kfree_const(mnt->mnt_devname); #ifdef CONFIG_SMP free_percpu(mnt->mnt_pcp); @@ -1055,6 +1061,9 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root, mnt->mnt.mnt_flags &= ~(MNT_WRITE_HOLD|MNT_MARKED|MNT_INTERNAL); atomic_inc(&sb->s_active); + mnt->mnt.mnt_userns = mnt_user_ns(&old->mnt); + if (mnt->mnt.mnt_userns != &init_user_ns) + mnt->mnt.mnt_userns = get_user_ns(mnt->mnt.mnt_userns); mnt->mnt.mnt_sb = sb; mnt->mnt.mnt_root = dget(root); mnt->mnt_mountpoint = mnt->mnt.mnt_root; diff --git a/include/linux/fs.h b/include/linux/fs.h index fd47deea7c17..fd0b80e6361d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -39,6 +39,7 @@ #include #include #include +#include #include #include @@ -2231,6 +2232,7 @@ struct file_system_type { #define FS_HAS_SUBTYPE 4 #define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */ #define FS_DISALLOW_NOTIFY_PERM 16 /* Disable fanotify permission events */ +#define FS_ALLOW_IDMAP 32 /* FS has been updated to handle vfs idmappings. */ #define FS_THP_SUPPORT 8192 /* Remove once all fs converted */ #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ int (*init_fs_context)(struct fs_context *); @@ -2517,6 +2519,10 @@ struct filename { }; static_assert(offsetof(struct filename, iname) % sizeof(long) == 0); +static inline struct user_namespace *file_mnt_user_ns(struct file *file) +{ + return mnt_user_ns(file->f_path.mnt); +} extern long vfs_truncate(const struct path *, loff_t); extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs, struct file *filp); diff --git a/include/linux/mount.h b/include/linux/mount.h index aaf343b38671..52de25e08319 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -72,8 +72,14 @@ struct vfsmount { struct dentry *mnt_root; /* root of the mounted tree */ struct super_block *mnt_sb; /* pointer to superblock */ int mnt_flags; + struct user_namespace *mnt_userns; } __randomize_layout; +static inline struct user_namespace *mnt_user_ns(const struct vfsmount *mnt) +{ + return mnt->mnt_userns; +} + struct file; /* forward dec */ struct path; -- cgit v1.2.3 From e6c9a71451560edba343cbcbd500bea0a188f0d1 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 21 Jan 2021 14:19:21 +0100 Subject: fs: add id translation helpers Add simple helpers to make it easy to map kuids into and from idmapped mounts. We provide simple wrappers that filesystems can use to e.g. initialize inodes similar to i_{uid,gid}_read() and i_{uid,gid}_write(). Accessing an inode through an idmapped mount maps the i_uid and i_gid of the inode to the mount's user namespace. If the fsids are used to initialize inodes they are unmapped according to the mount's user namespace. Passing the initial user namespace to these helpers makes them a nop and so any non-idmapped paths will not be impacted. Link: https://lore.kernel.org/r/20210121131959.646623-3-christian.brauner@ubuntu.com Cc: David Howells Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig Signed-off-by: Christian Brauner --- include/linux/fs.h | 47 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index fd0b80e6361d..3165998e2294 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -40,6 +40,7 @@ #include #include #include +#include #include #include @@ -1573,6 +1574,52 @@ static inline void i_gid_write(struct inode *inode, gid_t gid) inode->i_gid = make_kgid(inode->i_sb->s_user_ns, gid); } +static inline kuid_t kuid_into_mnt(struct user_namespace *mnt_userns, + kuid_t kuid) +{ + return make_kuid(mnt_userns, __kuid_val(kuid)); +} + +static inline kgid_t kgid_into_mnt(struct user_namespace *mnt_userns, + kgid_t kgid) +{ + return make_kgid(mnt_userns, __kgid_val(kgid)); +} + +static inline kuid_t i_uid_into_mnt(struct user_namespace *mnt_userns, + const struct inode *inode) +{ + return kuid_into_mnt(mnt_userns, inode->i_uid); +} + +static inline kgid_t i_gid_into_mnt(struct user_namespace *mnt_userns, + const struct inode *inode) +{ + return kgid_into_mnt(mnt_userns, inode->i_gid); +} + +static inline kuid_t kuid_from_mnt(struct user_namespace *mnt_userns, + kuid_t kuid) +{ + return KUIDT_INIT(from_kuid(mnt_userns, kuid)); +} + +static inline kgid_t kgid_from_mnt(struct user_namespace *mnt_userns, + kgid_t kgid) +{ + return KGIDT_INIT(from_kgid(mnt_userns, kgid)); +} + +static inline kuid_t fsuid_into_mnt(struct user_namespace *mnt_userns) +{ + return kuid_from_mnt(mnt_userns, current_fsuid()); +} + +static inline kgid_t fsgid_into_mnt(struct user_namespace *mnt_userns) +{ + return kgid_from_mnt(mnt_userns, current_fsgid()); +} + extern struct timespec64 current_time(struct inode *inode); /* -- cgit v1.2.3 From 02f92b3868a1b34ab98464e76b0e4e060474ba10 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 21 Jan 2021 14:19:22 +0100 Subject: fs: add file and path permissions helpers Add two simple helpers to check permissions on a file and path respectively and convert over some callers. It simplifies quite a few codepaths and also reduces the churn in later patches quite a bit. Christoph also correctly points out that this makes codepaths (e.g. ioctls) way easier to follow that would otherwise have to do more complex argument passing than necessary. Link: https://lore.kernel.org/r/20210121131959.646623-4-christian.brauner@ubuntu.com Cc: David Howells Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Suggested-by: Christoph Hellwig Reviewed-by: Christoph Hellwig Reviewed-by: James Morris Signed-off-by: Christian Brauner --- fs/init.c | 6 +++--- fs/notify/fanotify/fanotify_user.c | 2 +- fs/notify/inotify/inotify_user.c | 2 +- fs/open.c | 6 +++--- fs/udf/file.c | 2 +- fs/verity/enable.c | 2 +- include/linux/fs.h | 8 ++++++++ kernel/bpf/inode.c | 2 +- kernel/sys.c | 2 +- mm/madvise.c | 2 +- mm/memcontrol.c | 2 +- mm/mincore.c | 2 +- net/unix/af_unix.c | 2 +- 13 files changed, 24 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/fs/init.c b/fs/init.c index e9c320a48cf1..02723bea8499 100644 --- a/fs/init.c +++ b/fs/init.c @@ -49,7 +49,7 @@ int __init init_chdir(const char *filename) error = kern_path(filename, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &path); if (error) return error; - error = inode_permission(path.dentry->d_inode, MAY_EXEC | MAY_CHDIR); + error = path_permission(&path, MAY_EXEC | MAY_CHDIR); if (!error) set_fs_pwd(current->fs, &path); path_put(&path); @@ -64,7 +64,7 @@ int __init init_chroot(const char *filename) error = kern_path(filename, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &path); if (error) return error; - error = inode_permission(path.dentry->d_inode, MAY_EXEC | MAY_CHDIR); + error = path_permission(&path, MAY_EXEC | MAY_CHDIR); if (error) goto dput_and_out; error = -EPERM; @@ -118,7 +118,7 @@ int __init init_eaccess(const char *filename) error = kern_path(filename, LOOKUP_FOLLOW, &path); if (error) return error; - error = inode_permission(d_inode(path.dentry), MAY_ACCESS); + error = path_permission(&path, MAY_ACCESS); path_put(&path); return error; } diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index dcab112e1f00..64cfc1a3015d 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -702,7 +702,7 @@ static int fanotify_find_path(int dfd, const char __user *filename, } /* you can only watch an inode if you have read permissions on it */ - ret = inode_permission(path->dentry->d_inode, MAY_READ); + ret = path_permission(path, MAY_READ); if (ret) { path_put(path); goto out; diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index 59c177011a0f..e1155d32ef6f 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -352,7 +352,7 @@ static int inotify_find_inode(const char __user *dirname, struct path *path, if (error) return error; /* you can only watch an inode if you have read permissions on it */ - error = inode_permission(path->dentry->d_inode, MAY_READ); + error = path_permission(path, MAY_READ); if (error) { path_put(path); return error; diff --git a/fs/open.c b/fs/open.c index 1e06e443a565..cd1efd254cad 100644 --- a/fs/open.c +++ b/fs/open.c @@ -492,7 +492,7 @@ retry: if (error) goto out; - error = inode_permission(path.dentry->d_inode, MAY_EXEC | MAY_CHDIR); + error = path_permission(&path, MAY_EXEC | MAY_CHDIR); if (error) goto dput_and_out; @@ -521,7 +521,7 @@ SYSCALL_DEFINE1(fchdir, unsigned int, fd) if (!d_can_lookup(f.file->f_path.dentry)) goto out_putf; - error = inode_permission(file_inode(f.file), MAY_EXEC | MAY_CHDIR); + error = file_permission(f.file, MAY_EXEC | MAY_CHDIR); if (!error) set_fs_pwd(current->fs, &f.file->f_path); out_putf: @@ -540,7 +540,7 @@ retry: if (error) goto out; - error = inode_permission(path.dentry->d_inode, MAY_EXEC | MAY_CHDIR); + error = path_permission(&path, MAY_EXEC | MAY_CHDIR); if (error) goto dput_and_out; diff --git a/fs/udf/file.c b/fs/udf/file.c index ad8eefad27d7..3671a40ed3c3 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -183,7 +183,7 @@ long udf_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) long old_block, new_block; int result; - if (inode_permission(inode, MAY_READ) != 0) { + if (file_permission(filp, MAY_READ) != 0) { udf_debug("no permission to access inode %lu\n", inode->i_ino); return -EPERM; } diff --git a/fs/verity/enable.c b/fs/verity/enable.c index f7e997a01ad0..77e159a0346b 100644 --- a/fs/verity/enable.c +++ b/fs/verity/enable.c @@ -369,7 +369,7 @@ int fsverity_ioctl_enable(struct file *filp, const void __user *uarg) * has verity enabled, and to stabilize the data being hashed. */ - err = inode_permission(inode, MAY_WRITE); + err = file_permission(filp, MAY_WRITE); if (err) return err; diff --git a/include/linux/fs.h b/include/linux/fs.h index 3165998e2294..bcd17097d441 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2812,6 +2812,14 @@ static inline int bmap(struct inode *inode, sector_t *block) extern int notify_change(struct dentry *, struct iattr *, struct inode **); extern int inode_permission(struct inode *, int); extern int generic_permission(struct inode *, int); +static inline int file_permission(struct file *file, int mask) +{ + return inode_permission(file_inode(file), mask); +} +static inline int path_permission(const struct path *path, int mask) +{ + return inode_permission(d_inode(path->dentry), mask); +} extern int __check_sticky(struct inode *dir, struct inode *inode); static inline bool execute_ok(struct inode *inode) diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index dd4b7fd60ee7..8962f139521e 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -507,7 +507,7 @@ static void *bpf_obj_do_get(const char __user *pathname, return ERR_PTR(ret); inode = d_backing_inode(path.dentry); - ret = inode_permission(inode, ACC_MODE(flags)); + ret = path_permission(&path, ACC_MODE(flags)); if (ret) goto out; diff --git a/kernel/sys.c b/kernel/sys.c index 51f00fe20e4d..138fb253b344 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1848,7 +1848,7 @@ static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd) if (!S_ISREG(inode->i_mode) || path_noexec(&exe.file->f_path)) goto exit; - err = inode_permission(inode, MAY_EXEC); + err = file_permission(exe.file, MAY_EXEC); if (err) goto exit; diff --git a/mm/madvise.c b/mm/madvise.c index 6a660858784b..175c5582d8a9 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -540,7 +540,7 @@ static inline bool can_do_pageout(struct vm_area_struct *vma) * opens a side channel. */ return inode_owner_or_capable(file_inode(vma->vm_file)) || - inode_permission(file_inode(vma->vm_file), MAY_WRITE) == 0; + file_permission(vma->vm_file, MAY_WRITE) == 0; } static long madvise_pageout(struct vm_area_struct *vma, diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 605f671203ef..cf9076f58582 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4899,7 +4899,7 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of, /* the process need read permission on control file */ /* AV: shouldn't we check that it's been opened for read instead? */ - ret = inode_permission(file_inode(cfile.file), MAY_READ); + ret = file_permission(cfile.file, MAY_READ); if (ret < 0) goto out_put_cfile; diff --git a/mm/mincore.c b/mm/mincore.c index 02db1a834021..7bdb4673f776 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -167,7 +167,7 @@ static inline bool can_do_mincore(struct vm_area_struct *vma) * mappings, which opens a side channel. */ return inode_owner_or_capable(file_inode(vma->vm_file)) || - inode_permission(file_inode(vma->vm_file), MAY_WRITE) == 0; + file_permission(vma->vm_file, MAY_WRITE) == 0; } static const struct mm_walk_ops mincore_walk_ops = { diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 41c3303c3357..18453d15dddf 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -936,7 +936,7 @@ static struct sock *unix_find_other(struct net *net, if (err) goto fail; inode = d_backing_inode(path.dentry); - err = inode_permission(inode, MAY_WRITE); + err = path_permission(&path, MAY_WRITE); if (err) goto put_fail; -- cgit v1.2.3 From 0558c1bf5a0811bf5e3753eed911a15b9bd08271 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 21 Jan 2021 14:19:23 +0100 Subject: capability: handle idmapped mounts In order to determine whether a caller holds privilege over a given inode the capability framework exposes the two helpers privileged_wrt_inode_uidgid() and capable_wrt_inode_uidgid(). The former verifies that the inode has a mapping in the caller's user namespace and the latter additionally verifies that the caller has the requested capability in their current user namespace. If the inode is accessed through an idmapped mount map it into the mount's user namespace. Afterwards the checks are identical to non-idmapped inodes. If the initial user namespace is passed all operations are a nop so non-idmapped mounts will not see a change in behavior. Link: https://lore.kernel.org/r/20210121131959.646623-5-christian.brauner@ubuntu.com Cc: Christoph Hellwig Cc: David Howells Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig Reviewed-by: James Morris Acked-by: Serge Hallyn Signed-off-by: Christian Brauner --- fs/attr.c | 8 ++++---- fs/exec.c | 3 ++- fs/inode.c | 3 ++- fs/namei.c | 13 ++++++++----- fs/overlayfs/super.c | 2 +- fs/posix_acl.c | 2 +- fs/xfs/xfs_ioctl.c | 2 +- include/linux/capability.h | 7 +++++-- kernel/capability.c | 14 +++++++++----- security/commoncap.c | 5 +++-- 10 files changed, 36 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/fs/attr.c b/fs/attr.c index b4bbdbd4c8ca..d270f640a192 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -23,7 +23,7 @@ static bool chown_ok(const struct inode *inode, kuid_t uid) if (uid_eq(current_fsuid(), inode->i_uid) && uid_eq(uid, inode->i_uid)) return true; - if (capable_wrt_inode_uidgid(inode, CAP_CHOWN)) + if (capable_wrt_inode_uidgid(&init_user_ns, inode, CAP_CHOWN)) return true; if (uid_eq(inode->i_uid, INVALID_UID) && ns_capable(inode->i_sb->s_user_ns, CAP_CHOWN)) @@ -36,7 +36,7 @@ static bool chgrp_ok(const struct inode *inode, kgid_t gid) if (uid_eq(current_fsuid(), inode->i_uid) && (in_group_p(gid) || gid_eq(gid, inode->i_gid))) return true; - if (capable_wrt_inode_uidgid(inode, CAP_CHOWN)) + if (capable_wrt_inode_uidgid(&init_user_ns, inode, CAP_CHOWN)) return true; if (gid_eq(inode->i_gid, INVALID_GID) && ns_capable(inode->i_sb->s_user_ns, CAP_CHOWN)) @@ -92,7 +92,7 @@ int setattr_prepare(struct dentry *dentry, struct iattr *attr) /* Also check the setgid bit! */ if (!in_group_p((ia_valid & ATTR_GID) ? attr->ia_gid : inode->i_gid) && - !capable_wrt_inode_uidgid(inode, CAP_FSETID)) + !capable_wrt_inode_uidgid(&init_user_ns, inode, CAP_FSETID)) attr->ia_mode &= ~S_ISGID; } @@ -193,7 +193,7 @@ void setattr_copy(struct inode *inode, const struct iattr *attr) umode_t mode = attr->ia_mode; if (!in_group_p(inode->i_gid) && - !capable_wrt_inode_uidgid(inode, CAP_FSETID)) + !capable_wrt_inode_uidgid(&init_user_ns, inode, CAP_FSETID)) mode &= ~S_ISGID; inode->i_mode = mode; } diff --git a/fs/exec.c b/fs/exec.c index 5d4d52039105..89d4780ff48f 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1411,7 +1411,8 @@ void would_dump(struct linux_binprm *bprm, struct file *file) /* Ensure mm->user_ns contains the executable */ user_ns = old = bprm->mm->user_ns; while ((user_ns != &init_user_ns) && - !privileged_wrt_inode_uidgid(user_ns, inode)) + !privileged_wrt_inode_uidgid(user_ns, &init_user_ns, + inode)) user_ns = user_ns->parent; if (old != user_ns) { diff --git a/fs/inode.c b/fs/inode.c index 6442d97d9a4a..cd40cbf87ce4 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -2146,7 +2146,8 @@ void inode_init_owner(struct inode *inode, const struct inode *dir, mode |= S_ISGID; else if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP) && !in_group_p(inode->i_gid) && - !capable_wrt_inode_uidgid(dir, CAP_FSETID)) + !capable_wrt_inode_uidgid(&init_user_ns, dir, + CAP_FSETID)) mode &= ~S_ISGID; } else inode->i_gid = current_fsgid(); diff --git a/fs/namei.c b/fs/namei.c index 78443a85480a..fd4724bce4f5 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -357,10 +357,11 @@ int generic_permission(struct inode *inode, int mask) if (S_ISDIR(inode->i_mode)) { /* DACs are overridable for directories */ if (!(mask & MAY_WRITE)) - if (capable_wrt_inode_uidgid(inode, + if (capable_wrt_inode_uidgid(&init_user_ns, inode, CAP_DAC_READ_SEARCH)) return 0; - if (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE)) + if (capable_wrt_inode_uidgid(&init_user_ns, inode, + CAP_DAC_OVERRIDE)) return 0; return -EACCES; } @@ -370,7 +371,8 @@ int generic_permission(struct inode *inode, int mask) */ mask &= MAY_READ | MAY_WRITE | MAY_EXEC; if (mask == MAY_READ) - if (capable_wrt_inode_uidgid(inode, CAP_DAC_READ_SEARCH)) + if (capable_wrt_inode_uidgid(&init_user_ns, inode, + CAP_DAC_READ_SEARCH)) return 0; /* * Read/write DACs are always overridable. @@ -378,7 +380,8 @@ int generic_permission(struct inode *inode, int mask) * at least one exec bit set. */ if (!(mask & MAY_EXEC) || (inode->i_mode & S_IXUGO)) - if (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE)) + if (capable_wrt_inode_uidgid(&init_user_ns, inode, + CAP_DAC_OVERRIDE)) return 0; return -EACCES; @@ -2659,7 +2662,7 @@ int __check_sticky(struct inode *dir, struct inode *inode) return 0; if (uid_eq(dir->i_uid, fsuid)) return 0; - return !capable_wrt_inode_uidgid(inode, CAP_FOWNER); + return !capable_wrt_inode_uidgid(&init_user_ns, inode, CAP_FOWNER); } EXPORT_SYMBOL(__check_sticky); diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 2bd570cbe8a4..88d877787770 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -1017,7 +1017,7 @@ ovl_posix_acl_xattr_set(const struct xattr_handler *handler, if (unlikely(inode->i_mode & S_ISGID) && handler->flags == ACL_TYPE_ACCESS && !in_group_p(inode->i_gid) && - !capable_wrt_inode_uidgid(inode, CAP_FSETID)) { + !capable_wrt_inode_uidgid(&init_user_ns, inode, CAP_FSETID)) { struct iattr iattr = { .ia_valid = ATTR_KILL_SGID }; err = ovl_setattr(dentry, &iattr); diff --git a/fs/posix_acl.c b/fs/posix_acl.c index 95882b3f5f62..4ca6d53c6f0a 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -656,7 +656,7 @@ int posix_acl_update_mode(struct inode *inode, umode_t *mode_p, if (error == 0) *acl = NULL; if (!in_group_p(inode->i_gid) && - !capable_wrt_inode_uidgid(inode, CAP_FSETID)) + !capable_wrt_inode_uidgid(&init_user_ns, inode, CAP_FSETID)) mode &= ~S_ISGID; *mode_p = mode; return 0; diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 3fbd98f61ea5..97bd29fc8c43 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1502,7 +1502,7 @@ xfs_ioctl_setattr( */ if ((VFS_I(ip)->i_mode & (S_ISUID|S_ISGID)) && - !capable_wrt_inode_uidgid(VFS_I(ip), CAP_FSETID)) + !capable_wrt_inode_uidgid(&init_user_ns, VFS_I(ip), CAP_FSETID)) VFS_I(ip)->i_mode &= ~(S_ISUID|S_ISGID); /* Change the ownerships and register project quota modifications */ diff --git a/include/linux/capability.h b/include/linux/capability.h index b2f698915c0f..62bfa3ed84d7 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -247,8 +247,11 @@ static inline bool ns_capable_setid(struct user_namespace *ns, int cap) return true; } #endif /* CONFIG_MULTIUSER */ -extern bool privileged_wrt_inode_uidgid(struct user_namespace *ns, const struct inode *inode); -extern bool capable_wrt_inode_uidgid(const struct inode *inode, int cap); +bool privileged_wrt_inode_uidgid(struct user_namespace *ns, + struct user_namespace *mnt_userns, + const struct inode *inode); +bool capable_wrt_inode_uidgid(struct user_namespace *mnt_userns, + const struct inode *inode, int cap); extern bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap); extern bool ptracer_capable(struct task_struct *tsk, struct user_namespace *ns); static inline bool perfmon_capable(void) diff --git a/kernel/capability.c b/kernel/capability.c index de7eac903a2a..46a361dde042 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -484,10 +484,12 @@ EXPORT_SYMBOL(file_ns_capable); * * Return true if the inode uid and gid are within the namespace. */ -bool privileged_wrt_inode_uidgid(struct user_namespace *ns, const struct inode *inode) +bool privileged_wrt_inode_uidgid(struct user_namespace *ns, + struct user_namespace *mnt_userns, + const struct inode *inode) { - return kuid_has_mapping(ns, inode->i_uid) && - kgid_has_mapping(ns, inode->i_gid); + return kuid_has_mapping(ns, i_uid_into_mnt(mnt_userns, inode)) && + kgid_has_mapping(ns, i_gid_into_mnt(mnt_userns, inode)); } /** @@ -499,11 +501,13 @@ bool privileged_wrt_inode_uidgid(struct user_namespace *ns, const struct inode * * its own user namespace and that the given inode's uid and gid are * mapped into the current user namespace. */ -bool capable_wrt_inode_uidgid(const struct inode *inode, int cap) +bool capable_wrt_inode_uidgid(struct user_namespace *mnt_userns, + const struct inode *inode, int cap) { struct user_namespace *ns = current_user_ns(); - return ns_capable(ns, cap) && privileged_wrt_inode_uidgid(ns, inode); + return ns_capable(ns, cap) && + privileged_wrt_inode_uidgid(ns, mnt_userns, inode); } EXPORT_SYMBOL(capable_wrt_inode_uidgid); diff --git a/security/commoncap.c b/security/commoncap.c index bacc1111d871..88ee345f7bfa 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -489,7 +489,7 @@ int cap_convert_nscap(struct dentry *dentry, const void **ivalue, size_t size) return -EINVAL; if (!validheader(size, cap)) return -EINVAL; - if (!capable_wrt_inode_uidgid(inode, CAP_SETFCAP)) + if (!capable_wrt_inode_uidgid(&init_user_ns, inode, CAP_SETFCAP)) return -EPERM; if (size == XATTR_CAPS_SZ_2) if (ns_capable(inode->i_sb->s_user_ns, CAP_SETFCAP)) @@ -956,7 +956,8 @@ int cap_inode_removexattr(struct dentry *dentry, const char *name) struct inode *inode = d_backing_inode(dentry); if (!inode) return -EINVAL; - if (!capable_wrt_inode_uidgid(inode, CAP_SETFCAP)) + if (!capable_wrt_inode_uidgid(&init_user_ns, inode, + CAP_SETFCAP)) return -EPERM; return 0; } -- cgit v1.2.3 From 47291baa8ddfdae10663624ff0a15ab165952708 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 21 Jan 2021 14:19:24 +0100 Subject: namei: make permission helpers idmapped mount aware The two helpers inode_permission() and generic_permission() are used by the vfs to perform basic permission checking by verifying that the caller is privileged over an inode. In order to handle idmapped mounts we extend the two helpers with an additional user namespace argument. On idmapped mounts the two helpers will make sure to map the inode according to the mount's user namespace and then peform identical permission checks to inode_permission() and generic_permission(). If the initial user namespace is passed nothing changes so non-idmapped mounts will see identical behavior as before. Link: https://lore.kernel.org/r/20210121131959.646623-6-christian.brauner@ubuntu.com Cc: Christoph Hellwig Cc: David Howells Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig Reviewed-by: James Morris Acked-by: Serge Hallyn Signed-off-by: Christian Brauner --- fs/attr.c | 3 +- fs/btrfs/inode.c | 2 +- fs/btrfs/ioctl.c | 12 +++-- fs/ceph/inode.c | 2 +- fs/cifs/cifsfs.c | 2 +- fs/configfs/symlink.c | 3 +- fs/ecryptfs/inode.c | 3 +- fs/exec.c | 2 +- fs/fuse/dir.c | 5 +- fs/gfs2/inode.c | 2 +- fs/hostfs/hostfs_kern.c | 2 +- fs/kernfs/inode.c | 2 +- fs/libfs.c | 7 ++- fs/namei.c | 121 ++++++++++++++++++++++++++++++++-------------- fs/nfs/dir.c | 2 +- fs/nfsd/nfsfh.c | 3 +- fs/nfsd/vfs.c | 5 +- fs/nilfs2/inode.c | 2 +- fs/ocfs2/file.c | 2 +- fs/ocfs2/refcounttree.c | 4 +- fs/open.c | 4 +- fs/orangefs/inode.c | 2 +- fs/overlayfs/file.c | 2 +- fs/overlayfs/inode.c | 4 +- fs/overlayfs/util.c | 2 +- fs/posix_acl.c | 17 +++++-- fs/proc/base.c | 4 +- fs/proc/fd.c | 2 +- fs/reiserfs/xattr.c | 2 +- fs/remap_range.c | 2 +- fs/xattr.c | 2 +- include/linux/fs.h | 10 ++-- include/linux/posix_acl.h | 7 ++- ipc/mqueue.c | 2 +- kernel/bpf/inode.c | 2 +- kernel/cgroup/cgroup.c | 2 +- 36 files changed, 164 insertions(+), 88 deletions(-) (limited to 'include') diff --git a/fs/attr.c b/fs/attr.c index d270f640a192..c9e29e589cec 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -244,7 +244,8 @@ int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **de return -EPERM; if (!inode_owner_or_capable(inode)) { - error = inode_permission(inode, MAY_WRITE); + error = inode_permission(&init_user_ns, inode, + MAY_WRITE); if (error) return error; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index a8e0a6b038d3..512ee2650bbb 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -9889,7 +9889,7 @@ static int btrfs_permission(struct inode *inode, int mask) if (BTRFS_I(inode)->flags & BTRFS_INODE_READONLY) return -EACCES; } - return generic_permission(inode, mask); + return generic_permission(&init_user_ns, inode, mask); } static int btrfs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index dde49a791f3e..8ced6dfefee4 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -922,7 +922,7 @@ static int btrfs_may_delete(struct inode *dir, struct dentry *victim, int isdir) BUG_ON(d_inode(victim->d_parent) != dir); audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE); - error = inode_permission(dir, MAY_WRITE | MAY_EXEC); + error = inode_permission(&init_user_ns, dir, MAY_WRITE | MAY_EXEC); if (error) return error; if (IS_APPEND(dir)) @@ -951,7 +951,7 @@ static inline int btrfs_may_create(struct inode *dir, struct dentry *child) return -EEXIST; if (IS_DEADDIR(dir)) return -ENOENT; - return inode_permission(dir, MAY_WRITE | MAY_EXEC); + return inode_permission(&init_user_ns, dir, MAY_WRITE | MAY_EXEC); } /* @@ -2538,7 +2538,8 @@ static int btrfs_search_path_in_tree_user(struct inode *inode, ret = PTR_ERR(temp_inode); goto out_put; } - ret = inode_permission(temp_inode, MAY_READ | MAY_EXEC); + ret = inode_permission(&init_user_ns, temp_inode, + MAY_READ | MAY_EXEC); iput(temp_inode); if (ret) { ret = -EACCES; @@ -3068,7 +3069,8 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, if (root == dest) goto out_dput; - err = inode_permission(inode, MAY_WRITE | MAY_EXEC); + err = inode_permission(&init_user_ns, inode, + MAY_WRITE | MAY_EXEC); if (err) goto out_dput; } @@ -3139,7 +3141,7 @@ static int btrfs_ioctl_defrag(struct file *file, void __user *argp) * running and allows defrag on files open in read-only mode. */ if (!capable(CAP_SYS_ADMIN) && - inode_permission(inode, MAY_WRITE)) { + inode_permission(&init_user_ns, inode, MAY_WRITE)) { ret = -EPERM; goto out; } diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index adc8fc3c5d85..e8a15ee09bc1 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -2331,7 +2331,7 @@ int ceph_permission(struct inode *inode, int mask) err = ceph_do_getattr(inode, CEPH_CAP_AUTH_SHARED, false); if (!err) - err = generic_permission(inode, mask); + err = generic_permission(&init_user_ns, inode, mask); return err; } diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index ce0d0037fd0a..ce14e6f8adb6 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -320,7 +320,7 @@ static int cifs_permission(struct inode *inode, int mask) on the client (above and beyond ACL on servers) for servers which do not support setting and viewing mode bits, so allowing client to check permissions is useful */ - return generic_permission(inode, mask); + return generic_permission(&init_user_ns, inode, mask); } static struct kmem_cache *cifs_inode_cachep; diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c index cb61467478ca..8ca36394fa30 100644 --- a/fs/configfs/symlink.c +++ b/fs/configfs/symlink.c @@ -197,7 +197,8 @@ int configfs_symlink(struct inode *dir, struct dentry *dentry, const char *symna if (dentry->d_inode || d_unhashed(dentry)) ret = -EEXIST; else - ret = inode_permission(dir, MAY_WRITE | MAY_EXEC); + ret = inode_permission(&init_user_ns, dir, + MAY_WRITE | MAY_EXEC); if (!ret) ret = type->ct_item_ops->allow_link(parent_item, target_item); if (!ret) { diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index e23752d9a79f..0b346baf110d 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -864,7 +864,8 @@ int ecryptfs_truncate(struct dentry *dentry, loff_t new_length) static int ecryptfs_permission(struct inode *inode, int mask) { - return inode_permission(ecryptfs_inode_to_lower(inode), mask); + return inode_permission(&init_user_ns, + ecryptfs_inode_to_lower(inode), mask); } /** diff --git a/fs/exec.c b/fs/exec.c index 89d4780ff48f..a8ec371cd3cd 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1404,7 +1404,7 @@ EXPORT_SYMBOL(begin_new_exec); void would_dump(struct linux_binprm *bprm, struct file *file) { struct inode *inode = file_inode(file); - if (inode_permission(inode, MAY_READ) < 0) { + if (inode_permission(&init_user_ns, inode, MAY_READ) < 0) { struct user_namespace *old, *user_ns; bprm->interp_flags |= BINPRM_FLAGS_ENFORCE_NONDUMP; diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 78f9f209078c..7497009a5a45 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1280,7 +1280,7 @@ static int fuse_permission(struct inode *inode, int mask) } if (fc->default_permissions) { - err = generic_permission(inode, mask); + err = generic_permission(&init_user_ns, inode, mask); /* If permission is denied, try to refresh file attributes. This is also needed, because the root @@ -1288,7 +1288,8 @@ static int fuse_permission(struct inode *inode, int mask) if (err == -EACCES && !refreshed) { err = fuse_perm_getattr(inode, mask); if (!err) - err = generic_permission(inode, mask); + err = generic_permission(&init_user_ns, + inode, mask); } /* Note: the opposite of the above test does not diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index c1b77e8d6b1c..5b2ff0c74b67 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -1852,7 +1852,7 @@ int gfs2_permission(struct inode *inode, int mask) if ((mask & MAY_WRITE) && IS_IMMUTABLE(inode)) error = -EPERM; else - error = generic_permission(inode, mask); + error = generic_permission(&init_user_ns, inode, mask); if (gfs2_holder_initialized(&i_gh)) gfs2_glock_dq_uninit(&i_gh); diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index aea35459d390..b841a05a2b8c 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -779,7 +779,7 @@ static int hostfs_permission(struct inode *ino, int desired) err = access_file(name, r, w, x); __putname(name); if (!err) - err = generic_permission(ino, desired); + err = generic_permission(&init_user_ns, ino, desired); return err; } diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index fc2469a20fed..ff5598cc1de0 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -285,7 +285,7 @@ int kernfs_iop_permission(struct inode *inode, int mask) kernfs_refresh_inode(kn, inode); mutex_unlock(&kernfs_mutex); - return generic_permission(inode, mask); + return generic_permission(&init_user_ns, inode, mask); } int kernfs_xattr_get(struct kernfs_node *kn, const char *name, diff --git a/fs/libfs.c b/fs/libfs.c index d1c3bade9f30..f8b3c02b4f0f 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -1318,9 +1318,14 @@ static ssize_t empty_dir_listxattr(struct dentry *dentry, char *list, size_t siz return -EOPNOTSUPP; } +static int empty_dir_permission(struct inode *inode, int mask) +{ + return generic_permission(&init_user_ns, inode, mask); +} + static const struct inode_operations empty_dir_inode_operations = { .lookup = empty_dir_lookup, - .permission = generic_permission, + .permission = empty_dir_permission, .setattr = empty_dir_setattr, .getattr = empty_dir_getattr, .listxattr = empty_dir_listxattr, diff --git a/fs/namei.c b/fs/namei.c index fd4724bce4f5..d78d74f5f5af 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -259,7 +259,24 @@ void putname(struct filename *name) __putname(name); } -static int check_acl(struct inode *inode, int mask) +/** + * check_acl - perform ACL permission checking + * @mnt_userns: user namespace of the mount the inode was found from + * @inode: inode to check permissions on + * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC ...) + * + * This function performs the ACL permission checking. Since this function + * retrieve POSIX acls it needs to know whether it is called from a blocking or + * non-blocking context and thus cares about the MAY_NOT_BLOCK bit. + * + * If the inode has been found through an idmapped mount the user namespace of + * the vfsmount must be passed through @mnt_userns. This function will then take + * care to map the inode according to @mnt_userns before checking permissions. + * On non-idmapped mounts or if permission checking is to be performed on the + * raw inode simply passs init_user_ns. + */ +static int check_acl(struct user_namespace *mnt_userns, + struct inode *inode, int mask) { #ifdef CONFIG_FS_POSIX_ACL struct posix_acl *acl; @@ -271,14 +288,14 @@ static int check_acl(struct inode *inode, int mask) /* no ->get_acl() calls in RCU mode... */ if (is_uncached_acl(acl)) return -ECHILD; - return posix_acl_permission(inode, acl, mask); + return posix_acl_permission(mnt_userns, inode, acl, mask); } acl = get_acl(inode, ACL_TYPE_ACCESS); if (IS_ERR(acl)) return PTR_ERR(acl); if (acl) { - int error = posix_acl_permission(inode, acl, mask); + int error = posix_acl_permission(mnt_userns, inode, acl, mask); posix_acl_release(acl); return error; } @@ -287,18 +304,31 @@ static int check_acl(struct inode *inode, int mask) return -EAGAIN; } -/* - * This does the basic UNIX permission checking. +/** + * acl_permission_check - perform basic UNIX permission checking + * @mnt_userns: user namespace of the mount the inode was found from + * @inode: inode to check permissions on + * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC ...) + * + * This function performs the basic UNIX permission checking. Since this + * function may retrieve POSIX acls it needs to know whether it is called from a + * blocking or non-blocking context and thus cares about the MAY_NOT_BLOCK bit. * - * Note that the POSIX ACL check cares about the MAY_NOT_BLOCK bit, - * for RCU walking. + * If the inode has been found through an idmapped mount the user namespace of + * the vfsmount must be passed through @mnt_userns. This function will then take + * care to map the inode according to @mnt_userns before checking permissions. + * On non-idmapped mounts or if permission checking is to be performed on the + * raw inode simply passs init_user_ns. */ -static int acl_permission_check(struct inode *inode, int mask) +static int acl_permission_check(struct user_namespace *mnt_userns, + struct inode *inode, int mask) { unsigned int mode = inode->i_mode; + kuid_t i_uid; /* Are we the owner? If so, ACL's don't matter */ - if (likely(uid_eq(current_fsuid(), inode->i_uid))) { + i_uid = i_uid_into_mnt(mnt_userns, inode); + if (likely(uid_eq(current_fsuid(), i_uid))) { mask &= 7; mode >>= 6; return (mask & ~mode) ? -EACCES : 0; @@ -306,7 +336,7 @@ static int acl_permission_check(struct inode *inode, int mask) /* Do we have ACL's? */ if (IS_POSIXACL(inode) && (mode & S_IRWXG)) { - int error = check_acl(inode, mask); + int error = check_acl(mnt_userns, inode, mask); if (error != -EAGAIN) return error; } @@ -320,7 +350,8 @@ static int acl_permission_check(struct inode *inode, int mask) * about? Need to check group ownership if so. */ if (mask & (mode ^ (mode >> 3))) { - if (in_group_p(inode->i_gid)) + kgid_t kgid = i_gid_into_mnt(mnt_userns, inode); + if (in_group_p(kgid)) mode >>= 3; } @@ -330,6 +361,7 @@ static int acl_permission_check(struct inode *inode, int mask) /** * generic_permission - check for access rights on a Posix-like filesystem + * @mnt_userns: user namespace of the mount the inode was found from * @inode: inode to check access rights for * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC, * %MAY_NOT_BLOCK ...) @@ -342,25 +374,32 @@ static int acl_permission_check(struct inode *inode, int mask) * generic_permission is rcu-walk aware. It returns -ECHILD in case an rcu-walk * request cannot be satisfied (eg. requires blocking or too much complexity). * It would then be called again in ref-walk mode. + * + * If the inode has been found through an idmapped mount the user namespace of + * the vfsmount must be passed through @mnt_userns. This function will then take + * care to map the inode according to @mnt_userns before checking permissions. + * On non-idmapped mounts or if permission checking is to be performed on the + * raw inode simply passs init_user_ns. */ -int generic_permission(struct inode *inode, int mask) +int generic_permission(struct user_namespace *mnt_userns, struct inode *inode, + int mask) { int ret; /* * Do the basic permission checks. */ - ret = acl_permission_check(inode, mask); + ret = acl_permission_check(mnt_userns, inode, mask); if (ret != -EACCES) return ret; if (S_ISDIR(inode->i_mode)) { /* DACs are overridable for directories */ if (!(mask & MAY_WRITE)) - if (capable_wrt_inode_uidgid(&init_user_ns, inode, + if (capable_wrt_inode_uidgid(mnt_userns, inode, CAP_DAC_READ_SEARCH)) return 0; - if (capable_wrt_inode_uidgid(&init_user_ns, inode, + if (capable_wrt_inode_uidgid(mnt_userns, inode, CAP_DAC_OVERRIDE)) return 0; return -EACCES; @@ -371,7 +410,7 @@ int generic_permission(struct inode *inode, int mask) */ mask &= MAY_READ | MAY_WRITE | MAY_EXEC; if (mask == MAY_READ) - if (capable_wrt_inode_uidgid(&init_user_ns, inode, + if (capable_wrt_inode_uidgid(mnt_userns, inode, CAP_DAC_READ_SEARCH)) return 0; /* @@ -380,7 +419,7 @@ int generic_permission(struct inode *inode, int mask) * at least one exec bit set. */ if (!(mask & MAY_EXEC) || (inode->i_mode & S_IXUGO)) - if (capable_wrt_inode_uidgid(&init_user_ns, inode, + if (capable_wrt_inode_uidgid(mnt_userns, inode, CAP_DAC_OVERRIDE)) return 0; @@ -388,13 +427,19 @@ int generic_permission(struct inode *inode, int mask) } EXPORT_SYMBOL(generic_permission); -/* +/** + * do_inode_permission - UNIX permission checking + * @mnt_userns: user namespace of the mount the inode was found from + * @inode: inode to check permissions on + * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC ...) + * * We _really_ want to just do "generic_permission()" without * even looking at the inode->i_op values. So we keep a cache * flag in inode->i_opflags, that says "this has not special * permission function, use the fast case". */ -static inline int do_inode_permission(struct inode *inode, int mask) +static inline int do_inode_permission(struct user_namespace *mnt_userns, + struct inode *inode, int mask) { if (unlikely(!(inode->i_opflags & IOP_FASTPERM))) { if (likely(inode->i_op->permission)) @@ -405,7 +450,7 @@ static inline int do_inode_permission(struct inode *inode, int mask) inode->i_opflags |= IOP_FASTPERM; spin_unlock(&inode->i_lock); } - return generic_permission(inode, mask); + return generic_permission(mnt_userns, inode, mask); } /** @@ -430,8 +475,9 @@ static int sb_permission(struct super_block *sb, struct inode *inode, int mask) /** * inode_permission - Check for access rights to a given inode - * @inode: Inode to check permission on - * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC) + * @mnt_userns: User namespace of the mount the inode was found from + * @inode: Inode to check permission on + * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC) * * Check for read/write/execute permissions on an inode. We use fs[ug]id for * this, letting us set arbitrary permissions for filesystem access without @@ -439,7 +485,8 @@ static int sb_permission(struct super_block *sb, struct inode *inode, int mask) * * When checking for MAY_APPEND, MAY_WRITE must also be set in @mask. */ -int inode_permission(struct inode *inode, int mask) +int inode_permission(struct user_namespace *mnt_userns, + struct inode *inode, int mask) { int retval; @@ -463,7 +510,7 @@ int inode_permission(struct inode *inode, int mask) return -EACCES; } - retval = do_inode_permission(inode, mask); + retval = do_inode_permission(mnt_userns, inode, mask); if (retval) return retval; @@ -1009,7 +1056,7 @@ static bool safe_hardlink_source(struct inode *inode) return false; /* Hardlinking to unreadable or unwritable sources is dangerous. */ - if (inode_permission(inode, MAY_READ | MAY_WRITE)) + if (inode_permission(&init_user_ns, inode, MAY_READ | MAY_WRITE)) return false; return true; @@ -1569,13 +1616,14 @@ static struct dentry *lookup_slow(const struct qstr *name, static inline int may_lookup(struct nameidata *nd) { if (nd->flags & LOOKUP_RCU) { - int err = inode_permission(nd->inode, MAY_EXEC|MAY_NOT_BLOCK); + int err = inode_permission(&init_user_ns, nd->inode, + MAY_EXEC | MAY_NOT_BLOCK); if (err != -ECHILD) return err; if (unlazy_walk(nd)) return -ECHILD; } - return inode_permission(nd->inode, MAY_EXEC); + return inode_permission(&init_user_ns, nd->inode, MAY_EXEC); } static int reserve_stack(struct nameidata *nd, struct path *link, unsigned seq) @@ -2509,7 +2557,7 @@ static int lookup_one_len_common(const char *name, struct dentry *base, return err; } - return inode_permission(base->d_inode, MAY_EXEC); + return inode_permission(&init_user_ns, base->d_inode, MAY_EXEC); } /** @@ -2703,7 +2751,7 @@ static int may_delete(struct inode *dir, struct dentry *victim, bool isdir) audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE); - error = inode_permission(dir, MAY_WRITE | MAY_EXEC); + error = inode_permission(&init_user_ns, dir, MAY_WRITE | MAY_EXEC); if (error) return error; if (IS_APPEND(dir)) @@ -2747,7 +2795,7 @@ static inline int may_create(struct inode *dir, struct dentry *child) if (!kuid_has_mapping(s_user_ns, current_fsuid()) || !kgid_has_mapping(s_user_ns, current_fsgid())) return -EOVERFLOW; - return inode_permission(dir, MAY_WRITE | MAY_EXEC); + return inode_permission(&init_user_ns, dir, MAY_WRITE | MAY_EXEC); } /* @@ -2877,7 +2925,7 @@ static int may_open(const struct path *path, int acc_mode, int flag) break; } - error = inode_permission(inode, MAY_OPEN | acc_mode); + error = inode_permission(&init_user_ns, inode, MAY_OPEN | acc_mode); if (error) return error; @@ -2939,7 +2987,8 @@ static int may_o_create(const struct path *dir, struct dentry *dentry, umode_t m !kgid_has_mapping(s_user_ns, current_fsgid())) return -EOVERFLOW; - error = inode_permission(dir->dentry->d_inode, MAY_WRITE | MAY_EXEC); + error = inode_permission(&init_user_ns, dir->dentry->d_inode, + MAY_WRITE | MAY_EXEC); if (error) return error; @@ -3276,7 +3325,7 @@ struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode, int open_flag) int error; /* we want directory to be writable */ - error = inode_permission(dir, MAY_WRITE | MAY_EXEC); + error = inode_permission(&init_user_ns, dir, MAY_WRITE | MAY_EXEC); if (error) goto out_err; error = -EOPNOTSUPP; @@ -4267,12 +4316,14 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, */ if (new_dir != old_dir) { if (is_dir) { - error = inode_permission(source, MAY_WRITE); + error = inode_permission(&init_user_ns, source, + MAY_WRITE); if (error) return error; } if ((flags & RENAME_EXCHANGE) && new_is_dir) { - error = inode_permission(target, MAY_WRITE); + error = inode_permission(&init_user_ns, target, + MAY_WRITE); if (error) return error; } diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index ef827ae193d2..727e01a84503 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -2987,7 +2987,7 @@ out_notsup: res = nfs_revalidate_inode(NFS_SERVER(inode), inode); if (res == 0) - res = generic_permission(inode, mask); + res = generic_permission(&init_user_ns, inode, mask); goto out; } EXPORT_SYMBOL_GPL(nfs_permission); diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index 66f2ef67792a..8d90796e236a 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -40,7 +40,8 @@ static int nfsd_acceptable(void *expv, struct dentry *dentry) /* make sure parents give x permission to user */ int err; parent = dget_parent(tdentry); - err = inode_permission(d_inode(parent), MAY_EXEC); + err = inode_permission(&init_user_ns, + d_inode(parent), MAY_EXEC); if (err < 0) { dput(parent); break; diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 04937e51de56..0edf11258aaa 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -2391,13 +2391,14 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp, return 0; /* This assumes NFSD_MAY_{READ,WRITE,EXEC} == MAY_{READ,WRITE,EXEC} */ - err = inode_permission(inode, acc & (MAY_READ|MAY_WRITE|MAY_EXEC)); + err = inode_permission(&init_user_ns, inode, + acc & (MAY_READ | MAY_WRITE | MAY_EXEC)); /* Allow read access to binaries even when mode 111 */ if (err == -EACCES && S_ISREG(inode->i_mode) && (acc == (NFSD_MAY_READ | NFSD_MAY_OWNER_OVERRIDE) || acc == (NFSD_MAY_READ | NFSD_MAY_READ_IF_EXEC))) - err = inode_permission(inode, MAY_EXEC); + err = inode_permission(&init_user_ns, inode, MAY_EXEC); return err? nfserrno(err) : 0; } diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 745d371d6fea..b6517220cad5 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -851,7 +851,7 @@ int nilfs_permission(struct inode *inode, int mask) root->cno != NILFS_CPTREE_CURRENT_CNO) return -EROFS; /* snapshot is not writable */ - return generic_permission(inode, mask); + return generic_permission(&init_user_ns, inode, mask); } int nilfs_load_inode_block(struct inode *inode, struct buffer_head **pbh) diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 85979e2214b3..0c75619adf54 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1355,7 +1355,7 @@ int ocfs2_permission(struct inode *inode, int mask) dump_stack(); } - ret = generic_permission(inode, mask); + ret = generic_permission(&init_user_ns, inode, mask); ocfs2_inode_unlock_tracker(inode, 0, &oh, had_lock); out: diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index 3b397fa9c9e8..c26937824be1 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -4346,7 +4346,7 @@ static inline int ocfs2_may_create(struct inode *dir, struct dentry *child) return -EEXIST; if (IS_DEADDIR(dir)) return -ENOENT; - return inode_permission(dir, MAY_WRITE | MAY_EXEC); + return inode_permission(&init_user_ns, dir, MAY_WRITE | MAY_EXEC); } /** @@ -4400,7 +4400,7 @@ static int ocfs2_vfs_reflink(struct dentry *old_dentry, struct inode *dir, * file. */ if (!preserve) { - error = inode_permission(inode, MAY_READ); + error = inode_permission(&init_user_ns, inode, MAY_READ); if (error) return error; } diff --git a/fs/open.c b/fs/open.c index cd1efd254cad..a6dac6d97988 100644 --- a/fs/open.c +++ b/fs/open.c @@ -83,7 +83,7 @@ long vfs_truncate(const struct path *path, loff_t length) if (error) goto out; - error = inode_permission(inode, MAY_WRITE); + error = inode_permission(&init_user_ns, inode, MAY_WRITE); if (error) goto mnt_drop_write_and_out; @@ -436,7 +436,7 @@ retry: goto out_path_release; } - res = inode_permission(inode, mode | MAY_ACCESS); + res = inode_permission(&init_user_ns, inode, mode | MAY_ACCESS); /* SuS v2 requires we report a read only fs too */ if (res || !(mode & S_IWOTH) || special_file(inode->i_mode)) goto out_path_release; diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c index 48f0547d4850..4c790cc8042d 100644 --- a/fs/orangefs/inode.c +++ b/fs/orangefs/inode.c @@ -933,7 +933,7 @@ int orangefs_permission(struct inode *inode, int mask) if (ret < 0) return ret; - return generic_permission(inode, mask); + return generic_permission(&init_user_ns, inode, mask); } int orangefs_update_time(struct inode *inode, struct timespec64 *time, int flags) diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index bd9dd38347ae..b2948e7b3210 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -50,7 +50,7 @@ static struct file *ovl_open_realfile(const struct file *file, acc_mode |= MAY_APPEND; old_cred = ovl_override_creds(inode->i_sb); - err = inode_permission(realinode, MAY_OPEN | acc_mode); + err = inode_permission(&init_user_ns, realinode, MAY_OPEN | acc_mode); if (err) { realfile = ERR_PTR(err); } else { diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index d739e14c6814..c101ebbb7a77 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -294,7 +294,7 @@ int ovl_permission(struct inode *inode, int mask) * Check overlay inode with the creds of task and underlying inode * with creds of mounter */ - err = generic_permission(inode, mask); + err = generic_permission(&init_user_ns, inode, mask); if (err) return err; @@ -305,7 +305,7 @@ int ovl_permission(struct inode *inode, int mask) /* Make sure mounter can read file for copy up later */ mask |= MAY_READ; } - err = inode_permission(realinode, mask); + err = inode_permission(&init_user_ns, realinode, mask); revert_creds(old_cred); return err; diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c index 6569031af3cd..de5c2047a0e9 100644 --- a/fs/overlayfs/util.c +++ b/fs/overlayfs/util.c @@ -479,7 +479,7 @@ struct file *ovl_path_open(struct path *path, int flags) BUG(); } - err = inode_permission(inode, acc_mode | MAY_OPEN); + err = inode_permission(&init_user_ns, inode, acc_mode | MAY_OPEN); if (err) return ERR_PTR(err); diff --git a/fs/posix_acl.c b/fs/posix_acl.c index 4ca6d53c6f0a..5d9fe2fb2953 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -345,10 +345,13 @@ EXPORT_SYMBOL(posix_acl_from_mode); * by the acl. Returns -E... otherwise. */ int -posix_acl_permission(struct inode *inode, const struct posix_acl *acl, int want) +posix_acl_permission(struct user_namespace *mnt_userns, struct inode *inode, + const struct posix_acl *acl, int want) { const struct posix_acl_entry *pa, *pe, *mask_obj; int found = 0; + kuid_t uid; + kgid_t gid; want &= MAY_READ | MAY_WRITE | MAY_EXEC; @@ -356,22 +359,26 @@ posix_acl_permission(struct inode *inode, const struct posix_acl *acl, int want) switch(pa->e_tag) { case ACL_USER_OBJ: /* (May have been checked already) */ - if (uid_eq(inode->i_uid, current_fsuid())) + uid = i_uid_into_mnt(mnt_userns, inode); + if (uid_eq(uid, current_fsuid())) goto check_perm; break; case ACL_USER: - if (uid_eq(pa->e_uid, current_fsuid())) + uid = kuid_into_mnt(mnt_userns, pa->e_uid); + if (uid_eq(uid, current_fsuid())) goto mask; break; case ACL_GROUP_OBJ: - if (in_group_p(inode->i_gid)) { + gid = i_gid_into_mnt(mnt_userns, inode); + if (in_group_p(gid)) { found = 1; if ((pa->e_perm & want) == want) goto mask; } break; case ACL_GROUP: - if (in_group_p(pa->e_gid)) { + gid = kgid_into_mnt(mnt_userns, pa->e_gid); + if (in_group_p(gid)) { found = 1; if ((pa->e_perm & want) == want) goto mask; diff --git a/fs/proc/base.c b/fs/proc/base.c index b3422cda2a91..b4ec9293625e 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -751,7 +751,7 @@ static int proc_pid_permission(struct inode *inode, int mask) return -EPERM; } - return generic_permission(inode, mask); + return generic_permission(&init_user_ns, inode, mask); } @@ -3492,7 +3492,7 @@ static int proc_tid_comm_permission(struct inode *inode, int mask) return 0; } - return generic_permission(inode, mask); + return generic_permission(&init_user_ns, inode, mask); } static const struct inode_operations proc_tid_comm_inode_operations = { diff --git a/fs/proc/fd.c b/fs/proc/fd.c index cb51763ed554..d6e76461e135 100644 --- a/fs/proc/fd.c +++ b/fs/proc/fd.c @@ -281,7 +281,7 @@ int proc_fd_permission(struct inode *inode, int mask) struct task_struct *p; int rv; - rv = generic_permission(inode, mask); + rv = generic_permission(&init_user_ns, inode, mask); if (rv == 0) return rv; diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index fe63a7c3e0da..ec440d1957a1 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -957,7 +957,7 @@ int reiserfs_permission(struct inode *inode, int mask) if (IS_PRIVATE(inode)) return 0; - return generic_permission(inode, mask); + return generic_permission(&init_user_ns, inode, mask); } static int xattr_hide_revalidate(struct dentry *dentry, unsigned int flags) diff --git a/fs/remap_range.c b/fs/remap_range.c index 77dba3a49e65..29a4a4dbfe12 100644 --- a/fs/remap_range.c +++ b/fs/remap_range.c @@ -438,7 +438,7 @@ static bool allow_file_dedupe(struct file *file) return true; if (uid_eq(current_fsuid(), file_inode(file)->i_uid)) return true; - if (!inode_permission(file_inode(file), MAY_WRITE)) + if (!inode_permission(&init_user_ns, file_inode(file), MAY_WRITE)) return true; return false; } diff --git a/fs/xattr.c b/fs/xattr.c index fd57153b1f61..56151bd9e642 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -131,7 +131,7 @@ xattr_permission(struct inode *inode, const char *name, int mask) return -EPERM; } - return inode_permission(inode, mask); + return inode_permission(&init_user_ns, inode, mask); } /* diff --git a/include/linux/fs.h b/include/linux/fs.h index bcd17097d441..a85dfe6962df 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2810,15 +2810,17 @@ static inline int bmap(struct inode *inode, sector_t *block) #endif extern int notify_change(struct dentry *, struct iattr *, struct inode **); -extern int inode_permission(struct inode *, int); -extern int generic_permission(struct inode *, int); +int inode_permission(struct user_namespace *, struct inode *, int); +int generic_permission(struct user_namespace *, struct inode *, int); static inline int file_permission(struct file *file, int mask) { - return inode_permission(file_inode(file), mask); + return inode_permission(file_mnt_user_ns(file), + file_inode(file), mask); } static inline int path_permission(const struct path *path, int mask) { - return inode_permission(d_inode(path->dentry), mask); + return inode_permission(mnt_user_ns(path->mnt), + d_inode(path->dentry), mask); } extern int __check_sticky(struct inode *dir, struct inode *inode); diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index 90797f1b421d..85fb4c0c650a 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -15,6 +15,8 @@ #include #include +struct user_namespace; + struct posix_acl_entry { short e_tag; unsigned short e_perm; @@ -61,8 +63,6 @@ posix_acl_release(struct posix_acl *acl) extern void posix_acl_init(struct posix_acl *, int); extern struct posix_acl *posix_acl_alloc(int, gfp_t); -extern int posix_acl_valid(struct user_namespace *, const struct posix_acl *); -extern int posix_acl_permission(struct inode *, const struct posix_acl *, int); extern struct posix_acl *posix_acl_from_mode(umode_t, gfp_t); extern int posix_acl_equiv_mode(const struct posix_acl *, umode_t *); extern int __posix_acl_create(struct posix_acl **, gfp_t, umode_t *); @@ -85,6 +85,9 @@ struct posix_acl *get_cached_acl_rcu(struct inode *inode, int type); void set_cached_acl(struct inode *inode, int type, struct posix_acl *acl); void forget_cached_acl(struct inode *inode, int type); void forget_all_cached_acls(struct inode *inode); +int posix_acl_valid(struct user_namespace *, const struct posix_acl *); +int posix_acl_permission(struct user_namespace *, struct inode *, + const struct posix_acl *, int); static inline void cache_no_acl(struct inode *inode) { diff --git a/ipc/mqueue.c b/ipc/mqueue.c index beff0cfcd1e8..693f01fe1216 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -873,7 +873,7 @@ static int prepare_open(struct dentry *dentry, int oflag, int ro, if ((oflag & O_ACCMODE) == (O_RDWR | O_WRONLY)) return -EINVAL; acc = oflag2acc[oflag & O_ACCMODE]; - return inode_permission(d_inode(dentry), acc); + return inode_permission(&init_user_ns, d_inode(dentry), acc); } static int do_mq_open(const char __user *u_name, int oflag, umode_t mode, diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 8962f139521e..e3226b65f5dc 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -558,7 +558,7 @@ int bpf_obj_get_user(const char __user *pathname, int flags) static struct bpf_prog *__get_prog_inode(struct inode *inode, enum bpf_prog_type type) { struct bpf_prog *prog; - int ret = inode_permission(inode, MAY_READ); + int ret = inode_permission(&init_user_ns, inode, MAY_READ); if (ret) return ERR_PTR(ret); diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 613845769103..091ffb5d2939 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -4670,7 +4670,7 @@ static int cgroup_may_write(const struct cgroup *cgrp, struct super_block *sb) if (!inode) return -ENOMEM; - ret = inode_permission(inode, MAY_WRITE); + ret = inode_permission(&init_user_ns, inode, MAY_WRITE); iput(inode); return ret; } -- cgit v1.2.3 From 21cb47be6fb9ece7e6ee63f6780986faa384a77c Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 21 Jan 2021 14:19:25 +0100 Subject: inode: make init and permission helpers idmapped mount aware The inode_owner_or_capable() helper determines whether the caller is the owner of the inode or is capable with respect to that inode. Allow it to handle idmapped mounts. If the inode is accessed through an idmapped mount it according to the mount's user namespace. Afterwards the checks are identical to non-idmapped mounts. If the initial user namespace is passed nothing changes so non-idmapped mounts will see identical behavior as before. Similarly, allow the inode_init_owner() helper to handle idmapped mounts. It initializes a new inode on idmapped mounts by mapping the fsuid and fsgid of the caller from the mount's user namespace. If the initial user namespace is passed nothing changes so non-idmapped mounts will see identical behavior as before. Link: https://lore.kernel.org/r/20210121131959.646623-7-christian.brauner@ubuntu.com Cc: Christoph Hellwig Cc: David Howells Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig Reviewed-by: James Morris Signed-off-by: Christian Brauner --- fs/9p/acl.c | 2 +- fs/9p/vfs_inode.c | 2 +- fs/attr.c | 6 +++--- fs/bfs/dir.c | 2 +- fs/btrfs/inode.c | 2 +- fs/btrfs/ioctl.c | 10 +++++----- fs/btrfs/tests/btrfs-tests.c | 2 +- fs/crypto/policy.c | 2 +- fs/efivarfs/file.c | 2 +- fs/ext2/ialloc.c | 2 +- fs/ext2/ioctl.c | 6 +++--- fs/ext4/ialloc.c | 2 +- fs/ext4/ioctl.c | 15 ++++++++------- fs/f2fs/file.c | 14 +++++++------- fs/f2fs/namei.c | 2 +- fs/f2fs/xattr.c | 2 +- fs/fcntl.c | 2 +- fs/gfs2/file.c | 2 +- fs/hfsplus/inode.c | 2 +- fs/hfsplus/ioctl.c | 2 +- fs/hugetlbfs/inode.c | 2 +- fs/inode.c | 36 ++++++++++++++++++++++++++---------- fs/jfs/ioctl.c | 2 +- fs/jfs/jfs_inode.c | 2 +- fs/minix/bitmap.c | 2 +- fs/namei.c | 5 +++-- fs/nilfs2/inode.c | 2 +- fs/nilfs2/ioctl.c | 2 +- fs/ocfs2/dlmfs/dlmfs.c | 4 ++-- fs/ocfs2/ioctl.c | 2 +- fs/ocfs2/namei.c | 2 +- fs/omfs/inode.c | 2 +- fs/overlayfs/dir.c | 2 +- fs/overlayfs/file.c | 4 ++-- fs/overlayfs/super.c | 2 +- fs/overlayfs/util.c | 2 +- fs/posix_acl.c | 2 +- fs/ramfs/inode.c | 2 +- fs/reiserfs/ioctl.c | 4 ++-- fs/reiserfs/namei.c | 2 +- fs/sysv/ialloc.c | 2 +- fs/ubifs/dir.c | 2 +- fs/ubifs/ioctl.c | 2 +- fs/udf/ialloc.c | 2 +- fs/ufs/ialloc.c | 2 +- fs/xattr.c | 3 ++- fs/xfs/xfs_ioctl.c | 2 +- fs/zonefs/super.c | 2 +- include/linux/fs.h | 8 ++++---- kernel/bpf/inode.c | 2 +- mm/madvise.c | 3 ++- mm/mincore.c | 3 ++- mm/shmem.c | 2 +- security/selinux/hooks.c | 4 ++-- 54 files changed, 112 insertions(+), 91 deletions(-) (limited to 'include') diff --git a/fs/9p/acl.c b/fs/9p/acl.c index 6261719f6f2a..d77b28e8d57a 100644 --- a/fs/9p/acl.c +++ b/fs/9p/acl.c @@ -258,7 +258,7 @@ static int v9fs_xattr_set_acl(const struct xattr_handler *handler, if (S_ISLNK(inode->i_mode)) return -EOPNOTSUPP; - if (!inode_owner_or_capable(inode)) + if (!inode_owner_or_capable(&init_user_ns, inode)) return -EPERM; if (value) { /* update the cached acl value */ diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 4a937fac1acb..f66eb3c12c8a 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -251,7 +251,7 @@ int v9fs_init_inode(struct v9fs_session_info *v9ses, { int err = 0; - inode_init_owner(inode, NULL, mode); + inode_init_owner(&init_user_ns,inode, NULL, mode); inode->i_blocks = 0; inode->i_rdev = rdev; inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode); diff --git a/fs/attr.c b/fs/attr.c index c9e29e589cec..00ae0b000146 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -87,7 +87,7 @@ int setattr_prepare(struct dentry *dentry, struct iattr *attr) /* Make sure a caller can chmod. */ if (ia_valid & ATTR_MODE) { - if (!inode_owner_or_capable(inode)) + if (!inode_owner_or_capable(&init_user_ns, inode)) return -EPERM; /* Also check the setgid bit! */ if (!in_group_p((ia_valid & ATTR_GID) ? attr->ia_gid : @@ -98,7 +98,7 @@ int setattr_prepare(struct dentry *dentry, struct iattr *attr) /* Check for setting the inode time. */ if (ia_valid & (ATTR_MTIME_SET | ATTR_ATIME_SET | ATTR_TIMES_SET)) { - if (!inode_owner_or_capable(inode)) + if (!inode_owner_or_capable(&init_user_ns, inode)) return -EPERM; } @@ -243,7 +243,7 @@ int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **de if (IS_IMMUTABLE(inode)) return -EPERM; - if (!inode_owner_or_capable(inode)) { + if (!inode_owner_or_capable(&init_user_ns, inode)) { error = inode_permission(&init_user_ns, inode, MAY_WRITE); if (error) diff --git a/fs/bfs/dir.c b/fs/bfs/dir.c index d8dfe3a0cb39..be1335a8d25b 100644 --- a/fs/bfs/dir.c +++ b/fs/bfs/dir.c @@ -96,7 +96,7 @@ static int bfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, } set_bit(ino, info->si_imap); info->si_freei--; - inode_init_owner(inode, dir, mode); + inode_init_owner(&init_user_ns, inode, dir, mode); inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); inode->i_blocks = 0; inode->i_op = &bfs_file_inops; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 512ee2650bbb..07fe8b2f3bab 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -6190,7 +6190,7 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans, if (ret != 0) goto fail_unlock; - inode_init_owner(inode, dir, mode); + inode_init_owner(&init_user_ns, inode, dir, mode); inode_set_bytes(inode, 0); inode->i_mtime = current_time(inode); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 8ced6dfefee4..1f763c60415b 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -213,7 +213,7 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) const char *comp = NULL; u32 binode_flags; - if (!inode_owner_or_capable(inode)) + if (!inode_owner_or_capable(&init_user_ns, inode)) return -EPERM; if (btrfs_root_readonly(root)) @@ -429,7 +429,7 @@ static int btrfs_ioctl_fssetxattr(struct file *file, void __user *arg) unsigned old_i_flags; int ret = 0; - if (!inode_owner_or_capable(inode)) + if (!inode_owner_or_capable(&init_user_ns, inode)) return -EPERM; if (btrfs_root_readonly(root)) @@ -1862,7 +1862,7 @@ static noinline int __btrfs_ioctl_snap_create(struct file *file, btrfs_info(BTRFS_I(file_inode(file))->root->fs_info, "Snapshot src from another FS"); ret = -EXDEV; - } else if (!inode_owner_or_capable(src_inode)) { + } else if (!inode_owner_or_capable(&init_user_ns, src_inode)) { /* * Subvolume creation is not restricted, but snapshots * are limited to own subvolumes only @@ -1982,7 +1982,7 @@ static noinline int btrfs_ioctl_subvol_setflags(struct file *file, u64 flags; int ret = 0; - if (!inode_owner_or_capable(inode)) + if (!inode_owner_or_capable(&init_user_ns, inode)) return -EPERM; ret = mnt_want_write_file(file); @@ -4453,7 +4453,7 @@ static long _btrfs_ioctl_set_received_subvol(struct file *file, int ret = 0; int received_uuid_changed; - if (!inode_owner_or_capable(inode)) + if (!inode_owner_or_capable(&init_user_ns, inode)) return -EPERM; ret = mnt_want_write_file(file); diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c index 6bd97bd4cb37..3a4099a2bf05 100644 --- a/fs/btrfs/tests/btrfs-tests.c +++ b/fs/btrfs/tests/btrfs-tests.c @@ -62,7 +62,7 @@ struct inode *btrfs_new_test_inode(void) BTRFS_I(inode)->location.type = BTRFS_INODE_ITEM_KEY; BTRFS_I(inode)->location.objectid = BTRFS_FIRST_FREE_OBJECTID; BTRFS_I(inode)->location.offset = 0; - inode_init_owner(inode, NULL, S_IFREG); + inode_init_owner(&init_user_ns, inode, NULL, S_IFREG); return inode; } diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c index a51cef6bd27f..ed3d623724cd 100644 --- a/fs/crypto/policy.c +++ b/fs/crypto/policy.c @@ -465,7 +465,7 @@ int fscrypt_ioctl_set_policy(struct file *filp, const void __user *arg) return -EFAULT; policy.version = version; - if (!inode_owner_or_capable(inode)) + if (!inode_owner_or_capable(&init_user_ns, inode)) return -EACCES; ret = mnt_want_write_file(filp); diff --git a/fs/efivarfs/file.c b/fs/efivarfs/file.c index feaa5e182b7b..e6bc0302643b 100644 --- a/fs/efivarfs/file.c +++ b/fs/efivarfs/file.c @@ -137,7 +137,7 @@ efivarfs_ioc_setxflags(struct file *file, void __user *arg) unsigned int oldflags = efivarfs_getflags(inode); int error; - if (!inode_owner_or_capable(inode)) + if (!inode_owner_or_capable(&init_user_ns, inode)) return -EACCES; if (copy_from_user(&flags, arg, sizeof(flags))) diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c index 432c3febea6d..df14e750e9fe 100644 --- a/fs/ext2/ialloc.c +++ b/fs/ext2/ialloc.c @@ -551,7 +551,7 @@ got: inode->i_uid = current_fsuid(); inode->i_gid = dir->i_gid; } else - inode_init_owner(inode, dir, mode); + inode_init_owner(&init_user_ns, inode, dir, mode); inode->i_ino = ino; inode->i_blocks = 0; diff --git a/fs/ext2/ioctl.c b/fs/ext2/ioctl.c index 32a8d10b579d..b399cbb7022d 100644 --- a/fs/ext2/ioctl.c +++ b/fs/ext2/ioctl.c @@ -39,7 +39,7 @@ long ext2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) if (ret) return ret; - if (!inode_owner_or_capable(inode)) { + if (!inode_owner_or_capable(&init_user_ns, inode)) { ret = -EACCES; goto setflags_out; } @@ -84,7 +84,7 @@ setflags_out: case EXT2_IOC_SETVERSION: { __u32 generation; - if (!inode_owner_or_capable(inode)) + if (!inode_owner_or_capable(&init_user_ns, inode)) return -EPERM; ret = mnt_want_write_file(filp); if (ret) @@ -117,7 +117,7 @@ setversion_out: if (!test_opt(inode->i_sb, RESERVATION) ||!S_ISREG(inode->i_mode)) return -ENOTTY; - if (!inode_owner_or_capable(inode)) + if (!inode_owner_or_capable(&init_user_ns, inode)) return -EACCES; if (get_user(rsv_window_size, (int __user *)arg)) diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index b215c564bc31..00c1ec6eee16 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -972,7 +972,7 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir, inode->i_uid = current_fsuid(); inode->i_gid = dir->i_gid; } else - inode_init_owner(inode, dir, mode); + inode_init_owner(&init_user_ns, inode, dir, mode); if (ext4_has_feature_project(sb) && ext4_test_inode_flag(dir, EXT4_INODE_PROJINHERIT)) diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index d9665d2f82db..ab80e2493fdc 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -139,7 +139,8 @@ static long swap_inode_boot_loader(struct super_block *sb, } if (IS_RDONLY(inode) || IS_APPEND(inode) || IS_IMMUTABLE(inode) || - !inode_owner_or_capable(inode) || !capable(CAP_SYS_ADMIN)) { + !inode_owner_or_capable(&init_user_ns, inode) || + !capable(CAP_SYS_ADMIN)) { err = -EPERM; goto journal_err_out; } @@ -829,7 +830,7 @@ static long __ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) case FS_IOC_SETFLAGS: { int err; - if (!inode_owner_or_capable(inode)) + if (!inode_owner_or_capable(&init_user_ns, inode)) return -EACCES; if (get_user(flags, (int __user *) arg)) @@ -871,7 +872,7 @@ static long __ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) __u32 generation; int err; - if (!inode_owner_or_capable(inode)) + if (!inode_owner_or_capable(&init_user_ns, inode)) return -EPERM; if (ext4_has_metadata_csum(inode->i_sb)) { @@ -1010,7 +1011,7 @@ mext_out: case EXT4_IOC_MIGRATE: { int err; - if (!inode_owner_or_capable(inode)) + if (!inode_owner_or_capable(&init_user_ns, inode)) return -EACCES; err = mnt_want_write_file(filp); @@ -1032,7 +1033,7 @@ mext_out: case EXT4_IOC_ALLOC_DA_BLKS: { int err; - if (!inode_owner_or_capable(inode)) + if (!inode_owner_or_capable(&init_user_ns, inode)) return -EACCES; err = mnt_want_write_file(filp); @@ -1217,7 +1218,7 @@ resizefs_out: case EXT4_IOC_CLEAR_ES_CACHE: { - if (!inode_owner_or_capable(inode)) + if (!inode_owner_or_capable(&init_user_ns, inode)) return -EACCES; ext4_clear_inode_es(inode); return 0; @@ -1263,7 +1264,7 @@ resizefs_out: return -EFAULT; /* Make sure caller has proper permission */ - if (!inode_owner_or_capable(inode)) + if (!inode_owner_or_capable(&init_user_ns, inode)) return -EACCES; if (fa.fsx_xflags & ~EXT4_SUPPORTED_FS_XFLAGS) diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index f585545277d7..5fc0ff28b5dd 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -1961,7 +1961,7 @@ static int f2fs_ioc_setflags(struct file *filp, unsigned long arg) u32 iflags; int ret; - if (!inode_owner_or_capable(inode)) + if (!inode_owner_or_capable(&init_user_ns, inode)) return -EACCES; if (get_user(fsflags, (int __user *)arg)) @@ -2008,7 +2008,7 @@ static int f2fs_ioc_start_atomic_write(struct file *filp) struct f2fs_sb_info *sbi = F2FS_I_SB(inode); int ret; - if (!inode_owner_or_capable(inode)) + if (!inode_owner_or_capable(&init_user_ns, inode)) return -EACCES; if (!S_ISREG(inode->i_mode)) @@ -2075,7 +2075,7 @@ static int f2fs_ioc_commit_atomic_write(struct file *filp) struct inode *inode = file_inode(filp); int ret; - if (!inode_owner_or_capable(inode)) + if (!inode_owner_or_capable(&init_user_ns, inode)) return -EACCES; ret = mnt_want_write_file(filp); @@ -2117,7 +2117,7 @@ static int f2fs_ioc_start_volatile_write(struct file *filp) struct inode *inode = file_inode(filp); int ret; - if (!inode_owner_or_capable(inode)) + if (!inode_owner_or_capable(&init_user_ns, inode)) return -EACCES; if (!S_ISREG(inode->i_mode)) @@ -2152,7 +2152,7 @@ static int f2fs_ioc_release_volatile_write(struct file *filp) struct inode *inode = file_inode(filp); int ret; - if (!inode_owner_or_capable(inode)) + if (!inode_owner_or_capable(&init_user_ns, inode)) return -EACCES; ret = mnt_want_write_file(filp); @@ -2181,7 +2181,7 @@ static int f2fs_ioc_abort_volatile_write(struct file *filp) struct inode *inode = file_inode(filp); int ret; - if (!inode_owner_or_capable(inode)) + if (!inode_owner_or_capable(&init_user_ns, inode)) return -EACCES; ret = mnt_want_write_file(filp); @@ -3158,7 +3158,7 @@ static int f2fs_ioc_fssetxattr(struct file *filp, unsigned long arg) return -EFAULT; /* Make sure caller has proper permission */ - if (!inode_owner_or_capable(inode)) + if (!inode_owner_or_capable(&init_user_ns, inode)) return -EACCES; if (fa.fsx_xflags & ~F2FS_SUPPORTED_XFLAGS) diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index 6edb1ab579a1..ad98926bacac 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -46,7 +46,7 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode) nid_free = true; - inode_init_owner(inode, dir, mode); + inode_init_owner(&init_user_ns, inode, dir, mode); inode->i_ino = ino; inode->i_blocks = 0; diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index 65afcc3cc68a..d772bf13a814 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -114,7 +114,7 @@ static int f2fs_xattr_advise_set(const struct xattr_handler *handler, unsigned char old_advise = F2FS_I(inode)->i_advise; unsigned char new_advise; - if (!inode_owner_or_capable(inode)) + if (!inode_owner_or_capable(&init_user_ns, inode)) return -EPERM; if (value == NULL) return -EINVAL; diff --git a/fs/fcntl.c b/fs/fcntl.c index 05b36b28f2e8..74d99731fd43 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -46,7 +46,7 @@ static int setfl(int fd, struct file * filp, unsigned long arg) /* O_NOATIME can only be set by the owner or superuser */ if ((arg & O_NOATIME) && !(filp->f_flags & O_NOATIME)) - if (!inode_owner_or_capable(inode)) + if (!inode_owner_or_capable(&init_user_ns, inode)) return -EPERM; /* required for strict SunOS emulation */ diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index b39b339feddc..1d994bdfffaa 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -238,7 +238,7 @@ static int do_gfs2_set_flags(struct file *filp, u32 reqflags, u32 mask, goto out; error = -EACCES; - if (!inode_owner_or_capable(inode)) + if (!inode_owner_or_capable(&init_user_ns, inode)) goto out; error = 0; diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index e3da9e96b835..21357046b039 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -376,7 +376,7 @@ struct inode *hfsplus_new_inode(struct super_block *sb, struct inode *dir, return NULL; inode->i_ino = sbi->next_cnid++; - inode_init_owner(inode, dir, mode); + inode_init_owner(&init_user_ns, inode, dir, mode); set_nlink(inode, 1); inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); diff --git a/fs/hfsplus/ioctl.c b/fs/hfsplus/ioctl.c index ce15b9496b77..3edb1926d127 100644 --- a/fs/hfsplus/ioctl.c +++ b/fs/hfsplus/ioctl.c @@ -91,7 +91,7 @@ static int hfsplus_ioctl_setflags(struct file *file, int __user *user_flags) if (err) goto out; - if (!inode_owner_or_capable(inode)) { + if (!inode_owner_or_capable(&init_user_ns, inode)) { err = -EACCES; goto out_drop_write; } diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index b5c109703daa..6737929e443c 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -836,7 +836,7 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode); inode->i_ino = get_next_ino(); - inode_init_owner(inode, dir, mode); + inode_init_owner(&init_user_ns, inode, dir, mode); lockdep_set_class(&inode->i_mapping->i_mmap_rwsem, &hugetlbfs_i_mmap_rwsem_key); inode->i_mapping->a_ops = &hugetlbfs_aops; diff --git a/fs/inode.c b/fs/inode.c index cd40cbf87ce4..a9ac97a27784 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -2130,14 +2130,21 @@ EXPORT_SYMBOL(init_special_inode); /** * inode_init_owner - Init uid,gid,mode for new inode according to posix standards + * @mnt_userns: User namespace of the mount the inode was created from * @inode: New inode * @dir: Directory inode * @mode: mode of the new inode + * + * If the inode has been created through an idmapped mount the user namespace of + * the vfsmount must be passed through @mnt_userns. This function will then take + * care to map the inode according to @mnt_userns before checking permissions + * and initializing i_uid and i_gid. On non-idmapped mounts or if permission + * checking is to be performed on the raw inode simply passs init_user_ns. */ -void inode_init_owner(struct inode *inode, const struct inode *dir, - umode_t mode) +void inode_init_owner(struct user_namespace *mnt_userns, struct inode *inode, + const struct inode *dir, umode_t mode) { - inode->i_uid = current_fsuid(); + inode->i_uid = fsuid_into_mnt(mnt_userns); if (dir && dir->i_mode & S_ISGID) { inode->i_gid = dir->i_gid; @@ -2145,32 +2152,41 @@ void inode_init_owner(struct inode *inode, const struct inode *dir, if (S_ISDIR(mode)) mode |= S_ISGID; else if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP) && - !in_group_p(inode->i_gid) && - !capable_wrt_inode_uidgid(&init_user_ns, dir, - CAP_FSETID)) + !in_group_p(i_gid_into_mnt(mnt_userns, dir)) && + !capable_wrt_inode_uidgid(mnt_userns, dir, CAP_FSETID)) mode &= ~S_ISGID; } else - inode->i_gid = current_fsgid(); + inode->i_gid = fsgid_into_mnt(mnt_userns); inode->i_mode = mode; } EXPORT_SYMBOL(inode_init_owner); /** * inode_owner_or_capable - check current task permissions to inode + * @mnt_userns: user namespace of the mount the inode was found from * @inode: inode being checked * * Return true if current either has CAP_FOWNER in a namespace with the * inode owner uid mapped, or owns the file. + * + * If the inode has been found through an idmapped mount the user namespace of + * the vfsmount must be passed through @mnt_userns. This function will then take + * care to map the inode according to @mnt_userns before checking permissions. + * On non-idmapped mounts or if permission checking is to be performed on the + * raw inode simply passs init_user_ns. */ -bool inode_owner_or_capable(const struct inode *inode) +bool inode_owner_or_capable(struct user_namespace *mnt_userns, + const struct inode *inode) { + kuid_t i_uid; struct user_namespace *ns; - if (uid_eq(current_fsuid(), inode->i_uid)) + i_uid = i_uid_into_mnt(mnt_userns, inode); + if (uid_eq(current_fsuid(), i_uid)) return true; ns = current_user_ns(); - if (kuid_has_mapping(ns, inode->i_uid) && ns_capable(ns, CAP_FOWNER)) + if (kuid_has_mapping(ns, i_uid) && ns_capable(ns, CAP_FOWNER)) return true; return false; } diff --git a/fs/jfs/ioctl.c b/fs/jfs/ioctl.c index 10ee0ecca1a8..2581d4db58ff 100644 --- a/fs/jfs/ioctl.c +++ b/fs/jfs/ioctl.c @@ -76,7 +76,7 @@ long jfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) if (err) return err; - if (!inode_owner_or_capable(inode)) { + if (!inode_owner_or_capable(&init_user_ns, inode)) { err = -EACCES; goto setflags_out; } diff --git a/fs/jfs/jfs_inode.c b/fs/jfs/jfs_inode.c index 4cef170630db..59379089e939 100644 --- a/fs/jfs/jfs_inode.c +++ b/fs/jfs/jfs_inode.c @@ -64,7 +64,7 @@ struct inode *ialloc(struct inode *parent, umode_t mode) goto fail_put; } - inode_init_owner(inode, parent, mode); + inode_init_owner(&init_user_ns, inode, parent, mode); /* * New inodes need to save sane values on disk when * uid & gid mount options are used diff --git a/fs/minix/bitmap.c b/fs/minix/bitmap.c index f4e5e5181a14..9115948c624e 100644 --- a/fs/minix/bitmap.c +++ b/fs/minix/bitmap.c @@ -252,7 +252,7 @@ struct inode *minix_new_inode(const struct inode *dir, umode_t mode, int *error) iput(inode); return NULL; } - inode_init_owner(inode, dir, mode); + inode_init_owner(&init_user_ns, inode, dir, mode); inode->i_ino = j; inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); inode->i_blocks = 0; diff --git a/fs/namei.c b/fs/namei.c index d78d74f5f5af..04b001ddade3 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1088,7 +1088,8 @@ int may_linkat(struct path *link) /* Source inode owner (or CAP_FOWNER) can hardlink all they like, * otherwise, it must be a safe source. */ - if (safe_hardlink_source(inode) || inode_owner_or_capable(inode)) + if (safe_hardlink_source(inode) || + inode_owner_or_capable(&init_user_ns, inode)) return 0; audit_log_path_denied(AUDIT_ANOM_LINK, "linkat"); @@ -2940,7 +2941,7 @@ static int may_open(const struct path *path, int acc_mode, int flag) } /* O_NOATIME can only be set by the owner or superuser */ - if (flag & O_NOATIME && !inode_owner_or_capable(inode)) + if (flag & O_NOATIME && !inode_owner_or_capable(&init_user_ns, inode)) return -EPERM; return 0; diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index b6517220cad5..11225a659736 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -348,7 +348,7 @@ struct inode *nilfs_new_inode(struct inode *dir, umode_t mode) /* reference count of i_bh inherits from nilfs_mdt_read_block() */ atomic64_inc(&root->inodes_count); - inode_init_owner(inode, dir, mode); + inode_init_owner(&init_user_ns, inode, dir, mode); inode->i_ino = ino; inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c index 07d26f61f22a..b053b40315bf 100644 --- a/fs/nilfs2/ioctl.c +++ b/fs/nilfs2/ioctl.c @@ -132,7 +132,7 @@ static int nilfs_ioctl_setflags(struct inode *inode, struct file *filp, unsigned int flags, oldflags; int ret; - if (!inode_owner_or_capable(inode)) + if (!inode_owner_or_capable(&init_user_ns, inode)) return -EACCES; if (get_user(flags, (int __user *)argp)) diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c index 583820ec63e2..37c7d03a6284 100644 --- a/fs/ocfs2/dlmfs/dlmfs.c +++ b/fs/ocfs2/dlmfs/dlmfs.c @@ -329,7 +329,7 @@ static struct inode *dlmfs_get_root_inode(struct super_block *sb) if (inode) { inode->i_ino = get_next_ino(); - inode_init_owner(inode, NULL, mode); + inode_init_owner(&init_user_ns, inode, NULL, mode); inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode); inc_nlink(inode); @@ -352,7 +352,7 @@ static struct inode *dlmfs_get_inode(struct inode *parent, return NULL; inode->i_ino = get_next_ino(); - inode_init_owner(inode, parent, mode); + inode_init_owner(&init_user_ns, inode, parent, mode); inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode); ip = DLMFS_I(inode); diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c index 89984172fc4a..50c9b30ee9f6 100644 --- a/fs/ocfs2/ioctl.c +++ b/fs/ocfs2/ioctl.c @@ -96,7 +96,7 @@ static int ocfs2_set_inode_attr(struct inode *inode, unsigned flags, } status = -EACCES; - if (!inode_owner_or_capable(inode)) + if (!inode_owner_or_capable(&init_user_ns, inode)) goto bail_unlock; if (!S_ISDIR(inode->i_mode)) diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index 2a237ab00453..908b79e1082b 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -198,7 +198,7 @@ static struct inode *ocfs2_get_init_inode(struct inode *dir, umode_t mode) * callers. */ if (S_ISDIR(mode)) set_nlink(inode, 2); - inode_init_owner(inode, dir, mode); + inode_init_owner(&init_user_ns, inode, dir, mode); status = dquot_initialize(inode); if (status) return ERR_PTR(status); diff --git a/fs/omfs/inode.c b/fs/omfs/inode.c index ce93ccca8639..2a0e83236c01 100644 --- a/fs/omfs/inode.c +++ b/fs/omfs/inode.c @@ -48,7 +48,7 @@ struct inode *omfs_new_inode(struct inode *dir, umode_t mode) goto fail; inode->i_ino = new_block; - inode_init_owner(inode, NULL, mode); + inode_init_owner(&init_user_ns, inode, NULL, mode); inode->i_mapping->a_ops = &omfs_aops; inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode); diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 28a075b5f5b2..98a23353b19a 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -636,7 +636,7 @@ static int ovl_create_object(struct dentry *dentry, int mode, dev_t rdev, inode->i_state |= I_CREATING; spin_unlock(&inode->i_lock); - inode_init_owner(inode, dentry->d_parent->d_inode, mode); + inode_init_owner(&init_user_ns, inode, dentry->d_parent->d_inode, mode); attr.mode = inode->i_mode; err = ovl_create_or_link(dentry, inode, &attr, false); diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index b2948e7b3210..7d8b84c715b3 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -54,7 +54,7 @@ static struct file *ovl_open_realfile(const struct file *file, if (err) { realfile = ERR_PTR(err); } else { - if (!inode_owner_or_capable(realinode)) + if (!inode_owner_or_capable(&init_user_ns, realinode)) flags &= ~O_NOATIME; realfile = open_with_fake_path(&file->f_path, flags, realinode, @@ -520,7 +520,7 @@ static long ovl_ioctl_set_flags(struct file *file, unsigned int cmd, long ret; struct inode *inode = file_inode(file); - if (!inode_owner_or_capable(inode)) + if (!inode_owner_or_capable(&init_user_ns, inode)) return -EACCES; ret = mnt_want_write_file(file); diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 88d877787770..3e925deaa19a 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -1005,7 +1005,7 @@ ovl_posix_acl_xattr_set(const struct xattr_handler *handler, goto out_acl_release; } err = -EPERM; - if (!inode_owner_or_capable(inode)) + if (!inode_owner_or_capable(&init_user_ns, inode)) goto out_acl_release; posix_acl_release(acl); diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c index de5c2047a0e9..06013b7b1e87 100644 --- a/fs/overlayfs/util.c +++ b/fs/overlayfs/util.c @@ -484,7 +484,7 @@ struct file *ovl_path_open(struct path *path, int flags) return ERR_PTR(err); /* O_NOATIME is an optimization, don't fail if not permitted */ - if (inode_owner_or_capable(inode)) + if (inode_owner_or_capable(&init_user_ns, inode)) flags |= O_NOATIME; return dentry_open(path, flags, current_cred()); diff --git a/fs/posix_acl.c b/fs/posix_acl.c index 5d9fe2fb2953..9ce8214bfdac 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -874,7 +874,7 @@ set_posix_acl(struct inode *inode, int type, struct posix_acl *acl) if (type == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode)) return acl ? -EACCES : 0; - if (!inode_owner_or_capable(inode)) + if (!inode_owner_or_capable(&init_user_ns, inode)) return -EPERM; if (acl) { diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c index ee179a81b3da..3fd4326f36b5 100644 --- a/fs/ramfs/inode.c +++ b/fs/ramfs/inode.c @@ -67,7 +67,7 @@ struct inode *ramfs_get_inode(struct super_block *sb, if (inode) { inode->i_ino = get_next_ino(); - inode_init_owner(inode, dir, mode); + inode_init_owner(&init_user_ns, inode, dir, mode); inode->i_mapping->a_ops = &ramfs_aops; mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER); mapping_set_unevictable(inode->i_mapping); diff --git a/fs/reiserfs/ioctl.c b/fs/reiserfs/ioctl.c index adb21bea3d60..4f1cbd930179 100644 --- a/fs/reiserfs/ioctl.c +++ b/fs/reiserfs/ioctl.c @@ -59,7 +59,7 @@ long reiserfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) if (err) break; - if (!inode_owner_or_capable(inode)) { + if (!inode_owner_or_capable(&init_user_ns, inode)) { err = -EPERM; goto setflags_out; } @@ -101,7 +101,7 @@ setflags_out: err = put_user(inode->i_generation, (int __user *)arg); break; case REISERFS_IOC_SETVERSION: - if (!inode_owner_or_capable(inode)) { + if (!inode_owner_or_capable(&init_user_ns, inode)) { err = -EPERM; break; } diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c index 1594687582f0..a67a7d371725 100644 --- a/fs/reiserfs/namei.c +++ b/fs/reiserfs/namei.c @@ -615,7 +615,7 @@ static int new_inode_init(struct inode *inode, struct inode *dir, umode_t mode) * the quota init calls have to know who to charge the quota to, so * we have to set uid and gid here */ - inode_init_owner(inode, dir, mode); + inode_init_owner(&init_user_ns, inode, dir, mode); return dquot_initialize(inode); } diff --git a/fs/sysv/ialloc.c b/fs/sysv/ialloc.c index 6c9801986af6..50df794a3c1f 100644 --- a/fs/sysv/ialloc.c +++ b/fs/sysv/ialloc.c @@ -163,7 +163,7 @@ struct inode * sysv_new_inode(const struct inode * dir, umode_t mode) *sbi->s_sb_fic_count = cpu_to_fs16(sbi, count); fs16_add(sbi, sbi->s_sb_total_free_inodes, -1); dirty_sb(sb); - inode_init_owner(inode, dir, mode); + inode_init_owner(&init_user_ns, inode, dir, mode); inode->i_ino = fs16_to_cpu(sbi, ino); inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); inode->i_blocks = 0; diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index 9a6b8660425a..694e7714545b 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -94,7 +94,7 @@ struct inode *ubifs_new_inode(struct ubifs_info *c, struct inode *dir, */ inode->i_flags |= S_NOCMTIME; - inode_init_owner(inode, dir, mode); + inode_init_owner(&init_user_ns, inode, dir, mode); inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); inode->i_mapping->nrpages = 0; diff --git a/fs/ubifs/ioctl.c b/fs/ubifs/ioctl.c index 4363d85a3fd4..2326d5122beb 100644 --- a/fs/ubifs/ioctl.c +++ b/fs/ubifs/ioctl.c @@ -155,7 +155,7 @@ long ubifs_ioctl(struct file *file, unsigned int cmd, unsigned long arg) if (IS_RDONLY(inode)) return -EROFS; - if (!inode_owner_or_capable(inode)) + if (!inode_owner_or_capable(&init_user_ns, inode)) return -EACCES; if (get_user(flags, (int __user *) arg)) diff --git a/fs/udf/ialloc.c b/fs/udf/ialloc.c index 84ed23edebfd..2ecf0e87660e 100644 --- a/fs/udf/ialloc.c +++ b/fs/udf/ialloc.c @@ -103,7 +103,7 @@ struct inode *udf_new_inode(struct inode *dir, umode_t mode) mutex_unlock(&sbi->s_alloc_mutex); } - inode_init_owner(inode, dir, mode); + inode_init_owner(&init_user_ns, inode, dir, mode); if (UDF_QUERY_FLAG(sb, UDF_FLAG_UID_SET)) inode->i_uid = sbi->s_uid; if (UDF_QUERY_FLAG(sb, UDF_FLAG_GID_SET)) diff --git a/fs/ufs/ialloc.c b/fs/ufs/ialloc.c index 969fd60436d3..7e3e08c0166f 100644 --- a/fs/ufs/ialloc.c +++ b/fs/ufs/ialloc.c @@ -289,7 +289,7 @@ cg_found: ufs_mark_sb_dirty(sb); inode->i_ino = cg * uspi->s_ipg + bit; - inode_init_owner(inode, dir, mode); + inode_init_owner(&init_user_ns, inode, dir, mode); inode->i_blocks = 0; inode->i_generation = 0; inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); diff --git a/fs/xattr.c b/fs/xattr.c index 56151bd9e642..c669922e1bde 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -127,7 +127,8 @@ xattr_permission(struct inode *inode, const char *name, int mask) if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode)) return (mask & MAY_WRITE) ? -EPERM : -ENODATA; if (S_ISDIR(inode->i_mode) && (inode->i_mode & S_ISVTX) && - (mask & MAY_WRITE) && !inode_owner_or_capable(inode)) + (mask & MAY_WRITE) && + !inode_owner_or_capable(&init_user_ns, inode)) return -EPERM; } diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 97bd29fc8c43..218e80afc859 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1300,7 +1300,7 @@ xfs_ioctl_setattr_get_trans( * The user ID of the calling process must be equal to the file owner * ID, except in cases where the CAP_FSETID capability is applicable. */ - if (!inode_owner_or_capable(VFS_I(ip))) { + if (!inode_owner_or_capable(&init_user_ns, VFS_I(ip))) { error = -EPERM; goto out_cancel; } diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index bec47f2d074b..569525ee8f69 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -1223,7 +1223,7 @@ static void zonefs_init_dir_inode(struct inode *parent, struct inode *inode, struct super_block *sb = parent->i_sb; inode->i_ino = blkdev_nr_zones(sb->s_bdev->bd_disk) + type + 1; - inode_init_owner(inode, parent, S_IFDIR | 0555); + inode_init_owner(&init_user_ns, inode, parent, S_IFDIR | 0555); inode->i_op = &zonefs_dir_inode_operations; inode->i_fop = &simple_dir_operations; set_nlink(inode, 2); diff --git a/include/linux/fs.h b/include/linux/fs.h index a85dfe6962df..2a9d4af6a64d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1762,8 +1762,8 @@ static inline bool sb_start_intwrite_trylock(struct super_block *sb) return __sb_start_write_trylock(sb, SB_FREEZE_FS); } - -extern bool inode_owner_or_capable(const struct inode *inode); +bool inode_owner_or_capable(struct user_namespace *mnt_userns, + const struct inode *inode); /* * VFS helper functions.. @@ -1805,8 +1805,8 @@ extern long compat_ptr_ioctl(struct file *file, unsigned int cmd, /* * VFS file helper functions. */ -extern void inode_init_owner(struct inode *inode, const struct inode *dir, - umode_t mode); +void inode_init_owner(struct user_namespace *mnt_userns, struct inode *inode, + const struct inode *dir, umode_t mode); extern bool may_open_dev(const struct path *path); /* diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index e3226b65f5dc..05b1f51d15e0 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -122,7 +122,7 @@ static struct inode *bpf_get_inode(struct super_block *sb, inode->i_mtime = inode->i_atime; inode->i_ctime = inode->i_atime; - inode_init_owner(inode, dir, mode); + inode_init_owner(&init_user_ns, inode, dir, mode); return inode; } diff --git a/mm/madvise.c b/mm/madvise.c index 175c5582d8a9..d4f5eece9d56 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -539,7 +539,8 @@ static inline bool can_do_pageout(struct vm_area_struct *vma) * otherwise we'd be including shared non-exclusive mappings, which * opens a side channel. */ - return inode_owner_or_capable(file_inode(vma->vm_file)) || + return inode_owner_or_capable(&init_user_ns, + file_inode(vma->vm_file)) || file_permission(vma->vm_file, MAY_WRITE) == 0; } diff --git a/mm/mincore.c b/mm/mincore.c index 7bdb4673f776..9122676b54d6 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -166,7 +166,8 @@ static inline bool can_do_mincore(struct vm_area_struct *vma) * for writing; otherwise we'd be including shared non-exclusive * mappings, which opens a side channel. */ - return inode_owner_or_capable(file_inode(vma->vm_file)) || + return inode_owner_or_capable(&init_user_ns, + file_inode(vma->vm_file)) || file_permission(vma->vm_file, MAY_WRITE) == 0; } diff --git a/mm/shmem.c b/mm/shmem.c index 7c6b6d8f6c39..1c68c9edba5e 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2303,7 +2303,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode inode = new_inode(sb); if (inode) { inode->i_ino = ino; - inode_init_owner(inode, dir, mode); + inode_init_owner(&init_user_ns, inode, dir, mode); inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode); inode->i_generation = prandom_u32(); diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 644b17ec9e63..9d6d3da2caf2 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -3140,13 +3140,13 @@ static int selinux_inode_setxattr(struct dentry *dentry, const char *name, } if (!selinux_initialized(&selinux_state)) - return (inode_owner_or_capable(inode) ? 0 : -EPERM); + return (inode_owner_or_capable(&init_user_ns, inode) ? 0 : -EPERM); sbsec = inode->i_sb->s_security; if (!(sbsec->flags & SBLABEL_MNT)) return -EOPNOTSUPP; - if (!inode_owner_or_capable(inode)) + if (!inode_owner_or_capable(&init_user_ns, inode)) return -EPERM; ad.type = LSM_AUDIT_DATA_DENTRY; -- cgit v1.2.3 From 2f221d6f7b881d95de1f356a3097d755ab1e47d4 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 21 Jan 2021 14:19:26 +0100 Subject: attr: handle idmapped mounts When file attributes are changed most filesystems rely on the setattr_prepare(), setattr_copy(), and notify_change() helpers for initialization and permission checking. Let them handle idmapped mounts. If the inode is accessed through an idmapped mount map it into the mount's user namespace. Afterwards the checks are identical to non-idmapped mounts. If the initial user namespace is passed nothing changes so non-idmapped mounts will see identical behavior as before. Helpers that perform checks on the ia_uid and ia_gid fields in struct iattr assume that ia_uid and ia_gid are intended values and have already been mapped correctly at the userspace-kernelspace boundary as we already do today. If the initial user namespace is passed nothing changes so non-idmapped mounts will see identical behavior as before. Link: https://lore.kernel.org/r/20210121131959.646623-8-christian.brauner@ubuntu.com Cc: Christoph Hellwig Cc: David Howells Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig Signed-off-by: Christian Brauner --- arch/powerpc/platforms/cell/spufs/inode.c | 2 +- drivers/base/devtmpfs.c | 4 +- fs/9p/vfs_inode.c | 4 +- fs/9p/vfs_inode_dotl.c | 4 +- fs/adfs/inode.c | 2 +- fs/affs/inode.c | 4 +- fs/attr.c | 119 ++++++++++++++++++++++-------- fs/btrfs/inode.c | 4 +- fs/cachefiles/interface.c | 4 +- fs/ceph/inode.c | 2 +- fs/cifs/inode.c | 8 +- fs/ecryptfs/inode.c | 7 +- fs/exfat/file.c | 4 +- fs/ext2/inode.c | 4 +- fs/ext4/inode.c | 4 +- fs/f2fs/file.c | 10 ++- fs/fat/file.c | 4 +- fs/fuse/dir.c | 2 +- fs/gfs2/inode.c | 4 +- fs/hfs/inode.c | 4 +- fs/hfsplus/inode.c | 4 +- fs/hostfs/hostfs_kern.c | 4 +- fs/hpfs/inode.c | 4 +- fs/hugetlbfs/inode.c | 4 +- fs/inode.c | 2 +- fs/jffs2/fs.c | 2 +- fs/jfs/file.c | 4 +- fs/kernfs/inode.c | 4 +- fs/libfs.c | 4 +- fs/minix/file.c | 4 +- fs/nfsd/nfsproc.c | 2 +- fs/nfsd/vfs.c | 4 +- fs/nilfs2/inode.c | 4 +- fs/ntfs/inode.c | 2 +- fs/ocfs2/dlmfs/dlmfs.c | 4 +- fs/ocfs2/file.c | 4 +- fs/omfs/file.c | 4 +- fs/open.c | 8 +- fs/orangefs/inode.c | 4 +- fs/overlayfs/copy_up.c | 8 +- fs/overlayfs/dir.c | 2 +- fs/overlayfs/inode.c | 4 +- fs/overlayfs/super.c | 2 +- fs/proc/base.c | 4 +- fs/proc/generic.c | 4 +- fs/proc/proc_sysctl.c | 4 +- fs/ramfs/file-nommu.c | 4 +- fs/reiserfs/inode.c | 4 +- fs/sysv/file.c | 4 +- fs/ubifs/file.c | 2 +- fs/udf/file.c | 4 +- fs/ufs/inode.c | 4 +- fs/utimes.c | 3 +- fs/xfs/xfs_iops.c | 2 +- fs/zonefs/super.c | 4 +- include/linux/fs.h | 8 +- mm/shmem.c | 4 +- 57 files changed, 206 insertions(+), 137 deletions(-) (limited to 'include') diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index 25390569e24c..3de526eb2275 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -98,7 +98,7 @@ spufs_setattr(struct dentry *dentry, struct iattr *attr) if ((attr->ia_valid & ATTR_SIZE) && (attr->ia_size != inode->i_size)) return -EINVAL; - setattr_copy(inode, attr); + setattr_copy(&init_user_ns, inode, attr); mark_inode_dirty(inode); return 0; } diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c index eac184e6d657..2e0c3cdb4184 100644 --- a/drivers/base/devtmpfs.c +++ b/drivers/base/devtmpfs.c @@ -221,7 +221,7 @@ static int handle_create(const char *nodename, umode_t mode, kuid_t uid, newattrs.ia_gid = gid; newattrs.ia_valid = ATTR_MODE|ATTR_UID|ATTR_GID; inode_lock(d_inode(dentry)); - notify_change(dentry, &newattrs, NULL); + notify_change(&init_user_ns, dentry, &newattrs, NULL); inode_unlock(d_inode(dentry)); /* mark as kernel-created inode */ @@ -328,7 +328,7 @@ static int handle_remove(const char *nodename, struct device *dev) newattrs.ia_valid = ATTR_UID|ATTR_GID|ATTR_MODE; inode_lock(d_inode(dentry)); - notify_change(dentry, &newattrs, NULL); + notify_change(&init_user_ns, dentry, &newattrs, NULL); inode_unlock(d_inode(dentry)); err = vfs_unlink(d_inode(parent.dentry), dentry, NULL); if (!err || err == -ENOENT) diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index f66eb3c12c8a..9c3ff6e9ab82 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -1062,7 +1062,7 @@ static int v9fs_vfs_setattr(struct dentry *dentry, struct iattr *iattr) struct p9_wstat wstat; p9_debug(P9_DEBUG_VFS, "\n"); - retval = setattr_prepare(dentry, iattr); + retval = setattr_prepare(&init_user_ns, dentry, iattr); if (retval) return retval; @@ -1118,7 +1118,7 @@ static int v9fs_vfs_setattr(struct dentry *dentry, struct iattr *iattr) v9fs_invalidate_inode_attr(d_inode(dentry)); - setattr_copy(d_inode(dentry), iattr); + setattr_copy(&init_user_ns, d_inode(dentry), iattr); mark_inode_dirty(d_inode(dentry)); return 0; } diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index 823c2eb5f1bf..302553101fcb 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -549,7 +549,7 @@ int v9fs_vfs_setattr_dotl(struct dentry *dentry, struct iattr *iattr) p9_debug(P9_DEBUG_VFS, "\n"); - retval = setattr_prepare(dentry, iattr); + retval = setattr_prepare(&init_user_ns, dentry, iattr); if (retval) return retval; @@ -590,7 +590,7 @@ int v9fs_vfs_setattr_dotl(struct dentry *dentry, struct iattr *iattr) truncate_setsize(inode, iattr->ia_size); v9fs_invalidate_inode_attr(inode); - setattr_copy(inode, iattr); + setattr_copy(&init_user_ns, inode, iattr); mark_inode_dirty(inode); if (iattr->ia_valid & ATTR_MODE) { /* We also want to update ACL when we update mode bits */ diff --git a/fs/adfs/inode.c b/fs/adfs/inode.c index 32620f4a7623..278dcee6ae22 100644 --- a/fs/adfs/inode.c +++ b/fs/adfs/inode.c @@ -299,7 +299,7 @@ adfs_notify_change(struct dentry *dentry, struct iattr *attr) unsigned int ia_valid = attr->ia_valid; int error; - error = setattr_prepare(dentry, attr); + error = setattr_prepare(&init_user_ns, dentry, attr); /* * we can't change the UID or GID of any file - diff --git a/fs/affs/inode.c b/fs/affs/inode.c index 044412110b52..767e5bdfb703 100644 --- a/fs/affs/inode.c +++ b/fs/affs/inode.c @@ -223,7 +223,7 @@ affs_notify_change(struct dentry *dentry, struct iattr *attr) pr_debug("notify_change(%lu,0x%x)\n", inode->i_ino, attr->ia_valid); - error = setattr_prepare(dentry, attr); + error = setattr_prepare(&init_user_ns, dentry, attr); if (error) goto out; @@ -249,7 +249,7 @@ affs_notify_change(struct dentry *dentry, struct iattr *attr) affs_truncate(inode); } - setattr_copy(inode, attr); + setattr_copy(&init_user_ns, inode, attr); mark_inode_dirty(inode); if (attr->ia_valid & ATTR_MODE) diff --git a/fs/attr.c b/fs/attr.c index 00ae0b000146..f4543d2abdfb 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -18,27 +18,55 @@ #include #include -static bool chown_ok(const struct inode *inode, kuid_t uid) +/** + * chown_ok - verify permissions to chown inode + * @mnt_userns: user namespace of the mount @inode was found from + * @inode: inode to check permissions on + * @uid: uid to chown @inode to + * + * If the inode has been found through an idmapped mount the user namespace of + * the vfsmount must be passed through @mnt_userns. This function will then + * take care to map the inode according to @mnt_userns before checking + * permissions. On non-idmapped mounts or if permission checking is to be + * performed on the raw inode simply passs init_user_ns. + */ +static bool chown_ok(struct user_namespace *mnt_userns, + const struct inode *inode, + kuid_t uid) { - if (uid_eq(current_fsuid(), inode->i_uid) && - uid_eq(uid, inode->i_uid)) + kuid_t kuid = i_uid_into_mnt(mnt_userns, inode); + if (uid_eq(current_fsuid(), kuid) && uid_eq(uid, kuid)) return true; - if (capable_wrt_inode_uidgid(&init_user_ns, inode, CAP_CHOWN)) + if (capable_wrt_inode_uidgid(mnt_userns, inode, CAP_CHOWN)) return true; - if (uid_eq(inode->i_uid, INVALID_UID) && + if (uid_eq(kuid, INVALID_UID) && ns_capable(inode->i_sb->s_user_ns, CAP_CHOWN)) return true; return false; } -static bool chgrp_ok(const struct inode *inode, kgid_t gid) +/** + * chgrp_ok - verify permissions to chgrp inode + * @mnt_userns: user namespace of the mount @inode was found from + * @inode: inode to check permissions on + * @gid: gid to chown @inode to + * + * If the inode has been found through an idmapped mount the user namespace of + * the vfsmount must be passed through @mnt_userns. This function will then + * take care to map the inode according to @mnt_userns before checking + * permissions. On non-idmapped mounts or if permission checking is to be + * performed on the raw inode simply passs init_user_ns. + */ +static bool chgrp_ok(struct user_namespace *mnt_userns, + const struct inode *inode, kgid_t gid) { - if (uid_eq(current_fsuid(), inode->i_uid) && - (in_group_p(gid) || gid_eq(gid, inode->i_gid))) + kgid_t kgid = i_gid_into_mnt(mnt_userns, inode); + if (uid_eq(current_fsuid(), i_uid_into_mnt(mnt_userns, inode)) && + (in_group_p(gid) || gid_eq(gid, kgid))) return true; - if (capable_wrt_inode_uidgid(&init_user_ns, inode, CAP_CHOWN)) + if (capable_wrt_inode_uidgid(mnt_userns, inode, CAP_CHOWN)) return true; - if (gid_eq(inode->i_gid, INVALID_GID) && + if (gid_eq(kgid, INVALID_GID) && ns_capable(inode->i_sb->s_user_ns, CAP_CHOWN)) return true; return false; @@ -46,6 +74,7 @@ static bool chgrp_ok(const struct inode *inode, kgid_t gid) /** * setattr_prepare - check if attribute changes to a dentry are allowed + * @mnt_userns: user namespace of the mount the inode was found from * @dentry: dentry to check * @attr: attributes to change * @@ -55,10 +84,17 @@ static bool chgrp_ok(const struct inode *inode, kgid_t gid) * SGID bit from mode if user is not allowed to set it. Also file capabilities * and IMA extended attributes are cleared if ATTR_KILL_PRIV is set. * + * If the inode has been found through an idmapped mount the user namespace of + * the vfsmount must be passed through @mnt_userns. This function will then + * take care to map the inode according to @mnt_userns before checking + * permissions. On non-idmapped mounts or if permission checking is to be + * performed on the raw inode simply passs init_user_ns. + * * Should be called as the first thing in ->setattr implementations, * possibly after taking additional locks. */ -int setattr_prepare(struct dentry *dentry, struct iattr *attr) +int setattr_prepare(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *attr) { struct inode *inode = d_inode(dentry); unsigned int ia_valid = attr->ia_valid; @@ -78,27 +114,27 @@ int setattr_prepare(struct dentry *dentry, struct iattr *attr) goto kill_priv; /* Make sure a caller can chown. */ - if ((ia_valid & ATTR_UID) && !chown_ok(inode, attr->ia_uid)) + if ((ia_valid & ATTR_UID) && !chown_ok(mnt_userns, inode, attr->ia_uid)) return -EPERM; /* Make sure caller can chgrp. */ - if ((ia_valid & ATTR_GID) && !chgrp_ok(inode, attr->ia_gid)) + if ((ia_valid & ATTR_GID) && !chgrp_ok(mnt_userns, inode, attr->ia_gid)) return -EPERM; /* Make sure a caller can chmod. */ if (ia_valid & ATTR_MODE) { - if (!inode_owner_or_capable(&init_user_ns, inode)) + if (!inode_owner_or_capable(mnt_userns, inode)) return -EPERM; /* Also check the setgid bit! */ - if (!in_group_p((ia_valid & ATTR_GID) ? attr->ia_gid : - inode->i_gid) && - !capable_wrt_inode_uidgid(&init_user_ns, inode, CAP_FSETID)) + if (!in_group_p((ia_valid & ATTR_GID) ? attr->ia_gid : + i_gid_into_mnt(mnt_userns, inode)) && + !capable_wrt_inode_uidgid(mnt_userns, inode, CAP_FSETID)) attr->ia_mode &= ~S_ISGID; } /* Check for setting the inode time. */ if (ia_valid & (ATTR_MTIME_SET | ATTR_ATIME_SET | ATTR_TIMES_SET)) { - if (!inode_owner_or_capable(&init_user_ns, inode)) + if (!inode_owner_or_capable(mnt_userns, inode)) return -EPERM; } @@ -162,20 +198,33 @@ EXPORT_SYMBOL(inode_newsize_ok); /** * setattr_copy - copy simple metadata updates into the generic inode + * @mnt_userns: user namespace of the mount the inode was found from * @inode: the inode to be updated * @attr: the new attributes * * setattr_copy must be called with i_mutex held. * * setattr_copy updates the inode's metadata with that specified - * in attr. Noticeably missing is inode size update, which is more complex + * in attr on idmapped mounts. If file ownership is changed setattr_copy + * doesn't map ia_uid and ia_gid. It will asssume the caller has already + * provided the intended values. Necessary permission checks to determine + * whether or not the S_ISGID property needs to be removed are performed with + * the correct idmapped mount permission helpers. + * Noticeably missing is inode size update, which is more complex * as it requires pagecache updates. * + * If the inode has been found through an idmapped mount the user namespace of + * the vfsmount must be passed through @mnt_userns. This function will then + * take care to map the inode according to @mnt_userns before checking + * permissions. On non-idmapped mounts or if permission checking is to be + * performed on the raw inode simply passs init_user_ns. + * * The inode is not marked as dirty after this operation. The rationale is * that for "simple" filesystems, the struct inode is the inode storage. * The caller is free to mark the inode dirty afterwards if needed. */ -void setattr_copy(struct inode *inode, const struct iattr *attr) +void setattr_copy(struct user_namespace *mnt_userns, struct inode *inode, + const struct iattr *attr) { unsigned int ia_valid = attr->ia_valid; @@ -191,9 +240,9 @@ void setattr_copy(struct inode *inode, const struct iattr *attr) inode->i_ctime = attr->ia_ctime; if (ia_valid & ATTR_MODE) { umode_t mode = attr->ia_mode; - - if (!in_group_p(inode->i_gid) && - !capable_wrt_inode_uidgid(&init_user_ns, inode, CAP_FSETID)) + kgid_t kgid = i_gid_into_mnt(mnt_userns, inode); + if (!in_group_p(kgid) && + !capable_wrt_inode_uidgid(mnt_userns, inode, CAP_FSETID)) mode &= ~S_ISGID; inode->i_mode = mode; } @@ -202,6 +251,7 @@ EXPORT_SYMBOL(setattr_copy); /** * notify_change - modify attributes of a filesytem object + * @mnt_userns: user namespace of the mount the inode was found from * @dentry: object affected * @attr: new attributes * @delegated_inode: returns inode, if the inode is delegated @@ -214,13 +264,23 @@ EXPORT_SYMBOL(setattr_copy); * retry. Because breaking a delegation may take a long time, the * caller should drop the i_mutex before doing so. * + * If file ownership is changed notify_change() doesn't map ia_uid and + * ia_gid. It will asssume the caller has already provided the intended values. + * * Alternatively, a caller may pass NULL for delegated_inode. This may * be appropriate for callers that expect the underlying filesystem not * to be NFS exported. Also, passing NULL is fine for callers holding * the file open for write, as there can be no conflicting delegation in * that case. + * + * If the inode has been found through an idmapped mount the user namespace of + * the vfsmount must be passed through @mnt_userns. This function will then + * take care to map the inode according to @mnt_userns before checking + * permissions. On non-idmapped mounts or if permission checking is to be + * performed on the raw inode simply passs init_user_ns. */ -int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **delegated_inode) +int notify_change(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *attr, struct inode **delegated_inode) { struct inode *inode = dentry->d_inode; umode_t mode = inode->i_mode; @@ -243,9 +303,8 @@ int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **de if (IS_IMMUTABLE(inode)) return -EPERM; - if (!inode_owner_or_capable(&init_user_ns, inode)) { - error = inode_permission(&init_user_ns, inode, - MAY_WRITE); + if (!inode_owner_or_capable(mnt_userns, inode)) { + error = inode_permission(mnt_userns, inode, MAY_WRITE); if (error) return error; } @@ -321,9 +380,11 @@ int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **de /* Don't allow modifications of files with invalid uids or * gids unless those uids & gids are being made valid. */ - if (!(ia_valid & ATTR_UID) && !uid_valid(inode->i_uid)) + if (!(ia_valid & ATTR_UID) && + !uid_valid(i_uid_into_mnt(mnt_userns, inode))) return -EOVERFLOW; - if (!(ia_valid & ATTR_GID) && !gid_valid(inode->i_gid)) + if (!(ia_valid & ATTR_GID) && + !gid_valid(i_gid_into_mnt(mnt_userns, inode))) return -EOVERFLOW; error = security_inode_setattr(dentry, attr); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 07fe8b2f3bab..792191a8705b 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -5054,7 +5054,7 @@ static int btrfs_setattr(struct dentry *dentry, struct iattr *attr) if (btrfs_root_readonly(root)) return -EROFS; - err = setattr_prepare(dentry, attr); + err = setattr_prepare(&init_user_ns, dentry, attr); if (err) return err; @@ -5065,7 +5065,7 @@ static int btrfs_setattr(struct dentry *dentry, struct iattr *attr) } if (attr->ia_valid) { - setattr_copy(inode, attr); + setattr_copy(&init_user_ns, inode, attr); inode_inc_iversion(inode); err = btrfs_dirty_inode(inode); diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c index 4cea5fbf695e..5efa6a3702c0 100644 --- a/fs/cachefiles/interface.c +++ b/fs/cachefiles/interface.c @@ -470,14 +470,14 @@ static int cachefiles_attr_changed(struct fscache_object *_object) _debug("discard tail %llx", oi_size); newattrs.ia_valid = ATTR_SIZE; newattrs.ia_size = oi_size & PAGE_MASK; - ret = notify_change(object->backer, &newattrs, NULL); + ret = notify_change(&init_user_ns, object->backer, &newattrs, NULL); if (ret < 0) goto truncate_failed; } newattrs.ia_valid = ATTR_SIZE; newattrs.ia_size = ni_size; - ret = notify_change(object->backer, &newattrs, NULL); + ret = notify_change(&init_user_ns, object->backer, &newattrs, NULL); truncate_failed: inode_unlock(d_inode(object->backer)); diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index e8a15ee09bc1..285d3baca27e 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -2247,7 +2247,7 @@ int ceph_setattr(struct dentry *dentry, struct iattr *attr) if (ceph_snap(inode) != CEPH_NOSNAP) return -EROFS; - err = setattr_prepare(dentry, attr); + err = setattr_prepare(&init_user_ns, dentry, attr); if (err != 0) return err; diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index a83b3a8ffaac..27554f71f744 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -2610,7 +2610,7 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs) if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM) attrs->ia_valid |= ATTR_FORCE; - rc = setattr_prepare(direntry, attrs); + rc = setattr_prepare(&init_user_ns, direntry, attrs); if (rc < 0) goto out; @@ -2715,7 +2715,7 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs) attrs->ia_size != i_size_read(inode)) truncate_setsize(inode, attrs->ia_size); - setattr_copy(inode, attrs); + setattr_copy(&init_user_ns, inode, attrs); mark_inode_dirty(inode); /* force revalidate when any of these times are set since some @@ -2757,7 +2757,7 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs) if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM) attrs->ia_valid |= ATTR_FORCE; - rc = setattr_prepare(direntry, attrs); + rc = setattr_prepare(&init_user_ns, direntry, attrs); if (rc < 0) { free_xid(xid); return rc; @@ -2913,7 +2913,7 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs) attrs->ia_size != i_size_read(inode)) truncate_setsize(inode, attrs->ia_size); - setattr_copy(inode, attrs); + setattr_copy(&init_user_ns, inode, attrs); mark_inode_dirty(inode); cifs_setattr_exit: diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index 0b346baf110d..d3ea0c57b075 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -855,7 +855,8 @@ int ecryptfs_truncate(struct dentry *dentry, loff_t new_length) struct dentry *lower_dentry = ecryptfs_dentry_to_lower(dentry); inode_lock(d_inode(lower_dentry)); - rc = notify_change(lower_dentry, &lower_ia, NULL); + rc = notify_change(&init_user_ns, lower_dentry, + &lower_ia, NULL); inode_unlock(d_inode(lower_dentry)); } return rc; @@ -934,7 +935,7 @@ static int ecryptfs_setattr(struct dentry *dentry, struct iattr *ia) } mutex_unlock(&crypt_stat->cs_mutex); - rc = setattr_prepare(dentry, ia); + rc = setattr_prepare(&init_user_ns, dentry, ia); if (rc) goto out; if (ia->ia_valid & ATTR_SIZE) { @@ -960,7 +961,7 @@ static int ecryptfs_setattr(struct dentry *dentry, struct iattr *ia) lower_ia.ia_valid &= ~ATTR_MODE; inode_lock(d_inode(lower_dentry)); - rc = notify_change(lower_dentry, &lower_ia, NULL); + rc = notify_change(&init_user_ns, lower_dentry, &lower_ia, NULL); inode_unlock(d_inode(lower_dentry)); out: fsstack_copy_attr_all(inode, lower_inode); diff --git a/fs/exfat/file.c b/fs/exfat/file.c index a92478eabfa4..ace35aa8e64b 100644 --- a/fs/exfat/file.c +++ b/fs/exfat/file.c @@ -305,7 +305,7 @@ int exfat_setattr(struct dentry *dentry, struct iattr *attr) ATTR_TIMES_SET); } - error = setattr_prepare(dentry, attr); + error = setattr_prepare(&init_user_ns, dentry, attr); attr->ia_valid = ia_valid; if (error) goto out; @@ -340,7 +340,7 @@ int exfat_setattr(struct dentry *dentry, struct iattr *attr) up_write(&EXFAT_I(inode)->truncate_lock); } - setattr_copy(inode, attr); + setattr_copy(&init_user_ns, inode, attr); exfat_truncate_atime(&inode->i_atime); mark_inode_dirty(inode); diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 78c417d3c898..06c0cf28c1a0 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -1669,7 +1669,7 @@ int ext2_setattr(struct dentry *dentry, struct iattr *iattr) struct inode *inode = d_inode(dentry); int error; - error = setattr_prepare(dentry, iattr); + error = setattr_prepare(&init_user_ns, dentry, iattr); if (error) return error; @@ -1689,7 +1689,7 @@ int ext2_setattr(struct dentry *dentry, struct iattr *iattr) if (error) return error; } - setattr_copy(inode, iattr); + setattr_copy(&init_user_ns, inode, iattr); if (iattr->ia_valid & ATTR_MODE) error = posix_acl_chmod(inode, inode->i_mode); mark_inode_dirty(inode); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index c173c8405856..8edfa3e226e6 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5337,7 +5337,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) ATTR_GID | ATTR_TIMES_SET)))) return -EPERM; - error = setattr_prepare(dentry, attr); + error = setattr_prepare(&init_user_ns, dentry, attr); if (error) return error; @@ -5512,7 +5512,7 @@ out_mmap_sem: } if (!error) { - setattr_copy(inode, attr); + setattr_copy(&init_user_ns, inode, attr); mark_inode_dirty(inode); } diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 5fc0ff28b5dd..90d7b89176de 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -831,7 +831,8 @@ int f2fs_getattr(const struct path *path, struct kstat *stat, } #ifdef CONFIG_F2FS_FS_POSIX_ACL -static void __setattr_copy(struct inode *inode, const struct iattr *attr) +static void __setattr_copy(struct user_namespace *mnt_userns, struct inode *inode, + const struct iattr *attr) { unsigned int ia_valid = attr->ia_valid; @@ -847,8 +848,9 @@ static void __setattr_copy(struct inode *inode, const struct iattr *attr) inode->i_ctime = attr->ia_ctime; if (ia_valid & ATTR_MODE) { umode_t mode = attr->ia_mode; + kgid_t kgid = i_gid_into_mnt(mnt_userns, inode); - if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID)) + if (!in_group_p(kgid) && !capable(CAP_FSETID)) mode &= ~S_ISGID; set_acl_inode(inode, mode); } @@ -869,7 +871,7 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) !f2fs_is_compress_backend_ready(inode)) return -EOPNOTSUPP; - err = setattr_prepare(dentry, attr); + err = setattr_prepare(&init_user_ns, dentry, attr); if (err) return err; @@ -945,7 +947,7 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) spin_unlock(&F2FS_I(inode)->i_size_lock); } - __setattr_copy(inode, attr); + __setattr_copy(&init_user_ns, inode, attr); if (attr->ia_valid & ATTR_MODE) { err = posix_acl_chmod(inode, f2fs_get_inode_mode(inode)); diff --git a/fs/fat/file.c b/fs/fat/file.c index f9ee27cf4d7c..805b501467e9 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -480,7 +480,7 @@ int fat_setattr(struct dentry *dentry, struct iattr *attr) attr->ia_valid &= ~TIMES_SET_FLAGS; } - error = setattr_prepare(dentry, attr); + error = setattr_prepare(&init_user_ns, dentry, attr); attr->ia_valid = ia_valid; if (error) { if (sbi->options.quiet) @@ -550,7 +550,7 @@ int fat_setattr(struct dentry *dentry, struct iattr *attr) fat_truncate_time(inode, &attr->ia_mtime, S_MTIME); attr->ia_valid &= ~(ATTR_ATIME|ATTR_CTIME|ATTR_MTIME); - setattr_copy(inode, attr); + setattr_copy(&init_user_ns, inode, attr); mark_inode_dirty(inode); out: return error; diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 7497009a5a45..74fdb6a7ebb3 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1611,7 +1611,7 @@ int fuse_do_setattr(struct dentry *dentry, struct iattr *attr, if (!fc->default_permissions) attr->ia_valid |= ATTR_FORCE; - err = setattr_prepare(dentry, attr); + err = setattr_prepare(&init_user_ns, dentry, attr); if (err) return err; diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 5b2ff0c74b67..59c25181d108 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -1861,7 +1861,7 @@ int gfs2_permission(struct inode *inode, int mask) static int __gfs2_setattr_simple(struct inode *inode, struct iattr *attr) { - setattr_copy(inode, attr); + setattr_copy(&init_user_ns, inode, attr); mark_inode_dirty(inode); return 0; } @@ -1982,7 +1982,7 @@ static int gfs2_setattr(struct dentry *dentry, struct iattr *attr) if (IS_IMMUTABLE(inode) || IS_APPEND(inode)) goto error; - error = setattr_prepare(dentry, attr); + error = setattr_prepare(&init_user_ns, dentry, attr); if (error) goto error; diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index f35a37c65e5f..c646218b72bf 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -608,7 +608,7 @@ int hfs_inode_setattr(struct dentry *dentry, struct iattr * attr) struct hfs_sb_info *hsb = HFS_SB(inode->i_sb); int error; - error = setattr_prepare(dentry, attr); /* basic permission checks */ + error = setattr_prepare(&init_user_ns, dentry, attr); /* basic permission checks */ if (error) return error; @@ -647,7 +647,7 @@ int hfs_inode_setattr(struct dentry *dentry, struct iattr * attr) current_time(inode); } - setattr_copy(inode, attr); + setattr_copy(&init_user_ns, inode, attr); mark_inode_dirty(inode); return 0; } diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index 21357046b039..ffa137f8234e 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -246,7 +246,7 @@ static int hfsplus_setattr(struct dentry *dentry, struct iattr *attr) struct inode *inode = d_inode(dentry); int error; - error = setattr_prepare(dentry, attr); + error = setattr_prepare(&init_user_ns, dentry, attr); if (error) return error; @@ -264,7 +264,7 @@ static int hfsplus_setattr(struct dentry *dentry, struct iattr *attr) inode->i_mtime = inode->i_ctime = current_time(inode); } - setattr_copy(inode, attr); + setattr_copy(&init_user_ns, inode, attr); mark_inode_dirty(inode); return 0; diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index b841a05a2b8c..6970e29a5287 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -792,7 +792,7 @@ static int hostfs_setattr(struct dentry *dentry, struct iattr *attr) int fd = HOSTFS_I(inode)->fd; - err = setattr_prepare(dentry, attr); + err = setattr_prepare(&init_user_ns, dentry, attr); if (err) return err; @@ -849,7 +849,7 @@ static int hostfs_setattr(struct dentry *dentry, struct iattr *attr) attr->ia_size != i_size_read(inode)) truncate_setsize(inode, attr->ia_size); - setattr_copy(inode, attr); + setattr_copy(&init_user_ns, inode, attr); mark_inode_dirty(inode); return 0; } diff --git a/fs/hpfs/inode.c b/fs/hpfs/inode.c index eb8b4baf0f2e..8ba2152a78ba 100644 --- a/fs/hpfs/inode.c +++ b/fs/hpfs/inode.c @@ -274,7 +274,7 @@ int hpfs_setattr(struct dentry *dentry, struct iattr *attr) if ((attr->ia_valid & ATTR_SIZE) && attr->ia_size > inode->i_size) goto out_unlock; - error = setattr_prepare(dentry, attr); + error = setattr_prepare(&init_user_ns, dentry, attr); if (error) goto out_unlock; @@ -288,7 +288,7 @@ int hpfs_setattr(struct dentry *dentry, struct iattr *attr) hpfs_truncate(inode); } - setattr_copy(inode, attr); + setattr_copy(&init_user_ns, inode, attr); hpfs_write_inode(inode); diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 6737929e443c..327e572b4e00 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -761,7 +761,7 @@ static int hugetlbfs_setattr(struct dentry *dentry, struct iattr *attr) BUG_ON(!inode); - error = setattr_prepare(dentry, attr); + error = setattr_prepare(&init_user_ns, dentry, attr); if (error) return error; @@ -780,7 +780,7 @@ static int hugetlbfs_setattr(struct dentry *dentry, struct iattr *attr) return error; } - setattr_copy(inode, attr); + setattr_copy(&init_user_ns, inode, attr); mark_inode_dirty(inode); return 0; } diff --git a/fs/inode.c b/fs/inode.c index a9ac97a27784..49b512592dcd 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1912,7 +1912,7 @@ static int __remove_privs(struct dentry *dentry, int kill) * Note we call this on write, so notify_change will not * encounter any conflicting delegations: */ - return notify_change(dentry, &newattrs, NULL); + return notify_change(&init_user_ns, dentry, &newattrs, NULL); } /* diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c index 78858f6e9583..67993808f4da 100644 --- a/fs/jffs2/fs.c +++ b/fs/jffs2/fs.c @@ -195,7 +195,7 @@ int jffs2_setattr(struct dentry *dentry, struct iattr *iattr) struct inode *inode = d_inode(dentry); int rc; - rc = setattr_prepare(dentry, iattr); + rc = setattr_prepare(&init_user_ns, dentry, iattr); if (rc) return rc; diff --git a/fs/jfs/file.c b/fs/jfs/file.c index 930d2701f206..ff49876e9c9b 100644 --- a/fs/jfs/file.c +++ b/fs/jfs/file.c @@ -90,7 +90,7 @@ int jfs_setattr(struct dentry *dentry, struct iattr *iattr) struct inode *inode = d_inode(dentry); int rc; - rc = setattr_prepare(dentry, iattr); + rc = setattr_prepare(&init_user_ns, dentry, iattr); if (rc) return rc; @@ -118,7 +118,7 @@ int jfs_setattr(struct dentry *dentry, struct iattr *iattr) jfs_truncate(inode); } - setattr_copy(inode, iattr); + setattr_copy(&init_user_ns, inode, iattr); mark_inode_dirty(inode); if (iattr->ia_valid & ATTR_MODE) diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index ff5598cc1de0..86bd4c593b78 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -122,7 +122,7 @@ int kernfs_iop_setattr(struct dentry *dentry, struct iattr *iattr) return -EINVAL; mutex_lock(&kernfs_mutex); - error = setattr_prepare(dentry, iattr); + error = setattr_prepare(&init_user_ns, dentry, iattr); if (error) goto out; @@ -131,7 +131,7 @@ int kernfs_iop_setattr(struct dentry *dentry, struct iattr *iattr) goto out; /* this ignores size changes */ - setattr_copy(inode, iattr); + setattr_copy(&init_user_ns, inode, iattr); out: mutex_unlock(&kernfs_mutex); diff --git a/fs/libfs.c b/fs/libfs.c index f8b3c02b4f0f..a73fe109403c 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -497,13 +497,13 @@ int simple_setattr(struct dentry *dentry, struct iattr *iattr) struct inode *inode = d_inode(dentry); int error; - error = setattr_prepare(dentry, iattr); + error = setattr_prepare(&init_user_ns, dentry, iattr); if (error) return error; if (iattr->ia_valid & ATTR_SIZE) truncate_setsize(inode, iattr->ia_size); - setattr_copy(inode, iattr); + setattr_copy(&init_user_ns, inode, iattr); mark_inode_dirty(inode); return 0; } diff --git a/fs/minix/file.c b/fs/minix/file.c index c50b0a20fcd9..f07acd268577 100644 --- a/fs/minix/file.c +++ b/fs/minix/file.c @@ -27,7 +27,7 @@ static int minix_setattr(struct dentry *dentry, struct iattr *attr) struct inode *inode = d_inode(dentry); int error; - error = setattr_prepare(dentry, attr); + error = setattr_prepare(&init_user_ns, dentry, attr); if (error) return error; @@ -41,7 +41,7 @@ static int minix_setattr(struct dentry *dentry, struct iattr *attr) minix_truncate(inode); } - setattr_copy(inode, attr); + setattr_copy(&init_user_ns, inode, attr); mark_inode_dirty(inode); return 0; } diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index 9473d048efec..0ea0554d20d1 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -90,7 +90,7 @@ nfsd_proc_setattr(struct svc_rqst *rqstp) if (delta < 0) delta = -delta; if (delta < MAX_TOUCH_TIME_ERROR && - setattr_prepare(fhp->fh_dentry, iap) != 0) { + setattr_prepare(&init_user_ns, fhp->fh_dentry, iap) != 0) { /* * Turn off ATTR_[AM]TIME_SET but leave ATTR_[AM]TIME. * This will cause notify_change to set these times diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 0edf11258aaa..1905b39be1c2 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -448,7 +448,7 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, .ia_size = iap->ia_size, }; - host_err = notify_change(dentry, &size_attr, NULL); + host_err = notify_change(&init_user_ns, dentry, &size_attr, NULL); if (host_err) goto out_unlock; iap->ia_valid &= ~ATTR_SIZE; @@ -463,7 +463,7 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, } iap->ia_valid |= ATTR_CTIME; - host_err = notify_change(dentry, iap, NULL); + host_err = notify_change(&init_user_ns, dentry, iap, NULL); out_unlock: fh_unlock(fhp); diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 11225a659736..8aad3c48092a 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -812,7 +812,7 @@ int nilfs_setattr(struct dentry *dentry, struct iattr *iattr) struct super_block *sb = inode->i_sb; int err; - err = setattr_prepare(dentry, iattr); + err = setattr_prepare(&init_user_ns, dentry, iattr); if (err) return err; @@ -827,7 +827,7 @@ int nilfs_setattr(struct dentry *dentry, struct iattr *iattr) nilfs_truncate(inode); } - setattr_copy(inode, iattr); + setattr_copy(&init_user_ns, inode, iattr); mark_inode_dirty(inode); if (iattr->ia_valid & ATTR_MODE) { diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c index f7e4cbc26eaf..38f4cf1d4497 100644 --- a/fs/ntfs/inode.c +++ b/fs/ntfs/inode.c @@ -2866,7 +2866,7 @@ int ntfs_setattr(struct dentry *dentry, struct iattr *attr) int err; unsigned int ia_valid = attr->ia_valid; - err = setattr_prepare(dentry, attr); + err = setattr_prepare(&init_user_ns, dentry, attr); if (err) goto out; /* We do not support NTFS ACLs yet. */ diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c index 37c7d03a6284..9fa66cd1f622 100644 --- a/fs/ocfs2/dlmfs/dlmfs.c +++ b/fs/ocfs2/dlmfs/dlmfs.c @@ -196,11 +196,11 @@ static int dlmfs_file_setattr(struct dentry *dentry, struct iattr *attr) struct inode *inode = d_inode(dentry); attr->ia_valid &= ~ATTR_SIZE; - error = setattr_prepare(dentry, attr); + error = setattr_prepare(&init_user_ns, dentry, attr); if (error) return error; - setattr_copy(inode, attr); + setattr_copy(&init_user_ns, inode, attr); mark_inode_dirty(inode); return 0; } diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 0c75619adf54..cabf355b148f 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1142,7 +1142,7 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr) if (!(attr->ia_valid & OCFS2_VALID_ATTRS)) return 0; - status = setattr_prepare(dentry, attr); + status = setattr_prepare(&init_user_ns, dentry, attr); if (status) return status; @@ -1263,7 +1263,7 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr) } } - setattr_copy(inode, attr); + setattr_copy(&init_user_ns, inode, attr); mark_inode_dirty(inode); status = ocfs2_mark_inode_dirty(handle, inode, bh); diff --git a/fs/omfs/file.c b/fs/omfs/file.c index 2c7b70ee1388..729339cd7902 100644 --- a/fs/omfs/file.c +++ b/fs/omfs/file.c @@ -348,7 +348,7 @@ static int omfs_setattr(struct dentry *dentry, struct iattr *attr) struct inode *inode = d_inode(dentry); int error; - error = setattr_prepare(dentry, attr); + error = setattr_prepare(&init_user_ns, dentry, attr); if (error) return error; @@ -361,7 +361,7 @@ static int omfs_setattr(struct dentry *dentry, struct iattr *attr) omfs_truncate(inode); } - setattr_copy(inode, attr); + setattr_copy(&init_user_ns, inode, attr); mark_inode_dirty(inode); return 0; } diff --git a/fs/open.c b/fs/open.c index a6dac6d97988..c3e4dc43dd8d 100644 --- a/fs/open.c +++ b/fs/open.c @@ -61,7 +61,7 @@ int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs, inode_lock(dentry->d_inode); /* Note any delegations or leases have already been broken: */ - ret = notify_change(dentry, &newattrs, NULL); + ret = notify_change(&init_user_ns, dentry, &newattrs, NULL); inode_unlock(dentry->d_inode); return ret; } @@ -580,7 +580,8 @@ retry_deleg: goto out_unlock; newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO); newattrs.ia_valid = ATTR_MODE | ATTR_CTIME; - error = notify_change(path->dentry, &newattrs, &delegated_inode); + error = notify_change(&init_user_ns, path->dentry, &newattrs, + &delegated_inode); out_unlock: inode_unlock(inode); if (delegated_inode) { @@ -671,7 +672,8 @@ retry_deleg: inode_lock(inode); error = security_path_chown(path, uid, gid); if (!error) - error = notify_change(path->dentry, &newattrs, &delegated_inode); + error = notify_change(&init_user_ns, path->dentry, &newattrs, + &delegated_inode); inode_unlock(inode); if (delegated_inode) { error = break_deleg_wait(&delegated_inode); diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c index 4c790cc8042d..8ac9491ceb9a 100644 --- a/fs/orangefs/inode.c +++ b/fs/orangefs/inode.c @@ -855,7 +855,7 @@ again: ORANGEFS_I(inode)->attr_uid = current_fsuid(); ORANGEFS_I(inode)->attr_gid = current_fsgid(); } - setattr_copy(inode, iattr); + setattr_copy(&init_user_ns, inode, iattr); spin_unlock(&inode->i_lock); mark_inode_dirty(inode); @@ -876,7 +876,7 @@ int orangefs_setattr(struct dentry *dentry, struct iattr *iattr) int ret; gossip_debug(GOSSIP_INODE_DEBUG, "__orangefs_setattr: called on %pd\n", dentry); - ret = setattr_prepare(dentry, iattr); + ret = setattr_prepare(&init_user_ns, dentry, iattr); if (ret) goto out; ret = __orangefs_setattr(d_inode(dentry), iattr); diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index e5b616c93e11..3e9957ae19fa 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -235,7 +235,7 @@ static int ovl_set_size(struct dentry *upperdentry, struct kstat *stat) .ia_size = stat->size, }; - return notify_change(upperdentry, &attr, NULL); + return notify_change(&init_user_ns, upperdentry, &attr, NULL); } static int ovl_set_timestamps(struct dentry *upperdentry, struct kstat *stat) @@ -247,7 +247,7 @@ static int ovl_set_timestamps(struct dentry *upperdentry, struct kstat *stat) .ia_mtime = stat->mtime, }; - return notify_change(upperdentry, &attr, NULL); + return notify_change(&init_user_ns, upperdentry, &attr, NULL); } int ovl_set_attr(struct dentry *upperdentry, struct kstat *stat) @@ -259,7 +259,7 @@ int ovl_set_attr(struct dentry *upperdentry, struct kstat *stat) .ia_valid = ATTR_MODE, .ia_mode = stat->mode, }; - err = notify_change(upperdentry, &attr, NULL); + err = notify_change(&init_user_ns, upperdentry, &attr, NULL); } if (!err) { struct iattr attr = { @@ -267,7 +267,7 @@ int ovl_set_attr(struct dentry *upperdentry, struct kstat *stat) .ia_uid = stat->uid, .ia_gid = stat->gid, }; - err = notify_change(upperdentry, &attr, NULL); + err = notify_change(&init_user_ns, upperdentry, &attr, NULL); } if (!err) ovl_set_timestamps(upperdentry, stat); diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 98a23353b19a..29840820a46c 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -508,7 +508,7 @@ static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode, .ia_mode = cattr->mode, }; inode_lock(newdentry->d_inode); - err = notify_change(newdentry, &attr, NULL); + err = notify_change(&init_user_ns, newdentry, &attr, NULL); inode_unlock(newdentry->d_inode); if (err) goto out_cleanup; diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index c101ebbb7a77..5aa66881dbd7 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -21,7 +21,7 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr) struct dentry *upperdentry; const struct cred *old_cred; - err = setattr_prepare(dentry, attr); + err = setattr_prepare(&init_user_ns, dentry, attr); if (err) return err; @@ -79,7 +79,7 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr) inode_lock(upperdentry->d_inode); old_cred = ovl_override_creds(dentry->d_sb); - err = notify_change(upperdentry, attr, NULL); + err = notify_change(&init_user_ns, upperdentry, attr, NULL); revert_creds(old_cred); if (!err) ovl_copyattr(upperdentry->d_inode, dentry->d_inode); diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 3e925deaa19a..39b2e9aa0e5b 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -804,7 +804,7 @@ retry: /* Clear any inherited mode bits */ inode_lock(work->d_inode); - err = notify_change(work, &attr, NULL); + err = notify_change(&init_user_ns, work, &attr, NULL); inode_unlock(work->d_inode); if (err) goto out_dput; diff --git a/fs/proc/base.c b/fs/proc/base.c index b4ec9293625e..bb4e63a3684f 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -693,11 +693,11 @@ int proc_setattr(struct dentry *dentry, struct iattr *attr) if (attr->ia_valid & ATTR_MODE) return -EPERM; - error = setattr_prepare(dentry, attr); + error = setattr_prepare(&init_user_ns, dentry, attr); if (error) return error; - setattr_copy(inode, attr); + setattr_copy(&init_user_ns, inode, attr); mark_inode_dirty(inode); return 0; } diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 6c0a05f55d6b..6d4fabab8aa7 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -121,11 +121,11 @@ static int proc_notify_change(struct dentry *dentry, struct iattr *iattr) struct proc_dir_entry *de = PDE(inode); int error; - error = setattr_prepare(dentry, iattr); + error = setattr_prepare(&init_user_ns, dentry, iattr); if (error) return error; - setattr_copy(inode, iattr); + setattr_copy(&init_user_ns, inode, iattr); mark_inode_dirty(inode); proc_set_user(de, inode->i_uid, inode->i_gid); diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 317899222d7f..ec67dbc1f705 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -821,11 +821,11 @@ static int proc_sys_setattr(struct dentry *dentry, struct iattr *attr) if (attr->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID)) return -EPERM; - error = setattr_prepare(dentry, attr); + error = setattr_prepare(&init_user_ns, dentry, attr); if (error) return error; - setattr_copy(inode, attr); + setattr_copy(&init_user_ns, inode, attr); mark_inode_dirty(inode); return 0; } diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c index 355523f4a4bf..f0358fe410d3 100644 --- a/fs/ramfs/file-nommu.c +++ b/fs/ramfs/file-nommu.c @@ -165,7 +165,7 @@ static int ramfs_nommu_setattr(struct dentry *dentry, struct iattr *ia) int ret = 0; /* POSIX UID/GID verification for setting inode attributes */ - ret = setattr_prepare(dentry, ia); + ret = setattr_prepare(&init_user_ns, dentry, ia); if (ret) return ret; @@ -185,7 +185,7 @@ static int ramfs_nommu_setattr(struct dentry *dentry, struct iattr *ia) } } - setattr_copy(inode, ia); + setattr_copy(&init_user_ns, inode, ia); out: ia->ia_valid = old_ia_valid; return ret; diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index c76d563dec0e..944f2b487cf8 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -3288,7 +3288,7 @@ int reiserfs_setattr(struct dentry *dentry, struct iattr *attr) unsigned int ia_valid; int error; - error = setattr_prepare(dentry, attr); + error = setattr_prepare(&init_user_ns, dentry, attr); if (error) return error; @@ -3413,7 +3413,7 @@ int reiserfs_setattr(struct dentry *dentry, struct iattr *attr) } if (!error) { - setattr_copy(inode, attr); + setattr_copy(&init_user_ns, inode, attr); mark_inode_dirty(inode); } diff --git a/fs/sysv/file.c b/fs/sysv/file.c index 45fc79a18594..ca7e216b7b9e 100644 --- a/fs/sysv/file.c +++ b/fs/sysv/file.c @@ -34,7 +34,7 @@ static int sysv_setattr(struct dentry *dentry, struct iattr *attr) struct inode *inode = d_inode(dentry); int error; - error = setattr_prepare(dentry, attr); + error = setattr_prepare(&init_user_ns, dentry, attr); if (error) return error; @@ -47,7 +47,7 @@ static int sysv_setattr(struct dentry *dentry, struct iattr *attr) sysv_truncate(inode); } - setattr_copy(inode, attr); + setattr_copy(&init_user_ns, inode, attr); mark_inode_dirty(inode); return 0; } diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 2bc7780d2963..76ef392b1e41 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -1265,7 +1265,7 @@ int ubifs_setattr(struct dentry *dentry, struct iattr *attr) dbg_gen("ino %lu, mode %#x, ia_valid %#x", inode->i_ino, inode->i_mode, attr->ia_valid); - err = setattr_prepare(dentry, attr); + err = setattr_prepare(&init_user_ns, dentry, attr); if (err) return err; diff --git a/fs/udf/file.c b/fs/udf/file.c index 3671a40ed3c3..7c7d161315c2 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -259,7 +259,7 @@ static int udf_setattr(struct dentry *dentry, struct iattr *attr) struct super_block *sb = inode->i_sb; int error; - error = setattr_prepare(dentry, attr); + error = setattr_prepare(&init_user_ns, dentry, attr); if (error) return error; @@ -282,7 +282,7 @@ static int udf_setattr(struct dentry *dentry, struct iattr *attr) if (attr->ia_valid & ATTR_MODE) udf_update_extra_perms(inode, attr->ia_mode); - setattr_copy(inode, attr); + setattr_copy(&init_user_ns, inode, attr); mark_inode_dirty(inode); return 0; } diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c index c843ec858cf7..6b51f3b20143 100644 --- a/fs/ufs/inode.c +++ b/fs/ufs/inode.c @@ -1217,7 +1217,7 @@ int ufs_setattr(struct dentry *dentry, struct iattr *attr) unsigned int ia_valid = attr->ia_valid; int error; - error = setattr_prepare(dentry, attr); + error = setattr_prepare(&init_user_ns, dentry, attr); if (error) return error; @@ -1227,7 +1227,7 @@ int ufs_setattr(struct dentry *dentry, struct iattr *attr) return error; } - setattr_copy(inode, attr); + setattr_copy(&init_user_ns, inode, attr); mark_inode_dirty(inode); return 0; } diff --git a/fs/utimes.c b/fs/utimes.c index fd3cc4226224..4572b91ddb91 100644 --- a/fs/utimes.c +++ b/fs/utimes.c @@ -62,7 +62,8 @@ int vfs_utimes(const struct path *path, struct timespec64 *times) } retry_deleg: inode_lock(inode); - error = notify_change(path->dentry, &newattrs, &delegated_inode); + error = notify_change(&init_user_ns, path->dentry, &newattrs, + &delegated_inode); inode_unlock(inode); if (delegated_inode) { error = break_deleg_wait(&delegated_inode); diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 67c8dc9de8aa..08a478d25122 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -637,7 +637,7 @@ xfs_vn_change_ok( if (XFS_FORCED_SHUTDOWN(mp)) return -EIO; - return setattr_prepare(dentry, iattr); + return setattr_prepare(&init_user_ns, dentry, iattr); } /* diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index 569525ee8f69..8a1f69677784 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -488,7 +488,7 @@ static int zonefs_inode_setattr(struct dentry *dentry, struct iattr *iattr) if (unlikely(IS_IMMUTABLE(inode))) return -EPERM; - ret = setattr_prepare(dentry, iattr); + ret = setattr_prepare(&init_user_ns, dentry, iattr); if (ret) return ret; @@ -516,7 +516,7 @@ static int zonefs_inode_setattr(struct dentry *dentry, struct iattr *iattr) return ret; } - setattr_copy(inode, iattr); + setattr_copy(&init_user_ns, inode, iattr); return 0; } diff --git a/include/linux/fs.h b/include/linux/fs.h index 2a9d4af6a64d..e3ea1d7c3367 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2809,7 +2809,8 @@ static inline int bmap(struct inode *inode, sector_t *block) } #endif -extern int notify_change(struct dentry *, struct iattr *, struct inode **); +int notify_change(struct user_namespace *, struct dentry *, + struct iattr *, struct inode **); int inode_permission(struct user_namespace *, struct inode *, int); int generic_permission(struct user_namespace *, struct inode *, int); static inline int file_permission(struct file *file, int mask) @@ -3274,9 +3275,10 @@ extern int buffer_migrate_page_norefs(struct address_space *, #define buffer_migrate_page_norefs NULL #endif -extern int setattr_prepare(struct dentry *, struct iattr *); +int setattr_prepare(struct user_namespace *, struct dentry *, struct iattr *); extern int inode_newsize_ok(const struct inode *, loff_t offset); -extern void setattr_copy(struct inode *inode, const struct iattr *attr); +void setattr_copy(struct user_namespace *, struct inode *inode, + const struct iattr *attr); extern int file_update_time(struct file *file); diff --git a/mm/shmem.c b/mm/shmem.c index 1c68c9edba5e..1cb451e131ec 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1087,7 +1087,7 @@ static int shmem_setattr(struct dentry *dentry, struct iattr *attr) struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); int error; - error = setattr_prepare(dentry, attr); + error = setattr_prepare(&init_user_ns, dentry, attr); if (error) return error; @@ -1141,7 +1141,7 @@ static int shmem_setattr(struct dentry *dentry, struct iattr *attr) } } - setattr_copy(inode, attr); + setattr_copy(&init_user_ns, inode, attr); if (attr->ia_valid & ATTR_MODE) error = posix_acl_chmod(inode, inode->i_mode); return error; -- cgit v1.2.3 From e65ce2a50cf6af216bea6fd80d771fcbb4c0aaa1 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 21 Jan 2021 14:19:27 +0100 Subject: acl: handle idmapped mounts The posix acl permission checking helpers determine whether a caller is privileged over an inode according to the acls associated with the inode. Add helpers that make it possible to handle acls on idmapped mounts. The vfs and the filesystems targeted by this first iteration make use of posix_acl_fix_xattr_from_user() and posix_acl_fix_xattr_to_user() to translate basic posix access and default permissions such as the ACL_USER and ACL_GROUP type according to the initial user namespace (or the superblock's user namespace) to and from the caller's current user namespace. Adapt these two helpers to handle idmapped mounts whereby we either map from or into the mount's user namespace depending on in which direction we're translating. Similarly, cap_convert_nscap() is used by the vfs to translate user namespace and non-user namespace aware filesystem capabilities from the superblock's user namespace to the caller's user namespace. Enable it to handle idmapped mounts by accounting for the mount's user namespace. In addition the fileystems targeted in the first iteration of this patch series make use of the posix_acl_chmod() and, posix_acl_update_mode() helpers. Both helpers perform permission checks on the target inode. Let them handle idmapped mounts. These two helpers are called when posix acls are set by the respective filesystems to handle this case we extend the ->set() method to take an additional user namespace argument to pass the mount's user namespace down. Link: https://lore.kernel.org/r/20210121131959.646623-9-christian.brauner@ubuntu.com Cc: Christoph Hellwig Cc: David Howells Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig Signed-off-by: Christian Brauner --- Documentation/filesystems/locking.rst | 7 ++-- Documentation/filesystems/porting.rst | 2 + fs/9p/acl.c | 4 +- fs/9p/xattr.c | 1 + fs/afs/xattr.c | 2 + fs/btrfs/acl.c | 3 +- fs/btrfs/inode.c | 3 +- fs/btrfs/xattr.c | 2 + fs/ceph/acl.c | 3 +- fs/ceph/inode.c | 2 +- fs/ceph/xattr.c | 1 + fs/cifs/xattr.c | 1 + fs/ecryptfs/inode.c | 1 + fs/ext2/acl.c | 3 +- fs/ext2/inode.c | 2 +- fs/ext2/xattr_security.c | 1 + fs/ext2/xattr_trusted.c | 1 + fs/ext2/xattr_user.c | 1 + fs/ext4/acl.c | 3 +- fs/ext4/inode.c | 2 +- fs/ext4/xattr_hurd.c | 1 + fs/ext4/xattr_security.c | 1 + fs/ext4/xattr_trusted.c | 1 + fs/ext4/xattr_user.c | 1 + fs/f2fs/acl.c | 3 +- fs/f2fs/file.c | 7 ++-- fs/f2fs/xattr.c | 2 + fs/fuse/xattr.c | 2 + fs/gfs2/acl.c | 2 +- fs/gfs2/inode.c | 3 +- fs/gfs2/xattr.c | 1 + fs/hfs/attr.c | 1 + fs/hfsplus/xattr.c | 1 + fs/hfsplus/xattr_security.c | 1 + fs/hfsplus/xattr_trusted.c | 1 + fs/hfsplus/xattr_user.c | 1 + fs/jffs2/acl.c | 3 +- fs/jffs2/fs.c | 2 +- fs/jffs2/security.c | 1 + fs/jffs2/xattr_trusted.c | 1 + fs/jffs2/xattr_user.c | 1 + fs/jfs/acl.c | 2 +- fs/jfs/file.c | 2 +- fs/jfs/xattr.c | 2 + fs/kernfs/inode.c | 2 + fs/nfs/nfs4proc.c | 3 ++ fs/nfsd/nfs2acl.c | 6 ++- fs/nfsd/nfs3acl.c | 6 ++- fs/nfsd/nfs4acl.c | 5 ++- fs/ocfs2/acl.c | 3 +- fs/ocfs2/xattr.c | 3 ++ fs/orangefs/acl.c | 3 +- fs/orangefs/inode.c | 2 +- fs/orangefs/xattr.c | 1 + fs/overlayfs/super.c | 3 ++ fs/posix_acl.c | 79 +++++++++++++++++++++++++---------- fs/reiserfs/xattr_acl.c | 5 ++- fs/reiserfs/xattr_security.c | 3 +- fs/reiserfs/xattr_trusted.c | 3 +- fs/reiserfs/xattr_user.c | 3 +- fs/ubifs/xattr.c | 1 + fs/xattr.c | 14 ++++--- fs/xfs/xfs_acl.c | 3 +- fs/xfs/xfs_iops.c | 2 +- fs/xfs/xfs_xattr.c | 7 ++-- include/linux/capability.h | 3 +- include/linux/posix_acl.h | 11 +++-- include/linux/posix_acl_xattr.h | 12 ++++-- include/linux/xattr.h | 3 +- mm/shmem.c | 3 +- net/socket.c | 1 + security/commoncap.c | 45 ++++++++++++++++---- 72 files changed, 238 insertions(+), 85 deletions(-) (limited to 'include') diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst index c0f2c7586531..b7dcc86c92a4 100644 --- a/Documentation/filesystems/locking.rst +++ b/Documentation/filesystems/locking.rst @@ -126,9 +126,10 @@ prototypes:: int (*get)(const struct xattr_handler *handler, struct dentry *dentry, struct inode *inode, const char *name, void *buffer, size_t size); - int (*set)(const struct xattr_handler *handler, struct dentry *dentry, - struct inode *inode, const char *name, const void *buffer, - size_t size, int flags); + int (*set)(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, + struct dentry *dentry, struct inode *inode, const char *name, + const void *buffer, size_t size, int flags); locking rules: all may block diff --git a/Documentation/filesystems/porting.rst b/Documentation/filesystems/porting.rst index 867036aa90b8..de1dcec3b5b8 100644 --- a/Documentation/filesystems/porting.rst +++ b/Documentation/filesystems/porting.rst @@ -717,6 +717,8 @@ be removed. Switch while you still can; the old one won't stay. **mandatory** ->setxattr() and xattr_handler.set() get dentry and inode passed separately. +The xattr_handler.set() gets passed the user namespace of the mount the inode +is seen from so filesystems can idmap the i_uid and i_gid accordingly. dentry might be yet to be attached to inode, so do _not_ use its ->d_inode in the instances. Rationale: !@#!@# security_d_instantiate() needs to be called before we attach dentry to inode and !@#!@##!@$!$#!@#$!@$!@$ smack diff --git a/fs/9p/acl.c b/fs/9p/acl.c index d77b28e8d57a..1c14f18a6ec9 100644 --- a/fs/9p/acl.c +++ b/fs/9p/acl.c @@ -239,6 +239,7 @@ static int v9fs_xattr_get_acl(const struct xattr_handler *handler, } static int v9fs_xattr_set_acl(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *dentry, struct inode *inode, const char *name, const void *value, size_t size, int flags) @@ -279,7 +280,8 @@ static int v9fs_xattr_set_acl(const struct xattr_handler *handler, struct iattr iattr = { 0 }; struct posix_acl *old_acl = acl; - retval = posix_acl_update_mode(inode, &iattr.ia_mode, &acl); + retval = posix_acl_update_mode(mnt_userns, inode, + &iattr.ia_mode, &acl); if (retval) goto err_out; if (!acl) { diff --git a/fs/9p/xattr.c b/fs/9p/xattr.c index 87217dd0433e..ee331845e2c7 100644 --- a/fs/9p/xattr.c +++ b/fs/9p/xattr.c @@ -157,6 +157,7 @@ static int v9fs_xattr_handler_get(const struct xattr_handler *handler, } static int v9fs_xattr_handler_set(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *dentry, struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/fs/afs/xattr.c b/fs/afs/xattr.c index 95c573dcda11..c629caae5002 100644 --- a/fs/afs/xattr.c +++ b/fs/afs/xattr.c @@ -120,6 +120,7 @@ static const struct afs_operation_ops afs_store_acl_operation = { * Set a file's AFS3 ACL. */ static int afs_xattr_set_acl(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *dentry, struct inode *inode, const char *name, const void *buffer, size_t size, int flags) @@ -248,6 +249,7 @@ static const struct afs_operation_ops yfs_store_opaque_acl2_operation = { * Set a file's YFS ACL. */ static int afs_xattr_set_yfs(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *dentry, struct inode *inode, const char *name, const void *buffer, size_t size, int flags) diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c index a0af1b952c4d..d12a5a8730a8 100644 --- a/fs/btrfs/acl.c +++ b/fs/btrfs/acl.c @@ -113,7 +113,8 @@ int btrfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) umode_t old_mode = inode->i_mode; if (type == ACL_TYPE_ACCESS && acl) { - ret = posix_acl_update_mode(inode, &inode->i_mode, &acl); + ret = posix_acl_update_mode(&init_user_ns, inode, + &inode->i_mode, &acl); if (ret) return ret; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 792191a8705b..6c18fb1a25af 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -5070,7 +5070,8 @@ static int btrfs_setattr(struct dentry *dentry, struct iattr *attr) err = btrfs_dirty_inode(inode); if (!err && attr->ia_valid & ATTR_MODE) - err = posix_acl_chmod(inode, inode->i_mode); + err = posix_acl_chmod(&init_user_ns, inode, + inode->i_mode); } return err; diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index af6246f36a9e..b025102e435f 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -362,6 +362,7 @@ static int btrfs_xattr_handler_get(const struct xattr_handler *handler, } static int btrfs_xattr_handler_set(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *unused, struct inode *inode, const char *name, const void *buffer, size_t size, int flags) @@ -371,6 +372,7 @@ static int btrfs_xattr_handler_set(const struct xattr_handler *handler, } static int btrfs_xattr_handler_set_prop(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c index e0465741c591..52a01ddbc4ac 100644 --- a/fs/ceph/acl.c +++ b/fs/ceph/acl.c @@ -100,7 +100,8 @@ int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type) case ACL_TYPE_ACCESS: name = XATTR_NAME_POSIX_ACL_ACCESS; if (acl) { - ret = posix_acl_update_mode(inode, &new_mode, &acl); + ret = posix_acl_update_mode(&init_user_ns, inode, + &new_mode, &acl); if (ret) goto out; } diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 285d3baca27e..145e26a4ddbb 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -2262,7 +2262,7 @@ int ceph_setattr(struct dentry *dentry, struct iattr *attr) err = __ceph_setattr(inode, attr); if (err >= 0 && (attr->ia_valid & ATTR_MODE)) - err = posix_acl_chmod(inode, attr->ia_mode); + err = posix_acl_chmod(&init_user_ns, inode, attr->ia_mode); return err; } diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c index 24997982de01..02f59bcb4f27 100644 --- a/fs/ceph/xattr.c +++ b/fs/ceph/xattr.c @@ -1238,6 +1238,7 @@ static int ceph_get_xattr_handler(const struct xattr_handler *handler, } static int ceph_set_xattr_handler(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c index 6b658a1172ef..41a611e76bb7 100644 --- a/fs/cifs/xattr.c +++ b/fs/cifs/xattr.c @@ -101,6 +101,7 @@ static int cifs_creation_time_set(unsigned int xid, struct cifs_tcon *pTcon, } static int cifs_xattr_set(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *dentry, struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index d3ea0c57b075..ac6472a82567 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -1133,6 +1133,7 @@ static int ecryptfs_xattr_get(const struct xattr_handler *handler, } static int ecryptfs_xattr_set(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *dentry, struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/fs/ext2/acl.c b/fs/ext2/acl.c index cf4c77f8dd08..9031f7df2d48 100644 --- a/fs/ext2/acl.c +++ b/fs/ext2/acl.c @@ -223,7 +223,8 @@ ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type) umode_t mode = inode->i_mode; if (type == ACL_TYPE_ACCESS && acl) { - error = posix_acl_update_mode(inode, &mode, &acl); + error = posix_acl_update_mode(&init_user_ns, inode, &mode, + &acl); if (error) return error; update_mode = 1; diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 06c0cf28c1a0..9de813635d8d 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -1691,7 +1691,7 @@ int ext2_setattr(struct dentry *dentry, struct iattr *iattr) } setattr_copy(&init_user_ns, inode, iattr); if (iattr->ia_valid & ATTR_MODE) - error = posix_acl_chmod(inode, inode->i_mode); + error = posix_acl_chmod(&init_user_ns, inode, inode->i_mode); mark_inode_dirty(inode); return error; diff --git a/fs/ext2/xattr_security.c b/fs/ext2/xattr_security.c index 9a682e440acb..ebade1f52451 100644 --- a/fs/ext2/xattr_security.c +++ b/fs/ext2/xattr_security.c @@ -19,6 +19,7 @@ ext2_xattr_security_get(const struct xattr_handler *handler, static int ext2_xattr_security_set(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/fs/ext2/xattr_trusted.c b/fs/ext2/xattr_trusted.c index 49add1107850..18a87d5dd1ab 100644 --- a/fs/ext2/xattr_trusted.c +++ b/fs/ext2/xattr_trusted.c @@ -26,6 +26,7 @@ ext2_xattr_trusted_get(const struct xattr_handler *handler, static int ext2_xattr_trusted_set(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/fs/ext2/xattr_user.c b/fs/ext2/xattr_user.c index c243a3b4d69d..58092449f8ff 100644 --- a/fs/ext2/xattr_user.c +++ b/fs/ext2/xattr_user.c @@ -30,6 +30,7 @@ ext2_xattr_user_get(const struct xattr_handler *handler, static int ext2_xattr_user_set(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c index 68aaed48315f..7b0fb66bc04d 100644 --- a/fs/ext4/acl.c +++ b/fs/ext4/acl.c @@ -245,7 +245,8 @@ retry: ext4_fc_start_update(inode); if ((type == ACL_TYPE_ACCESS) && acl) { - error = posix_acl_update_mode(inode, &mode, &acl); + error = posix_acl_update_mode(&init_user_ns, inode, &mode, + &acl); if (error) goto out_stop; if (mode != inode->i_mode) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 8edfa3e226e6..24ea5851e90a 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5524,7 +5524,7 @@ out_mmap_sem: ext4_orphan_del(NULL, inode); if (!error && (ia_valid & ATTR_MODE)) - rc = posix_acl_chmod(inode, inode->i_mode); + rc = posix_acl_chmod(&init_user_ns, inode, inode->i_mode); err_out: if (error) diff --git a/fs/ext4/xattr_hurd.c b/fs/ext4/xattr_hurd.c index 8cfa74a56361..c78df5790377 100644 --- a/fs/ext4/xattr_hurd.c +++ b/fs/ext4/xattr_hurd.c @@ -32,6 +32,7 @@ ext4_xattr_hurd_get(const struct xattr_handler *handler, static int ext4_xattr_hurd_set(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/fs/ext4/xattr_security.c b/fs/ext4/xattr_security.c index 197a9d8a15ef..8213f66f7b2d 100644 --- a/fs/ext4/xattr_security.c +++ b/fs/ext4/xattr_security.c @@ -23,6 +23,7 @@ ext4_xattr_security_get(const struct xattr_handler *handler, static int ext4_xattr_security_set(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/fs/ext4/xattr_trusted.c b/fs/ext4/xattr_trusted.c index e9389e5d75c3..7c21ffb26d25 100644 --- a/fs/ext4/xattr_trusted.c +++ b/fs/ext4/xattr_trusted.c @@ -30,6 +30,7 @@ ext4_xattr_trusted_get(const struct xattr_handler *handler, static int ext4_xattr_trusted_set(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/fs/ext4/xattr_user.c b/fs/ext4/xattr_user.c index d4546184b34b..2fe7ff0a479c 100644 --- a/fs/ext4/xattr_user.c +++ b/fs/ext4/xattr_user.c @@ -31,6 +31,7 @@ ext4_xattr_user_get(const struct xattr_handler *handler, static int ext4_xattr_user_set(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c index 1e5e9b1136ee..6a95bf28f602 100644 --- a/fs/f2fs/acl.c +++ b/fs/f2fs/acl.c @@ -213,7 +213,8 @@ static int __f2fs_set_acl(struct inode *inode, int type, case ACL_TYPE_ACCESS: name_index = F2FS_XATTR_INDEX_POSIX_ACL_ACCESS; if (acl && !ipage) { - error = posix_acl_update_mode(inode, &mode, &acl); + error = posix_acl_update_mode(&init_user_ns, inode, + &mode, &acl); if (error) return error; set_acl_inode(inode, mode); diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 90d7b89176de..6ccdfe0606d9 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -831,8 +831,8 @@ int f2fs_getattr(const struct path *path, struct kstat *stat, } #ifdef CONFIG_F2FS_FS_POSIX_ACL -static void __setattr_copy(struct user_namespace *mnt_userns, struct inode *inode, - const struct iattr *attr) +static void __setattr_copy(struct user_namespace *mnt_userns, + struct inode *inode, const struct iattr *attr) { unsigned int ia_valid = attr->ia_valid; @@ -950,7 +950,8 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) __setattr_copy(&init_user_ns, inode, attr); if (attr->ia_valid & ATTR_MODE) { - err = posix_acl_chmod(inode, f2fs_get_inode_mode(inode)); + err = posix_acl_chmod(&init_user_ns, inode, + f2fs_get_inode_mode(inode)); if (err || is_inode_flag_set(inode, FI_ACL_MODE)) { inode->i_mode = F2FS_I(inode)->i_acl_mode; clear_inode_flag(inode, FI_ACL_MODE); diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index d772bf13a814..10081bf74324 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -64,6 +64,7 @@ static int f2fs_xattr_generic_get(const struct xattr_handler *handler, } static int f2fs_xattr_generic_set(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) @@ -107,6 +108,7 @@ static int f2fs_xattr_advise_get(const struct xattr_handler *handler, } static int f2fs_xattr_advise_set(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/fs/fuse/xattr.c b/fs/fuse/xattr.c index cdea18de94f7..1a7d7ace54e1 100644 --- a/fs/fuse/xattr.c +++ b/fs/fuse/xattr.c @@ -188,6 +188,7 @@ static int fuse_xattr_get(const struct xattr_handler *handler, } static int fuse_xattr_set(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *dentry, struct inode *inode, const char *name, const void *value, size_t size, int flags) @@ -214,6 +215,7 @@ static int no_xattr_get(const struct xattr_handler *handler, } static int no_xattr_set(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *dentry, struct inode *nodee, const char *name, const void *value, size_t size, int flags) diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c index 2e939f5fe751..ce88ef29eef0 100644 --- a/fs/gfs2/acl.c +++ b/fs/gfs2/acl.c @@ -130,7 +130,7 @@ int gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type) mode = inode->i_mode; if (type == ACL_TYPE_ACCESS && acl) { - ret = posix_acl_update_mode(inode, &mode, &acl); + ret = posix_acl_update_mode(&init_user_ns, inode, &mode, &acl); if (ret) goto unlock; } diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 59c25181d108..728405d15a05 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -1993,7 +1993,8 @@ static int gfs2_setattr(struct dentry *dentry, struct iattr *attr) else { error = gfs2_setattr_simple(inode, attr); if (!error && attr->ia_valid & ATTR_MODE) - error = posix_acl_chmod(inode, inode->i_mode); + error = posix_acl_chmod(&init_user_ns, inode, + inode->i_mode); } error: diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c index 9d7667bc4292..13969a813410 100644 --- a/fs/gfs2/xattr.c +++ b/fs/gfs2/xattr.c @@ -1214,6 +1214,7 @@ int __gfs2_xattr_set(struct inode *inode, const char *name, } static int gfs2_xattr_set(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/fs/hfs/attr.c b/fs/hfs/attr.c index 74fa62643136..2bd54efaf416 100644 --- a/fs/hfs/attr.c +++ b/fs/hfs/attr.c @@ -121,6 +121,7 @@ static int hfs_xattr_get(const struct xattr_handler *handler, } static int hfs_xattr_set(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/fs/hfsplus/xattr.c b/fs/hfsplus/xattr.c index bb0b27d88e50..4d169c5a2673 100644 --- a/fs/hfsplus/xattr.c +++ b/fs/hfsplus/xattr.c @@ -858,6 +858,7 @@ static int hfsplus_osx_getxattr(const struct xattr_handler *handler, } static int hfsplus_osx_setxattr(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *unused, struct inode *inode, const char *name, const void *buffer, size_t size, int flags) diff --git a/fs/hfsplus/xattr_security.c b/fs/hfsplus/xattr_security.c index cfbe6a3bfb1e..c1c7a16cbf21 100644 --- a/fs/hfsplus/xattr_security.c +++ b/fs/hfsplus/xattr_security.c @@ -23,6 +23,7 @@ static int hfsplus_security_getxattr(const struct xattr_handler *handler, } static int hfsplus_security_setxattr(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *unused, struct inode *inode, const char *name, const void *buffer, size_t size, int flags) diff --git a/fs/hfsplus/xattr_trusted.c b/fs/hfsplus/xattr_trusted.c index fbad91e1dada..e150372ec564 100644 --- a/fs/hfsplus/xattr_trusted.c +++ b/fs/hfsplus/xattr_trusted.c @@ -22,6 +22,7 @@ static int hfsplus_trusted_getxattr(const struct xattr_handler *handler, } static int hfsplus_trusted_setxattr(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *unused, struct inode *inode, const char *name, const void *buffer, size_t size, int flags) diff --git a/fs/hfsplus/xattr_user.c b/fs/hfsplus/xattr_user.c index 74d19faf255e..a6b60b153916 100644 --- a/fs/hfsplus/xattr_user.c +++ b/fs/hfsplus/xattr_user.c @@ -22,6 +22,7 @@ static int hfsplus_user_getxattr(const struct xattr_handler *handler, } static int hfsplus_user_setxattr(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *unused, struct inode *inode, const char *name, const void *buffer, size_t size, int flags) diff --git a/fs/jffs2/acl.c b/fs/jffs2/acl.c index 093ffbd82395..5f27ac593479 100644 --- a/fs/jffs2/acl.c +++ b/fs/jffs2/acl.c @@ -236,7 +236,8 @@ int jffs2_set_acl(struct inode *inode, struct posix_acl *acl, int type) if (acl) { umode_t mode; - rc = posix_acl_update_mode(inode, &mode, &acl); + rc = posix_acl_update_mode(&init_user_ns, inode, &mode, + &acl); if (rc) return rc; if (inode->i_mode != mode) { diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c index 67993808f4da..ee9f51bab4c6 100644 --- a/fs/jffs2/fs.c +++ b/fs/jffs2/fs.c @@ -201,7 +201,7 @@ int jffs2_setattr(struct dentry *dentry, struct iattr *iattr) rc = jffs2_do_setattr(inode, iattr); if (!rc && (iattr->ia_valid & ATTR_MODE)) - rc = posix_acl_chmod(inode, inode->i_mode); + rc = posix_acl_chmod(&init_user_ns, inode, inode->i_mode); return rc; } diff --git a/fs/jffs2/security.c b/fs/jffs2/security.c index c2332e30f218..aef5522551db 100644 --- a/fs/jffs2/security.c +++ b/fs/jffs2/security.c @@ -57,6 +57,7 @@ static int jffs2_security_getxattr(const struct xattr_handler *handler, } static int jffs2_security_setxattr(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *unused, struct inode *inode, const char *name, const void *buffer, size_t size, int flags) diff --git a/fs/jffs2/xattr_trusted.c b/fs/jffs2/xattr_trusted.c index 5d6030826c52..cc3f24883e7d 100644 --- a/fs/jffs2/xattr_trusted.c +++ b/fs/jffs2/xattr_trusted.c @@ -25,6 +25,7 @@ static int jffs2_trusted_getxattr(const struct xattr_handler *handler, } static int jffs2_trusted_setxattr(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *unused, struct inode *inode, const char *name, const void *buffer, size_t size, int flags) diff --git a/fs/jffs2/xattr_user.c b/fs/jffs2/xattr_user.c index 9d027b4abcf9..fb945977c013 100644 --- a/fs/jffs2/xattr_user.c +++ b/fs/jffs2/xattr_user.c @@ -25,6 +25,7 @@ static int jffs2_user_getxattr(const struct xattr_handler *handler, } static int jffs2_user_setxattr(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *unused, struct inode *inode, const char *name, const void *buffer, size_t size, int flags) diff --git a/fs/jfs/acl.c b/fs/jfs/acl.c index 92cc0ac2d1fc..cf79a34bfada 100644 --- a/fs/jfs/acl.c +++ b/fs/jfs/acl.c @@ -101,7 +101,7 @@ int jfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) tid = txBegin(inode->i_sb, 0); mutex_lock(&JFS_IP(inode)->commit_mutex); if (type == ACL_TYPE_ACCESS && acl) { - rc = posix_acl_update_mode(inode, &mode, &acl); + rc = posix_acl_update_mode(&init_user_ns, inode, &mode, &acl); if (rc) goto end_tx; if (mode != inode->i_mode) diff --git a/fs/jfs/file.c b/fs/jfs/file.c index ff49876e9c9b..61c3b0c1fbf6 100644 --- a/fs/jfs/file.c +++ b/fs/jfs/file.c @@ -122,7 +122,7 @@ int jfs_setattr(struct dentry *dentry, struct iattr *iattr) mark_inode_dirty(inode); if (iattr->ia_valid & ATTR_MODE) - rc = posix_acl_chmod(inode, inode->i_mode); + rc = posix_acl_chmod(&init_user_ns, inode, inode->i_mode); return rc; } diff --git a/fs/jfs/xattr.c b/fs/jfs/xattr.c index db41e7803163..f9273f6901c8 100644 --- a/fs/jfs/xattr.c +++ b/fs/jfs/xattr.c @@ -932,6 +932,7 @@ static int jfs_xattr_get(const struct xattr_handler *handler, } static int jfs_xattr_set(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) @@ -950,6 +951,7 @@ static int jfs_xattr_get_os2(const struct xattr_handler *handler, } static int jfs_xattr_set_os2(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index 86bd4c593b78..7e44052b42e1 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -319,6 +319,7 @@ static int kernfs_vfs_xattr_get(const struct xattr_handler *handler, } static int kernfs_vfs_xattr_set(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *unused, struct inode *inode, const char *suffix, const void *value, size_t size, int flags) @@ -385,6 +386,7 @@ static int kernfs_vfs_user_xattr_rm(struct kernfs_node *kn, } static int kernfs_vfs_user_xattr_set(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *unused, struct inode *inode, const char *suffix, const void *value, size_t size, int flags) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 2f4679a62712..a07530cf673d 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -7491,6 +7491,7 @@ nfs4_release_lockowner(struct nfs_server *server, struct nfs4_lock_state *lsp) #define XATTR_NAME_NFSV4_ACL "system.nfs4_acl" static int nfs4_xattr_set_nfs4_acl(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *unused, struct inode *inode, const char *key, const void *buf, size_t buflen, int flags) @@ -7513,6 +7514,7 @@ static bool nfs4_xattr_list_nfs4_acl(struct dentry *dentry) #ifdef CONFIG_NFS_V4_SECURITY_LABEL static int nfs4_xattr_set_nfs4_label(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *unused, struct inode *inode, const char *key, const void *buf, size_t buflen, int flags) @@ -7563,6 +7565,7 @@ nfs4_listxattr_nfs4_label(struct inode *inode, char *list, size_t list_len) #ifdef CONFIG_NFS_V4_2 static int nfs4_xattr_set_nfs4_user(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *unused, struct inode *inode, const char *key, const void *buf, size_t buflen, int flags) diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index b0f66604532a..b83f222558e3 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -113,10 +113,12 @@ static __be32 nfsacld_proc_setacl(struct svc_rqst *rqstp) fh_lock(fh); - error = set_posix_acl(inode, ACL_TYPE_ACCESS, argp->acl_access); + error = set_posix_acl(&init_user_ns, inode, ACL_TYPE_ACCESS, + argp->acl_access); if (error) goto out_drop_lock; - error = set_posix_acl(inode, ACL_TYPE_DEFAULT, argp->acl_default); + error = set_posix_acl(&init_user_ns, inode, ACL_TYPE_DEFAULT, + argp->acl_default); if (error) goto out_drop_lock; diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index 7c30876a31a1..f18ec7e8094d 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -103,10 +103,12 @@ static __be32 nfsd3_proc_setacl(struct svc_rqst *rqstp) fh_lock(fh); - error = set_posix_acl(inode, ACL_TYPE_ACCESS, argp->acl_access); + error = set_posix_acl(&init_user_ns, inode, ACL_TYPE_ACCESS, + argp->acl_access); if (error) goto out_drop_lock; - error = set_posix_acl(inode, ACL_TYPE_DEFAULT, argp->acl_default); + error = set_posix_acl(&init_user_ns, inode, ACL_TYPE_DEFAULT, + argp->acl_default); out_drop_lock: fh_unlock(fh); diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c index 71292a0d6f09..eaa3a0cf38f1 100644 --- a/fs/nfsd/nfs4acl.c +++ b/fs/nfsd/nfs4acl.c @@ -781,12 +781,13 @@ nfsd4_set_nfs4_acl(struct svc_rqst *rqstp, struct svc_fh *fhp, fh_lock(fhp); - host_error = set_posix_acl(inode, ACL_TYPE_ACCESS, pacl); + host_error = set_posix_acl(&init_user_ns, inode, ACL_TYPE_ACCESS, pacl); if (host_error < 0) goto out_drop_lock; if (S_ISDIR(inode->i_mode)) { - host_error = set_posix_acl(inode, ACL_TYPE_DEFAULT, dpacl); + host_error = set_posix_acl(&init_user_ns, inode, + ACL_TYPE_DEFAULT, dpacl); } out_drop_lock: diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c index 7b07f5df3a29..990756cee4bd 100644 --- a/fs/ocfs2/acl.c +++ b/fs/ocfs2/acl.c @@ -274,7 +274,8 @@ int ocfs2_iop_set_acl(struct inode *inode, struct posix_acl *acl, int type) if (type == ACL_TYPE_ACCESS && acl) { umode_t mode; - status = posix_acl_update_mode(inode, &mode, &acl); + status = posix_acl_update_mode(&init_user_ns, inode, &mode, + &acl); if (status) goto unlock; diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index 9ccd19d8f7b1..36ae47a4aef6 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -7249,6 +7249,7 @@ static int ocfs2_xattr_security_get(const struct xattr_handler *handler, } static int ocfs2_xattr_security_set(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) @@ -7321,6 +7322,7 @@ static int ocfs2_xattr_trusted_get(const struct xattr_handler *handler, } static int ocfs2_xattr_trusted_set(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) @@ -7351,6 +7353,7 @@ static int ocfs2_xattr_user_get(const struct xattr_handler *handler, } static int ocfs2_xattr_user_set(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/fs/orangefs/acl.c b/fs/orangefs/acl.c index a25e6c890975..628921952d16 100644 --- a/fs/orangefs/acl.c +++ b/fs/orangefs/acl.c @@ -132,7 +132,8 @@ int orangefs_set_acl(struct inode *inode, struct posix_acl *acl, int type) * and "mode" to the new desired value. It is up to * us to propagate the new mode back to the server... */ - error = posix_acl_update_mode(inode, &iattr.ia_mode, &acl); + error = posix_acl_update_mode(&init_user_ns, inode, + &iattr.ia_mode, &acl); if (error) { gossip_err("%s: posix_acl_update_mode err: %d\n", __func__, diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c index 8ac9491ceb9a..563fe9ab8eb2 100644 --- a/fs/orangefs/inode.c +++ b/fs/orangefs/inode.c @@ -861,7 +861,7 @@ again: if (iattr->ia_valid & ATTR_MODE) /* change mod on a file that has ACLs */ - ret = posix_acl_chmod(inode, inode->i_mode); + ret = posix_acl_chmod(&init_user_ns, inode, inode->i_mode); ret = 0; out: diff --git a/fs/orangefs/xattr.c b/fs/orangefs/xattr.c index bdc285aea360..9a5b757fbd2f 100644 --- a/fs/orangefs/xattr.c +++ b/fs/orangefs/xattr.c @@ -526,6 +526,7 @@ out_unlock: } static int orangefs_xattr_set_default(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *unused, struct inode *inode, const char *name, diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 39b2e9aa0e5b..e24c995c5fd4 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -980,6 +980,7 @@ ovl_posix_acl_xattr_get(const struct xattr_handler *handler, static int __maybe_unused ovl_posix_acl_xattr_set(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *dentry, struct inode *inode, const char *name, const void *value, size_t size, int flags) @@ -1044,6 +1045,7 @@ static int ovl_own_xattr_get(const struct xattr_handler *handler, } static int ovl_own_xattr_set(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *dentry, struct inode *inode, const char *name, const void *value, size_t size, int flags) @@ -1059,6 +1061,7 @@ static int ovl_other_xattr_get(const struct xattr_handler *handler, } static int ovl_other_xattr_set(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *dentry, struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/fs/posix_acl.c b/fs/posix_acl.c index 9ce8214bfdac..d31b60f5d40d 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -558,8 +558,22 @@ __posix_acl_chmod(struct posix_acl **acl, gfp_t gfp, umode_t mode) } EXPORT_SYMBOL(__posix_acl_chmod); +/** + * posix_acl_chmod - chmod a posix acl + * + * @mnt_userns: user namespace of the mount @inode was found from + * @inode: inode to check permissions on + * @mode: the new mode of @inode + * + * If the inode has been found through an idmapped mount the user namespace of + * the vfsmount must be passed through @mnt_userns. This function will then + * take care to map the inode according to @mnt_userns before checking + * permissions. On non-idmapped mounts or if permission checking is to be + * performed on the raw inode simply passs init_user_ns. + */ int -posix_acl_chmod(struct inode *inode, umode_t mode) + posix_acl_chmod(struct user_namespace *mnt_userns, struct inode *inode, + umode_t mode) { struct posix_acl *acl; int ret = 0; @@ -638,9 +652,10 @@ EXPORT_SYMBOL_GPL(posix_acl_create); /** * posix_acl_update_mode - update mode in set_acl - * @inode: target inode - * @mode_p: mode (pointer) for update - * @acl: acl pointer + * @mnt_userns: user namespace of the mount @inode was found from + * @inode: target inode + * @mode_p: mode (pointer) for update + * @acl: acl pointer * * Update the file mode when setting an ACL: compute the new file permission * bits based on the ACL. In addition, if the ACL is equivalent to the new @@ -649,9 +664,16 @@ EXPORT_SYMBOL_GPL(posix_acl_create); * As with chmod, clear the setgid bit if the caller is not in the owning group * or capable of CAP_FSETID (see inode_change_ok). * + * If the inode has been found through an idmapped mount the user namespace of + * the vfsmount must be passed through @mnt_userns. This function will then + * take care to map the inode according to @mnt_userns before checking + * permissions. On non-idmapped mounts or if permission checking is to be + * performed on the raw inode simply passs init_user_ns. + * * Called from set_acl inode operations. */ -int posix_acl_update_mode(struct inode *inode, umode_t *mode_p, +int posix_acl_update_mode(struct user_namespace *mnt_userns, + struct inode *inode, umode_t *mode_p, struct posix_acl **acl) { umode_t mode = inode->i_mode; @@ -662,8 +684,8 @@ int posix_acl_update_mode(struct inode *inode, umode_t *mode_p, return error; if (error == 0) *acl = NULL; - if (!in_group_p(inode->i_gid) && - !capable_wrt_inode_uidgid(&init_user_ns, inode, CAP_FSETID)) + if (!in_group_p(i_gid_into_mnt(mnt_userns, inode)) && + !capable_wrt_inode_uidgid(mnt_userns, inode, CAP_FSETID)) mode &= ~S_ISGID; *mode_p = mode; return 0; @@ -675,7 +697,8 @@ EXPORT_SYMBOL(posix_acl_update_mode); */ static void posix_acl_fix_xattr_userns( struct user_namespace *to, struct user_namespace *from, - void *value, size_t size) + struct user_namespace *mnt_userns, + void *value, size_t size, bool from_user) { struct posix_acl_xattr_header *header = value; struct posix_acl_xattr_entry *entry = (void *)(header + 1), *end; @@ -700,10 +723,18 @@ static void posix_acl_fix_xattr_userns( switch(le16_to_cpu(entry->e_tag)) { case ACL_USER: uid = make_kuid(from, le32_to_cpu(entry->e_id)); + if (from_user) + uid = kuid_from_mnt(mnt_userns, uid); + else + uid = kuid_into_mnt(mnt_userns, uid); entry->e_id = cpu_to_le32(from_kuid(to, uid)); break; case ACL_GROUP: gid = make_kgid(from, le32_to_cpu(entry->e_id)); + if (from_user) + gid = kgid_from_mnt(mnt_userns, gid); + else + gid = kgid_into_mnt(mnt_userns, gid); entry->e_id = cpu_to_le32(from_kgid(to, gid)); break; default: @@ -712,20 +743,24 @@ static void posix_acl_fix_xattr_userns( } } -void posix_acl_fix_xattr_from_user(void *value, size_t size) +void posix_acl_fix_xattr_from_user(struct user_namespace *mnt_userns, + void *value, size_t size) { struct user_namespace *user_ns = current_user_ns(); - if (user_ns == &init_user_ns) + if ((user_ns == &init_user_ns) && (mnt_userns == &init_user_ns)) return; - posix_acl_fix_xattr_userns(&init_user_ns, user_ns, value, size); + posix_acl_fix_xattr_userns(&init_user_ns, user_ns, mnt_userns, value, + size, true); } -void posix_acl_fix_xattr_to_user(void *value, size_t size) +void posix_acl_fix_xattr_to_user(struct user_namespace *mnt_userns, + void *value, size_t size) { struct user_namespace *user_ns = current_user_ns(); - if (user_ns == &init_user_ns) + if ((user_ns == &init_user_ns) && (mnt_userns == &init_user_ns)) return; - posix_acl_fix_xattr_userns(user_ns, &init_user_ns, value, size); + posix_acl_fix_xattr_userns(user_ns, &init_user_ns, mnt_userns, value, + size, false); } /* @@ -865,7 +900,8 @@ posix_acl_xattr_get(const struct xattr_handler *handler, } int -set_posix_acl(struct inode *inode, int type, struct posix_acl *acl) +set_posix_acl(struct user_namespace *mnt_userns, struct inode *inode, + int type, struct posix_acl *acl) { if (!IS_POSIXACL(inode)) return -EOPNOTSUPP; @@ -874,7 +910,7 @@ set_posix_acl(struct inode *inode, int type, struct posix_acl *acl) if (type == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode)) return acl ? -EACCES : 0; - if (!inode_owner_or_capable(&init_user_ns, inode)) + if (!inode_owner_or_capable(mnt_userns, inode)) return -EPERM; if (acl) { @@ -888,9 +924,10 @@ EXPORT_SYMBOL(set_posix_acl); static int posix_acl_xattr_set(const struct xattr_handler *handler, - struct dentry *unused, struct inode *inode, - const char *name, const void *value, - size_t size, int flags) + struct user_namespace *mnt_userns, + struct dentry *unused, struct inode *inode, + const char *name, const void *value, size_t size, + int flags) { struct posix_acl *acl = NULL; int ret; @@ -900,7 +937,7 @@ posix_acl_xattr_set(const struct xattr_handler *handler, if (IS_ERR(acl)) return PTR_ERR(acl); } - ret = set_posix_acl(inode, handler->flags, acl); + ret = set_posix_acl(mnt_userns, inode, handler->flags, acl); posix_acl_release(acl); return ret; } @@ -934,7 +971,7 @@ int simple_set_acl(struct inode *inode, struct posix_acl *acl, int type) int error; if (type == ACL_TYPE_ACCESS) { - error = posix_acl_update_mode(inode, + error = posix_acl_update_mode(&init_user_ns, inode, &inode->i_mode, &acl); if (error) return error; diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c index ccd40df6eb45..4bf976bc7bad 100644 --- a/fs/reiserfs/xattr_acl.c +++ b/fs/reiserfs/xattr_acl.c @@ -40,7 +40,8 @@ reiserfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) reiserfs_write_unlock(inode->i_sb); if (error == 0) { if (type == ACL_TYPE_ACCESS && acl) { - error = posix_acl_update_mode(inode, &mode, &acl); + error = posix_acl_update_mode(&init_user_ns, inode, + &mode, &acl); if (error) goto unlock; update_mode = 1; @@ -399,5 +400,5 @@ int reiserfs_acl_chmod(struct inode *inode) !reiserfs_posixacl(inode->i_sb)) return 0; - return posix_acl_chmod(inode, inode->i_mode); + return posix_acl_chmod(&init_user_ns, inode, inode->i_mode); } diff --git a/fs/reiserfs/xattr_security.c b/fs/reiserfs/xattr_security.c index 20be9a0e5870..8965c8e5e172 100644 --- a/fs/reiserfs/xattr_security.c +++ b/fs/reiserfs/xattr_security.c @@ -21,7 +21,8 @@ security_get(const struct xattr_handler *handler, struct dentry *unused, } static int -security_set(const struct xattr_handler *handler, struct dentry *unused, +security_set(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *unused, struct inode *inode, const char *name, const void *buffer, size_t size, int flags) { diff --git a/fs/reiserfs/xattr_trusted.c b/fs/reiserfs/xattr_trusted.c index 5ed48da3d02b..d853cea2afcd 100644 --- a/fs/reiserfs/xattr_trusted.c +++ b/fs/reiserfs/xattr_trusted.c @@ -20,7 +20,8 @@ trusted_get(const struct xattr_handler *handler, struct dentry *unused, } static int -trusted_set(const struct xattr_handler *handler, struct dentry *unused, +trusted_set(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *unused, struct inode *inode, const char *name, const void *buffer, size_t size, int flags) { diff --git a/fs/reiserfs/xattr_user.c b/fs/reiserfs/xattr_user.c index a573ca45bacc..65d9cd10a5ea 100644 --- a/fs/reiserfs/xattr_user.c +++ b/fs/reiserfs/xattr_user.c @@ -18,7 +18,8 @@ user_get(const struct xattr_handler *handler, struct dentry *unused, } static int -user_set(const struct xattr_handler *handler, struct dentry *unused, +user_set(const struct xattr_handler *handler, struct user_namespace *mnt_userns, + struct dentry *unused, struct inode *inode, const char *name, const void *buffer, size_t size, int flags) { diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c index a0b9b349efe6..8f4135c22ab6 100644 --- a/fs/ubifs/xattr.c +++ b/fs/ubifs/xattr.c @@ -681,6 +681,7 @@ static int xattr_get(const struct xattr_handler *handler, } static int xattr_set(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *dentry, struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/fs/xattr.c b/fs/xattr.c index c669922e1bde..d777025121e0 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -175,7 +175,8 @@ __vfs_setxattr(struct dentry *dentry, struct inode *inode, const char *name, return -EOPNOTSUPP; if (size == 0) value = ""; /* empty EA, do not remove */ - return handler->set(handler, dentry, inode, name, value, size, flags); + return handler->set(handler, &init_user_ns, dentry, inode, name, value, + size, flags); } EXPORT_SYMBOL(__vfs_setxattr); @@ -281,7 +282,7 @@ vfs_setxattr(struct dentry *dentry, const char *name, const void *value, int error; if (size && strcmp(name, XATTR_NAME_CAPS) == 0) { - error = cap_convert_nscap(dentry, &value, size); + error = cap_convert_nscap(&init_user_ns, dentry, &value, size); if (error < 0) return error; size = error; @@ -450,7 +451,8 @@ __vfs_removexattr(struct dentry *dentry, const char *name) return PTR_ERR(handler); if (!handler->set) return -EOPNOTSUPP; - return handler->set(handler, dentry, inode, name, NULL, 0, XATTR_REPLACE); + return handler->set(handler, &init_user_ns, dentry, inode, name, NULL, + 0, XATTR_REPLACE); } EXPORT_SYMBOL(__vfs_removexattr); @@ -548,7 +550,8 @@ setxattr(struct dentry *d, const char __user *name, const void __user *value, } if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) || (strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0)) - posix_acl_fix_xattr_from_user(kvalue, size); + posix_acl_fix_xattr_from_user(&init_user_ns, kvalue, + size); } error = vfs_setxattr(d, kname, kvalue, size, flags); @@ -642,7 +645,8 @@ getxattr(struct dentry *d, const char __user *name, void __user *value, if (error > 0) { if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) || (strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0)) - posix_acl_fix_xattr_to_user(kvalue, error); + posix_acl_fix_xattr_to_user(&init_user_ns, kvalue, + error); if (size && copy_to_user(value, kvalue, error)) error = -EFAULT; } else if (error == -ERANGE && size >= XATTR_SIZE_MAX) { diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c index 779cb73b3d00..368351298bd5 100644 --- a/fs/xfs/xfs_acl.c +++ b/fs/xfs/xfs_acl.c @@ -252,7 +252,8 @@ xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) return error; if (type == ACL_TYPE_ACCESS) { - error = posix_acl_update_mode(inode, &mode, &acl); + error = posix_acl_update_mode(&init_user_ns, inode, &mode, + &acl); if (error) return error; set_mode = true; diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 08a478d25122..26d22edef741 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -807,7 +807,7 @@ xfs_setattr_nonsize( * Posix ACL code seems to care about this issue either. */ if (mask & ATTR_MODE) { - error = posix_acl_chmod(inode, inode->i_mode); + error = posix_acl_chmod(&init_user_ns, inode, inode->i_mode); if (error) return error; } diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c index bca48b308c02..12be32f66dc1 100644 --- a/fs/xfs/xfs_xattr.c +++ b/fs/xfs/xfs_xattr.c @@ -38,9 +38,10 @@ xfs_xattr_get(const struct xattr_handler *handler, struct dentry *unused, } static int -xfs_xattr_set(const struct xattr_handler *handler, struct dentry *unused, - struct inode *inode, const char *name, const void *value, - size_t size, int flags) +xfs_xattr_set(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *unused, + struct inode *inode, const char *name, const void *value, + size_t size, int flags) { struct xfs_da_args args = { .dp = XFS_I(inode), diff --git a/include/linux/capability.h b/include/linux/capability.h index 62bfa3ed84d7..da21ef118b04 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -273,6 +273,7 @@ static inline bool checkpoint_restore_ns_capable(struct user_namespace *ns) /* audit system wants to get cap info from files as well */ extern int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps); -extern int cap_convert_nscap(struct dentry *dentry, const void **ivalue, size_t size); +int cap_convert_nscap(struct user_namespace *mnt_userns, struct dentry *dentry, + const void **ivalue, size_t size); #endif /* !_LINUX_CAPABILITY_H */ diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index 85fb4c0c650a..6dcd8b8f6ab5 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -69,13 +69,15 @@ extern int __posix_acl_create(struct posix_acl **, gfp_t, umode_t *); extern int __posix_acl_chmod(struct posix_acl **, gfp_t, umode_t); extern struct posix_acl *get_posix_acl(struct inode *, int); -extern int set_posix_acl(struct inode *, int, struct posix_acl *); +extern int set_posix_acl(struct user_namespace *, struct inode *, int, + struct posix_acl *); #ifdef CONFIG_FS_POSIX_ACL -extern int posix_acl_chmod(struct inode *, umode_t); +int posix_acl_chmod(struct user_namespace *, struct inode *, umode_t); extern int posix_acl_create(struct inode *, umode_t *, struct posix_acl **, struct posix_acl **); -extern int posix_acl_update_mode(struct inode *, umode_t *, struct posix_acl **); +int posix_acl_update_mode(struct user_namespace *, struct inode *, umode_t *, + struct posix_acl **); extern int simple_set_acl(struct inode *, struct posix_acl *, int); extern int simple_acl_create(struct inode *, struct inode *); @@ -95,7 +97,8 @@ static inline void cache_no_acl(struct inode *inode) inode->i_default_acl = NULL; } #else -static inline int posix_acl_chmod(struct inode *inode, umode_t mode) +static inline int posix_acl_chmod(struct user_namespace *mnt_userns, + struct inode *inode, umode_t mode) { return 0; } diff --git a/include/linux/posix_acl_xattr.h b/include/linux/posix_acl_xattr.h index 2387709991b5..060e8d203181 100644 --- a/include/linux/posix_acl_xattr.h +++ b/include/linux/posix_acl_xattr.h @@ -33,13 +33,17 @@ posix_acl_xattr_count(size_t size) } #ifdef CONFIG_FS_POSIX_ACL -void posix_acl_fix_xattr_from_user(void *value, size_t size); -void posix_acl_fix_xattr_to_user(void *value, size_t size); +void posix_acl_fix_xattr_from_user(struct user_namespace *mnt_userns, + void *value, size_t size); +void posix_acl_fix_xattr_to_user(struct user_namespace *mnt_userns, + void *value, size_t size); #else -static inline void posix_acl_fix_xattr_from_user(void *value, size_t size) +static inline void posix_acl_fix_xattr_from_user(struct user_namespace *mnt_userns, + void *value, size_t size) { } -static inline void posix_acl_fix_xattr_to_user(void *value, size_t size) +static inline void posix_acl_fix_xattr_to_user(struct user_namespace *mnt_userns, + void *value, size_t size) { } #endif diff --git a/include/linux/xattr.h b/include/linux/xattr.h index 10b4dc2709f0..260c9bcb0edb 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -34,7 +34,8 @@ struct xattr_handler { int (*get)(const struct xattr_handler *, struct dentry *dentry, struct inode *inode, const char *name, void *buffer, size_t size); - int (*set)(const struct xattr_handler *, struct dentry *dentry, + int (*set)(const struct xattr_handler *, + struct user_namespace *mnt_userns, struct dentry *dentry, struct inode *inode, const char *name, const void *buffer, size_t size, int flags); }; diff --git a/mm/shmem.c b/mm/shmem.c index 1cb451e131ec..23b8e9c15a42 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1143,7 +1143,7 @@ static int shmem_setattr(struct dentry *dentry, struct iattr *attr) setattr_copy(&init_user_ns, inode, attr); if (attr->ia_valid & ATTR_MODE) - error = posix_acl_chmod(inode, inode->i_mode); + error = posix_acl_chmod(&init_user_ns, inode, inode->i_mode); return error; } @@ -3273,6 +3273,7 @@ static int shmem_xattr_handler_get(const struct xattr_handler *handler, } static int shmem_xattr_handler_set(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/net/socket.c b/net/socket.c index 33e8b6c4e1d3..c76703c6f480 100644 --- a/net/socket.c +++ b/net/socket.c @@ -334,6 +334,7 @@ static const struct xattr_handler sockfs_xattr_handler = { }; static int sockfs_security_xattr_set(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *dentry, struct inode *inode, const char *suffix, const void *value, size_t size, int flags) diff --git a/security/commoncap.c b/security/commoncap.c index 88ee345f7bfa..c3fd9b86ea9a 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -450,16 +450,33 @@ int cap_inode_getsecurity(struct inode *inode, const char *name, void **buffer, return size; } +/** + * rootid_from_xattr - translate root uid of vfs caps + * + * @value: vfs caps value which may be modified by this function + * @size: size of @ivalue + * @task_ns: user namespace of the caller + * @mnt_userns: user namespace of the mount the inode was found from + * + * If the inode has been found through an idmapped mount the user namespace of + * the vfsmount must be passed through @mnt_userns. This function will then + * take care to map the inode according to @mnt_userns before checking + * permissions. On non-idmapped mounts or if permission checking is to be + * performed on the raw inode simply passs init_user_ns. + */ static kuid_t rootid_from_xattr(const void *value, size_t size, - struct user_namespace *task_ns) + struct user_namespace *task_ns, + struct user_namespace *mnt_userns) { const struct vfs_ns_cap_data *nscap = value; + kuid_t rootkid; uid_t rootid = 0; if (size == XATTR_CAPS_SZ_3) rootid = le32_to_cpu(nscap->rootid); - return make_kuid(task_ns, rootid); + rootkid = make_kuid(task_ns, rootid); + return kuid_from_mnt(mnt_userns, rootkid); } static bool validheader(size_t size, const struct vfs_cap_data *cap) @@ -467,13 +484,27 @@ static bool validheader(size_t size, const struct vfs_cap_data *cap) return is_v2header(size, cap) || is_v3header(size, cap); } -/* +/** + * cap_convert_nscap - check vfs caps + * + * @mnt_userns: user namespace of the mount the inode was found from + * @dentry: used to retrieve inode to check permissions on + * @ivalue: vfs caps value which may be modified by this function + * @size: size of @ivalue + * * User requested a write of security.capability. If needed, update the * xattr to change from v2 to v3, or to fixup the v3 rootid. * + * If the inode has been found through an idmapped mount the user namespace of + * the vfsmount must be passed through @mnt_userns. This function will then + * take care to map the inode according to @mnt_userns before checking + * permissions. On non-idmapped mounts or if permission checking is to be + * performed on the raw inode simply passs init_user_ns. + * * If all is ok, we return the new size, on error return < 0. */ -int cap_convert_nscap(struct dentry *dentry, const void **ivalue, size_t size) +int cap_convert_nscap(struct user_namespace *mnt_userns, struct dentry *dentry, + const void **ivalue, size_t size) { struct vfs_ns_cap_data *nscap; uid_t nsrootid; @@ -489,14 +520,14 @@ int cap_convert_nscap(struct dentry *dentry, const void **ivalue, size_t size) return -EINVAL; if (!validheader(size, cap)) return -EINVAL; - if (!capable_wrt_inode_uidgid(&init_user_ns, inode, CAP_SETFCAP)) + if (!capable_wrt_inode_uidgid(mnt_userns, inode, CAP_SETFCAP)) return -EPERM; - if (size == XATTR_CAPS_SZ_2) + if (size == XATTR_CAPS_SZ_2 && (mnt_userns == &init_user_ns)) if (ns_capable(inode->i_sb->s_user_ns, CAP_SETFCAP)) /* user is privileged, just write the v2 */ return size; - rootid = rootid_from_xattr(*ivalue, size, task_ns); + rootid = rootid_from_xattr(*ivalue, size, task_ns, mnt_userns); if (!uid_valid(rootid)) return -EINVAL; -- cgit v1.2.3 From c7c7a1a18af4c3bb7749d33e3df3acdf0a95bbb5 Mon Sep 17 00:00:00 2001 From: Tycho Andersen Date: Thu, 21 Jan 2021 14:19:28 +0100 Subject: xattr: handle idmapped mounts When interacting with extended attributes the vfs verifies that the caller is privileged over the inode with which the extended attribute is associated. For posix access and posix default extended attributes a uid or gid can be stored on-disk. Let the functions handle posix extended attributes on idmapped mounts. If the inode is accessed through an idmapped mount we need to map it according to the mount's user namespace. Afterwards the checks are identical to non-idmapped mounts. This has no effect for e.g. security xattrs since they don't store uids or gids and don't perform permission checks on them like posix acls do. Link: https://lore.kernel.org/r/20210121131959.646623-10-christian.brauner@ubuntu.com Cc: Christoph Hellwig Cc: David Howells Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig Reviewed-by: James Morris Signed-off-by: Tycho Andersen Signed-off-by: Christian Brauner --- fs/cachefiles/xattr.c | 29 ++++---- fs/ecryptfs/crypto.c | 4 +- fs/ecryptfs/inode.c | 5 +- fs/ecryptfs/mmap.c | 4 +- fs/nfsd/vfs.c | 14 ++-- fs/overlayfs/copy_up.c | 14 ++-- fs/overlayfs/dir.c | 2 +- fs/overlayfs/inode.c | 9 +-- fs/overlayfs/overlayfs.h | 6 +- fs/overlayfs/super.c | 6 +- fs/xattr.c | 120 +++++++++++++++++++--------------- include/linux/xattr.h | 27 +++++--- security/apparmor/domain.c | 4 +- security/commoncap.c | 6 +- security/integrity/evm/evm_crypto.c | 11 ++-- security/integrity/evm/evm_main.c | 4 +- security/integrity/ima/ima_appraise.c | 8 +-- security/selinux/hooks.c | 3 +- security/smack/smack_lsm.c | 8 ++- 19 files changed, 160 insertions(+), 124 deletions(-) (limited to 'include') diff --git a/fs/cachefiles/xattr.c b/fs/cachefiles/xattr.c index 72e42438f3d7..a591b5e09637 100644 --- a/fs/cachefiles/xattr.c +++ b/fs/cachefiles/xattr.c @@ -39,8 +39,8 @@ int cachefiles_check_object_type(struct cachefiles_object *object) _enter("%p{%s}", object, type); /* attempt to install a type label directly */ - ret = vfs_setxattr(dentry, cachefiles_xattr_cache, type, 2, - XATTR_CREATE); + ret = vfs_setxattr(&init_user_ns, dentry, cachefiles_xattr_cache, type, + 2, XATTR_CREATE); if (ret == 0) { _debug("SET"); /* we succeeded */ goto error; @@ -54,7 +54,8 @@ int cachefiles_check_object_type(struct cachefiles_object *object) } /* read the current type label */ - ret = vfs_getxattr(dentry, cachefiles_xattr_cache, xtype, 3); + ret = vfs_getxattr(&init_user_ns, dentry, cachefiles_xattr_cache, xtype, + 3); if (ret < 0) { if (ret == -ERANGE) goto bad_type_length; @@ -110,9 +111,8 @@ int cachefiles_set_object_xattr(struct cachefiles_object *object, _debug("SET #%u", auxdata->len); clear_bit(FSCACHE_COOKIE_AUX_UPDATED, &object->fscache.cookie->flags); - ret = vfs_setxattr(dentry, cachefiles_xattr_cache, - &auxdata->type, auxdata->len, - XATTR_CREATE); + ret = vfs_setxattr(&init_user_ns, dentry, cachefiles_xattr_cache, + &auxdata->type, auxdata->len, XATTR_CREATE); if (ret < 0 && ret != -ENOMEM) cachefiles_io_error_obj( object, @@ -140,9 +140,8 @@ int cachefiles_update_object_xattr(struct cachefiles_object *object, _debug("SET #%u", auxdata->len); clear_bit(FSCACHE_COOKIE_AUX_UPDATED, &object->fscache.cookie->flags); - ret = vfs_setxattr(dentry, cachefiles_xattr_cache, - &auxdata->type, auxdata->len, - XATTR_REPLACE); + ret = vfs_setxattr(&init_user_ns, dentry, cachefiles_xattr_cache, + &auxdata->type, auxdata->len, XATTR_REPLACE); if (ret < 0 && ret != -ENOMEM) cachefiles_io_error_obj( object, @@ -171,7 +170,7 @@ int cachefiles_check_auxdata(struct cachefiles_object *object) if (!auxbuf) return -ENOMEM; - xlen = vfs_getxattr(dentry, cachefiles_xattr_cache, + xlen = vfs_getxattr(&init_user_ns, dentry, cachefiles_xattr_cache, &auxbuf->type, 512 + 1); ret = -ESTALE; if (xlen < 1 || @@ -213,7 +212,7 @@ int cachefiles_check_object_xattr(struct cachefiles_object *object, } /* read the current type label */ - ret = vfs_getxattr(dentry, cachefiles_xattr_cache, + ret = vfs_getxattr(&init_user_ns, dentry, cachefiles_xattr_cache, &auxbuf->type, 512 + 1); if (ret < 0) { if (ret == -ENODATA) @@ -270,9 +269,9 @@ int cachefiles_check_object_xattr(struct cachefiles_object *object, } /* update the current label */ - ret = vfs_setxattr(dentry, cachefiles_xattr_cache, - &auxdata->type, auxdata->len, - XATTR_REPLACE); + ret = vfs_setxattr(&init_user_ns, dentry, + cachefiles_xattr_cache, &auxdata->type, + auxdata->len, XATTR_REPLACE); if (ret < 0) { cachefiles_io_error_obj(object, "Can't update xattr on %lu" @@ -309,7 +308,7 @@ int cachefiles_remove_object_xattr(struct cachefiles_cache *cache, { int ret; - ret = vfs_removexattr(dentry, cachefiles_xattr_cache); + ret = vfs_removexattr(&init_user_ns, dentry, cachefiles_xattr_cache); if (ret < 0) { if (ret == -ENOENT || ret == -ENODATA) ret = 0; diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c index 0681540c48d9..943e523f4c9d 100644 --- a/fs/ecryptfs/crypto.c +++ b/fs/ecryptfs/crypto.c @@ -1110,8 +1110,8 @@ ecryptfs_write_metadata_to_xattr(struct dentry *ecryptfs_dentry, } inode_lock(lower_inode); - rc = __vfs_setxattr(lower_dentry, lower_inode, ECRYPTFS_XATTR_NAME, - page_virt, size, 0); + rc = __vfs_setxattr(&init_user_ns, lower_dentry, lower_inode, + ECRYPTFS_XATTR_NAME, page_virt, size, 0); if (!rc && ecryptfs_inode) fsstack_copy_attr_all(ecryptfs_inode, lower_inode); inode_unlock(lower_inode); diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index ac6472a82567..b9ccc4085d46 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -1024,7 +1024,8 @@ ecryptfs_setxattr(struct dentry *dentry, struct inode *inode, rc = -EOPNOTSUPP; goto out; } - rc = vfs_setxattr(lower_dentry, name, value, size, flags); + rc = vfs_setxattr(&init_user_ns, lower_dentry, name, value, size, + flags); if (!rc && inode) fsstack_copy_attr_all(inode, d_inode(lower_dentry)); out: @@ -1089,7 +1090,7 @@ static int ecryptfs_removexattr(struct dentry *dentry, struct inode *inode, goto out; } inode_lock(lower_inode); - rc = __vfs_removexattr(lower_dentry, name); + rc = __vfs_removexattr(&init_user_ns, lower_dentry, name); inode_unlock(lower_inode); out: return rc; diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c index 019572c6b39a..2f333a40ff4d 100644 --- a/fs/ecryptfs/mmap.c +++ b/fs/ecryptfs/mmap.c @@ -426,8 +426,8 @@ static int ecryptfs_write_inode_size_to_xattr(struct inode *ecryptfs_inode) if (size < 0) size = 8; put_unaligned_be64(i_size_read(ecryptfs_inode), xattr_virt); - rc = __vfs_setxattr(lower_dentry, lower_inode, ECRYPTFS_XATTR_NAME, - xattr_virt, size, 0); + rc = __vfs_setxattr(&init_user_ns, lower_dentry, lower_inode, + ECRYPTFS_XATTR_NAME, xattr_virt, size, 0); inode_unlock(lower_inode); if (rc) printk(KERN_ERR "Error whilst attempting to write inode size " diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 1905b39be1c2..37d85046b4d6 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -499,7 +499,8 @@ int nfsd4_is_junction(struct dentry *dentry) return 0; if (!(inode->i_mode & S_ISVTX)) return 0; - if (vfs_getxattr(dentry, NFSD_JUNCTION_XATTR_NAME, NULL, 0) <= 0) + if (vfs_getxattr(&init_user_ns, dentry, NFSD_JUNCTION_XATTR_NAME, + NULL, 0) <= 0) return 0; return 1; } @@ -2149,7 +2150,7 @@ nfsd_getxattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name, inode_lock_shared(inode); - len = vfs_getxattr(dentry, name, NULL, 0); + len = vfs_getxattr(&init_user_ns, dentry, name, NULL, 0); /* * Zero-length attribute, just return. @@ -2176,7 +2177,7 @@ nfsd_getxattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name, goto out; } - len = vfs_getxattr(dentry, name, buf, len); + len = vfs_getxattr(&init_user_ns, dentry, name, buf, len); if (len <= 0) { kvfree(buf); buf = NULL; @@ -2283,7 +2284,8 @@ nfsd_removexattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name) fh_lock(fhp); - ret = __vfs_removexattr_locked(fhp->fh_dentry, name, NULL); + ret = __vfs_removexattr_locked(&init_user_ns, fhp->fh_dentry, + name, NULL); fh_unlock(fhp); fh_drop_write(fhp); @@ -2307,8 +2309,8 @@ nfsd_setxattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name, return nfserrno(ret); fh_lock(fhp); - ret = __vfs_setxattr_locked(fhp->fh_dentry, name, buf, len, flags, - NULL); + ret = __vfs_setxattr_locked(&init_user_ns, fhp->fh_dentry, name, buf, + len, flags, NULL); fh_unlock(fhp); fh_drop_write(fhp); diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 3e9957ae19fa..f81b836c2256 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -85,9 +85,9 @@ int ovl_copy_xattr(struct super_block *sb, struct dentry *old, if (ovl_is_private_xattr(sb, name)) continue; retry: - size = vfs_getxattr(old, name, value, value_size); + size = vfs_getxattr(&init_user_ns, old, name, value, value_size); if (size == -ERANGE) - size = vfs_getxattr(old, name, NULL, 0); + size = vfs_getxattr(&init_user_ns, old, name, NULL, 0); if (size < 0) { error = size; @@ -114,7 +114,7 @@ retry: error = 0; continue; /* Discard */ } - error = vfs_setxattr(new, name, value, size, 0); + error = vfs_setxattr(&init_user_ns, new, name, value, size, 0); if (error) { if (error != -EOPNOTSUPP || ovl_must_copy_xattr(name)) break; @@ -795,7 +795,7 @@ static ssize_t ovl_getxattr(struct dentry *dentry, char *name, char **value) ssize_t res; char *buf; - res = vfs_getxattr(dentry, name, NULL, 0); + res = vfs_getxattr(&init_user_ns, dentry, name, NULL, 0); if (res == -ENODATA || res == -EOPNOTSUPP) res = 0; @@ -804,7 +804,7 @@ static ssize_t ovl_getxattr(struct dentry *dentry, char *name, char **value) if (!buf) return -ENOMEM; - res = vfs_getxattr(dentry, name, buf, res); + res = vfs_getxattr(&init_user_ns, dentry, name, buf, res); if (res < 0) kfree(buf); else @@ -846,8 +846,8 @@ static int ovl_copy_up_meta_inode_data(struct ovl_copy_up_ctx *c) * don't want that to happen for normal copy-up operation. */ if (capability) { - err = vfs_setxattr(upperpath.dentry, XATTR_NAME_CAPS, - capability, cap_size, 0); + err = vfs_setxattr(&init_user_ns, upperpath.dentry, + XATTR_NAME_CAPS, capability, cap_size, 0); if (err) goto out_free; } diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 29840820a46c..d75c96cb18c3 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -449,7 +449,7 @@ static int ovl_set_upper_acl(struct dentry *upperdentry, const char *name, if (err < 0) goto out_free; - err = vfs_setxattr(upperdentry, name, buffer, size, XATTR_CREATE); + err = vfs_setxattr(&init_user_ns, upperdentry, name, buffer, size, XATTR_CREATE); out_free: kfree(buffer); return err; diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 5aa66881dbd7..023fde466e3a 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -352,7 +352,7 @@ int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char *name, goto out; if (!value && !upperdentry) { - err = vfs_getxattr(realdentry, name, NULL, 0); + err = vfs_getxattr(&init_user_ns, realdentry, name, NULL, 0); if (err < 0) goto out_drop_write; } @@ -367,10 +367,11 @@ int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char *name, old_cred = ovl_override_creds(dentry->d_sb); if (value) - err = vfs_setxattr(realdentry, name, value, size, flags); + err = vfs_setxattr(&init_user_ns, realdentry, name, value, size, + flags); else { WARN_ON(flags != XATTR_REPLACE); - err = vfs_removexattr(realdentry, name); + err = vfs_removexattr(&init_user_ns, realdentry, name); } revert_creds(old_cred); @@ -392,7 +393,7 @@ int ovl_xattr_get(struct dentry *dentry, struct inode *inode, const char *name, ovl_i_dentry_upper(inode) ?: ovl_dentry_lower(dentry); old_cred = ovl_override_creds(dentry->d_sb); - res = vfs_getxattr(realdentry, name, value, size); + res = vfs_getxattr(&init_user_ns, realdentry, name, value, size); revert_creds(old_cred); return res; } diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index b487e48c7fd4..0002834f664a 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -186,7 +186,7 @@ static inline ssize_t ovl_do_getxattr(struct ovl_fs *ofs, struct dentry *dentry, size_t size) { const char *name = ovl_xattr(ofs, ox); - return vfs_getxattr(dentry, name, value, size); + return vfs_getxattr(&init_user_ns, dentry, name, value, size); } static inline int ovl_do_setxattr(struct ovl_fs *ofs, struct dentry *dentry, @@ -194,7 +194,7 @@ static inline int ovl_do_setxattr(struct ovl_fs *ofs, struct dentry *dentry, size_t size) { const char *name = ovl_xattr(ofs, ox); - int err = vfs_setxattr(dentry, name, value, size, 0); + int err = vfs_setxattr(&init_user_ns, dentry, name, value, size, 0); pr_debug("setxattr(%pd2, \"%s\", \"%*pE\", %zu, 0) = %i\n", dentry, name, min((int)size, 48), value, size, err); return err; @@ -204,7 +204,7 @@ static inline int ovl_do_removexattr(struct ovl_fs *ofs, struct dentry *dentry, enum ovl_xattr ox) { const char *name = ovl_xattr(ofs, ox); - int err = vfs_removexattr(dentry, name); + int err = vfs_removexattr(&init_user_ns, dentry, name); pr_debug("removexattr(%pd2, \"%s\") = %i\n", dentry, name, err); return err; } diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index e24c995c5fd4..8168ab2dda11 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -794,11 +794,13 @@ retry: * allowed as upper are limited to "normal" ones, where checking * for the above two errors is sufficient. */ - err = vfs_removexattr(work, XATTR_NAME_POSIX_ACL_DEFAULT); + err = vfs_removexattr(&init_user_ns, work, + XATTR_NAME_POSIX_ACL_DEFAULT); if (err && err != -ENODATA && err != -EOPNOTSUPP) goto out_dput; - err = vfs_removexattr(work, XATTR_NAME_POSIX_ACL_ACCESS); + err = vfs_removexattr(&init_user_ns, work, + XATTR_NAME_POSIX_ACL_ACCESS); if (err && err != -ENODATA && err != -EOPNOTSUPP) goto out_dput; diff --git a/fs/xattr.c b/fs/xattr.c index d777025121e0..a49541713b11 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -83,7 +83,8 @@ xattr_resolve_name(struct inode *inode, const char **name) * because different namespaces have very different rules. */ static int -xattr_permission(struct inode *inode, const char *name, int mask) +xattr_permission(struct user_namespace *mnt_userns, struct inode *inode, + const char *name, int mask) { /* * We can never set or remove an extended attribute on a read-only @@ -128,11 +129,11 @@ xattr_permission(struct inode *inode, const char *name, int mask) return (mask & MAY_WRITE) ? -EPERM : -ENODATA; if (S_ISDIR(inode->i_mode) && (inode->i_mode & S_ISVTX) && (mask & MAY_WRITE) && - !inode_owner_or_capable(&init_user_ns, inode)) + !inode_owner_or_capable(mnt_userns, inode)) return -EPERM; } - return inode_permission(&init_user_ns, inode, mask); + return inode_permission(mnt_userns, inode, mask); } /* @@ -163,8 +164,9 @@ xattr_supported_namespace(struct inode *inode, const char *prefix) EXPORT_SYMBOL(xattr_supported_namespace); int -__vfs_setxattr(struct dentry *dentry, struct inode *inode, const char *name, - const void *value, size_t size, int flags) +__vfs_setxattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct inode *inode, const char *name, const void *value, + size_t size, int flags) { const struct xattr_handler *handler; @@ -175,7 +177,7 @@ __vfs_setxattr(struct dentry *dentry, struct inode *inode, const char *name, return -EOPNOTSUPP; if (size == 0) value = ""; /* empty EA, do not remove */ - return handler->set(handler, &init_user_ns, dentry, inode, name, value, + return handler->set(handler, mnt_userns, dentry, inode, name, value, size, flags); } EXPORT_SYMBOL(__vfs_setxattr); @@ -184,6 +186,7 @@ EXPORT_SYMBOL(__vfs_setxattr); * __vfs_setxattr_noperm - perform setxattr operation without performing * permission checks. * + * @mnt_userns - user namespace of the mount the inode was found from * @dentry - object to perform setxattr on * @name - xattr name to set * @value - value to set @name to @@ -196,8 +199,9 @@ EXPORT_SYMBOL(__vfs_setxattr); * is executed. It also assumes that the caller will make the appropriate * permission checks. */ -int __vfs_setxattr_noperm(struct dentry *dentry, const char *name, - const void *value, size_t size, int flags) +int __vfs_setxattr_noperm(struct user_namespace *mnt_userns, + struct dentry *dentry, const char *name, + const void *value, size_t size, int flags) { struct inode *inode = dentry->d_inode; int error = -EAGAIN; @@ -207,7 +211,8 @@ int __vfs_setxattr_noperm(struct dentry *dentry, const char *name, if (issec) inode->i_flags &= ~S_NOSEC; if (inode->i_opflags & IOP_XATTR) { - error = __vfs_setxattr(dentry, inode, name, value, size, flags); + error = __vfs_setxattr(mnt_userns, dentry, inode, name, value, + size, flags); if (!error) { fsnotify_xattr(dentry); security_inode_post_setxattr(dentry, name, value, @@ -246,14 +251,14 @@ int __vfs_setxattr_noperm(struct dentry *dentry, const char *name, * a delegation was broken on, NULL if none. */ int -__vfs_setxattr_locked(struct dentry *dentry, const char *name, - const void *value, size_t size, int flags, - struct inode **delegated_inode) +__vfs_setxattr_locked(struct user_namespace *mnt_userns, struct dentry *dentry, + const char *name, const void *value, size_t size, + int flags, struct inode **delegated_inode) { struct inode *inode = dentry->d_inode; int error; - error = xattr_permission(inode, name, MAY_WRITE); + error = xattr_permission(mnt_userns, inode, name, MAY_WRITE); if (error) return error; @@ -265,7 +270,8 @@ __vfs_setxattr_locked(struct dentry *dentry, const char *name, if (error) goto out; - error = __vfs_setxattr_noperm(dentry, name, value, size, flags); + error = __vfs_setxattr_noperm(mnt_userns, dentry, name, value, + size, flags); out: return error; @@ -273,8 +279,8 @@ out: EXPORT_SYMBOL_GPL(__vfs_setxattr_locked); int -vfs_setxattr(struct dentry *dentry, const char *name, const void *value, - size_t size, int flags) +vfs_setxattr(struct user_namespace *mnt_userns, struct dentry *dentry, + const char *name, const void *value, size_t size, int flags) { struct inode *inode = dentry->d_inode; struct inode *delegated_inode = NULL; @@ -282,7 +288,7 @@ vfs_setxattr(struct dentry *dentry, const char *name, const void *value, int error; if (size && strcmp(name, XATTR_NAME_CAPS) == 0) { - error = cap_convert_nscap(&init_user_ns, dentry, &value, size); + error = cap_convert_nscap(mnt_userns, dentry, &value, size); if (error < 0) return error; size = error; @@ -290,8 +296,8 @@ vfs_setxattr(struct dentry *dentry, const char *name, const void *value, retry_deleg: inode_lock(inode); - error = __vfs_setxattr_locked(dentry, name, value, size, flags, - &delegated_inode); + error = __vfs_setxattr_locked(mnt_userns, dentry, name, value, size, + flags, &delegated_inode); inode_unlock(inode); if (delegated_inode) { @@ -341,15 +347,16 @@ out_noalloc: * Returns the result of alloc, if failed, or the getxattr operation. */ ssize_t -vfs_getxattr_alloc(struct dentry *dentry, const char *name, char **xattr_value, - size_t xattr_size, gfp_t flags) +vfs_getxattr_alloc(struct user_namespace *mnt_userns, struct dentry *dentry, + const char *name, char **xattr_value, size_t xattr_size, + gfp_t flags) { const struct xattr_handler *handler; struct inode *inode = dentry->d_inode; char *value = *xattr_value; int error; - error = xattr_permission(inode, name, MAY_READ); + error = xattr_permission(mnt_userns, inode, name, MAY_READ); if (error) return error; @@ -390,12 +397,13 @@ __vfs_getxattr(struct dentry *dentry, struct inode *inode, const char *name, EXPORT_SYMBOL(__vfs_getxattr); ssize_t -vfs_getxattr(struct dentry *dentry, const char *name, void *value, size_t size) +vfs_getxattr(struct user_namespace *mnt_userns, struct dentry *dentry, + const char *name, void *value, size_t size) { struct inode *inode = dentry->d_inode; int error; - error = xattr_permission(inode, name, MAY_READ); + error = xattr_permission(mnt_userns, inode, name, MAY_READ); if (error) return error; @@ -441,7 +449,8 @@ vfs_listxattr(struct dentry *dentry, char *list, size_t size) EXPORT_SYMBOL_GPL(vfs_listxattr); int -__vfs_removexattr(struct dentry *dentry, const char *name) +__vfs_removexattr(struct user_namespace *mnt_userns, struct dentry *dentry, + const char *name) { struct inode *inode = d_inode(dentry); const struct xattr_handler *handler; @@ -451,8 +460,8 @@ __vfs_removexattr(struct dentry *dentry, const char *name) return PTR_ERR(handler); if (!handler->set) return -EOPNOTSUPP; - return handler->set(handler, &init_user_ns, dentry, inode, name, NULL, - 0, XATTR_REPLACE); + return handler->set(handler, mnt_userns, dentry, inode, name, NULL, 0, + XATTR_REPLACE); } EXPORT_SYMBOL(__vfs_removexattr); @@ -466,13 +475,14 @@ EXPORT_SYMBOL(__vfs_removexattr); * a delegation was broken on, NULL if none. */ int -__vfs_removexattr_locked(struct dentry *dentry, const char *name, - struct inode **delegated_inode) +__vfs_removexattr_locked(struct user_namespace *mnt_userns, + struct dentry *dentry, const char *name, + struct inode **delegated_inode) { struct inode *inode = dentry->d_inode; int error; - error = xattr_permission(inode, name, MAY_WRITE); + error = xattr_permission(mnt_userns, inode, name, MAY_WRITE); if (error) return error; @@ -484,7 +494,7 @@ __vfs_removexattr_locked(struct dentry *dentry, const char *name, if (error) goto out; - error = __vfs_removexattr(dentry, name); + error = __vfs_removexattr(mnt_userns, dentry, name); if (!error) { fsnotify_xattr(dentry); @@ -497,7 +507,8 @@ out: EXPORT_SYMBOL_GPL(__vfs_removexattr_locked); int -vfs_removexattr(struct dentry *dentry, const char *name) +vfs_removexattr(struct user_namespace *mnt_userns, struct dentry *dentry, + const char *name) { struct inode *inode = dentry->d_inode; struct inode *delegated_inode = NULL; @@ -505,7 +516,8 @@ vfs_removexattr(struct dentry *dentry, const char *name) retry_deleg: inode_lock(inode); - error = __vfs_removexattr_locked(dentry, name, &delegated_inode); + error = __vfs_removexattr_locked(mnt_userns, dentry, + name, &delegated_inode); inode_unlock(inode); if (delegated_inode) { @@ -522,8 +534,9 @@ EXPORT_SYMBOL_GPL(vfs_removexattr); * Extended attribute SET operations */ static long -setxattr(struct dentry *d, const char __user *name, const void __user *value, - size_t size, int flags) +setxattr(struct user_namespace *mnt_userns, struct dentry *d, + const char __user *name, const void __user *value, size_t size, + int flags) { int error; void *kvalue = NULL; @@ -550,11 +563,10 @@ setxattr(struct dentry *d, const char __user *name, const void __user *value, } if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) || (strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0)) - posix_acl_fix_xattr_from_user(&init_user_ns, kvalue, - size); + posix_acl_fix_xattr_from_user(mnt_userns, kvalue, size); } - error = vfs_setxattr(d, kname, kvalue, size, flags); + error = vfs_setxattr(mnt_userns, d, kname, kvalue, size, flags); out: kvfree(kvalue); @@ -567,13 +579,15 @@ static int path_setxattr(const char __user *pathname, { struct path path; int error; + retry: error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path); if (error) return error; error = mnt_want_write(path.mnt); if (!error) { - error = setxattr(path.dentry, name, value, size, flags); + error = setxattr(mnt_user_ns(path.mnt), path.dentry, name, + value, size, flags); mnt_drop_write(path.mnt); } path_put(&path); @@ -609,7 +623,9 @@ SYSCALL_DEFINE5(fsetxattr, int, fd, const char __user *, name, audit_file(f.file); error = mnt_want_write_file(f.file); if (!error) { - error = setxattr(f.file->f_path.dentry, name, value, size, flags); + error = setxattr(file_mnt_user_ns(f.file), + f.file->f_path.dentry, name, + value, size, flags); mnt_drop_write_file(f.file); } fdput(f); @@ -620,8 +636,8 @@ SYSCALL_DEFINE5(fsetxattr, int, fd, const char __user *, name, * Extended attribute GET operations */ static ssize_t -getxattr(struct dentry *d, const char __user *name, void __user *value, - size_t size) +getxattr(struct user_namespace *mnt_userns, struct dentry *d, + const char __user *name, void __user *value, size_t size) { ssize_t error; void *kvalue = NULL; @@ -641,12 +657,11 @@ getxattr(struct dentry *d, const char __user *name, void __user *value, return -ENOMEM; } - error = vfs_getxattr(d, kname, kvalue, size); + error = vfs_getxattr(mnt_userns, d, kname, kvalue, size); if (error > 0) { if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) || (strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0)) - posix_acl_fix_xattr_to_user(&init_user_ns, kvalue, - error); + posix_acl_fix_xattr_to_user(mnt_userns, kvalue, error); if (size && copy_to_user(value, kvalue, error)) error = -EFAULT; } else if (error == -ERANGE && size >= XATTR_SIZE_MAX) { @@ -670,7 +685,7 @@ retry: error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path); if (error) return error; - error = getxattr(path.dentry, name, value, size); + error = getxattr(mnt_user_ns(path.mnt), path.dentry, name, value, size); path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; @@ -700,7 +715,8 @@ SYSCALL_DEFINE4(fgetxattr, int, fd, const char __user *, name, if (!f.file) return error; audit_file(f.file); - error = getxattr(f.file->f_path.dentry, name, value, size); + error = getxattr(file_mnt_user_ns(f.file), f.file->f_path.dentry, + name, value, size); fdput(f); return error; } @@ -784,7 +800,8 @@ SYSCALL_DEFINE3(flistxattr, int, fd, char __user *, list, size_t, size) * Extended attribute REMOVE operations */ static long -removexattr(struct dentry *d, const char __user *name) +removexattr(struct user_namespace *mnt_userns, struct dentry *d, + const char __user *name) { int error; char kname[XATTR_NAME_MAX + 1]; @@ -795,7 +812,7 @@ removexattr(struct dentry *d, const char __user *name) if (error < 0) return error; - return vfs_removexattr(d, kname); + return vfs_removexattr(mnt_userns, d, kname); } static int path_removexattr(const char __user *pathname, @@ -809,7 +826,7 @@ retry: return error; error = mnt_want_write(path.mnt); if (!error) { - error = removexattr(path.dentry, name); + error = removexattr(mnt_user_ns(path.mnt), path.dentry, name); mnt_drop_write(path.mnt); } path_put(&path); @@ -842,7 +859,8 @@ SYSCALL_DEFINE2(fremovexattr, int, fd, const char __user *, name) audit_file(f.file); error = mnt_want_write_file(f.file); if (!error) { - error = removexattr(f.file->f_path.dentry, name); + error = removexattr(file_mnt_user_ns(f.file), + f.file->f_path.dentry, name); mnt_drop_write_file(f.file); } fdput(f); diff --git a/include/linux/xattr.h b/include/linux/xattr.h index 260c9bcb0edb..4c379d23ec6e 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -16,6 +16,7 @@ #include #include #include +#include #include struct inode; @@ -49,18 +50,26 @@ struct xattr { }; ssize_t __vfs_getxattr(struct dentry *, struct inode *, const char *, void *, size_t); -ssize_t vfs_getxattr(struct dentry *, const char *, void *, size_t); +ssize_t vfs_getxattr(struct user_namespace *, struct dentry *, const char *, + void *, size_t); ssize_t vfs_listxattr(struct dentry *d, char *list, size_t size); -int __vfs_setxattr(struct dentry *, struct inode *, const char *, const void *, size_t, int); -int __vfs_setxattr_noperm(struct dentry *, const char *, const void *, size_t, int); -int __vfs_setxattr_locked(struct dentry *, const char *, const void *, size_t, int, struct inode **); -int vfs_setxattr(struct dentry *, const char *, const void *, size_t, int); -int __vfs_removexattr(struct dentry *, const char *); -int __vfs_removexattr_locked(struct dentry *, const char *, struct inode **); -int vfs_removexattr(struct dentry *, const char *); +int __vfs_setxattr(struct user_namespace *, struct dentry *, struct inode *, + const char *, const void *, size_t, int); +int __vfs_setxattr_noperm(struct user_namespace *, struct dentry *, + const char *, const void *, size_t, int); +int __vfs_setxattr_locked(struct user_namespace *, struct dentry *, + const char *, const void *, size_t, int, + struct inode **); +int vfs_setxattr(struct user_namespace *, struct dentry *, const char *, + const void *, size_t, int); +int __vfs_removexattr(struct user_namespace *, struct dentry *, const char *); +int __vfs_removexattr_locked(struct user_namespace *, struct dentry *, + const char *, struct inode **); +int vfs_removexattr(struct user_namespace *, struct dentry *, const char *); ssize_t generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size); -ssize_t vfs_getxattr_alloc(struct dentry *dentry, const char *name, +ssize_t vfs_getxattr_alloc(struct user_namespace *mnt_userns, + struct dentry *dentry, const char *name, char **xattr_value, size_t size, gfp_t flags); int xattr_supported_namespace(struct inode *inode, const char *prefix); diff --git a/security/apparmor/domain.c b/security/apparmor/domain.c index f919ebd042fd..16f184bc48de 100644 --- a/security/apparmor/domain.c +++ b/security/apparmor/domain.c @@ -324,8 +324,8 @@ static int aa_xattrs_match(const struct linux_binprm *bprm, d = bprm->file->f_path.dentry; for (i = 0; i < profile->xattr_count; i++) { - size = vfs_getxattr_alloc(d, profile->xattrs[i], &value, - value_size, GFP_KERNEL); + size = vfs_getxattr_alloc(&init_user_ns, d, profile->xattrs[i], + &value, value_size, GFP_KERNEL); if (size >= 0) { u32 perm; diff --git a/security/commoncap.c b/security/commoncap.c index c3fd9b86ea9a..745dc1f2c97f 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -313,7 +313,7 @@ int cap_inode_killpriv(struct dentry *dentry) { int error; - error = __vfs_removexattr(dentry, XATTR_NAME_CAPS); + error = __vfs_removexattr(&init_user_ns, dentry, XATTR_NAME_CAPS); if (error == -EOPNOTSUPP) error = 0; return error; @@ -386,8 +386,8 @@ int cap_inode_getsecurity(struct inode *inode, const char *name, void **buffer, return -EINVAL; size = sizeof(struct vfs_ns_cap_data); - ret = (int) vfs_getxattr_alloc(dentry, XATTR_NAME_CAPS, - &tmpbuf, size, GFP_NOFS); + ret = (int)vfs_getxattr_alloc(&init_user_ns, dentry, XATTR_NAME_CAPS, + &tmpbuf, size, GFP_NOFS); dput(dentry); if (ret < 0) diff --git a/security/integrity/evm/evm_crypto.c b/security/integrity/evm/evm_crypto.c index 168c3b78ac47..f720f78cbbb1 100644 --- a/security/integrity/evm/evm_crypto.c +++ b/security/integrity/evm/evm_crypto.c @@ -222,7 +222,7 @@ static int evm_calc_hmac_or_hash(struct dentry *dentry, ima_present = true; continue; } - size = vfs_getxattr_alloc(dentry, xattr->name, + size = vfs_getxattr_alloc(&init_user_ns, dentry, xattr->name, &xattr_value, xattr_size, GFP_NOFS); if (size == -ENOMEM) { error = -ENOMEM; @@ -275,8 +275,8 @@ static int evm_is_immutable(struct dentry *dentry, struct inode *inode) return 1; /* Do this the hard way */ - rc = vfs_getxattr_alloc(dentry, XATTR_NAME_EVM, (char **)&xattr_data, 0, - GFP_NOFS); + rc = vfs_getxattr_alloc(&init_user_ns, dentry, XATTR_NAME_EVM, + (char **)&xattr_data, 0, GFP_NOFS); if (rc <= 0) { if (rc == -ENODATA) return 0; @@ -319,11 +319,12 @@ int evm_update_evmxattr(struct dentry *dentry, const char *xattr_name, xattr_value_len, &data); if (rc == 0) { data.hdr.xattr.sha1.type = EVM_XATTR_HMAC; - rc = __vfs_setxattr_noperm(dentry, XATTR_NAME_EVM, + rc = __vfs_setxattr_noperm(&init_user_ns, dentry, + XATTR_NAME_EVM, &data.hdr.xattr.data[1], SHA1_DIGEST_SIZE + 1, 0); } else if (rc == -ENODATA && (inode->i_opflags & IOP_XATTR)) { - rc = __vfs_removexattr(dentry, XATTR_NAME_EVM); + rc = __vfs_removexattr(&init_user_ns, dentry, XATTR_NAME_EVM); } return rc; } diff --git a/security/integrity/evm/evm_main.c b/security/integrity/evm/evm_main.c index 76d19146d74b..0de367aaa2d3 100644 --- a/security/integrity/evm/evm_main.c +++ b/security/integrity/evm/evm_main.c @@ -146,8 +146,8 @@ static enum integrity_status evm_verify_hmac(struct dentry *dentry, /* if status is not PASS, try to check again - against -ENOMEM */ /* first need to know the sig type */ - rc = vfs_getxattr_alloc(dentry, XATTR_NAME_EVM, (char **)&xattr_data, 0, - GFP_NOFS); + rc = vfs_getxattr_alloc(&init_user_ns, dentry, XATTR_NAME_EVM, + (char **)&xattr_data, 0, GFP_NOFS); if (rc <= 0) { evm_status = INTEGRITY_FAIL; if (rc == -ENODATA) { diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c index 8361941ee0a1..70b643c41c6b 100644 --- a/security/integrity/ima/ima_appraise.c +++ b/security/integrity/ima/ima_appraise.c @@ -94,7 +94,7 @@ static int ima_fix_xattr(struct dentry *dentry, iint->ima_hash->xattr.ng.type = IMA_XATTR_DIGEST_NG; iint->ima_hash->xattr.ng.algo = algo; } - rc = __vfs_setxattr_noperm(dentry, XATTR_NAME_IMA, + rc = __vfs_setxattr_noperm(&init_user_ns, dentry, XATTR_NAME_IMA, &iint->ima_hash->xattr.data[offset], (sizeof(iint->ima_hash->xattr) - offset) + iint->ima_hash->length, 0); @@ -215,8 +215,8 @@ int ima_read_xattr(struct dentry *dentry, { ssize_t ret; - ret = vfs_getxattr_alloc(dentry, XATTR_NAME_IMA, (char **)xattr_value, - 0, GFP_NOFS); + ret = vfs_getxattr_alloc(&init_user_ns, dentry, XATTR_NAME_IMA, + (char **)xattr_value, 0, GFP_NOFS); if (ret == -EOPNOTSUPP) ret = 0; return ret; @@ -520,7 +520,7 @@ void ima_inode_post_setattr(struct dentry *dentry) action = ima_must_appraise(inode, MAY_ACCESS, POST_SETATTR); if (!action) - __vfs_removexattr(dentry, XATTR_NAME_IMA); + __vfs_removexattr(&init_user_ns, dentry, XATTR_NAME_IMA); iint = integrity_iint_find(inode); if (iint) { set_bit(IMA_CHANGE_ATTR, &iint->atomic_flags); diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 9d6d3da2caf2..2efedd7001b2 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -6526,7 +6526,8 @@ static int selinux_inode_notifysecctx(struct inode *inode, void *ctx, u32 ctxlen */ static int selinux_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen) { - return __vfs_setxattr_noperm(dentry, XATTR_NAME_SELINUX, ctx, ctxlen, 0); + return __vfs_setxattr_noperm(&init_user_ns, dentry, XATTR_NAME_SELINUX, + ctx, ctxlen, 0); } static int selinux_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen) diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index f69c3dd9a0c6..746e5743accc 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -3425,7 +3425,7 @@ static void smack_d_instantiate(struct dentry *opt_dentry, struct inode *inode) */ if (isp->smk_flags & SMK_INODE_CHANGED) { isp->smk_flags &= ~SMK_INODE_CHANGED; - rc = __vfs_setxattr(dp, inode, + rc = __vfs_setxattr(&init_user_ns, dp, inode, XATTR_NAME_SMACKTRANSMUTE, TRANS_TRUE, TRANS_TRUE_SIZE, 0); @@ -4597,12 +4597,14 @@ static int smack_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid) static int smack_inode_notifysecctx(struct inode *inode, void *ctx, u32 ctxlen) { - return smack_inode_setsecurity(inode, XATTR_SMACK_SUFFIX, ctx, ctxlen, 0); + return smack_inode_setsecurity(inode, XATTR_SMACK_SUFFIX, ctx, + ctxlen, 0); } static int smack_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen) { - return __vfs_setxattr_noperm(dentry, XATTR_NAME_SMACK, ctx, ctxlen, 0); + return __vfs_setxattr_noperm(&init_user_ns, dentry, XATTR_NAME_SMACK, + ctx, ctxlen, 0); } static int smack_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen) -- cgit v1.2.3 From 71bc356f93a1c589fad13f7487258f89c417976e Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 21 Jan 2021 14:19:29 +0100 Subject: commoncap: handle idmapped mounts When interacting with user namespace and non-user namespace aware filesystem capabilities the vfs will perform various security checks to determine whether or not the filesystem capabilities can be used by the caller, whether they need to be removed and so on. The main infrastructure for this resides in the capability codepaths but they are called through the LSM security infrastructure even though they are not technically an LSM or optional. This extends the existing security hooks security_inode_removexattr(), security_inode_killpriv(), security_inode_getsecurity() to pass down the mount's user namespace and makes them aware of idmapped mounts. In order to actually get filesystem capabilities from disk the capability infrastructure exposes the get_vfs_caps_from_disk() helper. For user namespace aware filesystem capabilities a root uid is stored alongside the capabilities. In order to determine whether the caller can make use of the filesystem capability or whether it needs to be ignored it is translated according to the superblock's user namespace. If it can be translated to uid 0 according to that id mapping the caller can use the filesystem capabilities stored on disk. If we are accessing the inode that holds the filesystem capabilities through an idmapped mount we map the root uid according to the mount's user namespace. Afterwards the checks are identical to non-idmapped mounts: reading filesystem caps from disk enforces that the root uid associated with the filesystem capability must have a mapping in the superblock's user namespace and that the caller is either in the same user namespace or is a descendant of the superblock's user namespace. For filesystems that are mountable inside user namespace the caller can just mount the filesystem and won't usually need to idmap it. If they do want to idmap it they can create an idmapped mount and mark it with a user namespace they created and which is thus a descendant of s_user_ns. For filesystems that are not mountable inside user namespaces the descendant rule is trivially true because the s_user_ns will be the initial user namespace. If the initial user namespace is passed nothing changes so non-idmapped mounts will see identical behavior as before. Link: https://lore.kernel.org/r/20210121131959.646623-11-christian.brauner@ubuntu.com Cc: Christoph Hellwig Cc: David Howells Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig Acked-by: James Morris Signed-off-by: Christian Brauner --- fs/attr.c | 2 +- fs/xattr.c | 18 ++++++++----- include/linux/capability.h | 4 ++- include/linux/lsm_hook_defs.h | 15 ++++++----- include/linux/lsm_hooks.h | 1 + include/linux/security.h | 54 +++++++++++++++++++++++-------------- kernel/auditsc.c | 5 ++-- security/commoncap.c | 62 ++++++++++++++++++++++++++++++++++--------- security/security.c | 25 ++++++++++------- security/selinux/hooks.c | 20 ++++++++------ security/smack/smack_lsm.c | 14 +++++----- 11 files changed, 146 insertions(+), 74 deletions(-) (limited to 'include') diff --git a/fs/attr.c b/fs/attr.c index f4543d2abdfb..c2d3bc0869d4 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -143,7 +143,7 @@ kill_priv: if (ia_valid & ATTR_KILL_PRIV) { int error; - error = security_inode_killpriv(dentry); + error = security_inode_killpriv(mnt_userns, dentry); if (error) return error; } diff --git a/fs/xattr.c b/fs/xattr.c index a49541713b11..79c439d31eaa 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -262,7 +262,8 @@ __vfs_setxattr_locked(struct user_namespace *mnt_userns, struct dentry *dentry, if (error) return error; - error = security_inode_setxattr(dentry, name, value, size, flags); + error = security_inode_setxattr(mnt_userns, dentry, name, value, size, + flags); if (error) goto out; @@ -313,18 +314,20 @@ retry_deleg: EXPORT_SYMBOL_GPL(vfs_setxattr); static ssize_t -xattr_getsecurity(struct inode *inode, const char *name, void *value, - size_t size) +xattr_getsecurity(struct user_namespace *mnt_userns, struct inode *inode, + const char *name, void *value, size_t size) { void *buffer = NULL; ssize_t len; if (!value || !size) { - len = security_inode_getsecurity(inode, name, &buffer, false); + len = security_inode_getsecurity(mnt_userns, inode, name, + &buffer, false); goto out_noalloc; } - len = security_inode_getsecurity(inode, name, &buffer, true); + len = security_inode_getsecurity(mnt_userns, inode, name, &buffer, + true); if (len < 0) return len; if (size < len) { @@ -414,7 +417,8 @@ vfs_getxattr(struct user_namespace *mnt_userns, struct dentry *dentry, if (!strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN)) { const char *suffix = name + XATTR_SECURITY_PREFIX_LEN; - int ret = xattr_getsecurity(inode, suffix, value, size); + int ret = xattr_getsecurity(mnt_userns, inode, suffix, value, + size); /* * Only overwrite the return value if a security module * is actually active. @@ -486,7 +490,7 @@ __vfs_removexattr_locked(struct user_namespace *mnt_userns, if (error) return error; - error = security_inode_removexattr(dentry, name); + error = security_inode_removexattr(mnt_userns, dentry, name); if (error) goto out; diff --git a/include/linux/capability.h b/include/linux/capability.h index da21ef118b04..65efb74c3585 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -271,7 +271,9 @@ static inline bool checkpoint_restore_ns_capable(struct user_namespace *ns) } /* audit system wants to get cap info from files as well */ -extern int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps); +int get_vfs_caps_from_disk(struct user_namespace *mnt_userns, + const struct dentry *dentry, + struct cpu_vfs_cap_data *cpu_caps); int cap_convert_nscap(struct user_namespace *mnt_userns, struct dentry *dentry, const void **ivalue, size_t size); diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 7aaa753b8608..df4cdad6681e 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -133,17 +133,20 @@ LSM_HOOK(int, 0, inode_follow_link, struct dentry *dentry, struct inode *inode, LSM_HOOK(int, 0, inode_permission, struct inode *inode, int mask) LSM_HOOK(int, 0, inode_setattr, struct dentry *dentry, struct iattr *attr) LSM_HOOK(int, 0, inode_getattr, const struct path *path) -LSM_HOOK(int, 0, inode_setxattr, struct dentry *dentry, const char *name, - const void *value, size_t size, int flags) +LSM_HOOK(int, 0, inode_setxattr, struct user_namespace *mnt_userns, + struct dentry *dentry, const char *name, const void *value, + size_t size, int flags) LSM_HOOK(void, LSM_RET_VOID, inode_post_setxattr, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) LSM_HOOK(int, 0, inode_getxattr, struct dentry *dentry, const char *name) LSM_HOOK(int, 0, inode_listxattr, struct dentry *dentry) -LSM_HOOK(int, 0, inode_removexattr, struct dentry *dentry, const char *name) +LSM_HOOK(int, 0, inode_removexattr, struct user_namespace *mnt_userns, + struct dentry *dentry, const char *name) LSM_HOOK(int, 0, inode_need_killpriv, struct dentry *dentry) -LSM_HOOK(int, 0, inode_killpriv, struct dentry *dentry) -LSM_HOOK(int, -EOPNOTSUPP, inode_getsecurity, struct inode *inode, - const char *name, void **buffer, bool alloc) +LSM_HOOK(int, 0, inode_killpriv, struct user_namespace *mnt_userns, + struct dentry *dentry) +LSM_HOOK(int, -EOPNOTSUPP, inode_getsecurity, struct user_namespace *mnt_userns, + struct inode *inode, const char *name, void **buffer, bool alloc) LSM_HOOK(int, -EOPNOTSUPP, inode_setsecurity, struct inode *inode, const char *name, const void *value, size_t size, int flags) LSM_HOOK(int, 0, inode_listsecurity, struct inode *inode, char *buffer, diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index a19adef1f088..98a5e263aabb 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -444,6 +444,7 @@ * @inode_killpriv: * The setuid bit is being removed. Remove similar security labels. * Called with the dentry->d_inode->i_mutex held. + * @mnt_userns: user namespace of the mount * @dentry is the dentry being changed. * Return 0 on success. If error is returned, then the operation * causing setuid bit removal is failed. diff --git a/include/linux/security.h b/include/linux/security.h index c35ea0ffccd9..4e4f6c31e413 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -145,13 +145,16 @@ extern int cap_capset(struct cred *new, const struct cred *old, const kernel_cap_t *inheritable, const kernel_cap_t *permitted); extern int cap_bprm_creds_from_file(struct linux_binprm *bprm, struct file *file); -extern int cap_inode_setxattr(struct dentry *dentry, const char *name, - const void *value, size_t size, int flags); -extern int cap_inode_removexattr(struct dentry *dentry, const char *name); -extern int cap_inode_need_killpriv(struct dentry *dentry); -extern int cap_inode_killpriv(struct dentry *dentry); -extern int cap_inode_getsecurity(struct inode *inode, const char *name, - void **buffer, bool alloc); +int cap_inode_setxattr(struct dentry *dentry, const char *name, + const void *value, size_t size, int flags); +int cap_inode_removexattr(struct user_namespace *mnt_userns, + struct dentry *dentry, const char *name); +int cap_inode_need_killpriv(struct dentry *dentry); +int cap_inode_killpriv(struct user_namespace *mnt_userns, + struct dentry *dentry); +int cap_inode_getsecurity(struct user_namespace *mnt_userns, + struct inode *inode, const char *name, void **buffer, + bool alloc); extern int cap_mmap_addr(unsigned long addr); extern int cap_mmap_file(struct file *file, unsigned long reqprot, unsigned long prot, unsigned long flags); @@ -345,16 +348,21 @@ int security_inode_follow_link(struct dentry *dentry, struct inode *inode, int security_inode_permission(struct inode *inode, int mask); int security_inode_setattr(struct dentry *dentry, struct iattr *attr); int security_inode_getattr(const struct path *path); -int security_inode_setxattr(struct dentry *dentry, const char *name, +int security_inode_setxattr(struct user_namespace *mnt_userns, + struct dentry *dentry, const char *name, const void *value, size_t size, int flags); void security_inode_post_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags); int security_inode_getxattr(struct dentry *dentry, const char *name); int security_inode_listxattr(struct dentry *dentry); -int security_inode_removexattr(struct dentry *dentry, const char *name); +int security_inode_removexattr(struct user_namespace *mnt_userns, + struct dentry *dentry, const char *name); int security_inode_need_killpriv(struct dentry *dentry); -int security_inode_killpriv(struct dentry *dentry); -int security_inode_getsecurity(struct inode *inode, const char *name, void **buffer, bool alloc); +int security_inode_killpriv(struct user_namespace *mnt_userns, + struct dentry *dentry); +int security_inode_getsecurity(struct user_namespace *mnt_userns, + struct inode *inode, const char *name, + void **buffer, bool alloc); int security_inode_setsecurity(struct inode *inode, const char *name, const void *value, size_t size, int flags); int security_inode_listsecurity(struct inode *inode, char *buffer, size_t buffer_size); void security_inode_getsecid(struct inode *inode, u32 *secid); @@ -831,8 +839,9 @@ static inline int security_inode_getattr(const struct path *path) return 0; } -static inline int security_inode_setxattr(struct dentry *dentry, - const char *name, const void *value, size_t size, int flags) +static inline int security_inode_setxattr(struct user_namespace *mnt_userns, + struct dentry *dentry, const char *name, const void *value, + size_t size, int flags) { return cap_inode_setxattr(dentry, name, value, size, flags); } @@ -852,10 +861,11 @@ static inline int security_inode_listxattr(struct dentry *dentry) return 0; } -static inline int security_inode_removexattr(struct dentry *dentry, - const char *name) +static inline int security_inode_removexattr(struct user_namespace *mnt_userns, + struct dentry *dentry, + const char *name) { - return cap_inode_removexattr(dentry, name); + return cap_inode_removexattr(mnt_userns, dentry, name); } static inline int security_inode_need_killpriv(struct dentry *dentry) @@ -863,14 +873,18 @@ static inline int security_inode_need_killpriv(struct dentry *dentry) return cap_inode_need_killpriv(dentry); } -static inline int security_inode_killpriv(struct dentry *dentry) +static inline int security_inode_killpriv(struct user_namespace *mnt_userns, + struct dentry *dentry) { - return cap_inode_killpriv(dentry); + return cap_inode_killpriv(mnt_userns, dentry); } -static inline int security_inode_getsecurity(struct inode *inode, const char *name, void **buffer, bool alloc) +static inline int security_inode_getsecurity(struct user_namespace *mnt_userns, + struct inode *inode, + const char *name, void **buffer, + bool alloc) { - return cap_inode_getsecurity(inode, name, buffer, alloc); + return cap_inode_getsecurity(mnt_userns, inode, name, buffer, alloc); } static inline int security_inode_setsecurity(struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/kernel/auditsc.c b/kernel/auditsc.c index ce8c9e2279ba..fdfdd71405ff 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1930,7 +1930,7 @@ static inline int audit_copy_fcaps(struct audit_names *name, if (!dentry) return 0; - rc = get_vfs_caps_from_disk(dentry, &caps); + rc = get_vfs_caps_from_disk(&init_user_ns, dentry, &caps); if (rc) return rc; @@ -2481,7 +2481,8 @@ int __audit_log_bprm_fcaps(struct linux_binprm *bprm, ax->d.next = context->aux; context->aux = (void *)ax; - get_vfs_caps_from_disk(bprm->file->f_path.dentry, &vcaps); + get_vfs_caps_from_disk(&init_user_ns, + bprm->file->f_path.dentry, &vcaps); ax->fcap.permitted = vcaps.permitted; ax->fcap.inheritable = vcaps.inheritable; diff --git a/security/commoncap.c b/security/commoncap.c index 745dc1f2c97f..234b074c2c58 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -303,17 +303,25 @@ int cap_inode_need_killpriv(struct dentry *dentry) /** * cap_inode_killpriv - Erase the security markings on an inode - * @dentry: The inode/dentry to alter + * + * @mnt_userns: user namespace of the mount the inode was found from + * @dentry: The inode/dentry to alter * * Erase the privilege-enhancing security markings on an inode. * + * If the inode has been found through an idmapped mount the user namespace of + * the vfsmount must be passed through @mnt_userns. This function will then + * take care to map the inode according to @mnt_userns before checking + * permissions. On non-idmapped mounts or if permission checking is to be + * performed on the raw inode simply passs init_user_ns. + * * Returns 0 if successful, -ve on error. */ -int cap_inode_killpriv(struct dentry *dentry) +int cap_inode_killpriv(struct user_namespace *mnt_userns, struct dentry *dentry) { int error; - error = __vfs_removexattr(&init_user_ns, dentry, XATTR_NAME_CAPS); + error = __vfs_removexattr(mnt_userns, dentry, XATTR_NAME_CAPS); if (error == -EOPNOTSUPP) error = 0; return error; @@ -366,7 +374,8 @@ static bool is_v3header(size_t size, const struct vfs_cap_data *cap) * by the integrity subsystem, which really wants the unconverted values - * so that's good. */ -int cap_inode_getsecurity(struct inode *inode, const char *name, void **buffer, +int cap_inode_getsecurity(struct user_namespace *mnt_userns, + struct inode *inode, const char *name, void **buffer, bool alloc) { int size, ret; @@ -386,7 +395,7 @@ int cap_inode_getsecurity(struct inode *inode, const char *name, void **buffer, return -EINVAL; size = sizeof(struct vfs_ns_cap_data); - ret = (int)vfs_getxattr_alloc(&init_user_ns, dentry, XATTR_NAME_CAPS, + ret = (int)vfs_getxattr_alloc(mnt_userns, dentry, XATTR_NAME_CAPS, &tmpbuf, size, GFP_NOFS); dput(dentry); @@ -412,6 +421,9 @@ int cap_inode_getsecurity(struct inode *inode, const char *name, void **buffer, root = le32_to_cpu(nscap->rootid); kroot = make_kuid(fs_ns, root); + /* If this is an idmapped mount shift the kuid. */ + kroot = kuid_into_mnt(mnt_userns, kroot); + /* If the root kuid maps to a valid uid in current ns, then return * this as a nscap. */ mappedroot = from_kuid(current_user_ns(), kroot); @@ -595,10 +607,24 @@ static inline int bprm_caps_from_vfs_caps(struct cpu_vfs_cap_data *caps, return *effective ? ret : 0; } -/* +/** + * get_vfs_caps_from_disk - retrieve vfs caps from disk + * + * @mnt_userns: user namespace of the mount the inode was found from + * @dentry: dentry from which @inode is retrieved + * @cpu_caps: vfs capabilities + * * Extract the on-exec-apply capability sets for an executable file. + * + * If the inode has been found through an idmapped mount the user namespace of + * the vfsmount must be passed through @mnt_userns. This function will then + * take care to map the inode according to @mnt_userns before checking + * permissions. On non-idmapped mounts or if permission checking is to be + * performed on the raw inode simply passs init_user_ns. */ -int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps) +int get_vfs_caps_from_disk(struct user_namespace *mnt_userns, + const struct dentry *dentry, + struct cpu_vfs_cap_data *cpu_caps) { struct inode *inode = d_backing_inode(dentry); __u32 magic_etc; @@ -654,6 +680,7 @@ int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data /* Limit the caps to the mounter of the filesystem * or the more limited uid specified in the xattr. */ + rootkuid = kuid_into_mnt(mnt_userns, rootkuid); if (!rootid_owns_currentns(rootkuid)) return -ENODATA; @@ -699,7 +726,8 @@ static int get_file_caps(struct linux_binprm *bprm, struct file *file, if (!current_in_userns(file->f_path.mnt->mnt_sb->s_user_ns)) return 0; - rc = get_vfs_caps_from_disk(file->f_path.dentry, &vcaps); + rc = get_vfs_caps_from_disk(file_mnt_user_ns(file), + file->f_path.dentry, &vcaps); if (rc < 0) { if (rc == -EINVAL) printk(KERN_NOTICE "Invalid argument reading file caps for %s\n", @@ -964,16 +992,25 @@ int cap_inode_setxattr(struct dentry *dentry, const char *name, /** * cap_inode_removexattr - Determine whether an xattr may be removed - * @dentry: The inode/dentry being altered - * @name: The name of the xattr to be changed + * + * @mnt_userns: User namespace of the mount the inode was found from + * @dentry: The inode/dentry being altered + * @name: The name of the xattr to be changed * * Determine whether an xattr may be removed from an inode, returning 0 if * permission is granted, -ve if denied. * + * If the inode has been found through an idmapped mount the user namespace of + * the vfsmount must be passed through @mnt_userns. This function will then + * take care to map the inode according to @mnt_userns before checking + * permissions. On non-idmapped mounts or if permission checking is to be + * performed on the raw inode simply passs init_user_ns. + * * This is used to make sure security xattrs don't get removed by those who * aren't privileged to remove them. */ -int cap_inode_removexattr(struct dentry *dentry, const char *name) +int cap_inode_removexattr(struct user_namespace *mnt_userns, + struct dentry *dentry, const char *name) { struct user_namespace *user_ns = dentry->d_sb->s_user_ns; @@ -987,8 +1024,7 @@ int cap_inode_removexattr(struct dentry *dentry, const char *name) struct inode *inode = d_backing_inode(dentry); if (!inode) return -EINVAL; - if (!capable_wrt_inode_uidgid(&init_user_ns, inode, - CAP_SETFCAP)) + if (!capable_wrt_inode_uidgid(mnt_userns, inode, CAP_SETFCAP)) return -EPERM; return 0; } diff --git a/security/security.c b/security/security.c index 7b09cfbae94f..698a9f17bad7 100644 --- a/security/security.c +++ b/security/security.c @@ -1280,7 +1280,8 @@ int security_inode_getattr(const struct path *path) return call_int_hook(inode_getattr, 0, path); } -int security_inode_setxattr(struct dentry *dentry, const char *name, +int security_inode_setxattr(struct user_namespace *mnt_userns, + struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { int ret; @@ -1291,8 +1292,8 @@ int security_inode_setxattr(struct dentry *dentry, const char *name, * SELinux and Smack integrate the cap call, * so assume that all LSMs supplying this call do so. */ - ret = call_int_hook(inode_setxattr, 1, dentry, name, value, size, - flags); + ret = call_int_hook(inode_setxattr, 1, mnt_userns, dentry, name, value, + size, flags); if (ret == 1) ret = cap_inode_setxattr(dentry, name, value, size, flags); @@ -1327,7 +1328,8 @@ int security_inode_listxattr(struct dentry *dentry) return call_int_hook(inode_listxattr, 0, dentry); } -int security_inode_removexattr(struct dentry *dentry, const char *name) +int security_inode_removexattr(struct user_namespace *mnt_userns, + struct dentry *dentry, const char *name) { int ret; @@ -1337,9 +1339,9 @@ int security_inode_removexattr(struct dentry *dentry, const char *name) * SELinux and Smack integrate the cap call, * so assume that all LSMs supplying this call do so. */ - ret = call_int_hook(inode_removexattr, 1, dentry, name); + ret = call_int_hook(inode_removexattr, 1, mnt_userns, dentry, name); if (ret == 1) - ret = cap_inode_removexattr(dentry, name); + ret = cap_inode_removexattr(mnt_userns, dentry, name); if (ret) return ret; ret = ima_inode_removexattr(dentry, name); @@ -1353,12 +1355,15 @@ int security_inode_need_killpriv(struct dentry *dentry) return call_int_hook(inode_need_killpriv, 0, dentry); } -int security_inode_killpriv(struct dentry *dentry) +int security_inode_killpriv(struct user_namespace *mnt_userns, + struct dentry *dentry) { - return call_int_hook(inode_killpriv, 0, dentry); + return call_int_hook(inode_killpriv, 0, mnt_userns, dentry); } -int security_inode_getsecurity(struct inode *inode, const char *name, void **buffer, bool alloc) +int security_inode_getsecurity(struct user_namespace *mnt_userns, + struct inode *inode, const char *name, + void **buffer, bool alloc) { struct security_hook_list *hp; int rc; @@ -1369,7 +1374,7 @@ int security_inode_getsecurity(struct inode *inode, const char *name, void **buf * Only one module will provide an attribute with a given name. */ hlist_for_each_entry(hp, &security_hook_heads.inode_getsecurity, list) { - rc = hp->hook.inode_getsecurity(inode, name, buffer, alloc); + rc = hp->hook.inode_getsecurity(mnt_userns, inode, name, buffer, alloc); if (rc != LSM_RET_DEFAULT(inode_getsecurity)) return rc; } diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 2efedd7001b2..9719dd124221 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -3119,7 +3119,8 @@ static bool has_cap_mac_admin(bool audit) return true; } -static int selinux_inode_setxattr(struct dentry *dentry, const char *name, +static int selinux_inode_setxattr(struct user_namespace *mnt_userns, + struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct inode *inode = d_backing_inode(dentry); @@ -3140,13 +3141,13 @@ static int selinux_inode_setxattr(struct dentry *dentry, const char *name, } if (!selinux_initialized(&selinux_state)) - return (inode_owner_or_capable(&init_user_ns, inode) ? 0 : -EPERM); + return (inode_owner_or_capable(mnt_userns, inode) ? 0 : -EPERM); sbsec = inode->i_sb->s_security; if (!(sbsec->flags & SBLABEL_MNT)) return -EOPNOTSUPP; - if (!inode_owner_or_capable(&init_user_ns, inode)) + if (!inode_owner_or_capable(mnt_userns, inode)) return -EPERM; ad.type = LSM_AUDIT_DATA_DENTRY; @@ -3267,10 +3268,11 @@ static int selinux_inode_listxattr(struct dentry *dentry) return dentry_has_perm(cred, dentry, FILE__GETATTR); } -static int selinux_inode_removexattr(struct dentry *dentry, const char *name) +static int selinux_inode_removexattr(struct user_namespace *mnt_userns, + struct dentry *dentry, const char *name) { if (strcmp(name, XATTR_NAME_SELINUX)) { - int rc = cap_inode_removexattr(dentry, name); + int rc = cap_inode_removexattr(mnt_userns, dentry, name); if (rc) return rc; @@ -3336,7 +3338,9 @@ static int selinux_path_notify(const struct path *path, u64 mask, * * Permission check is handled by selinux_inode_getxattr hook. */ -static int selinux_inode_getsecurity(struct inode *inode, const char *name, void **buffer, bool alloc) +static int selinux_inode_getsecurity(struct user_namespace *mnt_userns, + struct inode *inode, const char *name, + void **buffer, bool alloc) { u32 size; int error; @@ -6533,8 +6537,8 @@ static int selinux_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen) static int selinux_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen) { int len = 0; - len = selinux_inode_getsecurity(inode, XATTR_SELINUX_SUFFIX, - ctx, true); + len = selinux_inode_getsecurity(&init_user_ns, inode, + XATTR_SELINUX_SUFFIX, ctx, true); if (len < 0) return len; *ctxlen = len; diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index 746e5743accc..12a45e61c1a5 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -1240,7 +1240,8 @@ static int smack_inode_getattr(const struct path *path) * * Returns 0 if access is permitted, an error code otherwise */ -static int smack_inode_setxattr(struct dentry *dentry, const char *name, +static int smack_inode_setxattr(struct user_namespace *mnt_userns, + struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct smk_audit_info ad; @@ -1362,7 +1363,8 @@ static int smack_inode_getxattr(struct dentry *dentry, const char *name) * * Returns 0 if access is permitted, an error code otherwise */ -static int smack_inode_removexattr(struct dentry *dentry, const char *name) +static int smack_inode_removexattr(struct user_namespace *mnt_userns, + struct dentry *dentry, const char *name) { struct inode_smack *isp; struct smk_audit_info ad; @@ -1377,7 +1379,7 @@ static int smack_inode_removexattr(struct dentry *dentry, const char *name) if (!smack_privileged(CAP_MAC_ADMIN)) rc = -EPERM; } else - rc = cap_inode_removexattr(dentry, name); + rc = cap_inode_removexattr(mnt_userns, dentry, name); if (rc != 0) return rc; @@ -1420,9 +1422,9 @@ static int smack_inode_removexattr(struct dentry *dentry, const char *name) * * Returns the size of the attribute or an error code */ -static int smack_inode_getsecurity(struct inode *inode, - const char *name, void **buffer, - bool alloc) +static int smack_inode_getsecurity(struct user_namespace *mnt_userns, + struct inode *inode, const char *name, + void **buffer, bool alloc) { struct socket_smack *ssp; struct socket *sock; -- cgit v1.2.3 From 0d56a4518d5eaf595a24ab2202e171330bb2ed72 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 21 Jan 2021 14:19:30 +0100 Subject: stat: handle idmapped mounts The generic_fillattr() helper fills in the basic attributes associated with an inode. Enable it to handle idmapped mounts. If the inode is accessed through an idmapped mount map it into the mount's user namespace before we store the uid and gid. If the initial user namespace is passed nothing changes so non-idmapped mounts will see identical behavior as before. Link: https://lore.kernel.org/r/20210121131959.646623-12-christian.brauner@ubuntu.com Cc: Christoph Hellwig Cc: David Howells Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig Reviewed-by: James Morris Signed-off-by: Christian Brauner --- fs/9p/vfs_inode.c | 4 ++-- fs/9p/vfs_inode_dotl.c | 4 ++-- fs/afs/inode.c | 2 +- fs/btrfs/inode.c | 2 +- fs/ceph/inode.c | 2 +- fs/cifs/inode.c | 2 +- fs/coda/inode.c | 2 +- fs/ecryptfs/inode.c | 4 ++-- fs/erofs/inode.c | 2 +- fs/exfat/file.c | 2 +- fs/ext2/inode.c | 2 +- fs/ext4/inode.c | 2 +- fs/f2fs/file.c | 2 +- fs/fat/file.c | 2 +- fs/fuse/dir.c | 2 +- fs/gfs2/inode.c | 2 +- fs/hfsplus/inode.c | 2 +- fs/kernfs/inode.c | 2 +- fs/libfs.c | 4 ++-- fs/minix/inode.c | 2 +- fs/nfs/inode.c | 2 +- fs/nfs/namespace.c | 2 +- fs/ocfs2/file.c | 2 +- fs/orangefs/inode.c | 2 +- fs/proc/base.c | 4 ++-- fs/proc/generic.c | 2 +- fs/proc/proc_net.c | 2 +- fs/proc/proc_sysctl.c | 2 +- fs/proc/root.c | 2 +- fs/stat.c | 20 ++++++++++++++------ fs/sysv/itree.c | 2 +- fs/ubifs/dir.c | 2 +- fs/udf/symlink.c | 2 +- fs/vboxsf/utils.c | 2 +- include/linux/fs.h | 2 +- mm/shmem.c | 2 +- 36 files changed, 54 insertions(+), 46 deletions(-) (limited to 'include') diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 9c3ff6e9ab82..c21b146c8d91 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -1027,7 +1027,7 @@ v9fs_vfs_getattr(const struct path *path, struct kstat *stat, p9_debug(P9_DEBUG_VFS, "dentry: %p\n", dentry); v9ses = v9fs_dentry2v9ses(dentry); if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) { - generic_fillattr(d_inode(dentry), stat); + generic_fillattr(&init_user_ns, d_inode(dentry), stat); return 0; } fid = v9fs_fid_lookup(dentry); @@ -1040,7 +1040,7 @@ v9fs_vfs_getattr(const struct path *path, struct kstat *stat, return PTR_ERR(st); v9fs_stat2inode(st, d_inode(dentry), dentry->d_sb, 0); - generic_fillattr(d_inode(dentry), stat); + generic_fillattr(&init_user_ns, d_inode(dentry), stat); p9stat_free(st); kfree(st); diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index 302553101fcb..984f28315d2a 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -468,7 +468,7 @@ v9fs_vfs_getattr_dotl(const struct path *path, struct kstat *stat, p9_debug(P9_DEBUG_VFS, "dentry: %p\n", dentry); v9ses = v9fs_dentry2v9ses(dentry); if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) { - generic_fillattr(d_inode(dentry), stat); + generic_fillattr(&init_user_ns, d_inode(dentry), stat); return 0; } fid = v9fs_fid_lookup(dentry); @@ -485,7 +485,7 @@ v9fs_vfs_getattr_dotl(const struct path *path, struct kstat *stat, return PTR_ERR(st); v9fs_stat2inode_dotl(st, d_inode(dentry), 0); - generic_fillattr(d_inode(dentry), stat); + generic_fillattr(&init_user_ns, d_inode(dentry), stat); /* Change block size to what the server returned */ stat->blksize = st->st_blksize; diff --git a/fs/afs/inode.c b/fs/afs/inode.c index b0d7b892090d..795ee5cb3817 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -745,7 +745,7 @@ int afs_getattr(const struct path *path, struct kstat *stat, do { read_seqbegin_or_lock(&vnode->cb_lock, &seq); - generic_fillattr(inode, stat); + generic_fillattr(&init_user_ns, inode, stat); if (test_bit(AFS_VNODE_SILLY_DELETED, &vnode->flags) && stat->nlink > 0) stat->nlink -= 1; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 6c18fb1a25af..a63faed171de 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -8842,7 +8842,7 @@ static int btrfs_getattr(const struct path *path, struct kstat *stat, STATX_ATTR_IMMUTABLE | STATX_ATTR_NODUMP); - generic_fillattr(inode, stat); + generic_fillattr(&init_user_ns, inode, stat); stat->dev = BTRFS_I(inode)->root->anon_dev; spin_lock(&BTRFS_I(inode)->lock); diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 145e26a4ddbb..179a2bb88538 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -2385,7 +2385,7 @@ int ceph_getattr(const struct path *path, struct kstat *stat, return err; } - generic_fillattr(inode, stat); + generic_fillattr(&init_user_ns, inode, stat); stat->ino = ceph_present_inode(inode); /* diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 27554f71f744..374abce7efaf 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -2408,7 +2408,7 @@ int cifs_getattr(const struct path *path, struct kstat *stat, return rc; } - generic_fillattr(inode, stat); + generic_fillattr(&init_user_ns, inode, stat); stat->blksize = cifs_sb->ctx->bsize; stat->ino = CIFS_I(inode)->uniqueid; diff --git a/fs/coda/inode.c b/fs/coda/inode.c index b1c70e2b9b1e..4d113e191cb8 100644 --- a/fs/coda/inode.c +++ b/fs/coda/inode.c @@ -256,7 +256,7 @@ int coda_getattr(const struct path *path, struct kstat *stat, { int err = coda_revalidate_inode(d_inode(path->dentry)); if (!err) - generic_fillattr(d_inode(path->dentry), stat); + generic_fillattr(&init_user_ns, d_inode(path->dentry), stat); return err; } diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index b9ccc4085d46..385b5e8741c0 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -977,7 +977,7 @@ static int ecryptfs_getattr_link(const struct path *path, struct kstat *stat, mount_crypt_stat = &ecryptfs_superblock_to_private( dentry->d_sb)->mount_crypt_stat; - generic_fillattr(d_inode(dentry), stat); + generic_fillattr(&init_user_ns, d_inode(dentry), stat); if (mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES) { char *target; size_t targetsiz; @@ -1005,7 +1005,7 @@ static int ecryptfs_getattr(const struct path *path, struct kstat *stat, if (!rc) { fsstack_copy_attr_all(d_inode(dentry), ecryptfs_inode_to_lower(d_inode(dentry))); - generic_fillattr(d_inode(dentry), stat); + generic_fillattr(&init_user_ns, d_inode(dentry), stat); stat->blocks = lower_stat.blocks; } return rc; diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c index 3e21c0e8adae..083818063ac6 100644 --- a/fs/erofs/inode.c +++ b/fs/erofs/inode.c @@ -343,7 +343,7 @@ int erofs_getattr(const struct path *path, struct kstat *stat, stat->attributes_mask |= (STATX_ATTR_COMPRESSED | STATX_ATTR_IMMUTABLE); - generic_fillattr(inode, stat); + generic_fillattr(&init_user_ns, inode, stat); return 0; } diff --git a/fs/exfat/file.c b/fs/exfat/file.c index ace35aa8e64b..e9705b3295d3 100644 --- a/fs/exfat/file.c +++ b/fs/exfat/file.c @@ -273,7 +273,7 @@ int exfat_getattr(const struct path *path, struct kstat *stat, struct inode *inode = d_backing_inode(path->dentry); struct exfat_inode_info *ei = EXFAT_I(inode); - generic_fillattr(inode, stat); + generic_fillattr(&init_user_ns, inode, stat); exfat_truncate_atime(&stat->atime); stat->result_mask |= STATX_BTIME; stat->btime.tv_sec = ei->i_crtime.tv_sec; diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 9de813635d8d..3d8acafca8ce 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -1660,7 +1660,7 @@ int ext2_getattr(const struct path *path, struct kstat *stat, STATX_ATTR_IMMUTABLE | STATX_ATTR_NODUMP); - generic_fillattr(inode, stat); + generic_fillattr(&init_user_ns, inode, stat); return 0; } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 24ea5851e90a..3a303d3f8423 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5571,7 +5571,7 @@ int ext4_getattr(const struct path *path, struct kstat *stat, STATX_ATTR_NODUMP | STATX_ATTR_VERITY); - generic_fillattr(inode, stat); + generic_fillattr(&init_user_ns, inode, stat); return 0; } diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 6ccdfe0606d9..44cd0dbdbb5d 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -820,7 +820,7 @@ int f2fs_getattr(const struct path *path, struct kstat *stat, STATX_ATTR_NODUMP | STATX_ATTR_VERITY); - generic_fillattr(inode, stat); + generic_fillattr(&init_user_ns, inode, stat); /* we need to show initial sectors used for inline_data/dentries */ if ((S_ISREG(inode->i_mode) && f2fs_has_inline_data(inode)) || diff --git a/fs/fat/file.c b/fs/fat/file.c index 805b501467e9..f7e04f533d31 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -398,7 +398,7 @@ int fat_getattr(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags) { struct inode *inode = d_inode(path->dentry); - generic_fillattr(inode, stat); + generic_fillattr(&init_user_ns, inode, stat); stat->blksize = MSDOS_SB(inode->i_sb)->cluster_size; if (MSDOS_SB(inode->i_sb)->options.nfs == FAT_NFS_NOSTALE_RO) { diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 74fdb6a7ebb3..d2e318ed9b26 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1087,7 +1087,7 @@ static int fuse_update_get_attr(struct inode *inode, struct file *file, forget_all_cached_acls(inode); err = fuse_do_getattr(inode, stat, file); } else if (stat) { - generic_fillattr(inode, stat); + generic_fillattr(&init_user_ns, inode, stat); stat->mode = fi->orig_i_mode; stat->ino = fi->orig_ino; } diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 728405d15a05..226b5b1dc1fa 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -2050,7 +2050,7 @@ static int gfs2_getattr(const struct path *path, struct kstat *stat, STATX_ATTR_IMMUTABLE | STATX_ATTR_NODUMP); - generic_fillattr(inode, stat); + generic_fillattr(&init_user_ns, inode, stat); if (gfs2_holder_initialized(&gh)) gfs2_glock_dq_uninit(&gh); diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index ffa137f8234e..642e067d8fe8 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -286,7 +286,7 @@ int hfsplus_getattr(const struct path *path, struct kstat *stat, stat->attributes_mask |= STATX_ATTR_APPEND | STATX_ATTR_IMMUTABLE | STATX_ATTR_NODUMP; - generic_fillattr(inode, stat); + generic_fillattr(&init_user_ns, inode, stat); return 0; } diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index 7e44052b42e1..032d3d7546d8 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -193,7 +193,7 @@ int kernfs_iop_getattr(const struct path *path, struct kstat *stat, kernfs_refresh_inode(kn, inode); mutex_unlock(&kernfs_mutex); - generic_fillattr(inode, stat); + generic_fillattr(&init_user_ns, inode, stat); return 0; } diff --git a/fs/libfs.c b/fs/libfs.c index a73fe109403c..508e9ea8e6f3 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -31,7 +31,7 @@ int simple_getattr(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); - generic_fillattr(inode, stat); + generic_fillattr(&init_user_ns, inode, stat); stat->blocks = inode->i_mapping->nrpages << (PAGE_SHIFT - 9); return 0; } @@ -1304,7 +1304,7 @@ static int empty_dir_getattr(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); - generic_fillattr(inode, stat); + generic_fillattr(&init_user_ns, inode, stat); return 0; } diff --git a/fs/minix/inode.c b/fs/minix/inode.c index 34f546404aa1..91c81d2fc90d 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -658,7 +658,7 @@ int minix_getattr(const struct path *path, struct kstat *stat, struct super_block *sb = path->dentry->d_sb; struct inode *inode = d_inode(path->dentry); - generic_fillattr(inode, stat); + generic_fillattr(&init_user_ns, inode, stat); if (INODE_VERSION(inode) == MINIX_V1) stat->blocks = (BLOCK_SIZE / 512) * V1_minix_blocks(stat->size, sb); else diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 522aa10a1a3e..cab123ec1664 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -857,7 +857,7 @@ out_no_revalidate: /* Only return attributes that were revalidated. */ stat->result_mask &= request_mask; out_no_update: - generic_fillattr(inode, stat); + generic_fillattr(&init_user_ns, inode, stat); stat->ino = nfs_compat_user_ino64(NFS_FILEID(inode)); if (S_ISDIR(inode->i_mode)) stat->blksize = NFS_SERVER(inode)->dtsize; diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c index 2bcbe38afe2e..55fc711e368b 100644 --- a/fs/nfs/namespace.c +++ b/fs/nfs/namespace.c @@ -213,7 +213,7 @@ nfs_namespace_getattr(const struct path *path, struct kstat *stat, { if (NFS_FH(d_inode(path->dentry))->size != 0) return nfs_getattr(path, stat, request_mask, query_flags); - generic_fillattr(d_inode(path->dentry), stat); + generic_fillattr(&init_user_ns, d_inode(path->dentry), stat); return 0; } diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index cabf355b148f..a070d4c9b6ed 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1313,7 +1313,7 @@ int ocfs2_getattr(const struct path *path, struct kstat *stat, goto bail; } - generic_fillattr(inode, stat); + generic_fillattr(&init_user_ns, inode, stat); /* * If there is inline data in the inode, the inode will normally not * have data blocks allocated (it may have an external xattr block). diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c index 563fe9ab8eb2..b94032f77e61 100644 --- a/fs/orangefs/inode.c +++ b/fs/orangefs/inode.c @@ -903,7 +903,7 @@ int orangefs_getattr(const struct path *path, struct kstat *stat, ret = orangefs_inode_getattr(inode, request_mask & STATX_SIZE ? ORANGEFS_GETATTR_SIZE : 0); if (ret == 0) { - generic_fillattr(inode, stat); + generic_fillattr(&init_user_ns, inode, stat); /* override block size reported to stat */ if (!(request_mask & STATX_SIZE)) diff --git a/fs/proc/base.c b/fs/proc/base.c index bb4e63a3684f..d45aa68c1f17 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1934,7 +1934,7 @@ int pid_getattr(const struct path *path, struct kstat *stat, struct proc_fs_info *fs_info = proc_sb_info(inode->i_sb); struct task_struct *task; - generic_fillattr(inode, stat); + generic_fillattr(&init_user_ns, inode, stat); stat->uid = GLOBAL_ROOT_UID; stat->gid = GLOBAL_ROOT_GID; @@ -3803,7 +3803,7 @@ static int proc_task_getattr(const struct path *path, struct kstat *stat, { struct inode *inode = d_inode(path->dentry); struct task_struct *p = get_proc_task(inode); - generic_fillattr(inode, stat); + generic_fillattr(&init_user_ns, inode, stat); if (p) { stat->nlink += get_nr_threads(p); diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 6d4fabab8aa7..0db96a761149 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -145,7 +145,7 @@ static int proc_getattr(const struct path *path, struct kstat *stat, } } - generic_fillattr(inode, stat); + generic_fillattr(&init_user_ns, inode, stat); return 0; } diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c index 18601042af99..4aef49ccf571 100644 --- a/fs/proc/proc_net.c +++ b/fs/proc/proc_net.c @@ -297,7 +297,7 @@ static int proc_tgid_net_getattr(const struct path *path, struct kstat *stat, net = get_proc_task_net(inode); - generic_fillattr(inode, stat); + generic_fillattr(&init_user_ns, inode, stat); if (net != NULL) { stat->nlink = net->proc_net->nlink; diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index ec67dbc1f705..87c828348140 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -840,7 +840,7 @@ static int proc_sys_getattr(const struct path *path, struct kstat *stat, if (IS_ERR(head)) return PTR_ERR(head); - generic_fillattr(inode, stat); + generic_fillattr(&init_user_ns, inode, stat); if (table) stat->mode = (stat->mode & S_IFMT) | table->mode; diff --git a/fs/proc/root.c b/fs/proc/root.c index 5e444d4f9717..244e4b6f15ef 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -311,7 +311,7 @@ void __init proc_root_init(void) static int proc_root_getattr(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { - generic_fillattr(d_inode(path->dentry), stat); + generic_fillattr(&init_user_ns, d_inode(path->dentry), stat); stat->nlink = proc_root.nlink + nr_processes(); return 0; } diff --git a/fs/stat.c b/fs/stat.c index dacecdda2e79..2c471c2fd766 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -26,21 +26,29 @@ /** * generic_fillattr - Fill in the basic attributes from the inode struct - * @inode: Inode to use as the source - * @stat: Where to fill in the attributes + * @mnt_userns: user namespace of the mount the inode was found from + * @inode: Inode to use as the source + * @stat: Where to fill in the attributes * * Fill in the basic attributes in the kstat structure from data that's to be * found on the VFS inode structure. This is the default if no getattr inode * operation is supplied. + * + * If the inode has been found through an idmapped mount the user namespace of + * the vfsmount must be passed through @mnt_userns. This function will then + * take care to map the inode according to @mnt_userns before filling in the + * uid and gid filds. On non-idmapped mounts or if permission checking is to be + * performed on the raw inode simply passs init_user_ns. */ -void generic_fillattr(struct inode *inode, struct kstat *stat) +void generic_fillattr(struct user_namespace *mnt_userns, struct inode *inode, + struct kstat *stat) { stat->dev = inode->i_sb->s_dev; stat->ino = inode->i_ino; stat->mode = inode->i_mode; stat->nlink = inode->i_nlink; - stat->uid = inode->i_uid; - stat->gid = inode->i_gid; + stat->uid = i_uid_into_mnt(mnt_userns, inode); + stat->gid = i_gid_into_mnt(mnt_userns, inode); stat->rdev = inode->i_rdev; stat->size = i_size_read(inode); stat->atime = inode->i_atime; @@ -87,7 +95,7 @@ int vfs_getattr_nosec(const struct path *path, struct kstat *stat, return inode->i_op->getattr(path, stat, request_mask, query_flags); - generic_fillattr(inode, stat); + generic_fillattr(mnt_user_ns(path->mnt), inode, stat); return 0; } EXPORT_SYMBOL(vfs_getattr_nosec); diff --git a/fs/sysv/itree.c b/fs/sysv/itree.c index bcb67b0cabe7..83cffab6955f 100644 --- a/fs/sysv/itree.c +++ b/fs/sysv/itree.c @@ -445,7 +445,7 @@ int sysv_getattr(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags) { struct super_block *s = path->dentry->d_sb; - generic_fillattr(d_inode(path->dentry), stat); + generic_fillattr(&init_user_ns, d_inode(path->dentry), stat); stat->blocks = (s->s_blocksize / 512) * sysv_nblocks(s, stat->size); stat->blksize = s->s_blocksize; return 0; diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index 694e7714545b..a8881ed61620 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -1589,7 +1589,7 @@ int ubifs_getattr(const struct path *path, struct kstat *stat, STATX_ATTR_ENCRYPTED | STATX_ATTR_IMMUTABLE); - generic_fillattr(inode, stat); + generic_fillattr(&init_user_ns, inode, stat); stat->blksize = UBIFS_BLOCK_SIZE; stat->size = ui->ui_size; diff --git a/fs/udf/symlink.c b/fs/udf/symlink.c index c973db239604..54a44d1f023c 100644 --- a/fs/udf/symlink.c +++ b/fs/udf/symlink.c @@ -159,7 +159,7 @@ static int udf_symlink_getattr(const struct path *path, struct kstat *stat, struct inode *inode = d_backing_inode(dentry); struct page *page; - generic_fillattr(inode, stat); + generic_fillattr(&init_user_ns, inode, stat); page = read_mapping_page(inode->i_mapping, 0, NULL); if (IS_ERR(page)) return PTR_ERR(page); diff --git a/fs/vboxsf/utils.c b/fs/vboxsf/utils.c index 018057546067..d2cd1c99f48e 100644 --- a/fs/vboxsf/utils.c +++ b/fs/vboxsf/utils.c @@ -233,7 +233,7 @@ int vboxsf_getattr(const struct path *path, struct kstat *kstat, if (err) return err; - generic_fillattr(d_inode(dentry), kstat); + generic_fillattr(&init_user_ns, d_inode(dentry), kstat); return 0; } diff --git a/include/linux/fs.h b/include/linux/fs.h index e3ea1d7c3367..182641d8322f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3154,7 +3154,7 @@ extern int __page_symlink(struct inode *inode, const char *symname, int len, extern int page_symlink(struct inode *inode, const char *symname, int len); extern const struct inode_operations page_symlink_inode_operations; extern void kfree_link(void *); -extern void generic_fillattr(struct inode *, struct kstat *); +void generic_fillattr(struct user_namespace *, struct inode *, struct kstat *); extern int vfs_getattr_nosec(const struct path *, struct kstat *, u32, unsigned int); extern int vfs_getattr(const struct path *, struct kstat *, u32, unsigned int); void __inode_add_bytes(struct inode *inode, loff_t bytes); diff --git a/mm/shmem.c b/mm/shmem.c index 23b8e9c15a42..339d5530d3a9 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1072,7 +1072,7 @@ static int shmem_getattr(const struct path *path, struct kstat *stat, shmem_recalc_inode(inode); spin_unlock_irq(&info->lock); } - generic_fillattr(inode, stat); + generic_fillattr(&init_user_ns, inode, stat); if (is_huge_enabled(sb_info)) stat->blksize = HPAGE_PMD_SIZE; -- cgit v1.2.3 From ba73d98745be1c10dc3cce68e8d7b95012d07d05 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 21 Jan 2021 14:19:31 +0100 Subject: namei: handle idmapped mounts in may_*() helpers The may_follow_link(), may_linkat(), may_lookup(), may_open(), may_o_create(), may_create_in_sticky(), may_delete(), and may_create() helpers determine whether the caller is privileged enough to perform the associated operations. Let them handle idmapped mounts by mapping the inode or fsids according to the mount's user namespace. Afterwards the checks are identical to non-idmapped inodes. The patch takes care to retrieve the mount's user namespace right before performing permission checks and passing it down into the fileystem so the user namespace can't change in between by someone idmapping a mount that is currently not idmapped. If the initial user namespace is passed nothing changes so non-idmapped mounts will see identical behavior as before. Link: https://lore.kernel.org/r/20210121131959.646623-13-christian.brauner@ubuntu.com Cc: Christoph Hellwig Cc: David Howells Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig Reviewed-by: James Morris Signed-off-by: Christian Brauner --- fs/btrfs/ioctl.c | 5 +- fs/init.c | 2 +- fs/inode.c | 2 +- fs/internal.h | 2 +- fs/namei.c | 148 +++++++++++++++++++++++++++++++++-------------------- fs/xattr.c | 2 +- include/linux/fs.h | 14 +++-- 7 files changed, 108 insertions(+), 67 deletions(-) (limited to 'include') diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 1f763c60415b..56f53d692fa2 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -927,8 +927,9 @@ static int btrfs_may_delete(struct inode *dir, struct dentry *victim, int isdir) return error; if (IS_APPEND(dir)) return -EPERM; - if (check_sticky(dir, d_inode(victim)) || IS_APPEND(d_inode(victim)) || - IS_IMMUTABLE(d_inode(victim)) || IS_SWAPFILE(d_inode(victim))) + if (check_sticky(&init_user_ns, dir, d_inode(victim)) || + IS_APPEND(d_inode(victim)) || IS_IMMUTABLE(d_inode(victim)) || + IS_SWAPFILE(d_inode(victim))) return -EPERM; if (isdir) { if (!d_is_dir(victim)) diff --git a/fs/init.c b/fs/init.c index 02723bea8499..891284f8a443 100644 --- a/fs/init.c +++ b/fs/init.c @@ -181,7 +181,7 @@ int __init init_link(const char *oldname, const char *newname) error = -EXDEV; if (old_path.mnt != new_path.mnt) goto out_dput; - error = may_linkat(&old_path); + error = may_linkat(&init_user_ns, &old_path); if (unlikely(error)) goto out_dput; error = security_path_link(old_path.dentry, &new_path, new_dentry); diff --git a/fs/inode.c b/fs/inode.c index 49b512592dcd..46116ef44c9f 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1796,7 +1796,7 @@ bool atime_needs_update(const struct path *path, struct inode *inode) /* Atime updates will likely cause i_uid and i_gid to be written * back improprely if their true value is unknown to the vfs. */ - if (HAS_UNMAPPED_ID(inode)) + if (HAS_UNMAPPED_ID(mnt_user_ns(mnt), inode)) return false; if (IS_NOATIME(inode)) diff --git a/fs/internal.h b/fs/internal.h index 77c50befbfbe..6c8a4eddc7e6 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -73,7 +73,7 @@ extern int vfs_path_lookup(struct dentry *, struct vfsmount *, const char *, unsigned int, struct path *); long do_rmdir(int dfd, struct filename *name); long do_unlinkat(int dfd, struct filename *name); -int may_linkat(struct path *link); +int may_linkat(struct user_namespace *mnt_userns, struct path *link); int do_renameat2(int olddfd, struct filename *oldname, int newdfd, struct filename *newname, unsigned int flags); diff --git a/fs/namei.c b/fs/namei.c index 04b001ddade3..93fa7d803fb2 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -506,7 +506,7 @@ int inode_permission(struct user_namespace *mnt_userns, * written back improperly if their true value is unknown * to the vfs. */ - if (HAS_UNMAPPED_ID(inode)) + if (HAS_UNMAPPED_ID(mnt_userns, inode)) return -EACCES; } @@ -1004,11 +1004,16 @@ int sysctl_protected_regular __read_mostly; */ static inline int may_follow_link(struct nameidata *nd, const struct inode *inode) { + struct user_namespace *mnt_userns; + kuid_t i_uid; + if (!sysctl_protected_symlinks) return 0; + mnt_userns = mnt_user_ns(nd->path.mnt); + i_uid = i_uid_into_mnt(mnt_userns, inode); /* Allowed if owner and follower match. */ - if (uid_eq(current_cred()->fsuid, inode->i_uid)) + if (uid_eq(current_cred()->fsuid, i_uid)) return 0; /* Allowed if parent directory not sticky and world-writable. */ @@ -1016,7 +1021,7 @@ static inline int may_follow_link(struct nameidata *nd, const struct inode *inod return 0; /* Allowed if parent directory and link owner match. */ - if (uid_valid(nd->dir_uid) && uid_eq(nd->dir_uid, inode->i_uid)) + if (uid_valid(nd->dir_uid) && uid_eq(nd->dir_uid, i_uid)) return 0; if (nd->flags & LOOKUP_RCU) @@ -1029,6 +1034,7 @@ static inline int may_follow_link(struct nameidata *nd, const struct inode *inod /** * safe_hardlink_source - Check for safe hardlink conditions + * @mnt_userns: user namespace of the mount the inode was found from * @inode: the source inode to hardlink from * * Return false if at least one of the following conditions: @@ -1039,7 +1045,8 @@ static inline int may_follow_link(struct nameidata *nd, const struct inode *inod * * Otherwise returns true. */ -static bool safe_hardlink_source(struct inode *inode) +static bool safe_hardlink_source(struct user_namespace *mnt_userns, + struct inode *inode) { umode_t mode = inode->i_mode; @@ -1056,7 +1063,7 @@ static bool safe_hardlink_source(struct inode *inode) return false; /* Hardlinking to unreadable or unwritable sources is dangerous. */ - if (inode_permission(&init_user_ns, inode, MAY_READ | MAY_WRITE)) + if (inode_permission(mnt_userns, inode, MAY_READ | MAY_WRITE)) return false; return true; @@ -1064,6 +1071,7 @@ static bool safe_hardlink_source(struct inode *inode) /** * may_linkat - Check permissions for creating a hardlink + * @mnt_userns: user namespace of the mount the inode was found from * @link: the source to hardlink from * * Block hardlink when all of: @@ -1072,14 +1080,21 @@ static bool safe_hardlink_source(struct inode *inode) * - hardlink source is unsafe (see safe_hardlink_source() above) * - not CAP_FOWNER in a namespace with the inode owner uid mapped * + * If the inode has been found through an idmapped mount the user namespace of + * the vfsmount must be passed through @mnt_userns. This function will then take + * care to map the inode according to @mnt_userns before checking permissions. + * On non-idmapped mounts or if permission checking is to be performed on the + * raw inode simply passs init_user_ns. + * * Returns 0 if successful, -ve on error. */ -int may_linkat(struct path *link) +int may_linkat(struct user_namespace *mnt_userns, struct path *link) { struct inode *inode = link->dentry->d_inode; /* Inode writeback is not safe when the uid or gid are invalid. */ - if (!uid_valid(inode->i_uid) || !gid_valid(inode->i_gid)) + if (!uid_valid(i_uid_into_mnt(mnt_userns, inode)) || + !gid_valid(i_gid_into_mnt(mnt_userns, inode))) return -EOVERFLOW; if (!sysctl_protected_hardlinks) @@ -1088,8 +1103,8 @@ int may_linkat(struct path *link) /* Source inode owner (or CAP_FOWNER) can hardlink all they like, * otherwise, it must be a safe source. */ - if (safe_hardlink_source(inode) || - inode_owner_or_capable(&init_user_ns, inode)) + if (safe_hardlink_source(mnt_userns, inode) || + inode_owner_or_capable(mnt_userns, inode)) return 0; audit_log_path_denied(AUDIT_ANOM_LINK, "linkat"); @@ -1100,6 +1115,7 @@ int may_linkat(struct path *link) * may_create_in_sticky - Check whether an O_CREAT open in a sticky directory * should be allowed, or not, on files that already * exist. + * @mnt_userns: user namespace of the mount the inode was found from * @dir_mode: mode bits of directory * @dir_uid: owner of directory * @inode: the inode of the file to open @@ -1115,16 +1131,25 @@ int may_linkat(struct path *link) * the directory doesn't have to be world writable: being group writable will * be enough. * + * If the inode has been found through an idmapped mount the user namespace of + * the vfsmount must be passed through @mnt_userns. This function will then take + * care to map the inode according to @mnt_userns before checking permissions. + * On non-idmapped mounts or if permission checking is to be performed on the + * raw inode simply passs init_user_ns. + * * Returns 0 if the open is allowed, -ve on error. */ -static int may_create_in_sticky(umode_t dir_mode, kuid_t dir_uid, - struct inode * const inode) +static int may_create_in_sticky(struct user_namespace *mnt_userns, + struct nameidata *nd, struct inode *const inode) { + umode_t dir_mode = nd->dir_mode; + kuid_t dir_uid = nd->dir_uid; + if ((!sysctl_protected_fifos && S_ISFIFO(inode->i_mode)) || (!sysctl_protected_regular && S_ISREG(inode->i_mode)) || likely(!(dir_mode & S_ISVTX)) || - uid_eq(inode->i_uid, dir_uid) || - uid_eq(current_fsuid(), inode->i_uid)) + uid_eq(i_uid_into_mnt(mnt_userns, inode), dir_uid) || + uid_eq(current_fsuid(), i_uid_into_mnt(mnt_userns, inode))) return 0; if (likely(dir_mode & 0002) || @@ -1614,17 +1639,18 @@ static struct dentry *lookup_slow(const struct qstr *name, return res; } -static inline int may_lookup(struct nameidata *nd) +static inline int may_lookup(struct user_namespace *mnt_userns, + struct nameidata *nd) { if (nd->flags & LOOKUP_RCU) { - int err = inode_permission(&init_user_ns, nd->inode, + int err = inode_permission(mnt_userns, nd->inode, MAY_EXEC | MAY_NOT_BLOCK); if (err != -ECHILD) return err; if (unlazy_walk(nd)) return -ECHILD; } - return inode_permission(&init_user_ns, nd->inode, MAY_EXEC); + return inode_permission(mnt_userns, nd->inode, MAY_EXEC); } static int reserve_stack(struct nameidata *nd, struct path *link, unsigned seq) @@ -2177,7 +2203,7 @@ static int link_path_walk(const char *name, struct nameidata *nd) u64 hash_len; int type; - err = may_lookup(nd); + err = may_lookup(&init_user_ns, nd); if (err) return err; @@ -2225,7 +2251,7 @@ static int link_path_walk(const char *name, struct nameidata *nd) OK: /* pathname or trailing symlink, done */ if (!depth) { - nd->dir_uid = nd->inode->i_uid; + nd->dir_uid = i_uid_into_mnt(&init_user_ns, nd->inode); nd->dir_mode = nd->inode->i_mode; nd->flags &= ~LOOKUP_PARENT; return 0; @@ -2703,15 +2729,16 @@ int user_path_at_empty(int dfd, const char __user *name, unsigned flags, } EXPORT_SYMBOL(user_path_at_empty); -int __check_sticky(struct inode *dir, struct inode *inode) +int __check_sticky(struct user_namespace *mnt_userns, struct inode *dir, + struct inode *inode) { kuid_t fsuid = current_fsuid(); - if (uid_eq(inode->i_uid, fsuid)) + if (uid_eq(i_uid_into_mnt(mnt_userns, inode), fsuid)) return 0; - if (uid_eq(dir->i_uid, fsuid)) + if (uid_eq(i_uid_into_mnt(mnt_userns, dir), fsuid)) return 0; - return !capable_wrt_inode_uidgid(&init_user_ns, inode, CAP_FOWNER); + return !capable_wrt_inode_uidgid(mnt_userns, inode, CAP_FOWNER); } EXPORT_SYMBOL(__check_sticky); @@ -2735,7 +2762,8 @@ EXPORT_SYMBOL(__check_sticky); * 11. We don't allow removal of NFS sillyrenamed files; it's handled by * nfs_async_unlink(). */ -static int may_delete(struct inode *dir, struct dentry *victim, bool isdir) +static int may_delete(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *victim, bool isdir) { struct inode *inode = d_backing_inode(victim); int error; @@ -2747,19 +2775,21 @@ static int may_delete(struct inode *dir, struct dentry *victim, bool isdir) BUG_ON(victim->d_parent->d_inode != dir); /* Inode writeback is not safe when the uid or gid are invalid. */ - if (!uid_valid(inode->i_uid) || !gid_valid(inode->i_gid)) + if (!uid_valid(i_uid_into_mnt(mnt_userns, inode)) || + !gid_valid(i_gid_into_mnt(mnt_userns, inode))) return -EOVERFLOW; audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE); - error = inode_permission(&init_user_ns, dir, MAY_WRITE | MAY_EXEC); + error = inode_permission(mnt_userns, dir, MAY_WRITE | MAY_EXEC); if (error) return error; if (IS_APPEND(dir)) return -EPERM; - if (check_sticky(dir, inode) || IS_APPEND(inode) || - IS_IMMUTABLE(inode) || IS_SWAPFILE(inode) || HAS_UNMAPPED_ID(inode)) + if (check_sticky(mnt_userns, dir, inode) || IS_APPEND(inode) || + IS_IMMUTABLE(inode) || IS_SWAPFILE(inode) || + HAS_UNMAPPED_ID(mnt_userns, inode)) return -EPERM; if (isdir) { if (!d_is_dir(victim)) @@ -2784,7 +2814,8 @@ static int may_delete(struct inode *dir, struct dentry *victim, bool isdir) * 4. We should have write and exec permissions on dir * 5. We can't do it if dir is immutable (done in permission()) */ -static inline int may_create(struct inode *dir, struct dentry *child) +static inline int may_create(struct user_namespace *mnt_userns, + struct inode *dir, struct dentry *child) { struct user_namespace *s_user_ns; audit_inode_child(dir, child, AUDIT_TYPE_CHILD_CREATE); @@ -2793,10 +2824,10 @@ static inline int may_create(struct inode *dir, struct dentry *child) if (IS_DEADDIR(dir)) return -ENOENT; s_user_ns = dir->i_sb->s_user_ns; - if (!kuid_has_mapping(s_user_ns, current_fsuid()) || - !kgid_has_mapping(s_user_ns, current_fsgid())) + if (!kuid_has_mapping(s_user_ns, fsuid_into_mnt(mnt_userns)) || + !kgid_has_mapping(s_user_ns, fsgid_into_mnt(mnt_userns))) return -EOVERFLOW; - return inode_permission(&init_user_ns, dir, MAY_WRITE | MAY_EXEC); + return inode_permission(mnt_userns, dir, MAY_WRITE | MAY_EXEC); } /* @@ -2846,7 +2877,7 @@ EXPORT_SYMBOL(unlock_rename); int vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool want_excl) { - int error = may_create(dir, dentry); + int error = may_create(&init_user_ns, dir, dentry); if (error) return error; @@ -2869,7 +2900,7 @@ int vfs_mkobj(struct dentry *dentry, umode_t mode, void *arg) { struct inode *dir = dentry->d_parent->d_inode; - int error = may_create(dir, dentry); + int error = may_create(&init_user_ns, dir, dentry); if (error) return error; @@ -2891,7 +2922,8 @@ bool may_open_dev(const struct path *path) !(path->mnt->mnt_sb->s_iflags & SB_I_NODEV); } -static int may_open(const struct path *path, int acc_mode, int flag) +static int may_open(struct user_namespace *mnt_userns, const struct path *path, + int acc_mode, int flag) { struct dentry *dentry = path->dentry; struct inode *inode = dentry->d_inode; @@ -2926,7 +2958,7 @@ static int may_open(const struct path *path, int acc_mode, int flag) break; } - error = inode_permission(&init_user_ns, inode, MAY_OPEN | acc_mode); + error = inode_permission(mnt_userns, inode, MAY_OPEN | acc_mode); if (error) return error; @@ -2941,7 +2973,7 @@ static int may_open(const struct path *path, int acc_mode, int flag) } /* O_NOATIME can only be set by the owner or superuser */ - if (flag & O_NOATIME && !inode_owner_or_capable(&init_user_ns, inode)) + if (flag & O_NOATIME && !inode_owner_or_capable(mnt_userns, inode)) return -EPERM; return 0; @@ -2976,7 +3008,9 @@ static inline int open_to_namei_flags(int flag) return flag; } -static int may_o_create(const struct path *dir, struct dentry *dentry, umode_t mode) +static int may_o_create(struct user_namespace *mnt_userns, + const struct path *dir, struct dentry *dentry, + umode_t mode) { struct user_namespace *s_user_ns; int error = security_path_mknod(dir, dentry, mode, 0); @@ -2984,11 +3018,11 @@ static int may_o_create(const struct path *dir, struct dentry *dentry, umode_t m return error; s_user_ns = dir->dentry->d_sb->s_user_ns; - if (!kuid_has_mapping(s_user_ns, current_fsuid()) || - !kgid_has_mapping(s_user_ns, current_fsgid())) + if (!kuid_has_mapping(s_user_ns, fsuid_into_mnt(mnt_userns)) || + !kgid_has_mapping(s_user_ns, fsgid_into_mnt(mnt_userns))) return -EOVERFLOW; - error = inode_permission(&init_user_ns, dir->dentry->d_inode, + error = inode_permission(mnt_userns, dir->dentry->d_inode, MAY_WRITE | MAY_EXEC); if (error) return error; @@ -3121,7 +3155,8 @@ static struct dentry *lookup_open(struct nameidata *nd, struct file *file, if (!IS_POSIXACL(dir->d_inode)) mode &= ~current_umask(); if (likely(got_write)) - create_error = may_o_create(&nd->path, dentry, mode); + create_error = may_o_create(&init_user_ns, &nd->path, + dentry, mode); else create_error = -EROFS; } @@ -3282,7 +3317,7 @@ static int do_open(struct nameidata *nd, return -EEXIST; if (d_is_dir(nd->path.dentry)) return -EISDIR; - error = may_create_in_sticky(nd->dir_mode, nd->dir_uid, + error = may_create_in_sticky(&init_user_ns, nd, d_backing_inode(nd->path.dentry)); if (unlikely(error)) return error; @@ -3302,7 +3337,7 @@ static int do_open(struct nameidata *nd, return error; do_truncate = true; } - error = may_open(&nd->path, acc_mode, open_flag); + error = may_open(&init_user_ns, &nd->path, acc_mode, open_flag); if (!error && !(file->f_mode & FMODE_OPENED)) error = vfs_open(&nd->path, file); if (!error) @@ -3377,7 +3412,7 @@ static int do_tmpfile(struct nameidata *nd, unsigned flags, path.dentry = child; audit_inode(nd->name, child, 0); /* Don't check for other permissions, the inode was just created */ - error = may_open(&path, 0, op->open_flag); + error = may_open(&init_user_ns, &path, 0, op->open_flag); if (error) goto out2; file->f_path.mnt = path.mnt; @@ -3584,7 +3619,7 @@ EXPORT_SYMBOL(user_path_create); int vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) { bool is_whiteout = S_ISCHR(mode) && dev == WHITEOUT_DEV; - int error = may_create(dir, dentry); + int error = may_create(&init_user_ns, dir, dentry); if (error) return error; @@ -3685,7 +3720,7 @@ SYSCALL_DEFINE3(mknod, const char __user *, filename, umode_t, mode, unsigned, d int vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) { - int error = may_create(dir, dentry); + int error = may_create(&init_user_ns, dir, dentry); unsigned max_links = dir->i_sb->s_max_links; if (error) @@ -3746,7 +3781,7 @@ SYSCALL_DEFINE2(mkdir, const char __user *, pathname, umode_t, mode) int vfs_rmdir(struct inode *dir, struct dentry *dentry) { - int error = may_delete(dir, dentry, 1); + int error = may_delete(&init_user_ns, dir, dentry, 1); if (error) return error; @@ -3868,7 +3903,7 @@ SYSCALL_DEFINE1(rmdir, const char __user *, pathname) int vfs_unlink(struct inode *dir, struct dentry *dentry, struct inode **delegated_inode) { struct inode *target = dentry->d_inode; - int error = may_delete(dir, dentry, 0); + int error = may_delete(&init_user_ns, dir, dentry, 0); if (error) return error; @@ -4000,7 +4035,7 @@ SYSCALL_DEFINE1(unlink, const char __user *, pathname) int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname) { - int error = may_create(dir, dentry); + int error = may_create(&init_user_ns, dir, dentry); if (error) return error; @@ -4089,7 +4124,7 @@ int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_de if (!inode) return -ENOENT; - error = may_create(dir, new_dentry); + error = may_create(&init_user_ns, dir, new_dentry); if (error) return error; @@ -4106,7 +4141,7 @@ int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_de * be writen back improperly if their true value is unknown to * the vfs. */ - if (HAS_UNMAPPED_ID(inode)) + if (HAS_UNMAPPED_ID(&init_user_ns, inode)) return -EPERM; if (!dir->i_op->link) return -EPERM; @@ -4188,7 +4223,7 @@ retry: error = -EXDEV; if (old_path.mnt != new_path.mnt) goto out_dput; - error = may_linkat(&old_path); + error = may_linkat(&init_user_ns, &old_path); if (unlikely(error)) goto out_dput; error = security_path_link(old_path.dentry, &new_path, new_dentry); @@ -4281,6 +4316,7 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode **delegated_inode, unsigned int flags) { int error; + struct user_namespace *mnt_userns = &init_user_ns; bool is_dir = d_is_dir(old_dentry); struct inode *source = old_dentry->d_inode; struct inode *target = new_dentry->d_inode; @@ -4291,19 +4327,19 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, if (source == target) return 0; - error = may_delete(old_dir, old_dentry, is_dir); + error = may_delete(mnt_userns, old_dir, old_dentry, is_dir); if (error) return error; if (!target) { - error = may_create(new_dir, new_dentry); + error = may_create(mnt_userns, new_dir, new_dentry); } else { new_is_dir = d_is_dir(new_dentry); if (!(flags & RENAME_EXCHANGE)) - error = may_delete(new_dir, new_dentry, is_dir); + error = may_delete(mnt_userns, new_dir, new_dentry, is_dir); else - error = may_delete(new_dir, new_dentry, new_is_dir); + error = may_delete(mnt_userns, new_dir, new_dentry, new_is_dir); } if (error) return error; diff --git a/fs/xattr.c b/fs/xattr.c index 79c439d31eaa..b3444e06cded 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -98,7 +98,7 @@ xattr_permission(struct user_namespace *mnt_userns, struct inode *inode, * to be writen back improperly if their true value is * unknown to the vfs. */ - if (HAS_UNMAPPED_ID(inode)) + if (HAS_UNMAPPED_ID(mnt_userns, inode)) return -EPERM; } diff --git a/include/linux/fs.h b/include/linux/fs.h index 182641d8322f..a27884af7222 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2083,9 +2083,11 @@ static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags #define IS_WHITEOUT(inode) (S_ISCHR(inode->i_mode) && \ (inode)->i_rdev == WHITEOUT_DEV) -static inline bool HAS_UNMAPPED_ID(struct inode *inode) +static inline bool HAS_UNMAPPED_ID(struct user_namespace *mnt_userns, + struct inode *inode) { - return !uid_valid(inode->i_uid) || !gid_valid(inode->i_gid); + return !uid_valid(i_uid_into_mnt(mnt_userns, inode)) || + !gid_valid(i_gid_into_mnt(mnt_userns, inode)); } static inline enum rw_hint file_write_hint(struct file *file) @@ -2823,7 +2825,8 @@ static inline int path_permission(const struct path *path, int mask) return inode_permission(mnt_user_ns(path->mnt), d_inode(path->dentry), mask); } -extern int __check_sticky(struct inode *dir, struct inode *inode); +int __check_sticky(struct user_namespace *mnt_userns, struct inode *dir, + struct inode *inode); static inline bool execute_ok(struct inode *inode) { @@ -3442,12 +3445,13 @@ static inline bool is_sxid(umode_t mode) return (mode & S_ISUID) || ((mode & S_ISGID) && (mode & S_IXGRP)); } -static inline int check_sticky(struct inode *dir, struct inode *inode) +static inline int check_sticky(struct user_namespace *mnt_userns, + struct inode *dir, struct inode *inode) { if (!(dir->i_mode & S_ISVTX)) return 0; - return __check_sticky(dir, inode); + return __check_sticky(mnt_userns, dir, inode); } static inline void inode_has_no_xattr(struct inode *inode) -- cgit v1.2.3 From 9fe61450972d3900bffb1dc26a17ebb9cdd92db2 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 21 Jan 2021 14:19:32 +0100 Subject: namei: introduce struct renamedata In order to handle idmapped mounts we will extend the vfs rename helper to take two new arguments in follow up patches. Since this operations already takes a bunch of arguments add a simple struct renamedata and make the current helper use it before we extend it. Link: https://lore.kernel.org/r/20210121131959.646623-14-christian.brauner@ubuntu.com Cc: Christoph Hellwig Cc: David Howells Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig Signed-off-by: Christian Brauner --- fs/cachefiles/namei.c | 9 +++++++-- fs/ecryptfs/inode.c | 10 +++++++--- fs/namei.c | 21 +++++++++++++++------ fs/nfsd/vfs.c | 8 +++++++- fs/overlayfs/overlayfs.h | 9 ++++++++- include/linux/fs.h | 12 +++++++++++- 6 files changed, 55 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index ecc8ecbbfa5a..7b987de0babe 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -412,9 +412,14 @@ try_again: if (ret < 0) { cachefiles_io_error(cache, "Rename security error %d", ret); } else { + struct renamedata rd = { + .old_dir = d_inode(dir), + .old_dentry = rep, + .new_dir = d_inode(cache->graveyard), + .new_dentry = grave, + }; trace_cachefiles_rename(object, rep, grave, why); - ret = vfs_rename(d_inode(dir), rep, - d_inode(cache->graveyard), grave, NULL, 0); + ret = vfs_rename(&rd); if (ret != 0 && ret != -ENOMEM) cachefiles_io_error(cache, "Rename failed with error %d", ret); diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index 385b5e8741c0..ff48abb09679 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -590,6 +590,7 @@ ecryptfs_rename(struct inode *old_dir, struct dentry *old_dentry, struct dentry *lower_new_dir_dentry; struct dentry *trap; struct inode *target_inode; + struct renamedata rd = {}; if (flags) return -EINVAL; @@ -619,9 +620,12 @@ ecryptfs_rename(struct inode *old_dir, struct dentry *old_dentry, rc = -ENOTEMPTY; goto out_lock; } - rc = vfs_rename(d_inode(lower_old_dir_dentry), lower_old_dentry, - d_inode(lower_new_dir_dentry), lower_new_dentry, - NULL, 0); + + rd.old_dir = d_inode(lower_old_dir_dentry); + rd.old_dentry = lower_old_dentry; + rd.new_dir = d_inode(lower_new_dir_dentry); + rd.new_dentry = lower_new_dentry; + rc = vfs_rename(&rd); if (rc) goto out_lock; if (target_inode) diff --git a/fs/namei.c b/fs/namei.c index 93fa7d803fb2..38ab51881247 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -4311,12 +4311,15 @@ SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname * ->i_mutex on parents, which works but leads to some truly excessive * locking]. */ -int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry, - struct inode **delegated_inode, unsigned int flags) +int vfs_rename(struct renamedata *rd) { int error; struct user_namespace *mnt_userns = &init_user_ns; + struct inode *old_dir = rd->old_dir, *new_dir = rd->new_dir; + struct dentry *old_dentry = rd->old_dentry; + struct dentry *new_dentry = rd->new_dentry; + struct inode **delegated_inode = rd->delegated_inode; + unsigned int flags = rd->flags; bool is_dir = d_is_dir(old_dentry); struct inode *source = old_dentry->d_inode; struct inode *target = new_dentry->d_inode; @@ -4442,6 +4445,7 @@ EXPORT_SYMBOL(vfs_rename); int do_renameat2(int olddfd, struct filename *from, int newdfd, struct filename *to, unsigned int flags) { + struct renamedata rd; struct dentry *old_dentry, *new_dentry; struct dentry *trap; struct path old_path, new_path; @@ -4545,9 +4549,14 @@ retry_deleg: &new_path, new_dentry, flags); if (error) goto exit5; - error = vfs_rename(old_path.dentry->d_inode, old_dentry, - new_path.dentry->d_inode, new_dentry, - &delegated_inode, flags); + + rd.old_dir = old_path.dentry->d_inode; + rd.old_dentry = old_dentry; + rd.new_dir = new_path.dentry->d_inode; + rd.new_dentry = new_dentry; + rd.delegated_inode = &delegated_inode; + rd.flags = flags; + error = vfs_rename(&rd); exit5: dput(new_dentry); exit4: diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 37d85046b4d6..f7d83ff2b44e 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -1798,7 +1798,13 @@ retry: close_cached = true; goto out_dput_old; } else { - host_err = vfs_rename(fdir, odentry, tdir, ndentry, NULL, 0); + struct renamedata rd = { + .old_dir = fdir, + .old_dentry = odentry, + .new_dir = tdir, + .new_dentry = ndentry, + }; + host_err = vfs_rename(&rd); if (!host_err) { host_err = commit_metadata(tfhp); if (!host_err) diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index 0002834f664a..426899681df7 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -214,9 +214,16 @@ static inline int ovl_do_rename(struct inode *olddir, struct dentry *olddentry, unsigned int flags) { int err; + struct renamedata rd = { + .old_dir = olddir, + .old_dentry = olddentry, + .new_dir = newdir, + .new_dentry = newdentry, + .flags = flags, + }; pr_debug("rename(%pd2, %pd2, 0x%x)\n", olddentry, newdentry, flags); - err = vfs_rename(olddir, olddentry, newdir, newdentry, NULL, flags); + err = vfs_rename(&rd); if (err) { pr_debug("...rename(%pd2, %pd2, ...) = %i\n", olddentry, newdentry, err); diff --git a/include/linux/fs.h b/include/linux/fs.h index a27884af7222..430e457f67f1 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1775,7 +1775,17 @@ extern int vfs_symlink(struct inode *, struct dentry *, const char *); extern int vfs_link(struct dentry *, struct inode *, struct dentry *, struct inode **); extern int vfs_rmdir(struct inode *, struct dentry *); extern int vfs_unlink(struct inode *, struct dentry *, struct inode **); -extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **, unsigned int); + +struct renamedata { + struct inode *old_dir; + struct dentry *old_dentry; + struct inode *new_dir; + struct dentry *new_dentry; + struct inode **delegated_inode; + unsigned int flags; +} __randomize_layout; + +int vfs_rename(struct renamedata *); static inline int vfs_whiteout(struct inode *dir, struct dentry *dentry) { -- cgit v1.2.3 From 6521f8917082928a4cb637eb64b77b5f2f5b30fc Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 21 Jan 2021 14:19:33 +0100 Subject: namei: prepare for idmapped mounts The various vfs_*() helpers are called by filesystems or by the vfs itself to perform core operations such as create, link, mkdir, mknod, rename, rmdir, tmpfile and unlink. Enable them to handle idmapped mounts. If the inode is accessed through an idmapped mount map it into the mount's user namespace and pass it down. Afterwards the checks and operations are identical to non-idmapped mounts. If the initial user namespace is passed nothing changes so non-idmapped mounts will see identical behavior as before. Link: https://lore.kernel.org/r/20210121131959.646623-15-christian.brauner@ubuntu.com Cc: Christoph Hellwig Cc: David Howells Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig Signed-off-by: Christian Brauner --- drivers/base/devtmpfs.c | 11 ++- fs/cachefiles/namei.c | 12 ++- fs/ecryptfs/inode.c | 33 ++++--- fs/init.c | 14 +-- fs/namei.c | 227 ++++++++++++++++++++++++++++++++++++++--------- fs/nfsd/nfs4recover.c | 6 +- fs/nfsd/vfs.c | 19 ++-- fs/overlayfs/dir.c | 4 +- fs/overlayfs/overlayfs.h | 20 +++-- include/linux/fs.h | 32 ++++--- ipc/mqueue.c | 3 +- net/unix/af_unix.c | 3 +- 12 files changed, 279 insertions(+), 105 deletions(-) (limited to 'include') diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c index 2e0c3cdb4184..653c8c6ac7a7 100644 --- a/drivers/base/devtmpfs.c +++ b/drivers/base/devtmpfs.c @@ -162,7 +162,7 @@ static int dev_mkdir(const char *name, umode_t mode) if (IS_ERR(dentry)) return PTR_ERR(dentry); - err = vfs_mkdir(d_inode(path.dentry), dentry, mode); + err = vfs_mkdir(&init_user_ns, d_inode(path.dentry), dentry, mode); if (!err) /* mark as kernel-created inode */ d_inode(dentry)->i_private = &thread; @@ -212,7 +212,8 @@ static int handle_create(const char *nodename, umode_t mode, kuid_t uid, if (IS_ERR(dentry)) return PTR_ERR(dentry); - err = vfs_mknod(d_inode(path.dentry), dentry, mode, dev->devt); + err = vfs_mknod(&init_user_ns, d_inode(path.dentry), dentry, mode, + dev->devt); if (!err) { struct iattr newattrs; @@ -242,7 +243,8 @@ static int dev_rmdir(const char *name) return PTR_ERR(dentry); if (d_really_is_positive(dentry)) { if (d_inode(dentry)->i_private == &thread) - err = vfs_rmdir(d_inode(parent.dentry), dentry); + err = vfs_rmdir(&init_user_ns, d_inode(parent.dentry), + dentry); else err = -EPERM; } else { @@ -330,7 +332,8 @@ static int handle_remove(const char *nodename, struct device *dev) inode_lock(d_inode(dentry)); notify_change(&init_user_ns, dentry, &newattrs, NULL); inode_unlock(d_inode(dentry)); - err = vfs_unlink(d_inode(parent.dentry), dentry, NULL); + err = vfs_unlink(&init_user_ns, d_inode(parent.dentry), + dentry, NULL); if (!err || err == -ENOENT) deleted = 1; } diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index 7b987de0babe..7bf0732ae25c 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -311,7 +311,8 @@ static int cachefiles_bury_object(struct cachefiles_cache *cache, cachefiles_io_error(cache, "Unlink security error"); } else { trace_cachefiles_unlink(object, rep, why); - ret = vfs_unlink(d_inode(dir), rep, NULL); + ret = vfs_unlink(&init_user_ns, d_inode(dir), rep, + NULL); if (preemptive) cachefiles_mark_object_buried(cache, rep, why); @@ -413,8 +414,10 @@ try_again: cachefiles_io_error(cache, "Rename security error %d", ret); } else { struct renamedata rd = { + .old_mnt_userns = &init_user_ns, .old_dir = d_inode(dir), .old_dentry = rep, + .new_mnt_userns = &init_user_ns, .new_dir = d_inode(cache->graveyard), .new_dentry = grave, }; @@ -566,7 +569,7 @@ lookup_again: if (ret < 0) goto create_error; start = jiffies; - ret = vfs_mkdir(d_inode(dir), next, 0); + ret = vfs_mkdir(&init_user_ns, d_inode(dir), next, 0); cachefiles_hist(cachefiles_mkdir_histogram, start); if (!key) trace_cachefiles_mkdir(object, next, ret); @@ -602,7 +605,8 @@ lookup_again: if (ret < 0) goto create_error; start = jiffies; - ret = vfs_create(d_inode(dir), next, S_IFREG, true); + ret = vfs_create(&init_user_ns, d_inode(dir), next, + S_IFREG, true); cachefiles_hist(cachefiles_create_histogram, start); trace_cachefiles_create(object, next, ret); if (ret < 0) @@ -796,7 +800,7 @@ retry: ret = security_path_mkdir(&path, subdir, 0700); if (ret < 0) goto mkdir_error; - ret = vfs_mkdir(d_inode(dir), subdir, 0700); + ret = vfs_mkdir(&init_user_ns, d_inode(dir), subdir, 0700); if (ret < 0) goto mkdir_error; diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index ff48abb09679..73e3d47e7b2d 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -141,7 +141,8 @@ static int ecryptfs_do_unlink(struct inode *dir, struct dentry *dentry, else if (d_unhashed(lower_dentry)) rc = -EINVAL; else - rc = vfs_unlink(lower_dir_inode, lower_dentry, NULL); + rc = vfs_unlink(&init_user_ns, lower_dir_inode, lower_dentry, + NULL); if (rc) { printk(KERN_ERR "Error in vfs_unlink; rc = [%d]\n", rc); goto out_unlock; @@ -180,7 +181,8 @@ ecryptfs_do_create(struct inode *directory_inode, lower_dentry = ecryptfs_dentry_to_lower(ecryptfs_dentry); lower_dir_dentry = lock_parent(lower_dentry); - rc = vfs_create(d_inode(lower_dir_dentry), lower_dentry, mode, true); + rc = vfs_create(&init_user_ns, d_inode(lower_dir_dentry), lower_dentry, + mode, true); if (rc) { printk(KERN_ERR "%s: Failure to create dentry in lower fs; " "rc = [%d]\n", __func__, rc); @@ -190,7 +192,8 @@ ecryptfs_do_create(struct inode *directory_inode, inode = __ecryptfs_get_inode(d_inode(lower_dentry), directory_inode->i_sb); if (IS_ERR(inode)) { - vfs_unlink(d_inode(lower_dir_dentry), lower_dentry, NULL); + vfs_unlink(&init_user_ns, d_inode(lower_dir_dentry), + lower_dentry, NULL); goto out_lock; } fsstack_copy_attr_times(directory_inode, d_inode(lower_dir_dentry)); @@ -436,8 +439,8 @@ static int ecryptfs_link(struct dentry *old_dentry, struct inode *dir, dget(lower_old_dentry); dget(lower_new_dentry); lower_dir_dentry = lock_parent(lower_new_dentry); - rc = vfs_link(lower_old_dentry, d_inode(lower_dir_dentry), - lower_new_dentry, NULL); + rc = vfs_link(lower_old_dentry, &init_user_ns, + d_inode(lower_dir_dentry), lower_new_dentry, NULL); if (rc || d_really_is_negative(lower_new_dentry)) goto out_lock; rc = ecryptfs_interpose(lower_new_dentry, new_dentry, dir->i_sb); @@ -481,7 +484,7 @@ static int ecryptfs_symlink(struct inode *dir, struct dentry *dentry, strlen(symname)); if (rc) goto out_lock; - rc = vfs_symlink(d_inode(lower_dir_dentry), lower_dentry, + rc = vfs_symlink(&init_user_ns, d_inode(lower_dir_dentry), lower_dentry, encoded_symname); kfree(encoded_symname); if (rc || d_really_is_negative(lower_dentry)) @@ -507,7 +510,8 @@ static int ecryptfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode lower_dentry = ecryptfs_dentry_to_lower(dentry); lower_dir_dentry = lock_parent(lower_dentry); - rc = vfs_mkdir(d_inode(lower_dir_dentry), lower_dentry, mode); + rc = vfs_mkdir(&init_user_ns, d_inode(lower_dir_dentry), lower_dentry, + mode); if (rc || d_really_is_negative(lower_dentry)) goto out; rc = ecryptfs_interpose(lower_dentry, dentry, dir->i_sb); @@ -541,7 +545,7 @@ static int ecryptfs_rmdir(struct inode *dir, struct dentry *dentry) else if (d_unhashed(lower_dentry)) rc = -EINVAL; else - rc = vfs_rmdir(lower_dir_inode, lower_dentry); + rc = vfs_rmdir(&init_user_ns, lower_dir_inode, lower_dentry); if (!rc) { clear_nlink(d_inode(dentry)); fsstack_copy_attr_times(dir, lower_dir_inode); @@ -563,7 +567,8 @@ ecryptfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev lower_dentry = ecryptfs_dentry_to_lower(dentry); lower_dir_dentry = lock_parent(lower_dentry); - rc = vfs_mknod(d_inode(lower_dir_dentry), lower_dentry, mode, dev); + rc = vfs_mknod(&init_user_ns, d_inode(lower_dir_dentry), lower_dentry, + mode, dev); if (rc || d_really_is_negative(lower_dentry)) goto out; rc = ecryptfs_interpose(lower_dentry, dentry, dir->i_sb); @@ -621,10 +626,12 @@ ecryptfs_rename(struct inode *old_dir, struct dentry *old_dentry, goto out_lock; } - rd.old_dir = d_inode(lower_old_dir_dentry); - rd.old_dentry = lower_old_dentry; - rd.new_dir = d_inode(lower_new_dir_dentry); - rd.new_dentry = lower_new_dentry; + rd.old_mnt_userns = &init_user_ns; + rd.old_dir = d_inode(lower_old_dir_dentry); + rd.old_dentry = lower_old_dentry; + rd.new_mnt_userns = &init_user_ns; + rd.new_dir = d_inode(lower_new_dir_dentry); + rd.new_dentry = lower_new_dentry; rc = vfs_rename(&rd); if (rc) goto out_lock; diff --git a/fs/init.c b/fs/init.c index 891284f8a443..e65452750fa5 100644 --- a/fs/init.c +++ b/fs/init.c @@ -157,8 +157,8 @@ int __init init_mknod(const char *filename, umode_t mode, unsigned int dev) mode &= ~current_umask(); error = security_path_mknod(&path, dentry, mode, dev); if (!error) - error = vfs_mknod(path.dentry->d_inode, dentry, mode, - new_decode_dev(dev)); + error = vfs_mknod(&init_user_ns, path.dentry->d_inode, dentry, + mode, new_decode_dev(dev)); done_path_create(&path, dentry); return error; } @@ -187,8 +187,8 @@ int __init init_link(const char *oldname, const char *newname) error = security_path_link(old_path.dentry, &new_path, new_dentry); if (error) goto out_dput; - error = vfs_link(old_path.dentry, new_path.dentry->d_inode, new_dentry, - NULL); + error = vfs_link(old_path.dentry, &init_user_ns, + new_path.dentry->d_inode, new_dentry, NULL); out_dput: done_path_create(&new_path, new_dentry); out: @@ -207,7 +207,8 @@ int __init init_symlink(const char *oldname, const char *newname) return PTR_ERR(dentry); error = security_path_symlink(&path, dentry, oldname); if (!error) - error = vfs_symlink(path.dentry->d_inode, dentry, oldname); + error = vfs_symlink(&init_user_ns, path.dentry->d_inode, dentry, + oldname); done_path_create(&path, dentry); return error; } @@ -230,7 +231,8 @@ int __init init_mkdir(const char *pathname, umode_t mode) mode &= ~current_umask(); error = security_path_mkdir(&path, dentry, mode); if (!error) - error = vfs_mkdir(path.dentry->d_inode, dentry, mode); + error = vfs_mkdir(&init_user_ns, path.dentry->d_inode, dentry, + mode); done_path_create(&path, dentry); return error; } diff --git a/fs/namei.c b/fs/namei.c index 38ab51881247..5c9f6f8e90c4 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2874,10 +2874,26 @@ void unlock_rename(struct dentry *p1, struct dentry *p2) } EXPORT_SYMBOL(unlock_rename); -int vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - bool want_excl) +/** + * vfs_create - create new file + * @mnt_userns: user namespace of the mount the inode was found from + * @dir: inode of @dentry + * @dentry: pointer to dentry of the base directory + * @mode: mode of the new file + * @want_excl: whether the file must not yet exist + * + * Create a new file. + * + * If the inode has been found through an idmapped mount the user namespace of + * the vfsmount must be passed through @mnt_userns. This function will then take + * care to map the inode according to @mnt_userns before checking permissions. + * On non-idmapped mounts or if permission checking is to be performed on the + * raw inode simply passs init_user_ns. + */ +int vfs_create(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, bool want_excl) { - int error = may_create(&init_user_ns, dir, dentry); + int error = may_create(mnt_userns, dir, dentry); if (error) return error; @@ -3353,7 +3369,23 @@ static int do_open(struct nameidata *nd, return error; } -struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode, int open_flag) +/** + * vfs_tmpfile - create tmpfile + * @mnt_userns: user namespace of the mount the inode was found from + * @dentry: pointer to dentry of the base directory + * @mode: mode of the new tmpfile + * @open_flags: flags + * + * Create a temporary file. + * + * If the inode has been found through an idmapped mount the user namespace of + * the vfsmount must be passed through @mnt_userns. This function will then take + * care to map the inode according to @mnt_userns before checking permissions. + * On non-idmapped mounts or if permission checking is to be performed on the + * raw inode simply passs init_user_ns. + */ +struct dentry *vfs_tmpfile(struct user_namespace *mnt_userns, + struct dentry *dentry, umode_t mode, int open_flag) { struct dentry *child = NULL; struct inode *dir = dentry->d_inode; @@ -3361,7 +3393,7 @@ struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode, int open_flag) int error; /* we want directory to be writable */ - error = inode_permission(&init_user_ns, dir, MAY_WRITE | MAY_EXEC); + error = inode_permission(mnt_userns, dir, MAY_WRITE | MAY_EXEC); if (error) goto out_err; error = -EOPNOTSUPP; @@ -3396,6 +3428,7 @@ static int do_tmpfile(struct nameidata *nd, unsigned flags, const struct open_flags *op, struct file *file) { + struct user_namespace *mnt_userns; struct dentry *child; struct path path; int error = path_lookupat(nd, flags | LOOKUP_DIRECTORY, &path); @@ -3404,7 +3437,8 @@ static int do_tmpfile(struct nameidata *nd, unsigned flags, error = mnt_want_write(path.mnt); if (unlikely(error)) goto out; - child = vfs_tmpfile(path.dentry, op->mode, op->open_flag); + mnt_userns = mnt_user_ns(path.mnt); + child = vfs_tmpfile(mnt_userns, path.dentry, op->mode, op->open_flag); error = PTR_ERR(child); if (IS_ERR(child)) goto out2; @@ -3616,10 +3650,27 @@ inline struct dentry *user_path_create(int dfd, const char __user *pathname, } EXPORT_SYMBOL(user_path_create); -int vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) +/** + * vfs_mknod - create device node or file + * @mnt_userns: user namespace of the mount the inode was found from + * @dir: inode of @dentry + * @dentry: pointer to dentry of the base directory + * @mode: mode of the new device node or file + * @dev: device number of device to create + * + * Create a device node or file. + * + * If the inode has been found through an idmapped mount the user namespace of + * the vfsmount must be passed through @mnt_userns. This function will then take + * care to map the inode according to @mnt_userns before checking permissions. + * On non-idmapped mounts or if permission checking is to be performed on the + * raw inode simply passs init_user_ns. + */ +int vfs_mknod(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, dev_t dev) { bool is_whiteout = S_ISCHR(mode) && dev == WHITEOUT_DEV; - int error = may_create(&init_user_ns, dir, dentry); + int error = may_create(mnt_userns, dir, dentry); if (error) return error; @@ -3666,6 +3717,7 @@ static int may_mknod(umode_t mode) static long do_mknodat(int dfd, const char __user *filename, umode_t mode, unsigned int dev) { + struct user_namespace *mnt_userns; struct dentry *dentry; struct path path; int error; @@ -3684,18 +3736,22 @@ retry: error = security_path_mknod(&path, dentry, mode, dev); if (error) goto out; + + mnt_userns = mnt_user_ns(path.mnt); switch (mode & S_IFMT) { case 0: case S_IFREG: - error = vfs_create(path.dentry->d_inode,dentry,mode,true); + error = vfs_create(mnt_userns, path.dentry->d_inode, + dentry, mode, true); if (!error) ima_post_path_mknod(dentry); break; case S_IFCHR: case S_IFBLK: - error = vfs_mknod(path.dentry->d_inode,dentry,mode, - new_decode_dev(dev)); + error = vfs_mknod(mnt_userns, path.dentry->d_inode, + dentry, mode, new_decode_dev(dev)); break; case S_IFIFO: case S_IFSOCK: - error = vfs_mknod(path.dentry->d_inode,dentry,mode,0); + error = vfs_mknod(mnt_userns, path.dentry->d_inode, + dentry, mode, 0); break; } out: @@ -3718,9 +3774,25 @@ SYSCALL_DEFINE3(mknod, const char __user *, filename, umode_t, mode, unsigned, d return do_mknodat(AT_FDCWD, filename, mode, dev); } -int vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +/** + * vfs_mkdir - create directory + * @mnt_userns: user namespace of the mount the inode was found from + * @dir: inode of @dentry + * @dentry: pointer to dentry of the base directory + * @mode: mode of the new directory + * + * Create a directory. + * + * If the inode has been found through an idmapped mount the user namespace of + * the vfsmount must be passed through @mnt_userns. This function will then take + * care to map the inode according to @mnt_userns before checking permissions. + * On non-idmapped mounts or if permission checking is to be performed on the + * raw inode simply passs init_user_ns. + */ +int vfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { - int error = may_create(&init_user_ns, dir, dentry); + int error = may_create(mnt_userns, dir, dentry); unsigned max_links = dir->i_sb->s_max_links; if (error) @@ -3759,8 +3831,11 @@ retry: if (!IS_POSIXACL(path.dentry->d_inode)) mode &= ~current_umask(); error = security_path_mkdir(&path, dentry, mode); - if (!error) - error = vfs_mkdir(path.dentry->d_inode, dentry, mode); + if (!error) { + struct user_namespace *mnt_userns; + mnt_userns = mnt_user_ns(path.mnt); + error = vfs_mkdir(mnt_userns, path.dentry->d_inode, dentry, mode); + } done_path_create(&path, dentry); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; @@ -3779,9 +3854,24 @@ SYSCALL_DEFINE2(mkdir, const char __user *, pathname, umode_t, mode) return do_mkdirat(AT_FDCWD, pathname, mode); } -int vfs_rmdir(struct inode *dir, struct dentry *dentry) +/** + * vfs_rmdir - remove directory + * @mnt_userns: user namespace of the mount the inode was found from + * @dir: inode of @dentry + * @dentry: pointer to dentry of the base directory + * + * Remove a directory. + * + * If the inode has been found through an idmapped mount the user namespace of + * the vfsmount must be passed through @mnt_userns. This function will then take + * care to map the inode according to @mnt_userns before checking permissions. + * On non-idmapped mounts or if permission checking is to be performed on the + * raw inode simply passs init_user_ns. + */ +int vfs_rmdir(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry) { - int error = may_delete(&init_user_ns, dir, dentry, 1); + int error = may_delete(mnt_userns, dir, dentry, 1); if (error) return error; @@ -3821,6 +3911,7 @@ EXPORT_SYMBOL(vfs_rmdir); long do_rmdir(int dfd, struct filename *name) { + struct user_namespace *mnt_userns; int error = 0; struct dentry *dentry; struct path path; @@ -3861,7 +3952,8 @@ retry: error = security_path_rmdir(&path, dentry); if (error) goto exit3; - error = vfs_rmdir(path.dentry->d_inode, dentry); + mnt_userns = mnt_user_ns(path.mnt); + error = vfs_rmdir(mnt_userns, path.dentry->d_inode, dentry); exit3: dput(dentry); exit2: @@ -3884,6 +3976,7 @@ SYSCALL_DEFINE1(rmdir, const char __user *, pathname) /** * vfs_unlink - unlink a filesystem object + * @mnt_userns: user namespace of the mount the inode was found from * @dir: parent directory * @dentry: victim * @delegated_inode: returns victim inode, if the inode is delegated. @@ -3899,11 +3992,18 @@ SYSCALL_DEFINE1(rmdir, const char __user *, pathname) * Alternatively, a caller may pass NULL for delegated_inode. This may * be appropriate for callers that expect the underlying filesystem not * to be NFS exported. + * + * If the inode has been found through an idmapped mount the user namespace of + * the vfsmount must be passed through @mnt_userns. This function will then take + * care to map the inode according to @mnt_userns before checking permissions. + * On non-idmapped mounts or if permission checking is to be performed on the + * raw inode simply passs init_user_ns. */ -int vfs_unlink(struct inode *dir, struct dentry *dentry, struct inode **delegated_inode) +int vfs_unlink(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, struct inode **delegated_inode) { struct inode *target = dentry->d_inode; - int error = may_delete(&init_user_ns, dir, dentry, 0); + int error = may_delete(mnt_userns, dir, dentry, 0); if (error) return error; @@ -3974,6 +4074,8 @@ retry_deleg: dentry = __lookup_hash(&last, path.dentry, lookup_flags); error = PTR_ERR(dentry); if (!IS_ERR(dentry)) { + struct user_namespace *mnt_userns; + /* Why not before? Because we want correct error value */ if (last.name[last.len]) goto slashes; @@ -3984,7 +4086,8 @@ retry_deleg: error = security_path_unlink(&path, dentry); if (error) goto exit2; - error = vfs_unlink(path.dentry->d_inode, dentry, &delegated_inode); + mnt_userns = mnt_user_ns(path.mnt); + error = vfs_unlink(mnt_userns, path.dentry->d_inode, dentry, &delegated_inode); exit2: dput(dentry); } @@ -4033,9 +4136,25 @@ SYSCALL_DEFINE1(unlink, const char __user *, pathname) return do_unlinkat(AT_FDCWD, getname(pathname)); } -int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname) +/** + * vfs_symlink - create symlink + * @mnt_userns: user namespace of the mount the inode was found from + * @dir: inode of @dentry + * @dentry: pointer to dentry of the base directory + * @oldname: name of the file to link to + * + * Create a symlink. + * + * If the inode has been found through an idmapped mount the user namespace of + * the vfsmount must be passed through @mnt_userns. This function will then take + * care to map the inode according to @mnt_userns before checking permissions. + * On non-idmapped mounts or if permission checking is to be performed on the + * raw inode simply passs init_user_ns. + */ +int vfs_symlink(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, const char *oldname) { - int error = may_create(&init_user_ns, dir, dentry); + int error = may_create(mnt_userns, dir, dentry); if (error) return error; @@ -4073,8 +4192,13 @@ retry: goto out_putname; error = security_path_symlink(&path, dentry, from->name); - if (!error) - error = vfs_symlink(path.dentry->d_inode, dentry, from->name); + if (!error) { + struct user_namespace *mnt_userns; + + mnt_userns = mnt_user_ns(path.mnt); + error = vfs_symlink(mnt_userns, path.dentry->d_inode, dentry, + from->name); + } done_path_create(&path, dentry); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; @@ -4099,6 +4223,7 @@ SYSCALL_DEFINE2(symlink, const char __user *, oldname, const char __user *, newn /** * vfs_link - create a new link * @old_dentry: object to be linked + * @mnt_userns: the user namespace of the mount * @dir: new parent * @new_dentry: where to create the new link * @delegated_inode: returns inode needing a delegation break @@ -4114,8 +4239,16 @@ SYSCALL_DEFINE2(symlink, const char __user *, oldname, const char __user *, newn * Alternatively, a caller may pass NULL for delegated_inode. This may * be appropriate for callers that expect the underlying filesystem not * to be NFS exported. + * + * If the inode has been found through an idmapped mount the user namespace of + * the vfsmount must be passed through @mnt_userns. This function will then take + * care to map the inode according to @mnt_userns before checking permissions. + * On non-idmapped mounts or if permission checking is to be performed on the + * raw inode simply passs init_user_ns. */ -int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry, struct inode **delegated_inode) +int vfs_link(struct dentry *old_dentry, struct user_namespace *mnt_userns, + struct inode *dir, struct dentry *new_dentry, + struct inode **delegated_inode) { struct inode *inode = old_dentry->d_inode; unsigned max_links = dir->i_sb->s_max_links; @@ -4124,7 +4257,7 @@ int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_de if (!inode) return -ENOENT; - error = may_create(&init_user_ns, dir, new_dentry); + error = may_create(mnt_userns, dir, new_dentry); if (error) return error; @@ -4141,7 +4274,7 @@ int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_de * be writen back improperly if their true value is unknown to * the vfs. */ - if (HAS_UNMAPPED_ID(&init_user_ns, inode)) + if (HAS_UNMAPPED_ID(mnt_userns, inode)) return -EPERM; if (!dir->i_op->link) return -EPERM; @@ -4188,6 +4321,7 @@ EXPORT_SYMBOL(vfs_link); static int do_linkat(int olddfd, const char __user *oldname, int newdfd, const char __user *newname, int flags) { + struct user_namespace *mnt_userns; struct dentry *new_dentry; struct path old_path, new_path; struct inode *delegated_inode = NULL; @@ -4229,7 +4363,9 @@ retry: error = security_path_link(old_path.dentry, &new_path, new_dentry); if (error) goto out_dput; - error = vfs_link(old_path.dentry, new_path.dentry->d_inode, new_dentry, &delegated_inode); + mnt_userns = mnt_user_ns(new_path.mnt); + error = vfs_link(old_path.dentry, mnt_userns, new_path.dentry->d_inode, + new_dentry, &delegated_inode); out_dput: done_path_create(&new_path, new_dentry); if (delegated_inode) { @@ -4263,12 +4399,14 @@ SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname /** * vfs_rename - rename a filesystem object - * @old_dir: parent of source - * @old_dentry: source - * @new_dir: parent of destination - * @new_dentry: destination - * @delegated_inode: returns an inode needing a delegation break - * @flags: rename flags + * @old_mnt_userns: old user namespace of the mount the inode was found from + * @old_dir: parent of source + * @old_dentry: source + * @new_mnt_userns: new user namespace of the mount the inode was found from + * @new_dir: parent of destination + * @new_dentry: destination + * @delegated_inode: returns an inode needing a delegation break + * @flags: rename flags * * The caller must hold multiple mutexes--see lock_rename()). * @@ -4314,7 +4452,6 @@ SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname int vfs_rename(struct renamedata *rd) { int error; - struct user_namespace *mnt_userns = &init_user_ns; struct inode *old_dir = rd->old_dir, *new_dir = rd->new_dir; struct dentry *old_dentry = rd->old_dentry; struct dentry *new_dentry = rd->new_dentry; @@ -4330,19 +4467,21 @@ int vfs_rename(struct renamedata *rd) if (source == target) return 0; - error = may_delete(mnt_userns, old_dir, old_dentry, is_dir); + error = may_delete(rd->old_mnt_userns, old_dir, old_dentry, is_dir); if (error) return error; if (!target) { - error = may_create(mnt_userns, new_dir, new_dentry); + error = may_create(rd->new_mnt_userns, new_dir, new_dentry); } else { new_is_dir = d_is_dir(new_dentry); if (!(flags & RENAME_EXCHANGE)) - error = may_delete(mnt_userns, new_dir, new_dentry, is_dir); + error = may_delete(rd->new_mnt_userns, new_dir, + new_dentry, is_dir); else - error = may_delete(mnt_userns, new_dir, new_dentry, new_is_dir); + error = may_delete(rd->new_mnt_userns, new_dir, + new_dentry, new_is_dir); } if (error) return error; @@ -4356,13 +4495,13 @@ int vfs_rename(struct renamedata *rd) */ if (new_dir != old_dir) { if (is_dir) { - error = inode_permission(&init_user_ns, source, + error = inode_permission(rd->old_mnt_userns, source, MAY_WRITE); if (error) return error; } if ((flags & RENAME_EXCHANGE) && new_is_dir) { - error = inode_permission(&init_user_ns, target, + error = inode_permission(rd->new_mnt_userns, target, MAY_WRITE); if (error) return error; @@ -4552,8 +4691,10 @@ retry_deleg: rd.old_dir = old_path.dentry->d_inode; rd.old_dentry = old_dentry; + rd.old_mnt_userns = mnt_user_ns(old_path.mnt); rd.new_dir = new_path.dentry->d_inode; rd.new_dentry = new_dentry; + rd.new_mnt_userns = mnt_user_ns(new_path.mnt); rd.delegated_inode = &delegated_inode; rd.flags = flags; error = vfs_rename(&rd); diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index 186fa2c2c6ba..891395c6c7d3 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -233,7 +233,7 @@ nfsd4_create_clid_dir(struct nfs4_client *clp) * as well be forgiving and just succeed silently. */ goto out_put; - status = vfs_mkdir(d_inode(dir), dentry, S_IRWXU); + status = vfs_mkdir(&init_user_ns, d_inode(dir), dentry, S_IRWXU); out_put: dput(dentry); out_unlock: @@ -353,7 +353,7 @@ nfsd4_unlink_clid_dir(char *name, int namlen, struct nfsd_net *nn) status = -ENOENT; if (d_really_is_negative(dentry)) goto out; - status = vfs_rmdir(d_inode(dir), dentry); + status = vfs_rmdir(&init_user_ns, d_inode(dir), dentry); out: dput(dentry); out_unlock: @@ -443,7 +443,7 @@ purge_old(struct dentry *parent, struct dentry *child, struct nfsd_net *nn) if (nfs4_has_reclaimed_state(name, nn)) goto out_free; - status = vfs_rmdir(d_inode(parent), child); + status = vfs_rmdir(&init_user_ns, d_inode(parent), child); if (status) printk("failed to remove client recovery directory %pd\n", child); diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index f7d83ff2b44e..fab873178140 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -1255,12 +1255,12 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp, host_err = 0; switch (type) { case S_IFREG: - host_err = vfs_create(dirp, dchild, iap->ia_mode, true); + host_err = vfs_create(&init_user_ns, dirp, dchild, iap->ia_mode, true); if (!host_err) nfsd_check_ignore_resizing(iap); break; case S_IFDIR: - host_err = vfs_mkdir(dirp, dchild, iap->ia_mode); + host_err = vfs_mkdir(&init_user_ns, dirp, dchild, iap->ia_mode); if (!host_err && unlikely(d_unhashed(dchild))) { struct dentry *d; d = lookup_one_len(dchild->d_name.name, @@ -1288,7 +1288,8 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp, case S_IFBLK: case S_IFIFO: case S_IFSOCK: - host_err = vfs_mknod(dirp, dchild, iap->ia_mode, rdev); + host_err = vfs_mknod(&init_user_ns, dirp, dchild, + iap->ia_mode, rdev); break; default: printk(KERN_WARNING "nfsd: bad file type %o in nfsd_create\n", @@ -1486,7 +1487,7 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, if (!IS_POSIXACL(dirp)) iap->ia_mode &= ~current_umask(); - host_err = vfs_create(dirp, dchild, iap->ia_mode, true); + host_err = vfs_create(&init_user_ns, dirp, dchild, iap->ia_mode, true); if (host_err < 0) { fh_drop_write(fhp); goto out_nfserr; @@ -1610,7 +1611,7 @@ nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp, if (IS_ERR(dnew)) goto out_nfserr; - host_err = vfs_symlink(d_inode(dentry), dnew, path); + host_err = vfs_symlink(&init_user_ns, d_inode(dentry), dnew, path); err = nfserrno(host_err); if (!err) err = nfserrno(commit_metadata(fhp)); @@ -1678,7 +1679,7 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp, err = nfserr_noent; if (d_really_is_negative(dold)) goto out_dput; - host_err = vfs_link(dold, dirp, dnew, NULL); + host_err = vfs_link(dold, &init_user_ns, dirp, dnew, NULL); if (!host_err) { err = nfserrno(commit_metadata(ffhp)); if (!err) @@ -1799,8 +1800,10 @@ retry: goto out_dput_old; } else { struct renamedata rd = { + .old_mnt_userns = &init_user_ns, .old_dir = fdir, .old_dentry = odentry, + .new_mnt_userns = &init_user_ns, .new_dir = tdir, .new_dentry = ndentry, }; @@ -1891,9 +1894,9 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, if (type != S_IFDIR) { if (rdentry->d_sb->s_export_op->flags & EXPORT_OP_CLOSE_BEFORE_UNLINK) nfsd_close_cached_files(rdentry); - host_err = vfs_unlink(dirp, rdentry, NULL); + host_err = vfs_unlink(&init_user_ns, dirp, rdentry, NULL); } else { - host_err = vfs_rmdir(dirp, rdentry); + host_err = vfs_rmdir(&init_user_ns, dirp, rdentry); } if (!host_err) diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index d75c96cb18c3..6904cc2ed7bb 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -821,9 +821,9 @@ static int ovl_remove_upper(struct dentry *dentry, bool is_dir, goto out_dput_upper; if (is_dir) - err = vfs_rmdir(dir, upper); + err = vfs_rmdir(&init_user_ns, dir, upper); else - err = vfs_unlink(dir, upper, NULL); + err = vfs_unlink(&init_user_ns, dir, upper, NULL); ovl_dir_modified(dentry->d_parent, ovl_type_origin(dentry)); /* diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index 426899681df7..5e9eb46e741a 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -123,7 +123,7 @@ static inline const char *ovl_xattr(struct ovl_fs *ofs, enum ovl_xattr ox) static inline int ovl_do_rmdir(struct inode *dir, struct dentry *dentry) { - int err = vfs_rmdir(dir, dentry); + int err = vfs_rmdir(&init_user_ns, dir, dentry); pr_debug("rmdir(%pd2) = %i\n", dentry, err); return err; @@ -131,7 +131,7 @@ static inline int ovl_do_rmdir(struct inode *dir, struct dentry *dentry) static inline int ovl_do_unlink(struct inode *dir, struct dentry *dentry) { - int err = vfs_unlink(dir, dentry, NULL); + int err = vfs_unlink(&init_user_ns, dir, dentry, NULL); pr_debug("unlink(%pd2) = %i\n", dentry, err); return err; @@ -140,7 +140,7 @@ static inline int ovl_do_unlink(struct inode *dir, struct dentry *dentry) static inline int ovl_do_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry) { - int err = vfs_link(old_dentry, dir, new_dentry, NULL); + int err = vfs_link(old_dentry, &init_user_ns, dir, new_dentry, NULL); pr_debug("link(%pd2, %pd2) = %i\n", old_dentry, new_dentry, err); return err; @@ -149,7 +149,7 @@ static inline int ovl_do_link(struct dentry *old_dentry, struct inode *dir, static inline int ovl_do_create(struct inode *dir, struct dentry *dentry, umode_t mode) { - int err = vfs_create(dir, dentry, mode, true); + int err = vfs_create(&init_user_ns, dir, dentry, mode, true); pr_debug("create(%pd2, 0%o) = %i\n", dentry, mode, err); return err; @@ -158,7 +158,7 @@ static inline int ovl_do_create(struct inode *dir, struct dentry *dentry, static inline int ovl_do_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) { - int err = vfs_mkdir(dir, dentry, mode); + int err = vfs_mkdir(&init_user_ns, dir, dentry, mode); pr_debug("mkdir(%pd2, 0%o) = %i\n", dentry, mode, err); return err; } @@ -166,7 +166,7 @@ static inline int ovl_do_mkdir(struct inode *dir, struct dentry *dentry, static inline int ovl_do_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) { - int err = vfs_mknod(dir, dentry, mode, dev); + int err = vfs_mknod(&init_user_ns, dir, dentry, mode, dev); pr_debug("mknod(%pd2, 0%o, 0%o) = %i\n", dentry, mode, dev, err); return err; @@ -175,7 +175,7 @@ static inline int ovl_do_mknod(struct inode *dir, struct dentry *dentry, static inline int ovl_do_symlink(struct inode *dir, struct dentry *dentry, const char *oldname) { - int err = vfs_symlink(dir, dentry, oldname); + int err = vfs_symlink(&init_user_ns, dir, dentry, oldname); pr_debug("symlink(\"%s\", %pd2) = %i\n", oldname, dentry, err); return err; @@ -215,8 +215,10 @@ static inline int ovl_do_rename(struct inode *olddir, struct dentry *olddentry, { int err; struct renamedata rd = { + .old_mnt_userns = &init_user_ns, .old_dir = olddir, .old_dentry = olddentry, + .new_mnt_userns = &init_user_ns, .new_dir = newdir, .new_dentry = newdentry, .flags = flags, @@ -233,14 +235,14 @@ static inline int ovl_do_rename(struct inode *olddir, struct dentry *olddentry, static inline int ovl_do_whiteout(struct inode *dir, struct dentry *dentry) { - int err = vfs_whiteout(dir, dentry); + int err = vfs_whiteout(&init_user_ns, dir, dentry); pr_debug("whiteout(%pd2) = %i\n", dentry, err); return err; } static inline struct dentry *ovl_do_tmpfile(struct dentry *dentry, umode_t mode) { - struct dentry *ret = vfs_tmpfile(dentry, mode, 0); + struct dentry *ret = vfs_tmpfile(&init_user_ns, dentry, mode, 0); int err = PTR_ERR_OR_ZERO(ret); pr_debug("tmpfile(%pd2, 0%o) = %i\n", dentry, mode, err); diff --git a/include/linux/fs.h b/include/linux/fs.h index 430e457f67f1..29d7b2fe7de4 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1768,17 +1768,25 @@ bool inode_owner_or_capable(struct user_namespace *mnt_userns, /* * VFS helper functions.. */ -extern int vfs_create(struct inode *, struct dentry *, umode_t, bool); -extern int vfs_mkdir(struct inode *, struct dentry *, umode_t); -extern int vfs_mknod(struct inode *, struct dentry *, umode_t, dev_t); -extern int vfs_symlink(struct inode *, struct dentry *, const char *); -extern int vfs_link(struct dentry *, struct inode *, struct dentry *, struct inode **); -extern int vfs_rmdir(struct inode *, struct dentry *); -extern int vfs_unlink(struct inode *, struct dentry *, struct inode **); +int vfs_create(struct user_namespace *, struct inode *, + struct dentry *, umode_t, bool); +int vfs_mkdir(struct user_namespace *, struct inode *, + struct dentry *, umode_t); +int vfs_mknod(struct user_namespace *, struct inode *, struct dentry *, + umode_t, dev_t); +int vfs_symlink(struct user_namespace *, struct inode *, + struct dentry *, const char *); +int vfs_link(struct dentry *, struct user_namespace *, struct inode *, + struct dentry *, struct inode **); +int vfs_rmdir(struct user_namespace *, struct inode *, struct dentry *); +int vfs_unlink(struct user_namespace *, struct inode *, struct dentry *, + struct inode **); struct renamedata { + struct user_namespace *old_mnt_userns; struct inode *old_dir; struct dentry *old_dentry; + struct user_namespace *new_mnt_userns; struct inode *new_dir; struct dentry *new_dentry; struct inode **delegated_inode; @@ -1787,13 +1795,15 @@ struct renamedata { int vfs_rename(struct renamedata *); -static inline int vfs_whiteout(struct inode *dir, struct dentry *dentry) +static inline int vfs_whiteout(struct user_namespace *mnt_userns, + struct inode *dir, struct dentry *dentry) { - return vfs_mknod(dir, dentry, S_IFCHR | WHITEOUT_MODE, WHITEOUT_DEV); + return vfs_mknod(mnt_userns, dir, dentry, S_IFCHR | WHITEOUT_MODE, + WHITEOUT_DEV); } -extern struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode, - int open_flag); +struct dentry *vfs_tmpfile(struct user_namespace *mnt_userns, + struct dentry *dentry, umode_t mode, int open_flag); int vfs_mkobj(struct dentry *, umode_t, int (*f)(struct dentry *, umode_t, void *), diff --git a/ipc/mqueue.c b/ipc/mqueue.c index 693f01fe1216..fcd56e077733 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -965,7 +965,8 @@ SYSCALL_DEFINE1(mq_unlink, const char __user *, u_name) err = -ENOENT; } else { ihold(inode); - err = vfs_unlink(d_inode(dentry->d_parent), dentry, NULL); + err = vfs_unlink(&init_user_ns, d_inode(dentry->d_parent), + dentry, NULL); } dput(dentry); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 18453d15dddf..9a1f3c04402e 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -996,7 +996,8 @@ static int unix_mknod(const char *sun_path, umode_t mode, struct path *res) */ err = security_path_mknod(&path, dentry, mode, 0); if (!err) { - err = vfs_mknod(d_inode(path.dentry), dentry, mode, 0); + err = vfs_mknod(&init_user_ns, d_inode(path.dentry), dentry, + mode, 0); if (!err) { res->mnt = mntget(path.mnt); res->dentry = dget(dentry); -- cgit v1.2.3 From 643fe55a0679ae5582a1a2a1df86dc240292cd1b Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 21 Jan 2021 14:19:34 +0100 Subject: open: handle idmapped mounts in do_truncate() When truncating files the vfs will verify that the caller is privileged over the inode. Extend it to handle idmapped mounts. If the inode is accessed through an idmapped mount it is mapped according to the mount's user namespace. Afterwards the permissions checks are identical to non-idmapped mounts. If the initial user namespace is passed nothing changes so non-idmapped mounts will see identical behavior as before. Link: https://lore.kernel.org/r/20210121131959.646623-16-christian.brauner@ubuntu.com Cc: Christoph Hellwig Cc: David Howells Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig Signed-off-by: Christian Brauner --- fs/coredump.c | 10 +++++++--- fs/inode.c | 7 ++++--- fs/namei.c | 2 +- fs/open.c | 16 +++++++++------- include/linux/fs.h | 4 ++-- 5 files changed, 23 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/fs/coredump.c b/fs/coredump.c index a2f6ecc8e345..ae778937a1ff 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -703,6 +703,7 @@ void do_coredump(const kernel_siginfo_t *siginfo) goto close_fail; } } else { + struct user_namespace *mnt_userns; struct inode *inode; int open_flags = O_CREAT | O_RDWR | O_NOFOLLOW | O_LARGEFILE | O_EXCL; @@ -780,13 +781,15 @@ void do_coredump(const kernel_siginfo_t *siginfo) * a process dumps core while its cwd is e.g. on a vfat * filesystem. */ - if (!uid_eq(inode->i_uid, current_fsuid())) + mnt_userns = file_mnt_user_ns(cprm.file); + if (!uid_eq(i_uid_into_mnt(mnt_userns, inode), current_fsuid())) goto close_fail; if ((inode->i_mode & 0677) != 0600) goto close_fail; if (!(cprm.file->f_mode & FMODE_CAN_WRITE)) goto close_fail; - if (do_truncate(cprm.file->f_path.dentry, 0, 0, cprm.file)) + if (do_truncate(mnt_userns, cprm.file->f_path.dentry, + 0, 0, cprm.file)) goto close_fail; } @@ -931,7 +934,8 @@ void dump_truncate(struct coredump_params *cprm) if (file->f_op->llseek && file->f_op->llseek != no_llseek) { offset = file->f_op->llseek(file, 0, SEEK_CUR); if (i_size_read(file->f_mapping->host) < offset) - do_truncate(file->f_path.dentry, offset, 0, file); + do_truncate(file_mnt_user_ns(file), file->f_path.dentry, + offset, 0, file); } } EXPORT_SYMBOL(dump_truncate); diff --git a/fs/inode.c b/fs/inode.c index 46116ef44c9f..08151968c9ef 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1903,7 +1903,8 @@ int dentry_needs_remove_privs(struct dentry *dentry) return mask; } -static int __remove_privs(struct dentry *dentry, int kill) +static int __remove_privs(struct user_namespace *mnt_userns, + struct dentry *dentry, int kill) { struct iattr newattrs; @@ -1912,7 +1913,7 @@ static int __remove_privs(struct dentry *dentry, int kill) * Note we call this on write, so notify_change will not * encounter any conflicting delegations: */ - return notify_change(&init_user_ns, dentry, &newattrs, NULL); + return notify_change(mnt_userns, dentry, &newattrs, NULL); } /* @@ -1939,7 +1940,7 @@ int file_remove_privs(struct file *file) if (kill < 0) return kill; if (kill) - error = __remove_privs(dentry, kill); + error = __remove_privs(file_mnt_user_ns(file), dentry, kill); if (!error) inode_has_no_xattr(inode); diff --git a/fs/namei.c b/fs/namei.c index 5c9f6f8e90c4..c8c083daf368 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3009,7 +3009,7 @@ static int handle_truncate(struct file *filp) if (!error) error = security_path_truncate(path); if (!error) { - error = do_truncate(path->dentry, 0, + error = do_truncate(&init_user_ns, path->dentry, 0, ATTR_MTIME|ATTR_CTIME|ATTR_OPEN, filp); } diff --git a/fs/open.c b/fs/open.c index c3e4dc43dd8d..8b3f3eb652d0 100644 --- a/fs/open.c +++ b/fs/open.c @@ -35,8 +35,8 @@ #include "internal.h" -int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs, - struct file *filp) +int do_truncate(struct user_namespace *mnt_userns, struct dentry *dentry, + loff_t length, unsigned int time_attrs, struct file *filp) { int ret; struct iattr newattrs; @@ -61,13 +61,14 @@ int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs, inode_lock(dentry->d_inode); /* Note any delegations or leases have already been broken: */ - ret = notify_change(&init_user_ns, dentry, &newattrs, NULL); + ret = notify_change(mnt_userns, dentry, &newattrs, NULL); inode_unlock(dentry->d_inode); return ret; } long vfs_truncate(const struct path *path, loff_t length) { + struct user_namespace *mnt_userns; struct inode *inode; long error; @@ -83,7 +84,8 @@ long vfs_truncate(const struct path *path, loff_t length) if (error) goto out; - error = inode_permission(&init_user_ns, inode, MAY_WRITE); + mnt_userns = mnt_user_ns(path->mnt); + error = inode_permission(mnt_userns, inode, MAY_WRITE); if (error) goto mnt_drop_write_and_out; @@ -107,7 +109,7 @@ long vfs_truncate(const struct path *path, loff_t length) if (!error) error = security_path_truncate(path); if (!error) - error = do_truncate(path->dentry, length, 0, NULL); + error = do_truncate(mnt_userns, path->dentry, length, 0, NULL); put_write_and_out: put_write_access(inode); @@ -186,13 +188,13 @@ long do_sys_ftruncate(unsigned int fd, loff_t length, int small) /* Check IS_APPEND on real upper inode */ if (IS_APPEND(file_inode(f.file))) goto out_putf; - sb_start_write(inode->i_sb); error = locks_verify_truncate(inode, f.file, length); if (!error) error = security_path_truncate(&f.file->f_path); if (!error) - error = do_truncate(dentry, length, ATTR_MTIME|ATTR_CTIME, f.file); + error = do_truncate(file_mnt_user_ns(f.file), dentry, length, + ATTR_MTIME | ATTR_CTIME, f.file); sb_end_write(inode->i_sb); out_putf: fdput(f); diff --git a/include/linux/fs.h b/include/linux/fs.h index 29d7b2fe7de4..f0601cca1930 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2593,8 +2593,8 @@ static inline struct user_namespace *file_mnt_user_ns(struct file *file) return mnt_user_ns(file->f_path.mnt); } extern long vfs_truncate(const struct path *, loff_t); -extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs, - struct file *filp); +int do_truncate(struct user_namespace *, struct dentry *, loff_t start, + unsigned int time_attrs, struct file *filp); extern int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len); extern long do_sys_open(int dfd, const char __user *filename, int flags, -- cgit v1.2.3 From 549c7297717c32ee53f156cd949e055e601f67bb Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 21 Jan 2021 14:19:43 +0100 Subject: fs: make helpers idmap mount aware Extend some inode methods with an additional user namespace argument. A filesystem that is aware of idmapped mounts will receive the user namespace the mount has been marked with. This can be used for additional permission checking and also to enable filesystems to translate between uids and gids if they need to. We have implemented all relevant helpers in earlier patches. As requested we simply extend the exisiting inode method instead of introducing new ones. This is a little more code churn but it's mostly mechanical and doesnt't leave us with additional inode methods. Link: https://lore.kernel.org/r/20210121131959.646623-25-christian.brauner@ubuntu.com Cc: Christoph Hellwig Cc: David Howells Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig Signed-off-by: Christian Brauner --- Documentation/filesystems/vfs.rst | 19 ++++++----- arch/powerpc/platforms/cell/spufs/inode.c | 3 +- drivers/android/binderfs.c | 6 ++-- fs/9p/acl.c | 4 +-- fs/9p/v9fs.h | 3 +- fs/9p/v9fs_vfs.h | 3 +- fs/9p/vfs_inode.c | 26 ++++++++------- fs/9p/vfs_inode_dotl.c | 31 +++++++++-------- fs/adfs/adfs.h | 3 +- fs/adfs/inode.c | 3 +- fs/affs/affs.h | 24 +++++++++----- fs/affs/inode.c | 3 +- fs/affs/namei.c | 15 +++++---- fs/afs/dir.c | 34 ++++++++++--------- fs/afs/inode.c | 7 ++-- fs/afs/internal.h | 7 ++-- fs/afs/security.c | 3 +- fs/attr.c | 4 +-- fs/autofs/root.c | 17 ++++++---- fs/bad_inode.c | 36 ++++++++++++-------- fs/bfs/dir.c | 10 +++--- fs/btrfs/acl.c | 3 +- fs/btrfs/ctree.h | 3 +- fs/btrfs/inode.c | 33 +++++++++++-------- fs/ceph/acl.c | 3 +- fs/ceph/dir.c | 23 ++++++------- fs/ceph/inode.c | 10 +++--- fs/ceph/super.h | 12 ++++--- fs/cifs/cifsfs.c | 3 +- fs/cifs/cifsfs.h | 25 ++++++++------ fs/cifs/dir.c | 8 ++--- fs/cifs/inode.c | 16 +++++---- fs/cifs/link.c | 3 +- fs/coda/coda_linux.h | 8 +++-- fs/coda/dir.c | 18 ++++++---- fs/coda/inode.c | 7 ++-- fs/coda/pioctl.c | 6 ++-- fs/configfs/configfs_internal.h | 6 ++-- fs/configfs/dir.c | 3 +- fs/configfs/inode.c | 5 +-- fs/configfs/symlink.c | 3 +- fs/debugfs/inode.c | 9 ++--- fs/ecryptfs/inode.c | 30 ++++++++++------- fs/efivarfs/inode.c | 4 +-- fs/erofs/inode.c | 5 +-- fs/erofs/internal.h | 5 +-- fs/exfat/exfat_fs.h | 8 +++-- fs/exfat/file.c | 8 +++-- fs/exfat/namei.c | 14 ++++---- fs/ext2/acl.c | 3 +- fs/ext2/acl.h | 3 +- fs/ext2/ext2.h | 5 +-- fs/ext2/inode.c | 7 ++-- fs/ext2/namei.c | 22 ++++++++----- fs/ext4/acl.c | 3 +- fs/ext4/acl.h | 3 +- fs/ext4/ext4.h | 9 +++-- fs/ext4/inode.c | 12 ++++--- fs/ext4/namei.c | 19 ++++++----- fs/f2fs/acl.c | 3 +- fs/f2fs/acl.h | 3 +- fs/f2fs/f2fs.h | 7 ++-- fs/f2fs/file.c | 7 ++-- fs/f2fs/namei.c | 21 +++++++----- fs/fat/fat.h | 6 ++-- fs/fat/file.c | 9 ++--- fs/fat/namei_msdos.c | 10 +++--- fs/fat/namei_vfat.c | 13 ++++---- fs/fuse/acl.c | 3 +- fs/fuse/dir.c | 37 ++++++++++++--------- fs/fuse/fuse_i.h | 4 +-- fs/gfs2/acl.c | 3 +- fs/gfs2/acl.h | 3 +- fs/gfs2/file.c | 2 +- fs/gfs2/inode.c | 53 +++++++++++++++++------------ fs/gfs2/inode.h | 3 +- fs/hfs/dir.c | 13 ++++---- fs/hfs/hfs_fs.h | 3 +- fs/hfs/inode.c | 6 ++-- fs/hfsplus/dir.c | 22 +++++++------ fs/hfsplus/hfsplus_fs.h | 5 +-- fs/hfsplus/inode.c | 8 +++-- fs/hostfs/hostfs_kern.c | 23 ++++++++----- fs/hpfs/hpfs_fn.h | 2 +- fs/hpfs/inode.c | 3 +- fs/hpfs/namei.c | 20 ++++++----- fs/hugetlbfs/inode.c | 29 +++++++++------- fs/jffs2/acl.c | 3 +- fs/jffs2/acl.h | 3 +- fs/jffs2/dir.c | 33 +++++++++++-------- fs/jffs2/fs.c | 3 +- fs/jffs2/os-linux.h | 2 +- fs/jfs/acl.c | 3 +- fs/jfs/file.c | 3 +- fs/jfs/jfs_acl.h | 3 +- fs/jfs/jfs_inode.h | 2 +- fs/jfs/namei.c | 21 ++++++------ fs/kernfs/dir.c | 6 ++-- fs/kernfs/inode.c | 9 +++-- fs/kernfs/kernfs-internal.h | 9 +++-- fs/libfs.c | 31 +++++++++-------- fs/minix/file.c | 3 +- fs/minix/inode.c | 4 +-- fs/minix/minix.h | 3 +- fs/minix/namei.c | 24 ++++++++------ fs/namei.c | 55 ++++++++++++++++++------------- fs/nfs/dir.c | 23 ++++++++----- fs/nfs/inode.c | 7 ++-- fs/nfs/internal.h | 14 +++++--- fs/nfs/namespace.c | 13 +++++--- fs/nfs/nfs3_fs.h | 3 +- fs/nfs/nfs3acl.c | 3 +- fs/nilfs2/inode.c | 6 ++-- fs/nilfs2/namei.c | 19 ++++++----- fs/nilfs2/nilfs.h | 6 ++-- fs/ntfs/inode.c | 4 ++- fs/ntfs/inode.h | 3 +- fs/ocfs2/acl.c | 3 +- fs/ocfs2/acl.h | 3 +- fs/ocfs2/dlmfs/dlmfs.c | 9 +++-- fs/ocfs2/file.c | 10 +++--- fs/ocfs2/file.h | 11 ++++--- fs/ocfs2/namei.c | 19 +++++++---- fs/omfs/dir.c | 13 ++++---- fs/omfs/file.c | 3 +- fs/orangefs/acl.c | 3 +- fs/orangefs/inode.c | 10 +++--- fs/orangefs/namei.c | 12 ++++--- fs/orangefs/orangefs-kernel.h | 13 +++++--- fs/overlayfs/dir.c | 21 ++++++------ fs/overlayfs/inode.c | 10 +++--- fs/overlayfs/overlayfs.h | 10 +++--- fs/overlayfs/super.c | 2 +- fs/posix_acl.c | 9 ++--- fs/proc/base.c | 16 +++++---- fs/proc/fd.c | 3 +- fs/proc/fd.h | 3 +- fs/proc/generic.c | 6 ++-- fs/proc/internal.h | 6 ++-- fs/proc/proc_net.c | 3 +- fs/proc/proc_sysctl.c | 9 +++-- fs/proc/root.c | 3 +- fs/ramfs/file-nommu.c | 5 +-- fs/ramfs/inode.c | 16 +++++---- fs/reiserfs/acl.h | 3 +- fs/reiserfs/inode.c | 3 +- fs/reiserfs/namei.c | 19 ++++++----- fs/reiserfs/reiserfs.h | 3 +- fs/reiserfs/xattr.c | 11 ++++--- fs/reiserfs/xattr.h | 3 +- fs/reiserfs/xattr_acl.c | 3 +- fs/stat.c | 8 +++-- fs/sysv/file.c | 3 +- fs/sysv/itree.c | 4 +-- fs/sysv/namei.c | 21 +++++++----- fs/sysv/sysv.h | 3 +- fs/tracefs/inode.c | 4 ++- fs/ubifs/dir.c | 26 ++++++++------- fs/ubifs/file.c | 3 +- fs/ubifs/ubifs.h | 5 +-- fs/udf/file.c | 3 +- fs/udf/namei.c | 24 +++++++------- fs/udf/symlink.c | 5 +-- fs/ufs/inode.c | 3 +- fs/ufs/namei.c | 19 ++++++----- fs/ufs/ufs.h | 3 +- fs/vboxsf/dir.c | 12 ++++--- fs/vboxsf/utils.c | 7 ++-- fs/vboxsf/vfsmod.h | 8 +++-- fs/xfs/xfs_acl.c | 3 +- fs/xfs/xfs_acl.h | 3 +- fs/xfs/xfs_iops.c | 52 ++++++++++++++++------------- fs/zonefs/super.c | 3 +- include/linux/fs.h | 39 ++++++++++++++-------- include/linux/nfs_fs.h | 7 ++-- include/linux/posix_acl.h | 3 +- ipc/mqueue.c | 4 +-- kernel/bpf/inode.c | 7 ++-- mm/shmem.c | 39 ++++++++++++++-------- net/socket.c | 5 +-- security/apparmor/apparmorfs.c | 3 +- security/integrity/evm/evm_secfs.c | 2 +- 182 files changed, 1121 insertions(+), 756 deletions(-) (limited to 'include') diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst index ca52c82e5bb5..98290ef311ca 100644 --- a/Documentation/filesystems/vfs.rst +++ b/Documentation/filesystems/vfs.rst @@ -415,28 +415,29 @@ As of kernel 2.6.22, the following members are defined: .. code-block:: c struct inode_operations { - int (*create) (struct inode *,struct dentry *, umode_t, bool); + int (*create) (struct user_namespace *, struct inode *,struct dentry *, umode_t, bool); struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); int (*link) (struct dentry *,struct inode *,struct dentry *); int (*unlink) (struct inode *,struct dentry *); - int (*symlink) (struct inode *,struct dentry *,const char *); - int (*mkdir) (struct inode *,struct dentry *,umode_t); + int (*symlink) (struct user_namespace *, struct inode *,struct dentry *,const char *); + int (*mkdir) (struct user_namespace *, struct inode *,struct dentry *,umode_t); int (*rmdir) (struct inode *,struct dentry *); - int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t); - int (*rename) (struct inode *, struct dentry *, + int (*mknod) (struct user_namespace *, struct inode *,struct dentry *,umode_t,dev_t); + int (*rename) (struct user_namespace *, struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); int (*readlink) (struct dentry *, char __user *,int); const char *(*get_link) (struct dentry *, struct inode *, struct delayed_call *); - int (*permission) (struct inode *, int); + int (*permission) (struct user_namespace *, struct inode *, int); int (*get_acl)(struct inode *, int); - int (*setattr) (struct dentry *, struct iattr *); - int (*getattr) (const struct path *, struct kstat *, u32, unsigned int); + int (*setattr) (struct user_namespace *, struct dentry *, struct iattr *); + int (*getattr) (struct user_namespace *, const struct path *, struct kstat *, u32, unsigned int); ssize_t (*listxattr) (struct dentry *, char *, size_t); void (*update_time)(struct inode *, struct timespec *, int); int (*atomic_open)(struct inode *, struct dentry *, struct file *, unsigned open_flag, umode_t create_mode); - int (*tmpfile) (struct inode *, struct dentry *, umode_t); + int (*tmpfile) (struct user_namespace *, struct inode *, struct dentry *, umode_t); + int (*set_acl)(struct user_namespace *, struct inode *, struct posix_acl *, int); }; Again, all methods are called without any locks being held, unless diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index 3de526eb2275..b83a3670bd74 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -91,7 +91,8 @@ out: } static int -spufs_setattr(struct dentry *dentry, struct iattr *attr) +spufs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *attr) { struct inode *inode = d_inode(dentry); diff --git a/drivers/android/binderfs.c b/drivers/android/binderfs.c index 7b4f154f07e6..e80ba93c62a9 100644 --- a/drivers/android/binderfs.c +++ b/drivers/android/binderfs.c @@ -355,7 +355,8 @@ static inline bool is_binderfs_control_device(const struct dentry *dentry) return info->control_dentry == dentry; } -static int binderfs_rename(struct inode *old_dir, struct dentry *old_dentry, +static int binderfs_rename(struct user_namespace *mnt_userns, + struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { @@ -363,7 +364,8 @@ static int binderfs_rename(struct inode *old_dir, struct dentry *old_dentry, is_binderfs_control_device(new_dentry)) return -EPERM; - return simple_rename(old_dir, old_dentry, new_dir, new_dentry, flags); + return simple_rename(&init_user_ns, old_dir, old_dentry, new_dir, + new_dentry, flags); } static int binderfs_unlink(struct inode *dir, struct dentry *dentry) diff --git a/fs/9p/acl.c b/fs/9p/acl.c index 1c14f18a6ec9..bb1b286c49ae 100644 --- a/fs/9p/acl.c +++ b/fs/9p/acl.c @@ -280,7 +280,7 @@ static int v9fs_xattr_set_acl(const struct xattr_handler *handler, struct iattr iattr = { 0 }; struct posix_acl *old_acl = acl; - retval = posix_acl_update_mode(mnt_userns, inode, + retval = posix_acl_update_mode(&init_user_ns, inode, &iattr.ia_mode, &acl); if (retval) goto err_out; @@ -299,7 +299,7 @@ static int v9fs_xattr_set_acl(const struct xattr_handler *handler, * What is the following setxattr update the * mode ? */ - v9fs_vfs_setattr_dotl(dentry, &iattr); + v9fs_vfs_setattr_dotl(&init_user_ns, dentry, &iattr); } break; case ACL_TYPE_DEFAULT: diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h index 7b763776306e..4ca56c5dd637 100644 --- a/fs/9p/v9fs.h +++ b/fs/9p/v9fs.h @@ -135,7 +135,8 @@ extern struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags); extern int v9fs_vfs_unlink(struct inode *i, struct dentry *d); extern int v9fs_vfs_rmdir(struct inode *i, struct dentry *d); -extern int v9fs_vfs_rename(struct inode *old_dir, struct dentry *old_dentry, +extern int v9fs_vfs_rename(struct user_namespace *mnt_userns, + struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags); extern struct inode *v9fs_inode_from_fid(struct v9fs_session_info *v9ses, diff --git a/fs/9p/v9fs_vfs.h b/fs/9p/v9fs_vfs.h index fd2a2b040250..d44ade76966a 100644 --- a/fs/9p/v9fs_vfs.h +++ b/fs/9p/v9fs_vfs.h @@ -59,7 +59,8 @@ void v9fs_inode2stat(struct inode *inode, struct p9_wstat *stat); int v9fs_uflags2omode(int uflags, int extended); void v9fs_blank_wstat(struct p9_wstat *wstat); -int v9fs_vfs_setattr_dotl(struct dentry *, struct iattr *); +int v9fs_vfs_setattr_dotl(struct user_namespace *, struct dentry *, + struct iattr *); int v9fs_file_fsync_dotl(struct file *filp, loff_t start, loff_t end, int datasync); int v9fs_refresh_inode(struct p9_fid *fid, struct inode *inode); diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index c21b146c8d91..648eb4c4cf7f 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -676,8 +676,8 @@ error: */ static int -v9fs_vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - bool excl) +v9fs_vfs_create(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, bool excl) { struct v9fs_session_info *v9ses = v9fs_inode2v9ses(dir); u32 perm = unixmode2p9mode(v9ses, mode); @@ -702,7 +702,8 @@ v9fs_vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, * */ -static int v9fs_vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +static int v9fs_vfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { int err; u32 perm; @@ -907,9 +908,9 @@ int v9fs_vfs_rmdir(struct inode *i, struct dentry *d) */ int -v9fs_vfs_rename(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry, - unsigned int flags) +v9fs_vfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, + struct dentry *old_dentry, struct inode *new_dir, + struct dentry *new_dentry, unsigned int flags) { int retval; struct inode *old_inode; @@ -1016,8 +1017,8 @@ done: */ static int -v9fs_vfs_getattr(const struct path *path, struct kstat *stat, - u32 request_mask, unsigned int flags) +v9fs_vfs_getattr(struct user_namespace *mnt_userns, const struct path *path, + struct kstat *stat, u32 request_mask, unsigned int flags) { struct dentry *dentry = path->dentry; struct v9fs_session_info *v9ses; @@ -1054,7 +1055,8 @@ v9fs_vfs_getattr(const struct path *path, struct kstat *stat, * */ -static int v9fs_vfs_setattr(struct dentry *dentry, struct iattr *iattr) +static int v9fs_vfs_setattr(struct user_namespace *mnt_userns, + struct dentry *dentry, struct iattr *iattr) { int retval, use_dentry = 0; struct v9fs_session_info *v9ses; @@ -1295,7 +1297,8 @@ static int v9fs_vfs_mkspecial(struct inode *dir, struct dentry *dentry, */ static int -v9fs_vfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname) +v9fs_vfs_symlink(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, const char *symname) { p9_debug(P9_DEBUG_VFS, " %lu,%pd,%s\n", dir->i_ino, dentry, symname); @@ -1348,7 +1351,8 @@ v9fs_vfs_link(struct dentry *old_dentry, struct inode *dir, */ static int -v9fs_vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) +v9fs_vfs_mknod(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, dev_t rdev) { struct v9fs_session_info *v9ses = v9fs_inode2v9ses(dir); int retval; diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index 984f28315d2a..1dc7af046615 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -33,8 +33,8 @@ #include "acl.h" static int -v9fs_vfs_mknod_dotl(struct inode *dir, struct dentry *dentry, umode_t omode, - dev_t rdev); +v9fs_vfs_mknod_dotl(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t omode, dev_t rdev); /** * v9fs_get_fsgid_for_create - Helper function to get the gid for creating a @@ -218,10 +218,10 @@ int v9fs_open_to_dotl_flags(int flags) */ static int -v9fs_vfs_create_dotl(struct inode *dir, struct dentry *dentry, umode_t omode, - bool excl) +v9fs_vfs_create_dotl(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t omode, bool excl) { - return v9fs_vfs_mknod_dotl(dir, dentry, omode, 0); + return v9fs_vfs_mknod_dotl(mnt_userns, dir, dentry, omode, 0); } static int @@ -367,8 +367,9 @@ err_clunk_old_fid: * */ -static int v9fs_vfs_mkdir_dotl(struct inode *dir, - struct dentry *dentry, umode_t omode) +static int v9fs_vfs_mkdir_dotl(struct user_namespace *mnt_userns, + struct inode *dir, struct dentry *dentry, + umode_t omode) { int err; struct v9fs_session_info *v9ses; @@ -457,8 +458,9 @@ error: } static int -v9fs_vfs_getattr_dotl(const struct path *path, struct kstat *stat, - u32 request_mask, unsigned int flags) +v9fs_vfs_getattr_dotl(struct user_namespace *mnt_userns, + const struct path *path, struct kstat *stat, + u32 request_mask, unsigned int flags) { struct dentry *dentry = path->dentry; struct v9fs_session_info *v9ses; @@ -540,7 +542,8 @@ static int v9fs_mapped_iattr_valid(int iattr_valid) * */ -int v9fs_vfs_setattr_dotl(struct dentry *dentry, struct iattr *iattr) +int v9fs_vfs_setattr_dotl(struct user_namespace *mnt_userns, + struct dentry *dentry, struct iattr *iattr) { int retval, use_dentry = 0; struct p9_fid *fid = NULL; @@ -684,8 +687,8 @@ v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode, } static int -v9fs_vfs_symlink_dotl(struct inode *dir, struct dentry *dentry, - const char *symname) +v9fs_vfs_symlink_dotl(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, const char *symname) { int err; kgid_t gid; @@ -824,8 +827,8 @@ v9fs_vfs_link_dotl(struct dentry *old_dentry, struct inode *dir, * */ static int -v9fs_vfs_mknod_dotl(struct inode *dir, struct dentry *dentry, umode_t omode, - dev_t rdev) +v9fs_vfs_mknod_dotl(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t omode, dev_t rdev) { int err; kgid_t gid; diff --git a/fs/adfs/adfs.h b/fs/adfs/adfs.h index 699c4fa8b78b..06b7c92343ad 100644 --- a/fs/adfs/adfs.h +++ b/fs/adfs/adfs.h @@ -144,7 +144,8 @@ struct adfs_discmap { /* Inode stuff */ struct inode *adfs_iget(struct super_block *sb, struct object_info *obj); int adfs_write_inode(struct inode *inode, struct writeback_control *wbc); -int adfs_notify_change(struct dentry *dentry, struct iattr *attr); +int adfs_notify_change(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *attr); /* map.c */ int adfs_map_lookup(struct super_block *sb, u32 frag_id, unsigned int offset); diff --git a/fs/adfs/inode.c b/fs/adfs/inode.c index 278dcee6ae22..fb7ee026d101 100644 --- a/fs/adfs/inode.c +++ b/fs/adfs/inode.c @@ -292,7 +292,8 @@ out: * later. */ int -adfs_notify_change(struct dentry *dentry, struct iattr *attr) +adfs_notify_change(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *attr) { struct inode *inode = d_inode(dentry); struct super_block *sb = inode->i_sb; diff --git a/fs/affs/affs.h b/fs/affs/affs.h index a755bef7c4c7..bfa89e131ead 100644 --- a/fs/affs/affs.h +++ b/fs/affs/affs.h @@ -167,27 +167,33 @@ extern const struct export_operations affs_export_ops; extern int affs_hash_name(struct super_block *sb, const u8 *name, unsigned int len); extern struct dentry *affs_lookup(struct inode *dir, struct dentry *dentry, unsigned int); extern int affs_unlink(struct inode *dir, struct dentry *dentry); -extern int affs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool); -extern int affs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode); +extern int affs_create(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, bool); +extern int affs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode); extern int affs_rmdir(struct inode *dir, struct dentry *dentry); extern int affs_link(struct dentry *olddentry, struct inode *dir, struct dentry *dentry); -extern int affs_symlink(struct inode *dir, struct dentry *dentry, - const char *symname); -extern int affs_rename2(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry, - unsigned int flags); +extern int affs_symlink(struct user_namespace *mnt_userns, + struct inode *dir, struct dentry *dentry, + const char *symname); +extern int affs_rename2(struct user_namespace *mnt_userns, + struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry, + unsigned int flags); /* inode.c */ extern struct inode *affs_new_inode(struct inode *dir); -extern int affs_notify_change(struct dentry *dentry, struct iattr *attr); +extern int affs_notify_change(struct user_namespace *mnt_userns, + struct dentry *dentry, struct iattr *attr); extern void affs_evict_inode(struct inode *inode); extern struct inode *affs_iget(struct super_block *sb, unsigned long ino); extern int affs_write_inode(struct inode *inode, struct writeback_control *wbc); -extern int affs_add_entry(struct inode *dir, struct inode *inode, struct dentry *dentry, s32 type); +extern int affs_add_entry(struct inode *dir, struct inode *inode, + struct dentry *dentry, s32 type); /* file.c */ diff --git a/fs/affs/inode.c b/fs/affs/inode.c index 767e5bdfb703..2352a75bd9d6 100644 --- a/fs/affs/inode.c +++ b/fs/affs/inode.c @@ -216,7 +216,8 @@ affs_write_inode(struct inode *inode, struct writeback_control *wbc) } int -affs_notify_change(struct dentry *dentry, struct iattr *attr) +affs_notify_change(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *attr) { struct inode *inode = d_inode(dentry); int error; diff --git a/fs/affs/namei.c b/fs/affs/namei.c index 41c5749f4db7..9ad22befce28 100644 --- a/fs/affs/namei.c +++ b/fs/affs/namei.c @@ -242,7 +242,8 @@ affs_unlink(struct inode *dir, struct dentry *dentry) } int -affs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) +affs_create(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, bool excl) { struct super_block *sb = dir->i_sb; struct inode *inode; @@ -273,7 +274,8 @@ affs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) } int -affs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +affs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct inode *inode; int error; @@ -311,7 +313,8 @@ affs_rmdir(struct inode *dir, struct dentry *dentry) } int -affs_symlink(struct inode *dir, struct dentry *dentry, const char *symname) +affs_symlink(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, const char *symname) { struct super_block *sb = dir->i_sb; struct buffer_head *bh; @@ -498,9 +501,9 @@ done: return retval; } -int affs_rename2(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry, - unsigned int flags) +int affs_rename2(struct user_namespace *mnt_userns, struct inode *old_dir, + struct dentry *old_dentry, struct inode *new_dir, + struct dentry *new_dentry, unsigned int flags) { if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE)) diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 7bd659ad959e..714fcca9af99 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -28,18 +28,19 @@ static int afs_lookup_one_filldir(struct dir_context *ctx, const char *name, int loff_t fpos, u64 ino, unsigned dtype); static int afs_lookup_filldir(struct dir_context *ctx, const char *name, int nlen, loff_t fpos, u64 ino, unsigned dtype); -static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - bool excl); -static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode); +static int afs_create(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, bool excl); +static int afs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode); static int afs_rmdir(struct inode *dir, struct dentry *dentry); static int afs_unlink(struct inode *dir, struct dentry *dentry); static int afs_link(struct dentry *from, struct inode *dir, struct dentry *dentry); -static int afs_symlink(struct inode *dir, struct dentry *dentry, - const char *content); -static int afs_rename(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry, - unsigned int flags); +static int afs_symlink(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, const char *content); +static int afs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, + struct dentry *old_dentry, struct inode *new_dir, + struct dentry *new_dentry, unsigned int flags); static int afs_dir_releasepage(struct page *page, gfp_t gfp_flags); static void afs_dir_invalidatepage(struct page *page, unsigned int offset, unsigned int length); @@ -1325,7 +1326,8 @@ static const struct afs_operation_ops afs_mkdir_operation = { /* * create a directory on an AFS filesystem */ -static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +static int afs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct afs_operation *op; struct afs_vnode *dvnode = AFS_FS_I(dir); @@ -1619,8 +1621,8 @@ static const struct afs_operation_ops afs_create_operation = { /* * create a regular file on an AFS filesystem */ -static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - bool excl) +static int afs_create(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, bool excl) { struct afs_operation *op; struct afs_vnode *dvnode = AFS_FS_I(dir); @@ -1741,8 +1743,8 @@ static const struct afs_operation_ops afs_symlink_operation = { /* * create a symlink in an AFS filesystem */ -static int afs_symlink(struct inode *dir, struct dentry *dentry, - const char *content) +static int afs_symlink(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, const char *content) { struct afs_operation *op; struct afs_vnode *dvnode = AFS_FS_I(dir); @@ -1876,9 +1878,9 @@ static const struct afs_operation_ops afs_rename_operation = { /* * rename a file in an AFS filesystem and/or move it between directories */ -static int afs_rename(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry, - unsigned int flags) +static int afs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, + struct dentry *old_dentry, struct inode *new_dir, + struct dentry *new_dentry, unsigned int flags) { struct afs_operation *op; struct afs_vnode *orig_dvnode, *new_dvnode, *vnode; diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 795ee5cb3817..1156b2df28d3 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -734,8 +734,8 @@ error_unlock: /* * read the attributes of an inode */ -int afs_getattr(const struct path *path, struct kstat *stat, - u32 request_mask, unsigned int query_flags) +int afs_getattr(struct user_namespace *mnt_userns, const struct path *path, + struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); struct afs_vnode *vnode = AFS_FS_I(inode); @@ -857,7 +857,8 @@ static const struct afs_operation_ops afs_setattr_operation = { /* * set the attributes of an inode */ -int afs_setattr(struct dentry *dentry, struct iattr *attr) +int afs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *attr) { struct afs_operation *op; struct afs_vnode *vnode = AFS_FS_I(d_inode(dentry)); diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 0d150a29e39e..b626e38e9ab5 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -1149,8 +1149,9 @@ extern struct inode *afs_iget(struct afs_operation *, struct afs_vnode_param *); extern struct inode *afs_root_iget(struct super_block *, struct key *); extern bool afs_check_validity(struct afs_vnode *); extern int afs_validate(struct afs_vnode *, struct key *); -extern int afs_getattr(const struct path *, struct kstat *, u32, unsigned int); -extern int afs_setattr(struct dentry *, struct iattr *); +extern int afs_getattr(struct user_namespace *mnt_userns, const struct path *, + struct kstat *, u32, unsigned int); +extern int afs_setattr(struct user_namespace *mnt_userns, struct dentry *, struct iattr *); extern void afs_evict_inode(struct inode *); extern int afs_drop_inode(struct inode *); @@ -1361,7 +1362,7 @@ extern void afs_zap_permits(struct rcu_head *); extern struct key *afs_request_key(struct afs_cell *); extern struct key *afs_request_key_rcu(struct afs_cell *); extern int afs_check_permit(struct afs_vnode *, struct key *, afs_access_t *); -extern int afs_permission(struct inode *, int); +extern int afs_permission(struct user_namespace *, struct inode *, int); extern void __exit afs_clean_up_permit_cache(void); /* diff --git a/fs/afs/security.c b/fs/afs/security.c index 9cf3102f370c..3c7a8fc4f93f 100644 --- a/fs/afs/security.c +++ b/fs/afs/security.c @@ -396,7 +396,8 @@ int afs_check_permit(struct afs_vnode *vnode, struct key *key, * - AFS ACLs are attached to directories only, and a file is controlled by its * parent directory's ACL */ -int afs_permission(struct inode *inode, int mask) +int afs_permission(struct user_namespace *mnt_userns, struct inode *inode, + int mask) { struct afs_vnode *vnode = AFS_FS_I(inode); afs_access_t access; diff --git a/fs/attr.c b/fs/attr.c index c2d3bc0869d4..41abd0d973d8 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -395,9 +395,9 @@ int notify_change(struct user_namespace *mnt_userns, struct dentry *dentry, return error; if (inode->i_op->setattr) - error = inode->i_op->setattr(dentry, attr); + error = inode->i_op->setattr(mnt_userns, dentry, attr); else - error = simple_setattr(dentry, attr); + error = simple_setattr(mnt_userns, dentry, attr); if (!error) { fsnotify_change(dentry, ia_valid); diff --git a/fs/autofs/root.c b/fs/autofs/root.c index 5aaa1732bf1e..91fe4548c256 100644 --- a/fs/autofs/root.c +++ b/fs/autofs/root.c @@ -10,10 +10,12 @@ #include "autofs_i.h" -static int autofs_dir_symlink(struct inode *, struct dentry *, const char *); +static int autofs_dir_symlink(struct user_namespace *, struct inode *, + struct dentry *, const char *); static int autofs_dir_unlink(struct inode *, struct dentry *); static int autofs_dir_rmdir(struct inode *, struct dentry *); -static int autofs_dir_mkdir(struct inode *, struct dentry *, umode_t); +static int autofs_dir_mkdir(struct user_namespace *, struct inode *, + struct dentry *, umode_t); static long autofs_root_ioctl(struct file *, unsigned int, unsigned long); #ifdef CONFIG_COMPAT static long autofs_root_compat_ioctl(struct file *, @@ -524,9 +526,9 @@ static struct dentry *autofs_lookup(struct inode *dir, return NULL; } -static int autofs_dir_symlink(struct inode *dir, - struct dentry *dentry, - const char *symname) +static int autofs_dir_symlink(struct user_namespace *mnt_userns, + struct inode *dir, struct dentry *dentry, + const char *symname) { struct autofs_sb_info *sbi = autofs_sbi(dir->i_sb); struct autofs_info *ino = autofs_dentry_ino(dentry); @@ -715,8 +717,9 @@ static int autofs_dir_rmdir(struct inode *dir, struct dentry *dentry) return 0; } -static int autofs_dir_mkdir(struct inode *dir, - struct dentry *dentry, umode_t mode) +static int autofs_dir_mkdir(struct user_namespace *mnt_userns, + struct inode *dir, struct dentry *dentry, + umode_t mode) { struct autofs_sb_info *sbi = autofs_sbi(dir->i_sb); struct autofs_info *ino = autofs_dentry_ino(dentry); diff --git a/fs/bad_inode.c b/fs/bad_inode.c index 54f0ce444272..48e16144c1f7 100644 --- a/fs/bad_inode.c +++ b/fs/bad_inode.c @@ -27,8 +27,9 @@ static const struct file_operations bad_file_ops = .open = bad_file_open, }; -static int bad_inode_create (struct inode *dir, struct dentry *dentry, - umode_t mode, bool excl) +static int bad_inode_create(struct user_namespace *mnt_userns, + struct inode *dir, struct dentry *dentry, + umode_t mode, bool excl) { return -EIO; } @@ -50,14 +51,15 @@ static int bad_inode_unlink(struct inode *dir, struct dentry *dentry) return -EIO; } -static int bad_inode_symlink (struct inode *dir, struct dentry *dentry, - const char *symname) +static int bad_inode_symlink(struct user_namespace *mnt_userns, + struct inode *dir, struct dentry *dentry, + const char *symname) { return -EIO; } -static int bad_inode_mkdir(struct inode *dir, struct dentry *dentry, - umode_t mode) +static int bad_inode_mkdir(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { return -EIO; } @@ -67,13 +69,14 @@ static int bad_inode_rmdir (struct inode *dir, struct dentry *dentry) return -EIO; } -static int bad_inode_mknod (struct inode *dir, struct dentry *dentry, - umode_t mode, dev_t rdev) +static int bad_inode_mknod(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, dev_t rdev) { return -EIO; } -static int bad_inode_rename2(struct inode *old_dir, struct dentry *old_dentry, +static int bad_inode_rename2(struct user_namespace *mnt_userns, + struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { @@ -86,18 +89,21 @@ static int bad_inode_readlink(struct dentry *dentry, char __user *buffer, return -EIO; } -static int bad_inode_permission(struct inode *inode, int mask) +static int bad_inode_permission(struct user_namespace *mnt_userns, + struct inode *inode, int mask) { return -EIO; } -static int bad_inode_getattr(const struct path *path, struct kstat *stat, +static int bad_inode_getattr(struct user_namespace *mnt_userns, + const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { return -EIO; } -static int bad_inode_setattr(struct dentry *direntry, struct iattr *attrs) +static int bad_inode_setattr(struct user_namespace *mnt_userns, + struct dentry *direntry, struct iattr *attrs) { return -EIO; } @@ -140,13 +146,15 @@ static int bad_inode_atomic_open(struct inode *inode, struct dentry *dentry, return -EIO; } -static int bad_inode_tmpfile(struct inode *inode, struct dentry *dentry, +static int bad_inode_tmpfile(struct user_namespace *mnt_userns, + struct inode *inode, struct dentry *dentry, umode_t mode) { return -EIO; } -static int bad_inode_set_acl(struct inode *inode, struct posix_acl *acl, +static int bad_inode_set_acl(struct user_namespace *mnt_userns, + struct inode *inode, struct posix_acl *acl, int type) { return -EIO; diff --git a/fs/bfs/dir.c b/fs/bfs/dir.c index be1335a8d25b..34d4f68f786b 100644 --- a/fs/bfs/dir.c +++ b/fs/bfs/dir.c @@ -75,8 +75,8 @@ const struct file_operations bfs_dir_operations = { .llseek = generic_file_llseek, }; -static int bfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - bool excl) +static int bfs_create(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, bool excl) { int err; struct inode *inode; @@ -199,9 +199,9 @@ out_brelse: return error; } -static int bfs_rename(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry, - unsigned int flags) +static int bfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, + struct dentry *old_dentry, struct inode *new_dir, + struct dentry *new_dentry, unsigned int flags) { struct inode *old_inode, *new_inode; struct buffer_head *old_bh, *new_bh; diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c index d12a5a8730a8..d95eb5c8cb37 100644 --- a/fs/btrfs/acl.c +++ b/fs/btrfs/acl.c @@ -107,7 +107,8 @@ out: return ret; } -int btrfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) +int btrfs_set_acl(struct user_namespace *mnt_userns, struct inode *inode, + struct posix_acl *acl, int type) { int ret; umode_t old_mode = inode->i_mode; diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index e6e37591f1de..9c0b43853cd2 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3625,7 +3625,8 @@ static inline int __btrfs_fs_compat_ro(struct btrfs_fs_info *fs_info, u64 flag) /* acl.c */ #ifdef CONFIG_BTRFS_FS_POSIX_ACL struct posix_acl *btrfs_get_acl(struct inode *inode, int type); -int btrfs_set_acl(struct inode *inode, struct posix_acl *acl, int type); +int btrfs_set_acl(struct user_namespace *mnt_userns, struct inode *inode, + struct posix_acl *acl, int type); int btrfs_init_acl(struct btrfs_trans_handle *trans, struct inode *inode, struct inode *dir); #else diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index a63faed171de..c0b11db98e5e 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -5045,7 +5045,8 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr) return ret; } -static int btrfs_setattr(struct dentry *dentry, struct iattr *attr) +static int btrfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *attr) { struct inode *inode = d_inode(dentry); struct btrfs_root *root = BTRFS_I(inode)->root; @@ -6352,8 +6353,8 @@ static int btrfs_add_nondir(struct btrfs_trans_handle *trans, return err; } -static int btrfs_mknod(struct inode *dir, struct dentry *dentry, - umode_t mode, dev_t rdev) +static int btrfs_mknod(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, dev_t rdev) { struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb); struct btrfs_trans_handle *trans; @@ -6416,8 +6417,8 @@ out_unlock: return err; } -static int btrfs_create(struct inode *dir, struct dentry *dentry, - umode_t mode, bool excl) +static int btrfs_create(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, bool excl) { struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb); struct btrfs_trans_handle *trans; @@ -6561,7 +6562,8 @@ fail: return err; } -static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +static int btrfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb); struct inode *inode = NULL; @@ -8816,7 +8818,8 @@ fail: return -ENOMEM; } -static int btrfs_getattr(const struct path *path, struct kstat *stat, +static int btrfs_getattr(struct user_namespace *mnt_userns, + const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags) { u64 delalloc_bytes; @@ -9333,9 +9336,9 @@ out_notrans: return ret; } -static int btrfs_rename2(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry, - unsigned int flags) +static int btrfs_rename2(struct user_namespace *mnt_userns, struct inode *old_dir, + struct dentry *old_dentry, struct inode *new_dir, + struct dentry *new_dentry, unsigned int flags) { if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT)) return -EINVAL; @@ -9543,8 +9546,8 @@ out: return ret; } -static int btrfs_symlink(struct inode *dir, struct dentry *dentry, - const char *symname) +static int btrfs_symlink(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, const char *symname) { struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb); struct btrfs_trans_handle *trans; @@ -9878,7 +9881,8 @@ static int btrfs_set_page_dirty(struct page *page) return __set_page_dirty_nobuffers(page); } -static int btrfs_permission(struct inode *inode, int mask) +static int btrfs_permission(struct user_namespace *mnt_userns, + struct inode *inode, int mask) { struct btrfs_root *root = BTRFS_I(inode)->root; umode_t mode = inode->i_mode; @@ -9893,7 +9897,8 @@ static int btrfs_permission(struct inode *inode, int mask) return generic_permission(&init_user_ns, inode, mask); } -static int btrfs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) +static int btrfs_tmpfile(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb); struct btrfs_trans_handle *trans; diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c index 52a01ddbc4ac..529af59d9fd3 100644 --- a/fs/ceph/acl.c +++ b/fs/ceph/acl.c @@ -82,7 +82,8 @@ retry: return acl; } -int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type) +int ceph_set_acl(struct user_namespace *mnt_userns, struct inode *inode, + struct posix_acl *acl, int type) { int ret = 0, size = 0; const char *name = NULL; diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 858ee7362ff5..83d9358854fb 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -823,8 +823,8 @@ int ceph_handle_notrace_create(struct inode *dir, struct dentry *dentry) return PTR_ERR(result); } -static int ceph_mknod(struct inode *dir, struct dentry *dentry, - umode_t mode, dev_t rdev) +static int ceph_mknod(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, dev_t rdev) { struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(dir->i_sb); struct ceph_mds_request *req; @@ -878,14 +878,14 @@ out: return err; } -static int ceph_create(struct inode *dir, struct dentry *dentry, umode_t mode, - bool excl) +static int ceph_create(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, bool excl) { - return ceph_mknod(dir, dentry, mode, 0); + return ceph_mknod(mnt_userns, dir, dentry, mode, 0); } -static int ceph_symlink(struct inode *dir, struct dentry *dentry, - const char *dest) +static int ceph_symlink(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, const char *dest) { struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(dir->i_sb); struct ceph_mds_request *req; @@ -937,7 +937,8 @@ out: return err; } -static int ceph_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +static int ceph_mkdir(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(dir->i_sb); struct ceph_mds_request *req; @@ -1183,9 +1184,9 @@ out: return err; } -static int ceph_rename(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry, - unsigned int flags) +static int ceph_rename(struct user_namespace *mnt_userns, struct inode *old_dir, + struct dentry *old_dentry, struct inode *new_dir, + struct dentry *new_dentry, unsigned int flags) { struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(old_dir->i_sb); struct ceph_mds_request *req; diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 179a2bb88538..d6ece56d40e8 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -2238,7 +2238,8 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr) /* * setattr */ -int ceph_setattr(struct dentry *dentry, struct iattr *attr) +int ceph_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *attr) { struct inode *inode = d_inode(dentry); struct ceph_fs_client *fsc = ceph_inode_to_client(inode); @@ -2321,7 +2322,8 @@ int __ceph_do_getattr(struct inode *inode, struct page *locked_page, * Check inode permissions. We verify we have a valid value for * the AUTH cap, then call the generic handler. */ -int ceph_permission(struct inode *inode, int mask) +int ceph_permission(struct user_namespace *mnt_userns, struct inode *inode, + int mask) { int err; @@ -2368,8 +2370,8 @@ static int statx_to_caps(u32 want, umode_t mode) * Get all the attributes. If we have sufficient caps for the requested attrs, * then we can avoid talking to the MDS at all. */ -int ceph_getattr(const struct path *path, struct kstat *stat, - u32 request_mask, unsigned int flags) +int ceph_getattr(struct user_namespace *mnt_userns, const struct path *path, + struct kstat *stat, u32 request_mask, unsigned int flags) { struct inode *inode = d_inode(path->dentry); struct ceph_inode_info *ci = ceph_inode(inode); diff --git a/fs/ceph/super.h b/fs/ceph/super.h index b62d8fee3b86..1ef0a2a15817 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -973,10 +973,13 @@ static inline int ceph_do_getattr(struct inode *inode, int mask, bool force) { return __ceph_do_getattr(inode, NULL, mask, force); } -extern int ceph_permission(struct inode *inode, int mask); +extern int ceph_permission(struct user_namespace *mnt_userns, + struct inode *inode, int mask); extern int __ceph_setattr(struct inode *inode, struct iattr *attr); -extern int ceph_setattr(struct dentry *dentry, struct iattr *attr); -extern int ceph_getattr(const struct path *path, struct kstat *stat, +extern int ceph_setattr(struct user_namespace *mnt_userns, + struct dentry *dentry, struct iattr *attr); +extern int ceph_getattr(struct user_namespace *mnt_userns, + const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags); /* xattr.c */ @@ -1037,7 +1040,8 @@ void ceph_release_acl_sec_ctx(struct ceph_acl_sec_ctx *as_ctx); #ifdef CONFIG_CEPH_FS_POSIX_ACL struct posix_acl *ceph_get_acl(struct inode *, int); -int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type); +int ceph_set_acl(struct user_namespace *mnt_userns, + struct inode *inode, struct posix_acl *acl, int type); int ceph_pre_init_acls(struct inode *dir, umode_t *mode, struct ceph_acl_sec_ctx *as_ctx); void ceph_init_inode_acls(struct inode *inode, diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index ce14e6f8adb6..39e51dcf796f 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -305,7 +305,8 @@ static long cifs_fallocate(struct file *file, int mode, loff_t off, loff_t len) return -EOPNOTSUPP; } -static int cifs_permission(struct inode *inode, int mask) +static int cifs_permission(struct user_namespace *mnt_userns, + struct inode *inode, int mask) { struct cifs_sb_info *cifs_sb; diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index 2307bb0f6147..71e9c6abb2a6 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -62,19 +62,22 @@ extern void cifs_sb_deactive(struct super_block *sb); /* Functions related to inodes */ extern const struct inode_operations cifs_dir_inode_ops; extern struct inode *cifs_root_iget(struct super_block *); -extern int cifs_create(struct inode *, struct dentry *, umode_t, - bool excl); +extern int cifs_create(struct user_namespace *, struct inode *, + struct dentry *, umode_t, bool excl); extern int cifs_atomic_open(struct inode *, struct dentry *, struct file *, unsigned, umode_t); extern struct dentry *cifs_lookup(struct inode *, struct dentry *, unsigned int); extern int cifs_unlink(struct inode *dir, struct dentry *dentry); extern int cifs_hardlink(struct dentry *, struct inode *, struct dentry *); -extern int cifs_mknod(struct inode *, struct dentry *, umode_t, dev_t); -extern int cifs_mkdir(struct inode *, struct dentry *, umode_t); +extern int cifs_mknod(struct user_namespace *, struct inode *, struct dentry *, + umode_t, dev_t); +extern int cifs_mkdir(struct user_namespace *, struct inode *, struct dentry *, + umode_t); extern int cifs_rmdir(struct inode *, struct dentry *); -extern int cifs_rename2(struct inode *, struct dentry *, struct inode *, - struct dentry *, unsigned int); +extern int cifs_rename2(struct user_namespace *, struct inode *, + struct dentry *, struct inode *, struct dentry *, + unsigned int); extern int cifs_revalidate_file_attr(struct file *filp); extern int cifs_revalidate_dentry_attr(struct dentry *); extern int cifs_revalidate_file(struct file *filp); @@ -82,8 +85,10 @@ extern int cifs_revalidate_dentry(struct dentry *); extern int cifs_invalidate_mapping(struct inode *inode); extern int cifs_revalidate_mapping(struct inode *inode); extern int cifs_zap_mapping(struct inode *inode); -extern int cifs_getattr(const struct path *, struct kstat *, u32, unsigned int); -extern int cifs_setattr(struct dentry *, struct iattr *); +extern int cifs_getattr(struct user_namespace *, const struct path *, + struct kstat *, u32, unsigned int); +extern int cifs_setattr(struct user_namespace *, struct dentry *, + struct iattr *); extern int cifs_fiemap(struct inode *, struct fiemap_extent_info *, u64 start, u64 len); @@ -132,8 +137,8 @@ extern struct vfsmount *cifs_dfs_d_automount(struct path *path); /* Functions related to symlinks */ extern const char *cifs_get_link(struct dentry *, struct inode *, struct delayed_call *); -extern int cifs_symlink(struct inode *inode, struct dentry *direntry, - const char *symname); +extern int cifs_symlink(struct user_namespace *mnt_userns, struct inode *inode, + struct dentry *direntry, const char *symname); #ifdef CONFIG_CIFS_XATTR extern const struct xattr_handler *cifs_xattr_handlers[]; diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index 68900f1629bf..68f4f8536e6a 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -567,8 +567,8 @@ out_free_xid: return rc; } -int cifs_create(struct inode *inode, struct dentry *direntry, umode_t mode, - bool excl) +int cifs_create(struct user_namespace *mnt_userns, struct inode *inode, + struct dentry *direntry, umode_t mode, bool excl) { int rc; unsigned int xid = get_xid(); @@ -611,8 +611,8 @@ out_free_xid: return rc; } -int cifs_mknod(struct inode *inode, struct dentry *direntry, umode_t mode, - dev_t device_number) +int cifs_mknod(struct user_namespace *mnt_userns, struct inode *inode, + struct dentry *direntry, umode_t mode, dev_t device_number) { int rc = -EPERM; unsigned int xid; diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 374abce7efaf..3e9c7bb23f26 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -1857,7 +1857,8 @@ posix_mkdir_get_info: goto posix_mkdir_out; } -int cifs_mkdir(struct inode *inode, struct dentry *direntry, umode_t mode) +int cifs_mkdir(struct user_namespace *mnt_userns, struct inode *inode, + struct dentry *direntry, umode_t mode) { int rc = 0; unsigned int xid; @@ -2067,9 +2068,9 @@ do_rename_exit: } int -cifs_rename2(struct inode *source_dir, struct dentry *source_dentry, - struct inode *target_dir, struct dentry *target_dentry, - unsigned int flags) +cifs_rename2(struct user_namespace *mnt_userns, struct inode *source_dir, + struct dentry *source_dentry, struct inode *target_dir, + struct dentry *target_dentry, unsigned int flags) { char *from_name = NULL; char *to_name = NULL; @@ -2370,8 +2371,8 @@ int cifs_revalidate_dentry(struct dentry *dentry) return cifs_revalidate_mapping(inode); } -int cifs_getattr(const struct path *path, struct kstat *stat, - u32 request_mask, unsigned int flags) +int cifs_getattr(struct user_namespace *mnt_userns, const struct path *path, + struct kstat *stat, u32 request_mask, unsigned int flags) { struct dentry *dentry = path->dentry; struct cifs_sb_info *cifs_sb = CIFS_SB(dentry->d_sb); @@ -2923,7 +2924,8 @@ cifs_setattr_exit: } int -cifs_setattr(struct dentry *direntry, struct iattr *attrs) +cifs_setattr(struct user_namespace *mnt_userns, struct dentry *direntry, + struct iattr *attrs) { struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb); struct cifs_tcon *pTcon = cifs_sb_master_tcon(cifs_sb); diff --git a/fs/cifs/link.c b/fs/cifs/link.c index 94dab4309fbb..7c5878a645d9 100644 --- a/fs/cifs/link.c +++ b/fs/cifs/link.c @@ -661,7 +661,8 @@ cifs_get_link(struct dentry *direntry, struct inode *inode, } int -cifs_symlink(struct inode *inode, struct dentry *direntry, const char *symname) +cifs_symlink(struct user_namespace *mnt_userns, struct inode *inode, + struct dentry *direntry, const char *symname) { int rc = -EOPNOTSUPP; unsigned int xid; diff --git a/fs/coda/coda_linux.h b/fs/coda/coda_linux.h index d5ebd36fb2cc..e7b27754ce78 100644 --- a/fs/coda/coda_linux.h +++ b/fs/coda/coda_linux.h @@ -46,10 +46,12 @@ extern const struct file_operations coda_ioctl_operations; /* operations shared over more than one file */ int coda_open(struct inode *i, struct file *f); int coda_release(struct inode *i, struct file *f); -int coda_permission(struct inode *inode, int mask); +int coda_permission(struct user_namespace *mnt_userns, struct inode *inode, + int mask); int coda_revalidate_inode(struct inode *); -int coda_getattr(const struct path *, struct kstat *, u32, unsigned int); -int coda_setattr(struct dentry *, struct iattr *); +int coda_getattr(struct user_namespace *, const struct path *, struct kstat *, + u32, unsigned int); +int coda_setattr(struct user_namespace *, struct dentry *, struct iattr *); /* this file: heloers */ char *coda_f2s(struct CodaFid *f); diff --git a/fs/coda/dir.c b/fs/coda/dir.c index ca40c2556ba6..d69989c1bac3 100644 --- a/fs/coda/dir.c +++ b/fs/coda/dir.c @@ -73,7 +73,8 @@ static struct dentry *coda_lookup(struct inode *dir, struct dentry *entry, unsig } -int coda_permission(struct inode *inode, int mask) +int coda_permission(struct user_namespace *mnt_userns, struct inode *inode, + int mask) { int error; @@ -132,7 +133,8 @@ static inline void coda_dir_drop_nlink(struct inode *dir) } /* creation routines: create, mknod, mkdir, link, symlink */ -static int coda_create(struct inode *dir, struct dentry *de, umode_t mode, bool excl) +static int coda_create(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *de, umode_t mode, bool excl) { int error; const char *name=de->d_name.name; @@ -164,7 +166,8 @@ err_out: return error; } -static int coda_mkdir(struct inode *dir, struct dentry *de, umode_t mode) +static int coda_mkdir(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *de, umode_t mode) { struct inode *inode; struct coda_vattr attrs; @@ -225,7 +228,8 @@ static int coda_link(struct dentry *source_de, struct inode *dir_inode, } -static int coda_symlink(struct inode *dir_inode, struct dentry *de, +static int coda_symlink(struct user_namespace *mnt_userns, + struct inode *dir_inode, struct dentry *de, const char *symname) { const char *name = de->d_name.name; @@ -291,9 +295,9 @@ static int coda_rmdir(struct inode *dir, struct dentry *de) } /* rename */ -static int coda_rename(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry, - unsigned int flags) +static int coda_rename(struct user_namespace *mnt_userns, struct inode *old_dir, + struct dentry *old_dentry, struct inode *new_dir, + struct dentry *new_dentry, unsigned int flags) { const char *old_name = old_dentry->d_name.name; const char *new_name = new_dentry->d_name.name; diff --git a/fs/coda/inode.c b/fs/coda/inode.c index 4d113e191cb8..d9f1bd7153df 100644 --- a/fs/coda/inode.c +++ b/fs/coda/inode.c @@ -251,8 +251,8 @@ static void coda_evict_inode(struct inode *inode) coda_cache_clear_inode(inode); } -int coda_getattr(const struct path *path, struct kstat *stat, - u32 request_mask, unsigned int flags) +int coda_getattr(struct user_namespace *mnt_userns, const struct path *path, + struct kstat *stat, u32 request_mask, unsigned int flags) { int err = coda_revalidate_inode(d_inode(path->dentry)); if (!err) @@ -260,7 +260,8 @@ int coda_getattr(const struct path *path, struct kstat *stat, return err; } -int coda_setattr(struct dentry *de, struct iattr *iattr) +int coda_setattr(struct user_namespace *mnt_userns, struct dentry *de, + struct iattr *iattr) { struct inode *inode = d_inode(de); struct coda_vattr vattr; diff --git a/fs/coda/pioctl.c b/fs/coda/pioctl.c index 3aec27e5eb82..cb9fd59a688c 100644 --- a/fs/coda/pioctl.c +++ b/fs/coda/pioctl.c @@ -24,7 +24,8 @@ #include "coda_linux.h" /* pioctl ops */ -static int coda_ioctl_permission(struct inode *inode, int mask); +static int coda_ioctl_permission(struct user_namespace *mnt_userns, + struct inode *inode, int mask); static long coda_pioctl(struct file *filp, unsigned int cmd, unsigned long user_data); @@ -40,7 +41,8 @@ const struct file_operations coda_ioctl_operations = { }; /* the coda pioctl inode ops */ -static int coda_ioctl_permission(struct inode *inode, int mask) +static int coda_ioctl_permission(struct user_namespace *mnt_userns, + struct inode *inode, int mask) { return (mask & MAY_EXEC) ? -EACCES : 0; } diff --git a/fs/configfs/configfs_internal.h b/fs/configfs/configfs_internal.h index 22dce2d35a4b..9a3aed249692 100644 --- a/fs/configfs/configfs_internal.h +++ b/fs/configfs/configfs_internal.h @@ -79,7 +79,8 @@ extern void configfs_hash_and_remove(struct dentry * dir, const char * name); extern const unsigned char * configfs_get_name(struct configfs_dirent *sd); extern void configfs_drop_dentry(struct configfs_dirent *sd, struct dentry *parent); -extern int configfs_setattr(struct dentry *dentry, struct iattr *iattr); +extern int configfs_setattr(struct user_namespace *mnt_userns, + struct dentry *dentry, struct iattr *iattr); extern struct dentry *configfs_pin_fs(void); extern void configfs_release_fs(void); @@ -92,7 +93,8 @@ extern const struct inode_operations configfs_root_inode_operations; extern const struct inode_operations configfs_symlink_inode_operations; extern const struct dentry_operations configfs_dentry_ops; -extern int configfs_symlink(struct inode *dir, struct dentry *dentry, +extern int configfs_symlink(struct user_namespace *mnt_userns, + struct inode *dir, struct dentry *dentry, const char *symname); extern int configfs_unlink(struct inode *dir, struct dentry *dentry); diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index b839dd1b459f..b6098e02e20b 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -1268,7 +1268,8 @@ out_root_unlock: } EXPORT_SYMBOL(configfs_depend_item_unlocked); -static int configfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +static int configfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { int ret = 0; int module_got = 0; diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c index 8bd6a883c94c..42c348bb2903 100644 --- a/fs/configfs/inode.c +++ b/fs/configfs/inode.c @@ -40,7 +40,8 @@ static const struct inode_operations configfs_inode_operations ={ .setattr = configfs_setattr, }; -int configfs_setattr(struct dentry * dentry, struct iattr * iattr) +int configfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *iattr) { struct inode * inode = d_inode(dentry); struct configfs_dirent * sd = dentry->d_fsdata; @@ -67,7 +68,7 @@ int configfs_setattr(struct dentry * dentry, struct iattr * iattr) } /* attributes were changed atleast once in past */ - error = simple_setattr(dentry, iattr); + error = simple_setattr(mnt_userns, dentry, iattr); if (error) return error; diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c index 8ca36394fa30..77c854364e60 100644 --- a/fs/configfs/symlink.c +++ b/fs/configfs/symlink.c @@ -139,7 +139,8 @@ static int get_target(const char *symname, struct path *path, } -int configfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname) +int configfs_symlink(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, const char *symname) { int ret; struct path path; diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 2fcf66473436..c35249497b9b 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -42,13 +42,14 @@ static unsigned int debugfs_allow = DEFAULT_DEBUGFS_ALLOW_BITS; * so that we can use the file mode as part of a heuristic to determine whether * to lock down individual files. */ -static int debugfs_setattr(struct dentry *dentry, struct iattr *ia) +static int debugfs_setattr(struct user_namespace *mnt_userns, + struct dentry *dentry, struct iattr *ia) { int ret = security_locked_down(LOCKDOWN_DEBUGFS); if (ret && (ia->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID))) return ret; - return simple_setattr(dentry, ia); + return simple_setattr(&init_user_ns, dentry, ia); } static const struct inode_operations debugfs_file_inode_operations = { @@ -775,8 +776,8 @@ struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry, take_dentry_name_snapshot(&old_name, old_dentry); - error = simple_rename(d_inode(old_dir), old_dentry, d_inode(new_dir), - dentry, 0); + error = simple_rename(&init_user_ns, d_inode(old_dir), old_dentry, + d_inode(new_dir), dentry, 0); if (error) { release_dentry_name_snapshot(&old_name); goto exit; diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index 73e3d47e7b2d..55da9a91f51a 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -257,7 +257,8 @@ out: * Returns zero on success; non-zero on error condition */ static int -ecryptfs_create(struct inode *directory_inode, struct dentry *ecryptfs_dentry, +ecryptfs_create(struct user_namespace *mnt_userns, + struct inode *directory_inode, struct dentry *ecryptfs_dentry, umode_t mode, bool excl) { struct inode *ecryptfs_inode; @@ -463,7 +464,8 @@ static int ecryptfs_unlink(struct inode *dir, struct dentry *dentry) return ecryptfs_do_unlink(dir, dentry, d_inode(dentry)); } -static int ecryptfs_symlink(struct inode *dir, struct dentry *dentry, +static int ecryptfs_symlink(struct user_namespace *mnt_userns, + struct inode *dir, struct dentry *dentry, const char *symname) { int rc; @@ -502,7 +504,8 @@ out_lock: return rc; } -static int ecryptfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +static int ecryptfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { int rc; struct dentry *lower_dentry; @@ -559,7 +562,8 @@ static int ecryptfs_rmdir(struct inode *dir, struct dentry *dentry) } static int -ecryptfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) +ecryptfs_mknod(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, dev_t dev) { int rc; struct dentry *lower_dentry; @@ -584,9 +588,9 @@ out: } static int -ecryptfs_rename(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry, - unsigned int flags) +ecryptfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, + struct dentry *old_dentry, struct inode *new_dir, + struct dentry *new_dentry, unsigned int flags) { int rc; struct dentry *lower_old_dentry; @@ -874,7 +878,8 @@ int ecryptfs_truncate(struct dentry *dentry, loff_t new_length) } static int -ecryptfs_permission(struct inode *inode, int mask) +ecryptfs_permission(struct user_namespace *mnt_userns, struct inode *inode, + int mask) { return inode_permission(&init_user_ns, ecryptfs_inode_to_lower(inode), mask); @@ -892,7 +897,8 @@ ecryptfs_permission(struct inode *inode, int mask) * All other metadata changes will be passed right to the lower filesystem, * and we will just update our inode to look like the lower. */ -static int ecryptfs_setattr(struct dentry *dentry, struct iattr *ia) +static int ecryptfs_setattr(struct user_namespace *mnt_userns, + struct dentry *dentry, struct iattr *ia) { int rc = 0; struct dentry *lower_dentry; @@ -979,7 +985,8 @@ out: return rc; } -static int ecryptfs_getattr_link(const struct path *path, struct kstat *stat, +static int ecryptfs_getattr_link(struct user_namespace *mnt_userns, + const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags) { struct dentry *dentry = path->dentry; @@ -1004,7 +1011,8 @@ static int ecryptfs_getattr_link(const struct path *path, struct kstat *stat, return rc; } -static int ecryptfs_getattr(const struct path *path, struct kstat *stat, +static int ecryptfs_getattr(struct user_namespace *mnt_userns, + const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags) { struct dentry *dentry = path->dentry; diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c index 0297ad95eb5c..14e2947975fd 100644 --- a/fs/efivarfs/inode.c +++ b/fs/efivarfs/inode.c @@ -66,8 +66,8 @@ bool efivarfs_valid_name(const char *str, int len) return uuid_is_valid(s); } -static int efivarfs_create(struct inode *dir, struct dentry *dentry, - umode_t mode, bool excl) +static int efivarfs_create(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, bool excl) { struct inode *inode = NULL; struct efivar_entry *var; diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c index 083818063ac6..119fdce1b520 100644 --- a/fs/erofs/inode.c +++ b/fs/erofs/inode.c @@ -331,8 +331,9 @@ struct inode *erofs_iget(struct super_block *sb, return inode; } -int erofs_getattr(const struct path *path, struct kstat *stat, - u32 request_mask, unsigned int query_flags) +int erofs_getattr(struct user_namespace *mnt_userns, const struct path *path, + struct kstat *stat, u32 request_mask, + unsigned int query_flags) { struct inode *const inode = d_inode(path->dentry); diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index 67a7ec945686..351dae524a0c 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -373,8 +373,9 @@ extern const struct inode_operations erofs_symlink_iops; extern const struct inode_operations erofs_fast_symlink_iops; struct inode *erofs_iget(struct super_block *sb, erofs_nid_t nid, bool dir); -int erofs_getattr(const struct path *path, struct kstat *stat, - u32 request_mask, unsigned int query_flags); +int erofs_getattr(struct user_namespace *mnt_userns, const struct path *path, + struct kstat *stat, u32 request_mask, + unsigned int query_flags); /* namei.c */ extern const struct inode_operations erofs_dir_iops; diff --git a/fs/exfat/exfat_fs.h b/fs/exfat/exfat_fs.h index b8f0e829ecbd..d905bb9cd2ca 100644 --- a/fs/exfat/exfat_fs.h +++ b/fs/exfat/exfat_fs.h @@ -416,9 +416,11 @@ int exfat_count_used_clusters(struct super_block *sb, unsigned int *ret_count); extern const struct file_operations exfat_file_operations; int __exfat_truncate(struct inode *inode, loff_t new_size); void exfat_truncate(struct inode *inode, loff_t size); -int exfat_setattr(struct dentry *dentry, struct iattr *attr); -int exfat_getattr(const struct path *path, struct kstat *stat, - unsigned int request_mask, unsigned int query_flags); +int exfat_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *attr); +int exfat_getattr(struct user_namespace *mnt_userns, const struct path *path, + struct kstat *stat, unsigned int request_mask, + unsigned int query_flags); int exfat_file_fsync(struct file *file, loff_t start, loff_t end, int datasync); /* namei.c */ diff --git a/fs/exfat/file.c b/fs/exfat/file.c index e9705b3295d3..3aa6eb4de5e3 100644 --- a/fs/exfat/file.c +++ b/fs/exfat/file.c @@ -267,8 +267,9 @@ write_size: mutex_unlock(&sbi->s_lock); } -int exfat_getattr(const struct path *path, struct kstat *stat, - unsigned int request_mask, unsigned int query_flags) +int exfat_getattr(struct user_namespace *mnt_uerns, const struct path *path, + struct kstat *stat, unsigned int request_mask, + unsigned int query_flags) { struct inode *inode = d_backing_inode(path->dentry); struct exfat_inode_info *ei = EXFAT_I(inode); @@ -282,7 +283,8 @@ int exfat_getattr(const struct path *path, struct kstat *stat, return 0; } -int exfat_setattr(struct dentry *dentry, struct iattr *attr) +int exfat_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *attr) { struct exfat_sb_info *sbi = EXFAT_SB(dentry->d_sb); struct inode *inode = dentry->d_inode; diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c index 2932b23a3b6c..d9e8ec689c55 100644 --- a/fs/exfat/namei.c +++ b/fs/exfat/namei.c @@ -541,8 +541,8 @@ out: return ret; } -static int exfat_create(struct inode *dir, struct dentry *dentry, umode_t mode, - bool excl) +static int exfat_create(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, bool excl) { struct super_block *sb = dir->i_sb; struct inode *inode; @@ -827,7 +827,8 @@ unlock: return err; } -static int exfat_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +static int exfat_mkdir(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct super_block *sb = dir->i_sb; struct inode *inode; @@ -1318,9 +1319,10 @@ out: return ret; } -static int exfat_rename(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry, - unsigned int flags) +static int exfat_rename(struct user_namespace *mnt_userns, + struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry, + unsigned int flags) { struct inode *old_inode, *new_inode; struct super_block *sb = old_dir->i_sb; diff --git a/fs/ext2/acl.c b/fs/ext2/acl.c index 9031f7df2d48..b9a9db98e94b 100644 --- a/fs/ext2/acl.c +++ b/fs/ext2/acl.c @@ -216,7 +216,8 @@ __ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type) * inode->i_mutex: down */ int -ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type) +ext2_set_acl(struct user_namespace *mnt_userns, struct inode *inode, + struct posix_acl *acl, int type) { int error; int update_mode = 0; diff --git a/fs/ext2/acl.h b/fs/ext2/acl.h index 0f01c759daac..917db5f6630a 100644 --- a/fs/ext2/acl.h +++ b/fs/ext2/acl.h @@ -56,7 +56,8 @@ static inline int ext2_acl_count(size_t size) /* acl.c */ extern struct posix_acl *ext2_get_acl(struct inode *inode, int type); -extern int ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type); +extern int ext2_set_acl(struct user_namespace *mnt_userns, struct inode *inode, + struct posix_acl *acl, int type); extern int ext2_init_acl (struct inode *, struct inode *); #else diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index 2a4175fbaf5e..3309fb2d327a 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -764,8 +764,9 @@ extern struct inode *ext2_iget (struct super_block *, unsigned long); extern int ext2_write_inode (struct inode *, struct writeback_control *); extern void ext2_evict_inode(struct inode *); extern int ext2_get_block(struct inode *, sector_t, struct buffer_head *, int); -extern int ext2_setattr (struct dentry *, struct iattr *); -extern int ext2_getattr (const struct path *, struct kstat *, u32, unsigned int); +extern int ext2_setattr (struct user_namespace *, struct dentry *, struct iattr *); +extern int ext2_getattr (struct user_namespace *, const struct path *, + struct kstat *, u32, unsigned int); extern void ext2_set_inode_flags(struct inode *inode); extern int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len); diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 3d8acafca8ce..68178b2234bd 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -1638,8 +1638,8 @@ int ext2_write_inode(struct inode *inode, struct writeback_control *wbc) return __ext2_write_inode(inode, wbc->sync_mode == WB_SYNC_ALL); } -int ext2_getattr(const struct path *path, struct kstat *stat, - u32 request_mask, unsigned int query_flags) +int ext2_getattr(struct user_namespace *mnt_userns, const struct path *path, + struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); struct ext2_inode_info *ei = EXT2_I(inode); @@ -1664,7 +1664,8 @@ int ext2_getattr(const struct path *path, struct kstat *stat, return 0; } -int ext2_setattr(struct dentry *dentry, struct iattr *iattr) +int ext2_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *iattr) { struct inode *inode = d_inode(dentry); int error; diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c index ea980f1e2e99..3367384d344d 100644 --- a/fs/ext2/namei.c +++ b/fs/ext2/namei.c @@ -100,7 +100,9 @@ struct dentry *ext2_get_parent(struct dentry *child) * If the create succeeds, we fill in the inode information * with d_instantiate(). */ -static int ext2_create (struct inode * dir, struct dentry * dentry, umode_t mode, bool excl) +static int ext2_create (struct user_namespace * mnt_userns, + struct inode * dir, struct dentry * dentry, + umode_t mode, bool excl) { struct inode *inode; int err; @@ -118,7 +120,8 @@ static int ext2_create (struct inode * dir, struct dentry * dentry, umode_t mode return ext2_add_nondir(dentry, inode); } -static int ext2_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) +static int ext2_tmpfile(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct inode *inode = ext2_new_inode(dir, mode, NULL); if (IS_ERR(inode)) @@ -131,7 +134,8 @@ static int ext2_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) return 0; } -static int ext2_mknod (struct inode * dir, struct dentry *dentry, umode_t mode, dev_t rdev) +static int ext2_mknod (struct user_namespace * mnt_userns, struct inode * dir, + struct dentry *dentry, umode_t mode, dev_t rdev) { struct inode * inode; int err; @@ -151,8 +155,8 @@ static int ext2_mknod (struct inode * dir, struct dentry *dentry, umode_t mode, return err; } -static int ext2_symlink (struct inode * dir, struct dentry * dentry, - const char * symname) +static int ext2_symlink (struct user_namespace * mnt_userns, struct inode * dir, + struct dentry * dentry, const char * symname) { struct super_block * sb = dir->i_sb; int err = -ENAMETOOLONG; @@ -225,7 +229,8 @@ static int ext2_link (struct dentry * old_dentry, struct inode * dir, return err; } -static int ext2_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode) +static int ext2_mkdir(struct user_namespace * mnt_userns, + struct inode * dir, struct dentry * dentry, umode_t mode) { struct inode * inode; int err; @@ -315,8 +320,9 @@ static int ext2_rmdir (struct inode * dir, struct dentry *dentry) return err; } -static int ext2_rename (struct inode * old_dir, struct dentry * old_dentry, - struct inode * new_dir, struct dentry * new_dentry, +static int ext2_rename (struct user_namespace * mnt_userns, + struct inode * old_dir, struct dentry * old_dentry, + struct inode * new_dir, struct dentry * new_dentry, unsigned int flags) { struct inode * old_inode = d_inode(old_dentry); diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c index 7b0fb66bc04d..059434e0f36c 100644 --- a/fs/ext4/acl.c +++ b/fs/ext4/acl.c @@ -222,7 +222,8 @@ __ext4_set_acl(handle_t *handle, struct inode *inode, int type, } int -ext4_set_acl(struct inode *inode, struct posix_acl *acl, int type) +ext4_set_acl(struct user_namespace *mnt_userns, struct inode *inode, + struct posix_acl *acl, int type) { handle_t *handle; int error, credits, retries = 0; diff --git a/fs/ext4/acl.h b/fs/ext4/acl.h index 9b63f5416a2f..84b8942a57f2 100644 --- a/fs/ext4/acl.h +++ b/fs/ext4/acl.h @@ -56,7 +56,8 @@ static inline int ext4_acl_count(size_t size) /* acl.c */ struct posix_acl *ext4_get_acl(struct inode *inode, int type); -int ext4_set_acl(struct inode *inode, struct posix_acl *acl, int type); +int ext4_set_acl(struct user_namespace *mnt_userns, struct inode *inode, + struct posix_acl *acl, int type); extern int ext4_init_acl(handle_t *, struct inode *, struct inode *); #else /* CONFIG_EXT4_FS_POSIX_ACL */ diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 2866d249f3d2..3c750f5e8ebd 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2877,11 +2877,14 @@ extern struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, __ext4_iget((sb), (ino), (flags), __func__, __LINE__) extern int ext4_write_inode(struct inode *, struct writeback_control *); -extern int ext4_setattr(struct dentry *, struct iattr *); -extern int ext4_getattr(const struct path *, struct kstat *, u32, unsigned int); +extern int ext4_setattr(struct user_namespace *, struct dentry *, + struct iattr *); +extern int ext4_getattr(struct user_namespace *, const struct path *, + struct kstat *, u32, unsigned int); extern void ext4_evict_inode(struct inode *); extern void ext4_clear_inode(struct inode *); -extern int ext4_file_getattr(const struct path *, struct kstat *, u32, unsigned int); +extern int ext4_file_getattr(struct user_namespace *, const struct path *, + struct kstat *, u32, unsigned int); extern int ext4_sync_inode(handle_t *, struct inode *); extern void ext4_dirty_inode(struct inode *, int); extern int ext4_change_inode_journal_flag(struct inode *, int); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 3a303d3f8423..ce45535336fa 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5319,7 +5319,8 @@ static void ext4_wait_for_tail_page_commit(struct inode *inode) * * Called with inode->i_mutex down. */ -int ext4_setattr(struct dentry *dentry, struct iattr *attr) +int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *attr) { struct inode *inode = d_inode(dentry); int error, rc = 0; @@ -5535,8 +5536,8 @@ err_out: return error; } -int ext4_getattr(const struct path *path, struct kstat *stat, - u32 request_mask, unsigned int query_flags) +int ext4_getattr(struct user_namespace *mnt_userns, const struct path *path, + struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); struct ext4_inode *raw_inode; @@ -5575,13 +5576,14 @@ int ext4_getattr(const struct path *path, struct kstat *stat, return 0; } -int ext4_file_getattr(const struct path *path, struct kstat *stat, +int ext4_file_getattr(struct user_namespace *mnt_userns, + const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); u64 delalloc_blocks; - ext4_getattr(path, stat, request_mask, query_flags); + ext4_getattr(&init_user_ns, path, stat, request_mask, query_flags); /* * If there is inline data in the inode, the inode will normally not diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index cf652ba3e74d..13dff80aedcb 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2596,8 +2596,8 @@ static int ext4_add_nondir(handle_t *handle, * If the create succeeds, we fill in the inode information * with d_instantiate(). */ -static int ext4_create(struct inode *dir, struct dentry *dentry, umode_t mode, - bool excl) +static int ext4_create(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, bool excl) { handle_t *handle; struct inode *inode; @@ -2631,8 +2631,8 @@ retry: return err; } -static int ext4_mknod(struct inode *dir, struct dentry *dentry, - umode_t mode, dev_t rdev) +static int ext4_mknod(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, dev_t rdev) { handle_t *handle; struct inode *inode; @@ -2665,7 +2665,8 @@ retry: return err; } -static int ext4_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) +static int ext4_tmpfile(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { handle_t *handle; struct inode *inode; @@ -2774,7 +2775,8 @@ out: return err; } -static int ext4_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +static int ext4_mkdir(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { handle_t *handle; struct inode *inode; @@ -3292,7 +3294,7 @@ out_trace: return retval; } -static int ext4_symlink(struct inode *dir, +static int ext4_symlink(struct user_namespace *mnt_userns, struct inode *dir, struct dentry *dentry, const char *symname) { handle_t *handle; @@ -4085,7 +4087,8 @@ end_rename: return retval; } -static int ext4_rename2(struct inode *old_dir, struct dentry *old_dentry, +static int ext4_rename2(struct user_namespace *mnt_userns, + struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c index 6a95bf28f602..a19e86c9adac 100644 --- a/fs/f2fs/acl.c +++ b/fs/f2fs/acl.c @@ -249,7 +249,8 @@ static int __f2fs_set_acl(struct inode *inode, int type, return error; } -int f2fs_set_acl(struct inode *inode, struct posix_acl *acl, int type) +int f2fs_set_acl(struct user_namespace *mnt_userns, struct inode *inode, + struct posix_acl *acl, int type) { if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) return -EIO; diff --git a/fs/f2fs/acl.h b/fs/f2fs/acl.h index 124868c13f80..986fd1bc780b 100644 --- a/fs/f2fs/acl.h +++ b/fs/f2fs/acl.h @@ -34,7 +34,8 @@ struct f2fs_acl_header { #ifdef CONFIG_F2FS_FS_POSIX_ACL extern struct posix_acl *f2fs_get_acl(struct inode *, int); -extern int f2fs_set_acl(struct inode *, struct posix_acl *, int); +extern int f2fs_set_acl(struct user_namespace *, struct inode *, + struct posix_acl *, int); extern int f2fs_init_acl(struct inode *, struct inode *, struct page *, struct page *); #else diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index bb11759191dc..c9002b1933f0 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -3135,9 +3135,10 @@ void f2fs_truncate_data_blocks(struct dnode_of_data *dn); int f2fs_do_truncate_blocks(struct inode *inode, u64 from, bool lock); int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock); int f2fs_truncate(struct inode *inode); -int f2fs_getattr(const struct path *path, struct kstat *stat, - u32 request_mask, unsigned int flags); -int f2fs_setattr(struct dentry *dentry, struct iattr *attr); +int f2fs_getattr(struct user_namespace *mnt_userns, const struct path *path, + struct kstat *stat, u32 request_mask, unsigned int flags); +int f2fs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *attr); int f2fs_truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end); void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count); int f2fs_precache_extents(struct inode *inode); diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 44cd0dbdbb5d..8f1e97e7d242 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -783,8 +783,8 @@ int f2fs_truncate(struct inode *inode) return 0; } -int f2fs_getattr(const struct path *path, struct kstat *stat, - u32 request_mask, unsigned int query_flags) +int f2fs_getattr(struct user_namespace *mnt_userns, const struct path *path, + struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); struct f2fs_inode_info *fi = F2FS_I(inode); @@ -859,7 +859,8 @@ static void __setattr_copy(struct user_namespace *mnt_userns, #define __setattr_copy setattr_copy #endif -int f2fs_setattr(struct dentry *dentry, struct iattr *attr) +int f2fs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *attr) { struct inode *inode = d_inode(dentry); int err; diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index ad98926bacac..c061a67e43a3 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -314,8 +314,8 @@ static void set_compress_inode(struct f2fs_sb_info *sbi, struct inode *inode, } } -static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - bool excl) +static int f2fs_create(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, bool excl) { struct f2fs_sb_info *sbi = F2FS_I_SB(dir); struct inode *inode; @@ -637,8 +637,8 @@ static const char *f2fs_get_link(struct dentry *dentry, return link; } -static int f2fs_symlink(struct inode *dir, struct dentry *dentry, - const char *symname) +static int f2fs_symlink(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, const char *symname) { struct f2fs_sb_info *sbi = F2FS_I_SB(dir); struct inode *inode; @@ -717,7 +717,8 @@ out_free_encrypted_link: return err; } -static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +static int f2fs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct f2fs_sb_info *sbi = F2FS_I_SB(dir); struct inode *inode; @@ -770,8 +771,8 @@ static int f2fs_rmdir(struct inode *dir, struct dentry *dentry) return -ENOTEMPTY; } -static int f2fs_mknod(struct inode *dir, struct dentry *dentry, - umode_t mode, dev_t rdev) +static int f2fs_mknod(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, dev_t rdev) { struct f2fs_sb_info *sbi = F2FS_I_SB(dir); struct inode *inode; @@ -874,7 +875,8 @@ out: return err; } -static int f2fs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) +static int f2fs_tmpfile(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct f2fs_sb_info *sbi = F2FS_I_SB(dir); @@ -1247,7 +1249,8 @@ out: return err; } -static int f2fs_rename2(struct inode *old_dir, struct dentry *old_dentry, +static int f2fs_rename2(struct user_namespace *mnt_userns, + struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { diff --git a/fs/fat/fat.h b/fs/fat/fat.h index 922a0c6ba46c..02d4d4234956 100644 --- a/fs/fat/fat.h +++ b/fs/fat/fat.h @@ -397,9 +397,11 @@ extern long fat_generic_ioctl(struct file *filp, unsigned int cmd, unsigned long arg); extern const struct file_operations fat_file_operations; extern const struct inode_operations fat_file_inode_operations; -extern int fat_setattr(struct dentry *dentry, struct iattr *attr); +extern int fat_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *attr); extern void fat_truncate_blocks(struct inode *inode, loff_t offset); -extern int fat_getattr(const struct path *path, struct kstat *stat, +extern int fat_getattr(struct user_namespace *mnt_userns, + const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags); extern int fat_file_fsync(struct file *file, loff_t start, loff_t end, int datasync); diff --git a/fs/fat/file.c b/fs/fat/file.c index f7e04f533d31..dd73d1b70c55 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -95,7 +95,7 @@ static int fat_ioctl_set_attributes(struct file *file, u32 __user *user_attr) goto out_unlock_inode; /* This MUST be done before doing anything irreversible... */ - err = fat_setattr(file->f_path.dentry, &ia); + err = fat_setattr(file_mnt_user_ns(file), file->f_path.dentry, &ia); if (err) goto out_unlock_inode; @@ -394,8 +394,8 @@ void fat_truncate_blocks(struct inode *inode, loff_t offset) fat_flush_inodes(inode->i_sb, inode, NULL); } -int fat_getattr(const struct path *path, struct kstat *stat, - u32 request_mask, unsigned int flags) +int fat_getattr(struct user_namespace *mnt_userns, const struct path *path, + struct kstat *stat, u32 request_mask, unsigned int flags) { struct inode *inode = d_inode(path->dentry); generic_fillattr(&init_user_ns, inode, stat); @@ -466,7 +466,8 @@ static int fat_allow_set_time(struct msdos_sb_info *sbi, struct inode *inode) /* valid file mode bits */ #define FAT_VALID_MODE (S_IFREG | S_IFDIR | S_IRWXUGO) -int fat_setattr(struct dentry *dentry, struct iattr *attr) +int fat_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *attr) { struct msdos_sb_info *sbi = MSDOS_SB(dentry->d_sb); struct inode *inode = d_inode(dentry); diff --git a/fs/fat/namei_msdos.c b/fs/fat/namei_msdos.c index 9d062886fbc1..a8f3375d9d10 100644 --- a/fs/fat/namei_msdos.c +++ b/fs/fat/namei_msdos.c @@ -261,8 +261,8 @@ static int msdos_add_entry(struct inode *dir, const unsigned char *name, } /***** Create a file */ -static int msdos_create(struct inode *dir, struct dentry *dentry, umode_t mode, - bool excl) +static int msdos_create(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, bool excl) { struct super_block *sb = dir->i_sb; struct inode *inode = NULL; @@ -339,7 +339,8 @@ out: } /***** Make a directory */ -static int msdos_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +static int msdos_mkdir(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct super_block *sb = dir->i_sb; struct fat_slot_info sinfo; @@ -593,7 +594,8 @@ error_inode: } /***** Rename, a wrapper for rename_same_dir & rename_diff_dir */ -static int msdos_rename(struct inode *old_dir, struct dentry *old_dentry, +static int msdos_rename(struct user_namespace *mnt_userns, + struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c index 0cdd0fb9f742..23936ecf79a5 100644 --- a/fs/fat/namei_vfat.c +++ b/fs/fat/namei_vfat.c @@ -756,8 +756,8 @@ error: return ERR_PTR(err); } -static int vfat_create(struct inode *dir, struct dentry *dentry, umode_t mode, - bool excl) +static int vfat_create(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, bool excl) { struct super_block *sb = dir->i_sb; struct inode *inode; @@ -846,7 +846,8 @@ out: return err; } -static int vfat_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +static int vfat_mkdir(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct super_block *sb = dir->i_sb; struct inode *inode; @@ -892,9 +893,9 @@ out: return err; } -static int vfat_rename(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry, - unsigned int flags) +static int vfat_rename(struct user_namespace *mnt_userns, struct inode *old_dir, + struct dentry *old_dentry, struct inode *new_dir, + struct dentry *new_dentry, unsigned int flags) { struct buffer_head *dotdot_bh; struct msdos_dir_entry *dotdot_de; diff --git a/fs/fuse/acl.c b/fs/fuse/acl.c index f529075a2ce8..e9c0f916349d 100644 --- a/fs/fuse/acl.c +++ b/fs/fuse/acl.c @@ -50,7 +50,8 @@ struct posix_acl *fuse_get_acl(struct inode *inode, int type) return acl; } -int fuse_set_acl(struct inode *inode, struct posix_acl *acl, int type) +int fuse_set_acl(struct user_namespace *mnt_userns, struct inode *inode, + struct posix_acl *acl, int type) { struct fuse_conn *fc = get_fuse_conn(inode); const char *name; diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index d2e318ed9b26..06a18700a845 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -605,7 +605,8 @@ out_err: return err; } -static int fuse_mknod(struct inode *, struct dentry *, umode_t, dev_t); +static int fuse_mknod(struct user_namespace *, struct inode *, struct dentry *, + umode_t, dev_t); static int fuse_atomic_open(struct inode *dir, struct dentry *entry, struct file *file, unsigned flags, umode_t mode) @@ -645,7 +646,7 @@ out_dput: return err; mknod: - err = fuse_mknod(dir, entry, mode, 0); + err = fuse_mknod(&init_user_ns, dir, entry, mode, 0); if (err) goto out_dput; no_open: @@ -715,8 +716,8 @@ static int create_new_entry(struct fuse_mount *fm, struct fuse_args *args, return err; } -static int fuse_mknod(struct inode *dir, struct dentry *entry, umode_t mode, - dev_t rdev) +static int fuse_mknod(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *entry, umode_t mode, dev_t rdev) { struct fuse_mknod_in inarg; struct fuse_mount *fm = get_fuse_mount(dir); @@ -738,13 +739,14 @@ static int fuse_mknod(struct inode *dir, struct dentry *entry, umode_t mode, return create_new_entry(fm, &args, dir, entry, mode); } -static int fuse_create(struct inode *dir, struct dentry *entry, umode_t mode, - bool excl) +static int fuse_create(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *entry, umode_t mode, bool excl) { - return fuse_mknod(dir, entry, mode, 0); + return fuse_mknod(&init_user_ns, dir, entry, mode, 0); } -static int fuse_mkdir(struct inode *dir, struct dentry *entry, umode_t mode) +static int fuse_mkdir(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *entry, umode_t mode) { struct fuse_mkdir_in inarg; struct fuse_mount *fm = get_fuse_mount(dir); @@ -765,8 +767,8 @@ static int fuse_mkdir(struct inode *dir, struct dentry *entry, umode_t mode) return create_new_entry(fm, &args, dir, entry, S_IFDIR); } -static int fuse_symlink(struct inode *dir, struct dentry *entry, - const char *link) +static int fuse_symlink(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *entry, const char *link) { struct fuse_mount *fm = get_fuse_mount(dir); unsigned len = strlen(link) + 1; @@ -908,9 +910,9 @@ static int fuse_rename_common(struct inode *olddir, struct dentry *oldent, return err; } -static int fuse_rename2(struct inode *olddir, struct dentry *oldent, - struct inode *newdir, struct dentry *newent, - unsigned int flags) +static int fuse_rename2(struct user_namespace *mnt_userns, struct inode *olddir, + struct dentry *oldent, struct inode *newdir, + struct dentry *newent, unsigned int flags) { struct fuse_conn *fc = get_fuse_conn(olddir); int err; @@ -1249,7 +1251,8 @@ static int fuse_perm_getattr(struct inode *inode, int mask) * access request is sent. Execute permission is still checked * locally based on file mode. */ -static int fuse_permission(struct inode *inode, int mask) +static int fuse_permission(struct user_namespace *mnt_userns, + struct inode *inode, int mask) { struct fuse_conn *fc = get_fuse_conn(inode); bool refreshed = false; @@ -1757,7 +1760,8 @@ error: return err; } -static int fuse_setattr(struct dentry *entry, struct iattr *attr) +static int fuse_setattr(struct user_namespace *mnt_userns, struct dentry *entry, + struct iattr *attr) { struct inode *inode = d_inode(entry); struct fuse_conn *fc = get_fuse_conn(inode); @@ -1819,7 +1823,8 @@ static int fuse_setattr(struct dentry *entry, struct iattr *attr) return ret; } -static int fuse_getattr(const struct path *path, struct kstat *stat, +static int fuse_getattr(struct user_namespace *mnt_userns, + const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags) { struct inode *inode = d_inode(path->dentry); diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 7c4b8cb93f9f..68cca8d4db6e 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -1180,8 +1180,8 @@ extern const struct xattr_handler *fuse_no_acl_xattr_handlers[]; struct posix_acl; struct posix_acl *fuse_get_acl(struct inode *inode, int type); -int fuse_set_acl(struct inode *inode, struct posix_acl *acl, int type); - +int fuse_set_acl(struct user_namespace *mnt_userns, struct inode *inode, + struct posix_acl *acl, int type); /* readdir.c */ int fuse_readdir(struct file *file, struct dir_context *ctx); diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c index ce88ef29eef0..9165d70ead07 100644 --- a/fs/gfs2/acl.c +++ b/fs/gfs2/acl.c @@ -106,7 +106,8 @@ out: return error; } -int gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type) +int gfs2_set_acl(struct user_namespace *mnt_userns, struct inode *inode, + struct posix_acl *acl, int type) { struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_holder gh; diff --git a/fs/gfs2/acl.h b/fs/gfs2/acl.h index 61353a1501c5..eccc6a43326c 100644 --- a/fs/gfs2/acl.h +++ b/fs/gfs2/acl.h @@ -13,6 +13,7 @@ extern struct posix_acl *gfs2_get_acl(struct inode *inode, int type); extern int __gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type); -extern int gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type); +extern int gfs2_set_acl(struct user_namespace *mnt_userns, struct inode *inode, + struct posix_acl *acl, int type); #endif /* __ACL_DOT_H__ */ diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 1d994bdfffaa..8f5523822788 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -256,7 +256,7 @@ static int do_gfs2_set_flags(struct file *filp, u32 reqflags, u32 mask, !capable(CAP_LINUX_IMMUTABLE)) goto out; if (!IS_IMMUTABLE(inode)) { - error = gfs2_permission(inode, MAY_WRITE); + error = gfs2_permission(&init_user_ns, inode, MAY_WRITE); if (error) goto out; } diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 226b5b1dc1fa..cfac2c1e67fa 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -325,7 +325,7 @@ struct inode *gfs2_lookupi(struct inode *dir, const struct qstr *name, } if (!is_root) { - error = gfs2_permission(dir, MAY_EXEC); + error = gfs2_permission(&init_user_ns, dir, MAY_EXEC); if (error) goto out; } @@ -355,7 +355,8 @@ static int create_ok(struct gfs2_inode *dip, const struct qstr *name, { int error; - error = gfs2_permission(&dip->i_inode, MAY_WRITE | MAY_EXEC); + error = gfs2_permission(&init_user_ns, &dip->i_inode, + MAY_WRITE | MAY_EXEC); if (error) return error; @@ -843,8 +844,8 @@ fail: * Returns: errno */ -static int gfs2_create(struct inode *dir, struct dentry *dentry, - umode_t mode, bool excl) +static int gfs2_create(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, bool excl) { return gfs2_create_inode(dir, dentry, NULL, S_IFREG | mode, 0, NULL, 0, excl); } @@ -951,7 +952,7 @@ static int gfs2_link(struct dentry *old_dentry, struct inode *dir, if (inode->i_nlink == 0) goto out_gunlock; - error = gfs2_permission(dir, MAY_WRITE | MAY_EXEC); + error = gfs2_permission(&init_user_ns, dir, MAY_WRITE | MAY_EXEC); if (error) goto out_gunlock; @@ -1068,7 +1069,8 @@ static int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name, if (IS_APPEND(&dip->i_inode)) return -EPERM; - error = gfs2_permission(&dip->i_inode, MAY_WRITE | MAY_EXEC); + error = gfs2_permission(&init_user_ns, &dip->i_inode, + MAY_WRITE | MAY_EXEC); if (error) return error; @@ -1204,8 +1206,8 @@ out_inodes: * Returns: errno */ -static int gfs2_symlink(struct inode *dir, struct dentry *dentry, - const char *symname) +static int gfs2_symlink(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, const char *symname) { unsigned int size; @@ -1225,7 +1227,8 @@ static int gfs2_symlink(struct inode *dir, struct dentry *dentry, * Returns: errno */ -static int gfs2_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +static int gfs2_mkdir(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { unsigned dsize = gfs2_max_stuffed_size(GFS2_I(dir)); return gfs2_create_inode(dir, dentry, NULL, S_IFDIR | mode, 0, NULL, dsize, 0); @@ -1240,8 +1243,8 @@ static int gfs2_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) * */ -static int gfs2_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, - dev_t dev) +static int gfs2_mknod(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, dev_t dev) { return gfs2_create_inode(dir, dentry, NULL, mode, dev, NULL, 0, 0); } @@ -1490,7 +1493,8 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry, } } } else { - error = gfs2_permission(ndir, MAY_WRITE | MAY_EXEC); + error = gfs2_permission(&init_user_ns, ndir, + MAY_WRITE | MAY_EXEC); if (error) goto out_gunlock; @@ -1525,7 +1529,8 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry, /* Check out the dir to be renamed */ if (dir_rename) { - error = gfs2_permission(d_inode(odentry), MAY_WRITE); + error = gfs2_permission(&init_user_ns, d_inode(odentry), + MAY_WRITE); if (error) goto out_gunlock; } @@ -1688,12 +1693,14 @@ static int gfs2_exchange(struct inode *odir, struct dentry *odentry, goto out_gunlock; if (S_ISDIR(old_mode)) { - error = gfs2_permission(odentry->d_inode, MAY_WRITE); + error = gfs2_permission(&init_user_ns, odentry->d_inode, + MAY_WRITE); if (error) goto out_gunlock; } if (S_ISDIR(new_mode)) { - error = gfs2_permission(ndentry->d_inode, MAY_WRITE); + error = gfs2_permission(&init_user_ns, ndentry->d_inode, + MAY_WRITE); if (error) goto out_gunlock; } @@ -1747,9 +1754,9 @@ out: return error; } -static int gfs2_rename2(struct inode *odir, struct dentry *odentry, - struct inode *ndir, struct dentry *ndentry, - unsigned int flags) +static int gfs2_rename2(struct user_namespace *mnt_userns, struct inode *odir, + struct dentry *odentry, struct inode *ndir, + struct dentry *ndentry, unsigned int flags) { flags &= ~RENAME_NOREPLACE; @@ -1833,7 +1840,8 @@ out: * Returns: errno */ -int gfs2_permission(struct inode *inode, int mask) +int gfs2_permission(struct user_namespace *mnt_userns, struct inode *inode, + int mask) { struct gfs2_inode *ip; struct gfs2_holder i_gh; @@ -1963,7 +1971,8 @@ out: * Returns: errno */ -static int gfs2_setattr(struct dentry *dentry, struct iattr *attr) +static int gfs2_setattr(struct user_namespace *mnt_userns, + struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); struct gfs2_inode *ip = GFS2_I(inode); @@ -2008,6 +2017,7 @@ out: /** * gfs2_getattr - Read out an inode's attributes + * @mnt_userns: user namespace of the mount the inode was found from * @path: Object to query * @stat: The inode's stats * @request_mask: Mask of STATX_xxx flags indicating the caller's interests @@ -2022,7 +2032,8 @@ out: * Returns: errno */ -static int gfs2_getattr(const struct path *path, struct kstat *stat, +static int gfs2_getattr(struct user_namespace *mnt_userns, + const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags) { struct inode *inode = d_inode(path->dentry); diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h index 8073b8d2c7fa..c447bd5b3017 100644 --- a/fs/gfs2/inode.h +++ b/fs/gfs2/inode.h @@ -99,7 +99,8 @@ extern int gfs2_inode_refresh(struct gfs2_inode *ip); extern struct inode *gfs2_lookupi(struct inode *dir, const struct qstr *name, int is_root); -extern int gfs2_permission(struct inode *inode, int mask); +extern int gfs2_permission(struct user_namespace *mnt_userns, + struct inode *inode, int mask); extern int gfs2_setattr_simple(struct inode *inode, struct iattr *attr); extern struct inode *gfs2_lookup_simple(struct inode *dip, const char *name); extern void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf); diff --git a/fs/hfs/dir.c b/fs/hfs/dir.c index 3bf2ae0e467c..527f6e46cbe8 100644 --- a/fs/hfs/dir.c +++ b/fs/hfs/dir.c @@ -189,8 +189,8 @@ static int hfs_dir_release(struct inode *inode, struct file *file) * a directory and return a corresponding inode, given the inode for * the directory and the name (and its length) of the new file. */ -static int hfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - bool excl) +static int hfs_create(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, bool excl) { struct inode *inode; int res; @@ -219,7 +219,8 @@ static int hfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, * in a directory, given the inode for the parent directory and the * name (and its length) of the new directory. */ -static int hfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +static int hfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct inode *inode; int res; @@ -279,9 +280,9 @@ static int hfs_remove(struct inode *dir, struct dentry *dentry) * new file/directory. * XXX: how do you handle must_be dir? */ -static int hfs_rename(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry, - unsigned int flags) +static int hfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, + struct dentry *old_dentry, struct inode *new_dir, + struct dentry *new_dentry, unsigned int flags) { int res; diff --git a/fs/hfs/hfs_fs.h b/fs/hfs/hfs_fs.h index f71c384064c8..b8eb0322a3e5 100644 --- a/fs/hfs/hfs_fs.h +++ b/fs/hfs/hfs_fs.h @@ -204,7 +204,8 @@ extern const struct address_space_operations hfs_btree_aops; extern struct inode *hfs_new_inode(struct inode *, const struct qstr *, umode_t); extern void hfs_inode_write_fork(struct inode *, struct hfs_extent *, __be32 *, __be32 *); extern int hfs_write_inode(struct inode *, struct writeback_control *); -extern int hfs_inode_setattr(struct dentry *, struct iattr *); +extern int hfs_inode_setattr(struct user_namespace *, struct dentry *, + struct iattr *); extern void hfs_inode_read_fork(struct inode *inode, struct hfs_extent *ext, __be32 log_size, __be32 phys_size, u32 clump_size); extern struct inode *hfs_iget(struct super_block *, struct hfs_cat_key *, hfs_cat_rec *); diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index c646218b72bf..3fc5cb346586 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -602,13 +602,15 @@ static int hfs_file_release(struct inode *inode, struct file *file) * correspond to the same HFS file. */ -int hfs_inode_setattr(struct dentry *dentry, struct iattr * attr) +int hfs_inode_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *attr) { struct inode *inode = d_inode(dentry); struct hfs_sb_info *hsb = HFS_SB(inode->i_sb); int error; - error = setattr_prepare(&init_user_ns, dentry, attr); /* basic permission checks */ + error = setattr_prepare(&init_user_ns, dentry, + attr); /* basic permission checks */ if (error) return error; diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c index 29a9dcfbe81f..03e6c046faf4 100644 --- a/fs/hfsplus/dir.c +++ b/fs/hfsplus/dir.c @@ -434,8 +434,8 @@ out: return res; } -static int hfsplus_symlink(struct inode *dir, struct dentry *dentry, - const char *symname) +static int hfsplus_symlink(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, const char *symname) { struct hfsplus_sb_info *sbi = HFSPLUS_SB(dir->i_sb); struct inode *inode; @@ -476,8 +476,8 @@ out: return res; } -static int hfsplus_mknod(struct inode *dir, struct dentry *dentry, - umode_t mode, dev_t rdev) +static int hfsplus_mknod(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, dev_t rdev) { struct hfsplus_sb_info *sbi = HFSPLUS_SB(dir->i_sb); struct inode *inode; @@ -517,18 +517,20 @@ out: return res; } -static int hfsplus_create(struct inode *dir, struct dentry *dentry, umode_t mode, - bool excl) +static int hfsplus_create(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, bool excl) { - return hfsplus_mknod(dir, dentry, mode, 0); + return hfsplus_mknod(&init_user_ns, dir, dentry, mode, 0); } -static int hfsplus_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +static int hfsplus_mkdir(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { - return hfsplus_mknod(dir, dentry, mode | S_IFDIR, 0); + return hfsplus_mknod(&init_user_ns, dir, dentry, mode | S_IFDIR, 0); } -static int hfsplus_rename(struct inode *old_dir, struct dentry *old_dentry, +static int hfsplus_rename(struct user_namespace *mnt_userns, + struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h index a92de5199ec3..12b20479ed2b 100644 --- a/fs/hfsplus/hfsplus_fs.h +++ b/fs/hfsplus/hfsplus_fs.h @@ -488,8 +488,9 @@ void hfsplus_inode_write_fork(struct inode *inode, struct hfsplus_fork_raw *fork); int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd); int hfsplus_cat_write_inode(struct inode *inode); -int hfsplus_getattr(const struct path *path, struct kstat *stat, - u32 request_mask, unsigned int query_flags); +int hfsplus_getattr(struct user_namespace *mnt_userns, const struct path *path, + struct kstat *stat, u32 request_mask, + unsigned int query_flags); int hfsplus_file_fsync(struct file *file, loff_t start, loff_t end, int datasync); diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index 642e067d8fe8..7a937de9b2ad 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -241,7 +241,8 @@ static int hfsplus_file_release(struct inode *inode, struct file *file) return 0; } -static int hfsplus_setattr(struct dentry *dentry, struct iattr *attr) +static int hfsplus_setattr(struct user_namespace *mnt_userns, + struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); int error; @@ -270,8 +271,9 @@ static int hfsplus_setattr(struct dentry *dentry, struct iattr *attr) return 0; } -int hfsplus_getattr(const struct path *path, struct kstat *stat, - u32 request_mask, unsigned int query_flags) +int hfsplus_getattr(struct user_namespace *mnt_userns, const struct path *path, + struct kstat *stat, u32 request_mask, + unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); struct hfsplus_inode_info *hip = HFSPLUS_I(inode); diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index 6970e29a5287..7c918cd816a3 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -555,8 +555,8 @@ static int read_name(struct inode *ino, char *name) return 0; } -static int hostfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - bool excl) +static int hostfs_create(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, bool excl) { struct inode *inode; char *name; @@ -654,8 +654,8 @@ static int hostfs_unlink(struct inode *ino, struct dentry *dentry) return err; } -static int hostfs_symlink(struct inode *ino, struct dentry *dentry, - const char *to) +static int hostfs_symlink(struct user_namespace *mnt_userns, struct inode *ino, + struct dentry *dentry, const char *to) { char *file; int err; @@ -667,7 +667,8 @@ static int hostfs_symlink(struct inode *ino, struct dentry *dentry, return err; } -static int hostfs_mkdir(struct inode *ino, struct dentry *dentry, umode_t mode) +static int hostfs_mkdir(struct user_namespace *mnt_userns, struct inode *ino, + struct dentry *dentry, umode_t mode) { char *file; int err; @@ -691,7 +692,8 @@ static int hostfs_rmdir(struct inode *ino, struct dentry *dentry) return err; } -static int hostfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) +static int hostfs_mknod(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, dev_t dev) { struct inode *inode; char *name; @@ -729,7 +731,8 @@ static int hostfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, return err; } -static int hostfs_rename2(struct inode *old_dir, struct dentry *old_dentry, +static int hostfs_rename2(struct user_namespace *mnt_userns, + struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { @@ -757,7 +760,8 @@ static int hostfs_rename2(struct inode *old_dir, struct dentry *old_dentry, return err; } -static int hostfs_permission(struct inode *ino, int desired) +static int hostfs_permission(struct user_namespace *mnt_userns, + struct inode *ino, int desired) { char *name; int r = 0, w = 0, x = 0, err; @@ -783,7 +787,8 @@ static int hostfs_permission(struct inode *ino, int desired) return err; } -static int hostfs_setattr(struct dentry *dentry, struct iattr *attr) +static int hostfs_setattr(struct user_namespace *mnt_userns, + struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); struct hostfs_iattr attrs; diff --git a/fs/hpfs/hpfs_fn.h b/fs/hpfs/hpfs_fn.h index 1cca83218fb5..167ec6884642 100644 --- a/fs/hpfs/hpfs_fn.h +++ b/fs/hpfs/hpfs_fn.h @@ -280,7 +280,7 @@ void hpfs_init_inode(struct inode *); void hpfs_read_inode(struct inode *); void hpfs_write_inode(struct inode *); void hpfs_write_inode_nolock(struct inode *); -int hpfs_setattr(struct dentry *, struct iattr *); +int hpfs_setattr(struct user_namespace *, struct dentry *, struct iattr *); void hpfs_write_if_changed(struct inode *); void hpfs_evict_inode(struct inode *); diff --git a/fs/hpfs/inode.c b/fs/hpfs/inode.c index 8ba2152a78ba..82208cc28ebd 100644 --- a/fs/hpfs/inode.c +++ b/fs/hpfs/inode.c @@ -257,7 +257,8 @@ void hpfs_write_inode_nolock(struct inode *i) brelse(bh); } -int hpfs_setattr(struct dentry *dentry, struct iattr *attr) +int hpfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *attr) { struct inode *inode = d_inode(dentry); int error = -EINVAL; diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c index 1aee39160ac5..d73f8a67168e 100644 --- a/fs/hpfs/namei.c +++ b/fs/hpfs/namei.c @@ -20,7 +20,8 @@ static void hpfs_update_directory_times(struct inode *dir) hpfs_write_inode_nolock(dir); } -static int hpfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +static int hpfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { const unsigned char *name = dentry->d_name.name; unsigned len = dentry->d_name.len; @@ -128,7 +129,8 @@ bail: return err; } -static int hpfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) +static int hpfs_create(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, bool excl) { const unsigned char *name = dentry->d_name.name; unsigned len = dentry->d_name.len; @@ -215,7 +217,8 @@ bail: return err; } -static int hpfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) +static int hpfs_mknod(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, dev_t rdev) { const unsigned char *name = dentry->d_name.name; unsigned len = dentry->d_name.len; @@ -289,7 +292,8 @@ bail: return err; } -static int hpfs_symlink(struct inode *dir, struct dentry *dentry, const char *symlink) +static int hpfs_symlink(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, const char *symlink) { const unsigned char *name = dentry->d_name.name; unsigned len = dentry->d_name.len; @@ -506,10 +510,10 @@ fail: const struct address_space_operations hpfs_symlink_aops = { .readpage = hpfs_symlink_readpage }; - -static int hpfs_rename(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry, - unsigned int flags) + +static int hpfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, + struct dentry *old_dentry, struct inode *new_dir, + struct dentry *new_dentry, unsigned int flags) { const unsigned char *old_name = old_dentry->d_name.name; unsigned old_len = old_dentry->d_name.len; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 327e572b4e00..c5c32eb59498 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -751,7 +751,8 @@ out: return error; } -static int hugetlbfs_setattr(struct dentry *dentry, struct iattr *attr) +static int hugetlbfs_setattr(struct user_namespace *mnt_userns, + struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); struct hstate *h = hstate_inode(inode); @@ -898,33 +899,39 @@ static int do_hugetlbfs_mknod(struct inode *dir, return error; } -static int hugetlbfs_mknod(struct inode *dir, - struct dentry *dentry, umode_t mode, dev_t dev) +static int hugetlbfs_mknod(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, dev_t dev) { return do_hugetlbfs_mknod(dir, dentry, mode, dev, false); } -static int hugetlbfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +static int hugetlbfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { - int retval = hugetlbfs_mknod(dir, dentry, mode | S_IFDIR, 0); + int retval = hugetlbfs_mknod(&init_user_ns, dir, dentry, + mode | S_IFDIR, 0); if (!retval) inc_nlink(dir); return retval; } -static int hugetlbfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) +static int hugetlbfs_create(struct user_namespace *mnt_userns, + struct inode *dir, struct dentry *dentry, + umode_t mode, bool excl) { - return hugetlbfs_mknod(dir, dentry, mode | S_IFREG, 0); + return hugetlbfs_mknod(&init_user_ns, dir, dentry, mode | S_IFREG, 0); } -static int hugetlbfs_tmpfile(struct inode *dir, - struct dentry *dentry, umode_t mode) +static int hugetlbfs_tmpfile(struct user_namespace *mnt_userns, + struct inode *dir, struct dentry *dentry, + umode_t mode) { return do_hugetlbfs_mknod(dir, dentry, mode | S_IFREG, 0, true); } -static int hugetlbfs_symlink(struct inode *dir, - struct dentry *dentry, const char *symname) +static int hugetlbfs_symlink(struct user_namespace *mnt_userns, + struct inode *dir, struct dentry *dentry, + const char *symname) { struct inode *inode; int error = -ENOSPC; diff --git a/fs/jffs2/acl.c b/fs/jffs2/acl.c index 5f27ac593479..55a79df70d24 100644 --- a/fs/jffs2/acl.c +++ b/fs/jffs2/acl.c @@ -226,7 +226,8 @@ static int __jffs2_set_acl(struct inode *inode, int xprefix, struct posix_acl *a return rc; } -int jffs2_set_acl(struct inode *inode, struct posix_acl *acl, int type) +int jffs2_set_acl(struct user_namespace *mnt_userns, struct inode *inode, + struct posix_acl *acl, int type) { int rc, xprefix; diff --git a/fs/jffs2/acl.h b/fs/jffs2/acl.h index 12d0271bdde3..62c50da9d493 100644 --- a/fs/jffs2/acl.h +++ b/fs/jffs2/acl.h @@ -28,7 +28,8 @@ struct jffs2_acl_header { #ifdef CONFIG_JFFS2_FS_POSIX_ACL struct posix_acl *jffs2_get_acl(struct inode *inode, int type); -int jffs2_set_acl(struct inode *inode, struct posix_acl *acl, int type); +int jffs2_set_acl(struct user_namespace *mnt_userns, struct inode *inode, + struct posix_acl *acl, int type); extern int jffs2_init_acl_pre(struct inode *, struct inode *, umode_t *); extern int jffs2_init_acl_post(struct inode *); diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c index 776493713153..c0aabbcbfd58 100644 --- a/fs/jffs2/dir.c +++ b/fs/jffs2/dir.c @@ -24,18 +24,21 @@ static int jffs2_readdir (struct file *, struct dir_context *); -static int jffs2_create (struct inode *,struct dentry *,umode_t, - bool); +static int jffs2_create (struct user_namespace *, struct inode *, + struct dentry *, umode_t, bool); static struct dentry *jffs2_lookup (struct inode *,struct dentry *, unsigned int); static int jffs2_link (struct dentry *,struct inode *,struct dentry *); static int jffs2_unlink (struct inode *,struct dentry *); -static int jffs2_symlink (struct inode *,struct dentry *,const char *); -static int jffs2_mkdir (struct inode *,struct dentry *,umode_t); +static int jffs2_symlink (struct user_namespace *, struct inode *, + struct dentry *, const char *); +static int jffs2_mkdir (struct user_namespace *, struct inode *,struct dentry *, + umode_t); static int jffs2_rmdir (struct inode *,struct dentry *); -static int jffs2_mknod (struct inode *,struct dentry *,umode_t,dev_t); -static int jffs2_rename (struct inode *, struct dentry *, - struct inode *, struct dentry *, +static int jffs2_mknod (struct user_namespace *, struct inode *,struct dentry *, + umode_t,dev_t); +static int jffs2_rename (struct user_namespace *, struct inode *, + struct dentry *, struct inode *, struct dentry *, unsigned int); const struct file_operations jffs2_dir_operations = @@ -157,8 +160,8 @@ static int jffs2_readdir(struct file *file, struct dir_context *ctx) /***********************************************************************/ -static int jffs2_create(struct inode *dir_i, struct dentry *dentry, - umode_t mode, bool excl) +static int jffs2_create(struct user_namespace *mnt_userns, struct inode *dir_i, + struct dentry *dentry, umode_t mode, bool excl) { struct jffs2_raw_inode *ri; struct jffs2_inode_info *f, *dir_f; @@ -276,7 +279,8 @@ static int jffs2_link (struct dentry *old_dentry, struct inode *dir_i, struct de /***********************************************************************/ -static int jffs2_symlink (struct inode *dir_i, struct dentry *dentry, const char *target) +static int jffs2_symlink (struct user_namespace *mnt_userns, struct inode *dir_i, + struct dentry *dentry, const char *target) { struct jffs2_inode_info *f, *dir_f; struct jffs2_sb_info *c; @@ -438,7 +442,8 @@ static int jffs2_symlink (struct inode *dir_i, struct dentry *dentry, const char } -static int jffs2_mkdir (struct inode *dir_i, struct dentry *dentry, umode_t mode) +static int jffs2_mkdir (struct user_namespace *mnt_userns, struct inode *dir_i, + struct dentry *dentry, umode_t mode) { struct jffs2_inode_info *f, *dir_f; struct jffs2_sb_info *c; @@ -609,7 +614,8 @@ static int jffs2_rmdir (struct inode *dir_i, struct dentry *dentry) return ret; } -static int jffs2_mknod (struct inode *dir_i, struct dentry *dentry, umode_t mode, dev_t rdev) +static int jffs2_mknod (struct user_namespace *mnt_userns, struct inode *dir_i, + struct dentry *dentry, umode_t mode, dev_t rdev) { struct jffs2_inode_info *f, *dir_f; struct jffs2_sb_info *c; @@ -756,7 +762,8 @@ static int jffs2_mknod (struct inode *dir_i, struct dentry *dentry, umode_t mode return ret; } -static int jffs2_rename (struct inode *old_dir_i, struct dentry *old_dentry, +static int jffs2_rename (struct user_namespace *mnt_userns, + struct inode *old_dir_i, struct dentry *old_dentry, struct inode *new_dir_i, struct dentry *new_dentry, unsigned int flags) { diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c index ee9f51bab4c6..2ac410477c4f 100644 --- a/fs/jffs2/fs.c +++ b/fs/jffs2/fs.c @@ -190,7 +190,8 @@ int jffs2_do_setattr (struct inode *inode, struct iattr *iattr) return 0; } -int jffs2_setattr(struct dentry *dentry, struct iattr *iattr) +int jffs2_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *iattr) { struct inode *inode = d_inode(dentry); int rc; diff --git a/fs/jffs2/os-linux.h b/fs/jffs2/os-linux.h index ef1cfa61549e..173eccac691d 100644 --- a/fs/jffs2/os-linux.h +++ b/fs/jffs2/os-linux.h @@ -164,7 +164,7 @@ long jffs2_ioctl(struct file *, unsigned int, unsigned long); extern const struct inode_operations jffs2_symlink_inode_operations; /* fs.c */ -int jffs2_setattr (struct dentry *, struct iattr *); +int jffs2_setattr (struct user_namespace *, struct dentry *, struct iattr *); int jffs2_do_setattr (struct inode *, struct iattr *); struct inode *jffs2_iget(struct super_block *, unsigned long); void jffs2_evict_inode (struct inode *); diff --git a/fs/jfs/acl.c b/fs/jfs/acl.c index cf79a34bfada..43c285c3d2a7 100644 --- a/fs/jfs/acl.c +++ b/fs/jfs/acl.c @@ -91,7 +91,8 @@ out: return rc; } -int jfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) +int jfs_set_acl(struct user_namespace *mnt_userns, struct inode *inode, + struct posix_acl *acl, int type) { int rc; tid_t tid; diff --git a/fs/jfs/file.c b/fs/jfs/file.c index 61c3b0c1fbf6..28b70e7c7dd4 100644 --- a/fs/jfs/file.c +++ b/fs/jfs/file.c @@ -85,7 +85,8 @@ static int jfs_release(struct inode *inode, struct file *file) return 0; } -int jfs_setattr(struct dentry *dentry, struct iattr *iattr) +int jfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *iattr) { struct inode *inode = d_inode(dentry); int rc; diff --git a/fs/jfs/jfs_acl.h b/fs/jfs/jfs_acl.h index 9f8f92dd6f84..7ae389a7a366 100644 --- a/fs/jfs/jfs_acl.h +++ b/fs/jfs/jfs_acl.h @@ -8,7 +8,8 @@ #ifdef CONFIG_JFS_POSIX_ACL struct posix_acl *jfs_get_acl(struct inode *inode, int type); -int jfs_set_acl(struct inode *inode, struct posix_acl *acl, int type); +int jfs_set_acl(struct user_namespace *mnt_userns, struct inode *inode, + struct posix_acl *acl, int type); int jfs_init_acl(tid_t, struct inode *, struct inode *); #else diff --git a/fs/jfs/jfs_inode.h b/fs/jfs/jfs_inode.h index 70a0d12e427e..01daa0cb0ae5 100644 --- a/fs/jfs/jfs_inode.h +++ b/fs/jfs/jfs_inode.h @@ -26,7 +26,7 @@ extern struct dentry *jfs_fh_to_parent(struct super_block *sb, struct fid *fid, int fh_len, int fh_type); extern void jfs_set_inode_flags(struct inode *); extern int jfs_get_block(struct inode *, sector_t, struct buffer_head *, int); -extern int jfs_setattr(struct dentry *, struct iattr *); +extern int jfs_setattr(struct user_namespace *, struct dentry *, struct iattr *); extern const struct address_space_operations jfs_aops; extern const struct inode_operations jfs_dir_inode_operations; diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c index 7a55d14cc1af..9abed0d750e5 100644 --- a/fs/jfs/namei.c +++ b/fs/jfs/namei.c @@ -59,8 +59,8 @@ static inline void free_ea_wmap(struct inode *inode) * RETURN: Errors from subroutines * */ -static int jfs_create(struct inode *dip, struct dentry *dentry, umode_t mode, - bool excl) +static int jfs_create(struct user_namespace *mnt_userns, struct inode *dip, + struct dentry *dentry, umode_t mode, bool excl) { int rc = 0; tid_t tid; /* transaction id */ @@ -192,7 +192,8 @@ static int jfs_create(struct inode *dip, struct dentry *dentry, umode_t mode, * note: * EACCES: user needs search+write permission on the parent directory */ -static int jfs_mkdir(struct inode *dip, struct dentry *dentry, umode_t mode) +static int jfs_mkdir(struct user_namespace *mnt_userns, struct inode *dip, + struct dentry *dentry, umode_t mode) { int rc = 0; tid_t tid; /* transaction id */ @@ -868,8 +869,8 @@ static int jfs_link(struct dentry *old_dentry, * an intermediate result whose length exceeds PATH_MAX [XPG4.2] */ -static int jfs_symlink(struct inode *dip, struct dentry *dentry, - const char *name) +static int jfs_symlink(struct user_namespace *mnt_userns, struct inode *dip, + struct dentry *dentry, const char *name) { int rc; tid_t tid; @@ -1058,9 +1059,9 @@ static int jfs_symlink(struct inode *dip, struct dentry *dentry, * * FUNCTION: rename a file or directory */ -static int jfs_rename(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry, - unsigned int flags) +static int jfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, + struct dentry *old_dentry, struct inode *new_dir, + struct dentry *new_dentry, unsigned int flags) { struct btstack btstack; ino_t ino; @@ -1344,8 +1345,8 @@ static int jfs_rename(struct inode *old_dir, struct dentry *old_dentry, * * FUNCTION: Create a special file (device) */ -static int jfs_mknod(struct inode *dir, struct dentry *dentry, - umode_t mode, dev_t rdev) +static int jfs_mknod(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, dev_t rdev) { struct jfs_inode_info *jfs_ip; struct btstack btstack; diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 7a53eed69fef..7e0e62deab53 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -1110,7 +1110,8 @@ static struct dentry *kernfs_iop_lookup(struct inode *dir, return ret; } -static int kernfs_iop_mkdir(struct inode *dir, struct dentry *dentry, +static int kernfs_iop_mkdir(struct user_namespace *mnt_userns, + struct inode *dir, struct dentry *dentry, umode_t mode) { struct kernfs_node *parent = dir->i_private; @@ -1147,7 +1148,8 @@ static int kernfs_iop_rmdir(struct inode *dir, struct dentry *dentry) return ret; } -static int kernfs_iop_rename(struct inode *old_dir, struct dentry *old_dentry, +static int kernfs_iop_rename(struct user_namespace *mnt_userns, + struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index 032d3d7546d8..d73950fc3d57 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -112,7 +112,8 @@ int kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr) return ret; } -int kernfs_iop_setattr(struct dentry *dentry, struct iattr *iattr) +int kernfs_iop_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *iattr) { struct inode *inode = d_inode(dentry); struct kernfs_node *kn = inode->i_private; @@ -183,7 +184,8 @@ static void kernfs_refresh_inode(struct kernfs_node *kn, struct inode *inode) set_nlink(inode, kn->dir.subdirs + 2); } -int kernfs_iop_getattr(const struct path *path, struct kstat *stat, +int kernfs_iop_getattr(struct user_namespace *mnt_userns, + const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); @@ -272,7 +274,8 @@ void kernfs_evict_inode(struct inode *inode) kernfs_put(kn); } -int kernfs_iop_permission(struct inode *inode, int mask) +int kernfs_iop_permission(struct user_namespace *mnt_userns, + struct inode *inode, int mask) { struct kernfs_node *kn; diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h index 7ee97ef59184..ccc3b44f6306 100644 --- a/fs/kernfs/kernfs-internal.h +++ b/fs/kernfs/kernfs-internal.h @@ -89,9 +89,12 @@ extern struct kmem_cache *kernfs_node_cache, *kernfs_iattrs_cache; */ extern const struct xattr_handler *kernfs_xattr_handlers[]; void kernfs_evict_inode(struct inode *inode); -int kernfs_iop_permission(struct inode *inode, int mask); -int kernfs_iop_setattr(struct dentry *dentry, struct iattr *iattr); -int kernfs_iop_getattr(const struct path *path, struct kstat *stat, +int kernfs_iop_permission(struct user_namespace *mnt_userns, + struct inode *inode, int mask); +int kernfs_iop_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *iattr); +int kernfs_iop_getattr(struct user_namespace *mnt_userns, + const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags); ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size); int __kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr); diff --git a/fs/libfs.c b/fs/libfs.c index 508e9ea8e6f3..967aefda6ee3 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -27,8 +27,9 @@ #include "internal.h" -int simple_getattr(const struct path *path, struct kstat *stat, - u32 request_mask, unsigned int query_flags) +int simple_getattr(struct user_namespace *mnt_userns, const struct path *path, + struct kstat *stat, u32 request_mask, + unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); generic_fillattr(&init_user_ns, inode, stat); @@ -447,9 +448,9 @@ int simple_rmdir(struct inode *dir, struct dentry *dentry) } EXPORT_SYMBOL(simple_rmdir); -int simple_rename(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry, - unsigned int flags) +int simple_rename(struct user_namespace *mnt_userns, struct inode *old_dir, + struct dentry *old_dentry, struct inode *new_dir, + struct dentry *new_dentry, unsigned int flags) { struct inode *inode = d_inode(old_dentry); int they_are_dirs = d_is_dir(old_dentry); @@ -492,18 +493,19 @@ EXPORT_SYMBOL(simple_rename); * on simple regular filesystems. Anything that needs to change on-disk * or wire state on size changes needs its own setattr method. */ -int simple_setattr(struct dentry *dentry, struct iattr *iattr) +int simple_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *iattr) { struct inode *inode = d_inode(dentry); int error; - error = setattr_prepare(&init_user_ns, dentry, iattr); + error = setattr_prepare(mnt_userns, dentry, iattr); if (error) return error; if (iattr->ia_valid & ATTR_SIZE) truncate_setsize(inode, iattr->ia_size); - setattr_copy(&init_user_ns, inode, iattr); + setattr_copy(mnt_userns, inode, iattr); mark_inode_dirty(inode); return 0; } @@ -1300,7 +1302,8 @@ static struct dentry *empty_dir_lookup(struct inode *dir, struct dentry *dentry, return ERR_PTR(-ENOENT); } -static int empty_dir_getattr(const struct path *path, struct kstat *stat, +static int empty_dir_getattr(struct user_namespace *mnt_userns, + const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); @@ -1308,7 +1311,8 @@ static int empty_dir_getattr(const struct path *path, struct kstat *stat, return 0; } -static int empty_dir_setattr(struct dentry *dentry, struct iattr *attr) +static int empty_dir_setattr(struct user_namespace *mnt_userns, + struct dentry *dentry, struct iattr *attr) { return -EPERM; } @@ -1318,14 +1322,9 @@ static ssize_t empty_dir_listxattr(struct dentry *dentry, char *list, size_t siz return -EOPNOTSUPP; } -static int empty_dir_permission(struct inode *inode, int mask) -{ - return generic_permission(&init_user_ns, inode, mask); -} - static const struct inode_operations empty_dir_inode_operations = { .lookup = empty_dir_lookup, - .permission = empty_dir_permission, + .permission = generic_permission, .setattr = empty_dir_setattr, .getattr = empty_dir_getattr, .listxattr = empty_dir_listxattr, diff --git a/fs/minix/file.c b/fs/minix/file.c index f07acd268577..6a7bd2d9eec0 100644 --- a/fs/minix/file.c +++ b/fs/minix/file.c @@ -22,7 +22,8 @@ const struct file_operations minix_file_operations = { .splice_read = generic_file_splice_read, }; -static int minix_setattr(struct dentry *dentry, struct iattr *attr) +static int minix_setattr(struct user_namespace *mnt_userns, + struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); int error; diff --git a/fs/minix/inode.c b/fs/minix/inode.c index 91c81d2fc90d..a532a99bbe81 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -652,8 +652,8 @@ static int minix_write_inode(struct inode *inode, struct writeback_control *wbc) return err; } -int minix_getattr(const struct path *path, struct kstat *stat, - u32 request_mask, unsigned int flags) +int minix_getattr(struct user_namespace *mnt_userns, const struct path *path, + struct kstat *stat, u32 request_mask, unsigned int flags) { struct super_block *sb = path->dentry->d_sb; struct inode *inode = d_inode(path->dentry); diff --git a/fs/minix/minix.h b/fs/minix/minix.h index 168d45d3de73..202173368025 100644 --- a/fs/minix/minix.h +++ b/fs/minix/minix.h @@ -51,7 +51,8 @@ extern unsigned long minix_count_free_inodes(struct super_block *sb); extern int minix_new_block(struct inode * inode); extern void minix_free_block(struct inode *inode, unsigned long block); extern unsigned long minix_count_free_blocks(struct super_block *sb); -extern int minix_getattr(const struct path *, struct kstat *, u32, unsigned int); +extern int minix_getattr(struct user_namespace *, const struct path *, + struct kstat *, u32, unsigned int); extern int minix_prepare_chunk(struct page *page, loff_t pos, unsigned len); extern void V1_minix_truncate(struct inode *); diff --git a/fs/minix/namei.c b/fs/minix/namei.c index 1a6084d2b02e..937fa5fae2b8 100644 --- a/fs/minix/namei.c +++ b/fs/minix/namei.c @@ -33,7 +33,8 @@ static struct dentry *minix_lookup(struct inode * dir, struct dentry *dentry, un return d_splice_alias(inode, dentry); } -static int minix_mknod(struct inode * dir, struct dentry *dentry, umode_t mode, dev_t rdev) +static int minix_mknod(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, dev_t rdev) { int error; struct inode *inode; @@ -51,7 +52,8 @@ static int minix_mknod(struct inode * dir, struct dentry *dentry, umode_t mode, return error; } -static int minix_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) +static int minix_tmpfile(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { int error; struct inode *inode = minix_new_inode(dir, mode, &error); @@ -63,14 +65,14 @@ static int minix_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) return error; } -static int minix_create(struct inode *dir, struct dentry *dentry, umode_t mode, - bool excl) +static int minix_create(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, bool excl) { - return minix_mknod(dir, dentry, mode, 0); + return minix_mknod(mnt_userns, dir, dentry, mode, 0); } -static int minix_symlink(struct inode * dir, struct dentry *dentry, - const char * symname) +static int minix_symlink(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, const char *symname) { int err = -ENAMETOOLONG; int i = strlen(symname)+1; @@ -109,7 +111,8 @@ static int minix_link(struct dentry * old_dentry, struct inode * dir, return add_nondir(dentry, inode); } -static int minix_mkdir(struct inode * dir, struct dentry *dentry, umode_t mode) +static int minix_mkdir(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct inode * inode; int err; @@ -181,8 +184,9 @@ static int minix_rmdir(struct inode * dir, struct dentry *dentry) return err; } -static int minix_rename(struct inode * old_dir, struct dentry *old_dentry, - struct inode * new_dir, struct dentry *new_dentry, +static int minix_rename(struct user_namespace *mnt_userns, + struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { struct inode * old_inode = d_inode(old_dentry); diff --git a/fs/namei.c b/fs/namei.c index c8c083daf368..d9ceb75ac169 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -443,7 +443,7 @@ static inline int do_inode_permission(struct user_namespace *mnt_userns, { if (unlikely(!(inode->i_opflags & IOP_FASTPERM))) { if (likely(inode->i_op->permission)) - return inode->i_op->permission(inode, mask); + return inode->i_op->permission(mnt_userns, inode, mask); /* This gets set once for the inode lifetime */ spin_lock(&inode->i_lock); @@ -2199,11 +2199,13 @@ static int link_path_walk(const char *name, struct nameidata *nd) /* At this point we know we have a real path component. */ for(;;) { + struct user_namespace *mnt_userns; const char *link; u64 hash_len; int type; - err = may_lookup(&init_user_ns, nd); + mnt_userns = mnt_user_ns(nd->path.mnt); + err = may_lookup(mnt_userns, nd); if (err) return err; @@ -2251,7 +2253,7 @@ static int link_path_walk(const char *name, struct nameidata *nd) OK: /* pathname or trailing symlink, done */ if (!depth) { - nd->dir_uid = i_uid_into_mnt(&init_user_ns, nd->inode); + nd->dir_uid = i_uid_into_mnt(mnt_userns, nd->inode); nd->dir_mode = nd->inode->i_mode; nd->flags &= ~LOOKUP_PARENT; return 0; @@ -2904,7 +2906,7 @@ int vfs_create(struct user_namespace *mnt_userns, struct inode *dir, error = security_inode_create(dir, dentry, mode); if (error) return error; - error = dir->i_op->create(dir, dentry, mode, want_excl); + error = dir->i_op->create(mnt_userns, dir, dentry, mode, want_excl); if (!error) fsnotify_create(dir, dentry); return error; @@ -2995,7 +2997,7 @@ static int may_open(struct user_namespace *mnt_userns, const struct path *path, return 0; } -static int handle_truncate(struct file *filp) +static int handle_truncate(struct user_namespace *mnt_userns, struct file *filp) { const struct path *path = &filp->f_path; struct inode *inode = path->dentry->d_inode; @@ -3009,7 +3011,7 @@ static int handle_truncate(struct file *filp) if (!error) error = security_path_truncate(path); if (!error) { - error = do_truncate(&init_user_ns, path->dentry, 0, + error = do_truncate(mnt_userns, path->dentry, 0, ATTR_MTIME|ATTR_CTIME|ATTR_OPEN, filp); } @@ -3118,6 +3120,7 @@ static struct dentry *lookup_open(struct nameidata *nd, struct file *file, const struct open_flags *op, bool got_write) { + struct user_namespace *mnt_userns; struct dentry *dir = nd->path.dentry; struct inode *dir_inode = dir->d_inode; int open_flag = op->open_flag; @@ -3165,13 +3168,14 @@ static struct dentry *lookup_open(struct nameidata *nd, struct file *file, */ if (unlikely(!got_write)) open_flag &= ~O_TRUNC; + mnt_userns = mnt_user_ns(nd->path.mnt); if (open_flag & O_CREAT) { if (open_flag & O_EXCL) open_flag &= ~O_TRUNC; if (!IS_POSIXACL(dir->d_inode)) mode &= ~current_umask(); if (likely(got_write)) - create_error = may_o_create(&init_user_ns, &nd->path, + create_error = may_o_create(mnt_userns, &nd->path, dentry, mode); else create_error = -EROFS; @@ -3207,8 +3211,9 @@ static struct dentry *lookup_open(struct nameidata *nd, struct file *file, error = -EACCES; goto out_dput; } - error = dir_inode->i_op->create(dir_inode, dentry, mode, - open_flag & O_EXCL); + + error = dir_inode->i_op->create(mnt_userns, dir_inode, dentry, + mode, open_flag & O_EXCL); if (error) goto out_dput; } @@ -3316,6 +3321,7 @@ finish_lookup: static int do_open(struct nameidata *nd, struct file *file, const struct open_flags *op) { + struct user_namespace *mnt_userns; int open_flag = op->open_flag; bool do_truncate; int acc_mode; @@ -3328,12 +3334,13 @@ static int do_open(struct nameidata *nd, } if (!(file->f_mode & FMODE_CREATED)) audit_inode(nd->name, nd->path.dentry, 0); + mnt_userns = mnt_user_ns(nd->path.mnt); if (open_flag & O_CREAT) { if ((open_flag & O_EXCL) && !(file->f_mode & FMODE_CREATED)) return -EEXIST; if (d_is_dir(nd->path.dentry)) return -EISDIR; - error = may_create_in_sticky(&init_user_ns, nd, + error = may_create_in_sticky(mnt_userns, nd, d_backing_inode(nd->path.dentry)); if (unlikely(error)) return error; @@ -3353,13 +3360,13 @@ static int do_open(struct nameidata *nd, return error; do_truncate = true; } - error = may_open(&init_user_ns, &nd->path, acc_mode, open_flag); + error = may_open(mnt_userns, &nd->path, acc_mode, open_flag); if (!error && !(file->f_mode & FMODE_OPENED)) error = vfs_open(&nd->path, file); if (!error) error = ima_file_check(file, op->acc_mode); if (!error && do_truncate) - error = handle_truncate(file); + error = handle_truncate(mnt_userns, file); if (unlikely(error > 0)) { WARN_ON(1); error = -EINVAL; @@ -3403,7 +3410,7 @@ struct dentry *vfs_tmpfile(struct user_namespace *mnt_userns, child = d_alloc(dentry, &slash_name); if (unlikely(!child)) goto out_err; - error = dir->i_op->tmpfile(dir, child, mode); + error = dir->i_op->tmpfile(mnt_userns, dir, child, mode); if (error) goto out_err; error = -ENOENT; @@ -3446,7 +3453,7 @@ static int do_tmpfile(struct nameidata *nd, unsigned flags, path.dentry = child; audit_inode(nd->name, child, 0); /* Don't check for other permissions, the inode was just created */ - error = may_open(&init_user_ns, &path, 0, op->open_flag); + error = may_open(mnt_userns, &path, 0, op->open_flag); if (error) goto out2; file->f_path.mnt = path.mnt; @@ -3690,7 +3697,7 @@ int vfs_mknod(struct user_namespace *mnt_userns, struct inode *dir, if (error) return error; - error = dir->i_op->mknod(dir, dentry, mode, dev); + error = dir->i_op->mknod(mnt_userns, dir, dentry, mode, dev); if (!error) fsnotify_create(dir, dentry); return error; @@ -3809,7 +3816,7 @@ int vfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, if (max_links && dir->i_nlink >= max_links) return -EMLINK; - error = dir->i_op->mkdir(dir, dentry, mode); + error = dir->i_op->mkdir(mnt_userns, dir, dentry, mode); if (!error) fsnotify_mkdir(dir, dentry); return error; @@ -3834,7 +3841,8 @@ retry: if (!error) { struct user_namespace *mnt_userns; mnt_userns = mnt_user_ns(path.mnt); - error = vfs_mkdir(mnt_userns, path.dentry->d_inode, dentry, mode); + error = vfs_mkdir(mnt_userns, path.dentry->d_inode, dentry, + mode); } done_path_create(&path, dentry); if (retry_estale(error, lookup_flags)) { @@ -4087,7 +4095,8 @@ retry_deleg: if (error) goto exit2; mnt_userns = mnt_user_ns(path.mnt); - error = vfs_unlink(mnt_userns, path.dentry->d_inode, dentry, &delegated_inode); + error = vfs_unlink(mnt_userns, path.dentry->d_inode, dentry, + &delegated_inode); exit2: dput(dentry); } @@ -4166,7 +4175,7 @@ int vfs_symlink(struct user_namespace *mnt_userns, struct inode *dir, if (error) return error; - error = dir->i_op->symlink(dir, dentry, oldname); + error = dir->i_op->symlink(mnt_userns, dir, dentry, oldname); if (!error) fsnotify_create(dir, dentry); return error; @@ -4357,13 +4366,13 @@ retry: error = -EXDEV; if (old_path.mnt != new_path.mnt) goto out_dput; - error = may_linkat(&init_user_ns, &old_path); + mnt_userns = mnt_user_ns(new_path.mnt); + error = may_linkat(mnt_userns, &old_path); if (unlikely(error)) goto out_dput; error = security_path_link(old_path.dentry, &new_path, new_dentry); if (error) goto out_dput; - mnt_userns = mnt_user_ns(new_path.mnt); error = vfs_link(old_path.dentry, mnt_userns, new_path.dentry->d_inode, new_dentry, &delegated_inode); out_dput: @@ -4542,8 +4551,8 @@ int vfs_rename(struct renamedata *rd) if (error) goto out; } - error = old_dir->i_op->rename(old_dir, old_dentry, - new_dir, new_dentry, flags); + error = old_dir->i_op->rename(rd->new_mnt_userns, old_dir, old_dentry, + new_dir, new_dentry, flags); if (error) goto out; diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 727e01a84503..19a9f434442f 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -2095,8 +2095,8 @@ EXPORT_SYMBOL_GPL(nfs_instantiate); * that the operation succeeded on the server, but an error in the * reply path made it appear to have failed. */ -int nfs_create(struct inode *dir, struct dentry *dentry, - umode_t mode, bool excl) +int nfs_create(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, bool excl) { struct iattr attr; int open_flags = excl ? O_CREAT | O_EXCL : O_CREAT; @@ -2124,7 +2124,8 @@ EXPORT_SYMBOL_GPL(nfs_create); * See comments for nfs_proc_create regarding failed operations. */ int -nfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) +nfs_mknod(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, dev_t rdev) { struct iattr attr; int status; @@ -2150,7 +2151,8 @@ EXPORT_SYMBOL_GPL(nfs_mknod); /* * See comments for nfs_proc_create regarding failed operations. */ -int nfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +int nfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct iattr attr; int error; @@ -2295,7 +2297,8 @@ EXPORT_SYMBOL_GPL(nfs_unlink); * now have a new file handle and can instantiate an in-core NFS inode * and move the raw page into its mapping. */ -int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname) +int nfs_symlink(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, const char *symname) { struct page *page; char *kaddr; @@ -2398,9 +2401,9 @@ EXPORT_SYMBOL_GPL(nfs_link); * If these conditions are met, we can drop the dentries before doing * the rename. */ -int nfs_rename(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry, - unsigned int flags) +int nfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, + struct dentry *old_dentry, struct inode *new_dir, + struct dentry *new_dentry, unsigned int flags) { struct inode *old_inode = d_inode(old_dentry); struct inode *new_inode = d_inode(new_dentry); @@ -2939,7 +2942,9 @@ static int nfs_execute_ok(struct inode *inode, int mask) return ret; } -int nfs_permission(struct inode *inode, int mask) +int nfs_permission(struct user_namespace *mnt_userns, + struct inode *inode, + int mask) { const struct cred *cred = current_cred(); int res = 0; diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index cab123ec1664..447e95974386 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -594,7 +594,8 @@ EXPORT_SYMBOL_GPL(nfs_fhget); #define NFS_VALID_ATTRS (ATTR_MODE|ATTR_UID|ATTR_GID|ATTR_SIZE|ATTR_ATIME|ATTR_ATIME_SET|ATTR_MTIME|ATTR_MTIME_SET|ATTR_FILE|ATTR_OPEN) int -nfs_setattr(struct dentry *dentry, struct iattr *attr) +nfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *attr) { struct inode *inode = d_inode(dentry); struct nfs_fattr *fattr; @@ -787,8 +788,8 @@ static bool nfs_need_revalidate_inode(struct inode *inode) return false; } -int nfs_getattr(const struct path *path, struct kstat *stat, - u32 request_mask, unsigned int query_flags) +int nfs_getattr(struct user_namespace *mnt_userns, const struct path *path, + struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); struct nfs_server *server = NFS_SERVER(inode); diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 62d3189745cd..25fb43b69e5a 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -378,14 +378,18 @@ extern unsigned long nfs_access_cache_count(struct shrinker *shrink, extern unsigned long nfs_access_cache_scan(struct shrinker *shrink, struct shrink_control *sc); struct dentry *nfs_lookup(struct inode *, struct dentry *, unsigned int); -int nfs_create(struct inode *, struct dentry *, umode_t, bool); -int nfs_mkdir(struct inode *, struct dentry *, umode_t); +int nfs_create(struct user_namespace *, struct inode *, struct dentry *, + umode_t, bool); +int nfs_mkdir(struct user_namespace *, struct inode *, struct dentry *, + umode_t); int nfs_rmdir(struct inode *, struct dentry *); int nfs_unlink(struct inode *, struct dentry *); -int nfs_symlink(struct inode *, struct dentry *, const char *); +int nfs_symlink(struct user_namespace *, struct inode *, struct dentry *, + const char *); int nfs_link(struct dentry *, struct inode *, struct dentry *); -int nfs_mknod(struct inode *, struct dentry *, umode_t, dev_t); -int nfs_rename(struct inode *, struct dentry *, +int nfs_mknod(struct user_namespace *, struct inode *, struct dentry *, umode_t, + dev_t); +int nfs_rename(struct user_namespace *, struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); /* file.c */ diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c index 55fc711e368b..93e60e921f92 100644 --- a/fs/nfs/namespace.c +++ b/fs/nfs/namespace.c @@ -208,20 +208,23 @@ out_fc: } static int -nfs_namespace_getattr(const struct path *path, struct kstat *stat, - u32 request_mask, unsigned int query_flags) +nfs_namespace_getattr(struct user_namespace *mnt_userns, + const struct path *path, struct kstat *stat, + u32 request_mask, unsigned int query_flags) { if (NFS_FH(d_inode(path->dentry))->size != 0) - return nfs_getattr(path, stat, request_mask, query_flags); + return nfs_getattr(mnt_userns, path, stat, request_mask, + query_flags); generic_fillattr(&init_user_ns, d_inode(path->dentry), stat); return 0; } static int -nfs_namespace_setattr(struct dentry *dentry, struct iattr *attr) +nfs_namespace_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *attr) { if (NFS_FH(d_inode(dentry))->size != 0) - return nfs_setattr(dentry, attr); + return nfs_setattr(mnt_userns, dentry, attr); return -EACCES; } diff --git a/fs/nfs/nfs3_fs.h b/fs/nfs/nfs3_fs.h index 1b950b66b3bb..c8a192802dda 100644 --- a/fs/nfs/nfs3_fs.h +++ b/fs/nfs/nfs3_fs.h @@ -12,7 +12,8 @@ */ #ifdef CONFIG_NFS_V3_ACL extern struct posix_acl *nfs3_get_acl(struct inode *inode, int type); -extern int nfs3_set_acl(struct inode *inode, struct posix_acl *acl, int type); +extern int nfs3_set_acl(struct user_namespace *mnt_userns, struct inode *inode, + struct posix_acl *acl, int type); extern int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl, struct posix_acl *dfacl); extern ssize_t nfs3_listxattr(struct dentry *, char *, size_t); diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c index c6c863382f37..5604e807fc01 100644 --- a/fs/nfs/nfs3acl.c +++ b/fs/nfs/nfs3acl.c @@ -251,7 +251,8 @@ int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl, } -int nfs3_set_acl(struct inode *inode, struct posix_acl *acl, int type) +int nfs3_set_acl(struct user_namespace *mnt_userns, struct inode *inode, + struct posix_acl *acl, int type) { struct posix_acl *orig = acl, *dfacl = NULL, *alloc; int status; diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 8aad3c48092a..2e8eb263cf0f 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -805,7 +805,8 @@ void nilfs_evict_inode(struct inode *inode) */ } -int nilfs_setattr(struct dentry *dentry, struct iattr *iattr) +int nilfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *iattr) { struct nilfs_transaction_info ti; struct inode *inode = d_inode(dentry); @@ -843,7 +844,8 @@ out_err: return err; } -int nilfs_permission(struct inode *inode, int mask) +int nilfs_permission(struct user_namespace *mnt_userns, struct inode *inode, + int mask) { struct nilfs_root *root = NILFS_I(inode)->i_root; diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c index a6ec7961d4f5..ecace5f96a95 100644 --- a/fs/nilfs2/namei.c +++ b/fs/nilfs2/namei.c @@ -72,8 +72,8 @@ nilfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) * If the create succeeds, we fill in the inode information * with d_instantiate(). */ -static int nilfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - bool excl) +static int nilfs_create(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, bool excl) { struct inode *inode; struct nilfs_transaction_info ti; @@ -100,7 +100,8 @@ static int nilfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, } static int -nilfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) +nilfs_mknod(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, dev_t rdev) { struct inode *inode; struct nilfs_transaction_info ti; @@ -124,8 +125,8 @@ nilfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) return err; } -static int nilfs_symlink(struct inode *dir, struct dentry *dentry, - const char *symname) +static int nilfs_symlink(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, const char *symname) { struct nilfs_transaction_info ti; struct super_block *sb = dir->i_sb; @@ -201,7 +202,8 @@ static int nilfs_link(struct dentry *old_dentry, struct inode *dir, return err; } -static int nilfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +static int nilfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct inode *inode; struct nilfs_transaction_info ti; @@ -338,8 +340,9 @@ static int nilfs_rmdir(struct inode *dir, struct dentry *dentry) return err; } -static int nilfs_rename(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry, +static int nilfs_rename(struct user_namespace *mnt_userns, + struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { struct inode *old_inode = d_inode(old_dentry); diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h index f8450ee3fd06..c4a45a081ade 100644 --- a/fs/nilfs2/nilfs.h +++ b/fs/nilfs2/nilfs.h @@ -267,9 +267,11 @@ extern struct inode *nilfs_iget_for_gc(struct super_block *sb, extern void nilfs_update_inode(struct inode *, struct buffer_head *, int); extern void nilfs_truncate(struct inode *); extern void nilfs_evict_inode(struct inode *); -extern int nilfs_setattr(struct dentry *, struct iattr *); +extern int nilfs_setattr(struct user_namespace *, struct dentry *, + struct iattr *); extern void nilfs_write_failed(struct address_space *mapping, loff_t to); -int nilfs_permission(struct inode *inode, int mask); +int nilfs_permission(struct user_namespace *mnt_userns, struct inode *inode, + int mask); int nilfs_load_inode_block(struct inode *inode, struct buffer_head **pbh); extern int nilfs_inode_dirty(struct inode *); int nilfs_set_file_dirty(struct inode *inode, unsigned int nr_dirty); diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c index 38f4cf1d4497..4435dbbc0b63 100644 --- a/fs/ntfs/inode.c +++ b/fs/ntfs/inode.c @@ -2848,6 +2848,7 @@ void ntfs_truncate_vfs(struct inode *vi) { /** * ntfs_setattr - called from notify_change() when an attribute is being changed + * @mnt_userns: user namespace of the mount the inode was found from * @dentry: dentry whose attributes to change * @attr: structure describing the attributes and the changes * @@ -2860,7 +2861,8 @@ void ntfs_truncate_vfs(struct inode *vi) { * * Called with ->i_mutex held. */ -int ntfs_setattr(struct dentry *dentry, struct iattr *attr) +int ntfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *attr) { struct inode *vi = d_inode(dentry); int err; diff --git a/fs/ntfs/inode.h b/fs/ntfs/inode.h index 363e4e820673..6f78ee00f57f 100644 --- a/fs/ntfs/inode.h +++ b/fs/ntfs/inode.h @@ -289,7 +289,8 @@ extern int ntfs_show_options(struct seq_file *sf, struct dentry *root); extern int ntfs_truncate(struct inode *vi); extern void ntfs_truncate_vfs(struct inode *vi); -extern int ntfs_setattr(struct dentry *dentry, struct iattr *attr); +extern int ntfs_setattr(struct user_namespace *mnt_userns, + struct dentry *dentry, struct iattr *attr); extern int __ntfs_write_inode(struct inode *vi, int sync); diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c index 990756cee4bd..5259badabb56 100644 --- a/fs/ocfs2/acl.c +++ b/fs/ocfs2/acl.c @@ -262,7 +262,8 @@ static int ocfs2_set_acl(handle_t *handle, return ret; } -int ocfs2_iop_set_acl(struct inode *inode, struct posix_acl *acl, int type) +int ocfs2_iop_set_acl(struct user_namespace *mnt_userns, struct inode *inode, + struct posix_acl *acl, int type) { struct buffer_head *bh = NULL; int status, had_lock; diff --git a/fs/ocfs2/acl.h b/fs/ocfs2/acl.h index 127b13432146..4e86450917b2 100644 --- a/fs/ocfs2/acl.h +++ b/fs/ocfs2/acl.h @@ -19,7 +19,8 @@ struct ocfs2_acl_entry { }; struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, int type); -int ocfs2_iop_set_acl(struct inode *inode, struct posix_acl *acl, int type); +int ocfs2_iop_set_acl(struct user_namespace *mnt_userns, struct inode *inode, + struct posix_acl *acl, int type); extern int ocfs2_acl_chmod(struct inode *, struct buffer_head *); extern int ocfs2_init_acl(handle_t *, struct inode *, struct inode *, struct buffer_head *, struct buffer_head *, diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c index 9fa66cd1f622..b2870f1a31df 100644 --- a/fs/ocfs2/dlmfs/dlmfs.c +++ b/fs/ocfs2/dlmfs/dlmfs.c @@ -190,7 +190,8 @@ static int dlmfs_file_release(struct inode *inode, * We do ->setattr() just to override size changes. Our size is the size * of the LVB and nothing else. */ -static int dlmfs_file_setattr(struct dentry *dentry, struct iattr *attr) +static int dlmfs_file_setattr(struct user_namespace *mnt_userns, + struct dentry *dentry, struct iattr *attr) { int error; struct inode *inode = d_inode(dentry); @@ -395,7 +396,8 @@ static struct inode *dlmfs_get_inode(struct inode *parent, * File creation. Allocate an inode, and we're done.. */ /* SMP-safe */ -static int dlmfs_mkdir(struct inode * dir, +static int dlmfs_mkdir(struct user_namespace * mnt_userns, + struct inode * dir, struct dentry * dentry, umode_t mode) { @@ -443,7 +445,8 @@ bail: return status; } -static int dlmfs_create(struct inode *dir, +static int dlmfs_create(struct user_namespace *mnt_userns, + struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index a070d4c9b6ed..e3039d973acd 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1112,7 +1112,8 @@ out: return ret; } -int ocfs2_setattr(struct dentry *dentry, struct iattr *attr) +int ocfs2_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *attr) { int status = 0, size_change; int inode_locked = 0; @@ -1298,8 +1299,8 @@ bail: return status; } -int ocfs2_getattr(const struct path *path, struct kstat *stat, - u32 request_mask, unsigned int flags) +int ocfs2_getattr(struct user_namespace *mnt_userns, const struct path *path, + struct kstat *stat, u32 request_mask, unsigned int flags) { struct inode *inode = d_inode(path->dentry); struct super_block *sb = path->dentry->d_sb; @@ -1330,7 +1331,8 @@ bail: return err; } -int ocfs2_permission(struct inode *inode, int mask) +int ocfs2_permission(struct user_namespace *mnt_userns, struct inode *inode, + int mask) { int ret, had_lock; struct ocfs2_lock_holder oh; diff --git a/fs/ocfs2/file.h b/fs/ocfs2/file.h index 4832cbceba5b..8536cec5f122 100644 --- a/fs/ocfs2/file.h +++ b/fs/ocfs2/file.h @@ -51,10 +51,13 @@ int ocfs2_extend_no_holes(struct inode *inode, struct buffer_head *di_bh, u64 new_i_size, u64 zero_to); int ocfs2_zero_extend(struct inode *inode, struct buffer_head *di_bh, loff_t zero_to); -int ocfs2_setattr(struct dentry *dentry, struct iattr *attr); -int ocfs2_getattr(const struct path *path, struct kstat *stat, - u32 request_mask, unsigned int flags); -int ocfs2_permission(struct inode *inode, int mask); +int ocfs2_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *attr); +int ocfs2_getattr(struct user_namespace *mnt_userns, const struct path *path, + struct kstat *stat, u32 request_mask, unsigned int flags); +int ocfs2_permission(struct user_namespace *mnt_userns, + struct inode *inode, + int mask); int ocfs2_should_update_atime(struct inode *inode, struct vfsmount *vfsmnt); diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index 908b79e1082b..3abdd36da2e2 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -221,7 +221,8 @@ static void ocfs2_cleanup_add_entry_failure(struct ocfs2_super *osb, iput(inode); } -static int ocfs2_mknod(struct inode *dir, +static int ocfs2_mknod(struct user_namespace *mnt_userns, + struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) @@ -645,7 +646,8 @@ static int ocfs2_mknod_locked(struct ocfs2_super *osb, return status; } -static int ocfs2_mkdir(struct inode *dir, +static int ocfs2_mkdir(struct user_namespace *mnt_userns, + struct inode *dir, struct dentry *dentry, umode_t mode) { @@ -653,14 +655,15 @@ static int ocfs2_mkdir(struct inode *dir, trace_ocfs2_mkdir(dir, dentry, dentry->d_name.len, dentry->d_name.name, OCFS2_I(dir)->ip_blkno, mode); - ret = ocfs2_mknod(dir, dentry, mode | S_IFDIR, 0); + ret = ocfs2_mknod(&init_user_ns, dir, dentry, mode | S_IFDIR, 0); if (ret) mlog_errno(ret); return ret; } -static int ocfs2_create(struct inode *dir, +static int ocfs2_create(struct user_namespace *mnt_userns, + struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) @@ -669,7 +672,7 @@ static int ocfs2_create(struct inode *dir, trace_ocfs2_create(dir, dentry, dentry->d_name.len, dentry->d_name.name, (unsigned long long)OCFS2_I(dir)->ip_blkno, mode); - ret = ocfs2_mknod(dir, dentry, mode | S_IFREG, 0); + ret = ocfs2_mknod(&init_user_ns, dir, dentry, mode | S_IFREG, 0); if (ret) mlog_errno(ret); @@ -1195,7 +1198,8 @@ static void ocfs2_double_unlock(struct inode *inode1, struct inode *inode2) ocfs2_inode_unlock(inode2, 1); } -static int ocfs2_rename(struct inode *old_dir, +static int ocfs2_rename(struct user_namespace *mnt_userns, + struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, @@ -1784,7 +1788,8 @@ bail: return status; } -static int ocfs2_symlink(struct inode *dir, +static int ocfs2_symlink(struct user_namespace *mnt_userns, + struct inode *dir, struct dentry *dentry, const char *symname) { diff --git a/fs/omfs/dir.c b/fs/omfs/dir.c index a0f45651f3b7..c219f91f44e9 100644 --- a/fs/omfs/dir.c +++ b/fs/omfs/dir.c @@ -279,13 +279,14 @@ out_free_inode: return err; } -static int omfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +static int omfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { return omfs_add_node(dir, dentry, mode | S_IFDIR); } -static int omfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - bool excl) +static int omfs_create(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, bool excl) { return omfs_add_node(dir, dentry, mode | S_IFREG); } @@ -369,9 +370,9 @@ static bool omfs_fill_chain(struct inode *dir, struct dir_context *ctx, return true; } -static int omfs_rename(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry, - unsigned int flags) +static int omfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, + struct dentry *old_dentry, struct inode *new_dir, + struct dentry *new_dentry, unsigned int flags) { struct inode *new_inode = d_inode(new_dentry); struct inode *old_inode = d_inode(old_dentry); diff --git a/fs/omfs/file.c b/fs/omfs/file.c index 729339cd7902..11e733aab25d 100644 --- a/fs/omfs/file.c +++ b/fs/omfs/file.c @@ -343,7 +343,8 @@ const struct file_operations omfs_file_operations = { .splice_read = generic_file_splice_read, }; -static int omfs_setattr(struct dentry *dentry, struct iattr *attr) +static int omfs_setattr(struct user_namespace *mnt_userns, + struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); int error; diff --git a/fs/orangefs/acl.c b/fs/orangefs/acl.c index 628921952d16..18852b9ed82b 100644 --- a/fs/orangefs/acl.c +++ b/fs/orangefs/acl.c @@ -116,7 +116,8 @@ out: return error; } -int orangefs_set_acl(struct inode *inode, struct posix_acl *acl, int type) +int orangefs_set_acl(struct user_namespace *mnt_userns, struct inode *inode, + struct posix_acl *acl, int type) { int error; struct iattr iattr; diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c index b94032f77e61..5079cfafa8d7 100644 --- a/fs/orangefs/inode.c +++ b/fs/orangefs/inode.c @@ -871,7 +871,8 @@ out: /* * Change attributes of an object referenced by dentry. */ -int orangefs_setattr(struct dentry *dentry, struct iattr *iattr) +int orangefs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *iattr) { int ret; gossip_debug(GOSSIP_INODE_DEBUG, "__orangefs_setattr: called on %pd\n", @@ -890,8 +891,8 @@ out: /* * Obtain attributes of an object given a dentry */ -int orangefs_getattr(const struct path *path, struct kstat *stat, - u32 request_mask, unsigned int flags) +int orangefs_getattr(struct user_namespace *mnt_userns, const struct path *path, + struct kstat *stat, u32 request_mask, unsigned int flags) { int ret; struct inode *inode = path->dentry->d_inode; @@ -919,7 +920,8 @@ int orangefs_getattr(const struct path *path, struct kstat *stat, return ret; } -int orangefs_permission(struct inode *inode, int mask) +int orangefs_permission(struct user_namespace *mnt_userns, + struct inode *inode, int mask) { int ret; diff --git a/fs/orangefs/namei.c b/fs/orangefs/namei.c index 3e7cf3d0a494..600e8eee541f 100644 --- a/fs/orangefs/namei.c +++ b/fs/orangefs/namei.c @@ -15,7 +15,8 @@ /* * Get a newly allocated inode to go with a negative dentry. */ -static int orangefs_create(struct inode *dir, +static int orangefs_create(struct user_namespace *mnt_userns, + struct inode *dir, struct dentry *dentry, umode_t mode, bool exclusive) @@ -215,7 +216,8 @@ static int orangefs_unlink(struct inode *dir, struct dentry *dentry) return ret; } -static int orangefs_symlink(struct inode *dir, +static int orangefs_symlink(struct user_namespace *mnt_userns, + struct inode *dir, struct dentry *dentry, const char *symname) { @@ -303,7 +305,8 @@ out: return ret; } -static int orangefs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +static int orangefs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct orangefs_inode_s *parent = ORANGEFS_I(dir); struct orangefs_kernel_op_s *new_op; @@ -372,7 +375,8 @@ out: return ret; } -static int orangefs_rename(struct inode *old_dir, +static int orangefs_rename(struct user_namespace *mnt_userns, + struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, diff --git a/fs/orangefs/orangefs-kernel.h b/fs/orangefs/orangefs-kernel.h index e12aeb9623d6..0e6b97682e41 100644 --- a/fs/orangefs/orangefs-kernel.h +++ b/fs/orangefs/orangefs-kernel.h @@ -107,7 +107,9 @@ extern int orangefs_init_acl(struct inode *inode, struct inode *dir); extern const struct xattr_handler *orangefs_xattr_handlers[]; extern struct posix_acl *orangefs_get_acl(struct inode *inode, int type); -extern int orangefs_set_acl(struct inode *inode, struct posix_acl *acl, int type); +extern int orangefs_set_acl(struct user_namespace *mnt_userns, + struct inode *inode, struct posix_acl *acl, + int type); /* * orangefs data structures @@ -359,12 +361,13 @@ struct inode *orangefs_new_inode(struct super_block *sb, struct orangefs_object_kref *ref); int __orangefs_setattr(struct inode *, struct iattr *); -int orangefs_setattr(struct dentry *, struct iattr *); +int orangefs_setattr(struct user_namespace *, struct dentry *, struct iattr *); -int orangefs_getattr(const struct path *path, struct kstat *stat, - u32 request_mask, unsigned int flags); +int orangefs_getattr(struct user_namespace *mnt_userns, const struct path *path, + struct kstat *stat, u32 request_mask, unsigned int flags); -int orangefs_permission(struct inode *inode, int mask); +int orangefs_permission(struct user_namespace *mnt_userns, + struct inode *inode, int mask); int orangefs_update_time(struct inode *, struct timespec64 *, int); diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 6904cc2ed7bb..8b3be7342a8c 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -650,19 +650,20 @@ out: return err; } -static int ovl_create(struct inode *dir, struct dentry *dentry, umode_t mode, - bool excl) +static int ovl_create(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, bool excl) { return ovl_create_object(dentry, (mode & 07777) | S_IFREG, 0, NULL); } -static int ovl_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +static int ovl_mkdir(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { return ovl_create_object(dentry, (mode & 07777) | S_IFDIR, 0, NULL); } -static int ovl_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, - dev_t rdev) +static int ovl_mknod(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, dev_t rdev) { /* Don't allow creation of "whiteout" on overlay */ if (S_ISCHR(mode) && rdev == WHITEOUT_DEV) @@ -671,8 +672,8 @@ static int ovl_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, return ovl_create_object(dentry, mode, rdev, NULL); } -static int ovl_symlink(struct inode *dir, struct dentry *dentry, - const char *link) +static int ovl_symlink(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, const char *link) { return ovl_create_object(dentry, S_IFLNK, 0, link); } @@ -1069,9 +1070,9 @@ static int ovl_set_redirect(struct dentry *dentry, bool samedir) return err; } -static int ovl_rename(struct inode *olddir, struct dentry *old, - struct inode *newdir, struct dentry *new, - unsigned int flags) +static int ovl_rename(struct user_namespace *mnt_userns, struct inode *olddir, + struct dentry *old, struct inode *newdir, + struct dentry *new, unsigned int flags) { int err; struct dentry *old_upperdir; diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 023fde466e3a..e78d45dfeaee 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -14,7 +14,8 @@ #include "overlayfs.h" -int ovl_setattr(struct dentry *dentry, struct iattr *attr) +int ovl_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *attr) { int err; bool full_copy_up = false; @@ -154,8 +155,8 @@ static int ovl_map_dev_ino(struct dentry *dentry, struct kstat *stat, int fsid) return 0; } -int ovl_getattr(const struct path *path, struct kstat *stat, - u32 request_mask, unsigned int flags) +int ovl_getattr(struct user_namespace *mnt_userns, const struct path *path, + struct kstat *stat, u32 request_mask, unsigned int flags) { struct dentry *dentry = path->dentry; enum ovl_path_type type; @@ -277,7 +278,8 @@ out: return err; } -int ovl_permission(struct inode *inode, int mask) +int ovl_permission(struct user_namespace *mnt_userns, + struct inode *inode, int mask) { struct inode *upperinode = ovl_inode_upper(inode); struct inode *realinode = upperinode ?: ovl_inode_lower(inode); diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index 5e9eb46e741a..78b9d93a33c9 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -444,10 +444,12 @@ int ovl_set_nlink_lower(struct dentry *dentry); unsigned int ovl_get_nlink(struct ovl_fs *ofs, struct dentry *lowerdentry, struct dentry *upperdentry, unsigned int fallback); -int ovl_setattr(struct dentry *dentry, struct iattr *attr); -int ovl_getattr(const struct path *path, struct kstat *stat, - u32 request_mask, unsigned int flags); -int ovl_permission(struct inode *inode, int mask); +int ovl_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *attr); +int ovl_getattr(struct user_namespace *mnt_userns, const struct path *path, + struct kstat *stat, u32 request_mask, unsigned int flags); +int ovl_permission(struct user_namespace *mnt_userns, struct inode *inode, + int mask); int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char *name, const void *value, size_t size, int flags); int ovl_xattr_get(struct dentry *dentry, struct inode *inode, const char *name, diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 8168ab2dda11..c04612b19054 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -1023,7 +1023,7 @@ ovl_posix_acl_xattr_set(const struct xattr_handler *handler, !capable_wrt_inode_uidgid(&init_user_ns, inode, CAP_FSETID)) { struct iattr iattr = { .ia_valid = ATTR_KILL_SGID }; - err = ovl_setattr(dentry, &iattr); + err = ovl_setattr(&init_user_ns, dentry, &iattr); if (err) return err; } diff --git a/fs/posix_acl.c b/fs/posix_acl.c index d31b60f5d40d..f3309a7edb49 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -593,7 +593,7 @@ int ret = __posix_acl_chmod(&acl, GFP_KERNEL, mode); if (ret) return ret; - ret = inode->i_op->set_acl(inode, acl, ACL_TYPE_ACCESS); + ret = inode->i_op->set_acl(mnt_userns, inode, acl, ACL_TYPE_ACCESS); posix_acl_release(acl); return ret; } @@ -918,7 +918,7 @@ set_posix_acl(struct user_namespace *mnt_userns, struct inode *inode, if (ret) return ret; } - return inode->i_op->set_acl(inode, acl, type); + return inode->i_op->set_acl(mnt_userns, inode, acl, type); } EXPORT_SYMBOL(set_posix_acl); @@ -966,12 +966,13 @@ const struct xattr_handler posix_acl_default_xattr_handler = { }; EXPORT_SYMBOL_GPL(posix_acl_default_xattr_handler); -int simple_set_acl(struct inode *inode, struct posix_acl *acl, int type) +int simple_set_acl(struct user_namespace *mnt_userns, struct inode *inode, + struct posix_acl *acl, int type) { int error; if (type == ACL_TYPE_ACCESS) { - error = posix_acl_update_mode(&init_user_ns, inode, + error = posix_acl_update_mode(mnt_userns, inode, &inode->i_mode, &acl); if (error) return error; diff --git a/fs/proc/base.c b/fs/proc/base.c index d45aa68c1f17..56bf14316122 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -685,7 +685,8 @@ static int proc_fd_access_allowed(struct inode *inode) return allowed; } -int proc_setattr(struct dentry *dentry, struct iattr *attr) +int proc_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *attr) { int error; struct inode *inode = d_inode(dentry); @@ -726,7 +727,8 @@ static bool has_pid_permissions(struct proc_fs_info *fs_info, } -static int proc_pid_permission(struct inode *inode, int mask) +static int proc_pid_permission(struct user_namespace *mnt_userns, + struct inode *inode, int mask) { struct proc_fs_info *fs_info = proc_sb_info(inode->i_sb); struct task_struct *task; @@ -1927,8 +1929,8 @@ out_unlock: return NULL; } -int pid_getattr(const struct path *path, struct kstat *stat, - u32 request_mask, unsigned int query_flags) +int pid_getattr(struct user_namespace *mnt_userns, const struct path *path, + struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); struct proc_fs_info *fs_info = proc_sb_info(inode->i_sb); @@ -3473,7 +3475,8 @@ int proc_pid_readdir(struct file *file, struct dir_context *ctx) * This function makes sure that the node is always accessible for members of * same thread group. */ -static int proc_tid_comm_permission(struct inode *inode, int mask) +static int proc_tid_comm_permission(struct user_namespace *mnt_userns, + struct inode *inode, int mask) { bool is_same_tgroup; struct task_struct *task; @@ -3798,7 +3801,8 @@ static int proc_task_readdir(struct file *file, struct dir_context *ctx) return 0; } -static int proc_task_getattr(const struct path *path, struct kstat *stat, +static int proc_task_getattr(struct user_namespace *mnt_userns, + const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); diff --git a/fs/proc/fd.c b/fs/proc/fd.c index d6e76461e135..07fc4fad2602 100644 --- a/fs/proc/fd.c +++ b/fs/proc/fd.c @@ -276,7 +276,8 @@ static struct dentry *proc_lookupfd(struct inode *dir, struct dentry *dentry, * /proc/pid/fd needs a special permission handler so that a process can still * access /proc/self/fd after it has executed a setuid(). */ -int proc_fd_permission(struct inode *inode, int mask) +int proc_fd_permission(struct user_namespace *mnt_userns, + struct inode *inode, int mask) { struct task_struct *p; int rv; diff --git a/fs/proc/fd.h b/fs/proc/fd.h index f371a602bf58..c5a921a06a0b 100644 --- a/fs/proc/fd.h +++ b/fs/proc/fd.h @@ -10,7 +10,8 @@ extern const struct inode_operations proc_fd_inode_operations; extern const struct file_operations proc_fdinfo_operations; extern const struct inode_operations proc_fdinfo_inode_operations; -extern int proc_fd_permission(struct inode *inode, int mask); +extern int proc_fd_permission(struct user_namespace *mnt_userns, + struct inode *inode, int mask); static inline unsigned int proc_fd(struct inode *inode) { diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 0db96a761149..bc86aa87cc41 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -115,7 +115,8 @@ static bool pde_subdir_insert(struct proc_dir_entry *dir, return true; } -static int proc_notify_change(struct dentry *dentry, struct iattr *iattr) +static int proc_notify_change(struct user_namespace *mnt_userns, + struct dentry *dentry, struct iattr *iattr) { struct inode *inode = d_inode(dentry); struct proc_dir_entry *de = PDE(inode); @@ -133,7 +134,8 @@ static int proc_notify_change(struct dentry *dentry, struct iattr *iattr) return 0; } -static int proc_getattr(const struct path *path, struct kstat *stat, +static int proc_getattr(struct user_namespace *mnt_userns, + const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); diff --git a/fs/proc/internal.h b/fs/proc/internal.h index f60b379dcdc7..03415f3fb3a8 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -162,8 +162,10 @@ extern int proc_pid_statm(struct seq_file *, struct pid_namespace *, * base.c */ extern const struct dentry_operations pid_dentry_operations; -extern int pid_getattr(const struct path *, struct kstat *, u32, unsigned int); -extern int proc_setattr(struct dentry *, struct iattr *); +extern int pid_getattr(struct user_namespace *, const struct path *, + struct kstat *, u32, unsigned int); +extern int proc_setattr(struct user_namespace *, struct dentry *, + struct iattr *); extern void proc_pid_evict_inode(struct proc_inode *); extern struct inode *proc_pid_make_inode(struct super_block *, struct task_struct *, umode_t); extern void pid_update_inode(struct task_struct *, struct inode *); diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c index 4aef49ccf571..15c2e55d2ed2 100644 --- a/fs/proc/proc_net.c +++ b/fs/proc/proc_net.c @@ -289,7 +289,8 @@ static struct dentry *proc_tgid_net_lookup(struct inode *dir, return de; } -static int proc_tgid_net_getattr(const struct path *path, struct kstat *stat, +static int proc_tgid_net_getattr(struct user_namespace *mnt_userns, + const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 87c828348140..2daac06727d0 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -785,7 +785,8 @@ out: return 0; } -static int proc_sys_permission(struct inode *inode, int mask) +static int proc_sys_permission(struct user_namespace *mnt_userns, + struct inode *inode, int mask) { /* * sysctl entries that are not writeable, @@ -813,7 +814,8 @@ static int proc_sys_permission(struct inode *inode, int mask) return error; } -static int proc_sys_setattr(struct dentry *dentry, struct iattr *attr) +static int proc_sys_setattr(struct user_namespace *mnt_userns, + struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); int error; @@ -830,7 +832,8 @@ static int proc_sys_setattr(struct dentry *dentry, struct iattr *attr) return 0; } -static int proc_sys_getattr(const struct path *path, struct kstat *stat, +static int proc_sys_getattr(struct user_namespace *mnt_userns, + const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); diff --git a/fs/proc/root.c b/fs/proc/root.c index 244e4b6f15ef..c7e3b1350ef8 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -308,7 +308,8 @@ void __init proc_root_init(void) register_filesystem(&proc_fs_type); } -static int proc_root_getattr(const struct path *path, struct kstat *stat, +static int proc_root_getattr(struct user_namespace *mnt_userns, + const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { generic_fillattr(&init_user_ns, d_inode(path->dentry), stat); diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c index f0358fe410d3..ba3525ccc27e 100644 --- a/fs/ramfs/file-nommu.c +++ b/fs/ramfs/file-nommu.c @@ -22,7 +22,7 @@ #include #include "internal.h" -static int ramfs_nommu_setattr(struct dentry *, struct iattr *); +static int ramfs_nommu_setattr(struct user_namespace *, struct dentry *, struct iattr *); static unsigned long ramfs_nommu_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, @@ -158,7 +158,8 @@ static int ramfs_nommu_resize(struct inode *inode, loff_t newsize, loff_t size) * handle a change of attributes * - we're specifically interested in a change of size */ -static int ramfs_nommu_setattr(struct dentry *dentry, struct iattr *ia) +static int ramfs_nommu_setattr(struct user_namespace *mnt_userns, + struct dentry *dentry, struct iattr *ia) { struct inode *inode = d_inode(dentry); unsigned int old_ia_valid = ia->ia_valid; diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c index 3fd4326f36b5..3c2658c8fde0 100644 --- a/fs/ramfs/inode.c +++ b/fs/ramfs/inode.c @@ -101,7 +101,8 @@ struct inode *ramfs_get_inode(struct super_block *sb, */ /* SMP-safe */ static int -ramfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) +ramfs_mknod(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, dev_t dev) { struct inode * inode = ramfs_get_inode(dir->i_sb, dir, mode, dev); int error = -ENOSPC; @@ -115,20 +116,23 @@ ramfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) return error; } -static int ramfs_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode) +static int ramfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { - int retval = ramfs_mknod(dir, dentry, mode | S_IFDIR, 0); + int retval = ramfs_mknod(&init_user_ns, dir, dentry, mode | S_IFDIR, 0); if (!retval) inc_nlink(dir); return retval; } -static int ramfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) +static int ramfs_create(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, bool excl) { - return ramfs_mknod(dir, dentry, mode | S_IFREG, 0); + return ramfs_mknod(&init_user_ns, dir, dentry, mode | S_IFREG, 0); } -static int ramfs_symlink(struct inode * dir, struct dentry *dentry, const char * symname) +static int ramfs_symlink(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, const char *symname) { struct inode *inode; int error = -ENOSPC; diff --git a/fs/reiserfs/acl.h b/fs/reiserfs/acl.h index 0c1c847f992f..fd58618da360 100644 --- a/fs/reiserfs/acl.h +++ b/fs/reiserfs/acl.h @@ -49,7 +49,8 @@ static inline int reiserfs_acl_count(size_t size) #ifdef CONFIG_REISERFS_FS_POSIX_ACL struct posix_acl *reiserfs_get_acl(struct inode *inode, int type); -int reiserfs_set_acl(struct inode *inode, struct posix_acl *acl, int type); +int reiserfs_set_acl(struct user_namespace *mnt_userns, struct inode *inode, + struct posix_acl *acl, int type); int reiserfs_acl_chmod(struct inode *inode); int reiserfs_inherit_default_acl(struct reiserfs_transaction_handle *th, struct inode *dir, struct dentry *dentry, diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index 944f2b487cf8..780bb90c1804 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -3282,7 +3282,8 @@ static ssize_t reiserfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) return ret; } -int reiserfs_setattr(struct dentry *dentry, struct iattr *attr) +int reiserfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *attr) { struct inode *inode = d_inode(dentry); unsigned int ia_valid; diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c index a67a7d371725..e6eb05e2b2f1 100644 --- a/fs/reiserfs/namei.c +++ b/fs/reiserfs/namei.c @@ -619,8 +619,8 @@ static int new_inode_init(struct inode *inode, struct inode *dir, umode_t mode) return dquot_initialize(inode); } -static int reiserfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - bool excl) +static int reiserfs_create(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, bool excl) { int retval; struct inode *inode; @@ -698,8 +698,8 @@ out_failed: return retval; } -static int reiserfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, - dev_t rdev) +static int reiserfs_mknod(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, dev_t rdev) { int retval; struct inode *inode; @@ -781,7 +781,8 @@ out_failed: return retval; } -static int reiserfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +static int reiserfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { int retval; struct inode *inode; @@ -1094,8 +1095,9 @@ out_unlink: return retval; } -static int reiserfs_symlink(struct inode *parent_dir, - struct dentry *dentry, const char *symname) +static int reiserfs_symlink(struct user_namespace *mnt_userns, + struct inode *parent_dir, struct dentry *dentry, + const char *symname) { int retval; struct inode *inode; @@ -1304,7 +1306,8 @@ static void set_ino_in_dir_entry(struct reiserfs_dir_entry *de, * one path. If it holds 2 or more, it can get into endless waiting in * get_empty_nodes or its clones */ -static int reiserfs_rename(struct inode *old_dir, struct dentry *old_dentry, +static int reiserfs_rename(struct user_namespace *mnt_userns, + struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { diff --git a/fs/reiserfs/reiserfs.h b/fs/reiserfs/reiserfs.h index f69871516167..0ca2ac62e534 100644 --- a/fs/reiserfs/reiserfs.h +++ b/fs/reiserfs/reiserfs.h @@ -3102,7 +3102,8 @@ static inline void reiserfs_update_sd(struct reiserfs_transaction_handle *th, } void sd_attrs_to_i_attrs(__u16 sd_attrs, struct inode *inode); -int reiserfs_setattr(struct dentry *dentry, struct iattr *attr); +int reiserfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *attr); int __reiserfs_write_begin(struct page *page, unsigned from, unsigned len); diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index ec440d1957a1..bd073836e141 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -66,14 +66,14 @@ static int xattr_create(struct inode *dir, struct dentry *dentry, int mode) { BUG_ON(!inode_is_locked(dir)); - return dir->i_op->create(dir, dentry, mode, true); + return dir->i_op->create(&init_user_ns, dir, dentry, mode, true); } #endif static int xattr_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) { BUG_ON(!inode_is_locked(dir)); - return dir->i_op->mkdir(dir, dentry, mode); + return dir->i_op->mkdir(&init_user_ns, dir, dentry, mode); } /* @@ -352,7 +352,7 @@ static int chown_one_xattr(struct dentry *dentry, void *data) * ATTR_MODE is set. */ attrs->ia_valid &= (ATTR_UID|ATTR_GID); - err = reiserfs_setattr(dentry, attrs); + err = reiserfs_setattr(&init_user_ns, dentry, attrs); attrs->ia_valid = ia_valid; return err; @@ -604,7 +604,7 @@ reiserfs_xattr_set_handle(struct reiserfs_transaction_handle *th, inode_lock_nested(d_inode(dentry), I_MUTEX_XATTR); inode_dio_wait(d_inode(dentry)); - err = reiserfs_setattr(dentry, &newattrs); + err = reiserfs_setattr(&init_user_ns, dentry, &newattrs); inode_unlock(d_inode(dentry)); } else update_ctime(inode); @@ -948,7 +948,8 @@ static int xattr_mount_check(struct super_block *s) return 0; } -int reiserfs_permission(struct inode *inode, int mask) +int reiserfs_permission(struct user_namespace *mnt_userns, struct inode *inode, + int mask) { /* * We don't do permission checks on the internal objects. diff --git a/fs/reiserfs/xattr.h b/fs/reiserfs/xattr.h index c764352447ba..9b3b06da568c 100644 --- a/fs/reiserfs/xattr.h +++ b/fs/reiserfs/xattr.h @@ -16,7 +16,8 @@ int reiserfs_xattr_init(struct super_block *sb, int mount_flags); int reiserfs_lookup_privroot(struct super_block *sb); int reiserfs_delete_xattrs(struct inode *inode); int reiserfs_chown_xattrs(struct inode *inode, struct iattr *attrs); -int reiserfs_permission(struct inode *inode, int mask); +int reiserfs_permission(struct user_namespace *mnt_userns, + struct inode *inode, int mask); #ifdef CONFIG_REISERFS_FS_XATTR #define has_xattr_dir(inode) (REISERFS_I(inode)->i_flags & i_has_xattr_dir) diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c index 4bf976bc7bad..a9547144a099 100644 --- a/fs/reiserfs/xattr_acl.c +++ b/fs/reiserfs/xattr_acl.c @@ -18,7 +18,8 @@ static int __reiserfs_set_acl(struct reiserfs_transaction_handle *th, int -reiserfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) +reiserfs_set_acl(struct user_namespace *mnt_userns, struct inode *inode, + struct posix_acl *acl, int type) { int error, error2; struct reiserfs_transaction_handle th; diff --git a/fs/stat.c b/fs/stat.c index 2c471c2fd766..fbc171d038aa 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -75,6 +75,7 @@ EXPORT_SYMBOL(generic_fillattr); int vfs_getattr_nosec(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { + struct user_namespace *mnt_userns; struct inode *inode = d_backing_inode(path->dentry); memset(stat, 0, sizeof(*stat)); @@ -91,11 +92,12 @@ int vfs_getattr_nosec(const struct path *path, struct kstat *stat, if (IS_DAX(inode)) stat->attributes |= STATX_ATTR_DAX; + mnt_userns = mnt_user_ns(path->mnt); if (inode->i_op->getattr) - return inode->i_op->getattr(path, stat, request_mask, - query_flags); + return inode->i_op->getattr(mnt_userns, path, stat, + request_mask, query_flags); - generic_fillattr(mnt_user_ns(path->mnt), inode, stat); + generic_fillattr(mnt_userns, inode, stat); return 0; } EXPORT_SYMBOL(vfs_getattr_nosec); diff --git a/fs/sysv/file.c b/fs/sysv/file.c index ca7e216b7b9e..90e00124ea07 100644 --- a/fs/sysv/file.c +++ b/fs/sysv/file.c @@ -29,7 +29,8 @@ const struct file_operations sysv_file_operations = { .splice_read = generic_file_splice_read, }; -static int sysv_setattr(struct dentry *dentry, struct iattr *attr) +static int sysv_setattr(struct user_namespace *mnt_userns, + struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); int error; diff --git a/fs/sysv/itree.c b/fs/sysv/itree.c index 83cffab6955f..8b2e99b7bc9f 100644 --- a/fs/sysv/itree.c +++ b/fs/sysv/itree.c @@ -441,8 +441,8 @@ static unsigned sysv_nblocks(struct super_block *s, loff_t size) return blocks; } -int sysv_getattr(const struct path *path, struct kstat *stat, - u32 request_mask, unsigned int flags) +int sysv_getattr(struct user_namespace *mnt_userns, const struct path *path, + struct kstat *stat, u32 request_mask, unsigned int flags) { struct super_block *s = path->dentry->d_sb; generic_fillattr(&init_user_ns, d_inode(path->dentry), stat); diff --git a/fs/sysv/namei.c b/fs/sysv/namei.c index ea2414b385ec..b2e6abc06a2d 100644 --- a/fs/sysv/namei.c +++ b/fs/sysv/namei.c @@ -41,7 +41,8 @@ static struct dentry *sysv_lookup(struct inode * dir, struct dentry * dentry, un return d_splice_alias(inode, dentry); } -static int sysv_mknod(struct inode * dir, struct dentry * dentry, umode_t mode, dev_t rdev) +static int sysv_mknod(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, dev_t rdev) { struct inode * inode; int err; @@ -60,13 +61,14 @@ static int sysv_mknod(struct inode * dir, struct dentry * dentry, umode_t mode, return err; } -static int sysv_create(struct inode * dir, struct dentry * dentry, umode_t mode, bool excl) +static int sysv_create(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, bool excl) { - return sysv_mknod(dir, dentry, mode, 0); + return sysv_mknod(&init_user_ns, dir, dentry, mode, 0); } -static int sysv_symlink(struct inode * dir, struct dentry * dentry, - const char * symname) +static int sysv_symlink(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, const char *symname) { int err = -ENAMETOOLONG; int l = strlen(symname)+1; @@ -108,7 +110,8 @@ static int sysv_link(struct dentry * old_dentry, struct inode * dir, return add_nondir(dentry, inode); } -static int sysv_mkdir(struct inode * dir, struct dentry *dentry, umode_t mode) +static int sysv_mkdir(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct inode * inode; int err; @@ -186,9 +189,9 @@ static int sysv_rmdir(struct inode * dir, struct dentry * dentry) * Anybody can rename anything with this: the permission checks are left to the * higher-level routines. */ -static int sysv_rename(struct inode * old_dir, struct dentry * old_dentry, - struct inode * new_dir, struct dentry * new_dentry, - unsigned int flags) +static int sysv_rename(struct user_namespace *mnt_userns, struct inode *old_dir, + struct dentry *old_dentry, struct inode *new_dir, + struct dentry *new_dentry, unsigned int flags) { struct inode * old_inode = d_inode(old_dentry); struct inode * new_inode = d_inode(new_dentry); diff --git a/fs/sysv/sysv.h b/fs/sysv/sysv.h index 1cff585526b1..99ddf033da4f 100644 --- a/fs/sysv/sysv.h +++ b/fs/sysv/sysv.h @@ -141,7 +141,8 @@ extern struct inode *sysv_iget(struct super_block *, unsigned int); extern int sysv_write_inode(struct inode *, struct writeback_control *wbc); extern int sysv_sync_inode(struct inode *); extern void sysv_set_inode(struct inode *, dev_t); -extern int sysv_getattr(const struct path *, struct kstat *, u32, unsigned int); +extern int sysv_getattr(struct user_namespace *, const struct path *, + struct kstat *, u32, unsigned int); extern int sysv_init_icache(void); extern void sysv_destroy_icache(void); diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index 0ee8c6dfb036..4b83cbded559 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -67,7 +67,9 @@ static char *get_dname(struct dentry *dentry) return name; } -static int tracefs_syscall_mkdir(struct inode *inode, struct dentry *dentry, umode_t mode) +static int tracefs_syscall_mkdir(struct user_namespace *mnt_userns, + struct inode *inode, struct dentry *dentry, + umode_t mode) { char *name; int ret; diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index a8881ed61620..d9d8d7794eff 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -280,8 +280,8 @@ static int ubifs_prepare_create(struct inode *dir, struct dentry *dentry, return fscrypt_setup_filename(dir, &dentry->d_name, 0, nm); } -static int ubifs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - bool excl) +static int ubifs_create(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, bool excl) { struct inode *inode; struct ubifs_info *c = dir->i_sb->s_fs_info; @@ -441,8 +441,8 @@ out_budg: return err; } -static int ubifs_tmpfile(struct inode *dir, struct dentry *dentry, - umode_t mode) +static int ubifs_tmpfile(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { return do_tmpfile(dir, dentry, mode, NULL); } @@ -942,7 +942,8 @@ out_fname: return err; } -static int ubifs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +static int ubifs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct inode *inode; struct ubifs_inode *dir_ui = ubifs_inode(dir); @@ -1013,8 +1014,8 @@ out_budg: return err; } -static int ubifs_mknod(struct inode *dir, struct dentry *dentry, - umode_t mode, dev_t rdev) +static int ubifs_mknod(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, dev_t rdev) { struct inode *inode; struct ubifs_inode *ui; @@ -1102,8 +1103,8 @@ out_budg: return err; } -static int ubifs_symlink(struct inode *dir, struct dentry *dentry, - const char *symname) +static int ubifs_symlink(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, const char *symname) { struct inode *inode; struct ubifs_inode *ui; @@ -1542,7 +1543,8 @@ static int ubifs_xrename(struct inode *old_dir, struct dentry *old_dentry, return err; } -static int ubifs_rename(struct inode *old_dir, struct dentry *old_dentry, +static int ubifs_rename(struct user_namespace *mnt_userns, + struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { @@ -1566,8 +1568,8 @@ static int ubifs_rename(struct inode *old_dir, struct dentry *old_dentry, return do_rename(old_dir, old_dentry, new_dir, new_dentry, flags); } -int ubifs_getattr(const struct path *path, struct kstat *stat, - u32 request_mask, unsigned int flags) +int ubifs_getattr(struct user_namespace *mnt_userns, const struct path *path, + struct kstat *stat, u32 request_mask, unsigned int flags) { loff_t size; struct inode *inode = d_inode(path->dentry); diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 76ef392b1e41..0e4b4be3aa26 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -1257,7 +1257,8 @@ static int do_setattr(struct ubifs_info *c, struct inode *inode, return err; } -int ubifs_setattr(struct dentry *dentry, struct iattr *attr) +int ubifs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *attr) { int err; struct inode *inode = d_inode(dentry); diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index fc2cdde3b549..7fdfdbda4b8a 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -1989,13 +1989,14 @@ int ubifs_calc_dark(const struct ubifs_info *c, int spc); /* file.c */ int ubifs_fsync(struct file *file, loff_t start, loff_t end, int datasync); -int ubifs_setattr(struct dentry *dentry, struct iattr *attr); +int ubifs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *attr); int ubifs_update_time(struct inode *inode, struct timespec64 *time, int flags); /* dir.c */ struct inode *ubifs_new_inode(struct ubifs_info *c, struct inode *dir, umode_t mode); -int ubifs_getattr(const struct path *path, struct kstat *stat, +int ubifs_getattr(struct user_namespace *mnt_userns, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags); int ubifs_check_dir_empty(struct inode *dir); diff --git a/fs/udf/file.c b/fs/udf/file.c index 7c7d161315c2..2846dcd92197 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -253,7 +253,8 @@ const struct file_operations udf_file_operations = { .llseek = generic_file_llseek, }; -static int udf_setattr(struct dentry *dentry, struct iattr *attr) +static int udf_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *attr) { struct inode *inode = d_inode(dentry); struct super_block *sb = inode->i_sb; diff --git a/fs/udf/namei.c b/fs/udf/namei.c index e169d8fe35b5..f146b3089f3d 100644 --- a/fs/udf/namei.c +++ b/fs/udf/namei.c @@ -604,8 +604,8 @@ static int udf_add_nondir(struct dentry *dentry, struct inode *inode) return 0; } -static int udf_create(struct inode *dir, struct dentry *dentry, umode_t mode, - bool excl) +static int udf_create(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, bool excl) { struct inode *inode = udf_new_inode(dir, mode); @@ -623,7 +623,8 @@ static int udf_create(struct inode *dir, struct dentry *dentry, umode_t mode, return udf_add_nondir(dentry, inode); } -static int udf_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) +static int udf_tmpfile(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct inode *inode = udf_new_inode(dir, mode); @@ -642,8 +643,8 @@ static int udf_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) return 0; } -static int udf_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, - dev_t rdev) +static int udf_mknod(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, dev_t rdev) { struct inode *inode; @@ -658,7 +659,8 @@ static int udf_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, return udf_add_nondir(dentry, inode); } -static int udf_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +static int udf_mkdir(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct inode *inode; struct udf_fileident_bh fibh; @@ -877,8 +879,8 @@ out: return retval; } -static int udf_symlink(struct inode *dir, struct dentry *dentry, - const char *symname) +static int udf_symlink(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, const char *symname) { struct inode *inode = udf_new_inode(dir, S_IFLNK | 0777); struct pathComponent *pc; @@ -1065,9 +1067,9 @@ static int udf_link(struct dentry *old_dentry, struct inode *dir, /* Anybody can rename anything with this: the permission checks are left to the * higher-level routines. */ -static int udf_rename(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry, - unsigned int flags) +static int udf_rename(struct user_namespace *mnt_userns, struct inode *old_dir, + struct dentry *old_dentry, struct inode *new_dir, + struct dentry *new_dentry, unsigned int flags) { struct inode *old_inode = d_inode(old_dentry); struct inode *new_inode = d_inode(new_dentry); diff --git a/fs/udf/symlink.c b/fs/udf/symlink.c index 54a44d1f023c..9b223421a3c5 100644 --- a/fs/udf/symlink.c +++ b/fs/udf/symlink.c @@ -152,8 +152,9 @@ out_unmap: return err; } -static int udf_symlink_getattr(const struct path *path, struct kstat *stat, - u32 request_mask, unsigned int flags) +static int udf_symlink_getattr(struct user_namespace *mnt_userns, + const struct path *path, struct kstat *stat, + u32 request_mask, unsigned int flags) { struct dentry *dentry = path->dentry; struct inode *inode = d_backing_inode(dentry); diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c index 6b51f3b20143..debc282c1bb4 100644 --- a/fs/ufs/inode.c +++ b/fs/ufs/inode.c @@ -1211,7 +1211,8 @@ out: return err; } -int ufs_setattr(struct dentry *dentry, struct iattr *attr) +int ufs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *attr) { struct inode *inode = d_inode(dentry); unsigned int ia_valid = attr->ia_valid; diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c index 9ef40f100415..29d5a0e0c8f0 100644 --- a/fs/ufs/namei.c +++ b/fs/ufs/namei.c @@ -69,7 +69,8 @@ static struct dentry *ufs_lookup(struct inode * dir, struct dentry *dentry, unsi * If the create succeeds, we fill in the inode information * with d_instantiate(). */ -static int ufs_create (struct inode * dir, struct dentry * dentry, umode_t mode, +static int ufs_create (struct user_namespace * mnt_userns, + struct inode * dir, struct dentry * dentry, umode_t mode, bool excl) { struct inode *inode; @@ -85,7 +86,8 @@ static int ufs_create (struct inode * dir, struct dentry * dentry, umode_t mode, return ufs_add_nondir(dentry, inode); } -static int ufs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) +static int ufs_mknod(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, dev_t rdev) { struct inode *inode; int err; @@ -104,8 +106,8 @@ static int ufs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev return err; } -static int ufs_symlink (struct inode * dir, struct dentry * dentry, - const char * symname) +static int ufs_symlink (struct user_namespace * mnt_userns, struct inode * dir, + struct dentry * dentry, const char * symname) { struct super_block * sb = dir->i_sb; int err; @@ -164,7 +166,8 @@ static int ufs_link (struct dentry * old_dentry, struct inode * dir, return error; } -static int ufs_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode) +static int ufs_mkdir(struct user_namespace * mnt_userns, struct inode * dir, + struct dentry * dentry, umode_t mode) { struct inode * inode; int err; @@ -240,9 +243,9 @@ static int ufs_rmdir (struct inode * dir, struct dentry *dentry) return err; } -static int ufs_rename(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry, - unsigned int flags) +static int ufs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, + struct dentry *old_dentry, struct inode *new_dir, + struct dentry *new_dentry, unsigned int flags) { struct inode *old_inode = d_inode(old_dentry); struct inode *new_inode = d_inode(new_dentry); diff --git a/fs/ufs/ufs.h b/fs/ufs/ufs.h index b49e0efdf3d7..550f7c5a3636 100644 --- a/fs/ufs/ufs.h +++ b/fs/ufs/ufs.h @@ -123,7 +123,8 @@ extern struct inode *ufs_iget(struct super_block *, unsigned long); extern int ufs_write_inode (struct inode *, struct writeback_control *); extern int ufs_sync_inode (struct inode *); extern void ufs_evict_inode (struct inode *); -extern int ufs_setattr(struct dentry *dentry, struct iattr *attr); +extern int ufs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *attr); /* namei.c */ extern const struct file_operations ufs_dir_operations; diff --git a/fs/vboxsf/dir.c b/fs/vboxsf/dir.c index 4d569f14a8d8..7aee0ec63ade 100644 --- a/fs/vboxsf/dir.c +++ b/fs/vboxsf/dir.c @@ -288,13 +288,15 @@ static int vboxsf_dir_create(struct inode *parent, struct dentry *dentry, return 0; } -static int vboxsf_dir_mkfile(struct inode *parent, struct dentry *dentry, +static int vboxsf_dir_mkfile(struct user_namespace *mnt_userns, + struct inode *parent, struct dentry *dentry, umode_t mode, bool excl) { return vboxsf_dir_create(parent, dentry, mode, 0); } -static int vboxsf_dir_mkdir(struct inode *parent, struct dentry *dentry, +static int vboxsf_dir_mkdir(struct user_namespace *mnt_userns, + struct inode *parent, struct dentry *dentry, umode_t mode) { return vboxsf_dir_create(parent, dentry, mode, 1); @@ -332,7 +334,8 @@ static int vboxsf_dir_unlink(struct inode *parent, struct dentry *dentry) return 0; } -static int vboxsf_dir_rename(struct inode *old_parent, +static int vboxsf_dir_rename(struct user_namespace *mnt_userns, + struct inode *old_parent, struct dentry *old_dentry, struct inode *new_parent, struct dentry *new_dentry, @@ -374,7 +377,8 @@ err_put_old_path: return err; } -static int vboxsf_dir_symlink(struct inode *parent, struct dentry *dentry, +static int vboxsf_dir_symlink(struct user_namespace *mnt_userns, + struct inode *parent, struct dentry *dentry, const char *symname) { struct vboxsf_inode *sf_parent_i = VBOXSF_I(parent); diff --git a/fs/vboxsf/utils.c b/fs/vboxsf/utils.c index d2cd1c99f48e..3b847e3fba24 100644 --- a/fs/vboxsf/utils.c +++ b/fs/vboxsf/utils.c @@ -212,8 +212,8 @@ int vboxsf_inode_revalidate(struct dentry *dentry) return 0; } -int vboxsf_getattr(const struct path *path, struct kstat *kstat, - u32 request_mask, unsigned int flags) +int vboxsf_getattr(struct user_namespace *mnt_userns, const struct path *path, + struct kstat *kstat, u32 request_mask, unsigned int flags) { int err; struct dentry *dentry = path->dentry; @@ -237,7 +237,8 @@ int vboxsf_getattr(const struct path *path, struct kstat *kstat, return 0; } -int vboxsf_setattr(struct dentry *dentry, struct iattr *iattr) +int vboxsf_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *iattr) { struct vboxsf_inode *sf_i = VBOXSF_I(d_inode(dentry)); struct vboxsf_sbi *sbi = VBOXSF_SBI(dentry->d_sb); diff --git a/fs/vboxsf/vfsmod.h b/fs/vboxsf/vfsmod.h index 18f95b00fc33..760524e78c88 100644 --- a/fs/vboxsf/vfsmod.h +++ b/fs/vboxsf/vfsmod.h @@ -90,9 +90,11 @@ int vboxsf_stat(struct vboxsf_sbi *sbi, struct shfl_string *path, struct shfl_fsobjinfo *info); int vboxsf_stat_dentry(struct dentry *dentry, struct shfl_fsobjinfo *info); int vboxsf_inode_revalidate(struct dentry *dentry); -int vboxsf_getattr(const struct path *path, struct kstat *kstat, - u32 request_mask, unsigned int query_flags); -int vboxsf_setattr(struct dentry *dentry, struct iattr *iattr); +int vboxsf_getattr(struct user_namespace *mnt_userns, const struct path *path, + struct kstat *kstat, u32 request_mask, + unsigned int query_flags); +int vboxsf_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *iattr); struct shfl_string *vboxsf_path_from_dentry(struct vboxsf_sbi *sbi, struct dentry *dentry); int vboxsf_nlscpy(struct vboxsf_sbi *sbi, char *name, size_t name_bound_len, diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c index 368351298bd5..332e87153c6c 100644 --- a/fs/xfs/xfs_acl.c +++ b/fs/xfs/xfs_acl.c @@ -238,7 +238,8 @@ xfs_acl_set_mode( } int -xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) +xfs_set_acl(struct user_namespace *mnt_userns, struct inode *inode, + struct posix_acl *acl, int type) { umode_t mode; bool set_mode = false; diff --git a/fs/xfs/xfs_acl.h b/fs/xfs/xfs_acl.h index c042c0868016..7bdb3a4ed798 100644 --- a/fs/xfs/xfs_acl.h +++ b/fs/xfs/xfs_acl.h @@ -11,7 +11,8 @@ struct posix_acl; #ifdef CONFIG_XFS_POSIX_ACL extern struct posix_acl *xfs_get_acl(struct inode *inode, int type); -extern int xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type); +extern int xfs_set_acl(struct user_namespace *mnt_userns, struct inode *inode, + struct posix_acl *acl, int type); extern int __xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type); void xfs_forget_acl(struct inode *inode, const char *name); #else diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 26d22edef741..f5dfa128af64 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -220,29 +220,32 @@ xfs_generic_create( STATIC int xfs_vn_mknod( - struct inode *dir, - struct dentry *dentry, - umode_t mode, - dev_t rdev) + struct user_namespace *mnt_userns, + struct inode *dir, + struct dentry *dentry, + umode_t mode, + dev_t rdev) { return xfs_generic_create(dir, dentry, mode, rdev, false); } STATIC int xfs_vn_create( - struct inode *dir, - struct dentry *dentry, - umode_t mode, - bool flags) + struct user_namespace *mnt_userns, + struct inode *dir, + struct dentry *dentry, + umode_t mode, + bool flags) { return xfs_generic_create(dir, dentry, mode, 0, false); } STATIC int xfs_vn_mkdir( - struct inode *dir, - struct dentry *dentry, - umode_t mode) + struct user_namespace *mnt_userns, + struct inode *dir, + struct dentry *dentry, + umode_t mode) { return xfs_generic_create(dir, dentry, mode | S_IFDIR, 0, false); } @@ -361,9 +364,10 @@ xfs_vn_unlink( STATIC int xfs_vn_symlink( - struct inode *dir, - struct dentry *dentry, - const char *symname) + struct user_namespace *mnt_userns, + struct inode *dir, + struct dentry *dentry, + const char *symname) { struct inode *inode; struct xfs_inode *cip = NULL; @@ -403,11 +407,12 @@ xfs_vn_symlink( STATIC int xfs_vn_rename( - struct inode *odir, - struct dentry *odentry, - struct inode *ndir, - struct dentry *ndentry, - unsigned int flags) + struct user_namespace *mnt_userns, + struct inode *odir, + struct dentry *odentry, + struct inode *ndir, + struct dentry *ndentry, + unsigned int flags) { struct inode *new_inode = d_inode(ndentry); int omode = 0; @@ -529,6 +534,7 @@ xfs_stat_blksize( STATIC int xfs_vn_getattr( + struct user_namespace *mnt_userns, const struct path *path, struct kstat *stat, u32 request_mask, @@ -1047,6 +1053,7 @@ xfs_vn_setattr_size( STATIC int xfs_vn_setattr( + struct user_namespace *mnt_userns, struct dentry *dentry, struct iattr *iattr) { @@ -1144,9 +1151,10 @@ xfs_vn_fiemap( STATIC int xfs_vn_tmpfile( - struct inode *dir, - struct dentry *dentry, - umode_t mode) + struct user_namespace *mnt_userns, + struct inode *dir, + struct dentry *dentry, + umode_t mode) { return xfs_generic_create(dir, dentry, mode, 0, true); } diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index 8a1f69677784..76e45d66d4ce 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -480,7 +480,8 @@ unlock: return ret; } -static int zonefs_inode_setattr(struct dentry *dentry, struct iattr *iattr) +static int zonefs_inode_setattr(struct user_namespace *mnt_userns, + struct dentry *dentry, struct iattr *iattr) { struct inode *inode = d_inode(dentry); int ret; diff --git a/include/linux/fs.h b/include/linux/fs.h index f0601cca1930..7762d3d75230 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1930,22 +1930,28 @@ struct file_operations { struct inode_operations { struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); const char * (*get_link) (struct dentry *, struct inode *, struct delayed_call *); - int (*permission) (struct inode *, int); + int (*permission) (struct user_namespace *, struct inode *, int); struct posix_acl * (*get_acl)(struct inode *, int); int (*readlink) (struct dentry *, char __user *,int); - int (*create) (struct inode *,struct dentry *, umode_t, bool); + int (*create) (struct user_namespace *, struct inode *,struct dentry *, + umode_t, bool); int (*link) (struct dentry *,struct inode *,struct dentry *); int (*unlink) (struct inode *,struct dentry *); - int (*symlink) (struct inode *,struct dentry *,const char *); - int (*mkdir) (struct inode *,struct dentry *,umode_t); + int (*symlink) (struct user_namespace *, struct inode *,struct dentry *, + const char *); + int (*mkdir) (struct user_namespace *, struct inode *,struct dentry *, + umode_t); int (*rmdir) (struct inode *,struct dentry *); - int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t); - int (*rename) (struct inode *, struct dentry *, + int (*mknod) (struct user_namespace *, struct inode *,struct dentry *, + umode_t,dev_t); + int (*rename) (struct user_namespace *, struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); - int (*setattr) (struct dentry *, struct iattr *); - int (*getattr) (const struct path *, struct kstat *, u32, unsigned int); + int (*setattr) (struct user_namespace *, struct dentry *, + struct iattr *); + int (*getattr) (struct user_namespace *, const struct path *, + struct kstat *, u32, unsigned int); ssize_t (*listxattr) (struct dentry *, char *, size_t); int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len); @@ -1953,8 +1959,10 @@ struct inode_operations { int (*atomic_open)(struct inode *, struct dentry *, struct file *, unsigned open_flag, umode_t create_mode); - int (*tmpfile) (struct inode *, struct dentry *, umode_t); - int (*set_acl)(struct inode *, struct posix_acl *, int); + int (*tmpfile) (struct user_namespace *, struct inode *, + struct dentry *, umode_t); + int (*set_acl)(struct user_namespace *, struct inode *, + struct posix_acl *, int); } ____cacheline_aligned; static inline ssize_t call_read_iter(struct file *file, struct kiocb *kio, @@ -3227,15 +3235,18 @@ extern int dcache_dir_open(struct inode *, struct file *); extern int dcache_dir_close(struct inode *, struct file *); extern loff_t dcache_dir_lseek(struct file *, loff_t, int); extern int dcache_readdir(struct file *, struct dir_context *); -extern int simple_setattr(struct dentry *, struct iattr *); -extern int simple_getattr(const struct path *, struct kstat *, u32, unsigned int); +extern int simple_setattr(struct user_namespace *, struct dentry *, + struct iattr *); +extern int simple_getattr(struct user_namespace *, const struct path *, + struct kstat *, u32, unsigned int); extern int simple_statfs(struct dentry *, struct kstatfs *); extern int simple_open(struct inode *inode, struct file *file); extern int simple_link(struct dentry *, struct inode *, struct dentry *); extern int simple_unlink(struct inode *, struct dentry *); extern int simple_rmdir(struct inode *, struct dentry *); -extern int simple_rename(struct inode *, struct dentry *, - struct inode *, struct dentry *, unsigned int); +extern int simple_rename(struct user_namespace *, struct inode *, + struct dentry *, struct inode *, struct dentry *, + unsigned int); extern void simple_recursive_removal(struct dentry *, void (*callback)(struct dentry *)); extern int noop_fsync(struct file *, loff_t, loff_t, int); diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 681ed98e4ba8..8c6c4e32fc2f 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -379,10 +379,11 @@ extern int nfs_refresh_inode(struct inode *, struct nfs_fattr *); extern int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr); extern int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr); extern int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fattr *fattr); -extern int nfs_getattr(const struct path *, struct kstat *, u32, unsigned int); +extern int nfs_getattr(struct user_namespace *, const struct path *, + struct kstat *, u32, unsigned int); extern void nfs_access_add_cache(struct inode *, struct nfs_access_entry *); extern void nfs_access_set_mask(struct nfs_access_entry *, u32); -extern int nfs_permission(struct inode *, int); +extern int nfs_permission(struct user_namespace *, struct inode *, int); extern int nfs_open(struct inode *, struct file *); extern int nfs_attribute_cache_expired(struct inode *inode); extern int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode); @@ -390,7 +391,7 @@ extern int __nfs_revalidate_inode(struct nfs_server *, struct inode *); extern bool nfs_mapping_need_revalidate_inode(struct inode *inode); extern int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping); extern int nfs_revalidate_mapping_rcu(struct inode *inode); -extern int nfs_setattr(struct dentry *, struct iattr *); +extern int nfs_setattr(struct user_namespace *, struct dentry *, struct iattr *); extern void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr, struct nfs_fattr *); extern void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr, struct nfs4_label *label); diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index 6dcd8b8f6ab5..307094ebb88c 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -79,7 +79,8 @@ extern int posix_acl_create(struct inode *, umode_t *, struct posix_acl **, int posix_acl_update_mode(struct user_namespace *, struct inode *, umode_t *, struct posix_acl **); -extern int simple_set_acl(struct inode *, struct posix_acl *, int); +extern int simple_set_acl(struct user_namespace *, struct inode *, + struct posix_acl *, int); extern int simple_acl_create(struct inode *, struct inode *); struct posix_acl *get_cached_acl(struct inode *inode, int type); diff --git a/ipc/mqueue.c b/ipc/mqueue.c index fcd56e077733..8031464ed4ae 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -594,8 +594,8 @@ out_unlock: return error; } -static int mqueue_create(struct inode *dir, struct dentry *dentry, - umode_t mode, bool excl) +static int mqueue_create(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, bool excl) { return mqueue_create_attr(dentry, mode, NULL); } diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 05b1f51d15e0..1576ff331ee4 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -152,7 +152,8 @@ static void bpf_dentry_finalize(struct dentry *dentry, struct inode *inode, dir->i_ctime = dir->i_mtime; } -static int bpf_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +static int bpf_mkdir(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct inode *inode; @@ -381,8 +382,8 @@ bpf_lookup(struct inode *dir, struct dentry *dentry, unsigned flags) return simple_lookup(dir, dentry, flags); } -static int bpf_symlink(struct inode *dir, struct dentry *dentry, - const char *target) +static int bpf_symlink(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, const char *target) { char *link = kstrdup(target, GFP_USER | __GFP_NOWARN); struct inode *inode; diff --git a/mm/shmem.c b/mm/shmem.c index 339d5530d3a9..facdd1a9c524 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1060,7 +1060,8 @@ void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend) } EXPORT_SYMBOL_GPL(shmem_truncate_range); -static int shmem_getattr(const struct path *path, struct kstat *stat, +static int shmem_getattr(struct user_namespace *mnt_userns, + const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = path->dentry->d_inode; @@ -1080,7 +1081,8 @@ static int shmem_getattr(const struct path *path, struct kstat *stat, return 0; } -static int shmem_setattr(struct dentry *dentry, struct iattr *attr) +static int shmem_setattr(struct user_namespace *mnt_userns, + struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); struct shmem_inode_info *info = SHMEM_I(inode); @@ -2917,7 +2919,8 @@ static int shmem_statfs(struct dentry *dentry, struct kstatfs *buf) * File creation. Allocate an inode, and we're done.. */ static int -shmem_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) +shmem_mknod(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, dev_t dev) { struct inode *inode; int error = -ENOSPC; @@ -2946,7 +2949,8 @@ out_iput: } static int -shmem_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) +shmem_tmpfile(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct inode *inode; int error = -ENOSPC; @@ -2969,20 +2973,22 @@ out_iput: return error; } -static int shmem_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +static int shmem_mkdir(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { int error; - if ((error = shmem_mknod(dir, dentry, mode | S_IFDIR, 0))) + if ((error = shmem_mknod(&init_user_ns, dir, dentry, + mode | S_IFDIR, 0))) return error; inc_nlink(dir); return 0; } -static int shmem_create(struct inode *dir, struct dentry *dentry, umode_t mode, - bool excl) +static int shmem_create(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, bool excl) { - return shmem_mknod(dir, dentry, mode | S_IFREG, 0); + return shmem_mknod(&init_user_ns, dir, dentry, mode | S_IFREG, 0); } /* @@ -3062,7 +3068,8 @@ static int shmem_exchange(struct inode *old_dir, struct dentry *old_dentry, stru return 0; } -static int shmem_whiteout(struct inode *old_dir, struct dentry *old_dentry) +static int shmem_whiteout(struct user_namespace *mnt_userns, + struct inode *old_dir, struct dentry *old_dentry) { struct dentry *whiteout; int error; @@ -3071,7 +3078,7 @@ static int shmem_whiteout(struct inode *old_dir, struct dentry *old_dentry) if (!whiteout) return -ENOMEM; - error = shmem_mknod(old_dir, whiteout, + error = shmem_mknod(&init_user_ns, old_dir, whiteout, S_IFCHR | WHITEOUT_MODE, WHITEOUT_DEV); dput(whiteout); if (error) @@ -3094,7 +3101,10 @@ static int shmem_whiteout(struct inode *old_dir, struct dentry *old_dentry) * it exists so that the VFS layer correctly free's it when it * gets overwritten. */ -static int shmem_rename2(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) +static int shmem_rename2(struct user_namespace *mnt_userns, + struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry, + unsigned int flags) { struct inode *inode = d_inode(old_dentry); int they_are_dirs = S_ISDIR(inode->i_mode); @@ -3111,7 +3121,7 @@ static int shmem_rename2(struct inode *old_dir, struct dentry *old_dentry, struc if (flags & RENAME_WHITEOUT) { int error; - error = shmem_whiteout(old_dir, old_dentry); + error = shmem_whiteout(&init_user_ns, old_dir, old_dentry); if (error) return error; } @@ -3135,7 +3145,8 @@ static int shmem_rename2(struct inode *old_dir, struct dentry *old_dentry, struc return 0; } -static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *symname) +static int shmem_symlink(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, const char *symname) { int error; int len; diff --git a/net/socket.c b/net/socket.c index c76703c6f480..2826698ff97c 100644 --- a/net/socket.c +++ b/net/socket.c @@ -538,9 +538,10 @@ static ssize_t sockfs_listxattr(struct dentry *dentry, char *buffer, return used; } -static int sockfs_setattr(struct dentry *dentry, struct iattr *iattr) +static int sockfs_setattr(struct user_namespace *mnt_userns, + struct dentry *dentry, struct iattr *iattr) { - int err = simple_setattr(dentry, iattr); + int err = simple_setattr(&init_user_ns, dentry, iattr); if (!err && (iattr->ia_valid & ATTR_UID)) { struct socket *sock = SOCKET_I(d_inode(dentry)); diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c index f95c6bfa8b8e..2ee3b3d29f10 100644 --- a/security/apparmor/apparmorfs.c +++ b/security/apparmor/apparmorfs.c @@ -1773,7 +1773,8 @@ fail2: return error; } -static int ns_mkdir_op(struct inode *dir, struct dentry *dentry, umode_t mode) +static int ns_mkdir_op(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct aa_ns *ns, *parent; /* TODO: improve permission check */ diff --git a/security/integrity/evm/evm_secfs.c b/security/integrity/evm/evm_secfs.c index cfc3075769bb..bbc85637e18b 100644 --- a/security/integrity/evm/evm_secfs.c +++ b/security/integrity/evm/evm_secfs.c @@ -219,7 +219,7 @@ static ssize_t evm_write_xattrs(struct file *file, const char __user *buf, newattrs.ia_valid = ATTR_MODE; inode = evm_xattrs->d_inode; inode_lock(inode); - err = simple_setattr(evm_xattrs, &newattrs); + err = simple_setattr(&init_user_ns, evm_xattrs, &newattrs); inode_unlock(inode); if (!err) err = count; -- cgit v1.2.3 From a2d2329e30e224ea68d575d2525b866df9805ea0 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 21 Jan 2021 14:19:45 +0100 Subject: ima: handle idmapped mounts IMA does sometimes access the inode's i_uid and compares it against the rules' fowner. Enable IMA to handle idmapped mounts by passing down the mount's user namespace. We simply make use of the helpers we introduced before. If the initial user namespace is passed nothing changes so non-idmapped mounts will see identical behavior as before. Link: https://lore.kernel.org/r/20210121131959.646623-27-christian.brauner@ubuntu.com Signed-off-by: Christian Brauner --- fs/attr.c | 2 +- fs/namei.c | 4 +-- include/linux/ima.h | 18 +++++++++----- security/integrity/ima/ima.h | 19 ++++++++------ security/integrity/ima/ima_api.c | 10 +++++--- security/integrity/ima/ima_appraise.c | 15 ++++++----- security/integrity/ima/ima_asymmetric_keys.c | 3 ++- security/integrity/ima/ima_main.c | 37 ++++++++++++++++++---------- security/integrity/ima/ima_policy.c | 20 +++++++++------ security/integrity/ima/ima_queue_keys.c | 4 ++- 10 files changed, 83 insertions(+), 49 deletions(-) (limited to 'include') diff --git a/fs/attr.c b/fs/attr.c index 41abd0d973d8..87ef39db1c34 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -401,7 +401,7 @@ int notify_change(struct user_namespace *mnt_userns, struct dentry *dentry, if (!error) { fsnotify_change(dentry, ia_valid); - ima_inode_post_setattr(dentry); + ima_inode_post_setattr(mnt_userns, dentry); evm_inode_post_setattr(dentry, ia_valid); } diff --git a/fs/namei.c b/fs/namei.c index d9ceb75ac169..dbf53b325ac9 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3422,7 +3422,7 @@ struct dentry *vfs_tmpfile(struct user_namespace *mnt_userns, inode->i_state |= I_LINKABLE; spin_unlock(&inode->i_lock); } - ima_post_create_tmpfile(inode); + ima_post_create_tmpfile(mnt_userns, inode); return child; out_err: @@ -3750,7 +3750,7 @@ retry: error = vfs_create(mnt_userns, path.dentry->d_inode, dentry, mode, true); if (!error) - ima_post_path_mknod(dentry); + ima_post_path_mknod(mnt_userns, dentry); break; case S_IFCHR: case S_IFBLK: error = vfs_mknod(mnt_userns, path.dentry->d_inode, diff --git a/include/linux/ima.h b/include/linux/ima.h index 7db9cca1af34..5486312d8ee6 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -16,7 +16,8 @@ struct linux_binprm; #ifdef CONFIG_IMA extern int ima_bprm_check(struct linux_binprm *bprm); extern int ima_file_check(struct file *file, int mask); -extern void ima_post_create_tmpfile(struct inode *inode); +extern void ima_post_create_tmpfile(struct user_namespace *mnt_userns, + struct inode *inode); extern void ima_file_free(struct file *file); extern int ima_file_mmap(struct file *file, unsigned long prot); extern int ima_file_mprotect(struct vm_area_struct *vma, unsigned long prot); @@ -27,7 +28,8 @@ extern int ima_read_file(struct file *file, enum kernel_read_file_id id, bool contents); extern int ima_post_read_file(struct file *file, void *buf, loff_t size, enum kernel_read_file_id id); -extern void ima_post_path_mknod(struct dentry *dentry); +extern void ima_post_path_mknod(struct user_namespace *mnt_userns, + struct dentry *dentry); extern int ima_file_hash(struct file *file, char *buf, size_t buf_size); extern int ima_inode_hash(struct inode *inode, char *buf, size_t buf_size); extern void ima_kexec_cmdline(int kernel_fd, const void *buf, int size); @@ -68,7 +70,8 @@ static inline int ima_file_check(struct file *file, int mask) return 0; } -static inline void ima_post_create_tmpfile(struct inode *inode) +static inline void ima_post_create_tmpfile(struct user_namespace *mnt_userns, + struct inode *inode) { } @@ -112,7 +115,8 @@ static inline int ima_post_read_file(struct file *file, void *buf, loff_t size, return 0; } -static inline void ima_post_path_mknod(struct dentry *dentry) +static inline void ima_post_path_mknod(struct user_namespace *mnt_userns, + struct dentry *dentry) { return; } @@ -153,7 +157,8 @@ static inline void ima_post_key_create_or_update(struct key *keyring, #ifdef CONFIG_IMA_APPRAISE extern bool is_ima_appraise_enabled(void); -extern void ima_inode_post_setattr(struct dentry *dentry); +extern void ima_inode_post_setattr(struct user_namespace *mnt_userns, + struct dentry *dentry); extern int ima_inode_setxattr(struct dentry *dentry, const char *xattr_name, const void *xattr_value, size_t xattr_value_len); extern int ima_inode_removexattr(struct dentry *dentry, const char *xattr_name); @@ -163,7 +168,8 @@ static inline bool is_ima_appraise_enabled(void) return 0; } -static inline void ima_inode_post_setattr(struct dentry *dentry) +static inline void ima_inode_post_setattr(struct user_namespace *mnt_userns, + struct dentry *dentry) { return; } diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h index 8e8b1e3cb847..b87c9006d577 100644 --- a/security/integrity/ima/ima.h +++ b/security/integrity/ima/ima.h @@ -253,8 +253,9 @@ static inline void ima_process_queued_keys(void) {} #endif /* CONFIG_IMA_QUEUE_EARLY_BOOT_KEYS */ /* LIM API function definitions */ -int ima_get_action(struct inode *inode, const struct cred *cred, u32 secid, - int mask, enum ima_hooks func, int *pcr, +int ima_get_action(struct user_namespace *mnt_userns, struct inode *inode, + const struct cred *cred, u32 secid, int mask, + enum ima_hooks func, int *pcr, struct ima_template_desc **template_desc, const char *keyring); int ima_must_measure(struct inode *inode, int mask, enum ima_hooks func); @@ -266,7 +267,8 @@ void ima_store_measurement(struct integrity_iint_cache *iint, struct file *file, struct evm_ima_xattr_data *xattr_value, int xattr_len, const struct modsig *modsig, int pcr, struct ima_template_desc *template_desc); -void process_buffer_measurement(struct inode *inode, const void *buf, int size, +void process_buffer_measurement(struct user_namespace *mnt_userns, + struct inode *inode, const void *buf, int size, const char *eventname, enum ima_hooks func, int pcr, const char *keyring); void ima_audit_measurement(struct integrity_iint_cache *iint, @@ -281,8 +283,9 @@ void ima_free_template_entry(struct ima_template_entry *entry); const char *ima_d_path(const struct path *path, char **pathbuf, char *filename); /* IMA policy related functions */ -int ima_match_policy(struct inode *inode, const struct cred *cred, u32 secid, - enum ima_hooks func, int mask, int flags, int *pcr, +int ima_match_policy(struct user_namespace *mnt_userns, struct inode *inode, + const struct cred *cred, u32 secid, enum ima_hooks func, + int mask, int flags, int *pcr, struct ima_template_desc **template_desc, const char *keyring); void ima_init_policy(void); @@ -313,7 +316,8 @@ int ima_appraise_measurement(enum ima_hooks func, struct file *file, const unsigned char *filename, struct evm_ima_xattr_data *xattr_value, int xattr_len, const struct modsig *modsig); -int ima_must_appraise(struct inode *inode, int mask, enum ima_hooks func); +int ima_must_appraise(struct user_namespace *mnt_userns, struct inode *inode, + int mask, enum ima_hooks func); void ima_update_xattr(struct integrity_iint_cache *iint, struct file *file); enum integrity_status ima_get_cache_status(struct integrity_iint_cache *iint, enum ima_hooks func); @@ -340,7 +344,8 @@ static inline int ima_appraise_measurement(enum ima_hooks func, return INTEGRITY_UNKNOWN; } -static inline int ima_must_appraise(struct inode *inode, int mask, +static inline int ima_must_appraise(struct user_namespace *mnt_userns, + struct inode *inode, int mask, enum ima_hooks func) { return 0; diff --git a/security/integrity/ima/ima_api.c b/security/integrity/ima/ima_api.c index 4f39fb93f278..ed410efb3597 100644 --- a/security/integrity/ima/ima_api.c +++ b/security/integrity/ima/ima_api.c @@ -162,6 +162,7 @@ err_out: /** * ima_get_action - appraise & measure decision based on policy. + * @mnt_userns: user namespace of the mount the inode was found from * @inode: pointer to the inode associated with the object being validated * @cred: pointer to credentials structure to validate * @secid: secid of the task being validated @@ -183,8 +184,9 @@ err_out: * Returns IMA_MEASURE, IMA_APPRAISE mask. * */ -int ima_get_action(struct inode *inode, const struct cred *cred, u32 secid, - int mask, enum ima_hooks func, int *pcr, +int ima_get_action(struct user_namespace *mnt_userns, struct inode *inode, + const struct cred *cred, u32 secid, int mask, + enum ima_hooks func, int *pcr, struct ima_template_desc **template_desc, const char *keyring) { @@ -192,8 +194,8 @@ int ima_get_action(struct inode *inode, const struct cred *cred, u32 secid, flags &= ima_policy_flag; - return ima_match_policy(inode, cred, secid, func, mask, flags, pcr, - template_desc, keyring); + return ima_match_policy(mnt_userns, inode, cred, secid, func, mask, + flags, pcr, template_desc, keyring); } /* diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c index 70b643c41c6b..2e64b9f281cc 100644 --- a/security/integrity/ima/ima_appraise.c +++ b/security/integrity/ima/ima_appraise.c @@ -68,7 +68,8 @@ bool is_ima_appraise_enabled(void) * * Return 1 to appraise or hash */ -int ima_must_appraise(struct inode *inode, int mask, enum ima_hooks func) +int ima_must_appraise(struct user_namespace *mnt_userns, struct inode *inode, + int mask, enum ima_hooks func) { u32 secid; @@ -76,8 +77,8 @@ int ima_must_appraise(struct inode *inode, int mask, enum ima_hooks func) return 0; security_task_getsecid(current, &secid); - return ima_match_policy(inode, current_cred(), secid, func, mask, - IMA_APPRAISE | IMA_HASH, NULL, NULL, NULL); + return ima_match_policy(mnt_userns, inode, current_cred(), secid, func, + mask, IMA_APPRAISE | IMA_HASH, NULL, NULL, NULL); } static int ima_fix_xattr(struct dentry *dentry, @@ -350,7 +351,7 @@ int ima_check_blacklist(struct integrity_iint_cache *iint, rc = is_binary_blacklisted(digest, digestsize); if ((rc == -EPERM) && (iint->flags & IMA_MEASURE)) - process_buffer_measurement(NULL, digest, digestsize, + process_buffer_measurement(&init_user_ns, NULL, digest, digestsize, "blacklisted-hash", NONE, pcr, NULL); } @@ -501,6 +502,7 @@ void ima_update_xattr(struct integrity_iint_cache *iint, struct file *file) /** * ima_inode_post_setattr - reflect file metadata changes + * @mnt_userns: user namespace of the mount the inode was found from * @dentry: pointer to the affected dentry * * Changes to a dentry's metadata might result in needing to appraise. @@ -508,7 +510,8 @@ void ima_update_xattr(struct integrity_iint_cache *iint, struct file *file) * This function is called from notify_change(), which expects the caller * to lock the inode's i_mutex. */ -void ima_inode_post_setattr(struct dentry *dentry) +void ima_inode_post_setattr(struct user_namespace *mnt_userns, + struct dentry *dentry) { struct inode *inode = d_backing_inode(dentry); struct integrity_iint_cache *iint; @@ -518,7 +521,7 @@ void ima_inode_post_setattr(struct dentry *dentry) || !(inode->i_opflags & IOP_XATTR)) return; - action = ima_must_appraise(inode, MAY_ACCESS, POST_SETATTR); + action = ima_must_appraise(mnt_userns, inode, MAY_ACCESS, POST_SETATTR); if (!action) __vfs_removexattr(&init_user_ns, dentry, XATTR_NAME_IMA); iint = integrity_iint_find(inode); diff --git a/security/integrity/ima/ima_asymmetric_keys.c b/security/integrity/ima/ima_asymmetric_keys.c index 1c68c500c26f..c4ef69100789 100644 --- a/security/integrity/ima/ima_asymmetric_keys.c +++ b/security/integrity/ima/ima_asymmetric_keys.c @@ -10,6 +10,7 @@ */ #include +#include #include "ima.h" /** @@ -58,7 +59,7 @@ void ima_post_key_create_or_update(struct key *keyring, struct key *key, * if the IMA policy is configured to measure a key linked * to the given keyring. */ - process_buffer_measurement(NULL, payload, payload_len, + process_buffer_measurement(&init_user_ns, NULL, payload, payload_len, keyring->description, KEY_CHECK, 0, keyring->description); } diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c index f87cb29329e9..cb1c56eccd6d 100644 --- a/security/integrity/ima/ima_main.c +++ b/security/integrity/ima/ima_main.c @@ -218,8 +218,8 @@ static int process_measurement(struct file *file, const struct cred *cred, * bitmask based on the appraise/audit/measurement policy. * Included is the appraise submask. */ - action = ima_get_action(inode, cred, secid, mask, func, &pcr, - &template_desc, NULL); + action = ima_get_action(file_mnt_user_ns(file), inode, cred, secid, + mask, func, &pcr, &template_desc, NULL); violation_check = ((func == FILE_CHECK || func == MMAP_CHECK) && (ima_policy_flag & IMA_MEASURE)); if (!action && !violation_check) @@ -431,8 +431,9 @@ int ima_file_mprotect(struct vm_area_struct *vma, unsigned long prot) security_task_getsecid(current, &secid); inode = file_inode(vma->vm_file); - action = ima_get_action(inode, current_cred(), secid, MAY_EXEC, - MMAP_CHECK, &pcr, &template, 0); + action = ima_get_action(file_mnt_user_ns(vma->vm_file), inode, + current_cred(), secid, MAY_EXEC, MMAP_CHECK, + &pcr, &template, 0); /* Is the mmap'ed file in policy? */ if (!(action & (IMA_MEASURE | IMA_APPRAISE_SUBMASK))) @@ -592,18 +593,21 @@ EXPORT_SYMBOL_GPL(ima_inode_hash); /** * ima_post_create_tmpfile - mark newly created tmpfile as new + * @mnt_userns: user namespace of the mount the inode was found from * @file : newly created tmpfile * * No measuring, appraising or auditing of newly created tmpfiles is needed. * Skip calling process_measurement(), but indicate which newly, created * tmpfiles are in policy. */ -void ima_post_create_tmpfile(struct inode *inode) +void ima_post_create_tmpfile(struct user_namespace *mnt_userns, + struct inode *inode) { struct integrity_iint_cache *iint; int must_appraise; - must_appraise = ima_must_appraise(inode, MAY_ACCESS, FILE_CHECK); + must_appraise = ima_must_appraise(mnt_userns, inode, MAY_ACCESS, + FILE_CHECK); if (!must_appraise) return; @@ -619,18 +623,21 @@ void ima_post_create_tmpfile(struct inode *inode) /** * ima_post_path_mknod - mark as a new inode + * @mnt_userns: user namespace of the mount the inode was found from * @dentry: newly created dentry * * Mark files created via the mknodat syscall as new, so that the * file data can be written later. */ -void ima_post_path_mknod(struct dentry *dentry) +void ima_post_path_mknod(struct user_namespace *mnt_userns, + struct dentry *dentry) { struct integrity_iint_cache *iint; struct inode *inode = dentry->d_inode; int must_appraise; - must_appraise = ima_must_appraise(inode, MAY_ACCESS, FILE_CHECK); + must_appraise = ima_must_appraise(mnt_userns, inode, MAY_ACCESS, + FILE_CHECK); if (!must_appraise) return; @@ -810,6 +817,7 @@ int ima_post_load_data(char *buf, loff_t size, /* * process_buffer_measurement - Measure the buffer to ima log. + * @mnt_userns: user namespace of the mount the inode was found from * @inode: inode associated with the object being measured (NULL for KEY_CHECK) * @buf: pointer to the buffer that needs to be added to the log. * @size: size of buffer(in bytes). @@ -820,7 +828,8 @@ int ima_post_load_data(char *buf, loff_t size, * * Based on policy, the buffer is measured into the ima log. */ -void process_buffer_measurement(struct inode *inode, const void *buf, int size, +void process_buffer_measurement(struct user_namespace *mnt_userns, + struct inode *inode, const void *buf, int size, const char *eventname, enum ima_hooks func, int pcr, const char *keyring) { @@ -860,8 +869,9 @@ void process_buffer_measurement(struct inode *inode, const void *buf, int size, */ if (func) { security_task_getsecid(current, &secid); - action = ima_get_action(inode, current_cred(), secid, 0, func, - &pcr, &template, keyring); + action = ima_get_action(mnt_userns, inode, current_cred(), + secid, 0, func, &pcr, &template, + keyring); if (!(action & IMA_MEASURE)) return; } @@ -919,8 +929,9 @@ void ima_kexec_cmdline(int kernel_fd, const void *buf, int size) if (!f.file) return; - process_buffer_measurement(file_inode(f.file), buf, size, - "kexec-cmdline", KEXEC_CMDLINE, 0, NULL); + process_buffer_measurement(file_mnt_user_ns(f.file), file_inode(f.file), + buf, size, "kexec-cmdline", KEXEC_CMDLINE, 0, + NULL); fdput(f); } diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c index 823a0c1379cb..e14426c24a19 100644 --- a/security/integrity/ima/ima_policy.c +++ b/security/integrity/ima/ima_policy.c @@ -488,6 +488,7 @@ static bool ima_match_keyring(struct ima_rule_entry *rule, /** * ima_match_rules - determine whether an inode matches the policy rule. * @rule: a pointer to a rule + * @mnt_userns: user namespace of the mount the inode was found from * @inode: a pointer to an inode * @cred: a pointer to a credentials structure for user validation * @secid: the secid of the task to be validated @@ -497,9 +498,10 @@ static bool ima_match_keyring(struct ima_rule_entry *rule, * * Returns true on rule match, false on failure. */ -static bool ima_match_rules(struct ima_rule_entry *rule, struct inode *inode, - const struct cred *cred, u32 secid, - enum ima_hooks func, int mask, +static bool ima_match_rules(struct ima_rule_entry *rule, + struct user_namespace *mnt_userns, + struct inode *inode, const struct cred *cred, + u32 secid, enum ima_hooks func, int mask, const char *keyring) { int i; @@ -539,7 +541,7 @@ static bool ima_match_rules(struct ima_rule_entry *rule, struct inode *inode, } if ((rule->flags & IMA_FOWNER) && - !rule->fowner_op(inode->i_uid, rule->fowner)) + !rule->fowner_op(i_uid_into_mnt(mnt_userns, inode), rule->fowner)) return false; for (i = 0; i < MAX_LSM_RULES; i++) { int rc = 0; @@ -602,6 +604,7 @@ static int get_subaction(struct ima_rule_entry *rule, enum ima_hooks func) /** * ima_match_policy - decision based on LSM and other conditions + * @mnt_userns: user namespace of the mount the inode was found from * @inode: pointer to an inode for which the policy decision is being made * @cred: pointer to a credentials structure for which the policy decision is * being made @@ -620,8 +623,9 @@ static int get_subaction(struct ima_rule_entry *rule, enum ima_hooks func) * list when walking it. Reads are many orders of magnitude more numerous * than writes so ima_match_policy() is classical RCU candidate. */ -int ima_match_policy(struct inode *inode, const struct cred *cred, u32 secid, - enum ima_hooks func, int mask, int flags, int *pcr, +int ima_match_policy(struct user_namespace *mnt_userns, struct inode *inode, + const struct cred *cred, u32 secid, enum ima_hooks func, + int mask, int flags, int *pcr, struct ima_template_desc **template_desc, const char *keyring) { @@ -637,8 +641,8 @@ int ima_match_policy(struct inode *inode, const struct cred *cred, u32 secid, if (!(entry->action & actmask)) continue; - if (!ima_match_rules(entry, inode, cred, secid, func, mask, - keyring)) + if (!ima_match_rules(entry, mnt_userns, inode, cred, secid, + func, mask, keyring)) continue; action |= entry->flags & IMA_ACTION_FLAGS; diff --git a/security/integrity/ima/ima_queue_keys.c b/security/integrity/ima/ima_queue_keys.c index 69a8626a35c0..ca3dea19da18 100644 --- a/security/integrity/ima/ima_queue_keys.c +++ b/security/integrity/ima/ima_queue_keys.c @@ -8,6 +8,7 @@ * Enables deferred processing of keys */ +#include #include #include #include "ima.h" @@ -158,7 +159,8 @@ void ima_process_queued_keys(void) list_for_each_entry_safe(entry, tmp, &ima_keys, list) { if (!timer_expired) - process_buffer_measurement(NULL, entry->payload, + process_buffer_measurement(&init_user_ns, NULL, + entry->payload, entry->payload_len, entry->keyring_name, KEY_CHECK, 0, -- cgit v1.2.3 From 2a1867219c7b27f928e2545782b86daaf9ad50bd Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 21 Jan 2021 14:19:53 +0100 Subject: fs: add mount_setattr() This implements the missing mount_setattr() syscall. While the new mount api allows to change the properties of a superblock there is currently no way to change the properties of a mount or a mount tree using file descriptors which the new mount api is based on. In addition the old mount api has the restriction that mount options cannot be applied recursively. This hasn't changed since changing mount options on a per-mount basis was implemented in [1] and has been a frequent request not just for convenience but also for security reasons. The legacy mount syscall is unable to accommodate this behavior without introducing a whole new set of flags because MS_REC | MS_REMOUNT | MS_BIND | MS_RDONLY | MS_NOEXEC | [...] only apply the mount option to the topmost mount. Changing MS_REC to apply to the whole mount tree would mean introducing a significant uapi change and would likely cause significant regressions. The new mount_setattr() syscall allows to recursively clear and set mount options in one shot. Multiple calls to change mount options requesting the same changes are idempotent: int mount_setattr(int dfd, const char *path, unsigned flags, struct mount_attr *uattr, size_t usize); Flags to modify path resolution behavior are specified in the @flags argument. Currently, AT_EMPTY_PATH, AT_RECURSIVE, AT_SYMLINK_NOFOLLOW, and AT_NO_AUTOMOUNT are supported. If useful, additional lookup flags to restrict path resolution as introduced with openat2() might be supported in the future. The mount_setattr() syscall can be expected to grow over time and is designed with extensibility in mind. It follows the extensible syscall pattern we have used with other syscalls such as openat2(), clone3(), sched_{set,get}attr(), and others. The set of mount options is passed in the uapi struct mount_attr which currently has the following layout: struct mount_attr { __u64 attr_set; __u64 attr_clr; __u64 propagation; __u64 userns_fd; }; The @attr_set and @attr_clr members are used to clear and set mount options. This way a user can e.g. request that a set of flags is to be raised such as turning mounts readonly by raising MOUNT_ATTR_RDONLY in @attr_set while at the same time requesting that another set of flags is to be lowered such as removing noexec from a mount tree by specifying MOUNT_ATTR_NOEXEC in @attr_clr. Note, since the MOUNT_ATTR_ values are an enum starting from 0, not a bitmap, users wanting to transition to a different atime setting cannot simply specify the atime setting in @attr_set, but must also specify MOUNT_ATTR__ATIME in the @attr_clr field. So we ensure that MOUNT_ATTR__ATIME can't be partially set in @attr_clr and that @attr_set can't have any atime bits set if MOUNT_ATTR__ATIME isn't set in @attr_clr. The @propagation field lets callers specify the propagation type of a mount tree. Propagation is a single property that has four different settings and as such is not really a flag argument but an enum. Specifically, it would be unclear what setting and clearing propagation settings in combination would amount to. The legacy mount() syscall thus forbids the combination of multiple propagation settings too. The goal is to keep the semantics of mount propagation somewhat simple as they are overly complex as it is. The @userns_fd field lets user specify a user namespace whose idmapping becomes the idmapping of the mount. This is implemented and explained in detail in the next patch. [1]: commit 2e4b7fcd9260 ("[PATCH] r/o bind mounts: honor mount writer counts at remount") Link: https://lore.kernel.org/r/20210121131959.646623-35-christian.brauner@ubuntu.com Cc: David Howells Cc: Aleksa Sarai Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Cc: linux-api@vger.kernel.org Reviewed-by: Christoph Hellwig Signed-off-by: Christian Brauner --- arch/alpha/kernel/syscalls/syscall.tbl | 1 + arch/arm/tools/syscall.tbl | 1 + arch/arm64/include/asm/unistd.h | 2 +- arch/arm64/include/asm/unistd32.h | 2 + arch/ia64/kernel/syscalls/syscall.tbl | 1 + arch/m68k/kernel/syscalls/syscall.tbl | 1 + arch/microblaze/kernel/syscalls/syscall.tbl | 1 + arch/mips/kernel/syscalls/syscall_n32.tbl | 1 + arch/mips/kernel/syscalls/syscall_n64.tbl | 1 + arch/mips/kernel/syscalls/syscall_o32.tbl | 1 + arch/parisc/kernel/syscalls/syscall.tbl | 1 + arch/powerpc/kernel/syscalls/syscall.tbl | 1 + arch/s390/kernel/syscalls/syscall.tbl | 1 + arch/sh/kernel/syscalls/syscall.tbl | 1 + arch/sparc/kernel/syscalls/syscall.tbl | 1 + arch/x86/entry/syscalls/syscall_32.tbl | 1 + arch/x86/entry/syscalls/syscall_64.tbl | 1 + arch/xtensa/kernel/syscalls/syscall.tbl | 1 + fs/namespace.c | 263 ++++++++++++++++++++++++++++ include/linux/syscalls.h | 4 + include/uapi/asm-generic/unistd.h | 4 +- include/uapi/linux/mount.h | 15 ++ tools/include/uapi/asm-generic/unistd.h | 4 +- 23 files changed, 307 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl index a6617067dbe6..02f0244e005c 100644 --- a/arch/alpha/kernel/syscalls/syscall.tbl +++ b/arch/alpha/kernel/syscalls/syscall.tbl @@ -481,3 +481,4 @@ 549 common faccessat2 sys_faccessat2 550 common process_madvise sys_process_madvise 551 common epoll_pwait2 sys_epoll_pwait2 +552 common mount_setattr sys_mount_setattr diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl index 20e1170e2e0a..dcc1191291a2 100644 --- a/arch/arm/tools/syscall.tbl +++ b/arch/arm/tools/syscall.tbl @@ -455,3 +455,4 @@ 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h index 86a9d7b3eabe..949788f5ba40 100644 --- a/arch/arm64/include/asm/unistd.h +++ b/arch/arm64/include/asm/unistd.h @@ -38,7 +38,7 @@ #define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE + 5) #define __ARM_NR_COMPAT_END (__ARM_NR_COMPAT_BASE + 0x800) -#define __NR_compat_syscalls 442 +#define __NR_compat_syscalls 443 #endif #define __ARCH_WANT_SYS_CLONE diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index cccfbbefbf95..3d874f624056 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -891,6 +891,8 @@ __SYSCALL(__NR_faccessat2, sys_faccessat2) __SYSCALL(__NR_process_madvise, sys_process_madvise) #define __NR_epoll_pwait2 441 __SYSCALL(__NR_epoll_pwait2, compat_sys_epoll_pwait2) +#define __NR_mount_setattr 442 +__SYSCALL(__NR_mount_setattr, sys_mount_setattr) /* * Please add new compat syscalls above this comment and update diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl index bfc00f2bd437..d89231166e19 100644 --- a/arch/ia64/kernel/syscalls/syscall.tbl +++ b/arch/ia64/kernel/syscalls/syscall.tbl @@ -362,3 +362,4 @@ 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl index 7fe4e45c864c..72bde6707dd3 100644 --- a/arch/m68k/kernel/syscalls/syscall.tbl +++ b/arch/m68k/kernel/syscalls/syscall.tbl @@ -441,3 +441,4 @@ 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl index a522adf194ab..d603a5ec9338 100644 --- a/arch/microblaze/kernel/syscalls/syscall.tbl +++ b/arch/microblaze/kernel/syscalls/syscall.tbl @@ -447,3 +447,4 @@ 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl index 0f03ad223f33..8fd8c1790941 100644 --- a/arch/mips/kernel/syscalls/syscall_n32.tbl +++ b/arch/mips/kernel/syscalls/syscall_n32.tbl @@ -380,3 +380,4 @@ 439 n32 faccessat2 sys_faccessat2 440 n32 process_madvise sys_process_madvise 441 n32 epoll_pwait2 compat_sys_epoll_pwait2 +442 n32 mount_setattr sys_mount_setattr diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl index 91649690b52f..169f21438065 100644 --- a/arch/mips/kernel/syscalls/syscall_n64.tbl +++ b/arch/mips/kernel/syscalls/syscall_n64.tbl @@ -356,3 +356,4 @@ 439 n64 faccessat2 sys_faccessat2 440 n64 process_madvise sys_process_madvise 441 n64 epoll_pwait2 sys_epoll_pwait2 +442 n64 mount_setattr sys_mount_setattr diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index 4bad0c40aed6..090d29ca80ff 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -429,3 +429,4 @@ 439 o32 faccessat2 sys_faccessat2 440 o32 process_madvise sys_process_madvise 441 o32 epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 +442 o32 mount_setattr sys_mount_setattr diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl index 6bcc31966b44..271a92519683 100644 --- a/arch/parisc/kernel/syscalls/syscall.tbl +++ b/arch/parisc/kernel/syscalls/syscall.tbl @@ -439,3 +439,4 @@ 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index f744eb5cba88..72e5aa67ab8a 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -531,3 +531,4 @@ 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index d443423495e5..3abef2144dac 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -444,3 +444,4 @@ 439 common faccessat2 sys_faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr sys_mount_setattr diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl index 9df40ac0ebc0..d08eebad6b7f 100644 --- a/arch/sh/kernel/syscalls/syscall.tbl +++ b/arch/sh/kernel/syscalls/syscall.tbl @@ -444,3 +444,4 @@ 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl index 40d8c7cd8298..84403a99039c 100644 --- a/arch/sparc/kernel/syscalls/syscall.tbl +++ b/arch/sparc/kernel/syscalls/syscall.tbl @@ -487,3 +487,4 @@ 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 874aeacde2dd..a1c9f496fca6 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -446,3 +446,4 @@ 439 i386 faccessat2 sys_faccessat2 440 i386 process_madvise sys_process_madvise 441 i386 epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 +442 i386 mount_setattr sys_mount_setattr diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index 78672124d28b..7bf01cbe582f 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -363,6 +363,7 @@ 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr # # Due to a historical design error, certain syscalls are numbered differently diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl index 46116a28eeed..365a9b849224 100644 --- a/arch/xtensa/kernel/syscalls/syscall.tbl +++ b/arch/xtensa/kernel/syscalls/syscall.tbl @@ -412,3 +412,4 @@ 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr diff --git a/fs/namespace.c b/fs/namespace.c index 00ed0d6cb2ee..726a51c8c46e 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -73,6 +73,14 @@ static DECLARE_RWSEM(namespace_sem); static HLIST_HEAD(unmounted); /* protected by namespace_sem */ static LIST_HEAD(ex_mountpoints); /* protected by namespace_sem */ +struct mount_kattr { + unsigned int attr_set; + unsigned int attr_clr; + unsigned int propagation; + unsigned int lookup_flags; + bool recurse; +}; + /* /sys/fs */ struct kobject *fs_kobj; EXPORT_SYMBOL_GPL(fs_kobj); @@ -3469,6 +3477,11 @@ out_type: (MOUNT_ATTR_RDONLY | MOUNT_ATTR_NOSUID | MOUNT_ATTR_NODEV | \ MOUNT_ATTR_NOEXEC | MOUNT_ATTR__ATIME | MOUNT_ATTR_NODIRATIME) +#define MOUNT_SETATTR_VALID_FLAGS FSMOUNT_VALID_FLAGS + +#define MOUNT_SETATTR_PROPAGATION_FLAGS \ + (MS_UNBINDABLE | MS_PRIVATE | MS_SLAVE | MS_SHARED) + static unsigned int attr_flags_to_mnt_flags(u64 attr_flags) { unsigned int mnt_flags = 0; @@ -3820,6 +3833,256 @@ out0: return error; } +static unsigned int recalc_flags(struct mount_kattr *kattr, struct mount *mnt) +{ + unsigned int flags = mnt->mnt.mnt_flags; + + /* flags to clear */ + flags &= ~kattr->attr_clr; + /* flags to raise */ + flags |= kattr->attr_set; + + return flags; +} + +static struct mount *mount_setattr_prepare(struct mount_kattr *kattr, + struct mount *mnt, int *err) +{ + struct mount *m = mnt, *last = NULL; + + if (!is_mounted(&m->mnt)) { + *err = -EINVAL; + goto out; + } + + if (!(mnt_has_parent(m) ? check_mnt(m) : is_anon_ns(m->mnt_ns))) { + *err = -EINVAL; + goto out; + } + + do { + unsigned int flags; + + flags = recalc_flags(kattr, m); + if (!can_change_locked_flags(m, flags)) { + *err = -EPERM; + goto out; + } + + last = m; + + if ((kattr->attr_set & MNT_READONLY) && + !(m->mnt.mnt_flags & MNT_READONLY)) { + *err = mnt_hold_writers(m); + if (*err) + goto out; + } + } while (kattr->recurse && (m = next_mnt(m, mnt))); + +out: + return last; +} + +static void mount_setattr_commit(struct mount_kattr *kattr, + struct mount *mnt, struct mount *last, + int err) +{ + struct mount *m = mnt; + + do { + if (!err) { + unsigned int flags; + + flags = recalc_flags(kattr, m); + WRITE_ONCE(m->mnt.mnt_flags, flags); + } + + /* + * We either set MNT_READONLY above so make it visible + * before ~MNT_WRITE_HOLD or we failed to recursively + * apply mount options. + */ + if ((kattr->attr_set & MNT_READONLY) && + (m->mnt.mnt_flags & MNT_WRITE_HOLD)) + mnt_unhold_writers(m); + + if (!err && kattr->propagation) + change_mnt_propagation(m, kattr->propagation); + + /* + * On failure, only cleanup until we found the first mount + * we failed to handle. + */ + if (err && m == last) + break; + } while (kattr->recurse && (m = next_mnt(m, mnt))); + + if (!err) + touch_mnt_namespace(mnt->mnt_ns); +} + +static int do_mount_setattr(struct path *path, struct mount_kattr *kattr) +{ + struct mount *mnt = real_mount(path->mnt), *last = NULL; + int err = 0; + + if (path->dentry != mnt->mnt.mnt_root) + return -EINVAL; + + if (kattr->propagation) { + /* + * Only take namespace_lock() if we're actually changing + * propagation. + */ + namespace_lock(); + if (kattr->propagation == MS_SHARED) { + err = invent_group_ids(mnt, kattr->recurse); + if (err) { + namespace_unlock(); + return err; + } + } + } + + lock_mount_hash(); + + /* + * Get the mount tree in a shape where we can change mount + * properties without failure. + */ + last = mount_setattr_prepare(kattr, mnt, &err); + if (last) /* Commit all changes or revert to the old state. */ + mount_setattr_commit(kattr, mnt, last, err); + + unlock_mount_hash(); + + if (kattr->propagation) { + namespace_unlock(); + if (err) + cleanup_group_ids(mnt, NULL); + } + + return err; +} + +static int build_mount_kattr(const struct mount_attr *attr, + struct mount_kattr *kattr, unsigned int flags) +{ + unsigned int lookup_flags = LOOKUP_AUTOMOUNT | LOOKUP_FOLLOW; + + if (flags & AT_NO_AUTOMOUNT) + lookup_flags &= ~LOOKUP_AUTOMOUNT; + if (flags & AT_SYMLINK_NOFOLLOW) + lookup_flags &= ~LOOKUP_FOLLOW; + if (flags & AT_EMPTY_PATH) + lookup_flags |= LOOKUP_EMPTY; + + *kattr = (struct mount_kattr) { + .lookup_flags = lookup_flags, + .recurse = !!(flags & AT_RECURSIVE), + }; + + if (attr->propagation & ~MOUNT_SETATTR_PROPAGATION_FLAGS) + return -EINVAL; + if (hweight32(attr->propagation & MOUNT_SETATTR_PROPAGATION_FLAGS) > 1) + return -EINVAL; + kattr->propagation = attr->propagation; + + if ((attr->attr_set | attr->attr_clr) & ~MOUNT_SETATTR_VALID_FLAGS) + return -EINVAL; + + if (attr->userns_fd) + return -EINVAL; + + kattr->attr_set = attr_flags_to_mnt_flags(attr->attr_set); + kattr->attr_clr = attr_flags_to_mnt_flags(attr->attr_clr); + + /* + * Since the MOUNT_ATTR_ values are an enum, not a bitmap, + * users wanting to transition to a different atime setting cannot + * simply specify the atime setting in @attr_set, but must also + * specify MOUNT_ATTR__ATIME in the @attr_clr field. + * So ensure that MOUNT_ATTR__ATIME can't be partially set in + * @attr_clr and that @attr_set can't have any atime bits set if + * MOUNT_ATTR__ATIME isn't set in @attr_clr. + */ + if (attr->attr_clr & MOUNT_ATTR__ATIME) { + if ((attr->attr_clr & MOUNT_ATTR__ATIME) != MOUNT_ATTR__ATIME) + return -EINVAL; + + /* + * Clear all previous time settings as they are mutually + * exclusive. + */ + kattr->attr_clr |= MNT_RELATIME | MNT_NOATIME; + switch (attr->attr_set & MOUNT_ATTR__ATIME) { + case MOUNT_ATTR_RELATIME: + kattr->attr_set |= MNT_RELATIME; + break; + case MOUNT_ATTR_NOATIME: + kattr->attr_set |= MNT_NOATIME; + break; + case MOUNT_ATTR_STRICTATIME: + break; + default: + return -EINVAL; + } + } else { + if (attr->attr_set & MOUNT_ATTR__ATIME) + return -EINVAL; + } + + return 0; +} + +SYSCALL_DEFINE5(mount_setattr, int, dfd, const char __user *, path, + unsigned int, flags, struct mount_attr __user *, uattr, + size_t, usize) +{ + int err; + struct path target; + struct mount_attr attr; + struct mount_kattr kattr; + + BUILD_BUG_ON(sizeof(struct mount_attr) != MOUNT_ATTR_SIZE_VER0); + + if (flags & ~(AT_EMPTY_PATH | + AT_RECURSIVE | + AT_SYMLINK_NOFOLLOW | + AT_NO_AUTOMOUNT)) + return -EINVAL; + + if (unlikely(usize > PAGE_SIZE)) + return -E2BIG; + if (unlikely(usize < MOUNT_ATTR_SIZE_VER0)) + return -EINVAL; + + if (!may_mount()) + return -EPERM; + + err = copy_struct_from_user(&attr, sizeof(attr), uattr, usize); + if (err) + return err; + + /* Don't bother walking through the mounts if this is a nop. */ + if (attr.attr_set == 0 && + attr.attr_clr == 0 && + attr.propagation == 0) + return 0; + + err = build_mount_kattr(&attr, &kattr, flags); + if (err) + return err; + + err = user_path_at(dfd, path, kattr.lookup_flags, &target); + if (err) + return err; + + err = do_mount_setattr(&target, &kattr); + path_put(&target); + return err; +} + static void __init init_mount_tree(void) { struct vfsmount *mnt; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 7688bc983de5..cd7b5c817ba2 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -68,6 +68,7 @@ union bpf_attr; struct io_uring_params; struct clone_args; struct open_how; +struct mount_attr; #include #include @@ -1028,6 +1029,9 @@ asmlinkage long sys_open_tree(int dfd, const char __user *path, unsigned flags); asmlinkage long sys_move_mount(int from_dfd, const char __user *from_path, int to_dfd, const char __user *to_path, unsigned int ms_flags); +asmlinkage long sys_mount_setattr(int dfd, const char __user *path, + unsigned int flags, + struct mount_attr __user *uattr, size_t usize); asmlinkage long sys_fsopen(const char __user *fs_name, unsigned int flags); asmlinkage long sys_fsconfig(int fs_fd, unsigned int cmd, const char __user *key, const void __user *value, int aux); diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 728752917785..ce58cff99b66 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -861,9 +861,11 @@ __SYSCALL(__NR_faccessat2, sys_faccessat2) __SYSCALL(__NR_process_madvise, sys_process_madvise) #define __NR_epoll_pwait2 441 __SC_COMP(__NR_epoll_pwait2, sys_epoll_pwait2, compat_sys_epoll_pwait2) +#define __NR_mount_setattr 442 +__SYSCALL(__NR_mount_setattr, sys_mount_setattr) #undef __NR_syscalls -#define __NR_syscalls 442 +#define __NR_syscalls 443 /* * 32 bit systems traditionally used different diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h index dd8306ea336c..d3bcefdfa73d 100644 --- a/include/uapi/linux/mount.h +++ b/include/uapi/linux/mount.h @@ -1,6 +1,8 @@ #ifndef _UAPI_LINUX_MOUNT_H #define _UAPI_LINUX_MOUNT_H +#include + /* * These are the fs-independent mount-flags: up to 32 flags are supported * @@ -118,4 +120,17 @@ enum fsconfig_command { #define MOUNT_ATTR_STRICTATIME 0x00000020 /* - Always perform atime updates */ #define MOUNT_ATTR_NODIRATIME 0x00000080 /* Do not update directory access times */ +/* + * mount_setattr() + */ +struct mount_attr { + __u64 attr_set; + __u64 attr_clr; + __u64 propagation; + __u64 userns_fd; +}; + +/* List of all mount_attr versions. */ +#define MOUNT_ATTR_SIZE_VER0 32 /* sizeof first published struct */ + #endif /* _UAPI_LINUX_MOUNT_H */ diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index 728752917785..ce58cff99b66 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -861,9 +861,11 @@ __SYSCALL(__NR_faccessat2, sys_faccessat2) __SYSCALL(__NR_process_madvise, sys_process_madvise) #define __NR_epoll_pwait2 441 __SC_COMP(__NR_epoll_pwait2, sys_epoll_pwait2, compat_sys_epoll_pwait2) +#define __NR_mount_setattr 442 +__SYSCALL(__NR_mount_setattr, sys_mount_setattr) #undef __NR_syscalls -#define __NR_syscalls 442 +#define __NR_syscalls 443 /* * 32 bit systems traditionally used different -- cgit v1.2.3 From 9caccd41541a6f7d6279928d9f971f6642c361af Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 21 Jan 2021 14:19:54 +0100 Subject: fs: introduce MOUNT_ATTR_IDMAP MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Introduce a new mount bind mount property to allow idmapping mounts. The MOUNT_ATTR_IDMAP flag can be set via the new mount_setattr() syscall together with a file descriptor referring to a user namespace. The user namespace referenced by the namespace file descriptor will be attached to the bind mount. All interactions with the filesystem going through that mount will be mapped according to the mapping specified in the user namespace attached to it. Using user namespaces to mark mounts means we can reuse all the existing infrastructure in the kernel that already exists to handle idmappings and can also use this for permission checking to allow unprivileged user to create idmapped mounts in the future. Idmapping a mount is decoupled from the caller's user and mount namespace. This means idmapped mounts can be created in the initial user namespace which is an important use-case for systemd-homed, portable usb-sticks between systems, sharing data between the initial user namespace and unprivileged containers, and other use-cases that have been brought up. For example, assume a home directory where all files are owned by uid and gid 1000 and the home directory is brought to a new laptop where the user has id 12345. The system administrator can simply create a mount of this home directory with a mapping of 1000:12345:1 and other mappings to indicate the ids should be kept. (With this it is e.g. also possible to create idmapped mounts on the host with an identity mapping 1:1:100000 where the root user is not mapped. A user with root access that e.g. has been pivot rooted into such a mount on the host will be not be able to execute, read, write, or create files as root.) Given that mapping a mount is decoupled from the caller's user namespace a sufficiently privileged process such as a container manager can set up an idmapped mount for the container and the container can simply pivot root to it. There's no need for the container to do anything. The mount will appear correctly mapped independent of the user namespace the container uses. This means we don't need to mark a mount as idmappable. In order to create an idmapped mount the caller must currently be privileged in the user namespace of the superblock the mount belongs to. Once a mount has been idmapped we don't allow it to change its mapping. This keeps permission checking and life-cycle management simple. Users wanting to change the idmapped can always create a new detached mount with a different idmapping. Link: https://lore.kernel.org/r/20210121131959.646623-36-christian.brauner@ubuntu.com Cc: Christoph Hellwig Cc: David Howells Cc: Mauricio Vásquez Bernal Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig Signed-off-by: Christian Brauner --- fs/namespace.c | 122 ++++++++++++++++++++++++++++++++++++++++++--- fs/proc_namespace.c | 3 ++ include/linux/mount.h | 3 +- include/uapi/linux/mount.h | 1 + 4 files changed, 121 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/fs/namespace.c b/fs/namespace.c index 726a51c8c46e..062fe984a697 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include #include @@ -79,6 +80,7 @@ struct mount_kattr { unsigned int propagation; unsigned int lookup_flags; bool recurse; + struct user_namespace *mnt_userns; }; /* /sys/fs */ @@ -3477,7 +3479,7 @@ out_type: (MOUNT_ATTR_RDONLY | MOUNT_ATTR_NOSUID | MOUNT_ATTR_NODEV | \ MOUNT_ATTR_NOEXEC | MOUNT_ATTR__ATIME | MOUNT_ATTR_NODIRATIME) -#define MOUNT_SETATTR_VALID_FLAGS FSMOUNT_VALID_FLAGS +#define MOUNT_SETATTR_VALID_FLAGS (FSMOUNT_VALID_FLAGS | MOUNT_ATTR_IDMAP) #define MOUNT_SETATTR_PROPAGATION_FLAGS \ (MS_UNBINDABLE | MS_PRIVATE | MS_SLAVE | MS_SHARED) @@ -3845,6 +3847,36 @@ static unsigned int recalc_flags(struct mount_kattr *kattr, struct mount *mnt) return flags; } +static int can_idmap_mount(const struct mount_kattr *kattr, struct mount *mnt) +{ + struct vfsmount *m = &mnt->mnt; + + if (!kattr->mnt_userns) + return 0; + + /* + * Once a mount has been idmapped we don't allow it to change its + * mapping. It makes things simpler and callers can just create + * another bind-mount they can idmap if they want to. + */ + if (mnt_user_ns(m) != &init_user_ns) + return -EPERM; + + /* The underlying filesystem doesn't support idmapped mounts yet. */ + if (!(m->mnt_sb->s_type->fs_flags & FS_ALLOW_IDMAP)) + return -EINVAL; + + /* We're not controlling the superblock. */ + if (!ns_capable(m->mnt_sb->s_user_ns, CAP_SYS_ADMIN)) + return -EPERM; + + /* Mount has already been visible in the filesystem hierarchy. */ + if (!is_anon_ns(mnt->mnt_ns)) + return -EINVAL; + + return 0; +} + static struct mount *mount_setattr_prepare(struct mount_kattr *kattr, struct mount *mnt, int *err) { @@ -3869,6 +3901,10 @@ static struct mount *mount_setattr_prepare(struct mount_kattr *kattr, goto out; } + *err = can_idmap_mount(kattr, m); + if (*err) + goto out; + last = m; if ((kattr->attr_set & MNT_READONLY) && @@ -3883,6 +3919,18 @@ out: return last; } +static void do_idmap_mount(const struct mount_kattr *kattr, struct mount *mnt) +{ + struct user_namespace *mnt_userns; + + if (!kattr->mnt_userns) + return; + + mnt_userns = get_user_ns(kattr->mnt_userns); + /* Pairs with smp_load_acquire() in mnt_user_ns(). */ + smp_store_release(&mnt->mnt.mnt_userns, mnt_userns); +} + static void mount_setattr_commit(struct mount_kattr *kattr, struct mount *mnt, struct mount *last, int err) @@ -3893,6 +3941,7 @@ static void mount_setattr_commit(struct mount_kattr *kattr, if (!err) { unsigned int flags; + do_idmap_mount(kattr, m); flags = recalc_flags(kattr, m); WRITE_ONCE(m->mnt.mnt_flags, flags); } @@ -3965,7 +4014,62 @@ static int do_mount_setattr(struct path *path, struct mount_kattr *kattr) return err; } -static int build_mount_kattr(const struct mount_attr *attr, +static int build_mount_idmapped(const struct mount_attr *attr, size_t usize, + struct mount_kattr *kattr, unsigned int flags) +{ + int err = 0; + struct ns_common *ns; + struct user_namespace *mnt_userns; + struct file *file; + + if (!((attr->attr_set | attr->attr_clr) & MOUNT_ATTR_IDMAP)) + return 0; + + /* + * We currently do not support clearing an idmapped mount. If this ever + * is a use-case we can revisit this but for now let's keep it simple + * and not allow it. + */ + if (attr->attr_clr & MOUNT_ATTR_IDMAP) + return -EINVAL; + + if (attr->userns_fd > INT_MAX) + return -EINVAL; + + file = fget(attr->userns_fd); + if (!file) + return -EBADF; + + if (!proc_ns_file(file)) { + err = -EINVAL; + goto out_fput; + } + + ns = get_proc_ns(file_inode(file)); + if (ns->ops->type != CLONE_NEWUSER) { + err = -EINVAL; + goto out_fput; + } + + /* + * The init_user_ns is used to indicate that a vfsmount is not idmapped. + * This is simpler than just having to treat NULL as unmapped. Users + * wanting to idmap a mount to init_user_ns can just use a namespace + * with an identity mapping. + */ + mnt_userns = container_of(ns, struct user_namespace, ns); + if (mnt_userns == &init_user_ns) { + err = -EPERM; + goto out_fput; + } + kattr->mnt_userns = get_user_ns(mnt_userns); + +out_fput: + fput(file); + return err; +} + +static int build_mount_kattr(const struct mount_attr *attr, size_t usize, struct mount_kattr *kattr, unsigned int flags) { unsigned int lookup_flags = LOOKUP_AUTOMOUNT | LOOKUP_FOLLOW; @@ -3991,9 +4095,6 @@ static int build_mount_kattr(const struct mount_attr *attr, if ((attr->attr_set | attr->attr_clr) & ~MOUNT_SETATTR_VALID_FLAGS) return -EINVAL; - if (attr->userns_fd) - return -EINVAL; - kattr->attr_set = attr_flags_to_mnt_flags(attr->attr_set); kattr->attr_clr = attr_flags_to_mnt_flags(attr->attr_clr); @@ -4032,7 +4133,13 @@ static int build_mount_kattr(const struct mount_attr *attr, return -EINVAL; } - return 0; + return build_mount_idmapped(attr, usize, kattr, flags); +} + +static void finish_mount_kattr(struct mount_kattr *kattr) +{ + put_user_ns(kattr->mnt_userns); + kattr->mnt_userns = NULL; } SYSCALL_DEFINE5(mount_setattr, int, dfd, const char __user *, path, @@ -4070,7 +4177,7 @@ SYSCALL_DEFINE5(mount_setattr, int, dfd, const char __user *, path, attr.propagation == 0) return 0; - err = build_mount_kattr(&attr, &kattr, flags); + err = build_mount_kattr(&attr, usize, &kattr, flags); if (err) return err; @@ -4079,6 +4186,7 @@ SYSCALL_DEFINE5(mount_setattr, int, dfd, const char __user *, path, return err; err = do_mount_setattr(&target, &kattr); + finish_mount_kattr(&kattr); path_put(&target); return err; } diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c index eafb75755fa3..392ef5162655 100644 --- a/fs/proc_namespace.c +++ b/fs/proc_namespace.c @@ -79,6 +79,9 @@ static void show_mnt_opts(struct seq_file *m, struct vfsmount *mnt) if (mnt->mnt_flags & fs_infop->flag) seq_puts(m, fs_infop->str); } + + if (mnt_user_ns(mnt) != &init_user_ns) + seq_puts(m, ",idmapped"); } static inline void mangle(struct seq_file *m, const char *s) diff --git a/include/linux/mount.h b/include/linux/mount.h index 52de25e08319..161f4419db6c 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -77,7 +77,8 @@ struct vfsmount { static inline struct user_namespace *mnt_user_ns(const struct vfsmount *mnt) { - return mnt->mnt_userns; + /* Pairs with smp_store_release() in do_idmap_mount(). */ + return smp_load_acquire(&mnt->mnt_userns); } struct file; /* forward dec */ diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h index d3bcefdfa73d..e6524ead2b7b 100644 --- a/include/uapi/linux/mount.h +++ b/include/uapi/linux/mount.h @@ -119,6 +119,7 @@ enum fsconfig_command { #define MOUNT_ATTR_NOATIME 0x00000010 /* - Do not update access times. */ #define MOUNT_ATTR_STRICTATIME 0x00000020 /* - Always perform atime updates */ #define MOUNT_ATTR_NODIRATIME 0x00000080 /* Do not update directory access times */ +#define MOUNT_ATTR_IDMAP 0x00100000 /* Idmap mount to @userns_fd in struct mount_attr. */ /* * mount_setattr() -- cgit v1.2.3 From 882227626459ce7a24191f13c6d9749a00992059 Mon Sep 17 00:00:00 2001 From: Scott Branden Date: Wed, 20 Jan 2021 09:58:15 -0800 Subject: bcm-vk: add bcm_vk UAPI Add user space api for bcm-vk driver. Provide ioctl api to load images and issue reset command to card. FW status registers in PCI BAR space also defined as part of API so that user space is able to interpret these memory locations as needed via direct PCIe access. Acked-by: Olof Johansson Signed-off-by: Scott Branden Link: https://lore.kernel.org/r/20210120175827.14820-2-scott.branden@broadcom.com Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/misc/bcm_vk.h | 84 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 84 insertions(+) create mode 100644 include/uapi/linux/misc/bcm_vk.h (limited to 'include') diff --git a/include/uapi/linux/misc/bcm_vk.h b/include/uapi/linux/misc/bcm_vk.h new file mode 100644 index 000000000000..ec28e0bd46a9 --- /dev/null +++ b/include/uapi/linux/misc/bcm_vk.h @@ -0,0 +1,84 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Copyright 2018-2020 Broadcom. + */ + +#ifndef __UAPI_LINUX_MISC_BCM_VK_H +#define __UAPI_LINUX_MISC_BCM_VK_H + +#include +#include + +#define BCM_VK_MAX_FILENAME 64 + +struct vk_image { + __u32 type; /* Type of image */ +#define VK_IMAGE_TYPE_BOOT1 1 /* 1st stage (load to SRAM) */ +#define VK_IMAGE_TYPE_BOOT2 2 /* 2nd stage (load to DDR) */ + __u8 filename[BCM_VK_MAX_FILENAME]; /* Filename of image */ +}; + +struct vk_reset { + __u32 arg1; + __u32 arg2; +}; + +#define VK_MAGIC 0x5e + +/* Load image to Valkyrie */ +#define VK_IOCTL_LOAD_IMAGE _IOW(VK_MAGIC, 0x2, struct vk_image) + +/* Send Reset to Valkyrie */ +#define VK_IOCTL_RESET _IOW(VK_MAGIC, 0x4, struct vk_reset) + +/* + * Firmware Status accessed directly via BAR space + */ +#define VK_BAR_FWSTS 0x41c +#define VK_BAR_COP_FWSTS 0x428 +/* VK_FWSTS definitions */ +#define VK_FWSTS_RELOCATION_ENTRY (1UL << 0) +#define VK_FWSTS_RELOCATION_EXIT (1UL << 1) +#define VK_FWSTS_INIT_START (1UL << 2) +#define VK_FWSTS_ARCH_INIT_DONE (1UL << 3) +#define VK_FWSTS_PRE_KNL1_INIT_DONE (1UL << 4) +#define VK_FWSTS_PRE_KNL2_INIT_DONE (1UL << 5) +#define VK_FWSTS_POST_KNL_INIT_DONE (1UL << 6) +#define VK_FWSTS_INIT_DONE (1UL << 7) +#define VK_FWSTS_APP_INIT_START (1UL << 8) +#define VK_FWSTS_APP_INIT_DONE (1UL << 9) +#define VK_FWSTS_MASK 0xffffffff +#define VK_FWSTS_READY (VK_FWSTS_INIT_START | \ + VK_FWSTS_ARCH_INIT_DONE | \ + VK_FWSTS_PRE_KNL1_INIT_DONE | \ + VK_FWSTS_PRE_KNL2_INIT_DONE | \ + VK_FWSTS_POST_KNL_INIT_DONE | \ + VK_FWSTS_INIT_DONE | \ + VK_FWSTS_APP_INIT_START | \ + VK_FWSTS_APP_INIT_DONE) +/* Deinit */ +#define VK_FWSTS_APP_DEINIT_START (1UL << 23) +#define VK_FWSTS_APP_DEINIT_DONE (1UL << 24) +#define VK_FWSTS_DRV_DEINIT_START (1UL << 25) +#define VK_FWSTS_DRV_DEINIT_DONE (1UL << 26) +#define VK_FWSTS_RESET_DONE (1UL << 27) +#define VK_FWSTS_DEINIT_TRIGGERED (VK_FWSTS_APP_DEINIT_START | \ + VK_FWSTS_APP_DEINIT_DONE | \ + VK_FWSTS_DRV_DEINIT_START | \ + VK_FWSTS_DRV_DEINIT_DONE) +/* Last nibble for reboot reason */ +#define VK_FWSTS_RESET_REASON_SHIFT 28 +#define VK_FWSTS_RESET_REASON_MASK (0xf << VK_FWSTS_RESET_REASON_SHIFT) +#define VK_FWSTS_RESET_SYS_PWRUP (0x0 << VK_FWSTS_RESET_REASON_SHIFT) +#define VK_FWSTS_RESET_MBOX_DB (0x1 << VK_FWSTS_RESET_REASON_SHIFT) +#define VK_FWSTS_RESET_M7_WDOG (0x2 << VK_FWSTS_RESET_REASON_SHIFT) +#define VK_FWSTS_RESET_TEMP (0x3 << VK_FWSTS_RESET_REASON_SHIFT) +#define VK_FWSTS_RESET_PCI_FLR (0x4 << VK_FWSTS_RESET_REASON_SHIFT) +#define VK_FWSTS_RESET_PCI_HOT (0x5 << VK_FWSTS_RESET_REASON_SHIFT) +#define VK_FWSTS_RESET_PCI_WARM (0x6 << VK_FWSTS_RESET_REASON_SHIFT) +#define VK_FWSTS_RESET_PCI_COLD (0x7 << VK_FWSTS_RESET_REASON_SHIFT) +#define VK_FWSTS_RESET_L1 (0x8 << VK_FWSTS_RESET_REASON_SHIFT) +#define VK_FWSTS_RESET_L0 (0x9 << VK_FWSTS_RESET_REASON_SHIFT) +#define VK_FWSTS_RESET_UNKNOWN (0xf << VK_FWSTS_RESET_REASON_SHIFT) + +#endif /* __UAPI_LINUX_MISC_BCM_VK_H */ -- cgit v1.2.3 From ceecd1bff6f9a741adc173f062f1f9312c3a66c8 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 19 Jan 2021 12:07:22 -0800 Subject: HID: correct kernel-doc notation in Correct kernel-doc notation in HID header files (include/linux/hid*.h). Add notation (comments) where it is missing. Use the documented "Return:" notation for function return values. Fix a few typos/spellos. Signed-off-by: Randy Dunlap Cc: Jiri Kosina Cc: Benjamin Tissoires Cc: linux-input@vger.kernel.org Signed-off-by: Jiri Kosina --- include/linux/hid-sensor-hub.h | 9 +++++---- include/linux/hid.h | 15 +++++++++++---- 2 files changed, 16 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/hid-sensor-hub.h b/include/linux/hid-sensor-hub.h index 46bcef380446..763802b2b8f9 100644 --- a/include/linux/hid-sensor-hub.h +++ b/include/linux/hid-sensor-hub.h @@ -150,7 +150,7 @@ int sensor_hub_remove_callback(struct hid_sensor_hub_device *hsdev, * @info: return information about attribute after parsing report * * Parses report and returns the attribute information such as report id, -* field index, units and exponet etc. +* field index, units and exponent etc. */ int sensor_hub_input_get_attribute_info(struct hid_sensor_hub_device *hsdev, u8 type, @@ -167,7 +167,7 @@ int sensor_hub_input_get_attribute_info(struct hid_sensor_hub_device *hsdev, * @is_signed: If true then fields < 32 bits will be sign-extended * * Issues a synchronous or asynchronous read request for an input attribute. -* Returns data upto 32 bits. +* Return: data up to 32 bits. */ enum sensor_hub_read_flags { @@ -205,8 +205,9 @@ int sensor_hub_set_feature(struct hid_sensor_hub_device *hsdev, u32 report_id, * @buffer: buffer to copy output * * Used to get a field in feature report. For example this can get polling -* interval, sensitivity, activate/deactivate state. On success it returns -* number of bytes copied to buffer. On failure, it returns value < 0. +* interval, sensitivity, activate/deactivate state. +* Return: On success, it returns the number of bytes copied to buffer. +* On failure, it returns value < 0. */ int sensor_hub_get_feature(struct hid_sensor_hub_device *hsdev, u32 report_id, u32 field_index, int buffer_size, void *buffer); diff --git a/include/linux/hid.h b/include/linux/hid.h index c39d71eb1fd0..ef702b3f56e3 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -918,7 +918,7 @@ __u32 hid_field_extract(const struct hid_device *hid, __u8 *report, /** * hid_device_io_start - enable HID input during probe, remove * - * @hid - the device + * @hid: the device * * This should only be called during probe or remove and only be * called by the thread calling probe or remove. It will allow @@ -936,7 +936,7 @@ static inline void hid_device_io_start(struct hid_device *hid) { /** * hid_device_io_stop - disable HID input during probe, remove * - * @hid - the device + * @hid: the device * * Should only be called after hid_device_io_start. It will prevent * incoming packets from going to the driver for the duration of @@ -1010,6 +1010,13 @@ static inline void hid_map_usage(struct hid_input *hidinput, /** * hid_map_usage_clear - map usage input bits and clear the input bit * + * @hidinput: hidinput which we are interested in + * @usage: usage to fill in + * @bit: pointer to input->{}bit (out parameter) + * @max: maximal valid usage->code to consider later (out parameter) + * @type: input event type (EV_KEY, EV_REL, ...) + * @c: code which corresponds to this usage and type + * * The same as hid_map_usage, except the @c bit is also cleared in supported * bits (@bit). */ @@ -1084,7 +1091,7 @@ static inline void hid_hw_request(struct hid_device *hdev, * @rtype: HID report type * @reqtype: HID_REQ_GET_REPORT or HID_REQ_SET_REPORT * - * @return: count of data transfered, negative if error + * Return: count of data transferred, negative if error * * Same behavior as hid_hw_request, but with raw buffers instead. */ @@ -1106,7 +1113,7 @@ static inline int hid_hw_raw_request(struct hid_device *hdev, * @buf: raw data to transfer * @len: length of buf * - * @return: count of data transfered, negative if error + * Return: count of data transferred, negative if error */ static inline int hid_hw_output_report(struct hid_device *hdev, __u8 *buf, size_t len) -- cgit v1.2.3 From 081df94301e317e84c3413686043987da2c3e39d Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Thu, 21 Jan 2021 15:29:23 -0600 Subject: objtool: Add asm version of STACK_FRAME_NON_STANDARD To be used for adding asm functions to the ignore list. The "aw" is needed to help the ELF section metadata match GCC-created sections. Otherwise the linker creates duplicate sections instead of combining them. Signed-off-by: Josh Poimboeuf Link: https://lore.kernel.org/r/8faa476f9a5ac89af27944ec184c89f95f3c6c49.1611263462.git.jpoimboe@redhat.com --- include/linux/objtool.h | 8 ++++++++ tools/include/linux/objtool.h | 8 ++++++++ 2 files changed, 16 insertions(+) (limited to 'include') diff --git a/include/linux/objtool.h b/include/linux/objtool.h index 577f51436cf9..add1c6eb157e 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -109,6 +109,12 @@ struct unwind_hint { .popsection .endm +.macro STACK_FRAME_NON_STANDARD func:req + .pushsection .discard.func_stack_frame_non_standard, "aw" + .long \func - . + .popsection +.endm + #endif /* __ASSEMBLY__ */ #else /* !CONFIG_STACK_VALIDATION */ @@ -122,6 +128,8 @@ struct unwind_hint { #define ANNOTATE_INTRA_FUNCTION_CALL .macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0 .endm +.macro STACK_FRAME_NON_STANDARD func:req +.endm #endif #endif /* CONFIG_STACK_VALIDATION */ diff --git a/tools/include/linux/objtool.h b/tools/include/linux/objtool.h index 577f51436cf9..add1c6eb157e 100644 --- a/tools/include/linux/objtool.h +++ b/tools/include/linux/objtool.h @@ -109,6 +109,12 @@ struct unwind_hint { .popsection .endm +.macro STACK_FRAME_NON_STANDARD func:req + .pushsection .discard.func_stack_frame_non_standard, "aw" + .long \func - . + .popsection +.endm + #endif /* __ASSEMBLY__ */ #else /* !CONFIG_STACK_VALIDATION */ @@ -122,6 +128,8 @@ struct unwind_hint { #define ANNOTATE_INTRA_FUNCTION_CALL .macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0 .endm +.macro STACK_FRAME_NON_STANDARD func:req +.endm #endif #endif /* CONFIG_STACK_VALIDATION */ -- cgit v1.2.3 From b735bd3e68824316655252a931a3353a6ebc036f Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Thu, 21 Jan 2021 15:29:24 -0600 Subject: objtool: Combine UNWIND_HINT_RET_OFFSET and UNWIND_HINT_FUNC The ORC metadata generated for UNWIND_HINT_FUNC isn't actually very func-like. With certain usages it can cause stack state mismatches because it doesn't set the return address (CFI_RA). Also, users of UNWIND_HINT_RET_OFFSET no longer need to set a custom return stack offset. Instead they just need to specify a func-like situation, so the current ret_offset code is hacky for no good reason. Solve both problems by simplifying the RET_OFFSET handling and converting it into a more useful UNWIND_HINT_FUNC. If we end up needing the old 'ret_offset' functionality again in the future, we should be able to support it pretty easily with the addition of a custom 'sp_offset' in UNWIND_HINT_FUNC. Signed-off-by: Josh Poimboeuf Link: https://lore.kernel.org/r/db9d1f5d79dddfbb3725ef6d8ec3477ad199948d.1611263462.git.jpoimboe@redhat.com --- arch/x86/include/asm/unwind_hints.h | 13 ++---------- arch/x86/kernel/ftrace_64.S | 2 +- arch/x86/lib/retpoline.S | 2 +- include/linux/objtool.h | 5 ++++- tools/include/linux/objtool.h | 5 ++++- tools/objtool/arch/x86/decode.c | 4 ++-- tools/objtool/check.c | 37 ++++++++++++++--------------------- tools/objtool/include/objtool/check.h | 1 - 8 files changed, 29 insertions(+), 40 deletions(-) (limited to 'include') diff --git a/arch/x86/include/asm/unwind_hints.h b/arch/x86/include/asm/unwind_hints.h index 664d4610d700..8e574c0afef8 100644 --- a/arch/x86/include/asm/unwind_hints.h +++ b/arch/x86/include/asm/unwind_hints.h @@ -48,17 +48,8 @@ UNWIND_HINT_REGS base=\base offset=\offset partial=1 .endm -.macro UNWIND_HINT_FUNC sp_offset=8 - UNWIND_HINT sp_reg=ORC_REG_SP sp_offset=\sp_offset type=UNWIND_HINT_TYPE_CALL -.endm - -/* - * RET_OFFSET: Used on instructions that terminate a function; mostly RETURN - * and sibling calls. On these, sp_offset denotes the expected offset from - * initial_func_cfi. - */ -.macro UNWIND_HINT_RET_OFFSET sp_offset=8 - UNWIND_HINT sp_reg=ORC_REG_SP type=UNWIND_HINT_TYPE_RET_OFFSET sp_offset=\sp_offset +.macro UNWIND_HINT_FUNC + UNWIND_HINT sp_reg=ORC_REG_SP sp_offset=8 type=UNWIND_HINT_TYPE_FUNC .endm #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S index 58d125ed9d1a..1bf568d901b1 100644 --- a/arch/x86/kernel/ftrace_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -277,7 +277,7 @@ SYM_INNER_LABEL(ftrace_regs_caller_end, SYM_L_GLOBAL) restore_mcount_regs 8 /* Restore flags */ popfq - UNWIND_HINT_RET_OFFSET + UNWIND_HINT_FUNC jmp ftrace_epilogue SYM_FUNC_END(ftrace_regs_caller) diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index b4c43a9b1483..f6fb1d218dcc 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -28,7 +28,7 @@ SYM_FUNC_START_NOALIGN(__x86_retpoline_\reg) jmp .Lspec_trap_\@ .Ldo_rop_\@: mov %\reg, (%_ASM_SP) - UNWIND_HINT_RET_OFFSET + UNWIND_HINT_FUNC ret SYM_FUNC_END(__x86_retpoline_\reg) diff --git a/include/linux/objtool.h b/include/linux/objtool.h index add1c6eb157e..7e72d975cb76 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -29,11 +29,14 @@ struct unwind_hint { * * UNWIND_HINT_TYPE_REGS_PARTIAL: Used in entry code to indicate that * sp_reg+sp_offset points to the iret return frame. + * + * UNWIND_HINT_FUNC: Generate the unwind metadata of a callable function. + * Useful for code which doesn't have an ELF function annotation. */ #define UNWIND_HINT_TYPE_CALL 0 #define UNWIND_HINT_TYPE_REGS 1 #define UNWIND_HINT_TYPE_REGS_PARTIAL 2 -#define UNWIND_HINT_TYPE_RET_OFFSET 3 +#define UNWIND_HINT_TYPE_FUNC 3 #ifdef CONFIG_STACK_VALIDATION diff --git a/tools/include/linux/objtool.h b/tools/include/linux/objtool.h index add1c6eb157e..7e72d975cb76 100644 --- a/tools/include/linux/objtool.h +++ b/tools/include/linux/objtool.h @@ -29,11 +29,14 @@ struct unwind_hint { * * UNWIND_HINT_TYPE_REGS_PARTIAL: Used in entry code to indicate that * sp_reg+sp_offset points to the iret return frame. + * + * UNWIND_HINT_FUNC: Generate the unwind metadata of a callable function. + * Useful for code which doesn't have an ELF function annotation. */ #define UNWIND_HINT_TYPE_CALL 0 #define UNWIND_HINT_TYPE_REGS 1 #define UNWIND_HINT_TYPE_REGS_PARTIAL 2 -#define UNWIND_HINT_TYPE_RET_OFFSET 3 +#define UNWIND_HINT_TYPE_FUNC 3 #ifdef CONFIG_STACK_VALIDATION diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index 6baa22732ca6..9637e3bf5ab8 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -563,8 +563,8 @@ void arch_initial_func_cfi_state(struct cfi_init_state *state) state->cfa.offset = 8; /* initial RA (return address) */ - state->regs[16].base = CFI_CFA; - state->regs[16].offset = -8; + state->regs[CFI_RA].base = CFI_CFA; + state->regs[CFI_RA].offset = -8; } const char *arch_nop_insn(int len) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index b4e1655017de..f88f20327bf2 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -1404,13 +1404,20 @@ static int add_jump_table_alts(struct objtool_file *file) return 0; } +static void set_func_state(struct cfi_state *state) +{ + state->cfa = initial_func_cfi.cfa; + memcpy(&state->regs, &initial_func_cfi.regs, + CFI_NUM_REGS * sizeof(struct cfi_reg)); + state->stack_size = initial_func_cfi.cfa.offset; +} + static int read_unwind_hints(struct objtool_file *file) { struct section *sec, *relocsec; struct reloc *reloc; struct unwind_hint *hint; struct instruction *insn; - struct cfi_reg *cfa; int i; sec = find_section_by_name(file->elf, ".discard.unwind_hints"); @@ -1445,22 +1452,20 @@ static int read_unwind_hints(struct objtool_file *file) return -1; } - cfa = &insn->cfi.cfa; + insn->hint = true; - if (hint->type == UNWIND_HINT_TYPE_RET_OFFSET) { - insn->ret_offset = bswap_if_needed(hint->sp_offset); + if (hint->type == UNWIND_HINT_TYPE_FUNC) { + set_func_state(&insn->cfi); continue; } - insn->hint = true; - if (arch_decode_hint_reg(insn, hint->sp_reg)) { WARN_FUNC("unsupported unwind_hint sp base reg %d", insn->sec, insn->offset, hint->sp_reg); return -1; } - cfa->offset = bswap_if_needed(hint->sp_offset); + insn->cfi.cfa.offset = bswap_if_needed(hint->sp_offset); insn->cfi.type = hint->type; insn->cfi.end = hint->end; } @@ -1716,27 +1721,18 @@ static bool is_fentry_call(struct instruction *insn) static bool has_modified_stack_frame(struct instruction *insn, struct insn_state *state) { - u8 ret_offset = insn->ret_offset; struct cfi_state *cfi = &state->cfi; int i; if (cfi->cfa.base != initial_func_cfi.cfa.base || cfi->drap) return true; - if (cfi->cfa.offset != initial_func_cfi.cfa.offset + ret_offset) + if (cfi->cfa.offset != initial_func_cfi.cfa.offset) return true; - if (cfi->stack_size != initial_func_cfi.cfa.offset + ret_offset) + if (cfi->stack_size != initial_func_cfi.cfa.offset) return true; - /* - * If there is a ret offset hint then don't check registers - * because a callee-saved register might have been pushed on - * the stack. - */ - if (ret_offset) - return false; - for (i = 0; i < CFI_NUM_REGS; i++) { if (cfi->regs[i].base != initial_func_cfi.regs[i].base || cfi->regs[i].offset != initial_func_cfi.regs[i].offset) @@ -2880,10 +2876,7 @@ static int validate_section(struct objtool_file *file, struct section *sec) continue; init_insn_state(&state, sec); - state.cfi.cfa = initial_func_cfi.cfa; - memcpy(&state.cfi.regs, &initial_func_cfi.regs, - CFI_NUM_REGS * sizeof(struct cfi_reg)); - state.cfi.stack_size = initial_func_cfi.cfa.offset; + set_func_state(&state.cfi); warnings += validate_symbol(file, sec, func, &state); } diff --git a/tools/objtool/include/objtool/check.h b/tools/objtool/include/objtool/check.h index b408636c0201..4891ead0e85f 100644 --- a/tools/objtool/include/objtool/check.h +++ b/tools/objtool/include/objtool/check.h @@ -50,7 +50,6 @@ struct instruction { bool retpoline_safe; s8 instr; u8 visited; - u8 ret_offset; struct alt_group *alt_group; struct symbol *call_dest; struct instruction *jump_dest; -- cgit v1.2.3 From d07b6621d948944c6828fc9b5cbdcb6f389b3b04 Mon Sep 17 00:00:00 2001 From: Fabio Estevam Date: Mon, 18 Jan 2021 09:15:48 -0300 Subject: dmaengine: imx-sdma: Remove platform data support Since 5.10-rc1, i.MX has been converted to a devicetree-only platform. The platform data support in this driver was only used for non-DT platforms. Remove the platform data support as it has no more users. Signed-off-by: Fabio Estevam Link: https://lore.kernel.org/r/20210118121549.1625217-1-festevam@gmail.com Signed-off-by: Vinod Koul --- drivers/dma/imx-sdma.c | 35 +++++++++--------------------- include/linux/platform_data/dma-imx-sdma.h | 11 ---------- 2 files changed, 10 insertions(+), 36 deletions(-) (limited to 'include') diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c index 41ba21eea7c8..a68950f80635 100644 --- a/drivers/dma/imx-sdma.c +++ b/drivers/dma/imx-sdma.c @@ -1961,7 +1961,6 @@ static int sdma_probe(struct platform_device *pdev) int irq; struct resource *iores; struct resource spba_res; - struct sdma_platform_data *pdata = dev_get_platdata(&pdev->dev); int i; struct sdma_engine *sdma; s32 *saddr_arr; @@ -2063,8 +2062,6 @@ static int sdma_probe(struct platform_device *pdev) if (sdma->drvdata->script_addrs) sdma_add_scripts(sdma, sdma->drvdata->script_addrs); - if (pdata && pdata->script_addrs) - sdma_add_scripts(sdma, pdata->script_addrs); sdma->dma_device.dev = &pdev->dev; @@ -2110,30 +2107,18 @@ static int sdma_probe(struct platform_device *pdev) } /* - * Kick off firmware loading as the very last step: - * attempt to load firmware only if we're not on the error path, because - * the firmware callback requires a fully functional and allocated sdma - * instance. + * Because that device tree does not encode ROM script address, + * the RAM script in firmware is mandatory for device tree + * probe, otherwise it fails. */ - if (pdata) { - ret = sdma_get_firmware(sdma, pdata->fw_name); - if (ret) - dev_warn(&pdev->dev, "failed to get firmware from platform data\n"); + ret = of_property_read_string(np, "fsl,sdma-ram-script-name", + &fw_name); + if (ret) { + dev_warn(&pdev->dev, "failed to get firmware name\n"); } else { - /* - * Because that device tree does not encode ROM script address, - * the RAM script in firmware is mandatory for device tree - * probe, otherwise it fails. - */ - ret = of_property_read_string(np, "fsl,sdma-ram-script-name", - &fw_name); - if (ret) { - dev_warn(&pdev->dev, "failed to get firmware name\n"); - } else { - ret = sdma_get_firmware(sdma, fw_name); - if (ret) - dev_warn(&pdev->dev, "failed to get firmware from device tree\n"); - } + ret = sdma_get_firmware(sdma, fw_name); + if (ret) + dev_warn(&pdev->dev, "failed to get firmware from device tree\n"); } return 0; diff --git a/include/linux/platform_data/dma-imx-sdma.h b/include/linux/platform_data/dma-imx-sdma.h index 30e676b36b24..725602d9df91 100644 --- a/include/linux/platform_data/dma-imx-sdma.h +++ b/include/linux/platform_data/dma-imx-sdma.h @@ -57,15 +57,4 @@ struct sdma_script_start_addrs { /* End of v4 array */ }; -/** - * struct sdma_platform_data - platform specific data for SDMA engine - * - * @fw_name The firmware name - * @script_addrs SDMA scripts addresses in SDMA ROM - */ -struct sdma_platform_data { - char *fw_name; - struct sdma_script_start_addrs *script_addrs; -}; - #endif /* __MACH_MXC_SDMA_H__ */ -- cgit v1.2.3 From ec6ab42f5aadd765b0b8c4e2d21508ac1e20f2ed Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 20 Jan 2021 14:18:57 +0100 Subject: dmaengine: remove sirfsoc driver The CSR SiRF prima2/atlas platforms are getting removed, so this driver is no longer needed. Signed-off-by: Arnd Bergmann Acked-by: Barry Song Cc: Barry Song Link: https://lore.kernel.org/r/20210120131859.2056308-2-arnd@kernel.org Signed-off-by: Vinod Koul --- .../devicetree/bindings/dma/sirfsoc-dma.txt | 44 - drivers/dma/Kconfig | 7 - drivers/dma/Makefile | 1 - drivers/dma/sirf-dma.c | 1170 -------------------- include/linux/sirfsoc_dma.h | 7 - 5 files changed, 1229 deletions(-) delete mode 100644 Documentation/devicetree/bindings/dma/sirfsoc-dma.txt delete mode 100644 drivers/dma/sirf-dma.c delete mode 100644 include/linux/sirfsoc_dma.h (limited to 'include') diff --git a/Documentation/devicetree/bindings/dma/sirfsoc-dma.txt b/Documentation/devicetree/bindings/dma/sirfsoc-dma.txt deleted file mode 100644 index ccd52d6a231a..000000000000 --- a/Documentation/devicetree/bindings/dma/sirfsoc-dma.txt +++ /dev/null @@ -1,44 +0,0 @@ -* CSR SiRFSoC DMA controller - -See dma.txt first - -Required properties: -- compatible: Should be "sirf,prima2-dmac", "sirf,atlas7-dmac" or - "sirf,atlas7-dmac-v2" -- reg: Should contain DMA registers location and length. -- interrupts: Should contain one interrupt shared by all channel -- #dma-cells: must be <1>. used to represent the number of integer - cells in the dmas property of client device. -- clocks: clock required - -Example: - -Controller: -dmac0: dma-controller@b00b0000 { - compatible = "sirf,prima2-dmac"; - reg = <0xb00b0000 0x10000>; - interrupts = <12>; - clocks = <&clks 24>; - #dma-cells = <1>; -}; - - -Client: -Fill the specific dma request line in dmas. In the below example, spi0 read -channel request line is 9 of the 2nd dma controller, while write channel uses -4 of the 2nd dma controller; spi1 read channel request line is 12 of the 1st -dma controller, while write channel uses 13 of the 1st dma controller: - -spi0: spi@b00d0000 { - compatible = "sirf,prima2-spi"; - dmas = <&dmac1 9>, - <&dmac1 4>; - dma-names = "rx", "tx"; -}; - -spi1: spi@b0170000 { - compatible = "sirf,prima2-spi"; - dmas = <&dmac0 12>, - <&dmac0 13>; - dma-names = "rx", "tx"; -}; diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index 6c92f075f7ce..2201ff280f7a 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -519,13 +519,6 @@ config PLX_DMA These are exposed via extra functions on the switch's upstream port. Each function exposes one DMA channel. -config SIRF_DMA - tristate "CSR SiRFprimaII/SiRFmarco DMA support" - depends on ARCH_SIRF - select DMA_ENGINE - help - Enable support for the CSR SiRFprimaII DMA engine. - config STE_DMA40 bool "ST-Ericsson DMA40 support" depends on ARCH_U8500 diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile index 649a4f95ea4b..b5b34c65b075 100644 --- a/drivers/dma/Makefile +++ b/drivers/dma/Makefile @@ -65,7 +65,6 @@ obj-$(CONFIG_PPC_BESTCOMM) += bestcomm/ obj-$(CONFIG_PXA_DMA) += pxa_dma.o obj-$(CONFIG_RENESAS_DMA) += sh/ obj-$(CONFIG_SF_PDMA) += sf-pdma/ -obj-$(CONFIG_SIRF_DMA) += sirf-dma.o obj-$(CONFIG_STE_DMA40) += ste_dma40.o ste_dma40_ll.o obj-$(CONFIG_STM32_DMA) += stm32-dma.o obj-$(CONFIG_STM32_DMAMUX) += stm32-dmamux.o diff --git a/drivers/dma/sirf-dma.c b/drivers/dma/sirf-dma.c deleted file mode 100644 index a5c2843384fd..000000000000 --- a/drivers/dma/sirf-dma.c +++ /dev/null @@ -1,1170 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * DMA controller driver for CSR SiRFprimaII - * - * Copyright (c) 2011 Cambridge Silicon Radio Limited, a CSR plc group company. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "dmaengine.h" - -#define SIRFSOC_DMA_VER_A7V1 1 -#define SIRFSOC_DMA_VER_A7V2 2 -#define SIRFSOC_DMA_VER_A6 4 - -#define SIRFSOC_DMA_DESCRIPTORS 16 -#define SIRFSOC_DMA_CHANNELS 16 -#define SIRFSOC_DMA_TABLE_NUM 256 - -#define SIRFSOC_DMA_CH_ADDR 0x00 -#define SIRFSOC_DMA_CH_XLEN 0x04 -#define SIRFSOC_DMA_CH_YLEN 0x08 -#define SIRFSOC_DMA_CH_CTRL 0x0C - -#define SIRFSOC_DMA_WIDTH_0 0x100 -#define SIRFSOC_DMA_CH_VALID 0x140 -#define SIRFSOC_DMA_CH_INT 0x144 -#define SIRFSOC_DMA_INT_EN 0x148 -#define SIRFSOC_DMA_INT_EN_CLR 0x14C -#define SIRFSOC_DMA_CH_LOOP_CTRL 0x150 -#define SIRFSOC_DMA_CH_LOOP_CTRL_CLR 0x154 -#define SIRFSOC_DMA_WIDTH_ATLAS7 0x10 -#define SIRFSOC_DMA_VALID_ATLAS7 0x14 -#define SIRFSOC_DMA_INT_ATLAS7 0x18 -#define SIRFSOC_DMA_INT_EN_ATLAS7 0x1c -#define SIRFSOC_DMA_LOOP_CTRL_ATLAS7 0x20 -#define SIRFSOC_DMA_CUR_DATA_ADDR 0x34 -#define SIRFSOC_DMA_MUL_ATLAS7 0x38 -#define SIRFSOC_DMA_CH_LOOP_CTRL_ATLAS7 0x158 -#define SIRFSOC_DMA_CH_LOOP_CTRL_CLR_ATLAS7 0x15C -#define SIRFSOC_DMA_IOBG_SCMD_EN 0x800 -#define SIRFSOC_DMA_EARLY_RESP_SET 0x818 -#define SIRFSOC_DMA_EARLY_RESP_CLR 0x81C - -#define SIRFSOC_DMA_MODE_CTRL_BIT 4 -#define SIRFSOC_DMA_DIR_CTRL_BIT 5 -#define SIRFSOC_DMA_MODE_CTRL_BIT_ATLAS7 2 -#define SIRFSOC_DMA_CHAIN_CTRL_BIT_ATLAS7 3 -#define SIRFSOC_DMA_DIR_CTRL_BIT_ATLAS7 4 -#define SIRFSOC_DMA_TAB_NUM_ATLAS7 7 -#define SIRFSOC_DMA_CHAIN_INT_BIT_ATLAS7 5 -#define SIRFSOC_DMA_CHAIN_FLAG_SHIFT_ATLAS7 25 -#define SIRFSOC_DMA_CHAIN_ADDR_SHIFT 32 - -#define SIRFSOC_DMA_INT_FINI_INT_ATLAS7 BIT(0) -#define SIRFSOC_DMA_INT_CNT_INT_ATLAS7 BIT(1) -#define SIRFSOC_DMA_INT_PAU_INT_ATLAS7 BIT(2) -#define SIRFSOC_DMA_INT_LOOP_INT_ATLAS7 BIT(3) -#define SIRFSOC_DMA_INT_INV_INT_ATLAS7 BIT(4) -#define SIRFSOC_DMA_INT_END_INT_ATLAS7 BIT(5) -#define SIRFSOC_DMA_INT_ALL_ATLAS7 0x3F - -/* xlen and dma_width register is in 4 bytes boundary */ -#define SIRFSOC_DMA_WORD_LEN 4 -#define SIRFSOC_DMA_XLEN_MAX_V1 0x800 -#define SIRFSOC_DMA_XLEN_MAX_V2 0x1000 - -struct sirfsoc_dma_desc { - struct dma_async_tx_descriptor desc; - struct list_head node; - - /* SiRFprimaII 2D-DMA parameters */ - - int xlen; /* DMA xlen */ - int ylen; /* DMA ylen */ - int width; /* DMA width */ - int dir; - bool cyclic; /* is loop DMA? */ - bool chain; /* is chain DMA? */ - u32 addr; /* DMA buffer address */ - u64 chain_table[SIRFSOC_DMA_TABLE_NUM]; /* chain tbl */ -}; - -struct sirfsoc_dma_chan { - struct dma_chan chan; - struct list_head free; - struct list_head prepared; - struct list_head queued; - struct list_head active; - struct list_head completed; - unsigned long happened_cyclic; - unsigned long completed_cyclic; - - /* Lock for this structure */ - spinlock_t lock; - - int mode; -}; - -struct sirfsoc_dma_regs { - u32 ctrl[SIRFSOC_DMA_CHANNELS]; - u32 interrupt_en; -}; - -struct sirfsoc_dma { - struct dma_device dma; - struct tasklet_struct tasklet; - struct sirfsoc_dma_chan channels[SIRFSOC_DMA_CHANNELS]; - void __iomem *base; - int irq; - struct clk *clk; - int type; - void (*exec_desc)(struct sirfsoc_dma_desc *sdesc, - int cid, int burst_mode, void __iomem *base); - struct sirfsoc_dma_regs regs_save; -}; - -struct sirfsoc_dmadata { - void (*exec)(struct sirfsoc_dma_desc *sdesc, - int cid, int burst_mode, void __iomem *base); - int type; -}; - -enum sirfsoc_dma_chain_flag { - SIRFSOC_DMA_CHAIN_NORMAL = 0x01, - SIRFSOC_DMA_CHAIN_PAUSE = 0x02, - SIRFSOC_DMA_CHAIN_LOOP = 0x03, - SIRFSOC_DMA_CHAIN_END = 0x04 -}; - -#define DRV_NAME "sirfsoc_dma" - -static int sirfsoc_dma_runtime_suspend(struct device *dev); - -/* Convert struct dma_chan to struct sirfsoc_dma_chan */ -static inline -struct sirfsoc_dma_chan *dma_chan_to_sirfsoc_dma_chan(struct dma_chan *c) -{ - return container_of(c, struct sirfsoc_dma_chan, chan); -} - -/* Convert struct dma_chan to struct sirfsoc_dma */ -static inline struct sirfsoc_dma *dma_chan_to_sirfsoc_dma(struct dma_chan *c) -{ - struct sirfsoc_dma_chan *schan = dma_chan_to_sirfsoc_dma_chan(c); - return container_of(schan, struct sirfsoc_dma, channels[c->chan_id]); -} - -static void sirfsoc_dma_execute_hw_a7v2(struct sirfsoc_dma_desc *sdesc, - int cid, int burst_mode, void __iomem *base) -{ - if (sdesc->chain) { - /* DMA v2 HW chain mode */ - writel_relaxed((sdesc->dir << SIRFSOC_DMA_DIR_CTRL_BIT_ATLAS7) | - (sdesc->chain << - SIRFSOC_DMA_CHAIN_CTRL_BIT_ATLAS7) | - (0x8 << SIRFSOC_DMA_TAB_NUM_ATLAS7) | 0x3, - base + SIRFSOC_DMA_CH_CTRL); - } else { - /* DMA v2 legacy mode */ - writel_relaxed(sdesc->xlen, base + SIRFSOC_DMA_CH_XLEN); - writel_relaxed(sdesc->ylen, base + SIRFSOC_DMA_CH_YLEN); - writel_relaxed(sdesc->width, base + SIRFSOC_DMA_WIDTH_ATLAS7); - writel_relaxed((sdesc->width*((sdesc->ylen+1)>>1)), - base + SIRFSOC_DMA_MUL_ATLAS7); - writel_relaxed((sdesc->dir << SIRFSOC_DMA_DIR_CTRL_BIT_ATLAS7) | - (sdesc->chain << - SIRFSOC_DMA_CHAIN_CTRL_BIT_ATLAS7) | - 0x3, base + SIRFSOC_DMA_CH_CTRL); - } - writel_relaxed(sdesc->chain ? SIRFSOC_DMA_INT_END_INT_ATLAS7 : - (SIRFSOC_DMA_INT_FINI_INT_ATLAS7 | - SIRFSOC_DMA_INT_LOOP_INT_ATLAS7), - base + SIRFSOC_DMA_INT_EN_ATLAS7); - writel(sdesc->addr, base + SIRFSOC_DMA_CH_ADDR); - if (sdesc->cyclic) - writel(0x10001, base + SIRFSOC_DMA_LOOP_CTRL_ATLAS7); -} - -static void sirfsoc_dma_execute_hw_a7v1(struct sirfsoc_dma_desc *sdesc, - int cid, int burst_mode, void __iomem *base) -{ - writel_relaxed(1, base + SIRFSOC_DMA_IOBG_SCMD_EN); - writel_relaxed((1 << cid), base + SIRFSOC_DMA_EARLY_RESP_SET); - writel_relaxed(sdesc->width, base + SIRFSOC_DMA_WIDTH_0 + cid * 4); - writel_relaxed(cid | (burst_mode << SIRFSOC_DMA_MODE_CTRL_BIT) | - (sdesc->dir << SIRFSOC_DMA_DIR_CTRL_BIT), - base + cid * 0x10 + SIRFSOC_DMA_CH_CTRL); - writel_relaxed(sdesc->xlen, base + cid * 0x10 + SIRFSOC_DMA_CH_XLEN); - writel_relaxed(sdesc->ylen, base + cid * 0x10 + SIRFSOC_DMA_CH_YLEN); - writel_relaxed(readl_relaxed(base + SIRFSOC_DMA_INT_EN) | - (1 << cid), base + SIRFSOC_DMA_INT_EN); - writel(sdesc->addr >> 2, base + cid * 0x10 + SIRFSOC_DMA_CH_ADDR); - if (sdesc->cyclic) { - writel((1 << cid) | 1 << (cid + 16) | - readl_relaxed(base + SIRFSOC_DMA_CH_LOOP_CTRL_ATLAS7), - base + SIRFSOC_DMA_CH_LOOP_CTRL_ATLAS7); - } - -} - -static void sirfsoc_dma_execute_hw_a6(struct sirfsoc_dma_desc *sdesc, - int cid, int burst_mode, void __iomem *base) -{ - writel_relaxed(sdesc->width, base + SIRFSOC_DMA_WIDTH_0 + cid * 4); - writel_relaxed(cid | (burst_mode << SIRFSOC_DMA_MODE_CTRL_BIT) | - (sdesc->dir << SIRFSOC_DMA_DIR_CTRL_BIT), - base + cid * 0x10 + SIRFSOC_DMA_CH_CTRL); - writel_relaxed(sdesc->xlen, base + cid * 0x10 + SIRFSOC_DMA_CH_XLEN); - writel_relaxed(sdesc->ylen, base + cid * 0x10 + SIRFSOC_DMA_CH_YLEN); - writel_relaxed(readl_relaxed(base + SIRFSOC_DMA_INT_EN) | - (1 << cid), base + SIRFSOC_DMA_INT_EN); - writel(sdesc->addr >> 2, base + cid * 0x10 + SIRFSOC_DMA_CH_ADDR); - if (sdesc->cyclic) { - writel((1 << cid) | 1 << (cid + 16) | - readl_relaxed(base + SIRFSOC_DMA_CH_LOOP_CTRL), - base + SIRFSOC_DMA_CH_LOOP_CTRL); - } - -} - -/* Execute all queued DMA descriptors */ -static void sirfsoc_dma_execute(struct sirfsoc_dma_chan *schan) -{ - struct sirfsoc_dma *sdma = dma_chan_to_sirfsoc_dma(&schan->chan); - int cid = schan->chan.chan_id; - struct sirfsoc_dma_desc *sdesc = NULL; - void __iomem *base; - - /* - * lock has been held by functions calling this, so we don't hold - * lock again - */ - base = sdma->base; - sdesc = list_first_entry(&schan->queued, struct sirfsoc_dma_desc, - node); - /* Move the first queued descriptor to active list */ - list_move_tail(&sdesc->node, &schan->active); - - if (sdma->type == SIRFSOC_DMA_VER_A7V2) - cid = 0; - - /* Start the DMA transfer */ - sdma->exec_desc(sdesc, cid, schan->mode, base); - - if (sdesc->cyclic) - schan->happened_cyclic = schan->completed_cyclic = 0; -} - -/* Interrupt handler */ -static irqreturn_t sirfsoc_dma_irq(int irq, void *data) -{ - struct sirfsoc_dma *sdma = data; - struct sirfsoc_dma_chan *schan; - struct sirfsoc_dma_desc *sdesc = NULL; - u32 is; - bool chain; - int ch; - void __iomem *reg; - - switch (sdma->type) { - case SIRFSOC_DMA_VER_A6: - case SIRFSOC_DMA_VER_A7V1: - is = readl(sdma->base + SIRFSOC_DMA_CH_INT); - reg = sdma->base + SIRFSOC_DMA_CH_INT; - while ((ch = fls(is) - 1) >= 0) { - is &= ~(1 << ch); - writel_relaxed(1 << ch, reg); - schan = &sdma->channels[ch]; - spin_lock(&schan->lock); - sdesc = list_first_entry(&schan->active, - struct sirfsoc_dma_desc, node); - if (!sdesc->cyclic) { - /* Execute queued descriptors */ - list_splice_tail_init(&schan->active, - &schan->completed); - dma_cookie_complete(&sdesc->desc); - if (!list_empty(&schan->queued)) - sirfsoc_dma_execute(schan); - } else - schan->happened_cyclic++; - spin_unlock(&schan->lock); - } - break; - - case SIRFSOC_DMA_VER_A7V2: - is = readl(sdma->base + SIRFSOC_DMA_INT_ATLAS7); - - reg = sdma->base + SIRFSOC_DMA_INT_ATLAS7; - writel_relaxed(SIRFSOC_DMA_INT_ALL_ATLAS7, reg); - schan = &sdma->channels[0]; - spin_lock(&schan->lock); - sdesc = list_first_entry(&schan->active, - struct sirfsoc_dma_desc, node); - if (!sdesc->cyclic) { - chain = sdesc->chain; - if ((chain && (is & SIRFSOC_DMA_INT_END_INT_ATLAS7)) || - (!chain && - (is & SIRFSOC_DMA_INT_FINI_INT_ATLAS7))) { - /* Execute queued descriptors */ - list_splice_tail_init(&schan->active, - &schan->completed); - dma_cookie_complete(&sdesc->desc); - if (!list_empty(&schan->queued)) - sirfsoc_dma_execute(schan); - } - } else if (sdesc->cyclic && (is & - SIRFSOC_DMA_INT_LOOP_INT_ATLAS7)) - schan->happened_cyclic++; - - spin_unlock(&schan->lock); - break; - - default: - break; - } - - /* Schedule tasklet */ - tasklet_schedule(&sdma->tasklet); - - return IRQ_HANDLED; -} - -/* process completed descriptors */ -static void sirfsoc_dma_process_completed(struct sirfsoc_dma *sdma) -{ - dma_cookie_t last_cookie = 0; - struct sirfsoc_dma_chan *schan; - struct sirfsoc_dma_desc *sdesc; - struct dma_async_tx_descriptor *desc; - unsigned long flags; - unsigned long happened_cyclic; - LIST_HEAD(list); - int i; - - for (i = 0; i < sdma->dma.chancnt; i++) { - schan = &sdma->channels[i]; - - /* Get all completed descriptors */ - spin_lock_irqsave(&schan->lock, flags); - if (!list_empty(&schan->completed)) { - list_splice_tail_init(&schan->completed, &list); - spin_unlock_irqrestore(&schan->lock, flags); - - /* Execute callbacks and run dependencies */ - list_for_each_entry(sdesc, &list, node) { - desc = &sdesc->desc; - - dmaengine_desc_get_callback_invoke(desc, NULL); - last_cookie = desc->cookie; - dma_run_dependencies(desc); - } - - /* Free descriptors */ - spin_lock_irqsave(&schan->lock, flags); - list_splice_tail_init(&list, &schan->free); - schan->chan.completed_cookie = last_cookie; - spin_unlock_irqrestore(&schan->lock, flags); - } else { - if (list_empty(&schan->active)) { - spin_unlock_irqrestore(&schan->lock, flags); - continue; - } - - /* for cyclic channel, desc is always in active list */ - sdesc = list_first_entry(&schan->active, - struct sirfsoc_dma_desc, node); - - /* cyclic DMA */ - happened_cyclic = schan->happened_cyclic; - spin_unlock_irqrestore(&schan->lock, flags); - - desc = &sdesc->desc; - while (happened_cyclic != schan->completed_cyclic) { - dmaengine_desc_get_callback_invoke(desc, NULL); - schan->completed_cyclic++; - } - } - } -} - -/* DMA Tasklet */ -static void sirfsoc_dma_tasklet(struct tasklet_struct *t) -{ - struct sirfsoc_dma *sdma = from_tasklet(sdma, t, tasklet); - - sirfsoc_dma_process_completed(sdma); -} - -/* Submit descriptor to hardware */ -static dma_cookie_t sirfsoc_dma_tx_submit(struct dma_async_tx_descriptor *txd) -{ - struct sirfsoc_dma_chan *schan = dma_chan_to_sirfsoc_dma_chan(txd->chan); - struct sirfsoc_dma_desc *sdesc; - unsigned long flags; - dma_cookie_t cookie; - - sdesc = container_of(txd, struct sirfsoc_dma_desc, desc); - - spin_lock_irqsave(&schan->lock, flags); - - /* Move descriptor to queue */ - list_move_tail(&sdesc->node, &schan->queued); - - cookie = dma_cookie_assign(txd); - - spin_unlock_irqrestore(&schan->lock, flags); - - return cookie; -} - -static int sirfsoc_dma_slave_config(struct dma_chan *chan, - struct dma_slave_config *config) -{ - struct sirfsoc_dma_chan *schan = dma_chan_to_sirfsoc_dma_chan(chan); - unsigned long flags; - - if ((config->src_addr_width != DMA_SLAVE_BUSWIDTH_4_BYTES) || - (config->dst_addr_width != DMA_SLAVE_BUSWIDTH_4_BYTES)) - return -EINVAL; - - spin_lock_irqsave(&schan->lock, flags); - schan->mode = (config->src_maxburst == 4 ? 1 : 0); - spin_unlock_irqrestore(&schan->lock, flags); - - return 0; -} - -static int sirfsoc_dma_terminate_all(struct dma_chan *chan) -{ - struct sirfsoc_dma_chan *schan = dma_chan_to_sirfsoc_dma_chan(chan); - struct sirfsoc_dma *sdma = dma_chan_to_sirfsoc_dma(&schan->chan); - int cid = schan->chan.chan_id; - unsigned long flags; - - spin_lock_irqsave(&schan->lock, flags); - - switch (sdma->type) { - case SIRFSOC_DMA_VER_A7V1: - writel_relaxed(1 << cid, sdma->base + SIRFSOC_DMA_INT_EN_CLR); - writel_relaxed(1 << cid, sdma->base + SIRFSOC_DMA_CH_INT); - writel_relaxed((1 << cid) | 1 << (cid + 16), - sdma->base + - SIRFSOC_DMA_CH_LOOP_CTRL_CLR_ATLAS7); - writel_relaxed(1 << cid, sdma->base + SIRFSOC_DMA_CH_VALID); - break; - case SIRFSOC_DMA_VER_A7V2: - writel_relaxed(0, sdma->base + SIRFSOC_DMA_INT_EN_ATLAS7); - writel_relaxed(SIRFSOC_DMA_INT_ALL_ATLAS7, - sdma->base + SIRFSOC_DMA_INT_ATLAS7); - writel_relaxed(0, sdma->base + SIRFSOC_DMA_LOOP_CTRL_ATLAS7); - writel_relaxed(0, sdma->base + SIRFSOC_DMA_VALID_ATLAS7); - break; - case SIRFSOC_DMA_VER_A6: - writel_relaxed(readl_relaxed(sdma->base + SIRFSOC_DMA_INT_EN) & - ~(1 << cid), sdma->base + SIRFSOC_DMA_INT_EN); - writel_relaxed(readl_relaxed(sdma->base + - SIRFSOC_DMA_CH_LOOP_CTRL) & - ~((1 << cid) | 1 << (cid + 16)), - sdma->base + SIRFSOC_DMA_CH_LOOP_CTRL); - writel_relaxed(1 << cid, sdma->base + SIRFSOC_DMA_CH_VALID); - break; - default: - break; - } - - list_splice_tail_init(&schan->active, &schan->free); - list_splice_tail_init(&schan->queued, &schan->free); - - spin_unlock_irqrestore(&schan->lock, flags); - - return 0; -} - -static int sirfsoc_dma_pause_chan(struct dma_chan *chan) -{ - struct sirfsoc_dma_chan *schan = dma_chan_to_sirfsoc_dma_chan(chan); - struct sirfsoc_dma *sdma = dma_chan_to_sirfsoc_dma(&schan->chan); - int cid = schan->chan.chan_id; - unsigned long flags; - - spin_lock_irqsave(&schan->lock, flags); - - switch (sdma->type) { - case SIRFSOC_DMA_VER_A7V1: - writel_relaxed((1 << cid) | 1 << (cid + 16), - sdma->base + - SIRFSOC_DMA_CH_LOOP_CTRL_CLR_ATLAS7); - break; - case SIRFSOC_DMA_VER_A7V2: - writel_relaxed(0, sdma->base + SIRFSOC_DMA_LOOP_CTRL_ATLAS7); - break; - case SIRFSOC_DMA_VER_A6: - writel_relaxed(readl_relaxed(sdma->base + - SIRFSOC_DMA_CH_LOOP_CTRL) & - ~((1 << cid) | 1 << (cid + 16)), - sdma->base + SIRFSOC_DMA_CH_LOOP_CTRL); - break; - - default: - break; - } - - spin_unlock_irqrestore(&schan->lock, flags); - - return 0; -} - -static int sirfsoc_dma_resume_chan(struct dma_chan *chan) -{ - struct sirfsoc_dma_chan *schan = dma_chan_to_sirfsoc_dma_chan(chan); - struct sirfsoc_dma *sdma = dma_chan_to_sirfsoc_dma(&schan->chan); - int cid = schan->chan.chan_id; - unsigned long flags; - - spin_lock_irqsave(&schan->lock, flags); - switch (sdma->type) { - case SIRFSOC_DMA_VER_A7V1: - writel_relaxed((1 << cid) | 1 << (cid + 16), - sdma->base + SIRFSOC_DMA_CH_LOOP_CTRL_ATLAS7); - break; - case SIRFSOC_DMA_VER_A7V2: - writel_relaxed(0x10001, - sdma->base + SIRFSOC_DMA_LOOP_CTRL_ATLAS7); - break; - case SIRFSOC_DMA_VER_A6: - writel_relaxed(readl_relaxed(sdma->base + - SIRFSOC_DMA_CH_LOOP_CTRL) | - ((1 << cid) | 1 << (cid + 16)), - sdma->base + SIRFSOC_DMA_CH_LOOP_CTRL); - break; - - default: - break; - } - - spin_unlock_irqrestore(&schan->lock, flags); - - return 0; -} - -/* Alloc channel resources */ -static int sirfsoc_dma_alloc_chan_resources(struct dma_chan *chan) -{ - struct sirfsoc_dma *sdma = dma_chan_to_sirfsoc_dma(chan); - struct sirfsoc_dma_chan *schan = dma_chan_to_sirfsoc_dma_chan(chan); - struct sirfsoc_dma_desc *sdesc; - unsigned long flags; - LIST_HEAD(descs); - int i; - - pm_runtime_get_sync(sdma->dma.dev); - - /* Alloc descriptors for this channel */ - for (i = 0; i < SIRFSOC_DMA_DESCRIPTORS; i++) { - sdesc = kzalloc(sizeof(*sdesc), GFP_KERNEL); - if (!sdesc) { - dev_notice(sdma->dma.dev, "Memory allocation error. " - "Allocated only %u descriptors\n", i); - break; - } - - dma_async_tx_descriptor_init(&sdesc->desc, chan); - sdesc->desc.flags = DMA_CTRL_ACK; - sdesc->desc.tx_submit = sirfsoc_dma_tx_submit; - - list_add_tail(&sdesc->node, &descs); - } - - /* Return error only if no descriptors were allocated */ - if (i == 0) - return -ENOMEM; - - spin_lock_irqsave(&schan->lock, flags); - - list_splice_tail_init(&descs, &schan->free); - spin_unlock_irqrestore(&schan->lock, flags); - - return i; -} - -/* Free channel resources */ -static void sirfsoc_dma_free_chan_resources(struct dma_chan *chan) -{ - struct sirfsoc_dma_chan *schan = dma_chan_to_sirfsoc_dma_chan(chan); - struct sirfsoc_dma *sdma = dma_chan_to_sirfsoc_dma(chan); - struct sirfsoc_dma_desc *sdesc, *tmp; - unsigned long flags; - LIST_HEAD(descs); - - spin_lock_irqsave(&schan->lock, flags); - - /* Channel must be idle */ - BUG_ON(!list_empty(&schan->prepared)); - BUG_ON(!list_empty(&schan->queued)); - BUG_ON(!list_empty(&schan->active)); - BUG_ON(!list_empty(&schan->completed)); - - /* Move data */ - list_splice_tail_init(&schan->free, &descs); - - spin_unlock_irqrestore(&schan->lock, flags); - - /* Free descriptors */ - list_for_each_entry_safe(sdesc, tmp, &descs, node) - kfree(sdesc); - - pm_runtime_put(sdma->dma.dev); -} - -/* Send pending descriptor to hardware */ -static void sirfsoc_dma_issue_pending(struct dma_chan *chan) -{ - struct sirfsoc_dma_chan *schan = dma_chan_to_sirfsoc_dma_chan(chan); - unsigned long flags; - - spin_lock_irqsave(&schan->lock, flags); - - if (list_empty(&schan->active) && !list_empty(&schan->queued)) - sirfsoc_dma_execute(schan); - - spin_unlock_irqrestore(&schan->lock, flags); -} - -/* Check request completion status */ -static enum dma_status -sirfsoc_dma_tx_status(struct dma_chan *chan, dma_cookie_t cookie, - struct dma_tx_state *txstate) -{ - struct sirfsoc_dma *sdma = dma_chan_to_sirfsoc_dma(chan); - struct sirfsoc_dma_chan *schan = dma_chan_to_sirfsoc_dma_chan(chan); - unsigned long flags; - enum dma_status ret; - struct sirfsoc_dma_desc *sdesc; - int cid = schan->chan.chan_id; - unsigned long dma_pos; - unsigned long dma_request_bytes; - unsigned long residue; - - spin_lock_irqsave(&schan->lock, flags); - - if (list_empty(&schan->active)) { - ret = dma_cookie_status(chan, cookie, txstate); - dma_set_residue(txstate, 0); - spin_unlock_irqrestore(&schan->lock, flags); - return ret; - } - sdesc = list_first_entry(&schan->active, struct sirfsoc_dma_desc, node); - if (sdesc->cyclic) - dma_request_bytes = (sdesc->xlen + 1) * (sdesc->ylen + 1) * - (sdesc->width * SIRFSOC_DMA_WORD_LEN); - else - dma_request_bytes = sdesc->xlen * SIRFSOC_DMA_WORD_LEN; - - ret = dma_cookie_status(chan, cookie, txstate); - - if (sdma->type == SIRFSOC_DMA_VER_A7V2) - cid = 0; - - if (sdma->type == SIRFSOC_DMA_VER_A7V2) { - dma_pos = readl_relaxed(sdma->base + SIRFSOC_DMA_CUR_DATA_ADDR); - } else { - dma_pos = readl_relaxed( - sdma->base + cid * 0x10 + SIRFSOC_DMA_CH_ADDR) << 2; - } - - residue = dma_request_bytes - (dma_pos - sdesc->addr); - dma_set_residue(txstate, residue); - - spin_unlock_irqrestore(&schan->lock, flags); - - return ret; -} - -static struct dma_async_tx_descriptor *sirfsoc_dma_prep_interleaved( - struct dma_chan *chan, struct dma_interleaved_template *xt, - unsigned long flags) -{ - struct sirfsoc_dma *sdma = dma_chan_to_sirfsoc_dma(chan); - struct sirfsoc_dma_chan *schan = dma_chan_to_sirfsoc_dma_chan(chan); - struct sirfsoc_dma_desc *sdesc = NULL; - unsigned long iflags; - int ret; - - if ((xt->dir != DMA_MEM_TO_DEV) && (xt->dir != DMA_DEV_TO_MEM)) { - ret = -EINVAL; - goto err_dir; - } - - /* Get free descriptor */ - spin_lock_irqsave(&schan->lock, iflags); - if (!list_empty(&schan->free)) { - sdesc = list_first_entry(&schan->free, struct sirfsoc_dma_desc, - node); - list_del(&sdesc->node); - } - spin_unlock_irqrestore(&schan->lock, iflags); - - if (!sdesc) { - /* try to free completed descriptors */ - sirfsoc_dma_process_completed(sdma); - ret = 0; - goto no_desc; - } - - /* Place descriptor in prepared list */ - spin_lock_irqsave(&schan->lock, iflags); - - /* - * Number of chunks in a frame can only be 1 for prima2 - * and ylen (number of frame - 1) must be at least 0 - */ - if ((xt->frame_size == 1) && (xt->numf > 0)) { - sdesc->cyclic = 0; - sdesc->xlen = xt->sgl[0].size / SIRFSOC_DMA_WORD_LEN; - sdesc->width = (xt->sgl[0].size + xt->sgl[0].icg) / - SIRFSOC_DMA_WORD_LEN; - sdesc->ylen = xt->numf - 1; - if (xt->dir == DMA_MEM_TO_DEV) { - sdesc->addr = xt->src_start; - sdesc->dir = 1; - } else { - sdesc->addr = xt->dst_start; - sdesc->dir = 0; - } - - list_add_tail(&sdesc->node, &schan->prepared); - } else { - pr_err("sirfsoc DMA Invalid xfer\n"); - ret = -EINVAL; - goto err_xfer; - } - spin_unlock_irqrestore(&schan->lock, iflags); - - return &sdesc->desc; -err_xfer: - spin_unlock_irqrestore(&schan->lock, iflags); -no_desc: -err_dir: - return ERR_PTR(ret); -} - -static struct dma_async_tx_descriptor * -sirfsoc_dma_prep_cyclic(struct dma_chan *chan, dma_addr_t addr, - size_t buf_len, size_t period_len, - enum dma_transfer_direction direction, unsigned long flags) -{ - struct sirfsoc_dma_chan *schan = dma_chan_to_sirfsoc_dma_chan(chan); - struct sirfsoc_dma_desc *sdesc = NULL; - unsigned long iflags; - - /* - * we only support cycle transfer with 2 period - * If the X-length is set to 0, it would be the loop mode. - * The DMA address keeps increasing until reaching the end of a loop - * area whose size is defined by (DMA_WIDTH x (Y_LENGTH + 1)). Then - * the DMA address goes back to the beginning of this area. - * In loop mode, the DMA data region is divided into two parts, BUFA - * and BUFB. DMA controller generates interrupts twice in each loop: - * when the DMA address reaches the end of BUFA or the end of the - * BUFB - */ - if (buf_len != 2 * period_len) - return ERR_PTR(-EINVAL); - - /* Get free descriptor */ - spin_lock_irqsave(&schan->lock, iflags); - if (!list_empty(&schan->free)) { - sdesc = list_first_entry(&schan->free, struct sirfsoc_dma_desc, - node); - list_del(&sdesc->node); - } - spin_unlock_irqrestore(&schan->lock, iflags); - - if (!sdesc) - return NULL; - - /* Place descriptor in prepared list */ - spin_lock_irqsave(&schan->lock, iflags); - sdesc->addr = addr; - sdesc->cyclic = 1; - sdesc->xlen = 0; - sdesc->ylen = buf_len / SIRFSOC_DMA_WORD_LEN - 1; - sdesc->width = 1; - list_add_tail(&sdesc->node, &schan->prepared); - spin_unlock_irqrestore(&schan->lock, iflags); - - return &sdesc->desc; -} - -/* - * The DMA controller consists of 16 independent DMA channels. - * Each channel is allocated to a different function - */ -bool sirfsoc_dma_filter_id(struct dma_chan *chan, void *chan_id) -{ - unsigned int ch_nr = (unsigned int) chan_id; - - if (ch_nr == chan->chan_id + - chan->device->dev_id * SIRFSOC_DMA_CHANNELS) - return true; - - return false; -} -EXPORT_SYMBOL(sirfsoc_dma_filter_id); - -#define SIRFSOC_DMA_BUSWIDTHS \ - (BIT(DMA_SLAVE_BUSWIDTH_UNDEFINED) | \ - BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) | \ - BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) | \ - BIT(DMA_SLAVE_BUSWIDTH_4_BYTES) | \ - BIT(DMA_SLAVE_BUSWIDTH_8_BYTES)) - -static struct dma_chan *of_dma_sirfsoc_xlate(struct of_phandle_args *dma_spec, - struct of_dma *ofdma) -{ - struct sirfsoc_dma *sdma = ofdma->of_dma_data; - unsigned int request = dma_spec->args[0]; - - if (request >= SIRFSOC_DMA_CHANNELS) - return NULL; - - return dma_get_slave_channel(&sdma->channels[request].chan); -} - -static int sirfsoc_dma_probe(struct platform_device *op) -{ - struct device_node *dn = op->dev.of_node; - struct device *dev = &op->dev; - struct dma_device *dma; - struct sirfsoc_dma *sdma; - struct sirfsoc_dma_chan *schan; - struct sirfsoc_dmadata *data; - struct resource res; - ulong regs_start, regs_size; - u32 id; - int ret, i; - - sdma = devm_kzalloc(dev, sizeof(*sdma), GFP_KERNEL); - if (!sdma) - return -ENOMEM; - - data = (struct sirfsoc_dmadata *) - (of_match_device(op->dev.driver->of_match_table, - &op->dev)->data); - sdma->exec_desc = data->exec; - sdma->type = data->type; - - if (of_property_read_u32(dn, "cell-index", &id)) { - dev_err(dev, "Fail to get DMAC index\n"); - return -ENODEV; - } - - sdma->irq = irq_of_parse_and_map(dn, 0); - if (!sdma->irq) { - dev_err(dev, "Error mapping IRQ!\n"); - return -EINVAL; - } - - sdma->clk = devm_clk_get(dev, NULL); - if (IS_ERR(sdma->clk)) { - dev_err(dev, "failed to get a clock.\n"); - return PTR_ERR(sdma->clk); - } - - ret = of_address_to_resource(dn, 0, &res); - if (ret) { - dev_err(dev, "Error parsing memory region!\n"); - goto irq_dispose; - } - - regs_start = res.start; - regs_size = resource_size(&res); - - sdma->base = devm_ioremap(dev, regs_start, regs_size); - if (!sdma->base) { - dev_err(dev, "Error mapping memory region!\n"); - ret = -ENOMEM; - goto irq_dispose; - } - - ret = request_irq(sdma->irq, &sirfsoc_dma_irq, 0, DRV_NAME, sdma); - if (ret) { - dev_err(dev, "Error requesting IRQ!\n"); - ret = -EINVAL; - goto irq_dispose; - } - - dma = &sdma->dma; - dma->dev = dev; - - dma->device_alloc_chan_resources = sirfsoc_dma_alloc_chan_resources; - dma->device_free_chan_resources = sirfsoc_dma_free_chan_resources; - dma->device_issue_pending = sirfsoc_dma_issue_pending; - dma->device_config = sirfsoc_dma_slave_config; - dma->device_pause = sirfsoc_dma_pause_chan; - dma->device_resume = sirfsoc_dma_resume_chan; - dma->device_terminate_all = sirfsoc_dma_terminate_all; - dma->device_tx_status = sirfsoc_dma_tx_status; - dma->device_prep_interleaved_dma = sirfsoc_dma_prep_interleaved; - dma->device_prep_dma_cyclic = sirfsoc_dma_prep_cyclic; - dma->src_addr_widths = SIRFSOC_DMA_BUSWIDTHS; - dma->dst_addr_widths = SIRFSOC_DMA_BUSWIDTHS; - dma->directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV); - - INIT_LIST_HEAD(&dma->channels); - dma_cap_set(DMA_SLAVE, dma->cap_mask); - dma_cap_set(DMA_CYCLIC, dma->cap_mask); - dma_cap_set(DMA_INTERLEAVE, dma->cap_mask); - dma_cap_set(DMA_PRIVATE, dma->cap_mask); - - for (i = 0; i < SIRFSOC_DMA_CHANNELS; i++) { - schan = &sdma->channels[i]; - - schan->chan.device = dma; - dma_cookie_init(&schan->chan); - - INIT_LIST_HEAD(&schan->free); - INIT_LIST_HEAD(&schan->prepared); - INIT_LIST_HEAD(&schan->queued); - INIT_LIST_HEAD(&schan->active); - INIT_LIST_HEAD(&schan->completed); - - spin_lock_init(&schan->lock); - list_add_tail(&schan->chan.device_node, &dma->channels); - } - - tasklet_setup(&sdma->tasklet, sirfsoc_dma_tasklet); - - /* Register DMA engine */ - dev_set_drvdata(dev, sdma); - - ret = dma_async_device_register(dma); - if (ret) - goto free_irq; - - /* Device-tree DMA controller registration */ - ret = of_dma_controller_register(dn, of_dma_sirfsoc_xlate, sdma); - if (ret) { - dev_err(dev, "failed to register DMA controller\n"); - goto unreg_dma_dev; - } - - pm_runtime_enable(&op->dev); - dev_info(dev, "initialized SIRFSOC DMAC driver\n"); - - return 0; - -unreg_dma_dev: - dma_async_device_unregister(dma); -free_irq: - free_irq(sdma->irq, sdma); -irq_dispose: - irq_dispose_mapping(sdma->irq); - return ret; -} - -static int sirfsoc_dma_remove(struct platform_device *op) -{ - struct device *dev = &op->dev; - struct sirfsoc_dma *sdma = dev_get_drvdata(dev); - - of_dma_controller_free(op->dev.of_node); - dma_async_device_unregister(&sdma->dma); - free_irq(sdma->irq, sdma); - tasklet_kill(&sdma->tasklet); - irq_dispose_mapping(sdma->irq); - pm_runtime_disable(&op->dev); - if (!pm_runtime_status_suspended(&op->dev)) - sirfsoc_dma_runtime_suspend(&op->dev); - - return 0; -} - -static int __maybe_unused sirfsoc_dma_runtime_suspend(struct device *dev) -{ - struct sirfsoc_dma *sdma = dev_get_drvdata(dev); - - clk_disable_unprepare(sdma->clk); - return 0; -} - -static int __maybe_unused sirfsoc_dma_runtime_resume(struct device *dev) -{ - struct sirfsoc_dma *sdma = dev_get_drvdata(dev); - int ret; - - ret = clk_prepare_enable(sdma->clk); - if (ret < 0) { - dev_err(dev, "clk_enable failed: %d\n", ret); - return ret; - } - return 0; -} - -static int __maybe_unused sirfsoc_dma_pm_suspend(struct device *dev) -{ - struct sirfsoc_dma *sdma = dev_get_drvdata(dev); - struct sirfsoc_dma_regs *save = &sdma->regs_save; - struct sirfsoc_dma_chan *schan; - int ch; - int ret; - int count; - u32 int_offset; - - /* - * if we were runtime-suspended before, resume to enable clock - * before accessing register - */ - if (pm_runtime_status_suspended(dev)) { - ret = sirfsoc_dma_runtime_resume(dev); - if (ret < 0) - return ret; - } - - if (sdma->type == SIRFSOC_DMA_VER_A7V2) { - count = 1; - int_offset = SIRFSOC_DMA_INT_EN_ATLAS7; - } else { - count = SIRFSOC_DMA_CHANNELS; - int_offset = SIRFSOC_DMA_INT_EN; - } - - /* - * DMA controller will lose all registers while suspending - * so we need to save registers for active channels - */ - for (ch = 0; ch < count; ch++) { - schan = &sdma->channels[ch]; - if (list_empty(&schan->active)) - continue; - save->ctrl[ch] = readl_relaxed(sdma->base + - ch * 0x10 + SIRFSOC_DMA_CH_CTRL); - } - save->interrupt_en = readl_relaxed(sdma->base + int_offset); - - /* Disable clock */ - sirfsoc_dma_runtime_suspend(dev); - - return 0; -} - -static int __maybe_unused sirfsoc_dma_pm_resume(struct device *dev) -{ - struct sirfsoc_dma *sdma = dev_get_drvdata(dev); - struct sirfsoc_dma_regs *save = &sdma->regs_save; - struct sirfsoc_dma_desc *sdesc; - struct sirfsoc_dma_chan *schan; - int ch; - int ret; - int count; - u32 int_offset; - u32 width_offset; - - /* Enable clock before accessing register */ - ret = sirfsoc_dma_runtime_resume(dev); - if (ret < 0) - return ret; - - if (sdma->type == SIRFSOC_DMA_VER_A7V2) { - count = 1; - int_offset = SIRFSOC_DMA_INT_EN_ATLAS7; - width_offset = SIRFSOC_DMA_WIDTH_ATLAS7; - } else { - count = SIRFSOC_DMA_CHANNELS; - int_offset = SIRFSOC_DMA_INT_EN; - width_offset = SIRFSOC_DMA_WIDTH_0; - } - - writel_relaxed(save->interrupt_en, sdma->base + int_offset); - for (ch = 0; ch < count; ch++) { - schan = &sdma->channels[ch]; - if (list_empty(&schan->active)) - continue; - sdesc = list_first_entry(&schan->active, - struct sirfsoc_dma_desc, - node); - writel_relaxed(sdesc->width, - sdma->base + width_offset + ch * 4); - writel_relaxed(sdesc->xlen, - sdma->base + ch * 0x10 + SIRFSOC_DMA_CH_XLEN); - writel_relaxed(sdesc->ylen, - sdma->base + ch * 0x10 + SIRFSOC_DMA_CH_YLEN); - writel_relaxed(save->ctrl[ch], - sdma->base + ch * 0x10 + SIRFSOC_DMA_CH_CTRL); - if (sdma->type == SIRFSOC_DMA_VER_A7V2) { - writel_relaxed(sdesc->addr, - sdma->base + SIRFSOC_DMA_CH_ADDR); - } else { - writel_relaxed(sdesc->addr >> 2, - sdma->base + ch * 0x10 + SIRFSOC_DMA_CH_ADDR); - - } - } - - /* if we were runtime-suspended before, suspend again */ - if (pm_runtime_status_suspended(dev)) - sirfsoc_dma_runtime_suspend(dev); - - return 0; -} - -static const struct dev_pm_ops sirfsoc_dma_pm_ops = { - SET_RUNTIME_PM_OPS(sirfsoc_dma_runtime_suspend, sirfsoc_dma_runtime_resume, NULL) - SET_SYSTEM_SLEEP_PM_OPS(sirfsoc_dma_pm_suspend, sirfsoc_dma_pm_resume) -}; - -static struct sirfsoc_dmadata sirfsoc_dmadata_a6 = { - .exec = sirfsoc_dma_execute_hw_a6, - .type = SIRFSOC_DMA_VER_A6, -}; - -static struct sirfsoc_dmadata sirfsoc_dmadata_a7v1 = { - .exec = sirfsoc_dma_execute_hw_a7v1, - .type = SIRFSOC_DMA_VER_A7V1, -}; - -static struct sirfsoc_dmadata sirfsoc_dmadata_a7v2 = { - .exec = sirfsoc_dma_execute_hw_a7v2, - .type = SIRFSOC_DMA_VER_A7V2, -}; - -static const struct of_device_id sirfsoc_dma_match[] = { - { .compatible = "sirf,prima2-dmac", .data = &sirfsoc_dmadata_a6,}, - { .compatible = "sirf,atlas7-dmac", .data = &sirfsoc_dmadata_a7v1,}, - { .compatible = "sirf,atlas7-dmac-v2", .data = &sirfsoc_dmadata_a7v2,}, - {}, -}; -MODULE_DEVICE_TABLE(of, sirfsoc_dma_match); - -static struct platform_driver sirfsoc_dma_driver = { - .probe = sirfsoc_dma_probe, - .remove = sirfsoc_dma_remove, - .driver = { - .name = DRV_NAME, - .pm = &sirfsoc_dma_pm_ops, - .of_match_table = sirfsoc_dma_match, - }, -}; - -static __init int sirfsoc_dma_init(void) -{ - return platform_driver_register(&sirfsoc_dma_driver); -} - -static void __exit sirfsoc_dma_exit(void) -{ - platform_driver_unregister(&sirfsoc_dma_driver); -} - -subsys_initcall(sirfsoc_dma_init); -module_exit(sirfsoc_dma_exit); - -MODULE_AUTHOR("Rongjun Ying "); -MODULE_AUTHOR("Barry Song "); -MODULE_DESCRIPTION("SIRFSOC DMA control driver"); -MODULE_LICENSE("GPL v2"); diff --git a/include/linux/sirfsoc_dma.h b/include/linux/sirfsoc_dma.h deleted file mode 100644 index 50161b6afb61..000000000000 --- a/include/linux/sirfsoc_dma.h +++ /dev/null @@ -1,7 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _SIRFSOC_DMA_H_ -#define _SIRFSOC_DMA_H_ - -bool sirfsoc_dma_filter_id(struct dma_chan *chan, void *chan_id); - -#endif -- cgit v1.2.3 From a033a74e8b66336fc2ea379842be6bcf176cbfbc Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 20 Jan 2021 14:18:59 +0100 Subject: dmaengine: remove coh901318 driver The ST-Ericsson U300 platform is getting removed, so this driver is no longer needed. Signed-off-by: Arnd Bergmann Reviewed-by: Linus Walleij Cc: Linus Walleij Link: https://lore.kernel.org/r/20210120131859.2056308-4-arnd@kernel.org Signed-off-by: Vinod Koul --- .../devicetree/bindings/dma/ste-coh901318.txt | 32 - drivers/dma/Kconfig | 7 - drivers/dma/Makefile | 1 - drivers/dma/coh901318.c | 2808 -------------------- drivers/dma/coh901318.h | 141 - drivers/dma/coh901318_lli.c | 313 --- include/linux/platform_data/dma-coh901318.h | 72 - 7 files changed, 3374 deletions(-) delete mode 100644 Documentation/devicetree/bindings/dma/ste-coh901318.txt delete mode 100644 drivers/dma/coh901318.c delete mode 100644 drivers/dma/coh901318.h delete mode 100644 drivers/dma/coh901318_lli.c delete mode 100644 include/linux/platform_data/dma-coh901318.h (limited to 'include') diff --git a/Documentation/devicetree/bindings/dma/ste-coh901318.txt b/Documentation/devicetree/bindings/dma/ste-coh901318.txt deleted file mode 100644 index 091ad057e9cf..000000000000 --- a/Documentation/devicetree/bindings/dma/ste-coh901318.txt +++ /dev/null @@ -1,32 +0,0 @@ -ST-Ericsson COH 901 318 DMA Controller - -This is a DMA controller which has begun as a fork of the -ARM PL08x PrimeCell VHDL code. - -Required properties: -- compatible: should be "stericsson,coh901318" -- reg: register locations and length -- interrupts: the single DMA IRQ -- #dma-cells: must be set to <1>, as the channels on the - COH 901 318 are simple and identified by a single number -- dma-channels: the number of DMA channels handled - -Example: - -dmac: dma-controller@c00020000 { - compatible = "stericsson,coh901318"; - reg = <0xc0020000 0x1000>; - interrupt-parent = <&vica>; - interrupts = <2>; - #dma-cells = <1>; - dma-channels = <40>; -}; - -Consumers example: - -uart0: serial@c0013000 { - compatible = "..."; - (...) - dmas = <&dmac 17 &dmac 18>; - dma-names = "tx", "rx"; -}; diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index 4fd6a90cfadf..725cda4aa2a3 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -124,13 +124,6 @@ config BCM_SBA_RAID has the capability to offload memcpy, xor and pq computation for raid5/6. -config COH901318 - bool "ST-Ericsson COH901318 DMA support" - select DMA_ENGINE - depends on ARCH_U300 || COMPILE_TEST - help - Enable support for ST-Ericsson COH 901 318 DMA. - config DMA_BCM2835 tristate "BCM2835 DMA engine support" depends on ARCH_BCM2835 diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile index 4aed5ea59922..aa69094e3547 100644 --- a/drivers/dma/Makefile +++ b/drivers/dma/Makefile @@ -20,7 +20,6 @@ obj-$(CONFIG_AT_HDMAC) += at_hdmac.o obj-$(CONFIG_AT_XDMAC) += at_xdmac.o obj-$(CONFIG_AXI_DMAC) += dma-axi-dmac.o obj-$(CONFIG_BCM_SBA_RAID) += bcm-sba-raid.o -obj-$(CONFIG_COH901318) += coh901318.o coh901318_lli.o obj-$(CONFIG_DMA_BCM2835) += bcm2835-dma.o obj-$(CONFIG_DMA_JZ4780) += dma-jz4780.o obj-$(CONFIG_DMA_SA11X0) += sa11x0-dma.o diff --git a/drivers/dma/coh901318.c b/drivers/dma/coh901318.c deleted file mode 100644 index 95b9b2f5358e..000000000000 --- a/drivers/dma/coh901318.c +++ /dev/null @@ -1,2808 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * driver/dma/coh901318.c - * - * Copyright (C) 2007-2009 ST-Ericsson - * DMA driver for COH 901 318 - * Author: Per Friden - */ - -#include -#include -#include /* printk() */ -#include /* everything... */ -#include -#include /* kmalloc() */ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "coh901318.h" -#include "dmaengine.h" - -#define COH901318_MOD32_MASK (0x1F) -#define COH901318_WORD_MASK (0xFFFFFFFF) -/* INT_STATUS - Interrupt Status Registers 32bit (R/-) */ -#define COH901318_INT_STATUS1 (0x0000) -#define COH901318_INT_STATUS2 (0x0004) -/* TC_INT_STATUS - Terminal Count Interrupt Status Registers 32bit (R/-) */ -#define COH901318_TC_INT_STATUS1 (0x0008) -#define COH901318_TC_INT_STATUS2 (0x000C) -/* TC_INT_CLEAR - Terminal Count Interrupt Clear Registers 32bit (-/W) */ -#define COH901318_TC_INT_CLEAR1 (0x0010) -#define COH901318_TC_INT_CLEAR2 (0x0014) -/* RAW_TC_INT_STATUS - Raw Term Count Interrupt Status Registers 32bit (R/-) */ -#define COH901318_RAW_TC_INT_STATUS1 (0x0018) -#define COH901318_RAW_TC_INT_STATUS2 (0x001C) -/* BE_INT_STATUS - Bus Error Interrupt Status Registers 32bit (R/-) */ -#define COH901318_BE_INT_STATUS1 (0x0020) -#define COH901318_BE_INT_STATUS2 (0x0024) -/* BE_INT_CLEAR - Bus Error Interrupt Clear Registers 32bit (-/W) */ -#define COH901318_BE_INT_CLEAR1 (0x0028) -#define COH901318_BE_INT_CLEAR2 (0x002C) -/* RAW_BE_INT_STATUS - Raw Term Count Interrupt Status Registers 32bit (R/-) */ -#define COH901318_RAW_BE_INT_STATUS1 (0x0030) -#define COH901318_RAW_BE_INT_STATUS2 (0x0034) - -/* - * CX_CFG - Channel Configuration Registers 32bit (R/W) - */ -#define COH901318_CX_CFG (0x0100) -#define COH901318_CX_CFG_SPACING (0x04) -/* Channel enable activates tha dma job */ -#define COH901318_CX_CFG_CH_ENABLE (0x00000001) -#define COH901318_CX_CFG_CH_DISABLE (0x00000000) -/* Request Mode */ -#define COH901318_CX_CFG_RM_MASK (0x00000006) -#define COH901318_CX_CFG_RM_MEMORY_TO_MEMORY (0x0 << 1) -#define COH901318_CX_CFG_RM_PRIMARY_TO_MEMORY (0x1 << 1) -#define COH901318_CX_CFG_RM_MEMORY_TO_PRIMARY (0x1 << 1) -#define COH901318_CX_CFG_RM_PRIMARY_TO_SECONDARY (0x3 << 1) -#define COH901318_CX_CFG_RM_SECONDARY_TO_PRIMARY (0x3 << 1) -/* Linked channel request field. RM must == 11 */ -#define COH901318_CX_CFG_LCRF_SHIFT 3 -#define COH901318_CX_CFG_LCRF_MASK (0x000001F8) -#define COH901318_CX_CFG_LCR_DISABLE (0x00000000) -/* Terminal Counter Interrupt Request Mask */ -#define COH901318_CX_CFG_TC_IRQ_ENABLE (0x00000200) -#define COH901318_CX_CFG_TC_IRQ_DISABLE (0x00000000) -/* Bus Error interrupt Mask */ -#define COH901318_CX_CFG_BE_IRQ_ENABLE (0x00000400) -#define COH901318_CX_CFG_BE_IRQ_DISABLE (0x00000000) - -/* - * CX_STAT - Channel Status Registers 32bit (R/-) - */ -#define COH901318_CX_STAT (0x0200) -#define COH901318_CX_STAT_SPACING (0x04) -#define COH901318_CX_STAT_RBE_IRQ_IND (0x00000008) -#define COH901318_CX_STAT_RTC_IRQ_IND (0x00000004) -#define COH901318_CX_STAT_ACTIVE (0x00000002) -#define COH901318_CX_STAT_ENABLED (0x00000001) - -/* - * CX_CTRL - Channel Control Registers 32bit (R/W) - */ -#define COH901318_CX_CTRL (0x0400) -#define COH901318_CX_CTRL_SPACING (0x10) -/* Transfer Count Enable */ -#define COH901318_CX_CTRL_TC_ENABLE (0x00001000) -#define COH901318_CX_CTRL_TC_DISABLE (0x00000000) -/* Transfer Count Value 0 - 4095 */ -#define COH901318_CX_CTRL_TC_VALUE_MASK (0x00000FFF) -/* Burst count */ -#define COH901318_CX_CTRL_BURST_COUNT_MASK (0x0000E000) -#define COH901318_CX_CTRL_BURST_COUNT_64_BYTES (0x7 << 13) -#define COH901318_CX_CTRL_BURST_COUNT_48_BYTES (0x6 << 13) -#define COH901318_CX_CTRL_BURST_COUNT_32_BYTES (0x5 << 13) -#define COH901318_CX_CTRL_BURST_COUNT_16_BYTES (0x4 << 13) -#define COH901318_CX_CTRL_BURST_COUNT_8_BYTES (0x3 << 13) -#define COH901318_CX_CTRL_BURST_COUNT_4_BYTES (0x2 << 13) -#define COH901318_CX_CTRL_BURST_COUNT_2_BYTES (0x1 << 13) -#define COH901318_CX_CTRL_BURST_COUNT_1_BYTE (0x0 << 13) -/* Source bus size */ -#define COH901318_CX_CTRL_SRC_BUS_SIZE_MASK (0x00030000) -#define COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS (0x2 << 16) -#define COH901318_CX_CTRL_SRC_BUS_SIZE_16_BITS (0x1 << 16) -#define COH901318_CX_CTRL_SRC_BUS_SIZE_8_BITS (0x0 << 16) -/* Source address increment */ -#define COH901318_CX_CTRL_SRC_ADDR_INC_ENABLE (0x00040000) -#define COH901318_CX_CTRL_SRC_ADDR_INC_DISABLE (0x00000000) -/* Destination Bus Size */ -#define COH901318_CX_CTRL_DST_BUS_SIZE_MASK (0x00180000) -#define COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS (0x2 << 19) -#define COH901318_CX_CTRL_DST_BUS_SIZE_16_BITS (0x1 << 19) -#define COH901318_CX_CTRL_DST_BUS_SIZE_8_BITS (0x0 << 19) -/* Destination address increment */ -#define COH901318_CX_CTRL_DST_ADDR_INC_ENABLE (0x00200000) -#define COH901318_CX_CTRL_DST_ADDR_INC_DISABLE (0x00000000) -/* Master Mode (Master2 is only connected to MSL) */ -#define COH901318_CX_CTRL_MASTER_MODE_MASK (0x00C00000) -#define COH901318_CX_CTRL_MASTER_MODE_M2R_M1W (0x3 << 22) -#define COH901318_CX_CTRL_MASTER_MODE_M1R_M2W (0x2 << 22) -#define COH901318_CX_CTRL_MASTER_MODE_M2RW (0x1 << 22) -#define COH901318_CX_CTRL_MASTER_MODE_M1RW (0x0 << 22) -/* Terminal Count flag to PER enable */ -#define COH901318_CX_CTRL_TCP_ENABLE (0x01000000) -#define COH901318_CX_CTRL_TCP_DISABLE (0x00000000) -/* Terminal Count flags to CPU enable */ -#define COH901318_CX_CTRL_TC_IRQ_ENABLE (0x02000000) -#define COH901318_CX_CTRL_TC_IRQ_DISABLE (0x00000000) -/* Hand shake to peripheral */ -#define COH901318_CX_CTRL_HSP_ENABLE (0x04000000) -#define COH901318_CX_CTRL_HSP_DISABLE (0x00000000) -#define COH901318_CX_CTRL_HSS_ENABLE (0x08000000) -#define COH901318_CX_CTRL_HSS_DISABLE (0x00000000) -/* DMA mode */ -#define COH901318_CX_CTRL_DDMA_MASK (0x30000000) -#define COH901318_CX_CTRL_DDMA_LEGACY (0x0 << 28) -#define COH901318_CX_CTRL_DDMA_DEMAND_DMA1 (0x1 << 28) -#define COH901318_CX_CTRL_DDMA_DEMAND_DMA2 (0x2 << 28) -/* Primary Request Data Destination */ -#define COH901318_CX_CTRL_PRDD_MASK (0x40000000) -#define COH901318_CX_CTRL_PRDD_DEST (0x1 << 30) -#define COH901318_CX_CTRL_PRDD_SOURCE (0x0 << 30) - -/* - * CX_SRC_ADDR - Channel Source Address Registers 32bit (R/W) - */ -#define COH901318_CX_SRC_ADDR (0x0404) -#define COH901318_CX_SRC_ADDR_SPACING (0x10) - -/* - * CX_DST_ADDR - Channel Destination Address Registers 32bit R/W - */ -#define COH901318_CX_DST_ADDR (0x0408) -#define COH901318_CX_DST_ADDR_SPACING (0x10) - -/* - * CX_LNK_ADDR - Channel Link Address Registers 32bit (R/W) - */ -#define COH901318_CX_LNK_ADDR (0x040C) -#define COH901318_CX_LNK_ADDR_SPACING (0x10) -#define COH901318_CX_LNK_LINK_IMMEDIATE (0x00000001) - -/** - * struct coh901318_params - parameters for DMAC configuration - * @config: DMA config register - * @ctrl_lli_last: DMA control register for the last lli in the list - * @ctrl_lli: DMA control register for an lli - * @ctrl_lli_chained: DMA control register for a chained lli - */ -struct coh901318_params { - u32 config; - u32 ctrl_lli_last; - u32 ctrl_lli; - u32 ctrl_lli_chained; -}; - -/** - * struct coh_dma_channel - dma channel base - * @name: ascii name of dma channel - * @number: channel id number - * @desc_nbr_max: number of preallocated descriptors - * @priority_high: prio of channel, 0 low otherwise high. - * @param: configuration parameters - */ -struct coh_dma_channel { - const char name[32]; - const int number; - const int desc_nbr_max; - const int priority_high; - const struct coh901318_params param; -}; - -/** - * struct powersave - DMA power save structure - * @lock: lock protecting data in this struct - * @started_channels: bit mask indicating active dma channels - */ -struct powersave { - spinlock_t lock; - u64 started_channels; -}; - -/* points out all dma slave channels. - * Syntax is [A1, B1, A2, B2, .... ,-1,-1] - * Select all channels from A to B, end of list is marked with -1,-1 - */ -static int dma_slave_channels[] = { - U300_DMA_MSL_TX_0, U300_DMA_SPI_RX, - U300_DMA_UART1_TX, U300_DMA_UART1_RX, -1, -1}; - -/* points out all dma memcpy channels. */ -static int dma_memcpy_channels[] = { - U300_DMA_GENERAL_PURPOSE_0, U300_DMA_GENERAL_PURPOSE_8, -1, -1}; - -#define flags_memcpy_config (COH901318_CX_CFG_CH_DISABLE | \ - COH901318_CX_CFG_RM_MEMORY_TO_MEMORY | \ - COH901318_CX_CFG_LCR_DISABLE | \ - COH901318_CX_CFG_TC_IRQ_ENABLE | \ - COH901318_CX_CFG_BE_IRQ_ENABLE) -#define flags_memcpy_lli_chained (COH901318_CX_CTRL_TC_ENABLE | \ - COH901318_CX_CTRL_BURST_COUNT_32_BYTES | \ - COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS | \ - COH901318_CX_CTRL_SRC_ADDR_INC_ENABLE | \ - COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS | \ - COH901318_CX_CTRL_DST_ADDR_INC_ENABLE | \ - COH901318_CX_CTRL_MASTER_MODE_M1RW | \ - COH901318_CX_CTRL_TCP_DISABLE | \ - COH901318_CX_CTRL_TC_IRQ_DISABLE | \ - COH901318_CX_CTRL_HSP_DISABLE | \ - COH901318_CX_CTRL_HSS_DISABLE | \ - COH901318_CX_CTRL_DDMA_LEGACY | \ - COH901318_CX_CTRL_PRDD_SOURCE) -#define flags_memcpy_lli (COH901318_CX_CTRL_TC_ENABLE | \ - COH901318_CX_CTRL_BURST_COUNT_32_BYTES | \ - COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS | \ - COH901318_CX_CTRL_SRC_ADDR_INC_ENABLE | \ - COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS | \ - COH901318_CX_CTRL_DST_ADDR_INC_ENABLE | \ - COH901318_CX_CTRL_MASTER_MODE_M1RW | \ - COH901318_CX_CTRL_TCP_DISABLE | \ - COH901318_CX_CTRL_TC_IRQ_DISABLE | \ - COH901318_CX_CTRL_HSP_DISABLE | \ - COH901318_CX_CTRL_HSS_DISABLE | \ - COH901318_CX_CTRL_DDMA_LEGACY | \ - COH901318_CX_CTRL_PRDD_SOURCE) -#define flags_memcpy_lli_last (COH901318_CX_CTRL_TC_ENABLE | \ - COH901318_CX_CTRL_BURST_COUNT_32_BYTES | \ - COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS | \ - COH901318_CX_CTRL_SRC_ADDR_INC_ENABLE | \ - COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS | \ - COH901318_CX_CTRL_DST_ADDR_INC_ENABLE | \ - COH901318_CX_CTRL_MASTER_MODE_M1RW | \ - COH901318_CX_CTRL_TCP_DISABLE | \ - COH901318_CX_CTRL_TC_IRQ_ENABLE | \ - COH901318_CX_CTRL_HSP_DISABLE | \ - COH901318_CX_CTRL_HSS_DISABLE | \ - COH901318_CX_CTRL_DDMA_LEGACY | \ - COH901318_CX_CTRL_PRDD_SOURCE) - -static const struct coh_dma_channel chan_config[U300_DMA_CHANNELS] = { - { - .number = U300_DMA_MSL_TX_0, - .name = "MSL TX 0", - .priority_high = 0, - }, - { - .number = U300_DMA_MSL_TX_1, - .name = "MSL TX 1", - .priority_high = 0, - .param.config = COH901318_CX_CFG_CH_DISABLE | - COH901318_CX_CFG_LCR_DISABLE | - COH901318_CX_CFG_TC_IRQ_ENABLE | - COH901318_CX_CFG_BE_IRQ_ENABLE, - .param.ctrl_lli_chained = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_BURST_COUNT_32_BYTES | - COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_SRC_ADDR_INC_ENABLE | - COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_DST_ADDR_INC_DISABLE | - COH901318_CX_CTRL_MASTER_MODE_M1R_M2W | - COH901318_CX_CTRL_TCP_DISABLE | - COH901318_CX_CTRL_TC_IRQ_DISABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_LEGACY | - COH901318_CX_CTRL_PRDD_SOURCE, - .param.ctrl_lli = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_BURST_COUNT_32_BYTES | - COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_SRC_ADDR_INC_ENABLE | - COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_DST_ADDR_INC_DISABLE | - COH901318_CX_CTRL_MASTER_MODE_M1R_M2W | - COH901318_CX_CTRL_TCP_ENABLE | - COH901318_CX_CTRL_TC_IRQ_DISABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_LEGACY | - COH901318_CX_CTRL_PRDD_SOURCE, - .param.ctrl_lli_last = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_BURST_COUNT_32_BYTES | - COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_SRC_ADDR_INC_ENABLE | - COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_DST_ADDR_INC_DISABLE | - COH901318_CX_CTRL_MASTER_MODE_M1R_M2W | - COH901318_CX_CTRL_TCP_ENABLE | - COH901318_CX_CTRL_TC_IRQ_ENABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_LEGACY | - COH901318_CX_CTRL_PRDD_SOURCE, - }, - { - .number = U300_DMA_MSL_TX_2, - .name = "MSL TX 2", - .priority_high = 0, - .param.config = COH901318_CX_CFG_CH_DISABLE | - COH901318_CX_CFG_LCR_DISABLE | - COH901318_CX_CFG_TC_IRQ_ENABLE | - COH901318_CX_CFG_BE_IRQ_ENABLE, - .param.ctrl_lli_chained = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_BURST_COUNT_32_BYTES | - COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_SRC_ADDR_INC_ENABLE | - COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_DST_ADDR_INC_DISABLE | - COH901318_CX_CTRL_MASTER_MODE_M1R_M2W | - COH901318_CX_CTRL_TCP_DISABLE | - COH901318_CX_CTRL_TC_IRQ_DISABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_LEGACY | - COH901318_CX_CTRL_PRDD_SOURCE, - .param.ctrl_lli = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_BURST_COUNT_32_BYTES | - COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_SRC_ADDR_INC_ENABLE | - COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_DST_ADDR_INC_DISABLE | - COH901318_CX_CTRL_MASTER_MODE_M1R_M2W | - COH901318_CX_CTRL_TCP_ENABLE | - COH901318_CX_CTRL_TC_IRQ_DISABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_LEGACY | - COH901318_CX_CTRL_PRDD_SOURCE, - .param.ctrl_lli_last = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_BURST_COUNT_32_BYTES | - COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_SRC_ADDR_INC_ENABLE | - COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_DST_ADDR_INC_DISABLE | - COH901318_CX_CTRL_MASTER_MODE_M1R_M2W | - COH901318_CX_CTRL_TCP_ENABLE | - COH901318_CX_CTRL_TC_IRQ_ENABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_LEGACY | - COH901318_CX_CTRL_PRDD_SOURCE, - .desc_nbr_max = 10, - }, - { - .number = U300_DMA_MSL_TX_3, - .name = "MSL TX 3", - .priority_high = 0, - .param.config = COH901318_CX_CFG_CH_DISABLE | - COH901318_CX_CFG_LCR_DISABLE | - COH901318_CX_CFG_TC_IRQ_ENABLE | - COH901318_CX_CFG_BE_IRQ_ENABLE, - .param.ctrl_lli_chained = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_BURST_COUNT_32_BYTES | - COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_SRC_ADDR_INC_ENABLE | - COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_DST_ADDR_INC_DISABLE | - COH901318_CX_CTRL_MASTER_MODE_M1R_M2W | - COH901318_CX_CTRL_TCP_DISABLE | - COH901318_CX_CTRL_TC_IRQ_DISABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_LEGACY | - COH901318_CX_CTRL_PRDD_SOURCE, - .param.ctrl_lli = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_BURST_COUNT_32_BYTES | - COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_SRC_ADDR_INC_ENABLE | - COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_DST_ADDR_INC_DISABLE | - COH901318_CX_CTRL_MASTER_MODE_M1R_M2W | - COH901318_CX_CTRL_TCP_ENABLE | - COH901318_CX_CTRL_TC_IRQ_DISABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_LEGACY | - COH901318_CX_CTRL_PRDD_SOURCE, - .param.ctrl_lli_last = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_BURST_COUNT_32_BYTES | - COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_SRC_ADDR_INC_ENABLE | - COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_DST_ADDR_INC_DISABLE | - COH901318_CX_CTRL_MASTER_MODE_M1R_M2W | - COH901318_CX_CTRL_TCP_ENABLE | - COH901318_CX_CTRL_TC_IRQ_ENABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_LEGACY | - COH901318_CX_CTRL_PRDD_SOURCE, - }, - { - .number = U300_DMA_MSL_TX_4, - .name = "MSL TX 4", - .priority_high = 0, - .param.config = COH901318_CX_CFG_CH_DISABLE | - COH901318_CX_CFG_LCR_DISABLE | - COH901318_CX_CFG_TC_IRQ_ENABLE | - COH901318_CX_CFG_BE_IRQ_ENABLE, - .param.ctrl_lli_chained = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_BURST_COUNT_32_BYTES | - COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_SRC_ADDR_INC_ENABLE | - COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_DST_ADDR_INC_DISABLE | - COH901318_CX_CTRL_MASTER_MODE_M1R_M2W | - COH901318_CX_CTRL_TCP_DISABLE | - COH901318_CX_CTRL_TC_IRQ_DISABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_LEGACY | - COH901318_CX_CTRL_PRDD_SOURCE, - .param.ctrl_lli = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_BURST_COUNT_32_BYTES | - COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_SRC_ADDR_INC_ENABLE | - COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_DST_ADDR_INC_DISABLE | - COH901318_CX_CTRL_MASTER_MODE_M1R_M2W | - COH901318_CX_CTRL_TCP_ENABLE | - COH901318_CX_CTRL_TC_IRQ_DISABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_LEGACY | - COH901318_CX_CTRL_PRDD_SOURCE, - .param.ctrl_lli_last = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_BURST_COUNT_32_BYTES | - COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_SRC_ADDR_INC_ENABLE | - COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_DST_ADDR_INC_DISABLE | - COH901318_CX_CTRL_MASTER_MODE_M1R_M2W | - COH901318_CX_CTRL_TCP_ENABLE | - COH901318_CX_CTRL_TC_IRQ_ENABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_LEGACY | - COH901318_CX_CTRL_PRDD_SOURCE, - }, - { - .number = U300_DMA_MSL_TX_5, - .name = "MSL TX 5", - .priority_high = 0, - }, - { - .number = U300_DMA_MSL_TX_6, - .name = "MSL TX 6", - .priority_high = 0, - }, - { - .number = U300_DMA_MSL_RX_0, - .name = "MSL RX 0", - .priority_high = 0, - }, - { - .number = U300_DMA_MSL_RX_1, - .name = "MSL RX 1", - .priority_high = 0, - .param.config = COH901318_CX_CFG_CH_DISABLE | - COH901318_CX_CFG_LCR_DISABLE | - COH901318_CX_CFG_TC_IRQ_ENABLE | - COH901318_CX_CFG_BE_IRQ_ENABLE, - .param.ctrl_lli_chained = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_BURST_COUNT_32_BYTES | - COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_SRC_ADDR_INC_DISABLE | - COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_DST_ADDR_INC_ENABLE | - COH901318_CX_CTRL_MASTER_MODE_M2R_M1W | - COH901318_CX_CTRL_TCP_DISABLE | - COH901318_CX_CTRL_TC_IRQ_DISABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_DEMAND_DMA1 | - COH901318_CX_CTRL_PRDD_DEST, - .param.ctrl_lli = 0, - .param.ctrl_lli_last = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_BURST_COUNT_32_BYTES | - COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_SRC_ADDR_INC_DISABLE | - COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_DST_ADDR_INC_ENABLE | - COH901318_CX_CTRL_MASTER_MODE_M2R_M1W | - COH901318_CX_CTRL_TCP_DISABLE | - COH901318_CX_CTRL_TC_IRQ_ENABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_DEMAND_DMA1 | - COH901318_CX_CTRL_PRDD_DEST, - }, - { - .number = U300_DMA_MSL_RX_2, - .name = "MSL RX 2", - .priority_high = 0, - .param.config = COH901318_CX_CFG_CH_DISABLE | - COH901318_CX_CFG_LCR_DISABLE | - COH901318_CX_CFG_TC_IRQ_ENABLE | - COH901318_CX_CFG_BE_IRQ_ENABLE, - .param.ctrl_lli_chained = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_BURST_COUNT_32_BYTES | - COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_SRC_ADDR_INC_DISABLE | - COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_DST_ADDR_INC_ENABLE | - COH901318_CX_CTRL_MASTER_MODE_M2R_M1W | - COH901318_CX_CTRL_TCP_DISABLE | - COH901318_CX_CTRL_TC_IRQ_DISABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_DEMAND_DMA1 | - COH901318_CX_CTRL_PRDD_DEST, - .param.ctrl_lli = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_BURST_COUNT_32_BYTES | - COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_SRC_ADDR_INC_DISABLE | - COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_DST_ADDR_INC_ENABLE | - COH901318_CX_CTRL_MASTER_MODE_M2R_M1W | - COH901318_CX_CTRL_TCP_DISABLE | - COH901318_CX_CTRL_TC_IRQ_ENABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_DEMAND_DMA1 | - COH901318_CX_CTRL_PRDD_DEST, - .param.ctrl_lli_last = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_BURST_COUNT_32_BYTES | - COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_SRC_ADDR_INC_DISABLE | - COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_DST_ADDR_INC_ENABLE | - COH901318_CX_CTRL_MASTER_MODE_M2R_M1W | - COH901318_CX_CTRL_TCP_DISABLE | - COH901318_CX_CTRL_TC_IRQ_ENABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_DEMAND_DMA1 | - COH901318_CX_CTRL_PRDD_DEST, - }, - { - .number = U300_DMA_MSL_RX_3, - .name = "MSL RX 3", - .priority_high = 0, - .param.config = COH901318_CX_CFG_CH_DISABLE | - COH901318_CX_CFG_LCR_DISABLE | - COH901318_CX_CFG_TC_IRQ_ENABLE | - COH901318_CX_CFG_BE_IRQ_ENABLE, - .param.ctrl_lli_chained = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_BURST_COUNT_32_BYTES | - COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_SRC_ADDR_INC_DISABLE | - COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_DST_ADDR_INC_ENABLE | - COH901318_CX_CTRL_MASTER_MODE_M2R_M1W | - COH901318_CX_CTRL_TCP_DISABLE | - COH901318_CX_CTRL_TC_IRQ_DISABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_DEMAND_DMA1 | - COH901318_CX_CTRL_PRDD_DEST, - .param.ctrl_lli = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_BURST_COUNT_32_BYTES | - COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_SRC_ADDR_INC_DISABLE | - COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_DST_ADDR_INC_ENABLE | - COH901318_CX_CTRL_MASTER_MODE_M2R_M1W | - COH901318_CX_CTRL_TCP_DISABLE | - COH901318_CX_CTRL_TC_IRQ_ENABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_DEMAND_DMA1 | - COH901318_CX_CTRL_PRDD_DEST, - .param.ctrl_lli_last = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_BURST_COUNT_32_BYTES | - COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_SRC_ADDR_INC_DISABLE | - COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_DST_ADDR_INC_ENABLE | - COH901318_CX_CTRL_MASTER_MODE_M2R_M1W | - COH901318_CX_CTRL_TCP_DISABLE | - COH901318_CX_CTRL_TC_IRQ_ENABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_DEMAND_DMA1 | - COH901318_CX_CTRL_PRDD_DEST, - }, - { - .number = U300_DMA_MSL_RX_4, - .name = "MSL RX 4", - .priority_high = 0, - .param.config = COH901318_CX_CFG_CH_DISABLE | - COH901318_CX_CFG_LCR_DISABLE | - COH901318_CX_CFG_TC_IRQ_ENABLE | - COH901318_CX_CFG_BE_IRQ_ENABLE, - .param.ctrl_lli_chained = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_BURST_COUNT_32_BYTES | - COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_SRC_ADDR_INC_DISABLE | - COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_DST_ADDR_INC_ENABLE | - COH901318_CX_CTRL_MASTER_MODE_M2R_M1W | - COH901318_CX_CTRL_TCP_DISABLE | - COH901318_CX_CTRL_TC_IRQ_DISABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_DEMAND_DMA1 | - COH901318_CX_CTRL_PRDD_DEST, - .param.ctrl_lli = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_BURST_COUNT_32_BYTES | - COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_SRC_ADDR_INC_DISABLE | - COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_DST_ADDR_INC_ENABLE | - COH901318_CX_CTRL_MASTER_MODE_M2R_M1W | - COH901318_CX_CTRL_TCP_DISABLE | - COH901318_CX_CTRL_TC_IRQ_ENABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_DEMAND_DMA1 | - COH901318_CX_CTRL_PRDD_DEST, - .param.ctrl_lli_last = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_BURST_COUNT_32_BYTES | - COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_SRC_ADDR_INC_DISABLE | - COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_DST_ADDR_INC_ENABLE | - COH901318_CX_CTRL_MASTER_MODE_M2R_M1W | - COH901318_CX_CTRL_TCP_DISABLE | - COH901318_CX_CTRL_TC_IRQ_ENABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_DEMAND_DMA1 | - COH901318_CX_CTRL_PRDD_DEST, - }, - { - .number = U300_DMA_MSL_RX_5, - .name = "MSL RX 5", - .priority_high = 0, - .param.config = COH901318_CX_CFG_CH_DISABLE | - COH901318_CX_CFG_LCR_DISABLE | - COH901318_CX_CFG_TC_IRQ_ENABLE | - COH901318_CX_CFG_BE_IRQ_ENABLE, - .param.ctrl_lli_chained = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_BURST_COUNT_32_BYTES | - COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_SRC_ADDR_INC_DISABLE | - COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_DST_ADDR_INC_ENABLE | - COH901318_CX_CTRL_MASTER_MODE_M2R_M1W | - COH901318_CX_CTRL_TCP_DISABLE | - COH901318_CX_CTRL_TC_IRQ_DISABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_DEMAND_DMA1 | - COH901318_CX_CTRL_PRDD_DEST, - .param.ctrl_lli = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_BURST_COUNT_32_BYTES | - COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_SRC_ADDR_INC_DISABLE | - COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_DST_ADDR_INC_ENABLE | - COH901318_CX_CTRL_MASTER_MODE_M2R_M1W | - COH901318_CX_CTRL_TCP_DISABLE | - COH901318_CX_CTRL_TC_IRQ_ENABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_DEMAND_DMA1 | - COH901318_CX_CTRL_PRDD_DEST, - .param.ctrl_lli_last = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_BURST_COUNT_32_BYTES | - COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_SRC_ADDR_INC_DISABLE | - COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_DST_ADDR_INC_ENABLE | - COH901318_CX_CTRL_MASTER_MODE_M2R_M1W | - COH901318_CX_CTRL_TCP_DISABLE | - COH901318_CX_CTRL_TC_IRQ_ENABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_DEMAND_DMA1 | - COH901318_CX_CTRL_PRDD_DEST, - }, - { - .number = U300_DMA_MSL_RX_6, - .name = "MSL RX 6", - .priority_high = 0, - }, - /* - * Don't set up device address, burst count or size of src - * or dst bus for this peripheral - handled by PrimeCell - * DMA extension. - */ - { - .number = U300_DMA_MMCSD_RX_TX, - .name = "MMCSD RX TX", - .priority_high = 0, - .param.config = COH901318_CX_CFG_CH_DISABLE | - COH901318_CX_CFG_LCR_DISABLE | - COH901318_CX_CFG_TC_IRQ_ENABLE | - COH901318_CX_CFG_BE_IRQ_ENABLE, - .param.ctrl_lli_chained = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_MASTER_MODE_M1RW | - COH901318_CX_CTRL_TCP_ENABLE | - COH901318_CX_CTRL_TC_IRQ_DISABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_LEGACY, - .param.ctrl_lli = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_MASTER_MODE_M1RW | - COH901318_CX_CTRL_TCP_ENABLE | - COH901318_CX_CTRL_TC_IRQ_DISABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_LEGACY, - .param.ctrl_lli_last = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_MASTER_MODE_M1RW | - COH901318_CX_CTRL_TCP_DISABLE | - COH901318_CX_CTRL_TC_IRQ_ENABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_LEGACY, - - }, - { - .number = U300_DMA_MSPRO_TX, - .name = "MSPRO TX", - .priority_high = 0, - }, - { - .number = U300_DMA_MSPRO_RX, - .name = "MSPRO RX", - .priority_high = 0, - }, - /* - * Don't set up device address, burst count or size of src - * or dst bus for this peripheral - handled by PrimeCell - * DMA extension. - */ - { - .number = U300_DMA_UART0_TX, - .name = "UART0 TX", - .priority_high = 0, - .param.config = COH901318_CX_CFG_CH_DISABLE | - COH901318_CX_CFG_LCR_DISABLE | - COH901318_CX_CFG_TC_IRQ_ENABLE | - COH901318_CX_CFG_BE_IRQ_ENABLE, - .param.ctrl_lli_chained = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_MASTER_MODE_M1RW | - COH901318_CX_CTRL_TCP_ENABLE | - COH901318_CX_CTRL_TC_IRQ_DISABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_LEGACY, - .param.ctrl_lli = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_MASTER_MODE_M1RW | - COH901318_CX_CTRL_TCP_ENABLE | - COH901318_CX_CTRL_TC_IRQ_ENABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_LEGACY, - .param.ctrl_lli_last = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_MASTER_MODE_M1RW | - COH901318_CX_CTRL_TCP_ENABLE | - COH901318_CX_CTRL_TC_IRQ_ENABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_LEGACY, - }, - { - .number = U300_DMA_UART0_RX, - .name = "UART0 RX", - .priority_high = 0, - .param.config = COH901318_CX_CFG_CH_DISABLE | - COH901318_CX_CFG_LCR_DISABLE | - COH901318_CX_CFG_TC_IRQ_ENABLE | - COH901318_CX_CFG_BE_IRQ_ENABLE, - .param.ctrl_lli_chained = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_MASTER_MODE_M1RW | - COH901318_CX_CTRL_TCP_ENABLE | - COH901318_CX_CTRL_TC_IRQ_DISABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_LEGACY, - .param.ctrl_lli = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_MASTER_MODE_M1RW | - COH901318_CX_CTRL_TCP_ENABLE | - COH901318_CX_CTRL_TC_IRQ_ENABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_LEGACY, - .param.ctrl_lli_last = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_MASTER_MODE_M1RW | - COH901318_CX_CTRL_TCP_ENABLE | - COH901318_CX_CTRL_TC_IRQ_ENABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_LEGACY, - }, - { - .number = U300_DMA_APEX_TX, - .name = "APEX TX", - .priority_high = 0, - }, - { - .number = U300_DMA_APEX_RX, - .name = "APEX RX", - .priority_high = 0, - }, - { - .number = U300_DMA_PCM_I2S0_TX, - .name = "PCM I2S0 TX", - .priority_high = 1, - .param.config = COH901318_CX_CFG_CH_DISABLE | - COH901318_CX_CFG_LCR_DISABLE | - COH901318_CX_CFG_TC_IRQ_ENABLE | - COH901318_CX_CFG_BE_IRQ_ENABLE, - .param.ctrl_lli_chained = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_BURST_COUNT_16_BYTES | - COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_SRC_ADDR_INC_ENABLE | - COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_DST_ADDR_INC_DISABLE | - COH901318_CX_CTRL_MASTER_MODE_M1RW | - COH901318_CX_CTRL_TCP_DISABLE | - COH901318_CX_CTRL_TC_IRQ_DISABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_LEGACY | - COH901318_CX_CTRL_PRDD_SOURCE, - .param.ctrl_lli = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_BURST_COUNT_16_BYTES | - COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_SRC_ADDR_INC_ENABLE | - COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_DST_ADDR_INC_DISABLE | - COH901318_CX_CTRL_MASTER_MODE_M1RW | - COH901318_CX_CTRL_TCP_ENABLE | - COH901318_CX_CTRL_TC_IRQ_DISABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_LEGACY | - COH901318_CX_CTRL_PRDD_SOURCE, - .param.ctrl_lli_last = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_BURST_COUNT_16_BYTES | - COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_SRC_ADDR_INC_ENABLE | - COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_DST_ADDR_INC_DISABLE | - COH901318_CX_CTRL_MASTER_MODE_M1RW | - COH901318_CX_CTRL_TCP_ENABLE | - COH901318_CX_CTRL_TC_IRQ_DISABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_LEGACY | - COH901318_CX_CTRL_PRDD_SOURCE, - }, - { - .number = U300_DMA_PCM_I2S0_RX, - .name = "PCM I2S0 RX", - .priority_high = 1, - .param.config = COH901318_CX_CFG_CH_DISABLE | - COH901318_CX_CFG_LCR_DISABLE | - COH901318_CX_CFG_TC_IRQ_ENABLE | - COH901318_CX_CFG_BE_IRQ_ENABLE, - .param.ctrl_lli_chained = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_BURST_COUNT_16_BYTES | - COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_SRC_ADDR_INC_DISABLE | - COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_DST_ADDR_INC_ENABLE | - COH901318_CX_CTRL_MASTER_MODE_M1RW | - COH901318_CX_CTRL_TCP_DISABLE | - COH901318_CX_CTRL_TC_IRQ_DISABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_LEGACY | - COH901318_CX_CTRL_PRDD_DEST, - .param.ctrl_lli = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_BURST_COUNT_16_BYTES | - COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_SRC_ADDR_INC_DISABLE | - COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_DST_ADDR_INC_ENABLE | - COH901318_CX_CTRL_MASTER_MODE_M1RW | - COH901318_CX_CTRL_TCP_ENABLE | - COH901318_CX_CTRL_TC_IRQ_DISABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_LEGACY | - COH901318_CX_CTRL_PRDD_DEST, - .param.ctrl_lli_last = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_BURST_COUNT_16_BYTES | - COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_SRC_ADDR_INC_DISABLE | - COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_DST_ADDR_INC_ENABLE | - COH901318_CX_CTRL_MASTER_MODE_M1RW | - COH901318_CX_CTRL_TCP_ENABLE | - COH901318_CX_CTRL_TC_IRQ_ENABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_LEGACY | - COH901318_CX_CTRL_PRDD_DEST, - }, - { - .number = U300_DMA_PCM_I2S1_TX, - .name = "PCM I2S1 TX", - .priority_high = 1, - .param.config = COH901318_CX_CFG_CH_DISABLE | - COH901318_CX_CFG_LCR_DISABLE | - COH901318_CX_CFG_TC_IRQ_ENABLE | - COH901318_CX_CFG_BE_IRQ_ENABLE, - .param.ctrl_lli_chained = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_BURST_COUNT_16_BYTES | - COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_SRC_ADDR_INC_ENABLE | - COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_DST_ADDR_INC_DISABLE | - COH901318_CX_CTRL_MASTER_MODE_M1RW | - COH901318_CX_CTRL_TCP_DISABLE | - COH901318_CX_CTRL_TC_IRQ_DISABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_LEGACY | - COH901318_CX_CTRL_PRDD_SOURCE, - .param.ctrl_lli = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_BURST_COUNT_16_BYTES | - COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_SRC_ADDR_INC_ENABLE | - COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_DST_ADDR_INC_DISABLE | - COH901318_CX_CTRL_MASTER_MODE_M1RW | - COH901318_CX_CTRL_TCP_ENABLE | - COH901318_CX_CTRL_TC_IRQ_DISABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_LEGACY | - COH901318_CX_CTRL_PRDD_SOURCE, - .param.ctrl_lli_last = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_BURST_COUNT_16_BYTES | - COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_SRC_ADDR_INC_ENABLE | - COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_DST_ADDR_INC_DISABLE | - COH901318_CX_CTRL_MASTER_MODE_M1RW | - COH901318_CX_CTRL_TCP_ENABLE | - COH901318_CX_CTRL_TC_IRQ_ENABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_LEGACY | - COH901318_CX_CTRL_PRDD_SOURCE, - }, - { - .number = U300_DMA_PCM_I2S1_RX, - .name = "PCM I2S1 RX", - .priority_high = 1, - .param.config = COH901318_CX_CFG_CH_DISABLE | - COH901318_CX_CFG_LCR_DISABLE | - COH901318_CX_CFG_TC_IRQ_ENABLE | - COH901318_CX_CFG_BE_IRQ_ENABLE, - .param.ctrl_lli_chained = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_BURST_COUNT_16_BYTES | - COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_SRC_ADDR_INC_DISABLE | - COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_DST_ADDR_INC_ENABLE | - COH901318_CX_CTRL_MASTER_MODE_M1RW | - COH901318_CX_CTRL_TCP_DISABLE | - COH901318_CX_CTRL_TC_IRQ_DISABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_LEGACY | - COH901318_CX_CTRL_PRDD_DEST, - .param.ctrl_lli = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_BURST_COUNT_16_BYTES | - COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_SRC_ADDR_INC_DISABLE | - COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_DST_ADDR_INC_ENABLE | - COH901318_CX_CTRL_MASTER_MODE_M1RW | - COH901318_CX_CTRL_TCP_ENABLE | - COH901318_CX_CTRL_TC_IRQ_DISABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_LEGACY | - COH901318_CX_CTRL_PRDD_DEST, - .param.ctrl_lli_last = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_BURST_COUNT_16_BYTES | - COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_SRC_ADDR_INC_DISABLE | - COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_DST_ADDR_INC_ENABLE | - COH901318_CX_CTRL_MASTER_MODE_M1RW | - COH901318_CX_CTRL_TCP_ENABLE | - COH901318_CX_CTRL_TC_IRQ_ENABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_LEGACY | - COH901318_CX_CTRL_PRDD_DEST, - }, - { - .number = U300_DMA_XGAM_CDI, - .name = "XGAM CDI", - .priority_high = 0, - }, - { - .number = U300_DMA_XGAM_PDI, - .name = "XGAM PDI", - .priority_high = 0, - }, - /* - * Don't set up device address, burst count or size of src - * or dst bus for this peripheral - handled by PrimeCell - * DMA extension. - */ - { - .number = U300_DMA_SPI_TX, - .name = "SPI TX", - .priority_high = 0, - .param.config = COH901318_CX_CFG_CH_DISABLE | - COH901318_CX_CFG_LCR_DISABLE | - COH901318_CX_CFG_TC_IRQ_ENABLE | - COH901318_CX_CFG_BE_IRQ_ENABLE, - .param.ctrl_lli_chained = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_MASTER_MODE_M1RW | - COH901318_CX_CTRL_TCP_DISABLE | - COH901318_CX_CTRL_TC_IRQ_DISABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_LEGACY, - .param.ctrl_lli = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_MASTER_MODE_M1RW | - COH901318_CX_CTRL_TCP_DISABLE | - COH901318_CX_CTRL_TC_IRQ_ENABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_LEGACY, - .param.ctrl_lli_last = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_MASTER_MODE_M1RW | - COH901318_CX_CTRL_TCP_DISABLE | - COH901318_CX_CTRL_TC_IRQ_ENABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_LEGACY, - }, - { - .number = U300_DMA_SPI_RX, - .name = "SPI RX", - .priority_high = 0, - .param.config = COH901318_CX_CFG_CH_DISABLE | - COH901318_CX_CFG_LCR_DISABLE | - COH901318_CX_CFG_TC_IRQ_ENABLE | - COH901318_CX_CFG_BE_IRQ_ENABLE, - .param.ctrl_lli_chained = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_MASTER_MODE_M1RW | - COH901318_CX_CTRL_TCP_DISABLE | - COH901318_CX_CTRL_TC_IRQ_DISABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_LEGACY, - .param.ctrl_lli = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_MASTER_MODE_M1RW | - COH901318_CX_CTRL_TCP_DISABLE | - COH901318_CX_CTRL_TC_IRQ_ENABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_LEGACY, - .param.ctrl_lli_last = 0 | - COH901318_CX_CTRL_TC_ENABLE | - COH901318_CX_CTRL_MASTER_MODE_M1RW | - COH901318_CX_CTRL_TCP_DISABLE | - COH901318_CX_CTRL_TC_IRQ_ENABLE | - COH901318_CX_CTRL_HSP_ENABLE | - COH901318_CX_CTRL_HSS_DISABLE | - COH901318_CX_CTRL_DDMA_LEGACY, - - }, - { - .number = U300_DMA_GENERAL_PURPOSE_0, - .name = "GENERAL 00", - .priority_high = 0, - - .param.config = flags_memcpy_config, - .param.ctrl_lli_chained = flags_memcpy_lli_chained, - .param.ctrl_lli = flags_memcpy_lli, - .param.ctrl_lli_last = flags_memcpy_lli_last, - }, - { - .number = U300_DMA_GENERAL_PURPOSE_1, - .name = "GENERAL 01", - .priority_high = 0, - - .param.config = flags_memcpy_config, - .param.ctrl_lli_chained = flags_memcpy_lli_chained, - .param.ctrl_lli = flags_memcpy_lli, - .param.ctrl_lli_last = flags_memcpy_lli_last, - }, - { - .number = U300_DMA_GENERAL_PURPOSE_2, - .name = "GENERAL 02", - .priority_high = 0, - - .param.config = flags_memcpy_config, - .param.ctrl_lli_chained = flags_memcpy_lli_chained, - .param.ctrl_lli = flags_memcpy_lli, - .param.ctrl_lli_last = flags_memcpy_lli_last, - }, - { - .number = U300_DMA_GENERAL_PURPOSE_3, - .name = "GENERAL 03", - .priority_high = 0, - - .param.config = flags_memcpy_config, - .param.ctrl_lli_chained = flags_memcpy_lli_chained, - .param.ctrl_lli = flags_memcpy_lli, - .param.ctrl_lli_last = flags_memcpy_lli_last, - }, - { - .number = U300_DMA_GENERAL_PURPOSE_4, - .name = "GENERAL 04", - .priority_high = 0, - - .param.config = flags_memcpy_config, - .param.ctrl_lli_chained = flags_memcpy_lli_chained, - .param.ctrl_lli = flags_memcpy_lli, - .param.ctrl_lli_last = flags_memcpy_lli_last, - }, - { - .number = U300_DMA_GENERAL_PURPOSE_5, - .name = "GENERAL 05", - .priority_high = 0, - - .param.config = flags_memcpy_config, - .param.ctrl_lli_chained = flags_memcpy_lli_chained, - .param.ctrl_lli = flags_memcpy_lli, - .param.ctrl_lli_last = flags_memcpy_lli_last, - }, - { - .number = U300_DMA_GENERAL_PURPOSE_6, - .name = "GENERAL 06", - .priority_high = 0, - - .param.config = flags_memcpy_config, - .param.ctrl_lli_chained = flags_memcpy_lli_chained, - .param.ctrl_lli = flags_memcpy_lli, - .param.ctrl_lli_last = flags_memcpy_lli_last, - }, - { - .number = U300_DMA_GENERAL_PURPOSE_7, - .name = "GENERAL 07", - .priority_high = 0, - - .param.config = flags_memcpy_config, - .param.ctrl_lli_chained = flags_memcpy_lli_chained, - .param.ctrl_lli = flags_memcpy_lli, - .param.ctrl_lli_last = flags_memcpy_lli_last, - }, - { - .number = U300_DMA_GENERAL_PURPOSE_8, - .name = "GENERAL 08", - .priority_high = 0, - - .param.config = flags_memcpy_config, - .param.ctrl_lli_chained = flags_memcpy_lli_chained, - .param.ctrl_lli = flags_memcpy_lli, - .param.ctrl_lli_last = flags_memcpy_lli_last, - }, - { - .number = U300_DMA_UART1_TX, - .name = "UART1 TX", - .priority_high = 0, - }, - { - .number = U300_DMA_UART1_RX, - .name = "UART1 RX", - .priority_high = 0, - } -}; - -#define COHC_2_DEV(cohc) (&cohc->chan.dev->device) - -#ifdef VERBOSE_DEBUG -#define COH_DBG(x) ({ if (1) x; 0; }) -#else -#define COH_DBG(x) ({ if (0) x; 0; }) -#endif - -struct coh901318_desc { - struct dma_async_tx_descriptor desc; - struct list_head node; - struct scatterlist *sg; - unsigned int sg_len; - struct coh901318_lli *lli; - enum dma_transfer_direction dir; - unsigned long flags; - u32 head_config; - u32 head_ctrl; -}; - -struct coh901318_base { - struct device *dev; - void __iomem *virtbase; - unsigned int irq; - struct coh901318_pool pool; - struct powersave pm; - struct dma_device dma_slave; - struct dma_device dma_memcpy; - struct coh901318_chan *chans; -}; - -struct coh901318_chan { - spinlock_t lock; - int allocated; - int id; - int stopped; - - struct work_struct free_work; - struct dma_chan chan; - - struct tasklet_struct tasklet; - - struct list_head active; - struct list_head queue; - struct list_head free; - - unsigned long nbr_active_done; - unsigned long busy; - - struct dma_slave_config config; - u32 addr; - u32 ctrl; - - struct coh901318_base *base; -}; - -static void coh901318_list_print(struct coh901318_chan *cohc, - struct coh901318_lli *lli) -{ - struct coh901318_lli *l = lli; - int i = 0; - - while (l) { - dev_vdbg(COHC_2_DEV(cohc), "i %d, lli %p, ctrl 0x%x, src %pad" - ", dst %pad, link %pad virt_link_addr 0x%p\n", - i, l, l->control, &l->src_addr, &l->dst_addr, - &l->link_addr, l->virt_link_addr); - i++; - l = l->virt_link_addr; - } -} - -#ifdef CONFIG_DEBUG_FS - -#define COH901318_DEBUGFS_ASSIGN(x, y) (x = y) - -static struct coh901318_base *debugfs_dma_base; -static struct dentry *dma_dentry; - -static ssize_t coh901318_debugfs_read(struct file *file, char __user *buf, - size_t count, loff_t *f_pos) -{ - u64 started_channels = debugfs_dma_base->pm.started_channels; - int pool_count = debugfs_dma_base->pool.debugfs_pool_counter; - char *dev_buf; - char *tmp; - int ret; - int i; - - dev_buf = kmalloc(4*1024, GFP_KERNEL); - if (dev_buf == NULL) - return -ENOMEM; - tmp = dev_buf; - - tmp += sprintf(tmp, "DMA -- enabled dma channels\n"); - - for (i = 0; i < U300_DMA_CHANNELS; i++) { - if (started_channels & (1ULL << i)) - tmp += sprintf(tmp, "channel %d\n", i); - } - - tmp += sprintf(tmp, "Pool alloc nbr %d\n", pool_count); - - ret = simple_read_from_buffer(buf, count, f_pos, dev_buf, - tmp - dev_buf); - kfree(dev_buf); - return ret; -} - -static const struct file_operations coh901318_debugfs_status_operations = { - .open = simple_open, - .read = coh901318_debugfs_read, - .llseek = default_llseek, -}; - - -static int __init init_coh901318_debugfs(void) -{ - - dma_dentry = debugfs_create_dir("dma", NULL); - - debugfs_create_file("status", S_IFREG | S_IRUGO, dma_dentry, NULL, - &coh901318_debugfs_status_operations); - return 0; -} - -static void __exit exit_coh901318_debugfs(void) -{ - debugfs_remove_recursive(dma_dentry); -} - -module_init(init_coh901318_debugfs); -module_exit(exit_coh901318_debugfs); -#else - -#define COH901318_DEBUGFS_ASSIGN(x, y) - -#endif /* CONFIG_DEBUG_FS */ - -static inline struct coh901318_chan *to_coh901318_chan(struct dma_chan *chan) -{ - return container_of(chan, struct coh901318_chan, chan); -} - -static int coh901318_dma_set_runtimeconfig(struct dma_chan *chan, - struct dma_slave_config *config, - enum dma_transfer_direction direction); - -static inline const struct coh901318_params * -cohc_chan_param(struct coh901318_chan *cohc) -{ - return &chan_config[cohc->id].param; -} - -static inline const struct coh_dma_channel * -cohc_chan_conf(struct coh901318_chan *cohc) -{ - return &chan_config[cohc->id]; -} - -static void enable_powersave(struct coh901318_chan *cohc) -{ - unsigned long flags; - struct powersave *pm = &cohc->base->pm; - - spin_lock_irqsave(&pm->lock, flags); - - pm->started_channels &= ~(1ULL << cohc->id); - - spin_unlock_irqrestore(&pm->lock, flags); -} -static void disable_powersave(struct coh901318_chan *cohc) -{ - unsigned long flags; - struct powersave *pm = &cohc->base->pm; - - spin_lock_irqsave(&pm->lock, flags); - - pm->started_channels |= (1ULL << cohc->id); - - spin_unlock_irqrestore(&pm->lock, flags); -} - -static inline int coh901318_set_ctrl(struct coh901318_chan *cohc, u32 control) -{ - int channel = cohc->id; - void __iomem *virtbase = cohc->base->virtbase; - - writel(control, - virtbase + COH901318_CX_CTRL + - COH901318_CX_CTRL_SPACING * channel); - return 0; -} - -static inline int coh901318_set_conf(struct coh901318_chan *cohc, u32 conf) -{ - int channel = cohc->id; - void __iomem *virtbase = cohc->base->virtbase; - - writel(conf, - virtbase + COH901318_CX_CFG + - COH901318_CX_CFG_SPACING*channel); - return 0; -} - - -static int coh901318_start(struct coh901318_chan *cohc) -{ - u32 val; - int channel = cohc->id; - void __iomem *virtbase = cohc->base->virtbase; - - disable_powersave(cohc); - - val = readl(virtbase + COH901318_CX_CFG + - COH901318_CX_CFG_SPACING * channel); - - /* Enable channel */ - val |= COH901318_CX_CFG_CH_ENABLE; - writel(val, virtbase + COH901318_CX_CFG + - COH901318_CX_CFG_SPACING * channel); - - return 0; -} - -static int coh901318_prep_linked_list(struct coh901318_chan *cohc, - struct coh901318_lli *lli) -{ - int channel = cohc->id; - void __iomem *virtbase = cohc->base->virtbase; - - BUG_ON(readl(virtbase + COH901318_CX_STAT + - COH901318_CX_STAT_SPACING*channel) & - COH901318_CX_STAT_ACTIVE); - - writel(lli->src_addr, - virtbase + COH901318_CX_SRC_ADDR + - COH901318_CX_SRC_ADDR_SPACING * channel); - - writel(lli->dst_addr, virtbase + - COH901318_CX_DST_ADDR + - COH901318_CX_DST_ADDR_SPACING * channel); - - writel(lli->link_addr, virtbase + COH901318_CX_LNK_ADDR + - COH901318_CX_LNK_ADDR_SPACING * channel); - - writel(lli->control, virtbase + COH901318_CX_CTRL + - COH901318_CX_CTRL_SPACING * channel); - - return 0; -} - -static struct coh901318_desc * -coh901318_desc_get(struct coh901318_chan *cohc) -{ - struct coh901318_desc *desc; - - if (list_empty(&cohc->free)) { - /* alloc new desc because we're out of used ones - * TODO: alloc a pile of descs instead of just one, - * avoid many small allocations. - */ - desc = kzalloc(sizeof(struct coh901318_desc), GFP_NOWAIT); - if (desc == NULL) - goto out; - INIT_LIST_HEAD(&desc->node); - dma_async_tx_descriptor_init(&desc->desc, &cohc->chan); - } else { - /* Reuse an old desc. */ - desc = list_first_entry(&cohc->free, - struct coh901318_desc, - node); - list_del(&desc->node); - /* Initialize it a bit so it's not insane */ - desc->sg = NULL; - desc->sg_len = 0; - desc->desc.callback = NULL; - desc->desc.callback_param = NULL; - } - - out: - return desc; -} - -static void -coh901318_desc_free(struct coh901318_chan *cohc, struct coh901318_desc *cohd) -{ - list_add_tail(&cohd->node, &cohc->free); -} - -/* call with irq lock held */ -static void -coh901318_desc_submit(struct coh901318_chan *cohc, struct coh901318_desc *desc) -{ - list_add_tail(&desc->node, &cohc->active); -} - -static struct coh901318_desc * -coh901318_first_active_get(struct coh901318_chan *cohc) -{ - return list_first_entry_or_null(&cohc->active, struct coh901318_desc, - node); -} - -static void -coh901318_desc_remove(struct coh901318_desc *cohd) -{ - list_del(&cohd->node); -} - -static void -coh901318_desc_queue(struct coh901318_chan *cohc, struct coh901318_desc *desc) -{ - list_add_tail(&desc->node, &cohc->queue); -} - -static struct coh901318_desc * -coh901318_first_queued(struct coh901318_chan *cohc) -{ - return list_first_entry_or_null(&cohc->queue, struct coh901318_desc, - node); -} - -static inline u32 coh901318_get_bytes_in_lli(struct coh901318_lli *in_lli) -{ - struct coh901318_lli *lli = in_lli; - u32 bytes = 0; - - while (lli) { - bytes += lli->control & COH901318_CX_CTRL_TC_VALUE_MASK; - lli = lli->virt_link_addr; - } - return bytes; -} - -/* - * Get the number of bytes left to transfer on this channel, - * it is unwise to call this before stopping the channel for - * absolute measures, but for a rough guess you can still call - * it. - */ -static u32 coh901318_get_bytes_left(struct dma_chan *chan) -{ - struct coh901318_chan *cohc = to_coh901318_chan(chan); - struct coh901318_desc *cohd; - struct list_head *pos; - unsigned long flags; - u32 left = 0; - int i = 0; - - spin_lock_irqsave(&cohc->lock, flags); - - /* - * If there are many queued jobs, we iterate and add the - * size of them all. We take a special look on the first - * job though, since it is probably active. - */ - list_for_each(pos, &cohc->active) { - /* - * The first job in the list will be working on the - * hardware. The job can be stopped but still active, - * so that the transfer counter is somewhere inside - * the buffer. - */ - cohd = list_entry(pos, struct coh901318_desc, node); - - if (i == 0) { - struct coh901318_lli *lli; - dma_addr_t ladd; - - /* Read current transfer count value */ - left = readl(cohc->base->virtbase + - COH901318_CX_CTRL + - COH901318_CX_CTRL_SPACING * cohc->id) & - COH901318_CX_CTRL_TC_VALUE_MASK; - - /* See if the transfer is linked... */ - ladd = readl(cohc->base->virtbase + - COH901318_CX_LNK_ADDR + - COH901318_CX_LNK_ADDR_SPACING * - cohc->id) & - ~COH901318_CX_LNK_LINK_IMMEDIATE; - /* Single transaction */ - if (!ladd) - continue; - - /* - * Linked transaction, follow the lli, find the - * currently processing lli, and proceed to the next - */ - lli = cohd->lli; - while (lli && lli->link_addr != ladd) - lli = lli->virt_link_addr; - - if (lli) - lli = lli->virt_link_addr; - - /* - * Follow remaining lli links around to count the total - * number of bytes left - */ - left += coh901318_get_bytes_in_lli(lli); - } else { - left += coh901318_get_bytes_in_lli(cohd->lli); - } - i++; - } - - /* Also count bytes in the queued jobs */ - list_for_each(pos, &cohc->queue) { - cohd = list_entry(pos, struct coh901318_desc, node); - left += coh901318_get_bytes_in_lli(cohd->lli); - } - - spin_unlock_irqrestore(&cohc->lock, flags); - - return left; -} - -/* - * Pauses a transfer without losing data. Enables power save. - * Use this function in conjunction with coh901318_resume. - */ -static int coh901318_pause(struct dma_chan *chan) -{ - u32 val; - unsigned long flags; - struct coh901318_chan *cohc = to_coh901318_chan(chan); - int channel = cohc->id; - void __iomem *virtbase = cohc->base->virtbase; - - spin_lock_irqsave(&cohc->lock, flags); - - /* Disable channel in HW */ - val = readl(virtbase + COH901318_CX_CFG + - COH901318_CX_CFG_SPACING * channel); - - /* Stopping infinite transfer */ - if ((val & COH901318_CX_CTRL_TC_ENABLE) == 0 && - (val & COH901318_CX_CFG_CH_ENABLE)) - cohc->stopped = 1; - - - val &= ~COH901318_CX_CFG_CH_ENABLE; - /* Enable twice, HW bug work around */ - writel(val, virtbase + COH901318_CX_CFG + - COH901318_CX_CFG_SPACING * channel); - writel(val, virtbase + COH901318_CX_CFG + - COH901318_CX_CFG_SPACING * channel); - - /* Spin-wait for it to actually go inactive */ - while (readl(virtbase + COH901318_CX_STAT+COH901318_CX_STAT_SPACING * - channel) & COH901318_CX_STAT_ACTIVE) - cpu_relax(); - - /* Check if we stopped an active job */ - if ((readl(virtbase + COH901318_CX_CTRL+COH901318_CX_CTRL_SPACING * - channel) & COH901318_CX_CTRL_TC_VALUE_MASK) > 0) - cohc->stopped = 1; - - enable_powersave(cohc); - - spin_unlock_irqrestore(&cohc->lock, flags); - return 0; -} - -/* Resumes a transfer that has been stopped via 300_dma_stop(..). - Power save is handled. -*/ -static int coh901318_resume(struct dma_chan *chan) -{ - u32 val; - unsigned long flags; - struct coh901318_chan *cohc = to_coh901318_chan(chan); - int channel = cohc->id; - - spin_lock_irqsave(&cohc->lock, flags); - - disable_powersave(cohc); - - if (cohc->stopped) { - /* Enable channel in HW */ - val = readl(cohc->base->virtbase + COH901318_CX_CFG + - COH901318_CX_CFG_SPACING * channel); - - val |= COH901318_CX_CFG_CH_ENABLE; - - writel(val, cohc->base->virtbase + COH901318_CX_CFG + - COH901318_CX_CFG_SPACING*channel); - - cohc->stopped = 0; - } - - spin_unlock_irqrestore(&cohc->lock, flags); - return 0; -} - -bool coh901318_filter_id(struct dma_chan *chan, void *chan_id) -{ - unsigned long ch_nr = (unsigned long) chan_id; - - if (ch_nr == to_coh901318_chan(chan)->id) - return true; - - return false; -} -EXPORT_SYMBOL(coh901318_filter_id); - -struct coh901318_filter_args { - struct coh901318_base *base; - unsigned int ch_nr; -}; - -static bool coh901318_filter_base_and_id(struct dma_chan *chan, void *data) -{ - struct coh901318_filter_args *args = data; - - if (&args->base->dma_slave == chan->device && - args->ch_nr == to_coh901318_chan(chan)->id) - return true; - - return false; -} - -static struct dma_chan *coh901318_xlate(struct of_phandle_args *dma_spec, - struct of_dma *ofdma) -{ - struct coh901318_filter_args args = { - .base = ofdma->of_dma_data, - .ch_nr = dma_spec->args[0], - }; - dma_cap_mask_t cap; - dma_cap_zero(cap); - dma_cap_set(DMA_SLAVE, cap); - - return dma_request_channel(cap, coh901318_filter_base_and_id, &args); -} -/* - * DMA channel allocation - */ -static int coh901318_config(struct coh901318_chan *cohc, - struct coh901318_params *param) -{ - const struct coh901318_params *p; - int channel = cohc->id; - void __iomem *virtbase = cohc->base->virtbase; - - if (param) - p = param; - else - p = cohc_chan_param(cohc); - - /* Clear any pending BE or TC interrupt */ - if (channel < 32) { - writel(1 << channel, virtbase + COH901318_BE_INT_CLEAR1); - writel(1 << channel, virtbase + COH901318_TC_INT_CLEAR1); - } else { - writel(1 << (channel - 32), virtbase + - COH901318_BE_INT_CLEAR2); - writel(1 << (channel - 32), virtbase + - COH901318_TC_INT_CLEAR2); - } - - coh901318_set_conf(cohc, p->config); - coh901318_set_ctrl(cohc, p->ctrl_lli_last); - - return 0; -} - -/* must lock when calling this function - * start queued jobs, if any - * TODO: start all queued jobs in one go - * - * Returns descriptor if queued job is started otherwise NULL. - * If the queue is empty NULL is returned. - */ -static struct coh901318_desc *coh901318_queue_start(struct coh901318_chan *cohc) -{ - struct coh901318_desc *cohd; - - /* - * start queued jobs, if any - * TODO: transmit all queued jobs in one go - */ - cohd = coh901318_first_queued(cohc); - - if (cohd != NULL) { - /* Remove from queue */ - coh901318_desc_remove(cohd); - /* initiate DMA job */ - cohc->busy = 1; - - coh901318_desc_submit(cohc, cohd); - - /* Program the transaction head */ - coh901318_set_conf(cohc, cohd->head_config); - coh901318_set_ctrl(cohc, cohd->head_ctrl); - coh901318_prep_linked_list(cohc, cohd->lli); - - /* start dma job on this channel */ - coh901318_start(cohc); - - } - - return cohd; -} - -/* - * This tasklet is called from the interrupt handler to - * handle each descriptor (DMA job) that is sent to a channel. - */ -static void dma_tasklet(struct tasklet_struct *t) -{ - struct coh901318_chan *cohc = from_tasklet(cohc, t, tasklet); - struct coh901318_desc *cohd_fin; - unsigned long flags; - struct dmaengine_desc_callback cb; - - dev_vdbg(COHC_2_DEV(cohc), "[%s] chan_id %d" - " nbr_active_done %ld\n", __func__, - cohc->id, cohc->nbr_active_done); - - spin_lock_irqsave(&cohc->lock, flags); - - /* get first active descriptor entry from list */ - cohd_fin = coh901318_first_active_get(cohc); - - if (cohd_fin == NULL) - goto err; - - /* locate callback to client */ - dmaengine_desc_get_callback(&cohd_fin->desc, &cb); - - /* sign this job as completed on the channel */ - dma_cookie_complete(&cohd_fin->desc); - - /* release the lli allocation and remove the descriptor */ - coh901318_lli_free(&cohc->base->pool, &cohd_fin->lli); - - /* return desc to free-list */ - coh901318_desc_remove(cohd_fin); - coh901318_desc_free(cohc, cohd_fin); - - spin_unlock_irqrestore(&cohc->lock, flags); - - /* Call the callback when we're done */ - dmaengine_desc_callback_invoke(&cb, NULL); - - spin_lock_irqsave(&cohc->lock, flags); - - /* - * If another interrupt fired while the tasklet was scheduling, - * we don't get called twice, so we have this number of active - * counter that keep track of the number of IRQs expected to - * be handled for this channel. If there happen to be more than - * one IRQ to be ack:ed, we simply schedule this tasklet again. - */ - cohc->nbr_active_done--; - if (cohc->nbr_active_done) { - dev_dbg(COHC_2_DEV(cohc), "scheduling tasklet again, new IRQs " - "came in while we were scheduling this tasklet\n"); - if (cohc_chan_conf(cohc)->priority_high) - tasklet_hi_schedule(&cohc->tasklet); - else - tasklet_schedule(&cohc->tasklet); - } - - spin_unlock_irqrestore(&cohc->lock, flags); - - return; - - err: - spin_unlock_irqrestore(&cohc->lock, flags); - dev_err(COHC_2_DEV(cohc), "[%s] No active dma desc\n", __func__); -} - - -/* called from interrupt context */ -static void dma_tc_handle(struct coh901318_chan *cohc) -{ - /* - * If the channel is not allocated, then we shouldn't have - * any TC interrupts on it. - */ - if (!cohc->allocated) { - dev_err(COHC_2_DEV(cohc), "spurious interrupt from " - "unallocated channel\n"); - return; - } - - /* - * When we reach this point, at least one queue item - * should have been moved over from cohc->queue to - * cohc->active and run to completion, that is why we're - * getting a terminal count interrupt is it not? - * If you get this BUG() the most probable cause is that - * the individual nodes in the lli chain have IRQ enabled, - * so check your platform config for lli chain ctrl. - */ - BUG_ON(list_empty(&cohc->active)); - - cohc->nbr_active_done++; - - /* - * This attempt to take a job from cohc->queue, put it - * into cohc->active and start it. - */ - if (coh901318_queue_start(cohc) == NULL) - cohc->busy = 0; - - /* - * This tasklet will remove items from cohc->active - * and thus terminates them. - */ - if (cohc_chan_conf(cohc)->priority_high) - tasklet_hi_schedule(&cohc->tasklet); - else - tasklet_schedule(&cohc->tasklet); -} - - -static irqreturn_t dma_irq_handler(int irq, void *dev_id) -{ - u32 status1; - u32 status2; - int i; - int ch; - struct coh901318_base *base = dev_id; - struct coh901318_chan *cohc; - void __iomem *virtbase = base->virtbase; - - status1 = readl(virtbase + COH901318_INT_STATUS1); - status2 = readl(virtbase + COH901318_INT_STATUS2); - - if (unlikely(status1 == 0 && status2 == 0)) { - dev_warn(base->dev, "spurious DMA IRQ from no channel!\n"); - return IRQ_HANDLED; - } - - /* TODO: consider handle IRQ in tasklet here to - * minimize interrupt latency */ - - /* Check the first 32 DMA channels for IRQ */ - while (status1) { - /* Find first bit set, return as a number. */ - i = ffs(status1) - 1; - ch = i; - - cohc = &base->chans[ch]; - spin_lock(&cohc->lock); - - /* Mask off this bit */ - status1 &= ~(1 << i); - /* Check the individual channel bits */ - if (test_bit(i, virtbase + COH901318_BE_INT_STATUS1)) { - dev_crit(COHC_2_DEV(cohc), - "DMA bus error on channel %d!\n", ch); - BUG_ON(1); - /* Clear BE interrupt */ - __set_bit(i, virtbase + COH901318_BE_INT_CLEAR1); - } else { - /* Caused by TC, really? */ - if (unlikely(!test_bit(i, virtbase + - COH901318_TC_INT_STATUS1))) { - dev_warn(COHC_2_DEV(cohc), - "ignoring interrupt not caused by terminal count on channel %d\n", ch); - /* Clear TC interrupt */ - BUG_ON(1); - __set_bit(i, virtbase + COH901318_TC_INT_CLEAR1); - } else { - /* Enable powersave if transfer has finished */ - if (!(readl(virtbase + COH901318_CX_STAT + - COH901318_CX_STAT_SPACING*ch) & - COH901318_CX_STAT_ENABLED)) { - enable_powersave(cohc); - } - - /* Must clear TC interrupt before calling - * dma_tc_handle - * in case tc_handle initiate a new dma job - */ - __set_bit(i, virtbase + COH901318_TC_INT_CLEAR1); - - dma_tc_handle(cohc); - } - } - spin_unlock(&cohc->lock); - } - - /* Check the remaining 32 DMA channels for IRQ */ - while (status2) { - /* Find first bit set, return as a number. */ - i = ffs(status2) - 1; - ch = i + 32; - cohc = &base->chans[ch]; - spin_lock(&cohc->lock); - - /* Mask off this bit */ - status2 &= ~(1 << i); - /* Check the individual channel bits */ - if (test_bit(i, virtbase + COH901318_BE_INT_STATUS2)) { - dev_crit(COHC_2_DEV(cohc), - "DMA bus error on channel %d!\n", ch); - /* Clear BE interrupt */ - BUG_ON(1); - __set_bit(i, virtbase + COH901318_BE_INT_CLEAR2); - } else { - /* Caused by TC, really? */ - if (unlikely(!test_bit(i, virtbase + - COH901318_TC_INT_STATUS2))) { - dev_warn(COHC_2_DEV(cohc), - "ignoring interrupt not caused by terminal count on channel %d\n", ch); - /* Clear TC interrupt */ - __set_bit(i, virtbase + COH901318_TC_INT_CLEAR2); - BUG_ON(1); - } else { - /* Enable powersave if transfer has finished */ - if (!(readl(virtbase + COH901318_CX_STAT + - COH901318_CX_STAT_SPACING*ch) & - COH901318_CX_STAT_ENABLED)) { - enable_powersave(cohc); - } - /* Must clear TC interrupt before calling - * dma_tc_handle - * in case tc_handle initiate a new dma job - */ - __set_bit(i, virtbase + COH901318_TC_INT_CLEAR2); - - dma_tc_handle(cohc); - } - } - spin_unlock(&cohc->lock); - } - - return IRQ_HANDLED; -} - -static int coh901318_terminate_all(struct dma_chan *chan) -{ - unsigned long flags; - struct coh901318_chan *cohc = to_coh901318_chan(chan); - struct coh901318_desc *cohd; - void __iomem *virtbase = cohc->base->virtbase; - - /* The remainder of this function terminates the transfer */ - coh901318_pause(chan); - spin_lock_irqsave(&cohc->lock, flags); - - /* Clear any pending BE or TC interrupt */ - if (cohc->id < 32) { - writel(1 << cohc->id, virtbase + COH901318_BE_INT_CLEAR1); - writel(1 << cohc->id, virtbase + COH901318_TC_INT_CLEAR1); - } else { - writel(1 << (cohc->id - 32), virtbase + - COH901318_BE_INT_CLEAR2); - writel(1 << (cohc->id - 32), virtbase + - COH901318_TC_INT_CLEAR2); - } - - enable_powersave(cohc); - - while ((cohd = coh901318_first_active_get(cohc))) { - /* release the lli allocation*/ - coh901318_lli_free(&cohc->base->pool, &cohd->lli); - - /* return desc to free-list */ - coh901318_desc_remove(cohd); - coh901318_desc_free(cohc, cohd); - } - - while ((cohd = coh901318_first_queued(cohc))) { - /* release the lli allocation*/ - coh901318_lli_free(&cohc->base->pool, &cohd->lli); - - /* return desc to free-list */ - coh901318_desc_remove(cohd); - coh901318_desc_free(cohc, cohd); - } - - - cohc->nbr_active_done = 0; - cohc->busy = 0; - - spin_unlock_irqrestore(&cohc->lock, flags); - - return 0; -} - -static int coh901318_alloc_chan_resources(struct dma_chan *chan) -{ - struct coh901318_chan *cohc = to_coh901318_chan(chan); - unsigned long flags; - - dev_vdbg(COHC_2_DEV(cohc), "[%s] DMA channel %d\n", - __func__, cohc->id); - - if (chan->client_count > 1) - return -EBUSY; - - spin_lock_irqsave(&cohc->lock, flags); - - coh901318_config(cohc, NULL); - - cohc->allocated = 1; - dma_cookie_init(chan); - - spin_unlock_irqrestore(&cohc->lock, flags); - - return 1; -} - -static void -coh901318_free_chan_resources(struct dma_chan *chan) -{ - struct coh901318_chan *cohc = to_coh901318_chan(chan); - int channel = cohc->id; - unsigned long flags; - - spin_lock_irqsave(&cohc->lock, flags); - - /* Disable HW */ - writel(0x00000000U, cohc->base->virtbase + COH901318_CX_CFG + - COH901318_CX_CFG_SPACING*channel); - writel(0x00000000U, cohc->base->virtbase + COH901318_CX_CTRL + - COH901318_CX_CTRL_SPACING*channel); - - cohc->allocated = 0; - - spin_unlock_irqrestore(&cohc->lock, flags); - - coh901318_terminate_all(chan); -} - - -static dma_cookie_t -coh901318_tx_submit(struct dma_async_tx_descriptor *tx) -{ - struct coh901318_desc *cohd = container_of(tx, struct coh901318_desc, - desc); - struct coh901318_chan *cohc = to_coh901318_chan(tx->chan); - unsigned long flags; - dma_cookie_t cookie; - - spin_lock_irqsave(&cohc->lock, flags); - cookie = dma_cookie_assign(tx); - - coh901318_desc_queue(cohc, cohd); - - spin_unlock_irqrestore(&cohc->lock, flags); - - return cookie; -} - -static struct dma_async_tx_descriptor * -coh901318_prep_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src, - size_t size, unsigned long flags) -{ - struct coh901318_lli *lli; - struct coh901318_desc *cohd; - unsigned long flg; - struct coh901318_chan *cohc = to_coh901318_chan(chan); - int lli_len; - u32 ctrl_last = cohc_chan_param(cohc)->ctrl_lli_last; - int ret; - - spin_lock_irqsave(&cohc->lock, flg); - - dev_vdbg(COHC_2_DEV(cohc), - "[%s] channel %d src %pad dest %pad size %zu\n", - __func__, cohc->id, &src, &dest, size); - - if (flags & DMA_PREP_INTERRUPT) - /* Trigger interrupt after last lli */ - ctrl_last |= COH901318_CX_CTRL_TC_IRQ_ENABLE; - - lli_len = size >> MAX_DMA_PACKET_SIZE_SHIFT; - if ((lli_len << MAX_DMA_PACKET_SIZE_SHIFT) < size) - lli_len++; - - lli = coh901318_lli_alloc(&cohc->base->pool, lli_len); - - if (lli == NULL) - goto err; - - ret = coh901318_lli_fill_memcpy( - &cohc->base->pool, lli, src, size, dest, - cohc_chan_param(cohc)->ctrl_lli_chained, - ctrl_last); - if (ret) - goto err; - - COH_DBG(coh901318_list_print(cohc, lli)); - - /* Pick a descriptor to handle this transfer */ - cohd = coh901318_desc_get(cohc); - cohd->lli = lli; - cohd->flags = flags; - cohd->desc.tx_submit = coh901318_tx_submit; - - spin_unlock_irqrestore(&cohc->lock, flg); - - return &cohd->desc; - err: - spin_unlock_irqrestore(&cohc->lock, flg); - return NULL; -} - -static struct dma_async_tx_descriptor * -coh901318_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl, - unsigned int sg_len, enum dma_transfer_direction direction, - unsigned long flags, void *context) -{ - struct coh901318_chan *cohc = to_coh901318_chan(chan); - struct coh901318_lli *lli; - struct coh901318_desc *cohd; - const struct coh901318_params *params; - struct scatterlist *sg; - int len = 0; - int size; - int i; - u32 ctrl_chained = cohc_chan_param(cohc)->ctrl_lli_chained; - u32 ctrl = cohc_chan_param(cohc)->ctrl_lli; - u32 ctrl_last = cohc_chan_param(cohc)->ctrl_lli_last; - u32 config; - unsigned long flg; - int ret; - - if (!sgl) - goto out; - if (sg_dma_len(sgl) == 0) - goto out; - - spin_lock_irqsave(&cohc->lock, flg); - - dev_vdbg(COHC_2_DEV(cohc), "[%s] sg_len %d dir %d\n", - __func__, sg_len, direction); - - if (flags & DMA_PREP_INTERRUPT) - /* Trigger interrupt after last lli */ - ctrl_last |= COH901318_CX_CTRL_TC_IRQ_ENABLE; - - params = cohc_chan_param(cohc); - config = params->config; - /* - * Add runtime-specific control on top, make - * sure the bits you set per peripheral channel are - * cleared in the default config from the platform. - */ - ctrl_chained |= cohc->ctrl; - ctrl_last |= cohc->ctrl; - ctrl |= cohc->ctrl; - - if (direction == DMA_MEM_TO_DEV) { - u32 tx_flags = COH901318_CX_CTRL_PRDD_SOURCE | - COH901318_CX_CTRL_SRC_ADDR_INC_ENABLE; - - config |= COH901318_CX_CFG_RM_MEMORY_TO_PRIMARY; - ctrl_chained |= tx_flags; - ctrl_last |= tx_flags; - ctrl |= tx_flags; - } else if (direction == DMA_DEV_TO_MEM) { - u32 rx_flags = COH901318_CX_CTRL_PRDD_DEST | - COH901318_CX_CTRL_DST_ADDR_INC_ENABLE; - - config |= COH901318_CX_CFG_RM_PRIMARY_TO_MEMORY; - ctrl_chained |= rx_flags; - ctrl_last |= rx_flags; - ctrl |= rx_flags; - } else - goto err_direction; - - /* The dma only supports transmitting packages up to - * MAX_DMA_PACKET_SIZE. Calculate to total number of - * dma elemts required to send the entire sg list - */ - for_each_sg(sgl, sg, sg_len, i) { - unsigned int factor; - size = sg_dma_len(sg); - - if (size <= MAX_DMA_PACKET_SIZE) { - len++; - continue; - } - - factor = size >> MAX_DMA_PACKET_SIZE_SHIFT; - if ((factor << MAX_DMA_PACKET_SIZE_SHIFT) < size) - factor++; - - len += factor; - } - - pr_debug("Allocate %d lli:s for this transfer\n", len); - lli = coh901318_lli_alloc(&cohc->base->pool, len); - - if (lli == NULL) - goto err_dma_alloc; - - coh901318_dma_set_runtimeconfig(chan, &cohc->config, direction); - - /* initiate allocated lli list */ - ret = coh901318_lli_fill_sg(&cohc->base->pool, lli, sgl, sg_len, - cohc->addr, - ctrl_chained, - ctrl, - ctrl_last, - direction, COH901318_CX_CTRL_TC_IRQ_ENABLE); - if (ret) - goto err_lli_fill; - - - COH_DBG(coh901318_list_print(cohc, lli)); - - /* Pick a descriptor to handle this transfer */ - cohd = coh901318_desc_get(cohc); - cohd->head_config = config; - /* - * Set the default head ctrl for the channel to the one from the - * lli, things may have changed due to odd buffer alignment - * etc. - */ - cohd->head_ctrl = lli->control; - cohd->dir = direction; - cohd->flags = flags; - cohd->desc.tx_submit = coh901318_tx_submit; - cohd->lli = lli; - - spin_unlock_irqrestore(&cohc->lock, flg); - - return &cohd->desc; - err_lli_fill: - err_dma_alloc: - err_direction: - spin_unlock_irqrestore(&cohc->lock, flg); - out: - return NULL; -} - -static enum dma_status -coh901318_tx_status(struct dma_chan *chan, dma_cookie_t cookie, - struct dma_tx_state *txstate) -{ - struct coh901318_chan *cohc = to_coh901318_chan(chan); - enum dma_status ret; - - ret = dma_cookie_status(chan, cookie, txstate); - if (ret == DMA_COMPLETE || !txstate) - return ret; - - dma_set_residue(txstate, coh901318_get_bytes_left(chan)); - - if (ret == DMA_IN_PROGRESS && cohc->stopped) - ret = DMA_PAUSED; - - return ret; -} - -static void -coh901318_issue_pending(struct dma_chan *chan) -{ - struct coh901318_chan *cohc = to_coh901318_chan(chan); - unsigned long flags; - - spin_lock_irqsave(&cohc->lock, flags); - - /* - * Busy means that pending jobs are already being processed, - * and then there is no point in starting the queue: the - * terminal count interrupt on the channel will take the next - * job on the queue and execute it anyway. - */ - if (!cohc->busy) - coh901318_queue_start(cohc); - - spin_unlock_irqrestore(&cohc->lock, flags); -} - -/* - * Here we wrap in the runtime dma control interface - */ -struct burst_table { - int burst_8bit; - int burst_16bit; - int burst_32bit; - u32 reg; -}; - -static const struct burst_table burst_sizes[] = { - { - .burst_8bit = 64, - .burst_16bit = 32, - .burst_32bit = 16, - .reg = COH901318_CX_CTRL_BURST_COUNT_64_BYTES, - }, - { - .burst_8bit = 48, - .burst_16bit = 24, - .burst_32bit = 12, - .reg = COH901318_CX_CTRL_BURST_COUNT_48_BYTES, - }, - { - .burst_8bit = 32, - .burst_16bit = 16, - .burst_32bit = 8, - .reg = COH901318_CX_CTRL_BURST_COUNT_32_BYTES, - }, - { - .burst_8bit = 16, - .burst_16bit = 8, - .burst_32bit = 4, - .reg = COH901318_CX_CTRL_BURST_COUNT_16_BYTES, - }, - { - .burst_8bit = 8, - .burst_16bit = 4, - .burst_32bit = 2, - .reg = COH901318_CX_CTRL_BURST_COUNT_8_BYTES, - }, - { - .burst_8bit = 4, - .burst_16bit = 2, - .burst_32bit = 1, - .reg = COH901318_CX_CTRL_BURST_COUNT_4_BYTES, - }, - { - .burst_8bit = 2, - .burst_16bit = 1, - .burst_32bit = 0, - .reg = COH901318_CX_CTRL_BURST_COUNT_2_BYTES, - }, - { - .burst_8bit = 1, - .burst_16bit = 0, - .burst_32bit = 0, - .reg = COH901318_CX_CTRL_BURST_COUNT_1_BYTE, - }, -}; - -static int coh901318_dma_set_runtimeconfig(struct dma_chan *chan, - struct dma_slave_config *config, - enum dma_transfer_direction direction) -{ - struct coh901318_chan *cohc = to_coh901318_chan(chan); - dma_addr_t addr; - enum dma_slave_buswidth addr_width; - u32 maxburst; - u32 ctrl = 0; - int i = 0; - - /* We only support mem to per or per to mem transfers */ - if (direction == DMA_DEV_TO_MEM) { - addr = config->src_addr; - addr_width = config->src_addr_width; - maxburst = config->src_maxburst; - } else if (direction == DMA_MEM_TO_DEV) { - addr = config->dst_addr; - addr_width = config->dst_addr_width; - maxburst = config->dst_maxburst; - } else { - dev_err(COHC_2_DEV(cohc), "illegal channel mode\n"); - return -EINVAL; - } - - dev_dbg(COHC_2_DEV(cohc), "configure channel for %d byte transfers\n", - addr_width); - switch (addr_width) { - case DMA_SLAVE_BUSWIDTH_1_BYTE: - ctrl |= - COH901318_CX_CTRL_SRC_BUS_SIZE_8_BITS | - COH901318_CX_CTRL_DST_BUS_SIZE_8_BITS; - - while (i < ARRAY_SIZE(burst_sizes)) { - if (burst_sizes[i].burst_8bit <= maxburst) - break; - i++; - } - - break; - case DMA_SLAVE_BUSWIDTH_2_BYTES: - ctrl |= - COH901318_CX_CTRL_SRC_BUS_SIZE_16_BITS | - COH901318_CX_CTRL_DST_BUS_SIZE_16_BITS; - - while (i < ARRAY_SIZE(burst_sizes)) { - if (burst_sizes[i].burst_16bit <= maxburst) - break; - i++; - } - - break; - case DMA_SLAVE_BUSWIDTH_4_BYTES: - /* Direction doesn't matter here, it's 32/32 bits */ - ctrl |= - COH901318_CX_CTRL_SRC_BUS_SIZE_32_BITS | - COH901318_CX_CTRL_DST_BUS_SIZE_32_BITS; - - while (i < ARRAY_SIZE(burst_sizes)) { - if (burst_sizes[i].burst_32bit <= maxburst) - break; - i++; - } - - break; - default: - dev_err(COHC_2_DEV(cohc), - "bad runtimeconfig: alien address width\n"); - return -EINVAL; - } - - ctrl |= burst_sizes[i].reg; - dev_dbg(COHC_2_DEV(cohc), - "selected burst size %d bytes for address width %d bytes, maxburst %d\n", - burst_sizes[i].burst_8bit, addr_width, maxburst); - - cohc->addr = addr; - cohc->ctrl = ctrl; - - return 0; -} - -static int coh901318_dma_slave_config(struct dma_chan *chan, - struct dma_slave_config *config) -{ - struct coh901318_chan *cohc = to_coh901318_chan(chan); - - memcpy(&cohc->config, config, sizeof(*config)); - - return 0; -} - -static void coh901318_base_init(struct dma_device *dma, const int *pick_chans, - struct coh901318_base *base) -{ - int chans_i; - int i = 0; - struct coh901318_chan *cohc; - - INIT_LIST_HEAD(&dma->channels); - - for (chans_i = 0; pick_chans[chans_i] != -1; chans_i += 2) { - for (i = pick_chans[chans_i]; i <= pick_chans[chans_i+1]; i++) { - cohc = &base->chans[i]; - - cohc->base = base; - cohc->chan.device = dma; - cohc->id = i; - - /* TODO: do we really need this lock if only one - * client is connected to each channel? - */ - - spin_lock_init(&cohc->lock); - - cohc->nbr_active_done = 0; - cohc->busy = 0; - INIT_LIST_HEAD(&cohc->free); - INIT_LIST_HEAD(&cohc->active); - INIT_LIST_HEAD(&cohc->queue); - - tasklet_setup(&cohc->tasklet, dma_tasklet); - - list_add_tail(&cohc->chan.device_node, - &dma->channels); - } - } -} - -static int __init coh901318_probe(struct platform_device *pdev) -{ - int err = 0; - struct coh901318_base *base; - int irq; - struct resource *io; - - io = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!io) - return -ENODEV; - - /* Map DMA controller registers to virtual memory */ - if (devm_request_mem_region(&pdev->dev, - io->start, - resource_size(io), - pdev->dev.driver->name) == NULL) - return -ENOMEM; - - base = devm_kzalloc(&pdev->dev, - ALIGN(sizeof(struct coh901318_base), 4) + - U300_DMA_CHANNELS * - sizeof(struct coh901318_chan), - GFP_KERNEL); - if (!base) - return -ENOMEM; - - base->chans = ((void *)base) + ALIGN(sizeof(struct coh901318_base), 4); - - base->virtbase = devm_ioremap(&pdev->dev, io->start, resource_size(io)); - if (!base->virtbase) - return -ENOMEM; - - base->dev = &pdev->dev; - spin_lock_init(&base->pm.lock); - base->pm.started_channels = 0; - - COH901318_DEBUGFS_ASSIGN(debugfs_dma_base, base); - - irq = platform_get_irq(pdev, 0); - if (irq < 0) - return irq; - - err = devm_request_irq(&pdev->dev, irq, dma_irq_handler, 0, - "coh901318", base); - if (err) - return err; - - base->irq = irq; - - err = coh901318_pool_create(&base->pool, &pdev->dev, - sizeof(struct coh901318_lli), - 32); - if (err) - return err; - - /* init channels for device transfers */ - coh901318_base_init(&base->dma_slave, dma_slave_channels, - base); - - dma_cap_zero(base->dma_slave.cap_mask); - dma_cap_set(DMA_SLAVE, base->dma_slave.cap_mask); - - base->dma_slave.device_alloc_chan_resources = coh901318_alloc_chan_resources; - base->dma_slave.device_free_chan_resources = coh901318_free_chan_resources; - base->dma_slave.device_prep_slave_sg = coh901318_prep_slave_sg; - base->dma_slave.device_tx_status = coh901318_tx_status; - base->dma_slave.device_issue_pending = coh901318_issue_pending; - base->dma_slave.device_config = coh901318_dma_slave_config; - base->dma_slave.device_pause = coh901318_pause; - base->dma_slave.device_resume = coh901318_resume; - base->dma_slave.device_terminate_all = coh901318_terminate_all; - base->dma_slave.dev = &pdev->dev; - - err = dma_async_device_register(&base->dma_slave); - - if (err) - goto err_register_slave; - - /* init channels for memcpy */ - coh901318_base_init(&base->dma_memcpy, dma_memcpy_channels, - base); - - dma_cap_zero(base->dma_memcpy.cap_mask); - dma_cap_set(DMA_MEMCPY, base->dma_memcpy.cap_mask); - - base->dma_memcpy.device_alloc_chan_resources = coh901318_alloc_chan_resources; - base->dma_memcpy.device_free_chan_resources = coh901318_free_chan_resources; - base->dma_memcpy.device_prep_dma_memcpy = coh901318_prep_memcpy; - base->dma_memcpy.device_tx_status = coh901318_tx_status; - base->dma_memcpy.device_issue_pending = coh901318_issue_pending; - base->dma_memcpy.device_config = coh901318_dma_slave_config; - base->dma_memcpy.device_pause = coh901318_pause; - base->dma_memcpy.device_resume = coh901318_resume; - base->dma_memcpy.device_terminate_all = coh901318_terminate_all; - base->dma_memcpy.dev = &pdev->dev; - /* - * This controller can only access address at even 32bit boundaries, - * i.e. 2^2 - */ - base->dma_memcpy.copy_align = DMAENGINE_ALIGN_4_BYTES; - err = dma_async_device_register(&base->dma_memcpy); - - if (err) - goto err_register_memcpy; - - err = of_dma_controller_register(pdev->dev.of_node, coh901318_xlate, - base); - if (err) - goto err_register_of_dma; - - platform_set_drvdata(pdev, base); - dev_info(&pdev->dev, "Initialized COH901318 DMA on virtual base 0x%p\n", - base->virtbase); - - return err; - - err_register_of_dma: - dma_async_device_unregister(&base->dma_memcpy); - err_register_memcpy: - dma_async_device_unregister(&base->dma_slave); - err_register_slave: - coh901318_pool_destroy(&base->pool); - return err; -} -static void coh901318_base_remove(struct coh901318_base *base, const int *pick_chans) -{ - int chans_i; - int i = 0; - struct coh901318_chan *cohc; - - for (chans_i = 0; pick_chans[chans_i] != -1; chans_i += 2) { - for (i = pick_chans[chans_i]; i <= pick_chans[chans_i+1]; i++) { - cohc = &base->chans[i]; - - tasklet_kill(&cohc->tasklet); - } - } - -} - -static int coh901318_remove(struct platform_device *pdev) -{ - struct coh901318_base *base = platform_get_drvdata(pdev); - - devm_free_irq(&pdev->dev, base->irq, base); - - coh901318_base_remove(base, dma_slave_channels); - coh901318_base_remove(base, dma_memcpy_channels); - - of_dma_controller_free(pdev->dev.of_node); - dma_async_device_unregister(&base->dma_memcpy); - dma_async_device_unregister(&base->dma_slave); - coh901318_pool_destroy(&base->pool); - return 0; -} - -static const struct of_device_id coh901318_dt_match[] = { - { .compatible = "stericsson,coh901318" }, - {}, -}; - -static struct platform_driver coh901318_driver = { - .remove = coh901318_remove, - .driver = { - .name = "coh901318", - .of_match_table = coh901318_dt_match, - }, -}; - -static int __init coh901318_init(void) -{ - return platform_driver_probe(&coh901318_driver, coh901318_probe); -} -subsys_initcall(coh901318_init); - -static void __exit coh901318_exit(void) -{ - platform_driver_unregister(&coh901318_driver); -} -module_exit(coh901318_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Per Friden"); diff --git a/drivers/dma/coh901318.h b/drivers/dma/coh901318.h deleted file mode 100644 index bbf533600558..000000000000 --- a/drivers/dma/coh901318.h +++ /dev/null @@ -1,141 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2007-2013 ST-Ericsson - * DMA driver for COH 901 318 - * Author: Per Friden - */ - -#ifndef COH901318_H -#define COH901318_H - -#define MAX_DMA_PACKET_SIZE_SHIFT 11 -#define MAX_DMA_PACKET_SIZE (1 << MAX_DMA_PACKET_SIZE_SHIFT) - -struct device; - -struct coh901318_pool { - spinlock_t lock; - struct dma_pool *dmapool; - struct device *dev; - -#ifdef CONFIG_DEBUG_FS - int debugfs_pool_counter; -#endif -}; - -/** - * struct coh901318_lli - linked list item for DMAC - * @control: control settings for DMAC - * @src_addr: transfer source address - * @dst_addr: transfer destination address - * @link_addr: physical address to next lli - * @virt_link_addr: virtual address of next lli (only used by pool_free) - * @phy_this: physical address of current lli (only used by pool_free) - */ -struct coh901318_lli { - u32 control; - dma_addr_t src_addr; - dma_addr_t dst_addr; - dma_addr_t link_addr; - - void *virt_link_addr; - dma_addr_t phy_this; -}; - -/** - * coh901318_pool_create() - Creates an dma pool for lli:s - * @pool: pool handle - * @dev: dma device - * @lli_nbr: number of lli:s in the pool - * @algin: address alignemtn of lli:s - * returns 0 on success otherwise none zero - */ -int coh901318_pool_create(struct coh901318_pool *pool, - struct device *dev, - size_t lli_nbr, size_t align); - -/** - * coh901318_pool_destroy() - Destroys the dma pool - * @pool: pool handle - * returns 0 on success otherwise none zero - */ -int coh901318_pool_destroy(struct coh901318_pool *pool); - -/** - * coh901318_lli_alloc() - Allocates a linked list - * - * @pool: pool handle - * @len: length to list - * return: none NULL if success otherwise NULL - */ -struct coh901318_lli * -coh901318_lli_alloc(struct coh901318_pool *pool, - unsigned int len); - -/** - * coh901318_lli_free() - Returns the linked list items to the pool - * @pool: pool handle - * @lli: reference to lli pointer to be freed - */ -void coh901318_lli_free(struct coh901318_pool *pool, - struct coh901318_lli **lli); - -/** - * coh901318_lli_fill_memcpy() - Prepares the lli:s for dma memcpy - * @pool: pool handle - * @lli: allocated lli - * @src: src address - * @size: transfer size - * @dst: destination address - * @ctrl_chained: ctrl for chained lli - * @ctrl_last: ctrl for the last lli - * returns number of CPU interrupts for the lli, negative on error. - */ -int -coh901318_lli_fill_memcpy(struct coh901318_pool *pool, - struct coh901318_lli *lli, - dma_addr_t src, unsigned int size, - dma_addr_t dst, u32 ctrl_chained, u32 ctrl_last); - -/** - * coh901318_lli_fill_single() - Prepares the lli:s for dma single transfer - * @pool: pool handle - * @lli: allocated lli - * @buf: transfer buffer - * @size: transfer size - * @dev_addr: address of periphal - * @ctrl_chained: ctrl for chained lli - * @ctrl_last: ctrl for the last lli - * @dir: direction of transfer (to or from device) - * returns number of CPU interrupts for the lli, negative on error. - */ -int -coh901318_lli_fill_single(struct coh901318_pool *pool, - struct coh901318_lli *lli, - dma_addr_t buf, unsigned int size, - dma_addr_t dev_addr, u32 ctrl_chained, u32 ctrl_last, - enum dma_transfer_direction dir); - -/** - * coh901318_lli_fill_single() - Prepares the lli:s for dma scatter list transfer - * @pool: pool handle - * @lli: allocated lli - * @sg: scatter gather list - * @nents: number of entries in sg - * @dev_addr: address of periphal - * @ctrl_chained: ctrl for chained lli - * @ctrl: ctrl of middle lli - * @ctrl_last: ctrl for the last lli - * @dir: direction of transfer (to or from device) - * @ctrl_irq_mask: ctrl mask for CPU interrupt - * returns number of CPU interrupts for the lli, negative on error. - */ -int -coh901318_lli_fill_sg(struct coh901318_pool *pool, - struct coh901318_lli *lli, - struct scatterlist *sg, unsigned int nents, - dma_addr_t dev_addr, u32 ctrl_chained, - u32 ctrl, u32 ctrl_last, - enum dma_transfer_direction dir, u32 ctrl_irq_mask); - -#endif /* COH901318_H */ diff --git a/drivers/dma/coh901318_lli.c b/drivers/dma/coh901318_lli.c deleted file mode 100644 index 6b6c2fd0865a..000000000000 --- a/drivers/dma/coh901318_lli.c +++ /dev/null @@ -1,313 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * driver/dma/coh901318_lli.c - * - * Copyright (C) 2007-2009 ST-Ericsson - * Support functions for handling lli for dma - * Author: Per Friden - */ - -#include -#include -#include -#include -#include - -#include "coh901318.h" - -#if (defined(CONFIG_DEBUG_FS) && defined(CONFIG_U300_DEBUG)) -#define DEBUGFS_POOL_COUNTER_RESET(pool) (pool->debugfs_pool_counter = 0) -#define DEBUGFS_POOL_COUNTER_ADD(pool, add) (pool->debugfs_pool_counter += add) -#else -#define DEBUGFS_POOL_COUNTER_RESET(pool) -#define DEBUGFS_POOL_COUNTER_ADD(pool, add) -#endif - -static struct coh901318_lli * -coh901318_lli_next(struct coh901318_lli *data) -{ - if (data == NULL || data->link_addr == 0) - return NULL; - - return (struct coh901318_lli *) data->virt_link_addr; -} - -int coh901318_pool_create(struct coh901318_pool *pool, - struct device *dev, - size_t size, size_t align) -{ - spin_lock_init(&pool->lock); - pool->dev = dev; - pool->dmapool = dma_pool_create("lli_pool", dev, size, align, 0); - - DEBUGFS_POOL_COUNTER_RESET(pool); - return 0; -} - -int coh901318_pool_destroy(struct coh901318_pool *pool) -{ - - dma_pool_destroy(pool->dmapool); - return 0; -} - -struct coh901318_lli * -coh901318_lli_alloc(struct coh901318_pool *pool, unsigned int len) -{ - int i; - struct coh901318_lli *head; - struct coh901318_lli *lli; - struct coh901318_lli *lli_prev; - dma_addr_t phy; - - if (len == 0) - return NULL; - - spin_lock(&pool->lock); - - head = dma_pool_alloc(pool->dmapool, GFP_NOWAIT, &phy); - - if (head == NULL) - goto err; - - DEBUGFS_POOL_COUNTER_ADD(pool, 1); - - lli = head; - lli->phy_this = phy; - lli->link_addr = 0x00000000; - lli->virt_link_addr = NULL; - - for (i = 1; i < len; i++) { - lli_prev = lli; - - lli = dma_pool_alloc(pool->dmapool, GFP_NOWAIT, &phy); - - if (lli == NULL) - goto err_clean_up; - - DEBUGFS_POOL_COUNTER_ADD(pool, 1); - lli->phy_this = phy; - lli->link_addr = 0x00000000; - lli->virt_link_addr = NULL; - - lli_prev->link_addr = phy; - lli_prev->virt_link_addr = lli; - } - - spin_unlock(&pool->lock); - - return head; - - err: - spin_unlock(&pool->lock); - return NULL; - - err_clean_up: - lli_prev->link_addr = 0x00000000U; - spin_unlock(&pool->lock); - coh901318_lli_free(pool, &head); - return NULL; -} - -void coh901318_lli_free(struct coh901318_pool *pool, - struct coh901318_lli **lli) -{ - struct coh901318_lli *l; - struct coh901318_lli *next; - - if (lli == NULL) - return; - - l = *lli; - - if (l == NULL) - return; - - spin_lock(&pool->lock); - - while (l->link_addr) { - next = l->virt_link_addr; - dma_pool_free(pool->dmapool, l, l->phy_this); - DEBUGFS_POOL_COUNTER_ADD(pool, -1); - l = next; - } - dma_pool_free(pool->dmapool, l, l->phy_this); - DEBUGFS_POOL_COUNTER_ADD(pool, -1); - - spin_unlock(&pool->lock); - *lli = NULL; -} - -int -coh901318_lli_fill_memcpy(struct coh901318_pool *pool, - struct coh901318_lli *lli, - dma_addr_t source, unsigned int size, - dma_addr_t destination, u32 ctrl_chained, - u32 ctrl_eom) -{ - int s = size; - dma_addr_t src = source; - dma_addr_t dst = destination; - - lli->src_addr = src; - lli->dst_addr = dst; - - while (lli->link_addr) { - lli->control = ctrl_chained | MAX_DMA_PACKET_SIZE; - lli->src_addr = src; - lli->dst_addr = dst; - - s -= MAX_DMA_PACKET_SIZE; - lli = coh901318_lli_next(lli); - - src += MAX_DMA_PACKET_SIZE; - dst += MAX_DMA_PACKET_SIZE; - } - - lli->control = ctrl_eom | s; - lli->src_addr = src; - lli->dst_addr = dst; - - return 0; -} - -int -coh901318_lli_fill_single(struct coh901318_pool *pool, - struct coh901318_lli *lli, - dma_addr_t buf, unsigned int size, - dma_addr_t dev_addr, u32 ctrl_chained, u32 ctrl_eom, - enum dma_transfer_direction dir) -{ - int s = size; - dma_addr_t src; - dma_addr_t dst; - - - if (dir == DMA_MEM_TO_DEV) { - src = buf; - dst = dev_addr; - - } else if (dir == DMA_DEV_TO_MEM) { - - src = dev_addr; - dst = buf; - } else { - return -EINVAL; - } - - while (lli->link_addr) { - size_t block_size = MAX_DMA_PACKET_SIZE; - lli->control = ctrl_chained | MAX_DMA_PACKET_SIZE; - - /* If we are on the next-to-final block and there will - * be less than half a DMA packet left for the last - * block, then we want to make this block a little - * smaller to balance the sizes. This is meant to - * avoid too small transfers if the buffer size is - * (MAX_DMA_PACKET_SIZE*N + 1) */ - if (s < (MAX_DMA_PACKET_SIZE + MAX_DMA_PACKET_SIZE/2)) - block_size = MAX_DMA_PACKET_SIZE/2; - - s -= block_size; - lli->src_addr = src; - lli->dst_addr = dst; - - lli = coh901318_lli_next(lli); - - if (dir == DMA_MEM_TO_DEV) - src += block_size; - else if (dir == DMA_DEV_TO_MEM) - dst += block_size; - } - - lli->control = ctrl_eom | s; - lli->src_addr = src; - lli->dst_addr = dst; - - return 0; -} - -int -coh901318_lli_fill_sg(struct coh901318_pool *pool, - struct coh901318_lli *lli, - struct scatterlist *sgl, unsigned int nents, - dma_addr_t dev_addr, u32 ctrl_chained, u32 ctrl, - u32 ctrl_last, - enum dma_transfer_direction dir, u32 ctrl_irq_mask) -{ - int i; - struct scatterlist *sg; - u32 ctrl_sg; - dma_addr_t src = 0; - dma_addr_t dst = 0; - u32 bytes_to_transfer; - u32 elem_size; - - if (lli == NULL) - goto err; - - spin_lock(&pool->lock); - - if (dir == DMA_MEM_TO_DEV) - dst = dev_addr; - else if (dir == DMA_DEV_TO_MEM) - src = dev_addr; - else - goto err; - - for_each_sg(sgl, sg, nents, i) { - if (sg_is_chain(sg)) { - /* sg continues to the next sg-element don't - * send ctrl_finish until the last - * sg-element in the chain - */ - ctrl_sg = ctrl_chained; - } else if (i == nents - 1) - ctrl_sg = ctrl_last; - else - ctrl_sg = ctrl ? ctrl : ctrl_last; - - - if (dir == DMA_MEM_TO_DEV) - /* increment source address */ - src = sg_dma_address(sg); - else - /* increment destination address */ - dst = sg_dma_address(sg); - - bytes_to_transfer = sg_dma_len(sg); - - while (bytes_to_transfer) { - u32 val; - - if (bytes_to_transfer > MAX_DMA_PACKET_SIZE) { - elem_size = MAX_DMA_PACKET_SIZE; - val = ctrl_chained; - } else { - elem_size = bytes_to_transfer; - val = ctrl_sg; - } - - lli->control = val | elem_size; - lli->src_addr = src; - lli->dst_addr = dst; - - if (dir == DMA_DEV_TO_MEM) - dst += elem_size; - else - src += elem_size; - - BUG_ON(lli->link_addr & 3); - - bytes_to_transfer -= elem_size; - lli = coh901318_lli_next(lli); - } - - } - spin_unlock(&pool->lock); - - return 0; - err: - spin_unlock(&pool->lock); - return -EINVAL; -} diff --git a/include/linux/platform_data/dma-coh901318.h b/include/linux/platform_data/dma-coh901318.h deleted file mode 100644 index 4cca529f8d56..000000000000 --- a/include/linux/platform_data/dma-coh901318.h +++ /dev/null @@ -1,72 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Platform data for the COH901318 DMA controller - * Copyright (C) 2007-2013 ST-Ericsson - */ - -#ifndef PLAT_COH901318_H -#define PLAT_COH901318_H - -#ifdef CONFIG_COH901318 - -/* We only support the U300 DMA channels */ -#define U300_DMA_MSL_TX_0 0 -#define U300_DMA_MSL_TX_1 1 -#define U300_DMA_MSL_TX_2 2 -#define U300_DMA_MSL_TX_3 3 -#define U300_DMA_MSL_TX_4 4 -#define U300_DMA_MSL_TX_5 5 -#define U300_DMA_MSL_TX_6 6 -#define U300_DMA_MSL_RX_0 7 -#define U300_DMA_MSL_RX_1 8 -#define U300_DMA_MSL_RX_2 9 -#define U300_DMA_MSL_RX_3 10 -#define U300_DMA_MSL_RX_4 11 -#define U300_DMA_MSL_RX_5 12 -#define U300_DMA_MSL_RX_6 13 -#define U300_DMA_MMCSD_RX_TX 14 -#define U300_DMA_MSPRO_TX 15 -#define U300_DMA_MSPRO_RX 16 -#define U300_DMA_UART0_TX 17 -#define U300_DMA_UART0_RX 18 -#define U300_DMA_APEX_TX 19 -#define U300_DMA_APEX_RX 20 -#define U300_DMA_PCM_I2S0_TX 21 -#define U300_DMA_PCM_I2S0_RX 22 -#define U300_DMA_PCM_I2S1_TX 23 -#define U300_DMA_PCM_I2S1_RX 24 -#define U300_DMA_XGAM_CDI 25 -#define U300_DMA_XGAM_PDI 26 -#define U300_DMA_SPI_TX 27 -#define U300_DMA_SPI_RX 28 -#define U300_DMA_GENERAL_PURPOSE_0 29 -#define U300_DMA_GENERAL_PURPOSE_1 30 -#define U300_DMA_GENERAL_PURPOSE_2 31 -#define U300_DMA_GENERAL_PURPOSE_3 32 -#define U300_DMA_GENERAL_PURPOSE_4 33 -#define U300_DMA_GENERAL_PURPOSE_5 34 -#define U300_DMA_GENERAL_PURPOSE_6 35 -#define U300_DMA_GENERAL_PURPOSE_7 36 -#define U300_DMA_GENERAL_PURPOSE_8 37 -#define U300_DMA_UART1_TX 38 -#define U300_DMA_UART1_RX 39 - -#define U300_DMA_DEVICE_CHANNELS 32 -#define U300_DMA_CHANNELS 40 - -/** - * coh901318_filter_id() - DMA channel filter function - * @chan: dma channel handle - * @chan_id: id of dma channel to be filter out - * - * In dma_request_channel() it specifies what channel id to be requested - */ -bool coh901318_filter_id(struct dma_chan *chan, void *chan_id); -#else -static inline bool coh901318_filter_id(struct dma_chan *chan, void *chan_id) -{ - return false; -} -#endif - -#endif /* PLAT_COH901318_H */ -- cgit v1.2.3 From e247f85a9bf6af9ce6bc36d86ac242f782ae0947 Mon Sep 17 00:00:00 2001 From: Lubomir Rintel Date: Thu, 21 Jan 2021 12:03:54 +0100 Subject: dmaengine: mmp_pdma: Remove mmp_pdma_filter_fn() It's not used anywhere -- drop it. Signed-off-by: Lubomir Rintel Link: https://lore.kernel.org/r/20210121110356.1768635-2-lkundrak@v3.sk Signed-off-by: Vinod Koul --- drivers/dma/mmp_pdma.c | 14 -------------- include/linux/dma/mmp-pdma.h | 16 ---------------- 2 files changed, 30 deletions(-) delete mode 100644 include/linux/dma/mmp-pdma.h (limited to 'include') diff --git a/drivers/dma/mmp_pdma.c b/drivers/dma/mmp_pdma.c index b84303be8edf..89f1814ff27a 100644 --- a/drivers/dma/mmp_pdma.c +++ b/drivers/dma/mmp_pdma.c @@ -18,7 +18,6 @@ #include #include #include -#include #include "dmaengine.h" @@ -1148,19 +1147,6 @@ static struct platform_driver mmp_pdma_driver = { .remove = mmp_pdma_remove, }; -bool mmp_pdma_filter_fn(struct dma_chan *chan, void *param) -{ - struct mmp_pdma_chan *c = to_mmp_pdma_chan(chan); - - if (chan->device->dev->driver != &mmp_pdma_driver.driver) - return false; - - c->drcmr = *(unsigned int *)param; - - return true; -} -EXPORT_SYMBOL_GPL(mmp_pdma_filter_fn); - module_platform_driver(mmp_pdma_driver); MODULE_DESCRIPTION("MARVELL MMP Peripheral DMA Driver"); diff --git a/include/linux/dma/mmp-pdma.h b/include/linux/dma/mmp-pdma.h deleted file mode 100644 index 25cab62a28c4..000000000000 --- a/include/linux/dma/mmp-pdma.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _MMP_PDMA_H_ -#define _MMP_PDMA_H_ - -struct dma_chan; - -#ifdef CONFIG_MMP_PDMA -bool mmp_pdma_filter_fn(struct dma_chan *chan, void *param); -#else -static inline bool mmp_pdma_filter_fn(struct dma_chan *chan, void *param) -{ - return false; -} -#endif - -#endif /* _MMP_PDMA_H_ */ -- cgit v1.2.3 From 7eecea89e44f64e60f1410483e79a0cab18ad580 Mon Sep 17 00:00:00 2001 From: Jorgen Hansen Date: Wed, 20 Jan 2021 08:33:40 -0800 Subject: VMCI: Enforce queuepair max size for IOCTL_VMCI_QUEUEPAIR_ALLOC When create the VMCI queue pair tracking data structures on the host side, the IOCTL for creating the VMCI queue pair didn't validate the queue pair size parameters. This change adds checks for this. This avoids a memory allocation issue in qp_host_alloc_queue, as reported by nslusarek@gmx.net. The check in qp_host_alloc_queue has also been updated to enforce the maximum queue pair size as defined by VMCI_MAX_GUEST_QP_MEMORY. The fix has been verified using sample code supplied by nslusarek@gmx.net. Reported-by: nslusarek@gmx.net Reviewed-by: Vishnu Dasa Signed-off-by: Jorgen Hansen Link: https://lore.kernel.org/r/1611160420-30573-1-git-send-email-jhansen@vmware.com Signed-off-by: Greg Kroah-Hartman --- drivers/misc/vmw_vmci/vmci_queue_pair.c | 12 ++++++++---- include/linux/vmw_vmci_defs.h | 4 ++-- 2 files changed, 10 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/drivers/misc/vmw_vmci/vmci_queue_pair.c b/drivers/misc/vmw_vmci/vmci_queue_pair.c index 525ef96d3a07..d787ddecee77 100644 --- a/drivers/misc/vmw_vmci/vmci_queue_pair.c +++ b/drivers/misc/vmw_vmci/vmci_queue_pair.c @@ -237,7 +237,9 @@ static struct qp_list qp_guest_endpoints = { #define QPE_NUM_PAGES(_QPE) ((u32) \ (DIV_ROUND_UP(_QPE.produce_size, PAGE_SIZE) + \ DIV_ROUND_UP(_QPE.consume_size, PAGE_SIZE) + 2)) - +#define QP_SIZES_ARE_VALID(_prod_qsize, _cons_qsize) \ + ((_prod_qsize) + (_cons_qsize) >= max(_prod_qsize, _cons_qsize) && \ + (_prod_qsize) + (_cons_qsize) <= VMCI_MAX_GUEST_QP_MEMORY) /* * Frees kernel VA space for a given queue and its queue header, and @@ -528,7 +530,7 @@ static struct vmci_queue *qp_host_alloc_queue(u64 size) u64 num_pages; const size_t queue_size = sizeof(*queue) + sizeof(*(queue->kernel_if)); - if (size > SIZE_MAX - PAGE_SIZE) + if (size > min_t(size_t, VMCI_MAX_GUEST_QP_MEMORY, SIZE_MAX - PAGE_SIZE)) return NULL; num_pages = DIV_ROUND_UP(size, PAGE_SIZE) + 1; if (num_pages > (SIZE_MAX - queue_size) / @@ -1929,6 +1931,9 @@ int vmci_qp_broker_alloc(struct vmci_handle handle, struct vmci_qp_page_store *page_store, struct vmci_ctx *context) { + if (!QP_SIZES_ARE_VALID(produce_size, consume_size)) + return VMCI_ERROR_NO_RESOURCES; + return qp_broker_alloc(handle, peer, flags, priv_flags, produce_size, consume_size, page_store, context, NULL, NULL, NULL, NULL); @@ -2685,8 +2690,7 @@ int vmci_qpair_alloc(struct vmci_qp **qpair, * used by the device is NO_RESOURCES, so use that here too. */ - if (produce_qsize + consume_qsize < max(produce_qsize, consume_qsize) || - produce_qsize + consume_qsize > VMCI_MAX_GUEST_QP_MEMORY) + if (!QP_SIZES_ARE_VALID(produce_qsize, consume_qsize)) return VMCI_ERROR_NO_RESOURCES; retval = vmci_route(&src, &dst, false, &route); diff --git a/include/linux/vmw_vmci_defs.h b/include/linux/vmw_vmci_defs.h index be0afe6f379b..e36cb114c188 100644 --- a/include/linux/vmw_vmci_defs.h +++ b/include/linux/vmw_vmci_defs.h @@ -66,7 +66,7 @@ enum { * consists of at least two pages, the memory limit also dictates the * number of queue pairs a guest can create. */ -#define VMCI_MAX_GUEST_QP_MEMORY (128 * 1024 * 1024) +#define VMCI_MAX_GUEST_QP_MEMORY ((size_t)(128 * 1024 * 1024)) #define VMCI_MAX_GUEST_QP_COUNT (VMCI_MAX_GUEST_QP_MEMORY / PAGE_SIZE / 2) /* @@ -80,7 +80,7 @@ enum { * too much kernel memory (especially on vmkernel). We limit a queuepair to * 32 KB, or 16 KB per queue for symmetrical pairs. */ -#define VMCI_MAX_PINNED_QP_MEMORY (32 * 1024) +#define VMCI_MAX_PINNED_QP_MEMORY ((size_t)(32 * 1024)) /* * We have a fixed set of resource IDs available in the VMX. -- cgit v1.2.3 From 0fc99422bc034de018607ef6b70f92d4bc4a236d Mon Sep 17 00:00:00 2001 From: Michal Simek Date: Mon, 18 Jan 2021 09:48:56 +0100 Subject: firmware: xilinx: Remove PM_API_MAX value There is no reason to keep PM_API_MAX around. The commit acfdd18591ea ("firmware: xilinx: Use hash-table for api feature check") removed its usage that's why it is not used anywhere now. Signed-off-by: Michal Simek Link: https://lore.kernel.org/r/86e94593a29a1b5b1958c539a1bfabdd08c0948e.1610959734.git.michal.simek@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 2a0da841c942..0a483249ff30 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -85,7 +85,6 @@ enum pm_api_id { PM_CLOCK_GETPARENT, PM_SECURE_AES = 47, PM_FEATURE_CHECK = 63, - PM_API_MAX, }; /* PMU-FW return status codes */ -- cgit v1.2.3 From ead0ffc95a89b6b2c276702ee7b5a2b9bb445dfe Mon Sep 17 00:00:00 2001 From: Anastasia Kovaleva Date: Thu, 3 Dec 2020 11:20:35 +0300 Subject: scsi: target: core: Change ASCQ for residual write According to FCP-4 (9.4.2): If the command requested that data beyond the length specified by the FCP_DL field be transferred, then the device server shall set the FCP_RESID_OVER bit (see 9.5.8) to one in the FCP_RSP IU and: a) process the command normally except that data beyond the FCP_DL count shall not be requested or transferred; b) transfer no data and return CHECK CONDITION status with the sense key set to ILLEGAL REQUEST and the additional sense code set to INVALID FIELD IN COMMAND INFORMATION UNIT; or c) may transfer data and return CHECK CONDITION status with the sense key set to ABORTED COMMAND and the additional sense code set to INVALID FIELD IN COMMAND INFORMATION UNIT. TCM follows b) and transfers no data for residual writes but returns INVALID FIELD IN CDB instead of INVALID FIELD IN COMMAND INFORMATION UNIT. Change the ASCQ to INVALID FIELD IN COMMAND INFORMATION UNIT to meet the standard. Link: https://lore.kernel.org/r/20201203082035.54566-4-a.kovaleva@yadro.com Signed-off-by: Anastasia Kovaleva Signed-off-by: Roman Bolshakov Signed-off-by: Martin K. Petersen --- drivers/target/target_core_transport.c | 8 +++++++- include/target/target_core_base.h | 1 + 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index bc565c226380..93ea17cbad79 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -1338,7 +1338,7 @@ target_cmd_size_check(struct se_cmd *cmd, unsigned int size) if (cmd->se_cmd_flags & SCF_SCSI_DATA_CDB) { pr_err_ratelimited("Rejecting underflow/overflow" " for WRITE data CDB\n"); - return TCM_INVALID_CDB_FIELD; + return TCM_INVALID_FIELD_IN_COMMAND_IU; } /* * Some fabric drivers like iscsi-target still expect to @@ -1877,6 +1877,7 @@ void transport_generic_request_failure(struct se_cmd *cmd, case TCM_UNSUPPORTED_TARGET_DESC_TYPE_CODE: case TCM_TOO_MANY_SEGMENT_DESCS: case TCM_UNSUPPORTED_SEGMENT_DESC_TYPE_CODE: + case TCM_INVALID_FIELD_IN_COMMAND_IU: break; case TCM_OUT_OF_RESOURCES: cmd->scsi_status = SAM_STAT_TASK_SET_FULL; @@ -3203,6 +3204,11 @@ static const struct sense_detail sense_detail_table[] = { .asc = 0x55, .ascq = 0x04, /* INSUFFICIENT REGISTRATION RESOURCES */ }, + [TCM_INVALID_FIELD_IN_COMMAND_IU] = { + .key = ILLEGAL_REQUEST, + .asc = 0x0e, + .ascq = 0x03, /* INVALID FIELD IN COMMAND INFORMATION UNIT */ + }, }; /** diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index 63dd12124139..54dcc0eb25fa 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -187,6 +187,7 @@ enum tcm_sense_reason_table { TCM_UNSUPPORTED_SEGMENT_DESC_TYPE_CODE = R(0x1c), TCM_INSUFFICIENT_REGISTRATION_RESOURCES = R(0x1d), TCM_LUN_BUSY = R(0x1e), + TCM_INVALID_FIELD_IN_COMMAND_IU = R(0x1f), #undef R }; -- cgit v1.2.3 From 9cc0aaeb96e7f894d4735f069174948c1516fea7 Mon Sep 17 00:00:00 2001 From: John Garry Date: Wed, 6 Jan 2021 21:35:06 +0800 Subject: iova: Make has_iova_flush_queue() private Function has_iova_flush_queue() has no users outside iova.c, so make it private. Signed-off-by: John Garry Acked-by: Will Deacon Link: https://lore.kernel.org/r/1609940111-28563-2-git-send-email-john.garry@huawei.com Signed-off-by: Joerg Roedel --- drivers/iommu/iova.c | 2 +- include/linux/iova.h | 6 ------ 2 files changed, 1 insertion(+), 7 deletions(-) (limited to 'include') diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c index d20b8b333d30..5f2caa95c1f0 100644 --- a/drivers/iommu/iova.c +++ b/drivers/iommu/iova.c @@ -55,7 +55,7 @@ init_iova_domain(struct iova_domain *iovad, unsigned long granule, } EXPORT_SYMBOL_GPL(init_iova_domain); -bool has_iova_flush_queue(struct iova_domain *iovad) +static bool has_iova_flush_queue(struct iova_domain *iovad) { return !!iovad->fq; } diff --git a/include/linux/iova.h b/include/linux/iova.h index 76e16ae20729..2b76e0be1c5b 100644 --- a/include/linux/iova.h +++ b/include/linux/iova.h @@ -153,7 +153,6 @@ struct iova *reserve_iova(struct iova_domain *iovad, unsigned long pfn_lo, void copy_reserved_iova(struct iova_domain *from, struct iova_domain *to); void init_iova_domain(struct iova_domain *iovad, unsigned long granule, unsigned long start_pfn); -bool has_iova_flush_queue(struct iova_domain *iovad); int init_iova_flush_queue(struct iova_domain *iovad, iova_flush_cb flush_cb, iova_entry_dtor entry_dtor); struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn); @@ -223,11 +222,6 @@ static inline void init_iova_domain(struct iova_domain *iovad, { } -static inline bool has_iova_flush_queue(struct iova_domain *iovad) -{ - return false; -} - static inline int init_iova_flush_queue(struct iova_domain *iovad, iova_flush_cb flush_cb, iova_entry_dtor entry_dtor) -- cgit v1.2.3 From acda36189cb8df27ef073d391ebd67c64ac36cf9 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Wed, 27 Jan 2021 13:11:33 +0200 Subject: dt-bindings: interconnect: Add Qualcomm SDX55 DT bindings The Qualcomm SDX55 platform has several bus fabrics that could be controlled and tuned dynamically over RPMh according to the bandwidth demand. Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20210121053254.8355-2-manivannan.sadhasivam@linaro.org Signed-off-by: Georgi Djakov --- .../bindings/interconnect/qcom,rpmh.yaml | 4 ++ include/dt-bindings/interconnect/qcom,sdx55.h | 76 ++++++++++++++++++++++ 2 files changed, 80 insertions(+) create mode 100644 include/dt-bindings/interconnect/qcom,sdx55.h (limited to 'include') diff --git a/Documentation/devicetree/bindings/interconnect/qcom,rpmh.yaml b/Documentation/devicetree/bindings/interconnect/qcom,rpmh.yaml index 30c2a092d2d3..f9b150b817d8 100644 --- a/Documentation/devicetree/bindings/interconnect/qcom,rpmh.yaml +++ b/Documentation/devicetree/bindings/interconnect/qcom,rpmh.yaml @@ -45,6 +45,10 @@ properties: - qcom,sdm845-mem-noc - qcom,sdm845-mmss-noc - qcom,sdm845-system-noc + - qcom,sdx55-ipa-virt + - qcom,sdx55-mc-virt + - qcom,sdx55-mem-noc + - qcom,sdx55-system-noc - qcom,sm8150-aggre1-noc - qcom,sm8150-aggre2-noc - qcom,sm8150-camnoc-noc diff --git a/include/dt-bindings/interconnect/qcom,sdx55.h b/include/dt-bindings/interconnect/qcom,sdx55.h new file mode 100644 index 000000000000..bfb6524a2d90 --- /dev/null +++ b/include/dt-bindings/interconnect/qcom,sdx55.h @@ -0,0 +1,76 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Qualcomm SDX55 interconnect IDs + * + * Copyright (c) 2021, Linaro Ltd. + * Author: Manivannan Sadhasivam + */ + +#ifndef __DT_BINDINGS_INTERCONNECT_QCOM_SDX55_H +#define __DT_BINDINGS_INTERCONNECT_QCOM_SDX55_H + +#define MASTER_LLCC 0 +#define SLAVE_EBI_CH0 1 + +#define MASTER_TCU_0 0 +#define MASTER_SNOC_GC_MEM_NOC 1 +#define MASTER_AMPSS_M0 2 +#define SLAVE_LLCC 3 +#define SLAVE_MEM_NOC_SNOC 4 +#define SLAVE_MEM_NOC_PCIE_SNOC 5 + +#define MASTER_AUDIO 0 +#define MASTER_BLSP_1 1 +#define MASTER_QDSS_BAM 2 +#define MASTER_QPIC 3 +#define MASTER_SNOC_CFG 4 +#define MASTER_SPMI_FETCHER 5 +#define MASTER_ANOC_SNOC 6 +#define MASTER_IPA 7 +#define MASTER_MEM_NOC_SNOC 8 +#define MASTER_MEM_NOC_PCIE_SNOC 9 +#define MASTER_CRYPTO_CORE_0 10 +#define MASTER_EMAC 11 +#define MASTER_IPA_PCIE 12 +#define MASTER_PCIE 13 +#define MASTER_QDSS_ETR 14 +#define MASTER_SDCC_1 15 +#define MASTER_USB3 16 +#define SLAVE_AOP 17 +#define SLAVE_AOSS 18 +#define SLAVE_APPSS 19 +#define SLAVE_AUDIO 20 +#define SLAVE_BLSP_1 21 +#define SLAVE_CLK_CTL 22 +#define SLAVE_CRYPTO_0_CFG 23 +#define SLAVE_CNOC_DDRSS 24 +#define SLAVE_ECC_CFG 25 +#define SLAVE_EMAC_CFG 26 +#define SLAVE_IMEM_CFG 27 +#define SLAVE_IPA_CFG 28 +#define SLAVE_CNOC_MSS 29 +#define SLAVE_PCIE_PARF 30 +#define SLAVE_PDM 31 +#define SLAVE_PRNG 32 +#define SLAVE_QDSS_CFG 33 +#define SLAVE_QPIC 34 +#define SLAVE_SDCC_1 35 +#define SLAVE_SNOC_CFG 36 +#define SLAVE_SPMI_FETCHER 37 +#define SLAVE_SPMI_VGI_COEX 38 +#define SLAVE_TCSR 39 +#define SLAVE_TLMM 40 +#define SLAVE_USB3 41 +#define SLAVE_USB3_PHY_CFG 42 +#define SLAVE_ANOC_SNOC 43 +#define SLAVE_SNOC_MEM_NOC_GC 44 +#define SLAVE_OCIMEM 45 +#define SLAVE_SERVICE_SNOC 46 +#define SLAVE_PCIE_0 47 +#define SLAVE_QDSS_STM 48 +#define SLAVE_TCU 49 + +#define MASTER_IPA_CORE 0 +#define SLAVE_IPA_CORE 1 + +#endif -- cgit v1.2.3 From 622106190175dbac2b0b0ee7d4275c474e5fe051 Mon Sep 17 00:00:00 2001 From: John Garry Date: Wed, 6 Jan 2021 21:35:07 +0800 Subject: iova: Delete copy_reserved_iova() Since commit c588072bba6b ("iommu/vt-d: Convert intel iommu driver to the iommu ops"), function copy_reserved_iova() is not referenced, so delete it. Signed-off-by: John Garry Acked-by: Will Deacon Link: https://lore.kernel.org/r/1609940111-28563-3-git-send-email-john.garry@huawei.com Signed-off-by: Joerg Roedel --- drivers/iommu/iova.c | 30 ------------------------------ include/linux/iova.h | 6 ------ 2 files changed, 36 deletions(-) (limited to 'include') diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c index 5f2caa95c1f0..9b114cd886d5 100644 --- a/drivers/iommu/iova.c +++ b/drivers/iommu/iova.c @@ -710,36 +710,6 @@ finish: } EXPORT_SYMBOL_GPL(reserve_iova); -/** - * copy_reserved_iova - copies the reserved between domains - * @from: - source domain from where to copy - * @to: - destination domin where to copy - * This function copies reserved iova's from one domain to - * other. - */ -void -copy_reserved_iova(struct iova_domain *from, struct iova_domain *to) -{ - unsigned long flags; - struct rb_node *node; - - spin_lock_irqsave(&from->iova_rbtree_lock, flags); - for (node = rb_first(&from->rbroot); node; node = rb_next(node)) { - struct iova *iova = rb_entry(node, struct iova, node); - struct iova *new_iova; - - if (iova->pfn_lo == IOVA_ANCHOR) - continue; - - new_iova = reserve_iova(to, iova->pfn_lo, iova->pfn_hi); - if (!new_iova) - pr_err("Reserve iova range %lx@%lx failed\n", - iova->pfn_lo, iova->pfn_lo); - } - spin_unlock_irqrestore(&from->iova_rbtree_lock, flags); -} -EXPORT_SYMBOL_GPL(copy_reserved_iova); - /* * Magazine caches for IOVA ranges. For an introduction to magazines, * see the USENIX 2001 paper "Magazines and Vmem: Extending the Slab diff --git a/include/linux/iova.h b/include/linux/iova.h index 2b76e0be1c5b..c834c01c0a5b 100644 --- a/include/linux/iova.h +++ b/include/linux/iova.h @@ -150,7 +150,6 @@ unsigned long alloc_iova_fast(struct iova_domain *iovad, unsigned long size, unsigned long limit_pfn, bool flush_rcache); struct iova *reserve_iova(struct iova_domain *iovad, unsigned long pfn_lo, unsigned long pfn_hi); -void copy_reserved_iova(struct iova_domain *from, struct iova_domain *to); void init_iova_domain(struct iova_domain *iovad, unsigned long granule, unsigned long start_pfn); int init_iova_flush_queue(struct iova_domain *iovad, @@ -211,11 +210,6 @@ static inline struct iova *reserve_iova(struct iova_domain *iovad, return NULL; } -static inline void copy_reserved_iova(struct iova_domain *from, - struct iova_domain *to) -{ -} - static inline void init_iova_domain(struct iova_domain *iovad, unsigned long granule, unsigned long start_pfn) -- cgit v1.2.3 From ab0a7119ba67be9e377b195d2b9baa9fb8b3b53e Mon Sep 17 00:00:00 2001 From: John Garry Date: Wed, 6 Jan 2021 21:35:10 +0800 Subject: iommu: Delete iommu_domain_window_disable() Function iommu_domain_window_disable() is not referenced in the tree, so delete it. Signed-off-by: John Garry Acked-by: Will Deacon Link: https://lore.kernel.org/r/1609940111-28563-6-git-send-email-john.garry@huawei.com Signed-off-by: Joerg Roedel --- drivers/iommu/iommu.c | 9 --------- include/linux/iommu.h | 6 ------ 2 files changed, 15 deletions(-) (limited to 'include') diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 4f4edb087ce6..20201ef97b8f 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -2598,15 +2598,6 @@ int iommu_domain_window_enable(struct iommu_domain *domain, u32 wnd_nr, } EXPORT_SYMBOL_GPL(iommu_domain_window_enable); -void iommu_domain_window_disable(struct iommu_domain *domain, u32 wnd_nr) -{ - if (unlikely(domain->ops->domain_window_disable == NULL)) - return; - - return domain->ops->domain_window_disable(domain, wnd_nr); -} -EXPORT_SYMBOL_GPL(iommu_domain_window_disable); - /** * report_iommu_fault() - report about an IOMMU fault to the IOMMU framework * @domain: the iommu domain where the fault has happened diff --git a/include/linux/iommu.h b/include/linux/iommu.h index b3f0e2018c62..72059fcfa108 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -514,7 +514,6 @@ extern int iommu_domain_set_attr(struct iommu_domain *domain, enum iommu_attr, extern int iommu_domain_window_enable(struct iommu_domain *domain, u32 wnd_nr, phys_addr_t offset, u64 size, int prot); -extern void iommu_domain_window_disable(struct iommu_domain *domain, u32 wnd_nr); extern int report_iommu_fault(struct iommu_domain *domain, struct device *dev, unsigned long iova, int flags); @@ -746,11 +745,6 @@ static inline int iommu_domain_window_enable(struct iommu_domain *domain, return -ENODEV; } -static inline void iommu_domain_window_disable(struct iommu_domain *domain, - u32 wnd_nr) -{ -} - static inline phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova) { return 0; -- cgit v1.2.3 From 262948f8ba573dc9c61650df8f23eaea7d43bc61 Mon Sep 17 00:00:00 2001 From: John Garry Date: Wed, 6 Jan 2021 21:35:11 +0800 Subject: iommu: Delete iommu_dev_has_feature() Function iommu_dev_has_feature() has never been referenced in the tree, and there does not appear to be anything coming soon to use it, so delete it. Signed-off-by: John Garry Acked-by: Will Deacon Link: https://lore.kernel.org/r/1609940111-28563-7-git-send-email-john.garry@huawei.com Signed-off-by: Joerg Roedel --- drivers/iommu/iommu.c | 11 ----------- include/linux/iommu.h | 7 ------- 2 files changed, 18 deletions(-) (limited to 'include') diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 20201ef97b8f..91f7871f5a37 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -2853,17 +2853,6 @@ EXPORT_SYMBOL_GPL(iommu_fwspec_add_ids); /* * Per device IOMMU features. */ -bool iommu_dev_has_feature(struct device *dev, enum iommu_dev_features feat) -{ - const struct iommu_ops *ops = dev->bus->iommu_ops; - - if (ops && ops->dev_has_feat) - return ops->dev_has_feat(dev, feat); - - return false; -} -EXPORT_SYMBOL_GPL(iommu_dev_has_feature); - int iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features feat) { const struct iommu_ops *ops = dev->bus->iommu_ops; diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 72059fcfa108..91d94c014f47 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -626,7 +626,6 @@ static inline void dev_iommu_priv_set(struct device *dev, void *priv) int iommu_probe_device(struct device *dev); void iommu_release_device(struct device *dev); -bool iommu_dev_has_feature(struct device *dev, enum iommu_dev_features f); int iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features f); int iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features f); bool iommu_dev_feature_enabled(struct device *dev, enum iommu_dev_features f); @@ -975,12 +974,6 @@ const struct iommu_ops *iommu_ops_from_fwnode(struct fwnode_handle *fwnode) return NULL; } -static inline bool -iommu_dev_has_feature(struct device *dev, enum iommu_dev_features feat) -{ - return false; -} - static inline bool iommu_dev_feature_enabled(struct device *dev, enum iommu_dev_features feat) { -- cgit v1.2.3 From 2ebbd25873cef06f739489fd8ff9f707a3dfa2fa Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Thu, 7 Jan 2021 20:29:04 +0800 Subject: iommu: Add iova and size as parameters in iotlb_sync_map iotlb_sync_map allow IOMMU drivers tlb sync after completing the whole mapping. This patch adds iova and size as the parameters in it. then the IOMMU driver could flush tlb with the whole range once after iova mapping to improve performance. Signed-off-by: Yong Wu Reviewed-by: Robin Murphy Acked-by: Will Deacon Link: https://lore.kernel.org/r/20210107122909.16317-3-yong.wu@mediatek.com Signed-off-by: Will Deacon --- drivers/iommu/iommu.c | 4 ++-- drivers/iommu/tegra-gart.c | 7 +++++-- include/linux/iommu.h | 3 ++- 3 files changed, 9 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index c304a6a30d42..3d099a31ddca 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -2443,7 +2443,7 @@ static int _iommu_map(struct iommu_domain *domain, unsigned long iova, ret = __iommu_map(domain, iova, paddr, size, prot, GFP_KERNEL); if (ret == 0 && ops->iotlb_sync_map) - ops->iotlb_sync_map(domain); + ops->iotlb_sync_map(domain, iova, size); return ret; } @@ -2575,7 +2575,7 @@ static size_t __iommu_map_sg(struct iommu_domain *domain, unsigned long iova, } if (ops->iotlb_sync_map) - ops->iotlb_sync_map(domain); + ops->iotlb_sync_map(domain, iova, mapped); return mapped; out_err: diff --git a/drivers/iommu/tegra-gart.c b/drivers/iommu/tegra-gart.c index fac720273889..05e8e19b8269 100644 --- a/drivers/iommu/tegra-gart.c +++ b/drivers/iommu/tegra-gart.c @@ -261,7 +261,8 @@ static int gart_iommu_of_xlate(struct device *dev, return 0; } -static void gart_iommu_sync_map(struct iommu_domain *domain) +static void gart_iommu_sync_map(struct iommu_domain *domain, unsigned long iova, + size_t size) { FLUSH_GART_REGS(gart_handle); } @@ -269,7 +270,9 @@ static void gart_iommu_sync_map(struct iommu_domain *domain) static void gart_iommu_sync(struct iommu_domain *domain, struct iommu_iotlb_gather *gather) { - gart_iommu_sync_map(domain); + size_t length = gather->end - gather->start; + + gart_iommu_sync_map(domain, gather->start, length); } static const struct iommu_ops gart_iommu_ops = { diff --git a/include/linux/iommu.h b/include/linux/iommu.h index b3f0e2018c62..9ce0aa9e236b 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -246,7 +246,8 @@ struct iommu_ops { size_t (*unmap)(struct iommu_domain *domain, unsigned long iova, size_t size, struct iommu_iotlb_gather *iotlb_gather); void (*flush_iotlb_all)(struct iommu_domain *domain); - void (*iotlb_sync_map)(struct iommu_domain *domain); + void (*iotlb_sync_map)(struct iommu_domain *domain, unsigned long iova, + size_t size); void (*iotlb_sync)(struct iommu_domain *domain, struct iommu_iotlb_gather *iotlb_gather); phys_addr_t (*iova_to_phys)(struct iommu_domain *domain, dma_addr_t iova); -- cgit v1.2.3 From 862c3715de8f3e5350489240c951d697f04bd8c9 Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Thu, 7 Jan 2021 20:29:06 +0800 Subject: iommu: Switch gather->end to the inclusive end Currently gather->end is "unsigned long" which may be overflow in arch32 in the corner case: 0xfff00000 + 0x100000(iova + size). Although it doesn't affect the size(end - start), it affects the checking "gather->end < end" This patch changes this "end" to the real end address (end = start + size - 1). Correspondingly, update the length to "end - start + 1". Fixes: a7d20dc19d9e ("iommu: Introduce struct iommu_iotlb_gather for batching TLB flushes") Signed-off-by: Yong Wu Reviewed-by: Robin Murphy Acked-by: Will Deacon Link: https://lore.kernel.org/r/20210107122909.16317-5-yong.wu@mediatek.com Signed-off-by: Will Deacon --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 2 +- drivers/iommu/mtk_iommu.c | 2 +- drivers/iommu/tegra-gart.c | 2 +- include/linux/iommu.h | 4 ++-- 4 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index 8ca7415d785d..c70d6e79f534 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -2280,7 +2280,7 @@ static void arm_smmu_iotlb_sync(struct iommu_domain *domain, { struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); - arm_smmu_tlb_inv_range(gather->start, gather->end - gather->start, + arm_smmu_tlb_inv_range(gather->start, gather->end - gather->start + 1, gather->pgsize, true, smmu_domain); } diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index f579fc21971e..66a00a2cb445 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -443,7 +443,7 @@ static void mtk_iommu_iotlb_sync(struct iommu_domain *domain, struct iommu_iotlb_gather *gather) { struct mtk_iommu_data *data = mtk_iommu_get_m4u_data(); - size_t length = gather->end - gather->start; + size_t length = gather->end - gather->start + 1; if (gather->start == ULONG_MAX) return; diff --git a/drivers/iommu/tegra-gart.c b/drivers/iommu/tegra-gart.c index 05e8e19b8269..6f130e51f072 100644 --- a/drivers/iommu/tegra-gart.c +++ b/drivers/iommu/tegra-gart.c @@ -270,7 +270,7 @@ static void gart_iommu_sync_map(struct iommu_domain *domain, unsigned long iova, static void gart_iommu_sync(struct iommu_domain *domain, struct iommu_iotlb_gather *gather) { - size_t length = gather->end - gather->start; + size_t length = gather->end - gather->start + 1; gart_iommu_sync_map(domain, gather->start, length); } diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 9ce0aa9e236b..ae8eddd4621b 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -170,7 +170,7 @@ enum iommu_dev_features { * struct iommu_iotlb_gather - Range information for a pending IOTLB flush * * @start: IOVA representing the start of the range to be flushed - * @end: IOVA representing the end of the range to be flushed (exclusive) + * @end: IOVA representing the end of the range to be flushed (inclusive) * @pgsize: The interval at which to perform the flush * * This structure is intended to be updated by multiple calls to the @@ -539,7 +539,7 @@ static inline void iommu_iotlb_gather_add_page(struct iommu_domain *domain, struct iommu_iotlb_gather *gather, unsigned long iova, size_t size) { - unsigned long start = iova, end = start + size; + unsigned long start = iova, end = start + size - 1; /* * If the new page is disjoint from the current range or is mapped at -- cgit v1.2.3 From 77e0992aee4e980e8c553e512a5dfa3e704cf030 Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Thu, 7 Jan 2021 20:29:07 +0800 Subject: iommu/io-pgtable: Allow io_pgtable_tlb ops optional This patch allows io_pgtable_tlb ops could be null since the IOMMU drivers may use the tlb ops from iommu framework. Signed-off-by: Yong Wu Reviewed-by: Robin Murphy Acked-by: Will Deacon Link: https://lore.kernel.org/r/20210107122909.16317-6-yong.wu@mediatek.com Signed-off-by: Will Deacon --- include/linux/io-pgtable.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index ea727eb1a1a9..2a5686ca2ba3 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -214,14 +214,16 @@ struct io_pgtable_domain_attr { static inline void io_pgtable_tlb_flush_all(struct io_pgtable *iop) { - iop->cfg.tlb->tlb_flush_all(iop->cookie); + if (iop->cfg.tlb && iop->cfg.tlb->tlb_flush_all) + iop->cfg.tlb->tlb_flush_all(iop->cookie); } static inline void io_pgtable_tlb_flush_walk(struct io_pgtable *iop, unsigned long iova, size_t size, size_t granule) { - iop->cfg.tlb->tlb_flush_walk(iova, size, granule, iop->cookie); + if (iop->cfg.tlb && iop->cfg.tlb->tlb_flush_walk) + iop->cfg.tlb->tlb_flush_walk(iova, size, granule, iop->cookie); } static inline void @@ -229,7 +231,7 @@ io_pgtable_tlb_add_page(struct io_pgtable *iop, struct iommu_iotlb_gather * gather, unsigned long iova, size_t granule) { - if (iop->cfg.tlb->tlb_add_page) + if (iop->cfg.tlb && iop->cfg.tlb->tlb_add_page) iop->cfg.tlb->tlb_add_page(gather, iova, granule, iop->cookie); } -- cgit v1.2.3 From 8ba59e9dee31246fc34b4d4bec032093e9c06510 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 22 Jan 2021 13:43:58 +0200 Subject: misc: pti: Remove driver for deprecated platform Intel Moorestown and Medfield are quite old Intel Atom based 32-bit platforms, which were in limited use in some Android phones, tablets and consumer electronics more than eight years ago. There are no bugs or problems ever reported outside from Intel for breaking any of that platforms for years. It seems no real users exists who run more or less fresh kernel on it. The commit 05f4434bc130 ("ASoC: Intel: remove mfld_machine") also in align with this theory. Due to above and to reduce a burden of supporting outdated drivers we remove the support of outdated platforms completely. Cc: Alexander Shishkin Acked-by: Linus Walleij Acked-by: Arnd Bergmann Acked-by: Alexander Shishkin Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20210122114358.39299-1-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- Documentation/driver-api/pti_intel_mid.rst | 108 ---- drivers/misc/Kconfig | 13 - drivers/misc/Makefile | 1 - drivers/misc/pti.c | 978 ----------------------------- drivers/tty/Makefile | 2 - drivers/tty/n_tracerouter.c | 233 ------- drivers/tty/n_tracesink.c | 228 ------- drivers/tty/n_tracesink.h | 26 - include/linux/intel-pti.h | 35 -- 9 files changed, 1624 deletions(-) delete mode 100644 Documentation/driver-api/pti_intel_mid.rst delete mode 100644 drivers/misc/pti.c delete mode 100644 drivers/tty/n_tracerouter.c delete mode 100644 drivers/tty/n_tracesink.c delete mode 100644 drivers/tty/n_tracesink.h delete mode 100644 include/linux/intel-pti.h (limited to 'include') diff --git a/Documentation/driver-api/pti_intel_mid.rst b/Documentation/driver-api/pti_intel_mid.rst deleted file mode 100644 index bacc2a4ee89f..000000000000 --- a/Documentation/driver-api/pti_intel_mid.rst +++ /dev/null @@ -1,108 +0,0 @@ -.. SPDX-License-Identifier: GPL-2.0 - -============= -Intel MID PTI -============= - -The Intel MID PTI project is HW implemented in Intel Atom -system-on-a-chip designs based on the Parallel Trace -Interface for MIPI P1149.7 cJTAG standard. The kernel solution -for this platform involves the following files:: - - ./include/linux/pti.h - ./drivers/.../n_tracesink.h - ./drivers/.../n_tracerouter.c - ./drivers/.../n_tracesink.c - ./drivers/.../pti.c - -pti.c is the driver that enables various debugging features -popular on platforms from certain mobile manufacturers. -n_tracerouter.c and n_tracesink.c allow extra system information to -be collected and routed to the pti driver, such as trace -debugging data from a modem. Although n_tracerouter -and n_tracesink are a part of the complete PTI solution, -these two line disciplines can work separately from -pti.c and route any data stream from one /dev/tty node -to another /dev/tty node via kernel-space. This provides -a stable, reliable connection that will not break unless -the user-space application shuts down (plus avoids -kernel->user->kernel context switch overheads of routing -data). - -An example debugging usage for this driver system: - - * Hook /dev/ttyPTI0 to syslogd. Opening this port will also start - a console device to further capture debugging messages to PTI. - * Hook /dev/ttyPTI1 to modem debugging data to write to PTI HW. - This is where n_tracerouter and n_tracesink are used. - * Hook /dev/pti to a user-level debugging application for writing - to PTI HW. - * `Use mipi_` Kernel Driver API in other device drivers for - debugging to PTI by first requesting a PTI write address via - mipi_request_masterchannel(1). - -Below is example pseudo-code on how a 'privileged' application -can hook up n_tracerouter and n_tracesink to any tty on -a system. 'Privileged' means the application has enough -privileges to successfully manipulate the ldisc drivers -but is not just blindly executing as 'root'. Keep in mind -the use of ioctl(,TIOCSETD,) is not specific to the n_tracerouter -and n_tracesink line discpline drivers but is a generic -operation for a program to use a line discpline driver -on a tty port other than the default n_tty: - -.. code-block:: c - - /////////// To hook up n_tracerouter and n_tracesink ///////// - - // Note that n_tracerouter depends on n_tracesink. - #include - #define ONE_TTY "/dev/ttyOne" - #define TWO_TTY "/dev/ttyTwo" - - // needed global to hand onto ldisc connection - static int g_fd_source = -1; - static int g_fd_sink = -1; - - // these two vars used to grab LDISC values from loaded ldisc drivers - // in OS. Look at /proc/tty/ldiscs to get the right numbers from - // the ldiscs loaded in the system. - int source_ldisc_num, sink_ldisc_num = -1; - int retval; - - g_fd_source = open(ONE_TTY, O_RDWR); // must be R/W - g_fd_sink = open(TWO_TTY, O_RDWR); // must be R/W - - if (g_fd_source <= 0) || (g_fd_sink <= 0) { - // doubt you'll want to use these exact error lines of code - printf("Error on open(). errno: %d\n",errno); - return errno; - } - - retval = ioctl(g_fd_sink, TIOCSETD, &sink_ldisc_num); - if (retval < 0) { - printf("Error on ioctl(). errno: %d\n", errno); - return errno; - } - - retval = ioctl(g_fd_source, TIOCSETD, &source_ldisc_num); - if (retval < 0) { - printf("Error on ioctl(). errno: %d\n", errno); - return errno; - } - - /////////// To disconnect n_tracerouter and n_tracesink //////// - - // First make sure data through the ldiscs has stopped. - - // Second, disconnect ldiscs. This provides a - // little cleaner shutdown on tty stack. - sink_ldisc_num = 0; - source_ldisc_num = 0; - ioctl(g_fd_uart, TIOCSETD, &sink_ldisc_num); - ioctl(g_fd_gadget, TIOCSETD, &source_ldisc_num); - - // Three, program closes connection, and cleanup: - close(g_fd_uart); - close(g_fd_gadget); - g_fd_uart = g_fd_gadget = NULL; diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig index 8085213913cc..f532c59bb59b 100644 --- a/drivers/misc/Kconfig +++ b/drivers/misc/Kconfig @@ -104,19 +104,6 @@ config PHANTOM If you choose to build module, its name will be phantom. If unsure, say N here. -config INTEL_MID_PTI - tristate "Parallel Trace Interface for MIPI P1149.7 cJTAG standard" - depends on PCI && TTY && (X86_INTEL_MID || COMPILE_TEST) - help - The PTI (Parallel Trace Interface) driver directs - trace data routed from various parts in the system out - through an Intel Penwell PTI port and out of the mobile - device for analysis with a debugging tool (Lauterbach or Fido). - - You should select this driver if the target kernel is meant for - an Intel Atom (non-netbook) mobile device containing a MIPI - P1149.7 standard implementation. - config TIFM_CORE tristate "TI Flash Media interface support" depends on PCI diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile index 456aa8a4c896..99b6f15a3c70 100644 --- a/drivers/misc/Makefile +++ b/drivers/misc/Makefile @@ -8,7 +8,6 @@ obj-$(CONFIG_IBMVMC) += ibmvmc.o obj-$(CONFIG_AD525X_DPOT) += ad525x_dpot.o obj-$(CONFIG_AD525X_DPOT_I2C) += ad525x_dpot-i2c.o obj-$(CONFIG_AD525X_DPOT_SPI) += ad525x_dpot-spi.o -obj-$(CONFIG_INTEL_MID_PTI) += pti.o obj-$(CONFIG_ATMEL_SSC) += atmel-ssc.o obj-$(CONFIG_DUMMY_IRQ) += dummy-irq.o obj-$(CONFIG_ICS932S401) += ics932s401.o diff --git a/drivers/misc/pti.c b/drivers/misc/pti.c deleted file mode 100644 index 7236ae527b19..000000000000 --- a/drivers/misc/pti.c +++ /dev/null @@ -1,978 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * pti.c - PTI driver for cJTAG data extration - * - * Copyright (C) Intel 2010 - * - * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - * - * The PTI (Parallel Trace Interface) driver directs trace data routed from - * various parts in the system out through the Intel Penwell PTI port and - * out of the mobile device for analysis with a debugging tool - * (Lauterbach, Fido). This is part of a solution for the MIPI P1149.7, - * compact JTAG, standard. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#define DRIVERNAME "pti" -#define PCINAME "pciPTI" -#define TTYNAME "ttyPTI" -#define CHARNAME "pti" -#define PTITTY_MINOR_START 0 -#define PTITTY_MINOR_NUM 2 -#define MAX_APP_IDS 16 /* 128 channel ids / u8 bit size */ -#define MAX_OS_IDS 16 /* 128 channel ids / u8 bit size */ -#define MAX_MODEM_IDS 16 /* 128 channel ids / u8 bit size */ -#define MODEM_BASE_ID 71 /* modem master ID address */ -#define CONTROL_ID 72 /* control master ID address */ -#define CONSOLE_ID 73 /* console master ID address */ -#define OS_BASE_ID 74 /* base OS master ID address */ -#define APP_BASE_ID 80 /* base App master ID address */ -#define CONTROL_FRAME_LEN 32 /* PTI control frame maximum size */ -#define USER_COPY_SIZE 8192 /* 8Kb buffer for user space copy */ -#define APERTURE_14 0x3800000 /* offset to first OS write addr */ -#define APERTURE_LEN 0x400000 /* address length */ - -struct pti_tty { - struct pti_masterchannel *mc; -}; - -struct pti_dev { - struct tty_port port[PTITTY_MINOR_NUM]; - unsigned long pti_addr; - unsigned long aperture_base; - void __iomem *pti_ioaddr; - u8 ia_app[MAX_APP_IDS]; - u8 ia_os[MAX_OS_IDS]; - u8 ia_modem[MAX_MODEM_IDS]; -}; - -/* - * This protects access to ia_app, ia_os, and ia_modem, - * which keeps track of channels allocated in - * an aperture write id. - */ -static DEFINE_MUTEX(alloclock); - -static const struct pci_device_id pci_ids[] = { - {PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x82B)}, - {0} -}; - -static struct tty_driver *pti_tty_driver; -static struct pti_dev *drv_data; - -static unsigned int pti_console_channel; -static unsigned int pti_control_channel; - -/** - * pti_write_to_aperture()- The private write function to PTI HW. - * - * @mc: The 'aperture'. It's part of a write address that holds - * a master and channel ID. - * @buf: Data being written to the HW that will ultimately be seen - * in a debugging tool (Fido, Lauterbach). - * @len: Size of buffer. - * - * Since each aperture is specified by a unique - * master/channel ID, no two processes will be writing - * to the same aperture at the same time so no lock is required. The - * PTI-Output agent will send these out in the order that they arrived, and - * thus, it will intermix these messages. The debug tool can then later - * regroup the appropriate message segments together reconstituting each - * message. - */ -static void pti_write_to_aperture(struct pti_masterchannel *mc, - u8 *buf, - int len) -{ - int dwordcnt; - int final; - int i; - u32 ptiword; - u32 __iomem *aperture; - u8 *p = buf; - - /* - * calculate the aperture offset from the base using the master and - * channel id's. - */ - aperture = drv_data->pti_ioaddr + (mc->master << 15) - + (mc->channel << 8); - - dwordcnt = len >> 2; - final = len - (dwordcnt << 2); /* final = trailing bytes */ - if (final == 0 && dwordcnt != 0) { /* always need a final dword */ - final += 4; - dwordcnt--; - } - - for (i = 0; i < dwordcnt; i++) { - ptiword = be32_to_cpu(*(u32 *)p); - p += 4; - iowrite32(ptiword, aperture); - } - - aperture += PTI_LASTDWORD_DTS; /* adding DTS signals that is EOM */ - - ptiword = 0; - for (i = 0; i < final; i++) - ptiword |= *p++ << (24-(8*i)); - - iowrite32(ptiword, aperture); - return; -} - -/** - * pti_control_frame_built_and_sent()- control frame build and send function. - * - * @mc: The master / channel structure on which the function - * built a control frame. - * @thread_name: The thread name associated with the master / channel or - * 'NULL' if using the 'current' global variable. - * - * To be able to post process the PTI contents on host side, a control frame - * is added before sending any PTI content. So the host side knows on - * each PTI frame the name of the thread using a dedicated master / channel. - * The thread name is retrieved from 'current' global variable if 'thread_name' - * is 'NULL', else it is retrieved from 'thread_name' parameter. - * This function builds this frame and sends it to a master ID CONTROL_ID. - * The overhead is only 32 bytes since the driver only writes to HW - * in 32 byte chunks. - */ -static void pti_control_frame_built_and_sent(struct pti_masterchannel *mc, - const char *thread_name) -{ - /* - * Since we access the comm member in current's task_struct, we only - * need to be as large as what 'comm' in that structure is. - */ - char comm[TASK_COMM_LEN]; - struct pti_masterchannel mccontrol = {.master = CONTROL_ID, - .channel = 0}; - const char *thread_name_p; - const char *control_format = "%3d %3d %s"; - u8 control_frame[CONTROL_FRAME_LEN]; - - if (!thread_name) { - if (!in_interrupt()) - get_task_comm(comm, current); - else - strncpy(comm, "Interrupt", TASK_COMM_LEN); - - /* Absolutely ensure our buffer is zero terminated. */ - comm[TASK_COMM_LEN-1] = 0; - thread_name_p = comm; - } else { - thread_name_p = thread_name; - } - - mccontrol.channel = pti_control_channel; - pti_control_channel = (pti_control_channel + 1) & 0x7f; - - snprintf(control_frame, CONTROL_FRAME_LEN, control_format, mc->master, - mc->channel, thread_name_p); - pti_write_to_aperture(&mccontrol, control_frame, strlen(control_frame)); -} - -/** - * pti_write_full_frame_to_aperture()- high level function to - * write to PTI. - * - * @mc: The 'aperture'. It's part of a write address that holds - * a master and channel ID. - * @buf: Data being written to the HW that will ultimately be seen - * in a debugging tool (Fido, Lauterbach). - * @len: Size of buffer. - * - * All threads sending data (either console, user space application, ...) - * are calling the high level function to write to PTI meaning that it is - * possible to add a control frame before sending the content. - */ -static void pti_write_full_frame_to_aperture(struct pti_masterchannel *mc, - const unsigned char *buf, - int len) -{ - pti_control_frame_built_and_sent(mc, NULL); - pti_write_to_aperture(mc, (u8 *)buf, len); -} - -/** - * get_id()- Allocate a master and channel ID. - * - * @id_array: an array of bits representing what channel - * id's are allocated for writing. - * @max_ids: The max amount of available write IDs to use. - * @base_id: The starting SW channel ID, based on the Intel - * PTI arch. - * @thread_name: The thread name associated with the master / channel or - * 'NULL' if using the 'current' global variable. - * - * Returns: - * pti_masterchannel struct with master, channel ID address - * 0 for error - * - * Each bit in the arrays ia_app and ia_os correspond to a master and - * channel id. The bit is one if the id is taken and 0 if free. For - * every master there are 128 channel id's. - */ -static struct pti_masterchannel *get_id(u8 *id_array, - int max_ids, - int base_id, - const char *thread_name) -{ - struct pti_masterchannel *mc; - int i, j, mask; - - mc = kmalloc(sizeof(struct pti_masterchannel), GFP_KERNEL); - if (mc == NULL) - return NULL; - - /* look for a byte with a free bit */ - for (i = 0; i < max_ids; i++) - if (id_array[i] != 0xff) - break; - if (i == max_ids) { - kfree(mc); - return NULL; - } - /* find the bit in the 128 possible channel opportunities */ - mask = 0x80; - for (j = 0; j < 8; j++) { - if ((id_array[i] & mask) == 0) - break; - mask >>= 1; - } - - /* grab it */ - id_array[i] |= mask; - mc->master = base_id; - mc->channel = ((i & 0xf)<<3) + j; - /* write new master Id / channel Id allocation to channel control */ - pti_control_frame_built_and_sent(mc, thread_name); - return mc; -} - -/* - * The following three functions: - * pti_request_mastercahannel(), mipi_release_masterchannel() - * and pti_writedata() are an API for other kernel drivers to - * access PTI. - */ - -/** - * pti_request_masterchannel()- Kernel API function used to allocate - * a master, channel ID address - * to write to PTI HW. - * - * @type: 0- request Application master, channel aperture ID - * write address. - * 1- request OS master, channel aperture ID write - * address. - * 2- request Modem master, channel aperture ID - * write address. - * Other values, error. - * @thread_name: The thread name associated with the master / channel or - * 'NULL' if using the 'current' global variable. - * - * Returns: - * pti_masterchannel struct - * 0 for error - */ -struct pti_masterchannel *pti_request_masterchannel(u8 type, - const char *thread_name) -{ - struct pti_masterchannel *mc; - - mutex_lock(&alloclock); - - switch (type) { - - case 0: - mc = get_id(drv_data->ia_app, MAX_APP_IDS, - APP_BASE_ID, thread_name); - break; - - case 1: - mc = get_id(drv_data->ia_os, MAX_OS_IDS, - OS_BASE_ID, thread_name); - break; - - case 2: - mc = get_id(drv_data->ia_modem, MAX_MODEM_IDS, - MODEM_BASE_ID, thread_name); - break; - default: - mc = NULL; - } - - mutex_unlock(&alloclock); - return mc; -} -EXPORT_SYMBOL_GPL(pti_request_masterchannel); - -/** - * pti_release_masterchannel()- Kernel API function used to release - * a master, channel ID address - * used to write to PTI HW. - * - * @mc: master, channel apeture ID address to be released. This - * will de-allocate the structure via kfree(). - */ -void pti_release_masterchannel(struct pti_masterchannel *mc) -{ - u8 master, channel, i; - - mutex_lock(&alloclock); - - if (mc) { - master = mc->master; - channel = mc->channel; - - if (master == APP_BASE_ID) { - i = channel >> 3; - drv_data->ia_app[i] &= ~(0x80>>(channel & 0x7)); - } else if (master == OS_BASE_ID) { - i = channel >> 3; - drv_data->ia_os[i] &= ~(0x80>>(channel & 0x7)); - } else { - i = channel >> 3; - drv_data->ia_modem[i] &= ~(0x80>>(channel & 0x7)); - } - - kfree(mc); - } - - mutex_unlock(&alloclock); -} -EXPORT_SYMBOL_GPL(pti_release_masterchannel); - -/** - * pti_writedata()- Kernel API function used to write trace - * debugging data to PTI HW. - * - * @mc: Master, channel aperture ID address to write to. - * Null value will return with no write occurring. - * @buf: Trace debuging data to write to the PTI HW. - * Null value will return with no write occurring. - * @count: Size of buf. Value of 0 or a negative number will - * return with no write occuring. - */ -void pti_writedata(struct pti_masterchannel *mc, u8 *buf, int count) -{ - /* - * since this function is exported, this is treated like an - * API function, thus, all parameters should - * be checked for validity. - */ - if ((mc != NULL) && (buf != NULL) && (count > 0)) - pti_write_to_aperture(mc, buf, count); - return; -} -EXPORT_SYMBOL_GPL(pti_writedata); - -/* - * for the tty_driver_*() basic function descriptions, see tty_driver.h. - * Specific header comments made for PTI-related specifics. - */ - -/** - * pti_tty_driver_open()- Open an Application master, channel aperture - * ID to the PTI device via tty device. - * - * @tty: tty interface. - * @filp: filp interface pased to tty_port_open() call. - * - * Returns: - * int, 0 for success - * otherwise, fail value - * - * The main purpose of using the tty device interface is for - * each tty port to have a unique PTI write aperture. In an - * example use case, ttyPTI0 gets syslogd and an APP aperture - * ID and ttyPTI1 is where the n_tracesink ldisc hooks to route - * modem messages into PTI. Modem trace data does not have to - * go to ttyPTI1, but ttyPTI0 and ttyPTI1 do need to be distinct - * master IDs. These messages go through the PTI HW and out of - * the handheld platform and to the Fido/Lauterbach device. - */ -static int pti_tty_driver_open(struct tty_struct *tty, struct file *filp) -{ - /* - * we actually want to allocate a new channel per open, per - * system arch. HW gives more than plenty channels for a single - * system task to have its own channel to write trace data. This - * also removes a locking requirement for the actual write - * procedure. - */ - return tty_port_open(tty->port, tty, filp); -} - -/** - * pti_tty_driver_close()- close tty device and release Application - * master, channel aperture ID to the PTI device via tty device. - * - * @tty: tty interface. - * @filp: filp interface pased to tty_port_close() call. - * - * The main purpose of using the tty device interface is to route - * syslog daemon messages to the PTI HW and out of the handheld platform - * and to the Fido/Lauterbach device. - */ -static void pti_tty_driver_close(struct tty_struct *tty, struct file *filp) -{ - tty_port_close(tty->port, tty, filp); -} - -/** - * pti_tty_install()- Used to set up specific master-channels - * to tty ports for organizational purposes when - * tracing viewed from debuging tools. - * - * @driver: tty driver information. - * @tty: tty struct containing pti information. - * - * Returns: - * 0 for success - * otherwise, error - */ -static int pti_tty_install(struct tty_driver *driver, struct tty_struct *tty) -{ - int idx = tty->index; - struct pti_tty *pti_tty_data; - int ret = tty_standard_install(driver, tty); - - if (ret == 0) { - pti_tty_data = kmalloc(sizeof(struct pti_tty), GFP_KERNEL); - if (pti_tty_data == NULL) - return -ENOMEM; - - if (idx == PTITTY_MINOR_START) - pti_tty_data->mc = pti_request_masterchannel(0, NULL); - else - pti_tty_data->mc = pti_request_masterchannel(2, NULL); - - if (pti_tty_data->mc == NULL) { - kfree(pti_tty_data); - return -ENXIO; - } - tty->driver_data = pti_tty_data; - } - - return ret; -} - -/** - * pti_tty_cleanup()- Used to de-allocate master-channel resources - * tied to tty's of this driver. - * - * @tty: tty struct containing pti information. - */ -static void pti_tty_cleanup(struct tty_struct *tty) -{ - struct pti_tty *pti_tty_data = tty->driver_data; - if (pti_tty_data == NULL) - return; - pti_release_masterchannel(pti_tty_data->mc); - kfree(pti_tty_data); - tty->driver_data = NULL; -} - -/** - * pti_tty_driver_write()- Write trace debugging data through the char - * interface to the PTI HW. Part of the misc device implementation. - * - * @tty: tty struct containing pti information. - * @buf: trace data to be written. - * @len: # of byte to write. - * - * Returns: - * int, # of bytes written - * otherwise, error - */ -static int pti_tty_driver_write(struct tty_struct *tty, - const unsigned char *buf, int len) -{ - struct pti_tty *pti_tty_data = tty->driver_data; - if ((pti_tty_data != NULL) && (pti_tty_data->mc != NULL)) { - pti_write_to_aperture(pti_tty_data->mc, (u8 *)buf, len); - return len; - } - /* - * we can't write to the pti hardware if the private driver_data - * and the mc address is not there. - */ - else - return -EFAULT; -} - -/** - * pti_tty_write_room()- Always returns 2048. - * - * @tty: contains tty info of the pti driver. - */ -static int pti_tty_write_room(struct tty_struct *tty) -{ - return 2048; -} - -/** - * pti_char_open()- Open an Application master, channel aperture - * ID to the PTI device. Part of the misc device implementation. - * - * @inode: not used. - * @filp: Output- will have a masterchannel struct set containing - * the allocated application PTI aperture write address. - * - * Returns: - * int, 0 for success - * otherwise, a fail value - */ -static int pti_char_open(struct inode *inode, struct file *filp) -{ - struct pti_masterchannel *mc; - - /* - * We really do want to fail immediately if - * pti_request_masterchannel() fails, - * before assigning the value to filp->private_data. - * Slightly easier to debug if this driver needs debugging. - */ - mc = pti_request_masterchannel(0, NULL); - if (mc == NULL) - return -ENOMEM; - filp->private_data = mc; - return 0; -} - -/** - * pti_char_release()- Close a char channel to the PTI device. Part - * of the misc device implementation. - * - * @inode: Not used in this implementaiton. - * @filp: Contains private_data that contains the master, channel - * ID to be released by the PTI device. - * - * Returns: - * always 0 - */ -static int pti_char_release(struct inode *inode, struct file *filp) -{ - pti_release_masterchannel(filp->private_data); - filp->private_data = NULL; - return 0; -} - -/** - * pti_char_write()- Write trace debugging data through the char - * interface to the PTI HW. Part of the misc device implementation. - * - * @filp: Contains private data which is used to obtain - * master, channel write ID. - * @data: trace data to be written. - * @len: # of byte to write. - * @ppose: Not used in this function implementation. - * - * Returns: - * int, # of bytes written - * otherwise, error value - * - * Notes: From side discussions with Alan Cox and experimenting - * with PTI debug HW like Nokia's Fido box and Lauterbach - * devices, 8192 byte write buffer used by USER_COPY_SIZE was - * deemed an appropriate size for this type of usage with - * debugging HW. - */ -static ssize_t pti_char_write(struct file *filp, const char __user *data, - size_t len, loff_t *ppose) -{ - struct pti_masterchannel *mc; - void *kbuf; - const char __user *tmp; - size_t size = USER_COPY_SIZE; - size_t n = 0; - - tmp = data; - mc = filp->private_data; - - kbuf = kmalloc(size, GFP_KERNEL); - if (kbuf == NULL) { - pr_err("%s(%d): buf allocation failed\n", - __func__, __LINE__); - return -ENOMEM; - } - - do { - if (len - n > USER_COPY_SIZE) - size = USER_COPY_SIZE; - else - size = len - n; - - if (copy_from_user(kbuf, tmp, size)) { - kfree(kbuf); - return n ? n : -EFAULT; - } - - pti_write_to_aperture(mc, kbuf, size); - n += size; - tmp += size; - - } while (len > n); - - kfree(kbuf); - return len; -} - -static const struct tty_operations pti_tty_driver_ops = { - .open = pti_tty_driver_open, - .close = pti_tty_driver_close, - .write = pti_tty_driver_write, - .write_room = pti_tty_write_room, - .install = pti_tty_install, - .cleanup = pti_tty_cleanup -}; - -static const struct file_operations pti_char_driver_ops = { - .owner = THIS_MODULE, - .write = pti_char_write, - .open = pti_char_open, - .release = pti_char_release, -}; - -static struct miscdevice pti_char_driver = { - .minor = MISC_DYNAMIC_MINOR, - .name = CHARNAME, - .fops = &pti_char_driver_ops -}; - -/** - * pti_console_write()- Write to the console that has been acquired. - * - * @c: Not used in this implementaiton. - * @buf: Data to be written. - * @len: Length of buf. - */ -static void pti_console_write(struct console *c, const char *buf, unsigned len) -{ - static struct pti_masterchannel mc = {.master = CONSOLE_ID, - .channel = 0}; - - mc.channel = pti_console_channel; - pti_console_channel = (pti_console_channel + 1) & 0x7f; - - pti_write_full_frame_to_aperture(&mc, buf, len); -} - -/** - * pti_console_device()- Return the driver tty structure and set the - * associated index implementation. - * - * @c: Console device of the driver. - * @index: index associated with c. - * - * Returns: - * always value of pti_tty_driver structure when this function - * is called. - */ -static struct tty_driver *pti_console_device(struct console *c, int *index) -{ - *index = c->index; - return pti_tty_driver; -} - -/** - * pti_console_setup()- Initialize console variables used by the driver. - * - * @c: Not used. - * @opts: Not used. - * - * Returns: - * always 0. - */ -static int pti_console_setup(struct console *c, char *opts) -{ - pti_console_channel = 0; - pti_control_channel = 0; - return 0; -} - -/* - * pti_console struct, used to capture OS printk()'s and shift - * out to the PTI device for debugging. This cannot be - * enabled upon boot because of the possibility of eating - * any serial console printk's (race condition discovered). - * The console should be enabled upon when the tty port is - * used for the first time. Since the primary purpose for - * the tty port is to hook up syslog to it, the tty port - * will be open for a really long time. - */ -static struct console pti_console = { - .name = TTYNAME, - .write = pti_console_write, - .device = pti_console_device, - .setup = pti_console_setup, - .flags = CON_PRINTBUFFER, - .index = 0, -}; - -/** - * pti_port_activate()- Used to start/initialize any items upon - * first opening of tty_port(). - * - * @port: The tty port number of the PTI device. - * @tty: The tty struct associated with this device. - * - * Returns: - * always returns 0 - * - * Notes: The primary purpose of the PTI tty port 0 is to hook - * the syslog daemon to it; thus this port will be open for a - * very long time. - */ -static int pti_port_activate(struct tty_port *port, struct tty_struct *tty) -{ - if (port->tty->index == PTITTY_MINOR_START) - console_start(&pti_console); - return 0; -} - -/** - * pti_port_shutdown()- Used to stop/shutdown any items upon the - * last tty port close. - * - * @port: The tty port number of the PTI device. - * - * Notes: The primary purpose of the PTI tty port 0 is to hook - * the syslog daemon to it; thus this port will be open for a - * very long time. - */ -static void pti_port_shutdown(struct tty_port *port) -{ - if (port->tty->index == PTITTY_MINOR_START) - console_stop(&pti_console); -} - -static const struct tty_port_operations tty_port_ops = { - .activate = pti_port_activate, - .shutdown = pti_port_shutdown, -}; - -/* - * Note the _probe() call sets everything up and ties the char and tty - * to successfully detecting the PTI device on the pci bus. - */ - -/** - * pti_pci_probe()- Used to detect pti on the pci bus and set - * things up in the driver. - * - * @pdev: pci_dev struct values for pti. - * @ent: pci_device_id struct for pti driver. - * - * Returns: - * 0 for success - * otherwise, error - */ -static int pti_pci_probe(struct pci_dev *pdev, - const struct pci_device_id *ent) -{ - unsigned int a; - int retval; - int pci_bar = 1; - - dev_dbg(&pdev->dev, "%s %s(%d): PTI PCI ID %04x:%04x\n", __FILE__, - __func__, __LINE__, pdev->vendor, pdev->device); - - retval = misc_register(&pti_char_driver); - if (retval) { - pr_err("%s(%d): CHAR registration failed of pti driver\n", - __func__, __LINE__); - pr_err("%s(%d): Error value returned: %d\n", - __func__, __LINE__, retval); - goto err; - } - - retval = pci_enable_device(pdev); - if (retval != 0) { - dev_err(&pdev->dev, - "%s: pci_enable_device() returned error %d\n", - __func__, retval); - goto err_unreg_misc; - } - - drv_data = kzalloc(sizeof(*drv_data), GFP_KERNEL); - if (drv_data == NULL) { - retval = -ENOMEM; - dev_err(&pdev->dev, - "%s(%d): kmalloc() returned NULL memory.\n", - __func__, __LINE__); - goto err_disable_pci; - } - drv_data->pti_addr = pci_resource_start(pdev, pci_bar); - - retval = pci_request_region(pdev, pci_bar, dev_name(&pdev->dev)); - if (retval != 0) { - dev_err(&pdev->dev, - "%s(%d): pci_request_region() returned error %d\n", - __func__, __LINE__, retval); - goto err_free_dd; - } - drv_data->aperture_base = drv_data->pti_addr+APERTURE_14; - drv_data->pti_ioaddr = - ioremap((u32)drv_data->aperture_base, - APERTURE_LEN); - if (!drv_data->pti_ioaddr) { - retval = -ENOMEM; - goto err_rel_reg; - } - - pci_set_drvdata(pdev, drv_data); - - for (a = 0; a < PTITTY_MINOR_NUM; a++) { - struct tty_port *port = &drv_data->port[a]; - tty_port_init(port); - port->ops = &tty_port_ops; - - tty_port_register_device(port, pti_tty_driver, a, &pdev->dev); - } - - register_console(&pti_console); - - return 0; -err_rel_reg: - pci_release_region(pdev, pci_bar); -err_free_dd: - kfree(drv_data); -err_disable_pci: - pci_disable_device(pdev); -err_unreg_misc: - misc_deregister(&pti_char_driver); -err: - return retval; -} - -/** - * pti_pci_remove()- Driver exit method to remove PTI from - * PCI bus. - * @pdev: variable containing pci info of PTI. - */ -static void pti_pci_remove(struct pci_dev *pdev) -{ - struct pti_dev *drv_data = pci_get_drvdata(pdev); - unsigned int a; - - unregister_console(&pti_console); - - for (a = 0; a < PTITTY_MINOR_NUM; a++) { - tty_unregister_device(pti_tty_driver, a); - tty_port_destroy(&drv_data->port[a]); - } - - iounmap(drv_data->pti_ioaddr); - kfree(drv_data); - pci_release_region(pdev, 1); - pci_disable_device(pdev); - - misc_deregister(&pti_char_driver); -} - -static struct pci_driver pti_pci_driver = { - .name = PCINAME, - .id_table = pci_ids, - .probe = pti_pci_probe, - .remove = pti_pci_remove, -}; - -/** - * pti_init()- Overall entry/init call to the pti driver. - * It starts the registration process with the kernel. - * - * Returns: - * int __init, 0 for success - * otherwise value is an error - * - */ -static int __init pti_init(void) -{ - int retval; - - /* First register module as tty device */ - - pti_tty_driver = alloc_tty_driver(PTITTY_MINOR_NUM); - if (pti_tty_driver == NULL) { - pr_err("%s(%d): Memory allocation failed for ptiTTY driver\n", - __func__, __LINE__); - return -ENOMEM; - } - - pti_tty_driver->driver_name = DRIVERNAME; - pti_tty_driver->name = TTYNAME; - pti_tty_driver->major = 0; - pti_tty_driver->minor_start = PTITTY_MINOR_START; - pti_tty_driver->type = TTY_DRIVER_TYPE_SYSTEM; - pti_tty_driver->subtype = SYSTEM_TYPE_SYSCONS; - pti_tty_driver->flags = TTY_DRIVER_REAL_RAW | - TTY_DRIVER_DYNAMIC_DEV; - pti_tty_driver->init_termios = tty_std_termios; - - tty_set_operations(pti_tty_driver, &pti_tty_driver_ops); - - retval = tty_register_driver(pti_tty_driver); - if (retval) { - pr_err("%s(%d): TTY registration failed of pti driver\n", - __func__, __LINE__); - pr_err("%s(%d): Error value returned: %d\n", - __func__, __LINE__, retval); - - goto put_tty; - } - - retval = pci_register_driver(&pti_pci_driver); - if (retval) { - pr_err("%s(%d): PCI registration failed of pti driver\n", - __func__, __LINE__); - pr_err("%s(%d): Error value returned: %d\n", - __func__, __LINE__, retval); - goto unreg_tty; - } - - return 0; -unreg_tty: - tty_unregister_driver(pti_tty_driver); -put_tty: - put_tty_driver(pti_tty_driver); - pti_tty_driver = NULL; - return retval; -} - -/** - * pti_exit()- Unregisters this module as a tty and pci driver. - */ -static void __exit pti_exit(void) -{ - tty_unregister_driver(pti_tty_driver); - pci_unregister_driver(&pti_pci_driver); - put_tty_driver(pti_tty_driver); -} - -module_init(pti_init); -module_exit(pti_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Ken Mills, Jay Freyensee"); -MODULE_DESCRIPTION("PTI Driver"); - diff --git a/drivers/tty/Makefile b/drivers/tty/Makefile index b3ccae932660..730de6bf048b 100644 --- a/drivers/tty/Makefile +++ b/drivers/tty/Makefile @@ -9,8 +9,6 @@ obj-$(CONFIG_AUDIT) += tty_audit.o obj-$(CONFIG_MAGIC_SYSRQ) += sysrq.o obj-$(CONFIG_N_HDLC) += n_hdlc.o obj-$(CONFIG_N_GSM) += n_gsm.o -obj-$(CONFIG_TRACE_ROUTER) += n_tracerouter.o -obj-$(CONFIG_TRACE_SINK) += n_tracesink.o obj-$(CONFIG_R3964) += n_r3964.o obj-y += vt/ diff --git a/drivers/tty/n_tracerouter.c b/drivers/tty/n_tracerouter.c deleted file mode 100644 index 4479af4d2fa5..000000000000 --- a/drivers/tty/n_tracerouter.c +++ /dev/null @@ -1,233 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * n_tracerouter.c - Trace data router through tty space - * - * Copyright (C) Intel 2011 - * - * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - * - * This trace router uses the Linux line discipline framework to route - * trace data coming from a HW Modem to a PTI (Parallel Trace Module) port. - * The solution is not specific to a HW modem and this line disciple can - * be used to route any stream of data in kernel space. - * This is part of a solution for the P1149.7, compact JTAG, standard. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include "n_tracesink.h" - -/* - * Other ldisc drivers use 65536 which basically means, - * 'I can always accept 64k' and flow control is off. - * This number is deemed appropriate for this driver. - */ -#define RECEIVE_ROOM 65536 -#define DRIVERNAME "n_tracerouter" - -/* - * struct to hold private configuration data for this ldisc. - * opencalled is used to hold if this ldisc has been opened. - * kref_tty holds the tty reference the ldisc sits on top of. - */ -struct tracerouter_data { - u8 opencalled; - struct tty_struct *kref_tty; -}; -static struct tracerouter_data *tr_data; - -/* lock for when tty reference is being used */ -static DEFINE_MUTEX(routelock); - -/** - * n_tracerouter_open() - Called when a tty is opened by a SW entity. - * @tty: terminal device to the ldisc. - * - * Return: - * 0 for success. - * - * Caveats: This should only be opened one time per SW entity. - */ -static int n_tracerouter_open(struct tty_struct *tty) -{ - int retval = -EEXIST; - - mutex_lock(&routelock); - if (tr_data->opencalled == 0) { - - tr_data->kref_tty = tty_kref_get(tty); - if (tr_data->kref_tty == NULL) { - retval = -EFAULT; - } else { - tr_data->opencalled = 1; - tty->disc_data = tr_data; - tty->receive_room = RECEIVE_ROOM; - tty_driver_flush_buffer(tty); - retval = 0; - } - } - mutex_unlock(&routelock); - return retval; -} - -/** - * n_tracerouter_close() - close connection - * @tty: terminal device to the ldisc. - * - * Called when a software entity wants to close a connection. - */ -static void n_tracerouter_close(struct tty_struct *tty) -{ - struct tracerouter_data *tptr = tty->disc_data; - - mutex_lock(&routelock); - WARN_ON(tptr->kref_tty != tr_data->kref_tty); - tty_driver_flush_buffer(tty); - tty_kref_put(tr_data->kref_tty); - tr_data->kref_tty = NULL; - tr_data->opencalled = 0; - tty->disc_data = NULL; - mutex_unlock(&routelock); -} - -/** - * n_tracerouter_read() - read request from user space - * @tty: terminal device passed into the ldisc. - * @file: pointer to open file object. - * @buf: pointer to the data buffer that gets eventually returned. - * @nr: number of bytes of the data buffer that is returned. - * - * function that allows read() functionality in userspace. By default if this - * is not implemented it returns -EIO. This module is functioning like a - * router via n_tracerouter_receivebuf(), and there is no real requirement - * to implement this function. However, an error return value other than - * -EIO should be used just to show that there was an intent not to have - * this function implemented. Return value based on read() man pages. - * - * Return: - * -EINVAL - */ -static ssize_t n_tracerouter_read(struct tty_struct *tty, struct file *file, - unsigned char __user *buf, size_t nr) { - return -EINVAL; -} - -/** - * n_tracerouter_write() - Function that allows write() in userspace. - * @tty: terminal device passed into the ldisc. - * @file: pointer to open file object. - * @buf: pointer to the data buffer that gets eventually returned. - * @nr: number of bytes of the data buffer that is returned. - * - * By default if this is not implemented, it returns -EIO. - * This should not be implemented, ever, because - * 1. this driver is functioning like a router via - * n_tracerouter_receivebuf() - * 2. No writes to HW will ever go through this line discpline driver. - * However, an error return value other than -EIO should be used - * just to show that there was an intent not to have this function - * implemented. Return value based on write() man pages. - * - * Return: - * -EINVAL - */ -static ssize_t n_tracerouter_write(struct tty_struct *tty, struct file *file, - const unsigned char *buf, size_t nr) { - return -EINVAL; -} - -/** - * n_tracerouter_receivebuf() - Routing function for driver. - * @tty: terminal device passed into the ldisc. It's assumed - * tty will never be NULL. - * @cp: buffer, block of characters to be eventually read by - * someone, somewhere (user read() call or some kernel function). - * @fp: flag buffer. - * @count: number of characters (aka, bytes) in cp. - * - * This function takes the input buffer, cp, and passes it to - * an external API function for processing. - */ -static void n_tracerouter_receivebuf(struct tty_struct *tty, - const unsigned char *cp, - char *fp, int count) -{ - mutex_lock(&routelock); - n_tracesink_datadrain((u8 *) cp, count); - mutex_unlock(&routelock); -} - -/* - * Flush buffer is not impelemented as the ldisc has no internal buffering - * so the tty_driver_flush_buffer() is sufficient for this driver's needs. - */ - -static struct tty_ldisc_ops tty_ptirouter_ldisc = { - .owner = THIS_MODULE, - .magic = TTY_LDISC_MAGIC, - .name = DRIVERNAME, - .open = n_tracerouter_open, - .close = n_tracerouter_close, - .read = n_tracerouter_read, - .write = n_tracerouter_write, - .receive_buf = n_tracerouter_receivebuf -}; - -/** - * n_tracerouter_init - module initialisation - * - * Registers this module as a line discipline driver. - * - * Return: - * 0 for success, any other value error. - */ -static int __init n_tracerouter_init(void) -{ - int retval; - - tr_data = kzalloc(sizeof(struct tracerouter_data), GFP_KERNEL); - if (tr_data == NULL) - return -ENOMEM; - - - /* Note N_TRACEROUTER is defined in linux/tty.h */ - retval = tty_register_ldisc(N_TRACEROUTER, &tty_ptirouter_ldisc); - if (retval < 0) { - pr_err("%s: Registration failed: %d\n", __func__, retval); - kfree(tr_data); - } - return retval; -} - -/** - * n_tracerouter_exit - module unload - * - * Removes this module as a line discipline driver. - */ -static void __exit n_tracerouter_exit(void) -{ - int retval = tty_unregister_ldisc(N_TRACEROUTER); - - if (retval < 0) - pr_err("%s: Unregistration failed: %d\n", __func__, retval); - else - kfree(tr_data); -} - -module_init(n_tracerouter_init); -module_exit(n_tracerouter_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Jay Freyensee"); -MODULE_ALIAS_LDISC(N_TRACEROUTER); -MODULE_DESCRIPTION("Trace router ldisc driver"); diff --git a/drivers/tty/n_tracesink.c b/drivers/tty/n_tracesink.c deleted file mode 100644 index d96ba82cc356..000000000000 --- a/drivers/tty/n_tracesink.c +++ /dev/null @@ -1,228 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * n_tracesink.c - Trace data router and sink path through tty space. - * - * Copyright (C) Intel 2011 - * - * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - * - * The trace sink uses the Linux line discipline framework to receive - * trace data coming from the PTI source line discipline driver - * to a user-desired tty port, like USB. - * This is to provide a way to extract modem trace data on - * devices that do not have a PTI HW module, or just need modem - * trace data to come out of a different HW output port. - * This is part of a solution for the P1149.7, compact JTAG, standard. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include "n_tracesink.h" - -/* - * Other ldisc drivers use 65536 which basically means, - * 'I can always accept 64k' and flow control is off. - * This number is deemed appropriate for this driver. - */ -#define RECEIVE_ROOM 65536 -#define DRIVERNAME "n_tracesink" - -/* - * there is a quirk with this ldisc is he can write data - * to a tty from anyone calling his kernel API, which - * meets customer requirements in the drivers/misc/pti.c - * project. So he needs to know when he can and cannot write when - * the API is called. In theory, the API can be called - * after an init() but before a successful open() which - * would crash the system if tty is not checked. - */ -static struct tty_struct *this_tty; -static DEFINE_MUTEX(writelock); - -/** - * n_tracesink_open() - Called when a tty is opened by a SW entity. - * @tty: terminal device to the ldisc. - * - * Return: - * 0 for success, - * -EFAULT = couldn't get a tty kref n_tracesink will sit - * on top of - * -EEXIST = open() called successfully once and it cannot - * be called again. - * - * Caveats: open() should only be successful the first time a - * SW entity calls it. - */ -static int n_tracesink_open(struct tty_struct *tty) -{ - int retval = -EEXIST; - - mutex_lock(&writelock); - if (this_tty == NULL) { - this_tty = tty_kref_get(tty); - if (this_tty == NULL) { - retval = -EFAULT; - } else { - tty->disc_data = this_tty; - tty_driver_flush_buffer(tty); - retval = 0; - } - } - mutex_unlock(&writelock); - - return retval; -} - -/** - * n_tracesink_close() - close connection - * @tty: terminal device to the ldisc. - * - * Called when a software entity wants to close a connection. - */ -static void n_tracesink_close(struct tty_struct *tty) -{ - mutex_lock(&writelock); - tty_driver_flush_buffer(tty); - tty_kref_put(this_tty); - this_tty = NULL; - tty->disc_data = NULL; - mutex_unlock(&writelock); -} - -/** - * n_tracesink_read() - read request from user space - * @tty: terminal device passed into the ldisc. - * @file: pointer to open file object. - * @buf: pointer to the data buffer that gets eventually returned. - * @nr: number of bytes of the data buffer that is returned. - * - * function that allows read() functionality in userspace. By default if this - * is not implemented it returns -EIO. This module is functioning like a - * router via n_tracesink_receivebuf(), and there is no real requirement - * to implement this function. However, an error return value other than - * -EIO should be used just to show that there was an intent not to have - * this function implemented. Return value based on read() man pages. - * - * Return: - * -EINVAL - */ -static ssize_t n_tracesink_read(struct tty_struct *tty, struct file *file, - unsigned char __user *buf, size_t nr) { - return -EINVAL; -} - -/** - * n_tracesink_write() - Function that allows write() in userspace. - * @tty: terminal device passed into the ldisc. - * @file: pointer to open file object. - * @buf: pointer to the data buffer that gets eventually returned. - * @nr: number of bytes of the data buffer that is returned. - * - * By default if this is not implemented, it returns -EIO. - * This should not be implemented, ever, because - * 1. this driver is functioning like a router via - * n_tracesink_receivebuf() - * 2. No writes to HW will ever go through this line discpline driver. - * However, an error return value other than -EIO should be used - * just to show that there was an intent not to have this function - * implemented. Return value based on write() man pages. - * - * Return: - * -EINVAL - */ -static ssize_t n_tracesink_write(struct tty_struct *tty, struct file *file, - const unsigned char *buf, size_t nr) { - return -EINVAL; -} - -/** - * n_tracesink_datadrain() - Kernel API function used to route - * trace debugging data to user-defined - * port like USB. - * - * @buf: Trace debuging data buffer to write to tty target - * port. Null value will return with no write occurring. - * @count: Size of buf. Value of 0 or a negative number will - * return with no write occuring. - * - * Caveat: If this line discipline does not set the tty it sits - * on top of via an open() call, this API function will not - * call the tty's write() call because it will have no pointer - * to call the write(). - */ -void n_tracesink_datadrain(u8 *buf, int count) -{ - mutex_lock(&writelock); - - if ((buf != NULL) && (count > 0) && (this_tty != NULL)) - this_tty->ops->write(this_tty, buf, count); - - mutex_unlock(&writelock); -} -EXPORT_SYMBOL_GPL(n_tracesink_datadrain); - -/* - * Flush buffer is not impelemented as the ldisc has no internal buffering - * so the tty_driver_flush_buffer() is sufficient for this driver's needs. - */ - -/* - * tty_ldisc function operations for this driver. - */ -static struct tty_ldisc_ops tty_n_tracesink = { - .owner = THIS_MODULE, - .magic = TTY_LDISC_MAGIC, - .name = DRIVERNAME, - .open = n_tracesink_open, - .close = n_tracesink_close, - .read = n_tracesink_read, - .write = n_tracesink_write -}; - -/** - * n_tracesink_init- module initialisation - * - * Registers this module as a line discipline driver. - * - * Return: - * 0 for success, any other value error. - */ -static int __init n_tracesink_init(void) -{ - /* Note N_TRACESINK is defined in linux/tty.h */ - int retval = tty_register_ldisc(N_TRACESINK, &tty_n_tracesink); - - if (retval < 0) - pr_err("%s: Registration failed: %d\n", __func__, retval); - - return retval; -} - -/** - * n_tracesink_exit - module unload - * - * Removes this module as a line discipline driver. - */ -static void __exit n_tracesink_exit(void) -{ - int retval = tty_unregister_ldisc(N_TRACESINK); - - if (retval < 0) - pr_err("%s: Unregistration failed: %d\n", __func__, retval); -} - -module_init(n_tracesink_init); -module_exit(n_tracesink_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Jay Freyensee"); -MODULE_ALIAS_LDISC(N_TRACESINK); -MODULE_DESCRIPTION("Trace sink ldisc driver"); diff --git a/drivers/tty/n_tracesink.h b/drivers/tty/n_tracesink.h deleted file mode 100644 index 7031d515a700..000000000000 --- a/drivers/tty/n_tracesink.h +++ /dev/null @@ -1,26 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * n_tracesink.h - Kernel driver API to route trace data in kernel space. - * - * Copyright (C) Intel 2011 - * - * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - * - * The PTI (Parallel Trace Interface) driver directs trace data routed from - * various parts in the system out through the Intel Penwell PTI port and - * out of the mobile device for analysis with a debugging tool - * (Lauterbach, Fido). This is part of a solution for the MIPI P1149.7, - * compact JTAG, standard. - * - * This header file is used by n_tracerouter to be able to send the - * data of it's tty port to the tty port this module sits. This - * mechanism can also be used independent of the PTI module. - * - */ - -#ifndef N_TRACESINK_H_ -#define N_TRACESINK_H_ - -void n_tracesink_datadrain(u8 *buf, int count); - -#endif diff --git a/include/linux/intel-pti.h b/include/linux/intel-pti.h deleted file mode 100644 index fcd841a90f2f..000000000000 --- a/include/linux/intel-pti.h +++ /dev/null @@ -1,35 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) Intel 2011 - * - * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - * - * The PTI (Parallel Trace Interface) driver directs trace data routed from - * various parts in the system out through the Intel Penwell PTI port and - * out of the mobile device for analysis with a debugging tool - * (Lauterbach, Fido). This is part of a solution for the MIPI P1149.7, - * compact JTAG, standard. - * - * This header file will allow other parts of the OS to use the - * interface to write out it's contents for debugging a mobile system. - */ - -#ifndef LINUX_INTEL_PTI_H_ -#define LINUX_INTEL_PTI_H_ - -/* offset for last dword of any PTI message. Part of MIPI P1149.7 */ -#define PTI_LASTDWORD_DTS 0x30 - -/* basic structure used as a write address to the PTI HW */ -struct pti_masterchannel { - u8 master; - u8 channel; -}; - -/* the following functions are defined in misc/pti.c */ -void pti_writedata(struct pti_masterchannel *mc, u8 *buf, int count); -struct pti_masterchannel *pti_request_masterchannel(u8 type, - const char *thread_name); -void pti_release_masterchannel(struct pti_masterchannel *mc); - -#endif /* LINUX_INTEL_PTI_H_ */ -- cgit v1.2.3 From 8544717cdacc2f33f0f53a3b34c5125b37e13ce9 Mon Sep 17 00:00:00 2001 From: Ioana Ciornei Date: Thu, 14 Jan 2021 19:07:48 +0200 Subject: bus: fsl-mc: move fsl_mc_command struct in a uapi header Define "struct fsl_mc_command" as a structure that can cross the user/kernel boundary. Acked-by: Laurentiu Tudor Signed-off-by: Ioana Ciornei Link: https://lore.kernel.org/r/20210114170752.2927915-2-ciorneiioana@gmail.com Signed-off-by: Greg Kroah-Hartman --- MAINTAINERS | 1 + include/linux/fsl/mc.h | 8 +------- include/uapi/linux/fsl_mc.h | 25 +++++++++++++++++++++++++ 3 files changed, 27 insertions(+), 7 deletions(-) create mode 100644 include/uapi/linux/fsl_mc.h (limited to 'include') diff --git a/MAINTAINERS b/MAINTAINERS index 23273a59da6f..128455811980 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14652,6 +14652,7 @@ S: Maintained F: Documentation/devicetree/bindings/misc/fsl,qoriq-mc.txt F: Documentation/networking/device_drivers/ethernet/freescale/dpaa2/overview.rst F: drivers/bus/fsl-mc/ +F: include/uapi/linux/fsl_mc.h QT1010 MEDIA DRIVER M: Antti Palosaari diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h index db244874e834..63b56aba925a 100644 --- a/include/linux/fsl/mc.h +++ b/include/linux/fsl/mc.h @@ -13,6 +13,7 @@ #include #include #include +#include #define FSL_MC_VENDOR_FREESCALE 0x1957 @@ -209,8 +210,6 @@ struct fsl_mc_device { #define to_fsl_mc_device(_dev) \ container_of(_dev, struct fsl_mc_device, dev) -#define MC_CMD_NUM_OF_PARAMS 7 - struct mc_cmd_header { u8 src_id; u8 flags_hw; @@ -220,11 +219,6 @@ struct mc_cmd_header { __le16 cmd_id; }; -struct fsl_mc_command { - __le64 header; - __le64 params[MC_CMD_NUM_OF_PARAMS]; -}; - enum mc_cmd_status { MC_CMD_STATUS_OK = 0x0, /* Completed successfully */ MC_CMD_STATUS_READY = 0x1, /* Ready to be processed */ diff --git a/include/uapi/linux/fsl_mc.h b/include/uapi/linux/fsl_mc.h new file mode 100644 index 000000000000..cf56d46f052e --- /dev/null +++ b/include/uapi/linux/fsl_mc.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Management Complex (MC) userspace public interface + * + * Copyright 2021 NXP + * + */ +#ifndef _UAPI_FSL_MC_H_ +#define _UAPI_FSL_MC_H_ + +#include + +#define MC_CMD_NUM_OF_PARAMS 7 + +/** + * struct fsl_mc_command - Management Complex (MC) command structure + * @header: MC command header + * @params: MC command parameters + */ +struct fsl_mc_command { + __le64 header; + __le64 params[MC_CMD_NUM_OF_PARAMS]; +}; + +#endif /* _UAPI_FSL_MC_H_ */ -- cgit v1.2.3 From 2cf1e703f066cfa82eb5a358ae84c29fe15a3b3a Mon Sep 17 00:00:00 2001 From: Ioana Ciornei Date: Thu, 14 Jan 2021 19:07:50 +0200 Subject: bus: fsl-mc: add fsl-mc userspace support Adding userspace support for the MC (Management Complex) means exporting an ioctl capable device file representing the root resource container. This new functionality in the fsl-mc bus driver intends to provide userspace applications an interface to interact with the MC firmware. Commands that are composed in userspace are sent to the MC firmware through the FSL_MC_SEND_MC_COMMAND ioctl. By default the implicit MC I/O portal is used for this operation, but if the implicit one is busy, a dynamic portal is allocated and then freed upon execution. The command received through the ioctl interface is checked against a known whitelist of accepted MC commands. Commands that attempt a change in hardware configuration will need CAP_NET_ADMIN, while commands used in debugging do not need it. Acked-by: Laurentiu Tudor Signed-off-by: Ioana Ciornei Link: https://lore.kernel.org/r/20210114170752.2927915-4-ciorneiioana@gmail.com Signed-off-by: Greg Kroah-Hartman --- Documentation/userspace-api/ioctl/ioctl-number.rst | 1 + drivers/bus/fsl-mc/Kconfig | 7 + drivers/bus/fsl-mc/Makefile | 3 + drivers/bus/fsl-mc/dprc-driver.c | 12 + drivers/bus/fsl-mc/fsl-mc-private.h | 39 ++ drivers/bus/fsl-mc/fsl-mc-uapi.c | 547 +++++++++++++++++++++ include/uapi/linux/fsl_mc.h | 9 + 7 files changed, 618 insertions(+) create mode 100644 drivers/bus/fsl-mc/fsl-mc-uapi.c (limited to 'include') diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst index a4c75a28c839..19d730f9d136 100644 --- a/Documentation/userspace-api/ioctl/ioctl-number.rst +++ b/Documentation/userspace-api/ioctl/ioctl-number.rst @@ -180,6 +180,7 @@ Code Seq# Include File Comments 'R' 00-1F linux/random.h conflict! 'R' 01 linux/rfkill.h conflict! 'R' C0-DF net/bluetooth/rfcomm.h +'R' E0 uapi/linux/fsl_mc.h 'S' all linux/cdrom.h conflict! 'S' 80-81 scsi/scsi_ioctl.h conflict! 'S' 82-FF scsi/scsi.h conflict! diff --git a/drivers/bus/fsl-mc/Kconfig b/drivers/bus/fsl-mc/Kconfig index c23c77c9b705..b1fd55901c50 100644 --- a/drivers/bus/fsl-mc/Kconfig +++ b/drivers/bus/fsl-mc/Kconfig @@ -14,3 +14,10 @@ config FSL_MC_BUS architecture. The fsl-mc bus driver handles discovery of DPAA2 objects (which are represented as Linux devices) and binding objects to drivers. + +config FSL_MC_UAPI_SUPPORT + bool "Management Complex (MC) userspace support" + depends on FSL_MC_BUS + help + Provides userspace support for interrogating, creating, destroying or + configuring DPAA2 objects exported by the Management Complex. diff --git a/drivers/bus/fsl-mc/Makefile b/drivers/bus/fsl-mc/Makefile index 3c518c7e8374..4ae292a30e53 100644 --- a/drivers/bus/fsl-mc/Makefile +++ b/drivers/bus/fsl-mc/Makefile @@ -16,3 +16,6 @@ mc-bus-driver-objs := fsl-mc-bus.o \ fsl-mc-allocator.o \ fsl-mc-msi.o \ dpmcp.o + +# MC userspace support +obj-$(CONFIG_FSL_MC_UAPI_SUPPORT) += fsl-mc-uapi.o diff --git a/drivers/bus/fsl-mc/dprc-driver.c b/drivers/bus/fsl-mc/dprc-driver.c index 68488a7ad0d6..ccec375095f2 100644 --- a/drivers/bus/fsl-mc/dprc-driver.c +++ b/drivers/bus/fsl-mc/dprc-driver.c @@ -603,6 +603,7 @@ int dprc_setup(struct fsl_mc_device *mc_dev) struct irq_domain *mc_msi_domain; bool mc_io_created = false; bool msi_domain_set = false; + bool uapi_created = false; u16 major_ver, minor_ver; size_t region_size; int error; @@ -635,6 +636,11 @@ int dprc_setup(struct fsl_mc_device *mc_dev) return error; mc_io_created = true; + } else { + error = fsl_mc_uapi_create_device_file(mc_bus); + if (error < 0) + return -EPROBE_DEFER; + uapi_created = true; } mc_msi_domain = fsl_mc_find_msi_domain(&mc_dev->dev); @@ -692,6 +698,9 @@ error_cleanup_msi_domain: mc_dev->mc_io = NULL; } + if (uapi_created) + fsl_mc_uapi_remove_device_file(mc_bus); + return error; } EXPORT_SYMBOL_GPL(dprc_setup); @@ -763,6 +772,7 @@ static void dprc_teardown_irq(struct fsl_mc_device *mc_dev) int dprc_cleanup(struct fsl_mc_device *mc_dev) { + struct fsl_mc_bus *mc_bus = to_fsl_mc_bus(mc_dev); int error; /* this function should be called only for DPRCs, it @@ -793,6 +803,8 @@ int dprc_cleanup(struct fsl_mc_device *mc_dev) if (!fsl_mc_is_root_dprc(&mc_dev->dev)) { fsl_destroy_mc_io(mc_dev->mc_io); mc_dev->mc_io = NULL; + } else { + fsl_mc_uapi_remove_device_file(mc_bus); } return 0; diff --git a/drivers/bus/fsl-mc/fsl-mc-private.h b/drivers/bus/fsl-mc/fsl-mc-private.h index be686c363121..6293a24de456 100644 --- a/drivers/bus/fsl-mc/fsl-mc-private.h +++ b/drivers/bus/fsl-mc/fsl-mc-private.h @@ -10,6 +10,8 @@ #include #include +#include +#include /* * Data Path Management Complex (DPMNG) General API @@ -542,6 +544,22 @@ struct fsl_mc_resource_pool { struct fsl_mc_bus *mc_bus; }; +/** + * struct fsl_mc_uapi - information associated with a device file + * @misc: struct miscdevice linked to the root dprc + * @device: newly created device in /dev + * @mutex: mutex lock to serialize the open/release operations + * @local_instance_in_use: local MC I/O instance in use or not + * @static_mc_io: pointer to the static MC I/O object + */ +struct fsl_mc_uapi { + struct miscdevice misc; + struct device *device; + struct mutex mutex; /* serialize open/release operations */ + u32 local_instance_in_use; + struct fsl_mc_io *static_mc_io; +}; + /** * struct fsl_mc_bus - logical bus that corresponds to a physical DPRC * @mc_dev: fsl-mc device for the bus device itself. @@ -551,6 +569,7 @@ struct fsl_mc_resource_pool { * @irq_resources: Pointer to array of IRQ objects for the IRQ pool * @scan_mutex: Serializes bus scanning * @dprc_attr: DPRC attributes + * @uapi_misc: struct that abstracts the interaction with userspace */ struct fsl_mc_bus { struct fsl_mc_device mc_dev; @@ -558,6 +577,7 @@ struct fsl_mc_bus { struct fsl_mc_device_irq *irq_resources; struct mutex scan_mutex; /* serializes bus scanning */ struct dprc_attributes dprc_attr; + struct fsl_mc_uapi uapi_misc; }; #define to_fsl_mc_bus(_mc_dev) \ @@ -614,4 +634,23 @@ struct fsl_mc_device *fsl_mc_device_lookup(struct fsl_mc_obj_desc *obj_desc, u16 mc_cmd_hdr_read_cmdid(struct fsl_mc_command *cmd); +#ifdef CONFIG_FSL_MC_UAPI_SUPPORT + +int fsl_mc_uapi_create_device_file(struct fsl_mc_bus *mc_bus); + +void fsl_mc_uapi_remove_device_file(struct fsl_mc_bus *mc_bus); + +#else + +static inline int fsl_mc_uapi_create_device_file(struct fsl_mc_bus *mc_bus) +{ + return 0; +} + +static inline void fsl_mc_uapi_remove_device_file(struct fsl_mc_bus *mc_bus) +{ +} + +#endif + #endif /* _FSL_MC_PRIVATE_H_ */ diff --git a/drivers/bus/fsl-mc/fsl-mc-uapi.c b/drivers/bus/fsl-mc/fsl-mc-uapi.c new file mode 100644 index 000000000000..eeb988c9f4bb --- /dev/null +++ b/drivers/bus/fsl-mc/fsl-mc-uapi.c @@ -0,0 +1,547 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Management Complex (MC) userspace support + * + * Copyright 2021 NXP + * + */ + +#include +#include +#include +#include + +#include "fsl-mc-private.h" + +struct uapi_priv_data { + struct fsl_mc_uapi *uapi; + struct fsl_mc_io *mc_io; +}; + +struct fsl_mc_cmd_desc { + u16 cmdid_value; + u16 cmdid_mask; + int size; + bool token; + int flags; +}; + +#define FSL_MC_CHECK_MODULE_ID BIT(0) +#define FSL_MC_CAP_NET_ADMIN_NEEDED BIT(1) + +enum fsl_mc_cmd_index { + DPDBG_DUMP = 0, + DPDBG_SET, + DPRC_GET_CONTAINER_ID, + DPRC_CREATE_CONT, + DPRC_DESTROY_CONT, + DPRC_ASSIGN, + DPRC_UNASSIGN, + DPRC_GET_OBJ_COUNT, + DPRC_GET_OBJ, + DPRC_GET_RES_COUNT, + DPRC_GET_RES_IDS, + DPRC_SET_OBJ_LABEL, + DPRC_SET_LOCKED, + DPRC_CONNECT, + DPRC_DISCONNECT, + DPRC_GET_POOL, + DPRC_GET_POOL_COUNT, + DPRC_GET_CONNECTION, + DPCI_GET_LINK_STATE, + DPCI_GET_PEER_ATTR, + DPAIOP_GET_SL_VERSION, + DPAIOP_GET_STATE, + DPMNG_GET_VERSION, + DPSECI_GET_TX_QUEUE, + DPMAC_GET_COUNTER, + DPMAC_GET_MAC_ADDR, + DPNI_SET_PRIM_MAC, + DPNI_GET_PRIM_MAC, + DPNI_GET_STATISTICS, + DPNI_GET_LINK_STATE, + GET_ATTR, + GET_IRQ_MASK, + GET_IRQ_STATUS, + CLOSE, + OPEN, + GET_API_VERSION, + DESTROY, + CREATE, +}; + +static struct fsl_mc_cmd_desc fsl_mc_accepted_cmds[] = { + [DPDBG_DUMP] = { + .cmdid_value = 0x1300, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 28, + }, + [DPDBG_SET] = { + .cmdid_value = 0x1400, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 28, + }, + [DPRC_GET_CONTAINER_ID] = { + .cmdid_value = 0x8300, + .cmdid_mask = 0xFFF0, + .token = false, + .size = 8, + }, + [DPRC_CREATE_CONT] = { + .cmdid_value = 0x1510, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 40, + .flags = FSL_MC_CAP_NET_ADMIN_NEEDED, + }, + [DPRC_DESTROY_CONT] = { + .cmdid_value = 0x1520, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 12, + .flags = FSL_MC_CAP_NET_ADMIN_NEEDED, + }, + [DPRC_ASSIGN] = { + .cmdid_value = 0x1570, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 40, + .flags = FSL_MC_CAP_NET_ADMIN_NEEDED, + }, + [DPRC_UNASSIGN] = { + .cmdid_value = 0x1580, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 40, + .flags = FSL_MC_CAP_NET_ADMIN_NEEDED, + }, + [DPRC_GET_OBJ_COUNT] = { + .cmdid_value = 0x1590, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 16, + }, + [DPRC_GET_OBJ] = { + .cmdid_value = 0x15A0, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 12, + }, + [DPRC_GET_RES_COUNT] = { + .cmdid_value = 0x15B0, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 32, + }, + [DPRC_GET_RES_IDS] = { + .cmdid_value = 0x15C0, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 40, + }, + [DPRC_SET_OBJ_LABEL] = { + .cmdid_value = 0x1610, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 48, + .flags = FSL_MC_CAP_NET_ADMIN_NEEDED, + }, + [DPRC_SET_LOCKED] = { + .cmdid_value = 0x16B0, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 16, + .flags = FSL_MC_CAP_NET_ADMIN_NEEDED, + }, + [DPRC_CONNECT] = { + .cmdid_value = 0x1670, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 56, + .flags = FSL_MC_CAP_NET_ADMIN_NEEDED, + }, + [DPRC_DISCONNECT] = { + .cmdid_value = 0x1680, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 32, + .flags = FSL_MC_CAP_NET_ADMIN_NEEDED, + }, + [DPRC_GET_POOL] = { + .cmdid_value = 0x1690, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 12, + }, + [DPRC_GET_POOL_COUNT] = { + .cmdid_value = 0x16A0, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 8, + }, + [DPRC_GET_CONNECTION] = { + .cmdid_value = 0x16C0, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 32, + }, + + [DPCI_GET_LINK_STATE] = { + .cmdid_value = 0x0E10, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 8, + }, + [DPCI_GET_PEER_ATTR] = { + .cmdid_value = 0x0E20, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 8, + }, + [DPAIOP_GET_SL_VERSION] = { + .cmdid_value = 0x2820, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 8, + }, + [DPAIOP_GET_STATE] = { + .cmdid_value = 0x2830, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 8, + }, + [DPMNG_GET_VERSION] = { + .cmdid_value = 0x8310, + .cmdid_mask = 0xFFF0, + .token = false, + .size = 8, + }, + [DPSECI_GET_TX_QUEUE] = { + .cmdid_value = 0x1970, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 14, + }, + [DPMAC_GET_COUNTER] = { + .cmdid_value = 0x0c40, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 9, + }, + [DPMAC_GET_MAC_ADDR] = { + .cmdid_value = 0x0c50, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 8, + }, + [DPNI_SET_PRIM_MAC] = { + .cmdid_value = 0x2240, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 16, + .flags = FSL_MC_CAP_NET_ADMIN_NEEDED, + }, + [DPNI_GET_PRIM_MAC] = { + .cmdid_value = 0x2250, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 8, + }, + [DPNI_GET_STATISTICS] = { + .cmdid_value = 0x25D0, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 10, + }, + [DPNI_GET_LINK_STATE] = { + .cmdid_value = 0x2150, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 8, + }, + [GET_ATTR] = { + .cmdid_value = 0x0040, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 8, + }, + [GET_IRQ_MASK] = { + .cmdid_value = 0x0150, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 13, + }, + [GET_IRQ_STATUS] = { + .cmdid_value = 0x0160, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 13, + }, + [CLOSE] = { + .cmdid_value = 0x8000, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 8, + }, + + /* Common commands amongst all types of objects. Must be checked last. */ + [OPEN] = { + .cmdid_value = 0x8000, + .cmdid_mask = 0xFC00, + .token = false, + .size = 12, + .flags = FSL_MC_CHECK_MODULE_ID, + }, + [GET_API_VERSION] = { + .cmdid_value = 0xA000, + .cmdid_mask = 0xFC00, + .token = false, + .size = 8, + .flags = FSL_MC_CHECK_MODULE_ID, + }, + [DESTROY] = { + .cmdid_value = 0x9800, + .cmdid_mask = 0xFC00, + .token = true, + .size = 12, + .flags = FSL_MC_CHECK_MODULE_ID | FSL_MC_CAP_NET_ADMIN_NEEDED, + }, + [CREATE] = { + .cmdid_value = 0x9000, + .cmdid_mask = 0xFC00, + .token = true, + .size = 64, + .flags = FSL_MC_CHECK_MODULE_ID | FSL_MC_CAP_NET_ADMIN_NEEDED, + }, +}; + +#define FSL_MC_NUM_ACCEPTED_CMDS ARRAY_SIZE(fsl_mc_accepted_cmds) + +#define FSL_MC_MAX_MODULE_ID 0x10 + +static int fsl_mc_command_check(struct fsl_mc_device *mc_dev, + struct fsl_mc_command *mc_cmd) +{ + struct fsl_mc_cmd_desc *desc = NULL; + int mc_cmd_max_size, i; + bool token_provided; + u16 cmdid, module_id; + char *mc_cmd_end; + char sum = 0; + + /* Check if this is an accepted MC command */ + cmdid = mc_cmd_hdr_read_cmdid(mc_cmd); + for (i = 0; i < FSL_MC_NUM_ACCEPTED_CMDS; i++) { + desc = &fsl_mc_accepted_cmds[i]; + if ((cmdid & desc->cmdid_mask) == desc->cmdid_value) + break; + } + if (!desc) { + dev_err(&mc_dev->dev, "MC command 0x%04x: cmdid not accepted\n", cmdid); + return -EACCES; + } + + /* Check if the size of the command is honored. Anything beyond the + * last valid byte of the command should be zeroed. + */ + mc_cmd_max_size = sizeof(*mc_cmd); + mc_cmd_end = ((char *)mc_cmd) + desc->size; + for (i = desc->size; i < mc_cmd_max_size; i++) + sum |= *mc_cmd_end++; + if (sum) { + dev_err(&mc_dev->dev, "MC command 0x%04x: garbage beyond max size of %d bytes!\n", + cmdid, desc->size); + return -EACCES; + } + + /* Some MC commands request a token to be passed so that object + * identification is possible. Check if the token passed in the command + * is as expected. + */ + token_provided = mc_cmd_hdr_read_token(mc_cmd) ? true : false; + if (token_provided != desc->token) { + dev_err(&mc_dev->dev, "MC command 0x%04x: token 0x%04x is invalid!\n", + cmdid, mc_cmd_hdr_read_token(mc_cmd)); + return -EACCES; + } + + /* If needed, check if the module ID passed is valid */ + if (desc->flags & FSL_MC_CHECK_MODULE_ID) { + /* The module ID is represented by bits [4:9] from the cmdid */ + module_id = (cmdid & GENMASK(9, 4)) >> 4; + if (module_id == 0 || module_id > FSL_MC_MAX_MODULE_ID) { + dev_err(&mc_dev->dev, "MC command 0x%04x: unknown module ID 0x%x\n", + cmdid, module_id); + return -EACCES; + } + } + + /* Some commands alter how hardware resources are managed. For these + * commands, check for CAP_NET_ADMIN. + */ + if (desc->flags & FSL_MC_CAP_NET_ADMIN_NEEDED) { + if (!capable(CAP_NET_ADMIN)) { + dev_err(&mc_dev->dev, "MC command 0x%04x: needs CAP_NET_ADMIN!\n", + cmdid); + return -EPERM; + } + } + + return 0; +} + +static int fsl_mc_uapi_send_command(struct fsl_mc_device *mc_dev, unsigned long arg, + struct fsl_mc_io *mc_io) +{ + struct fsl_mc_command mc_cmd; + int error; + + error = copy_from_user(&mc_cmd, (void __user *)arg, sizeof(mc_cmd)); + if (error) + return -EFAULT; + + error = fsl_mc_command_check(mc_dev, &mc_cmd); + if (error) + return error; + + error = mc_send_command(mc_io, &mc_cmd); + if (error) + return error; + + error = copy_to_user((void __user *)arg, &mc_cmd, sizeof(mc_cmd)); + if (error) + return -EFAULT; + + return 0; +} + +static int fsl_mc_uapi_dev_open(struct inode *inode, struct file *filep) +{ + struct fsl_mc_device *root_mc_device; + struct uapi_priv_data *priv_data; + struct fsl_mc_io *dynamic_mc_io; + struct fsl_mc_uapi *mc_uapi; + struct fsl_mc_bus *mc_bus; + int error; + + priv_data = kzalloc(sizeof(*priv_data), GFP_KERNEL); + if (!priv_data) + return -ENOMEM; + + mc_uapi = container_of(filep->private_data, struct fsl_mc_uapi, misc); + mc_bus = container_of(mc_uapi, struct fsl_mc_bus, uapi_misc); + root_mc_device = &mc_bus->mc_dev; + + mutex_lock(&mc_uapi->mutex); + + if (!mc_uapi->local_instance_in_use) { + priv_data->mc_io = mc_uapi->static_mc_io; + mc_uapi->local_instance_in_use = 1; + } else { + error = fsl_mc_portal_allocate(root_mc_device, 0, + &dynamic_mc_io); + if (error) { + dev_dbg(&root_mc_device->dev, + "Could not allocate MC portal\n"); + goto error_portal_allocate; + } + + priv_data->mc_io = dynamic_mc_io; + } + priv_data->uapi = mc_uapi; + filep->private_data = priv_data; + + mutex_unlock(&mc_uapi->mutex); + + return 0; + +error_portal_allocate: + mutex_unlock(&mc_uapi->mutex); + kfree(priv_data); + + return error; +} + +static int fsl_mc_uapi_dev_release(struct inode *inode, struct file *filep) +{ + struct uapi_priv_data *priv_data; + struct fsl_mc_uapi *mc_uapi; + struct fsl_mc_io *mc_io; + + priv_data = filep->private_data; + mc_uapi = priv_data->uapi; + mc_io = priv_data->mc_io; + + mutex_lock(&mc_uapi->mutex); + + if (mc_io == mc_uapi->static_mc_io) + mc_uapi->local_instance_in_use = 0; + else + fsl_mc_portal_free(mc_io); + + kfree(filep->private_data); + filep->private_data = NULL; + + mutex_unlock(&mc_uapi->mutex); + + return 0; +} + +static long fsl_mc_uapi_dev_ioctl(struct file *file, + unsigned int cmd, + unsigned long arg) +{ + struct uapi_priv_data *priv_data = file->private_data; + struct fsl_mc_device *root_mc_device; + struct fsl_mc_bus *mc_bus; + int error; + + mc_bus = container_of(priv_data->uapi, struct fsl_mc_bus, uapi_misc); + root_mc_device = &mc_bus->mc_dev; + + switch (cmd) { + case FSL_MC_SEND_MC_COMMAND: + error = fsl_mc_uapi_send_command(root_mc_device, arg, priv_data->mc_io); + break; + default: + dev_dbg(&root_mc_device->dev, "unexpected ioctl call number\n"); + error = -EINVAL; + } + + return error; +} + +static const struct file_operations fsl_mc_uapi_dev_fops = { + .owner = THIS_MODULE, + .open = fsl_mc_uapi_dev_open, + .release = fsl_mc_uapi_dev_release, + .unlocked_ioctl = fsl_mc_uapi_dev_ioctl, +}; + +int fsl_mc_uapi_create_device_file(struct fsl_mc_bus *mc_bus) +{ + struct fsl_mc_device *mc_dev = &mc_bus->mc_dev; + struct fsl_mc_uapi *mc_uapi = &mc_bus->uapi_misc; + int error; + + mc_uapi->misc.minor = MISC_DYNAMIC_MINOR; + mc_uapi->misc.name = dev_name(&mc_dev->dev); + mc_uapi->misc.fops = &fsl_mc_uapi_dev_fops; + + error = misc_register(&mc_uapi->misc); + if (error) + return error; + + mc_uapi->static_mc_io = mc_bus->mc_dev.mc_io; + + mutex_init(&mc_uapi->mutex); + + return 0; +} + +void fsl_mc_uapi_remove_device_file(struct fsl_mc_bus *mc_bus) +{ + misc_deregister(&mc_bus->uapi_misc.misc); +} diff --git a/include/uapi/linux/fsl_mc.h b/include/uapi/linux/fsl_mc.h index cf56d46f052e..e57451570033 100644 --- a/include/uapi/linux/fsl_mc.h +++ b/include/uapi/linux/fsl_mc.h @@ -16,10 +16,19 @@ * struct fsl_mc_command - Management Complex (MC) command structure * @header: MC command header * @params: MC command parameters + * + * Used by FSL_MC_SEND_MC_COMMAND */ struct fsl_mc_command { __le64 header; __le64 params[MC_CMD_NUM_OF_PARAMS]; }; +#define FSL_MC_SEND_CMD_IOCTL_TYPE 'R' +#define FSL_MC_SEND_CMD_IOCTL_SEQ 0xE0 + +#define FSL_MC_SEND_MC_COMMAND \ + _IOWR(FSL_MC_SEND_CMD_IOCTL_TYPE, FSL_MC_SEND_CMD_IOCTL_SEQ, \ + struct fsl_mc_command) + #endif /* _UAPI_FSL_MC_H_ */ -- cgit v1.2.3 From 1423de718e6a0ce00372ab119fa40060ff50883e Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 2 Jun 2020 15:56:55 -0500 Subject: PCI/ACPI: Make acpi_pci_osc_control_set() static acpi_pci_osc_control_set() is only called from pci_root.c, so stop exporting it and make it static. Signed-off-by: Bjorn Helgaas Acked-by: Rafael J. Wysocki --- drivers/acpi/pci_root.c | 3 +-- include/linux/acpi.h | 3 --- 2 files changed, 1 insertion(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c index 0bf072cef6cf..7d5a4bd4207c 100644 --- a/drivers/acpi/pci_root.c +++ b/drivers/acpi/pci_root.c @@ -353,7 +353,7 @@ EXPORT_SYMBOL_GPL(acpi_get_pci_dev); * _OSC bits the BIOS has granted control of, but its contents are meaningless * on failure. **/ -acpi_status acpi_pci_osc_control_set(acpi_handle handle, u32 *mask, u32 req) +static acpi_status acpi_pci_osc_control_set(acpi_handle handle, u32 *mask, u32 req) { struct acpi_pci_root *root; acpi_status status = AE_OK; @@ -406,7 +406,6 @@ out: mutex_unlock(&osc_lock); return status; } -EXPORT_SYMBOL(acpi_pci_osc_control_set); static void negotiate_os_control(struct acpi_pci_root *root, int *no_aspm, bool is_pcie) diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 053bf05fb1f7..4703daafcce9 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -581,9 +581,6 @@ extern bool osc_pc_lpi_support_confirmed; #define ACPI_GSB_ACCESS_ATTRIB_RAW_BYTES 0x0000000E #define ACPI_GSB_ACCESS_ATTRIB_RAW_PROCESS 0x0000000F -extern acpi_status acpi_pci_osc_control_set(acpi_handle handle, - u32 *mask, u32 req); - /* Enable _OST when all relevant hotplug operations are enabled */ #if defined(CONFIG_ACPI_HOTPLUG_CPU) && \ defined(CONFIG_ACPI_HOTPLUG_MEMORY) && \ -- cgit v1.2.3 From c209e742141bc0064ecdb73ef0dd825310de28cb Mon Sep 17 00:00:00 2001 From: Ofir Bitton Date: Thu, 3 Dec 2020 17:12:09 +0200 Subject: habanalabs: allow user to pass a staged submission seq In order to support the staged submission feature, user must be allowed to use the same CS sequence for all submissions in the same staged submission. Signed-off-by: Ofir Bitton Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- .../misc/habanalabs/common/command_submission.c | 16 +++++++++---- include/uapi/misc/habanalabs.h | 28 +++++++++++++++------- 2 files changed, 30 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/drivers/misc/habanalabs/common/command_submission.c b/drivers/misc/habanalabs/common/command_submission.c index ccb4972a555f..348b0ecb4489 100644 --- a/drivers/misc/habanalabs/common/command_submission.c +++ b/drivers/misc/habanalabs/common/command_submission.c @@ -807,7 +807,7 @@ static int hl_cs_copy_chunk_array(struct hl_device *hdev, } static int cs_ioctl_default(struct hl_fpriv *hpriv, void __user *chunks, - u32 num_chunks, u64 *cs_seq, bool timestamp) + u32 num_chunks, u64 *cs_seq, u32 flags) { bool int_queues_only = true; struct hl_device *hdev = hpriv->hdev; @@ -836,7 +836,7 @@ static int cs_ioctl_default(struct hl_fpriv *hpriv, void __user *chunks, goto free_cs_chunk_array; } - cs->timestamp = !!timestamp; + cs->timestamp = !!(flags & HL_CS_FLAGS_TIMESTAMP); *cs_seq = cs->sequence; hl_debugfs_add_cs(cs); @@ -1004,7 +1004,7 @@ static int hl_cs_ctx_switch(struct hl_fpriv *hpriv, union hl_cs_args *args, rc = 0; } else { rc = cs_ioctl_default(hpriv, chunks, num_chunks, - cs_seq, false); + cs_seq, 0); } mutex_unlock(&hpriv->restore_phase_mutex); @@ -1347,7 +1347,7 @@ int hl_cs_ioctl(struct hl_fpriv *hpriv, void *data) enum hl_cs_type cs_type; u64 cs_seq = ULONG_MAX; void __user *chunks; - u32 num_chunks; + u32 num_chunks, flags; int rc; rc = hl_cs_sanity_checks(hpriv, args); @@ -1362,6 +1362,12 @@ int hl_cs_ioctl(struct hl_fpriv *hpriv, void *data) ~HL_CS_FLAGS_FORCE_RESTORE); chunks = (void __user *) (uintptr_t) args->in.chunks_execute; num_chunks = args->in.num_chunks_execute; + flags = args->in.cs_flags; + + /* In case this is a staged CS, user should supply the CS sequence */ + if ((flags & HL_CS_FLAGS_STAGED_SUBMISSION) && + !(flags & HL_CS_FLAGS_STAGED_SUBMISSION_FIRST)) + cs_seq = args->in.seq; switch (cs_type) { case CS_TYPE_SIGNAL: @@ -1372,7 +1378,7 @@ int hl_cs_ioctl(struct hl_fpriv *hpriv, void *data) break; default: rc = cs_ioctl_default(hpriv, chunks, num_chunks, &cs_seq, - args->in.cs_flags & HL_CS_FLAGS_TIMESTAMP); + args->in.cs_flags); break; } diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index dba3827c43ca..b9afe1cdac24 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -604,11 +604,14 @@ struct hl_cs_chunk { }; /* SIGNAL and WAIT/COLLECTIVE_WAIT flags are mutually exclusive */ -#define HL_CS_FLAGS_FORCE_RESTORE 0x1 -#define HL_CS_FLAGS_SIGNAL 0x2 -#define HL_CS_FLAGS_WAIT 0x4 -#define HL_CS_FLAGS_COLLECTIVE_WAIT 0x8 -#define HL_CS_FLAGS_TIMESTAMP 0x20 +#define HL_CS_FLAGS_FORCE_RESTORE 0x1 +#define HL_CS_FLAGS_SIGNAL 0x2 +#define HL_CS_FLAGS_WAIT 0x4 +#define HL_CS_FLAGS_COLLECTIVE_WAIT 0x8 +#define HL_CS_FLAGS_TIMESTAMP 0x20 +#define HL_CS_FLAGS_STAGED_SUBMISSION 0x40 +#define HL_CS_FLAGS_STAGED_SUBMISSION_FIRST 0x80 +#define HL_CS_FLAGS_STAGED_SUBMISSION_LAST 0x100 #define HL_CS_STATUS_SUCCESS 0 @@ -622,10 +625,17 @@ struct hl_cs_in { /* holds address of array of hl_cs_chunk for execution phase */ __u64 chunks_execute; - /* this holds address of array of hl_cs_chunk for store phase - - * Currently not in use - */ - __u64 chunks_store; + union { + /* this holds address of array of hl_cs_chunk for store phase - + * Currently not in use + */ + __u64 chunks_store; + + /* Sequence number of a staged submission CS + * valid only if HL_CS_FLAGS_STAGED_SUBMISSION is set + */ + __u64 seq; + }; /* Number of chunks in restore phase array. Maximum number is * HL_MAX_JOBS_PER_CS -- cgit v1.2.3 From 0eda23d77e1beede9c61b0cba6d9267d3a92bd4e Mon Sep 17 00:00:00 2001 From: Moti Haimovski Date: Mon, 7 Dec 2020 09:10:34 +0200 Subject: habanalabs: report dram_page_size in hw_ip_info ioctl Instead of having it hard-coded as a define, pass it to the user in runtime. Signed-off-by: Moti Haimovski Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/common/habanalabs_ioctl.c | 1 + include/uapi/misc/habanalabs.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include') diff --git a/drivers/misc/habanalabs/common/habanalabs_ioctl.c b/drivers/misc/habanalabs/common/habanalabs_ioctl.c index d25892d61ec9..394a2e1767ce 100644 --- a/drivers/misc/habanalabs/common/habanalabs_ioctl.c +++ b/drivers/misc/habanalabs/common/habanalabs_ioctl.c @@ -63,6 +63,7 @@ static int hw_ip_info(struct hl_device *hdev, struct hl_info_args *args) hw_ip.dram_size = prop->dram_size - dram_kmd_size; if (hw_ip.dram_size > PAGE_SIZE) hw_ip.dram_enabled = 1; + hw_ip.dram_page_size = prop->dram_page_size; hw_ip.num_of_events = prop->num_of_events; memcpy(hw_ip.cpucp_version, prop->cpucp_info.cpucp_version, diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index b9afe1cdac24..b431a70e1b8b 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -320,6 +320,8 @@ struct hl_info_hw_ip_info { __u8 pad[2]; __u8 cpucp_version[HL_INFO_VERSION_MAX_LEN]; __u8 card_name[HL_INFO_CARD_NAME_MAX_LEN]; + __u64 reserved2; + __u64 dram_page_size; }; struct hl_info_dram_usage { -- cgit v1.2.3 From e1fa724dd17a6a9b9934636226e683912d12c876 Mon Sep 17 00:00:00 2001 From: Ofir Bitton Date: Wed, 6 Jan 2021 15:40:37 +0200 Subject: habanalabs: add user available interrupt to hw_ip In order to support completions that arrive directly to the user, the driver needs to supply the user with the first available msix interrupt available. Signed-off-by: Ofir Bitton Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/common/habanalabs.h | 3 +++ drivers/misc/habanalabs/common/habanalabs_ioctl.c | 2 ++ drivers/misc/habanalabs/gaudi/gaudi.c | 2 ++ drivers/misc/habanalabs/goya/goya.c | 2 ++ include/uapi/misc/habanalabs.h | 6 ++++-- 5 files changed, 13 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h index 3923b03e99aa..ce1a1e70a6d5 100644 --- a/drivers/misc/habanalabs/common/habanalabs.h +++ b/drivers/misc/habanalabs/common/habanalabs.h @@ -408,6 +408,8 @@ struct hl_mmu_properties { * @sync_stream_first_mon: first monitor available for sync stream use * @first_available_user_sob: first sob available for the user * @first_available_user_mon: first monitor available for the user + * @first_available_user_msix_interrupt: first available msix interrupt + * reserved for the user * @tpc_enabled_mask: which TPCs are enabled. * @completion_queues_count: number of completion queues. * @fw_security_disabled: true if security measures are disabled in firmware, @@ -469,6 +471,7 @@ struct asic_fixed_properties { u16 sync_stream_first_mon; u16 first_available_user_sob[HL_MAX_DCORES]; u16 first_available_user_mon[HL_MAX_DCORES]; + u16 first_available_user_msix_interrupt; u8 tpc_enabled_mask; u8 completion_queues_count; u8 fw_security_disabled; diff --git a/drivers/misc/habanalabs/common/habanalabs_ioctl.c b/drivers/misc/habanalabs/common/habanalabs_ioctl.c index dfac5c8cadb3..628bdc56dca3 100644 --- a/drivers/misc/habanalabs/common/habanalabs_ioctl.c +++ b/drivers/misc/habanalabs/common/habanalabs_ioctl.c @@ -90,6 +90,8 @@ static int hw_ip_info(struct hl_device *hdev, struct hl_info_args *args) hw_ip.psoc_pci_pll_od = prop->psoc_pci_pll_od; hw_ip.psoc_pci_pll_div_factor = prop->psoc_pci_pll_div_factor; + hw_ip.first_available_interrupt_id = + prop->first_available_user_msix_interrupt; return copy_to_user(out, &hw_ip, min((size_t)size, sizeof(hw_ip))) ? -EFAULT : 0; } diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c index 2b01c081404a..69b3867bc151 100644 --- a/drivers/misc/habanalabs/gaudi/gaudi.c +++ b/drivers/misc/habanalabs/gaudi/gaudi.c @@ -527,6 +527,8 @@ static int gaudi_get_fixed_properties(struct hl_device *hdev) prop->sync_stream_first_mon + (num_sync_stream_queues * HL_RSVD_MONS); + prop->first_available_user_msix_interrupt = USHRT_MAX; + /* disable fw security for now, set it in a later stage */ prop->fw_security_disabled = true; prop->fw_security_status_valid = false; diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index 50dcefc02cdd..82f69274def7 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -455,6 +455,8 @@ int goya_get_fixed_properties(struct hl_device *hdev) prop->max_pending_cs = GOYA_MAX_PENDING_CS; + prop->first_available_user_msix_interrupt = USHRT_MAX; + /* disable fw security for now, set it in a later stage */ prop->fw_security_disabled = true; prop->fw_security_status_valid = false; diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index b431a70e1b8b..866355a53188 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -309,7 +309,9 @@ struct hl_info_hw_ip_info { __u32 num_of_events; __u32 device_id; /* PCI Device ID */ __u32 module_id; /* For mezzanine cards in servers (From OCP spec.) */ - __u32 reserved[2]; + __u32 reserved; + __u16 first_available_interrupt_id; + __u16 reserved2; __u32 cpld_version; __u32 psoc_pci_pll_nr; __u32 psoc_pci_pll_nf; @@ -320,7 +322,7 @@ struct hl_info_hw_ip_info { __u8 pad[2]; __u8 cpucp_version[HL_INFO_VERSION_MAX_LEN]; __u8 card_name[HL_INFO_CARD_NAME_MAX_LEN]; - __u64 reserved2; + __u64 reserved3; __u64 dram_page_size; }; -- cgit v1.2.3 From d00697fbe13ccc1dfb7adb82204e1469a7783b07 Mon Sep 17 00:00:00 2001 From: Ofir Bitton Date: Tue, 5 Jan 2021 12:55:06 +0200 Subject: habanalabs: add new mem ioctl op for mapping hw blocks For future ASIC support the driver allows user to map certain regions in the device's configuration space for direct access from userspace. Signed-off-by: Ofir Bitton Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/common/device.c | 3 + drivers/misc/habanalabs/common/habanalabs.h | 16 +++-- drivers/misc/habanalabs/common/memory.c | 93 ++++++++++++++++++++++++++++- drivers/misc/habanalabs/gaudi/gaudi.c | 17 +++++- drivers/misc/habanalabs/goya/goya.c | 16 ++++- include/uapi/misc/habanalabs.h | 18 +++++- 6 files changed, 153 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/drivers/misc/habanalabs/common/device.c b/drivers/misc/habanalabs/common/device.c index 13405d47d843..59219c862ca0 100644 --- a/drivers/misc/habanalabs/common/device.c +++ b/drivers/misc/habanalabs/common/device.c @@ -142,6 +142,9 @@ static int hl_mmap(struct file *filp, struct vm_area_struct *vma) switch (vm_pgoff & HL_MMAP_TYPE_MASK) { case HL_MMAP_TYPE_CB: return hl_cb_mmap(hpriv, vma); + + case HL_MMAP_TYPE_BLOCK: + return hl_hw_block_mmap(hpriv, vma); } return -EINVAL; diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h index 4129e4e6a7b5..e105612ed577 100644 --- a/drivers/misc/habanalabs/common/habanalabs.h +++ b/drivers/misc/habanalabs/common/habanalabs.h @@ -28,17 +28,18 @@ #define HL_NAME "habanalabs" /* Use upper bits of mmap offset to store habana driver specific information. - * bits[63:62] - Encode mmap type + * bits[63:61] - Encode mmap type * bits[45:0] - mmap offset value * * NOTE: struct vm_area_struct.vm_pgoff uses offset in pages. Hence, these * defines are w.r.t to PAGE_SIZE */ -#define HL_MMAP_TYPE_SHIFT (62 - PAGE_SHIFT) -#define HL_MMAP_TYPE_MASK (0x3ull << HL_MMAP_TYPE_SHIFT) +#define HL_MMAP_TYPE_SHIFT (61 - PAGE_SHIFT) +#define HL_MMAP_TYPE_MASK (0x7ull << HL_MMAP_TYPE_SHIFT) +#define HL_MMAP_TYPE_BLOCK (0x4ull << HL_MMAP_TYPE_SHIFT) #define HL_MMAP_TYPE_CB (0x2ull << HL_MMAP_TYPE_SHIFT) -#define HL_MMAP_OFFSET_VALUE_MASK (0x3FFFFFFFFFFFull >> PAGE_SHIFT) +#define HL_MMAP_OFFSET_VALUE_MASK (0x1FFFFFFFFFFFull >> PAGE_SHIFT) #define HL_MMAP_OFFSET_VALUE_GET(off) (off & HL_MMAP_OFFSET_VALUE_MASK) #define HL_PENDING_RESET_PER_SEC 10 @@ -856,6 +857,8 @@ enum div_select_defs { * @descramble_addr: Routine to de-scramble the address prior of * showing it to users. * @ack_protection_bits_errors: ack and dump all security violations + * @get_hw_block_id: retrieve a HW block id to be used by the user to mmap it. + * @hw_block_mmap: mmap a HW block with a given id. */ struct hl_asic_funcs { int (*early_init)(struct hl_device *hdev); @@ -968,6 +971,10 @@ struct hl_asic_funcs { u64 (*scramble_addr)(struct hl_device *hdev, u64 addr); u64 (*descramble_addr)(struct hl_device *hdev, u64 addr); void (*ack_protection_bits_errors)(struct hl_device *hdev); + int (*get_hw_block_id)(struct hl_device *hdev, u64 block_addr, + u32 *block_id); + int (*hw_block_mmap)(struct hl_device *hdev, struct vm_area_struct *vma, + u32 block_id, u32 block_size); }; @@ -2167,6 +2174,7 @@ int hl_cb_create(struct hl_device *hdev, struct hl_cb_mgr *mgr, bool map_cb, u64 *handle); int hl_cb_destroy(struct hl_device *hdev, struct hl_cb_mgr *mgr, u64 cb_handle); int hl_cb_mmap(struct hl_fpriv *hpriv, struct vm_area_struct *vma); +int hl_hw_block_mmap(struct hl_fpriv *hpriv, struct vm_area_struct *vma); struct hl_cb *hl_cb_get(struct hl_device *hdev, struct hl_cb_mgr *mgr, u32 handle); void hl_cb_put(struct hl_cb *cb); diff --git a/drivers/misc/habanalabs/common/memory.c b/drivers/misc/habanalabs/common/memory.c index 36de0d05d3a2..7171e8820a2d 100644 --- a/drivers/misc/habanalabs/common/memory.c +++ b/drivers/misc/habanalabs/common/memory.c @@ -1289,11 +1289,88 @@ vm_type_err: return rc; } +static int map_block(struct hl_device *hdev, u64 address, u64 *handle) +{ + u32 block_id = 0; + int rc; + + rc = hdev->asic_funcs->get_hw_block_id(hdev, address, &block_id); + + *handle = block_id | HL_MMAP_TYPE_BLOCK; + *handle <<= PAGE_SHIFT; + + return rc; +} + +static void hw_block_vm_close(struct vm_area_struct *vma) +{ + struct hl_ctx *ctx = (struct hl_ctx *) vma->vm_private_data; + + hl_ctx_put(ctx); + vma->vm_private_data = NULL; +} + +static const struct vm_operations_struct hw_block_vm_ops = { + .close = hw_block_vm_close +}; + +/** + * hl_hw_block_mmap() - mmap a hw block to user. + * @hpriv: pointer to the private data of the fd + * @vma: pointer to vm_area_struct of the process + * + * Driver increments context reference for every HW block mapped in order + * to prevent user from closing FD without unmapping first + */ +int hl_hw_block_mmap(struct hl_fpriv *hpriv, struct vm_area_struct *vma) +{ + struct hl_device *hdev = hpriv->hdev; + u32 block_id, block_size; + int rc; + + /* We use the page offset to hold the block id and thus we need to clear + * it before doing the mmap itself + */ + block_id = vma->vm_pgoff; + vma->vm_pgoff = 0; + + /* Driver only allows mapping of a complete HW block */ + block_size = vma->vm_end - vma->vm_start; + +#ifdef _HAS_TYPE_ARG_IN_ACCESS_OK + if (!access_ok(VERIFY_WRITE, + (void __user *) (uintptr_t) vma->vm_start, block_size)) { +#else + if (!access_ok((void __user *) (uintptr_t) vma->vm_start, block_size)) { +#endif + dev_err(hdev->dev, + "user pointer is invalid - 0x%lx\n", + vma->vm_start); + + return -EINVAL; + } + + vma->vm_ops = &hw_block_vm_ops; + vma->vm_private_data = hpriv->ctx; + + hl_ctx_get(hdev, hpriv->ctx); + + rc = hdev->asic_funcs->hw_block_mmap(hdev, vma, block_id, block_size); + if (rc) { + hl_ctx_put(hpriv->ctx); + return rc; + } + + vma->vm_pgoff = block_id; + + return 0; +} + static int mem_ioctl_no_mmu(struct hl_fpriv *hpriv, union hl_mem_args *args) { struct hl_device *hdev = hpriv->hdev; struct hl_ctx *ctx = hpriv->ctx; - u64 device_addr = 0; + u64 block_handle, device_addr = 0; u32 handle = 0; int rc; @@ -1337,6 +1414,12 @@ static int mem_ioctl_no_mmu(struct hl_fpriv *hpriv, union hl_mem_args *args) rc = 0; break; + case HL_MEM_OP_MAP_BLOCK: + rc = map_block(hdev, args->in.map_block.block_addr, + &block_handle); + args->out.handle = block_handle; + break; + default: dev_err(hdev->dev, "Unknown opcode for memory IOCTL\n"); rc = -ENOTTY; @@ -1353,7 +1436,7 @@ int hl_mem_ioctl(struct hl_fpriv *hpriv, void *data) union hl_mem_args *args = data; struct hl_device *hdev = hpriv->hdev; struct hl_ctx *ctx = hpriv->ctx; - u64 device_addr = 0; + u64 block_handle, device_addr = 0; u32 handle = 0; int rc; @@ -1439,6 +1522,12 @@ int hl_mem_ioctl(struct hl_fpriv *hpriv, void *data) rc = unmap_device_va(ctx, &args->in, false); break; + case HL_MEM_OP_MAP_BLOCK: + rc = map_block(hdev, args->in.map_block.block_addr, + &block_handle); + args->out.handle = block_handle; + break; + default: dev_err(hdev->dev, "Unknown opcode for memory IOCTL\n"); rc = -ENOTTY; diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c index b49e10394ed4..e1c6072e5fb3 100644 --- a/drivers/misc/habanalabs/gaudi/gaudi.c +++ b/drivers/misc/habanalabs/gaudi/gaudi.c @@ -8471,6 +8471,19 @@ static u64 gaudi_get_device_time(struct hl_device *hdev) return device_time | RREG32(mmPSOC_TIMESTAMP_CNTCVL); } +static int gaudi_get_hw_block_id(struct hl_device *hdev, u64 block_addr, + u32 *block_id) +{ + return -EPERM; +} + +static int gaudi_block_mmap(struct hl_device *hdev, + struct vm_area_struct *vma, + u32 block_id, u32 block_size) +{ + return -EPERM; +} + static const struct hl_asic_funcs gaudi_funcs = { .early_init = gaudi_early_init, .early_fini = gaudi_early_fini, @@ -8550,7 +8563,9 @@ static const struct hl_asic_funcs gaudi_funcs = { .collective_wait_create_jobs = gaudi_collective_wait_create_jobs, .scramble_addr = hl_mmu_scramble_addr, .descramble_addr = hl_mmu_descramble_addr, - .ack_protection_bits_errors = gaudi_ack_protection_bits_errors + .ack_protection_bits_errors = gaudi_ack_protection_bits_errors, + .get_hw_block_id = gaudi_get_hw_block_id, + .hw_block_mmap = gaudi_block_mmap }; /** diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index db951d622ad5..6b4c41188495 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -5382,6 +5382,18 @@ static void goya_ctx_fini(struct hl_ctx *ctx) } +static int goya_get_hw_block_id(struct hl_device *hdev, u64 block_addr, + u32 *block_id) +{ + return -EPERM; +} + +static int goya_block_mmap(struct hl_device *hdev, struct vm_area_struct *vma, + u32 block_id, u32 block_size) +{ + return -EPERM; +} + static const struct hl_asic_funcs goya_funcs = { .early_init = goya_early_init, .early_fini = goya_early_fini, @@ -5461,7 +5473,9 @@ static const struct hl_asic_funcs goya_funcs = { .collective_wait_create_jobs = goya_collective_wait_create_jobs, .scramble_addr = hl_mmu_scramble_addr, .descramble_addr = hl_mmu_descramble_addr, - .ack_protection_bits_errors = goya_ack_protection_bits_errors + .ack_protection_bits_errors = goya_ack_protection_bits_errors, + .get_hw_block_id = goya_get_hw_block_id, + .hw_block_mmap = goya_block_mmap }; /* diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index 866355a53188..b1c09eba8ac2 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -718,6 +718,8 @@ union hl_wait_cs_args { #define HL_MEM_OP_MAP 2 /* Opcode to unmap previously mapped host and device memory */ #define HL_MEM_OP_UNMAP 3 +/* Opcode to map a hw block */ +#define HL_MEM_OP_MAP_BLOCK 4 /* Memory flags */ #define HL_MEM_CONTIGUOUS 0x1 @@ -772,6 +774,17 @@ struct hl_mem_in { __u64 mem_size; } map_host; + /* HL_MEM_OP_MAP_BLOCK - map a hw block */ + struct { + /* + * HW block address to map, a handle will be returned + * to the user and will be used to mmap the relevant + * block. Only addresses from configuration space are + * allowed. + */ + __u64 block_addr; + } map_block; + /* HL_MEM_OP_UNMAP - unmap host memory */ struct { /* Virtual address returned from HL_MEM_OP_MAP */ @@ -798,8 +811,9 @@ struct hl_mem_out { __u64 device_virt_addr; /* - * Used for HL_MEM_OP_ALLOC. This is the assigned - * handle for the allocated memory + * Used for HL_MEM_OP_ALLOC and HL_MEM_OP_MAP_BLOCK. + * This is the assigned handle for the allocated memory + * or mapped block */ __u64 handle; }; -- cgit v1.2.3 From cf30339d3f44a64115e88d46a932fdc3d3644785 Mon Sep 17 00:00:00 2001 From: Ohad Sharabi Date: Sun, 17 Jan 2021 16:01:56 +0200 Subject: habanalabs: modify device_idle interface Currently this API uses single 64 bits mask for engines idle indication. Recently, it was observed that more bits are needed for some ASICs. This patch modifies the use of the idle mask and the idle_extensions mask. Signed-off-by: Ohad Sharabi Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/common/context.c | 9 +++--- drivers/misc/habanalabs/common/debugfs.c | 2 +- drivers/misc/habanalabs/common/habanalabs.h | 4 +-- drivers/misc/habanalabs/common/habanalabs_ioctl.c | 5 +-- drivers/misc/habanalabs/gaudi/gaudi.c | 37 ++++++++++------------- drivers/misc/habanalabs/goya/goya.c | 21 ++++++------- include/uapi/misc/habanalabs.h | 4 ++- 7 files changed, 40 insertions(+), 42 deletions(-) (limited to 'include') diff --git a/drivers/misc/habanalabs/common/context.c b/drivers/misc/habanalabs/common/context.c index 829fe98eed61..cda871afb8f4 100644 --- a/drivers/misc/habanalabs/common/context.c +++ b/drivers/misc/habanalabs/common/context.c @@ -12,7 +12,7 @@ static void hl_ctx_fini(struct hl_ctx *ctx) { struct hl_device *hdev = ctx->hdev; - u64 idle_mask = 0; + u64 idle_mask[HL_BUSY_ENGINES_MASK_EXT_SIZE] = {0}; int i; /* Release all allocated pending cb's, those cb's were never @@ -55,10 +55,11 @@ static void hl_ctx_fini(struct hl_ctx *ctx) if ((!hdev->pldm) && (hdev->pdev) && (!hdev->asic_funcs->is_device_idle(hdev, - &idle_mask, NULL))) + idle_mask, + HL_BUSY_ENGINES_MASK_EXT_SIZE, NULL))) dev_notice(hdev->dev, - "device not idle after user context is closed (0x%llx)\n", - idle_mask); + "device not idle after user context is closed (0x%llx, 0x%llx)\n", + idle_mask[0], idle_mask[1]); } else { dev_dbg(hdev->dev, "closing kernel context\n"); hdev->asic_funcs->ctx_fini(ctx); diff --git a/drivers/misc/habanalabs/common/debugfs.c b/drivers/misc/habanalabs/common/debugfs.c index 9e3c1efe56ba..df847a6d19f4 100644 --- a/drivers/misc/habanalabs/common/debugfs.c +++ b/drivers/misc/habanalabs/common/debugfs.c @@ -414,7 +414,7 @@ static int engines_show(struct seq_file *s, void *data) return 0; } - hdev->asic_funcs->is_device_idle(hdev, NULL, s); + hdev->asic_funcs->is_device_idle(hdev, NULL, 0, s); return 0; } diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h index fd2fffd20ba1..be7947d69dfa 100644 --- a/drivers/misc/habanalabs/common/habanalabs.h +++ b/drivers/misc/habanalabs/common/habanalabs.h @@ -933,8 +933,8 @@ struct hl_asic_funcs { void (*set_clock_gating)(struct hl_device *hdev); void (*disable_clock_gating)(struct hl_device *hdev); int (*debug_coresight)(struct hl_device *hdev, void *data); - bool (*is_device_idle)(struct hl_device *hdev, u64 *mask, - struct seq_file *s); + bool (*is_device_idle)(struct hl_device *hdev, u64 *mask_arr, + u8 mask_len, struct seq_file *s); int (*soft_reset_late_init)(struct hl_device *hdev); void (*hw_queues_lock)(struct hl_device *hdev); void (*hw_queues_unlock)(struct hl_device *hdev); diff --git a/drivers/misc/habanalabs/common/habanalabs_ioctl.c b/drivers/misc/habanalabs/common/habanalabs_ioctl.c index 628bdc56dca3..e86f46d4b613 100644 --- a/drivers/misc/habanalabs/common/habanalabs_ioctl.c +++ b/drivers/misc/habanalabs/common/habanalabs_ioctl.c @@ -145,9 +145,10 @@ static int hw_idle(struct hl_device *hdev, struct hl_info_args *args) return -EINVAL; hw_idle.is_idle = hdev->asic_funcs->is_device_idle(hdev, - &hw_idle.busy_engines_mask_ext, NULL); + hw_idle.busy_engines_mask_ext, + HL_BUSY_ENGINES_MASK_EXT_SIZE, NULL); hw_idle.busy_engines_mask = - lower_32_bits(hw_idle.busy_engines_mask_ext); + lower_32_bits(hw_idle.busy_engines_mask_ext[0]); return copy_to_user(out, &hw_idle, min((size_t) max_size, sizeof(hw_idle))) ? -EFAULT : 0; diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c index e1c6072e5fb3..9a3d2fb477a8 100644 --- a/drivers/misc/habanalabs/gaudi/gaudi.c +++ b/drivers/misc/habanalabs/gaudi/gaudi.c @@ -4538,7 +4538,6 @@ static int gaudi_scrub_device_mem(struct hl_device *hdev, u64 addr, u64 size) { struct asic_fixed_properties *prop = &hdev->asic_prop; struct gaudi_device *gaudi = hdev->asic_specific; - u64 idle_mask = 0; int rc = 0; u64 val = 0; @@ -4551,8 +4550,8 @@ static int gaudi_scrub_device_mem(struct hl_device *hdev, u64 addr, u64 size) hdev, mmDMA0_CORE_STS0/* dummy */, val/* dummy */, - (hdev->asic_funcs->is_device_idle(hdev, - &idle_mask, NULL)), + (hdev->asic_funcs->is_device_idle(hdev, NULL, + 0, NULL)), 1000, HBM_SCRUBBING_TIMEOUT_US); if (rc) { @@ -6423,7 +6422,7 @@ static int gaudi_send_job_on_qman0(struct hl_device *hdev, else timeout = HL_DEVICE_TIMEOUT_USEC; - if (!hdev->asic_funcs->is_device_idle(hdev, NULL, NULL)) { + if (!hdev->asic_funcs->is_device_idle(hdev, NULL, 0, NULL)) { dev_err_ratelimited(hdev->dev, "Can't send driver job on QMAN0 because the device is not idle\n"); return -EBUSY; @@ -7706,13 +7705,14 @@ static int gaudi_cpucp_info_get(struct hl_device *hdev) return 0; } -static bool gaudi_is_device_idle(struct hl_device *hdev, u64 *mask, - struct seq_file *s) +static bool gaudi_is_device_idle(struct hl_device *hdev, u64 *mask_arr, + u8 mask_len, struct seq_file *s) { struct gaudi_device *gaudi = hdev->asic_specific; const char *fmt = "%-5d%-9s%#-14x%#-12x%#x\n"; const char *mme_slave_fmt = "%-5d%-9s%-14s%-12s%#x\n"; const char *nic_fmt = "%-5d%-9s%#-14x%#x\n"; + unsigned long *mask = (unsigned long *)mask_arr; u32 qm_glbl_sts0, qm_cgm_sts, dma_core_sts0, tpc_cfg_sts, mme_arch_sts; bool is_idle = true, is_eng_idle, is_slave; u64 offset; @@ -7738,9 +7738,8 @@ static bool gaudi_is_device_idle(struct hl_device *hdev, u64 *mask, IS_DMA_IDLE(dma_core_sts0); is_idle &= is_eng_idle; - if (mask) - *mask |= ((u64) !is_eng_idle) << - (GAUDI_ENGINE_ID_DMA_0 + dma_id); + if (mask && !is_eng_idle) + set_bit(GAUDI_ENGINE_ID_DMA_0 + dma_id, mask); if (s) seq_printf(s, fmt, dma_id, is_eng_idle ? "Y" : "N", qm_glbl_sts0, @@ -7761,9 +7760,8 @@ static bool gaudi_is_device_idle(struct hl_device *hdev, u64 *mask, IS_TPC_IDLE(tpc_cfg_sts); is_idle &= is_eng_idle; - if (mask) - *mask |= ((u64) !is_eng_idle) << - (GAUDI_ENGINE_ID_TPC_0 + i); + if (mask && !is_eng_idle) + set_bit(GAUDI_ENGINE_ID_TPC_0 + i, mask); if (s) seq_printf(s, fmt, i, is_eng_idle ? "Y" : "N", @@ -7790,9 +7788,8 @@ static bool gaudi_is_device_idle(struct hl_device *hdev, u64 *mask, is_idle &= is_eng_idle; - if (mask) - *mask |= ((u64) !is_eng_idle) << - (GAUDI_ENGINE_ID_MME_0 + i); + if (mask && !is_eng_idle) + set_bit(GAUDI_ENGINE_ID_MME_0 + i, mask); if (s) { if (!is_slave) seq_printf(s, fmt, i, @@ -7818,9 +7815,8 @@ static bool gaudi_is_device_idle(struct hl_device *hdev, u64 *mask, is_eng_idle = IS_QM_IDLE(qm_glbl_sts0, qm_cgm_sts); is_idle &= is_eng_idle; - if (mask) - *mask |= ((u64) !is_eng_idle) << - (GAUDI_ENGINE_ID_NIC_0 + port); + if (mask && !is_eng_idle) + set_bit(GAUDI_ENGINE_ID_NIC_0 + port, mask); if (s) seq_printf(s, nic_fmt, port, is_eng_idle ? "Y" : "N", @@ -7834,9 +7830,8 @@ static bool gaudi_is_device_idle(struct hl_device *hdev, u64 *mask, is_eng_idle = IS_QM_IDLE(qm_glbl_sts0, qm_cgm_sts); is_idle &= is_eng_idle; - if (mask) - *mask |= ((u64) !is_eng_idle) << - (GAUDI_ENGINE_ID_NIC_0 + port); + if (mask && !is_eng_idle) + set_bit(GAUDI_ENGINE_ID_NIC_0 + port, mask); if (s) seq_printf(s, nic_fmt, port, is_eng_idle ? "Y" : "N", diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index 6b4c41188495..a954e7c02375 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -2916,7 +2916,7 @@ static int goya_send_job_on_qman0(struct hl_device *hdev, struct hl_cs_job *job) else timeout = HL_DEVICE_TIMEOUT_USEC; - if (!hdev->asic_funcs->is_device_idle(hdev, NULL, NULL)) { + if (!hdev->asic_funcs->is_device_idle(hdev, NULL, 0, NULL)) { dev_err_ratelimited(hdev->dev, "Can't send driver job on QMAN0 because the device is not idle\n"); return -EBUSY; @@ -5187,11 +5187,12 @@ static void goya_disable_clock_gating(struct hl_device *hdev) /* clock gating not supported in Goya */ } -static bool goya_is_device_idle(struct hl_device *hdev, u64 *mask, - struct seq_file *s) +static bool goya_is_device_idle(struct hl_device *hdev, u64 *mask_arr, + u8 mask_len, struct seq_file *s) { const char *fmt = "%-5d%-9s%#-14x%#-16x%#x\n"; const char *dma_fmt = "%-5d%-9s%#-14x%#x\n"; + unsigned long *mask = (unsigned long *)mask_arr; u32 qm_glbl_sts0, cmdq_glbl_sts0, dma_core_sts0, tpc_cfg_sts, mme_arch_sts; bool is_idle = true, is_eng_idle; @@ -5211,9 +5212,8 @@ static bool goya_is_device_idle(struct hl_device *hdev, u64 *mask, IS_DMA_IDLE(dma_core_sts0); is_idle &= is_eng_idle; - if (mask) - *mask |= ((u64) !is_eng_idle) << - (GOYA_ENGINE_ID_DMA_0 + i); + if (mask && !is_eng_idle) + set_bit(GOYA_ENGINE_ID_DMA_0 + i, mask); if (s) seq_printf(s, dma_fmt, i, is_eng_idle ? "Y" : "N", qm_glbl_sts0, dma_core_sts0); @@ -5235,9 +5235,8 @@ static bool goya_is_device_idle(struct hl_device *hdev, u64 *mask, IS_TPC_IDLE(tpc_cfg_sts); is_idle &= is_eng_idle; - if (mask) - *mask |= ((u64) !is_eng_idle) << - (GOYA_ENGINE_ID_TPC_0 + i); + if (mask && !is_eng_idle) + set_bit(GOYA_ENGINE_ID_TPC_0 + i, mask); if (s) seq_printf(s, fmt, i, is_eng_idle ? "Y" : "N", qm_glbl_sts0, cmdq_glbl_sts0, tpc_cfg_sts); @@ -5256,8 +5255,8 @@ static bool goya_is_device_idle(struct hl_device *hdev, u64 *mask, IS_MME_IDLE(mme_arch_sts); is_idle &= is_eng_idle; - if (mask) - *mask |= ((u64) !is_eng_idle) << GOYA_ENGINE_ID_MME_0; + if (mask && !is_eng_idle) + set_bit(GOYA_ENGINE_ID_MME_0, mask); if (s) { seq_printf(s, fmt, 0, is_eng_idle ? "Y" : "N", qm_glbl_sts0, cmdq_glbl_sts0, mme_arch_sts); diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index b1c09eba8ac2..ebde42b37b43 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -331,6 +331,8 @@ struct hl_info_dram_usage { __u64 ctx_dram_mem; }; +#define HL_BUSY_ENGINES_MASK_EXT_SIZE 2 + struct hl_info_hw_idle { __u32 is_idle; /* @@ -343,7 +345,7 @@ struct hl_info_hw_idle { * Extended Bitmask of busy engines. * Bits definition is according to `enum _enging_id'. */ - __u64 busy_engines_mask_ext; + __u64 busy_engines_mask_ext[HL_BUSY_ENGINES_MASK_EXT_SIZE]; }; struct hl_info_device_status { -- cgit v1.2.3 From e5befc024cb4515d815662ed8746712cc5366bfc Mon Sep 17 00:00:00 2001 From: Eddie James Date: Tue, 22 Dec 2020 09:26:39 -0600 Subject: hwmon: (pmbus) Add a PMBUS_NO_CAPABILITY platform data flag Some PMBus chips don't respond with valid data when reading the CAPABILITY register. Add a flag that device drivers can set so that the PMBus core driver doesn't use CAPABILITY to determine it's behavior. Signed-off-by: Eddie James Link: https://lore.kernel.org/r/20201222152640.27749-2-eajames@linux.ibm.com Signed-off-by: Guenter Roeck --- drivers/hwmon/pmbus/pmbus_core.c | 8 +++++--- include/linux/pmbus.h | 9 +++++++++ 2 files changed, 14 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/hwmon/pmbus/pmbus_core.c b/drivers/hwmon/pmbus/pmbus_core.c index 192442b3b7a2..906c9fec9cce 100644 --- a/drivers/hwmon/pmbus/pmbus_core.c +++ b/drivers/hwmon/pmbus/pmbus_core.c @@ -2204,9 +2204,11 @@ static int pmbus_init_common(struct i2c_client *client, struct pmbus_data *data, } /* Enable PEC if the controller supports it */ - ret = i2c_smbus_read_byte_data(client, PMBUS_CAPABILITY); - if (ret >= 0 && (ret & PB_CAPABILITY_ERROR_CHECK)) - client->flags |= I2C_CLIENT_PEC; + if (!(data->flags & PMBUS_NO_CAPABILITY)) { + ret = i2c_smbus_read_byte_data(client, PMBUS_CAPABILITY); + if (ret >= 0 && (ret & PB_CAPABILITY_ERROR_CHECK)) + client->flags |= I2C_CLIENT_PEC; + } /* * Check if the chip is write protected. If it is, we can not clear diff --git a/include/linux/pmbus.h b/include/linux/pmbus.h index 1ea5bae708a1..12cbbf305969 100644 --- a/include/linux/pmbus.h +++ b/include/linux/pmbus.h @@ -34,6 +34,15 @@ */ #define PMBUS_WRITE_PROTECTED BIT(1) +/* + * PMBUS_NO_CAPABILITY + * + * Some PMBus chips don't respond with valid data when reading the CAPABILITY + * register. For such chips, this flag should be set so that the PMBus core + * driver doesn't use CAPABILITY to determine it's behavior. + */ +#define PMBUS_NO_CAPABILITY BIT(2) + struct pmbus_platform_data { u32 flags; /* Device specific flags */ -- cgit v1.2.3 From 88dde5e23da1a16fe9a417171e6c941736b8d3a6 Mon Sep 17 00:00:00 2001 From: Andre Przywara Date: Wed, 27 Jan 2021 17:24:43 +0000 Subject: clk: sunxi-ng: Add support for the Allwinner H616 CCU While the clocks are fairly similar to the H6, many differ in tiny details, so a separate clock driver seems indicated. Derived from the H6 clock driver, and adjusted according to the manual. Signed-off-by: Andre Przywara Acked-by: Maxime Ripard Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20210127172500.13356-4-andre.przywara@arm.com --- drivers/clk/sunxi-ng/Kconfig | 5 + drivers/clk/sunxi-ng/Makefile | 1 + drivers/clk/sunxi-ng/ccu-sun50i-h616.c | 1150 +++++++++++++++++++++++++++ drivers/clk/sunxi-ng/ccu-sun50i-h616.h | 56 ++ include/dt-bindings/clock/sun50i-h616-ccu.h | 115 +++ include/dt-bindings/reset/sun50i-h616-ccu.h | 70 ++ 6 files changed, 1397 insertions(+) create mode 100644 drivers/clk/sunxi-ng/ccu-sun50i-h616.c create mode 100644 drivers/clk/sunxi-ng/ccu-sun50i-h616.h create mode 100644 include/dt-bindings/clock/sun50i-h616-ccu.h create mode 100644 include/dt-bindings/reset/sun50i-h616-ccu.h (limited to 'include') diff --git a/drivers/clk/sunxi-ng/Kconfig b/drivers/clk/sunxi-ng/Kconfig index feeb8d2074ee..cd46d8853876 100644 --- a/drivers/clk/sunxi-ng/Kconfig +++ b/drivers/clk/sunxi-ng/Kconfig @@ -32,6 +32,11 @@ config SUN50I_H6_CCU default ARM64 && ARCH_SUNXI depends on (ARM64 && ARCH_SUNXI) || COMPILE_TEST +config SUN50I_H616_CCU + bool "Support for the Allwinner H616 CCU" + default ARM64 && ARCH_SUNXI + depends on (ARM64 && ARCH_SUNXI) || COMPILE_TEST + config SUN50I_H6_R_CCU bool "Support for the Allwinner H6 and H616 PRCM CCU" default ARM64 && ARCH_SUNXI diff --git a/drivers/clk/sunxi-ng/Makefile b/drivers/clk/sunxi-ng/Makefile index 3eb5cff40eac..96c324306d97 100644 --- a/drivers/clk/sunxi-ng/Makefile +++ b/drivers/clk/sunxi-ng/Makefile @@ -26,6 +26,7 @@ obj-$(CONFIG_SUN50I_A64_CCU) += ccu-sun50i-a64.o obj-$(CONFIG_SUN50I_A100_CCU) += ccu-sun50i-a100.o obj-$(CONFIG_SUN50I_A100_R_CCU) += ccu-sun50i-a100-r.o obj-$(CONFIG_SUN50I_H6_CCU) += ccu-sun50i-h6.o +obj-$(CONFIG_SUN50I_H616_CCU) += ccu-sun50i-h616.o obj-$(CONFIG_SUN50I_H6_R_CCU) += ccu-sun50i-h6-r.o obj-$(CONFIG_SUN4I_A10_CCU) += ccu-sun4i-a10.o obj-$(CONFIG_SUN5I_CCU) += ccu-sun5i.o diff --git a/drivers/clk/sunxi-ng/ccu-sun50i-h616.c b/drivers/clk/sunxi-ng/ccu-sun50i-h616.c new file mode 100644 index 000000000000..225307305880 --- /dev/null +++ b/drivers/clk/sunxi-ng/ccu-sun50i-h616.c @@ -0,0 +1,1150 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2020 Arm Ltd. + * Based on the H6 CCU driver, which is: + * Copyright (c) 2017 Icenowy Zheng + */ + +#include +#include +#include +#include + +#include "ccu_common.h" +#include "ccu_reset.h" + +#include "ccu_div.h" +#include "ccu_gate.h" +#include "ccu_mp.h" +#include "ccu_mult.h" +#include "ccu_nk.h" +#include "ccu_nkm.h" +#include "ccu_nkmp.h" +#include "ccu_nm.h" + +#include "ccu-sun50i-h616.h" + +/* + * The CPU PLL is actually NP clock, with P being /1, /2 or /4. However + * P should only be used for output frequencies lower than 288 MHz. + * + * For now we can just model it as a multiplier clock, and force P to /1. + * + * The M factor is present in the register's description, but not in the + * frequency formula, and it's documented as "M is only used for backdoor + * testing", so it's not modelled and then force to 0. + */ +#define SUN50I_H616_PLL_CPUX_REG 0x000 +static struct ccu_mult pll_cpux_clk = { + .enable = BIT(31), + .lock = BIT(28), + .mult = _SUNXI_CCU_MULT_MIN(8, 8, 12), + .common = { + .reg = 0x000, + .hw.init = CLK_HW_INIT("pll-cpux", "osc24M", + &ccu_mult_ops, + CLK_SET_RATE_UNGATE), + }, +}; + +/* Some PLLs are input * N / div1 / P. Model them as NKMP with no K */ +#define SUN50I_H616_PLL_DDR0_REG 0x010 +static struct ccu_nkmp pll_ddr0_clk = { + .enable = BIT(31), + .lock = BIT(28), + .n = _SUNXI_CCU_MULT_MIN(8, 8, 12), + .m = _SUNXI_CCU_DIV(1, 1), /* input divider */ + .p = _SUNXI_CCU_DIV(0, 1), /* output divider */ + .common = { + .reg = 0x010, + .hw.init = CLK_HW_INIT("pll-ddr0", "osc24M", + &ccu_nkmp_ops, + CLK_SET_RATE_UNGATE), + }, +}; + +#define SUN50I_H616_PLL_DDR1_REG 0x018 +static struct ccu_nkmp pll_ddr1_clk = { + .enable = BIT(31), + .lock = BIT(28), + .n = _SUNXI_CCU_MULT_MIN(8, 8, 12), + .m = _SUNXI_CCU_DIV(1, 1), /* input divider */ + .p = _SUNXI_CCU_DIV(0, 1), /* output divider */ + .common = { + .reg = 0x018, + .hw.init = CLK_HW_INIT("pll-ddr1", "osc24M", + &ccu_nkmp_ops, + CLK_SET_RATE_UNGATE), + }, +}; + +#define SUN50I_H616_PLL_PERIPH0_REG 0x020 +static struct ccu_nkmp pll_periph0_clk = { + .enable = BIT(31), + .lock = BIT(28), + .n = _SUNXI_CCU_MULT_MIN(8, 8, 12), + .m = _SUNXI_CCU_DIV(1, 1), /* input divider */ + .p = _SUNXI_CCU_DIV(0, 1), /* output divider */ + .fixed_post_div = 2, + .common = { + .reg = 0x020, + .features = CCU_FEATURE_FIXED_POSTDIV, + .hw.init = CLK_HW_INIT("pll-periph0", "osc24M", + &ccu_nkmp_ops, + CLK_SET_RATE_UNGATE), + }, +}; + +#define SUN50I_H616_PLL_PERIPH1_REG 0x028 +static struct ccu_nkmp pll_periph1_clk = { + .enable = BIT(31), + .lock = BIT(28), + .n = _SUNXI_CCU_MULT_MIN(8, 8, 12), + .m = _SUNXI_CCU_DIV(1, 1), /* input divider */ + .p = _SUNXI_CCU_DIV(0, 1), /* output divider */ + .fixed_post_div = 2, + .common = { + .reg = 0x028, + .features = CCU_FEATURE_FIXED_POSTDIV, + .hw.init = CLK_HW_INIT("pll-periph1", "osc24M", + &ccu_nkmp_ops, + CLK_SET_RATE_UNGATE), + }, +}; + +#define SUN50I_H616_PLL_GPU_REG 0x030 +static struct ccu_nkmp pll_gpu_clk = { + .enable = BIT(31), + .lock = BIT(28), + .n = _SUNXI_CCU_MULT_MIN(8, 8, 12), + .m = _SUNXI_CCU_DIV(1, 1), /* input divider */ + .p = _SUNXI_CCU_DIV(0, 1), /* output divider */ + .common = { + .reg = 0x030, + .hw.init = CLK_HW_INIT("pll-gpu", "osc24M", + &ccu_nkmp_ops, + CLK_SET_RATE_UNGATE), + }, +}; + +/* + * For Video PLLs, the output divider is described as "used for testing" + * in the user manual. So it's not modelled and forced to 0. + */ +#define SUN50I_H616_PLL_VIDEO0_REG 0x040 +static struct ccu_nm pll_video0_clk = { + .enable = BIT(31), + .lock = BIT(28), + .n = _SUNXI_CCU_MULT_MIN(8, 8, 12), + .m = _SUNXI_CCU_DIV(1, 1), /* input divider */ + .fixed_post_div = 4, + .min_rate = 288000000, + .max_rate = 2400000000UL, + .common = { + .reg = 0x040, + .features = CCU_FEATURE_FIXED_POSTDIV, + .hw.init = CLK_HW_INIT("pll-video0", "osc24M", + &ccu_nm_ops, + CLK_SET_RATE_UNGATE), + }, +}; + +#define SUN50I_H616_PLL_VIDEO1_REG 0x048 +static struct ccu_nm pll_video1_clk = { + .enable = BIT(31), + .lock = BIT(28), + .n = _SUNXI_CCU_MULT_MIN(8, 8, 12), + .m = _SUNXI_CCU_DIV(1, 1), /* input divider */ + .fixed_post_div = 4, + .min_rate = 288000000, + .max_rate = 2400000000UL, + .common = { + .reg = 0x048, + .features = CCU_FEATURE_FIXED_POSTDIV, + .hw.init = CLK_HW_INIT("pll-video1", "osc24M", + &ccu_nm_ops, + CLK_SET_RATE_UNGATE), + }, +}; + +#define SUN50I_H616_PLL_VIDEO2_REG 0x050 +static struct ccu_nm pll_video2_clk = { + .enable = BIT(31), + .lock = BIT(28), + .n = _SUNXI_CCU_MULT_MIN(8, 8, 12), + .m = _SUNXI_CCU_DIV(1, 1), /* input divider */ + .fixed_post_div = 4, + .min_rate = 288000000, + .max_rate = 2400000000UL, + .common = { + .reg = 0x050, + .features = CCU_FEATURE_FIXED_POSTDIV, + .hw.init = CLK_HW_INIT("pll-video2", "osc24M", + &ccu_nm_ops, + CLK_SET_RATE_UNGATE), + }, +}; + +#define SUN50I_H616_PLL_VE_REG 0x058 +static struct ccu_nkmp pll_ve_clk = { + .enable = BIT(31), + .lock = BIT(28), + .n = _SUNXI_CCU_MULT_MIN(8, 8, 12), + .m = _SUNXI_CCU_DIV(1, 1), /* input divider */ + .p = _SUNXI_CCU_DIV(0, 1), /* output divider */ + .common = { + .reg = 0x058, + .hw.init = CLK_HW_INIT("pll-ve", "osc24M", + &ccu_nkmp_ops, + CLK_SET_RATE_UNGATE), + }, +}; + +#define SUN50I_H616_PLL_DE_REG 0x060 +static struct ccu_nkmp pll_de_clk = { + .enable = BIT(31), + .lock = BIT(28), + .n = _SUNXI_CCU_MULT_MIN(8, 8, 12), + .m = _SUNXI_CCU_DIV(1, 1), /* input divider */ + .p = _SUNXI_CCU_DIV(0, 1), /* output divider */ + .common = { + .reg = 0x060, + .hw.init = CLK_HW_INIT("pll-de", "osc24M", + &ccu_nkmp_ops, + CLK_SET_RATE_UNGATE), + }, +}; + +/* + * TODO: Determine SDM settings for the audio PLL. The manual suggests + * PLL_FACTOR_N=16, PLL_POST_DIV_P=2, OUTPUT_DIV=2, pattern=0xe000c49b + * for 24.576 MHz, and PLL_FACTOR_N=22, PLL_POST_DIV_P=3, OUTPUT_DIV=2, + * pattern=0xe001288c for 22.5792 MHz. + * This clashes with our fixed PLL_POST_DIV_P. + */ +#define SUN50I_H616_PLL_AUDIO_REG 0x078 +static struct ccu_nm pll_audio_hs_clk = { + .enable = BIT(31), + .lock = BIT(28), + .n = _SUNXI_CCU_MULT_MIN(8, 8, 12), + .m = _SUNXI_CCU_DIV(1, 1), /* input divider */ + .common = { + .reg = 0x078, + .hw.init = CLK_HW_INIT("pll-audio-hs", "osc24M", + &ccu_nm_ops, + CLK_SET_RATE_UNGATE), + }, +}; + +static const char * const cpux_parents[] = { "osc24M", "osc32k", + "iosc", "pll-cpux", "pll-periph0" }; +static SUNXI_CCU_MUX(cpux_clk, "cpux", cpux_parents, + 0x500, 24, 3, CLK_SET_RATE_PARENT | CLK_IS_CRITICAL); +static SUNXI_CCU_M(axi_clk, "axi", "cpux", 0x500, 0, 2, 0); +static SUNXI_CCU_M(cpux_apb_clk, "cpux-apb", "cpux", 0x500, 8, 2, 0); + +static const char * const psi_ahb1_ahb2_parents[] = { "osc24M", "osc32k", + "iosc", "pll-periph0" }; +static SUNXI_CCU_MP_WITH_MUX(psi_ahb1_ahb2_clk, "psi-ahb1-ahb2", + psi_ahb1_ahb2_parents, + 0x510, + 0, 2, /* M */ + 8, 2, /* P */ + 24, 2, /* mux */ + 0); + +static const char * const ahb3_apb1_apb2_parents[] = { "osc24M", "osc32k", + "psi-ahb1-ahb2", + "pll-periph0" }; +static SUNXI_CCU_MP_WITH_MUX(ahb3_clk, "ahb3", ahb3_apb1_apb2_parents, 0x51c, + 0, 2, /* M */ + 8, 2, /* P */ + 24, 2, /* mux */ + 0); + +static SUNXI_CCU_MP_WITH_MUX(apb1_clk, "apb1", ahb3_apb1_apb2_parents, 0x520, + 0, 2, /* M */ + 8, 2, /* P */ + 24, 2, /* mux */ + 0); + +static SUNXI_CCU_MP_WITH_MUX(apb2_clk, "apb2", ahb3_apb1_apb2_parents, 0x524, + 0, 2, /* M */ + 8, 2, /* P */ + 24, 2, /* mux */ + 0); + +static const char * const mbus_parents[] = { "osc24M", "pll-periph0-2x", + "pll-ddr0", "pll-ddr1" }; +static SUNXI_CCU_M_WITH_MUX_GATE(mbus_clk, "mbus", mbus_parents, 0x540, + 0, 3, /* M */ + 24, 2, /* mux */ + BIT(31), /* gate */ + CLK_IS_CRITICAL); + +static const char * const de_parents[] = { "pll-de", "pll-periph0-2x" }; +static SUNXI_CCU_M_WITH_MUX_GATE(de_clk, "de", de_parents, 0x600, + 0, 4, /* M */ + 24, 1, /* mux */ + BIT(31), /* gate */ + CLK_SET_RATE_PARENT); + +static SUNXI_CCU_GATE(bus_de_clk, "bus-de", "psi-ahb1-ahb2", + 0x60c, BIT(0), 0); + +static SUNXI_CCU_M_WITH_MUX_GATE(deinterlace_clk, "deinterlace", + de_parents, + 0x620, + 0, 4, /* M */ + 24, 1, /* mux */ + BIT(31), /* gate */ + 0); + +static SUNXI_CCU_GATE(bus_deinterlace_clk, "bus-deinterlace", "psi-ahb1-ahb2", + 0x62c, BIT(0), 0); + +static SUNXI_CCU_M_WITH_MUX_GATE(g2d_clk, "g2d", de_parents, 0x630, + 0, 4, /* M */ + 24, 1, /* mux */ + BIT(31), /* gate */ + 0); + +static SUNXI_CCU_GATE(bus_g2d_clk, "bus-g2d", "psi-ahb1-ahb2", + 0x63c, BIT(0), 0); + +static const char * const gpu0_parents[] = { "pll-gpu", "gpu1" }; +static SUNXI_CCU_M_WITH_MUX_GATE(gpu0_clk, "gpu0", gpu0_parents, 0x670, + 0, 2, /* M */ + 24, 1, /* mux */ + BIT(31), /* gate */ + CLK_SET_RATE_PARENT); +static SUNXI_CCU_M_WITH_GATE(gpu1_clk, "gpu1", "pll-periph0-2x", 0x674, + 0, 2, /* M */ + BIT(31),/* gate */ + 0); + +static SUNXI_CCU_GATE(bus_gpu_clk, "bus-gpu", "psi-ahb1-ahb2", + 0x67c, BIT(0), 0); + +static const char * const ce_parents[] = { "osc24M", "pll-periph0-2x" }; +static SUNXI_CCU_MP_WITH_MUX_GATE(ce_clk, "ce", ce_parents, 0x680, + 0, 4, /* M */ + 8, 2, /* N */ + 24, 1, /* mux */ + BIT(31),/* gate */ + 0); + +static SUNXI_CCU_GATE(bus_ce_clk, "bus-ce", "psi-ahb1-ahb2", + 0x68c, BIT(0), 0); + +static const char * const ve_parents[] = { "pll-ve" }; +static SUNXI_CCU_M_WITH_MUX_GATE(ve_clk, "ve", ve_parents, 0x690, + 0, 3, /* M */ + 24, 1, /* mux */ + BIT(31), /* gate */ + CLK_SET_RATE_PARENT); + +static SUNXI_CCU_GATE(bus_ve_clk, "bus-ve", "psi-ahb1-ahb2", + 0x69c, BIT(0), 0); + +static SUNXI_CCU_GATE(bus_dma_clk, "bus-dma", "psi-ahb1-ahb2", + 0x70c, BIT(0), 0); + +static SUNXI_CCU_GATE(bus_hstimer_clk, "bus-hstimer", "psi-ahb1-ahb2", + 0x73c, BIT(0), 0); + +static SUNXI_CCU_GATE(avs_clk, "avs", "osc24M", 0x740, BIT(31), 0); + +static SUNXI_CCU_GATE(bus_dbg_clk, "bus-dbg", "psi-ahb1-ahb2", + 0x78c, BIT(0), 0); + +static SUNXI_CCU_GATE(bus_psi_clk, "bus-psi", "psi-ahb1-ahb2", + 0x79c, BIT(0), 0); + +static SUNXI_CCU_GATE(bus_pwm_clk, "bus-pwm", "apb1", 0x7ac, BIT(0), 0); + +static SUNXI_CCU_GATE(bus_iommu_clk, "bus-iommu", "apb1", 0x7bc, BIT(0), 0); + +static const char * const dram_parents[] = { "pll-ddr0", "pll-ddr1" }; +static struct ccu_div dram_clk = { + .div = _SUNXI_CCU_DIV(0, 2), + .mux = _SUNXI_CCU_MUX(24, 2), + .common = { + .reg = 0x800, + .hw.init = CLK_HW_INIT_PARENTS("dram", + dram_parents, + &ccu_div_ops, + CLK_IS_CRITICAL), + }, +}; + +static SUNXI_CCU_GATE(mbus_dma_clk, "mbus-dma", "mbus", + 0x804, BIT(0), 0); +static SUNXI_CCU_GATE(mbus_ve_clk, "mbus-ve", "mbus", + 0x804, BIT(1), 0); +static SUNXI_CCU_GATE(mbus_ce_clk, "mbus-ce", "mbus", + 0x804, BIT(2), 0); +static SUNXI_CCU_GATE(mbus_ts_clk, "mbus-ts", "mbus", + 0x804, BIT(3), 0); +static SUNXI_CCU_GATE(mbus_nand_clk, "mbus-nand", "mbus", + 0x804, BIT(5), 0); +static SUNXI_CCU_GATE(mbus_g2d_clk, "mbus-g2d", "mbus", + 0x804, BIT(10), 0); + +static SUNXI_CCU_GATE(bus_dram_clk, "bus-dram", "psi-ahb1-ahb2", + 0x80c, BIT(0), CLK_IS_CRITICAL); + +static const char * const nand_spi_parents[] = { "osc24M", "pll-periph0", + "pll-periph1", "pll-periph0-2x", + "pll-periph1-2x" }; +static SUNXI_CCU_MP_WITH_MUX_GATE(nand0_clk, "nand0", nand_spi_parents, 0x810, + 0, 4, /* M */ + 8, 2, /* N */ + 24, 3, /* mux */ + BIT(31),/* gate */ + 0); + +static SUNXI_CCU_MP_WITH_MUX_GATE(nand1_clk, "nand1", nand_spi_parents, 0x814, + 0, 4, /* M */ + 8, 2, /* N */ + 24, 3, /* mux */ + BIT(31),/* gate */ + 0); + +static SUNXI_CCU_GATE(bus_nand_clk, "bus-nand", "ahb3", 0x82c, BIT(0), 0); + +static const char * const mmc_parents[] = { "osc24M", "pll-periph0-2x", + "pll-periph1-2x" }; +static SUNXI_CCU_MP_WITH_MUX_GATE_POSTDIV(mmc0_clk, "mmc0", mmc_parents, 0x830, + 0, 4, /* M */ + 8, 2, /* N */ + 24, 2, /* mux */ + BIT(31), /* gate */ + 2, /* post-div */ + 0); + +static SUNXI_CCU_MP_WITH_MUX_GATE_POSTDIV(mmc1_clk, "mmc1", mmc_parents, 0x834, + 0, 4, /* M */ + 8, 2, /* N */ + 24, 2, /* mux */ + BIT(31), /* gate */ + 2, /* post-div */ + 0); + +static SUNXI_CCU_MP_WITH_MUX_GATE_POSTDIV(mmc2_clk, "mmc2", mmc_parents, 0x838, + 0, 4, /* M */ + 8, 2, /* N */ + 24, 2, /* mux */ + BIT(31), /* gate */ + 2, /* post-div */ + 0); + +static SUNXI_CCU_GATE(bus_mmc0_clk, "bus-mmc0", "ahb3", 0x84c, BIT(0), 0); +static SUNXI_CCU_GATE(bus_mmc1_clk, "bus-mmc1", "ahb3", 0x84c, BIT(1), 0); +static SUNXI_CCU_GATE(bus_mmc2_clk, "bus-mmc2", "ahb3", 0x84c, BIT(2), 0); + +static SUNXI_CCU_GATE(bus_uart0_clk, "bus-uart0", "apb2", 0x90c, BIT(0), 0); +static SUNXI_CCU_GATE(bus_uart1_clk, "bus-uart1", "apb2", 0x90c, BIT(1), 0); +static SUNXI_CCU_GATE(bus_uart2_clk, "bus-uart2", "apb2", 0x90c, BIT(2), 0); +static SUNXI_CCU_GATE(bus_uart3_clk, "bus-uart3", "apb2", 0x90c, BIT(3), 0); +static SUNXI_CCU_GATE(bus_uart4_clk, "bus-uart4", "apb2", 0x90c, BIT(4), 0); +static SUNXI_CCU_GATE(bus_uart5_clk, "bus-uart5", "apb2", 0x90c, BIT(5), 0); + +static SUNXI_CCU_GATE(bus_i2c0_clk, "bus-i2c0", "apb2", 0x91c, BIT(0), 0); +static SUNXI_CCU_GATE(bus_i2c1_clk, "bus-i2c1", "apb2", 0x91c, BIT(1), 0); +static SUNXI_CCU_GATE(bus_i2c2_clk, "bus-i2c2", "apb2", 0x91c, BIT(2), 0); +static SUNXI_CCU_GATE(bus_i2c3_clk, "bus-i2c3", "apb2", 0x91c, BIT(3), 0); +static SUNXI_CCU_GATE(bus_i2c4_clk, "bus-i2c4", "apb2", 0x91c, BIT(4), 0); + +static SUNXI_CCU_MP_WITH_MUX_GATE(spi0_clk, "spi0", nand_spi_parents, 0x940, + 0, 4, /* M */ + 8, 2, /* N */ + 24, 3, /* mux */ + BIT(31),/* gate */ + 0); + +static SUNXI_CCU_MP_WITH_MUX_GATE(spi1_clk, "spi1", nand_spi_parents, 0x944, + 0, 4, /* M */ + 8, 2, /* N */ + 24, 3, /* mux */ + BIT(31),/* gate */ + 0); + +static SUNXI_CCU_GATE(bus_spi0_clk, "bus-spi0", "ahb3", 0x96c, BIT(0), 0); +static SUNXI_CCU_GATE(bus_spi1_clk, "bus-spi1", "ahb3", 0x96c, BIT(1), 0); + +static SUNXI_CCU_GATE(emac_25m_clk, "emac-25m", "ahb3", 0x970, + BIT(31) | BIT(30), 0); + +static SUNXI_CCU_GATE(bus_emac0_clk, "bus-emac0", "ahb3", 0x97c, BIT(0), 0); +static SUNXI_CCU_GATE(bus_emac1_clk, "bus-emac1", "ahb3", 0x97c, BIT(1), 0); + +static const char * const ts_parents[] = { "osc24M", "pll-periph0" }; +static SUNXI_CCU_MP_WITH_MUX_GATE(ts_clk, "ts", ts_parents, 0x9b0, + 0, 4, /* M */ + 8, 2, /* N */ + 24, 1, /* mux */ + BIT(31),/* gate */ + 0); + +static SUNXI_CCU_GATE(bus_ts_clk, "bus-ts", "ahb3", 0x9bc, BIT(0), 0); + +static SUNXI_CCU_GATE(bus_ths_clk, "bus-ths", "apb1", 0x9fc, BIT(0), 0); + +static const char * const audio_parents[] = { "pll-audio-1x", "pll-audio-2x", + "pll-audio-4x", "pll-audio-hs" }; +static struct ccu_div spdif_clk = { + .enable = BIT(31), + .div = _SUNXI_CCU_DIV_FLAGS(8, 2, CLK_DIVIDER_POWER_OF_TWO), + .mux = _SUNXI_CCU_MUX(24, 2), + .common = { + .reg = 0xa20, + .hw.init = CLK_HW_INIT_PARENTS("spdif", + audio_parents, + &ccu_div_ops, + 0), + }, +}; + +static SUNXI_CCU_GATE(bus_spdif_clk, "bus-spdif", "apb1", 0xa2c, BIT(0), 0); + +static struct ccu_div dmic_clk = { + .enable = BIT(31), + .div = _SUNXI_CCU_DIV_FLAGS(8, 2, CLK_DIVIDER_POWER_OF_TWO), + .mux = _SUNXI_CCU_MUX(24, 2), + .common = { + .reg = 0xa40, + .hw.init = CLK_HW_INIT_PARENTS("dmic", + audio_parents, + &ccu_div_ops, + 0), + }, +}; + +static SUNXI_CCU_GATE(bus_dmic_clk, "bus-dmic", "apb1", 0xa4c, BIT(0), 0); + +static SUNXI_CCU_M_WITH_MUX_GATE(audio_codec_1x_clk, "audio-codec-1x", + audio_parents, 0xa50, + 0, 4, /* M */ + 24, 2, /* mux */ + BIT(31), /* gate */ + CLK_SET_RATE_PARENT); +static SUNXI_CCU_M_WITH_MUX_GATE(audio_codec_4x_clk, "audio-codec-4x", + audio_parents, 0xa54, + 0, 4, /* M */ + 24, 2, /* mux */ + BIT(31), /* gate */ + CLK_SET_RATE_PARENT); + +static SUNXI_CCU_GATE(bus_audio_codec_clk, "bus-audio-codec", "apb1", 0xa5c, + BIT(0), 0); + +static struct ccu_div audio_hub_clk = { + .enable = BIT(31), + .div = _SUNXI_CCU_DIV_FLAGS(8, 2, CLK_DIVIDER_POWER_OF_TWO), + .mux = _SUNXI_CCU_MUX(24, 2), + .common = { + .reg = 0xa60, + .hw.init = CLK_HW_INIT_PARENTS("audio-hub", + audio_parents, + &ccu_div_ops, + 0), + }, +}; + +static SUNXI_CCU_GATE(bus_audio_hub_clk, "bus-audio-hub", "apb1", 0xa6c, BIT(0), 0); + +/* + * There are OHCI 12M clock source selection bits for the four USB 2.0 ports. + * We will force them to 0 (12M divided from 48M). + */ +#define SUN50I_H616_USB0_CLK_REG 0xa70 +#define SUN50I_H616_USB1_CLK_REG 0xa74 +#define SUN50I_H616_USB2_CLK_REG 0xa78 +#define SUN50I_H616_USB3_CLK_REG 0xa7c + +static SUNXI_CCU_GATE(usb_ohci0_clk, "usb-ohci0", "osc12M", 0xa70, BIT(31), 0); +static SUNXI_CCU_GATE(usb_phy0_clk, "usb-phy0", "osc24M", 0xa70, BIT(29), 0); + +static SUNXI_CCU_GATE(usb_ohci1_clk, "usb-ohci1", "osc12M", 0xa74, BIT(31), 0); +static SUNXI_CCU_GATE(usb_phy1_clk, "usb-phy1", "osc24M", 0xa74, BIT(29), 0); + +static SUNXI_CCU_GATE(usb_ohci2_clk, "usb-ohci2", "osc12M", 0xa78, BIT(31), 0); +static SUNXI_CCU_GATE(usb_phy2_clk, "usb-phy2", "osc24M", 0xa78, BIT(29), 0); + +static SUNXI_CCU_GATE(usb_ohci3_clk, "usb-ohci3", "osc12M", 0xa7c, BIT(31), 0); +static SUNXI_CCU_GATE(usb_phy3_clk, "usb-phy3", "osc24M", 0xa7c, BIT(29), 0); + +static SUNXI_CCU_GATE(bus_ohci0_clk, "bus-ohci0", "ahb3", 0xa8c, BIT(0), 0); +static SUNXI_CCU_GATE(bus_ohci1_clk, "bus-ohci1", "ahb3", 0xa8c, BIT(1), 0); +static SUNXI_CCU_GATE(bus_ohci2_clk, "bus-ohci2", "ahb3", 0xa8c, BIT(2), 0); +static SUNXI_CCU_GATE(bus_ohci3_clk, "bus-ohci3", "ahb3", 0xa8c, BIT(3), 0); +static SUNXI_CCU_GATE(bus_ehci0_clk, "bus-ehci0", "ahb3", 0xa8c, BIT(4), 0); +static SUNXI_CCU_GATE(bus_ehci1_clk, "bus-ehci1", "ahb3", 0xa8c, BIT(5), 0); +static SUNXI_CCU_GATE(bus_ehci2_clk, "bus-ehci2", "ahb3", 0xa8c, BIT(6), 0); +static SUNXI_CCU_GATE(bus_ehci3_clk, "bus-ehci3", "ahb3", 0xa8c, BIT(7), 0); +static SUNXI_CCU_GATE(bus_otg_clk, "bus-otg", "ahb3", 0xa8c, BIT(8), 0); + +static SUNXI_CCU_GATE(bus_keyadc_clk, "bus-keyadc", "apb1", 0xa9c, BIT(0), 0); + +static const char * const hdmi_parents[] = { "pll-video0", "pll-video0-4x", + "pll-video2", "pll-video2-4x" }; +static SUNXI_CCU_M_WITH_MUX_GATE(hdmi_clk, "hdmi", hdmi_parents, 0xb00, + 0, 4, /* M */ + 24, 2, /* mux */ + BIT(31), /* gate */ + 0); + +static SUNXI_CCU_GATE(hdmi_slow_clk, "hdmi-slow", "osc24M", 0xb04, BIT(31), 0); + +static const char * const hdmi_cec_parents[] = { "osc32k", "pll-periph0-2x" }; +static const struct ccu_mux_fixed_prediv hdmi_cec_predivs[] = { + { .index = 1, .div = 36621 }, +}; + +#define SUN50I_H616_HDMI_CEC_CLK_REG 0xb10 +static struct ccu_mux hdmi_cec_clk = { + .enable = BIT(31) | BIT(30), + + .mux = { + .shift = 24, + .width = 2, + + .fixed_predivs = hdmi_cec_predivs, + .n_predivs = ARRAY_SIZE(hdmi_cec_predivs), + }, + + .common = { + .reg = 0xb10, + .features = CCU_FEATURE_FIXED_PREDIV, + .hw.init = CLK_HW_INIT_PARENTS("hdmi-cec", + hdmi_cec_parents, + &ccu_mux_ops, + 0), + }, +}; + +static SUNXI_CCU_GATE(bus_hdmi_clk, "bus-hdmi", "ahb3", 0xb1c, BIT(0), 0); + +static SUNXI_CCU_GATE(bus_tcon_top_clk, "bus-tcon-top", "ahb3", + 0xb5c, BIT(0), 0); + +static const char * const tcon_tv_parents[] = { "pll-video0", + "pll-video0-4x", + "pll-video1", + "pll-video1-4x" }; +static SUNXI_CCU_MP_WITH_MUX_GATE(tcon_tv0_clk, "tcon-tv0", + tcon_tv_parents, 0xb80, + 0, 4, /* M */ + 8, 2, /* P */ + 24, 3, /* mux */ + BIT(31), /* gate */ + CLK_SET_RATE_PARENT); +static SUNXI_CCU_MP_WITH_MUX_GATE(tcon_tv1_clk, "tcon-tv1", + tcon_tv_parents, 0xb84, + 0, 4, /* M */ + 8, 2, /* P */ + 24, 3, /* mux */ + BIT(31), /* gate */ + CLK_SET_RATE_PARENT); + +static SUNXI_CCU_GATE(bus_tcon_tv0_clk, "bus-tcon-tv0", "ahb3", + 0xb9c, BIT(0), 0); +static SUNXI_CCU_GATE(bus_tcon_tv1_clk, "bus-tcon-tv1", "ahb3", + 0xb9c, BIT(1), 0); + +static SUNXI_CCU_MP_WITH_MUX_GATE(tve0_clk, "tve0", + tcon_tv_parents, 0xbb0, + 0, 4, /* M */ + 8, 2, /* P */ + 24, 3, /* mux */ + BIT(31), /* gate */ + CLK_SET_RATE_PARENT); + +static SUNXI_CCU_GATE(bus_tve_top_clk, "bus-tve-top", "ahb3", + 0xbbc, BIT(0), 0); +static SUNXI_CCU_GATE(bus_tve0_clk, "bus-tve0", "ahb3", + 0xbbc, BIT(1), 0); + +static const char * const hdcp_parents[] = { "pll-periph0", "pll-periph1" }; +static SUNXI_CCU_M_WITH_MUX_GATE(hdcp_clk, "hdcp", hdcp_parents, 0xc40, + 0, 4, /* M */ + 24, 2, /* mux */ + BIT(31), /* gate */ + 0); + +static SUNXI_CCU_GATE(bus_hdcp_clk, "bus-hdcp", "ahb3", 0xc4c, BIT(0), 0); + +/* Fixed factor clocks */ +static CLK_FIXED_FACTOR_FW_NAME(osc12M_clk, "osc12M", "hosc", 2, 1, 0); + +static const struct clk_hw *clk_parent_pll_audio[] = { + &pll_audio_hs_clk.common.hw +}; + +/* + * The divider of pll-audio is fixed to 24 for now, so 24576000 and 22579200 + * rates can be set exactly in conjunction with sigma-delta modulation. + */ +static CLK_FIXED_FACTOR_HWS(pll_audio_1x_clk, "pll-audio-1x", + clk_parent_pll_audio, + 96, 1, CLK_SET_RATE_PARENT); +static CLK_FIXED_FACTOR_HWS(pll_audio_2x_clk, "pll-audio-2x", + clk_parent_pll_audio, + 48, 1, CLK_SET_RATE_PARENT); +static CLK_FIXED_FACTOR_HWS(pll_audio_4x_clk, "pll-audio-4x", + clk_parent_pll_audio, + 24, 1, CLK_SET_RATE_PARENT); + +static const struct clk_hw *pll_periph0_parents[] = { + &pll_periph0_clk.common.hw +}; + +static CLK_FIXED_FACTOR_HWS(pll_periph0_2x_clk, "pll-periph0-2x", + pll_periph0_parents, + 1, 2, 0); + +static const struct clk_hw *pll_periph1_parents[] = { + &pll_periph1_clk.common.hw +}; + +static CLK_FIXED_FACTOR_HWS(pll_periph1_2x_clk, "pll-periph1-2x", + pll_periph1_parents, + 1, 2, 0); + +static CLK_FIXED_FACTOR_HW(pll_video0_4x_clk, "pll-video0-4x", + &pll_video0_clk.common.hw, + 1, 4, CLK_SET_RATE_PARENT); +static CLK_FIXED_FACTOR_HW(pll_video1_4x_clk, "pll-video1-4x", + &pll_video1_clk.common.hw, + 1, 4, CLK_SET_RATE_PARENT); +static CLK_FIXED_FACTOR_HW(pll_video2_4x_clk, "pll-video2-4x", + &pll_video2_clk.common.hw, + 1, 4, CLK_SET_RATE_PARENT); + +static struct ccu_common *sun50i_h616_ccu_clks[] = { + &pll_cpux_clk.common, + &pll_ddr0_clk.common, + &pll_ddr1_clk.common, + &pll_periph0_clk.common, + &pll_periph1_clk.common, + &pll_gpu_clk.common, + &pll_video0_clk.common, + &pll_video1_clk.common, + &pll_video2_clk.common, + &pll_ve_clk.common, + &pll_de_clk.common, + &pll_audio_hs_clk.common, + &cpux_clk.common, + &axi_clk.common, + &cpux_apb_clk.common, + &psi_ahb1_ahb2_clk.common, + &ahb3_clk.common, + &apb1_clk.common, + &apb2_clk.common, + &mbus_clk.common, + &de_clk.common, + &bus_de_clk.common, + &deinterlace_clk.common, + &bus_deinterlace_clk.common, + &g2d_clk.common, + &bus_g2d_clk.common, + &gpu0_clk.common, + &bus_gpu_clk.common, + &gpu1_clk.common, + &ce_clk.common, + &bus_ce_clk.common, + &ve_clk.common, + &bus_ve_clk.common, + &bus_dma_clk.common, + &bus_hstimer_clk.common, + &avs_clk.common, + &bus_dbg_clk.common, + &bus_psi_clk.common, + &bus_pwm_clk.common, + &bus_iommu_clk.common, + &dram_clk.common, + &mbus_dma_clk.common, + &mbus_ve_clk.common, + &mbus_ce_clk.common, + &mbus_ts_clk.common, + &mbus_nand_clk.common, + &mbus_g2d_clk.common, + &bus_dram_clk.common, + &nand0_clk.common, + &nand1_clk.common, + &bus_nand_clk.common, + &mmc0_clk.common, + &mmc1_clk.common, + &mmc2_clk.common, + &bus_mmc0_clk.common, + &bus_mmc1_clk.common, + &bus_mmc2_clk.common, + &bus_uart0_clk.common, + &bus_uart1_clk.common, + &bus_uart2_clk.common, + &bus_uart3_clk.common, + &bus_uart4_clk.common, + &bus_uart5_clk.common, + &bus_i2c0_clk.common, + &bus_i2c1_clk.common, + &bus_i2c2_clk.common, + &bus_i2c3_clk.common, + &bus_i2c4_clk.common, + &spi0_clk.common, + &spi1_clk.common, + &bus_spi0_clk.common, + &bus_spi1_clk.common, + &emac_25m_clk.common, + &bus_emac0_clk.common, + &bus_emac1_clk.common, + &ts_clk.common, + &bus_ts_clk.common, + &bus_ths_clk.common, + &spdif_clk.common, + &bus_spdif_clk.common, + &dmic_clk.common, + &bus_dmic_clk.common, + &audio_codec_1x_clk.common, + &audio_codec_4x_clk.common, + &bus_audio_codec_clk.common, + &audio_hub_clk.common, + &bus_audio_hub_clk.common, + &usb_ohci0_clk.common, + &usb_phy0_clk.common, + &usb_ohci1_clk.common, + &usb_phy1_clk.common, + &usb_ohci2_clk.common, + &usb_phy2_clk.common, + &usb_ohci3_clk.common, + &usb_phy3_clk.common, + &bus_ohci0_clk.common, + &bus_ohci1_clk.common, + &bus_ohci2_clk.common, + &bus_ohci3_clk.common, + &bus_ehci0_clk.common, + &bus_ehci1_clk.common, + &bus_ehci2_clk.common, + &bus_ehci3_clk.common, + &bus_otg_clk.common, + &bus_keyadc_clk.common, + &hdmi_clk.common, + &hdmi_slow_clk.common, + &hdmi_cec_clk.common, + &bus_hdmi_clk.common, + &bus_tcon_top_clk.common, + &tcon_tv0_clk.common, + &tcon_tv1_clk.common, + &bus_tcon_tv0_clk.common, + &bus_tcon_tv1_clk.common, + &tve0_clk.common, + &bus_tve_top_clk.common, + &bus_tve0_clk.common, + &hdcp_clk.common, + &bus_hdcp_clk.common, +}; + +static struct clk_hw_onecell_data sun50i_h616_hw_clks = { + .hws = { + [CLK_OSC12M] = &osc12M_clk.hw, + [CLK_PLL_CPUX] = &pll_cpux_clk.common.hw, + [CLK_PLL_DDR0] = &pll_ddr0_clk.common.hw, + [CLK_PLL_DDR1] = &pll_ddr1_clk.common.hw, + [CLK_PLL_PERIPH0] = &pll_periph0_clk.common.hw, + [CLK_PLL_PERIPH0_2X] = &pll_periph0_2x_clk.hw, + [CLK_PLL_PERIPH1] = &pll_periph1_clk.common.hw, + [CLK_PLL_PERIPH1_2X] = &pll_periph1_2x_clk.hw, + [CLK_PLL_GPU] = &pll_gpu_clk.common.hw, + [CLK_PLL_VIDEO0] = &pll_video0_clk.common.hw, + [CLK_PLL_VIDEO0_4X] = &pll_video0_4x_clk.hw, + [CLK_PLL_VIDEO1] = &pll_video1_clk.common.hw, + [CLK_PLL_VIDEO1_4X] = &pll_video1_4x_clk.hw, + [CLK_PLL_VIDEO2] = &pll_video2_clk.common.hw, + [CLK_PLL_VIDEO2_4X] = &pll_video2_4x_clk.hw, + [CLK_PLL_VE] = &pll_ve_clk.common.hw, + [CLK_PLL_DE] = &pll_de_clk.common.hw, + [CLK_PLL_AUDIO_HS] = &pll_audio_hs_clk.common.hw, + [CLK_PLL_AUDIO_1X] = &pll_audio_1x_clk.hw, + [CLK_PLL_AUDIO_2X] = &pll_audio_2x_clk.hw, + [CLK_PLL_AUDIO_4X] = &pll_audio_4x_clk.hw, + [CLK_CPUX] = &cpux_clk.common.hw, + [CLK_AXI] = &axi_clk.common.hw, + [CLK_CPUX_APB] = &cpux_apb_clk.common.hw, + [CLK_PSI_AHB1_AHB2] = &psi_ahb1_ahb2_clk.common.hw, + [CLK_AHB3] = &ahb3_clk.common.hw, + [CLK_APB1] = &apb1_clk.common.hw, + [CLK_APB2] = &apb2_clk.common.hw, + [CLK_MBUS] = &mbus_clk.common.hw, + [CLK_DE] = &de_clk.common.hw, + [CLK_BUS_DE] = &bus_de_clk.common.hw, + [CLK_DEINTERLACE] = &deinterlace_clk.common.hw, + [CLK_BUS_DEINTERLACE] = &bus_deinterlace_clk.common.hw, + [CLK_G2D] = &g2d_clk.common.hw, + [CLK_BUS_G2D] = &bus_g2d_clk.common.hw, + [CLK_GPU0] = &gpu0_clk.common.hw, + [CLK_BUS_GPU] = &bus_gpu_clk.common.hw, + [CLK_GPU1] = &gpu1_clk.common.hw, + [CLK_CE] = &ce_clk.common.hw, + [CLK_BUS_CE] = &bus_ce_clk.common.hw, + [CLK_VE] = &ve_clk.common.hw, + [CLK_BUS_VE] = &bus_ve_clk.common.hw, + [CLK_BUS_DMA] = &bus_dma_clk.common.hw, + [CLK_BUS_HSTIMER] = &bus_hstimer_clk.common.hw, + [CLK_AVS] = &avs_clk.common.hw, + [CLK_BUS_DBG] = &bus_dbg_clk.common.hw, + [CLK_BUS_PSI] = &bus_psi_clk.common.hw, + [CLK_BUS_PWM] = &bus_pwm_clk.common.hw, + [CLK_BUS_IOMMU] = &bus_iommu_clk.common.hw, + [CLK_DRAM] = &dram_clk.common.hw, + [CLK_MBUS_DMA] = &mbus_dma_clk.common.hw, + [CLK_MBUS_VE] = &mbus_ve_clk.common.hw, + [CLK_MBUS_CE] = &mbus_ce_clk.common.hw, + [CLK_MBUS_TS] = &mbus_ts_clk.common.hw, + [CLK_MBUS_NAND] = &mbus_nand_clk.common.hw, + [CLK_MBUS_G2D] = &mbus_g2d_clk.common.hw, + [CLK_BUS_DRAM] = &bus_dram_clk.common.hw, + [CLK_NAND0] = &nand0_clk.common.hw, + [CLK_NAND1] = &nand1_clk.common.hw, + [CLK_BUS_NAND] = &bus_nand_clk.common.hw, + [CLK_MMC0] = &mmc0_clk.common.hw, + [CLK_MMC1] = &mmc1_clk.common.hw, + [CLK_MMC2] = &mmc2_clk.common.hw, + [CLK_BUS_MMC0] = &bus_mmc0_clk.common.hw, + [CLK_BUS_MMC1] = &bus_mmc1_clk.common.hw, + [CLK_BUS_MMC2] = &bus_mmc2_clk.common.hw, + [CLK_BUS_UART0] = &bus_uart0_clk.common.hw, + [CLK_BUS_UART1] = &bus_uart1_clk.common.hw, + [CLK_BUS_UART2] = &bus_uart2_clk.common.hw, + [CLK_BUS_UART3] = &bus_uart3_clk.common.hw, + [CLK_BUS_UART4] = &bus_uart4_clk.common.hw, + [CLK_BUS_UART5] = &bus_uart5_clk.common.hw, + [CLK_BUS_I2C0] = &bus_i2c0_clk.common.hw, + [CLK_BUS_I2C1] = &bus_i2c1_clk.common.hw, + [CLK_BUS_I2C2] = &bus_i2c2_clk.common.hw, + [CLK_BUS_I2C3] = &bus_i2c3_clk.common.hw, + [CLK_BUS_I2C4] = &bus_i2c4_clk.common.hw, + [CLK_SPI0] = &spi0_clk.common.hw, + [CLK_SPI1] = &spi1_clk.common.hw, + [CLK_BUS_SPI0] = &bus_spi0_clk.common.hw, + [CLK_BUS_SPI1] = &bus_spi1_clk.common.hw, + [CLK_EMAC_25M] = &emac_25m_clk.common.hw, + [CLK_BUS_EMAC0] = &bus_emac0_clk.common.hw, + [CLK_BUS_EMAC1] = &bus_emac1_clk.common.hw, + [CLK_TS] = &ts_clk.common.hw, + [CLK_BUS_TS] = &bus_ts_clk.common.hw, + [CLK_BUS_THS] = &bus_ths_clk.common.hw, + [CLK_SPDIF] = &spdif_clk.common.hw, + [CLK_BUS_SPDIF] = &bus_spdif_clk.common.hw, + [CLK_DMIC] = &dmic_clk.common.hw, + [CLK_BUS_DMIC] = &bus_dmic_clk.common.hw, + [CLK_AUDIO_CODEC_1X] = &audio_codec_1x_clk.common.hw, + [CLK_AUDIO_CODEC_4X] = &audio_codec_4x_clk.common.hw, + [CLK_BUS_AUDIO_CODEC] = &bus_audio_codec_clk.common.hw, + [CLK_AUDIO_HUB] = &audio_hub_clk.common.hw, + [CLK_BUS_AUDIO_HUB] = &bus_audio_hub_clk.common.hw, + [CLK_USB_OHCI0] = &usb_ohci0_clk.common.hw, + [CLK_USB_PHY0] = &usb_phy0_clk.common.hw, + [CLK_USB_OHCI1] = &usb_ohci1_clk.common.hw, + [CLK_USB_PHY1] = &usb_phy1_clk.common.hw, + [CLK_USB_OHCI2] = &usb_ohci2_clk.common.hw, + [CLK_USB_PHY2] = &usb_phy2_clk.common.hw, + [CLK_USB_OHCI3] = &usb_ohci3_clk.common.hw, + [CLK_USB_PHY3] = &usb_phy3_clk.common.hw, + [CLK_BUS_OHCI0] = &bus_ohci0_clk.common.hw, + [CLK_BUS_OHCI1] = &bus_ohci1_clk.common.hw, + [CLK_BUS_OHCI2] = &bus_ohci2_clk.common.hw, + [CLK_BUS_OHCI3] = &bus_ohci3_clk.common.hw, + [CLK_BUS_EHCI0] = &bus_ehci0_clk.common.hw, + [CLK_BUS_EHCI1] = &bus_ehci1_clk.common.hw, + [CLK_BUS_EHCI2] = &bus_ehci2_clk.common.hw, + [CLK_BUS_EHCI3] = &bus_ehci3_clk.common.hw, + [CLK_BUS_OTG] = &bus_otg_clk.common.hw, + [CLK_BUS_KEYADC] = &bus_keyadc_clk.common.hw, + [CLK_HDMI] = &hdmi_clk.common.hw, + [CLK_HDMI_SLOW] = &hdmi_slow_clk.common.hw, + [CLK_HDMI_CEC] = &hdmi_cec_clk.common.hw, + [CLK_BUS_HDMI] = &bus_hdmi_clk.common.hw, + [CLK_BUS_TCON_TOP] = &bus_tcon_top_clk.common.hw, + [CLK_TCON_TV0] = &tcon_tv0_clk.common.hw, + [CLK_TCON_TV1] = &tcon_tv1_clk.common.hw, + [CLK_BUS_TCON_TV0] = &bus_tcon_tv0_clk.common.hw, + [CLK_BUS_TCON_TV1] = &bus_tcon_tv1_clk.common.hw, + [CLK_TVE0] = &tve0_clk.common.hw, + [CLK_BUS_TVE_TOP] = &bus_tve_top_clk.common.hw, + [CLK_BUS_TVE0] = &bus_tve0_clk.common.hw, + [CLK_HDCP] = &hdcp_clk.common.hw, + [CLK_BUS_HDCP] = &bus_hdcp_clk.common.hw, + }, + .num = CLK_NUMBER, +}; + +static struct ccu_reset_map sun50i_h616_ccu_resets[] = { + [RST_MBUS] = { 0x540, BIT(30) }, + + [RST_BUS_DE] = { 0x60c, BIT(16) }, + [RST_BUS_DEINTERLACE] = { 0x62c, BIT(16) }, + [RST_BUS_GPU] = { 0x67c, BIT(16) }, + [RST_BUS_CE] = { 0x68c, BIT(16) }, + [RST_BUS_VE] = { 0x69c, BIT(16) }, + [RST_BUS_DMA] = { 0x70c, BIT(16) }, + [RST_BUS_HSTIMER] = { 0x73c, BIT(16) }, + [RST_BUS_DBG] = { 0x78c, BIT(16) }, + [RST_BUS_PSI] = { 0x79c, BIT(16) }, + [RST_BUS_PWM] = { 0x7ac, BIT(16) }, + [RST_BUS_IOMMU] = { 0x7bc, BIT(16) }, + [RST_BUS_DRAM] = { 0x80c, BIT(16) }, + [RST_BUS_NAND] = { 0x82c, BIT(16) }, + [RST_BUS_MMC0] = { 0x84c, BIT(16) }, + [RST_BUS_MMC1] = { 0x84c, BIT(17) }, + [RST_BUS_MMC2] = { 0x84c, BIT(18) }, + [RST_BUS_UART0] = { 0x90c, BIT(16) }, + [RST_BUS_UART1] = { 0x90c, BIT(17) }, + [RST_BUS_UART2] = { 0x90c, BIT(18) }, + [RST_BUS_UART3] = { 0x90c, BIT(19) }, + [RST_BUS_UART4] = { 0x90c, BIT(20) }, + [RST_BUS_UART5] = { 0x90c, BIT(21) }, + [RST_BUS_I2C0] = { 0x91c, BIT(16) }, + [RST_BUS_I2C1] = { 0x91c, BIT(17) }, + [RST_BUS_I2C2] = { 0x91c, BIT(18) }, + [RST_BUS_I2C3] = { 0x91c, BIT(19) }, + [RST_BUS_I2C4] = { 0x91c, BIT(20) }, + [RST_BUS_SPI0] = { 0x96c, BIT(16) }, + [RST_BUS_SPI1] = { 0x96c, BIT(17) }, + [RST_BUS_EMAC0] = { 0x97c, BIT(16) }, + [RST_BUS_EMAC1] = { 0x97c, BIT(17) }, + [RST_BUS_TS] = { 0x9bc, BIT(16) }, + [RST_BUS_THS] = { 0x9fc, BIT(16) }, + [RST_BUS_SPDIF] = { 0xa2c, BIT(16) }, + [RST_BUS_DMIC] = { 0xa4c, BIT(16) }, + [RST_BUS_AUDIO_CODEC] = { 0xa5c, BIT(16) }, + [RST_BUS_AUDIO_HUB] = { 0xa6c, BIT(16) }, + + [RST_USB_PHY0] = { 0xa70, BIT(30) }, + [RST_USB_PHY1] = { 0xa74, BIT(30) }, + [RST_USB_PHY2] = { 0xa78, BIT(30) }, + [RST_USB_PHY3] = { 0xa7c, BIT(30) }, + [RST_BUS_OHCI0] = { 0xa8c, BIT(16) }, + [RST_BUS_OHCI1] = { 0xa8c, BIT(17) }, + [RST_BUS_OHCI2] = { 0xa8c, BIT(18) }, + [RST_BUS_OHCI3] = { 0xa8c, BIT(19) }, + [RST_BUS_EHCI0] = { 0xa8c, BIT(20) }, + [RST_BUS_EHCI1] = { 0xa8c, BIT(21) }, + [RST_BUS_EHCI2] = { 0xa8c, BIT(22) }, + [RST_BUS_EHCI3] = { 0xa8c, BIT(23) }, + [RST_BUS_OTG] = { 0xa8c, BIT(24) }, + [RST_BUS_KEYADC] = { 0xa9c, BIT(16) }, + + [RST_BUS_HDMI] = { 0xb1c, BIT(16) }, + [RST_BUS_HDMI_SUB] = { 0xb1c, BIT(17) }, + [RST_BUS_TCON_TOP] = { 0xb5c, BIT(16) }, + [RST_BUS_TCON_TV0] = { 0xb9c, BIT(16) }, + [RST_BUS_TCON_TV1] = { 0xb9c, BIT(17) }, + [RST_BUS_TVE_TOP] = { 0xbbc, BIT(16) }, + [RST_BUS_TVE0] = { 0xbbc, BIT(17) }, + [RST_BUS_HDCP] = { 0xc4c, BIT(16) }, +}; + +static const struct sunxi_ccu_desc sun50i_h616_ccu_desc = { + .ccu_clks = sun50i_h616_ccu_clks, + .num_ccu_clks = ARRAY_SIZE(sun50i_h616_ccu_clks), + + .hw_clks = &sun50i_h616_hw_clks, + + .resets = sun50i_h616_ccu_resets, + .num_resets = ARRAY_SIZE(sun50i_h616_ccu_resets), +}; + +static const u32 pll_regs[] = { + SUN50I_H616_PLL_CPUX_REG, + SUN50I_H616_PLL_DDR0_REG, + SUN50I_H616_PLL_DDR1_REG, + SUN50I_H616_PLL_PERIPH0_REG, + SUN50I_H616_PLL_PERIPH1_REG, + SUN50I_H616_PLL_GPU_REG, + SUN50I_H616_PLL_VIDEO0_REG, + SUN50I_H616_PLL_VIDEO1_REG, + SUN50I_H616_PLL_VIDEO2_REG, + SUN50I_H616_PLL_VE_REG, + SUN50I_H616_PLL_DE_REG, + SUN50I_H616_PLL_AUDIO_REG, +}; + +static const u32 pll_video_regs[] = { + SUN50I_H616_PLL_VIDEO0_REG, + SUN50I_H616_PLL_VIDEO1_REG, + SUN50I_H616_PLL_VIDEO2_REG, +}; + +static const u32 usb2_clk_regs[] = { + SUN50I_H616_USB0_CLK_REG, + SUN50I_H616_USB1_CLK_REG, + SUN50I_H616_USB2_CLK_REG, + SUN50I_H616_USB3_CLK_REG, +}; + +static void __init sun50i_h616_ccu_setup(struct device_node *node) +{ + void __iomem *reg; + u32 val; + int i; + + reg = of_io_request_and_map(node, 0, of_node_full_name(node)); + if (IS_ERR(reg)) { + pr_err("%pOF: Could not map clock registers\n", node); + return; + } + + /* Enable the lock bits and the output enable bits on all PLLs */ + for (i = 0; i < ARRAY_SIZE(pll_regs); i++) { + val = readl(reg + pll_regs[i]); + val |= BIT(29) | BIT(27); + writel(val, reg + pll_regs[i]); + } + + /* + * Force the output divider of video PLLs to 0. + * + * See the comment before pll-video0 definition for the reason. + */ + for (i = 0; i < ARRAY_SIZE(pll_video_regs); i++) { + val = readl(reg + pll_video_regs[i]); + val &= ~BIT(0); + writel(val, reg + pll_video_regs[i]); + } + + /* + * Force OHCI 12M clock sources to 00 (12MHz divided from 48MHz) + * + * This clock mux is still mysterious, and the code just enforces + * it to have a valid clock parent. + */ + for (i = 0; i < ARRAY_SIZE(usb2_clk_regs); i++) { + val = readl(reg + usb2_clk_regs[i]); + val &= ~GENMASK(25, 24); + writel(val, reg + usb2_clk_regs[i]); + } + + /* + * Force the post-divider of pll-audio to 12 and the output divider + * of it to 2, so 24576000 and 22579200 rates can be set exactly. + */ + val = readl(reg + SUN50I_H616_PLL_AUDIO_REG); + val &= ~(GENMASK(21, 16) | BIT(0)); + writel(val | (11 << 16) | BIT(0), reg + SUN50I_H616_PLL_AUDIO_REG); + + /* + * First clock parent (osc32K) is unusable for CEC. But since there + * is no good way to force parent switch (both run with same frequency), + * just set second clock parent here. + */ + val = readl(reg + SUN50I_H616_HDMI_CEC_CLK_REG); + val |= BIT(24); + writel(val, reg + SUN50I_H616_HDMI_CEC_CLK_REG); + + i = sunxi_ccu_probe(node, reg, &sun50i_h616_ccu_desc); + if (i) + pr_err("%pOF: probing clocks fails: %d\n", node, i); +} + +CLK_OF_DECLARE(sun50i_h616_ccu, "allwinner,sun50i-h616-ccu", + sun50i_h616_ccu_setup); diff --git a/drivers/clk/sunxi-ng/ccu-sun50i-h616.h b/drivers/clk/sunxi-ng/ccu-sun50i-h616.h new file mode 100644 index 000000000000..dd671b413f22 --- /dev/null +++ b/drivers/clk/sunxi-ng/ccu-sun50i-h616.h @@ -0,0 +1,56 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright 2020 Arm Ltd. + */ + +#ifndef _CCU_SUN50I_H616_H_ +#define _CCU_SUN50I_H616_H_ + +#include +#include + +#define CLK_OSC12M 0 +#define CLK_PLL_CPUX 1 +#define CLK_PLL_DDR0 2 +#define CLK_PLL_DDR1 3 + +/* PLL_PERIPH0 exported for PRCM */ + +#define CLK_PLL_PERIPH0_2X 5 +#define CLK_PLL_PERIPH1 6 +#define CLK_PLL_PERIPH1_2X 7 +#define CLK_PLL_GPU 8 +#define CLK_PLL_VIDEO0 9 +#define CLK_PLL_VIDEO0_4X 10 +#define CLK_PLL_VIDEO1 11 +#define CLK_PLL_VIDEO1_4X 12 +#define CLK_PLL_VIDEO2 13 +#define CLK_PLL_VIDEO2_4X 14 +#define CLK_PLL_VE 15 +#define CLK_PLL_DE 16 +#define CLK_PLL_AUDIO_HS 17 +#define CLK_PLL_AUDIO_1X 18 +#define CLK_PLL_AUDIO_2X 19 +#define CLK_PLL_AUDIO_4X 20 + +/* CPUX clock exported for DVFS */ + +#define CLK_AXI 22 +#define CLK_CPUX_APB 23 +#define CLK_PSI_AHB1_AHB2 24 +#define CLK_AHB3 25 + +/* APB1 clock exported for PIO */ + +#define CLK_APB2 27 +#define CLK_MBUS 28 + +/* All module clocks and bus gates are exported except DRAM */ + +#define CLK_DRAM 49 + +#define CLK_BUS_DRAM 56 + +#define CLK_NUMBER (CLK_BUS_HDCP + 1) + +#endif /* _CCU_SUN50I_H616_H_ */ diff --git a/include/dt-bindings/clock/sun50i-h616-ccu.h b/include/dt-bindings/clock/sun50i-h616-ccu.h new file mode 100644 index 000000000000..4fc08b0df2f3 --- /dev/null +++ b/include/dt-bindings/clock/sun50i-h616-ccu.h @@ -0,0 +1,115 @@ +/* SPDX-License-Identifier: (GPL-2.0+ or MIT) */ +/* + * Copyright (C) 2020 Arm Ltd. + */ + +#ifndef _DT_BINDINGS_CLK_SUN50I_H616_H_ +#define _DT_BINDINGS_CLK_SUN50I_H616_H_ + +#define CLK_PLL_PERIPH0 4 + +#define CLK_CPUX 21 + +#define CLK_APB1 26 + +#define CLK_DE 29 +#define CLK_BUS_DE 30 +#define CLK_DEINTERLACE 31 +#define CLK_BUS_DEINTERLACE 32 +#define CLK_G2D 33 +#define CLK_BUS_G2D 34 +#define CLK_GPU0 35 +#define CLK_BUS_GPU 36 +#define CLK_GPU1 37 +#define CLK_CE 38 +#define CLK_BUS_CE 39 +#define CLK_VE 40 +#define CLK_BUS_VE 41 +#define CLK_BUS_DMA 42 +#define CLK_BUS_HSTIMER 43 +#define CLK_AVS 44 +#define CLK_BUS_DBG 45 +#define CLK_BUS_PSI 46 +#define CLK_BUS_PWM 47 +#define CLK_BUS_IOMMU 48 + +#define CLK_MBUS_DMA 50 +#define CLK_MBUS_VE 51 +#define CLK_MBUS_CE 52 +#define CLK_MBUS_TS 53 +#define CLK_MBUS_NAND 54 +#define CLK_MBUS_G2D 55 + +#define CLK_NAND0 57 +#define CLK_NAND1 58 +#define CLK_BUS_NAND 59 +#define CLK_MMC0 60 +#define CLK_MMC1 61 +#define CLK_MMC2 62 +#define CLK_BUS_MMC0 63 +#define CLK_BUS_MMC1 64 +#define CLK_BUS_MMC2 65 +#define CLK_BUS_UART0 66 +#define CLK_BUS_UART1 67 +#define CLK_BUS_UART2 68 +#define CLK_BUS_UART3 69 +#define CLK_BUS_UART4 70 +#define CLK_BUS_UART5 71 +#define CLK_BUS_I2C0 72 +#define CLK_BUS_I2C1 73 +#define CLK_BUS_I2C2 74 +#define CLK_BUS_I2C3 75 +#define CLK_BUS_I2C4 76 +#define CLK_SPI0 77 +#define CLK_SPI1 78 +#define CLK_BUS_SPI0 79 +#define CLK_BUS_SPI1 80 +#define CLK_EMAC_25M 81 +#define CLK_BUS_EMAC0 82 +#define CLK_BUS_EMAC1 83 +#define CLK_TS 84 +#define CLK_BUS_TS 85 +#define CLK_BUS_THS 86 +#define CLK_SPDIF 87 +#define CLK_BUS_SPDIF 88 +#define CLK_DMIC 89 +#define CLK_BUS_DMIC 90 +#define CLK_AUDIO_CODEC_1X 91 +#define CLK_AUDIO_CODEC_4X 92 +#define CLK_BUS_AUDIO_CODEC 93 +#define CLK_AUDIO_HUB 94 +#define CLK_BUS_AUDIO_HUB 95 +#define CLK_USB_OHCI0 96 +#define CLK_USB_PHY0 97 +#define CLK_USB_OHCI1 98 +#define CLK_USB_PHY1 99 +#define CLK_USB_OHCI2 100 +#define CLK_USB_PHY2 101 +#define CLK_USB_OHCI3 102 +#define CLK_USB_PHY3 103 +#define CLK_BUS_OHCI0 104 +#define CLK_BUS_OHCI1 105 +#define CLK_BUS_OHCI2 106 +#define CLK_BUS_OHCI3 107 +#define CLK_BUS_EHCI0 108 +#define CLK_BUS_EHCI1 109 +#define CLK_BUS_EHCI2 110 +#define CLK_BUS_EHCI3 111 +#define CLK_BUS_OTG 112 +#define CLK_BUS_KEYADC 113 +#define CLK_HDMI 114 +#define CLK_HDMI_SLOW 115 +#define CLK_HDMI_CEC 116 +#define CLK_BUS_HDMI 117 +#define CLK_BUS_TCON_TOP 118 +#define CLK_TCON_TV0 119 +#define CLK_TCON_TV1 120 +#define CLK_BUS_TCON_TV0 121 +#define CLK_BUS_TCON_TV1 122 +#define CLK_TVE0 123 +#define CLK_BUS_TVE_TOP 124 +#define CLK_BUS_TVE0 125 +#define CLK_HDCP 126 +#define CLK_BUS_HDCP 127 + +#endif /* _DT_BINDINGS_CLK_SUN50I_H616_H_ */ diff --git a/include/dt-bindings/reset/sun50i-h616-ccu.h b/include/dt-bindings/reset/sun50i-h616-ccu.h new file mode 100644 index 000000000000..cb6285a8d128 --- /dev/null +++ b/include/dt-bindings/reset/sun50i-h616-ccu.h @@ -0,0 +1,70 @@ +/* SPDX-License-Identifier: (GPL-2.0+ or MIT) */ +/* + * Copyright (C) 2020 Arm Ltd. + */ + +#ifndef _DT_BINDINGS_RESET_SUN50I_H616_H_ +#define _DT_BINDINGS_RESET_SUN50I_H616_H_ + +#define RST_MBUS 0 +#define RST_BUS_DE 1 +#define RST_BUS_DEINTERLACE 2 +#define RST_BUS_GPU 3 +#define RST_BUS_CE 4 +#define RST_BUS_VE 5 +#define RST_BUS_DMA 6 +#define RST_BUS_HSTIMER 7 +#define RST_BUS_DBG 8 +#define RST_BUS_PSI 9 +#define RST_BUS_PWM 10 +#define RST_BUS_IOMMU 11 +#define RST_BUS_DRAM 12 +#define RST_BUS_NAND 13 +#define RST_BUS_MMC0 14 +#define RST_BUS_MMC1 15 +#define RST_BUS_MMC2 16 +#define RST_BUS_UART0 17 +#define RST_BUS_UART1 18 +#define RST_BUS_UART2 19 +#define RST_BUS_UART3 20 +#define RST_BUS_UART4 21 +#define RST_BUS_UART5 22 +#define RST_BUS_I2C0 23 +#define RST_BUS_I2C1 24 +#define RST_BUS_I2C2 25 +#define RST_BUS_I2C3 26 +#define RST_BUS_I2C4 27 +#define RST_BUS_SPI0 28 +#define RST_BUS_SPI1 29 +#define RST_BUS_EMAC0 30 +#define RST_BUS_EMAC1 31 +#define RST_BUS_TS 32 +#define RST_BUS_THS 33 +#define RST_BUS_SPDIF 34 +#define RST_BUS_DMIC 35 +#define RST_BUS_AUDIO_CODEC 36 +#define RST_BUS_AUDIO_HUB 37 +#define RST_USB_PHY0 38 +#define RST_USB_PHY1 39 +#define RST_USB_PHY2 40 +#define RST_USB_PHY3 41 +#define RST_BUS_OHCI0 42 +#define RST_BUS_OHCI1 43 +#define RST_BUS_OHCI2 44 +#define RST_BUS_OHCI3 45 +#define RST_BUS_EHCI0 46 +#define RST_BUS_EHCI1 47 +#define RST_BUS_EHCI2 48 +#define RST_BUS_EHCI3 49 +#define RST_BUS_OTG 50 +#define RST_BUS_HDMI 51 +#define RST_BUS_HDMI_SUB 52 +#define RST_BUS_TCON_TOP 53 +#define RST_BUS_TCON_TV0 54 +#define RST_BUS_TCON_TV1 55 +#define RST_BUS_TVE_TOP 56 +#define RST_BUS_TVE0 57 +#define RST_BUS_HDCP 58 +#define RST_BUS_KEYADC 59 + +#endif /* _DT_BINDINGS_RESET_SUN50I_H616_H_ */ -- cgit v1.2.3 From f2dd871799ba5d80f95f9bdbc0e60d390e1bcd22 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Thu, 14 Jan 2021 17:04:00 +0800 Subject: iommu/vt-d: Add qi_submit trace event This adds a new trace event to track the submissions of requests to the invalidation queue. This event will provide the information like: - IOMMU name - Invalidation type - Descriptor raw data A sample output like: | qi_submit: iotlb_inv dmar1: 0x100e2 0x0 0x0 0x0 | qi_submit: dev_tlb_inv dmar1: 0x1000000003 0x7ffffffffffff001 0x0 0x0 | qi_submit: iotlb_inv dmar2: 0x800f2 0xf9a00005 0x0 0x0 This will be helpful for queued invalidation related debugging. Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20210114090400.736104-1-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/dmar.c | 3 +++ include/trace/events/intel_iommu.h | 37 +++++++++++++++++++++++++++++++++++++ 2 files changed, 40 insertions(+) (limited to 'include') diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index 004feaed3c72..bd51f33642e0 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -31,6 +31,7 @@ #include #include #include +#include #include "../irq_remapping.h" @@ -1307,6 +1308,8 @@ restart: offset = ((index + i) % QI_LENGTH) << shift; memcpy(qi->desc + offset, &desc[i], 1 << shift); qi->desc_status[(index + i) % QI_LENGTH] = QI_IN_USE; + trace_qi_submit(iommu, desc[i].qw0, desc[i].qw1, + desc[i].qw2, desc[i].qw3); } qi->desc_status[wait_index] = QI_IN_USE; diff --git a/include/trace/events/intel_iommu.h b/include/trace/events/intel_iommu.h index 112bd06487bf..aad2ff0c1e2e 100644 --- a/include/trace/events/intel_iommu.h +++ b/include/trace/events/intel_iommu.h @@ -135,6 +135,43 @@ DEFINE_EVENT(dma_map_sg, bounce_map_sg, struct scatterlist *sg), TP_ARGS(dev, index, total, sg) ); + +TRACE_EVENT(qi_submit, + TP_PROTO(struct intel_iommu *iommu, u64 qw0, u64 qw1, u64 qw2, u64 qw3), + + TP_ARGS(iommu, qw0, qw1, qw2, qw3), + + TP_STRUCT__entry( + __field(u64, qw0) + __field(u64, qw1) + __field(u64, qw2) + __field(u64, qw3) + __string(iommu, iommu->name) + ), + + TP_fast_assign( + __assign_str(iommu, iommu->name); + __entry->qw0 = qw0; + __entry->qw1 = qw1; + __entry->qw2 = qw2; + __entry->qw3 = qw3; + ), + + TP_printk("%s %s: 0x%llx 0x%llx 0x%llx 0x%llx", + __print_symbolic(__entry->qw0 & 0xf, + { QI_CC_TYPE, "cc_inv" }, + { QI_IOTLB_TYPE, "iotlb_inv" }, + { QI_DIOTLB_TYPE, "dev_tlb_inv" }, + { QI_IEC_TYPE, "iec_inv" }, + { QI_IWD_TYPE, "inv_wait" }, + { QI_EIOTLB_TYPE, "p_iotlb_inv" }, + { QI_PC_TYPE, "pc_inv" }, + { QI_DEIOTLB_TYPE, "p_dev_tlb_inv" }, + { QI_PGRP_RESP_TYPE, "page_grp_resp" }), + __get_str(iommu), + __entry->qw0, __entry->qw1, __entry->qw2, __entry->qw3 + ) +); #endif /* _TRACE_INTEL_IOMMU_H */ /* This part must be outside protection */ -- cgit v1.2.3 From a8ce9ebbecdfda3322bbcece6b3b25888217f8e3 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Fri, 15 Jan 2021 08:42:02 +0800 Subject: iommu/vt-d: Preset Access/Dirty bits for IOVA over FL The Access/Dirty bits in the first level page table entry will be set whenever a page table entry was used for address translation or write permission was successfully translated. This is always true when using the first-level page table for kernel IOVA. Instead of wasting hardware cycles to update the certain bits, it's better to set them up at the beginning. Suggested-by: Ashok Raj Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20210115004202.953965-1-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 14 ++++++++++++-- include/linux/intel-iommu.h | 2 ++ 2 files changed, 14 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index f665322a0991..be85af612bc1 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -1017,8 +1017,11 @@ static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain, domain_flush_cache(domain, tmp_page, VTD_PAGE_SIZE); pteval = ((uint64_t)virt_to_dma_pfn(tmp_page) << VTD_PAGE_SHIFT) | DMA_PTE_READ | DMA_PTE_WRITE; - if (domain_use_first_level(domain)) + if (domain_use_first_level(domain)) { pteval |= DMA_FL_PTE_XD | DMA_FL_PTE_US; + if (domain->domain.type == IOMMU_DOMAIN_DMA) + pteval |= DMA_FL_PTE_ACCESS; + } if (cmpxchg64(&pte->val, 0ULL, pteval)) /* Someone else set it while we were thinking; use theirs. */ free_pgtable_page(tmp_page); @@ -2310,9 +2313,16 @@ __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn, return -EINVAL; attr = prot & (DMA_PTE_READ | DMA_PTE_WRITE | DMA_PTE_SNP); - if (domain_use_first_level(domain)) + if (domain_use_first_level(domain)) { attr |= DMA_FL_PTE_PRESENT | DMA_FL_PTE_XD | DMA_FL_PTE_US; + if (domain->domain.type == IOMMU_DOMAIN_DMA) { + attr |= DMA_FL_PTE_ACCESS; + if (prot & DMA_PTE_WRITE) + attr |= DMA_FL_PTE_DIRTY; + } + } + pteval = ((phys_addr_t)phys_pfn << VTD_PAGE_SHIFT) | attr; while (nr_pages > 0) { diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 09c6a0bf3892..ecb35fdff03e 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -42,6 +42,8 @@ #define DMA_FL_PTE_PRESENT BIT_ULL(0) #define DMA_FL_PTE_US BIT_ULL(2) +#define DMA_FL_PTE_ACCESS BIT_ULL(5) +#define DMA_FL_PTE_DIRTY BIT_ULL(6) #define DMA_FL_PTE_XD BIT_ULL(63) #define ADDR_WIDTH_5LEVEL (57) -- cgit v1.2.3 From 3ab657291638ea267654c3e4798161b2cee6ae01 Mon Sep 17 00:00:00 2001 From: Lianbo Jiang Date: Tue, 26 Jan 2021 19:53:37 +0800 Subject: iommu: use the __iommu_attach_device() directly for deferred attach Currently, because domain attach allows to be deferred from iommu driver to device driver, and when iommu initializes, the devices on the bus will be scanned and the default groups will be allocated. Due to the above changes, some devices could be added to the same group as below: [ 3.859417] pci 0000:01:00.0: Adding to iommu group 16 [ 3.864572] pci 0000:01:00.1: Adding to iommu group 16 [ 3.869738] pci 0000:02:00.0: Adding to iommu group 17 [ 3.874892] pci 0000:02:00.1: Adding to iommu group 17 But when attaching these devices, it doesn't allow that a group has more than one device, otherwise it will return an error. This conflicts with the deferred attaching. Unfortunately, it has two devices in the same group for my side, for example: [ 9.627014] iommu_group_device_count(): device name[0]:0000:01:00.0 [ 9.633545] iommu_group_device_count(): device name[1]:0000:01:00.1 ... [ 10.255609] iommu_group_device_count(): device name[0]:0000:02:00.0 [ 10.262144] iommu_group_device_count(): device name[1]:0000:02:00.1 Finally, which caused the failure of tg3 driver when tg3 driver calls the dma_alloc_coherent() to allocate coherent memory in the tg3_test_dma(). [ 9.660310] tg3 0000:01:00.0: DMA engine test failed, aborting [ 9.754085] tg3: probe of 0000:01:00.0 failed with error -12 [ 9.997512] tg3 0000:01:00.1: DMA engine test failed, aborting [ 10.043053] tg3: probe of 0000:01:00.1 failed with error -12 [ 10.288905] tg3 0000:02:00.0: DMA engine test failed, aborting [ 10.334070] tg3: probe of 0000:02:00.0 failed with error -12 [ 10.578303] tg3 0000:02:00.1: DMA engine test failed, aborting [ 10.622629] tg3: probe of 0000:02:00.1 failed with error -12 In addition, the similar situations also occur in other drivers such as the bnxt_en driver. That can be reproduced easily in kdump kernel when SME is active. Let's move the handling currently in iommu_dma_deferred_attach() into the iommu core code so that it can call the __iommu_attach_device() directly instead of the iommu_attach_device(). The external interface iommu_attach_device() is not suitable for handling this situation. Signed-off-by: Lianbo Jiang Reviewed-by: Robin Murphy Link: https://lore.kernel.org/r/20210126115337.20068-3-lijiang@redhat.com Signed-off-by: Joerg Roedel --- drivers/iommu/dma-iommu.c | 18 +++--------------- drivers/iommu/iommu.c | 10 ++++++++++ include/linux/iommu.h | 1 + 3 files changed, 14 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index c80056f6c9f9..f659395e7959 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -380,18 +380,6 @@ static int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base, return iova_reserve_iommu_regions(dev, domain); } -static int iommu_dma_deferred_attach(struct device *dev, - struct iommu_domain *domain) -{ - const struct iommu_ops *ops = domain->ops; - - if (unlikely(ops->is_attach_deferred && - ops->is_attach_deferred(domain, dev))) - return iommu_attach_device(domain, dev); - - return 0; -} - /** * dma_info_to_prot - Translate DMA API directions and attributes to IOMMU API * page flags. @@ -535,7 +523,7 @@ static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys, dma_addr_t iova; if (static_branch_unlikely(&iommu_deferred_attach_enabled) && - iommu_dma_deferred_attach(dev, domain)) + iommu_deferred_attach(dev, domain)) return DMA_MAPPING_ERROR; size = iova_align(iovad, size + iova_off); @@ -694,7 +682,7 @@ static void *iommu_dma_alloc_remap(struct device *dev, size_t size, *dma_handle = DMA_MAPPING_ERROR; if (static_branch_unlikely(&iommu_deferred_attach_enabled) && - iommu_dma_deferred_attach(dev, domain)) + iommu_deferred_attach(dev, domain)) return NULL; min_size = alloc_sizes & -alloc_sizes; @@ -978,7 +966,7 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg, int i; if (static_branch_unlikely(&iommu_deferred_attach_enabled) && - iommu_dma_deferred_attach(dev, domain)) + iommu_deferred_attach(dev, domain)) return 0; if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 91f7871f5a37..fd76e2f579fe 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -1980,6 +1980,16 @@ out_unlock: } EXPORT_SYMBOL_GPL(iommu_attach_device); +int iommu_deferred_attach(struct device *dev, struct iommu_domain *domain) +{ + const struct iommu_ops *ops = domain->ops; + + if (ops->is_attach_deferred && ops->is_attach_deferred(domain, dev)) + return __iommu_attach_device(domain, dev); + + return 0; +} + /* * Check flags and other user provided data for valid combinations. We also * make sure no reserved fields or unused flags are set. This is to ensure diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 91d94c014f47..524ffc2ff64f 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -376,6 +376,7 @@ int iommu_device_sysfs_add(struct iommu_device *iommu, void iommu_device_sysfs_remove(struct iommu_device *iommu); int iommu_device_link(struct iommu_device *iommu, struct device *link); void iommu_device_unlink(struct iommu_device *iommu, struct device *link); +int iommu_deferred_attach(struct device *dev, struct iommu_domain *domain); static inline void __iommu_device_set_ops(struct iommu_device *iommu, const struct iommu_ops *ops) -- cgit v1.2.3 From c9b258c6be09283663c6851725b322568d867c0b Mon Sep 17 00:00:00 2001 From: Suravee Suthikulpanit Date: Tue, 15 Dec 2020 01:36:54 -0600 Subject: iommu/amd: Prepare for generic IO page table framework Add initial hook up code to implement generic IO page table framework. Signed-off-by: Suravee Suthikulpanit Link: https://lore.kernel.org/r/20201215073705.123786-3-suravee.suthikulpanit@amd.com Signed-off-by: Joerg Roedel --- drivers/iommu/amd/Kconfig | 1 + drivers/iommu/amd/Makefile | 2 +- drivers/iommu/amd/amd_iommu_types.h | 35 +++++++++++++++++++ drivers/iommu/amd/io_pgtable.c | 69 +++++++++++++++++++++++++++++++++++++ drivers/iommu/amd/iommu.c | 10 ------ drivers/iommu/io-pgtable.c | 3 ++ include/linux/io-pgtable.h | 2 ++ 7 files changed, 111 insertions(+), 11 deletions(-) create mode 100644 drivers/iommu/amd/io_pgtable.c (limited to 'include') diff --git a/drivers/iommu/amd/Kconfig b/drivers/iommu/amd/Kconfig index 626b97d0dd21..a3cbafb603f5 100644 --- a/drivers/iommu/amd/Kconfig +++ b/drivers/iommu/amd/Kconfig @@ -10,6 +10,7 @@ config AMD_IOMMU select IOMMU_API select IOMMU_IOVA select IOMMU_DMA + select IOMMU_IO_PGTABLE depends on X86_64 && PCI && ACPI && HAVE_CMPXCHG_DOUBLE help With this option you can enable support for AMD IOMMU hardware in diff --git a/drivers/iommu/amd/Makefile b/drivers/iommu/amd/Makefile index dc5a2fa4fd37..a935f8f4b974 100644 --- a/drivers/iommu/amd/Makefile +++ b/drivers/iommu/amd/Makefile @@ -1,4 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only -obj-$(CONFIG_AMD_IOMMU) += iommu.o init.o quirks.o +obj-$(CONFIG_AMD_IOMMU) += iommu.o init.o quirks.o io_pgtable.o obj-$(CONFIG_AMD_IOMMU_DEBUGFS) += debugfs.o obj-$(CONFIG_AMD_IOMMU_V2) += iommu_v2.o diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h index 553587827771..b2365924d898 100644 --- a/drivers/iommu/amd/amd_iommu_types.h +++ b/drivers/iommu/amd/amd_iommu_types.h @@ -15,6 +15,7 @@ #include #include #include +#include /* * Maximum number of IOMMUs supported @@ -252,6 +253,19 @@ #define GA_GUEST_NR 0x1 +#define IOMMU_IN_ADDR_BIT_SIZE 52 +#define IOMMU_OUT_ADDR_BIT_SIZE 52 + +/* + * This bitmap is used to advertise the page sizes our hardware support + * to the IOMMU core, which will then use this information to split + * physically contiguous memory regions it is mapping into page sizes + * that we support. + * + * 512GB Pages are not supported due to a hardware bug + */ +#define AMD_IOMMU_PGSIZES ((~0xFFFUL) & ~(2ULL << 38)) + /* Bit value definition for dte irq remapping fields*/ #define DTE_IRQ_PHYS_ADDR_MASK (((1ULL << 45)-1) << 6) #define DTE_IRQ_REMAP_INTCTL_MASK (0x3ULL << 60) @@ -466,6 +480,26 @@ struct amd_irte_ops; #define AMD_IOMMU_FLAG_TRANS_PRE_ENABLED (1 << 0) +#define io_pgtable_to_data(x) \ + container_of((x), struct amd_io_pgtable, iop) + +#define io_pgtable_ops_to_data(x) \ + io_pgtable_to_data(io_pgtable_ops_to_pgtable(x)) + +#define io_pgtable_ops_to_domain(x) \ + container_of(io_pgtable_ops_to_data(x), \ + struct protection_domain, iop) + +#define io_pgtable_cfg_to_data(x) \ + container_of((x), struct amd_io_pgtable, pgtbl_cfg) + +struct amd_io_pgtable { + struct io_pgtable_cfg pgtbl_cfg; + struct io_pgtable iop; + int mode; + u64 *root; +}; + /* * This structure contains generic data for IOMMU protection domains * independent of their use. @@ -474,6 +508,7 @@ struct protection_domain { struct list_head dev_list; /* List of all devices in this domain */ struct iommu_domain domain; /* generic domain handle used by iommu core code */ + struct amd_io_pgtable iop; spinlock_t lock; /* mostly used to lock the page table*/ u16 id; /* the domain id written to the device table */ atomic64_t pt_root; /* pgtable root and pgtable mode */ diff --git a/drivers/iommu/amd/io_pgtable.c b/drivers/iommu/amd/io_pgtable.c new file mode 100644 index 000000000000..cf2cd2d2e43e --- /dev/null +++ b/drivers/iommu/amd/io_pgtable.c @@ -0,0 +1,69 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * CPU-agnostic AMD IO page table allocator. + * + * Copyright (C) 2020 Advanced Micro Devices, Inc. + * Author: Suravee Suthikulpanit + */ + +#define pr_fmt(fmt) "AMD-Vi: " fmt +#define dev_fmt(fmt) pr_fmt(fmt) + +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "amd_iommu_types.h" +#include "amd_iommu.h" + +static void v1_tlb_flush_all(void *cookie) +{ +} + +static void v1_tlb_flush_walk(unsigned long iova, size_t size, + size_t granule, void *cookie) +{ +} + +static void v1_tlb_add_page(struct iommu_iotlb_gather *gather, + unsigned long iova, size_t granule, + void *cookie) +{ +} + +static const struct iommu_flush_ops v1_flush_ops = { + .tlb_flush_all = v1_tlb_flush_all, + .tlb_flush_walk = v1_tlb_flush_walk, + .tlb_add_page = v1_tlb_add_page, +}; + +/* + * ---------------------------------------------------- + */ +static void v1_free_pgtable(struct io_pgtable *iop) +{ +} + +static struct io_pgtable *v1_alloc_pgtable(struct io_pgtable_cfg *cfg, void *cookie) +{ + struct amd_io_pgtable *pgtable = io_pgtable_cfg_to_data(cfg); + + cfg->pgsize_bitmap = AMD_IOMMU_PGSIZES, + cfg->ias = IOMMU_IN_ADDR_BIT_SIZE, + cfg->oas = IOMMU_OUT_ADDR_BIT_SIZE, + cfg->tlb = &v1_flush_ops; + + return &pgtable->iop; +} + +struct io_pgtable_init_fns io_pgtable_amd_iommu_v1_init_fns = { + .alloc = v1_alloc_pgtable, + .free = v1_free_pgtable, +}; diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 3485f8b60d7a..18d8c97f681e 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -57,16 +57,6 @@ #define HT_RANGE_START (0xfd00000000ULL) #define HT_RANGE_END (0xffffffffffULL) -/* - * This bitmap is used to advertise the page sizes our hardware support - * to the IOMMU core, which will then use this information to split - * physically contiguous memory regions it is mapping into page sizes - * that we support. - * - * 512GB Pages are not supported due to a hardware bug - */ -#define AMD_IOMMU_PGSIZES ((~0xFFFUL) & ~(2ULL << 38)) - #define DEFAULT_PGTABLE_LEVEL PAGE_MODE_3_LEVEL static DEFINE_SPINLOCK(pd_bitmap_lock); diff --git a/drivers/iommu/io-pgtable.c b/drivers/iommu/io-pgtable.c index 94394c81468f..6e9917ce980f 100644 --- a/drivers/iommu/io-pgtable.c +++ b/drivers/iommu/io-pgtable.c @@ -24,6 +24,9 @@ io_pgtable_init_table[IO_PGTABLE_NUM_FMTS] = { #ifdef CONFIG_IOMMU_IO_PGTABLE_ARMV7S [ARM_V7S] = &io_pgtable_arm_v7s_init_fns, #endif +#ifdef CONFIG_AMD_IOMMU + [AMD_IOMMU_V1] = &io_pgtable_amd_iommu_v1_init_fns, +#endif }; struct io_pgtable_ops *alloc_io_pgtable_ops(enum io_pgtable_fmt fmt, diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index ea727eb1a1a9..f58c14218ee1 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -15,6 +15,7 @@ enum io_pgtable_fmt { ARM_64_LPAE_S2, ARM_V7S, ARM_MALI_LPAE, + AMD_IOMMU_V1, IO_PGTABLE_NUM_FMTS, }; @@ -251,5 +252,6 @@ extern struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s1_init_fns; extern struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s2_init_fns; extern struct io_pgtable_init_fns io_pgtable_arm_v7s_init_fns; extern struct io_pgtable_init_fns io_pgtable_arm_mali_lpae_init_fns; +extern struct io_pgtable_init_fns io_pgtable_amd_iommu_v1_init_fns; #endif /* __IO_PGTABLE_H */ -- cgit v1.2.3 From a321fc2b4e60fc1b39517d26c8104351636a6062 Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Mon, 25 Jan 2021 19:36:35 +0200 Subject: drm/dp/mst: Export drm_dp_get_vc_payload_bw() This function will be needed by the next patch where the driver calculates the BW based on driver specific parameters, so export it. At the same time sanitize the function params, passing the more natural link rate instead of the encoding of the same rate. v2: - Fix function documentation. (Lyude) Cc: Lyude Paul Cc: Ville Syrjala Cc: Cc: dri-devel@lists.freedesktop.org Signed-off-by: Imre Deak Reviewed-by: Lyude Paul Link: https://patchwork.freedesktop.org/patch/msgid/20210125173636.1733812-1-imre.deak@intel.com --- drivers/gpu/drm/drm_dp_mst_topology.c | 24 ++++++++++++++++++------ include/drm/drm_dp_mst_helper.h | 1 + 2 files changed, 19 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index a2e692a0c6c2..d7af663f4895 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -3629,14 +3629,26 @@ static int drm_dp_send_up_ack_reply(struct drm_dp_mst_topology_mgr *mgr, return 0; } -static int drm_dp_get_vc_payload_bw(u8 dp_link_bw, u8 dp_link_count) +/** + * drm_dp_get_vc_payload_bw - get the VC payload BW for an MST link + * @link_rate: link rate in 10kbits/s units + * @link_lane_count: lane count + * + * Calculate the total bandwidth of a MultiStream Transport link. The returned + * value is in units of PBNs/(timeslots/1 MTP). This value can be used to + * convert the number of PBNs required for a given stream to the number of + * timeslots this stream requires in each MTP. + */ +int drm_dp_get_vc_payload_bw(int link_rate, int link_lane_count) { - if (dp_link_bw == 0 || dp_link_count == 0) - DRM_DEBUG_KMS("invalid link bandwidth in DPCD: %x (link count: %d)\n", - dp_link_bw, dp_link_count); + if (link_rate == 0 || link_lane_count == 0) + DRM_DEBUG_KMS("invalid link rate/lane count: (%d / %d)\n", + link_rate, link_lane_count); - return dp_link_bw * dp_link_count / 2; + /* See DP v2.0 2.6.4.2, VCPayload_Bandwidth_for_OneTimeSlotPer_MTP_Allocation */ + return link_rate * link_lane_count / 54000; } +EXPORT_SYMBOL(drm_dp_get_vc_payload_bw); /** * drm_dp_read_mst_cap() - check whether or not a sink supports MST @@ -3692,7 +3704,7 @@ int drm_dp_mst_topology_mgr_set_mst(struct drm_dp_mst_topology_mgr *mgr, bool ms goto out_unlock; } - mgr->pbn_div = drm_dp_get_vc_payload_bw(mgr->dpcd[1], + mgr->pbn_div = drm_dp_get_vc_payload_bw(drm_dp_bw_code_to_link_rate(mgr->dpcd[1]), mgr->dpcd[2] & DP_MAX_LANE_COUNT_MASK); if (mgr->pbn_div == 0) { ret = -EINVAL; diff --git a/include/drm/drm_dp_mst_helper.h b/include/drm/drm_dp_mst_helper.h index f5e92fe9151c..bd1c39907b92 100644 --- a/include/drm/drm_dp_mst_helper.h +++ b/include/drm/drm_dp_mst_helper.h @@ -783,6 +783,7 @@ drm_dp_mst_detect_port(struct drm_connector *connector, struct edid *drm_dp_mst_get_edid(struct drm_connector *connector, struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_port *port); +int drm_dp_get_vc_payload_bw(int link_rate, int link_lane_count); int drm_dp_calc_pbn_mode(int clock, int bpp, bool dsc); -- cgit v1.2.3 From 3d5eab41451f8e28f3e45eef8f6b372bf56612fb Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Wed, 27 Jan 2021 16:29:29 +0000 Subject: iommu/io-pgtable: Remove TLBI_ON_MAP quirk IO_PGTABLE_QUIRK_TLBI_ON_MAP is now fully superseded by the core API's iotlb_sync_map callback. Signed-off-by: Robin Murphy Link: https://lore.kernel.org/r/5abb80bba3a7c371d5ffb7e59c05586deddb9a91.1611764372.git.robin.murphy@arm.com [will: Remove unused 'iop' local variable from arm_v7s_map()] Signed-off-by: Will Deacon --- drivers/iommu/io-pgtable-arm-v7s.c | 9 +-------- include/linux/io-pgtable.h | 5 ----- 2 files changed, 1 insertion(+), 13 deletions(-) (limited to 'include') diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c index 1d92ac948db7..929cb1518db1 100644 --- a/drivers/iommu/io-pgtable-arm-v7s.c +++ b/drivers/iommu/io-pgtable-arm-v7s.c @@ -519,7 +519,6 @@ static int arm_v7s_map(struct io_pgtable_ops *ops, unsigned long iova, phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { struct arm_v7s_io_pgtable *data = io_pgtable_ops_to_data(ops); - struct io_pgtable *iop = &data->iop; int ret; if (WARN_ON(iova >= (1ULL << data->iop.cfg.ias) || @@ -535,12 +534,7 @@ static int arm_v7s_map(struct io_pgtable_ops *ops, unsigned long iova, * Synchronise all PTE updates for the new mapping before there's * a chance for anything to kick off a table walk for the new iova. */ - if (iop->cfg.quirks & IO_PGTABLE_QUIRK_TLBI_ON_MAP) { - io_pgtable_tlb_flush_walk(iop, iova, size, - ARM_V7S_BLOCK_SIZE(2)); - } else { - wmb(); - } + wmb(); return ret; } @@ -759,7 +753,6 @@ static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg, if (cfg->quirks & ~(IO_PGTABLE_QUIRK_ARM_NS | IO_PGTABLE_QUIRK_NO_PERMS | - IO_PGTABLE_QUIRK_TLBI_ON_MAP | IO_PGTABLE_QUIRK_ARM_MTK_EXT | IO_PGTABLE_QUIRK_NON_STRICT)) return NULL; diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index 2a5686ca2ba3..06753323a15e 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -68,10 +68,6 @@ struct io_pgtable_cfg { * hardware which does not implement the permissions of a given * format, and/or requires some format-specific default value. * - * IO_PGTABLE_QUIRK_TLBI_ON_MAP: If the format forbids caching invalid - * (unmapped) entries but the hardware might do so anyway, perform - * TLB maintenance when mapping as well as when unmapping. - * * IO_PGTABLE_QUIRK_ARM_MTK_EXT: (ARM v7s format) MediaTek IOMMUs extend * to support up to 34 bits PA where the bit32 and bit33 are * encoded in the bit9 and bit4 of the PTE respectively. @@ -88,7 +84,6 @@ struct io_pgtable_cfg { */ #define IO_PGTABLE_QUIRK_ARM_NS BIT(0) #define IO_PGTABLE_QUIRK_NO_PERMS BIT(1) - #define IO_PGTABLE_QUIRK_TLBI_ON_MAP BIT(2) #define IO_PGTABLE_QUIRK_ARM_MTK_EXT BIT(3) #define IO_PGTABLE_QUIRK_NON_STRICT BIT(4) #define IO_PGTABLE_QUIRK_ARM_TTBR1 BIT(5) -- cgit v1.2.3 From c52eef0b6ee1a3c57f6fccb30ea0b5ae19358471 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Fri, 22 Jan 2021 19:44:28 -0800 Subject: of/device: Don't NULLify match table in of_match_device() with CONFIG_OF=n This effectively reverts 1db73ae39a97 ("of/device: Nullify match table in of_match_device() for CONFIG_OF=n") because that commit makes it more surprising to users of this API that the arguments may never be referenced by any code. This is because the pre-processor will replace the argument with NULL and then the match table will be left unreferenced by any code but the compiler optimizer doesn't know to drop it. This can lead to compilers warning that match tables are unused, when we really want to pass the match table to the API but have the compiler see that it's all inlined and not used and then drop the match table while silencing the warning. We're being too smart here and not giving the compiler the chance to do dead code elimination. Signed-off-by: Stephen Boyd Acked-by: Frank Rowand Cc: Arnd Bergmann Cc: Geert Uytterhoeven Cc: Rob Herring Cc: Frank Rowand Reviewed-by: Geert Uytterhoeven Acked-by: Geert Uytterhoeven Reviewed-by: Arnd Bergmann Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/20210123034428.2841052-7-swboyd@chromium.org --- include/linux/of_device.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/of_device.h b/include/linux/of_device.h index 07ca187fc5e4..937f32f6aecb 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -99,13 +99,11 @@ static inline int of_device_uevent_modalias(struct device *dev, static inline void of_device_node_put(struct device *dev) { } -static inline const struct of_device_id *__of_match_device( +static inline const struct of_device_id *of_match_device( const struct of_device_id *matches, const struct device *dev) { return NULL; } -#define of_match_device(matches, dev) \ - __of_match_device(of_match_ptr(matches), (dev)) static inline struct device_node *of_cpu_device_node_get(int cpu) { -- cgit v1.2.3 From 75a352bc6611e79227328e39d42086b0eebf24f3 Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Mon, 25 Jan 2021 18:41:33 +0100 Subject: clk: imx8mq: add PLL monitor output The PLL monitor is mentioned as a debug feature in the reference manual, but there are some boards that use this clock output as a reference clock for board level components. Add support for those clocks in the clock driver, so this clock output can be used properly. Note that the VIDEO1, GPU and VPU mux inputs are rotated compared to the description in the reference manual. The order in this patch has been empirically validated. Signed-off-by: Lucas Stach Reviewed-by: Abel Vesa Signed-off-by: Shawn Guo --- drivers/clk/imx/clk-imx8mq.c | 22 ++++++++++++++++++++++ include/dt-bindings/clock/imx8mq-clock.h | 16 +++++++++++++++- 2 files changed, 37 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/clk/imx/clk-imx8mq.c b/drivers/clk/imx/clk-imx8mq.c index 779ea69e639c..4dd4ae9d022b 100644 --- a/drivers/clk/imx/clk-imx8mq.c +++ b/drivers/clk/imx/clk-imx8mq.c @@ -270,6 +270,14 @@ static const char * const imx8mq_clko1_sels[] = {"osc_25m", "sys1_pll_800m", "os static const char * const imx8mq_clko2_sels[] = {"osc_25m", "sys2_pll_200m", "sys1_pll_400m", "sys2_pll_166m", "sys3_pll_out", "audio_pll1_out", "video_pll1_out", "ckil", }; +static const char * const pllout_monitor_sels[] = {"osc_25m", "osc_27m", "dummy", "dummy", "ckil", + "audio_pll1_out_monitor", "audio_pll2_out_monitor", + "video_pll1_out_monitor", "gpu_pll_out_monitor", + "vpu_pll_out_monitor", "arm_pll_out_monitor", + "sys_pll1_out_monitor", "sys_pll2_out_monitor", + "sys_pll3_out_monitor", "dram_pll_out_monitor", + "video_pll2_out_monitor", }; + static struct clk_hw_onecell_data *clk_hw_data; static struct clk_hw **hws; @@ -399,6 +407,20 @@ static int imx8mq_clocks_probe(struct platform_device *pdev) hws[IMX8MQ_SYS2_PLL_500M] = imx_clk_hw_fixed_factor("sys2_pll_500m", "sys2_pll_500m_cg", 1, 2); hws[IMX8MQ_SYS2_PLL_1000M] = imx_clk_hw_fixed_factor("sys2_pll_1000m", "sys2_pll_1000m_cg", 1, 1); + hws[IMX8MQ_CLK_MON_AUDIO_PLL1_DIV] = imx_clk_hw_divider("audio_pll1_out_monitor", "audio_pll1_bypass", base + 0x78, 0, 3); + hws[IMX8MQ_CLK_MON_AUDIO_PLL2_DIV] = imx_clk_hw_divider("audio_pll2_out_monitor", "audio_pll2_bypass", base + 0x78, 4, 3); + hws[IMX8MQ_CLK_MON_VIDEO_PLL1_DIV] = imx_clk_hw_divider("video_pll1_out_monitor", "video_pll1_bypass", base + 0x78, 8, 3); + hws[IMX8MQ_CLK_MON_GPU_PLL_DIV] = imx_clk_hw_divider("gpu_pll_out_monitor", "gpu_pll_bypass", base + 0x78, 12, 3); + hws[IMX8MQ_CLK_MON_VPU_PLL_DIV] = imx_clk_hw_divider("vpu_pll_out_monitor", "vpu_pll_bypass", base + 0x78, 16, 3); + hws[IMX8MQ_CLK_MON_ARM_PLL_DIV] = imx_clk_hw_divider("arm_pll_out_monitor", "arm_pll_bypass", base + 0x78, 20, 3); + hws[IMX8MQ_CLK_MON_SYS_PLL1_DIV] = imx_clk_hw_divider("sys_pll1_out_monitor", "sys1_pll_out", base + 0x7c, 0, 3); + hws[IMX8MQ_CLK_MON_SYS_PLL2_DIV] = imx_clk_hw_divider("sys_pll2_out_monitor", "sys2_pll_out", base + 0x7c, 4, 3); + hws[IMX8MQ_CLK_MON_SYS_PLL3_DIV] = imx_clk_hw_divider("sys_pll3_out_monitor", "sys3_pll_out", base + 0x7c, 8, 3); + hws[IMX8MQ_CLK_MON_DRAM_PLL_DIV] = imx_clk_hw_divider("dram_pll_out_monitor", "dram_pll_out", base + 0x7c, 12, 3); + hws[IMX8MQ_CLK_MON_VIDEO_PLL2_DIV] = imx_clk_hw_divider("video_pll2_out_monitor", "video2_pll_out", base + 0x7c, 16, 3); + hws[IMX8MQ_CLK_MON_SEL] = imx_clk_hw_mux("pllout_monitor_sel", base + 0x74, 0, 4, pllout_monitor_sels, ARRAY_SIZE(pllout_monitor_sels)); + hws[IMX8MQ_CLK_MON_CLK2_OUT] = imx_clk_hw_gate("pllout_monitor_clk2", "pllout_monitor_sel", base + 0x74, 4); + np = dev->of_node; base = devm_platform_ioremap_resource(pdev, 0); if (WARN_ON(IS_ERR(base))) diff --git a/include/dt-bindings/clock/imx8mq-clock.h b/include/dt-bindings/clock/imx8mq-clock.h index 9b8045d75b8b..82e907ce7bdd 100644 --- a/include/dt-bindings/clock/imx8mq-clock.h +++ b/include/dt-bindings/clock/imx8mq-clock.h @@ -431,6 +431,20 @@ #define IMX8MQ_CLK_A53_CORE 289 -#define IMX8MQ_CLK_END 290 +#define IMX8MQ_CLK_MON_AUDIO_PLL1_DIV 290 +#define IMX8MQ_CLK_MON_AUDIO_PLL2_DIV 291 +#define IMX8MQ_CLK_MON_VIDEO_PLL1_DIV 292 +#define IMX8MQ_CLK_MON_GPU_PLL_DIV 293 +#define IMX8MQ_CLK_MON_VPU_PLL_DIV 294 +#define IMX8MQ_CLK_MON_ARM_PLL_DIV 295 +#define IMX8MQ_CLK_MON_SYS_PLL1_DIV 296 +#define IMX8MQ_CLK_MON_SYS_PLL2_DIV 297 +#define IMX8MQ_CLK_MON_SYS_PLL3_DIV 298 +#define IMX8MQ_CLK_MON_DRAM_PLL_DIV 299 +#define IMX8MQ_CLK_MON_VIDEO_PLL2_DIV 300 +#define IMX8MQ_CLK_MON_SEL 301 +#define IMX8MQ_CLK_MON_CLK2_OUT 302 + +#define IMX8MQ_CLK_END 303 #endif /* __DT_BINDINGS_CLOCK_IMX8MQ_H */ -- cgit v1.2.3 From c1ae5c6f789acde2ad32226cb5461cc1bc60cdf3 Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Mon, 25 Jan 2021 18:41:34 +0100 Subject: clk: imx8mm: add clkout1/2 support clkout1 and clkout2 allow to supply clocks from the SoC to the board, which is used by some board designs to provide reference clocks. Signed-off-by: Lucas Stach Reviewed-by: Abel Vesa Signed-off-by: Shawn Guo --- drivers/clk/imx/clk-imx8mm.c | 12 ++++++++++++ include/dt-bindings/clock/imx8mm-clock.h | 10 +++++++++- 2 files changed, 21 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/clk/imx/clk-imx8mm.c b/drivers/clk/imx/clk-imx8mm.c index 7c905861af5d..6a01eec36dd0 100644 --- a/drivers/clk/imx/clk-imx8mm.c +++ b/drivers/clk/imx/clk-imx8mm.c @@ -288,6 +288,11 @@ static const char *imx8mm_clko1_sels[] = {"osc_24m", "sys_pll1_800m", "dummy", " static const char *imx8mm_clko2_sels[] = {"osc_24m", "sys_pll2_200m", "sys_pll1_400m", "sys_pll2_166m", "sys_pll3_out", "audio_pll1_out", "video_pll1_out", "osc_32k", }; +static const char * const clkout_sels[] = {"audio_pll1_out", "audio_pll2_out", "video_pll1_out", + "dummy", "dummy", "gpu_pll_out", "vpu_pll_out", + "arm_pll_out", "sys_pll1", "sys_pll2", "sys_pll3", + "dummy", "dummy", "osc_24m", "dummy", "osc_32k"}; + static struct clk_hw_onecell_data *clk_hw_data; static struct clk_hw **hws; @@ -410,6 +415,13 @@ static int imx8mm_clocks_probe(struct platform_device *pdev) hws[IMX8MM_SYS_PLL2_500M] = imx_clk_hw_fixed_factor("sys_pll2_500m", "sys_pll2_500m_cg", 1, 2); hws[IMX8MM_SYS_PLL2_1000M] = imx_clk_hw_fixed_factor("sys_pll2_1000m", "sys_pll2_out", 1, 1); + hws[IMX8MM_CLK_CLKOUT1_SEL] = imx_clk_hw_mux("clkout1_sel", base + 0x128, 4, 4, clkout_sels, ARRAY_SIZE(clkout_sels)); + hws[IMX8MM_CLK_CLKOUT1_DIV] = imx_clk_hw_divider("clkout1_div", "clkout1_sel", base + 0x128, 0, 4); + hws[IMX8MM_CLK_CLKOUT1] = imx_clk_hw_gate("clkout1", "clkout1_div", base + 0x128, 8); + hws[IMX8MM_CLK_CLKOUT2_SEL] = imx_clk_hw_mux("clkout2_sel", base + 0x128, 20, 4, clkout_sels, ARRAY_SIZE(clkout_sels)); + hws[IMX8MM_CLK_CLKOUT2_DIV] = imx_clk_hw_divider("clkout2_div", "clkout2_sel", base + 0x128, 16, 4); + hws[IMX8MM_CLK_CLKOUT2] = imx_clk_hw_gate("clkout2", "clkout2_div", base + 0x128, 24); + np = dev->of_node; base = devm_platform_ioremap_resource(pdev, 0); if (WARN_ON(IS_ERR(base))) diff --git a/include/dt-bindings/clock/imx8mm-clock.h b/include/dt-bindings/clock/imx8mm-clock.h index e63a5530aed7..47c6f7f9582c 100644 --- a/include/dt-bindings/clock/imx8mm-clock.h +++ b/include/dt-bindings/clock/imx8mm-clock.h @@ -274,6 +274,14 @@ #define IMX8MM_CLK_A53_CORE 251 -#define IMX8MM_CLK_END 252 +#define IMX8MM_CLK_CLKOUT1_SEL 252 +#define IMX8MM_CLK_CLKOUT1_DIV 253 +#define IMX8MM_CLK_CLKOUT1 254 +#define IMX8MM_CLK_CLKOUT2_SEL 255 +#define IMX8MM_CLK_CLKOUT2_DIV 256 +#define IMX8MM_CLK_CLKOUT2 257 + + +#define IMX8MM_CLK_END 258 #endif -- cgit v1.2.3 From 3af4df65504088e9a7d20c0251e1016e521ad4fc Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Mon, 25 Jan 2021 18:41:35 +0100 Subject: clk: imx8mn: add clkout1/2 support clkout1 and clkout2 allow to supply clocks from the SoC to the board, which is used by some board designs to provide reference clocks. Signed-off-by: Lucas Stach Reviewed-by: Abel Vesa Signed-off-by: Shawn Guo --- drivers/clk/imx/clk-imx8mn.c | 12 ++++++++++++ include/dt-bindings/clock/imx8mn-clock.h | 9 ++++++++- 2 files changed, 20 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/clk/imx/clk-imx8mn.c b/drivers/clk/imx/clk-imx8mn.c index 3c21db942d5b..324c5fd0aa04 100644 --- a/drivers/clk/imx/clk-imx8mn.c +++ b/drivers/clk/imx/clk-imx8mn.c @@ -281,6 +281,11 @@ static const char * const imx8mn_clko2_sels[] = {"osc_24m", "sys_pll2_200m", "sy "sys_pll2_166m", "sys_pll3_out", "audio_pll1_out", "video_pll1_out", "osc_32k", }; +static const char * const clkout_sels[] = {"audio_pll1_out", "audio_pll2_out", "video_pll1_out", + "dummy", "dummy", "gpu_pll_out", "dummy", + "arm_pll_out", "sys_pll1", "sys_pll2", "sys_pll3", + "dummy", "dummy", "osc_24m", "dummy", "osc_32k"}; + static struct clk_hw_onecell_data *clk_hw_data; static struct clk_hw **hws; @@ -405,6 +410,13 @@ static int imx8mn_clocks_probe(struct platform_device *pdev) hws[IMX8MN_SYS_PLL2_500M] = imx_clk_hw_fixed_factor("sys_pll2_500m", "sys_pll2_500m_cg", 1, 2); hws[IMX8MN_SYS_PLL2_1000M] = imx_clk_hw_fixed_factor("sys_pll2_1000m", "sys_pll2_out", 1, 1); + hws[IMX8MN_CLK_CLKOUT1_SEL] = imx_clk_hw_mux("clkout1_sel", base + 0x128, 4, 4, clkout_sels, ARRAY_SIZE(clkout_sels)); + hws[IMX8MN_CLK_CLKOUT1_DIV] = imx_clk_hw_divider("clkout1_div", "clkout1_sel", base + 0x128, 0, 4); + hws[IMX8MN_CLK_CLKOUT1] = imx_clk_hw_gate("clkout1", "clkout1_div", base + 0x128, 8); + hws[IMX8MN_CLK_CLKOUT2_SEL] = imx_clk_hw_mux("clkout2_sel", base + 0x128, 20, 4, clkout_sels, ARRAY_SIZE(clkout_sels)); + hws[IMX8MN_CLK_CLKOUT2_DIV] = imx_clk_hw_divider("clkout2_div", "clkout2_sel", base + 0x128, 16, 4); + hws[IMX8MN_CLK_CLKOUT2] = imx_clk_hw_gate("clkout2", "clkout2_div", base + 0x128, 24); + np = dev->of_node; base = devm_platform_ioremap_resource(pdev, 0); if (WARN_ON(IS_ERR(base))) { diff --git a/include/dt-bindings/clock/imx8mn-clock.h b/include/dt-bindings/clock/imx8mn-clock.h index 621ea0e87c67..d24b627cb2e7 100644 --- a/include/dt-bindings/clock/imx8mn-clock.h +++ b/include/dt-bindings/clock/imx8mn-clock.h @@ -234,6 +234,13 @@ #define IMX8MN_CLK_A53_CORE 214 -#define IMX8MN_CLK_END 215 +#define IMX8MN_CLK_CLKOUT1_SEL 215 +#define IMX8MN_CLK_CLKOUT1_DIV 216 +#define IMX8MN_CLK_CLKOUT1 217 +#define IMX8MN_CLK_CLKOUT2_SEL 218 +#define IMX8MN_CLK_CLKOUT2_DIV 219 +#define IMX8MN_CLK_CLKOUT2 220 + +#define IMX8MN_CLK_END 221 #endif -- cgit v1.2.3 From de5774d192ba15539191ed8b0c79f3d52464b8e3 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Tue, 26 Jan 2021 12:45:39 +0000 Subject: clk: imx: Move 'imx6sl_set_wait_clk()'s prototype out to accessible header MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fixes the following W=1 kernel build warning(s): drivers/clk/imx/clk-imx6sl.c:156:6: warning: no previous prototype for ‘imx6sl_set_wait_clk’ [-Wmissing-prototypes] Cc: Russell King Cc: Shawn Guo Cc: Sascha Hauer Cc: Pengutronix Kernel Team Cc: Fabio Estevam Cc: NXP Linux Team Cc: Ahmad Fatoum Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Lee Jones Signed-off-by: Shawn Guo --- arch/arm/mach-imx/common.h | 1 - arch/arm/mach-imx/cpuidle-imx6sl.c | 1 + arch/arm/mach-imx/pm-imx6.c | 1 + drivers/clk/imx/clk-imx6sl.c | 1 + include/linux/clk/imx.h | 15 +++++++++++++++ 5 files changed, 18 insertions(+), 1 deletion(-) create mode 100644 include/linux/clk/imx.h (limited to 'include') diff --git a/arch/arm/mach-imx/common.h b/arch/arm/mach-imx/common.h index 2d76e2c6c99e..2b004cc4f95e 100644 --- a/arch/arm/mach-imx/common.h +++ b/arch/arm/mach-imx/common.h @@ -85,7 +85,6 @@ void imx_anatop_pre_suspend(void); void imx_anatop_post_resume(void); int imx6_set_lpm(enum mxc_cpu_pwr_mode mode); void imx6_set_int_mem_clk_lpm(bool enable); -void imx6sl_set_wait_clk(bool enter); int imx_mmdc_get_ddr_type(void); int imx7ulp_set_lpm(enum ulp_cpu_pwr_mode mode); diff --git a/arch/arm/mach-imx/cpuidle-imx6sl.c b/arch/arm/mach-imx/cpuidle-imx6sl.c index 4521e5352bf6..b86ffbeb28e4 100644 --- a/arch/arm/mach-imx/cpuidle-imx6sl.c +++ b/arch/arm/mach-imx/cpuidle-imx6sl.c @@ -3,6 +3,7 @@ * Copyright (C) 2014 Freescale Semiconductor, Inc. */ +#include #include #include #include diff --git a/arch/arm/mach-imx/pm-imx6.c b/arch/arm/mach-imx/pm-imx6.c index 40c74b4c4d73..9244437cb1b9 100644 --- a/arch/arm/mach-imx/pm-imx6.c +++ b/arch/arm/mach-imx/pm-imx6.c @@ -4,6 +4,7 @@ * Copyright 2011 Linaro Ltd. */ +#include #include #include #include diff --git a/drivers/clk/imx/clk-imx6sl.c b/drivers/clk/imx/clk-imx6sl.c index 2f9361946a0e..29eab05c9068 100644 --- a/drivers/clk/imx/clk-imx6sl.c +++ b/drivers/clk/imx/clk-imx6sl.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include #include diff --git a/include/linux/clk/imx.h b/include/linux/clk/imx.h new file mode 100644 index 000000000000..75a0d9696552 --- /dev/null +++ b/include/linux/clk/imx.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2020 Freescale Semiconductor, Inc. + * + * Author: Lee Jones + */ + +#ifndef __LINUX_CLK_IMX_H +#define __LINUX_CLK_IMX_H + +#include + +void imx6sl_set_wait_clk(bool enter); + +#endif -- cgit v1.2.3 From a0f2a1cb65c9d8a66853e1b67184022663950f6d Mon Sep 17 00:00:00 2001 From: Grygorii Strashko Date: Fri, 29 Jan 2021 21:31:17 +0200 Subject: dmaengine: ti: k3-psil: optimize struct psil_endpoint_config for size Optimize struct psil_endpoint_config for size by - reordering fields - grouping bitfields - change mapped_channel_id type to s16 (32K channel is enough) - default_flow_id type to s16 as it's assigned to -1 before: text data bss dec hex filename 12654100 5211472 666904 18532476 11ac87c vmlinux after: 12654100 5208528 666904 18529532 11abcfc vmlinux diff: 2944 bytes Signed-off-by: Grygorii Strashko Link: https://lore.kernel.org/r/20210129193117.28833-1-grygorii.strashko@ti.com Signed-off-by: Vinod Koul --- include/linux/dma/k3-psil.h | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/dma/k3-psil.h b/include/linux/dma/k3-psil.h index 36e22c5a0f29..5f106d852f1c 100644 --- a/include/linux/dma/k3-psil.h +++ b/include/linux/dma/k3-psil.h @@ -42,14 +42,14 @@ enum psil_endpoint_type { /** * struct psil_endpoint_config - PSI-L Endpoint configuration * @ep_type: PSI-L endpoint type + * @channel_tpl: Desired throughput level for the channel * @pkt_mode: If set, the channel must be in Packet mode, otherwise in * TR mode * @notdpkt: TDCM must be suppressed on the TX channel * @needs_epib: Endpoint needs EPIB - * @psd_size: If set, PSdata is used by the endpoint - * @channel_tpl: Desired throughput level for the channel * @pdma_acc32: ACC32 must be enabled on the PDMA side * @pdma_burst: BURST must be enabled on the PDMA side + * @psd_size: If set, PSdata is used by the endpoint * @mapped_channel_id: PKTDMA thread to channel mapping for mapped channels. * The thread must be serviced by the specified channel if * mapped_channel_id is >= 0 in case of PKTDMA @@ -62,23 +62,22 @@ enum psil_endpoint_type { */ struct psil_endpoint_config { enum psil_endpoint_type ep_type; + enum udma_tp_level channel_tpl; unsigned pkt_mode:1; unsigned notdpkt:1; unsigned needs_epib:1; - u32 psd_size; - enum udma_tp_level channel_tpl; - /* PDMA properties, valid for PSIL_EP_PDMA_* */ unsigned pdma_acc32:1; unsigned pdma_burst:1; + u32 psd_size; /* PKDMA mapped channel */ - int mapped_channel_id; + s16 mapped_channel_id; /* PKTDMA tflow and rflow ranges for mapped channel */ u16 flow_start; u16 flow_num; - u16 default_flow_id; + s16 default_flow_id; }; int psil_set_new_ep_config(struct device *dev, const char *name, -- cgit v1.2.3 From 67a73230fbaed9ff4902389d4f040abe57c5783c Mon Sep 17 00:00:00 2001 From: "H. Nikolaus Schaller" Date: Wed, 23 Dec 2020 10:01:51 +0100 Subject: mmc: omap: remove unused struct component card_detect_irq I have not found any user for this struct component. Signed-off-by: H. Nikolaus Schaller Link: https://lore.kernel.org/r/b6f2168b863e4273c6bca5a22fbd4a3a8ddf68d6.1608714110.git.hns@goldelico.com Signed-off-by: Ulf Hansson --- include/linux/platform_data/mmc-omap.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/platform_data/mmc-omap.h b/include/linux/platform_data/mmc-omap.h index f0b8947e6b07..91051e9907f3 100644 --- a/include/linux/platform_data/mmc-omap.h +++ b/include/linux/platform_data/mmc-omap.h @@ -108,8 +108,7 @@ struct omap_mmc_platform_data { const char *name; u32 ocr_mask; - /* Card detection IRQs */ - int card_detect_irq; + /* Card detection */ int (*card_detect)(struct device *dev, int slot); unsigned int ban_openended:1; -- cgit v1.2.3 From 3561afa02605b398d1b98e1ce913ea6411cdc5dd Mon Sep 17 00:00:00 2001 From: Andrew Jeffery Date: Thu, 14 Jan 2021 13:44:28 +1030 Subject: mmc: core: Add helper for parsing clock phase properties Drivers for MMC hosts that accept phase corrections can take advantage of the helper by embedding an instance of struct mmc_clk_phase_map in their private data and invoking mmc_of_parse_clk_phase() to extract phase parameters. It is the responsibility of the host driver to translate and apply the extracted values to hardware as required. Signed-off-by: Andrew Jeffery Link: https://lore.kernel.org/r/20210114031433.2388532-2-andrew@aj.id.au Signed-off-by: Ulf Hansson --- drivers/mmc/core/host.c | 44 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/mmc/host.h | 13 +++++++++++++ 2 files changed, 57 insertions(+) (limited to 'include') diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c index 96b2ca1f1b06..74e853bb6948 100644 --- a/drivers/mmc/core/host.c +++ b/drivers/mmc/core/host.c @@ -163,6 +163,50 @@ static void mmc_retune_timer(struct timer_list *t) mmc_retune_needed(host); } +static void mmc_of_parse_timing_phase(struct device *dev, const char *prop, + struct mmc_clk_phase *phase) +{ + int degrees[2] = {0}; + int rc; + + rc = device_property_read_u32_array(dev, prop, degrees, 2); + phase->valid = !rc; + if (phase->valid) { + phase->in_deg = degrees[0]; + phase->out_deg = degrees[1]; + } +} + +void +mmc_of_parse_clk_phase(struct mmc_host *host, struct mmc_clk_phase_map *map) +{ + struct device *dev = host->parent; + + mmc_of_parse_timing_phase(dev, "clk-phase-legacy", + &map->phase[MMC_TIMING_LEGACY]); + mmc_of_parse_timing_phase(dev, "clk-phase-mmc-hs", + &map->phase[MMC_TIMING_MMC_HS]); + mmc_of_parse_timing_phase(dev, "clk-phase-sd-hs", + &map->phase[MMC_TIMING_SD_HS]); + mmc_of_parse_timing_phase(dev, "clk-phase-uhs-sdr12", + &map->phase[MMC_TIMING_UHS_SDR12]); + mmc_of_parse_timing_phase(dev, "clk-phase-uhs-sdr25", + &map->phase[MMC_TIMING_UHS_SDR25]); + mmc_of_parse_timing_phase(dev, "clk-phase-uhs-sdr50", + &map->phase[MMC_TIMING_UHS_SDR50]); + mmc_of_parse_timing_phase(dev, "clk-phase-uhs-sdr104", + &map->phase[MMC_TIMING_UHS_SDR104]); + mmc_of_parse_timing_phase(dev, "clk-phase-uhs-ddr50", + &map->phase[MMC_TIMING_UHS_DDR50]); + mmc_of_parse_timing_phase(dev, "clk-phase-mmc-ddr52", + &map->phase[MMC_TIMING_MMC_DDR52]); + mmc_of_parse_timing_phase(dev, "clk-phase-mmc-hs200", + &map->phase[MMC_TIMING_MMC_HS200]); + mmc_of_parse_timing_phase(dev, "clk-phase-mmc-hs400", + &map->phase[MMC_TIMING_MMC_HS400]); +} +EXPORT_SYMBOL(mmc_of_parse_clk_phase); + /** * mmc_of_parse() - parse host's device-tree node * @host: host whose node should be parsed. diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 01bba36545c5..8cf686d98a68 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -79,6 +79,17 @@ struct mmc_ios { bool enhanced_strobe; /* hs400es selection */ }; +struct mmc_clk_phase { + bool valid; + u16 in_deg; + u16 out_deg; +}; + +#define MMC_NUM_CLK_PHASES (MMC_TIMING_MMC_HS400 + 1) +struct mmc_clk_phase_map { + struct mmc_clk_phase phase[MMC_NUM_CLK_PHASES]; +}; + struct mmc_host; struct mmc_host_ops { @@ -490,6 +501,8 @@ struct mmc_host *mmc_alloc_host(int extra, struct device *); int mmc_add_host(struct mmc_host *); void mmc_remove_host(struct mmc_host *); void mmc_free_host(struct mmc_host *); +void mmc_of_parse_clk_phase(struct mmc_host *host, + struct mmc_clk_phase_map *map); int mmc_of_parse(struct mmc_host *host); int mmc_of_parse_voltage(struct device_node *np, u32 *mask); -- cgit v1.2.3 From 5851d3b042b694839d2241fbb3200ce958135cdf Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Thu, 21 Jan 2021 00:21:54 -0800 Subject: block/keyslot-manager: introduce devm_blk_ksm_init() Add a resource-managed variant of blk_ksm_init() so that drivers don't have to worry about calling blk_ksm_destroy(). Note that the implementation uses a custom devres action to call blk_ksm_destroy() rather than switching the two allocations to be directly devres-managed, e.g. with devm_kmalloc(). This is because we need to keep zeroing the memory containing the keyslots when it is freed, and also because we want to continue using kvmalloc() (and there is no devm_kvmalloc()). Signed-off-by: Eric Biggers Reviewed-by: Satya Tangirala Acked-by: Jens Axboe Link: https://lore.kernel.org/r/20210121082155.111333-2-ebiggers@kernel.org Signed-off-by: Ulf Hansson --- Documentation/block/inline-encryption.rst | 12 ++++++------ block/keyslot-manager.c | 29 +++++++++++++++++++++++++++++ include/linux/keyslot-manager.h | 3 +++ 3 files changed, 38 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/Documentation/block/inline-encryption.rst b/Documentation/block/inline-encryption.rst index e75151e467d3..7f9b40d6b416 100644 --- a/Documentation/block/inline-encryption.rst +++ b/Documentation/block/inline-encryption.rst @@ -182,8 +182,9 @@ API presented to device drivers A :c:type:``struct blk_keyslot_manager`` should be set up by device drivers in the ``request_queue`` of the device. The device driver needs to call -``blk_ksm_init`` on the ``blk_keyslot_manager``, which specifying the number of -keyslots supported by the hardware. +``blk_ksm_init`` (or its resource-managed variant ``devm_blk_ksm_init``) on the +``blk_keyslot_manager``, while specifying the number of keyslots supported by +the hardware. The device driver also needs to tell the KSM how to actually manipulate the IE hardware in the device to do things like programming the crypto key into @@ -202,10 +203,9 @@ needs each and every of its keyslots to be reprogrammed with the key it "should have" at the point in time when the function is called. This is useful e.g. if a device loses all its keys on runtime power down/up. -``blk_ksm_destroy`` should be called to free up all resources used by a keyslot -manager upon ``blk_ksm_init``, once the ``blk_keyslot_manager`` is no longer -needed. - +If the driver used ``blk_ksm_init`` instead of ``devm_blk_ksm_init``, then +``blk_ksm_destroy`` should be called to free up all resources used by a +``blk_keyslot_manager`` once it is no longer needed. Layered Devices =============== diff --git a/block/keyslot-manager.c b/block/keyslot-manager.c index 86f8195d8039..324bf4244f5f 100644 --- a/block/keyslot-manager.c +++ b/block/keyslot-manager.c @@ -29,6 +29,7 @@ #define pr_fmt(fmt) "blk-crypto: " fmt #include +#include #include #include #include @@ -127,6 +128,34 @@ err_destroy_ksm: } EXPORT_SYMBOL_GPL(blk_ksm_init); +static void blk_ksm_destroy_callback(void *ksm) +{ + blk_ksm_destroy(ksm); +} + +/** + * devm_blk_ksm_init() - Resource-managed blk_ksm_init() + * @dev: The device which owns the blk_keyslot_manager. + * @ksm: The blk_keyslot_manager to initialize. + * @num_slots: The number of key slots to manage. + * + * Like blk_ksm_init(), but causes blk_ksm_destroy() to be called automatically + * on driver detach. + * + * Return: 0 on success, or else a negative error code. + */ +int devm_blk_ksm_init(struct device *dev, struct blk_keyslot_manager *ksm, + unsigned int num_slots) +{ + int err = blk_ksm_init(ksm, num_slots); + + if (err) + return err; + + return devm_add_action_or_reset(dev, blk_ksm_destroy_callback, ksm); +} +EXPORT_SYMBOL_GPL(devm_blk_ksm_init); + static inline struct hlist_head * blk_ksm_hash_bucket_for_key(struct blk_keyslot_manager *ksm, const struct blk_crypto_key *key) diff --git a/include/linux/keyslot-manager.h b/include/linux/keyslot-manager.h index 18f3f5346843..443ad817c6c5 100644 --- a/include/linux/keyslot-manager.h +++ b/include/linux/keyslot-manager.h @@ -85,6 +85,9 @@ struct blk_keyslot_manager { int blk_ksm_init(struct blk_keyslot_manager *ksm, unsigned int num_slots); +int devm_blk_ksm_init(struct device *dev, struct blk_keyslot_manager *ksm, + unsigned int num_slots); + blk_status_t blk_ksm_get_slot_for_key(struct blk_keyslot_manager *ksm, const struct blk_crypto_key *key, struct blk_ksm_keyslot **slot_ptr); -- cgit v1.2.3 From 93f1c150cb0d043e1e8985db7824b4e2e1ac653f Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 25 Jan 2021 16:14:48 -0800 Subject: mmc: core: Add basic support for inline encryption In preparation for adding CQHCI crypto engine (inline encryption) support, add the code required to make mmc_core and mmc_block aware of inline encryption. Specifically: - Add a capability flag MMC_CAP2_CRYPTO to struct mmc_host. Drivers will set this if the host and driver support inline encryption. - Embed a blk_keyslot_manager in struct mmc_host. Drivers will initialize this (as a device-managed resource) if the host and driver support inline encryption. mmc_block registers this keyslot manager with the request_queue of any MMC card attached to the host. - Make mmc_block copy the crypto keyslot and crypto data unit number from struct request to struct mmc_request, so that drivers will have access to them. - If the MMC host is reset, reprogram all the keyslots to ensure that the software state stays in sync with the hardware state. Co-developed-by: Satya Tangirala Signed-off-by: Satya Tangirala Acked-by: Adrian Hunter Reviewed-by: Satya Tangirala Reviewed-and-tested-by: Peng Zhou Signed-off-by: Eric Biggers Link: https://lore.kernel.org/r/20210126001456.382989-2-ebiggers@kernel.org Signed-off-by: Ulf Hansson --- drivers/mmc/core/Kconfig | 8 ++++++++ drivers/mmc/core/Makefile | 1 + drivers/mmc/core/block.c | 3 +++ drivers/mmc/core/core.c | 3 +++ drivers/mmc/core/crypto.c | 48 +++++++++++++++++++++++++++++++++++++++++++++++ drivers/mmc/core/crypto.h | 40 +++++++++++++++++++++++++++++++++++++++ drivers/mmc/core/host.c | 1 + drivers/mmc/core/queue.c | 3 +++ include/linux/mmc/core.h | 6 ++++++ include/linux/mmc/host.h | 11 +++++++++++ 10 files changed, 124 insertions(+) create mode 100644 drivers/mmc/core/crypto.c create mode 100644 drivers/mmc/core/crypto.h (limited to 'include') diff --git a/drivers/mmc/core/Kconfig b/drivers/mmc/core/Kconfig index c12fe13e4b14..ae8b69aee619 100644 --- a/drivers/mmc/core/Kconfig +++ b/drivers/mmc/core/Kconfig @@ -81,3 +81,11 @@ config MMC_TEST This driver is only of interest to those developing or testing a host driver. Most people should say N here. +config MMC_CRYPTO + bool "MMC Crypto Engine Support" + depends on BLK_INLINE_ENCRYPTION + help + Enable Crypto Engine Support in MMC. + Enabling this makes it possible for the kernel to use the crypto + capabilities of the MMC device (if present) to perform crypto + operations on data being transferred to/from the device. diff --git a/drivers/mmc/core/Makefile b/drivers/mmc/core/Makefile index 95ffe008ebdf..6a907736cd7a 100644 --- a/drivers/mmc/core/Makefile +++ b/drivers/mmc/core/Makefile @@ -18,3 +18,4 @@ obj-$(CONFIG_MMC_BLOCK) += mmc_block.o mmc_block-objs := block.o queue.o obj-$(CONFIG_MMC_TEST) += mmc_test.o obj-$(CONFIG_SDIO_UART) += sdio_uart.o +mmc_core-$(CONFIG_MMC_CRYPTO) += crypto.o diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 42e27a298218..b877f62df366 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -51,6 +51,7 @@ #include "block.h" #include "core.h" #include "card.h" +#include "crypto.h" #include "host.h" #include "bus.h" #include "mmc_ops.h" @@ -1247,6 +1248,8 @@ static void mmc_blk_data_prep(struct mmc_queue *mq, struct mmc_queue_req *mqrq, memset(brq, 0, sizeof(struct mmc_blk_request)); + mmc_crypto_prepare_req(mqrq); + brq->mrq.data = &brq->data; brq->mrq.tag = req->tag; diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c index 49d9117550af..1136b859ddd8 100644 --- a/drivers/mmc/core/core.c +++ b/drivers/mmc/core/core.c @@ -37,6 +37,7 @@ #include "core.h" #include "card.h" +#include "crypto.h" #include "bus.h" #include "host.h" #include "sdio_bus.h" @@ -992,6 +993,8 @@ void mmc_set_initial_state(struct mmc_host *host) host->ops->hs400_enhanced_strobe(host, &host->ios); mmc_set_ios(host); + + mmc_crypto_set_initial_state(host); } /** diff --git a/drivers/mmc/core/crypto.c b/drivers/mmc/core/crypto.c new file mode 100644 index 000000000000..419a368f8402 --- /dev/null +++ b/drivers/mmc/core/crypto.c @@ -0,0 +1,48 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * MMC crypto engine (inline encryption) support + * + * Copyright 2020 Google LLC + */ + +#include +#include + +#include "core.h" +#include "crypto.h" +#include "queue.h" + +void mmc_crypto_set_initial_state(struct mmc_host *host) +{ + /* Reset might clear all keys, so reprogram all the keys. */ + if (host->caps2 & MMC_CAP2_CRYPTO) + blk_ksm_reprogram_all_keys(&host->ksm); +} + +void mmc_crypto_setup_queue(struct request_queue *q, struct mmc_host *host) +{ + if (host->caps2 & MMC_CAP2_CRYPTO) + blk_ksm_register(&host->ksm, q); +} +EXPORT_SYMBOL_GPL(mmc_crypto_setup_queue); + +void mmc_crypto_prepare_req(struct mmc_queue_req *mqrq) +{ + struct request *req = mmc_queue_req_to_req(mqrq); + struct mmc_request *mrq = &mqrq->brq.mrq; + + if (!req->crypt_keyslot) + return; + + mrq->crypto_enabled = true; + mrq->crypto_key_slot = blk_ksm_get_slot_idx(req->crypt_keyslot); + + /* + * For now we assume that all MMC drivers set max_dun_bytes_supported=4, + * which is the limit for CQHCI crypto. So all DUNs should be 32-bit. + */ + WARN_ON_ONCE(req->crypt_ctx->bc_dun[0] > U32_MAX); + + mrq->data_unit_num = req->crypt_ctx->bc_dun[0]; +} +EXPORT_SYMBOL_GPL(mmc_crypto_prepare_req); diff --git a/drivers/mmc/core/crypto.h b/drivers/mmc/core/crypto.h new file mode 100644 index 000000000000..fbe9a520bf90 --- /dev/null +++ b/drivers/mmc/core/crypto.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * MMC crypto engine (inline encryption) support + * + * Copyright 2020 Google LLC + */ + +#ifndef _MMC_CORE_CRYPTO_H +#define _MMC_CORE_CRYPTO_H + +struct mmc_host; +struct mmc_queue_req; +struct request_queue; + +#ifdef CONFIG_MMC_CRYPTO + +void mmc_crypto_set_initial_state(struct mmc_host *host); + +void mmc_crypto_setup_queue(struct request_queue *q, struct mmc_host *host); + +void mmc_crypto_prepare_req(struct mmc_queue_req *mqrq); + +#else /* CONFIG_MMC_CRYPTO */ + +static inline void mmc_crypto_set_initial_state(struct mmc_host *host) +{ +} + +static inline void mmc_crypto_setup_queue(struct request_queue *q, + struct mmc_host *host) +{ +} + +static inline void mmc_crypto_prepare_req(struct mmc_queue_req *mqrq) +{ +} + +#endif /* !CONFIG_MMC_CRYPTO */ + +#endif /* _MMC_CORE_CRYPTO_H */ diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c index 74e853bb6948..9b89a91b6b47 100644 --- a/drivers/mmc/core/host.c +++ b/drivers/mmc/core/host.c @@ -25,6 +25,7 @@ #include #include "core.h" +#include "crypto.h" #include "host.h" #include "slot-gpio.h" #include "pwrseq.h" diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c index 002426e3cf76..33e7e65b6dde 100644 --- a/drivers/mmc/core/queue.c +++ b/drivers/mmc/core/queue.c @@ -19,6 +19,7 @@ #include "block.h" #include "core.h" #include "card.h" +#include "crypto.h" #include "host.h" #define MMC_DMA_MAP_MERGE_SEGMENTS 512 @@ -407,6 +408,8 @@ static void mmc_setup_queue(struct mmc_queue *mq, struct mmc_card *card) mutex_init(&mq->complete_lock); init_waitqueue_head(&mq->wait); + + mmc_crypto_setup_queue(mq->queue, host); } static inline bool mmc_merge_capable(struct mmc_host *host) diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index 29aa50711626..ab19245e9945 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -162,6 +162,12 @@ struct mmc_request { bool cap_cmd_during_tfr; int tag; + +#ifdef CONFIG_MMC_CRYPTO + bool crypto_enabled; + int crypto_key_slot; + u32 data_unit_num; +#endif }; struct mmc_card; diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 8cf686d98a68..927ba7566617 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -15,6 +15,7 @@ #include #include #include +#include struct mmc_ios { unsigned int clock; /* clock rate */ @@ -395,6 +396,11 @@ struct mmc_host { #define MMC_CAP2_CQE_DCMD (1 << 24) /* CQE can issue a direct command */ #define MMC_CAP2_AVOID_3_3V (1 << 25) /* Host must negotiate down from 3.3V */ #define MMC_CAP2_MERGE_CAPABLE (1 << 26) /* Host can merge a segment over the segment size */ +#ifdef CONFIG_MMC_CRYPTO +#define MMC_CAP2_CRYPTO (1 << 27) /* Host supports inline encryption */ +#else +#define MMC_CAP2_CRYPTO 0 +#endif int fixed_drv_type; /* fixed driver type for non-removable media */ @@ -489,6 +495,11 @@ struct mmc_host { bool cqe_enabled; bool cqe_on; + /* Inline encryption support */ +#ifdef CONFIG_MMC_CRYPTO + struct blk_keyslot_manager ksm; +#endif + /* Host Software Queue support */ bool hsq_enabled; -- cgit v1.2.3 From 5cf482f2f7a658fe4f74e97ed7e6e7f8263df03f Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Mon, 11 Jan 2021 19:18:43 +0800 Subject: dt-bindings: memory: mediatek: Add a common memory header file Put all the macros about smi larb/port togethers. Signed-off-by: Yong Wu Acked-by: Rob Herring Acked-by: Krzysztof Kozlowski Reviewed-by: Tomasz Figa Link: https://lore.kernel.org/r/20210111111914.22211-3-yong.wu@mediatek.com Signed-off-by: Will Deacon --- include/dt-bindings/memory/mt2712-larb-port.h | 2 +- include/dt-bindings/memory/mt6779-larb-port.h | 2 +- include/dt-bindings/memory/mt8167-larb-port.h | 2 +- include/dt-bindings/memory/mt8173-larb-port.h | 2 +- include/dt-bindings/memory/mt8183-larb-port.h | 2 +- include/dt-bindings/memory/mtk-memory-port.h | 15 +++++++++++++++ 6 files changed, 20 insertions(+), 5 deletions(-) create mode 100644 include/dt-bindings/memory/mtk-memory-port.h (limited to 'include') diff --git a/include/dt-bindings/memory/mt2712-larb-port.h b/include/dt-bindings/memory/mt2712-larb-port.h index 6f9aa7349cef..83e8070b4c1c 100644 --- a/include/dt-bindings/memory/mt2712-larb-port.h +++ b/include/dt-bindings/memory/mt2712-larb-port.h @@ -6,7 +6,7 @@ #ifndef __DTS_IOMMU_PORT_MT2712_H #define __DTS_IOMMU_PORT_MT2712_H -#define MTK_M4U_ID(larb, port) (((larb) << 5) | (port)) +#include #define M4U_LARB0_ID 0 #define M4U_LARB1_ID 1 diff --git a/include/dt-bindings/memory/mt6779-larb-port.h b/include/dt-bindings/memory/mt6779-larb-port.h index 2ad0899fbf2f..91b0be285f41 100644 --- a/include/dt-bindings/memory/mt6779-larb-port.h +++ b/include/dt-bindings/memory/mt6779-larb-port.h @@ -7,7 +7,7 @@ #ifndef _DTS_IOMMU_PORT_MT6779_H_ #define _DTS_IOMMU_PORT_MT6779_H_ -#define MTK_M4U_ID(larb, port) (((larb) << 5) | (port)) +#include #define M4U_LARB0_ID 0 #define M4U_LARB1_ID 1 diff --git a/include/dt-bindings/memory/mt8167-larb-port.h b/include/dt-bindings/memory/mt8167-larb-port.h index 000fb299a408..13925c4fee00 100644 --- a/include/dt-bindings/memory/mt8167-larb-port.h +++ b/include/dt-bindings/memory/mt8167-larb-port.h @@ -8,7 +8,7 @@ #ifndef __DTS_IOMMU_PORT_MT8167_H #define __DTS_IOMMU_PORT_MT8167_H -#define MTK_M4U_ID(larb, port) (((larb) << 5) | (port)) +#include #define M4U_LARB0_ID 0 #define M4U_LARB1_ID 1 diff --git a/include/dt-bindings/memory/mt8173-larb-port.h b/include/dt-bindings/memory/mt8173-larb-port.h index 9f31ccfeca21..c2379b3236d6 100644 --- a/include/dt-bindings/memory/mt8173-larb-port.h +++ b/include/dt-bindings/memory/mt8173-larb-port.h @@ -6,7 +6,7 @@ #ifndef __DTS_IOMMU_PORT_MT8173_H #define __DTS_IOMMU_PORT_MT8173_H -#define MTK_M4U_ID(larb, port) (((larb) << 5) | (port)) +#include #define M4U_LARB0_ID 0 #define M4U_LARB1_ID 1 diff --git a/include/dt-bindings/memory/mt8183-larb-port.h b/include/dt-bindings/memory/mt8183-larb-port.h index 2c579f305162..de8bf81b5d9e 100644 --- a/include/dt-bindings/memory/mt8183-larb-port.h +++ b/include/dt-bindings/memory/mt8183-larb-port.h @@ -6,7 +6,7 @@ #ifndef __DTS_IOMMU_PORT_MT8183_H #define __DTS_IOMMU_PORT_MT8183_H -#define MTK_M4U_ID(larb, port) (((larb) << 5) | (port)) +#include #define M4U_LARB0_ID 0 #define M4U_LARB1_ID 1 diff --git a/include/dt-bindings/memory/mtk-memory-port.h b/include/dt-bindings/memory/mtk-memory-port.h new file mode 100644 index 000000000000..53354cf4f6e3 --- /dev/null +++ b/include/dt-bindings/memory/mtk-memory-port.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2020 MediaTek Inc. + * Author: Yong Wu + */ +#ifndef __DT_BINDINGS_MEMORY_MTK_MEMORY_PORT_H_ +#define __DT_BINDINGS_MEMORY_MTK_MEMORY_PORT_H_ + +#define MTK_LARB_NR_MAX 16 + +#define MTK_M4U_ID(larb, port) (((larb) << 5) | (port)) +#define MTK_M4U_TO_LARB(id) (((id) >> 5) & 0xf) +#define MTK_M4U_TO_PORT(id) ((id) & 0x1f) + +#endif -- cgit v1.2.3 From ca49a4b4c9895a873213ae93abae5855e8d226c6 Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Mon, 11 Jan 2021 19:18:44 +0800 Subject: dt-bindings: memory: mediatek: Extend LARB_NR_MAX to 32 Extend the max larb number definition as mt8192 has larb_nr over 16. Signed-off-by: Yong Wu Acked-by: Rob Herring Acked-by: Krzysztof Kozlowski Reviewed-by: Tomasz Figa Link: https://lore.kernel.org/r/20210111111914.22211-4-yong.wu@mediatek.com Signed-off-by: Will Deacon --- Documentation/devicetree/bindings/iommu/mediatek,iommu.yaml | 2 +- include/dt-bindings/memory/mtk-memory-port.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/Documentation/devicetree/bindings/iommu/mediatek,iommu.yaml b/Documentation/devicetree/bindings/iommu/mediatek,iommu.yaml index b9946809fc2b..ba6626347381 100644 --- a/Documentation/devicetree/bindings/iommu/mediatek,iommu.yaml +++ b/Documentation/devicetree/bindings/iommu/mediatek,iommu.yaml @@ -99,7 +99,7 @@ properties: mediatek,larbs: $ref: /schemas/types.yaml#/definitions/phandle-array minItems: 1 - maxItems: 16 + maxItems: 32 description: | List of phandle to the local arbiters in the current Socs. Refer to bindings/memory-controllers/mediatek,smi-larb.yaml. It must sort diff --git a/include/dt-bindings/memory/mtk-memory-port.h b/include/dt-bindings/memory/mtk-memory-port.h index 53354cf4f6e3..7d64103209af 100644 --- a/include/dt-bindings/memory/mtk-memory-port.h +++ b/include/dt-bindings/memory/mtk-memory-port.h @@ -6,10 +6,10 @@ #ifndef __DT_BINDINGS_MEMORY_MTK_MEMORY_PORT_H_ #define __DT_BINDINGS_MEMORY_MTK_MEMORY_PORT_H_ -#define MTK_LARB_NR_MAX 16 +#define MTK_LARB_NR_MAX 32 #define MTK_M4U_ID(larb, port) (((larb) << 5) | (port)) -#define MTK_M4U_TO_LARB(id) (((id) >> 5) & 0xf) +#define MTK_M4U_TO_LARB(id) (((id) >> 5) & 0x1f) #define MTK_M4U_TO_PORT(id) ((id) & 0x1f) #endif -- cgit v1.2.3 From ddd3e349b8aad5b814d17fc3bcf7a5a90af6d296 Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Mon, 11 Jan 2021 19:18:45 +0800 Subject: dt-bindings: memory: mediatek: Rename header guard for SMI header file Only rename the header guard for all the SoC larb port header file. No funtional change. Suggested-by: Krzysztof Kozlowski Signed-off-by: Yong Wu Acked-by: Krzysztof Kozlowski Acked-by: Rob Herring Reviewed-by: Tomasz Figa Link: https://lore.kernel.org/r/20210111111914.22211-5-yong.wu@mediatek.com Signed-off-by: Will Deacon --- include/dt-bindings/memory/mt2701-larb-port.h | 4 ++-- include/dt-bindings/memory/mt2712-larb-port.h | 4 ++-- include/dt-bindings/memory/mt6779-larb-port.h | 4 ++-- include/dt-bindings/memory/mt8167-larb-port.h | 4 ++-- include/dt-bindings/memory/mt8173-larb-port.h | 4 ++-- include/dt-bindings/memory/mt8183-larb-port.h | 4 ++-- 6 files changed, 12 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/dt-bindings/memory/mt2701-larb-port.h b/include/dt-bindings/memory/mt2701-larb-port.h index 2d85c2ec6cfd..25d03526f142 100644 --- a/include/dt-bindings/memory/mt2701-larb-port.h +++ b/include/dt-bindings/memory/mt2701-larb-port.h @@ -4,8 +4,8 @@ * Author: Honghui Zhang */ -#ifndef _MT2701_LARB_PORT_H_ -#define _MT2701_LARB_PORT_H_ +#ifndef _DT_BINDINGS_MEMORY_MT2701_LARB_PORT_H_ +#define _DT_BINDINGS_MEMORY_MT2701_LARB_PORT_H_ /* * Mediatek m4u generation 1 such as mt2701 has flat m4u port numbers, diff --git a/include/dt-bindings/memory/mt2712-larb-port.h b/include/dt-bindings/memory/mt2712-larb-port.h index 83e8070b4c1c..e41a2841bcff 100644 --- a/include/dt-bindings/memory/mt2712-larb-port.h +++ b/include/dt-bindings/memory/mt2712-larb-port.h @@ -3,8 +3,8 @@ * Copyright (c) 2017 MediaTek Inc. * Author: Yong Wu */ -#ifndef __DTS_IOMMU_PORT_MT2712_H -#define __DTS_IOMMU_PORT_MT2712_H +#ifndef _DT_BINDINGS_MEMORY_MT2712_LARB_PORT_H_ +#define _DT_BINDINGS_MEMORY_MT2712_LARB_PORT_H_ #include diff --git a/include/dt-bindings/memory/mt6779-larb-port.h b/include/dt-bindings/memory/mt6779-larb-port.h index 91b0be285f41..3fb438a96e35 100644 --- a/include/dt-bindings/memory/mt6779-larb-port.h +++ b/include/dt-bindings/memory/mt6779-larb-port.h @@ -4,8 +4,8 @@ * Author: Chao Hao */ -#ifndef _DTS_IOMMU_PORT_MT6779_H_ -#define _DTS_IOMMU_PORT_MT6779_H_ +#ifndef _DT_BINDINGS_MEMORY_MT6779_LARB_PORT_H_ +#define _DT_BINDINGS_MEMORY_MT6779_LARB_PORT_H_ #include diff --git a/include/dt-bindings/memory/mt8167-larb-port.h b/include/dt-bindings/memory/mt8167-larb-port.h index 13925c4fee00..aae57d4824ca 100644 --- a/include/dt-bindings/memory/mt8167-larb-port.h +++ b/include/dt-bindings/memory/mt8167-larb-port.h @@ -5,8 +5,8 @@ * Author: Honghui Zhang * Author: Fabien Parent */ -#ifndef __DTS_IOMMU_PORT_MT8167_H -#define __DTS_IOMMU_PORT_MT8167_H +#ifndef _DT_BINDINGS_MEMORY_MT8167_LARB_PORT_H_ +#define _DT_BINDINGS_MEMORY_MT8167_LARB_PORT_H_ #include diff --git a/include/dt-bindings/memory/mt8173-larb-port.h b/include/dt-bindings/memory/mt8173-larb-port.h index c2379b3236d6..167a7fc51868 100644 --- a/include/dt-bindings/memory/mt8173-larb-port.h +++ b/include/dt-bindings/memory/mt8173-larb-port.h @@ -3,8 +3,8 @@ * Copyright (c) 2015-2016 MediaTek Inc. * Author: Yong Wu */ -#ifndef __DTS_IOMMU_PORT_MT8173_H -#define __DTS_IOMMU_PORT_MT8173_H +#ifndef _DT_BINDINGS_MEMORY_MT8173_LARB_PORT_H_ +#define _DT_BINDINGS_MEMORY_MT8173_LARB_PORT_H_ #include diff --git a/include/dt-bindings/memory/mt8183-larb-port.h b/include/dt-bindings/memory/mt8183-larb-port.h index de8bf81b5d9e..36abdf0ce5a2 100644 --- a/include/dt-bindings/memory/mt8183-larb-port.h +++ b/include/dt-bindings/memory/mt8183-larb-port.h @@ -3,8 +3,8 @@ * Copyright (c) 2018 MediaTek Inc. * Author: Yong Wu */ -#ifndef __DTS_IOMMU_PORT_MT8183_H -#define __DTS_IOMMU_PORT_MT8183_H +#ifndef _DT_BINDINGS_MEMORY_MT8183_LARB_PORT_H_ +#define _DT_BINDINGS_MEMORY_MT8183_LARB_PORT_H_ #include -- cgit v1.2.3 From fc3734698a435b301183acc8332f0a5fba868bc3 Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Mon, 11 Jan 2021 19:18:46 +0800 Subject: dt-bindings: mediatek: Add binding for mt8192 IOMMU This patch adds decriptions for mt8192 IOMMU and SMI. mt8192 also is MTK IOMMU gen2 which uses ARM Short-Descriptor translation table format. The M4U-SMI HW diagram is as below: EMI | M4U | ------------ SMI Common ------------ | +-------+------+------+----------------------+-------+ | | | | ...... | | | | | | | | larb0 larb1 larb2 larb4 ...... larb19 larb20 disp0 disp1 mdp vdec IPE IPE All the connections are HW fixed, SW can NOT adjust it. mt8192 M4U support 0~16GB iova range. we preassign different engines into different iova ranges: domain-id module iova-range larbs 0 disp 0 ~ 4G larb0/1 1 vcodec 4G ~ 8G larb4/5/7 2 cam/mdp 8G ~ 12G larb2/9/11/13/14/16/17/18/19/20 3 CCU0 0x4000_0000 ~ 0x43ff_ffff larb13: port 9/10 4 CCU1 0x4400_0000 ~ 0x47ff_ffff larb14: port 4/5 The iova range for CCU0/1(camera control unit) is HW requirement. Signed-off-by: Yong Wu Reviewed-by: Rob Herring Acked-by: Krzysztof Kozlowski Reviewed-by: Tomasz Figa Link: https://lore.kernel.org/r/20210111111914.22211-6-yong.wu@mediatek.com Signed-off-by: Will Deacon --- .../devicetree/bindings/iommu/mediatek,iommu.yaml | 18 +- include/dt-bindings/memory/mt8192-larb-port.h | 243 +++++++++++++++++++++ 2 files changed, 260 insertions(+), 1 deletion(-) create mode 100644 include/dt-bindings/memory/mt8192-larb-port.h (limited to 'include') diff --git a/Documentation/devicetree/bindings/iommu/mediatek,iommu.yaml b/Documentation/devicetree/bindings/iommu/mediatek,iommu.yaml index ba6626347381..0f26fe14c8e2 100644 --- a/Documentation/devicetree/bindings/iommu/mediatek,iommu.yaml +++ b/Documentation/devicetree/bindings/iommu/mediatek,iommu.yaml @@ -76,6 +76,7 @@ properties: - mediatek,mt8167-m4u # generation two - mediatek,mt8173-m4u # generation two - mediatek,mt8183-m4u # generation two + - mediatek,mt8192-m4u # generation two - description: mt7623 generation one items: @@ -115,7 +116,11 @@ properties: dt-binding/memory/mt6779-larb-port.h for mt6779, dt-binding/memory/mt8167-larb-port.h for mt8167, dt-binding/memory/mt8173-larb-port.h for mt8173, - dt-binding/memory/mt8183-larb-port.h for mt8183. + dt-binding/memory/mt8183-larb-port.h for mt8183, + dt-binding/memory/mt8192-larb-port.h for mt8192. + + power-domains: + maxItems: 1 required: - compatible @@ -133,11 +138,22 @@ allOf: - mediatek,mt2701-m4u - mediatek,mt2712-m4u - mediatek,mt8173-m4u + - mediatek,mt8192-m4u then: required: - clocks + - if: + properties: + compatible: + enum: + - mediatek,mt8192-m4u + + then: + required: + - power-domains + additionalProperties: false examples: diff --git a/include/dt-bindings/memory/mt8192-larb-port.h b/include/dt-bindings/memory/mt8192-larb-port.h new file mode 100644 index 000000000000..23035a52c675 --- /dev/null +++ b/include/dt-bindings/memory/mt8192-larb-port.h @@ -0,0 +1,243 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2020 MediaTek Inc. + * + * Author: Chao Hao + * Author: Yong Wu + */ +#ifndef _DT_BINDINGS_MEMORY_MT8192_LARB_PORT_H_ +#define _DT_BINDINGS_MEMORY_MT8192_LARB_PORT_H_ + +#include + +/* + * MM IOMMU supports 16GB dma address. + * + * The address will preassign like this: + * + * modules dma-address-region larbs-ports + * disp 0 ~ 4G larb0/1 + * vcodec 4G ~ 8G larb4/5/7 + * cam/mdp 8G ~ 12G larb2/9/11/13/14/16/17/18/19/20 + * CCU0 0x4000_0000 ~ 0x43ff_ffff larb13: port 9/10 + * CCU1 0x4400_0000 ~ 0x47ff_ffff larb14: port 4/5 + * + * larb3/6/8/10/12/15 is null. + */ + +/* larb0 */ +#define M4U_PORT_L0_DISP_POSTMASK0 MTK_M4U_ID(0, 0) +#define M4U_PORT_L0_OVL_RDMA0_HDR MTK_M4U_ID(0, 1) +#define M4U_PORT_L0_OVL_RDMA0 MTK_M4U_ID(0, 2) +#define M4U_PORT_L0_DISP_RDMA0 MTK_M4U_ID(0, 3) +#define M4U_PORT_L0_DISP_WDMA0 MTK_M4U_ID(0, 4) +#define M4U_PORT_L0_DISP_FAKE0 MTK_M4U_ID(0, 5) + +/* larb1 */ +#define M4U_PORT_L1_OVL_2L_RDMA0_HDR MTK_M4U_ID(1, 0) +#define M4U_PORT_L1_OVL_2L_RDMA2_HDR MTK_M4U_ID(1, 1) +#define M4U_PORT_L1_OVL_2L_RDMA0 MTK_M4U_ID(1, 2) +#define M4U_PORT_L1_OVL_2L_RDMA2 MTK_M4U_ID(1, 3) +#define M4U_PORT_L1_DISP_MDP_RDMA4 MTK_M4U_ID(1, 4) +#define M4U_PORT_L1_DISP_RDMA4 MTK_M4U_ID(1, 5) +#define M4U_PORT_L1_DISP_UFBC_WDMA0 MTK_M4U_ID(1, 6) +#define M4U_PORT_L1_DISP_FAKE1 MTK_M4U_ID(1, 7) + +/* larb2 */ +#define M4U_PORT_L2_MDP_RDMA0 MTK_M4U_ID(2, 0) +#define M4U_PORT_L2_MDP_RDMA1 MTK_M4U_ID(2, 1) +#define M4U_PORT_L2_MDP_WROT0 MTK_M4U_ID(2, 2) +#define M4U_PORT_L2_MDP_WROT1 MTK_M4U_ID(2, 3) +#define M4U_PORT_L2_MDP_DISP_FAKE0 MTK_M4U_ID(2, 4) + +/* larb3: null */ + +/* larb4 */ +#define M4U_PORT_L4_VDEC_MC_EXT MTK_M4U_ID(4, 0) +#define M4U_PORT_L4_VDEC_UFO_EXT MTK_M4U_ID(4, 1) +#define M4U_PORT_L4_VDEC_PP_EXT MTK_M4U_ID(4, 2) +#define M4U_PORT_L4_VDEC_PRED_RD_EXT MTK_M4U_ID(4, 3) +#define M4U_PORT_L4_VDEC_PRED_WR_EXT MTK_M4U_ID(4, 4) +#define M4U_PORT_L4_VDEC_PPWRAP_EXT MTK_M4U_ID(4, 5) +#define M4U_PORT_L4_VDEC_TILE_EXT MTK_M4U_ID(4, 6) +#define M4U_PORT_L4_VDEC_VLD_EXT MTK_M4U_ID(4, 7) +#define M4U_PORT_L4_VDEC_VLD2_EXT MTK_M4U_ID(4, 8) +#define M4U_PORT_L4_VDEC_AVC_MV_EXT MTK_M4U_ID(4, 9) +#define M4U_PORT_L4_VDEC_RG_CTRL_DMA_EXT MTK_M4U_ID(4, 10) + +/* larb5 */ +#define M4U_PORT_L5_VDEC_LAT0_VLD_EXT MTK_M4U_ID(5, 0) +#define M4U_PORT_L5_VDEC_LAT0_VLD2_EXT MTK_M4U_ID(5, 1) +#define M4U_PORT_L5_VDEC_LAT0_AVC_MV_EXT MTK_M4U_ID(5, 2) +#define M4U_PORT_L5_VDEC_LAT0_PRED_RD_EXT MTK_M4U_ID(5, 3) +#define M4U_PORT_L5_VDEC_LAT0_TILE_EXT MTK_M4U_ID(5, 4) +#define M4U_PORT_L5_VDEC_LAT0_WDMA_EXT MTK_M4U_ID(5, 5) +#define M4U_PORT_L5_VDEC_LAT0_RG_CTRL_DMA_EXT MTK_M4U_ID(5, 6) +#define M4U_PORT_L5_VDEC_UFO_ENC_EXT MTK_M4U_ID(5, 7) + +/* larb6: null */ + +/* larb7 */ +#define M4U_PORT_L7_VENC_RCPU MTK_M4U_ID(7, 0) +#define M4U_PORT_L7_VENC_REC MTK_M4U_ID(7, 1) +#define M4U_PORT_L7_VENC_BSDMA MTK_M4U_ID(7, 2) +#define M4U_PORT_L7_VENC_SV_COMV MTK_M4U_ID(7, 3) +#define M4U_PORT_L7_VENC_RD_COMV MTK_M4U_ID(7, 4) +#define M4U_PORT_L7_VENC_CUR_LUMA MTK_M4U_ID(7, 5) +#define M4U_PORT_L7_VENC_CUR_CHROMA MTK_M4U_ID(7, 6) +#define M4U_PORT_L7_VENC_REF_LUMA MTK_M4U_ID(7, 7) +#define M4U_PORT_L7_VENC_REF_CHROMA MTK_M4U_ID(7, 8) +#define M4U_PORT_L7_JPGENC_Y_RDMA MTK_M4U_ID(7, 9) +#define M4U_PORT_L7_JPGENC_Q_RDMA MTK_M4U_ID(7, 10) +#define M4U_PORT_L7_JPGENC_C_TABLE MTK_M4U_ID(7, 11) +#define M4U_PORT_L7_JPGENC_BSDMA MTK_M4U_ID(7, 12) +#define M4U_PORT_L7_VENC_SUB_R_LUMA MTK_M4U_ID(7, 13) +#define M4U_PORT_L7_VENC_SUB_W_LUMA MTK_M4U_ID(7, 14) + +/* larb8: null */ + +/* larb9 */ +#define M4U_PORT_L9_IMG_IMGI_D1 MTK_M4U_ID(9, 0) +#define M4U_PORT_L9_IMG_IMGBI_D1 MTK_M4U_ID(9, 1) +#define M4U_PORT_L9_IMG_DMGI_D1 MTK_M4U_ID(9, 2) +#define M4U_PORT_L9_IMG_DEPI_D1 MTK_M4U_ID(9, 3) +#define M4U_PORT_L9_IMG_ICE_D1 MTK_M4U_ID(9, 4) +#define M4U_PORT_L9_IMG_SMTI_D1 MTK_M4U_ID(9, 5) +#define M4U_PORT_L9_IMG_SMTO_D2 MTK_M4U_ID(9, 6) +#define M4U_PORT_L9_IMG_SMTO_D1 MTK_M4U_ID(9, 7) +#define M4U_PORT_L9_IMG_CRZO_D1 MTK_M4U_ID(9, 8) +#define M4U_PORT_L9_IMG_IMG3O_D1 MTK_M4U_ID(9, 9) +#define M4U_PORT_L9_IMG_VIPI_D1 MTK_M4U_ID(9, 10) +#define M4U_PORT_L9_IMG_SMTI_D5 MTK_M4U_ID(9, 11) +#define M4U_PORT_L9_IMG_TIMGO_D1 MTK_M4U_ID(9, 12) +#define M4U_PORT_L9_IMG_UFBC_W0 MTK_M4U_ID(9, 13) +#define M4U_PORT_L9_IMG_UFBC_R0 MTK_M4U_ID(9, 14) + +/* larb10: null */ + +/* larb11 */ +#define M4U_PORT_L11_IMG_IMGI_D1 MTK_M4U_ID(11, 0) +#define M4U_PORT_L11_IMG_IMGBI_D1 MTK_M4U_ID(11, 1) +#define M4U_PORT_L11_IMG_DMGI_D1 MTK_M4U_ID(11, 2) +#define M4U_PORT_L11_IMG_DEPI_D1 MTK_M4U_ID(11, 3) +#define M4U_PORT_L11_IMG_ICE_D1 MTK_M4U_ID(11, 4) +#define M4U_PORT_L11_IMG_SMTI_D1 MTK_M4U_ID(11, 5) +#define M4U_PORT_L11_IMG_SMTO_D2 MTK_M4U_ID(11, 6) +#define M4U_PORT_L11_IMG_SMTO_D1 MTK_M4U_ID(11, 7) +#define M4U_PORT_L11_IMG_CRZO_D1 MTK_M4U_ID(11, 8) +#define M4U_PORT_L11_IMG_IMG3O_D1 MTK_M4U_ID(11, 9) +#define M4U_PORT_L11_IMG_VIPI_D1 MTK_M4U_ID(11, 10) +#define M4U_PORT_L11_IMG_SMTI_D5 MTK_M4U_ID(11, 11) +#define M4U_PORT_L11_IMG_TIMGO_D1 MTK_M4U_ID(11, 12) +#define M4U_PORT_L11_IMG_UFBC_W0 MTK_M4U_ID(11, 13) +#define M4U_PORT_L11_IMG_UFBC_R0 MTK_M4U_ID(11, 14) +#define M4U_PORT_L11_IMG_WPE_RDMA1 MTK_M4U_ID(11, 15) +#define M4U_PORT_L11_IMG_WPE_RDMA0 MTK_M4U_ID(11, 16) +#define M4U_PORT_L11_IMG_WPE_WDMA MTK_M4U_ID(11, 17) +#define M4U_PORT_L11_IMG_MFB_RDMA0 MTK_M4U_ID(11, 18) +#define M4U_PORT_L11_IMG_MFB_RDMA1 MTK_M4U_ID(11, 19) +#define M4U_PORT_L11_IMG_MFB_RDMA2 MTK_M4U_ID(11, 20) +#define M4U_PORT_L11_IMG_MFB_RDMA3 MTK_M4U_ID(11, 21) +#define M4U_PORT_L11_IMG_MFB_RDMA4 MTK_M4U_ID(11, 22) +#define M4U_PORT_L11_IMG_MFB_RDMA5 MTK_M4U_ID(11, 23) +#define M4U_PORT_L11_IMG_MFB_WDMA0 MTK_M4U_ID(11, 24) +#define M4U_PORT_L11_IMG_MFB_WDMA1 MTK_M4U_ID(11, 25) + +/* larb12: null */ + +/* larb13 */ +#define M4U_PORT_L13_CAM_MRAWI MTK_M4U_ID(13, 0) +#define M4U_PORT_L13_CAM_MRAWO0 MTK_M4U_ID(13, 1) +#define M4U_PORT_L13_CAM_MRAWO1 MTK_M4U_ID(13, 2) +#define M4U_PORT_L13_CAM_CAMSV1 MTK_M4U_ID(13, 3) +#define M4U_PORT_L13_CAM_CAMSV2 MTK_M4U_ID(13, 4) +#define M4U_PORT_L13_CAM_CAMSV3 MTK_M4U_ID(13, 5) +#define M4U_PORT_L13_CAM_CAMSV4 MTK_M4U_ID(13, 6) +#define M4U_PORT_L13_CAM_CAMSV5 MTK_M4U_ID(13, 7) +#define M4U_PORT_L13_CAM_CAMSV6 MTK_M4U_ID(13, 8) +#define M4U_PORT_L13_CAM_CCUI MTK_M4U_ID(13, 9) +#define M4U_PORT_L13_CAM_CCUO MTK_M4U_ID(13, 10) +#define M4U_PORT_L13_CAM_FAKE MTK_M4U_ID(13, 11) + +/* larb14 */ +#define M4U_PORT_L14_CAM_RESERVE1 MTK_M4U_ID(14, 0) +#define M4U_PORT_L14_CAM_RESERVE2 MTK_M4U_ID(14, 1) +#define M4U_PORT_L14_CAM_RESERVE3 MTK_M4U_ID(14, 2) +#define M4U_PORT_L14_CAM_CAMSV0 MTK_M4U_ID(14, 3) +#define M4U_PORT_L14_CAM_CCUI MTK_M4U_ID(14, 4) +#define M4U_PORT_L14_CAM_CCUO MTK_M4U_ID(14, 5) + +/* larb15: null */ + +/* larb16 */ +#define M4U_PORT_L16_CAM_IMGO_R1_A MTK_M4U_ID(16, 0) +#define M4U_PORT_L16_CAM_RRZO_R1_A MTK_M4U_ID(16, 1) +#define M4U_PORT_L16_CAM_CQI_R1_A MTK_M4U_ID(16, 2) +#define M4U_PORT_L16_CAM_BPCI_R1_A MTK_M4U_ID(16, 3) +#define M4U_PORT_L16_CAM_YUVO_R1_A MTK_M4U_ID(16, 4) +#define M4U_PORT_L16_CAM_UFDI_R2_A MTK_M4U_ID(16, 5) +#define M4U_PORT_L16_CAM_RAWI_R2_A MTK_M4U_ID(16, 6) +#define M4U_PORT_L16_CAM_RAWI_R3_A MTK_M4U_ID(16, 7) +#define M4U_PORT_L16_CAM_AAO_R1_A MTK_M4U_ID(16, 8) +#define M4U_PORT_L16_CAM_AFO_R1_A MTK_M4U_ID(16, 9) +#define M4U_PORT_L16_CAM_FLKO_R1_A MTK_M4U_ID(16, 10) +#define M4U_PORT_L16_CAM_LCESO_R1_A MTK_M4U_ID(16, 11) +#define M4U_PORT_L16_CAM_CRZO_R1_A MTK_M4U_ID(16, 12) +#define M4U_PORT_L16_CAM_LTMSO_R1_A MTK_M4U_ID(16, 13) +#define M4U_PORT_L16_CAM_RSSO_R1_A MTK_M4U_ID(16, 14) +#define M4U_PORT_L16_CAM_AAHO_R1_A MTK_M4U_ID(16, 15) +#define M4U_PORT_L16_CAM_LSCI_R1_A MTK_M4U_ID(16, 16) + +/* larb17 */ +#define M4U_PORT_L17_CAM_IMGO_R1_B MTK_M4U_ID(17, 0) +#define M4U_PORT_L17_CAM_RRZO_R1_B MTK_M4U_ID(17, 1) +#define M4U_PORT_L17_CAM_CQI_R1_B MTK_M4U_ID(17, 2) +#define M4U_PORT_L17_CAM_BPCI_R1_B MTK_M4U_ID(17, 3) +#define M4U_PORT_L17_CAM_YUVO_R1_B MTK_M4U_ID(17, 4) +#define M4U_PORT_L17_CAM_UFDI_R2_B MTK_M4U_ID(17, 5) +#define M4U_PORT_L17_CAM_RAWI_R2_B MTK_M4U_ID(17, 6) +#define M4U_PORT_L17_CAM_RAWI_R3_B MTK_M4U_ID(17, 7) +#define M4U_PORT_L17_CAM_AAO_R1_B MTK_M4U_ID(17, 8) +#define M4U_PORT_L17_CAM_AFO_R1_B MTK_M4U_ID(17, 9) +#define M4U_PORT_L17_CAM_FLKO_R1_B MTK_M4U_ID(17, 10) +#define M4U_PORT_L17_CAM_LCESO_R1_B MTK_M4U_ID(17, 11) +#define M4U_PORT_L17_CAM_CRZO_R1_B MTK_M4U_ID(17, 12) +#define M4U_PORT_L17_CAM_LTMSO_R1_B MTK_M4U_ID(17, 13) +#define M4U_PORT_L17_CAM_RSSO_R1_B MTK_M4U_ID(17, 14) +#define M4U_PORT_L17_CAM_AAHO_R1_B MTK_M4U_ID(17, 15) +#define M4U_PORT_L17_CAM_LSCI_R1_B MTK_M4U_ID(17, 16) + +/* larb18 */ +#define M4U_PORT_L18_CAM_IMGO_R1_C MTK_M4U_ID(18, 0) +#define M4U_PORT_L18_CAM_RRZO_R1_C MTK_M4U_ID(18, 1) +#define M4U_PORT_L18_CAM_CQI_R1_C MTK_M4U_ID(18, 2) +#define M4U_PORT_L18_CAM_BPCI_R1_C MTK_M4U_ID(18, 3) +#define M4U_PORT_L18_CAM_YUVO_R1_C MTK_M4U_ID(18, 4) +#define M4U_PORT_L18_CAM_UFDI_R2_C MTK_M4U_ID(18, 5) +#define M4U_PORT_L18_CAM_RAWI_R2_C MTK_M4U_ID(18, 6) +#define M4U_PORT_L18_CAM_RAWI_R3_C MTK_M4U_ID(18, 7) +#define M4U_PORT_L18_CAM_AAO_R1_C MTK_M4U_ID(18, 8) +#define M4U_PORT_L18_CAM_AFO_R1_C MTK_M4U_ID(18, 9) +#define M4U_PORT_L18_CAM_FLKO_R1_C MTK_M4U_ID(18, 10) +#define M4U_PORT_L18_CAM_LCESO_R1_C MTK_M4U_ID(18, 11) +#define M4U_PORT_L18_CAM_CRZO_R1_C MTK_M4U_ID(18, 12) +#define M4U_PORT_L18_CAM_LTMSO_R1_C MTK_M4U_ID(18, 13) +#define M4U_PORT_L18_CAM_RSSO_R1_C MTK_M4U_ID(18, 14) +#define M4U_PORT_L18_CAM_AAHO_R1_C MTK_M4U_ID(18, 15) +#define M4U_PORT_L18_CAM_LSCI_R1_C MTK_M4U_ID(18, 16) + +/* larb19 */ +#define M4U_PORT_L19_IPE_DVS_RDMA MTK_M4U_ID(19, 0) +#define M4U_PORT_L19_IPE_DVS_WDMA MTK_M4U_ID(19, 1) +#define M4U_PORT_L19_IPE_DVP_RDMA MTK_M4U_ID(19, 2) +#define M4U_PORT_L19_IPE_DVP_WDMA MTK_M4U_ID(19, 3) + +/* larb20 */ +#define M4U_PORT_L20_IPE_FDVT_RDA MTK_M4U_ID(20, 0) +#define M4U_PORT_L20_IPE_FDVT_RDB MTK_M4U_ID(20, 1) +#define M4U_PORT_L20_IPE_FDVT_WRA MTK_M4U_ID(20, 2) +#define M4U_PORT_L20_IPE_FDVT_WRB MTK_M4U_ID(20, 3) +#define M4U_PORT_L20_IPE_RSC_RDMA0 MTK_M4U_ID(20, 4) +#define M4U_PORT_L20_IPE_RSC_WDMA MTK_M4U_ID(20, 5) + +#endif -- cgit v1.2.3 From 66a28915541549f0fe0f4c705dab77443f22b5d6 Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Mon, 11 Jan 2021 19:18:49 +0800 Subject: iommu/mediatek: Use the common mtk-memory-port.h Use the common memory header(larb-port) in the source code. Signed-off-by: Yong Wu Acked-by: Krzysztof Kozlowski Reviewed-by: Tomasz Figa Link: https://lore.kernel.org/r/20210111111914.22211-9-yong.wu@mediatek.com Signed-off-by: Will Deacon --- drivers/iommu/mtk_iommu.c | 7 ------- drivers/iommu/mtk_iommu.h | 1 + drivers/memory/mtk-smi.c | 1 + include/soc/mediatek/smi.h | 2 -- 4 files changed, 2 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index 86ab577c9520..f594971dbeb2 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -103,13 +103,6 @@ #define MTK_PROTECT_PA_ALIGN 256 -/* - * Get the local arbiter ID and the portid within the larb arbiter - * from mtk_m4u_id which is defined by MTK_M4U_ID. - */ -#define MTK_M4U_TO_LARB(id) (((id) >> 5) & 0xf) -#define MTK_M4U_TO_PORT(id) ((id) & 0x1f) - #define HAS_4GB_MODE BIT(0) /* HW will use the EMI clock if there isn't the "bclk". */ #define HAS_BCLK BIT(1) diff --git a/drivers/iommu/mtk_iommu.h b/drivers/iommu/mtk_iommu.h index df32b3e3408b..c1584dea66cb 100644 --- a/drivers/iommu/mtk_iommu.h +++ b/drivers/iommu/mtk_iommu.h @@ -17,6 +17,7 @@ #include #include #include +#include #define MTK_LARB_COM_MAX 8 #define MTK_LARB_SUBCOM_MAX 4 diff --git a/drivers/memory/mtk-smi.c b/drivers/memory/mtk-smi.c index ac350f8d1e20..89f92fa2afa5 100644 --- a/drivers/memory/mtk-smi.c +++ b/drivers/memory/mtk-smi.c @@ -15,6 +15,7 @@ #include #include #include +#include /* mt8173 */ #define SMI_LARB_MMU_EN 0xf00 diff --git a/include/soc/mediatek/smi.h b/include/soc/mediatek/smi.h index 5a34b87d89e3..9371bf572ab8 100644 --- a/include/soc/mediatek/smi.h +++ b/include/soc/mediatek/smi.h @@ -11,8 +11,6 @@ #ifdef CONFIG_MTK_SMI -#define MTK_LARB_NR_MAX 16 - #define MTK_SMI_MMU_EN(port) BIT(port) struct mtk_smi_larb_iommu { -- cgit v1.2.3 From 40596d2f2b6075f6c33180b2f55c814ff4885475 Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Mon, 11 Jan 2021 19:18:51 +0800 Subject: iommu/io-pgtable-arm-v7s: Extend PA34 for MediaTek MediaTek extend the bit5 in lvl1 and lvl2 descriptor as PA34. Signed-off-by: Yong Wu Acked-by: Will Deacon Reviewed-by: Robin Murphy Reviewed-by: Tomasz Figa Link: https://lore.kernel.org/r/20210111111914.22211-11-yong.wu@mediatek.com Signed-off-by: Will Deacon --- drivers/iommu/io-pgtable-arm-v7s.c | 9 +++++++-- drivers/iommu/mtk_iommu.c | 2 +- include/linux/io-pgtable.h | 4 ++-- 3 files changed, 10 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c index 03f35065acff..b1b2ff069040 100644 --- a/drivers/iommu/io-pgtable-arm-v7s.c +++ b/drivers/iommu/io-pgtable-arm-v7s.c @@ -112,9 +112,10 @@ #define ARM_V7S_TEX_MASK 0x7 #define ARM_V7S_ATTR_TEX(val) (((val) & ARM_V7S_TEX_MASK) << ARM_V7S_TEX_SHIFT) -/* MediaTek extend the two bits for PA 32bit/33bit */ +/* MediaTek extend the bits below for PA 32bit/33bit/34bit */ #define ARM_V7S_ATTR_MTK_PA_BIT32 BIT(9) #define ARM_V7S_ATTR_MTK_PA_BIT33 BIT(4) +#define ARM_V7S_ATTR_MTK_PA_BIT34 BIT(5) /* *well, except for TEX on level 2 large pages, of course :( */ #define ARM_V7S_CONT_PAGE_TEX_SHIFT 6 @@ -194,6 +195,8 @@ static arm_v7s_iopte paddr_to_iopte(phys_addr_t paddr, int lvl, pte |= ARM_V7S_ATTR_MTK_PA_BIT32; if (paddr & BIT_ULL(33)) pte |= ARM_V7S_ATTR_MTK_PA_BIT33; + if (paddr & BIT_ULL(34)) + pte |= ARM_V7S_ATTR_MTK_PA_BIT34; return pte; } @@ -218,6 +221,8 @@ static phys_addr_t iopte_to_paddr(arm_v7s_iopte pte, int lvl, paddr |= BIT_ULL(32); if (pte & ARM_V7S_ATTR_MTK_PA_BIT33) paddr |= BIT_ULL(33); + if (pte & ARM_V7S_ATTR_MTK_PA_BIT34) + paddr |= BIT_ULL(34); return paddr; } @@ -748,7 +753,7 @@ static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg, if (cfg->ias > ARM_V7S_ADDR_BITS) return NULL; - if (cfg->oas > (arm_v7s_is_mtk_enabled(cfg) ? 34 : ARM_V7S_ADDR_BITS)) + if (cfg->oas > (arm_v7s_is_mtk_enabled(cfg) ? 35 : ARM_V7S_ADDR_BITS)) return NULL; if (cfg->quirks & ~(IO_PGTABLE_QUIRK_ARM_NS | diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index f594971dbeb2..485f3b6d1a21 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -300,7 +300,7 @@ static int mtk_iommu_domain_finalise(struct mtk_iommu_domain *dom) IO_PGTABLE_QUIRK_ARM_MTK_EXT, .pgsize_bitmap = mtk_iommu_ops.pgsize_bitmap, .ias = 32, - .oas = 34, + .oas = 35, .iommu_dev = data->dev, }; diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index 06753323a15e..d69234a4a65e 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -69,8 +69,8 @@ struct io_pgtable_cfg { * format, and/or requires some format-specific default value. * * IO_PGTABLE_QUIRK_ARM_MTK_EXT: (ARM v7s format) MediaTek IOMMUs extend - * to support up to 34 bits PA where the bit32 and bit33 are - * encoded in the bit9 and bit4 of the PTE respectively. + * to support up to 35 bits PA where the bit32, bit33 and bit34 are + * encoded in the bit9, bit4 and bit5 of the PTE respectively. * * IO_PGTABLE_QUIRK_NON_STRICT: Skip issuing synchronous leaf TLBIs * on unmap, for DMA domains using the flush queue mechanism for -- cgit v1.2.3 From 8d2c749e5252466d8fc1917101f137966c61fd1c Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Mon, 11 Jan 2021 19:19:11 +0800 Subject: iommu/mediatek: Support master use iova over 32bit After extending v7s, our pagetable already support iova reach 16GB(34bit). the master got the iova via dma_alloc_attrs may reach 34bits, but its HW register still is 32bit. then how to set the bit32/bit33 iova? this depend on a SMI larb setting(bank_sel). we separate whole 16GB iova to four banks: bank: 0: 0~4G; 1: 4~8G; 2: 8-12G; 3: 12-16G; The bank number is (iova >> 32). We will preassign which bank the larbs belong to. currently we don't have a interface for master to adjust its bank number. Each a bank is a iova_region which is a independent iommu-domain. the iova range for each iommu-domain can't cross 4G. Signed-off-by: Yong Wu Acked-by: Krzysztof Kozlowski #for memory part Reviewed-by: Tomasz Figa Link: https://lore.kernel.org/r/20210111111914.22211-31-yong.wu@mediatek.com Signed-off-by: Will Deacon --- drivers/iommu/mtk_iommu.c | 18 ++++++++++++------ drivers/memory/mtk-smi.c | 7 +++++++ include/soc/mediatek/smi.h | 1 + 3 files changed, 20 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index 764dc0b93477..7403a7cb90ea 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -345,21 +345,27 @@ static int mtk_iommu_get_domain_id(struct device *dev, return -EINVAL; } -static void mtk_iommu_config(struct mtk_iommu_data *data, - struct device *dev, bool enable) +static void mtk_iommu_config(struct mtk_iommu_data *data, struct device *dev, + bool enable, unsigned int domid) { struct mtk_smi_larb_iommu *larb_mmu; unsigned int larbid, portid; struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); + const struct mtk_iommu_iova_region *region; int i; for (i = 0; i < fwspec->num_ids; ++i) { larbid = MTK_M4U_TO_LARB(fwspec->ids[i]); portid = MTK_M4U_TO_PORT(fwspec->ids[i]); + larb_mmu = &data->larb_imu[larbid]; - dev_dbg(dev, "%s iommu port: %d\n", - enable ? "enable" : "disable", portid); + region = data->plat_data->iova_region + domid; + larb_mmu->bank[portid] = upper_32_bits(region->iova_base); + + dev_dbg(dev, "%s iommu for larb(%s) port %d dom %d bank %d.\n", + enable ? "enable" : "disable", dev_name(larb_mmu->dev), + portid, domid, larb_mmu->bank[portid]); if (enable) larb_mmu->mmu |= MTK_SMI_MMU_EN(portid); @@ -477,7 +483,7 @@ static int mtk_iommu_attach_device(struct iommu_domain *domain, pm_runtime_put(m4udev); } - mtk_iommu_config(data, dev, true); + mtk_iommu_config(data, dev, true, domid); return 0; } @@ -489,7 +495,7 @@ static void mtk_iommu_detach_device(struct iommu_domain *domain, if (!data) return; - mtk_iommu_config(data, dev, false); + mtk_iommu_config(data, dev, false, 0); } static int mtk_iommu_map(struct iommu_domain *domain, unsigned long iova, diff --git a/drivers/memory/mtk-smi.c b/drivers/memory/mtk-smi.c index 89f92fa2afa5..fae61c5fbd70 100644 --- a/drivers/memory/mtk-smi.c +++ b/drivers/memory/mtk-smi.c @@ -44,6 +44,10 @@ /* mt2712 */ #define SMI_LARB_NONSEC_CON(id) (0x380 + ((id) * 4)) #define F_MMU_EN BIT(0) +#define BANK_SEL(id) ({ \ + u32 _id = (id) & 0x3; \ + (_id << 8 | _id << 10 | _id << 12 | _id << 14); \ +}) /* SMI COMMON */ #define SMI_BUS_SEL 0x220 @@ -88,6 +92,7 @@ struct mtk_smi_larb { /* larb: local arbiter */ const struct mtk_smi_larb_gen *larb_gen; int larbid; u32 *mmu; + unsigned char *bank; }; static int mtk_smi_clk_enable(const struct mtk_smi *smi) @@ -154,6 +159,7 @@ mtk_smi_larb_bind(struct device *dev, struct device *master, void *data) if (dev == larb_mmu[i].dev) { larb->larbid = i; larb->mmu = &larb_mmu[i].mmu; + larb->bank = larb_mmu[i].bank; return 0; } } @@ -172,6 +178,7 @@ static void mtk_smi_larb_config_port_gen2_general(struct device *dev) for_each_set_bit(i, (unsigned long *)larb->mmu, 32) { reg = readl_relaxed(larb->base + SMI_LARB_NONSEC_CON(i)); reg |= F_MMU_EN; + reg |= BANK_SEL(larb->bank[i]); writel(reg, larb->base + SMI_LARB_NONSEC_CON(i)); } } diff --git a/include/soc/mediatek/smi.h b/include/soc/mediatek/smi.h index 9371bf572ab8..4cf445dbbdaa 100644 --- a/include/soc/mediatek/smi.h +++ b/include/soc/mediatek/smi.h @@ -16,6 +16,7 @@ struct mtk_smi_larb_iommu { struct device *dev; unsigned int mmu; + unsigned char bank[32]; }; /* -- cgit v1.2.3 From 1af7e7f8c12f521c111bd7cf0d138be7e15b51a5 Mon Sep 17 00:00:00 2001 From: Dave Wysochanski Date: Thu, 28 Jan 2021 09:55:01 -0500 Subject: NFS: Refactor nfs_readpage() and nfs_readpage_async() to use nfs_readdesc Both nfs_readpage() and nfs_readpages() use similar code. This patch should be no functional change, and refactors nfs_readpage_async() to use nfs_readdesc to enable future merging of nfs_readpage_async() and nfs_readpage_async_filler(). Signed-off-by: Dave Wysochanski Signed-off-by: Anna Schumaker --- fs/nfs/read.c | 62 ++++++++++++++++++++++++-------------------------- include/linux/nfs_fs.h | 3 +-- 2 files changed, 31 insertions(+), 34 deletions(-) (limited to 'include') diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 464077daf62f..8c05e56dab65 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -114,18 +114,23 @@ static void nfs_readpage_release(struct nfs_page *req, int error) nfs_release_request(req); } -int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode, +struct nfs_readdesc { + struct nfs_pageio_descriptor pgio; + struct nfs_open_context *ctx; +}; + +int nfs_readpage_async(void *data, struct inode *inode, struct page *page) { + struct nfs_readdesc *desc = data; struct nfs_page *new; unsigned int len; - struct nfs_pageio_descriptor pgio; struct nfs_pgio_mirror *pgm; len = nfs_page_length(page); if (len == 0) return nfs_return_empty_page(page); - new = nfs_create_request(ctx, page, 0, len); + new = nfs_create_request(desc->ctx, page, 0, len); if (IS_ERR(new)) { unlock_page(page); return PTR_ERR(new); @@ -133,21 +138,21 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode, if (len < PAGE_SIZE) zero_user_segment(page, len, PAGE_SIZE); - nfs_pageio_init_read(&pgio, inode, false, + nfs_pageio_init_read(&desc->pgio, inode, false, &nfs_async_read_completion_ops); - if (!nfs_pageio_add_request(&pgio, new)) { + if (!nfs_pageio_add_request(&desc->pgio, new)) { nfs_list_remove_request(new); - nfs_readpage_release(new, pgio.pg_error); + nfs_readpage_release(new, desc->pgio.pg_error); } - nfs_pageio_complete(&pgio); + nfs_pageio_complete(&desc->pgio); /* It doesn't make sense to do mirrored reads! */ - WARN_ON_ONCE(pgio.pg_mirror_count != 1); + WARN_ON_ONCE(desc->pgio.pg_mirror_count != 1); - pgm = &pgio.pg_mirrors[0]; + pgm = &desc->pgio.pg_mirrors[0]; NFS_I(inode)->read_io += pgm->pg_bytes_written; - return pgio.pg_error < 0 ? pgio.pg_error : 0; + return desc->pgio.pg_error < 0 ? desc->pgio.pg_error : 0; } static void nfs_page_group_set_uptodate(struct nfs_page *req) @@ -312,7 +317,7 @@ static void nfs_readpage_result(struct rpc_task *task, */ int nfs_readpage(struct file *file, struct page *page) { - struct nfs_open_context *ctx; + struct nfs_readdesc desc; struct inode *inode = page_file_mapping(page)->host; int ret; @@ -339,39 +344,34 @@ int nfs_readpage(struct file *file, struct page *page) if (file == NULL) { ret = -EBADF; - ctx = nfs_find_open_context(inode, NULL, FMODE_READ); - if (ctx == NULL) + desc.ctx = nfs_find_open_context(inode, NULL, FMODE_READ); + if (desc.ctx == NULL) goto out_unlock; } else - ctx = get_nfs_open_context(nfs_file_open_context(file)); + desc.ctx = get_nfs_open_context(nfs_file_open_context(file)); if (!IS_SYNC(inode)) { - ret = nfs_readpage_from_fscache(ctx, inode, page); + ret = nfs_readpage_from_fscache(desc.ctx, inode, page); if (ret == 0) goto out; } - xchg(&ctx->error, 0); - ret = nfs_readpage_async(ctx, inode, page); + xchg(&desc.ctx->error, 0); + ret = nfs_readpage_async(&desc, inode, page); if (!ret) { ret = wait_on_page_locked_killable(page); if (!PageUptodate(page) && !ret) - ret = xchg(&ctx->error, 0); + ret = xchg(&desc.ctx->error, 0); } nfs_add_stats(inode, NFSIOS_READPAGES, 1); out: - put_nfs_open_context(ctx); + put_nfs_open_context(desc.ctx); return ret; out_unlock: unlock_page(page); return ret; } -struct nfs_readdesc { - struct nfs_pageio_descriptor *pgio; - struct nfs_open_context *ctx; -}; - static int readpage_async_filler(void *data, struct page *page) { @@ -390,9 +390,9 @@ readpage_async_filler(void *data, struct page *page) if (len < PAGE_SIZE) zero_user_segment(page, len, PAGE_SIZE); - if (!nfs_pageio_add_request(desc->pgio, new)) { + if (!nfs_pageio_add_request(&desc->pgio, new)) { nfs_list_remove_request(new); - error = desc->pgio->pg_error; + error = desc->pgio.pg_error; nfs_readpage_release(new, error); goto out; } @@ -407,7 +407,6 @@ out: int nfs_readpages(struct file *file, struct address_space *mapping, struct list_head *pages, unsigned nr_pages) { - struct nfs_pageio_descriptor pgio; struct nfs_pgio_mirror *pgm; struct nfs_readdesc desc; struct inode *inode = mapping->host; @@ -440,17 +439,16 @@ int nfs_readpages(struct file *file, struct address_space *mapping, if (ret == 0) goto read_complete; /* all pages were read */ - desc.pgio = &pgio; - nfs_pageio_init_read(&pgio, inode, false, + nfs_pageio_init_read(&desc.pgio, inode, false, &nfs_async_read_completion_ops); ret = read_cache_pages(mapping, pages, readpage_async_filler, &desc); - nfs_pageio_complete(&pgio); + nfs_pageio_complete(&desc.pgio); /* It doesn't make sense to do mirrored reads! */ - WARN_ON_ONCE(pgio.pg_mirror_count != 1); + WARN_ON_ONCE(desc.pgio.pg_mirror_count != 1); - pgm = &pgio.pg_mirrors[0]; + pgm = &desc.pgio.pg_mirrors[0]; NFS_I(inode)->read_io += pgm->pg_bytes_written; npages = (pgm->pg_bytes_written + PAGE_SIZE - 1) >> PAGE_SHIFT; diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 681ed98e4ba8..cb0248a34518 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -570,8 +570,7 @@ nfs_have_writebacks(struct inode *inode) extern int nfs_readpage(struct file *, struct page *); extern int nfs_readpages(struct file *, struct address_space *, struct list_head *, unsigned); -extern int nfs_readpage_async(struct nfs_open_context *, struct inode *, - struct page *); +extern int nfs_readpage_async(void *, struct inode *, struct page *); /* * inline functions -- cgit v1.2.3 From 1e83b173b2663b7d357309584678cf24787f0713 Mon Sep 17 00:00:00 2001 From: Dave Wysochanski Date: Thu, 28 Jan 2021 09:55:03 -0500 Subject: NFS: Add nfs_pageio_complete_read() and remove nfs_readpage_async() Add nfs_pageio_complete_read() and call this from both nfs_readpage() and nfs_readpages(), since the submission and accounting is the same for both functions. Signed-off-by: Dave Wysochanski Signed-off-by: Anna Schumaker --- fs/nfs/fscache.c | 4 -- fs/nfs/read.c | 137 ++++++++++++++++++++++--------------------------- include/linux/nfs_fs.h | 1 - 3 files changed, 61 insertions(+), 81 deletions(-) (limited to 'include') diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index a60df88efc40..c4c021c6ebbd 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -390,10 +390,6 @@ static void nfs_readpage_from_fscache_complete(struct page *page, if (!error) { SetPageUptodate(page); unlock_page(page); - } else { - error = nfs_readpage_async(context, page->mapping->host, page); - if (error) - unlock_page(page); } } diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 0ed79e6bc486..d2b6dce1f99f 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -74,6 +74,24 @@ void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, } EXPORT_SYMBOL_GPL(nfs_pageio_init_read); +static void nfs_pageio_complete_read(struct nfs_pageio_descriptor *pgio, + struct inode *inode) +{ + struct nfs_pgio_mirror *pgm; + unsigned long npages; + + nfs_pageio_complete(pgio); + + /* It doesn't make sense to do mirrored reads! */ + WARN_ON_ONCE(pgio->pg_mirror_count != 1); + + pgm = &pgio->pg_mirrors[0]; + NFS_I(inode)->read_io += pgm->pg_bytes_written; + npages = (pgm->pg_bytes_written + PAGE_SIZE - 1) >> PAGE_SHIFT; + nfs_add_stats(inode, NFSIOS_READPAGES, npages); +} + + void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio) { struct nfs_pgio_mirror *mirror; @@ -119,36 +137,6 @@ struct nfs_readdesc { struct nfs_open_context *ctx; }; -static int readpage_async_filler(void *data, struct page *page); - -int nfs_readpage_async(void *data, struct inode *inode, - struct page *page) -{ - struct nfs_readdesc *desc = data; - struct nfs_pgio_mirror *pgm; - int error; - - nfs_pageio_init_read(&desc->pgio, inode, false, - &nfs_async_read_completion_ops); - - error = readpage_async_filler(desc, page); - if (error) - goto out; - - nfs_pageio_complete(&desc->pgio); - - /* It doesn't make sense to do mirrored reads! */ - WARN_ON_ONCE(desc->pgio.pg_mirror_count != 1); - - pgm = &desc->pgio.pg_mirrors[0]; - NFS_I(inode)->read_io += pgm->pg_bytes_written; - - return desc->pgio.pg_error < 0 ? desc->pgio.pg_error : 0; - -out: - return error; -} - static void nfs_page_group_set_uptodate(struct nfs_page *req) { if (nfs_page_group_sync_on_bit(req, PG_UPTODATE)) @@ -170,8 +158,7 @@ static void nfs_read_completion(struct nfs_pgio_header *hdr) if (test_bit(NFS_IOHDR_EOF, &hdr->flags)) { /* note: regions of the page not covered by a - * request are zeroed in nfs_readpage_async / - * readpage_async_filler */ + * request are zeroed in readpage_async_filler */ if (bytes > hdr->good_bytes) { /* nothing in this request was good, so zero * the full extent of the request */ @@ -303,6 +290,38 @@ static void nfs_readpage_result(struct rpc_task *task, nfs_readpage_retry(task, hdr); } +static int +readpage_async_filler(void *data, struct page *page) +{ + struct nfs_readdesc *desc = data; + struct nfs_page *new; + unsigned int len; + int error; + + len = nfs_page_length(page); + if (len == 0) + return nfs_return_empty_page(page); + + new = nfs_create_request(desc->ctx, page, 0, len); + if (IS_ERR(new)) + goto out_error; + + if (len < PAGE_SIZE) + zero_user_segment(page, len, PAGE_SIZE); + if (!nfs_pageio_add_request(&desc->pgio, new)) { + nfs_list_remove_request(new); + error = desc->pgio.pg_error; + nfs_readpage_release(new, error); + goto out; + } + return 0; +out_error: + error = PTR_ERR(new); + unlock_page(page); +out: + return error; +} + /* * Read a page over NFS. * We read the page synchronously in the following case: @@ -351,13 +370,20 @@ int nfs_readpage(struct file *file, struct page *page) } xchg(&desc.ctx->error, 0); - ret = nfs_readpage_async(&desc, inode, page); + nfs_pageio_init_read(&desc.pgio, inode, false, + &nfs_async_read_completion_ops); + + ret = readpage_async_filler(&desc, page); + + if (!ret) + nfs_pageio_complete_read(&desc.pgio, inode); + + ret = desc.pgio.pg_error < 0 ? desc.pgio.pg_error : 0; if (!ret) { ret = wait_on_page_locked_killable(page); if (!PageUptodate(page) && !ret) ret = xchg(&desc.ctx->error, 0); } - nfs_add_stats(inode, NFSIOS_READPAGES, 1); out: put_nfs_open_context(desc.ctx); return ret; @@ -366,45 +392,11 @@ out_unlock: return ret; } -static int -readpage_async_filler(void *data, struct page *page) -{ - struct nfs_readdesc *desc = (struct nfs_readdesc *)data; - struct nfs_page *new; - unsigned int len; - int error; - - len = nfs_page_length(page); - if (len == 0) - return nfs_return_empty_page(page); - - new = nfs_create_request(desc->ctx, page, 0, len); - if (IS_ERR(new)) - goto out_error; - - if (len < PAGE_SIZE) - zero_user_segment(page, len, PAGE_SIZE); - if (!nfs_pageio_add_request(&desc->pgio, new)) { - nfs_list_remove_request(new); - error = desc->pgio.pg_error; - nfs_readpage_release(new, error); - goto out; - } - return 0; -out_error: - error = PTR_ERR(new); - unlock_page(page); -out: - return error; -} - int nfs_readpages(struct file *file, struct address_space *mapping, struct list_head *pages, unsigned nr_pages) { - struct nfs_pgio_mirror *pgm; struct nfs_readdesc desc; struct inode *inode = mapping->host; - unsigned long npages; int ret; dprintk("NFS: nfs_readpages (%s/%Lu %d)\n", @@ -437,16 +429,9 @@ int nfs_readpages(struct file *file, struct address_space *mapping, &nfs_async_read_completion_ops); ret = read_cache_pages(mapping, pages, readpage_async_filler, &desc); - nfs_pageio_complete(&desc.pgio); - /* It doesn't make sense to do mirrored reads! */ - WARN_ON_ONCE(desc.pgio.pg_mirror_count != 1); + nfs_pageio_complete_read(&desc.pgio, inode); - pgm = &desc.pgio.pg_mirrors[0]; - NFS_I(inode)->read_io += pgm->pg_bytes_written; - npages = (pgm->pg_bytes_written + PAGE_SIZE - 1) >> - PAGE_SHIFT; - nfs_add_stats(inode, NFSIOS_READPAGES, npages); read_complete: put_nfs_open_context(desc.ctx); out: diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index cb0248a34518..3cfcf219e96b 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -570,7 +570,6 @@ nfs_have_writebacks(struct inode *inode) extern int nfs_readpage(struct file *, struct page *); extern int nfs_readpages(struct file *, struct address_space *, struct list_head *, unsigned); -extern int nfs_readpage_async(void *, struct inode *, struct page *); /* * inline functions -- cgit v1.2.3 From c98fe7c2a2038af2bc24f039ccdb5a65c22ba11a Mon Sep 17 00:00:00 2001 From: Steve Sistare Date: Fri, 29 Jan 2021 08:54:04 -0800 Subject: vfio: option to unmap all For the UNMAP_DMA ioctl, delete all mappings if VFIO_DMA_UNMAP_FLAG_ALL is set. Define the corresponding VFIO_UNMAP_ALL extension. Signed-off-by: Steve Sistare Reviewed-by: Cornelia Huck Signed-off-by: Alex Williamson --- include/uapi/linux/vfio.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index d1812777139f..78462599e5ed 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -46,6 +46,9 @@ */ #define VFIO_NOIOMMU_IOMMU 8 +/* Supports VFIO_DMA_UNMAP_FLAG_ALL */ +#define VFIO_UNMAP_ALL 9 + /* * The IOCTL interface is designed for extensibility by embedding the * structure length (argsz) and flags into structures passed between @@ -1102,6 +1105,7 @@ struct vfio_bitmap { * field. No guarantee is made to the user that arbitrary unmaps of iova * or size different from those used in the original mapping call will * succeed. + * * VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP should be set to get the dirty bitmap * before unmapping IO virtual addresses. When this flag is set, the user must * provide a struct vfio_bitmap in data[]. User must provide zero-allocated @@ -1111,11 +1115,15 @@ struct vfio_bitmap { * indicates that the page at that offset from iova is dirty. A Bitmap of the * pages in the range of unmapped size is returned in the user-provided * vfio_bitmap.data. + * + * If flags & VFIO_DMA_UNMAP_FLAG_ALL, unmap all addresses. iova and size + * must be 0. This cannot be combined with the get-dirty-bitmap flag. */ struct vfio_iommu_type1_dma_unmap { __u32 argsz; __u32 flags; #define VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP (1 << 0) +#define VFIO_DMA_UNMAP_FLAG_ALL (1 << 1) __u64 iova; /* IO virtual address */ __u64 size; /* Size of mapping (bytes) */ __u8 data[]; -- cgit v1.2.3 From 441e8106a238920f28e2e79cff462044551f60e2 Mon Sep 17 00:00:00 2001 From: Steve Sistare Date: Fri, 29 Jan 2021 08:54:07 -0800 Subject: vfio: interfaces to update vaddr Define interfaces that allow the underlying memory object of an iova range to be mapped to a new host virtual address in the host process: - VFIO_DMA_UNMAP_FLAG_VADDR for VFIO_IOMMU_UNMAP_DMA - VFIO_DMA_MAP_FLAG_VADDR flag for VFIO_IOMMU_MAP_DMA - VFIO_UPDATE_VADDR extension for VFIO_CHECK_EXTENSION Unmap vaddr invalidates the host virtual address in an iova range, and blocks vfio translation of host virtual addresses. DMA to already-mapped pages continues. Map vaddr updates the base VA and resumes translation. See comments in uapi/linux/vfio.h for more details. Signed-off-by: Steve Sistare Reviewed-by: Cornelia Huck Signed-off-by: Alex Williamson --- include/uapi/linux/vfio.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 78462599e5ed..8ce36c1d53ca 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -49,6 +49,9 @@ /* Supports VFIO_DMA_UNMAP_FLAG_ALL */ #define VFIO_UNMAP_ALL 9 +/* Supports the vaddr flag for DMA map and unmap */ +#define VFIO_UPDATE_VADDR 10 + /* * The IOCTL interface is designed for extensibility by embedding the * structure length (argsz) and flags into structures passed between @@ -1077,12 +1080,22 @@ struct vfio_iommu_type1_info_dma_avail { * * Map process virtual addresses to IO virtual addresses using the * provided struct vfio_dma_map. Caller sets argsz. READ &/ WRITE required. + * + * If flags & VFIO_DMA_MAP_FLAG_VADDR, update the base vaddr for iova, and + * unblock translation of host virtual addresses in the iova range. The vaddr + * must have previously been invalidated with VFIO_DMA_UNMAP_FLAG_VADDR. To + * maintain memory consistency within the user application, the updated vaddr + * must address the same memory object as originally mapped. Failure to do so + * will result in user memory corruption and/or device misbehavior. iova and + * size must match those in the original MAP_DMA call. Protection is not + * changed, and the READ & WRITE flags must be 0. */ struct vfio_iommu_type1_dma_map { __u32 argsz; __u32 flags; #define VFIO_DMA_MAP_FLAG_READ (1 << 0) /* readable from device */ #define VFIO_DMA_MAP_FLAG_WRITE (1 << 1) /* writable from device */ +#define VFIO_DMA_MAP_FLAG_VADDR (1 << 2) __u64 vaddr; /* Process virtual address */ __u64 iova; /* IO virtual address */ __u64 size; /* Size of mapping (bytes) */ @@ -1118,12 +1131,18 @@ struct vfio_bitmap { * * If flags & VFIO_DMA_UNMAP_FLAG_ALL, unmap all addresses. iova and size * must be 0. This cannot be combined with the get-dirty-bitmap flag. + * + * If flags & VFIO_DMA_UNMAP_FLAG_VADDR, do not unmap, but invalidate host + * virtual addresses in the iova range. Tasks that attempt to translate an + * iova's vaddr will block. DMA to already-mapped pages continues. This + * cannot be combined with the get-dirty-bitmap flag. */ struct vfio_iommu_type1_dma_unmap { __u32 argsz; __u32 flags; #define VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP (1 << 0) #define VFIO_DMA_UNMAP_FLAG_ALL (1 << 1) +#define VFIO_DMA_UNMAP_FLAG_VADDR (1 << 2) __u64 iova; /* IO virtual address */ __u64 size; /* Size of mapping (bytes) */ __u8 data[]; -- cgit v1.2.3 From ec5e32940cc9d2a8a321cb7d756fb6ae45702d03 Mon Sep 17 00:00:00 2001 From: Steve Sistare Date: Fri, 29 Jan 2021 08:54:10 -0800 Subject: vfio: iommu driver notify callback Define a vfio_iommu_driver_ops notify callback, for sending events to the driver. Drivers are not required to provide the callback, and may ignore any events. The handling of events is driver specific. Define the CONTAINER_CLOSE event, called when the container's file descriptor is closed. This event signifies that no further state changes will occur via container ioctl's. Signed-off-by: Steve Sistare Reviewed-by: Cornelia Huck Signed-off-by: Alex Williamson --- drivers/vfio/vfio.c | 5 +++++ include/linux/vfio.h | 7 +++++++ 2 files changed, 12 insertions(+) (limited to 'include') diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index 4ad8a35667a7..38779e6fd80c 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -1220,6 +1220,11 @@ static int vfio_fops_open(struct inode *inode, struct file *filep) static int vfio_fops_release(struct inode *inode, struct file *filep) { struct vfio_container *container = filep->private_data; + struct vfio_iommu_driver *driver = container->iommu_driver; + + if (driver && driver->ops->notify) + driver->ops->notify(container->iommu_data, + VFIO_IOMMU_CONTAINER_CLOSE); filep->private_data = NULL; diff --git a/include/linux/vfio.h b/include/linux/vfio.h index f45940b38a02..b7e18bde5aa8 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -57,6 +57,11 @@ extern struct vfio_device *vfio_device_get_from_dev(struct device *dev); extern void vfio_device_put(struct vfio_device *device); extern void *vfio_device_data(struct vfio_device *device); +/* events for the backend driver notify callback */ +enum vfio_iommu_notify_type { + VFIO_IOMMU_CONTAINER_CLOSE = 0, +}; + /** * struct vfio_iommu_driver_ops - VFIO IOMMU driver callbacks */ @@ -92,6 +97,8 @@ struct vfio_iommu_driver_ops { void *data, size_t count, bool write); struct iommu_domain *(*group_iommu_domain)(void *iommu_data, struct iommu_group *group); + void (*notify)(void *iommu_data, + enum vfio_iommu_notify_type event); }; extern int vfio_register_iommu_driver(const struct vfio_iommu_driver_ops *ops); -- cgit v1.2.3 From 9ff0c6db0605e9b88360048c8d0a6a9ff647eb71 Mon Sep 17 00:00:00 2001 From: Vadim Pasternak Date: Fri, 22 Jan 2021 21:24:57 +0200 Subject: platform/x86: mlxcpld: Update module license Update license to SPDX-License. Signed-off-by: Vadim Pasternak Acked-by: Peter Rosin Signed-off-by: Wolfram Sang --- include/linux/platform_data/x86/mlxcpld.h | 34 +++---------------------------- 1 file changed, 3 insertions(+), 31 deletions(-) (limited to 'include') diff --git a/include/linux/platform_data/x86/mlxcpld.h b/include/linux/platform_data/x86/mlxcpld.h index b08dcb183fca..e6c18bf017dd 100644 --- a/include/linux/platform_data/x86/mlxcpld.h +++ b/include/linux/platform_data/x86/mlxcpld.h @@ -1,36 +1,8 @@ +/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */ /* - * mlxcpld.h - Mellanox I2C multiplexer support in CPLD + * Mellanox I2C multiplexer support in CPLD * - * Copyright (c) 2016 Mellanox Technologies. All rights reserved. - * Copyright (c) 2016 Michael Shych - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions are met: - * - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * 3. Neither the names of the copyright holders nor the names of its - * contributors may be used to endorse or promote products derived from - * this software without specific prior written permission. - * - * Alternatively, this software may be distributed under the terms of the - * GNU General Public License ("GPL") version 2 as published by the Free - * Software Foundation. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" - * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE - * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE - * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE - * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR - * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF - * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS - * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN - * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) - * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE - * POSSIBILITY OF SUCH DAMAGE. + * Copyright (C) 2016-2020 Mellanox Technologies */ #ifndef _LINUX_I2C_MLXCPLD_H -- cgit v1.2.3 From 98d29c410475f30b627502d845794352e9be4046 Mon Sep 17 00:00:00 2001 From: Vadim Pasternak Date: Fri, 22 Jan 2021 21:24:58 +0200 Subject: i2c: mux: mlxcpld: Move header file out of x86 realm Move out header file from include/linux/platform_data/x86/ to include/linux/platform_data/, since it does not depend on x86 architecture. Signed-off-by: Vadim Pasternak Reviewed-by: Michael Shych Acked-by: Peter Rosin Signed-off-by: Wolfram Sang --- drivers/i2c/muxes/i2c-mux-mlxcpld.c | 2 +- include/linux/platform_data/mlxcpld.h | 24 ++++++++++++++++++++++++ include/linux/platform_data/x86/mlxcpld.h | 24 ------------------------ 3 files changed, 25 insertions(+), 25 deletions(-) create mode 100644 include/linux/platform_data/mlxcpld.h delete mode 100644 include/linux/platform_data/x86/mlxcpld.h (limited to 'include') diff --git a/drivers/i2c/muxes/i2c-mux-mlxcpld.c b/drivers/i2c/muxes/i2c-mux-mlxcpld.c index 53bce81cf5c9..3d894cfb19df 100644 --- a/drivers/i2c/muxes/i2c-mux-mlxcpld.c +++ b/drivers/i2c/muxes/i2c-mux-mlxcpld.c @@ -11,7 +11,7 @@ #include #include #include -#include +#include #include #include diff --git a/include/linux/platform_data/mlxcpld.h b/include/linux/platform_data/mlxcpld.h new file mode 100644 index 000000000000..e6c18bf017dd --- /dev/null +++ b/include/linux/platform_data/mlxcpld.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */ +/* + * Mellanox I2C multiplexer support in CPLD + * + * Copyright (C) 2016-2020 Mellanox Technologies + */ + +#ifndef _LINUX_I2C_MLXCPLD_H +#define _LINUX_I2C_MLXCPLD_H + +/* Platform data for the CPLD I2C multiplexers */ + +/* mlxcpld_mux_plat_data - per mux data, used with i2c_register_board_info + * @adap_ids - adapter array + * @num_adaps - number of adapters + * @sel_reg_addr - mux select register offset in CPLD space + */ +struct mlxcpld_mux_plat_data { + int *adap_ids; + int num_adaps; + int sel_reg_addr; +}; + +#endif /* _LINUX_I2C_MLXCPLD_H */ diff --git a/include/linux/platform_data/x86/mlxcpld.h b/include/linux/platform_data/x86/mlxcpld.h deleted file mode 100644 index e6c18bf017dd..000000000000 --- a/include/linux/platform_data/x86/mlxcpld.h +++ /dev/null @@ -1,24 +0,0 @@ -/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */ -/* - * Mellanox I2C multiplexer support in CPLD - * - * Copyright (C) 2016-2020 Mellanox Technologies - */ - -#ifndef _LINUX_I2C_MLXCPLD_H -#define _LINUX_I2C_MLXCPLD_H - -/* Platform data for the CPLD I2C multiplexers */ - -/* mlxcpld_mux_plat_data - per mux data, used with i2c_register_board_info - * @adap_ids - adapter array - * @num_adaps - number of adapters - * @sel_reg_addr - mux select register offset in CPLD space - */ -struct mlxcpld_mux_plat_data { - int *adap_ids; - int num_adaps; - int sel_reg_addr; -}; - -#endif /* _LINUX_I2C_MLXCPLD_H */ -- cgit v1.2.3 From dd9267034c0e364b49261c3e0070b863286d1242 Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Thu, 28 Jan 2021 10:10:48 +0100 Subject: i3c: Make remove callback return void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver core ignores the return value of struct bus_type::remove() because there is only little that can be done. To simplify the quest to make this function return void, let struct i3c_driver::remove() return void, too. This makes it obvious that returning an error code is a bad idea and future driver authors cannot get that wrong. Up to now there are no drivers with a remove callback, so there is no need to adapt drivers. Signed-off-by: Uwe Kleine-König Signed-off-by: Alexandre Belloni Link: https://lore.kernel.org/r/20210128091048.17006-2-u.kleine-koenig@pengutronix.de --- drivers/i3c/master.c | 10 +++------- include/linux/i3c/device.h | 2 +- 2 files changed, 4 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/drivers/i3c/master.c b/drivers/i3c/master.c index 57a4f699eb8d..f8e9b7305c13 100644 --- a/drivers/i3c/master.c +++ b/drivers/i3c/master.c @@ -326,17 +326,13 @@ static int i3c_device_remove(struct device *dev) { struct i3c_device *i3cdev = dev_to_i3cdev(dev); struct i3c_driver *driver = drv_to_i3cdrv(dev->driver); - int ret = 0; - if (driver->remove) { - ret = driver->remove(i3cdev); - if (ret) - return ret; - } + if (driver->remove) + driver->remove(i3cdev); i3c_device_free_ibi(i3cdev); - return ret; + return 0; } struct bus_type i3c_bus_type = { diff --git a/include/linux/i3c/device.h b/include/linux/i3c/device.h index de102e4418ab..8242e13e7b0b 100644 --- a/include/linux/i3c/device.h +++ b/include/linux/i3c/device.h @@ -176,7 +176,7 @@ struct i3c_device; struct i3c_driver { struct device_driver driver; int (*probe)(struct i3c_device *dev); - int (*remove)(struct i3c_device *dev); + void (*remove)(struct i3c_device *dev); const struct i3c_device_id *id_table; }; -- cgit v1.2.3 From 3fd269e74f2feec973f45ee11d822faeda4fe284 Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Tue, 26 Jan 2021 17:58:34 +0100 Subject: amba: Make the remove callback return void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit All amba drivers return 0 in their remove callback. Together with the driver core ignoring the return value anyhow, it doesn't make sense to return a value here. Change the remove prototype to return void, which makes it explicit that returning an error value doesn't work as expected. This simplifies changing the core remove callback to return void, too. Reviewed-by: Ulf Hansson Reviewed-by: Arnd Bergmann Acked-by: Alexandre Belloni Acked-by: Dmitry Torokhov Acked-by: Krzysztof Kozlowski # for drivers/memory Acked-by: Mark Brown Acked-by: Linus Walleij Acked-by: Suzuki K Poulose # for hwtracing/coresight Acked-By: Vinod Koul # for dmaengine Acked-by: Guenter Roeck # for watchdog Acked-by: Wolfram Sang # for I2C Acked-by: Takashi Iwai # for sound Acked-by: Vladimir Zapolskiy # for memory/pl172 Acked-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20210126165835.687514-5-u.kleine-koenig@pengutronix.de Signed-off-by: Uwe Kleine-König --- drivers/amba/bus.c | 5 ++--- drivers/char/hw_random/nomadik-rng.c | 3 +-- drivers/dma/pl330.c | 3 +-- drivers/gpu/drm/pl111/pl111_drv.c | 4 +--- drivers/hwtracing/coresight/coresight-catu.c | 3 +-- drivers/hwtracing/coresight/coresight-cpu-debug.c | 4 +--- drivers/hwtracing/coresight/coresight-cti-core.c | 4 +--- drivers/hwtracing/coresight/coresight-etb10.c | 4 +--- drivers/hwtracing/coresight/coresight-etm3x-core.c | 4 +--- drivers/hwtracing/coresight/coresight-etm4x-core.c | 4 +--- drivers/hwtracing/coresight/coresight-funnel.c | 4 ++-- drivers/hwtracing/coresight/coresight-replicator.c | 4 ++-- drivers/hwtracing/coresight/coresight-stm.c | 4 +--- drivers/hwtracing/coresight/coresight-tmc-core.c | 4 +--- drivers/hwtracing/coresight/coresight-tpiu.c | 4 +--- drivers/i2c/busses/i2c-nomadik.c | 4 +--- drivers/input/serio/ambakmi.c | 3 +-- drivers/memory/pl172.c | 4 +--- drivers/memory/pl353-smc.c | 4 +--- drivers/mmc/host/mmci.c | 4 +--- drivers/rtc/rtc-pl030.c | 4 +--- drivers/rtc/rtc-pl031.c | 4 +--- drivers/spi/spi-pl022.c | 5 ++--- drivers/tty/serial/amba-pl010.c | 4 +--- drivers/tty/serial/amba-pl011.c | 3 +-- drivers/vfio/platform/vfio_amba.c | 3 +-- drivers/video/fbdev/amba-clcd.c | 4 +--- drivers/watchdog/sp805_wdt.c | 4 +--- include/linux/amba/bus.h | 2 +- sound/arm/aaci.c | 4 +--- 30 files changed, 34 insertions(+), 80 deletions(-) (limited to 'include') diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c index 8c4a42df47c6..48b5d4b4e889 100644 --- a/drivers/amba/bus.c +++ b/drivers/amba/bus.c @@ -300,11 +300,10 @@ static int amba_remove(struct device *dev) { struct amba_device *pcdev = to_amba_device(dev); struct amba_driver *drv = to_amba_driver(dev->driver); - int ret = 0; pm_runtime_get_sync(dev); if (drv->remove) - ret = drv->remove(pcdev); + drv->remove(pcdev); pm_runtime_put_noidle(dev); /* Undo the runtime PM settings in amba_probe() */ @@ -315,7 +314,7 @@ static int amba_remove(struct device *dev) amba_put_disable_pclk(pcdev); dev_pm_domain_detach(dev, true); - return ret; + return 0; } static void amba_shutdown(struct device *dev) diff --git a/drivers/char/hw_random/nomadik-rng.c b/drivers/char/hw_random/nomadik-rng.c index b0ded41eb865..67947a19aa22 100644 --- a/drivers/char/hw_random/nomadik-rng.c +++ b/drivers/char/hw_random/nomadik-rng.c @@ -69,11 +69,10 @@ out_clk: return ret; } -static int nmk_rng_remove(struct amba_device *dev) +static void nmk_rng_remove(struct amba_device *dev) { amba_release_regions(dev); clk_disable(rng_clk); - return 0; } static const struct amba_id nmk_rng_ids[] = { diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c index bc0f66af0f11..fd8d2bc3be9f 100644 --- a/drivers/dma/pl330.c +++ b/drivers/dma/pl330.c @@ -3195,7 +3195,7 @@ probe_err2: return ret; } -static int pl330_remove(struct amba_device *adev) +static void pl330_remove(struct amba_device *adev) { struct pl330_dmac *pl330 = amba_get_drvdata(adev); struct dma_pl330_chan *pch, *_p; @@ -3235,7 +3235,6 @@ static int pl330_remove(struct amba_device *adev) if (pl330->rstc) reset_control_assert(pl330->rstc); - return 0; } static const struct amba_id pl330_ids[] = { diff --git a/drivers/gpu/drm/pl111/pl111_drv.c b/drivers/gpu/drm/pl111/pl111_drv.c index 40e6708fbbe2..1fb5eacefd2d 100644 --- a/drivers/gpu/drm/pl111/pl111_drv.c +++ b/drivers/gpu/drm/pl111/pl111_drv.c @@ -320,7 +320,7 @@ dev_put: return ret; } -static int pl111_amba_remove(struct amba_device *amba_dev) +static void pl111_amba_remove(struct amba_device *amba_dev) { struct device *dev = &amba_dev->dev; struct drm_device *drm = amba_get_drvdata(amba_dev); @@ -331,8 +331,6 @@ static int pl111_amba_remove(struct amba_device *amba_dev) drm_panel_bridge_remove(priv->bridge); drm_dev_put(drm); of_reserved_mem_device_release(dev); - - return 0; } /* diff --git a/drivers/hwtracing/coresight/coresight-catu.c b/drivers/hwtracing/coresight/coresight-catu.c index a61313f320bd..8e19e8cdcce5 100644 --- a/drivers/hwtracing/coresight/coresight-catu.c +++ b/drivers/hwtracing/coresight/coresight-catu.c @@ -567,12 +567,11 @@ out: return ret; } -static int catu_remove(struct amba_device *adev) +static void catu_remove(struct amba_device *adev) { struct catu_drvdata *drvdata = dev_get_drvdata(&adev->dev); coresight_unregister(drvdata->csdev); - return 0; } static struct amba_id catu_ids[] = { diff --git a/drivers/hwtracing/coresight/coresight-cpu-debug.c b/drivers/hwtracing/coresight/coresight-cpu-debug.c index e1d232411d8d..2dcf13de751f 100644 --- a/drivers/hwtracing/coresight/coresight-cpu-debug.c +++ b/drivers/hwtracing/coresight/coresight-cpu-debug.c @@ -627,7 +627,7 @@ err: return ret; } -static int debug_remove(struct amba_device *adev) +static void debug_remove(struct amba_device *adev) { struct device *dev = &adev->dev; struct debug_drvdata *drvdata = amba_get_drvdata(adev); @@ -642,8 +642,6 @@ static int debug_remove(struct amba_device *adev) if (!--debug_count) debug_func_exit(); - - return 0; } static const struct amba_cs_uci_id uci_id_debug[] = { diff --git a/drivers/hwtracing/coresight/coresight-cti-core.c b/drivers/hwtracing/coresight/coresight-cti-core.c index 61dbc1afd8da..30e48809ba00 100644 --- a/drivers/hwtracing/coresight/coresight-cti-core.c +++ b/drivers/hwtracing/coresight/coresight-cti-core.c @@ -836,7 +836,7 @@ static void cti_device_release(struct device *dev) if (drvdata->csdev_release) drvdata->csdev_release(dev); } -static int cti_remove(struct amba_device *adev) +static void cti_remove(struct amba_device *adev) { struct cti_drvdata *drvdata = dev_get_drvdata(&adev->dev); @@ -845,8 +845,6 @@ static int cti_remove(struct amba_device *adev) mutex_unlock(&ect_mutex); coresight_unregister(drvdata->csdev); - - return 0; } static int cti_probe(struct amba_device *adev, const struct amba_id *id) diff --git a/drivers/hwtracing/coresight/coresight-etb10.c b/drivers/hwtracing/coresight/coresight-etb10.c index 0cf6f0b947b6..51c801c05e5c 100644 --- a/drivers/hwtracing/coresight/coresight-etb10.c +++ b/drivers/hwtracing/coresight/coresight-etb10.c @@ -803,7 +803,7 @@ err_misc_register: return ret; } -static int etb_remove(struct amba_device *adev) +static void etb_remove(struct amba_device *adev) { struct etb_drvdata *drvdata = dev_get_drvdata(&adev->dev); @@ -814,8 +814,6 @@ static int etb_remove(struct amba_device *adev) */ misc_deregister(&drvdata->miscdev); coresight_unregister(drvdata->csdev); - - return 0; } #ifdef CONFIG_PM diff --git a/drivers/hwtracing/coresight/coresight-etm3x-core.c b/drivers/hwtracing/coresight/coresight-etm3x-core.c index 5bf5a5a4ce6d..683a69e88efd 100644 --- a/drivers/hwtracing/coresight/coresight-etm3x-core.c +++ b/drivers/hwtracing/coresight/coresight-etm3x-core.c @@ -909,7 +909,7 @@ static void clear_etmdrvdata(void *info) etmdrvdata[cpu] = NULL; } -static int etm_remove(struct amba_device *adev) +static void etm_remove(struct amba_device *adev) { struct etm_drvdata *drvdata = dev_get_drvdata(&adev->dev); @@ -932,8 +932,6 @@ static int etm_remove(struct amba_device *adev) cpus_read_unlock(); coresight_unregister(drvdata->csdev); - - return 0; } #ifdef CONFIG_PM diff --git a/drivers/hwtracing/coresight/coresight-etm4x-core.c b/drivers/hwtracing/coresight/coresight-etm4x-core.c index b20b6ff17cf6..82787cba537d 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x-core.c +++ b/drivers/hwtracing/coresight/coresight-etm4x-core.c @@ -1680,7 +1680,7 @@ static void clear_etmdrvdata(void *info) etmdrvdata[cpu] = NULL; } -static int etm4_remove(struct amba_device *adev) +static void etm4_remove(struct amba_device *adev) { struct etmv4_drvdata *drvdata = dev_get_drvdata(&adev->dev); @@ -1703,8 +1703,6 @@ static int etm4_remove(struct amba_device *adev) cpus_read_unlock(); coresight_unregister(drvdata->csdev); - - return 0; } static const struct amba_id etm4_ids[] = { diff --git a/drivers/hwtracing/coresight/coresight-funnel.c b/drivers/hwtracing/coresight/coresight-funnel.c index 071c723227db..01f8f9285168 100644 --- a/drivers/hwtracing/coresight/coresight-funnel.c +++ b/drivers/hwtracing/coresight/coresight-funnel.c @@ -370,9 +370,9 @@ static int dynamic_funnel_probe(struct amba_device *adev, return funnel_probe(&adev->dev, &adev->res); } -static int dynamic_funnel_remove(struct amba_device *adev) +static void dynamic_funnel_remove(struct amba_device *adev) { - return funnel_remove(&adev->dev); + funnel_remove(&adev->dev); } static const struct amba_id dynamic_funnel_ids[] = { diff --git a/drivers/hwtracing/coresight/coresight-replicator.c b/drivers/hwtracing/coresight/coresight-replicator.c index 7e2a2b7f503f..34fc2f6f3ea9 100644 --- a/drivers/hwtracing/coresight/coresight-replicator.c +++ b/drivers/hwtracing/coresight/coresight-replicator.c @@ -388,9 +388,9 @@ static int dynamic_replicator_probe(struct amba_device *adev, return replicator_probe(&adev->dev, &adev->res); } -static int dynamic_replicator_remove(struct amba_device *adev) +static void dynamic_replicator_remove(struct amba_device *adev) { - return replicator_remove(&adev->dev); + replicator_remove(&adev->dev); } static const struct amba_id dynamic_replicator_ids[] = { diff --git a/drivers/hwtracing/coresight/coresight-stm.c b/drivers/hwtracing/coresight/coresight-stm.c index 99791773f682..423df0d30d9c 100644 --- a/drivers/hwtracing/coresight/coresight-stm.c +++ b/drivers/hwtracing/coresight/coresight-stm.c @@ -951,15 +951,13 @@ stm_unregister: return ret; } -static int stm_remove(struct amba_device *adev) +static void stm_remove(struct amba_device *adev) { struct stm_drvdata *drvdata = dev_get_drvdata(&adev->dev); coresight_unregister(drvdata->csdev); stm_unregister_device(&drvdata->stm); - - return 0; } #ifdef CONFIG_PM diff --git a/drivers/hwtracing/coresight/coresight-tmc-core.c b/drivers/hwtracing/coresight/coresight-tmc-core.c index 8169dff5a9f6..e29b3914fc0f 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-core.c +++ b/drivers/hwtracing/coresight/coresight-tmc-core.c @@ -559,7 +559,7 @@ out: spin_unlock_irqrestore(&drvdata->spinlock, flags); } -static int tmc_remove(struct amba_device *adev) +static void tmc_remove(struct amba_device *adev) { struct tmc_drvdata *drvdata = dev_get_drvdata(&adev->dev); @@ -570,8 +570,6 @@ static int tmc_remove(struct amba_device *adev) */ misc_deregister(&drvdata->miscdev); coresight_unregister(drvdata->csdev); - - return 0; } static const struct amba_id tmc_ids[] = { diff --git a/drivers/hwtracing/coresight/coresight-tpiu.c b/drivers/hwtracing/coresight/coresight-tpiu.c index d5dfee9ee556..f77c4b0ea4aa 100644 --- a/drivers/hwtracing/coresight/coresight-tpiu.c +++ b/drivers/hwtracing/coresight/coresight-tpiu.c @@ -173,13 +173,11 @@ static int tpiu_probe(struct amba_device *adev, const struct amba_id *id) return PTR_ERR(drvdata->csdev); } -static int tpiu_remove(struct amba_device *adev) +static void tpiu_remove(struct amba_device *adev) { struct tpiu_drvdata *drvdata = dev_get_drvdata(&adev->dev); coresight_unregister(drvdata->csdev); - - return 0; } #ifdef CONFIG_PM diff --git a/drivers/i2c/busses/i2c-nomadik.c b/drivers/i2c/busses/i2c-nomadik.c index d4b1b0865f67..a3363b20f168 100644 --- a/drivers/i2c/busses/i2c-nomadik.c +++ b/drivers/i2c/busses/i2c-nomadik.c @@ -1055,7 +1055,7 @@ static int nmk_i2c_probe(struct amba_device *adev, const struct amba_id *id) return ret; } -static int nmk_i2c_remove(struct amba_device *adev) +static void nmk_i2c_remove(struct amba_device *adev) { struct resource *res = &adev->res; struct nmk_i2c_dev *dev = amba_get_drvdata(adev); @@ -1068,8 +1068,6 @@ static int nmk_i2c_remove(struct amba_device *adev) i2c_clr_bit(dev->virtbase + I2C_CR, I2C_CR_PE); clk_disable_unprepare(dev->clk); release_mem_region(res->start, resource_size(res)); - - return 0; } static struct i2c_vendor_data vendor_stn8815 = { diff --git a/drivers/input/serio/ambakmi.c b/drivers/input/serio/ambakmi.c index ecdeca147ed7..4408245b61d2 100644 --- a/drivers/input/serio/ambakmi.c +++ b/drivers/input/serio/ambakmi.c @@ -159,7 +159,7 @@ static int amba_kmi_probe(struct amba_device *dev, return ret; } -static int amba_kmi_remove(struct amba_device *dev) +static void amba_kmi_remove(struct amba_device *dev) { struct amba_kmi_port *kmi = amba_get_drvdata(dev); @@ -168,7 +168,6 @@ static int amba_kmi_remove(struct amba_device *dev) iounmap(kmi->base); kfree(kmi); amba_release_regions(dev); - return 0; } static int __maybe_unused amba_kmi_resume(struct device *dev) diff --git a/drivers/memory/pl172.c b/drivers/memory/pl172.c index 575fadbffa30..9eb8cc7de494 100644 --- a/drivers/memory/pl172.c +++ b/drivers/memory/pl172.c @@ -273,14 +273,12 @@ err_clk_enable: return ret; } -static int pl172_remove(struct amba_device *adev) +static void pl172_remove(struct amba_device *adev) { struct pl172_data *pl172 = amba_get_drvdata(adev); clk_disable_unprepare(pl172->clk); amba_release_regions(adev); - - return 0; } static const struct amba_id pl172_ids[] = { diff --git a/drivers/memory/pl353-smc.c b/drivers/memory/pl353-smc.c index 73bd3023202f..3b5b1045edd9 100644 --- a/drivers/memory/pl353-smc.c +++ b/drivers/memory/pl353-smc.c @@ -426,14 +426,12 @@ out_clk_dis_aper: return err; } -static int pl353_smc_remove(struct amba_device *adev) +static void pl353_smc_remove(struct amba_device *adev) { struct pl353_smc_data *pl353_smc = amba_get_drvdata(adev); clk_disable_unprepare(pl353_smc->memclk); clk_disable_unprepare(pl353_smc->aclk); - - return 0; } static const struct amba_id pl353_ids[] = { diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c index b5a41a7ce165..32f52d070bbd 100644 --- a/drivers/mmc/host/mmci.c +++ b/drivers/mmc/host/mmci.c @@ -2195,7 +2195,7 @@ static int mmci_probe(struct amba_device *dev, return ret; } -static int mmci_remove(struct amba_device *dev) +static void mmci_remove(struct amba_device *dev) { struct mmc_host *mmc = amba_get_drvdata(dev); @@ -2223,8 +2223,6 @@ static int mmci_remove(struct amba_device *dev) clk_disable_unprepare(host->clk); mmc_free_host(mmc); } - - return 0; } #ifdef CONFIG_PM diff --git a/drivers/rtc/rtc-pl030.c b/drivers/rtc/rtc-pl030.c index 5a880516f3e8..39038c0754ee 100644 --- a/drivers/rtc/rtc-pl030.c +++ b/drivers/rtc/rtc-pl030.c @@ -137,7 +137,7 @@ static int pl030_probe(struct amba_device *dev, const struct amba_id *id) return ret; } -static int pl030_remove(struct amba_device *dev) +static void pl030_remove(struct amba_device *dev) { struct pl030_rtc *rtc = amba_get_drvdata(dev); @@ -146,8 +146,6 @@ static int pl030_remove(struct amba_device *dev) free_irq(dev->irq[0], rtc); iounmap(rtc->base); amba_release_regions(dev); - - return 0; } static struct amba_id pl030_ids[] = { diff --git a/drivers/rtc/rtc-pl031.c b/drivers/rtc/rtc-pl031.c index 224bbf096262..620c8dc33647 100644 --- a/drivers/rtc/rtc-pl031.c +++ b/drivers/rtc/rtc-pl031.c @@ -280,7 +280,7 @@ static int pl031_set_alarm(struct device *dev, struct rtc_wkalrm *alarm) return 0; } -static int pl031_remove(struct amba_device *adev) +static void pl031_remove(struct amba_device *adev) { struct pl031_local *ldata = dev_get_drvdata(&adev->dev); @@ -289,8 +289,6 @@ static int pl031_remove(struct amba_device *adev) if (adev->irq[0]) free_irq(adev->irq[0], ldata); amba_release_regions(adev); - - return 0; } static int pl031_probe(struct amba_device *adev, const struct amba_id *id) diff --git a/drivers/spi/spi-pl022.c b/drivers/spi/spi-pl022.c index d1776fea287e..fd74ddfbb686 100644 --- a/drivers/spi/spi-pl022.c +++ b/drivers/spi/spi-pl022.c @@ -2314,13 +2314,13 @@ static int pl022_probe(struct amba_device *adev, const struct amba_id *id) return status; } -static int +static void pl022_remove(struct amba_device *adev) { struct pl022 *pl022 = amba_get_drvdata(adev); if (!pl022) - return 0; + return; /* * undo pm_runtime_put() in probe. I assume that we're not @@ -2335,7 +2335,6 @@ pl022_remove(struct amba_device *adev) clk_disable_unprepare(pl022->clk); amba_release_regions(adev); tasklet_disable(&pl022->pump_transfers); - return 0; } #ifdef CONFIG_PM_SLEEP diff --git a/drivers/tty/serial/amba-pl010.c b/drivers/tty/serial/amba-pl010.c index 3284f34e9dfe..3f96edfe569c 100644 --- a/drivers/tty/serial/amba-pl010.c +++ b/drivers/tty/serial/amba-pl010.c @@ -754,7 +754,7 @@ static int pl010_probe(struct amba_device *dev, const struct amba_id *id) return ret; } -static int pl010_remove(struct amba_device *dev) +static void pl010_remove(struct amba_device *dev) { struct uart_amba_port *uap = amba_get_drvdata(dev); int i; @@ -770,8 +770,6 @@ static int pl010_remove(struct amba_device *dev) if (!busy) uart_unregister_driver(&amba_reg); - - return 0; } #ifdef CONFIG_PM_SLEEP diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c index c255476cce28..4ead0c9048a8 100644 --- a/drivers/tty/serial/amba-pl011.c +++ b/drivers/tty/serial/amba-pl011.c @@ -2679,13 +2679,12 @@ static int pl011_probe(struct amba_device *dev, const struct amba_id *id) return pl011_register_port(uap); } -static int pl011_remove(struct amba_device *dev) +static void pl011_remove(struct amba_device *dev) { struct uart_amba_port *uap = amba_get_drvdata(dev); uart_remove_one_port(&amba_reg, &uap->port); pl011_unregister_port(uap); - return 0; } #ifdef CONFIG_PM_SLEEP diff --git a/drivers/vfio/platform/vfio_amba.c b/drivers/vfio/platform/vfio_amba.c index 7b3ebf1558e1..3626c2150101 100644 --- a/drivers/vfio/platform/vfio_amba.c +++ b/drivers/vfio/platform/vfio_amba.c @@ -71,14 +71,13 @@ static int vfio_amba_probe(struct amba_device *adev, const struct amba_id *id) return ret; } -static int vfio_amba_remove(struct amba_device *adev) +static void vfio_amba_remove(struct amba_device *adev) { struct vfio_platform_device *vdev = vfio_platform_remove_common(&adev->dev); kfree(vdev->name); kfree(vdev); - return 0; } static const struct amba_id pl330_ids[] = { diff --git a/drivers/video/fbdev/amba-clcd.c b/drivers/video/fbdev/amba-clcd.c index b7682de412d8..33595cc4778e 100644 --- a/drivers/video/fbdev/amba-clcd.c +++ b/drivers/video/fbdev/amba-clcd.c @@ -925,7 +925,7 @@ static int clcdfb_probe(struct amba_device *dev, const struct amba_id *id) return ret; } -static int clcdfb_remove(struct amba_device *dev) +static void clcdfb_remove(struct amba_device *dev) { struct clcd_fb *fb = amba_get_drvdata(dev); @@ -942,8 +942,6 @@ static int clcdfb_remove(struct amba_device *dev) kfree(fb); amba_release_regions(dev); - - return 0; } static const struct amba_id clcdfb_id_table[] = { diff --git a/drivers/watchdog/sp805_wdt.c b/drivers/watchdog/sp805_wdt.c index 958dc32a708f..58a00e1ab23b 100644 --- a/drivers/watchdog/sp805_wdt.c +++ b/drivers/watchdog/sp805_wdt.c @@ -305,14 +305,12 @@ err: return ret; } -static int sp805_wdt_remove(struct amba_device *adev) +static void sp805_wdt_remove(struct amba_device *adev) { struct sp805_wdt *wdt = amba_get_drvdata(adev); watchdog_unregister_device(&wdt->wdd); watchdog_set_drvdata(&wdt->wdd, NULL); - - return 0; } static int __maybe_unused sp805_wdt_suspend(struct device *dev) diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h index 0bbfd647f5c6..6cc93ab5b809 100644 --- a/include/linux/amba/bus.h +++ b/include/linux/amba/bus.h @@ -76,7 +76,7 @@ struct amba_device { struct amba_driver { struct device_driver drv; int (*probe)(struct amba_device *, const struct amba_id *); - int (*remove)(struct amba_device *); + void (*remove)(struct amba_device *); void (*shutdown)(struct amba_device *); const struct amba_id *id_table; }; diff --git a/sound/arm/aaci.c b/sound/arm/aaci.c index a0996c47e58f..b326a5f5f0d5 100644 --- a/sound/arm/aaci.c +++ b/sound/arm/aaci.c @@ -1055,7 +1055,7 @@ static int aaci_probe(struct amba_device *dev, return ret; } -static int aaci_remove(struct amba_device *dev) +static void aaci_remove(struct amba_device *dev) { struct snd_card *card = amba_get_drvdata(dev); @@ -1066,8 +1066,6 @@ static int aaci_remove(struct amba_device *dev) snd_card_free(card); amba_release_regions(dev); } - - return 0; } static struct amba_id aaci_ids[] = { -- cgit v1.2.3 From e1ed66ac300373a8d7e8d95fd86ca522f36602d9 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Sat, 30 Jan 2021 23:19:07 +0800 Subject: iommu/vt-d: Fix compile error [-Werror=implicit-function-declaration] trace_qi_submit() could be used when interrupt remapping is supported, but DMA remapping is not. In this case, the following compile error occurs. ../drivers/iommu/intel/dmar.c: In function 'qi_submit_sync': ../drivers/iommu/intel/dmar.c:1311:3: error: implicit declaration of function 'trace_qi_submit'; did you mean 'ftrace_nmi_exit'? [-Werror=implicit-function-declaration] trace_qi_submit(iommu, desc[i].qw0, desc[i].qw1, ^~~~~~~~~~~~~~~ ftrace_nmi_exit Fixes: f2dd871799ba5 ("iommu/vt-d: Add qi_submit trace event") Reported-by: kernel test robot Reported-by: Randy Dunlap Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20210130151907.3929148-1-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/Makefile | 2 +- drivers/iommu/intel/iommu.c | 1 - include/trace/events/intel_iommu.h | 2 -- 3 files changed, 1 insertion(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/iommu/intel/Makefile b/drivers/iommu/intel/Makefile index fb8e1e8c8029..ae570810a35e 100644 --- a/drivers/iommu/intel/Makefile +++ b/drivers/iommu/intel/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_DMAR_TABLE) += dmar.o obj-$(CONFIG_INTEL_IOMMU) += iommu.o pasid.o -obj-$(CONFIG_INTEL_IOMMU) += trace.o +obj-$(CONFIG_DMAR_TABLE) += trace.o obj-$(CONFIG_INTEL_IOMMU_DEBUGFS) += debugfs.o obj-$(CONFIG_INTEL_IOMMU_SVM) += svm.o obj-$(CONFIG_IRQ_REMAP) += irq_remapping.o diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index be85af612bc1..87d0ef79ba6a 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -44,7 +44,6 @@ #include #include #include -#include #include "../irq_remapping.h" #include "pasid.h" diff --git a/include/trace/events/intel_iommu.h b/include/trace/events/intel_iommu.h index aad2ff0c1e2e..e801f4910522 100644 --- a/include/trace/events/intel_iommu.h +++ b/include/trace/events/intel_iommu.h @@ -6,7 +6,6 @@ * * Author: Lu Baolu */ -#ifdef CONFIG_INTEL_IOMMU #undef TRACE_SYSTEM #define TRACE_SYSTEM intel_iommu @@ -176,4 +175,3 @@ TRACE_EVENT(qi_submit, /* This part must be outside protection */ #include -#endif /* CONFIG_INTEL_IOMMU */ -- cgit v1.2.3 From bd0c9706430240e3b7e9323361bb25066540d2a8 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Mon, 21 Dec 2020 08:27:15 -0800 Subject: tracing: Add printf attribute to log function Attributing the function allows the compiler to more thoroughly check the use of the function with -Wformat and similar flags. Link: https://lkml.kernel.org/r/20201221162715.3757291-1-trix@redhat.com Signed-off-by: Tom Rix Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/trace.h b/include/linux/trace.h index 886a4ffd9d45..be1e130ed87c 100644 --- a/include/linux/trace.h +++ b/include/linux/trace.h @@ -34,8 +34,9 @@ int unregister_ftrace_export(struct trace_export *export); struct trace_array; void trace_printk_init_buffers(void); +__printf(3, 4) int trace_array_printk(struct trace_array *tr, unsigned long ip, - const char *fmt, ...); + const char *fmt, ...); int trace_array_init_printk(struct trace_array *tr); void trace_array_put(struct trace_array *tr); struct trace_array *trace_array_get_by_name(const char *name); -- cgit v1.2.3 From 36590c50b2d0729952511129916beeea30d31d81 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Mon, 25 Jan 2021 20:45:08 +0100 Subject: tracing: Merge irqflags + preempt counter. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The state of the interrupts (irqflags) and the preemption counter are both passed down to tracing_generic_entry_update(). Only one bit of irqflags is actually required: The on/off state. The complete 32bit of the preemption counter isn't needed. Just whether of the upper bits (softirq, hardirq and NMI) are set and the preemption depth is needed. The irqflags and the preemption counter could be evaluated early and the information stored in an integer `trace_ctx'. tracing_generic_entry_update() would use the upper bits as the TRACE_FLAG_* and the lower 8bit as the disabled-preemption depth (considering that one must be substracted from the counter in one special cases). The actual preemption value is not used except for the tracing record. The `irqflags' variable is mostly used only for the tracing record. An exception here is for instance wakeup_tracer_call() or probe_wakeup_sched_switch() which explicilty disable interrupts and use that `irqflags' to save (and restore) the IRQ state and to record the state. Struct trace_event_buffer has also the `pc' and flags' members which can be replaced with `trace_ctx' since their actual value is not used outside of trace recording. This will reduce tracing_generic_entry_update() to simply assign values to struct trace_entry. The evaluation of the TRACE_FLAG_* bits is moved to _tracing_gen_ctx_flags() which replaces preempt_count() and local_save_flags() invocations. As an example, ftrace_syscall_enter() may invoke: - trace_buffer_lock_reserve() -> … -> tracing_generic_entry_update() - event_trigger_unlock_commit() -> ftrace_trace_stack() -> … -> tracing_generic_entry_update() -> ftrace_trace_userstack() -> … -> tracing_generic_entry_update() In this case the TRACE_FLAG_* bits were evaluated three times. By using the `trace_ctx' they are evaluated once and assigned three times. A build with all tracers enabled on x86-64 with and without the patch: text data bss dec hex filename 21970669 17084168 7639260 46694097 2c87ed1 vmlinux.old 21970293 17084168 7639260 46693721 2c87d59 vmlinux.new text shrank by 379 bytes, data remained constant. Link: https://lkml.kernel.org/r/20210125194511.3924915-2-bigeasy@linutronix.de Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_events.h | 25 +++-- kernel/trace/blktrace.c | 17 +-- kernel/trace/trace.c | 208 +++++++++++++++++++---------------- kernel/trace/trace.h | 38 +++---- kernel/trace/trace_branch.c | 6 +- kernel/trace/trace_event_perf.c | 5 +- kernel/trace/trace_events.c | 18 +-- kernel/trace/trace_events_inject.c | 6 +- kernel/trace/trace_functions.c | 28 ++--- kernel/trace/trace_functions_graph.c | 32 +++--- kernel/trace/trace_hwlat.c | 7 +- kernel/trace/trace_irqsoff.c | 86 ++++++--------- kernel/trace/trace_kprobe.c | 10 +- kernel/trace/trace_mmiotrace.c | 14 ++- kernel/trace/trace_sched_wakeup.c | 71 ++++++------ kernel/trace/trace_syscalls.c | 20 ++-- kernel/trace/trace_uprobe.c | 4 +- 17 files changed, 287 insertions(+), 308 deletions(-) (limited to 'include') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index d321fe5ad1a1..091250b0895a 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -148,17 +148,29 @@ enum print_line_t { enum print_line_t trace_handle_return(struct trace_seq *s); -void tracing_generic_entry_update(struct trace_entry *entry, - unsigned short type, - unsigned long flags, - int pc); +static inline void tracing_generic_entry_update(struct trace_entry *entry, + unsigned short type, + unsigned int trace_ctx) +{ + struct task_struct *tsk = current; + + entry->preempt_count = trace_ctx & 0xff; + entry->pid = (tsk) ? tsk->pid : 0; + entry->type = type; + entry->flags = trace_ctx >> 16; +} + +unsigned int tracing_gen_ctx_flags(unsigned long irqflags); +unsigned int tracing_gen_ctx(void); +unsigned int tracing_gen_ctx_dec(void); + struct trace_event_file; struct ring_buffer_event * trace_event_buffer_lock_reserve(struct trace_buffer **current_buffer, struct trace_event_file *trace_file, int type, unsigned long len, - unsigned long flags, int pc); + unsigned int trace_ctx); #define TRACE_RECORD_CMDLINE BIT(0) #define TRACE_RECORD_TGID BIT(1) @@ -232,8 +244,7 @@ struct trace_event_buffer { struct ring_buffer_event *event; struct trace_event_file *trace_file; void *entry; - unsigned long flags; - int pc; + unsigned int trace_ctx; struct pt_regs *regs; }; diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index fb0fe4c66b84..c54eae2ab208 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -72,17 +72,17 @@ static void trace_note(struct blk_trace *bt, pid_t pid, int action, struct blk_io_trace *t; struct ring_buffer_event *event = NULL; struct trace_buffer *buffer = NULL; - int pc = 0; + unsigned int trace_ctx = 0; int cpu = smp_processor_id(); bool blk_tracer = blk_tracer_enabled; ssize_t cgid_len = cgid ? sizeof(cgid) : 0; if (blk_tracer) { buffer = blk_tr->array_buffer.buffer; - pc = preempt_count(); + trace_ctx = tracing_gen_ctx_flags(0); event = trace_buffer_lock_reserve(buffer, TRACE_BLK, sizeof(*t) + len + cgid_len, - 0, pc); + trace_ctx); if (!event) return; t = ring_buffer_event_data(event); @@ -107,7 +107,7 @@ record_it: memcpy((void *) t + sizeof(*t) + cgid_len, data, len); if (blk_tracer) - trace_buffer_unlock_commit(blk_tr, buffer, event, 0, pc); + trace_buffer_unlock_commit(blk_tr, buffer, event, trace_ctx); } } @@ -222,8 +222,9 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, struct blk_io_trace *t; unsigned long flags = 0; unsigned long *sequence; + unsigned int trace_ctx = 0; pid_t pid; - int cpu, pc = 0; + int cpu; bool blk_tracer = blk_tracer_enabled; ssize_t cgid_len = cgid ? sizeof(cgid) : 0; @@ -252,10 +253,10 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, tracing_record_cmdline(current); buffer = blk_tr->array_buffer.buffer; - pc = preempt_count(); + trace_ctx = tracing_gen_ctx_flags(0); event = trace_buffer_lock_reserve(buffer, TRACE_BLK, sizeof(*t) + pdu_len + cgid_len, - 0, pc); + trace_ctx); if (!event) return; t = ring_buffer_event_data(event); @@ -301,7 +302,7 @@ record_it: memcpy((void *)t + sizeof(*t) + cgid_len, pdu_data, pdu_len); if (blk_tracer) { - trace_buffer_unlock_commit(blk_tr, buffer, event, 0, pc); + trace_buffer_unlock_commit(blk_tr, buffer, event, trace_ctx); return; } } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 9e4f4043a3df..0b3cce6ecf52 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -176,7 +176,7 @@ static union trace_eval_map_item *trace_eval_maps; int tracing_set_tracer(struct trace_array *tr, const char *buf); static void ftrace_trace_userstack(struct trace_array *tr, struct trace_buffer *buffer, - unsigned long flags, int pc); + unsigned int trace_ctx); #define MAX_TRACER_SIZE 100 static char bootup_tracer_buf[MAX_TRACER_SIZE] __initdata; @@ -906,23 +906,23 @@ static inline void trace_access_lock_init(void) #ifdef CONFIG_STACKTRACE static void __ftrace_trace_stack(struct trace_buffer *buffer, - unsigned long flags, - int skip, int pc, struct pt_regs *regs); + unsigned int trace_ctx, + int skip, struct pt_regs *regs); static inline void ftrace_trace_stack(struct trace_array *tr, struct trace_buffer *buffer, - unsigned long flags, - int skip, int pc, struct pt_regs *regs); + unsigned int trace_ctx, + int skip, struct pt_regs *regs); #else static inline void __ftrace_trace_stack(struct trace_buffer *buffer, - unsigned long flags, - int skip, int pc, struct pt_regs *regs) + unsigned int trace_ctx, + int skip, struct pt_regs *regs) { } static inline void ftrace_trace_stack(struct trace_array *tr, struct trace_buffer *buffer, - unsigned long flags, - int skip, int pc, struct pt_regs *regs) + unsigned long trace_ctx, + int skip, struct pt_regs *regs) { } @@ -930,24 +930,24 @@ static inline void ftrace_trace_stack(struct trace_array *tr, static __always_inline void trace_event_setup(struct ring_buffer_event *event, - int type, unsigned long flags, int pc) + int type, unsigned int trace_ctx) { struct trace_entry *ent = ring_buffer_event_data(event); - tracing_generic_entry_update(ent, type, flags, pc); + tracing_generic_entry_update(ent, type, trace_ctx); } static __always_inline struct ring_buffer_event * __trace_buffer_lock_reserve(struct trace_buffer *buffer, int type, unsigned long len, - unsigned long flags, int pc) + unsigned int trace_ctx) { struct ring_buffer_event *event; event = ring_buffer_lock_reserve(buffer, len); if (event != NULL) - trace_event_setup(event, type, flags, pc); + trace_event_setup(event, type, trace_ctx); return event; } @@ -1008,25 +1008,22 @@ int __trace_puts(unsigned long ip, const char *str, int size) struct ring_buffer_event *event; struct trace_buffer *buffer; struct print_entry *entry; - unsigned long irq_flags; + unsigned int trace_ctx; int alloc; - int pc; if (!(global_trace.trace_flags & TRACE_ITER_PRINTK)) return 0; - pc = preempt_count(); - if (unlikely(tracing_selftest_running || tracing_disabled)) return 0; alloc = sizeof(*entry) + size + 2; /* possible \n added */ - local_save_flags(irq_flags); + trace_ctx = tracing_gen_ctx(); buffer = global_trace.array_buffer.buffer; ring_buffer_nest_start(buffer); - event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, alloc, - irq_flags, pc); + event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, alloc, + trace_ctx); if (!event) { size = 0; goto out; @@ -1045,7 +1042,7 @@ int __trace_puts(unsigned long ip, const char *str, int size) entry->buf[size] = '\0'; __buffer_unlock_commit(buffer, event); - ftrace_trace_stack(&global_trace, buffer, irq_flags, 4, pc, NULL); + ftrace_trace_stack(&global_trace, buffer, trace_ctx, 4, NULL); out: ring_buffer_nest_end(buffer); return size; @@ -1062,25 +1059,22 @@ int __trace_bputs(unsigned long ip, const char *str) struct ring_buffer_event *event; struct trace_buffer *buffer; struct bputs_entry *entry; - unsigned long irq_flags; + unsigned int trace_ctx; int size = sizeof(struct bputs_entry); int ret = 0; - int pc; if (!(global_trace.trace_flags & TRACE_ITER_PRINTK)) return 0; - pc = preempt_count(); - if (unlikely(tracing_selftest_running || tracing_disabled)) return 0; - local_save_flags(irq_flags); + trace_ctx = tracing_gen_ctx(); buffer = global_trace.array_buffer.buffer; ring_buffer_nest_start(buffer); event = __trace_buffer_lock_reserve(buffer, TRACE_BPUTS, size, - irq_flags, pc); + trace_ctx); if (!event) goto out; @@ -1089,7 +1083,7 @@ int __trace_bputs(unsigned long ip, const char *str) entry->str = str; __buffer_unlock_commit(buffer, event); - ftrace_trace_stack(&global_trace, buffer, irq_flags, 4, pc, NULL); + ftrace_trace_stack(&global_trace, buffer, trace_ctx, 4, NULL); ret = 1; out: @@ -2585,36 +2579,69 @@ enum print_line_t trace_handle_return(struct trace_seq *s) } EXPORT_SYMBOL_GPL(trace_handle_return); -void -tracing_generic_entry_update(struct trace_entry *entry, unsigned short type, - unsigned long flags, int pc) +unsigned int tracing_gen_ctx_flags(unsigned long irqflags) { - struct task_struct *tsk = current; + unsigned int trace_flags = 0; + unsigned int pc; + + pc = preempt_count(); - entry->preempt_count = pc & 0xff; - entry->pid = (tsk) ? tsk->pid : 0; - entry->type = type; - entry->flags = #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT - (irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) | + if (irqs_disabled_flags(irqflags)) + trace_flags |= TRACE_FLAG_IRQS_OFF; #else - TRACE_FLAG_IRQS_NOSUPPORT | + trace_flags |= TRACE_FLAG_IRQS_NOSUPPORT; #endif - ((pc & NMI_MASK ) ? TRACE_FLAG_NMI : 0) | - ((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) | - ((pc & SOFTIRQ_OFFSET) ? TRACE_FLAG_SOFTIRQ : 0) | - (tif_need_resched() ? TRACE_FLAG_NEED_RESCHED : 0) | - (test_preempt_need_resched() ? TRACE_FLAG_PREEMPT_RESCHED : 0); + + if (pc & NMI_MASK) + trace_flags |= TRACE_FLAG_NMI; + if (pc & HARDIRQ_MASK) + trace_flags |= TRACE_FLAG_HARDIRQ; + + if (pc & SOFTIRQ_OFFSET) + trace_flags |= TRACE_FLAG_SOFTIRQ; + + if (tif_need_resched()) + trace_flags |= TRACE_FLAG_NEED_RESCHED; + if (test_preempt_need_resched()) + trace_flags |= TRACE_FLAG_PREEMPT_RESCHED; + return (trace_flags << 16) | (pc & 0xff); +} + +unsigned int tracing_gen_ctx(void) +{ + unsigned long irqflags; + +#ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT + local_save_flags(irqflags); +#else + irqflags = 0; +#endif + return tracing_gen_ctx_flags(irqflags); +} + +unsigned int tracing_gen_ctx_dec(void) +{ + unsigned int trace_ctx; + + trace_ctx = tracing_gen_ctx(); + + /* + * Subtract one from the preeption counter if preemption is enabled, + * see trace_event_buffer_reserve()for details. + */ + if (IS_ENABLED(CONFIG_PREEMPTION)) + trace_ctx--; + return trace_ctx; } -EXPORT_SYMBOL_GPL(tracing_generic_entry_update); struct ring_buffer_event * trace_buffer_lock_reserve(struct trace_buffer *buffer, int type, unsigned long len, - unsigned long flags, int pc) + unsigned int trace_ctx) { - return __trace_buffer_lock_reserve(buffer, type, len, flags, pc); + return __trace_buffer_lock_reserve(buffer, type, len, trace_ctx); } DEFINE_PER_CPU(struct ring_buffer_event *, trace_buffered_event); @@ -2734,7 +2761,7 @@ struct ring_buffer_event * trace_event_buffer_lock_reserve(struct trace_buffer **current_rb, struct trace_event_file *trace_file, int type, unsigned long len, - unsigned long flags, int pc) + unsigned int trace_ctx) { struct ring_buffer_event *entry; int val; @@ -2747,15 +2774,15 @@ trace_event_buffer_lock_reserve(struct trace_buffer **current_rb, /* Try to use the per cpu buffer first */ val = this_cpu_inc_return(trace_buffered_event_cnt); if (val == 1) { - trace_event_setup(entry, type, flags, pc); + trace_event_setup(entry, type, trace_ctx); entry->array[0] = len; return entry; } this_cpu_dec(trace_buffered_event_cnt); } - entry = __trace_buffer_lock_reserve(*current_rb, - type, len, flags, pc); + entry = __trace_buffer_lock_reserve(*current_rb, type, len, + trace_ctx); /* * If tracing is off, but we have triggers enabled * we still need to look at the event data. Use the temp_buffer @@ -2764,8 +2791,8 @@ trace_event_buffer_lock_reserve(struct trace_buffer **current_rb, */ if (!entry && trace_file->flags & EVENT_FILE_FL_TRIGGER_COND) { *current_rb = temp_buffer; - entry = __trace_buffer_lock_reserve(*current_rb, - type, len, flags, pc); + entry = __trace_buffer_lock_reserve(*current_rb, type, len, + trace_ctx); } return entry; } @@ -2851,7 +2878,7 @@ void trace_event_buffer_commit(struct trace_event_buffer *fbuffer) ftrace_exports(fbuffer->event, TRACE_EXPORT_EVENT); event_trigger_unlock_commit_regs(fbuffer->trace_file, fbuffer->buffer, fbuffer->event, fbuffer->entry, - fbuffer->flags, fbuffer->pc, fbuffer->regs); + fbuffer->trace_ctx, fbuffer->regs); } EXPORT_SYMBOL_GPL(trace_event_buffer_commit); @@ -2867,7 +2894,7 @@ EXPORT_SYMBOL_GPL(trace_event_buffer_commit); void trace_buffer_unlock_commit_regs(struct trace_array *tr, struct trace_buffer *buffer, struct ring_buffer_event *event, - unsigned long flags, int pc, + unsigned int trace_ctx, struct pt_regs *regs) { __buffer_unlock_commit(buffer, event); @@ -2878,8 +2905,8 @@ void trace_buffer_unlock_commit_regs(struct trace_array *tr, * and mmiotrace, but that's ok if they lose a function or * two. They are not that meaningful. */ - ftrace_trace_stack(tr, buffer, flags, regs ? 0 : STACK_SKIP, pc, regs); - ftrace_trace_userstack(tr, buffer, flags, pc); + ftrace_trace_stack(tr, buffer, trace_ctx, regs ? 0 : STACK_SKIP, regs); + ftrace_trace_userstack(tr, buffer, trace_ctx); } /* @@ -2893,9 +2920,8 @@ trace_buffer_unlock_commit_nostack(struct trace_buffer *buffer, } void -trace_function(struct trace_array *tr, - unsigned long ip, unsigned long parent_ip, unsigned long flags, - int pc) +trace_function(struct trace_array *tr, unsigned long ip, unsigned long + parent_ip, unsigned int trace_ctx) { struct trace_event_call *call = &event_function; struct trace_buffer *buffer = tr->array_buffer.buffer; @@ -2903,7 +2929,7 @@ trace_function(struct trace_array *tr, struct ftrace_entry *entry; event = __trace_buffer_lock_reserve(buffer, TRACE_FN, sizeof(*entry), - flags, pc); + trace_ctx); if (!event) return; entry = ring_buffer_event_data(event); @@ -2937,8 +2963,8 @@ static DEFINE_PER_CPU(struct ftrace_stacks, ftrace_stacks); static DEFINE_PER_CPU(int, ftrace_stack_reserve); static void __ftrace_trace_stack(struct trace_buffer *buffer, - unsigned long flags, - int skip, int pc, struct pt_regs *regs) + unsigned int trace_ctx, + int skip, struct pt_regs *regs) { struct trace_event_call *call = &event_kernel_stack; struct ring_buffer_event *event; @@ -2985,7 +3011,7 @@ static void __ftrace_trace_stack(struct trace_buffer *buffer, size = nr_entries * sizeof(unsigned long); event = __trace_buffer_lock_reserve(buffer, TRACE_STACK, - sizeof(*entry) + size, flags, pc); + sizeof(*entry) + size, trace_ctx); if (!event) goto out; entry = ring_buffer_event_data(event); @@ -3006,22 +3032,22 @@ static void __ftrace_trace_stack(struct trace_buffer *buffer, static inline void ftrace_trace_stack(struct trace_array *tr, struct trace_buffer *buffer, - unsigned long flags, - int skip, int pc, struct pt_regs *regs) + unsigned int trace_ctx, + int skip, struct pt_regs *regs) { if (!(tr->trace_flags & TRACE_ITER_STACKTRACE)) return; - __ftrace_trace_stack(buffer, flags, skip, pc, regs); + __ftrace_trace_stack(buffer, trace_ctx, skip, regs); } -void __trace_stack(struct trace_array *tr, unsigned long flags, int skip, - int pc) +void __trace_stack(struct trace_array *tr, unsigned int trace_ctx, + int skip) { struct trace_buffer *buffer = tr->array_buffer.buffer; if (rcu_is_watching()) { - __ftrace_trace_stack(buffer, flags, skip, pc, NULL); + __ftrace_trace_stack(buffer, trace_ctx, skip, NULL); return; } @@ -3035,7 +3061,7 @@ void __trace_stack(struct trace_array *tr, unsigned long flags, int skip, return; rcu_irq_enter_irqson(); - __ftrace_trace_stack(buffer, flags, skip, pc, NULL); + __ftrace_trace_stack(buffer, trace_ctx, skip, NULL); rcu_irq_exit_irqson(); } @@ -3045,19 +3071,15 @@ void __trace_stack(struct trace_array *tr, unsigned long flags, int skip, */ void trace_dump_stack(int skip) { - unsigned long flags; - if (tracing_disabled || tracing_selftest_running) return; - local_save_flags(flags); - #ifndef CONFIG_UNWINDER_ORC /* Skip 1 to skip this function. */ skip++; #endif __ftrace_trace_stack(global_trace.array_buffer.buffer, - flags, skip, preempt_count(), NULL); + tracing_gen_ctx(), skip, NULL); } EXPORT_SYMBOL_GPL(trace_dump_stack); @@ -3066,7 +3088,7 @@ static DEFINE_PER_CPU(int, user_stack_count); static void ftrace_trace_userstack(struct trace_array *tr, - struct trace_buffer *buffer, unsigned long flags, int pc) + struct trace_buffer *buffer, unsigned int trace_ctx) { struct trace_event_call *call = &event_user_stack; struct ring_buffer_event *event; @@ -3093,7 +3115,7 @@ ftrace_trace_userstack(struct trace_array *tr, __this_cpu_inc(user_stack_count); event = __trace_buffer_lock_reserve(buffer, TRACE_USER_STACK, - sizeof(*entry), flags, pc); + sizeof(*entry), trace_ctx); if (!event) goto out_drop_count; entry = ring_buffer_event_data(event); @@ -3113,7 +3135,7 @@ ftrace_trace_userstack(struct trace_array *tr, #else /* CONFIG_USER_STACKTRACE_SUPPORT */ static void ftrace_trace_userstack(struct trace_array *tr, struct trace_buffer *buffer, - unsigned long flags, int pc) + unsigned int trace_ctx) { } #endif /* !CONFIG_USER_STACKTRACE_SUPPORT */ @@ -3243,9 +3265,9 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args) struct trace_buffer *buffer; struct trace_array *tr = &global_trace; struct bprint_entry *entry; - unsigned long flags; + unsigned int trace_ctx; char *tbuffer; - int len = 0, size, pc; + int len = 0, size; if (unlikely(tracing_selftest_running || tracing_disabled)) return 0; @@ -3253,7 +3275,7 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args) /* Don't pollute graph traces with trace_vprintk internals */ pause_graph_tracing(); - pc = preempt_count(); + trace_ctx = tracing_gen_ctx(); preempt_disable_notrace(); tbuffer = get_trace_buf(); @@ -3267,12 +3289,11 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args) if (len > TRACE_BUF_SIZE/sizeof(int) || len < 0) goto out_put; - local_save_flags(flags); size = sizeof(*entry) + sizeof(u32) * len; buffer = tr->array_buffer.buffer; ring_buffer_nest_start(buffer); event = __trace_buffer_lock_reserve(buffer, TRACE_BPRINT, size, - flags, pc); + trace_ctx); if (!event) goto out; entry = ring_buffer_event_data(event); @@ -3282,7 +3303,7 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args) memcpy(entry->buf, tbuffer, sizeof(u32) * len); if (!call_filter_check_discard(call, entry, buffer, event)) { __buffer_unlock_commit(buffer, event); - ftrace_trace_stack(tr, buffer, flags, 6, pc, NULL); + ftrace_trace_stack(tr, buffer, trace_ctx, 6, NULL); } out: @@ -3305,9 +3326,9 @@ __trace_array_vprintk(struct trace_buffer *buffer, { struct trace_event_call *call = &event_print; struct ring_buffer_event *event; - int len = 0, size, pc; + int len = 0, size; struct print_entry *entry; - unsigned long flags; + unsigned int trace_ctx; char *tbuffer; if (tracing_disabled || tracing_selftest_running) @@ -3316,7 +3337,7 @@ __trace_array_vprintk(struct trace_buffer *buffer, /* Don't pollute graph traces with trace_vprintk internals */ pause_graph_tracing(); - pc = preempt_count(); + trace_ctx = tracing_gen_ctx(); preempt_disable_notrace(); @@ -3328,11 +3349,10 @@ __trace_array_vprintk(struct trace_buffer *buffer, len = vscnprintf(tbuffer, TRACE_BUF_SIZE, fmt, args); - local_save_flags(flags); size = sizeof(*entry) + len + 1; ring_buffer_nest_start(buffer); event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, size, - flags, pc); + trace_ctx); if (!event) goto out; entry = ring_buffer_event_data(event); @@ -3341,7 +3361,7 @@ __trace_array_vprintk(struct trace_buffer *buffer, memcpy(&entry->buf, tbuffer, len + 1); if (!call_filter_check_discard(call, entry, buffer, event)) { __buffer_unlock_commit(buffer, event); - ftrace_trace_stack(&global_trace, buffer, flags, 6, pc, NULL); + ftrace_trace_stack(&global_trace, buffer, trace_ctx, 6, NULL); } out: @@ -6654,7 +6674,6 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, enum event_trigger_type tt = ETT_NONE; struct trace_buffer *buffer; struct print_entry *entry; - unsigned long irq_flags; ssize_t written; int size; int len; @@ -6674,7 +6693,6 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, BUILD_BUG_ON(TRACE_BUF_SIZE >= PAGE_SIZE); - local_save_flags(irq_flags); size = sizeof(*entry) + cnt + 2; /* add '\0' and possible '\n' */ /* If less than "", then make sure we can still add that */ @@ -6683,7 +6701,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, buffer = tr->array_buffer.buffer; event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, size, - irq_flags, preempt_count()); + tracing_gen_ctx()); if (unlikely(!event)) /* Ring buffer disabled, return as if not open for write */ return -EBADF; @@ -6735,7 +6753,6 @@ tracing_mark_raw_write(struct file *filp, const char __user *ubuf, struct ring_buffer_event *event; struct trace_buffer *buffer; struct raw_data_entry *entry; - unsigned long irq_flags; ssize_t written; int size; int len; @@ -6757,14 +6774,13 @@ tracing_mark_raw_write(struct file *filp, const char __user *ubuf, BUILD_BUG_ON(TRACE_BUF_SIZE >= PAGE_SIZE); - local_save_flags(irq_flags); size = sizeof(*entry) + cnt; if (cnt < FAULT_SIZE_ID) size += FAULT_SIZE_ID - cnt; buffer = tr->array_buffer.buffer; event = __trace_buffer_lock_reserve(buffer, TRACE_RAW_DATA, size, - irq_flags, preempt_count()); + tracing_gen_ctx()); if (!event) /* Ring buffer disabled, return as if not open for write */ return -EBADF; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index e448d2da0b99..8daf3a0758b1 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -589,8 +589,7 @@ struct ring_buffer_event * trace_buffer_lock_reserve(struct trace_buffer *buffer, int type, unsigned long len, - unsigned long flags, - int pc); + unsigned int trace_ctx); struct trace_entry *tracing_get_trace_entry(struct trace_array *tr, struct trace_array_cpu *data); @@ -615,11 +614,11 @@ unsigned long trace_total_entries(struct trace_array *tr); void trace_function(struct trace_array *tr, unsigned long ip, unsigned long parent_ip, - unsigned long flags, int pc); + unsigned int trace_ctx); void trace_graph_function(struct trace_array *tr, unsigned long ip, unsigned long parent_ip, - unsigned long flags, int pc); + unsigned int trace_ctx); void trace_latency_header(struct seq_file *m); void trace_default_header(struct seq_file *m); void print_trace_header(struct seq_file *m, struct trace_iterator *iter); @@ -687,11 +686,10 @@ static inline void latency_fsnotify(struct trace_array *tr) { } #endif #ifdef CONFIG_STACKTRACE -void __trace_stack(struct trace_array *tr, unsigned long flags, int skip, - int pc); +void __trace_stack(struct trace_array *tr, unsigned int trace_ctx, int skip); #else -static inline void __trace_stack(struct trace_array *tr, unsigned long flags, - int skip, int pc) +static inline void __trace_stack(struct trace_array *tr, unsigned int trace_ctx, + int skip) { } #endif /* CONFIG_STACKTRACE */ @@ -831,10 +829,10 @@ extern void graph_trace_open(struct trace_iterator *iter); extern void graph_trace_close(struct trace_iterator *iter); extern int __trace_graph_entry(struct trace_array *tr, struct ftrace_graph_ent *trace, - unsigned long flags, int pc); + unsigned int trace_ctx); extern void __trace_graph_return(struct trace_array *tr, struct ftrace_graph_ret *trace, - unsigned long flags, int pc); + unsigned int trace_ctx); #ifdef CONFIG_DYNAMIC_FTRACE extern struct ftrace_hash __rcu *ftrace_graph_hash; @@ -1297,15 +1295,15 @@ extern int call_filter_check_discard(struct trace_event_call *call, void *rec, void trace_buffer_unlock_commit_regs(struct trace_array *tr, struct trace_buffer *buffer, struct ring_buffer_event *event, - unsigned long flags, int pc, + unsigned int trcace_ctx, struct pt_regs *regs); static inline void trace_buffer_unlock_commit(struct trace_array *tr, struct trace_buffer *buffer, struct ring_buffer_event *event, - unsigned long flags, int pc) + unsigned int trace_ctx) { - trace_buffer_unlock_commit_regs(tr, buffer, event, flags, pc, NULL); + trace_buffer_unlock_commit_regs(tr, buffer, event, trace_ctx, NULL); } DECLARE_PER_CPU(struct ring_buffer_event *, trace_buffered_event); @@ -1366,8 +1364,7 @@ __event_trigger_test_discard(struct trace_event_file *file, * @buffer: The ring buffer that the event is being written to * @event: The event meta data in the ring buffer * @entry: The event itself - * @irq_flags: The state of the interrupts at the start of the event - * @pc: The state of the preempt count at the start of the event. + * @trace_ctx: The tracing context flags. * * This is a helper function to handle triggers that require data * from the event itself. It also tests the event against filters and @@ -1377,12 +1374,12 @@ static inline void event_trigger_unlock_commit(struct trace_event_file *file, struct trace_buffer *buffer, struct ring_buffer_event *event, - void *entry, unsigned long irq_flags, int pc) + void *entry, unsigned int trace_ctx) { enum event_trigger_type tt = ETT_NONE; if (!__event_trigger_test_discard(file, buffer, event, entry, &tt)) - trace_buffer_unlock_commit(file->tr, buffer, event, irq_flags, pc); + trace_buffer_unlock_commit(file->tr, buffer, event, trace_ctx); if (tt) event_triggers_post_call(file, tt); @@ -1394,8 +1391,7 @@ event_trigger_unlock_commit(struct trace_event_file *file, * @buffer: The ring buffer that the event is being written to * @event: The event meta data in the ring buffer * @entry: The event itself - * @irq_flags: The state of the interrupts at the start of the event - * @pc: The state of the preempt count at the start of the event. + * @trace_ctx: The tracing context flags. * * This is a helper function to handle triggers that require data * from the event itself. It also tests the event against filters and @@ -1408,14 +1404,14 @@ static inline void event_trigger_unlock_commit_regs(struct trace_event_file *file, struct trace_buffer *buffer, struct ring_buffer_event *event, - void *entry, unsigned long irq_flags, int pc, + void *entry, unsigned int trace_ctx, struct pt_regs *regs) { enum event_trigger_type tt = ETT_NONE; if (!__event_trigger_test_discard(file, buffer, event, entry, &tt)) trace_buffer_unlock_commit_regs(file->tr, buffer, event, - irq_flags, pc, regs); + trace_ctx, regs); if (tt) event_triggers_post_call(file, tt); diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c index eff099123aa2..e47fdb4c92fb 100644 --- a/kernel/trace/trace_branch.c +++ b/kernel/trace/trace_branch.c @@ -37,7 +37,7 @@ probe_likely_condition(struct ftrace_likely_data *f, int val, int expect) struct ring_buffer_event *event; struct trace_branch *entry; unsigned long flags; - int pc; + unsigned int trace_ctx; const char *p; if (current->trace_recursion & TRACE_BRANCH_BIT) @@ -59,10 +59,10 @@ probe_likely_condition(struct ftrace_likely_data *f, int val, int expect) if (atomic_read(&data->disabled)) goto out; - pc = preempt_count(); + trace_ctx = tracing_gen_ctx_flags(flags); buffer = tr->array_buffer.buffer; event = trace_buffer_lock_reserve(buffer, TRACE_BRANCH, - sizeof(*entry), flags, pc); + sizeof(*entry), trace_ctx); if (!event) goto out; diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index a71181655958..288ad2c274fb 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -421,11 +421,8 @@ NOKPROBE_SYMBOL(perf_trace_buf_alloc); void perf_trace_buf_update(void *record, u16 type) { struct trace_entry *entry = record; - int pc = preempt_count(); - unsigned long flags; - local_save_flags(flags); - tracing_generic_entry_update(entry, type, flags, pc); + tracing_generic_entry_update(entry, type, tracing_gen_ctx()); } NOKPROBE_SYMBOL(perf_trace_buf_update); diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index e9d28eeccb7e..20ccce3e4ffb 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -258,22 +258,19 @@ void *trace_event_buffer_reserve(struct trace_event_buffer *fbuffer, trace_event_ignore_this_pid(trace_file)) return NULL; - local_save_flags(fbuffer->flags); - fbuffer->pc = preempt_count(); /* * If CONFIG_PREEMPTION is enabled, then the tracepoint itself disables * preemption (adding one to the preempt_count). Since we are * interested in the preempt_count at the time the tracepoint was * hit, we need to subtract one to offset the increment. */ - if (IS_ENABLED(CONFIG_PREEMPTION)) - fbuffer->pc--; + fbuffer->trace_ctx = tracing_gen_ctx_dec(); fbuffer->trace_file = trace_file; fbuffer->event = trace_event_buffer_lock_reserve(&fbuffer->buffer, trace_file, event_call->event.type, len, - fbuffer->flags, fbuffer->pc); + fbuffer->trace_ctx); if (!fbuffer->event) return NULL; @@ -3678,12 +3675,11 @@ function_test_events_call(unsigned long ip, unsigned long parent_ip, struct trace_buffer *buffer; struct ring_buffer_event *event; struct ftrace_entry *entry; - unsigned long flags; + unsigned int trace_ctx; long disabled; int cpu; - int pc; - pc = preempt_count(); + trace_ctx = tracing_gen_ctx(); preempt_disable_notrace(); cpu = raw_smp_processor_id(); disabled = atomic_inc_return(&per_cpu(ftrace_test_event_disable, cpu)); @@ -3691,11 +3687,9 @@ function_test_events_call(unsigned long ip, unsigned long parent_ip, if (disabled != 1) goto out; - local_save_flags(flags); - event = trace_event_buffer_lock_reserve(&buffer, &event_trace_file, TRACE_FN, sizeof(*entry), - flags, pc); + trace_ctx); if (!event) goto out; entry = ring_buffer_event_data(event); @@ -3703,7 +3697,7 @@ function_test_events_call(unsigned long ip, unsigned long parent_ip, entry->parent_ip = parent_ip; event_trigger_unlock_commit(&event_trace_file, buffer, event, - entry, flags, pc); + entry, trace_ctx); out: atomic_dec(&per_cpu(ftrace_test_event_disable, cpu)); preempt_enable_notrace(); diff --git a/kernel/trace/trace_events_inject.c b/kernel/trace/trace_events_inject.c index 22bcf7c51d1e..c188045c5f97 100644 --- a/kernel/trace/trace_events_inject.c +++ b/kernel/trace/trace_events_inject.c @@ -192,7 +192,6 @@ static void *trace_alloc_entry(struct trace_event_call *call, int *size) static int parse_entry(char *str, struct trace_event_call *call, void **pentry) { struct ftrace_event_field *field; - unsigned long irq_flags; void *entry = NULL; int entry_size; u64 val = 0; @@ -203,9 +202,8 @@ static int parse_entry(char *str, struct trace_event_call *call, void **pentry) if (!entry) return -ENOMEM; - local_save_flags(irq_flags); - tracing_generic_entry_update(entry, call->event.type, irq_flags, - preempt_count()); + tracing_generic_entry_update(entry, call->event.type, + tracing_gen_ctx()); while ((len = parse_field(str, call, &field, &val)) > 0) { if (is_function_field(field)) diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index f67aec5bb771..f93723ca66bc 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -131,10 +131,9 @@ function_trace_call(unsigned long ip, unsigned long parent_ip, { struct trace_array *tr = op->private; struct trace_array_cpu *data; - unsigned long flags; + unsigned int trace_ctx; int bit; int cpu; - int pc; if (unlikely(!tr->function_enabled)) return; @@ -143,15 +142,14 @@ function_trace_call(unsigned long ip, unsigned long parent_ip, if (bit < 0) return; - pc = preempt_count(); + trace_ctx = tracing_gen_ctx(); preempt_disable_notrace(); cpu = smp_processor_id(); data = per_cpu_ptr(tr->array_buffer.data, cpu); - if (!atomic_read(&data->disabled)) { - local_save_flags(flags); - trace_function(tr, ip, parent_ip, flags, pc); - } + if (!atomic_read(&data->disabled)) + trace_function(tr, ip, parent_ip, trace_ctx); + ftrace_test_recursion_unlock(bit); preempt_enable_notrace(); } @@ -183,7 +181,7 @@ function_stack_trace_call(unsigned long ip, unsigned long parent_ip, unsigned long flags; long disabled; int cpu; - int pc; + unsigned int trace_ctx; if (unlikely(!tr->function_enabled)) return; @@ -198,9 +196,9 @@ function_stack_trace_call(unsigned long ip, unsigned long parent_ip, disabled = atomic_inc_return(&data->disabled); if (likely(disabled == 1)) { - pc = preempt_count(); - trace_function(tr, ip, parent_ip, flags, pc); - __trace_stack(tr, flags, STACK_SKIP, pc); + trace_ctx = tracing_gen_ctx_flags(flags); + trace_function(tr, ip, parent_ip, trace_ctx); + __trace_stack(tr, trace_ctx, STACK_SKIP); } atomic_dec(&data->disabled); @@ -403,13 +401,11 @@ ftrace_traceoff(unsigned long ip, unsigned long parent_ip, static __always_inline void trace_stack(struct trace_array *tr) { - unsigned long flags; - int pc; + unsigned int trace_ctx; - local_save_flags(flags); - pc = preempt_count(); + trace_ctx = tracing_gen_ctx(); - __trace_stack(tr, flags, FTRACE_STACK_SKIP, pc); + __trace_stack(tr, trace_ctx, FTRACE_STACK_SKIP); } static void diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index d874dec87131..0aa6e6faa943 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -96,8 +96,7 @@ print_graph_duration(struct trace_array *tr, unsigned long long duration, int __trace_graph_entry(struct trace_array *tr, struct ftrace_graph_ent *trace, - unsigned long flags, - int pc) + unsigned int trace_ctx) { struct trace_event_call *call = &event_funcgraph_entry; struct ring_buffer_event *event; @@ -105,7 +104,7 @@ int __trace_graph_entry(struct trace_array *tr, struct ftrace_graph_ent_entry *entry; event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_ENT, - sizeof(*entry), flags, pc); + sizeof(*entry), trace_ctx); if (!event) return 0; entry = ring_buffer_event_data(event); @@ -129,10 +128,10 @@ int trace_graph_entry(struct ftrace_graph_ent *trace) struct trace_array *tr = graph_array; struct trace_array_cpu *data; unsigned long flags; + unsigned int trace_ctx; long disabled; int ret; int cpu; - int pc; if (trace_recursion_test(TRACE_GRAPH_NOTRACE_BIT)) return 0; @@ -174,8 +173,8 @@ int trace_graph_entry(struct ftrace_graph_ent *trace) data = per_cpu_ptr(tr->array_buffer.data, cpu); disabled = atomic_inc_return(&data->disabled); if (likely(disabled == 1)) { - pc = preempt_count(); - ret = __trace_graph_entry(tr, trace, flags, pc); + trace_ctx = tracing_gen_ctx_flags(flags); + ret = __trace_graph_entry(tr, trace, trace_ctx); } else { ret = 0; } @@ -188,7 +187,7 @@ int trace_graph_entry(struct ftrace_graph_ent *trace) static void __trace_graph_function(struct trace_array *tr, - unsigned long ip, unsigned long flags, int pc) + unsigned long ip, unsigned int trace_ctx) { u64 time = trace_clock_local(); struct ftrace_graph_ent ent = { @@ -202,22 +201,21 @@ __trace_graph_function(struct trace_array *tr, .rettime = time, }; - __trace_graph_entry(tr, &ent, flags, pc); - __trace_graph_return(tr, &ret, flags, pc); + __trace_graph_entry(tr, &ent, trace_ctx); + __trace_graph_return(tr, &ret, trace_ctx); } void trace_graph_function(struct trace_array *tr, unsigned long ip, unsigned long parent_ip, - unsigned long flags, int pc) + unsigned int trace_ctx) { - __trace_graph_function(tr, ip, flags, pc); + __trace_graph_function(tr, ip, trace_ctx); } void __trace_graph_return(struct trace_array *tr, struct ftrace_graph_ret *trace, - unsigned long flags, - int pc) + unsigned int trace_ctx) { struct trace_event_call *call = &event_funcgraph_exit; struct ring_buffer_event *event; @@ -225,7 +223,7 @@ void __trace_graph_return(struct trace_array *tr, struct ftrace_graph_ret_entry *entry; event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_RET, - sizeof(*entry), flags, pc); + sizeof(*entry), trace_ctx); if (!event) return; entry = ring_buffer_event_data(event); @@ -239,9 +237,9 @@ void trace_graph_return(struct ftrace_graph_ret *trace) struct trace_array *tr = graph_array; struct trace_array_cpu *data; unsigned long flags; + unsigned int trace_ctx; long disabled; int cpu; - int pc; ftrace_graph_addr_finish(trace); @@ -255,8 +253,8 @@ void trace_graph_return(struct ftrace_graph_ret *trace) data = per_cpu_ptr(tr->array_buffer.data, cpu); disabled = atomic_inc_return(&data->disabled); if (likely(disabled == 1)) { - pc = preempt_count(); - __trace_graph_return(tr, trace, flags, pc); + trace_ctx = tracing_gen_ctx_flags(flags); + __trace_graph_return(tr, trace, trace_ctx); } atomic_dec(&data->disabled); local_irq_restore(flags); diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c index c0df9b97f147..34dc1a712dcb 100644 --- a/kernel/trace/trace_hwlat.c +++ b/kernel/trace/trace_hwlat.c @@ -108,14 +108,9 @@ static void trace_hwlat_sample(struct hwlat_sample *sample) struct trace_buffer *buffer = tr->array_buffer.buffer; struct ring_buffer_event *event; struct hwlat_entry *entry; - unsigned long flags; - int pc; - - pc = preempt_count(); - local_save_flags(flags); event = trace_buffer_lock_reserve(buffer, TRACE_HWLAT, sizeof(*entry), - flags, pc); + tracing_gen_ctx()); if (!event) return; entry = ring_buffer_event_data(event); diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index 6756379b661f..590b3d51afae 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -143,11 +143,14 @@ irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip, struct trace_array *tr = irqsoff_trace; struct trace_array_cpu *data; unsigned long flags; + unsigned int trace_ctx; if (!func_prolog_dec(tr, &data, &flags)) return; - trace_function(tr, ip, parent_ip, flags, preempt_count()); + trace_ctx = tracing_gen_ctx_flags(flags); + + trace_function(tr, ip, parent_ip, trace_ctx); atomic_dec(&data->disabled); } @@ -177,8 +180,8 @@ static int irqsoff_graph_entry(struct ftrace_graph_ent *trace) struct trace_array *tr = irqsoff_trace; struct trace_array_cpu *data; unsigned long flags; + unsigned int trace_ctx; int ret; - int pc; if (ftrace_graph_ignore_func(trace)) return 0; @@ -195,8 +198,8 @@ static int irqsoff_graph_entry(struct ftrace_graph_ent *trace) if (!func_prolog_dec(tr, &data, &flags)) return 0; - pc = preempt_count(); - ret = __trace_graph_entry(tr, trace, flags, pc); + trace_ctx = tracing_gen_ctx_flags(flags); + ret = __trace_graph_entry(tr, trace, trace_ctx); atomic_dec(&data->disabled); return ret; @@ -207,15 +210,15 @@ static void irqsoff_graph_return(struct ftrace_graph_ret *trace) struct trace_array *tr = irqsoff_trace; struct trace_array_cpu *data; unsigned long flags; - int pc; + unsigned int trace_ctx; ftrace_graph_addr_finish(trace); if (!func_prolog_dec(tr, &data, &flags)) return; - pc = preempt_count(); - __trace_graph_return(tr, trace, flags, pc); + trace_ctx = tracing_gen_ctx_flags(flags); + __trace_graph_return(tr, trace, trace_ctx); atomic_dec(&data->disabled); } @@ -267,12 +270,12 @@ static void irqsoff_print_header(struct seq_file *s) static void __trace_function(struct trace_array *tr, unsigned long ip, unsigned long parent_ip, - unsigned long flags, int pc) + unsigned int trace_ctx) { if (is_graph(tr)) - trace_graph_function(tr, ip, parent_ip, flags, pc); + trace_graph_function(tr, ip, parent_ip, trace_ctx); else - trace_function(tr, ip, parent_ip, flags, pc); + trace_function(tr, ip, parent_ip, trace_ctx); } #else @@ -322,15 +325,13 @@ check_critical_timing(struct trace_array *tr, { u64 T0, T1, delta; unsigned long flags; - int pc; + unsigned int trace_ctx; T0 = data->preempt_timestamp; T1 = ftrace_now(cpu); delta = T1-T0; - local_save_flags(flags); - - pc = preempt_count(); + trace_ctx = tracing_gen_ctx(); if (!report_latency(tr, delta)) goto out; @@ -341,9 +342,9 @@ check_critical_timing(struct trace_array *tr, if (!report_latency(tr, delta)) goto out_unlock; - __trace_function(tr, CALLER_ADDR0, parent_ip, flags, pc); + __trace_function(tr, CALLER_ADDR0, parent_ip, trace_ctx); /* Skip 5 functions to get to the irq/preempt enable function */ - __trace_stack(tr, flags, 5, pc); + __trace_stack(tr, trace_ctx, 5); if (data->critical_sequence != max_sequence) goto out_unlock; @@ -363,16 +364,15 @@ out_unlock: out: data->critical_sequence = max_sequence; data->preempt_timestamp = ftrace_now(cpu); - __trace_function(tr, CALLER_ADDR0, parent_ip, flags, pc); + __trace_function(tr, CALLER_ADDR0, parent_ip, trace_ctx); } static nokprobe_inline void -start_critical_timing(unsigned long ip, unsigned long parent_ip, int pc) +start_critical_timing(unsigned long ip, unsigned long parent_ip) { int cpu; struct trace_array *tr = irqsoff_trace; struct trace_array_cpu *data; - unsigned long flags; if (!tracer_enabled || !tracing_is_enabled()) return; @@ -393,9 +393,7 @@ start_critical_timing(unsigned long ip, unsigned long parent_ip, int pc) data->preempt_timestamp = ftrace_now(cpu); data->critical_start = parent_ip ? : ip; - local_save_flags(flags); - - __trace_function(tr, ip, parent_ip, flags, pc); + __trace_function(tr, ip, parent_ip, tracing_gen_ctx()); per_cpu(tracing_cpu, cpu) = 1; @@ -403,12 +401,12 @@ start_critical_timing(unsigned long ip, unsigned long parent_ip, int pc) } static nokprobe_inline void -stop_critical_timing(unsigned long ip, unsigned long parent_ip, int pc) +stop_critical_timing(unsigned long ip, unsigned long parent_ip) { int cpu; struct trace_array *tr = irqsoff_trace; struct trace_array_cpu *data; - unsigned long flags; + unsigned int trace_ctx; cpu = raw_smp_processor_id(); /* Always clear the tracing cpu on stopping the trace */ @@ -428,8 +426,8 @@ stop_critical_timing(unsigned long ip, unsigned long parent_ip, int pc) atomic_inc(&data->disabled); - local_save_flags(flags); - __trace_function(tr, ip, parent_ip, flags, pc); + trace_ctx = tracing_gen_ctx(); + __trace_function(tr, ip, parent_ip, trace_ctx); check_critical_timing(tr, data, parent_ip ? : ip, cpu); data->critical_start = 0; atomic_dec(&data->disabled); @@ -438,20 +436,16 @@ stop_critical_timing(unsigned long ip, unsigned long parent_ip, int pc) /* start and stop critical timings used to for stoppage (in idle) */ void start_critical_timings(void) { - int pc = preempt_count(); - - if (preempt_trace(pc) || irq_trace()) - start_critical_timing(CALLER_ADDR0, CALLER_ADDR1, pc); + if (preempt_trace(preempt_count()) || irq_trace()) + start_critical_timing(CALLER_ADDR0, CALLER_ADDR1); } EXPORT_SYMBOL_GPL(start_critical_timings); NOKPROBE_SYMBOL(start_critical_timings); void stop_critical_timings(void) { - int pc = preempt_count(); - - if (preempt_trace(pc) || irq_trace()) - stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1, pc); + if (preempt_trace(preempt_count()) || irq_trace()) + stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1); } EXPORT_SYMBOL_GPL(stop_critical_timings); NOKPROBE_SYMBOL(stop_critical_timings); @@ -613,19 +607,15 @@ static void irqsoff_tracer_stop(struct trace_array *tr) */ void tracer_hardirqs_on(unsigned long a0, unsigned long a1) { - unsigned int pc = preempt_count(); - - if (!preempt_trace(pc) && irq_trace()) - stop_critical_timing(a0, a1, pc); + if (!preempt_trace(preempt_count()) && irq_trace()) + stop_critical_timing(a0, a1); } NOKPROBE_SYMBOL(tracer_hardirqs_on); void tracer_hardirqs_off(unsigned long a0, unsigned long a1) { - unsigned int pc = preempt_count(); - - if (!preempt_trace(pc) && irq_trace()) - start_critical_timing(a0, a1, pc); + if (!preempt_trace(preempt_count()) && irq_trace()) + start_critical_timing(a0, a1); } NOKPROBE_SYMBOL(tracer_hardirqs_off); @@ -665,18 +655,14 @@ static struct tracer irqsoff_tracer __read_mostly = #ifdef CONFIG_PREEMPT_TRACER void tracer_preempt_on(unsigned long a0, unsigned long a1) { - int pc = preempt_count(); - - if (preempt_trace(pc) && !irq_trace()) - stop_critical_timing(a0, a1, pc); + if (preempt_trace(preempt_count()) && !irq_trace()) + stop_critical_timing(a0, a1); } void tracer_preempt_off(unsigned long a0, unsigned long a1) { - int pc = preempt_count(); - - if (preempt_trace(pc) && !irq_trace()) - start_critical_timing(a0, a1, pc); + if (preempt_trace(preempt_count()) && !irq_trace()) + start_critical_timing(a0, a1); } static int preemptoff_tracer_init(struct trace_array *tr) diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 56c7fbff7bd7..f6c459aba8a6 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1386,8 +1386,7 @@ __kprobe_trace_func(struct trace_kprobe *tk, struct pt_regs *regs, if (trace_trigger_soft_disabled(trace_file)) return; - local_save_flags(fbuffer.flags); - fbuffer.pc = preempt_count(); + fbuffer.trace_ctx = tracing_gen_ctx(); fbuffer.trace_file = trace_file; dsize = __get_data_size(&tk->tp, regs); @@ -1396,7 +1395,7 @@ __kprobe_trace_func(struct trace_kprobe *tk, struct pt_regs *regs, trace_event_buffer_lock_reserve(&fbuffer.buffer, trace_file, call->event.type, sizeof(*entry) + tk->tp.size + dsize, - fbuffer.flags, fbuffer.pc); + fbuffer.trace_ctx); if (!fbuffer.event) return; @@ -1434,8 +1433,7 @@ __kretprobe_trace_func(struct trace_kprobe *tk, struct kretprobe_instance *ri, if (trace_trigger_soft_disabled(trace_file)) return; - local_save_flags(fbuffer.flags); - fbuffer.pc = preempt_count(); + fbuffer.trace_ctx = tracing_gen_ctx(); fbuffer.trace_file = trace_file; dsize = __get_data_size(&tk->tp, regs); @@ -1443,7 +1441,7 @@ __kretprobe_trace_func(struct trace_kprobe *tk, struct kretprobe_instance *ri, trace_event_buffer_lock_reserve(&fbuffer.buffer, trace_file, call->event.type, sizeof(*entry) + tk->tp.size + dsize, - fbuffer.flags, fbuffer.pc); + fbuffer.trace_ctx); if (!fbuffer.event) return; diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c index 84582bf1ed5f..7221ae0b4c47 100644 --- a/kernel/trace/trace_mmiotrace.c +++ b/kernel/trace/trace_mmiotrace.c @@ -300,10 +300,11 @@ static void __trace_mmiotrace_rw(struct trace_array *tr, struct trace_buffer *buffer = tr->array_buffer.buffer; struct ring_buffer_event *event; struct trace_mmiotrace_rw *entry; - int pc = preempt_count(); + unsigned int trace_ctx; + trace_ctx = tracing_gen_ctx_flags(0); event = trace_buffer_lock_reserve(buffer, TRACE_MMIO_RW, - sizeof(*entry), 0, pc); + sizeof(*entry), trace_ctx); if (!event) { atomic_inc(&dropped_count); return; @@ -312,7 +313,7 @@ static void __trace_mmiotrace_rw(struct trace_array *tr, entry->rw = *rw; if (!call_filter_check_discard(call, entry, buffer, event)) - trace_buffer_unlock_commit(tr, buffer, event, 0, pc); + trace_buffer_unlock_commit(tr, buffer, event, trace_ctx); } void mmio_trace_rw(struct mmiotrace_rw *rw) @@ -330,10 +331,11 @@ static void __trace_mmiotrace_map(struct trace_array *tr, struct trace_buffer *buffer = tr->array_buffer.buffer; struct ring_buffer_event *event; struct trace_mmiotrace_map *entry; - int pc = preempt_count(); + unsigned int trace_ctx; + trace_ctx = tracing_gen_ctx_flags(0); event = trace_buffer_lock_reserve(buffer, TRACE_MMIO_MAP, - sizeof(*entry), 0, pc); + sizeof(*entry), trace_ctx); if (!event) { atomic_inc(&dropped_count); return; @@ -342,7 +344,7 @@ static void __trace_mmiotrace_map(struct trace_array *tr, entry->map = *map; if (!call_filter_check_discard(call, entry, buffer, event)) - trace_buffer_unlock_commit(tr, buffer, event, 0, pc); + trace_buffer_unlock_commit(tr, buffer, event, trace_ctx); } void mmio_trace_mapping(struct mmiotrace_map *map) diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index c0181066dbe9..e5778d1d7a5b 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -67,7 +67,7 @@ static bool function_enabled; static int func_prolog_preempt_disable(struct trace_array *tr, struct trace_array_cpu **data, - int *pc) + unsigned int *trace_ctx) { long disabled; int cpu; @@ -75,7 +75,7 @@ func_prolog_preempt_disable(struct trace_array *tr, if (likely(!wakeup_task)) return 0; - *pc = preempt_count(); + *trace_ctx = tracing_gen_ctx(); preempt_disable_notrace(); cpu = raw_smp_processor_id(); @@ -116,8 +116,8 @@ static int wakeup_graph_entry(struct ftrace_graph_ent *trace) { struct trace_array *tr = wakeup_trace; struct trace_array_cpu *data; - unsigned long flags; - int pc, ret = 0; + unsigned int trace_ctx; + int ret = 0; if (ftrace_graph_ignore_func(trace)) return 0; @@ -131,11 +131,10 @@ static int wakeup_graph_entry(struct ftrace_graph_ent *trace) if (ftrace_graph_notrace_addr(trace->func)) return 1; - if (!func_prolog_preempt_disable(tr, &data, &pc)) + if (!func_prolog_preempt_disable(tr, &data, &trace_ctx)) return 0; - local_save_flags(flags); - ret = __trace_graph_entry(tr, trace, flags, pc); + ret = __trace_graph_entry(tr, trace, trace_ctx); atomic_dec(&data->disabled); preempt_enable_notrace(); @@ -146,16 +145,14 @@ static void wakeup_graph_return(struct ftrace_graph_ret *trace) { struct trace_array *tr = wakeup_trace; struct trace_array_cpu *data; - unsigned long flags; - int pc; + unsigned int trace_ctx; ftrace_graph_addr_finish(trace); - if (!func_prolog_preempt_disable(tr, &data, &pc)) + if (!func_prolog_preempt_disable(tr, &data, &trace_ctx)) return; - local_save_flags(flags); - __trace_graph_return(tr, trace, flags, pc); + __trace_graph_return(tr, trace, trace_ctx); atomic_dec(&data->disabled); preempt_enable_notrace(); @@ -217,13 +214,13 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip, struct trace_array *tr = wakeup_trace; struct trace_array_cpu *data; unsigned long flags; - int pc; + unsigned int trace_ctx; - if (!func_prolog_preempt_disable(tr, &data, &pc)) + if (!func_prolog_preempt_disable(tr, &data, &trace_ctx)) return; local_irq_save(flags); - trace_function(tr, ip, parent_ip, flags, pc); + trace_function(tr, ip, parent_ip, trace_ctx); local_irq_restore(flags); atomic_dec(&data->disabled); @@ -303,12 +300,12 @@ static void wakeup_print_header(struct seq_file *s) static void __trace_function(struct trace_array *tr, unsigned long ip, unsigned long parent_ip, - unsigned long flags, int pc) + unsigned int trace_ctx) { if (is_graph(tr)) - trace_graph_function(tr, ip, parent_ip, flags, pc); + trace_graph_function(tr, ip, parent_ip, trace_ctx); else - trace_function(tr, ip, parent_ip, flags, pc); + trace_function(tr, ip, parent_ip, trace_ctx); } static int wakeup_flag_changed(struct trace_array *tr, u32 mask, int set) @@ -375,7 +372,7 @@ static void tracing_sched_switch_trace(struct trace_array *tr, struct task_struct *prev, struct task_struct *next, - unsigned long flags, int pc) + unsigned int trace_ctx) { struct trace_event_call *call = &event_context_switch; struct trace_buffer *buffer = tr->array_buffer.buffer; @@ -383,7 +380,7 @@ tracing_sched_switch_trace(struct trace_array *tr, struct ctx_switch_entry *entry; event = trace_buffer_lock_reserve(buffer, TRACE_CTX, - sizeof(*entry), flags, pc); + sizeof(*entry), trace_ctx); if (!event) return; entry = ring_buffer_event_data(event); @@ -396,14 +393,14 @@ tracing_sched_switch_trace(struct trace_array *tr, entry->next_cpu = task_cpu(next); if (!call_filter_check_discard(call, entry, buffer, event)) - trace_buffer_unlock_commit(tr, buffer, event, flags, pc); + trace_buffer_unlock_commit(tr, buffer, event, trace_ctx); } static void tracing_sched_wakeup_trace(struct trace_array *tr, struct task_struct *wakee, struct task_struct *curr, - unsigned long flags, int pc) + unsigned int trace_ctx) { struct trace_event_call *call = &event_wakeup; struct ring_buffer_event *event; @@ -411,7 +408,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr, struct trace_buffer *buffer = tr->array_buffer.buffer; event = trace_buffer_lock_reserve(buffer, TRACE_WAKE, - sizeof(*entry), flags, pc); + sizeof(*entry), trace_ctx); if (!event) return; entry = ring_buffer_event_data(event); @@ -424,7 +421,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr, entry->next_cpu = task_cpu(wakee); if (!call_filter_check_discard(call, entry, buffer, event)) - trace_buffer_unlock_commit(tr, buffer, event, flags, pc); + trace_buffer_unlock_commit(tr, buffer, event, trace_ctx); } static void notrace @@ -436,7 +433,7 @@ probe_wakeup_sched_switch(void *ignore, bool preempt, unsigned long flags; long disabled; int cpu; - int pc; + unsigned int trace_ctx; tracing_record_cmdline(prev); @@ -455,8 +452,6 @@ probe_wakeup_sched_switch(void *ignore, bool preempt, if (next != wakeup_task) return; - pc = preempt_count(); - /* disable local data, not wakeup_cpu data */ cpu = raw_smp_processor_id(); disabled = atomic_inc_return(&per_cpu_ptr(wakeup_trace->array_buffer.data, cpu)->disabled); @@ -464,6 +459,8 @@ probe_wakeup_sched_switch(void *ignore, bool preempt, goto out; local_irq_save(flags); + trace_ctx = tracing_gen_ctx_flags(flags); + arch_spin_lock(&wakeup_lock); /* We could race with grabbing wakeup_lock */ @@ -473,9 +470,9 @@ probe_wakeup_sched_switch(void *ignore, bool preempt, /* The task we are waiting for is waking up */ data = per_cpu_ptr(wakeup_trace->array_buffer.data, wakeup_cpu); - __trace_function(wakeup_trace, CALLER_ADDR0, CALLER_ADDR1, flags, pc); - tracing_sched_switch_trace(wakeup_trace, prev, next, flags, pc); - __trace_stack(wakeup_trace, flags, 0, pc); + __trace_function(wakeup_trace, CALLER_ADDR0, CALLER_ADDR1, trace_ctx); + tracing_sched_switch_trace(wakeup_trace, prev, next, trace_ctx); + __trace_stack(wakeup_trace, trace_ctx, 0); T0 = data->preempt_timestamp; T1 = ftrace_now(cpu); @@ -527,9 +524,8 @@ probe_wakeup(void *ignore, struct task_struct *p) { struct trace_array_cpu *data; int cpu = smp_processor_id(); - unsigned long flags; long disabled; - int pc; + unsigned int trace_ctx; if (likely(!tracer_enabled)) return; @@ -550,11 +546,12 @@ probe_wakeup(void *ignore, struct task_struct *p) (!dl_task(p) && (p->prio >= wakeup_prio || p->prio >= current->prio))) return; - pc = preempt_count(); disabled = atomic_inc_return(&per_cpu_ptr(wakeup_trace->array_buffer.data, cpu)->disabled); if (unlikely(disabled != 1)) goto out; + trace_ctx = tracing_gen_ctx(); + /* interrupts should be off from try_to_wake_up */ arch_spin_lock(&wakeup_lock); @@ -581,19 +578,17 @@ probe_wakeup(void *ignore, struct task_struct *p) wakeup_task = get_task_struct(p); - local_save_flags(flags); - data = per_cpu_ptr(wakeup_trace->array_buffer.data, wakeup_cpu); data->preempt_timestamp = ftrace_now(cpu); - tracing_sched_wakeup_trace(wakeup_trace, p, current, flags, pc); - __trace_stack(wakeup_trace, flags, 0, pc); + tracing_sched_wakeup_trace(wakeup_trace, p, current, trace_ctx); + __trace_stack(wakeup_trace, trace_ctx, 0); /* * We must be careful in using CALLER_ADDR2. But since wake_up * is not called by an assembly function (where as schedule is) * it should be safe to use it here. */ - __trace_function(wakeup_trace, CALLER_ADDR1, CALLER_ADDR2, flags, pc); + __trace_function(wakeup_trace, CALLER_ADDR1, CALLER_ADDR2, trace_ctx); out_locked: arch_spin_unlock(&wakeup_lock); diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index d85a2f0f316b..8bfcd3b09422 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -298,9 +298,8 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) struct syscall_metadata *sys_data; struct ring_buffer_event *event; struct trace_buffer *buffer; - unsigned long irq_flags; + unsigned int trace_ctx; unsigned long args[6]; - int pc; int syscall_nr; int size; @@ -322,12 +321,11 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args; - local_save_flags(irq_flags); - pc = preempt_count(); + trace_ctx = tracing_gen_ctx(); buffer = tr->array_buffer.buffer; event = trace_buffer_lock_reserve(buffer, - sys_data->enter_event->event.type, size, irq_flags, pc); + sys_data->enter_event->event.type, size, trace_ctx); if (!event) return; @@ -337,7 +335,7 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) memcpy(entry->args, args, sizeof(unsigned long) * sys_data->nb_args); event_trigger_unlock_commit(trace_file, buffer, event, entry, - irq_flags, pc); + trace_ctx); } static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret) @@ -348,8 +346,7 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret) struct syscall_metadata *sys_data; struct ring_buffer_event *event; struct trace_buffer *buffer; - unsigned long irq_flags; - int pc; + unsigned int trace_ctx; int syscall_nr; syscall_nr = trace_get_syscall_nr(current, regs); @@ -368,13 +365,12 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret) if (!sys_data) return; - local_save_flags(irq_flags); - pc = preempt_count(); + trace_ctx = tracing_gen_ctx(); buffer = tr->array_buffer.buffer; event = trace_buffer_lock_reserve(buffer, sys_data->exit_event->event.type, sizeof(*entry), - irq_flags, pc); + trace_ctx); if (!event) return; @@ -383,7 +379,7 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret) entry->ret = syscall_get_return_value(current, regs); event_trigger_unlock_commit(trace_file, buffer, event, entry, - irq_flags, pc); + trace_ctx); } static int reg_event_syscall_enter(struct trace_event_file *file, diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 3cf7128e1ad3..a1ed96a7a462 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -961,7 +961,7 @@ static void __uprobe_trace_func(struct trace_uprobe *tu, esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); size = esize + tu->tp.size + dsize; event = trace_event_buffer_lock_reserve(&buffer, trace_file, - call->event.type, size, 0, 0); + call->event.type, size, 0); if (!event) return; @@ -977,7 +977,7 @@ static void __uprobe_trace_func(struct trace_uprobe *tu, memcpy(data, ucb->buf, tu->tp.size + dsize); - event_trigger_unlock_commit(trace_file, buffer, event, entry, 0, 0); + event_trigger_unlock_commit(trace_file, buffer, event, entry, 0); } /* uprobe handler */ -- cgit v1.2.3 From 0c02006e6f5b0a3e73499bbf5943d9174c5ed640 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Mon, 25 Jan 2021 20:45:09 +0100 Subject: tracing: Inline tracing_gen_ctx_flags() Inline tracing_gen_ctx_flags(). This allows to have one ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT. This requires to move `trace_flag_type' so tracing_gen_ctx_flags() can use it. Link: https://lkml.kernel.org/r/20210125194511.3924915-3-bigeasy@linutronix.de Suggested-by: Steven Rostedt Link: https://lkml.kernel.org/r/20210125140323.6b1ff20c@gandalf.local.home Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_events.h | 54 +++++++++++++++++++++++++++++++++++++++++--- kernel/trace/trace.c | 38 ++----------------------------- kernel/trace/trace.h | 19 ---------------- 3 files changed, 53 insertions(+), 58 deletions(-) (limited to 'include') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 091250b0895a..67ae708de40d 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -160,9 +160,57 @@ static inline void tracing_generic_entry_update(struct trace_entry *entry, entry->flags = trace_ctx >> 16; } -unsigned int tracing_gen_ctx_flags(unsigned long irqflags); -unsigned int tracing_gen_ctx(void); -unsigned int tracing_gen_ctx_dec(void); +unsigned int tracing_gen_ctx_irq_test(unsigned int irqs_status); + +enum trace_flag_type { + TRACE_FLAG_IRQS_OFF = 0x01, + TRACE_FLAG_IRQS_NOSUPPORT = 0x02, + TRACE_FLAG_NEED_RESCHED = 0x04, + TRACE_FLAG_HARDIRQ = 0x08, + TRACE_FLAG_SOFTIRQ = 0x10, + TRACE_FLAG_PREEMPT_RESCHED = 0x20, + TRACE_FLAG_NMI = 0x40, +}; + +#ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT +static inline unsigned int tracing_gen_ctx_flags(unsigned long irqflags) +{ + unsigned int irq_status = irqs_disabled_flags(irqflags) ? + TRACE_FLAG_IRQS_OFF : 0; + return tracing_gen_ctx_irq_test(irq_status); +} +static inline unsigned int tracing_gen_ctx(void) +{ + unsigned long irqflags; + + local_save_flags(irqflags); + return tracing_gen_ctx_flags(irqflags); +} +#else + +static inline unsigned int tracing_gen_ctx_flags(unsigned long irqflags) +{ + return tracing_gen_ctx_irq_test(TRACE_FLAG_IRQS_NOSUPPORT); +} +static inline unsigned int tracing_gen_ctx(void) +{ + return tracing_gen_ctx_irq_test(TRACE_FLAG_IRQS_NOSUPPORT); +} +#endif + +static inline unsigned int tracing_gen_ctx_dec(void) +{ + unsigned int trace_ctx; + + trace_ctx = tracing_gen_ctx(); + /* + * Subtract one from the preeption counter if preemption is enabled, + * see trace_event_buffer_reserve()for details. + */ + if (IS_ENABLED(CONFIG_PREEMPTION)) + trace_ctx--; + return trace_ctx; +} struct trace_event_file; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 0b3cce6ecf52..584fa2a1304a 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2579,20 +2579,13 @@ enum print_line_t trace_handle_return(struct trace_seq *s) } EXPORT_SYMBOL_GPL(trace_handle_return); -unsigned int tracing_gen_ctx_flags(unsigned long irqflags) +unsigned int tracing_gen_ctx_irq_test(unsigned int irqs_status) { - unsigned int trace_flags = 0; + unsigned int trace_flags = irqs_status; unsigned int pc; pc = preempt_count(); -#ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT - if (irqs_disabled_flags(irqflags)) - trace_flags |= TRACE_FLAG_IRQS_OFF; -#else - trace_flags |= TRACE_FLAG_IRQS_NOSUPPORT; -#endif - if (pc & NMI_MASK) trace_flags |= TRACE_FLAG_NMI; if (pc & HARDIRQ_MASK) @@ -2608,33 +2601,6 @@ unsigned int tracing_gen_ctx_flags(unsigned long irqflags) return (trace_flags << 16) | (pc & 0xff); } -unsigned int tracing_gen_ctx(void) -{ - unsigned long irqflags; - -#ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT - local_save_flags(irqflags); -#else - irqflags = 0; -#endif - return tracing_gen_ctx_flags(irqflags); -} - -unsigned int tracing_gen_ctx_dec(void) -{ - unsigned int trace_ctx; - - trace_ctx = tracing_gen_ctx(); - - /* - * Subtract one from the preeption counter if preemption is enabled, - * see trace_event_buffer_reserve()for details. - */ - if (IS_ENABLED(CONFIG_PREEMPTION)) - trace_ctx--; - return trace_ctx; -} - struct ring_buffer_event * trace_buffer_lock_reserve(struct trace_buffer *buffer, int type, diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 8daf3a0758b1..93fb08ab8bb6 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -136,25 +136,6 @@ struct kretprobe_trace_entry_head { unsigned long ret_ip; }; -/* - * trace_flag_type is an enumeration that holds different - * states when a trace occurs. These are: - * IRQS_OFF - interrupts were disabled - * IRQS_NOSUPPORT - arch does not support irqs_disabled_flags - * NEED_RESCHED - reschedule is requested - * HARDIRQ - inside an interrupt handler - * SOFTIRQ - inside a softirq handler - */ -enum trace_flag_type { - TRACE_FLAG_IRQS_OFF = 0x01, - TRACE_FLAG_IRQS_NOSUPPORT = 0x02, - TRACE_FLAG_NEED_RESCHED = 0x04, - TRACE_FLAG_HARDIRQ = 0x08, - TRACE_FLAG_SOFTIRQ = 0x10, - TRACE_FLAG_PREEMPT_RESCHED = 0x20, - TRACE_FLAG_NMI = 0x40, -}; - #define TRACE_BUF_SIZE 1024 struct trace_array; -- cgit v1.2.3 From 5817708493bec547914d23dcdd064919ac409f33 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Mon, 25 Jan 2021 20:45:11 +0100 Subject: tracing: Remove NULL check from current in tracing_generic_entry_update(). I can't imagine when or why `current' would return a NULL pointer. This check was added in commit 72829bc3d63cd ("ftrace: move enums to ftrace.h and make helper function global") but it doesn't give me hint why it was needed. Assume `current' never returns a NULL pointer and remove the check. Link: https://lkml.kernel.org/r/20210125194511.3924915-5-bigeasy@linutronix.de Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_events.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 67ae708de40d..5d1eeac4bfbe 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -152,10 +152,8 @@ static inline void tracing_generic_entry_update(struct trace_entry *entry, unsigned short type, unsigned int trace_ctx) { - struct task_struct *tsk = current; - entry->preempt_count = trace_ctx & 0xff; - entry->pid = (tsk) ? tsk->pid : 0; + entry->pid = current->pid; entry->type = type; entry->flags = trace_ctx >> 16; } -- cgit v1.2.3 From 01531ac354051667f80d23bb85bf2643ae11260a Mon Sep 17 00:00:00 2001 From: BingJing Chang Date: Fri, 29 Jan 2021 12:52:42 +0800 Subject: parser: add unsigned int parser Will be used by fs parsing options Link: https://lore.kernel.org/r/20210129045242.10268-1-bingjingc@synology.com Reviewed-by: Robbie Ko Reviewed-by: Chung-Chiang Cheng Signed-off-by: BingJing Chang Signed-off-by: Jan Kara --- include/linux/parser.h | 1 + lib/parser.c | 22 ++++++++++++++++++++++ 2 files changed, 23 insertions(+) (limited to 'include') diff --git a/include/linux/parser.h b/include/linux/parser.h index 89e2b23fb888..dd79f45a37b8 100644 --- a/include/linux/parser.h +++ b/include/linux/parser.h @@ -29,6 +29,7 @@ typedef struct { int match_token(char *, const match_table_t table, substring_t args[]); int match_int(substring_t *, int *result); +int match_uint(substring_t *s, unsigned int *result); int match_u64(substring_t *, u64 *result); int match_octal(substring_t *, int *result); int match_hex(substring_t *, int *result); diff --git a/lib/parser.c b/lib/parser.c index f5b3e5d7a7f9..7785e41fa5eb 100644 --- a/lib/parser.c +++ b/lib/parser.c @@ -188,6 +188,28 @@ int match_int(substring_t *s, int *result) } EXPORT_SYMBOL(match_int); +/* + * match_uint - scan a decimal representation of an integer from a substring_t + * @s: substring_t to be scanned + * @result: resulting integer on success + * + * Description: Attempts to parse the &substring_t @s as a decimal integer. On + * success, sets @result to the integer represented by the string and returns 0. + * Returns -ENOMEM, -EINVAL, or -ERANGE on failure. + */ +int match_uint(substring_t *s, unsigned int *result) +{ + int err = -ENOMEM; + char *buf = match_strdup(s); + + if (buf) { + err = kstrtouint(buf, 10, result); + kfree(buf); + } + return err; +} +EXPORT_SYMBOL(match_uint); + /** * match_u64: - scan a decimal representation of a u64 from * a substring_t -- cgit v1.2.3 From ed8188a0c1f0f49739c727a53df1174826c1a80b Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Thu, 4 Feb 2021 09:43:55 +0800 Subject: iommu/vt-d: Fix 'physical' typos Fix misspellings of "physical". Signed-off-by: Bjorn Helgaas Signed-off-by: Lu Baolu Link: https://lore.kernel.org/linux-iommu/20210126211738.2920789-1-helgaas@kernel.org Link: https://lore.kernel.org/r/20210204014401.2846425-2-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index ecb35fdff03e..f8ab154c979d 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -664,7 +664,7 @@ static inline struct dmar_domain *to_dmar_domain(struct iommu_domain *dom) * 7: super page * 8-10: available * 11: snoop behavior - * 12-63: Host physcial address + * 12-63: Host physical address */ struct dma_pte { u64 val; -- cgit v1.2.3 From ad3d19029979b19378ece2011fc8ce07be98c905 Mon Sep 17 00:00:00 2001 From: Kyung Min Park Date: Thu, 4 Feb 2021 09:43:56 +0800 Subject: iommu/vt-d: Audit IOMMU Capabilities and add helper functions Audit IOMMU Capability/Extended Capability and check if the IOMMUs have the consistent value for features. Report out or scale to the lowest supported when IOMMU features have incompatibility among IOMMUs. Report out features when below features are mismatched: - First Level 5 Level Paging Support (FL5LP) - First Level 1 GByte Page Support (FL1GP) - Read Draining (DRD) - Write Draining (DWD) - Page Selective Invalidation (PSI) - Zero Length Read (ZLR) - Caching Mode (CM) - Protected High/Low-Memory Region (PHMR/PLMR) - Required Write-Buffer Flushing (RWBF) - Advanced Fault Logging (AFL) - RID-PASID Support (RPS) - Scalable Mode Page Walk Coherency (SMPWC) - First Level Translation Support (FLTS) - Second Level Translation Support (SLTS) - No Write Flag Support (NWFS) - Second Level Accessed/Dirty Support (SLADS) - Virtual Command Support (VCS) - Scalable Mode Translation Support (SMTS) - Device TLB Invalidation Throttle (DIT) - Page Drain Support (PDS) - Process Address Space ID Support (PASID) - Extended Accessed Flag Support (EAFS) - Supervisor Request Support (SRS) - Execute Request Support (ERS) - Page Request Support (PRS) - Nested Translation Support (NEST) - Snoop Control (SC) - Pass Through (PT) - Device TLB Support (DT) - Queued Invalidation (QI) - Page walk Coherency (C) Set capability to the lowest supported when below features are mismatched: - Maximum Address Mask Value (MAMV) - Number of Fault Recording Registers (NFR) - Second Level Large Page Support (SLLPS) - Fault Recording Offset (FRO) - Maximum Guest Address Width (MGAW) - Supported Adjusted Guest Address Width (SAGAW) - Number of Domains supported (NDOMS) - Pasid Size Supported (PSS) - Maximum Handle Mask Value (MHMV) - IOTLB Register Offset (IRO) Signed-off-by: Kyung Min Park Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20210130184452.31711-1-kyung.min.park@intel.com Link: https://lore.kernel.org/r/20210204014401.2846425-3-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/Makefile | 2 +- drivers/iommu/intel/cap_audit.c | 185 ++++++++++++++++++++++++++++++++++++ drivers/iommu/intel/cap_audit.h | 110 +++++++++++++++++++++ drivers/iommu/intel/iommu.c | 9 ++ drivers/iommu/intel/irq_remapping.c | 8 ++ include/linux/intel-iommu.h | 39 ++++---- 6 files changed, 334 insertions(+), 19 deletions(-) create mode 100644 drivers/iommu/intel/cap_audit.c create mode 100644 drivers/iommu/intel/cap_audit.h (limited to 'include') diff --git a/drivers/iommu/intel/Makefile b/drivers/iommu/intel/Makefile index ae570810a35e..ae236ec7d219 100644 --- a/drivers/iommu/intel/Makefile +++ b/drivers/iommu/intel/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_DMAR_TABLE) += dmar.o obj-$(CONFIG_INTEL_IOMMU) += iommu.o pasid.o -obj-$(CONFIG_DMAR_TABLE) += trace.o +obj-$(CONFIG_DMAR_TABLE) += trace.o cap_audit.o obj-$(CONFIG_INTEL_IOMMU_DEBUGFS) += debugfs.o obj-$(CONFIG_INTEL_IOMMU_SVM) += svm.o obj-$(CONFIG_IRQ_REMAP) += irq_remapping.o diff --git a/drivers/iommu/intel/cap_audit.c b/drivers/iommu/intel/cap_audit.c new file mode 100644 index 000000000000..049bc0c76a00 --- /dev/null +++ b/drivers/iommu/intel/cap_audit.c @@ -0,0 +1,185 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * cap_audit.c - audit iommu capabilities for boot time and hot plug + * + * Copyright (C) 2021 Intel Corporation + * + * Author: Kyung Min Park + * Lu Baolu + */ + +#define pr_fmt(fmt) "DMAR: " fmt + +#include +#include "cap_audit.h" + +static u64 intel_iommu_cap_sanity; +static u64 intel_iommu_ecap_sanity; + +static inline void check_irq_capabilities(struct intel_iommu *a, + struct intel_iommu *b) +{ + CHECK_FEATURE_MISMATCH(a, b, cap, pi_support, CAP_PI_MASK); + CHECK_FEATURE_MISMATCH(a, b, ecap, eim_support, ECAP_EIM_MASK); +} + +static inline void check_dmar_capabilities(struct intel_iommu *a, + struct intel_iommu *b) +{ + MINIMAL_FEATURE_IOMMU(b, cap, CAP_MAMV_MASK); + MINIMAL_FEATURE_IOMMU(b, cap, CAP_NFR_MASK); + MINIMAL_FEATURE_IOMMU(b, cap, CAP_SLLPS_MASK); + MINIMAL_FEATURE_IOMMU(b, cap, CAP_FRO_MASK); + MINIMAL_FEATURE_IOMMU(b, cap, CAP_MGAW_MASK); + MINIMAL_FEATURE_IOMMU(b, cap, CAP_SAGAW_MASK); + MINIMAL_FEATURE_IOMMU(b, cap, CAP_NDOMS_MASK); + MINIMAL_FEATURE_IOMMU(b, ecap, ECAP_PSS_MASK); + MINIMAL_FEATURE_IOMMU(b, ecap, ECAP_MHMV_MASK); + MINIMAL_FEATURE_IOMMU(b, ecap, ECAP_IRO_MASK); + + CHECK_FEATURE_MISMATCH(a, b, cap, 5lp_support, CAP_FL5LP_MASK); + CHECK_FEATURE_MISMATCH(a, b, cap, fl1gp_support, CAP_FL1GP_MASK); + CHECK_FEATURE_MISMATCH(a, b, cap, read_drain, CAP_RD_MASK); + CHECK_FEATURE_MISMATCH(a, b, cap, write_drain, CAP_WD_MASK); + CHECK_FEATURE_MISMATCH(a, b, cap, pgsel_inv, CAP_PSI_MASK); + CHECK_FEATURE_MISMATCH(a, b, cap, zlr, CAP_ZLR_MASK); + CHECK_FEATURE_MISMATCH(a, b, cap, caching_mode, CAP_CM_MASK); + CHECK_FEATURE_MISMATCH(a, b, cap, phmr, CAP_PHMR_MASK); + CHECK_FEATURE_MISMATCH(a, b, cap, plmr, CAP_PLMR_MASK); + CHECK_FEATURE_MISMATCH(a, b, cap, rwbf, CAP_RWBF_MASK); + CHECK_FEATURE_MISMATCH(a, b, cap, afl, CAP_AFL_MASK); + CHECK_FEATURE_MISMATCH(a, b, ecap, rps, ECAP_RPS_MASK); + CHECK_FEATURE_MISMATCH(a, b, ecap, smpwc, ECAP_SMPWC_MASK); + CHECK_FEATURE_MISMATCH(a, b, ecap, flts, ECAP_FLTS_MASK); + CHECK_FEATURE_MISMATCH(a, b, ecap, slts, ECAP_SLTS_MASK); + CHECK_FEATURE_MISMATCH(a, b, ecap, nwfs, ECAP_NWFS_MASK); + CHECK_FEATURE_MISMATCH(a, b, ecap, slads, ECAP_SLADS_MASK); + CHECK_FEATURE_MISMATCH(a, b, ecap, vcs, ECAP_VCS_MASK); + CHECK_FEATURE_MISMATCH(a, b, ecap, smts, ECAP_SMTS_MASK); + CHECK_FEATURE_MISMATCH(a, b, ecap, pds, ECAP_PDS_MASK); + CHECK_FEATURE_MISMATCH(a, b, ecap, dit, ECAP_DIT_MASK); + CHECK_FEATURE_MISMATCH(a, b, ecap, pasid, ECAP_PASID_MASK); + CHECK_FEATURE_MISMATCH(a, b, ecap, eafs, ECAP_EAFS_MASK); + CHECK_FEATURE_MISMATCH(a, b, ecap, srs, ECAP_SRS_MASK); + CHECK_FEATURE_MISMATCH(a, b, ecap, ers, ECAP_ERS_MASK); + CHECK_FEATURE_MISMATCH(a, b, ecap, prs, ECAP_PRS_MASK); + CHECK_FEATURE_MISMATCH(a, b, ecap, nest, ECAP_NEST_MASK); + CHECK_FEATURE_MISMATCH(a, b, ecap, mts, ECAP_MTS_MASK); + CHECK_FEATURE_MISMATCH(a, b, ecap, sc_support, ECAP_SC_MASK); + CHECK_FEATURE_MISMATCH(a, b, ecap, pass_through, ECAP_PT_MASK); + CHECK_FEATURE_MISMATCH(a, b, ecap, dev_iotlb_support, ECAP_DT_MASK); + CHECK_FEATURE_MISMATCH(a, b, ecap, qis, ECAP_QI_MASK); + CHECK_FEATURE_MISMATCH(a, b, ecap, coherent, ECAP_C_MASK); +} + +static int cap_audit_hotplug(struct intel_iommu *iommu, enum cap_audit_type type) +{ + bool mismatch = false; + u64 old_cap = intel_iommu_cap_sanity; + u64 old_ecap = intel_iommu_ecap_sanity; + + if (type == CAP_AUDIT_HOTPLUG_IRQR) { + CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, cap, pi_support, CAP_PI_MASK); + CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, eim_support, ECAP_EIM_MASK); + goto out; + } + + CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, cap, 5lp_support, CAP_FL5LP_MASK); + CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, cap, fl1gp_support, CAP_FL1GP_MASK); + CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, cap, read_drain, CAP_RD_MASK); + CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, cap, write_drain, CAP_WD_MASK); + CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, cap, pgsel_inv, CAP_PSI_MASK); + CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, cap, zlr, CAP_ZLR_MASK); + CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, cap, caching_mode, CAP_CM_MASK); + CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, cap, phmr, CAP_PHMR_MASK); + CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, cap, plmr, CAP_PLMR_MASK); + CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, cap, rwbf, CAP_RWBF_MASK); + CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, cap, afl, CAP_AFL_MASK); + CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, rps, ECAP_RPS_MASK); + CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, smpwc, ECAP_SMPWC_MASK); + CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, flts, ECAP_FLTS_MASK); + CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, slts, ECAP_SLTS_MASK); + CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, nwfs, ECAP_NWFS_MASK); + CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, slads, ECAP_SLADS_MASK); + CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, vcs, ECAP_VCS_MASK); + CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, smts, ECAP_SMTS_MASK); + CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, pds, ECAP_PDS_MASK); + CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, dit, ECAP_DIT_MASK); + CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, pasid, ECAP_PASID_MASK); + CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, eafs, ECAP_EAFS_MASK); + CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, srs, ECAP_SRS_MASK); + CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, ers, ECAP_ERS_MASK); + CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, prs, ECAP_PRS_MASK); + CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, nest, ECAP_NEST_MASK); + CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, mts, ECAP_MTS_MASK); + CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, sc_support, ECAP_SC_MASK); + CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, pass_through, ECAP_PT_MASK); + CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, dev_iotlb_support, ECAP_DT_MASK); + CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, qis, ECAP_QI_MASK); + CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, coherent, ECAP_C_MASK); + + /* Abort hot plug if the hot plug iommu feature is smaller than global */ + MINIMAL_FEATURE_HOTPLUG(iommu, cap, max_amask_val, CAP_MAMV_MASK, mismatch); + MINIMAL_FEATURE_HOTPLUG(iommu, cap, num_fault_regs, CAP_NFR_MASK, mismatch); + MINIMAL_FEATURE_HOTPLUG(iommu, cap, super_page_val, CAP_SLLPS_MASK, mismatch); + MINIMAL_FEATURE_HOTPLUG(iommu, cap, fault_reg_offset, CAP_FRO_MASK, mismatch); + MINIMAL_FEATURE_HOTPLUG(iommu, cap, mgaw, CAP_MGAW_MASK, mismatch); + MINIMAL_FEATURE_HOTPLUG(iommu, cap, sagaw, CAP_SAGAW_MASK, mismatch); + MINIMAL_FEATURE_HOTPLUG(iommu, cap, ndoms, CAP_NDOMS_MASK, mismatch); + MINIMAL_FEATURE_HOTPLUG(iommu, ecap, pss, ECAP_PSS_MASK, mismatch); + MINIMAL_FEATURE_HOTPLUG(iommu, ecap, max_handle_mask, ECAP_MHMV_MASK, mismatch); + MINIMAL_FEATURE_HOTPLUG(iommu, ecap, iotlb_offset, ECAP_IRO_MASK, mismatch); + +out: + if (mismatch) { + intel_iommu_cap_sanity = old_cap; + intel_iommu_ecap_sanity = old_ecap; + return -EFAULT; + } + + return 0; +} + +static int cap_audit_static(struct intel_iommu *iommu, enum cap_audit_type type) +{ + struct dmar_drhd_unit *d; + struct intel_iommu *i; + + rcu_read_lock(); + if (list_empty(&dmar_drhd_units)) + goto out; + + for_each_active_iommu(i, d) { + if (!iommu) { + intel_iommu_ecap_sanity = i->ecap; + intel_iommu_cap_sanity = i->cap; + iommu = i; + continue; + } + + if (type == CAP_AUDIT_STATIC_DMAR) + check_dmar_capabilities(iommu, i); + else + check_irq_capabilities(iommu, i); + } + +out: + rcu_read_unlock(); + return 0; +} + +int intel_cap_audit(enum cap_audit_type type, struct intel_iommu *iommu) +{ + switch (type) { + case CAP_AUDIT_STATIC_DMAR: + case CAP_AUDIT_STATIC_IRQR: + return cap_audit_static(iommu, type); + case CAP_AUDIT_HOTPLUG_DMAR: + case CAP_AUDIT_HOTPLUG_IRQR: + return cap_audit_hotplug(iommu, type); + default: + break; + } + + return -EFAULT; +} diff --git a/drivers/iommu/intel/cap_audit.h b/drivers/iommu/intel/cap_audit.h new file mode 100644 index 000000000000..a6a1530441b7 --- /dev/null +++ b/drivers/iommu/intel/cap_audit.h @@ -0,0 +1,110 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * cap_audit.h - audit iommu capabilities header + * + * Copyright (C) 2021 Intel Corporation + * + * Author: Kyung Min Park + */ + +/* + * Capability Register Mask + */ +#define CAP_FL5LP_MASK BIT_ULL(60) +#define CAP_PI_MASK BIT_ULL(59) +#define CAP_FL1GP_MASK BIT_ULL(56) +#define CAP_RD_MASK BIT_ULL(55) +#define CAP_WD_MASK BIT_ULL(54) +#define CAP_MAMV_MASK GENMASK_ULL(53, 48) +#define CAP_NFR_MASK GENMASK_ULL(47, 40) +#define CAP_PSI_MASK BIT_ULL(39) +#define CAP_SLLPS_MASK GENMASK_ULL(37, 34) +#define CAP_FRO_MASK GENMASK_ULL(33, 24) +#define CAP_ZLR_MASK BIT_ULL(22) +#define CAP_MGAW_MASK GENMASK_ULL(21, 16) +#define CAP_SAGAW_MASK GENMASK_ULL(12, 8) +#define CAP_CM_MASK BIT_ULL(7) +#define CAP_PHMR_MASK BIT_ULL(6) +#define CAP_PLMR_MASK BIT_ULL(5) +#define CAP_RWBF_MASK BIT_ULL(4) +#define CAP_AFL_MASK BIT_ULL(3) +#define CAP_NDOMS_MASK GENMASK_ULL(2, 0) + +/* + * Extended Capability Register Mask + */ +#define ECAP_RPS_MASK BIT_ULL(49) +#define ECAP_SMPWC_MASK BIT_ULL(48) +#define ECAP_FLTS_MASK BIT_ULL(47) +#define ECAP_SLTS_MASK BIT_ULL(46) +#define ECAP_SLADS_MASK BIT_ULL(45) +#define ECAP_VCS_MASK BIT_ULL(44) +#define ECAP_SMTS_MASK BIT_ULL(43) +#define ECAP_PDS_MASK BIT_ULL(42) +#define ECAP_DIT_MASK BIT_ULL(41) +#define ECAP_PASID_MASK BIT_ULL(40) +#define ECAP_PSS_MASK GENMASK_ULL(39, 35) +#define ECAP_EAFS_MASK BIT_ULL(34) +#define ECAP_NWFS_MASK BIT_ULL(33) +#define ECAP_SRS_MASK BIT_ULL(31) +#define ECAP_ERS_MASK BIT_ULL(30) +#define ECAP_PRS_MASK BIT_ULL(29) +#define ECAP_NEST_MASK BIT_ULL(26) +#define ECAP_MTS_MASK BIT_ULL(25) +#define ECAP_MHMV_MASK GENMASK_ULL(23, 20) +#define ECAP_IRO_MASK GENMASK_ULL(17, 8) +#define ECAP_SC_MASK BIT_ULL(7) +#define ECAP_PT_MASK BIT_ULL(6) +#define ECAP_EIM_MASK BIT_ULL(4) +#define ECAP_DT_MASK BIT_ULL(2) +#define ECAP_QI_MASK BIT_ULL(1) +#define ECAP_C_MASK BIT_ULL(0) + +/* + * u64 intel_iommu_cap_sanity, intel_iommu_ecap_sanity will be adjusted as each + * IOMMU gets audited. + */ +#define DO_CHECK_FEATURE_MISMATCH(a, b, cap, feature, MASK) \ +do { \ + if (cap##_##feature(a) != cap##_##feature(b)) { \ + intel_iommu_##cap##_sanity &= ~(MASK); \ + pr_info("IOMMU feature %s inconsistent", #feature); \ + } \ +} while (0) + +#define CHECK_FEATURE_MISMATCH(a, b, cap, feature, MASK) \ + DO_CHECK_FEATURE_MISMATCH((a)->cap, (b)->cap, cap, feature, MASK) + +#define CHECK_FEATURE_MISMATCH_HOTPLUG(b, cap, feature, MASK) \ +do { \ + if (cap##_##feature(intel_iommu_##cap##_sanity)) \ + DO_CHECK_FEATURE_MISMATCH(intel_iommu_##cap##_sanity, \ + (b)->cap, cap, feature, MASK); \ +} while (0) + +#define MINIMAL_FEATURE_IOMMU(iommu, cap, MASK) \ +do { \ + u64 min_feature = intel_iommu_##cap##_sanity & (MASK); \ + min_feature = min_t(u64, min_feature, (iommu)->cap & (MASK)); \ + intel_iommu_##cap##_sanity = (intel_iommu_##cap##_sanity & ~(MASK)) | \ + min_feature; \ +} while (0) + +#define MINIMAL_FEATURE_HOTPLUG(iommu, cap, feature, MASK, mismatch) \ +do { \ + if ((intel_iommu_##cap##_sanity & (MASK)) > \ + (cap##_##feature((iommu)->cap))) \ + mismatch = true; \ + else \ + (iommu)->cap = ((iommu)->cap & ~(MASK)) | \ + (intel_iommu_##cap##_sanity & (MASK)); \ +} while (0) + +enum cap_audit_type { + CAP_AUDIT_STATIC_DMAR, + CAP_AUDIT_STATIC_IRQR, + CAP_AUDIT_HOTPLUG_DMAR, + CAP_AUDIT_HOTPLUG_IRQR, +}; + +int intel_cap_audit(enum cap_audit_type type, struct intel_iommu *iommu); diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 87d0ef79ba6a..de82d5da01f9 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -47,6 +47,7 @@ #include "../irq_remapping.h" #include "pasid.h" +#include "cap_audit.h" #define ROOT_SIZE VTD_PAGE_SIZE #define CONTEXT_SIZE VTD_PAGE_SIZE @@ -3206,6 +3207,10 @@ static int __init init_dmars(void) goto error; } + ret = intel_cap_audit(CAP_AUDIT_STATIC_DMAR, NULL); + if (ret) + goto free_iommu; + for_each_iommu(iommu, drhd) { if (drhd->ignored) { iommu_disable_translation(iommu); @@ -3757,6 +3762,10 @@ static int intel_iommu_add(struct dmar_drhd_unit *dmaru) if (g_iommus[iommu->seq_id]) return 0; + ret = intel_cap_audit(CAP_AUDIT_HOTPLUG_DMAR, iommu); + if (ret) + goto out; + if (hw_pass_through && !ecap_pass_through(iommu->ecap)) { pr_warn("%s: Doesn't support hardware pass through.\n", iommu->name); diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c index 685200a5cff0..611ef5243cb6 100644 --- a/drivers/iommu/intel/irq_remapping.c +++ b/drivers/iommu/intel/irq_remapping.c @@ -22,6 +22,7 @@ #include #include "../irq_remapping.h" +#include "cap_audit.h" enum irq_mode { IRQ_REMAPPING, @@ -734,6 +735,9 @@ static int __init intel_prepare_irq_remapping(void) if (dmar_table_init() < 0) return -ENODEV; + if (intel_cap_audit(CAP_AUDIT_STATIC_IRQR, NULL)) + goto error; + if (!dmar_ir_support()) return -ENODEV; @@ -1439,6 +1443,10 @@ static int dmar_ir_add(struct dmar_drhd_unit *dmaru, struct intel_iommu *iommu) int ret; int eim = x2apic_enabled(); + ret = intel_cap_audit(CAP_AUDIT_HOTPLUG_IRQR, iommu); + if (ret) + return ret; + if (eim && !ecap_eim_support(iommu->ecap)) { pr_info("DRHD %Lx: EIM not supported by DRHD, ecap %Lx\n", iommu->reg_phys, iommu->ecap); diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index f8ab154c979d..1bc46b88711a 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -170,34 +170,37 @@ * Extended Capability Register */ +#define ecap_rps(e) (((e) >> 49) & 0x1) #define ecap_smpwc(e) (((e) >> 48) & 0x1) #define ecap_flts(e) (((e) >> 47) & 0x1) #define ecap_slts(e) (((e) >> 46) & 0x1) +#define ecap_slads(e) (((e) >> 45) & 0x1) #define ecap_vcs(e) (((e) >> 44) & 0x1) #define ecap_smts(e) (((e) >> 43) & 0x1) -#define ecap_dit(e) ((e >> 41) & 0x1) -#define ecap_pasid(e) ((e >> 40) & 0x1) -#define ecap_pss(e) ((e >> 35) & 0x1f) -#define ecap_eafs(e) ((e >> 34) & 0x1) -#define ecap_nwfs(e) ((e >> 33) & 0x1) -#define ecap_srs(e) ((e >> 31) & 0x1) -#define ecap_ers(e) ((e >> 30) & 0x1) -#define ecap_prs(e) ((e >> 29) & 0x1) -#define ecap_broken_pasid(e) ((e >> 28) & 0x1) -#define ecap_dis(e) ((e >> 27) & 0x1) -#define ecap_nest(e) ((e >> 26) & 0x1) -#define ecap_mts(e) ((e >> 25) & 0x1) -#define ecap_ecs(e) ((e >> 24) & 0x1) +#define ecap_dit(e) (((e) >> 41) & 0x1) +#define ecap_pds(e) (((e) >> 42) & 0x1) +#define ecap_pasid(e) (((e) >> 40) & 0x1) +#define ecap_pss(e) (((e) >> 35) & 0x1f) +#define ecap_eafs(e) (((e) >> 34) & 0x1) +#define ecap_nwfs(e) (((e) >> 33) & 0x1) +#define ecap_srs(e) (((e) >> 31) & 0x1) +#define ecap_ers(e) (((e) >> 30) & 0x1) +#define ecap_prs(e) (((e) >> 29) & 0x1) +#define ecap_broken_pasid(e) (((e) >> 28) & 0x1) +#define ecap_dis(e) (((e) >> 27) & 0x1) +#define ecap_nest(e) (((e) >> 26) & 0x1) +#define ecap_mts(e) (((e) >> 25) & 0x1) +#define ecap_ecs(e) (((e) >> 24) & 0x1) #define ecap_iotlb_offset(e) ((((e) >> 8) & 0x3ff) * 16) #define ecap_max_iotlb_offset(e) (ecap_iotlb_offset(e) + 16) #define ecap_coherent(e) ((e) & 0x1) #define ecap_qis(e) ((e) & 0x2) -#define ecap_pass_through(e) ((e >> 6) & 0x1) -#define ecap_eim_support(e) ((e >> 4) & 0x1) -#define ecap_ir_support(e) ((e >> 3) & 0x1) +#define ecap_pass_through(e) (((e) >> 6) & 0x1) +#define ecap_eim_support(e) (((e) >> 4) & 0x1) +#define ecap_ir_support(e) (((e) >> 3) & 0x1) #define ecap_dev_iotlb_support(e) (((e) >> 2) & 0x1) -#define ecap_max_handle_mask(e) ((e >> 20) & 0xf) -#define ecap_sc_support(e) ((e >> 7) & 0x1) /* Snooping Control */ +#define ecap_max_handle_mask(e) (((e) >> 20) & 0xf) +#define ecap_sc_support(e) (((e) >> 7) & 0x1) /* Snooping Control */ /* Virtual command interface capability */ #define vccap_pasid(v) (((v) & DMA_VCS_PAS)) /* PASID allocation */ -- cgit v1.2.3 From 81d3c75bb3c32ca61712e093b8dce89d73c22150 Mon Sep 17 00:00:00 2001 From: Yian Chen Date: Thu, 4 Feb 2021 09:43:59 +0800 Subject: iommu/vt-d: Add new enum value and structure for SATC Starting from Intel Platform VT-d v3.2, BIOS may provide new remapping structure SATC for SOC integrated devices, according to section 8.8 of Intel VT-d architecture specification v3.2. The SATC structure reports a list of the devices that require ATS for normal device operation. It is a functional requirement that these devices will not work without OS enabling ATS capability. This patch introduces the new enum value and structure to represent the remapping information. Kernel should parse the information from the reporting structure and enable ATC for the devices as needed. Signed-off-by: Yian Chen Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20210203093329.1617808-1-baolu.lu@linux.intel.com Link: https://lore.kernel.org/r/20210204014401.2846425-6-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/acpi/actbl1.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/acpi/actbl1.h b/include/acpi/actbl1.h index 43549547ed3e..c38e08cf1b9e 100644 --- a/include/acpi/actbl1.h +++ b/include/acpi/actbl1.h @@ -514,7 +514,8 @@ enum acpi_dmar_type { ACPI_DMAR_TYPE_ROOT_ATS = 2, ACPI_DMAR_TYPE_HARDWARE_AFFINITY = 3, ACPI_DMAR_TYPE_NAMESPACE = 4, - ACPI_DMAR_TYPE_RESERVED = 5 /* 5 and greater are reserved */ + ACPI_DMAR_TYPE_SATC = 5, + ACPI_DMAR_TYPE_RESERVED = 6 /* 6 and greater are reserved */ }; /* DMAR Device Scope structure */ @@ -607,6 +608,14 @@ struct acpi_dmar_andd { char device_name[1]; }; +/* 5: SOC Integrated Address Translation Cache Reporting Structure */ + +struct acpi_dmar_satc { + struct acpi_dmar_header header; + u8 flags; + u8 reserved; + u16 segment; +}; /******************************************************************************* * * DRTM - Dynamic Root of Trust for Measurement table -- cgit v1.2.3 From 31a75cbbb9274cf8185f402904bf11386917870b Mon Sep 17 00:00:00 2001 From: Yian Chen Date: Thu, 4 Feb 2021 09:44:00 +0800 Subject: iommu/vt-d: Parse SATC reporting structure Software should parse every SATC table and all devices in the tables reported by the BIOS and keep the information in kernel list for further reference. Signed-off-by: Yian Chen Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20210203093329.1617808-1-baolu.lu@linux.intel.com Link: https://lore.kernel.org/r/20210204014401.2846425-7-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/dmar.c | 8 ++++ drivers/iommu/intel/iommu.c | 89 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/dmar.h | 2 + 3 files changed, 99 insertions(+) (limited to 'include') diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index bd51f33642e0..6b8fce1c85c4 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -526,6 +526,7 @@ dmar_table_print_dmar_entry(struct acpi_dmar_header *header) struct acpi_dmar_reserved_memory *rmrr; struct acpi_dmar_atsr *atsr; struct acpi_dmar_rhsa *rhsa; + struct acpi_dmar_satc *satc; switch (header->type) { case ACPI_DMAR_TYPE_HARDWARE_UNIT: @@ -555,6 +556,10 @@ dmar_table_print_dmar_entry(struct acpi_dmar_header *header) /* We don't print this here because we need to sanity-check it first. So print it in dmar_parse_one_andd() instead. */ break; + case ACPI_DMAR_TYPE_SATC: + satc = container_of(header, struct acpi_dmar_satc, header); + pr_info("SATC flags: 0x%x\n", satc->flags); + break; } } @@ -642,6 +647,7 @@ parse_dmar_table(void) .cb[ACPI_DMAR_TYPE_ROOT_ATS] = &dmar_parse_one_atsr, .cb[ACPI_DMAR_TYPE_HARDWARE_AFFINITY] = &dmar_parse_one_rhsa, .cb[ACPI_DMAR_TYPE_NAMESPACE] = &dmar_parse_one_andd, + .cb[ACPI_DMAR_TYPE_SATC] = &dmar_parse_one_satc, }; /* @@ -2077,6 +2083,7 @@ static guid_t dmar_hp_guid = #define DMAR_DSM_FUNC_DRHD 1 #define DMAR_DSM_FUNC_ATSR 2 #define DMAR_DSM_FUNC_RHSA 3 +#define DMAR_DSM_FUNC_SATC 4 static inline bool dmar_detect_dsm(acpi_handle handle, int func) { @@ -2094,6 +2101,7 @@ static int dmar_walk_dsm_resource(acpi_handle handle, int func, [DMAR_DSM_FUNC_DRHD] = ACPI_DMAR_TYPE_HARDWARE_UNIT, [DMAR_DSM_FUNC_ATSR] = ACPI_DMAR_TYPE_ROOT_ATS, [DMAR_DSM_FUNC_RHSA] = ACPI_DMAR_TYPE_HARDWARE_AFFINITY, + [DMAR_DSM_FUNC_SATC] = ACPI_DMAR_TYPE_SATC, }; if (!dmar_detect_dsm(handle, func)) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 761c1b251c1e..384cc546632a 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -316,8 +316,18 @@ struct dmar_atsr_unit { u8 include_all:1; /* include all ports */ }; +struct dmar_satc_unit { + struct list_head list; /* list of SATC units */ + struct acpi_dmar_header *hdr; /* ACPI header */ + struct dmar_dev_scope *devices; /* target devices */ + struct intel_iommu *iommu; /* the corresponding iommu */ + int devices_cnt; /* target device count */ + u8 atc_required:1; /* ATS is required */ +}; + static LIST_HEAD(dmar_atsr_units); static LIST_HEAD(dmar_rmrr_units); +static LIST_HEAD(dmar_satc_units); #define for_each_rmrr_units(rmrr) \ list_for_each_entry(rmrr, &dmar_rmrr_units, list) @@ -3716,6 +3726,57 @@ int dmar_check_one_atsr(struct acpi_dmar_header *hdr, void *arg) return 0; } +static struct dmar_satc_unit *dmar_find_satc(struct acpi_dmar_satc *satc) +{ + struct dmar_satc_unit *satcu; + struct acpi_dmar_satc *tmp; + + list_for_each_entry_rcu(satcu, &dmar_satc_units, list, + dmar_rcu_check()) { + tmp = (struct acpi_dmar_satc *)satcu->hdr; + if (satc->segment != tmp->segment) + continue; + if (satc->header.length != tmp->header.length) + continue; + if (memcmp(satc, tmp, satc->header.length) == 0) + return satcu; + } + + return NULL; +} + +int dmar_parse_one_satc(struct acpi_dmar_header *hdr, void *arg) +{ + struct acpi_dmar_satc *satc; + struct dmar_satc_unit *satcu; + + if (system_state >= SYSTEM_RUNNING && !intel_iommu_enabled) + return 0; + + satc = container_of(hdr, struct acpi_dmar_satc, header); + satcu = dmar_find_satc(satc); + if (satcu) + return 0; + + satcu = kzalloc(sizeof(*satcu) + hdr->length, GFP_KERNEL); + if (!satcu) + return -ENOMEM; + + satcu->hdr = (void *)(satcu + 1); + memcpy(satcu->hdr, hdr, hdr->length); + satcu->atc_required = satc->flags & 0x1; + satcu->devices = dmar_alloc_dev_scope((void *)(satc + 1), + (void *)satc + satc->header.length, + &satcu->devices_cnt); + if (satcu->devices_cnt && !satcu->devices) { + kfree(satcu); + return -ENOMEM; + } + list_add_rcu(&satcu->list, &dmar_satc_units); + + return 0; +} + static int intel_iommu_add(struct dmar_drhd_unit *dmaru) { int sp, ret; @@ -3823,6 +3884,7 @@ static void intel_iommu_free_dmars(void) { struct dmar_rmrr_unit *rmrru, *rmrr_n; struct dmar_atsr_unit *atsru, *atsr_n; + struct dmar_satc_unit *satcu, *satc_n; list_for_each_entry_safe(rmrru, rmrr_n, &dmar_rmrr_units, list) { list_del(&rmrru->list); @@ -3834,6 +3896,11 @@ static void intel_iommu_free_dmars(void) list_del(&atsru->list); intel_iommu_free_atsr(atsru); } + list_for_each_entry_safe(satcu, satc_n, &dmar_satc_units, list) { + list_del(&satcu->list); + dmar_free_dev_scope(&satcu->devices, &satcu->devices_cnt); + kfree(satcu); + } } int dmar_find_matched_atsr_unit(struct pci_dev *dev) @@ -3885,8 +3952,10 @@ int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info) int ret; struct dmar_rmrr_unit *rmrru; struct dmar_atsr_unit *atsru; + struct dmar_satc_unit *satcu; struct acpi_dmar_atsr *atsr; struct acpi_dmar_reserved_memory *rmrr; + struct acpi_dmar_satc *satc; if (!intel_iommu_enabled && system_state >= SYSTEM_RUNNING) return 0; @@ -3927,6 +3996,23 @@ int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info) break; } } + list_for_each_entry(satcu, &dmar_satc_units, list) { + satc = container_of(satcu->hdr, struct acpi_dmar_satc, header); + if (info->event == BUS_NOTIFY_ADD_DEVICE) { + ret = dmar_insert_dev_scope(info, (void *)(satc + 1), + (void *)satc + satc->header.length, + satc->segment, satcu->devices, + satcu->devices_cnt); + if (ret > 0) + break; + else if (ret < 0) + return ret; + } else if (info->event == BUS_NOTIFY_REMOVED_DEVICE) { + if (dmar_remove_dev_scope(info, satc->segment, + satcu->devices, satcu->devices_cnt)) + break; + } + } return 0; } @@ -4270,6 +4356,9 @@ int __init intel_iommu_init(void) if (list_empty(&dmar_atsr_units)) pr_info("No ATSR found\n"); + if (list_empty(&dmar_satc_units)) + pr_info("No SATC found\n"); + if (dmar_map_gfx) intel_iommu_gfx_mapped = 1; diff --git a/include/linux/dmar.h b/include/linux/dmar.h index 65565820328a..e04436a7ff27 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -138,6 +138,7 @@ extern void intel_iommu_shutdown(void); extern int dmar_parse_one_rmrr(struct acpi_dmar_header *header, void *arg); extern int dmar_parse_one_atsr(struct acpi_dmar_header *header, void *arg); extern int dmar_check_one_atsr(struct acpi_dmar_header *hdr, void *arg); +extern int dmar_parse_one_satc(struct acpi_dmar_header *hdr, void *arg); extern int dmar_release_one_atsr(struct acpi_dmar_header *hdr, void *arg); extern int dmar_iommu_hotplug(struct dmar_drhd_unit *dmaru, bool insert); extern int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info); @@ -149,6 +150,7 @@ static inline void intel_iommu_shutdown(void) { } #define dmar_parse_one_atsr dmar_res_noop #define dmar_check_one_atsr dmar_res_noop #define dmar_release_one_atsr dmar_res_noop +#define dmar_parse_one_satc dmar_res_noop static inline int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info) { -- cgit v1.2.3 From e1e4f7fea37572f0ccf3887430e52c491e9accb6 Mon Sep 17 00:00:00 2001 From: CK Hu Date: Tue, 21 Jul 2020 15:46:06 +0800 Subject: soc / drm: mediatek: Move mtk mutex driver to soc folder mtk mutex is used by DRM and MDP driver, and its function is SoC-specific, so move it to soc folder. Signed-off-by: CK Hu Signed-off-by: Chun-Kuang Hu Acked-by: Matthias Brugger --- drivers/gpu/drm/mediatek/Makefile | 3 +- drivers/gpu/drm/mediatek/mtk_drm_crtc.c | 2 +- drivers/gpu/drm/mediatek/mtk_drm_drv.c | 1 - drivers/gpu/drm/mediatek/mtk_drm_drv.h | 1 - drivers/gpu/drm/mediatek/mtk_mutex.c | 463 ------------------------------- drivers/gpu/drm/mediatek/mtk_mutex.h | 26 -- drivers/soc/mediatek/Makefile | 1 + drivers/soc/mediatek/mtk-mutex.c | 474 ++++++++++++++++++++++++++++++++ include/linux/soc/mediatek/mtk-mutex.h | 26 ++ 9 files changed, 503 insertions(+), 494 deletions(-) delete mode 100644 drivers/gpu/drm/mediatek/mtk_mutex.c delete mode 100644 drivers/gpu/drm/mediatek/mtk_mutex.h create mode 100644 drivers/soc/mediatek/mtk-mutex.c create mode 100644 include/linux/soc/mediatek/mtk-mutex.h (limited to 'include') diff --git a/drivers/gpu/drm/mediatek/Makefile b/drivers/gpu/drm/mediatek/Makefile index 09979c4c340a..01d06332f767 100644 --- a/drivers/gpu/drm/mediatek/Makefile +++ b/drivers/gpu/drm/mediatek/Makefile @@ -9,8 +9,7 @@ mediatek-drm-y := mtk_disp_color.o \ mtk_drm_gem.o \ mtk_drm_plane.o \ mtk_dsi.o \ - mtk_dpi.o \ - mtk_mutex.o + mtk_dpi.o obj-$(CONFIG_DRM_MEDIATEK) += mediatek-drm.o diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c index 1e3a9450680b..e9b6788d52cd 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include @@ -22,7 +23,6 @@ #include "mtk_drm_ddp_comp.h" #include "mtk_drm_gem.h" #include "mtk_drm_plane.h" -#include "mtk_mutex.h" /* * struct mtk_drm_crtc - MediaTek specific crtc structure. diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c index b99a06e6834e..5d39dd54255d 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c @@ -588,7 +588,6 @@ static struct platform_driver mtk_drm_platform_driver = { }; static struct platform_driver * const mtk_drm_drivers[] = { - &mtk_mutex_driver, &mtk_disp_color_driver, &mtk_disp_ovl_driver, &mtk_disp_rdma_driver, diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.h b/drivers/gpu/drm/mediatek/mtk_drm_drv.h index ae366868d01a..e8238fa4aa2a 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.h +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.h @@ -46,7 +46,6 @@ struct mtk_drm_private { struct drm_atomic_state *suspend_state; }; -extern struct platform_driver mtk_mutex_driver; extern struct platform_driver mtk_disp_color_driver; extern struct platform_driver mtk_disp_ovl_driver; extern struct platform_driver mtk_disp_rdma_driver; diff --git a/drivers/gpu/drm/mediatek/mtk_mutex.c b/drivers/gpu/drm/mediatek/mtk_mutex.c deleted file mode 100644 index 66344759e622..000000000000 --- a/drivers/gpu/drm/mediatek/mtk_mutex.c +++ /dev/null @@ -1,463 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (c) 2015 MediaTek Inc. - */ - -#include -#include -#include -#include -#include -#include -#include - -#include "mtk_mutex.h" - -#define MT2701_MUTEX0_MOD0 0x2c -#define MT2701_MUTEX0_SOF0 0x30 - -#define DISP_REG_MUTEX_EN(n) (0x20 + 0x20 * (n)) -#define DISP_REG_MUTEX(n) (0x24 + 0x20 * (n)) -#define DISP_REG_MUTEX_RST(n) (0x28 + 0x20 * (n)) -#define DISP_REG_MUTEX_MOD(mutex_mod_reg, n) (mutex_mod_reg + 0x20 * (n)) -#define DISP_REG_MUTEX_SOF(mutex_sof_reg, n) (mutex_sof_reg + 0x20 * (n)) -#define DISP_REG_MUTEX_MOD2(n) (0x34 + 0x20 * (n)) - -#define INT_MUTEX BIT(1) - -#define MT8167_MUTEX_MOD_DISP_PWM 1 -#define MT8167_MUTEX_MOD_DISP_OVL0 6 -#define MT8167_MUTEX_MOD_DISP_OVL1 7 -#define MT8167_MUTEX_MOD_DISP_RDMA0 8 -#define MT8167_MUTEX_MOD_DISP_RDMA1 9 -#define MT8167_MUTEX_MOD_DISP_WDMA0 10 -#define MT8167_MUTEX_MOD_DISP_CCORR 11 -#define MT8167_MUTEX_MOD_DISP_COLOR 12 -#define MT8167_MUTEX_MOD_DISP_AAL 13 -#define MT8167_MUTEX_MOD_DISP_GAMMA 14 -#define MT8167_MUTEX_MOD_DISP_DITHER 15 -#define MT8167_MUTEX_MOD_DISP_UFOE 16 - -#define MT8173_MUTEX_MOD_DISP_OVL0 11 -#define MT8173_MUTEX_MOD_DISP_OVL1 12 -#define MT8173_MUTEX_MOD_DISP_RDMA0 13 -#define MT8173_MUTEX_MOD_DISP_RDMA1 14 -#define MT8173_MUTEX_MOD_DISP_RDMA2 15 -#define MT8173_MUTEX_MOD_DISP_WDMA0 16 -#define MT8173_MUTEX_MOD_DISP_WDMA1 17 -#define MT8173_MUTEX_MOD_DISP_COLOR0 18 -#define MT8173_MUTEX_MOD_DISP_COLOR1 19 -#define MT8173_MUTEX_MOD_DISP_AAL 20 -#define MT8173_MUTEX_MOD_DISP_GAMMA 21 -#define MT8173_MUTEX_MOD_DISP_UFOE 22 -#define MT8173_MUTEX_MOD_DISP_PWM0 23 -#define MT8173_MUTEX_MOD_DISP_PWM1 24 -#define MT8173_MUTEX_MOD_DISP_OD 25 - -#define MT2712_MUTEX_MOD_DISP_PWM2 10 -#define MT2712_MUTEX_MOD_DISP_OVL0 11 -#define MT2712_MUTEX_MOD_DISP_OVL1 12 -#define MT2712_MUTEX_MOD_DISP_RDMA0 13 -#define MT2712_MUTEX_MOD_DISP_RDMA1 14 -#define MT2712_MUTEX_MOD_DISP_RDMA2 15 -#define MT2712_MUTEX_MOD_DISP_WDMA0 16 -#define MT2712_MUTEX_MOD_DISP_WDMA1 17 -#define MT2712_MUTEX_MOD_DISP_COLOR0 18 -#define MT2712_MUTEX_MOD_DISP_COLOR1 19 -#define MT2712_MUTEX_MOD_DISP_AAL0 20 -#define MT2712_MUTEX_MOD_DISP_UFOE 22 -#define MT2712_MUTEX_MOD_DISP_PWM0 23 -#define MT2712_MUTEX_MOD_DISP_PWM1 24 -#define MT2712_MUTEX_MOD_DISP_OD0 25 -#define MT2712_MUTEX_MOD2_DISP_AAL1 33 -#define MT2712_MUTEX_MOD2_DISP_OD1 34 - -#define MT2701_MUTEX_MOD_DISP_OVL 3 -#define MT2701_MUTEX_MOD_DISP_WDMA 6 -#define MT2701_MUTEX_MOD_DISP_COLOR 7 -#define MT2701_MUTEX_MOD_DISP_BLS 9 -#define MT2701_MUTEX_MOD_DISP_RDMA0 10 -#define MT2701_MUTEX_MOD_DISP_RDMA1 12 - -#define MT2712_MUTEX_SOF_SINGLE_MODE 0 -#define MT2712_MUTEX_SOF_DSI0 1 -#define MT2712_MUTEX_SOF_DSI1 2 -#define MT2712_MUTEX_SOF_DPI0 3 -#define MT2712_MUTEX_SOF_DPI1 4 -#define MT2712_MUTEX_SOF_DSI2 5 -#define MT2712_MUTEX_SOF_DSI3 6 -#define MT8167_MUTEX_SOF_DPI0 2 -#define MT8167_MUTEX_SOF_DPI1 3 - -struct mtk_mutex { - int id; - bool claimed; -}; - -enum mtk_mutex_sof_id { - MUTEX_SOF_SINGLE_MODE, - MUTEX_SOF_DSI0, - MUTEX_SOF_DSI1, - MUTEX_SOF_DPI0, - MUTEX_SOF_DPI1, - MUTEX_SOF_DSI2, - MUTEX_SOF_DSI3, -}; - -struct mtk_mutex_data { - const unsigned int *mutex_mod; - const unsigned int *mutex_sof; - const unsigned int mutex_mod_reg; - const unsigned int mutex_sof_reg; - const bool no_clk; -}; - -struct mtk_mutex_ctx { - struct device *dev; - struct clk *clk; - void __iomem *regs; - struct mtk_mutex mutex[10]; - const struct mtk_mutex_data *data; -}; - -static const unsigned int mt2701_mutex_mod[DDP_COMPONENT_ID_MAX] = { - [DDP_COMPONENT_BLS] = MT2701_MUTEX_MOD_DISP_BLS, - [DDP_COMPONENT_COLOR0] = MT2701_MUTEX_MOD_DISP_COLOR, - [DDP_COMPONENT_OVL0] = MT2701_MUTEX_MOD_DISP_OVL, - [DDP_COMPONENT_RDMA0] = MT2701_MUTEX_MOD_DISP_RDMA0, - [DDP_COMPONENT_RDMA1] = MT2701_MUTEX_MOD_DISP_RDMA1, - [DDP_COMPONENT_WDMA0] = MT2701_MUTEX_MOD_DISP_WDMA, -}; - -static const unsigned int mt2712_mutex_mod[DDP_COMPONENT_ID_MAX] = { - [DDP_COMPONENT_AAL0] = MT2712_MUTEX_MOD_DISP_AAL0, - [DDP_COMPONENT_AAL1] = MT2712_MUTEX_MOD2_DISP_AAL1, - [DDP_COMPONENT_COLOR0] = MT2712_MUTEX_MOD_DISP_COLOR0, - [DDP_COMPONENT_COLOR1] = MT2712_MUTEX_MOD_DISP_COLOR1, - [DDP_COMPONENT_OD0] = MT2712_MUTEX_MOD_DISP_OD0, - [DDP_COMPONENT_OD1] = MT2712_MUTEX_MOD2_DISP_OD1, - [DDP_COMPONENT_OVL0] = MT2712_MUTEX_MOD_DISP_OVL0, - [DDP_COMPONENT_OVL1] = MT2712_MUTEX_MOD_DISP_OVL1, - [DDP_COMPONENT_PWM0] = MT2712_MUTEX_MOD_DISP_PWM0, - [DDP_COMPONENT_PWM1] = MT2712_MUTEX_MOD_DISP_PWM1, - [DDP_COMPONENT_PWM2] = MT2712_MUTEX_MOD_DISP_PWM2, - [DDP_COMPONENT_RDMA0] = MT2712_MUTEX_MOD_DISP_RDMA0, - [DDP_COMPONENT_RDMA1] = MT2712_MUTEX_MOD_DISP_RDMA1, - [DDP_COMPONENT_RDMA2] = MT2712_MUTEX_MOD_DISP_RDMA2, - [DDP_COMPONENT_UFOE] = MT2712_MUTEX_MOD_DISP_UFOE, - [DDP_COMPONENT_WDMA0] = MT2712_MUTEX_MOD_DISP_WDMA0, - [DDP_COMPONENT_WDMA1] = MT2712_MUTEX_MOD_DISP_WDMA1, -}; - -static const unsigned int mt8167_mutex_mod[DDP_COMPONENT_ID_MAX] = { - [DDP_COMPONENT_AAL0] = MT8167_MUTEX_MOD_DISP_AAL, - [DDP_COMPONENT_CCORR] = MT8167_MUTEX_MOD_DISP_CCORR, - [DDP_COMPONENT_COLOR0] = MT8167_MUTEX_MOD_DISP_COLOR, - [DDP_COMPONENT_DITHER] = MT8167_MUTEX_MOD_DISP_DITHER, - [DDP_COMPONENT_GAMMA] = MT8167_MUTEX_MOD_DISP_GAMMA, - [DDP_COMPONENT_OVL0] = MT8167_MUTEX_MOD_DISP_OVL0, - [DDP_COMPONENT_OVL1] = MT8167_MUTEX_MOD_DISP_OVL1, - [DDP_COMPONENT_PWM0] = MT8167_MUTEX_MOD_DISP_PWM, - [DDP_COMPONENT_RDMA0] = MT8167_MUTEX_MOD_DISP_RDMA0, - [DDP_COMPONENT_RDMA1] = MT8167_MUTEX_MOD_DISP_RDMA1, - [DDP_COMPONENT_UFOE] = MT8167_MUTEX_MOD_DISP_UFOE, - [DDP_COMPONENT_WDMA0] = MT8167_MUTEX_MOD_DISP_WDMA0, -}; - -static const unsigned int mt8173_mutex_mod[DDP_COMPONENT_ID_MAX] = { - [DDP_COMPONENT_AAL0] = MT8173_MUTEX_MOD_DISP_AAL, - [DDP_COMPONENT_COLOR0] = MT8173_MUTEX_MOD_DISP_COLOR0, - [DDP_COMPONENT_COLOR1] = MT8173_MUTEX_MOD_DISP_COLOR1, - [DDP_COMPONENT_GAMMA] = MT8173_MUTEX_MOD_DISP_GAMMA, - [DDP_COMPONENT_OD0] = MT8173_MUTEX_MOD_DISP_OD, - [DDP_COMPONENT_OVL0] = MT8173_MUTEX_MOD_DISP_OVL0, - [DDP_COMPONENT_OVL1] = MT8173_MUTEX_MOD_DISP_OVL1, - [DDP_COMPONENT_PWM0] = MT8173_MUTEX_MOD_DISP_PWM0, - [DDP_COMPONENT_PWM1] = MT8173_MUTEX_MOD_DISP_PWM1, - [DDP_COMPONENT_RDMA0] = MT8173_MUTEX_MOD_DISP_RDMA0, - [DDP_COMPONENT_RDMA1] = MT8173_MUTEX_MOD_DISP_RDMA1, - [DDP_COMPONENT_RDMA2] = MT8173_MUTEX_MOD_DISP_RDMA2, - [DDP_COMPONENT_UFOE] = MT8173_MUTEX_MOD_DISP_UFOE, - [DDP_COMPONENT_WDMA0] = MT8173_MUTEX_MOD_DISP_WDMA0, - [DDP_COMPONENT_WDMA1] = MT8173_MUTEX_MOD_DISP_WDMA1, -}; - -static const unsigned int mt2712_mutex_sof[MUTEX_SOF_DSI3 + 1] = { - [MUTEX_SOF_SINGLE_MODE] = MUTEX_SOF_SINGLE_MODE, - [MUTEX_SOF_DSI0] = MUTEX_SOF_DSI0, - [MUTEX_SOF_DSI1] = MUTEX_SOF_DSI1, - [MUTEX_SOF_DPI0] = MUTEX_SOF_DPI0, - [MUTEX_SOF_DPI1] = MUTEX_SOF_DPI1, - [MUTEX_SOF_DSI2] = MUTEX_SOF_DSI2, - [MUTEX_SOF_DSI3] = MUTEX_SOF_DSI3, -}; - -static const unsigned int mt8167_mutex_sof[MUTEX_SOF_DSI3 + 1] = { - [MUTEX_SOF_SINGLE_MODE] = MUTEX_SOF_SINGLE_MODE, - [MUTEX_SOF_DSI0] = MUTEX_SOF_DSI0, - [MUTEX_SOF_DPI0] = MT8167_MUTEX_SOF_DPI0, - [MUTEX_SOF_DPI1] = MT8167_MUTEX_SOF_DPI1, -}; - -static const struct mtk_mutex_data mt2701_mutex_driver_data = { - .mutex_mod = mt2701_mutex_mod, - .mutex_sof = mt2712_mutex_sof, - .mutex_mod_reg = MT2701_MUTEX0_MOD0, - .mutex_sof_reg = MT2701_MUTEX0_SOF0, -}; - -static const struct mtk_mutex_data mt2712_mutex_driver_data = { - .mutex_mod = mt2712_mutex_mod, - .mutex_sof = mt2712_mutex_sof, - .mutex_mod_reg = MT2701_MUTEX0_MOD0, - .mutex_sof_reg = MT2701_MUTEX0_SOF0, -}; - -static const struct mtk_mutex_data mt8167_mutex_driver_data = { - .mutex_mod = mt8167_mutex_mod, - .mutex_sof = mt8167_mutex_sof, - .mutex_mod_reg = MT2701_MUTEX0_MOD0, - .mutex_sof_reg = MT2701_MUTEX0_SOF0, - .no_clk = true, -}; - -static const struct mtk_mutex_data mt8173_mutex_driver_data = { - .mutex_mod = mt8173_mutex_mod, - .mutex_sof = mt2712_mutex_sof, - .mutex_mod_reg = MT2701_MUTEX0_MOD0, - .mutex_sof_reg = MT2701_MUTEX0_SOF0, -}; - -struct mtk_mutex *mtk_mutex_get(struct device *dev) -{ - struct mtk_mutex_ctx *mtx = dev_get_drvdata(dev); - int i; - - for (i = 0; i < 10; i++) - if (!mtx->mutex[i].claimed) { - mtx->mutex[i].claimed = true; - return &mtx->mutex[i]; - } - - return ERR_PTR(-EBUSY); -} - -void mtk_mutex_put(struct mtk_mutex *mutex) -{ - struct mtk_mutex_ctx *mtx = container_of(mutex, struct mtk_mutex_ctx, - mutex[mutex->id]); - - WARN_ON(&mtx->mutex[mutex->id] != mutex); - - mutex->claimed = false; -} - -int mtk_mutex_prepare(struct mtk_mutex *mutex) -{ - struct mtk_mutex_ctx *mtx = container_of(mutex, struct mtk_mutex_ctx, - mutex[mutex->id]); - return clk_prepare_enable(mtx->clk); -} - -void mtk_mutex_unprepare(struct mtk_mutex *mutex) -{ - struct mtk_mutex_ctx *mtx = container_of(mutex, struct mtk_mutex_ctx, - mutex[mutex->id]); - clk_disable_unprepare(mtx->clk); -} - -void mtk_mutex_add_comp(struct mtk_mutex *mutex, - enum mtk_ddp_comp_id id) -{ - struct mtk_mutex_ctx *mtx = container_of(mutex, struct mtk_mutex_ctx, - mutex[mutex->id]); - unsigned int reg; - unsigned int sof_id; - unsigned int offset; - - WARN_ON(&mtx->mutex[mutex->id] != mutex); - - switch (id) { - case DDP_COMPONENT_DSI0: - sof_id = MUTEX_SOF_DSI0; - break; - case DDP_COMPONENT_DSI1: - sof_id = MUTEX_SOF_DSI0; - break; - case DDP_COMPONENT_DSI2: - sof_id = MUTEX_SOF_DSI2; - break; - case DDP_COMPONENT_DSI3: - sof_id = MUTEX_SOF_DSI3; - break; - case DDP_COMPONENT_DPI0: - sof_id = MUTEX_SOF_DPI0; - break; - case DDP_COMPONENT_DPI1: - sof_id = MUTEX_SOF_DPI1; - break; - default: - if (mtx->data->mutex_mod[id] < 32) { - offset = DISP_REG_MUTEX_MOD(mtx->data->mutex_mod_reg, - mutex->id); - reg = readl_relaxed(mtx->regs + offset); - reg |= 1 << mtx->data->mutex_mod[id]; - writel_relaxed(reg, mtx->regs + offset); - } else { - offset = DISP_REG_MUTEX_MOD2(mutex->id); - reg = readl_relaxed(mtx->regs + offset); - reg |= 1 << (mtx->data->mutex_mod[id] - 32); - writel_relaxed(reg, mtx->regs + offset); - } - return; - } - - writel_relaxed(mtx->data->mutex_sof[sof_id], - mtx->regs + - DISP_REG_MUTEX_SOF(mtx->data->mutex_sof_reg, mutex->id)); -} - -void mtk_mutex_remove_comp(struct mtk_mutex *mutex, - enum mtk_ddp_comp_id id) -{ - struct mtk_mutex_ctx *mtx = container_of(mutex, struct mtk_mutex_ctx, - mutex[mutex->id]); - unsigned int reg; - unsigned int offset; - - WARN_ON(&mtx->mutex[mutex->id] != mutex); - - switch (id) { - case DDP_COMPONENT_DSI0: - case DDP_COMPONENT_DSI1: - case DDP_COMPONENT_DSI2: - case DDP_COMPONENT_DSI3: - case DDP_COMPONENT_DPI0: - case DDP_COMPONENT_DPI1: - writel_relaxed(MUTEX_SOF_SINGLE_MODE, - mtx->regs + - DISP_REG_MUTEX_SOF(mtx->data->mutex_sof_reg, - mutex->id)); - break; - default: - if (mtx->data->mutex_mod[id] < 32) { - offset = DISP_REG_MUTEX_MOD(mtx->data->mutex_mod_reg, - mutex->id); - reg = readl_relaxed(mtx->regs + offset); - reg &= ~(1 << mtx->data->mutex_mod[id]); - writel_relaxed(reg, mtx->regs + offset); - } else { - offset = DISP_REG_MUTEX_MOD2(mutex->id); - reg = readl_relaxed(mtx->regs + offset); - reg &= ~(1 << (mtx->data->mutex_mod[id] - 32)); - writel_relaxed(reg, mtx->regs + offset); - } - break; - } -} - -void mtk_mutex_enable(struct mtk_mutex *mutex) -{ - struct mtk_mutex_ctx *mtx = container_of(mutex, struct mtk_mutex_ctx, - mutex[mutex->id]); - - WARN_ON(&mtx->mutex[mutex->id] != mutex); - - writel(1, mtx->regs + DISP_REG_MUTEX_EN(mutex->id)); -} - -void mtk_mutex_disable(struct mtk_mutex *mutex) -{ - struct mtk_mutex_ctx *mtx = container_of(mutex, struct mtk_mutex_ctx, - mutex[mutex->id]); - - WARN_ON(&mtx->mutex[mutex->id] != mutex); - - writel(0, mtx->regs + DISP_REG_MUTEX_EN(mutex->id)); -} - -void mtk_mutex_acquire(struct mtk_mutex *mutex) -{ - struct mtk_mutex_ctx *mtx = container_of(mutex, struct mtk_mutex_ctx, - mutex[mutex->id]); - u32 tmp; - - writel(1, mtx->regs + DISP_REG_MUTEX_EN(mutex->id)); - writel(1, mtx->regs + DISP_REG_MUTEX(mutex->id)); - if (readl_poll_timeout_atomic(mtx->regs + DISP_REG_MUTEX(mutex->id), - tmp, tmp & INT_MUTEX, 1, 10000)) - pr_err("could not acquire mutex %d\n", mutex->id); -} - -void mtk_mutex_release(struct mtk_mutex *mutex) -{ - struct mtk_mutex_ctx *mtx = container_of(mutex, struct mtk_mutex_ctx, - mutex[mutex->id]); - - writel(0, mtx->regs + DISP_REG_MUTEX(mutex->id)); -} - -static int mtk_mutex_probe(struct platform_device *pdev) -{ - struct device *dev = &pdev->dev; - struct mtk_mutex_ctx *mtx; - struct resource *regs; - int i; - - mtx = devm_kzalloc(dev, sizeof(*mtx), GFP_KERNEL); - if (!mtx) - return -ENOMEM; - - for (i = 0; i < 10; i++) - mtx->mutex[i].id = i; - - mtx->data = of_device_get_match_data(dev); - - if (!mtx->data->no_clk) { - mtx->clk = devm_clk_get(dev, NULL); - if (IS_ERR(mtx->clk)) { - if (PTR_ERR(mtx->clk) != -EPROBE_DEFER) - dev_err(dev, "Failed to get clock\n"); - return PTR_ERR(mtx->clk); - } - } - - regs = platform_get_resource(pdev, IORESOURCE_MEM, 0); - mtx->regs = devm_ioremap_resource(dev, regs); - if (IS_ERR(mtx->regs)) { - dev_err(dev, "Failed to map mutex registers\n"); - return PTR_ERR(mtx->regs); - } - - platform_set_drvdata(pdev, mtx); - - return 0; -} - -static int mtk_mutex_remove(struct platform_device *pdev) -{ - return 0; -} - -static const struct of_device_id mutex_driver_dt_match[] = { - { .compatible = "mediatek,mt2701-disp-mutex", - .data = &mt2701_mutex_driver_data}, - { .compatible = "mediatek,mt2712-disp-mutex", - .data = &mt2712_mutex_driver_data}, - { .compatible = "mediatek,mt8167-disp-mutex", - .data = &mt8167_mutex_driver_data}, - { .compatible = "mediatek,mt8173-disp-mutex", - .data = &mt8173_mutex_driver_data}, - {}, -}; -MODULE_DEVICE_TABLE(of, mutex_driver_dt_match); - -struct platform_driver mtk_mutex_driver = { - .probe = mtk_mutex_probe, - .remove = mtk_mutex_remove, - .driver = { - .name = "mediatek-mutex", - .owner = THIS_MODULE, - .of_match_table = mutex_driver_dt_match, - }, -}; diff --git a/drivers/gpu/drm/mediatek/mtk_mutex.h b/drivers/gpu/drm/mediatek/mtk_mutex.h deleted file mode 100644 index 6fe4ffbde290..000000000000 --- a/drivers/gpu/drm/mediatek/mtk_mutex.h +++ /dev/null @@ -1,26 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (c) 2015 MediaTek Inc. - */ - -#ifndef MTK_MUTEX_H -#define MTK_MUTEX_H - -struct regmap; -struct device; -struct mtk_mutex; - -struct mtk_mutex *mtk_mutex_get(struct device *dev); -int mtk_mutex_prepare(struct mtk_mutex *mutex); -void mtk_mutex_add_comp(struct mtk_mutex *mutex, - enum mtk_ddp_comp_id id); -void mtk_mutex_enable(struct mtk_mutex *mutex); -void mtk_mutex_disable(struct mtk_mutex *mutex); -void mtk_mutex_remove_comp(struct mtk_mutex *mutex, - enum mtk_ddp_comp_id id); -void mtk_mutex_unprepare(struct mtk_mutex *mutex); -void mtk_mutex_put(struct mtk_mutex *mutex); -void mtk_mutex_acquire(struct mtk_mutex *mutex); -void mtk_mutex_release(struct mtk_mutex *mutex); - -#endif /* MTK_MUTEX_H */ diff --git a/drivers/soc/mediatek/Makefile b/drivers/soc/mediatek/Makefile index b6908db534c2..90270f8114ed 100644 --- a/drivers/soc/mediatek/Makefile +++ b/drivers/soc/mediatek/Makefile @@ -6,3 +6,4 @@ obj-$(CONFIG_MTK_PMIC_WRAP) += mtk-pmic-wrap.o obj-$(CONFIG_MTK_SCPSYS) += mtk-scpsys.o obj-$(CONFIG_MTK_SCPSYS_PM_DOMAINS) += mtk-pm-domains.o obj-$(CONFIG_MTK_MMSYS) += mtk-mmsys.o +obj-$(CONFIG_MTK_MMSYS) += mtk-mutex.o diff --git a/drivers/soc/mediatek/mtk-mutex.c b/drivers/soc/mediatek/mtk-mutex.c new file mode 100644 index 000000000000..f531b119da7a --- /dev/null +++ b/drivers/soc/mediatek/mtk-mutex.c @@ -0,0 +1,474 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2015 MediaTek Inc. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#define MT2701_MUTEX0_MOD0 0x2c +#define MT2701_MUTEX0_SOF0 0x30 + +#define DISP_REG_MUTEX_EN(n) (0x20 + 0x20 * (n)) +#define DISP_REG_MUTEX(n) (0x24 + 0x20 * (n)) +#define DISP_REG_MUTEX_RST(n) (0x28 + 0x20 * (n)) +#define DISP_REG_MUTEX_MOD(mutex_mod_reg, n) (mutex_mod_reg + 0x20 * (n)) +#define DISP_REG_MUTEX_SOF(mutex_sof_reg, n) (mutex_sof_reg + 0x20 * (n)) +#define DISP_REG_MUTEX_MOD2(n) (0x34 + 0x20 * (n)) + +#define INT_MUTEX BIT(1) + +#define MT8167_MUTEX_MOD_DISP_PWM 1 +#define MT8167_MUTEX_MOD_DISP_OVL0 6 +#define MT8167_MUTEX_MOD_DISP_OVL1 7 +#define MT8167_MUTEX_MOD_DISP_RDMA0 8 +#define MT8167_MUTEX_MOD_DISP_RDMA1 9 +#define MT8167_MUTEX_MOD_DISP_WDMA0 10 +#define MT8167_MUTEX_MOD_DISP_CCORR 11 +#define MT8167_MUTEX_MOD_DISP_COLOR 12 +#define MT8167_MUTEX_MOD_DISP_AAL 13 +#define MT8167_MUTEX_MOD_DISP_GAMMA 14 +#define MT8167_MUTEX_MOD_DISP_DITHER 15 +#define MT8167_MUTEX_MOD_DISP_UFOE 16 + +#define MT8173_MUTEX_MOD_DISP_OVL0 11 +#define MT8173_MUTEX_MOD_DISP_OVL1 12 +#define MT8173_MUTEX_MOD_DISP_RDMA0 13 +#define MT8173_MUTEX_MOD_DISP_RDMA1 14 +#define MT8173_MUTEX_MOD_DISP_RDMA2 15 +#define MT8173_MUTEX_MOD_DISP_WDMA0 16 +#define MT8173_MUTEX_MOD_DISP_WDMA1 17 +#define MT8173_MUTEX_MOD_DISP_COLOR0 18 +#define MT8173_MUTEX_MOD_DISP_COLOR1 19 +#define MT8173_MUTEX_MOD_DISP_AAL 20 +#define MT8173_MUTEX_MOD_DISP_GAMMA 21 +#define MT8173_MUTEX_MOD_DISP_UFOE 22 +#define MT8173_MUTEX_MOD_DISP_PWM0 23 +#define MT8173_MUTEX_MOD_DISP_PWM1 24 +#define MT8173_MUTEX_MOD_DISP_OD 25 + +#define MT2712_MUTEX_MOD_DISP_PWM2 10 +#define MT2712_MUTEX_MOD_DISP_OVL0 11 +#define MT2712_MUTEX_MOD_DISP_OVL1 12 +#define MT2712_MUTEX_MOD_DISP_RDMA0 13 +#define MT2712_MUTEX_MOD_DISP_RDMA1 14 +#define MT2712_MUTEX_MOD_DISP_RDMA2 15 +#define MT2712_MUTEX_MOD_DISP_WDMA0 16 +#define MT2712_MUTEX_MOD_DISP_WDMA1 17 +#define MT2712_MUTEX_MOD_DISP_COLOR0 18 +#define MT2712_MUTEX_MOD_DISP_COLOR1 19 +#define MT2712_MUTEX_MOD_DISP_AAL0 20 +#define MT2712_MUTEX_MOD_DISP_UFOE 22 +#define MT2712_MUTEX_MOD_DISP_PWM0 23 +#define MT2712_MUTEX_MOD_DISP_PWM1 24 +#define MT2712_MUTEX_MOD_DISP_OD0 25 +#define MT2712_MUTEX_MOD2_DISP_AAL1 33 +#define MT2712_MUTEX_MOD2_DISP_OD1 34 + +#define MT2701_MUTEX_MOD_DISP_OVL 3 +#define MT2701_MUTEX_MOD_DISP_WDMA 6 +#define MT2701_MUTEX_MOD_DISP_COLOR 7 +#define MT2701_MUTEX_MOD_DISP_BLS 9 +#define MT2701_MUTEX_MOD_DISP_RDMA0 10 +#define MT2701_MUTEX_MOD_DISP_RDMA1 12 + +#define MT2712_MUTEX_SOF_SINGLE_MODE 0 +#define MT2712_MUTEX_SOF_DSI0 1 +#define MT2712_MUTEX_SOF_DSI1 2 +#define MT2712_MUTEX_SOF_DPI0 3 +#define MT2712_MUTEX_SOF_DPI1 4 +#define MT2712_MUTEX_SOF_DSI2 5 +#define MT2712_MUTEX_SOF_DSI3 6 +#define MT8167_MUTEX_SOF_DPI0 2 +#define MT8167_MUTEX_SOF_DPI1 3 + +struct mtk_mutex { + int id; + bool claimed; +}; + +enum mtk_mutex_sof_id { + MUTEX_SOF_SINGLE_MODE, + MUTEX_SOF_DSI0, + MUTEX_SOF_DSI1, + MUTEX_SOF_DPI0, + MUTEX_SOF_DPI1, + MUTEX_SOF_DSI2, + MUTEX_SOF_DSI3, +}; + +struct mtk_mutex_data { + const unsigned int *mutex_mod; + const unsigned int *mutex_sof; + const unsigned int mutex_mod_reg; + const unsigned int mutex_sof_reg; + const bool no_clk; +}; + +struct mtk_mutex_ctx { + struct device *dev; + struct clk *clk; + void __iomem *regs; + struct mtk_mutex mutex[10]; + const struct mtk_mutex_data *data; +}; + +static const unsigned int mt2701_mutex_mod[DDP_COMPONENT_ID_MAX] = { + [DDP_COMPONENT_BLS] = MT2701_MUTEX_MOD_DISP_BLS, + [DDP_COMPONENT_COLOR0] = MT2701_MUTEX_MOD_DISP_COLOR, + [DDP_COMPONENT_OVL0] = MT2701_MUTEX_MOD_DISP_OVL, + [DDP_COMPONENT_RDMA0] = MT2701_MUTEX_MOD_DISP_RDMA0, + [DDP_COMPONENT_RDMA1] = MT2701_MUTEX_MOD_DISP_RDMA1, + [DDP_COMPONENT_WDMA0] = MT2701_MUTEX_MOD_DISP_WDMA, +}; + +static const unsigned int mt2712_mutex_mod[DDP_COMPONENT_ID_MAX] = { + [DDP_COMPONENT_AAL0] = MT2712_MUTEX_MOD_DISP_AAL0, + [DDP_COMPONENT_AAL1] = MT2712_MUTEX_MOD2_DISP_AAL1, + [DDP_COMPONENT_COLOR0] = MT2712_MUTEX_MOD_DISP_COLOR0, + [DDP_COMPONENT_COLOR1] = MT2712_MUTEX_MOD_DISP_COLOR1, + [DDP_COMPONENT_OD0] = MT2712_MUTEX_MOD_DISP_OD0, + [DDP_COMPONENT_OD1] = MT2712_MUTEX_MOD2_DISP_OD1, + [DDP_COMPONENT_OVL0] = MT2712_MUTEX_MOD_DISP_OVL0, + [DDP_COMPONENT_OVL1] = MT2712_MUTEX_MOD_DISP_OVL1, + [DDP_COMPONENT_PWM0] = MT2712_MUTEX_MOD_DISP_PWM0, + [DDP_COMPONENT_PWM1] = MT2712_MUTEX_MOD_DISP_PWM1, + [DDP_COMPONENT_PWM2] = MT2712_MUTEX_MOD_DISP_PWM2, + [DDP_COMPONENT_RDMA0] = MT2712_MUTEX_MOD_DISP_RDMA0, + [DDP_COMPONENT_RDMA1] = MT2712_MUTEX_MOD_DISP_RDMA1, + [DDP_COMPONENT_RDMA2] = MT2712_MUTEX_MOD_DISP_RDMA2, + [DDP_COMPONENT_UFOE] = MT2712_MUTEX_MOD_DISP_UFOE, + [DDP_COMPONENT_WDMA0] = MT2712_MUTEX_MOD_DISP_WDMA0, + [DDP_COMPONENT_WDMA1] = MT2712_MUTEX_MOD_DISP_WDMA1, +}; + +static const unsigned int mt8167_mutex_mod[DDP_COMPONENT_ID_MAX] = { + [DDP_COMPONENT_AAL0] = MT8167_MUTEX_MOD_DISP_AAL, + [DDP_COMPONENT_CCORR] = MT8167_MUTEX_MOD_DISP_CCORR, + [DDP_COMPONENT_COLOR0] = MT8167_MUTEX_MOD_DISP_COLOR, + [DDP_COMPONENT_DITHER] = MT8167_MUTEX_MOD_DISP_DITHER, + [DDP_COMPONENT_GAMMA] = MT8167_MUTEX_MOD_DISP_GAMMA, + [DDP_COMPONENT_OVL0] = MT8167_MUTEX_MOD_DISP_OVL0, + [DDP_COMPONENT_OVL1] = MT8167_MUTEX_MOD_DISP_OVL1, + [DDP_COMPONENT_PWM0] = MT8167_MUTEX_MOD_DISP_PWM, + [DDP_COMPONENT_RDMA0] = MT8167_MUTEX_MOD_DISP_RDMA0, + [DDP_COMPONENT_RDMA1] = MT8167_MUTEX_MOD_DISP_RDMA1, + [DDP_COMPONENT_UFOE] = MT8167_MUTEX_MOD_DISP_UFOE, + [DDP_COMPONENT_WDMA0] = MT8167_MUTEX_MOD_DISP_WDMA0, +}; + +static const unsigned int mt8173_mutex_mod[DDP_COMPONENT_ID_MAX] = { + [DDP_COMPONENT_AAL0] = MT8173_MUTEX_MOD_DISP_AAL, + [DDP_COMPONENT_COLOR0] = MT8173_MUTEX_MOD_DISP_COLOR0, + [DDP_COMPONENT_COLOR1] = MT8173_MUTEX_MOD_DISP_COLOR1, + [DDP_COMPONENT_GAMMA] = MT8173_MUTEX_MOD_DISP_GAMMA, + [DDP_COMPONENT_OD0] = MT8173_MUTEX_MOD_DISP_OD, + [DDP_COMPONENT_OVL0] = MT8173_MUTEX_MOD_DISP_OVL0, + [DDP_COMPONENT_OVL1] = MT8173_MUTEX_MOD_DISP_OVL1, + [DDP_COMPONENT_PWM0] = MT8173_MUTEX_MOD_DISP_PWM0, + [DDP_COMPONENT_PWM1] = MT8173_MUTEX_MOD_DISP_PWM1, + [DDP_COMPONENT_RDMA0] = MT8173_MUTEX_MOD_DISP_RDMA0, + [DDP_COMPONENT_RDMA1] = MT8173_MUTEX_MOD_DISP_RDMA1, + [DDP_COMPONENT_RDMA2] = MT8173_MUTEX_MOD_DISP_RDMA2, + [DDP_COMPONENT_UFOE] = MT8173_MUTEX_MOD_DISP_UFOE, + [DDP_COMPONENT_WDMA0] = MT8173_MUTEX_MOD_DISP_WDMA0, + [DDP_COMPONENT_WDMA1] = MT8173_MUTEX_MOD_DISP_WDMA1, +}; + +static const unsigned int mt2712_mutex_sof[MUTEX_SOF_DSI3 + 1] = { + [MUTEX_SOF_SINGLE_MODE] = MUTEX_SOF_SINGLE_MODE, + [MUTEX_SOF_DSI0] = MUTEX_SOF_DSI0, + [MUTEX_SOF_DSI1] = MUTEX_SOF_DSI1, + [MUTEX_SOF_DPI0] = MUTEX_SOF_DPI0, + [MUTEX_SOF_DPI1] = MUTEX_SOF_DPI1, + [MUTEX_SOF_DSI2] = MUTEX_SOF_DSI2, + [MUTEX_SOF_DSI3] = MUTEX_SOF_DSI3, +}; + +static const unsigned int mt8167_mutex_sof[MUTEX_SOF_DSI3 + 1] = { + [MUTEX_SOF_SINGLE_MODE] = MUTEX_SOF_SINGLE_MODE, + [MUTEX_SOF_DSI0] = MUTEX_SOF_DSI0, + [MUTEX_SOF_DPI0] = MT8167_MUTEX_SOF_DPI0, + [MUTEX_SOF_DPI1] = MT8167_MUTEX_SOF_DPI1, +}; + +static const struct mtk_mutex_data mt2701_mutex_driver_data = { + .mutex_mod = mt2701_mutex_mod, + .mutex_sof = mt2712_mutex_sof, + .mutex_mod_reg = MT2701_MUTEX0_MOD0, + .mutex_sof_reg = MT2701_MUTEX0_SOF0, +}; + +static const struct mtk_mutex_data mt2712_mutex_driver_data = { + .mutex_mod = mt2712_mutex_mod, + .mutex_sof = mt2712_mutex_sof, + .mutex_mod_reg = MT2701_MUTEX0_MOD0, + .mutex_sof_reg = MT2701_MUTEX0_SOF0, +}; + +static const struct mtk_mutex_data mt8167_mutex_driver_data = { + .mutex_mod = mt8167_mutex_mod, + .mutex_sof = mt8167_mutex_sof, + .mutex_mod_reg = MT2701_MUTEX0_MOD0, + .mutex_sof_reg = MT2701_MUTEX0_SOF0, + .no_clk = true, +}; + +static const struct mtk_mutex_data mt8173_mutex_driver_data = { + .mutex_mod = mt8173_mutex_mod, + .mutex_sof = mt2712_mutex_sof, + .mutex_mod_reg = MT2701_MUTEX0_MOD0, + .mutex_sof_reg = MT2701_MUTEX0_SOF0, +}; + +struct mtk_mutex *mtk_mutex_get(struct device *dev) +{ + struct mtk_mutex_ctx *mtx = dev_get_drvdata(dev); + int i; + + for (i = 0; i < 10; i++) + if (!mtx->mutex[i].claimed) { + mtx->mutex[i].claimed = true; + return &mtx->mutex[i]; + } + + return ERR_PTR(-EBUSY); +} +EXPORT_SYMBOL_GPL(mtk_mutex_get); + +void mtk_mutex_put(struct mtk_mutex *mutex) +{ + struct mtk_mutex_ctx *mtx = container_of(mutex, struct mtk_mutex_ctx, + mutex[mutex->id]); + + WARN_ON(&mtx->mutex[mutex->id] != mutex); + + mutex->claimed = false; +} +EXPORT_SYMBOL_GPL(mtk_mutex_put); + +int mtk_mutex_prepare(struct mtk_mutex *mutex) +{ + struct mtk_mutex_ctx *mtx = container_of(mutex, struct mtk_mutex_ctx, + mutex[mutex->id]); + return clk_prepare_enable(mtx->clk); +} +EXPORT_SYMBOL_GPL(mtk_mutex_prepare); + +void mtk_mutex_unprepare(struct mtk_mutex *mutex) +{ + struct mtk_mutex_ctx *mtx = container_of(mutex, struct mtk_mutex_ctx, + mutex[mutex->id]); + clk_disable_unprepare(mtx->clk); +} +EXPORT_SYMBOL_GPL(mtk_mutex_unprepare); + +void mtk_mutex_add_comp(struct mtk_mutex *mutex, + enum mtk_ddp_comp_id id) +{ + struct mtk_mutex_ctx *mtx = container_of(mutex, struct mtk_mutex_ctx, + mutex[mutex->id]); + unsigned int reg; + unsigned int sof_id; + unsigned int offset; + + WARN_ON(&mtx->mutex[mutex->id] != mutex); + + switch (id) { + case DDP_COMPONENT_DSI0: + sof_id = MUTEX_SOF_DSI0; + break; + case DDP_COMPONENT_DSI1: + sof_id = MUTEX_SOF_DSI0; + break; + case DDP_COMPONENT_DSI2: + sof_id = MUTEX_SOF_DSI2; + break; + case DDP_COMPONENT_DSI3: + sof_id = MUTEX_SOF_DSI3; + break; + case DDP_COMPONENT_DPI0: + sof_id = MUTEX_SOF_DPI0; + break; + case DDP_COMPONENT_DPI1: + sof_id = MUTEX_SOF_DPI1; + break; + default: + if (mtx->data->mutex_mod[id] < 32) { + offset = DISP_REG_MUTEX_MOD(mtx->data->mutex_mod_reg, + mutex->id); + reg = readl_relaxed(mtx->regs + offset); + reg |= 1 << mtx->data->mutex_mod[id]; + writel_relaxed(reg, mtx->regs + offset); + } else { + offset = DISP_REG_MUTEX_MOD2(mutex->id); + reg = readl_relaxed(mtx->regs + offset); + reg |= 1 << (mtx->data->mutex_mod[id] - 32); + writel_relaxed(reg, mtx->regs + offset); + } + return; + } + + writel_relaxed(mtx->data->mutex_sof[sof_id], + mtx->regs + + DISP_REG_MUTEX_SOF(mtx->data->mutex_sof_reg, mutex->id)); +} +EXPORT_SYMBOL_GPL(mtk_mutex_add_comp); + +void mtk_mutex_remove_comp(struct mtk_mutex *mutex, + enum mtk_ddp_comp_id id) +{ + struct mtk_mutex_ctx *mtx = container_of(mutex, struct mtk_mutex_ctx, + mutex[mutex->id]); + unsigned int reg; + unsigned int offset; + + WARN_ON(&mtx->mutex[mutex->id] != mutex); + + switch (id) { + case DDP_COMPONENT_DSI0: + case DDP_COMPONENT_DSI1: + case DDP_COMPONENT_DSI2: + case DDP_COMPONENT_DSI3: + case DDP_COMPONENT_DPI0: + case DDP_COMPONENT_DPI1: + writel_relaxed(MUTEX_SOF_SINGLE_MODE, + mtx->regs + + DISP_REG_MUTEX_SOF(mtx->data->mutex_sof_reg, + mutex->id)); + break; + default: + if (mtx->data->mutex_mod[id] < 32) { + offset = DISP_REG_MUTEX_MOD(mtx->data->mutex_mod_reg, + mutex->id); + reg = readl_relaxed(mtx->regs + offset); + reg &= ~(1 << mtx->data->mutex_mod[id]); + writel_relaxed(reg, mtx->regs + offset); + } else { + offset = DISP_REG_MUTEX_MOD2(mutex->id); + reg = readl_relaxed(mtx->regs + offset); + reg &= ~(1 << (mtx->data->mutex_mod[id] - 32)); + writel_relaxed(reg, mtx->regs + offset); + } + break; + } +} +EXPORT_SYMBOL_GPL(mtk_mutex_remove_comp); + +void mtk_mutex_enable(struct mtk_mutex *mutex) +{ + struct mtk_mutex_ctx *mtx = container_of(mutex, struct mtk_mutex_ctx, + mutex[mutex->id]); + + WARN_ON(&mtx->mutex[mutex->id] != mutex); + + writel(1, mtx->regs + DISP_REG_MUTEX_EN(mutex->id)); +} +EXPORT_SYMBOL_GPL(mtk_mutex_enable); + +void mtk_mutex_disable(struct mtk_mutex *mutex) +{ + struct mtk_mutex_ctx *mtx = container_of(mutex, struct mtk_mutex_ctx, + mutex[mutex->id]); + + WARN_ON(&mtx->mutex[mutex->id] != mutex); + + writel(0, mtx->regs + DISP_REG_MUTEX_EN(mutex->id)); +} +EXPORT_SYMBOL_GPL(mtk_mutex_disable); + +void mtk_mutex_acquire(struct mtk_mutex *mutex) +{ + struct mtk_mutex_ctx *mtx = container_of(mutex, struct mtk_mutex_ctx, + mutex[mutex->id]); + u32 tmp; + + writel(1, mtx->regs + DISP_REG_MUTEX_EN(mutex->id)); + writel(1, mtx->regs + DISP_REG_MUTEX(mutex->id)); + if (readl_poll_timeout_atomic(mtx->regs + DISP_REG_MUTEX(mutex->id), + tmp, tmp & INT_MUTEX, 1, 10000)) + pr_err("could not acquire mutex %d\n", mutex->id); +} +EXPORT_SYMBOL_GPL(mtk_mutex_acquire); + +void mtk_mutex_release(struct mtk_mutex *mutex) +{ + struct mtk_mutex_ctx *mtx = container_of(mutex, struct mtk_mutex_ctx, + mutex[mutex->id]); + + writel(0, mtx->regs + DISP_REG_MUTEX(mutex->id)); +} +EXPORT_SYMBOL_GPL(mtk_mutex_release); + +static int mtk_mutex_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct mtk_mutex_ctx *mtx; + struct resource *regs; + int i; + + mtx = devm_kzalloc(dev, sizeof(*mtx), GFP_KERNEL); + if (!mtx) + return -ENOMEM; + + for (i = 0; i < 10; i++) + mtx->mutex[i].id = i; + + mtx->data = of_device_get_match_data(dev); + + if (!mtx->data->no_clk) { + mtx->clk = devm_clk_get(dev, NULL); + if (IS_ERR(mtx->clk)) { + if (PTR_ERR(mtx->clk) != -EPROBE_DEFER) + dev_err(dev, "Failed to get clock\n"); + return PTR_ERR(mtx->clk); + } + } + + regs = platform_get_resource(pdev, IORESOURCE_MEM, 0); + mtx->regs = devm_ioremap_resource(dev, regs); + if (IS_ERR(mtx->regs)) { + dev_err(dev, "Failed to map mutex registers\n"); + return PTR_ERR(mtx->regs); + } + + platform_set_drvdata(pdev, mtx); + + return 0; +} + +static int mtk_mutex_remove(struct platform_device *pdev) +{ + return 0; +} + +static const struct of_device_id mutex_driver_dt_match[] = { + { .compatible = "mediatek,mt2701-disp-mutex", + .data = &mt2701_mutex_driver_data}, + { .compatible = "mediatek,mt2712-disp-mutex", + .data = &mt2712_mutex_driver_data}, + { .compatible = "mediatek,mt8167-disp-mutex", + .data = &mt8167_mutex_driver_data}, + { .compatible = "mediatek,mt8173-disp-mutex", + .data = &mt8173_mutex_driver_data}, + {}, +}; +MODULE_DEVICE_TABLE(of, mutex_driver_dt_match); + +struct platform_driver mtk_mutex_driver = { + .probe = mtk_mutex_probe, + .remove = mtk_mutex_remove, + .driver = { + .name = "mediatek-mutex", + .owner = THIS_MODULE, + .of_match_table = mutex_driver_dt_match, + }, +}; + +builtin_platform_driver(mtk_mutex_driver); diff --git a/include/linux/soc/mediatek/mtk-mutex.h b/include/linux/soc/mediatek/mtk-mutex.h new file mode 100644 index 000000000000..6fe4ffbde290 --- /dev/null +++ b/include/linux/soc/mediatek/mtk-mutex.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2015 MediaTek Inc. + */ + +#ifndef MTK_MUTEX_H +#define MTK_MUTEX_H + +struct regmap; +struct device; +struct mtk_mutex; + +struct mtk_mutex *mtk_mutex_get(struct device *dev); +int mtk_mutex_prepare(struct mtk_mutex *mutex); +void mtk_mutex_add_comp(struct mtk_mutex *mutex, + enum mtk_ddp_comp_id id); +void mtk_mutex_enable(struct mtk_mutex *mutex); +void mtk_mutex_disable(struct mtk_mutex *mutex); +void mtk_mutex_remove_comp(struct mtk_mutex *mutex, + enum mtk_ddp_comp_id id); +void mtk_mutex_unprepare(struct mtk_mutex *mutex); +void mtk_mutex_put(struct mtk_mutex *mutex); +void mtk_mutex_acquire(struct mtk_mutex *mutex); +void mtk_mutex_release(struct mtk_mutex *mutex); + +#endif /* MTK_MUTEX_H */ -- cgit v1.2.3 From 6e736c60a9fe905b3e4f4b07171a31ad602d56d2 Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Mon, 1 Feb 2021 11:13:25 -0700 Subject: coresight: Introduce device access abstraction We are about to introduce support for sysreg access to ETMv4.4+ component. Since there are generic routines that access the registers (e.g, CS_LOCK/UNLOCK , claim/disclaim operations, timeout) and in order to preserve the logic of these operations at a single place we introduce an abstraction layer for the accesses to a given device. Link: https://lore.kernel.org/r/20210110224850.1880240-4-suzuki.poulose@arm.com Cc: Mike Leach Signed-off-by: Suzuki K Poulose Signed-off-by: Mathieu Poirier Link: https://lore.kernel.org/r/20210201181351.1475223-6-mathieu.poirier@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/coresight/coresight-catu.c | 1 + drivers/hwtracing/coresight/coresight-core.c | 43 +++++ drivers/hwtracing/coresight/coresight-cti-core.c | 1 + drivers/hwtracing/coresight/coresight-etb10.c | 1 + drivers/hwtracing/coresight/coresight-etm3x-core.c | 1 + drivers/hwtracing/coresight/coresight-etm4x-core.c | 1 + drivers/hwtracing/coresight/coresight-funnel.c | 1 + drivers/hwtracing/coresight/coresight-replicator.c | 1 + drivers/hwtracing/coresight/coresight-stm.c | 1 + drivers/hwtracing/coresight/coresight-tmc-core.c | 1 + drivers/hwtracing/coresight/coresight-tpiu.c | 1 + include/linux/coresight.h | 191 ++++++++++++++++++++- 12 files changed, 241 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/hwtracing/coresight/coresight-catu.c b/drivers/hwtracing/coresight/coresight-catu.c index a61313f320bd..867c932c7b26 100644 --- a/drivers/hwtracing/coresight/coresight-catu.c +++ b/drivers/hwtracing/coresight/coresight-catu.c @@ -551,6 +551,7 @@ static int catu_probe(struct amba_device *adev, const struct amba_id *id) dev->platform_data = pdata; drvdata->base = base; + catu_desc.access = CSDEV_ACCESS_IOMEM(base); catu_desc.pdata = pdata; catu_desc.dev = dev; catu_desc.groups = catu_groups; diff --git a/drivers/hwtracing/coresight/coresight-core.c b/drivers/hwtracing/coresight/coresight-core.c index 4ba801dffcb7..a38af8f0831b 100644 --- a/drivers/hwtracing/coresight/coresight-core.c +++ b/drivers/hwtracing/coresight/coresight-core.c @@ -1458,6 +1458,48 @@ int coresight_timeout(void __iomem *addr, u32 offset, int position, int value) } EXPORT_SYMBOL_GPL(coresight_timeout); +u32 coresight_relaxed_read32(struct coresight_device *csdev, u32 offset) +{ + return csdev_access_relaxed_read32(&csdev->access, offset); +} + +u32 coresight_read32(struct coresight_device *csdev, u32 offset) +{ + return csdev_access_read32(&csdev->access, offset); +} + +void coresight_relaxed_write32(struct coresight_device *csdev, + u32 val, u32 offset) +{ + csdev_access_relaxed_write32(&csdev->access, val, offset); +} + +void coresight_write32(struct coresight_device *csdev, u32 val, u32 offset) +{ + csdev_access_write32(&csdev->access, val, offset); +} + +u64 coresight_relaxed_read64(struct coresight_device *csdev, u32 offset) +{ + return csdev_access_relaxed_read64(&csdev->access, offset); +} + +u64 coresight_read64(struct coresight_device *csdev, u32 offset) +{ + return csdev_access_read64(&csdev->access, offset); +} + +void coresight_relaxed_write64(struct coresight_device *csdev, + u64 val, u32 offset) +{ + csdev_access_relaxed_write64(&csdev->access, val, offset); +} + +void coresight_write64(struct coresight_device *csdev, u64 val, u32 offset) +{ + csdev_access_write64(&csdev->access, val, offset); +} + /* * coresight_release_platform_data: Release references to the devices connected * to the output port of this device. @@ -1522,6 +1564,7 @@ struct coresight_device *coresight_register(struct coresight_desc *desc) csdev->type = desc->type; csdev->subtype = desc->subtype; csdev->ops = desc->ops; + csdev->access = desc->access; csdev->orphan = false; csdev->dev.type = &coresight_dev_type[desc->type]; diff --git a/drivers/hwtracing/coresight/coresight-cti-core.c b/drivers/hwtracing/coresight/coresight-cti-core.c index 61dbc1afd8da..b38a8db5f252 100644 --- a/drivers/hwtracing/coresight/coresight-cti-core.c +++ b/drivers/hwtracing/coresight/coresight-cti-core.c @@ -870,6 +870,7 @@ static int cti_probe(struct amba_device *adev, const struct amba_id *id) return PTR_ERR(base); drvdata->base = base; + cti_desc.access = CSDEV_ACCESS_IOMEM(base); dev_set_drvdata(dev, drvdata); diff --git a/drivers/hwtracing/coresight/coresight-etb10.c b/drivers/hwtracing/coresight/coresight-etb10.c index 0cf6f0b947b6..cc742561a986 100644 --- a/drivers/hwtracing/coresight/coresight-etb10.c +++ b/drivers/hwtracing/coresight/coresight-etb10.c @@ -757,6 +757,7 @@ static int etb_probe(struct amba_device *adev, const struct amba_id *id) return PTR_ERR(base); drvdata->base = base; + desc.access = CSDEV_ACCESS_IOMEM(base); spin_lock_init(&drvdata->spinlock); diff --git a/drivers/hwtracing/coresight/coresight-etm3x-core.c b/drivers/hwtracing/coresight/coresight-etm3x-core.c index 5bf5a5a4ce6d..3b7837cbe376 100644 --- a/drivers/hwtracing/coresight/coresight-etm3x-core.c +++ b/drivers/hwtracing/coresight/coresight-etm3x-core.c @@ -839,6 +839,7 @@ static int etm_probe(struct amba_device *adev, const struct amba_id *id) return PTR_ERR(base); drvdata->base = base; + desc.access = CSDEV_ACCESS_IOMEM(base); spin_lock_init(&drvdata->spinlock); diff --git a/drivers/hwtracing/coresight/coresight-etm4x-core.c b/drivers/hwtracing/coresight/coresight-etm4x-core.c index 0924c376e35a..b9e01357ffad 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x-core.c +++ b/drivers/hwtracing/coresight/coresight-etm4x-core.c @@ -1626,6 +1626,7 @@ static int etm4_probe(struct amba_device *adev, const struct amba_id *id) return PTR_ERR(base); drvdata->base = base; + desc.access = CSDEV_ACCESS_IOMEM(base); spin_lock_init(&drvdata->spinlock); diff --git a/drivers/hwtracing/coresight/coresight-funnel.c b/drivers/hwtracing/coresight/coresight-funnel.c index 071c723227db..8f7c40d7d8d6 100644 --- a/drivers/hwtracing/coresight/coresight-funnel.c +++ b/drivers/hwtracing/coresight/coresight-funnel.c @@ -242,6 +242,7 @@ static int funnel_probe(struct device *dev, struct resource *res) } drvdata->base = base; desc.groups = coresight_funnel_groups; + desc.access = CSDEV_ACCESS_IOMEM(base); } dev_set_drvdata(dev, drvdata); diff --git a/drivers/hwtracing/coresight/coresight-replicator.c b/drivers/hwtracing/coresight/coresight-replicator.c index 7e2a2b7f503f..205756fab729 100644 --- a/drivers/hwtracing/coresight/coresight-replicator.c +++ b/drivers/hwtracing/coresight/coresight-replicator.c @@ -254,6 +254,7 @@ static int replicator_probe(struct device *dev, struct resource *res) } drvdata->base = base; desc.groups = replicator_groups; + desc.access = CSDEV_ACCESS_IOMEM(base); } if (fwnode_property_present(dev_fwnode(dev), diff --git a/drivers/hwtracing/coresight/coresight-stm.c b/drivers/hwtracing/coresight/coresight-stm.c index 99791773f682..41d9a922c2d4 100644 --- a/drivers/hwtracing/coresight/coresight-stm.c +++ b/drivers/hwtracing/coresight/coresight-stm.c @@ -884,6 +884,7 @@ static int stm_probe(struct amba_device *adev, const struct amba_id *id) if (IS_ERR(base)) return PTR_ERR(base); drvdata->base = base; + desc.access = CSDEV_ACCESS_IOMEM(base); ret = stm_get_stimulus_area(dev, &ch_res); if (ret) diff --git a/drivers/hwtracing/coresight/coresight-tmc-core.c b/drivers/hwtracing/coresight/coresight-tmc-core.c index 8169dff5a9f6..e61b75be66b6 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-core.c +++ b/drivers/hwtracing/coresight/coresight-tmc-core.c @@ -456,6 +456,7 @@ static int tmc_probe(struct amba_device *adev, const struct amba_id *id) } drvdata->base = base; + desc.access = CSDEV_ACCESS_IOMEM(base); spin_lock_init(&drvdata->spinlock); diff --git a/drivers/hwtracing/coresight/coresight-tpiu.c b/drivers/hwtracing/coresight/coresight-tpiu.c index d5dfee9ee556..6ca396799883 100644 --- a/drivers/hwtracing/coresight/coresight-tpiu.c +++ b/drivers/hwtracing/coresight/coresight-tpiu.c @@ -149,6 +149,7 @@ static int tpiu_probe(struct amba_device *adev, const struct amba_id *id) return PTR_ERR(base); drvdata->base = base; + desc.access = CSDEV_ACCESS_IOMEM(base); /* Disable tpiu to support older devices */ tpiu_disable_hw(drvdata); diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 7d3c87e5b97c..6107cf4021d3 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -7,6 +7,7 @@ #define _LINUX_CORESIGHT_H #include +#include #include #include @@ -114,6 +115,32 @@ struct coresight_platform_data { struct coresight_connection *conns; }; +/** + * struct csdev_access - Abstraction of a CoreSight device access. + * + * @io_mem : True if the device has memory mapped I/O + * @base : When io_mem == true, base address of the component + * @read : Read from the given "offset" of the given instance. + * @write : Write "val" to the given "offset". + */ +struct csdev_access { + bool io_mem; + union { + void __iomem *base; + struct { + u64 (*read)(u32 offset, bool relaxed, bool _64bit); + void (*write)(u64 val, u32 offset, bool relaxed, + bool _64bit); + }; + }; +}; + +#define CSDEV_ACCESS_IOMEM(_addr) \ + ((struct csdev_access) { \ + .io_mem = true, \ + .base = (_addr), \ + }) + /** * struct coresight_desc - description of a component required from drivers * @type: as defined by @coresight_dev_type. @@ -125,6 +152,7 @@ struct coresight_platform_data { * @groups: operations specific to this component. These will end up * in the component's sysfs sub-directory. * @name: name for the coresight device, also shown under sysfs. + * @access: Describe access to the device */ struct coresight_desc { enum coresight_dev_type type; @@ -134,6 +162,7 @@ struct coresight_desc { struct device *dev; const struct attribute_group **groups; const char *name; + struct csdev_access access; }; /** @@ -173,7 +202,8 @@ struct coresight_sysfs_link { * @type: as defined by @coresight_dev_type. * @subtype: as defined by @coresight_dev_subtype. * @ops: generic operations for this component, as defined - by @coresight_ops. + * by @coresight_ops. + * @access: Device i/o access abstraction for this device. * @dev: The device entity associated to this component. * @refcnt: keep track of what is in use. * @orphan: true if the component has connections that haven't been linked. @@ -195,6 +225,7 @@ struct coresight_device { enum coresight_dev_type type; union coresight_dev_subtype subtype; const struct coresight_ops *ops; + struct csdev_access access; struct device dev; atomic_t *refcnt; bool orphan; @@ -326,6 +357,104 @@ struct coresight_ops { }; #if IS_ENABLED(CONFIG_CORESIGHT) + +static inline u32 csdev_access_relaxed_read32(struct csdev_access *csa, + u32 offset) +{ + if (likely(csa->io_mem)) + return readl_relaxed(csa->base + offset); + + return csa->read(offset, true, false); +} + +static inline u32 csdev_access_read32(struct csdev_access *csa, u32 offset) +{ + if (likely(csa->io_mem)) + return readl(csa->base + offset); + + return csa->read(offset, false, false); +} + +static inline void csdev_access_relaxed_write32(struct csdev_access *csa, + u32 val, u32 offset) +{ + if (likely(csa->io_mem)) + writel_relaxed(val, csa->base + offset); + else + csa->write(val, offset, true, false); +} + +static inline void csdev_access_write32(struct csdev_access *csa, u32 val, u32 offset) +{ + if (likely(csa->io_mem)) + writel(val, csa->base + offset); + else + csa->write(val, offset, false, false); +} + +#ifdef CONFIG_64BIT + +static inline u64 csdev_access_relaxed_read64(struct csdev_access *csa, + u32 offset) +{ + if (likely(csa->io_mem)) + return readq_relaxed(csa->base + offset); + + return csa->read(offset, true, true); +} + +static inline u64 csdev_access_read64(struct csdev_access *csa, u32 offset) +{ + if (likely(csa->io_mem)) + return readq(csa->base + offset); + + return csa->read(offset, false, true); +} + +static inline void csdev_access_relaxed_write64(struct csdev_access *csa, + u64 val, u32 offset) +{ + if (likely(csa->io_mem)) + writeq_relaxed(val, csa->base + offset); + else + csa->write(val, offset, true, true); +} + +static inline void csdev_access_write64(struct csdev_access *csa, u64 val, u32 offset) +{ + if (likely(csa->io_mem)) + writeq(val, csa->base + offset); + else + csa->write(val, offset, false, true); +} + +#else /* !CONFIG_64BIT */ + +static inline u64 csdev_access_relaxed_read64(struct csdev_access *csa, + u32 offset) +{ + WARN_ON(1); + return 0; +} + +static inline u64 csdev_access_read64(struct csdev_access *csa, u32 offset) +{ + WARN_ON(1); + return 0; +} + +static inline void csdev_access_relaxed_write64(struct csdev_access *csa, + u64 val, u32 offset) +{ + WARN_ON(1); +} + +static inline void csdev_access_write64(struct csdev_access *csa, u64 val, u32 offset) +{ + WARN_ON(1); +} +#endif /* CONFIG_64BIT */ + extern struct coresight_device * coresight_register(struct coresight_desc *desc); extern void coresight_unregister(struct coresight_device *csdev); @@ -343,6 +472,18 @@ extern char *coresight_alloc_device_name(struct coresight_dev_list *devs, struct device *dev); extern bool coresight_loses_context_with_cpu(struct device *dev); + +u32 coresight_relaxed_read32(struct coresight_device *csdev, u32 offset); +u32 coresight_read32(struct coresight_device *csdev, u32 offset); +void coresight_write32(struct coresight_device *csdev, u32 val, u32 offset); +void coresight_relaxed_write32(struct coresight_device *csdev, + u32 val, u32 offset); +u64 coresight_relaxed_read64(struct coresight_device *csdev, u32 offset); +u64 coresight_read64(struct coresight_device *csdev, u32 offset); +void coresight_relaxed_write64(struct coresight_device *csdev, + u64 val, u32 offset); +void coresight_write64(struct coresight_device *csdev, u64 val, u32 offset); + #else static inline struct coresight_device * coresight_register(struct coresight_desc *desc) { return NULL; } @@ -369,10 +510,54 @@ static inline bool coresight_loses_context_with_cpu(struct device *dev) { return false; } -#endif + +static inline u32 coresight_relaxed_read32(struct coresight_device *csdev, u32 offset) +{ + WARN_ON_ONCE(1); + return 0; +} + +static inline u32 coresight_read32(struct coresight_device *csdev, u32 offset) +{ + WARN_ON_ONCE(1); + return 0; +} + +static inline void coresight_write32(struct coresight_device *csdev, u32 val, u32 offset) +{ +} + +static inline void coresight_relaxed_write32(struct coresight_device *csdev, + u32 val, u32 offset) +{ +} + +static inline u64 coresight_relaxed_read64(struct coresight_device *csdev, + u32 offset) +{ + WARN_ON_ONCE(1); + return 0; +} + +static inline u64 coresight_read64(struct coresight_device *csdev, u32 offset) +{ + WARN_ON_ONCE(1); + return 0; +} + +static inline void coresight_relaxed_write64(struct coresight_device *csdev, + u64 val, u32 offset) +{ +} + +static inline void coresight_write64(struct coresight_device *csdev, u64 val, u32 offset) +{ +} + +#endif /* IS_ENABLED(CONFIG_CORESIGHT) */ extern int coresight_get_cpu(struct device *dev); struct coresight_platform_data *coresight_get_platform_data(struct device *dev); -#endif +#endif /* _LINUX_COREISGHT_H */ -- cgit v1.2.3 From 020052825e49128d381d6444d1ce079e8ca82386 Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Mon, 1 Feb 2021 11:13:27 -0700 Subject: coresight: Convert coresight_timeout to use access abstraction Convert the generic routines to use the new access abstraction layer gradually, starting with coresigth_timeout. Link: https://lore.kernel.org/r/20210110224850.1880240-6-suzuki.poulose@arm.com Cc: Mike Leach Signed-off-by: Suzuki K Poulose Signed-off-by: Mathieu Poirier Link: https://lore.kernel.org/r/20210201181351.1475223-8-mathieu.poirier@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/coresight/coresight-catu.c | 5 ++-- drivers/hwtracing/coresight/coresight-core.c | 13 +++++----- drivers/hwtracing/coresight/coresight-etb10.c | 5 ++-- drivers/hwtracing/coresight/coresight-etm4x-core.c | 30 ++++++++++++++-------- drivers/hwtracing/coresight/coresight-stm.c | 3 ++- drivers/hwtracing/coresight/coresight-tmc-core.c | 15 ++++++----- drivers/hwtracing/coresight/coresight-tpiu.c | 4 +-- include/linux/coresight.h | 11 +++++--- 8 files changed, 54 insertions(+), 32 deletions(-) (limited to 'include') diff --git a/drivers/hwtracing/coresight/coresight-catu.c b/drivers/hwtracing/coresight/coresight-catu.c index 867c932c7b26..d6097454d399 100644 --- a/drivers/hwtracing/coresight/coresight-catu.c +++ b/drivers/hwtracing/coresight/coresight-catu.c @@ -401,8 +401,9 @@ static const struct attribute_group *catu_groups[] = { static inline int catu_wait_for_ready(struct catu_drvdata *drvdata) { - return coresight_timeout(drvdata->base, - CATU_STATUS, CATU_STATUS_READY, 1); + struct csdev_access *csa = &drvdata->csdev->access; + + return coresight_timeout(csa, CATU_STATUS, CATU_STATUS_READY, 1); } static int catu_enable_hw(struct catu_drvdata *drvdata, void *data) diff --git a/drivers/hwtracing/coresight/coresight-core.c b/drivers/hwtracing/coresight/coresight-core.c index a38af8f0831b..74985068f325 100644 --- a/drivers/hwtracing/coresight/coresight-core.c +++ b/drivers/hwtracing/coresight/coresight-core.c @@ -1418,23 +1418,24 @@ static void coresight_remove_conns(struct coresight_device *csdev) } /** - * coresight_timeout - loop until a bit has changed to a specific state. - * @addr: base address of the area of interest. - * @offset: address of a register, starting from @addr. + * coresight_timeout - loop until a bit has changed to a specific register + * state. + * @csa: coresight device access for the device + * @offset: Offset of the register from the base of the device. * @position: the position of the bit of interest. * @value: the value the bit should have. * * Return: 0 as soon as the bit has taken the desired state or -EAGAIN if * TIMEOUT_US has elapsed, which ever happens first. */ - -int coresight_timeout(void __iomem *addr, u32 offset, int position, int value) +int coresight_timeout(struct csdev_access *csa, u32 offset, + int position, int value) { int i; u32 val; for (i = TIMEOUT_US; i > 0; i--) { - val = __raw_readl(addr + offset); + val = csdev_access_read32(csa, offset); /* waiting on the bit to go from 0 to 1 */ if (value) { if (val & BIT(position)) diff --git a/drivers/hwtracing/coresight/coresight-etb10.c b/drivers/hwtracing/coresight/coresight-etb10.c index cc742561a986..0f664aeeda93 100644 --- a/drivers/hwtracing/coresight/coresight-etb10.c +++ b/drivers/hwtracing/coresight/coresight-etb10.c @@ -252,6 +252,7 @@ static void __etb_disable_hw(struct etb_drvdata *drvdata) { u32 ffcr; struct device *dev = &drvdata->csdev->dev; + struct csdev_access *csa = &drvdata->csdev->access; CS_UNLOCK(drvdata->base); @@ -263,7 +264,7 @@ static void __etb_disable_hw(struct etb_drvdata *drvdata) ffcr |= ETB_FFCR_FON_MAN; writel_relaxed(ffcr, drvdata->base + ETB_FFCR); - if (coresight_timeout(drvdata->base, ETB_FFCR, ETB_FFCR_BIT, 0)) { + if (coresight_timeout(csa, ETB_FFCR, ETB_FFCR_BIT, 0)) { dev_err(dev, "timeout while waiting for completion of Manual Flush\n"); } @@ -271,7 +272,7 @@ static void __etb_disable_hw(struct etb_drvdata *drvdata) /* disable trace capture */ writel_relaxed(0x0, drvdata->base + ETB_CTL_REG); - if (coresight_timeout(drvdata->base, ETB_FFSR, ETB_FFSR_BIT, 1)) { + if (coresight_timeout(csa, ETB_FFSR, ETB_FFSR_BIT, 1)) { dev_err(dev, "timeout while waiting for Formatter to Stop\n"); } diff --git a/drivers/hwtracing/coresight/coresight-etm4x-core.c b/drivers/hwtracing/coresight/coresight-etm4x-core.c index b9e01357ffad..180bb6ed9090 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x-core.c +++ b/drivers/hwtracing/coresight/coresight-etm4x-core.c @@ -217,7 +217,9 @@ static int etm4_enable_hw(struct etmv4_drvdata *drvdata) { int i, rc; struct etmv4_config *config = &drvdata->config; - struct device *etm_dev = &drvdata->csdev->dev; + struct coresight_device *csdev = drvdata->csdev; + struct device *etm_dev = &csdev->dev; + struct csdev_access *csa = &csdev->access; CS_UNLOCK(drvdata->base); etm4_enable_arch_specific(drvdata); @@ -232,7 +234,7 @@ static int etm4_enable_hw(struct etmv4_drvdata *drvdata) writel_relaxed(0, drvdata->base + TRCPRGCTLR); /* wait for TRCSTATR.IDLE to go up */ - if (coresight_timeout(drvdata->base, TRCSTATR, TRCSTATR_IDLE_BIT, 1)) + if (coresight_timeout(csa, TRCSTATR, TRCSTATR_IDLE_BIT, 1)) dev_err(etm_dev, "timeout while waiting for Idle Trace Status\n"); if (drvdata->nr_pe) @@ -323,7 +325,7 @@ static int etm4_enable_hw(struct etmv4_drvdata *drvdata) writel_relaxed(1, drvdata->base + TRCPRGCTLR); /* wait for TRCSTATR.IDLE to go back down to '0' */ - if (coresight_timeout(drvdata->base, TRCSTATR, TRCSTATR_IDLE_BIT, 0)) + if (coresight_timeout(csa, TRCSTATR, TRCSTATR_IDLE_BIT, 0)) dev_err(etm_dev, "timeout while waiting for Idle Trace Status\n"); @@ -587,7 +589,9 @@ static void etm4_disable_hw(void *info) u32 control; struct etmv4_drvdata *drvdata = info; struct etmv4_config *config = &drvdata->config; - struct device *etm_dev = &drvdata->csdev->dev; + struct coresight_device *csdev = drvdata->csdev; + struct device *etm_dev = &csdev->dev; + struct csdev_access *csa = &csdev->access; int i; CS_UNLOCK(drvdata->base); @@ -615,8 +619,7 @@ static void etm4_disable_hw(void *info) writel_relaxed(control, drvdata->base + TRCPRGCTLR); /* wait for TRCSTATR.PMSTABLE to go to '1' */ - if (coresight_timeout(drvdata->base, TRCSTATR, - TRCSTATR_PMSTABLE_BIT, 1)) + if (coresight_timeout(csa, TRCSTATR, TRCSTATR_PMSTABLE_BIT, 1)) dev_err(etm_dev, "timeout while waiting for PM stable Trace Status\n"); @@ -1272,7 +1275,15 @@ static int etm4_cpu_save(struct etmv4_drvdata *drvdata) { int i, ret = 0; struct etmv4_save_state *state; - struct device *etm_dev = &drvdata->csdev->dev; + struct coresight_device *csdev = drvdata->csdev; + struct csdev_access *csa; + struct device *etm_dev; + + if (WARN_ON(!csdev)) + return -ENODEV; + + etm_dev = &csdev->dev; + csa = &csdev->access; /* * As recommended by 3.4.1 ("The procedure when powering down the PE") @@ -1287,8 +1298,7 @@ static int etm4_cpu_save(struct etmv4_drvdata *drvdata) etm4_os_lock(drvdata); /* wait for TRCSTATR.PMSTABLE to go up */ - if (coresight_timeout(drvdata->base, TRCSTATR, - TRCSTATR_PMSTABLE_BIT, 1)) { + if (coresight_timeout(csa, TRCSTATR, TRCSTATR_PMSTABLE_BIT, 1)) { dev_err(etm_dev, "timeout while waiting for PM Stable Status\n"); etm4_os_unlock(drvdata); @@ -1377,7 +1387,7 @@ static int etm4_cpu_save(struct etmv4_drvdata *drvdata) state->trcpdcr = readl(drvdata->base + TRCPDCR); /* wait for TRCSTATR.IDLE to go up */ - if (coresight_timeout(drvdata->base, TRCSTATR, TRCSTATR_IDLE_BIT, 1)) { + if (coresight_timeout(csa, TRCSTATR, TRCSTATR_IDLE_BIT, 1)) { dev_err(etm_dev, "timeout while waiting for Idle Trace Status\n"); etm4_os_unlock(drvdata); diff --git a/drivers/hwtracing/coresight/coresight-stm.c b/drivers/hwtracing/coresight/coresight-stm.c index 41d9a922c2d4..5927316d7a03 100644 --- a/drivers/hwtracing/coresight/coresight-stm.c +++ b/drivers/hwtracing/coresight/coresight-stm.c @@ -258,6 +258,7 @@ static void stm_disable(struct coresight_device *csdev, struct perf_event *event) { struct stm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + struct csdev_access *csa = &csdev->access; /* * For as long as the tracer isn't disabled another entity can't @@ -270,7 +271,7 @@ static void stm_disable(struct coresight_device *csdev, spin_unlock(&drvdata->spinlock); /* Wait until the engine has completely stopped */ - coresight_timeout(drvdata->base, STMTCSR, STMTCSR_BUSY_BIT, 0); + coresight_timeout(csa, STMTCSR, STMTCSR_BUSY_BIT, 0); pm_runtime_put(csdev->dev.parent); diff --git a/drivers/hwtracing/coresight/coresight-tmc-core.c b/drivers/hwtracing/coresight/coresight-tmc-core.c index e61b75be66b6..4dc1ea2c19b5 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-core.c +++ b/drivers/hwtracing/coresight/coresight-tmc-core.c @@ -33,16 +33,20 @@ DEFINE_CORESIGHT_DEVLIST(etr_devs, "tmc_etr"); void tmc_wait_for_tmcready(struct tmc_drvdata *drvdata) { + struct coresight_device *csdev = drvdata->csdev; + struct csdev_access *csa = &csdev->access; + /* Ensure formatter, unformatter and hardware fifo are empty */ - if (coresight_timeout(drvdata->base, - TMC_STS, TMC_STS_TMCREADY_BIT, 1)) { - dev_err(&drvdata->csdev->dev, + if (coresight_timeout(csa, TMC_STS, TMC_STS_TMCREADY_BIT, 1)) { + dev_err(&csdev->dev, "timeout while waiting for TMC to be Ready\n"); } } void tmc_flush_and_stop(struct tmc_drvdata *drvdata) { + struct coresight_device *csdev = drvdata->csdev; + struct csdev_access *csa = &csdev->access; u32 ffcr; ffcr = readl_relaxed(drvdata->base + TMC_FFCR); @@ -51,9 +55,8 @@ void tmc_flush_and_stop(struct tmc_drvdata *drvdata) ffcr |= BIT(TMC_FFCR_FLUSHMAN_BIT); writel_relaxed(ffcr, drvdata->base + TMC_FFCR); /* Ensure flush completes */ - if (coresight_timeout(drvdata->base, - TMC_FFCR, TMC_FFCR_FLUSHMAN_BIT, 0)) { - dev_err(&drvdata->csdev->dev, + if (coresight_timeout(csa, TMC_FFCR, TMC_FFCR_FLUSHMAN_BIT, 0)) { + dev_err(&csdev->dev, "timeout while waiting for completion of Manual Flush\n"); } diff --git a/drivers/hwtracing/coresight/coresight-tpiu.c b/drivers/hwtracing/coresight/coresight-tpiu.c index a12b6ee0a576..2ec057892799 100644 --- a/drivers/hwtracing/coresight/coresight-tpiu.c +++ b/drivers/hwtracing/coresight/coresight-tpiu.c @@ -86,9 +86,9 @@ static void tpiu_disable_hw(struct csdev_access *csa) /* Generate manual flush */ csdev_access_relaxed_write32(csa, FFCR_STOP_FI | FFCR_FON_MAN, TPIU_FFCR); /* Wait for flush to complete */ - coresight_timeout(csa->base, TPIU_FFCR, FFCR_FON_MAN_BIT, 0); + coresight_timeout(csa, TPIU_FFCR, FFCR_FON_MAN_BIT, 0); /* Wait for formatter to stop */ - coresight_timeout(csa->base, TPIU_FFSR, FFSR_FT_STOPPED_BIT, 1); + coresight_timeout(csa, TPIU_FFSR, FFSR_FT_STOPPED_BIT, 1); CS_LOCK(csa->base); } diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 6107cf4021d3..18bc7f9fb041 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -460,7 +460,7 @@ coresight_register(struct coresight_desc *desc); extern void coresight_unregister(struct coresight_device *csdev); extern int coresight_enable(struct coresight_device *csdev); extern void coresight_disable(struct coresight_device *csdev); -extern int coresight_timeout(void __iomem *addr, u32 offset, +extern int coresight_timeout(struct csdev_access *csa, u32 offset, int position, int value); extern int coresight_claim_device(void __iomem *base); @@ -491,8 +491,13 @@ static inline void coresight_unregister(struct coresight_device *csdev) {} static inline int coresight_enable(struct coresight_device *csdev) { return -ENOSYS; } static inline void coresight_disable(struct coresight_device *csdev) {} -static inline int coresight_timeout(void __iomem *addr, u32 offset, - int position, int value) { return 1; } + +static inline int coresight_timeout(struct csdev_access *csa, u32 offset, + int position, int value) +{ + return 1; +} + static inline int coresight_claim_device_unlocked(void __iomem *base) { return -EINVAL; -- cgit v1.2.3 From 8ce0029658ba16c52670e869b9ccde02ae7dec6b Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Mon, 1 Feb 2021 11:13:28 -0700 Subject: coresight: Convert claim/disclaim operations to use access wrappers Convert the generic CLAIM tag management APIs to use the device access layer abstraction. Link: https://lore.kernel.org/r/20210110224850.1880240-7-suzuki.poulose@arm.com Cc: Mike Leach Signed-off-by: Suzuki K Poulose Signed-off-by: Mathieu Poirier Link: https://lore.kernel.org/r/20210201181351.1475223-9-mathieu.poirier@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/coresight/coresight-catu.c | 6 +- drivers/hwtracing/coresight/coresight-core.c | 66 +++++++++++++--------- drivers/hwtracing/coresight/coresight-cti-core.c | 17 +++--- drivers/hwtracing/coresight/coresight-etb10.c | 4 +- drivers/hwtracing/coresight/coresight-etm3x-core.c | 8 ++- drivers/hwtracing/coresight/coresight-etm4x-core.c | 4 +- drivers/hwtracing/coresight/coresight-funnel.c | 6 +- drivers/hwtracing/coresight/coresight-replicator.c | 12 ++-- drivers/hwtracing/coresight/coresight-tmc-etf.c | 10 ++-- drivers/hwtracing/coresight/coresight-tmc-etr.c | 4 +- include/linux/coresight.h | 16 +++--- 11 files changed, 91 insertions(+), 62 deletions(-) (limited to 'include') diff --git a/drivers/hwtracing/coresight/coresight-catu.c b/drivers/hwtracing/coresight/coresight-catu.c index d6097454d399..9a0b9ce4a7da 100644 --- a/drivers/hwtracing/coresight/coresight-catu.c +++ b/drivers/hwtracing/coresight/coresight-catu.c @@ -412,6 +412,7 @@ static int catu_enable_hw(struct catu_drvdata *drvdata, void *data) u32 control, mode; struct etr_buf *etr_buf = data; struct device *dev = &drvdata->csdev->dev; + struct coresight_device *csdev = drvdata->csdev; if (catu_wait_for_ready(drvdata)) dev_warn(dev, "Timeout while waiting for READY\n"); @@ -422,7 +423,7 @@ static int catu_enable_hw(struct catu_drvdata *drvdata, void *data) return -EBUSY; } - rc = coresight_claim_device_unlocked(drvdata->base); + rc = coresight_claim_device_unlocked(csdev); if (rc) return rc; @@ -466,9 +467,10 @@ static int catu_disable_hw(struct catu_drvdata *drvdata) { int rc = 0; struct device *dev = &drvdata->csdev->dev; + struct coresight_device *csdev = drvdata->csdev; catu_write_control(drvdata, 0); - coresight_disclaim_device_unlocked(drvdata->base); + coresight_disclaim_device_unlocked(csdev); if (catu_wait_for_ready(drvdata)) { dev_info(dev, "Timeout while waiting for READY\n"); rc = -EAGAIN; diff --git a/drivers/hwtracing/coresight/coresight-core.c b/drivers/hwtracing/coresight/coresight-core.c index 74985068f325..0062c8935653 100644 --- a/drivers/hwtracing/coresight/coresight-core.c +++ b/drivers/hwtracing/coresight/coresight-core.c @@ -145,30 +145,32 @@ static int coresight_find_link_outport(struct coresight_device *csdev, return -ENODEV; } -static inline u32 coresight_read_claim_tags(void __iomem *base) +static inline u32 coresight_read_claim_tags(struct coresight_device *csdev) { - return readl_relaxed(base + CORESIGHT_CLAIMCLR); + return csdev_access_relaxed_read32(&csdev->access, CORESIGHT_CLAIMCLR); } -static inline bool coresight_is_claimed_self_hosted(void __iomem *base) +static inline bool coresight_is_claimed_self_hosted(struct coresight_device *csdev) { - return coresight_read_claim_tags(base) == CORESIGHT_CLAIM_SELF_HOSTED; + return coresight_read_claim_tags(csdev) == CORESIGHT_CLAIM_SELF_HOSTED; } -static inline bool coresight_is_claimed_any(void __iomem *base) +static inline bool coresight_is_claimed_any(struct coresight_device *csdev) { - return coresight_read_claim_tags(base) != 0; + return coresight_read_claim_tags(csdev) != 0; } -static inline void coresight_set_claim_tags(void __iomem *base) +static inline void coresight_set_claim_tags(struct coresight_device *csdev) { - writel_relaxed(CORESIGHT_CLAIM_SELF_HOSTED, base + CORESIGHT_CLAIMSET); + csdev_access_relaxed_write32(&csdev->access, CORESIGHT_CLAIM_SELF_HOSTED, + CORESIGHT_CLAIMSET); isb(); } -static inline void coresight_clear_claim_tags(void __iomem *base) +static inline void coresight_clear_claim_tags(struct coresight_device *csdev) { - writel_relaxed(CORESIGHT_CLAIM_SELF_HOSTED, base + CORESIGHT_CLAIMCLR); + csdev_access_relaxed_write32(&csdev->access, CORESIGHT_CLAIM_SELF_HOSTED, + CORESIGHT_CLAIMCLR); isb(); } @@ -182,27 +184,33 @@ static inline void coresight_clear_claim_tags(void __iomem *base) * Called with CS_UNLOCKed for the component. * Returns : 0 on success */ -int coresight_claim_device_unlocked(void __iomem *base) +int coresight_claim_device_unlocked(struct coresight_device *csdev) { - if (coresight_is_claimed_any(base)) + if (WARN_ON(!csdev)) + return -EINVAL; + + if (coresight_is_claimed_any(csdev)) return -EBUSY; - coresight_set_claim_tags(base); - if (coresight_is_claimed_self_hosted(base)) + coresight_set_claim_tags(csdev); + if (coresight_is_claimed_self_hosted(csdev)) return 0; /* There was a race setting the tags, clean up and fail */ - coresight_clear_claim_tags(base); + coresight_clear_claim_tags(csdev); return -EBUSY; } EXPORT_SYMBOL_GPL(coresight_claim_device_unlocked); -int coresight_claim_device(void __iomem *base) +int coresight_claim_device(struct coresight_device *csdev) { int rc; - CS_UNLOCK(base); - rc = coresight_claim_device_unlocked(base); - CS_LOCK(base); + if (WARN_ON(!csdev)) + return -EINVAL; + + CS_UNLOCK(csdev->access.base); + rc = coresight_claim_device_unlocked(csdev); + CS_LOCK(csdev->access.base); return rc; } @@ -212,11 +220,14 @@ EXPORT_SYMBOL_GPL(coresight_claim_device); * coresight_disclaim_device_unlocked : Clear the claim tags for the device. * Called with CS_UNLOCKed for the component. */ -void coresight_disclaim_device_unlocked(void __iomem *base) +void coresight_disclaim_device_unlocked(struct coresight_device *csdev) { - if (coresight_is_claimed_self_hosted(base)) - coresight_clear_claim_tags(base); + if (WARN_ON(!csdev)) + return; + + if (coresight_is_claimed_self_hosted(csdev)) + coresight_clear_claim_tags(csdev); else /* * The external agent may have not honoured our claim @@ -227,11 +238,14 @@ void coresight_disclaim_device_unlocked(void __iomem *base) } EXPORT_SYMBOL_GPL(coresight_disclaim_device_unlocked); -void coresight_disclaim_device(void __iomem *base) +void coresight_disclaim_device(struct coresight_device *csdev) { - CS_UNLOCK(base); - coresight_disclaim_device_unlocked(base); - CS_LOCK(base); + if (WARN_ON(!csdev)) + return; + + CS_UNLOCK(csdev->access.base); + coresight_disclaim_device_unlocked(csdev); + CS_LOCK(csdev->access.base); } EXPORT_SYMBOL_GPL(coresight_disclaim_device); diff --git a/drivers/hwtracing/coresight/coresight-cti-core.c b/drivers/hwtracing/coresight/coresight-cti-core.c index b38a8db5f252..0c81eb9603ae 100644 --- a/drivers/hwtracing/coresight/coresight-cti-core.c +++ b/drivers/hwtracing/coresight/coresight-cti-core.c @@ -102,7 +102,7 @@ static int cti_enable_hw(struct cti_drvdata *drvdata) goto cti_state_unchanged; /* claim the device */ - rc = coresight_claim_device(drvdata->base); + rc = coresight_claim_device(drvdata->csdev); if (rc) goto cti_err_not_enabled; @@ -136,7 +136,7 @@ static void cti_cpuhp_enable_hw(struct cti_drvdata *drvdata) goto cti_hp_not_enabled; /* try to claim the device */ - if (coresight_claim_device(drvdata->base)) + if (coresight_claim_device(drvdata->csdev)) goto cti_hp_not_enabled; cti_write_all_hw_regs(drvdata); @@ -154,6 +154,7 @@ static int cti_disable_hw(struct cti_drvdata *drvdata) { struct cti_config *config = &drvdata->config; struct device *dev = &drvdata->csdev->dev; + struct coresight_device *csdev = drvdata->csdev; spin_lock(&drvdata->spinlock); @@ -171,7 +172,7 @@ static int cti_disable_hw(struct cti_drvdata *drvdata) writel_relaxed(0, drvdata->base + CTICONTROL); config->hw_enabled = false; - coresight_disclaim_device_unlocked(drvdata->base); + coresight_disclaim_device_unlocked(csdev); CS_LOCK(drvdata->base); spin_unlock(&drvdata->spinlock); pm_runtime_put(dev); @@ -655,6 +656,7 @@ static int cti_cpu_pm_notify(struct notifier_block *nb, unsigned long cmd, void *v) { struct cti_drvdata *drvdata; + struct coresight_device *csdev; unsigned int cpu = smp_processor_id(); int notify_res = NOTIFY_OK; @@ -662,6 +664,7 @@ static int cti_cpu_pm_notify(struct notifier_block *nb, unsigned long cmd, return NOTIFY_OK; drvdata = cti_cpu_drvdata[cpu]; + csdev = drvdata->csdev; if (WARN_ON_ONCE(drvdata->ctidev.cpu != cpu)) return NOTIFY_BAD; @@ -673,13 +676,13 @@ static int cti_cpu_pm_notify(struct notifier_block *nb, unsigned long cmd, /* CTI regs all static - we have a copy & nothing to save */ drvdata->config.hw_powered = false; if (drvdata->config.hw_enabled) - coresight_disclaim_device(drvdata->base); + coresight_disclaim_device(csdev); break; case CPU_PM_ENTER_FAILED: drvdata->config.hw_powered = true; if (drvdata->config.hw_enabled) { - if (coresight_claim_device(drvdata->base)) + if (coresight_claim_device(csdev)) drvdata->config.hw_enabled = false; } break; @@ -692,7 +695,7 @@ static int cti_cpu_pm_notify(struct notifier_block *nb, unsigned long cmd, /* check enable reference count to enable HW */ if (atomic_read(&drvdata->config.enable_req_count)) { /* check we can claim the device as we re-power */ - if (coresight_claim_device(drvdata->base)) + if (coresight_claim_device(csdev)) goto cti_notify_exit; drvdata->config.hw_enabled = true; @@ -736,7 +739,7 @@ static int cti_dying_cpu(unsigned int cpu) spin_lock(&drvdata->spinlock); drvdata->config.hw_powered = false; if (drvdata->config.hw_enabled) - coresight_disclaim_device(drvdata->base); + coresight_disclaim_device(drvdata->csdev); spin_unlock(&drvdata->spinlock); return 0; } diff --git a/drivers/hwtracing/coresight/coresight-etb10.c b/drivers/hwtracing/coresight/coresight-etb10.c index 0f664aeeda93..74922c94f4b1 100644 --- a/drivers/hwtracing/coresight/coresight-etb10.c +++ b/drivers/hwtracing/coresight/coresight-etb10.c @@ -132,7 +132,7 @@ static void __etb_enable_hw(struct etb_drvdata *drvdata) static int etb_enable_hw(struct etb_drvdata *drvdata) { - int rc = coresight_claim_device(drvdata->base); + int rc = coresight_claim_device(drvdata->csdev); if (rc) return rc; @@ -345,7 +345,7 @@ static void etb_disable_hw(struct etb_drvdata *drvdata) { __etb_disable_hw(drvdata); etb_dump_hw(drvdata); - coresight_disclaim_device(drvdata->base); + coresight_disclaim_device(drvdata->csdev); } static int etb_disable(struct coresight_device *csdev) diff --git a/drivers/hwtracing/coresight/coresight-etm3x-core.c b/drivers/hwtracing/coresight/coresight-etm3x-core.c index 3b7837cbe376..29d4dba4bee9 100644 --- a/drivers/hwtracing/coresight/coresight-etm3x-core.c +++ b/drivers/hwtracing/coresight/coresight-etm3x-core.c @@ -358,10 +358,11 @@ static int etm_enable_hw(struct etm_drvdata *drvdata) int i, rc; u32 etmcr; struct etm_config *config = &drvdata->config; + struct coresight_device *csdev = drvdata->csdev; CS_UNLOCK(drvdata->base); - rc = coresight_claim_device_unlocked(drvdata->base); + rc = coresight_claim_device_unlocked(csdev); if (rc) goto done; @@ -566,6 +567,7 @@ static void etm_disable_hw(void *info) int i; struct etm_drvdata *drvdata = info; struct etm_config *config = &drvdata->config; + struct coresight_device *csdev = drvdata->csdev; CS_UNLOCK(drvdata->base); etm_set_prog(drvdata); @@ -577,7 +579,7 @@ static void etm_disable_hw(void *info) config->cntr_val[i] = etm_readl(drvdata, ETMCNTVRn(i)); etm_set_pwrdwn(drvdata); - coresight_disclaim_device_unlocked(drvdata->base); + coresight_disclaim_device_unlocked(csdev); CS_LOCK(drvdata->base); @@ -602,7 +604,7 @@ static void etm_disable_perf(struct coresight_device *csdev) * power down the tracer. */ etm_set_pwrdwn(drvdata); - coresight_disclaim_device_unlocked(drvdata->base); + coresight_disclaim_device_unlocked(csdev); CS_LOCK(drvdata->base); } diff --git a/drivers/hwtracing/coresight/coresight-etm4x-core.c b/drivers/hwtracing/coresight/coresight-etm4x-core.c index 180bb6ed9090..a041ad52737f 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x-core.c +++ b/drivers/hwtracing/coresight/coresight-etm4x-core.c @@ -226,7 +226,7 @@ static int etm4_enable_hw(struct etmv4_drvdata *drvdata) etm4_os_unlock(drvdata); - rc = coresight_claim_device_unlocked(drvdata->base); + rc = coresight_claim_device_unlocked(csdev); if (rc) goto done; @@ -635,7 +635,7 @@ static void etm4_disable_hw(void *info) readl_relaxed(drvdata->base + TRCCNTVRn(i)); } - coresight_disclaim_device_unlocked(drvdata->base); + coresight_disclaim_device_unlocked(csdev); CS_LOCK(drvdata->base); diff --git a/drivers/hwtracing/coresight/coresight-funnel.c b/drivers/hwtracing/coresight/coresight-funnel.c index 8f7c40d7d8d6..38bebdddcbff 100644 --- a/drivers/hwtracing/coresight/coresight-funnel.c +++ b/drivers/hwtracing/coresight/coresight-funnel.c @@ -52,13 +52,14 @@ static int dynamic_funnel_enable_hw(struct funnel_drvdata *drvdata, int port) { u32 functl; int rc = 0; + struct coresight_device *csdev = drvdata->csdev; CS_UNLOCK(drvdata->base); functl = readl_relaxed(drvdata->base + FUNNEL_FUNCTL); /* Claim the device only when we enable the first slave */ if (!(functl & FUNNEL_ENSx_MASK)) { - rc = coresight_claim_device_unlocked(drvdata->base); + rc = coresight_claim_device_unlocked(csdev); if (rc) goto done; } @@ -101,6 +102,7 @@ static void dynamic_funnel_disable_hw(struct funnel_drvdata *drvdata, int inport) { u32 functl; + struct coresight_device *csdev = drvdata->csdev; CS_UNLOCK(drvdata->base); @@ -110,7 +112,7 @@ static void dynamic_funnel_disable_hw(struct funnel_drvdata *drvdata, /* Disclaim the device if none of the slaves are now active */ if (!(functl & FUNNEL_ENSx_MASK)) - coresight_disclaim_device_unlocked(drvdata->base); + coresight_disclaim_device_unlocked(csdev); CS_LOCK(drvdata->base); } diff --git a/drivers/hwtracing/coresight/coresight-replicator.c b/drivers/hwtracing/coresight/coresight-replicator.c index 205756fab729..a73fea9185b6 100644 --- a/drivers/hwtracing/coresight/coresight-replicator.c +++ b/drivers/hwtracing/coresight/coresight-replicator.c @@ -45,12 +45,14 @@ struct replicator_drvdata { static void dynamic_replicator_reset(struct replicator_drvdata *drvdata) { + struct coresight_device *csdev = drvdata->csdev; + CS_UNLOCK(drvdata->base); - if (!coresight_claim_device_unlocked(drvdata->base)) { + if (!coresight_claim_device_unlocked(csdev)) { writel_relaxed(0xff, drvdata->base + REPLICATOR_IDFILTER0); writel_relaxed(0xff, drvdata->base + REPLICATOR_IDFILTER1); - coresight_disclaim_device_unlocked(drvdata->base); + coresight_disclaim_device_unlocked(csdev); } CS_LOCK(drvdata->base); @@ -70,6 +72,7 @@ static int dynamic_replicator_enable(struct replicator_drvdata *drvdata, { int rc = 0; u32 id0val, id1val; + struct coresight_device *csdev = drvdata->csdev; CS_UNLOCK(drvdata->base); @@ -84,7 +87,7 @@ static int dynamic_replicator_enable(struct replicator_drvdata *drvdata, id0val = id1val = 0xff; if (id0val == 0xff && id1val == 0xff) - rc = coresight_claim_device_unlocked(drvdata->base); + rc = coresight_claim_device_unlocked(csdev); if (!rc) { switch (outport) { @@ -140,6 +143,7 @@ static void dynamic_replicator_disable(struct replicator_drvdata *drvdata, int inport, int outport) { u32 reg; + struct coresight_device *csdev = drvdata->csdev; switch (outport) { case 0: @@ -160,7 +164,7 @@ static void dynamic_replicator_disable(struct replicator_drvdata *drvdata, if ((readl_relaxed(drvdata->base + REPLICATOR_IDFILTER0) == 0xff) && (readl_relaxed(drvdata->base + REPLICATOR_IDFILTER1) == 0xff)) - coresight_disclaim_device_unlocked(drvdata->base); + coresight_disclaim_device_unlocked(csdev); CS_LOCK(drvdata->base); } diff --git a/drivers/hwtracing/coresight/coresight-tmc-etf.c b/drivers/hwtracing/coresight/coresight-tmc-etf.c index 989d965f3d90..45b85edfc690 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etf.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etf.c @@ -37,7 +37,7 @@ static void __tmc_etb_enable_hw(struct tmc_drvdata *drvdata) static int tmc_etb_enable_hw(struct tmc_drvdata *drvdata) { - int rc = coresight_claim_device(drvdata->base); + int rc = coresight_claim_device(drvdata->csdev); if (rc) return rc; @@ -88,7 +88,7 @@ static void __tmc_etb_disable_hw(struct tmc_drvdata *drvdata) static void tmc_etb_disable_hw(struct tmc_drvdata *drvdata) { __tmc_etb_disable_hw(drvdata); - coresight_disclaim_device(drvdata->base); + coresight_disclaim_device(drvdata->csdev); } static void __tmc_etf_enable_hw(struct tmc_drvdata *drvdata) @@ -109,7 +109,7 @@ static void __tmc_etf_enable_hw(struct tmc_drvdata *drvdata) static int tmc_etf_enable_hw(struct tmc_drvdata *drvdata) { - int rc = coresight_claim_device(drvdata->base); + int rc = coresight_claim_device(drvdata->csdev); if (rc) return rc; @@ -120,11 +120,13 @@ static int tmc_etf_enable_hw(struct tmc_drvdata *drvdata) static void tmc_etf_disable_hw(struct tmc_drvdata *drvdata) { + struct coresight_device *csdev = drvdata->csdev; + CS_UNLOCK(drvdata->base); tmc_flush_and_stop(drvdata); tmc_disable_hw(drvdata); - coresight_disclaim_device_unlocked(drvdata->base); + coresight_disclaim_device_unlocked(csdev); CS_LOCK(drvdata->base); } diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c index bf5230e39c5b..acdb59e0e661 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etr.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c @@ -1040,7 +1040,7 @@ static int tmc_etr_enable_hw(struct tmc_drvdata *drvdata, rc = tmc_etr_enable_catu(drvdata, etr_buf); if (rc) return rc; - rc = coresight_claim_device(drvdata->base); + rc = coresight_claim_device(drvdata->csdev); if (!rc) { drvdata->etr_buf = etr_buf; __tmc_etr_enable_hw(drvdata); @@ -1134,7 +1134,7 @@ void tmc_etr_disable_hw(struct tmc_drvdata *drvdata) __tmc_etr_disable_hw(drvdata); /* Disable CATU device if this ETR is connected to one */ tmc_etr_disable_catu(drvdata); - coresight_disclaim_device(drvdata->base); + coresight_disclaim_device(drvdata->csdev); /* Reset the ETR buf used by hardware */ drvdata->etr_buf = NULL; } diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 18bc7f9fb041..976ec2697610 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -463,11 +463,11 @@ extern void coresight_disable(struct coresight_device *csdev); extern int coresight_timeout(struct csdev_access *csa, u32 offset, int position, int value); -extern int coresight_claim_device(void __iomem *base); -extern int coresight_claim_device_unlocked(void __iomem *base); +extern int coresight_claim_device(struct coresight_device *csdev); +extern int coresight_claim_device_unlocked(struct coresight_device *csdev); -extern void coresight_disclaim_device(void __iomem *base); -extern void coresight_disclaim_device_unlocked(void __iomem *base); +extern void coresight_disclaim_device(struct coresight_device *csdev); +extern void coresight_disclaim_device_unlocked(struct coresight_device *csdev); extern char *coresight_alloc_device_name(struct coresight_dev_list *devs, struct device *dev); @@ -498,18 +498,18 @@ static inline int coresight_timeout(struct csdev_access *csa, u32 offset, return 1; } -static inline int coresight_claim_device_unlocked(void __iomem *base) +static inline int coresight_claim_device_unlocked(struct coresight_device *csdev) { return -EINVAL; } -static inline int coresight_claim_device(void __iomem *base) +static inline int coresight_claim_device(struct coresight_device *csdev) { return -EINVAL; } -static inline void coresight_disclaim_device(void __iomem *base) {} -static inline void coresight_disclaim_device_unlocked(void __iomem *base) {} +static inline void coresight_disclaim_device(struct coresight_device *csdev) {} +static inline void coresight_disclaim_device_unlocked(struct coresight_device *csdev) {} static inline bool coresight_loses_context_with_cpu(struct device *dev) { -- cgit v1.2.3 From 3ce60f443b143e649aa26cd3f668d645434647ac Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Wed, 3 Feb 2021 15:01:29 +0200 Subject: IB/mlx5: Move mlx5_port_caps from mlx5_core_dev to mlx5_ib_dev mlx5_port_caps are RDMA specific capabilities. These are not used by the mlx5_core_device at all. Move them to mlx5_ib_dev where it is used and reduce the scope of it to multiple drivers. Link: https://lore.kernel.org/r/20210203130133.4057329-2-leon@kernel.org Signed-off-by: Parav Pandit Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/mlx5/mad.c | 8 ++++---- drivers/infiniband/hw/mlx5/main.c | 14 ++++++-------- drivers/infiniband/hw/mlx5/mlx5_ib.h | 8 ++++++++ drivers/infiniband/hw/mlx5/qp.c | 6 +++--- drivers/infiniband/hw/mlx5/wr.c | 2 +- include/linux/mlx5/driver.h | 8 -------- 6 files changed, 22 insertions(+), 24 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/hw/mlx5/mad.c b/drivers/infiniband/hw/mlx5/mad.c index 53dec6063245..e9d0a5269582 100644 --- a/drivers/infiniband/hw/mlx5/mad.c +++ b/drivers/infiniband/hw/mlx5/mad.c @@ -48,7 +48,7 @@ static bool can_do_mad_ifc(struct mlx5_ib_dev *dev, u8 port_num, if (in_mad->mad_hdr.mgmt_class != IB_MGMT_CLASS_SUBN_LID_ROUTED && in_mad->mad_hdr.mgmt_class != IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE) return true; - return dev->mdev->port_caps[port_num - 1].has_smi; + return dev->port_caps[port_num - 1].has_smi; } static int mlx5_MAD_IFC(struct mlx5_ib_dev *dev, int ignore_mkey, @@ -299,7 +299,7 @@ int mlx5_query_ext_port_caps(struct mlx5_ib_dev *dev, u8 port) packet_error = be16_to_cpu(out_mad->status); - dev->mdev->port_caps[port - 1].ext_port_cap = (!err && !packet_error) ? + dev->port_caps[port - 1].ext_port_cap = (!err && !packet_error) ? MLX_EXT_PORT_CAP_FLAG_EXTENDED_PORT_INFO : 0; out: @@ -549,7 +549,7 @@ int mlx5_query_mad_ifc_port(struct ib_device *ibdev, u8 port, props->port_cap_flags = be32_to_cpup((__be32 *)(out_mad->data + 20)); props->gid_tbl_len = out_mad->data[50]; props->max_msg_sz = 1 << MLX5_CAP_GEN(mdev, log_max_msg); - props->pkey_tbl_len = mdev->port_caps[port - 1].pkey_table_len; + props->pkey_tbl_len = dev->port_caps[port - 1].pkey_table_len; props->bad_pkey_cntr = be16_to_cpup((__be16 *)(out_mad->data + 46)); props->qkey_viol_cntr = be16_to_cpup((__be16 *)(out_mad->data + 48)); props->active_width = out_mad->data[31] & 0xf; @@ -589,7 +589,7 @@ int mlx5_query_mad_ifc_port(struct ib_device *ibdev, u8 port, /* If reported active speed is QDR, check if is FDR-10 */ if (props->active_speed == 4) { - if (mdev->port_caps[port - 1].ext_port_cap & + if (dev->port_caps[port - 1].ext_port_cap & MLX_EXT_PORT_CAP_FLAG_EXTENDED_PORT_INFO) { init_query_mad(in_mad); in_mad->attr_id = MLX5_ATTR_EXTENDED_PORT_INFO; diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 40fb86db3376..d2f185ae2b9c 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -2946,8 +2946,8 @@ static int set_has_smi_cap(struct mlx5_ib_dev *dev) int err; int port; - for (port = 1; port <= ARRAY_SIZE(dev->mdev->port_caps); port++) { - dev->mdev->port_caps[port - 1].has_smi = false; + for (port = 1; port <= ARRAY_SIZE(dev->port_caps); port++) { + dev->port_caps[port - 1].has_smi = false; if (MLX5_CAP_GEN(dev->mdev, port_type) == MLX5_CAP_PORT_TYPE_IB) { if (MLX5_CAP_GEN(dev->mdev, ib_virt)) { @@ -2959,10 +2959,10 @@ static int set_has_smi_cap(struct mlx5_ib_dev *dev) port, err); return err; } - dev->mdev->port_caps[port - 1].has_smi = + dev->port_caps[port - 1].has_smi = vport_ctx.has_smi; } else { - dev->mdev->port_caps[port - 1].has_smi = true; + dev->port_caps[port - 1].has_smi = true; } } } @@ -3004,10 +3004,8 @@ static int __get_port_caps(struct mlx5_ib_dev *dev, u8 port) goto out; } - dev->mdev->port_caps[port - 1].pkey_table_len = - dprops->max_pkeys; - dev->mdev->port_caps[port - 1].gid_table_len = - pprops->gid_tbl_len; + dev->port_caps[port - 1].pkey_table_len = dprops->max_pkeys; + dev->port_caps[port - 1].gid_table_len = pprops->gid_tbl_len; mlx5_ib_dbg(dev, "port %d: pkey_table_len %d, gid_table_len %d\n", port, dprops->max_pkeys, pprops->gid_tbl_len); diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index 2fd2927abe45..c2f91c15b973 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -1036,6 +1036,13 @@ struct mlx5_var_table { u64 num_var_hw_entries; }; +struct mlx5_port_caps { + int gid_table_len; + int pkey_table_len; + bool has_smi; + u8 ext_port_cap; +}; + struct mlx5_ib_dev { struct ib_device ib_dev; struct mlx5_core_dev *mdev; @@ -1096,6 +1103,7 @@ struct mlx5_ib_dev { struct mlx5_var_table var_table; struct xarray sig_mrs; + struct mlx5_port_caps port_caps[MLX5_MAX_PORTS]; }; static inline struct mlx5_ib_cq *to_mibcq(struct mlx5_core_cq *mcq) diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index 88be94215708..5274349dd998 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -3177,10 +3177,10 @@ static int mlx5_set_path(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, if (ah_flags & IB_AH_GRH) { if (grh->sgid_index >= - dev->mdev->port_caps[port - 1].gid_table_len) { + dev->port_caps[port - 1].gid_table_len) { pr_err("sgid_index (%u) too large. max is %d\n", grh->sgid_index, - dev->mdev->port_caps[port - 1].gid_table_len); + dev->port_caps[port - 1].gid_table_len); return -EINVAL; } } @@ -4311,7 +4311,7 @@ int mlx5_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, if (attr_mask & IB_QP_PKEY_INDEX) { port = attr_mask & IB_QP_PORT ? attr->port_num : qp->port; if (attr->pkey_index >= - dev->mdev->port_caps[port - 1].pkey_table_len) { + dev->port_caps[port - 1].pkey_table_len) { mlx5_ib_dbg(dev, "invalid pkey index %d\n", attr->pkey_index); goto out; diff --git a/drivers/infiniband/hw/mlx5/wr.c b/drivers/infiniband/hw/mlx5/wr.c index d6038fb6c50c..cf2852cba45c 100644 --- a/drivers/infiniband/hw/mlx5/wr.c +++ b/drivers/infiniband/hw/mlx5/wr.c @@ -1369,7 +1369,7 @@ int mlx5_ib_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr, handle_qpt_uc(wr, &seg, &size); break; case IB_QPT_SMI: - if (unlikely(!mdev->port_caps[qp->port - 1].has_smi)) { + if (unlikely(!dev->port_caps[qp->port - 1].has_smi)) { mlx5_ib_warn(dev, "Send SMP MADs is not allowed\n"); err = -EPERM; *bad_wr = wr; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index f93bfe7473aa..11558c2e99f0 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -305,13 +305,6 @@ struct mlx5_cmd { struct mlx5_cmd_stats *stats; }; -struct mlx5_port_caps { - int gid_table_len; - int pkey_table_len; - u8 ext_port_cap; - bool has_smi; -}; - struct mlx5_cmd_mailbox { void *buf; dma_addr_t dma; @@ -694,7 +687,6 @@ struct mlx5_core_dev { u8 rev_id; char board_id[MLX5_BOARD_ID_LEN]; struct mlx5_cmd cmd; - struct mlx5_port_caps port_caps[MLX5_MAX_PORTS]; struct { u32 hca_cur[MLX5_CAP_NUM][MLX5_UN_SZ_DW(hca_cap_union)]; u32 hca_max[MLX5_CAP_NUM][MLX5_UN_SZ_DW(hca_cap_union)]; -- cgit v1.2.3 From 7416790e22452bfa86de6b55638eacf7780c8f6f Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Wed, 3 Feb 2021 15:01:32 +0200 Subject: RDMA/core: Introduce and use API to read port immutable data Currently mlx5 driver caches port GID table length for 2 ports. It is also cached by IB core as port immutable data. When mlx5 representor ports are present, which are usually more than 2, invalid access to port_caps array can happen while validating the GID table length which is only for 2 ports. To avoid this, take help of the IB cores port immutable data by exposing an API to read the port immutable fields. Remove mlx5 driver's internal cache, thereby reduce code and data. Link: https://lore.kernel.org/r/20210203130133.4057329-5-leon@kernel.org Signed-off-by: Parav Pandit Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/device.c | 14 +++++++++ drivers/infiniband/hw/mlx5/main.c | 55 +----------------------------------- drivers/infiniband/hw/mlx5/mlx5_ib.h | 1 - drivers/infiniband/hw/mlx5/qp.c | 8 ++++-- include/rdma/ib_verbs.h | 3 ++ 5 files changed, 23 insertions(+), 58 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index c895d7bfa512..051c018fb73c 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -848,6 +848,20 @@ static int setup_port_data(struct ib_device *device) return 0; } +/** + * ib_port_immutable_read() - Read rdma port's immutable data + * @dev - IB device + * @port - port number whose immutable data to read. It starts with index 1 and + * valid upto including rdma_end_port(). + */ +const struct ib_port_immutable* +ib_port_immutable_read(struct ib_device *dev, unsigned int port) +{ + WARN_ON(!rdma_is_port_valid(dev, port)); + return &dev->port_data[port].immutable; +} +EXPORT_SYMBOL(ib_port_immutable_read); + void ib_get_device_fw_str(struct ib_device *dev, char *str) { if (dev->ops.get_dev_fw_str) diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 176f2a866f12..1e1e3edcb1d5 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -2964,41 +2964,6 @@ static void get_ext_port_caps(struct mlx5_ib_dev *dev) mlx5_query_ext_port_caps(dev, port); } -static int __get_port_caps(struct mlx5_ib_dev *dev, u8 port) -{ - struct ib_port_attr *pprops = NULL; - int err = -ENOMEM; - - pprops = kzalloc(sizeof(*pprops), GFP_KERNEL); - if (!pprops) - goto out; - - err = mlx5_ib_query_port(&dev->ib_dev, port, pprops); - if (err) { - mlx5_ib_warn(dev, "query_port %d failed %d\n", - port, err); - goto out; - } - - dev->port_caps[port - 1].gid_table_len = pprops->gid_tbl_len; - mlx5_ib_dbg(dev, "port %d: pkey_table_len %d, gid_table_len %d\n", - port, dev->pkey_table_len, pprops->gid_tbl_len); - -out: - kfree(pprops); - return err; -} - -static int get_port_caps(struct mlx5_ib_dev *dev, u8 port) -{ - /* For representors use port 1, is this is the only native - * port - */ - if (dev->is_rep) - return __get_port_caps(dev, 1); - return __get_port_caps(dev, port); -} - static u8 mlx5_get_umr_fence(u8 umr_fence_cap) { switch (umr_fence_cap) { @@ -3472,10 +3437,6 @@ static bool mlx5_ib_bind_slave_port(struct mlx5_ib_dev *ibdev, if (err) goto unbind; - err = get_port_caps(ibdev, mlx5_core_native_port_num(mpi->mdev)); - if (err) - goto unbind; - err = mlx5_add_netdev_notifier(ibdev, port_num); if (err) { mlx5_ib_err(ibdev, "failed adding netdev notifier for port %u\n", @@ -3553,11 +3514,9 @@ static int mlx5_ib_init_multiport_master(struct mlx5_ib_dev *dev) break; } } - if (!bound) { - get_port_caps(dev, i + 1); + if (!bound) mlx5_ib_dbg(dev, "no free port found for port %d\n", i + 1); - } } list_add_tail(&dev->ib_dev_list, &mlx5_ib_dev_list); @@ -3940,18 +3899,6 @@ static int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev) if (err) goto err_mp; - if (!mlx5_core_mp_enabled(mdev)) { - for (i = 1; i <= dev->num_ports; i++) { - err = get_port_caps(dev, i); - if (err) - break; - } - } else { - err = get_port_caps(dev, mlx5_core_native_port_num(mdev)); - } - if (err) - goto err_mp; - err = mlx5_query_max_pkeys(&dev->ib_dev, &dev->pkey_table_len); if (err) goto err_mp; diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index 36a92f3c29e3..0f567d570230 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -1037,7 +1037,6 @@ struct mlx5_var_table { }; struct mlx5_port_caps { - int gid_table_len; bool has_smi; u8 ext_port_cap; }; diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index 475470237e0b..358c44c5a8fc 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -3176,11 +3176,13 @@ static int mlx5_set_path(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, alt ? attr->alt_pkey_index : attr->pkey_index); if (ah_flags & IB_AH_GRH) { - if (grh->sgid_index >= - dev->port_caps[port - 1].gid_table_len) { + const struct ib_port_immutable *immutable; + + immutable = ib_port_immutable_read(&dev->ib_dev, port); + if (grh->sgid_index >= immutable->gid_tbl_len) { pr_err("sgid_index (%u) too large. max is %d\n", grh->sgid_index, - dev->port_caps[port - 1].gid_table_len); + immutable->gid_tbl_len); return -EINVAL; } } diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 62e574c50555..ca28fca5736b 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -4674,4 +4674,7 @@ static inline u32 rdma_calc_flow_label(u32 lqpn, u32 rqpn) return (u32)(v & IB_GRH_FLOWLABEL_MASK); } + +const struct ib_port_immutable* +ib_port_immutable_read(struct ib_device *dev, unsigned int port); #endif /* IB_VERBS_H */ -- cgit v1.2.3 From c30f259a213802d5f4440fbb02e73b3b03403049 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 4 Feb 2021 11:59:32 -0500 Subject: rpcrdma: Capture bytes received in Receive completion tracepoints Make it easier to spot messages of an unusual size. Signed-off-by: Chuck Lever Acked-by: Tom Talpey Signed-off-by: Anna Schumaker --- include/trace/events/rpcrdma.h | 50 ++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 48 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index 76e85e16854b..c838e7ac1c2d 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -60,6 +60,51 @@ DECLARE_EVENT_CLASS(rpcrdma_completion_class, ), \ TP_ARGS(wc, cid)) +DECLARE_EVENT_CLASS(rpcrdma_receive_completion_class, + TP_PROTO( + const struct ib_wc *wc, + const struct rpc_rdma_cid *cid + ), + + TP_ARGS(wc, cid), + + TP_STRUCT__entry( + __field(u32, cq_id) + __field(int, completion_id) + __field(u32, received) + __field(unsigned long, status) + __field(unsigned int, vendor_err) + ), + + TP_fast_assign( + __entry->cq_id = cid->ci_queue_id; + __entry->completion_id = cid->ci_completion_id; + __entry->status = wc->status; + if (wc->status) { + __entry->received = 0; + __entry->vendor_err = wc->vendor_err; + } else { + __entry->received = wc->byte_len; + __entry->vendor_err = 0; + } + ), + + TP_printk("cq.id=%u cid=%d status=%s (%lu/0x%x) received=%u", + __entry->cq_id, __entry->completion_id, + rdma_show_wc_status(__entry->status), + __entry->status, __entry->vendor_err, + __entry->received + ) +); + +#define DEFINE_RECEIVE_COMPLETION_EVENT(name) \ + DEFINE_EVENT(rpcrdma_receive_completion_class, name, \ + TP_PROTO( \ + const struct ib_wc *wc, \ + const struct rpc_rdma_cid *cid \ + ), \ + TP_ARGS(wc, cid)) + DECLARE_EVENT_CLASS(xprtrdma_reply_class, TP_PROTO( const struct rpcrdma_rep *rep @@ -838,7 +883,8 @@ TRACE_EVENT(xprtrdma_post_linv_err, ** Completion events **/ -DEFINE_COMPLETION_EVENT(xprtrdma_wc_receive); +DEFINE_RECEIVE_COMPLETION_EVENT(xprtrdma_wc_receive); + DEFINE_COMPLETION_EVENT(xprtrdma_wc_send); DEFINE_COMPLETION_EVENT(xprtrdma_wc_fastreg); DEFINE_COMPLETION_EVENT(xprtrdma_wc_li); @@ -1790,7 +1836,7 @@ TRACE_EVENT(svcrdma_post_recv, ) ); -DEFINE_COMPLETION_EVENT(svcrdma_wc_receive); +DEFINE_RECEIVE_COMPLETION_EVENT(svcrdma_wc_receive); TRACE_EVENT(svcrdma_rq_post_err, TP_PROTO( -- cgit v1.2.3 From 0be10b6f68b217876665031f643e571a5661fc9c Mon Sep 17 00:00:00 2001 From: Heiko Stuebner Date: Fri, 5 Feb 2021 12:04:58 +0100 Subject: clk: rockchip: add clock ids for PCLK_DPHYRX and PCLK_DPHYTX0 on rk3368 Needed by the mipi dphys. The naming follows the clock names in the manual. Signed-off-by: Heiko Stuebner Link: https://lore.kernel.org/r/20210205110502.1850669-1-heiko@sntech.de --- include/dt-bindings/clock/rk3368-cru.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/clock/rk3368-cru.h b/include/dt-bindings/clock/rk3368-cru.h index 0a06c5f514d7..f89683295935 100644 --- a/include/dt-bindings/clock/rk3368-cru.h +++ b/include/dt-bindings/clock/rk3368-cru.h @@ -148,6 +148,8 @@ #define PCLK_VIP 367 #define PCLK_WDT 368 #define PCLK_EFUSE256 369 +#define PCLK_DPHYRX 370 +#define PCLK_DPHYTX0 371 /* hclk gates */ #define HCLK_SFC 448 -- cgit v1.2.3 From 686458aa752362f86d881d7fa4576c9f175b2d9b Mon Sep 17 00:00:00 2001 From: Heiko Stuebner Date: Fri, 5 Feb 2021 12:05:00 +0100 Subject: clk: rockchip: add clock id for SCLK_VIP_OUT on rk3368 Needed to provide clocks for cameras. Signed-off-by: Heiko Stuebner Link: https://lore.kernel.org/r/20210205110502.1850669-3-heiko@sntech.de --- include/dt-bindings/clock/rk3368-cru.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/dt-bindings/clock/rk3368-cru.h b/include/dt-bindings/clock/rk3368-cru.h index f89683295935..83c72a163fd3 100644 --- a/include/dt-bindings/clock/rk3368-cru.h +++ b/include/dt-bindings/clock/rk3368-cru.h @@ -78,6 +78,7 @@ #define SCLK_TIMER13 136 #define SCLK_TIMER14 137 #define SCLK_TIMER15 138 +#define SCLK_VIP_OUT 139 #define DCLK_VOP 190 #define MCLK_CRYPTO 191 -- cgit v1.2.3 From 167790abb90fa073d8341ee0e408ccad3d2109cd Mon Sep 17 00:00:00 2001 From: Bard Liao Date: Fri, 22 Jan 2021 15:06:29 +0800 Subject: soundwire: export sdw_write/read_no_pm functions sdw_write_no_pm and sdw_read_no_pm are useful when we want to do IO without touching PM. Fixes: 0231453bc08f ('soundwire: bus: add clock stop helpers') Fixes: 60ee9be25571 ('soundwire: bus: add PM/no-PM versions of read/write functions') Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20210122070634.12825-5-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- drivers/soundwire/bus.c | 7 ++++--- include/linux/soundwire/sdw.h | 2 ++ 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c index 675d028e923d..45e9fc9f472a 100644 --- a/drivers/soundwire/bus.c +++ b/drivers/soundwire/bus.c @@ -407,10 +407,11 @@ sdw_nwrite_no_pm(struct sdw_slave *slave, u32 addr, size_t count, u8 *val) return sdw_transfer(slave->bus, &msg); } -static int sdw_write_no_pm(struct sdw_slave *slave, u32 addr, u8 value) +int sdw_write_no_pm(struct sdw_slave *slave, u32 addr, u8 value) { return sdw_nwrite_no_pm(slave, addr, 1, &value); } +EXPORT_SYMBOL(sdw_write_no_pm); static int sdw_bread_no_pm(struct sdw_bus *bus, u16 dev_num, u32 addr) @@ -478,8 +479,7 @@ int sdw_bwrite_no_pm_unlocked(struct sdw_bus *bus, u16 dev_num, u32 addr, u8 val } EXPORT_SYMBOL(sdw_bwrite_no_pm_unlocked); -static int -sdw_read_no_pm(struct sdw_slave *slave, u32 addr) +int sdw_read_no_pm(struct sdw_slave *slave, u32 addr) { u8 buf; int ret; @@ -490,6 +490,7 @@ sdw_read_no_pm(struct sdw_slave *slave, u32 addr) else return buf; } +EXPORT_SYMBOL(sdw_read_no_pm); static int sdw_update_no_pm(struct sdw_slave *slave, u32 addr, u8 mask, u8 val) { diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index f0b01b728640..d08039d65825 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -1005,6 +1005,8 @@ int sdw_bus_exit_clk_stop(struct sdw_bus *bus); int sdw_read(struct sdw_slave *slave, u32 addr); int sdw_write(struct sdw_slave *slave, u32 addr, u8 value); +int sdw_write_no_pm(struct sdw_slave *slave, u32 addr, u8 value); +int sdw_read_no_pm(struct sdw_slave *slave, u32 addr); int sdw_nread(struct sdw_slave *slave, u32 addr, size_t count, u8 *val); int sdw_nwrite(struct sdw_slave *slave, u32 addr, size_t count, u8 *val); -- cgit v1.2.3 From af2a30fb70017ef10a08e1547183627fb529a1fe Mon Sep 17 00:00:00 2001 From: Crystal Guo Date: Wed, 14 Oct 2020 21:19:35 +0800 Subject: dt-binding: mt8192: add toprgu reset-controller head file add toprgu reset-controller head file for MT8192 platform Signed-off-by: Crystal Guo Reviewed-by: Matthias Brugger Acked-by: Guenter Roeck Link: https://lore.kernel.org/r/20201014131936.20584-4-crystal.guo@mediatek.com Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- .../dt-bindings/reset-controller/mt8192-resets.h | 30 ++++++++++++++++++++++ 1 file changed, 30 insertions(+) create mode 100644 include/dt-bindings/reset-controller/mt8192-resets.h (limited to 'include') diff --git a/include/dt-bindings/reset-controller/mt8192-resets.h b/include/dt-bindings/reset-controller/mt8192-resets.h new file mode 100644 index 000000000000..be9a7ca245b9 --- /dev/null +++ b/include/dt-bindings/reset-controller/mt8192-resets.h @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2020 MediaTek Inc. + * Author: Yong Liang + */ + +#ifndef _DT_BINDINGS_RESET_CONTROLLER_MT8192 +#define _DT_BINDINGS_RESET_CONTROLLER_MT8192 + +#define MT8192_TOPRGU_MM_SW_RST 1 +#define MT8192_TOPRGU_MFG_SW_RST 2 +#define MT8192_TOPRGU_VENC_SW_RST 3 +#define MT8192_TOPRGU_VDEC_SW_RST 4 +#define MT8192_TOPRGU_IMG_SW_RST 5 +#define MT8192_TOPRGU_MD_SW_RST 7 +#define MT8192_TOPRGU_CONN_SW_RST 9 +#define MT8192_TOPRGU_CONN_MCU_SW_RST 12 +#define MT8192_TOPRGU_IPU0_SW_RST 14 +#define MT8192_TOPRGU_IPU1_SW_RST 15 +#define MT8192_TOPRGU_AUDIO_SW_RST 17 +#define MT8192_TOPRGU_CAMSYS_SW_RST 18 +#define MT8192_TOPRGU_MJC_SW_RST 19 +#define MT8192_TOPRGU_C2K_S2_SW_RST 20 +#define MT8192_TOPRGU_C2K_SW_RST 21 +#define MT8192_TOPRGU_PERI_SW_RST 22 +#define MT8192_TOPRGU_PERI_AO_SW_RST 23 + +#define MT8192_TOPRGU_SW_RST_NUM 23 + +#endif /* _DT_BINDINGS_RESET_CONTROLLER_MT8192 */ -- cgit v1.2.3 From a006050575745ca2be25118b90f1c37f454ac542 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 2 Feb 2021 13:13:25 +0100 Subject: module: use RCU to synchronize find_module Allow for a RCU-sched critical section around find_module, following the lower level find_module_all helper, and switch the two callers outside of module.c to use such a RCU-sched critical section instead of module_mutex. Reviewed-by: Petr Mladek Acked-by: Miroslav Benes Signed-off-by: Christoph Hellwig Signed-off-by: Jessica Yu --- include/linux/module.h | 2 +- kernel/livepatch/core.c | 5 +++-- kernel/module.c | 1 - kernel/trace/trace_kprobe.c | 4 ++-- 4 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/module.h b/include/linux/module.h index 7a0bcb5b1ffc..a64aa84d1b18 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -586,7 +586,7 @@ static inline bool within_module(unsigned long addr, const struct module *mod) return within_module_init(addr, mod) || within_module_core(addr, mod); } -/* Search for module by name: must hold module_mutex. */ +/* Search for module by name: must be in a RCU-sched critical section. */ struct module *find_module(const char *name); struct symsearch { diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c index f76fdb925532..262cd9b003b9 100644 --- a/kernel/livepatch/core.c +++ b/kernel/livepatch/core.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include "core.h" #include "patch.h" @@ -57,7 +58,7 @@ static void klp_find_object_module(struct klp_object *obj) if (!klp_is_module(obj)) return; - mutex_lock(&module_mutex); + rcu_read_lock_sched(); /* * We do not want to block removal of patched modules and therefore * we do not take a reference here. The patches are removed by @@ -74,7 +75,7 @@ static void klp_find_object_module(struct klp_object *obj) if (mod && mod->klp_alive) obj->mod = mod; - mutex_unlock(&module_mutex); + rcu_read_unlock_sched(); } static bool klp_initialized(void) diff --git a/kernel/module.c b/kernel/module.c index 8fb16e704b89..63cc03393a07 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -668,7 +668,6 @@ static struct module *find_module_all(const char *name, size_t len, struct module *find_module(const char *name) { - module_assert_mutex(); return find_module_all(name, strlen(name), false); } diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index e6fba1798771..3137992baa5e 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -124,9 +124,9 @@ static nokprobe_inline bool trace_kprobe_module_exist(struct trace_kprobe *tk) if (!p) return true; *p = '\0'; - mutex_lock(&module_mutex); + rcu_read_lock_sched(); ret = !!find_module(tk->symbol); - mutex_unlock(&module_mutex); + rcu_read_unlock_sched(); *p = ':'; return ret; -- cgit v1.2.3 From 3e3552056ab42f883d7723eeb42fed712b66bacf Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 2 Feb 2021 13:13:27 +0100 Subject: kallsyms: only build {,module_}kallsyms_on_each_symbol when required kallsyms_on_each_symbol and module_kallsyms_on_each_symbol are only used by the livepatching code, so don't build them if livepatching is not enabled. Reviewed-by: Miroslav Benes Signed-off-by: Christoph Hellwig Signed-off-by: Jessica Yu --- include/linux/kallsyms.h | 17 ++++------------- include/linux/module.h | 16 ++++------------ kernel/kallsyms.c | 2 ++ kernel/module.c | 2 ++ 4 files changed, 12 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h index 481273f0c72d..465060acc981 100644 --- a/include/linux/kallsyms.h +++ b/include/linux/kallsyms.h @@ -71,15 +71,14 @@ static inline void *dereference_symbol_descriptor(void *ptr) return ptr; } -#ifdef CONFIG_KALLSYMS -/* Lookup the address for a symbol. Returns 0 if not found. */ -unsigned long kallsyms_lookup_name(const char *name); - -/* Call a function on each kallsyms symbol in the core kernel */ int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, unsigned long), void *data); +#ifdef CONFIG_KALLSYMS +/* Lookup the address for a symbol. Returns 0 if not found. */ +unsigned long kallsyms_lookup_name(const char *name); + extern int kallsyms_lookup_size_offset(unsigned long addr, unsigned long *symbolsize, unsigned long *offset); @@ -108,14 +107,6 @@ static inline unsigned long kallsyms_lookup_name(const char *name) return 0; } -static inline int kallsyms_on_each_symbol(int (*fn)(void *, const char *, - struct module *, - unsigned long), - void *data) -{ - return 0; -} - static inline int kallsyms_lookup_size_offset(unsigned long addr, unsigned long *symbolsize, unsigned long *offset) diff --git a/include/linux/module.h b/include/linux/module.h index a64aa84d1b18..3ea4ffae608f 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -608,10 +608,6 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, /* Look for this name: can be of form module:name. */ unsigned long module_kallsyms_lookup_name(const char *name); -int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, - struct module *, unsigned long), - void *data); - extern void __noreturn __module_put_and_exit(struct module *mod, long code); #define module_put_and_exit(code) __module_put_and_exit(THIS_MODULE, code) @@ -795,14 +791,6 @@ static inline unsigned long module_kallsyms_lookup_name(const char *name) return 0; } -static inline int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, - struct module *, - unsigned long), - void *data) -{ - return 0; -} - static inline int register_module_notifier(struct notifier_block *nb) { /* no events will happen anyway, so this can always succeed */ @@ -891,4 +879,8 @@ static inline bool module_sig_ok(struct module *module) } #endif /* CONFIG_MODULE_SIG */ +int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, + struct module *, unsigned long), + void *data); + #endif /* _LINUX_MODULE_H */ diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index a0d3f0865916..8043a90aa50e 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -177,6 +177,7 @@ unsigned long kallsyms_lookup_name(const char *name) return module_kallsyms_lookup_name(name); } +#ifdef CONFIG_LIVEPATCH /* * Iterate over all symbols in vmlinux. For symbols from modules use * module_kallsyms_on_each_symbol instead. @@ -198,6 +199,7 @@ int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, } return 0; } +#endif /* CONFIG_LIVEPATCH */ static unsigned long get_symbol_pos(unsigned long addr, unsigned long *symbolsize, diff --git a/kernel/module.c b/kernel/module.c index 481eb348564e..06155c454779 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -4488,6 +4488,7 @@ unsigned long module_kallsyms_lookup_name(const char *name) return ret; } +#ifdef CONFIG_LIVEPATCH int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, unsigned long), void *data) @@ -4518,6 +4519,7 @@ int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, mutex_unlock(&module_mutex); return ret; } +#endif /* CONFIG_LIVEPATCH */ #endif /* CONFIG_KALLSYMS */ /* Maximum number of characters written by module_flags() */ -- cgit v1.2.3 From 922f2a7c822bf76dffb218331bd95b1eea3cf637 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 2 Feb 2021 13:13:28 +0100 Subject: module: mark module_mutex static Except for two lockdep asserts module_mutex is only used in module.c. Remove the two asserts given that the functions they are in are not exported and just called from the module code, and mark module_mutex static. Reviewed-by: Miroslav Benes Signed-off-by: Christoph Hellwig Signed-off-by: Jessica Yu --- include/linux/module.h | 2 -- kernel/module.c | 2 +- lib/bug.c | 3 --- 3 files changed, 1 insertion(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/module.h b/include/linux/module.h index 3ea4ffae608f..0f360c48fe92 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -550,8 +550,6 @@ static inline unsigned long kallsyms_symbol_value(const Elf_Sym *sym) } #endif -extern struct mutex module_mutex; - /* FIXME: It'd be nice to isolate modules during init, too, so they aren't used before they (may) fail. But presently too much code (IDE & SCSI) require entry into the module during init.*/ diff --git a/kernel/module.c b/kernel/module.c index 06155c454779..9befd793997e 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -87,7 +87,7 @@ * 3) module_addr_min/module_addr_max. * (delete and add uses RCU list operations). */ -DEFINE_MUTEX(module_mutex); +static DEFINE_MUTEX(module_mutex); static LIST_HEAD(modules); /* Work queue for freeing init sections in success case */ diff --git a/lib/bug.c b/lib/bug.c index 7103440c0ee1..8f9d537bfb2a 100644 --- a/lib/bug.c +++ b/lib/bug.c @@ -91,8 +91,6 @@ void module_bug_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, char *secstrings; unsigned int i; - lockdep_assert_held(&module_mutex); - mod->bug_table = NULL; mod->num_bugs = 0; @@ -118,7 +116,6 @@ void module_bug_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, void module_bug_cleanup(struct module *mod) { - lockdep_assert_held(&module_mutex); list_del_rcu(&mod->bug_list); } -- cgit v1.2.3 From 00cc2c1cd34f81f777085cb2d65267edcd403fd0 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 2 Feb 2021 13:13:32 +0100 Subject: module: move struct symsearch to module.c struct symsearch is only used inside of module.h, so move the definition out of module.h. Reviewed-by: Miroslav Benes Reviewed-by: Emil Velikov Signed-off-by: Christoph Hellwig Signed-off-by: Jessica Yu --- include/linux/module.h | 11 ----------- kernel/module.c | 11 +++++++++++ 2 files changed, 11 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/module.h b/include/linux/module.h index 0f360c48fe92..da0f5966ee80 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -587,17 +587,6 @@ static inline bool within_module(unsigned long addr, const struct module *mod) /* Search for module by name: must be in a RCU-sched critical section. */ struct module *find_module(const char *name); -struct symsearch { - const struct kernel_symbol *start, *stop; - const s32 *crcs; - enum mod_license { - NOT_GPL_ONLY, - GPL_ONLY, - WILL_BE_GPL_ONLY, - } license; - bool unused; -}; - /* Returns 0 and fills in value, defined and namebuf, or -ERANGE if symnum out of range. */ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, diff --git a/kernel/module.c b/kernel/module.c index 2e7ddf544338..9cd6814405b9 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -428,6 +428,17 @@ extern const s32 __start___kcrctab_unused_gpl[]; #define symversion(base, idx) ((base != NULL) ? ((base) + (idx)) : NULL) #endif +struct symsearch { + const struct kernel_symbol *start, *stop; + const s32 *crcs; + enum mod_license { + NOT_GPL_ONLY, + GPL_ONLY, + WILL_BE_GPL_ONLY, + } license; + bool unused; +}; + struct find_symbol_arg { /* Input */ const char *name; -- cgit v1.2.3 From f1c3d73e973cfad85ff5d3d86086503e742d8c62 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 2 Feb 2021 13:13:33 +0100 Subject: module: remove EXPORT_SYMBOL_GPL_FUTURE As far as I can tell this has never been used at all, and certainly not any time recently. Reviewed-by: Miroslav Benes Reviewed-by: Emil Velikov Signed-off-by: Christoph Hellwig Signed-off-by: Jessica Yu --- arch/x86/tools/relocs.c | 4 ++-- include/asm-generic/vmlinux.lds.h | 14 -------------- include/linux/export.h | 1 - include/linux/module.h | 5 ----- kernel/module.c | 29 ++--------------------------- scripts/mod/modpost.c | 13 +------------ scripts/mod/modpost.h | 1 - scripts/module.lds.S | 2 -- tools/include/linux/export.h | 1 - 9 files changed, 5 insertions(+), 65 deletions(-) (limited to 'include') diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c index ce7188cbdae5..0d210d0e83e2 100644 --- a/arch/x86/tools/relocs.c +++ b/arch/x86/tools/relocs.c @@ -61,8 +61,8 @@ static const char * const sym_regex_kernel[S_NSYMTYPES] = { "(__iommu_table|__apicdrivers|__smp_locks)(|_end)|" "__(start|end)_pci_.*|" "__(start|end)_builtin_fw|" - "__(start|stop)___ksymtab(|_gpl|_unused|_unused_gpl|_gpl_future)|" - "__(start|stop)___kcrctab(|_gpl|_unused|_unused_gpl|_gpl_future)|" + "__(start|stop)___ksymtab(|_gpl|_unused|_unused_gpl)|" + "__(start|stop)___kcrctab(|_gpl|_unused|_unused_gpl)|" "__(start|stop)___param|" "__(start|stop)___modver|" "__(start|stop)___bug_table|" diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index b2b3d81b1535..83243506e68b 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -495,13 +495,6 @@ __stop___ksymtab_unused_gpl = .; \ } \ \ - /* Kernel symbol table: GPL-future-only symbols */ \ - __ksymtab_gpl_future : AT(ADDR(__ksymtab_gpl_future) - LOAD_OFFSET) { \ - __start___ksymtab_gpl_future = .; \ - KEEP(*(SORT(___ksymtab_gpl_future+*))) \ - __stop___ksymtab_gpl_future = .; \ - } \ - \ /* Kernel symbol table: Normal symbols */ \ __kcrctab : AT(ADDR(__kcrctab) - LOAD_OFFSET) { \ __start___kcrctab = .; \ @@ -530,13 +523,6 @@ __stop___kcrctab_unused_gpl = .; \ } \ \ - /* Kernel symbol table: GPL-future-only symbols */ \ - __kcrctab_gpl_future : AT(ADDR(__kcrctab_gpl_future) - LOAD_OFFSET) { \ - __start___kcrctab_gpl_future = .; \ - KEEP(*(SORT(___kcrctab_gpl_future+*))) \ - __stop___kcrctab_gpl_future = .; \ - } \ - \ /* Kernel symbol table: strings */ \ __ksymtab_strings : AT(ADDR(__ksymtab_strings) - LOAD_OFFSET) { \ *(__ksymtab_strings) \ diff --git a/include/linux/export.h b/include/linux/export.h index fceb5e855717..362b64f8d4a7 100644 --- a/include/linux/export.h +++ b/include/linux/export.h @@ -157,7 +157,6 @@ struct kernel_symbol { #define EXPORT_SYMBOL(sym) _EXPORT_SYMBOL(sym, "") #define EXPORT_SYMBOL_GPL(sym) _EXPORT_SYMBOL(sym, "_gpl") -#define EXPORT_SYMBOL_GPL_FUTURE(sym) _EXPORT_SYMBOL(sym, "_gpl_future") #define EXPORT_SYMBOL_NS(sym, ns) __EXPORT_SYMBOL(sym, "", #ns) #define EXPORT_SYMBOL_NS_GPL(sym, ns) __EXPORT_SYMBOL(sym, "_gpl", #ns) diff --git a/include/linux/module.h b/include/linux/module.h index da0f5966ee80..e6e50ee30412 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -411,11 +411,6 @@ struct module { bool async_probe_requested; - /* symbols that will be GPL-only in the near future. */ - const struct kernel_symbol *gpl_future_syms; - const s32 *gpl_future_crcs; - unsigned int num_gpl_future_syms; - /* Exception table */ unsigned int num_exentries; struct exception_table_entry *extable; diff --git a/kernel/module.c b/kernel/module.c index 9cd6814405b9..95186c9d81ea 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -408,11 +408,8 @@ extern const struct kernel_symbol __start___ksymtab[]; extern const struct kernel_symbol __stop___ksymtab[]; extern const struct kernel_symbol __start___ksymtab_gpl[]; extern const struct kernel_symbol __stop___ksymtab_gpl[]; -extern const struct kernel_symbol __start___ksymtab_gpl_future[]; -extern const struct kernel_symbol __stop___ksymtab_gpl_future[]; extern const s32 __start___kcrctab[]; extern const s32 __start___kcrctab_gpl[]; -extern const s32 __start___kcrctab_gpl_future[]; #ifdef CONFIG_UNUSED_SYMBOLS extern const struct kernel_symbol __start___ksymtab_unused[]; extern const struct kernel_symbol __stop___ksymtab_unused[]; @@ -434,7 +431,6 @@ struct symsearch { enum mod_license { NOT_GPL_ONLY, GPL_ONLY, - WILL_BE_GPL_ONLY, } license; bool unused; }; @@ -458,15 +454,8 @@ static bool check_exported_symbol(const struct symsearch *syms, { struct find_symbol_arg *fsa = data; - if (!fsa->gplok) { - if (syms->license == GPL_ONLY) - return false; - if (syms->license == WILL_BE_GPL_ONLY && fsa->warn) { - pr_warn("Symbol %s is being used by a non-GPL module, " - "which will not be allowed in the future\n", - fsa->name); - } - } + if (!fsa->gplok && syms->license == GPL_ONLY) + return false; #ifdef CONFIG_UNUSED_SYMBOLS if (syms->unused && fsa->warn) { @@ -550,9 +539,6 @@ static bool find_symbol(struct find_symbol_arg *fsa) { __start___ksymtab_gpl, __stop___ksymtab_gpl, __start___kcrctab_gpl, GPL_ONLY, false }, - { __start___ksymtab_gpl_future, __stop___ksymtab_gpl_future, - __start___kcrctab_gpl_future, - WILL_BE_GPL_ONLY, false }, #ifdef CONFIG_UNUSED_SYMBOLS { __start___ksymtab_unused, __stop___ksymtab_unused, __start___kcrctab_unused, @@ -579,10 +565,6 @@ static bool find_symbol(struct find_symbol_arg *fsa) { mod->gpl_syms, mod->gpl_syms + mod->num_gpl_syms, mod->gpl_crcs, GPL_ONLY, false }, - { mod->gpl_future_syms, - mod->gpl_future_syms + mod->num_gpl_future_syms, - mod->gpl_future_crcs, - WILL_BE_GPL_ONLY, false }, #ifdef CONFIG_UNUSED_SYMBOLS { mod->unused_syms, mod->unused_syms + mod->num_unused_syms, @@ -2292,7 +2274,6 @@ static int verify_exported_symbols(struct module *mod) } arr[] = { { mod->syms, mod->num_syms }, { mod->gpl_syms, mod->num_gpl_syms }, - { mod->gpl_future_syms, mod->num_gpl_future_syms }, #ifdef CONFIG_UNUSED_SYMBOLS { mod->unused_syms, mod->num_unused_syms }, { mod->unused_gpl_syms, mod->num_unused_gpl_syms }, @@ -3308,11 +3289,6 @@ static int find_module_sections(struct module *mod, struct load_info *info) sizeof(*mod->gpl_syms), &mod->num_gpl_syms); mod->gpl_crcs = section_addr(info, "__kcrctab_gpl"); - mod->gpl_future_syms = section_objs(info, - "__ksymtab_gpl_future", - sizeof(*mod->gpl_future_syms), - &mod->num_gpl_future_syms); - mod->gpl_future_crcs = section_addr(info, "__kcrctab_gpl_future"); #ifdef CONFIG_UNUSED_SYMBOLS mod->unused_syms = section_objs(info, "__ksymtab_unused", @@ -3506,7 +3482,6 @@ static int check_module_license_and_versions(struct module *mod) #ifdef CONFIG_MODVERSIONS if ((mod->num_syms && !mod->crcs) || (mod->num_gpl_syms && !mod->gpl_crcs) - || (mod->num_gpl_future_syms && !mod->gpl_future_crcs) #ifdef CONFIG_UNUSED_SYMBOLS || (mod->num_unused_syms && !mod->unused_crcs) || (mod->num_unused_gpl_syms && !mod->unused_gpl_crcs) diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index d6c81657d695..25c1446055d1 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -44,7 +44,7 @@ static bool error_occurred; enum export { export_plain, export_unused, export_gpl, - export_unused_gpl, export_gpl_future, export_unknown + export_unused_gpl, export_unknown }; /* In kernel, this size is defined in linux/module.h; @@ -304,7 +304,6 @@ static const struct { { .str = "EXPORT_UNUSED_SYMBOL", .export = export_unused }, { .str = "EXPORT_SYMBOL_GPL", .export = export_gpl }, { .str = "EXPORT_UNUSED_SYMBOL_GPL", .export = export_unused_gpl }, - { .str = "EXPORT_SYMBOL_GPL_FUTURE", .export = export_gpl_future }, { .str = "(unknown)", .export = export_unknown }, }; @@ -369,8 +368,6 @@ static enum export export_from_secname(struct elf_info *elf, unsigned int sec) return export_gpl; else if (strstarts(secname, "___ksymtab_unused_gpl+")) return export_unused_gpl; - else if (strstarts(secname, "___ksymtab_gpl_future+")) - return export_gpl_future; else return export_unknown; } @@ -385,8 +382,6 @@ static enum export export_from_sec(struct elf_info *elf, unsigned int sec) return export_gpl; else if (sec == elf->export_unused_gpl_sec) return export_unused_gpl; - else if (sec == elf->export_gpl_future_sec) - return export_gpl_future; else return export_unknown; } @@ -596,8 +591,6 @@ static int parse_elf(struct elf_info *info, const char *filename) info->export_gpl_sec = i; else if (strcmp(secname, "__ksymtab_unused_gpl") == 0) info->export_unused_gpl_sec = i; - else if (strcmp(secname, "__ksymtab_gpl_future") == 0) - info->export_gpl_future_sec = i; if (sechdrs[i].sh_type == SHT_SYMTAB) { unsigned int sh_link_idx; @@ -2152,10 +2145,6 @@ static void check_for_gpl_usage(enum export exp, const char *m, const char *s) error("GPL-incompatible module %s.ko uses GPL-only symbol marked UNUSED '%s'\n", m, s); break; - case export_gpl_future: - warn("GPL-incompatible module %s.ko uses future GPL-only symbol '%s'\n", - m, s); - break; case export_plain: case export_unused: case export_unknown: diff --git a/scripts/mod/modpost.h b/scripts/mod/modpost.h index e6f46eee0af0..834220de002b 100644 --- a/scripts/mod/modpost.h +++ b/scripts/mod/modpost.h @@ -142,7 +142,6 @@ struct elf_info { Elf_Section export_unused_sec; Elf_Section export_gpl_sec; Elf_Section export_unused_gpl_sec; - Elf_Section export_gpl_future_sec; char *strtab; char *modinfo; unsigned int modinfo_len; diff --git a/scripts/module.lds.S b/scripts/module.lds.S index 69b9b71a6a47..d82b452e8a71 100644 --- a/scripts/module.lds.S +++ b/scripts/module.lds.S @@ -13,12 +13,10 @@ SECTIONS { __ksymtab_gpl 0 : { *(SORT(___ksymtab_gpl+*)) } __ksymtab_unused 0 : { *(SORT(___ksymtab_unused+*)) } __ksymtab_unused_gpl 0 : { *(SORT(___ksymtab_unused_gpl+*)) } - __ksymtab_gpl_future 0 : { *(SORT(___ksymtab_gpl_future+*)) } __kcrctab 0 : { *(SORT(___kcrctab+*)) } __kcrctab_gpl 0 : { *(SORT(___kcrctab_gpl+*)) } __kcrctab_unused 0 : { *(SORT(___kcrctab_unused+*)) } __kcrctab_unused_gpl 0 : { *(SORT(___kcrctab_unused_gpl+*)) } - __kcrctab_gpl_future 0 : { *(SORT(___kcrctab_gpl_future+*)) } .init_array 0 : ALIGN(8) { *(SORT(.init_array.*)) *(.init_array) } diff --git a/tools/include/linux/export.h b/tools/include/linux/export.h index d07e586b9ba0..9f61349a8944 100644 --- a/tools/include/linux/export.h +++ b/tools/include/linux/export.h @@ -3,7 +3,6 @@ #define EXPORT_SYMBOL(sym) #define EXPORT_SYMBOL_GPL(sym) -#define EXPORT_SYMBOL_GPL_FUTURE(sym) #define EXPORT_UNUSED_SYMBOL(sym) #define EXPORT_UNUSED_SYMBOL_GPL(sym) -- cgit v1.2.3 From 367948220fcefcad1bf0d3d595a06efe0694acae Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 2 Feb 2021 13:13:34 +0100 Subject: module: remove EXPORT_UNUSED_SYMBOL* EXPORT_UNUSED_SYMBOL* is not actually used anywhere. Remove the unused functionality as we generally just remove unused code anyway. Reviewed-by: Miroslav Benes Reviewed-by: Emil Velikov Signed-off-by: Christoph Hellwig Signed-off-by: Jessica Yu --- arch/arm/configs/bcm2835_defconfig | 1 - arch/arm/configs/mxs_defconfig | 1 - arch/mips/configs/nlm_xlp_defconfig | 1 - arch/mips/configs/nlm_xlr_defconfig | 1 - arch/parisc/configs/generic-32bit_defconfig | 1 - arch/parisc/configs/generic-64bit_defconfig | 1 - arch/powerpc/configs/ppc6xx_defconfig | 1 - arch/s390/configs/debug_defconfig | 1 - arch/s390/configs/defconfig | 1 - arch/sh/configs/edosk7760_defconfig | 1 - arch/sh/configs/sdk7780_defconfig | 1 - arch/x86/configs/i386_defconfig | 1 - arch/x86/configs/x86_64_defconfig | 1 - arch/x86/tools/relocs.c | 4 +- include/asm-generic/vmlinux.lds.h | 28 ------------ include/linux/export.h | 8 ---- include/linux/module.h | 12 ----- init/Kconfig | 17 ------- kernel/module.c | 71 +++-------------------------- scripts/checkpatch.pl | 6 +-- scripts/mod/modpost.c | 39 ++-------------- scripts/mod/modpost.h | 2 - scripts/module.lds.S | 4 -- tools/include/linux/export.h | 2 - 24 files changed, 13 insertions(+), 193 deletions(-) (limited to 'include') diff --git a/arch/arm/configs/bcm2835_defconfig b/arch/arm/configs/bcm2835_defconfig index 44ff9cd88d81..d6c6c2e031c4 100644 --- a/arch/arm/configs/bcm2835_defconfig +++ b/arch/arm/configs/bcm2835_defconfig @@ -177,7 +177,6 @@ CONFIG_BOOT_PRINTK_DELAY=y CONFIG_DYNAMIC_DEBUG=y CONFIG_DEBUG_INFO=y # CONFIG_ENABLE_MUST_CHECK is not set -CONFIG_UNUSED_SYMBOLS=y CONFIG_DEBUG_MEMORY_INIT=y CONFIG_LOCKUP_DETECTOR=y CONFIG_SCHED_TRACER=y diff --git a/arch/arm/configs/mxs_defconfig b/arch/arm/configs/mxs_defconfig index a9c6f32a9b1c..ca32446b187f 100644 --- a/arch/arm/configs/mxs_defconfig +++ b/arch/arm/configs/mxs_defconfig @@ -164,7 +164,6 @@ CONFIG_FONTS=y CONFIG_PRINTK_TIME=y CONFIG_DEBUG_INFO=y CONFIG_FRAME_WARN=2048 -CONFIG_UNUSED_SYMBOLS=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_KERNEL=y CONFIG_SOFTLOCKUP_DETECTOR=y diff --git a/arch/mips/configs/nlm_xlp_defconfig b/arch/mips/configs/nlm_xlp_defconfig index 72a211d2d556..32c290611723 100644 --- a/arch/mips/configs/nlm_xlp_defconfig +++ b/arch/mips/configs/nlm_xlp_defconfig @@ -549,7 +549,6 @@ CONFIG_PRINTK_TIME=y CONFIG_DEBUG_INFO=y # CONFIG_ENABLE_MUST_CHECK is not set CONFIG_FRAME_WARN=1024 -CONFIG_UNUSED_SYMBOLS=y CONFIG_DEBUG_MEMORY_INIT=y CONFIG_DETECT_HUNG_TASK=y CONFIG_SCHEDSTATS=y diff --git a/arch/mips/configs/nlm_xlr_defconfig b/arch/mips/configs/nlm_xlr_defconfig index 4ecb157e56d4..bf9b9244929e 100644 --- a/arch/mips/configs/nlm_xlr_defconfig +++ b/arch/mips/configs/nlm_xlr_defconfig @@ -500,7 +500,6 @@ CONFIG_CRC7=m CONFIG_PRINTK_TIME=y CONFIG_DEBUG_INFO=y # CONFIG_ENABLE_MUST_CHECK is not set -CONFIG_UNUSED_SYMBOLS=y CONFIG_DEBUG_MEMORY_INIT=y CONFIG_DETECT_HUNG_TASK=y CONFIG_SCHEDSTATS=y diff --git a/arch/parisc/configs/generic-32bit_defconfig b/arch/parisc/configs/generic-32bit_defconfig index 3cbcfad5f724..7611d48c599e 100644 --- a/arch/parisc/configs/generic-32bit_defconfig +++ b/arch/parisc/configs/generic-32bit_defconfig @@ -22,7 +22,6 @@ CONFIG_PCI_LBA=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y -CONFIG_UNUSED_SYMBOLS=y # CONFIG_BLK_DEV_BSG is not set # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set CONFIG_BINFMT_MISC=m diff --git a/arch/parisc/configs/generic-64bit_defconfig b/arch/parisc/configs/generic-64bit_defconfig index 8f81fcbf04c4..53054b81461a 100644 --- a/arch/parisc/configs/generic-64bit_defconfig +++ b/arch/parisc/configs/generic-64bit_defconfig @@ -31,7 +31,6 @@ CONFIG_MODULE_FORCE_LOAD=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODVERSIONS=y -CONFIG_UNUSED_SYMBOLS=y CONFIG_BLK_DEV_INTEGRITY=y CONFIG_BINFMT_MISC=m # CONFIG_COMPACTION is not set diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index ef09f3cce1fa..34c3859040f9 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -1072,7 +1072,6 @@ CONFIG_NLS_ISO8859_15=m CONFIG_NLS_KOI8_R=m CONFIG_NLS_KOI8_U=m CONFIG_DEBUG_INFO=y -CONFIG_UNUSED_SYMBOLS=y CONFIG_HEADERS_INSTALL=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_KERNEL=y diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index c4f6ff98a612..58e54d17e315 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -71,7 +71,6 @@ CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODVERSIONS=y CONFIG_MODULE_SRCVERSION_ALL=y CONFIG_MODULE_SIG_SHA256=y -CONFIG_UNUSED_SYMBOLS=y CONFIG_BLK_DEV_INTEGRITY=y CONFIG_BLK_DEV_THROTTLING=y CONFIG_BLK_WBT=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 51135893cffe..b5e62c0d3e23 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -66,7 +66,6 @@ CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODVERSIONS=y CONFIG_MODULE_SRCVERSION_ALL=y CONFIG_MODULE_SIG_SHA256=y -CONFIG_UNUSED_SYMBOLS=y CONFIG_BLK_DEV_THROTTLING=y CONFIG_BLK_WBT=y CONFIG_BLK_CGROUP_IOLATENCY=y diff --git a/arch/sh/configs/edosk7760_defconfig b/arch/sh/configs/edosk7760_defconfig index 02ba62298576..d77f54e906fd 100644 --- a/arch/sh/configs/edosk7760_defconfig +++ b/arch/sh/configs/edosk7760_defconfig @@ -102,7 +102,6 @@ CONFIG_NLS_UTF8=y CONFIG_PRINTK_TIME=y # CONFIG_ENABLE_MUST_CHECK is not set CONFIG_MAGIC_SYSRQ=y -CONFIG_UNUSED_SYMBOLS=y CONFIG_DEBUG_KERNEL=y CONFIG_DEBUG_SHIRQ=y CONFIG_DETECT_HUNG_TASK=y diff --git a/arch/sh/configs/sdk7780_defconfig b/arch/sh/configs/sdk7780_defconfig index d10a0414123a..d53c4595fb2e 100644 --- a/arch/sh/configs/sdk7780_defconfig +++ b/arch/sh/configs/sdk7780_defconfig @@ -130,7 +130,6 @@ CONFIG_NLS_ISO8859_15=y CONFIG_NLS_UTF8=y # CONFIG_ENABLE_MUST_CHECK is not set CONFIG_MAGIC_SYSRQ=y -CONFIG_UNUSED_SYMBOLS=y CONFIG_DEBUG_KERNEL=y CONFIG_DETECT_HUNG_TASK=y # CONFIG_SCHED_DEBUG is not set diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index 78210793d357..9c9c4a888b1d 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -50,7 +50,6 @@ CONFIG_JUMP_LABEL=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y -# CONFIG_UNUSED_SYMBOLS is not set CONFIG_BINFMT_MISC=y CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index 9936528e1939..b60bd2d86034 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -48,7 +48,6 @@ CONFIG_JUMP_LABEL=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y -# CONFIG_UNUSED_SYMBOLS is not set CONFIG_BINFMT_MISC=y CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c index 0d210d0e83e2..b9c577a3cacc 100644 --- a/arch/x86/tools/relocs.c +++ b/arch/x86/tools/relocs.c @@ -61,8 +61,8 @@ static const char * const sym_regex_kernel[S_NSYMTYPES] = { "(__iommu_table|__apicdrivers|__smp_locks)(|_end)|" "__(start|end)_pci_.*|" "__(start|end)_builtin_fw|" - "__(start|stop)___ksymtab(|_gpl|_unused|_unused_gpl)|" - "__(start|stop)___kcrctab(|_gpl|_unused|_unused_gpl)|" + "__(start|stop)___ksymtab(|_gpl)|" + "__(start|stop)___kcrctab(|_gpl)|" "__(start|stop)___param|" "__(start|stop)___modver|" "__(start|stop)___bug_table|" diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 83243506e68b..1fa338ac6a54 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -481,20 +481,6 @@ __stop___ksymtab_gpl = .; \ } \ \ - /* Kernel symbol table: Normal unused symbols */ \ - __ksymtab_unused : AT(ADDR(__ksymtab_unused) - LOAD_OFFSET) { \ - __start___ksymtab_unused = .; \ - KEEP(*(SORT(___ksymtab_unused+*))) \ - __stop___ksymtab_unused = .; \ - } \ - \ - /* Kernel symbol table: GPL-only unused symbols */ \ - __ksymtab_unused_gpl : AT(ADDR(__ksymtab_unused_gpl) - LOAD_OFFSET) { \ - __start___ksymtab_unused_gpl = .; \ - KEEP(*(SORT(___ksymtab_unused_gpl+*))) \ - __stop___ksymtab_unused_gpl = .; \ - } \ - \ /* Kernel symbol table: Normal symbols */ \ __kcrctab : AT(ADDR(__kcrctab) - LOAD_OFFSET) { \ __start___kcrctab = .; \ @@ -509,20 +495,6 @@ __stop___kcrctab_gpl = .; \ } \ \ - /* Kernel symbol table: Normal unused symbols */ \ - __kcrctab_unused : AT(ADDR(__kcrctab_unused) - LOAD_OFFSET) { \ - __start___kcrctab_unused = .; \ - KEEP(*(SORT(___kcrctab_unused+*))) \ - __stop___kcrctab_unused = .; \ - } \ - \ - /* Kernel symbol table: GPL-only unused symbols */ \ - __kcrctab_unused_gpl : AT(ADDR(__kcrctab_unused_gpl) - LOAD_OFFSET) { \ - __start___kcrctab_unused_gpl = .; \ - KEEP(*(SORT(___kcrctab_unused_gpl+*))) \ - __stop___kcrctab_unused_gpl = .; \ - } \ - \ /* Kernel symbol table: strings */ \ __ksymtab_strings : AT(ADDR(__ksymtab_strings) - LOAD_OFFSET) { \ *(__ksymtab_strings) \ diff --git a/include/linux/export.h b/include/linux/export.h index 362b64f8d4a7..6271a5d9c988 100644 --- a/include/linux/export.h +++ b/include/linux/export.h @@ -160,14 +160,6 @@ struct kernel_symbol { #define EXPORT_SYMBOL_NS(sym, ns) __EXPORT_SYMBOL(sym, "", #ns) #define EXPORT_SYMBOL_NS_GPL(sym, ns) __EXPORT_SYMBOL(sym, "_gpl", #ns) -#ifdef CONFIG_UNUSED_SYMBOLS -#define EXPORT_UNUSED_SYMBOL(sym) _EXPORT_SYMBOL(sym, "_unused") -#define EXPORT_UNUSED_SYMBOL_GPL(sym) _EXPORT_SYMBOL(sym, "_unused_gpl") -#else -#define EXPORT_UNUSED_SYMBOL(sym) -#define EXPORT_UNUSED_SYMBOL_GPL(sym) -#endif - #endif /* !__ASSEMBLY__ */ #endif /* _LINUX_EXPORT_H */ diff --git a/include/linux/module.h b/include/linux/module.h index e6e50ee30412..59f094fa6f74 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -392,18 +392,6 @@ struct module { const s32 *gpl_crcs; bool using_gplonly_symbols; -#ifdef CONFIG_UNUSED_SYMBOLS - /* unused exported symbols. */ - const struct kernel_symbol *unused_syms; - const s32 *unused_crcs; - unsigned int num_unused_syms; - - /* GPL-only, unused exported symbols. */ - unsigned int num_unused_gpl_syms; - const struct kernel_symbol *unused_gpl_syms; - const s32 *unused_gpl_crcs; -#endif - #ifdef CONFIG_MODULE_SIG /* Signature was verified. */ bool sig_ok; diff --git a/init/Kconfig b/init/Kconfig index b77c60f8b963..11b803b45c19 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -2262,25 +2262,8 @@ config MODULE_ALLOW_MISSING_NAMESPACE_IMPORTS If unsure, say N. -config UNUSED_SYMBOLS - bool "Enable unused/obsolete exported symbols" - default y if X86 - help - Unused but exported symbols make the kernel needlessly bigger. For - that reason most of these unused exports will soon be removed. This - option is provided temporarily to provide a transition period in case - some external kernel module needs one of these symbols anyway. If you - encounter such a case in your module, consider if you are actually - using the right API. (rationale: since nobody in the kernel is using - this in a module, there is a pretty good chance it's actually the - wrong interface to use). If you really need the symbol, please send a - mail to the linux kernel mailing list mentioning the symbol and why - you really need it, and what the merge plan to the mainline kernel for - your module is. - config TRIM_UNUSED_KSYMS bool "Trim unused exported kernel symbols" - depends on !UNUSED_SYMBOLS help The kernel and some modules make many symbols available for other modules to use via EXPORT_SYMBOL() and variants. Depending diff --git a/kernel/module.c b/kernel/module.c index 95186c9d81ea..93f360250bcb 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -410,14 +410,6 @@ extern const struct kernel_symbol __start___ksymtab_gpl[]; extern const struct kernel_symbol __stop___ksymtab_gpl[]; extern const s32 __start___kcrctab[]; extern const s32 __start___kcrctab_gpl[]; -#ifdef CONFIG_UNUSED_SYMBOLS -extern const struct kernel_symbol __start___ksymtab_unused[]; -extern const struct kernel_symbol __stop___ksymtab_unused[]; -extern const struct kernel_symbol __start___ksymtab_unused_gpl[]; -extern const struct kernel_symbol __stop___ksymtab_unused_gpl[]; -extern const s32 __start___kcrctab_unused[]; -extern const s32 __start___kcrctab_unused_gpl[]; -#endif #ifndef CONFIG_MODVERSIONS #define symversion(base, idx) NULL @@ -432,7 +424,6 @@ struct symsearch { NOT_GPL_ONLY, GPL_ONLY, } license; - bool unused; }; struct find_symbol_arg { @@ -456,19 +447,6 @@ static bool check_exported_symbol(const struct symsearch *syms, if (!fsa->gplok && syms->license == GPL_ONLY) return false; - -#ifdef CONFIG_UNUSED_SYMBOLS - if (syms->unused && fsa->warn) { - pr_warn("Symbol %s is marked as UNUSED, however this module is " - "using it.\n", fsa->name); - pr_warn("This symbol will go away in the future.\n"); - pr_warn("Please evaluate if this is the right api to use and " - "if it really is, submit a report to the linux kernel " - "mailing list together with submitting your code for " - "inclusion.\n"); - } -#endif - fsa->owner = owner; fsa->crc = symversion(syms->crcs, symnum); fsa->sym = &syms->start[symnum]; @@ -535,18 +513,10 @@ static bool find_symbol(struct find_symbol_arg *fsa) { static const struct symsearch arr[] = { { __start___ksymtab, __stop___ksymtab, __start___kcrctab, - NOT_GPL_ONLY, false }, + NOT_GPL_ONLY }, { __start___ksymtab_gpl, __stop___ksymtab_gpl, __start___kcrctab_gpl, - GPL_ONLY, false }, -#ifdef CONFIG_UNUSED_SYMBOLS - { __start___ksymtab_unused, __stop___ksymtab_unused, - __start___kcrctab_unused, - NOT_GPL_ONLY, true }, - { __start___ksymtab_unused_gpl, __stop___ksymtab_unused_gpl, - __start___kcrctab_unused_gpl, - GPL_ONLY, true }, -#endif + GPL_ONLY }, }; struct module *mod; unsigned int i; @@ -561,20 +531,10 @@ static bool find_symbol(struct find_symbol_arg *fsa) lockdep_is_held(&module_mutex)) { struct symsearch arr[] = { { mod->syms, mod->syms + mod->num_syms, mod->crcs, - NOT_GPL_ONLY, false }, + NOT_GPL_ONLY }, { mod->gpl_syms, mod->gpl_syms + mod->num_gpl_syms, mod->gpl_crcs, - GPL_ONLY, false }, -#ifdef CONFIG_UNUSED_SYMBOLS - { mod->unused_syms, - mod->unused_syms + mod->num_unused_syms, - mod->unused_crcs, - NOT_GPL_ONLY, true }, - { mod->unused_gpl_syms, - mod->unused_gpl_syms + mod->num_unused_gpl_syms, - mod->unused_gpl_crcs, - GPL_ONLY, true }, -#endif + GPL_ONLY }, }; if (mod->state == MODULE_STATE_UNFORMED) @@ -2274,10 +2234,6 @@ static int verify_exported_symbols(struct module *mod) } arr[] = { { mod->syms, mod->num_syms }, { mod->gpl_syms, mod->num_gpl_syms }, -#ifdef CONFIG_UNUSED_SYMBOLS - { mod->unused_syms, mod->num_unused_syms }, - { mod->unused_gpl_syms, mod->num_unused_gpl_syms }, -#endif }; for (i = 0; i < ARRAY_SIZE(arr); i++) { @@ -3290,16 +3246,6 @@ static int find_module_sections(struct module *mod, struct load_info *info) &mod->num_gpl_syms); mod->gpl_crcs = section_addr(info, "__kcrctab_gpl"); -#ifdef CONFIG_UNUSED_SYMBOLS - mod->unused_syms = section_objs(info, "__ksymtab_unused", - sizeof(*mod->unused_syms), - &mod->num_unused_syms); - mod->unused_crcs = section_addr(info, "__kcrctab_unused"); - mod->unused_gpl_syms = section_objs(info, "__ksymtab_unused_gpl", - sizeof(*mod->unused_gpl_syms), - &mod->num_unused_gpl_syms); - mod->unused_gpl_crcs = section_addr(info, "__kcrctab_unused_gpl"); -#endif #ifdef CONFIG_CONSTRUCTORS mod->ctors = section_objs(info, ".ctors", sizeof(*mod->ctors), &mod->num_ctors); @@ -3480,13 +3426,8 @@ static int check_module_license_and_versions(struct module *mod) pr_warn("%s: module license taints kernel.\n", mod->name); #ifdef CONFIG_MODVERSIONS - if ((mod->num_syms && !mod->crcs) - || (mod->num_gpl_syms && !mod->gpl_crcs) -#ifdef CONFIG_UNUSED_SYMBOLS - || (mod->num_unused_syms && !mod->unused_crcs) - || (mod->num_unused_gpl_syms && !mod->unused_gpl_crcs) -#endif - ) { + if ((mod->num_syms && !mod->crcs) || + (mod->num_gpl_syms && !mod->gpl_crcs)) { return try_to_force_load(mod, "no versions for exported symbols"); } diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 92e888ed939f..eabd2d5467b1 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -4290,8 +4290,7 @@ sub process { if (defined $realline_next && exists $lines[$realline_next - 1] && !defined $suppress_export{$realline_next} && - ($lines[$realline_next - 1] =~ /EXPORT_SYMBOL.*\((.*)\)/ || - $lines[$realline_next - 1] =~ /EXPORT_UNUSED_SYMBOL.*\((.*)\)/)) { + ($lines[$realline_next - 1] =~ /EXPORT_SYMBOL.*\((.*)\)/)) { # Handle definitions which produce identifiers with # a prefix: # XXX(foo); @@ -4318,8 +4317,7 @@ sub process { } if (!defined $suppress_export{$linenr} && $prevline =~ /^.\s*$/ && - ($line =~ /EXPORT_SYMBOL.*\((.*)\)/ || - $line =~ /EXPORT_UNUSED_SYMBOL.*\((.*)\)/)) { + ($line =~ /EXPORT_SYMBOL.*\((.*)\)/)) { #print "FOO B <$lines[$linenr - 1]>\n"; $suppress_export{$linenr} = 2; } diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 25c1446055d1..20fc57837881 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -43,8 +43,9 @@ static int allow_missing_ns_imports; static bool error_occurred; enum export { - export_plain, export_unused, export_gpl, - export_unused_gpl, export_unknown + export_plain, + export_gpl, + export_unknown }; /* In kernel, this size is defined in linux/module.h; @@ -301,9 +302,7 @@ static const struct { enum export export; } export_list[] = { { .str = "EXPORT_SYMBOL", .export = export_plain }, - { .str = "EXPORT_UNUSED_SYMBOL", .export = export_unused }, { .str = "EXPORT_SYMBOL_GPL", .export = export_gpl }, - { .str = "EXPORT_UNUSED_SYMBOL_GPL", .export = export_unused_gpl }, { .str = "(unknown)", .export = export_unknown }, }; @@ -362,12 +361,8 @@ static enum export export_from_secname(struct elf_info *elf, unsigned int sec) if (strstarts(secname, "___ksymtab+")) return export_plain; - else if (strstarts(secname, "___ksymtab_unused+")) - return export_unused; else if (strstarts(secname, "___ksymtab_gpl+")) return export_gpl; - else if (strstarts(secname, "___ksymtab_unused_gpl+")) - return export_unused_gpl; else return export_unknown; } @@ -376,12 +371,8 @@ static enum export export_from_sec(struct elf_info *elf, unsigned int sec) { if (sec == elf->export_sec) return export_plain; - else if (sec == elf->export_unused_sec) - return export_unused; else if (sec == elf->export_gpl_sec) return export_gpl; - else if (sec == elf->export_unused_gpl_sec) - return export_unused_gpl; else return export_unknown; } @@ -585,12 +576,8 @@ static int parse_elf(struct elf_info *info, const char *filename) info->modinfo_len = sechdrs[i].sh_size; } else if (strcmp(secname, "__ksymtab") == 0) info->export_sec = i; - else if (strcmp(secname, "__ksymtab_unused") == 0) - info->export_unused_sec = i; else if (strcmp(secname, "__ksymtab_gpl") == 0) info->export_gpl_sec = i; - else if (strcmp(secname, "__ksymtab_unused_gpl") == 0) - info->export_unused_gpl_sec = i; if (sechdrs[i].sh_type == SHT_SYMTAB) { unsigned int sh_link_idx; @@ -2141,32 +2128,13 @@ static void check_for_gpl_usage(enum export exp, const char *m, const char *s) error("GPL-incompatible module %s.ko uses GPL-only symbol '%s'\n", m, s); break; - case export_unused_gpl: - error("GPL-incompatible module %s.ko uses GPL-only symbol marked UNUSED '%s'\n", - m, s); - break; case export_plain: - case export_unused: case export_unknown: /* ignore */ break; } } -static void check_for_unused(enum export exp, const char *m, const char *s) -{ - switch (exp) { - case export_unused: - case export_unused_gpl: - warn("module %s.ko uses symbol '%s' marked UNUSED\n", - m, s); - break; - default: - /* ignore */ - break; - } -} - static void check_exports(struct module *mod) { struct symbol *s, *exp; @@ -2197,7 +2165,6 @@ static void check_exports(struct module *mod) if (!mod->gpl_compatible) check_for_gpl_usage(exp->export, basename, exp->name); - check_for_unused(exp->export, basename, exp->name); } } diff --git a/scripts/mod/modpost.h b/scripts/mod/modpost.h index 834220de002b..0c47ff95c0e2 100644 --- a/scripts/mod/modpost.h +++ b/scripts/mod/modpost.h @@ -139,9 +139,7 @@ struct elf_info { Elf_Sym *symtab_start; Elf_Sym *symtab_stop; Elf_Section export_sec; - Elf_Section export_unused_sec; Elf_Section export_gpl_sec; - Elf_Section export_unused_gpl_sec; char *strtab; char *modinfo; unsigned int modinfo_len; diff --git a/scripts/module.lds.S b/scripts/module.lds.S index d82b452e8a71..24e8af579ce3 100644 --- a/scripts/module.lds.S +++ b/scripts/module.lds.S @@ -11,12 +11,8 @@ SECTIONS { __ksymtab 0 : { *(SORT(___ksymtab+*)) } __ksymtab_gpl 0 : { *(SORT(___ksymtab_gpl+*)) } - __ksymtab_unused 0 : { *(SORT(___ksymtab_unused+*)) } - __ksymtab_unused_gpl 0 : { *(SORT(___ksymtab_unused_gpl+*)) } __kcrctab 0 : { *(SORT(___kcrctab+*)) } __kcrctab_gpl 0 : { *(SORT(___kcrctab_gpl+*)) } - __kcrctab_unused 0 : { *(SORT(___kcrctab_unused+*)) } - __kcrctab_unused_gpl 0 : { *(SORT(___kcrctab_unused_gpl+*)) } .init_array 0 : ALIGN(8) { *(SORT(.init_array.*)) *(.init_array) } diff --git a/tools/include/linux/export.h b/tools/include/linux/export.h index 9f61349a8944..acb6f4daa2f0 100644 --- a/tools/include/linux/export.h +++ b/tools/include/linux/export.h @@ -3,7 +3,5 @@ #define EXPORT_SYMBOL(sym) #define EXPORT_SYMBOL_GPL(sym) -#define EXPORT_UNUSED_SYMBOL(sym) -#define EXPORT_UNUSED_SYMBOL_GPL(sym) #endif -- cgit v1.2.3 From 7aa382cfe714f61b0c29f02c31d389c506b4e2ae Mon Sep 17 00:00:00 2001 From: Hsin-Hsiung Wang Date: Sun, 7 Feb 2021 14:14:16 +0800 Subject: regulator: mt6315: Add support for MT6315 regulator The MT6315 is a regulator found on boards based on MediaTek MT8192 and probably other SoCs. It connects as a slave to SoC using SPMI. Signed-off-by: Hsin-Hsiung Wang Link: https://lore.kernel.org/r/1612678457-11548-3-git-send-email-hsin-hsiung.wang@mediatek.com Signed-off-by: Mark Brown --- drivers/regulator/Kconfig | 10 + drivers/regulator/Makefile | 1 + drivers/regulator/mt6315-regulator.c | 299 +++++++++++++++++++++++++++++ include/linux/regulator/mt6315-regulator.h | 44 +++++ 4 files changed, 354 insertions(+) create mode 100644 drivers/regulator/mt6315-regulator.c create mode 100644 include/linux/regulator/mt6315-regulator.h (limited to 'include') diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig index 88316b8a65d2..77c43134bc9e 100644 --- a/drivers/regulator/Kconfig +++ b/drivers/regulator/Kconfig @@ -731,6 +731,16 @@ config REGULATOR_MT6311 This driver supports the control of different power rails of device through regulator interface. +config REGULATOR_MT6315 + tristate "MediaTek MT6315 PMIC" + depends on SPMI + select REGMAP_SPMI + help + Say y here to select this option to enable the power regulator of + MediaTek MT6315 PMIC. + This driver supports the control of different power rails of device + through regulator interface. + config REGULATOR_MT6323 tristate "MediaTek MT6323 PMIC" depends on MFD_MT6397 diff --git a/drivers/regulator/Makefile b/drivers/regulator/Makefile index d1957629537b..44d2f8bf4b74 100644 --- a/drivers/regulator/Makefile +++ b/drivers/regulator/Makefile @@ -89,6 +89,7 @@ obj-$(CONFIG_REGULATOR_MP8859) += mp8859.o obj-$(CONFIG_REGULATOR_MP886X) += mp886x.o obj-$(CONFIG_REGULATOR_MPQ7920) += mpq7920.o obj-$(CONFIG_REGULATOR_MT6311) += mt6311-regulator.o +obj-$(CONFIG_REGULATOR_MT6315) += mt6315-regulator.o obj-$(CONFIG_REGULATOR_MT6323) += mt6323-regulator.o obj-$(CONFIG_REGULATOR_MT6358) += mt6358-regulator.o obj-$(CONFIG_REGULATOR_MT6360) += mt6360-regulator.o diff --git a/drivers/regulator/mt6315-regulator.c b/drivers/regulator/mt6315-regulator.c new file mode 100644 index 000000000000..d49a1534d8e9 --- /dev/null +++ b/drivers/regulator/mt6315-regulator.c @@ -0,0 +1,299 @@ +// SPDX-License-Identifier: GPL-2.0 +// +// Copyright (c) 2021 MediaTek Inc. + +#include +#include +#include +#include +#include +#include +#include +#include + +#define MT6315_BUCK_MODE_AUTO 0 +#define MT6315_BUCK_MODE_FORCE_PWM 1 +#define MT6315_BUCK_MODE_LP 2 + +struct mt6315_regulator_info { + struct regulator_desc desc; + u32 status_reg; + u32 lp_mode_mask; + u32 lp_mode_shift; +}; + +struct mt_regulator_init_data { + u32 modeset_mask[MT6315_VBUCK_MAX]; +}; + +struct mt6315_chip { + struct device *dev; + struct regmap *regmap; +}; + +#define MT_BUCK(_name, _bid, _vsel) \ +[_bid] = { \ + .desc = { \ + .name = _name, \ + .of_match = of_match_ptr(_name), \ + .regulators_node = "regulators", \ + .ops = &mt6315_volt_range_ops, \ + .type = REGULATOR_VOLTAGE, \ + .id = _bid, \ + .owner = THIS_MODULE, \ + .n_voltages = 0xbf, \ + .linear_ranges = mt_volt_range1, \ + .n_linear_ranges = ARRAY_SIZE(mt_volt_range1), \ + .vsel_reg = _vsel, \ + .vsel_mask = 0xff, \ + .enable_reg = MT6315_BUCK_TOP_CON0, \ + .enable_mask = BIT(_bid), \ + .of_map_mode = mt6315_map_mode, \ + }, \ + .status_reg = _bid##_DBG4, \ + .lp_mode_mask = BIT(_bid), \ + .lp_mode_shift = _bid, \ +} + +static const struct linear_range mt_volt_range1[] = { + REGULATOR_LINEAR_RANGE(0, 0, 0xbf, 6250), +}; + +static unsigned int mt6315_map_mode(u32 mode) +{ + switch (mode) { + case MT6315_BUCK_MODE_AUTO: + return REGULATOR_MODE_NORMAL; + case MT6315_BUCK_MODE_FORCE_PWM: + return REGULATOR_MODE_FAST; + case MT6315_BUCK_MODE_LP: + return REGULATOR_MODE_IDLE; + default: + return -EINVAL; + } +} + +static unsigned int mt6315_regulator_get_mode(struct regulator_dev *rdev) +{ + struct mt_regulator_init_data *init = rdev_get_drvdata(rdev); + const struct mt6315_regulator_info *info; + int ret, regval; + u32 modeset_mask; + + info = container_of(rdev->desc, struct mt6315_regulator_info, desc); + modeset_mask = init->modeset_mask[rdev_get_id(rdev)]; + ret = regmap_read(rdev->regmap, MT6315_BUCK_TOP_4PHASE_ANA_CON42, ®val); + if (ret != 0) { + dev_notice(&rdev->dev, "Failed to get mode: %d\n", ret); + return ret; + } + + if ((regval & modeset_mask) == modeset_mask) + return REGULATOR_MODE_FAST; + + ret = regmap_read(rdev->regmap, MT6315_BUCK_TOP_CON1, ®val); + if (ret != 0) { + dev_notice(&rdev->dev, "Failed to get lp mode: %d\n", ret); + return ret; + } + + if (regval & info->lp_mode_mask) + return REGULATOR_MODE_IDLE; + else + return REGULATOR_MODE_NORMAL; +} + +static int mt6315_regulator_set_mode(struct regulator_dev *rdev, + u32 mode) +{ + struct mt_regulator_init_data *init = rdev_get_drvdata(rdev); + const struct mt6315_regulator_info *info; + int ret, val, curr_mode; + u32 modeset_mask; + + info = container_of(rdev->desc, struct mt6315_regulator_info, desc); + modeset_mask = init->modeset_mask[rdev_get_id(rdev)]; + curr_mode = mt6315_regulator_get_mode(rdev); + switch (mode) { + case REGULATOR_MODE_FAST: + ret = regmap_update_bits(rdev->regmap, + MT6315_BUCK_TOP_4PHASE_ANA_CON42, + modeset_mask, + modeset_mask); + break; + case REGULATOR_MODE_NORMAL: + if (curr_mode == REGULATOR_MODE_FAST) { + ret = regmap_update_bits(rdev->regmap, + MT6315_BUCK_TOP_4PHASE_ANA_CON42, + modeset_mask, + 0); + } else if (curr_mode == REGULATOR_MODE_IDLE) { + ret = regmap_update_bits(rdev->regmap, + MT6315_BUCK_TOP_CON1, + info->lp_mode_mask, + 0); + usleep_range(100, 110); + } else { + ret = -EINVAL; + } + break; + case REGULATOR_MODE_IDLE: + val = MT6315_BUCK_MODE_LP >> 1; + val <<= info->lp_mode_shift; + ret = regmap_update_bits(rdev->regmap, + MT6315_BUCK_TOP_CON1, + info->lp_mode_mask, + val); + break; + default: + ret = -EINVAL; + dev_notice(&rdev->dev, "Unsupported mode: %d\n", mode); + break; + } + + if (ret != 0) { + dev_notice(&rdev->dev, "Failed to set mode: %d\n", ret); + return ret; + } + + return 0; +} + +static int mt6315_get_status(struct regulator_dev *rdev) +{ + const struct mt6315_regulator_info *info; + int ret; + u32 regval; + + info = container_of(rdev->desc, struct mt6315_regulator_info, desc); + ret = regmap_read(rdev->regmap, info->status_reg, ®val); + if (ret < 0) { + dev_notice(&rdev->dev, "Failed to get enable reg: %d\n", ret); + return ret; + } + + return (regval & BIT(0)) ? REGULATOR_STATUS_ON : REGULATOR_STATUS_OFF; +} + +static const struct regulator_ops mt6315_volt_range_ops = { + .list_voltage = regulator_list_voltage_linear_range, + .map_voltage = regulator_map_voltage_linear_range, + .set_voltage_sel = regulator_set_voltage_sel_regmap, + .get_voltage_sel = regulator_get_voltage_sel_regmap, + .set_voltage_time_sel = regulator_set_voltage_time_sel, + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .is_enabled = regulator_is_enabled_regmap, + .get_status = mt6315_get_status, + .set_mode = mt6315_regulator_set_mode, + .get_mode = mt6315_regulator_get_mode, +}; + +static const struct mt6315_regulator_info mt6315_regulators[MT6315_VBUCK_MAX] = { + MT_BUCK("vbuck1", MT6315_VBUCK1, MT6315_BUCK_TOP_ELR0), + MT_BUCK("vbuck2", MT6315_VBUCK2, MT6315_BUCK_TOP_ELR2), + MT_BUCK("vbuck3", MT6315_VBUCK3, MT6315_BUCK_TOP_ELR4), + MT_BUCK("vbuck4", MT6315_VBUCK4, MT6315_BUCK_TOP_ELR6), +}; + +static const struct regmap_config mt6315_regmap_config = { + .reg_bits = 16, + .val_bits = 8, + .max_register = 0x16d0, + .fast_io = true, +}; + +static const struct of_device_id mt6315_of_match[] = { + { + .compatible = "mediatek,mt6315-regulator", + }, { + /* sentinel */ + }, +}; +MODULE_DEVICE_TABLE(of, mt6315_of_match); + +static int mt6315_regulator_probe(struct spmi_device *pdev) +{ + struct device *dev = &pdev->dev; + struct regmap *regmap; + struct mt6315_chip *chip; + struct mt_regulator_init_data *init_data; + struct regulator_config config = {}; + struct regulator_dev *rdev; + int i; + + regmap = devm_regmap_init_spmi_ext(pdev, &mt6315_regmap_config); + if (!regmap) + return -ENODEV; + + chip = devm_kzalloc(dev, sizeof(struct mt6315_chip), GFP_KERNEL); + if (!chip) + return -ENOMEM; + + init_data = devm_kzalloc(dev, sizeof(struct mt_regulator_init_data), GFP_KERNEL); + if (!init_data) + return -ENOMEM; + + switch (pdev->usid) { + case MT6315_PP: + init_data->modeset_mask[MT6315_VBUCK1] = BIT(MT6315_VBUCK1) | BIT(MT6315_VBUCK2) | + BIT(MT6315_VBUCK4); + break; + case MT6315_SP: + case MT6315_RP: + init_data->modeset_mask[MT6315_VBUCK1] = BIT(MT6315_VBUCK1) | BIT(MT6315_VBUCK2); + break; + default: + init_data->modeset_mask[MT6315_VBUCK1] = BIT(MT6315_VBUCK1); + break; + } + for (i = MT6315_VBUCK2; i < MT6315_VBUCK_MAX; i++) + init_data->modeset_mask[i] = BIT(i); + + chip->dev = dev; + chip->regmap = regmap; + dev_set_drvdata(dev, chip); + + config.dev = dev; + config.regmap = regmap; + for (i = MT6315_VBUCK1; i < MT6315_VBUCK_MAX; i++) { + config.driver_data = init_data; + rdev = devm_regulator_register(dev, &mt6315_regulators[i].desc, &config); + if (IS_ERR(rdev)) { + dev_notice(dev, "Failed to register %s\n", mt6315_regulators[i].desc.name); + continue; + } + } + + return 0; +} + +static void mt6315_regulator_shutdown(struct spmi_device *pdev) +{ + struct mt6315_chip *chip = dev_get_drvdata(&pdev->dev); + int ret = 0; + + ret |= regmap_write(chip->regmap, MT6315_TOP_TMA_KEY_H, PROTECTION_KEY_H); + ret |= regmap_write(chip->regmap, MT6315_TOP_TMA_KEY, PROTECTION_KEY); + ret |= regmap_update_bits(chip->regmap, MT6315_TOP2_ELR7, 1, 1); + ret |= regmap_write(chip->regmap, MT6315_TOP_TMA_KEY, 0); + ret |= regmap_write(chip->regmap, MT6315_TOP_TMA_KEY_H, 0); + if (ret < 0) + dev_notice(&pdev->dev, "[%#x] Failed to enable power off sequence. %d\n", + pdev->usid, ret); +} + +static struct spmi_driver mt6315_regulator_driver = { + .driver = { + .name = "mt6315-regulator", + .of_match_table = mt6315_of_match, + }, + .probe = mt6315_regulator_probe, + .shutdown = mt6315_regulator_shutdown, +}; + +module_spmi_driver(mt6315_regulator_driver); + +MODULE_AUTHOR("Hsin-Hsiung Wang "); +MODULE_DESCRIPTION("Regulator Driver for MediaTek MT6315 PMIC"); +MODULE_LICENSE("GPL"); diff --git a/include/linux/regulator/mt6315-regulator.h b/include/linux/regulator/mt6315-regulator.h new file mode 100644 index 000000000000..3b80d3f3910c --- /dev/null +++ b/include/linux/regulator/mt6315-regulator.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2021 MediaTek Inc. + */ + +#ifndef __LINUX_REGULATOR_MT6315_H +#define __LINUX_REGULATOR_MT6315_H + +#define MT6315_RP 3 +#define MT6315_PP 6 +#define MT6315_SP 7 + +enum { + MT6315_VBUCK1 = 0, + MT6315_VBUCK2, + MT6315_VBUCK3, + MT6315_VBUCK4, + MT6315_VBUCK_MAX, +}; + +/* Register */ +#define MT6315_TOP2_ELR7 0x139 +#define MT6315_TOP_TMA_KEY 0x39F +#define MT6315_TOP_TMA_KEY_H 0x3A0 +#define MT6315_BUCK_TOP_CON0 0x1440 +#define MT6315_BUCK_TOP_CON1 0x1443 +#define MT6315_BUCK_TOP_ELR0 0x1449 +#define MT6315_BUCK_TOP_ELR2 0x144B +#define MT6315_BUCK_TOP_ELR4 0x144D +#define MT6315_BUCK_TOP_ELR6 0x144F +#define MT6315_VBUCK1_DBG0 0x1499 +#define MT6315_VBUCK1_DBG4 0x149D +#define MT6315_VBUCK2_DBG0 0x1519 +#define MT6315_VBUCK2_DBG4 0x151D +#define MT6315_VBUCK3_DBG0 0x1599 +#define MT6315_VBUCK3_DBG4 0x159D +#define MT6315_VBUCK4_DBG0 0x1619 +#define MT6315_VBUCK4_DBG4 0x161D +#define MT6315_BUCK_TOP_4PHASE_ANA_CON42 0x16B1 + +#define PROTECTION_KEY_H 0x9C +#define PROTECTION_KEY 0xEA + +#endif /* __LINUX_REGULATOR_MT6315_H */ -- cgit v1.2.3 From 951f6ccfcbb7e4a18bf5fef1fb373d21e5831957 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Tue, 2 Feb 2021 11:19:24 +0100 Subject: mmc: core: Drop redundant member in struct mmc host The Kconfig option to use the blk-mq support was removed in commit 1bec43a3b181 ("mmc: core: Remove option not to use blk-mq"), but forgot to remove the use_blk_mq member in the struct mmc_host, let's fix it. Signed-off-by: Ulf Hansson Link: https://lore.kernel.org/r/20210202101924.69970-1-ulf.hansson@linaro.org --- include/linux/mmc/host.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 927ba7566617..26a3c7bc29ae 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -429,7 +429,6 @@ struct mmc_host { unsigned int doing_retune:1; /* re-tuning in progress */ unsigned int retune_now:1; /* do re-tuning at next req */ unsigned int retune_paused:1; /* re-tuning is temporarily disabled */ - unsigned int use_blk_mq:1; /* use blk-mq */ unsigned int retune_crc_disable:1; /* don't trigger retune upon crc */ unsigned int can_dma_map_merge:1; /* merging can be used */ -- cgit v1.2.3 From 40c735db06e16bf29c74c3626318719783be3784 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Tue, 2 Feb 2021 11:16:26 +0100 Subject: mmc: core: Drop redundant bouncesz from struct mmc_card The commit de3ee99b097d ("mmc: Delete bounce buffer handling") removed the bounce buffer handling from the mmc core, but forgot to remove the bouncesz member from the struct mmc_card, let's fix it. Signed-off-by: Ulf Hansson Link: https://lore.kernel.org/r/20210202101626.64503-1-ulf.hansson@linaro.org --- include/linux/mmc/card.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index 42df06c6b19c..f9ad35dd6012 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -311,7 +311,6 @@ struct mmc_card { struct mmc_part part[MMC_NUM_PHY_PARTITION]; /* physical partitions */ unsigned int nr_parts; - unsigned int bouncesz; /* Bounce buffer size */ struct workqueue_struct *complete_wq; /* Private workqueue */ }; -- cgit v1.2.3 From 883c36a32fc031046218ef5802023d5aa54d6cb0 Mon Sep 17 00:00:00 2001 From: Bhaskar Chowdhury Date: Mon, 8 Feb 2021 17:19:28 +0530 Subject: spi: Change provied to provided in the file spi.h s/provied/provided/ Signed-off-by: Bhaskar Chowdhury Link: https://lore.kernel.org/r/20210208114928.32241-1-unixbhaskar@gmail.com Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 797ef28fa7d5..592897fa4f03 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -622,7 +622,7 @@ struct spi_controller { /* * These hooks are for drivers that use a generic implementation - * of transfer_one_message() provied by the core. + * of transfer_one_message() provided by the core. */ void (*set_cs)(struct spi_device *spi, bool enable); int (*transfer_one)(struct spi_controller *ctlr, struct spi_device *spi, -- cgit v1.2.3 From 866eef48d80234e1ea3a2f78b54afc563be3ea4a Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Fri, 5 Feb 2021 17:10:18 +0000 Subject: gfs2: Add trusted xattr support Add support for an additional filesystem version (sb_fs_format = 1802). When a filesystem with the new version is mounted, the filesystem supports "trusted.*" xattrs. In addition, version 1802 filesystems implement a form of forward compatibility for xattrs: when xattrs with an unknown prefix (ea_type) are found on a version 1802 filesystem, those attributes are not shown by listxattr, and they are not accessible by getxattr, setxattr, or removexattr. This mechanism might turn out to be what we need in the future, but if not, we can always bump the filesystem version and break compatibility instead. Signed-off-by: Andreas Gruenbacher Signed-off-by: Andrew Price --- fs/gfs2/ops_fstype.c | 14 +++++++++++- fs/gfs2/super.h | 4 +++- fs/gfs2/xattr.c | 48 ++++++++++++++++++++++++++++++++++++---- include/uapi/linux/gfs2_ondisk.h | 5 +++-- 4 files changed, 63 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index c6537e94f4d8..d89764856f21 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -489,6 +489,19 @@ static int init_sb(struct gfs2_sbd *sdp, int silent) goto out; } + switch(sdp->sd_sb.sb_fs_format) { + case GFS2_FS_FORMAT_MAX: + sb->s_xattr = gfs2_xattr_handlers_max; + break; + + case GFS2_FS_FORMAT_MIN: + sb->s_xattr = gfs2_xattr_handlers_min; + break; + + default: + BUG(); + } + /* Set up the buffer cache and SB for real */ if (sdp->sd_sb.sb_bsize < bdev_logical_block_size(sb->s_bdev)) { ret = -EINVAL; @@ -1110,7 +1123,6 @@ static int gfs2_fill_super(struct super_block *sb, struct fs_context *fc) sb->s_op = &gfs2_super_ops; sb->s_d_op = &gfs2_dops; sb->s_export_op = &gfs2_export_ops; - sb->s_xattr = gfs2_xattr_handlers; sb->s_qcop = &gfs2_quotactl_ops; sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP; sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE; diff --git a/fs/gfs2/super.h b/fs/gfs2/super.h index 977079693bdc..08e502dec7ec 100644 --- a/fs/gfs2/super.h +++ b/fs/gfs2/super.h @@ -58,7 +58,9 @@ extern struct file_system_type gfs2meta_fs_type; extern const struct export_operations gfs2_export_ops; extern const struct super_operations gfs2_super_ops; extern const struct dentry_operations gfs2_dops; -extern const struct xattr_handler *gfs2_xattr_handlers[]; + +extern const struct xattr_handler *gfs2_xattr_handlers_max[]; +extern const struct xattr_handler **gfs2_xattr_handlers_min; #endif /* __SUPER_DOT_H__ */ diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c index 9d7667bc4292..2b520ac49d5f 100644 --- a/fs/gfs2/xattr.c +++ b/fs/gfs2/xattr.c @@ -70,6 +70,20 @@ static int ea_check_size(struct gfs2_sbd *sdp, unsigned int nsize, size_t dsize) return 0; } +static bool gfs2_eatype_valid(struct gfs2_sbd *sdp, u8 type) +{ + switch(sdp->sd_sb.sb_fs_format) { + case GFS2_FS_FORMAT_MAX: + return true; + + case GFS2_FS_FORMAT_MIN: + return type <= GFS2_EATYPE_SECURITY; + + default: + return false; + } +} + typedef int (*ea_call_t) (struct gfs2_inode *ip, struct buffer_head *bh, struct gfs2_ea_header *ea, struct gfs2_ea_header *prev, void *private); @@ -77,6 +91,7 @@ typedef int (*ea_call_t) (struct gfs2_inode *ip, struct buffer_head *bh, static int ea_foreach_i(struct gfs2_inode *ip, struct buffer_head *bh, ea_call_t ea_call, void *data) { + struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct gfs2_ea_header *ea, *prev = NULL; int error = 0; @@ -89,9 +104,8 @@ static int ea_foreach_i(struct gfs2_inode *ip, struct buffer_head *bh, if (!(bh->b_data <= (char *)ea && (char *)GFS2_EA2NEXT(ea) <= bh->b_data + bh->b_size)) goto fail; - if (!GFS2_EATYPE_VALID(ea->ea_type)) + if (!gfs2_eatype_valid(sdp, ea->ea_type)) goto fail; - error = ea_call(ip, bh, ea, prev, data); if (error) return error; @@ -344,6 +358,7 @@ static int ea_list_i(struct gfs2_inode *ip, struct buffer_head *bh, struct gfs2_ea_header *ea, struct gfs2_ea_header *prev, void *private) { + struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct ea_list *ei = private; struct gfs2_ea_request *er = ei->ei_er; unsigned int ea_size; @@ -353,6 +368,8 @@ static int ea_list_i(struct gfs2_inode *ip, struct buffer_head *bh, if (ea->ea_type == GFS2_EATYPE_UNUSED) return 0; + BUG_ON(ea->ea_type > GFS2_EATYPE_SECURITY && + sdp->sd_sb.sb_fs_format == GFS2_FS_FORMAT_MIN); switch (ea->ea_type) { case GFS2_EATYPE_USR: prefix = "user."; @@ -366,8 +383,12 @@ static int ea_list_i(struct gfs2_inode *ip, struct buffer_head *bh, prefix = "security."; l = 9; break; + case GFS2_EATYPE_TRUSTED: + prefix = "trusted."; + l = 8; + break; default: - BUG(); + return 0; } ea_size = l + ea->ea_name_len + 1; @@ -1463,7 +1484,25 @@ static const struct xattr_handler gfs2_xattr_security_handler = { .set = gfs2_xattr_set, }; -const struct xattr_handler *gfs2_xattr_handlers[] = { +static bool +gfs2_xattr_trusted_list(struct dentry *dentry) +{ + return capable(CAP_SYS_ADMIN); +} + +static const struct xattr_handler gfs2_xattr_trusted_handler = { + .prefix = XATTR_TRUSTED_PREFIX, + .flags = GFS2_EATYPE_TRUSTED, + .list = gfs2_xattr_trusted_list, + .get = gfs2_xattr_get, + .set = gfs2_xattr_set, +}; + +const struct xattr_handler *gfs2_xattr_handlers_max[] = { + /* GFS2_FS_FORMAT_MAX */ + &gfs2_xattr_trusted_handler, + + /* GFS2_FS_FORMAT_MIN */ &gfs2_xattr_user_handler, &gfs2_xattr_security_handler, &posix_acl_access_xattr_handler, @@ -1471,3 +1510,4 @@ const struct xattr_handler *gfs2_xattr_handlers[] = { NULL, }; +const struct xattr_handler **gfs2_xattr_handlers_min = gfs2_xattr_handlers_max + 1; diff --git a/include/uapi/linux/gfs2_ondisk.h b/include/uapi/linux/gfs2_ondisk.h index 07e508e6691b..6ec4291bcc7a 100644 --- a/include/uapi/linux/gfs2_ondisk.h +++ b/include/uapi/linux/gfs2_ondisk.h @@ -47,7 +47,7 @@ #define GFS2_FORMAT_DE 1200 #define GFS2_FORMAT_QU 1500 /* These are part of the superblock */ -#define GFS2_FORMAT_FS 1801 +#define GFS2_FORMAT_FS 1802 #define GFS2_FORMAT_MULTI 1900 /* @@ -389,8 +389,9 @@ struct gfs2_leaf { #define GFS2_EATYPE_USR 1 #define GFS2_EATYPE_SYS 2 #define GFS2_EATYPE_SECURITY 3 +#define GFS2_EATYPE_TRUSTED 4 -#define GFS2_EATYPE_LAST 3 +#define GFS2_EATYPE_LAST 4 #define GFS2_EATYPE_VALID(x) ((x) <= GFS2_EATYPE_LAST) #define GFS2_EAFLAG_LAST 0x01 /* last ea in block */ -- cgit v1.2.3 From db783e769a950b3f9502dfbc0f7fdbea499a1da6 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Thu, 17 Dec 2020 08:34:20 +0000 Subject: mfd: Standardise MFD_CELL_* helper names Start all helpers with "MFD_CELL_". Cc: Gene Chen Cc: linux-mediatek@lists.infradead.org Signed-off-by: Lee Jones Reviewed-by: Linus Walleij Reviewed-by: Matthias Brugger Signed-off-by: Lee Jones --- drivers/mfd/ab8500-core.c | 42 +++++++++++++++++++++--------------------- drivers/mfd/db8500-prcmu.c | 6 +++--- drivers/mfd/mt6360-core.c | 12 ++++++------ include/linux/mfd/core.h | 6 +++--- 4 files changed, 33 insertions(+), 33 deletions(-) (limited to 'include') diff --git a/drivers/mfd/ab8500-core.c b/drivers/mfd/ab8500-core.c index a3bac9da8cbb..ba8da061af0e 100644 --- a/drivers/mfd/ab8500-core.c +++ b/drivers/mfd/ab8500-core.c @@ -610,52 +610,52 @@ int ab8500_suspend(struct ab8500 *ab8500) } static const struct mfd_cell ab8500_bm_devs[] = { - OF_MFD_CELL("ab8500-charger", NULL, &ab8500_bm_data, + MFD_CELL_OF("ab8500-charger", NULL, &ab8500_bm_data, sizeof(ab8500_bm_data), 0, "stericsson,ab8500-charger"), - OF_MFD_CELL("ab8500-btemp", NULL, &ab8500_bm_data, + MFD_CELL_OF("ab8500-btemp", NULL, &ab8500_bm_data, sizeof(ab8500_bm_data), 0, "stericsson,ab8500-btemp"), - OF_MFD_CELL("ab8500-fg", NULL, &ab8500_bm_data, + MFD_CELL_OF("ab8500-fg", NULL, &ab8500_bm_data, sizeof(ab8500_bm_data), 0, "stericsson,ab8500-fg"), - OF_MFD_CELL("ab8500-chargalg", NULL, &ab8500_bm_data, + MFD_CELL_OF("ab8500-chargalg", NULL, &ab8500_bm_data, sizeof(ab8500_bm_data), 0, "stericsson,ab8500-chargalg"), }; static const struct mfd_cell ab8500_devs[] = { #ifdef CONFIG_DEBUG_FS - OF_MFD_CELL("ab8500-debug", + MFD_CELL_OF("ab8500-debug", NULL, NULL, 0, 0, "stericsson,ab8500-debug"), #endif - OF_MFD_CELL("ab8500-sysctrl", + MFD_CELL_OF("ab8500-sysctrl", NULL, NULL, 0, 0, "stericsson,ab8500-sysctrl"), - OF_MFD_CELL("ab8500-ext-regulator", + MFD_CELL_OF("ab8500-ext-regulator", NULL, NULL, 0, 0, "stericsson,ab8500-ext-regulator"), - OF_MFD_CELL("ab8500-regulator", + MFD_CELL_OF("ab8500-regulator", NULL, NULL, 0, 0, "stericsson,ab8500-regulator"), - OF_MFD_CELL("ab8500-clk", + MFD_CELL_OF("ab8500-clk", NULL, NULL, 0, 0, "stericsson,ab8500-clk"), - OF_MFD_CELL("ab8500-gpadc", + MFD_CELL_OF("ab8500-gpadc", NULL, NULL, 0, 0, "stericsson,ab8500-gpadc"), - OF_MFD_CELL("ab8500-rtc", + MFD_CELL_OF("ab8500-rtc", NULL, NULL, 0, 0, "stericsson,ab8500-rtc"), - OF_MFD_CELL("ab8500-acc-det", + MFD_CELL_OF("ab8500-acc-det", NULL, NULL, 0, 0, "stericsson,ab8500-acc-det"), - OF_MFD_CELL("ab8500-poweron-key", + MFD_CELL_OF("ab8500-poweron-key", NULL, NULL, 0, 0, "stericsson,ab8500-poweron-key"), - OF_MFD_CELL("ab8500-pwm", + MFD_CELL_OF("ab8500-pwm", NULL, NULL, 0, 1, "stericsson,ab8500-pwm"), - OF_MFD_CELL("ab8500-pwm", + MFD_CELL_OF("ab8500-pwm", NULL, NULL, 0, 2, "stericsson,ab8500-pwm"), - OF_MFD_CELL("ab8500-pwm", + MFD_CELL_OF("ab8500-pwm", NULL, NULL, 0, 3, "stericsson,ab8500-pwm"), - OF_MFD_CELL("ab8500-denc", + MFD_CELL_OF("ab8500-denc", NULL, NULL, 0, 0, "stericsson,ab8500-denc"), - OF_MFD_CELL("pinctrl-ab8500", + MFD_CELL_OF("pinctrl-ab8500", NULL, NULL, 0, 0, "stericsson,ab8500-gpio"), - OF_MFD_CELL("abx500-temp", + MFD_CELL_OF("abx500-temp", NULL, NULL, 0, 0, "stericsson,abx500-temp"), - OF_MFD_CELL("ab8500-usb", + MFD_CELL_OF("ab8500-usb", NULL, NULL, 0, 0, "stericsson,ab8500-usb"), - OF_MFD_CELL("ab8500-codec", + MFD_CELL_OF("ab8500-codec", NULL, NULL, 0, 0, "stericsson,ab8500-codec"), }; diff --git a/drivers/mfd/db8500-prcmu.c b/drivers/mfd/db8500-prcmu.c index a5983d515db0..167faac9b75b 100644 --- a/drivers/mfd/db8500-prcmu.c +++ b/drivers/mfd/db8500-prcmu.c @@ -2954,12 +2954,12 @@ static const struct mfd_cell common_prcmu_devs[] = { }; static const struct mfd_cell db8500_prcmu_devs[] = { - OF_MFD_CELL("db8500-prcmu-regulators", NULL, + MFD_CELL_OF("db8500-prcmu-regulators", NULL, &db8500_regulators, sizeof(db8500_regulators), 0, "stericsson,db8500-prcmu-regulator"), - OF_MFD_CELL("cpuidle-dbx500", + MFD_CELL_OF("cpuidle-dbx500", NULL, NULL, 0, 0, "stericsson,cpuidle-dbx500"), - OF_MFD_CELL("db8500-thermal", + MFD_CELL_OF("db8500-thermal", NULL, NULL, 0, 0, "stericsson,db8500-thermal"), }; diff --git a/drivers/mfd/mt6360-core.c b/drivers/mfd/mt6360-core.c index 4661c1b29a72..480722acf706 100644 --- a/drivers/mfd/mt6360-core.c +++ b/drivers/mfd/mt6360-core.c @@ -292,17 +292,17 @@ static const struct resource mt6360_ldo_resources[] = { }; static const struct mfd_cell mt6360_devs[] = { - OF_MFD_CELL("mt6360_adc", mt6360_adc_resources, + MFD_CELL_OF("mt6360_adc", mt6360_adc_resources, NULL, 0, 0, "mediatek,mt6360_adc"), - OF_MFD_CELL("mt6360_chg", mt6360_chg_resources, + MFD_CELL_OF("mt6360_chg", mt6360_chg_resources, NULL, 0, 0, "mediatek,mt6360_chg"), - OF_MFD_CELL("mt6360_led", mt6360_led_resources, + MFD_CELL_OF("mt6360_led", mt6360_led_resources, NULL, 0, 0, "mediatek,mt6360_led"), - OF_MFD_CELL("mt6360_pmic", mt6360_pmic_resources, + MFD_CELL_OF("mt6360_pmic", mt6360_pmic_resources, NULL, 0, 0, "mediatek,mt6360_pmic"), - OF_MFD_CELL("mt6360_ldo", mt6360_ldo_resources, + MFD_CELL_OF("mt6360_ldo", mt6360_ldo_resources, NULL, 0, 0, "mediatek,mt6360_ldo"), - OF_MFD_CELL("mt6360_tcpc", NULL, + MFD_CELL_OF("mt6360_tcpc", NULL, NULL, 0, 0, "mediatek,mt6360_tcpc"), }; diff --git a/include/linux/mfd/core.h b/include/linux/mfd/core.h index 4b35baa14d30..2009c4b936d9 100644 --- a/include/linux/mfd/core.h +++ b/include/linux/mfd/core.h @@ -28,13 +28,13 @@ .id = (_id), \ } -#define OF_MFD_CELL_REG(_name, _res, _pdata, _pdsize, _id, _compat, _of_reg) \ +#define MFD_CELL_OF_REG(_name, _res, _pdata, _pdsize, _id, _compat, _of_reg) \ MFD_CELL_ALL(_name, _res, _pdata, _pdsize, _id, _compat, _of_reg, true, NULL) -#define OF_MFD_CELL(_name, _res, _pdata, _pdsize, _id, _compat) \ +#define MFD_CELL_OF(_name, _res, _pdata, _pdsize, _id, _compat) \ MFD_CELL_ALL(_name, _res, _pdata, _pdsize, _id, _compat, 0, false, NULL) -#define ACPI_MFD_CELL(_name, _res, _pdata, _pdsize, _id, _match) \ +#define MFD_CELL_ACPI(_name, _res, _pdata, _pdsize, _id, _match) \ MFD_CELL_ALL(_name, _res, _pdata, _pdsize, _id, NULL, 0, false, _match) #define MFD_CELL_BASIC(_name, _res, _pdata, _pdsize, _id) \ -- cgit v1.2.3 From 296f5568c6ee906e2a8db00adc751674f1745bd8 Mon Sep 17 00:00:00 2001 From: Russ Weight Date: Thu, 14 Jan 2021 15:16:48 -0800 Subject: mfd: intel-m10-bmc: Expose MAC address and count Create two sysfs entries for exposing the MAC address and count from the MAX10 BMC register space. The MAC address is the first in a sequential block of MAC addresses reserved for the FPGA card. The MAC count is the number of MAC addresses in the reserved block. Signed-off-by: Russ Weight Signed-off-by: Xu Yilun Signed-off-by: Lee Jones --- .../ABI/testing/sysfs-driver-intel-m10-bmc | 21 +++++++++++ drivers/mfd/intel-m10-bmc.c | 43 ++++++++++++++++++++++ include/linux/mfd/intel-m10-bmc.h | 9 +++++ 3 files changed, 73 insertions(+) (limited to 'include') diff --git a/Documentation/ABI/testing/sysfs-driver-intel-m10-bmc b/Documentation/ABI/testing/sysfs-driver-intel-m10-bmc index 979a2d62513f..9773925138af 100644 --- a/Documentation/ABI/testing/sysfs-driver-intel-m10-bmc +++ b/Documentation/ABI/testing/sysfs-driver-intel-m10-bmc @@ -13,3 +13,24 @@ Contact: Xu Yilun Description: Read only. Returns the firmware version of Intel MAX10 BMC chip. Format: "0x%x". + +What: /sys/bus/spi/devices/.../mac_address +Date: January 2021 +KernelVersion: 5.12 +Contact: Russ Weight +Description: Read only. Returns the first MAC address in a block + of sequential MAC addresses assigned to the board + that is managed by the Intel MAX10 BMC. It is stored in + FLASH storage and is mirrored in the MAX10 BMC register + space. + Format: "%02x:%02x:%02x:%02x:%02x:%02x". + +What: /sys/bus/spi/devices/.../mac_count +Date: January 2021 +KernelVersion: 5.12 +Contact: Russ Weight +Description: Read only. Returns the number of sequential MAC + addresses assigned to the board managed by the Intel + MAX10 BMC. This value is stored in FLASH and is mirrored + in the MAX10 BMC register space. + Format: "%u". diff --git a/drivers/mfd/intel-m10-bmc.c b/drivers/mfd/intel-m10-bmc.c index b84579b7b4f0..06c977519479 100644 --- a/drivers/mfd/intel-m10-bmc.c +++ b/drivers/mfd/intel-m10-bmc.c @@ -60,9 +60,52 @@ static ssize_t bmcfw_version_show(struct device *dev, } static DEVICE_ATTR_RO(bmcfw_version); +static ssize_t mac_address_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct intel_m10bmc *max10 = dev_get_drvdata(dev); + unsigned int macaddr_low, macaddr_high; + int ret; + + ret = m10bmc_sys_read(max10, M10BMC_MAC_LOW, &macaddr_low); + if (ret) + return ret; + + ret = m10bmc_sys_read(max10, M10BMC_MAC_HIGH, &macaddr_high); + if (ret) + return ret; + + return sysfs_emit(buf, "%02x:%02x:%02x:%02x:%02x:%02x\n", + (u8)FIELD_GET(M10BMC_MAC_BYTE1, macaddr_low), + (u8)FIELD_GET(M10BMC_MAC_BYTE2, macaddr_low), + (u8)FIELD_GET(M10BMC_MAC_BYTE3, macaddr_low), + (u8)FIELD_GET(M10BMC_MAC_BYTE4, macaddr_low), + (u8)FIELD_GET(M10BMC_MAC_BYTE5, macaddr_high), + (u8)FIELD_GET(M10BMC_MAC_BYTE6, macaddr_high)); +} +static DEVICE_ATTR_RO(mac_address); + +static ssize_t mac_count_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct intel_m10bmc *max10 = dev_get_drvdata(dev); + unsigned int macaddr_high; + int ret; + + ret = m10bmc_sys_read(max10, M10BMC_MAC_HIGH, &macaddr_high); + if (ret) + return ret; + + return sysfs_emit(buf, "%u\n", + (u8)FIELD_GET(M10BMC_MAC_COUNT, macaddr_high)); +} +static DEVICE_ATTR_RO(mac_count); + static struct attribute *m10bmc_attrs[] = { &dev_attr_bmc_version.attr, &dev_attr_bmcfw_version.attr, + &dev_attr_mac_address.attr, + &dev_attr_mac_count.attr, NULL, }; ATTRIBUTE_GROUPS(m10bmc); diff --git a/include/linux/mfd/intel-m10-bmc.h b/include/linux/mfd/intel-m10-bmc.h index c8ef2f1654a4..74d4e193966a 100644 --- a/include/linux/mfd/intel-m10-bmc.h +++ b/include/linux/mfd/intel-m10-bmc.h @@ -15,6 +15,15 @@ /* Register offset of system registers */ #define NIOS2_FW_VERSION 0x0 +#define M10BMC_MAC_LOW 0x10 +#define M10BMC_MAC_BYTE4 GENMASK(7, 0) +#define M10BMC_MAC_BYTE3 GENMASK(15, 8) +#define M10BMC_MAC_BYTE2 GENMASK(23, 16) +#define M10BMC_MAC_BYTE1 GENMASK(31, 24) +#define M10BMC_MAC_HIGH 0x14 +#define M10BMC_MAC_BYTE6 GENMASK(7, 0) +#define M10BMC_MAC_BYTE5 GENMASK(15, 8) +#define M10BMC_MAC_COUNT GENMASK(23, 16) #define M10BMC_TEST_REG 0x3c #define M10BMC_BUILD_VER 0x68 #define M10BMC_VER_MAJOR_MSK GENMASK(23, 16) -- cgit v1.2.3 From 02e550d5b706f034d24e7e46234eb1982f05a137 Mon Sep 17 00:00:00 2001 From: Jeff LaBundy Date: Sun, 17 Jan 2021 21:57:07 -0600 Subject: mfd: iqs62x: Do not poll during ATI After loading firmware, the driver triggers ATI (calibration) with the newly loaded register configuration in place. Next, the driver polls a register field to ensure ATI completed in a timely fashion and that the device is ready to sense. However, communicating with the device over I2C while ATI is under- way may induce noise in the device and cause ATI to fail. As such, the vendor recommends not to poll the device during ATI. To solve this problem, let the device naturally signal to the host that ATI is complete by way of an interrupt. A completion prevents the sub-devices from being registered until this happens. The former logic that scaled ATI timeout and filter settling delay is not carried forward with the new implementation, as it produces overly conservative delays at lower clock rates. Instead, a single pair of delays that covers all cases is used. Signed-off-by: Jeff LaBundy Signed-off-by: Lee Jones --- drivers/mfd/iqs62x.c | 125 +++++++++++++++++++++++++-------------------- include/linux/mfd/iqs62x.h | 11 ++-- 2 files changed, 73 insertions(+), 63 deletions(-) (limited to 'include') diff --git a/drivers/mfd/iqs62x.c b/drivers/mfd/iqs62x.c index 07c972531715..9b5c389ca2c3 100644 --- a/drivers/mfd/iqs62x.c +++ b/drivers/mfd/iqs62x.c @@ -36,7 +36,6 @@ #define IQS62X_PROD_NUM 0x00 #define IQS62X_SYS_FLAGS 0x10 -#define IQS62X_SYS_FLAGS_IN_ATI BIT(2) #define IQS620_HALL_FLAGS 0x16 #define IQS621_HALL_FLAGS 0x19 @@ -60,6 +59,7 @@ #define IQS62X_SYS_SETTINGS_ACK_RESET BIT(6) #define IQS62X_SYS_SETTINGS_EVENT_MODE BIT(5) #define IQS62X_SYS_SETTINGS_CLK_DIV BIT(4) +#define IQS62X_SYS_SETTINGS_COMM_ATI BIT(3) #define IQS62X_SYS_SETTINGS_REDO_ATI BIT(1) #define IQS62X_PWR_SETTINGS 0xD2 @@ -81,9 +81,7 @@ #define IQS62X_FW_REC_TYPE_MASK 3 #define IQS62X_FW_REC_TYPE_DATA 4 -#define IQS62X_ATI_POLL_SLEEP_US 10000 -#define IQS62X_ATI_POLL_TIMEOUT_US 500000 -#define IQS62X_ATI_STABLE_DELAY_MS 150 +#define IQS62X_FILT_SETTLE_MS 250 struct iqs62x_fw_rec { u8 type; @@ -111,7 +109,6 @@ static int iqs62x_dev_init(struct iqs62x_core *iqs62x) struct iqs62x_fw_blk *fw_blk; unsigned int val; int ret; - u8 clk_div = 1; list_for_each_entry(fw_blk, &iqs62x->fw_blk_head, list) { if (fw_blk->mask) @@ -181,28 +178,32 @@ static int iqs62x_dev_init(struct iqs62x_core *iqs62x) return ret; } - ret = regmap_read(iqs62x->regmap, IQS62X_SYS_SETTINGS, &val); - if (ret) - return ret; - - if (val & IQS62X_SYS_SETTINGS_CLK_DIV) - clk_div = iqs62x->dev_desc->clk_div; - - ret = regmap_write(iqs62x->regmap, IQS62X_SYS_SETTINGS, val | - IQS62X_SYS_SETTINGS_ACK_RESET | - IQS62X_SYS_SETTINGS_EVENT_MODE | - IQS62X_SYS_SETTINGS_REDO_ATI); - if (ret) - return ret; - - ret = regmap_read_poll_timeout(iqs62x->regmap, IQS62X_SYS_FLAGS, val, - !(val & IQS62X_SYS_FLAGS_IN_ATI), - IQS62X_ATI_POLL_SLEEP_US, - IQS62X_ATI_POLL_TIMEOUT_US * clk_div); + /* + * Place the device in streaming mode at first so as not to miss the + * limited number of interrupts that would otherwise occur after ATI + * completes. The device is subsequently placed in event mode by the + * interrupt handler. + * + * In the meantime, mask interrupts during ATI to prevent the device + * from soliciting I2C traffic until the noise-sensitive ATI process + * is complete. + */ + ret = regmap_update_bits(iqs62x->regmap, IQS62X_SYS_SETTINGS, + IQS62X_SYS_SETTINGS_ACK_RESET | + IQS62X_SYS_SETTINGS_EVENT_MODE | + IQS62X_SYS_SETTINGS_COMM_ATI | + IQS62X_SYS_SETTINGS_REDO_ATI, + IQS62X_SYS_SETTINGS_ACK_RESET | + IQS62X_SYS_SETTINGS_REDO_ATI); if (ret) return ret; - msleep(IQS62X_ATI_STABLE_DELAY_MS * clk_div); + /* + * The following delay gives the device time to deassert its RDY output + * in case a communication window was open while the REDO_ATI field was + * written. This prevents an interrupt from being serviced prematurely. + */ + usleep_range(5000, 5100); return 0; } @@ -433,6 +434,11 @@ const struct iqs62x_event_desc iqs62x_events[IQS62X_NUM_EVENTS] = { .mask = BIT(7), .val = BIT(7), }, + [IQS62X_EVENT_SYS_ATI] = { + .reg = IQS62X_EVENT_SYS, + .mask = BIT(2), + .val = BIT(2), + }, }; EXPORT_SYMBOL_GPL(iqs62x_events); @@ -521,12 +527,39 @@ static irqreturn_t iqs62x_irq(int irq, void *context) "Failed to re-initialize device: %d\n", ret); return IRQ_NONE; } + + iqs62x->event_cache |= BIT(IQS62X_EVENT_SYS_RESET); + reinit_completion(&iqs62x->ati_done); + } else if (event_flags & BIT(IQS62X_EVENT_SYS_ATI)) { + iqs62x->event_cache |= BIT(IQS62X_EVENT_SYS_ATI); + reinit_completion(&iqs62x->ati_done); + } else if (!completion_done(&iqs62x->ati_done)) { + ret = regmap_update_bits(iqs62x->regmap, IQS62X_SYS_SETTINGS, + IQS62X_SYS_SETTINGS_EVENT_MODE, 0xFF); + if (ret) { + dev_err(&client->dev, + "Failed to enable event mode: %d\n", ret); + return IRQ_NONE; + } + + msleep(IQS62X_FILT_SETTLE_MS); + complete_all(&iqs62x->ati_done); } - ret = blocking_notifier_call_chain(&iqs62x->nh, event_flags, - &event_data); - if (ret & NOTIFY_STOP_MASK) - return IRQ_NONE; + /* + * Reset and ATI events are not broadcast to the sub-device drivers + * until ATI has completed. Any other events that may have occurred + * during ATI are ignored. + */ + if (completion_done(&iqs62x->ati_done)) { + event_flags |= iqs62x->event_cache; + ret = blocking_notifier_call_chain(&iqs62x->nh, event_flags, + &event_data); + if (ret & NOTIFY_STOP_MASK) + return IRQ_NONE; + + iqs62x->event_cache = 0; + } /* * Once the communication window is closed, a small delay is added to @@ -567,6 +600,12 @@ static void iqs62x_firmware_load(const struct firmware *fw, void *context) goto err_out; } + if (!wait_for_completion_timeout(&iqs62x->ati_done, + msecs_to_jiffies(2000))) { + dev_err(&client->dev, "Failed to complete ATI\n"); + goto err_out; + } + ret = devm_mfd_add_devices(&client->dev, PLATFORM_DEVID_NONE, iqs62x->dev_desc->sub_devs, iqs62x->dev_desc->num_sub_devs, @@ -748,22 +787,17 @@ static const struct iqs62x_dev_desc iqs62x_devs[] = { .dev_name = "iqs620at", .sub_devs = iqs620at_sub_devs, .num_sub_devs = ARRAY_SIZE(iqs620at_sub_devs), - .prod_num = IQS620_PROD_NUM, .sw_num = 0x08, .cal_regs = iqs620at_cal_regs, .num_cal_regs = ARRAY_SIZE(iqs620at_cal_regs), - .prox_mask = BIT(0), .sar_mask = BIT(1) | BIT(7), .hall_mask = BIT(2), .hyst_mask = BIT(3), .temp_mask = BIT(4), - .prox_settings = IQS620_PROX_SETTINGS_4, .hall_flags = IQS620_HALL_FLAGS, - - .clk_div = 4, .fw_name = "iqs620a.bin", .event_regs = &iqs620a_event_regs[IQS62X_UI_PROX], }, @@ -771,20 +805,15 @@ static const struct iqs62x_dev_desc iqs62x_devs[] = { .dev_name = "iqs620a", .sub_devs = iqs620a_sub_devs, .num_sub_devs = ARRAY_SIZE(iqs620a_sub_devs), - .prod_num = IQS620_PROD_NUM, .sw_num = 0x08, - .prox_mask = BIT(0), .sar_mask = BIT(1) | BIT(7), .hall_mask = BIT(2), .hyst_mask = BIT(3), .temp_mask = BIT(4), - .prox_settings = IQS620_PROX_SETTINGS_4, .hall_flags = IQS620_HALL_FLAGS, - - .clk_div = 4, .fw_name = "iqs620a.bin", .event_regs = &iqs620a_event_regs[IQS62X_UI_PROX], }, @@ -792,23 +821,18 @@ static const struct iqs62x_dev_desc iqs62x_devs[] = { .dev_name = "iqs621", .sub_devs = iqs621_sub_devs, .num_sub_devs = ARRAY_SIZE(iqs621_sub_devs), - .prod_num = IQS621_PROD_NUM, .sw_num = 0x09, .cal_regs = iqs621_cal_regs, .num_cal_regs = ARRAY_SIZE(iqs621_cal_regs), - .prox_mask = BIT(0), .hall_mask = BIT(1), .als_mask = BIT(2), .hyst_mask = BIT(3), .temp_mask = BIT(4), - .als_flags = IQS621_ALS_FLAGS, .hall_flags = IQS621_HALL_FLAGS, .hyst_shift = 5, - - .clk_div = 2, .fw_name = "iqs621.bin", .event_regs = &iqs621_event_regs[IQS62X_UI_PROX], }, @@ -816,21 +840,16 @@ static const struct iqs62x_dev_desc iqs62x_devs[] = { .dev_name = "iqs622", .sub_devs = iqs622_sub_devs, .num_sub_devs = ARRAY_SIZE(iqs622_sub_devs), - .prod_num = IQS622_PROD_NUM, .sw_num = 0x06, - .prox_mask = BIT(0), .sar_mask = BIT(1), .hall_mask = BIT(2), .als_mask = BIT(3), .ir_mask = BIT(4), - .prox_settings = IQS622_PROX_SETTINGS_4, .als_flags = IQS622_ALS_FLAGS, .hall_flags = IQS622_HALL_FLAGS, - - .clk_div = 2, .fw_name = "iqs622.bin", .event_regs = &iqs622_event_regs[IQS62X_UI_PROX], }, @@ -838,14 +857,10 @@ static const struct iqs62x_dev_desc iqs62x_devs[] = { .dev_name = "iqs624", .sub_devs = iqs624_sub_devs, .num_sub_devs = ARRAY_SIZE(iqs624_sub_devs), - .prod_num = IQS624_PROD_NUM, .sw_num = 0x0B, - .interval = IQS624_INTERVAL_NUM, .interval_div = 3, - - .clk_div = 2, .fw_name = "iqs624.bin", .event_regs = &iqs624_event_regs[IQS62X_UI_PROX], }, @@ -853,14 +868,10 @@ static const struct iqs62x_dev_desc iqs62x_devs[] = { .dev_name = "iqs625", .sub_devs = iqs625_sub_devs, .num_sub_devs = ARRAY_SIZE(iqs625_sub_devs), - .prod_num = IQS625_PROD_NUM, .sw_num = 0x0B, - .interval = IQS625_INTERVAL_NUM, .interval_div = 10, - - .clk_div = 2, .fw_name = "iqs625.bin", .event_regs = &iqs625_event_regs[IQS62X_UI_PROX], }, @@ -890,6 +901,8 @@ static int iqs62x_probe(struct i2c_client *client) BLOCKING_INIT_NOTIFIER_HEAD(&iqs62x->nh); INIT_LIST_HEAD(&iqs62x->fw_blk_head); + + init_completion(&iqs62x->ati_done); init_completion(&iqs62x->fw_done); iqs62x->regmap = devm_regmap_init_i2c(client, &iqs62x_regmap_config); diff --git a/include/linux/mfd/iqs62x.h b/include/linux/mfd/iqs62x.h index 043d3b6de9ec..5ced55eae11b 100644 --- a/include/linux/mfd/iqs62x.h +++ b/include/linux/mfd/iqs62x.h @@ -28,7 +28,7 @@ #define IQS620_GLBL_EVENT_MASK_PMU BIT(6) #define IQS62X_NUM_KEYS 16 -#define IQS62X_NUM_EVENTS (IQS62X_NUM_KEYS + 5) +#define IQS62X_NUM_EVENTS (IQS62X_NUM_KEYS + 6) #define IQS62X_EVENT_SIZE 10 @@ -78,6 +78,7 @@ enum iqs62x_event_flag { /* everything else */ IQS62X_EVENT_SYS_RESET, + IQS62X_EVENT_SYS_ATI, }; struct iqs62x_event_data { @@ -97,12 +98,10 @@ struct iqs62x_dev_desc { const char *dev_name; const struct mfd_cell *sub_devs; int num_sub_devs; - u8 prod_num; u8 sw_num; const u8 *cal_regs; int num_cal_regs; - u8 prox_mask; u8 sar_mask; u8 hall_mask; @@ -110,16 +109,12 @@ struct iqs62x_dev_desc { u8 temp_mask; u8 als_mask; u8 ir_mask; - u8 prox_settings; u8 als_flags; u8 hall_flags; u8 hyst_shift; - u8 interval; u8 interval_div; - - u8 clk_div; const char *fw_name; const enum iqs62x_event_reg (*event_regs)[IQS62X_EVENT_SIZE]; }; @@ -130,8 +125,10 @@ struct iqs62x_core { struct regmap *regmap; struct blocking_notifier_head nh; struct list_head fw_blk_head; + struct completion ati_done; struct completion fw_done; enum iqs62x_ui_sel ui_sel; + unsigned long event_cache; }; extern const struct iqs62x_event_desc iqs62x_events[IQS62X_NUM_EVENTS]; -- cgit v1.2.3 From e52606d2f5363f4900cfe8419e391644b0229c6f Mon Sep 17 00:00:00 2001 From: Ofir Bitton Date: Wed, 27 Jan 2021 16:34:37 +0200 Subject: habanalabs: support fetching first available user CQ User must be aware of the available CQs when it needs to use them. Signed-off-by: Ofir Bitton Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/common/habanalabs.h | 2 ++ drivers/misc/habanalabs/common/habanalabs_ioctl.c | 3 ++- drivers/misc/habanalabs/gaudi/gaudi.c | 3 +++ drivers/misc/habanalabs/goya/goya.c | 3 +++ include/uapi/misc/habanalabs.h | 3 +++ 5 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h index 3c54010f7ab9..98163317ec43 100644 --- a/drivers/misc/habanalabs/common/habanalabs.h +++ b/drivers/misc/habanalabs/common/habanalabs.h @@ -411,6 +411,7 @@ struct hl_mmu_properties { * @first_available_user_mon: first monitor available for the user * @first_available_user_msix_interrupt: first available msix interrupt * reserved for the user + * @first_available_cq: first available CQ for the user. * @tpc_enabled_mask: which TPCs are enabled. * @completion_queues_count: number of completion queues. * @fw_security_disabled: true if security measures are disabled in firmware, @@ -475,6 +476,7 @@ struct asic_fixed_properties { u16 first_available_user_sob[HL_MAX_DCORES]; u16 first_available_user_mon[HL_MAX_DCORES]; u16 first_available_user_msix_interrupt; + u16 first_available_cq[HL_MAX_DCORES]; u8 tpc_enabled_mask; u8 completion_queues_count; u8 fw_security_disabled; diff --git a/drivers/misc/habanalabs/common/habanalabs_ioctl.c b/drivers/misc/habanalabs/common/habanalabs_ioctl.c index e86f46d4b613..03af61cecd37 100644 --- a/drivers/misc/habanalabs/common/habanalabs_ioctl.c +++ b/drivers/misc/habanalabs/common/habanalabs_ioctl.c @@ -397,7 +397,8 @@ static int sync_manager_info(struct hl_fpriv *hpriv, struct hl_info_args *args) prop->first_available_user_sob[args->dcore_id]; sm_info.first_available_monitor = prop->first_available_user_mon[args->dcore_id]; - + sm_info.first_available_cq = + prop->first_available_cq[args->dcore_id]; return copy_to_user(out, &sm_info, min_t(size_t, (size_t) max_size, sizeof(sm_info))) ? -EFAULT : 0; diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c index 006c34ae35c2..8fc0de3cf3a9 100644 --- a/drivers/misc/habanalabs/gaudi/gaudi.c +++ b/drivers/misc/habanalabs/gaudi/gaudi.c @@ -529,6 +529,9 @@ static int gaudi_get_fixed_properties(struct hl_device *hdev) prop->first_available_user_msix_interrupt = USHRT_MAX; + for (i = 0 ; i < HL_MAX_DCORES ; i++) + prop->first_available_cq[i] = USHRT_MAX; + /* disable fw security for now, set it in a later stage */ prop->fw_security_disabled = true; prop->fw_security_status_valid = false; diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index 53db7e966866..d26b405f0c17 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -457,6 +457,9 @@ int goya_get_fixed_properties(struct hl_device *hdev) prop->first_available_user_msix_interrupt = USHRT_MAX; + for (i = 0 ; i < HL_MAX_DCORES ; i++) + prop->first_available_cq[i] = USHRT_MAX; + /* disable fw security for now, set it in a later stage */ prop->fw_security_disabled = true; prop->fw_security_status_valid = false; diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index ebde42b37b43..64ae83b5f8e5 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -414,10 +414,13 @@ struct hl_pll_frequency_info { * struct hl_info_sync_manager - sync manager information * @first_available_sync_object: first available sob * @first_available_monitor: first available monitor + * @first_available_cq: first available cq */ struct hl_info_sync_manager { __u32 first_available_sync_object; __u32 first_available_monitor; + __u32 first_available_cq; + __u32 reserved; }; /** -- cgit v1.2.3 From 6df50d274363aa189a31435024339b781a6e32a9 Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Fri, 5 Feb 2021 16:04:34 +0200 Subject: habanalabs: return block size + block ID When user gives us a block address to get its ID to mmap it, he also needs to get from us the block size to pass to the driver in the mmap function. Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/common/habanalabs.h | 4 +++- drivers/misc/habanalabs/common/memory.c | 19 +++++++++++-------- drivers/misc/habanalabs/gaudi/gaudi.c | 2 +- drivers/misc/habanalabs/goya/goya.c | 2 +- include/uapi/misc/habanalabs.h | 27 +++++++++++++++++++++------ 5 files changed, 37 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h index 46c37b0c704a..dc9f5a83dfc9 100644 --- a/drivers/misc/habanalabs/common/habanalabs.h +++ b/drivers/misc/habanalabs/common/habanalabs.h @@ -862,6 +862,8 @@ enum div_select_defs { * showing it to users. * @ack_protection_bits_errors: ack and dump all security violations * @get_hw_block_id: retrieve a HW block id to be used by the user to mmap it. + * also returns the size of the block if caller supplies + * a valid pointer for it * @hw_block_mmap: mmap a HW block with a given id. * @enable_events_from_fw: send interrupt to firmware to notify them the * driver is ready to receive asynchronous events. This @@ -980,7 +982,7 @@ struct hl_asic_funcs { u64 (*descramble_addr)(struct hl_device *hdev, u64 addr); void (*ack_protection_bits_errors)(struct hl_device *hdev); int (*get_hw_block_id)(struct hl_device *hdev, u64 block_addr, - u32 *block_id); + u32 *block_size, u32 *block_id); int (*hw_block_mmap)(struct hl_device *hdev, struct vm_area_struct *vma, u32 block_id, u32 block_size); void (*enable_events_from_fw)(struct hl_device *hdev); diff --git a/drivers/misc/habanalabs/common/memory.c b/drivers/misc/habanalabs/common/memory.c index 7171e8820a2d..7cadf75ebb81 100644 --- a/drivers/misc/habanalabs/common/memory.c +++ b/drivers/misc/habanalabs/common/memory.c @@ -1289,12 +1289,13 @@ vm_type_err: return rc; } -static int map_block(struct hl_device *hdev, u64 address, u64 *handle) +static int map_block(struct hl_device *hdev, u64 address, u64 *handle, + u32 *size) { u32 block_id = 0; int rc; - rc = hdev->asic_funcs->get_hw_block_id(hdev, address, &block_id); + rc = hdev->asic_funcs->get_hw_block_id(hdev, address, size, &block_id); *handle = block_id | HL_MMAP_TYPE_BLOCK; *handle <<= PAGE_SHIFT; @@ -1371,7 +1372,7 @@ static int mem_ioctl_no_mmu(struct hl_fpriv *hpriv, union hl_mem_args *args) struct hl_device *hdev = hpriv->hdev; struct hl_ctx *ctx = hpriv->ctx; u64 block_handle, device_addr = 0; - u32 handle = 0; + u32 handle = 0, block_size; int rc; switch (args->in.op) { @@ -1416,8 +1417,9 @@ static int mem_ioctl_no_mmu(struct hl_fpriv *hpriv, union hl_mem_args *args) case HL_MEM_OP_MAP_BLOCK: rc = map_block(hdev, args->in.map_block.block_addr, - &block_handle); - args->out.handle = block_handle; + &block_handle, &block_size); + args->out.block_handle = block_handle; + args->out.block_size = block_size; break; default: @@ -1437,7 +1439,7 @@ int hl_mem_ioctl(struct hl_fpriv *hpriv, void *data) struct hl_device *hdev = hpriv->hdev; struct hl_ctx *ctx = hpriv->ctx; u64 block_handle, device_addr = 0; - u32 handle = 0; + u32 handle = 0, block_size; int rc; if (!hl_device_operational(hdev, &status)) { @@ -1524,8 +1526,9 @@ int hl_mem_ioctl(struct hl_fpriv *hpriv, void *data) case HL_MEM_OP_MAP_BLOCK: rc = map_block(hdev, args->in.map_block.block_addr, - &block_handle); - args->out.handle = block_handle; + &block_handle, &block_size); + args->out.block_handle = block_handle; + args->out.block_size = block_size; break; default: diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c index f937d90786b2..35342edd4a02 100644 --- a/drivers/misc/habanalabs/gaudi/gaudi.c +++ b/drivers/misc/habanalabs/gaudi/gaudi.c @@ -8490,7 +8490,7 @@ static u64 gaudi_get_device_time(struct hl_device *hdev) } static int gaudi_get_hw_block_id(struct hl_device *hdev, u64 block_addr, - u32 *block_id) + u32 *block_size, u32 *block_id) { return -EPERM; } diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index c30524660761..ed566c52ccaa 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -5390,7 +5390,7 @@ static void goya_ctx_fini(struct hl_ctx *ctx) } static int goya_get_hw_block_id(struct hl_device *hdev, u64 block_addr, - u32 *block_id) + u32 *block_size, u32 *block_id) { return -EPERM; } diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index 64ae83b5f8e5..5a86b521a450 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -782,10 +782,10 @@ struct hl_mem_in { /* HL_MEM_OP_MAP_BLOCK - map a hw block */ struct { /* - * HW block address to map, a handle will be returned - * to the user and will be used to mmap the relevant - * block. Only addresses from configuration space are - * allowed. + * HW block address to map, a handle and size will be + * returned to the user and will be used to mmap the + * relevant block. Only addresses from configuration + * space are allowed. */ __u64 block_addr; } map_block; @@ -816,11 +816,26 @@ struct hl_mem_out { __u64 device_virt_addr; /* - * Used for HL_MEM_OP_ALLOC and HL_MEM_OP_MAP_BLOCK. + * Used in HL_MEM_OP_ALLOC * This is the assigned handle for the allocated memory - * or mapped block */ __u64 handle; + + struct { + /* + * Used in HL_MEM_OP_MAP_BLOCK. + * This is the assigned handle for the mapped block + */ + __u64 block_handle; + + /* + * Used in HL_MEM_OP_MAP_BLOCK + * This is the size of the mapped block + */ + __u32 block_size; + + __u32 pad; + }; }; }; -- cgit v1.2.3 From 28aa2f9e73e762dbaa28fdca20cccb59c74cc139 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 8 Feb 2021 08:55:47 -0500 Subject: NFS: Always clear an invalid mapping when attempting a buffered write If the page cache is invalid, then we can't do read-modify-write, so ensure that we do clear it when we know it is invalid. Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- fs/nfs/file.c | 2 ++ fs/nfs/inode.c | 97 ++++++++++++++++++++++++++++---------------------- include/linux/nfs_fs.h | 1 + 3 files changed, 57 insertions(+), 43 deletions(-) (limited to 'include') diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 02795a01c7ef..03fd1dcc96bd 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -632,6 +632,8 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from) goto out; } + nfs_clear_invalid_mapping(file->f_mapping); + since = filemap_sample_wb_err(file->f_mapping); nfs_start_io_write(inode); result = generic_write_checks(iocb, from); diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 522aa10a1a3e..2533053d764a 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -1257,55 +1257,19 @@ static int nfs_invalidate_mapping(struct inode *inode, struct address_space *map return 0; } -bool nfs_mapping_need_revalidate_inode(struct inode *inode) -{ - return nfs_check_cache_invalid(inode, NFS_INO_REVAL_PAGECACHE) || - NFS_STALE(inode); -} - -int nfs_revalidate_mapping_rcu(struct inode *inode) -{ - struct nfs_inode *nfsi = NFS_I(inode); - unsigned long *bitlock = &nfsi->flags; - int ret = 0; - - if (IS_SWAPFILE(inode)) - goto out; - if (nfs_mapping_need_revalidate_inode(inode)) { - ret = -ECHILD; - goto out; - } - spin_lock(&inode->i_lock); - if (test_bit(NFS_INO_INVALIDATING, bitlock) || - (nfsi->cache_validity & NFS_INO_INVALID_DATA)) - ret = -ECHILD; - spin_unlock(&inode->i_lock); -out: - return ret; -} - /** - * nfs_revalidate_mapping - Revalidate the pagecache - * @inode: pointer to host inode + * nfs_clear_invalid_mapping - Conditionally clear a mapping * @mapping: pointer to mapping + * + * If the NFS_INO_INVALID_DATA inode flag is set, clear the mapping. */ -int nfs_revalidate_mapping(struct inode *inode, - struct address_space *mapping) +int nfs_clear_invalid_mapping(struct address_space *mapping) { + struct inode *inode = mapping->host; struct nfs_inode *nfsi = NFS_I(inode); unsigned long *bitlock = &nfsi->flags; int ret = 0; - /* swapfiles are not supposed to be shared. */ - if (IS_SWAPFILE(inode)) - goto out; - - if (nfs_mapping_need_revalidate_inode(inode)) { - ret = __nfs_revalidate_inode(NFS_SERVER(inode), inode); - if (ret < 0) - goto out; - } - /* * We must clear NFS_INO_INVALID_DATA first to ensure that * invalidations that come in while we're shooting down the mappings @@ -1336,8 +1300,8 @@ int nfs_revalidate_mapping(struct inode *inode, set_bit(NFS_INO_INVALIDATING, bitlock); smp_wmb(); - nfsi->cache_validity &= ~(NFS_INO_INVALID_DATA| - NFS_INO_DATA_INVAL_DEFER); + nfsi->cache_validity &= + ~(NFS_INO_INVALID_DATA | NFS_INO_DATA_INVAL_DEFER); spin_unlock(&inode->i_lock); trace_nfs_invalidate_mapping_enter(inode); ret = nfs_invalidate_mapping(inode, mapping); @@ -1350,6 +1314,53 @@ out: return ret; } +bool nfs_mapping_need_revalidate_inode(struct inode *inode) +{ + return nfs_check_cache_invalid(inode, NFS_INO_REVAL_PAGECACHE) || + NFS_STALE(inode); +} + +int nfs_revalidate_mapping_rcu(struct inode *inode) +{ + struct nfs_inode *nfsi = NFS_I(inode); + unsigned long *bitlock = &nfsi->flags; + int ret = 0; + + if (IS_SWAPFILE(inode)) + goto out; + if (nfs_mapping_need_revalidate_inode(inode)) { + ret = -ECHILD; + goto out; + } + spin_lock(&inode->i_lock); + if (test_bit(NFS_INO_INVALIDATING, bitlock) || + (nfsi->cache_validity & NFS_INO_INVALID_DATA)) + ret = -ECHILD; + spin_unlock(&inode->i_lock); +out: + return ret; +} + +/** + * nfs_revalidate_mapping - Revalidate the pagecache + * @inode: pointer to host inode + * @mapping: pointer to mapping + */ +int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping) +{ + /* swapfiles are not supposed to be shared. */ + if (IS_SWAPFILE(inode)) + return 0; + + if (nfs_mapping_need_revalidate_inode(inode)) { + int ret = __nfs_revalidate_inode(NFS_SERVER(inode), inode); + if (ret < 0) + return ret; + } + + return nfs_clear_invalid_mapping(mapping); +} + static bool nfs_file_has_writers(struct nfs_inode *nfsi) { struct inode *inode = &nfsi->vfs_inode; diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 3cfcf219e96b..2c662857247a 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -387,6 +387,7 @@ extern int nfs_open(struct inode *, struct file *); extern int nfs_attribute_cache_expired(struct inode *inode); extern int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode); extern int __nfs_revalidate_inode(struct nfs_server *, struct inode *); +extern int nfs_clear_invalid_mapping(struct address_space *mapping); extern bool nfs_mapping_need_revalidate_inode(struct inode *inode); extern int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping); extern int nfs_revalidate_mapping_rcu(struct inode *inode); -- cgit v1.2.3 From 0fadcdfdcf570c3b1db90375f4b87fbd339bde2c Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Mon, 25 Jan 2021 20:31:54 -0800 Subject: dt-bindings: clock: Add SC8180x GCC binding Add devicetree binding for the global clock controller found in the Qualcomm SC8180x platform. Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20210126043155.1847823-1-bjorn.andersson@linaro.org Signed-off-by: Stephen Boyd --- .../bindings/clock/qcom,gcc-sc8180x.yaml | 76 +++++ include/dt-bindings/clock/qcom,gcc-sc8180x.h | 309 +++++++++++++++++++++ 2 files changed, 385 insertions(+) create mode 100644 Documentation/devicetree/bindings/clock/qcom,gcc-sc8180x.yaml create mode 100644 include/dt-bindings/clock/qcom,gcc-sc8180x.h (limited to 'include') diff --git a/Documentation/devicetree/bindings/clock/qcom,gcc-sc8180x.yaml b/Documentation/devicetree/bindings/clock/qcom,gcc-sc8180x.yaml new file mode 100644 index 000000000000..f03ef96e57fa --- /dev/null +++ b/Documentation/devicetree/bindings/clock/qcom,gcc-sc8180x.yaml @@ -0,0 +1,76 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/clock/qcom,gcc-sc8180x.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Qualcomm Global Clock & Reset Controller Binding for SC8180x + +maintainers: + - Bjorn Andersson + +description: | + Qualcomm global clock control module which supports the clocks, resets and + power domains on SC8180x. + + See also: + - dt-bindings/clock/qcom,gcc-sc8180x.h + +properties: + compatible: + const: qcom,gcc-sc8180x + + clocks: + items: + - description: Board XO source + - description: Board active XO source + - description: Sleep clock source + + clock-names: + items: + - const: bi_tcxo + - const: bi_tcxo_ao + - const: sleep_clk + + '#clock-cells': + const: 1 + + '#reset-cells': + const: 1 + + '#power-domain-cells': + const: 1 + + reg: + maxItems: 1 + + protected-clocks: + description: + Protected clock specifier list as per common clock binding. + +required: + - compatible + - clocks + - clock-names + - reg + - '#clock-cells' + - '#reset-cells' + - '#power-domain-cells' + +additionalProperties: false + +examples: + - | + #include + clock-controller@100000 { + compatible = "qcom,gcc-sc8180x"; + reg = <0x00100000 0x1f0000>; + clocks = <&rpmhcc RPMH_CXO_CLK>, + <&rpmhcc RPMH_CXO_CLK_A>, + <&sleep_clk>; + clock-names = "bi_tcxo", "bi_tcxo_ao", "sleep_clk"; + #clock-cells = <1>; + #reset-cells = <1>; + #power-domain-cells = <1>; + }; +... diff --git a/include/dt-bindings/clock/qcom,gcc-sc8180x.h b/include/dt-bindings/clock/qcom,gcc-sc8180x.h new file mode 100644 index 000000000000..e893415ae13d --- /dev/null +++ b/include/dt-bindings/clock/qcom,gcc-sc8180x.h @@ -0,0 +1,309 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (c) 2018-2019, The Linux Foundation. All rights reserved. + * Copyright (c) 2021, Linaro Ltd. + */ + +#ifndef _DT_BINDINGS_CLK_QCOM_GCC_SC8180X_H +#define _DT_BINDINGS_CLK_QCOM_GCC_SC8180X_H + +#define GCC_AGGRE_NOC_PCIE_TBU_CLK 0 +#define GCC_AGGRE_UFS_CARD_AXI_CLK 1 +#define GCC_AGGRE_UFS_CARD_AXI_HW_CTL_CLK 2 +#define GCC_AGGRE_UFS_PHY_AXI_CLK 3 +#define GCC_AGGRE_UFS_PHY_AXI_HW_CTL_CLK 4 +#define GCC_AGGRE_USB3_MP_AXI_CLK 5 +#define GCC_AGGRE_USB3_PRIM_AXI_CLK 6 +#define GCC_AGGRE_USB3_SEC_AXI_CLK 7 +#define GCC_BOOT_ROM_AHB_CLK 8 +#define GCC_CAMERA_HF_AXI_CLK 9 +#define GCC_CAMERA_SF_AXI_CLK 10 +#define GCC_CFG_NOC_USB3_MP_AXI_CLK 11 +#define GCC_CFG_NOC_USB3_PRIM_AXI_CLK 12 +#define GCC_CFG_NOC_USB3_SEC_AXI_CLK 13 +#define GCC_CPUSS_AHB_CLK 14 +#define GCC_CPUSS_AHB_CLK_SRC 15 +#define GCC_CPUSS_RBCPR_CLK 16 +#define GCC_DDRSS_GPU_AXI_CLK 17 +#define GCC_DISP_HF_AXI_CLK 18 +#define GCC_DISP_SF_AXI_CLK 19 +#define GCC_EMAC_AXI_CLK 20 +#define GCC_EMAC_PTP_CLK 21 +#define GCC_EMAC_PTP_CLK_SRC 22 +#define GCC_EMAC_RGMII_CLK 23 +#define GCC_EMAC_RGMII_CLK_SRC 24 +#define GCC_EMAC_SLV_AHB_CLK 25 +#define GCC_GP1_CLK 26 +#define GCC_GP1_CLK_SRC 27 +#define GCC_GP2_CLK 28 +#define GCC_GP2_CLK_SRC 29 +#define GCC_GP3_CLK 30 +#define GCC_GP3_CLK_SRC 31 +#define GCC_GP4_CLK 32 +#define GCC_GP4_CLK_SRC 33 +#define GCC_GP5_CLK 34 +#define GCC_GP5_CLK_SRC 35 +#define GCC_GPU_GPLL0_CLK_SRC 36 +#define GCC_GPU_GPLL0_DIV_CLK_SRC 37 +#define GCC_GPU_MEMNOC_GFX_CLK 38 +#define GCC_GPU_SNOC_DVM_GFX_CLK 39 +#define GCC_NPU_AT_CLK 40 +#define GCC_NPU_AXI_CLK 41 +#define GCC_NPU_AXI_CLK_SRC 42 +#define GCC_NPU_GPLL0_CLK_SRC 43 +#define GCC_NPU_GPLL0_DIV_CLK_SRC 44 +#define GCC_NPU_TRIG_CLK 45 +#define GCC_PCIE0_PHY_REFGEN_CLK 46 +#define GCC_PCIE1_PHY_REFGEN_CLK 47 +#define GCC_PCIE2_PHY_REFGEN_CLK 48 +#define GCC_PCIE3_PHY_REFGEN_CLK 49 +#define GCC_PCIE_0_AUX_CLK 50 +#define GCC_PCIE_0_AUX_CLK_SRC 51 +#define GCC_PCIE_0_CFG_AHB_CLK 52 +#define GCC_PCIE_0_MSTR_AXI_CLK 53 +#define GCC_PCIE_0_PIPE_CLK 54 +#define GCC_PCIE_0_SLV_AXI_CLK 55 +#define GCC_PCIE_0_SLV_Q2A_AXI_CLK 56 +#define GCC_PCIE_1_AUX_CLK 57 +#define GCC_PCIE_1_AUX_CLK_SRC 58 +#define GCC_PCIE_1_CFG_AHB_CLK 59 +#define GCC_PCIE_1_MSTR_AXI_CLK 60 +#define GCC_PCIE_1_PIPE_CLK 61 +#define GCC_PCIE_1_SLV_AXI_CLK 62 +#define GCC_PCIE_1_SLV_Q2A_AXI_CLK 63 +#define GCC_PCIE_2_AUX_CLK 64 +#define GCC_PCIE_2_AUX_CLK_SRC 65 +#define GCC_PCIE_2_CFG_AHB_CLK 66 +#define GCC_PCIE_2_MSTR_AXI_CLK 67 +#define GCC_PCIE_2_PIPE_CLK 68 +#define GCC_PCIE_2_SLV_AXI_CLK 69 +#define GCC_PCIE_2_SLV_Q2A_AXI_CLK 70 +#define GCC_PCIE_3_AUX_CLK 71 +#define GCC_PCIE_3_AUX_CLK_SRC 72 +#define GCC_PCIE_3_CFG_AHB_CLK 73 +#define GCC_PCIE_3_MSTR_AXI_CLK 74 +#define GCC_PCIE_3_PIPE_CLK 75 +#define GCC_PCIE_3_SLV_AXI_CLK 76 +#define GCC_PCIE_3_SLV_Q2A_AXI_CLK 77 +#define GCC_PCIE_PHY_AUX_CLK 78 +#define GCC_PCIE_PHY_REFGEN_CLK_SRC 79 +#define GCC_PDM2_CLK 80 +#define GCC_PDM2_CLK_SRC 81 +#define GCC_PDM_AHB_CLK 82 +#define GCC_PDM_XO4_CLK 83 +#define GCC_PRNG_AHB_CLK 84 +#define GCC_QMIP_CAMERA_NRT_AHB_CLK 85 +#define GCC_QMIP_CAMERA_RT_AHB_CLK 86 +#define GCC_QMIP_DISP_AHB_CLK 87 +#define GCC_QMIP_VIDEO_CVP_AHB_CLK 88 +#define GCC_QMIP_VIDEO_VCODEC_AHB_CLK 89 +#define GCC_QSPI_1_CNOC_PERIPH_AHB_CLK 90 +#define GCC_QSPI_1_CORE_CLK 91 +#define GCC_QSPI_1_CORE_CLK_SRC 92 +#define GCC_QSPI_CNOC_PERIPH_AHB_CLK 93 +#define GCC_QSPI_CORE_CLK 94 +#define GCC_QSPI_CORE_CLK_SRC 95 +#define GCC_QUPV3_WRAP0_S0_CLK 96 +#define GCC_QUPV3_WRAP0_S0_CLK_SRC 97 +#define GCC_QUPV3_WRAP0_S1_CLK 98 +#define GCC_QUPV3_WRAP0_S1_CLK_SRC 99 +#define GCC_QUPV3_WRAP0_S2_CLK 100 +#define GCC_QUPV3_WRAP0_S2_CLK_SRC 101 +#define GCC_QUPV3_WRAP0_S3_CLK 102 +#define GCC_QUPV3_WRAP0_S3_CLK_SRC 103 +#define GCC_QUPV3_WRAP0_S4_CLK 104 +#define GCC_QUPV3_WRAP0_S4_CLK_SRC 105 +#define GCC_QUPV3_WRAP0_S5_CLK 106 +#define GCC_QUPV3_WRAP0_S5_CLK_SRC 107 +#define GCC_QUPV3_WRAP0_S6_CLK 108 +#define GCC_QUPV3_WRAP0_S6_CLK_SRC 109 +#define GCC_QUPV3_WRAP0_S7_CLK 110 +#define GCC_QUPV3_WRAP0_S7_CLK_SRC 111 +#define GCC_QUPV3_WRAP1_S0_CLK 112 +#define GCC_QUPV3_WRAP1_S0_CLK_SRC 113 +#define GCC_QUPV3_WRAP1_S1_CLK 114 +#define GCC_QUPV3_WRAP1_S1_CLK_SRC 115 +#define GCC_QUPV3_WRAP1_S2_CLK 116 +#define GCC_QUPV3_WRAP1_S2_CLK_SRC 117 +#define GCC_QUPV3_WRAP1_S3_CLK 118 +#define GCC_QUPV3_WRAP1_S3_CLK_SRC 119 +#define GCC_QUPV3_WRAP1_S4_CLK 120 +#define GCC_QUPV3_WRAP1_S4_CLK_SRC 121 +#define GCC_QUPV3_WRAP1_S5_CLK 122 +#define GCC_QUPV3_WRAP1_S5_CLK_SRC 123 +#define GCC_QUPV3_WRAP2_S0_CLK 124 +#define GCC_QUPV3_WRAP2_S0_CLK_SRC 125 +#define GCC_QUPV3_WRAP2_S1_CLK 126 +#define GCC_QUPV3_WRAP2_S1_CLK_SRC 127 +#define GCC_QUPV3_WRAP2_S2_CLK 128 +#define GCC_QUPV3_WRAP2_S2_CLK_SRC 129 +#define GCC_QUPV3_WRAP2_S3_CLK 130 +#define GCC_QUPV3_WRAP2_S3_CLK_SRC 131 +#define GCC_QUPV3_WRAP2_S4_CLK 132 +#define GCC_QUPV3_WRAP2_S4_CLK_SRC 133 +#define GCC_QUPV3_WRAP2_S5_CLK 134 +#define GCC_QUPV3_WRAP2_S5_CLK_SRC 135 +#define GCC_QUPV3_WRAP_0_M_AHB_CLK 136 +#define GCC_QUPV3_WRAP_0_S_AHB_CLK 137 +#define GCC_QUPV3_WRAP_1_M_AHB_CLK 138 +#define GCC_QUPV3_WRAP_1_S_AHB_CLK 139 +#define GCC_QUPV3_WRAP_2_M_AHB_CLK 140 +#define GCC_QUPV3_WRAP_2_S_AHB_CLK 141 +#define GCC_SDCC2_AHB_CLK 142 +#define GCC_SDCC2_APPS_CLK 143 +#define GCC_SDCC2_APPS_CLK_SRC 144 +#define GCC_SDCC4_AHB_CLK 145 +#define GCC_SDCC4_APPS_CLK 146 +#define GCC_SDCC4_APPS_CLK_SRC 147 +#define GCC_SYS_NOC_CPUSS_AHB_CLK 148 +#define GCC_TSIF_AHB_CLK 149 +#define GCC_TSIF_INACTIVITY_TIMERS_CLK 150 +#define GCC_TSIF_REF_CLK 151 +#define GCC_TSIF_REF_CLK_SRC 152 +#define GCC_UFS_CARD_2_AHB_CLK 153 +#define GCC_UFS_CARD_2_AXI_CLK 154 +#define GCC_UFS_CARD_2_AXI_CLK_SRC 155 +#define GCC_UFS_CARD_2_ICE_CORE_CLK 156 +#define GCC_UFS_CARD_2_ICE_CORE_CLK_SRC 157 +#define GCC_UFS_CARD_2_PHY_AUX_CLK 158 +#define GCC_UFS_CARD_2_PHY_AUX_CLK_SRC 159 +#define GCC_UFS_CARD_2_RX_SYMBOL_0_CLK 160 +#define GCC_UFS_CARD_2_RX_SYMBOL_1_CLK 161 +#define GCC_UFS_CARD_2_TX_SYMBOL_0_CLK 162 +#define GCC_UFS_CARD_2_UNIPRO_CORE_CLK 163 +#define GCC_UFS_CARD_2_UNIPRO_CORE_CLK_SRC 164 +#define GCC_UFS_CARD_AHB_CLK 165 +#define GCC_UFS_CARD_AXI_CLK 166 +#define GCC_UFS_CARD_AXI_CLK_SRC 167 +#define GCC_UFS_CARD_AXI_HW_CTL_CLK 168 +#define GCC_UFS_CARD_ICE_CORE_CLK 169 +#define GCC_UFS_CARD_ICE_CORE_CLK_SRC 170 +#define GCC_UFS_CARD_ICE_CORE_HW_CTL_CLK 171 +#define GCC_UFS_CARD_PHY_AUX_CLK 172 +#define GCC_UFS_CARD_PHY_AUX_CLK_SRC 173 +#define GCC_UFS_CARD_PHY_AUX_HW_CTL_CLK 174 +#define GCC_UFS_CARD_RX_SYMBOL_0_CLK 175 +#define GCC_UFS_CARD_RX_SYMBOL_1_CLK 176 +#define GCC_UFS_CARD_TX_SYMBOL_0_CLK 177 +#define GCC_UFS_CARD_UNIPRO_CORE_CLK 178 +#define GCC_UFS_CARD_UNIPRO_CORE_CLK_SRC 179 +#define GCC_UFS_CARD_UNIPRO_CORE_HW_CTL_CLK 180 +#define GCC_UFS_PHY_AHB_CLK 181 +#define GCC_UFS_PHY_AXI_CLK 182 +#define GCC_UFS_PHY_AXI_CLK_SRC 183 +#define GCC_UFS_PHY_AXI_HW_CTL_CLK 184 +#define GCC_UFS_PHY_ICE_CORE_CLK 185 +#define GCC_UFS_PHY_ICE_CORE_CLK_SRC 186 +#define GCC_UFS_PHY_ICE_CORE_HW_CTL_CLK 187 +#define GCC_UFS_PHY_PHY_AUX_CLK 188 +#define GCC_UFS_PHY_PHY_AUX_CLK_SRC 189 +#define GCC_UFS_PHY_PHY_AUX_HW_CTL_CLK 190 +#define GCC_UFS_PHY_RX_SYMBOL_0_CLK 191 +#define GCC_UFS_PHY_RX_SYMBOL_1_CLK 192 +#define GCC_UFS_PHY_TX_SYMBOL_0_CLK 193 +#define GCC_UFS_PHY_UNIPRO_CORE_CLK 194 +#define GCC_UFS_PHY_UNIPRO_CORE_CLK_SRC 195 +#define GCC_UFS_PHY_UNIPRO_CORE_HW_CTL_CLK 196 +#define GCC_USB30_MP_MASTER_CLK 197 +#define GCC_USB30_MP_MASTER_CLK_SRC 198 +#define GCC_USB30_MP_MOCK_UTMI_CLK 199 +#define GCC_USB30_MP_MOCK_UTMI_CLK_SRC 200 +#define GCC_USB30_MP_SLEEP_CLK 201 +#define GCC_USB30_PRIM_MASTER_CLK 202 +#define GCC_USB30_PRIM_MASTER_CLK_SRC 203 +#define GCC_USB30_PRIM_MOCK_UTMI_CLK 204 +#define GCC_USB30_PRIM_MOCK_UTMI_CLK_SRC 205 +#define GCC_USB30_PRIM_SLEEP_CLK 206 +#define GCC_USB30_SEC_MASTER_CLK 207 +#define GCC_USB30_SEC_MASTER_CLK_SRC 208 +#define GCC_USB30_SEC_MOCK_UTMI_CLK 209 +#define GCC_USB30_SEC_MOCK_UTMI_CLK_SRC 210 +#define GCC_USB30_SEC_SLEEP_CLK 211 +#define GCC_USB3_MP_PHY_AUX_CLK 212 +#define GCC_USB3_MP_PHY_AUX_CLK_SRC 213 +#define GCC_USB3_MP_PHY_COM_AUX_CLK 214 +#define GCC_USB3_MP_PHY_PIPE_0_CLK 215 +#define GCC_USB3_MP_PHY_PIPE_1_CLK 216 +#define GCC_USB3_PRIM_PHY_AUX_CLK 217 +#define GCC_USB3_PRIM_PHY_AUX_CLK_SRC 218 +#define GCC_USB3_PRIM_PHY_COM_AUX_CLK 219 +#define GCC_USB3_PRIM_PHY_PIPE_CLK 220 +#define GCC_USB3_SEC_PHY_AUX_CLK 221 +#define GCC_USB3_SEC_PHY_AUX_CLK_SRC 222 +#define GCC_USB3_SEC_PHY_COM_AUX_CLK 223 +#define GCC_USB3_SEC_PHY_PIPE_CLK 224 +#define GCC_VIDEO_AXI0_CLK 225 +#define GCC_VIDEO_AXI1_CLK 226 +#define GCC_VIDEO_AXIC_CLK 227 +#define GPLL0 228 +#define GPLL0_OUT_EVEN 229 +#define GPLL1 230 +#define GPLL4 231 +#define GPLL7 232 +#define GCC_PCIE_0_CLKREF_CLK 233 +#define GCC_PCIE_1_CLKREF_CLK 234 +#define GCC_PCIE_2_CLKREF_CLK 235 +#define GCC_PCIE_3_CLKREF_CLK 236 +#define GCC_USB3_PRIM_CLKREF_CLK 237 +#define GCC_USB3_SEC_CLKREF_CLK 238 + +#define GCC_EMAC_BCR 0 +#define GCC_GPU_BCR 1 +#define GCC_MMSS_BCR 2 +#define GCC_NPU_BCR 3 +#define GCC_PCIE_0_BCR 4 +#define GCC_PCIE_0_PHY_BCR 5 +#define GCC_PCIE_1_BCR 6 +#define GCC_PCIE_1_PHY_BCR 7 +#define GCC_PCIE_2_BCR 8 +#define GCC_PCIE_2_PHY_BCR 9 +#define GCC_PCIE_3_BCR 10 +#define GCC_PCIE_3_PHY_BCR 11 +#define GCC_PCIE_PHY_BCR 12 +#define GCC_PDM_BCR 13 +#define GCC_PRNG_BCR 14 +#define GCC_QSPI_1_BCR 15 +#define GCC_QSPI_BCR 16 +#define GCC_QUPV3_WRAPPER_0_BCR 17 +#define GCC_QUPV3_WRAPPER_1_BCR 18 +#define GCC_QUPV3_WRAPPER_2_BCR 19 +#define GCC_QUSB2PHY_5_BCR 20 +#define GCC_QUSB2PHY_MP0_BCR 21 +#define GCC_QUSB2PHY_MP1_BCR 22 +#define GCC_QUSB2PHY_PRIM_BCR 23 +#define GCC_QUSB2PHY_SEC_BCR 24 +#define GCC_USB3_PHY_PRIM_SP0_BCR 25 +#define GCC_USB3_PHY_PRIM_SP1_BCR 26 +#define GCC_USB3_DP_PHY_PRIM_SP0_BCR 27 +#define GCC_USB3_DP_PHY_PRIM_SP1_BCR 28 +#define GCC_USB3_PHY_SEC_BCR 29 +#define GCC_USB3PHY_PHY_SEC_BCR 30 +#define GCC_SDCC2_BCR 31 +#define GCC_SDCC4_BCR 32 +#define GCC_TSIF_BCR 33 +#define GCC_UFS_CARD_2_BCR 34 +#define GCC_UFS_CARD_BCR 35 +#define GCC_UFS_PHY_BCR 36 +#define GCC_USB30_MP_BCR 37 +#define GCC_USB30_PRIM_BCR 38 +#define GCC_USB30_SEC_BCR 39 +#define GCC_USB_PHY_CFG_AHB2PHY_BCR 40 +#define GCC_VIDEO_AXIC_CLK_BCR 41 +#define GCC_VIDEO_AXI0_CLK_BCR 42 +#define GCC_VIDEO_AXI1_CLK_BCR 43 +#define GCC_USB3_DP_PHY_SEC_BCR 44 + +/* GCC GDSCRs */ +#define EMAC_GDSC 0 +#define PCIE_0_GDSC 1 +#define PCIE_1_GDSC 2 +#define PCIE_2_GDSC 3 +#define PCIE_3_GDSC 4 +#define UFS_CARD_2_GDSC 5 +#define UFS_CARD_GDSC 6 +#define UFS_PHY_GDSC 7 +#define USB30_MP_GDSC 8 +#define USB30_PRIM_GDSC 9 +#define USB30_SEC_GDSC 10 + +#endif -- cgit v1.2.3 From a2e8c80845be43607e4957e9d10ec0c05df57a02 Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Wed, 27 Jan 2021 12:38:10 +0530 Subject: dt-bindings: clock: Add SM8350 GCC clock bindings Add device tree bindings for global clock controller on SM8350 SoCs. Reviewed-by: Rob Herring Reviewed-by: Bjorn Andersson Signed-off-by: Vinod Koul Link: https://lore.kernel.org/r/20210127070811.152690-5-vkoul@kernel.org Signed-off-by: Stephen Boyd --- .../devicetree/bindings/clock/qcom,gcc-sm8350.yaml | 96 ++++++++ include/dt-bindings/clock/qcom,gcc-sm8350.h | 254 +++++++++++++++++++++ 2 files changed, 350 insertions(+) create mode 100644 Documentation/devicetree/bindings/clock/qcom,gcc-sm8350.yaml create mode 100644 include/dt-bindings/clock/qcom,gcc-sm8350.h (limited to 'include') diff --git a/Documentation/devicetree/bindings/clock/qcom,gcc-sm8350.yaml b/Documentation/devicetree/bindings/clock/qcom,gcc-sm8350.yaml new file mode 100644 index 000000000000..78f35832aa41 --- /dev/null +++ b/Documentation/devicetree/bindings/clock/qcom,gcc-sm8350.yaml @@ -0,0 +1,96 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/clock/qcom,gcc-sm8350.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Qualcomm Global Clock & Reset Controller Binding for SM8350 + +maintainers: + - Vinod Koul + +description: | + Qualcomm global clock control module which supports the clocks, resets and + power domains on SM8350. + + See also: + - dt-bindings/clock/qcom,gcc-sm8350.h + +properties: + compatible: + const: qcom,gcc-sm8350 + + clocks: + items: + - description: Board XO source + - description: Sleep clock source + - description: PLL test clock source (Optional clock) + - description: PCIE 0 Pipe clock source (Optional clock) + - description: PCIE 1 Pipe clock source (Optional clock) + - description: UFS card Rx symbol 0 clock source (Optional clock) + - description: UFS card Rx symbol 1 clock source (Optional clock) + - description: UFS card Tx symbol 0 clock source (Optional clock) + - description: UFS phy Rx symbol 0 clock source (Optional clock) + - description: UFS phy Rx symbol 1 clock source (Optional clock) + - description: UFS phy Tx symbol 0 clock source (Optional clock) + - description: USB3 phy wrapper pipe clock source (Optional clock) + - description: USB3 phy sec pipe clock source (Optional clock) + minItems: 2 + maxItems: 13 + + clock-names: + items: + - const: bi_tcxo + - const: sleep_clk + - const: core_bi_pll_test_se # Optional clock + - const: pcie_0_pipe_clk # Optional clock + - const: pcie_1_pipe_clk # Optional clock + - const: ufs_card_rx_symbol_0_clk # Optional clock + - const: ufs_card_rx_symbol_1_clk # Optional clock + - const: ufs_card_tx_symbol_0_clk # Optional clock + - const: ufs_phy_rx_symbol_0_clk # Optional clock + - const: ufs_phy_rx_symbol_1_clk # Optional clock + - const: ufs_phy_tx_symbol_0_clk # Optional clock + - const: usb3_phy_wrapper_gcc_usb30_pipe_clk # Optional clock + - const: usb3_uni_phy_sec_gcc_usb30_pipe_clk # Optional clock + minItems: 2 + maxItems: 13 + + '#clock-cells': + const: 1 + + '#reset-cells': + const: 1 + + '#power-domain-cells': + const: 1 + + reg: + maxItems: 1 + +required: + - compatible + - clocks + - clock-names + - reg + - '#clock-cells' + - '#reset-cells' + - '#power-domain-cells' + +additionalProperties: false + +examples: + - | + #include + clock-controller@100000 { + compatible = "qcom,gcc-sm8350"; + reg = <0x00100000 0x1f0000>; + clocks = <&rpmhcc RPMH_CXO_CLK>, + <&sleep_clk>; + clock-names = "bi_tcxo", "sleep_clk"; + #clock-cells = <1>; + #reset-cells = <1>; + #power-domain-cells = <1>; + }; + +... diff --git a/include/dt-bindings/clock/qcom,gcc-sm8350.h b/include/dt-bindings/clock/qcom,gcc-sm8350.h new file mode 100644 index 000000000000..1331da65f669 --- /dev/null +++ b/include/dt-bindings/clock/qcom,gcc-sm8350.h @@ -0,0 +1,254 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (c) 2019-2020, The Linux Foundation. All rights reserved. + * Copyright (c) 2020-2021, Linaro Limited + */ + +#ifndef _DT_BINDINGS_CLK_QCOM_GCC_SM8350_H +#define _DT_BINDINGS_CLK_QCOM_GCC_SM8350_H + +/* GCC HW clocks */ +#define CORE_BI_PLL_TEST_SE 0 +#define PCIE_0_PIPE_CLK 1 +#define PCIE_1_PIPE_CLK 2 +#define UFS_CARD_RX_SYMBOL_0_CLK 3 +#define UFS_CARD_RX_SYMBOL_1_CLK 4 +#define UFS_CARD_TX_SYMBOL_0_CLK 5 +#define UFS_PHY_RX_SYMBOL_0_CLK 6 +#define UFS_PHY_RX_SYMBOL_1_CLK 7 +#define UFS_PHY_TX_SYMBOL_0_CLK 8 +#define USB3_PHY_WRAPPER_GCC_USB30_PIPE_CLK 9 +#define USB3_UNI_PHY_SEC_GCC_USB30_PIPE_CLK 10 + +/* GCC clocks */ +#define GCC_AGGRE_NOC_PCIE_0_AXI_CLK 11 +#define GCC_AGGRE_NOC_PCIE_1_AXI_CLK 12 +#define GCC_AGGRE_NOC_PCIE_TBU_CLK 13 +#define GCC_AGGRE_UFS_CARD_AXI_CLK 14 +#define GCC_AGGRE_UFS_CARD_AXI_HW_CTL_CLK 15 +#define GCC_AGGRE_UFS_PHY_AXI_CLK 16 +#define GCC_AGGRE_UFS_PHY_AXI_HW_CTL_CLK 17 +#define GCC_AGGRE_USB3_PRIM_AXI_CLK 18 +#define GCC_AGGRE_USB3_SEC_AXI_CLK 19 +#define GCC_BOOT_ROM_AHB_CLK 20 +#define GCC_CAMERA_HF_AXI_CLK 21 +#define GCC_CAMERA_SF_AXI_CLK 22 +#define GCC_CFG_NOC_USB3_PRIM_AXI_CLK 23 +#define GCC_CFG_NOC_USB3_SEC_AXI_CLK 24 +#define GCC_DDRSS_GPU_AXI_CLK 25 +#define GCC_DDRSS_PCIE_SF_TBU_CLK 26 +#define GCC_DISP_HF_AXI_CLK 27 +#define GCC_DISP_SF_AXI_CLK 28 +#define GCC_GP1_CLK 29 +#define GCC_GP1_CLK_SRC 30 +#define GCC_GP2_CLK 31 +#define GCC_GP2_CLK_SRC 32 +#define GCC_GP3_CLK 33 +#define GCC_GP3_CLK_SRC 34 +#define GCC_GPLL0 35 +#define GCC_GPLL0_OUT_EVEN 36 +#define GCC_GPLL4 37 +#define GCC_GPLL9 38 +#define GCC_GPU_GPLL0_CLK_SRC 39 +#define GCC_GPU_GPLL0_DIV_CLK_SRC 40 +#define GCC_GPU_IREF_EN 41 +#define GCC_GPU_MEMNOC_GFX_CLK 42 +#define GCC_GPU_SNOC_DVM_GFX_CLK 43 +#define GCC_PCIE0_PHY_RCHNG_CLK 44 +#define GCC_PCIE1_PHY_RCHNG_CLK 45 +#define GCC_PCIE_0_AUX_CLK 46 +#define GCC_PCIE_0_AUX_CLK_SRC 47 +#define GCC_PCIE_0_CFG_AHB_CLK 48 +#define GCC_PCIE_0_CLKREF_EN 49 +#define GCC_PCIE_0_MSTR_AXI_CLK 50 +#define GCC_PCIE_0_PHY_RCHNG_CLK_SRC 51 +#define GCC_PCIE_0_PIPE_CLK 52 +#define GCC_PCIE_0_PIPE_CLK_SRC 53 +#define GCC_PCIE_0_SLV_AXI_CLK 54 +#define GCC_PCIE_0_SLV_Q2A_AXI_CLK 55 +#define GCC_PCIE_1_AUX_CLK 56 +#define GCC_PCIE_1_AUX_CLK_SRC 57 +#define GCC_PCIE_1_CFG_AHB_CLK 58 +#define GCC_PCIE_1_CLKREF_EN 59 +#define GCC_PCIE_1_MSTR_AXI_CLK 60 +#define GCC_PCIE_1_PHY_RCHNG_CLK_SRC 61 +#define GCC_PCIE_1_PIPE_CLK 62 +#define GCC_PCIE_1_PIPE_CLK_SRC 63 +#define GCC_PCIE_1_SLV_AXI_CLK 64 +#define GCC_PCIE_1_SLV_Q2A_AXI_CLK 65 +#define GCC_PDM2_CLK 66 +#define GCC_PDM2_CLK_SRC 67 +#define GCC_PDM_AHB_CLK 68 +#define GCC_PDM_XO4_CLK 69 +#define GCC_QMIP_CAMERA_NRT_AHB_CLK 70 +#define GCC_QMIP_CAMERA_RT_AHB_CLK 71 +#define GCC_QMIP_DISP_AHB_CLK 72 +#define GCC_QMIP_VIDEO_CVP_AHB_CLK 73 +#define GCC_QMIP_VIDEO_VCODEC_AHB_CLK 74 +#define GCC_QUPV3_WRAP0_CORE_2X_CLK 75 +#define GCC_QUPV3_WRAP0_CORE_CLK 76 +#define GCC_QUPV3_WRAP0_S0_CLK 77 +#define GCC_QUPV3_WRAP0_S0_CLK_SRC 78 +#define GCC_QUPV3_WRAP0_S1_CLK 79 +#define GCC_QUPV3_WRAP0_S1_CLK_SRC 80 +#define GCC_QUPV3_WRAP0_S2_CLK 81 +#define GCC_QUPV3_WRAP0_S2_CLK_SRC 82 +#define GCC_QUPV3_WRAP0_S3_CLK 83 +#define GCC_QUPV3_WRAP0_S3_CLK_SRC 84 +#define GCC_QUPV3_WRAP0_S4_CLK 85 +#define GCC_QUPV3_WRAP0_S4_CLK_SRC 86 +#define GCC_QUPV3_WRAP0_S5_CLK 87 +#define GCC_QUPV3_WRAP0_S5_CLK_SRC 88 +#define GCC_QUPV3_WRAP0_S6_CLK 89 +#define GCC_QUPV3_WRAP0_S6_CLK_SRC 90 +#define GCC_QUPV3_WRAP0_S7_CLK 91 +#define GCC_QUPV3_WRAP0_S7_CLK_SRC 92 +#define GCC_QUPV3_WRAP1_CORE_2X_CLK 93 +#define GCC_QUPV3_WRAP1_CORE_CLK 94 +#define GCC_QUPV3_WRAP1_S0_CLK 95 +#define GCC_QUPV3_WRAP1_S0_CLK_SRC 96 +#define GCC_QUPV3_WRAP1_S1_CLK 97 +#define GCC_QUPV3_WRAP1_S1_CLK_SRC 98 +#define GCC_QUPV3_WRAP1_S2_CLK 99 +#define GCC_QUPV3_WRAP1_S2_CLK_SRC 100 +#define GCC_QUPV3_WRAP1_S3_CLK 101 +#define GCC_QUPV3_WRAP1_S3_CLK_SRC 102 +#define GCC_QUPV3_WRAP1_S4_CLK 103 +#define GCC_QUPV3_WRAP1_S4_CLK_SRC 104 +#define GCC_QUPV3_WRAP1_S5_CLK 105 +#define GCC_QUPV3_WRAP1_S5_CLK_SRC 106 +#define GCC_QUPV3_WRAP2_CORE_2X_CLK 107 +#define GCC_QUPV3_WRAP2_CORE_CLK 108 +#define GCC_QUPV3_WRAP2_S0_CLK 109 +#define GCC_QUPV3_WRAP2_S0_CLK_SRC 110 +#define GCC_QUPV3_WRAP2_S1_CLK 111 +#define GCC_QUPV3_WRAP2_S1_CLK_SRC 112 +#define GCC_QUPV3_WRAP2_S2_CLK 113 +#define GCC_QUPV3_WRAP2_S2_CLK_SRC 114 +#define GCC_QUPV3_WRAP2_S3_CLK 115 +#define GCC_QUPV3_WRAP2_S3_CLK_SRC 116 +#define GCC_QUPV3_WRAP2_S4_CLK 117 +#define GCC_QUPV3_WRAP2_S4_CLK_SRC 118 +#define GCC_QUPV3_WRAP2_S5_CLK 119 +#define GCC_QUPV3_WRAP2_S5_CLK_SRC 120 +#define GCC_QUPV3_WRAP_0_M_AHB_CLK 121 +#define GCC_QUPV3_WRAP_0_S_AHB_CLK 122 +#define GCC_QUPV3_WRAP_1_M_AHB_CLK 123 +#define GCC_QUPV3_WRAP_1_S_AHB_CLK 124 +#define GCC_QUPV3_WRAP_2_M_AHB_CLK 125 +#define GCC_QUPV3_WRAP_2_S_AHB_CLK 126 +#define GCC_SDCC2_AHB_CLK 127 +#define GCC_SDCC2_APPS_CLK 128 +#define GCC_SDCC2_APPS_CLK_SRC 129 +#define GCC_SDCC4_AHB_CLK 130 +#define GCC_SDCC4_APPS_CLK 131 +#define GCC_SDCC4_APPS_CLK_SRC 132 +#define GCC_THROTTLE_PCIE_AHB_CLK 133 +#define GCC_UFS_1_CLKREF_EN 134 +#define GCC_UFS_CARD_AHB_CLK 135 +#define GCC_UFS_CARD_AXI_CLK 136 +#define GCC_UFS_CARD_AXI_CLK_SRC 137 +#define GCC_UFS_CARD_AXI_HW_CTL_CLK 138 +#define GCC_UFS_CARD_ICE_CORE_CLK 139 +#define GCC_UFS_CARD_ICE_CORE_CLK_SRC 140 +#define GCC_UFS_CARD_ICE_CORE_HW_CTL_CLK 141 +#define GCC_UFS_CARD_PHY_AUX_CLK 142 +#define GCC_UFS_CARD_PHY_AUX_CLK_SRC 143 +#define GCC_UFS_CARD_PHY_AUX_HW_CTL_CLK 144 +#define GCC_UFS_CARD_RX_SYMBOL_0_CLK 145 +#define GCC_UFS_CARD_RX_SYMBOL_0_CLK_SRC 146 +#define GCC_UFS_CARD_RX_SYMBOL_1_CLK 147 +#define GCC_UFS_CARD_RX_SYMBOL_1_CLK_SRC 148 +#define GCC_UFS_CARD_TX_SYMBOL_0_CLK 149 +#define GCC_UFS_CARD_TX_SYMBOL_0_CLK_SRC 150 +#define GCC_UFS_CARD_UNIPRO_CORE_CLK 151 +#define GCC_UFS_CARD_UNIPRO_CORE_CLK_SRC 152 +#define GCC_UFS_CARD_UNIPRO_CORE_HW_CTL_CLK 153 +#define GCC_UFS_PHY_AHB_CLK 154 +#define GCC_UFS_PHY_AXI_CLK 155 +#define GCC_UFS_PHY_AXI_CLK_SRC 156 +#define GCC_UFS_PHY_AXI_HW_CTL_CLK 157 +#define GCC_UFS_PHY_ICE_CORE_CLK 158 +#define GCC_UFS_PHY_ICE_CORE_CLK_SRC 159 +#define GCC_UFS_PHY_ICE_CORE_HW_CTL_CLK 160 +#define GCC_UFS_PHY_PHY_AUX_CLK 161 +#define GCC_UFS_PHY_PHY_AUX_CLK_SRC 162 +#define GCC_UFS_PHY_PHY_AUX_HW_CTL_CLK 163 +#define GCC_UFS_PHY_RX_SYMBOL_0_CLK 164 +#define GCC_UFS_PHY_RX_SYMBOL_0_CLK_SRC 165 +#define GCC_UFS_PHY_RX_SYMBOL_1_CLK 166 +#define GCC_UFS_PHY_RX_SYMBOL_1_CLK_SRC 167 +#define GCC_UFS_PHY_TX_SYMBOL_0_CLK 168 +#define GCC_UFS_PHY_TX_SYMBOL_0_CLK_SRC 169 +#define GCC_UFS_PHY_UNIPRO_CORE_CLK 170 +#define GCC_UFS_PHY_UNIPRO_CORE_CLK_SRC 171 +#define GCC_UFS_PHY_UNIPRO_CORE_HW_CTL_CLK 172 +#define GCC_USB30_PRIM_MASTER_CLK 173 +#define GCC_USB30_PRIM_MASTER_CLK__FORCE_MEM_CORE_ON 174 +#define GCC_USB30_PRIM_MASTER_CLK_SRC 175 +#define GCC_USB30_PRIM_MOCK_UTMI_CLK 176 +#define GCC_USB30_PRIM_MOCK_UTMI_CLK_SRC 177 +#define GCC_USB30_PRIM_MOCK_UTMI_POSTDIV_CLK_SRC 178 +#define GCC_USB30_PRIM_SLEEP_CLK 179 +#define GCC_USB30_SEC_MASTER_CLK 180 +#define GCC_USB30_SEC_MASTER_CLK__FORCE_MEM_CORE_ON 181 +#define GCC_USB30_SEC_MASTER_CLK_SRC 182 +#define GCC_USB30_SEC_MOCK_UTMI_CLK 183 +#define GCC_USB30_SEC_MOCK_UTMI_CLK_SRC 184 +#define GCC_USB30_SEC_MOCK_UTMI_POSTDIV_CLK_SRC 185 +#define GCC_USB30_SEC_SLEEP_CLK 186 +#define GCC_USB3_PRIM_PHY_AUX_CLK 187 +#define GCC_USB3_PRIM_PHY_AUX_CLK_SRC 188 +#define GCC_USB3_PRIM_PHY_COM_AUX_CLK 189 +#define GCC_USB3_PRIM_PHY_PIPE_CLK 190 +#define GCC_USB3_PRIM_PHY_PIPE_CLK_SRC 191 +#define GCC_USB3_SEC_CLKREF_EN 192 +#define GCC_USB3_SEC_PHY_AUX_CLK 193 +#define GCC_USB3_SEC_PHY_AUX_CLK_SRC 194 +#define GCC_USB3_SEC_PHY_COM_AUX_CLK 195 +#define GCC_USB3_SEC_PHY_PIPE_CLK 196 +#define GCC_USB3_SEC_PHY_PIPE_CLK_SRC 197 +#define GCC_VIDEO_AXI0_CLK 198 +#define GCC_VIDEO_AXI1_CLK 199 + +/* GCC resets */ +#define GCC_CAMERA_BCR 0 +#define GCC_DISPLAY_BCR 1 +#define GCC_GPU_BCR 2 +#define GCC_MMSS_BCR 3 +#define GCC_PCIE_0_BCR 4 +#define GCC_PCIE_0_LINK_DOWN_BCR 5 +#define GCC_PCIE_0_NOCSR_COM_PHY_BCR 6 +#define GCC_PCIE_0_PHY_BCR 7 +#define GCC_PCIE_0_PHY_NOCSR_COM_PHY_BCR 8 +#define GCC_PCIE_1_BCR 9 +#define GCC_PCIE_1_LINK_DOWN_BCR 10 +#define GCC_PCIE_1_NOCSR_COM_PHY_BCR 11 +#define GCC_PCIE_1_PHY_BCR 12 +#define GCC_PCIE_1_PHY_NOCSR_COM_PHY_BCR 13 +#define GCC_PCIE_PHY_CFG_AHB_BCR 14 +#define GCC_PCIE_PHY_COM_BCR 15 +#define GCC_PDM_BCR 16 +#define GCC_QUPV3_WRAPPER_0_BCR 17 +#define GCC_QUPV3_WRAPPER_1_BCR 18 +#define GCC_QUPV3_WRAPPER_2_BCR 19 +#define GCC_QUSB2PHY_PRIM_BCR 20 +#define GCC_QUSB2PHY_SEC_BCR 21 +#define GCC_SDCC2_BCR 22 +#define GCC_SDCC4_BCR 23 +#define GCC_UFS_CARD_BCR 24 +#define GCC_UFS_PHY_BCR 25 +#define GCC_USB30_PRIM_BCR 26 +#define GCC_USB30_SEC_BCR 27 +#define GCC_USB3_DP_PHY_PRIM_BCR 28 +#define GCC_USB3_DP_PHY_SEC_BCR 29 +#define GCC_USB3_PHY_PRIM_BCR 30 +#define GCC_USB3_PHY_SEC_BCR 31 +#define GCC_USB3PHY_PHY_PRIM_BCR 32 +#define GCC_USB3PHY_PHY_SEC_BCR 33 +#define GCC_USB_PHY_CFG_AHB2PHY_BCR 34 +#define GCC_VIDEO_AXI0_CLK_ARES 35 +#define GCC_VIDEO_AXI1_CLK_ARES 36 +#define GCC_VIDEO_BCR 37 + +#endif -- cgit v1.2.3 From 9ba80d849c833ba178acf34992b879f2d933811c Mon Sep 17 00:00:00 2001 From: Bryan O'Donoghue Date: Thu, 4 Feb 2021 15:01:17 +0000 Subject: dt-bindings: clock: Add missing SM8250 videoc clock indices Two indexes need to be added to videocc-sm8250.h for venus to function properly. Rather than adding the missing indexes when used we add them separately here to keep checkpatch.pl happy. Signed-off-by: Bryan O'Donoghue Reviewed-by: Dmitry Baryshkov Tested-by: Dmitry Baryshkov Link: https://lore.kernel.org/r/20210204150120.1521959-2-bryan.odonoghue@linaro.org Signed-off-by: Stephen Boyd --- include/dt-bindings/clock/qcom,videocc-sm8250.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/clock/qcom,videocc-sm8250.h b/include/dt-bindings/clock/qcom,videocc-sm8250.h index 2b2b3867af25..8d321ac3b1fa 100644 --- a/include/dt-bindings/clock/qcom,videocc-sm8250.h +++ b/include/dt-bindings/clock/qcom,videocc-sm8250.h @@ -16,6 +16,8 @@ #define VIDEO_CC_MVS1C_DIV2_DIV_CLK_SRC 6 #define VIDEO_CC_PLL0 7 #define VIDEO_CC_PLL1 8 +#define VIDEO_CC_MVS0_DIV_CLK_SRC 9 +#define VIDEO_CC_MVS0_CLK 10 /* VIDEO_CC resets */ #define VIDEO_CC_CVP_INTERFACE_BCR 0 -- cgit v1.2.3 From 68e5d392a38e3934e42a66260a4cb5eb986033cd Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Thu, 14 Jan 2021 23:10:49 +0100 Subject: dt-bindings: clocks: gcc-msm8998: Add GCC_MMSS_GPLL0_CLK definition Add new clock definition to gcc-msm8998 dt-bindings. Signed-off-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20210114221059.483390-2-angelogioacchino.delregno@somainline.org Signed-off-by: Stephen Boyd --- include/dt-bindings/clock/qcom,gcc-msm8998.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/dt-bindings/clock/qcom,gcc-msm8998.h b/include/dt-bindings/clock/qcom,gcc-msm8998.h index 6a73a174f049..47ca17df780b 100644 --- a/include/dt-bindings/clock/qcom,gcc-msm8998.h +++ b/include/dt-bindings/clock/qcom,gcc-msm8998.h @@ -184,6 +184,7 @@ #define GCC_MSS_MNOC_BIMC_AXI_CLK 175 #define GCC_BIMC_GFX_CLK 176 #define UFS_UNIPRO_CORE_CLK_SRC 177 +#define GCC_MMSS_GPLL0_CLK 178 #define PCIE_0_GDSC 0 #define UFS_GDSC 1 -- cgit v1.2.3 From e9f322f71cbeeb59a0626744bcc204bd9adbbb55 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Thu, 14 Jan 2021 23:10:51 +0100 Subject: dt-bindings: clock: gcc-msm8998: Add HMSS_GPLL0_CLK_SRC definition Add new clock definition to gcc-msm8998 dt-bindings Signed-off-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20210114221059.483390-4-angelogioacchino.delregno@somainline.org Signed-off-by: Stephen Boyd --- include/dt-bindings/clock/qcom,gcc-msm8998.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/dt-bindings/clock/qcom,gcc-msm8998.h b/include/dt-bindings/clock/qcom,gcc-msm8998.h index 47ca17df780b..72c99e486d86 100644 --- a/include/dt-bindings/clock/qcom,gcc-msm8998.h +++ b/include/dt-bindings/clock/qcom,gcc-msm8998.h @@ -185,6 +185,7 @@ #define GCC_BIMC_GFX_CLK 176 #define UFS_UNIPRO_CORE_CLK_SRC 177 #define GCC_MMSS_GPLL0_CLK 178 +#define HMSS_GPLL0_CLK_SRC 179 #define PCIE_0_GDSC 0 #define UFS_GDSC 1 -- cgit v1.2.3 From db72438c9319cfd37e3c237a7754ca862ae12d63 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Tue, 2 Feb 2021 09:13:09 +0200 Subject: RDMA/mlx5: Cleanup the synchronize_srcu() from the ODP flow Cleanup the synchronize_srcu() from the ODP flow as it was found to be a very heavy time consumer as part of dereg_mr. For example de-registration of 10000 ODP MRs each with size of 2M hugepage took 19.6 sec comparing de-registration of same number of non ODP MRs that took 172 ms. The new locking scheme uses the wait_event() mechanism which follows the use count of the MR instead of using synchronize_srcu(). By that change, the time required for the above test took 95 ms which is even better than the non ODP flow. Once fully dropped the srcu usage, had to come with a lock to protect the XA access. As part of using the above mechanism we could also clean the num_deferred_work stuff and follow the use count instead. Link: https://lore.kernel.org/r/20210202071309.2057998-1-leon@kernel.org Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/mlx5/devx.c | 13 +- drivers/infiniband/hw/mlx5/main.c | 5 - drivers/infiniband/hw/mlx5/mlx5_ib.h | 31 +++- drivers/infiniband/hw/mlx5/mr.c | 26 ++-- drivers/infiniband/hw/mlx5/odp.c | 224 ++++++++++----------------- drivers/net/ethernet/mellanox/mlx5/core/mr.c | 1 + include/linux/mlx5/driver.h | 2 + 7 files changed, 127 insertions(+), 175 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c index e6d2709eb09e..e39661db0d2f 100644 --- a/drivers/infiniband/hw/mlx5/devx.c +++ b/drivers/infiniband/hw/mlx5/devx.c @@ -1310,9 +1310,9 @@ static int devx_handle_mkey_indirect(struct devx_obj *obj, mkey->size = MLX5_GET64(mkc, mkc, len); mkey->pd = MLX5_GET(mkc, mkc, pd); devx_mr->ndescs = MLX5_GET(mkc, mkc, translations_octword_size); + init_waitqueue_head(&mkey->wait); - return xa_err(xa_store(&dev->odp_mkeys, mlx5_base_mkey(mkey->key), mkey, - GFP_KERNEL)); + return mlx5r_store_odp_mkey(dev, mkey); } static int devx_handle_mkey_create(struct mlx5_ib_dev *dev, @@ -1385,16 +1385,15 @@ static int devx_obj_cleanup(struct ib_uobject *uobject, int ret; dev = mlx5_udata_to_mdev(&attrs->driver_udata); - if (obj->flags & DEVX_OBJ_FLAGS_INDIRECT_MKEY) { + if (obj->flags & DEVX_OBJ_FLAGS_INDIRECT_MKEY && + xa_erase(&obj->ib_dev->odp_mkeys, + mlx5_base_mkey(obj->devx_mr.mmkey.key))) /* * The pagefault_single_data_segment() does commands against * the mmkey, we must wait for that to stop before freeing the * mkey, as another allocation could get the same mkey #. */ - xa_erase(&obj->ib_dev->odp_mkeys, - mlx5_base_mkey(obj->devx_mr.mmkey.key)); - synchronize_srcu(&dev->odp_srcu); - } + mlx5r_deref_wait_odp_mkey(&obj->devx_mr.mmkey); if (obj->flags & DEVX_OBJ_FLAGS_DCT) ret = mlx5_core_destroy_dct(obj->ib_dev, &obj->core_dct); diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index ce4a9eba53f9..93dd568a5397 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -3869,7 +3869,6 @@ static void mlx5_ib_stage_init_cleanup(struct mlx5_ib_dev *dev) { mlx5_ib_cleanup_multiport_master(dev); WARN_ON(!xa_empty(&dev->odp_mkeys)); - cleanup_srcu_struct(&dev->odp_srcu); mutex_destroy(&dev->cap_mask_mutex); WARN_ON(!xa_empty(&dev->sig_mrs)); WARN_ON(!bitmap_empty(dev->dm.memic_alloc_pages, MLX5_MAX_MEMIC_PAGES)); @@ -3914,10 +3913,6 @@ static int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev) dev->ib_dev.num_comp_vectors = mlx5_comp_vectors_count(mdev); - err = init_srcu_struct(&dev->odp_srcu); - if (err) - goto err_mp; - mutex_init(&dev->cap_mask_mutex); INIT_LIST_HEAD(&dev->qp_list); spin_lock_init(&dev->reset_flow_resource_lock); diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index ab52083634e6..88cc26e008fc 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -684,11 +684,8 @@ struct mlx5_ib_mr { u64 pi_iova; /* For ODP and implicit */ - atomic_t num_deferred_work; - wait_queue_head_t q_deferred_work; struct xarray implicit_children; union { - struct rcu_head rcu; struct list_head elm; struct work_struct work; } odp_destroy; @@ -1068,11 +1065,6 @@ struct mlx5_ib_dev { u64 odp_max_size; struct mlx5_ib_pf_eq odp_pf_eq; - /* - * Sleepable RCU that prevents destruction of MRs while they are still - * being used by a page fault handler. - */ - struct srcu_struct odp_srcu; struct xarray odp_mkeys; u32 null_mkey; @@ -1599,6 +1591,29 @@ static inline bool mlx5_ib_can_reconfig_with_umr(struct mlx5_ib_dev *dev, return true; } +static inline int mlx5r_store_odp_mkey(struct mlx5_ib_dev *dev, + struct mlx5_core_mkey *mmkey) +{ + refcount_set(&mmkey->usecount, 1); + + return xa_err(xa_store(&dev->odp_mkeys, mlx5_base_mkey(mmkey->key), + mmkey, GFP_KERNEL)); +} + +/* deref an mkey that can participate in ODP flow */ +static inline void mlx5r_deref_odp_mkey(struct mlx5_core_mkey *mmkey) +{ + if (refcount_dec_and_test(&mmkey->usecount)) + wake_up(&mmkey->wait); +} + +/* deref an mkey that can participate in ODP flow and wait for relese */ +static inline void mlx5r_deref_wait_odp_mkey(struct mlx5_core_mkey *mmkey) +{ + mlx5r_deref_odp_mkey(mmkey); + wait_event(mmkey->wait, refcount_read(&mmkey->usecount) == 0); +} + int mlx5_ib_test_wc(struct mlx5_ib_dev *dev); static inline bool mlx5_ib_lag_should_assign_affinity(struct mlx5_ib_dev *dev) diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index a63ef7c66e38..db05b0e0a8d7 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -158,6 +158,7 @@ static void create_mkey_callback(int status, struct mlx5_async_work *context) mr->mmkey.type = MLX5_MKEY_MR; mr->mmkey.key |= mlx5_idx_to_mkey( MLX5_GET(create_mkey_out, mr->out, mkey_index)); + init_waitqueue_head(&mr->mmkey.wait); WRITE_ONCE(dev->cache.last_add, jiffies); @@ -1551,10 +1552,7 @@ static struct ib_mr *create_user_odp_mr(struct ib_pd *pd, u64 start, u64 length, } odp->private = mr; - init_waitqueue_head(&mr->q_deferred_work); - atomic_set(&mr->num_deferred_work, 0); - err = xa_err(xa_store(&dev->odp_mkeys, mlx5_base_mkey(mr->mmkey.key), - &mr->mmkey, GFP_KERNEL)); + err = mlx5r_store_odp_mkey(dev, &mr->mmkey); if (err) goto err_dereg_mr; @@ -1651,10 +1649,7 @@ struct ib_mr *mlx5_ib_reg_user_mr_dmabuf(struct ib_pd *pd, u64 offset, atomic_add(ib_umem_num_pages(mr->umem), &dev->mdev->priv.reg_pages); umem_dmabuf->private = mr; - init_waitqueue_head(&mr->q_deferred_work); - atomic_set(&mr->num_deferred_work, 0); - err = xa_err(xa_store(&dev->odp_mkeys, mlx5_base_mkey(mr->mmkey.key), - &mr->mmkey, GFP_KERNEL)); + err = mlx5r_store_odp_mkey(dev, &mr->mmkey); if (err) goto err_dereg_mr; @@ -2330,9 +2325,7 @@ int mlx5_ib_alloc_mw(struct ib_mw *ibmw, struct ib_udata *udata) } if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)) { - err = xa_err(xa_store(&dev->odp_mkeys, - mlx5_base_mkey(mw->mmkey.key), &mw->mmkey, - GFP_KERNEL)); + err = mlx5r_store_odp_mkey(dev, &mw->mmkey); if (err) goto free_mkey; } @@ -2352,14 +2345,13 @@ int mlx5_ib_dealloc_mw(struct ib_mw *mw) struct mlx5_ib_dev *dev = to_mdev(mw->device); struct mlx5_ib_mw *mmw = to_mmw(mw); - if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)) { - xa_erase(&dev->odp_mkeys, mlx5_base_mkey(mmw->mmkey.key)); + if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING) && + xa_erase(&dev->odp_mkeys, mlx5_base_mkey(mmw->mmkey.key))) /* - * pagefault_single_data_segment() may be accessing mmw under - * SRCU if the user bound an ODP MR to this MW. + * pagefault_single_data_segment() may be accessing mmw + * if the user bound an ODP MR to this MW. */ - synchronize_srcu(&dev->odp_srcu); - } + mlx5r_deref_wait_odp_mkey(&mmw->mmkey); return mlx5_core_destroy_mkey(dev->mdev, &mmw->mmkey); } diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index e77b1db73893..374698186662 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -115,7 +115,6 @@ static void populate_klm(struct mlx5_klm *pklm, size_t idx, size_t nentries, * xarray would be protected by the umem_mutex, however that is not * possible. Instead this uses a weaker update-then-lock pattern: * - * srcu_read_lock() * xa_store() * mutex_lock(umem_mutex) * mlx5_ib_update_xlt() @@ -126,12 +125,9 @@ static void populate_klm(struct mlx5_klm *pklm, size_t idx, size_t nentries, * before destroying. * * The umem_mutex provides the acquire/release semantic needed to make - * the xa_store() visible to a racing thread. While SRCU is not - * technically required, using it gives consistent use of the SRCU - * locking around the xarray. + * the xa_store() visible to a racing thread. */ lockdep_assert_held(&to_ib_umem_odp(imr->umem)->umem_mutex); - lockdep_assert_held(&mr_to_mdev(imr)->odp_srcu); for (; pklm != end; pklm++, idx++) { struct mlx5_ib_mr *mtt = xa_load(&imr->implicit_children, idx); @@ -207,8 +203,8 @@ static void dma_fence_odp_mr(struct mlx5_ib_mr *mr) } /* - * This must be called after the mr has been removed from implicit_children - * and the SRCU synchronized. NOTE: The MR does not necessarily have to be + * This must be called after the mr has been removed from implicit_children. + * NOTE: The MR does not necessarily have to be * empty here, parallel page faults could have raced with the free process and * added pages to it. */ @@ -218,19 +214,15 @@ static void free_implicit_child_mr(struct mlx5_ib_mr *mr, bool need_imr_xlt) struct ib_umem_odp *odp_imr = to_ib_umem_odp(imr->umem); struct ib_umem_odp *odp = to_ib_umem_odp(mr->umem); unsigned long idx = ib_umem_start(odp) >> MLX5_IMR_MTT_SHIFT; - int srcu_key; - /* implicit_child_mr's are not allowed to have deferred work */ - WARN_ON(atomic_read(&mr->num_deferred_work)); + mlx5r_deref_wait_odp_mkey(&mr->mmkey); if (need_imr_xlt) { - srcu_key = srcu_read_lock(&mr_to_mdev(mr)->odp_srcu); mutex_lock(&odp_imr->umem_mutex); mlx5_ib_update_xlt(mr->parent, idx, 1, 0, MLX5_IB_UPD_XLT_INDIRECT | MLX5_IB_UPD_XLT_ATOMIC); mutex_unlock(&odp_imr->umem_mutex); - srcu_read_unlock(&mr_to_mdev(mr)->odp_srcu, srcu_key); } dma_fence_odp_mr(mr); @@ -238,26 +230,16 @@ static void free_implicit_child_mr(struct mlx5_ib_mr *mr, bool need_imr_xlt) mr->parent = NULL; mlx5_mr_cache_free(mr_to_mdev(mr), mr); ib_umem_odp_release(odp); - if (atomic_dec_and_test(&imr->num_deferred_work)) - wake_up(&imr->q_deferred_work); } static void free_implicit_child_mr_work(struct work_struct *work) { struct mlx5_ib_mr *mr = container_of(work, struct mlx5_ib_mr, odp_destroy.work); + struct mlx5_ib_mr *imr = mr->parent; free_implicit_child_mr(mr, true); -} - -static void free_implicit_child_mr_rcu(struct rcu_head *head) -{ - struct mlx5_ib_mr *mr = - container_of(head, struct mlx5_ib_mr, odp_destroy.rcu); - - /* Freeing a MR is a sleeping operation, so bounce to a work queue */ - INIT_WORK(&mr->odp_destroy.work, free_implicit_child_mr_work); - queue_work(system_unbound_wq, &mr->odp_destroy.work); + mlx5r_deref_odp_mkey(&imr->mmkey); } static void destroy_unused_implicit_child_mr(struct mlx5_ib_mr *mr) @@ -266,21 +248,14 @@ static void destroy_unused_implicit_child_mr(struct mlx5_ib_mr *mr) unsigned long idx = ib_umem_start(odp) >> MLX5_IMR_MTT_SHIFT; struct mlx5_ib_mr *imr = mr->parent; - xa_lock(&imr->implicit_children); - /* - * This can race with mlx5_ib_free_implicit_mr(), the first one to - * reach the xa lock wins the race and destroys the MR. - */ - if (__xa_cmpxchg(&imr->implicit_children, idx, mr, NULL, GFP_ATOMIC) != - mr) - goto out_unlock; + if (!refcount_inc_not_zero(&imr->mmkey.usecount)) + return; - atomic_inc(&imr->num_deferred_work); - call_srcu(&mr_to_mdev(mr)->odp_srcu, &mr->odp_destroy.rcu, - free_implicit_child_mr_rcu); + xa_erase(&imr->implicit_children, idx); -out_unlock: - xa_unlock(&imr->implicit_children); + /* Freeing a MR is a sleeping operation, so bounce to a work queue */ + INIT_WORK(&mr->odp_destroy.work, free_implicit_child_mr_work); + queue_work(system_unbound_wq, &mr->odp_destroy.work); } static bool mlx5_ib_invalidate_range(struct mmu_interval_notifier *mni, @@ -492,6 +467,12 @@ static struct mlx5_ib_mr *implicit_get_child_mr(struct mlx5_ib_mr *imr, mr->parent = imr; odp->private = mr; + /* + * First refcount is owned by the xarray and second refconut + * is returned to the caller. + */ + refcount_set(&mr->mmkey.usecount, 2); + err = mlx5_ib_update_xlt(mr, 0, MLX5_IMR_MTT_ENTRIES, PAGE_SHIFT, @@ -502,27 +483,28 @@ static struct mlx5_ib_mr *implicit_get_child_mr(struct mlx5_ib_mr *imr, goto out_mr; } - /* - * Once the store to either xarray completes any error unwind has to - * use synchronize_srcu(). Avoid this with xa_reserve() - */ - ret = xa_cmpxchg(&imr->implicit_children, idx, NULL, mr, - GFP_KERNEL); + xa_lock(&imr->implicit_children); + ret = __xa_cmpxchg(&imr->implicit_children, idx, NULL, mr, + GFP_KERNEL); if (unlikely(ret)) { if (xa_is_err(ret)) { ret = ERR_PTR(xa_err(ret)); - goto out_mr; + goto out_lock; } /* * Another thread beat us to creating the child mr, use * theirs. */ - goto out_mr; + refcount_inc(&ret->mmkey.usecount); + goto out_lock; } + xa_unlock(&imr->implicit_children); mlx5_ib_dbg(mr_to_mdev(imr), "key %x mr %p\n", mr->mmkey.key, mr); return mr; +out_lock: + xa_unlock(&imr->implicit_children); out_mr: mlx5_mr_cache_free(mr_to_mdev(imr), mr); out_umem: @@ -561,8 +543,6 @@ struct mlx5_ib_mr *mlx5_ib_alloc_implicit_mr(struct mlx5_ib_pd *pd, imr->ibmr.device = &dev->ib_dev; imr->umem = &umem_odp->umem; imr->is_odp_implicit = true; - atomic_set(&imr->num_deferred_work, 0); - init_waitqueue_head(&imr->q_deferred_work); xa_init(&imr->implicit_children); err = mlx5_ib_update_xlt(imr, 0, @@ -574,8 +554,7 @@ struct mlx5_ib_mr *mlx5_ib_alloc_implicit_mr(struct mlx5_ib_pd *pd, if (err) goto out_mr; - err = xa_err(xa_store(&dev->odp_mkeys, mlx5_base_mkey(imr->mmkey.key), - &imr->mmkey, GFP_KERNEL)); + err = mlx5r_store_odp_mkey(dev, &imr->mmkey); if (err) goto out_mr; @@ -593,51 +572,24 @@ void mlx5_ib_free_implicit_mr(struct mlx5_ib_mr *imr) { struct ib_umem_odp *odp_imr = to_ib_umem_odp(imr->umem); struct mlx5_ib_dev *dev = mr_to_mdev(imr); - struct list_head destroy_list; struct mlx5_ib_mr *mtt; - struct mlx5_ib_mr *tmp; unsigned long idx; - INIT_LIST_HEAD(&destroy_list); - xa_erase(&dev->odp_mkeys, mlx5_base_mkey(imr->mmkey.key)); - /* - * This stops the SRCU protected page fault path from touching either - * the imr or any children. The page fault path can only reach the - * children xarray via the imr. - */ - synchronize_srcu(&dev->odp_srcu); - /* * All work on the prefetch list must be completed, xa_erase() prevented * new work from being created. */ - wait_event(imr->q_deferred_work, !atomic_read(&imr->num_deferred_work)); - + mlx5r_deref_wait_odp_mkey(&imr->mmkey); /* * At this point it is forbidden for any other thread to enter * pagefault_mr() on this imr. It is already forbidden to call * pagefault_mr() on an implicit child. Due to this additions to * implicit_children are prevented. + * In addition, any new call to destroy_unused_implicit_child_mr() + * may return immediately. */ - /* - * Block destroy_unused_implicit_child_mr() from incrementing - * num_deferred_work. - */ - xa_lock(&imr->implicit_children); - xa_for_each (&imr->implicit_children, idx, mtt) { - __xa_erase(&imr->implicit_children, idx); - list_add(&mtt->odp_destroy.elm, &destroy_list); - } - xa_unlock(&imr->implicit_children); - - /* - * Wait for any concurrent destroy_unused_implicit_child_mr() to - * complete. - */ - wait_event(imr->q_deferred_work, !atomic_read(&imr->num_deferred_work)); - /* * Fence the imr before we destroy the children. This allows us to * skip updating the XLT of the imr during destroy of the child mkey @@ -645,8 +597,10 @@ void mlx5_ib_free_implicit_mr(struct mlx5_ib_mr *imr) */ mlx5_mr_cache_invalidate(imr); - list_for_each_entry_safe (mtt, tmp, &destroy_list, odp_destroy.elm) + xa_for_each(&imr->implicit_children, idx, mtt) { + xa_erase(&imr->implicit_children, idx); free_implicit_child_mr(mtt, false); + } mlx5_mr_cache_free(dev, imr); ib_umem_odp_release(odp_imr); @@ -665,9 +619,7 @@ void mlx5_ib_fence_odp_mr(struct mlx5_ib_mr *mr) xa_erase(&mr_to_mdev(mr)->odp_mkeys, mlx5_base_mkey(mr->mmkey.key)); /* Wait for all running page-fault handlers to finish. */ - synchronize_srcu(&mr_to_mdev(mr)->odp_srcu); - - wait_event(mr->q_deferred_work, !atomic_read(&mr->num_deferred_work)); + mlx5r_deref_wait_odp_mkey(&mr->mmkey); dma_fence_odp_mr(mr); } @@ -686,10 +638,7 @@ void mlx5_ib_fence_dmabuf_mr(struct mlx5_ib_mr *mr) /* Prevent new page faults and prefetch requests from succeeding */ xa_erase(&mr_to_mdev(mr)->odp_mkeys, mlx5_base_mkey(mr->mmkey.key)); - /* Wait for all running page-fault handlers to finish. */ - synchronize_srcu(&mr_to_mdev(mr)->odp_srcu); - - wait_event(mr->q_deferred_work, !atomic_read(&mr->num_deferred_work)); + mlx5r_deref_wait_odp_mkey(&mr->mmkey); dma_resv_lock(umem_dmabuf->attach->dmabuf->resv, NULL); mlx5_mr_cache_invalidate(mr); @@ -780,8 +729,10 @@ static int pagefault_implicit_mr(struct mlx5_ib_mr *imr, struct mlx5_ib_mr *mtt; u64 len; + xa_lock(&imr->implicit_children); mtt = xa_load(&imr->implicit_children, idx); if (unlikely(!mtt)) { + xa_unlock(&imr->implicit_children); mtt = implicit_get_child_mr(imr, idx); if (IS_ERR(mtt)) { ret = PTR_ERR(mtt); @@ -789,6 +740,9 @@ static int pagefault_implicit_mr(struct mlx5_ib_mr *imr, } upd_start_idx = min(upd_start_idx, idx); upd_len = idx - upd_start_idx + 1; + } else { + refcount_inc(&mtt->mmkey.usecount); + xa_unlock(&imr->implicit_children); } umem_odp = to_ib_umem_odp(mtt->umem); @@ -797,6 +751,9 @@ static int pagefault_implicit_mr(struct mlx5_ib_mr *imr, ret = pagefault_real_mr(mtt, umem_odp, user_va, len, bytes_mapped, flags); + + mlx5r_deref_odp_mkey(&mtt->mmkey); + if (ret < 0) goto out; user_va += len; @@ -888,7 +845,6 @@ static int pagefault_mr(struct mlx5_ib_mr *mr, u64 io_virt, size_t bcnt, { struct ib_umem_odp *odp = to_ib_umem_odp(mr->umem); - lockdep_assert_held(&mr_to_mdev(mr)->odp_srcu); if (unlikely(io_virt < mr->mmkey.iova)) return -EFAULT; @@ -980,7 +936,7 @@ static int pagefault_single_data_segment(struct mlx5_ib_dev *dev, u32 *bytes_committed, u32 *bytes_mapped) { - int npages = 0, srcu_key, ret, i, outlen, cur_outlen = 0, depth = 0; + int npages = 0, ret, i, outlen, cur_outlen = 0, depth = 0; struct pf_frame *head = NULL, *frame; struct mlx5_core_mkey *mmkey; struct mlx5_ib_mr *mr; @@ -989,14 +945,14 @@ static int pagefault_single_data_segment(struct mlx5_ib_dev *dev, size_t offset; int ndescs; - srcu_key = srcu_read_lock(&dev->odp_srcu); - io_virt += *bytes_committed; bcnt -= *bytes_committed; next_mr: + xa_lock(&dev->odp_mkeys); mmkey = xa_load(&dev->odp_mkeys, mlx5_base_mkey(key)); if (!mmkey) { + xa_unlock(&dev->odp_mkeys); mlx5_ib_dbg( dev, "skipping non ODP MR (lkey=0x%06x) in page fault handler.\n", @@ -1009,12 +965,15 @@ next_mr: * faulted. */ ret = 0; - goto srcu_unlock; + goto end; } + refcount_inc(&mmkey->usecount); + xa_unlock(&dev->odp_mkeys); + if (!mkey_is_eq(mmkey, key)) { mlx5_ib_dbg(dev, "failed to find mkey %x\n", key); ret = -EFAULT; - goto srcu_unlock; + goto end; } switch (mmkey->type) { @@ -1023,7 +982,7 @@ next_mr: ret = pagefault_mr(mr, io_virt, bcnt, bytes_mapped, 0); if (ret < 0) - goto srcu_unlock; + goto end; mlx5_update_odp_stats(mr, faults, ret); @@ -1038,7 +997,7 @@ next_mr: if (depth >= MLX5_CAP_GEN(dev->mdev, max_indirection)) { mlx5_ib_dbg(dev, "indirection level exceeded\n"); ret = -EFAULT; - goto srcu_unlock; + goto end; } outlen = MLX5_ST_SZ_BYTES(query_mkey_out) + @@ -1049,7 +1008,7 @@ next_mr: out = kzalloc(outlen, GFP_KERNEL); if (!out) { ret = -ENOMEM; - goto srcu_unlock; + goto end; } cur_outlen = outlen; } @@ -1059,7 +1018,7 @@ next_mr: ret = mlx5_core_query_mkey(dev->mdev, mmkey, out, outlen); if (ret) - goto srcu_unlock; + goto end; offset = io_virt - MLX5_GET64(query_mkey_out, out, memory_key_mkey_entry.start_addr); @@ -1073,7 +1032,7 @@ next_mr: frame = kzalloc(sizeof(*frame), GFP_KERNEL); if (!frame) { ret = -ENOMEM; - goto srcu_unlock; + goto end; } frame->key = be32_to_cpu(pklm->key); @@ -1092,7 +1051,7 @@ next_mr: default: mlx5_ib_dbg(dev, "wrong mkey type %d\n", mmkey->type); ret = -EFAULT; - goto srcu_unlock; + goto end; } if (head) { @@ -1105,10 +1064,13 @@ next_mr: depth = frame->depth; kfree(frame); + mlx5r_deref_odp_mkey(mmkey); goto next_mr; } -srcu_unlock: +end: + if (mmkey) + mlx5r_deref_odp_mkey(mmkey); while (head) { frame = head; head = frame->next; @@ -1116,7 +1078,6 @@ srcu_unlock: } kfree(out); - srcu_read_unlock(&dev->odp_srcu, srcu_key); *bytes_committed = 0; return ret ? ret : npages; } @@ -1824,8 +1785,8 @@ static void destroy_prefetch_work(struct prefetch_mr_work *work) u32 i; for (i = 0; i < work->num_sge; ++i) - if (atomic_dec_and_test(&work->frags[i].mr->num_deferred_work)) - wake_up(&work->frags[i].mr->q_deferred_work); + mlx5r_deref_odp_mkey(&work->frags[i].mr->mmkey); + kvfree(work); } @@ -1835,24 +1796,30 @@ get_prefetchable_mr(struct ib_pd *pd, enum ib_uverbs_advise_mr_advice advice, { struct mlx5_ib_dev *dev = to_mdev(pd->device); struct mlx5_core_mkey *mmkey; - struct mlx5_ib_mr *mr; - - lockdep_assert_held(&dev->odp_srcu); + struct mlx5_ib_mr *mr = NULL; + xa_lock(&dev->odp_mkeys); mmkey = xa_load(&dev->odp_mkeys, mlx5_base_mkey(lkey)); if (!mmkey || mmkey->key != lkey || mmkey->type != MLX5_MKEY_MR) - return NULL; + goto end; mr = container_of(mmkey, struct mlx5_ib_mr, mmkey); - if (mr->ibmr.pd != pd) - return NULL; + if (mr->ibmr.pd != pd) { + mr = NULL; + goto end; + } /* prefetch with write-access must be supported by the MR */ if (advice == IB_UVERBS_ADVISE_MR_ADVICE_PREFETCH_WRITE && - !mr->umem->writable) - return NULL; + !mr->umem->writable) { + mr = NULL; + goto end; + } + refcount_inc(&mmkey->usecount); +end: + xa_unlock(&dev->odp_mkeys); return mr; } @@ -1860,17 +1827,12 @@ static void mlx5_ib_prefetch_mr_work(struct work_struct *w) { struct prefetch_mr_work *work = container_of(w, struct prefetch_mr_work, work); - struct mlx5_ib_dev *dev; u32 bytes_mapped = 0; - int srcu_key; int ret; u32 i; /* We rely on IB/core that work is executed if we have num_sge != 0 only. */ WARN_ON(!work->num_sge); - dev = mr_to_mdev(work->frags[0].mr); - /* SRCU should be held when calling to mlx5_odp_populate_xlt() */ - srcu_key = srcu_read_lock(&dev->odp_srcu); for (i = 0; i < work->num_sge; ++i) { ret = pagefault_mr(work->frags[i].mr, work->frags[i].io_virt, work->frags[i].length, &bytes_mapped, @@ -1879,7 +1841,6 @@ static void mlx5_ib_prefetch_mr_work(struct work_struct *w) continue; mlx5_update_odp_stats(work->frags[i].mr, prefetch, ret); } - srcu_read_unlock(&dev->odp_srcu, srcu_key); destroy_prefetch_work(work); } @@ -1903,9 +1864,6 @@ static bool init_prefetch_work(struct ib_pd *pd, work->num_sge = i; return false; } - - /* Keep the MR pointer will valid outside the SRCU */ - atomic_inc(&work->frags[i].mr->num_deferred_work); } work->num_sge = num_sge; return true; @@ -1916,42 +1874,35 @@ static int mlx5_ib_prefetch_sg_list(struct ib_pd *pd, u32 pf_flags, struct ib_sge *sg_list, u32 num_sge) { - struct mlx5_ib_dev *dev = to_mdev(pd->device); u32 bytes_mapped = 0; - int srcu_key; int ret = 0; u32 i; - srcu_key = srcu_read_lock(&dev->odp_srcu); for (i = 0; i < num_sge; ++i) { struct mlx5_ib_mr *mr; mr = get_prefetchable_mr(pd, advice, sg_list[i].lkey); - if (!mr) { - ret = -ENOENT; - goto out; - } + if (!mr) + return -ENOENT; ret = pagefault_mr(mr, sg_list[i].addr, sg_list[i].length, &bytes_mapped, pf_flags); - if (ret < 0) - goto out; + if (ret < 0) { + mlx5r_deref_odp_mkey(&mr->mmkey); + return ret; + } mlx5_update_odp_stats(mr, prefetch, ret); + mlx5r_deref_odp_mkey(&mr->mmkey); } - ret = 0; -out: - srcu_read_unlock(&dev->odp_srcu, srcu_key); - return ret; + return 0; } int mlx5_ib_advise_mr_prefetch(struct ib_pd *pd, enum ib_uverbs_advise_mr_advice advice, u32 flags, struct ib_sge *sg_list, u32 num_sge) { - struct mlx5_ib_dev *dev = to_mdev(pd->device); u32 pf_flags = 0; struct prefetch_mr_work *work; - int srcu_key; if (advice == IB_UVERBS_ADVISE_MR_ADVICE_PREFETCH) pf_flags |= MLX5_PF_FLAGS_DOWNGRADE; @@ -1967,13 +1918,10 @@ int mlx5_ib_advise_mr_prefetch(struct ib_pd *pd, if (!work) return -ENOMEM; - srcu_key = srcu_read_lock(&dev->odp_srcu); if (!init_prefetch_work(pd, advice, pf_flags, work, sg_list, num_sge)) { - srcu_read_unlock(&dev->odp_srcu, srcu_key); destroy_prefetch_work(work); return -EINVAL; } queue_work(system_unbound_wq, &work->work); - srcu_read_unlock(&dev->odp_srcu, srcu_key); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c index 9eb51f06d3ae..50af84e76fb6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c @@ -56,6 +56,7 @@ int mlx5_core_create_mkey(struct mlx5_core_dev *dev, mkey->size = MLX5_GET64(mkc, mkc, len); mkey->key |= mlx5_idx_to_mkey(mkey_index); mkey->pd = MLX5_GET(mkc, mkc, pd); + init_waitqueue_head(&mkey->wait); mlx5_core_dbg(dev, "out 0x%x, mkey 0x%x\n", mkey_index, mkey->key); return 0; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 11558c2e99f0..b0a59a18a708 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -366,6 +366,8 @@ struct mlx5_core_mkey { u32 key; u32 pd; u32 type; + struct wait_queue_head wait; + refcount_t usecount; }; #define MLX5_24BIT_MASK ((1 << 24) - 1) -- cgit v1.2.3 From bc6b9dc79c87cf3bbf3e150fef64ef45f652ae41 Mon Sep 17 00:00:00 2001 From: Michael Tretter Date: Thu, 21 Jan 2021 08:16:45 +0100 Subject: ARM: dts: vcu: define indexes for output clocks The VCU System-Level Control has 4 output clocks. Define indexes for these clocks to allow to reference them in the device tree. Signed-off-by: Michael Tretter Acked-by: Rob Herring Acked-by: Stephen Boyd Acked-by: Michal Simek Link: https://lore.kernel.org/r/20210121071659.1226489-2-m.tretter@pengutronix.de Signed-off-by: Stephen Boyd --- include/dt-bindings/clock/xlnx-vcu.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) create mode 100644 include/dt-bindings/clock/xlnx-vcu.h (limited to 'include') diff --git a/include/dt-bindings/clock/xlnx-vcu.h b/include/dt-bindings/clock/xlnx-vcu.h new file mode 100644 index 000000000000..1ed76b9563b6 --- /dev/null +++ b/include/dt-bindings/clock/xlnx-vcu.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2020 Pengutronix, Michael Tretter + */ + +#ifndef _DT_BINDINGS_CLOCK_XLNX_VCU_H +#define _DT_BINDINGS_CLOCK_XLNX_VCU_H + +#define CLK_XVCU_ENC_CORE 0 +#define CLK_XVCU_ENC_MCU 1 +#define CLK_XVCU_DEC_CORE 2 +#define CLK_XVCU_DEC_MCU 3 +#define CLK_XVCU_NUM_CLOCKS 4 + +#endif /* _DT_BINDINGS_CLOCK_XLNX_VCU_H */ -- cgit v1.2.3 From 5923d64b7ab63dcc6f0df946098f50902f9540d1 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Sat, 6 Feb 2021 22:46:01 -0600 Subject: scsi: libiscsi: Drop taskqueuelock The purpose of the taskqueuelock was to handle the issue where a bad target decides to send a R2T and before its data has been sent decides to send a cmd response to complete the cmd. The following patches fix up the frwd/back locks so they are taken from the queue/xmit (frwd) and completion (back) paths again. To get there this patch removes the taskqueuelock which for iSCSI xmit wq based drivers was taken in the queue, xmit and completion paths. Instead of the lock, we just make sure we have a ref to the task when we queue a R2T, and then we always remove the task from the requeue list in the xmit path or the forced cleanup paths. Link: https://lore.kernel.org/r/20210207044608.27585-3-michael.christie@oracle.com Reviewed-by: Lee Duncan Signed-off-by: Mike Christie Signed-off-by: Martin K. Petersen --- drivers/scsi/libiscsi.c | 178 ++++++++++++++++++++++++++++---------------- drivers/scsi/libiscsi_tcp.c | 86 +++++++++++++-------- include/scsi/libiscsi.h | 4 +- 3 files changed, 172 insertions(+), 96 deletions(-) (limited to 'include') diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index cee1dbaa1b93..3d74fdd9f31a 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -523,16 +523,6 @@ static void iscsi_complete_task(struct iscsi_task *task, int state) WARN_ON_ONCE(task->state == ISCSI_TASK_FREE); task->state = state; - spin_lock_bh(&conn->taskqueuelock); - if (!list_empty(&task->running)) { - pr_debug_once("%s while task on list", __func__); - list_del_init(&task->running); - } - spin_unlock_bh(&conn->taskqueuelock); - - if (conn->task == task) - conn->task = NULL; - if (READ_ONCE(conn->ping_task) == task) WRITE_ONCE(conn->ping_task, NULL); @@ -564,9 +554,40 @@ void iscsi_complete_scsi_task(struct iscsi_task *task, } EXPORT_SYMBOL_GPL(iscsi_complete_scsi_task); +/* + * Must be called with back and frwd lock + */ +static bool cleanup_queued_task(struct iscsi_task *task) +{ + struct iscsi_conn *conn = task->conn; + bool early_complete = false; + + /* Bad target might have completed task while it was still running */ + if (task->state == ISCSI_TASK_COMPLETED) + early_complete = true; + + if (!list_empty(&task->running)) { + list_del_init(&task->running); + /* + * If it's on a list but still running, this could be from + * a bad target sending a rsp early, cleanup from a TMF, or + * session recovery. + */ + if (task->state == ISCSI_TASK_RUNNING || + task->state == ISCSI_TASK_COMPLETED) + __iscsi_put_task(task); + } + + if (conn->task == task) { + conn->task = NULL; + __iscsi_put_task(task); + } + + return early_complete; +} /* - * session back_lock must be held and if not called for a task that is + * session frwd_lock must be held and if not called for a task that is * still pending or from the xmit thread, then xmit thread must * be suspended. */ @@ -585,6 +606,13 @@ static void fail_scsi_task(struct iscsi_task *task, int err) if (!sc) return; + /* regular RX path uses back_lock */ + spin_lock_bh(&conn->session->back_lock); + if (cleanup_queued_task(task)) { + spin_unlock_bh(&conn->session->back_lock); + return; + } + if (task->state == ISCSI_TASK_PENDING) { /* * cmd never made it to the xmit thread, so we should not count @@ -600,9 +628,6 @@ static void fail_scsi_task(struct iscsi_task *task, int err) sc->result = err << 16; scsi_set_resid(sc, scsi_bufflen(sc)); - - /* regular RX path uses back_lock */ - spin_lock_bh(&conn->session->back_lock); iscsi_complete_task(task, state); spin_unlock_bh(&conn->session->back_lock); } @@ -748,9 +773,7 @@ __iscsi_conn_send_pdu(struct iscsi_conn *conn, struct iscsi_hdr *hdr, if (session->tt->xmit_task(task)) goto free_task; } else { - spin_lock_bh(&conn->taskqueuelock); list_add_tail(&task->running, &conn->mgmtqueue); - spin_unlock_bh(&conn->taskqueuelock); iscsi_conn_queue_work(conn); } @@ -1411,31 +1434,61 @@ static int iscsi_check_cmdsn_window_closed(struct iscsi_conn *conn) return 0; } -static int iscsi_xmit_task(struct iscsi_conn *conn) +static int iscsi_xmit_task(struct iscsi_conn *conn, struct iscsi_task *task, + bool was_requeue) { - struct iscsi_task *task = conn->task; int rc; - if (test_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx)) - return -ENODATA; - spin_lock_bh(&conn->session->back_lock); - if (conn->task == NULL) { + + if (!conn->task) { + /* Take a ref so we can access it after xmit_task() */ + __iscsi_get_task(task); + } else { + /* Already have a ref from when we failed to send it last call */ + conn->task = NULL; + } + + /* + * If this was a requeue for a R2T we have an extra ref on the task in + * case a bad target sends a cmd rsp before we have handled the task. + */ + if (was_requeue) + __iscsi_put_task(task); + + /* + * Do this after dropping the extra ref because if this was a requeue + * it's removed from that list and cleanup_queued_task would miss it. + */ + if (test_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx)) { + /* + * Save the task and ref in case we weren't cleaning up this + * task and get woken up again. + */ + conn->task = task; spin_unlock_bh(&conn->session->back_lock); return -ENODATA; } - __iscsi_get_task(task); spin_unlock_bh(&conn->session->back_lock); + spin_unlock_bh(&conn->session->frwd_lock); rc = conn->session->tt->xmit_task(task); spin_lock_bh(&conn->session->frwd_lock); if (!rc) { /* done with this task */ task->last_xfer = jiffies; - conn->task = NULL; } /* regular RX path uses back_lock */ spin_lock(&conn->session->back_lock); + if (rc && task->state == ISCSI_TASK_RUNNING) { + /* + * get an extra ref that is released next time we access it + * as conn->task above. + */ + __iscsi_get_task(task); + conn->task = task; + } + __iscsi_put_task(task); spin_unlock(&conn->session->back_lock); return rc; @@ -1445,9 +1498,7 @@ static int iscsi_xmit_task(struct iscsi_conn *conn) * iscsi_requeue_task - requeue task to run from session workqueue * @task: task to requeue * - * LLDs that need to run a task from the session workqueue should call - * this. The session frwd_lock must be held. This should only be called - * by software drivers. + * Callers must have taken a ref to the task that is going to be requeued. */ void iscsi_requeue_task(struct iscsi_task *task) { @@ -1457,11 +1508,18 @@ void iscsi_requeue_task(struct iscsi_task *task) * this may be on the requeue list already if the xmit_task callout * is handling the r2ts while we are adding new ones */ - spin_lock_bh(&conn->taskqueuelock); - if (list_empty(&task->running)) + spin_lock_bh(&conn->session->frwd_lock); + if (list_empty(&task->running)) { list_add_tail(&task->running, &conn->requeue); - spin_unlock_bh(&conn->taskqueuelock); + } else { + /* + * Don't need the extra ref since it's already requeued and + * has a ref. + */ + iscsi_put_task(task); + } iscsi_conn_queue_work(conn); + spin_unlock_bh(&conn->session->frwd_lock); } EXPORT_SYMBOL_GPL(iscsi_requeue_task); @@ -1487,7 +1545,7 @@ static int iscsi_data_xmit(struct iscsi_conn *conn) } if (conn->task) { - rc = iscsi_xmit_task(conn); + rc = iscsi_xmit_task(conn, conn->task, false); if (rc) goto done; } @@ -1497,49 +1555,41 @@ static int iscsi_data_xmit(struct iscsi_conn *conn) * only have one nop-out as a ping from us and targets should not * overflow us with nop-ins */ - spin_lock_bh(&conn->taskqueuelock); check_mgmt: while (!list_empty(&conn->mgmtqueue)) { - conn->task = list_entry(conn->mgmtqueue.next, - struct iscsi_task, running); - list_del_init(&conn->task->running); - spin_unlock_bh(&conn->taskqueuelock); - if (iscsi_prep_mgmt_task(conn, conn->task)) { + task = list_entry(conn->mgmtqueue.next, struct iscsi_task, + running); + list_del_init(&task->running); + if (iscsi_prep_mgmt_task(conn, task)) { /* regular RX path uses back_lock */ spin_lock_bh(&conn->session->back_lock); - __iscsi_put_task(conn->task); + __iscsi_put_task(task); spin_unlock_bh(&conn->session->back_lock); - conn->task = NULL; - spin_lock_bh(&conn->taskqueuelock); continue; } - rc = iscsi_xmit_task(conn); + rc = iscsi_xmit_task(conn, task, false); if (rc) goto done; - spin_lock_bh(&conn->taskqueuelock); } /* process pending command queue */ while (!list_empty(&conn->cmdqueue)) { - conn->task = list_entry(conn->cmdqueue.next, struct iscsi_task, - running); - list_del_init(&conn->task->running); - spin_unlock_bh(&conn->taskqueuelock); + task = list_entry(conn->cmdqueue.next, struct iscsi_task, + running); + list_del_init(&task->running); if (conn->session->state == ISCSI_STATE_LOGGING_OUT) { - fail_scsi_task(conn->task, DID_IMM_RETRY); - spin_lock_bh(&conn->taskqueuelock); + fail_scsi_task(task, DID_IMM_RETRY); continue; } - rc = iscsi_prep_scsi_cmd_pdu(conn->task); + rc = iscsi_prep_scsi_cmd_pdu(task); if (rc) { if (rc == -ENOMEM || rc == -EACCES) - fail_scsi_task(conn->task, DID_IMM_RETRY); + fail_scsi_task(task, DID_IMM_RETRY); else - fail_scsi_task(conn->task, DID_ABORT); - spin_lock_bh(&conn->taskqueuelock); + fail_scsi_task(task, DID_ABORT); continue; } - rc = iscsi_xmit_task(conn); + rc = iscsi_xmit_task(conn, task, false); if (rc) goto done; /* @@ -1547,7 +1597,6 @@ check_mgmt: * we need to check the mgmt queue for nops that need to * be sent to aviod starvation */ - spin_lock_bh(&conn->taskqueuelock); if (!list_empty(&conn->mgmtqueue)) goto check_mgmt; } @@ -1561,21 +1610,17 @@ check_mgmt: task = list_entry(conn->requeue.next, struct iscsi_task, running); + if (iscsi_check_tmf_restrictions(task, ISCSI_OP_SCSI_DATA_OUT)) break; - conn->task = task; - list_del_init(&conn->task->running); - conn->task->state = ISCSI_TASK_RUNNING; - spin_unlock_bh(&conn->taskqueuelock); - rc = iscsi_xmit_task(conn); + list_del_init(&task->running); + rc = iscsi_xmit_task(conn, task, true); if (rc) goto done; - spin_lock_bh(&conn->taskqueuelock); if (!list_empty(&conn->mgmtqueue)) goto check_mgmt; } - spin_unlock_bh(&conn->taskqueuelock); spin_unlock_bh(&conn->session->frwd_lock); return -ENODATA; @@ -1741,9 +1786,7 @@ int iscsi_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *sc) goto prepd_reject; } } else { - spin_lock_bh(&conn->taskqueuelock); list_add_tail(&task->running, &conn->cmdqueue); - spin_unlock_bh(&conn->taskqueuelock); iscsi_conn_queue_work(conn); } @@ -2914,7 +2957,6 @@ iscsi_conn_setup(struct iscsi_cls_session *cls_session, int dd_size, INIT_LIST_HEAD(&conn->mgmtqueue); INIT_LIST_HEAD(&conn->cmdqueue); INIT_LIST_HEAD(&conn->requeue); - spin_lock_init(&conn->taskqueuelock); INIT_WORK(&conn->xmitwork, iscsi_xmitworker); /* allocate login_task used for the login/text sequences */ @@ -3080,10 +3122,16 @@ fail_mgmt_tasks(struct iscsi_session *session, struct iscsi_conn *conn) ISCSI_DBG_SESSION(conn->session, "failing mgmt itt 0x%x state %d\n", task->itt, task->state); + + spin_lock_bh(&session->back_lock); + if (cleanup_queued_task(task)) { + spin_unlock_bh(&session->back_lock); + continue; + } + state = ISCSI_TASK_ABRT_SESS_RECOV; if (task->state == ISCSI_TASK_PENDING) state = ISCSI_TASK_COMPLETED; - spin_lock_bh(&session->back_lock); iscsi_complete_task(task, state); spin_unlock_bh(&session->back_lock); } diff --git a/drivers/scsi/libiscsi_tcp.c b/drivers/scsi/libiscsi_tcp.c index 83f14b2c8804..2e9ffe3d1a55 100644 --- a/drivers/scsi/libiscsi_tcp.c +++ b/drivers/scsi/libiscsi_tcp.c @@ -524,48 +524,79 @@ static int iscsi_tcp_data_in(struct iscsi_conn *conn, struct iscsi_task *task) /** * iscsi_tcp_r2t_rsp - iSCSI R2T Response processing * @conn: iscsi connection - * @task: scsi command task + * @hdr: PDU header */ -static int iscsi_tcp_r2t_rsp(struct iscsi_conn *conn, struct iscsi_task *task) +static int iscsi_tcp_r2t_rsp(struct iscsi_conn *conn, struct iscsi_hdr *hdr) { struct iscsi_session *session = conn->session; - struct iscsi_tcp_task *tcp_task = task->dd_data; - struct iscsi_tcp_conn *tcp_conn = conn->dd_data; - struct iscsi_r2t_rsp *rhdr = (struct iscsi_r2t_rsp *)tcp_conn->in.hdr; + struct iscsi_tcp_task *tcp_task; + struct iscsi_tcp_conn *tcp_conn; + struct iscsi_r2t_rsp *rhdr; struct iscsi_r2t_info *r2t; - int r2tsn = be32_to_cpu(rhdr->r2tsn); + struct iscsi_task *task; u32 data_length; u32 data_offset; + int r2tsn; int rc; + spin_lock(&session->back_lock); + task = iscsi_itt_to_ctask(conn, hdr->itt); + if (!task) { + spin_unlock(&session->back_lock); + return ISCSI_ERR_BAD_ITT; + } else if (task->sc->sc_data_direction != DMA_TO_DEVICE) { + spin_unlock(&session->back_lock); + return ISCSI_ERR_PROTO; + } + /* + * A bad target might complete the cmd before we have handled R2Ts + * so get a ref to the task that will be dropped in the xmit path. + */ + if (task->state != ISCSI_TASK_RUNNING) { + spin_unlock(&session->back_lock); + /* Let the path that got the early rsp complete it */ + return 0; + } + task->last_xfer = jiffies; + __iscsi_get_task(task); + + tcp_conn = conn->dd_data; + rhdr = (struct iscsi_r2t_rsp *)tcp_conn->in.hdr; + /* fill-in new R2T associated with the task */ + iscsi_update_cmdsn(session, (struct iscsi_nopin *)rhdr); + spin_unlock(&session->back_lock); + if (tcp_conn->in.datalen) { iscsi_conn_printk(KERN_ERR, conn, "invalid R2t with datalen %d\n", tcp_conn->in.datalen); - return ISCSI_ERR_DATALEN; + rc = ISCSI_ERR_DATALEN; + goto put_task; } + tcp_task = task->dd_data; + r2tsn = be32_to_cpu(rhdr->r2tsn); if (tcp_task->exp_datasn != r2tsn){ ISCSI_DBG_TCP(conn, "task->exp_datasn(%d) != rhdr->r2tsn(%d)\n", tcp_task->exp_datasn, r2tsn); - return ISCSI_ERR_R2TSN; + rc = ISCSI_ERR_R2TSN; + goto put_task; } - /* fill-in new R2T associated with the task */ - iscsi_update_cmdsn(session, (struct iscsi_nopin*)rhdr); - - if (!task->sc || session->state != ISCSI_STATE_LOGGED_IN) { + if (session->state != ISCSI_STATE_LOGGED_IN) { iscsi_conn_printk(KERN_INFO, conn, "dropping R2T itt %d in recovery.\n", task->itt); - return 0; + rc = 0; + goto put_task; } data_length = be32_to_cpu(rhdr->data_length); if (data_length == 0) { iscsi_conn_printk(KERN_ERR, conn, "invalid R2T with zero data len\n"); - return ISCSI_ERR_DATALEN; + rc = ISCSI_ERR_DATALEN; + goto put_task; } if (data_length > session->max_burst) @@ -579,7 +610,8 @@ static int iscsi_tcp_r2t_rsp(struct iscsi_conn *conn, struct iscsi_task *task) "invalid R2T with data len %u at offset %u " "and total length %d\n", data_length, data_offset, task->sc->sdb.length); - return ISCSI_ERR_DATALEN; + rc = ISCSI_ERR_DATALEN; + goto put_task; } spin_lock(&tcp_task->pool2queue); @@ -589,7 +621,8 @@ static int iscsi_tcp_r2t_rsp(struct iscsi_conn *conn, struct iscsi_task *task) "Target has sent more R2Ts than it " "negotiated for or driver has leaked.\n"); spin_unlock(&tcp_task->pool2queue); - return ISCSI_ERR_PROTO; + rc = ISCSI_ERR_PROTO; + goto put_task; } r2t->exp_statsn = rhdr->statsn; @@ -607,6 +640,10 @@ static int iscsi_tcp_r2t_rsp(struct iscsi_conn *conn, struct iscsi_task *task) iscsi_requeue_task(task); return 0; + +put_task: + iscsi_put_task(task); + return rc; } /* @@ -730,20 +767,11 @@ iscsi_tcp_hdr_dissect(struct iscsi_conn *conn, struct iscsi_hdr *hdr) rc = iscsi_complete_pdu(conn, hdr, NULL, 0); break; case ISCSI_OP_R2T: - spin_lock(&conn->session->back_lock); - task = iscsi_itt_to_ctask(conn, hdr->itt); - spin_unlock(&conn->session->back_lock); - if (!task) - rc = ISCSI_ERR_BAD_ITT; - else if (ahslen) + if (ahslen) { rc = ISCSI_ERR_AHSLEN; - else if (task->sc->sc_data_direction == DMA_TO_DEVICE) { - task->last_xfer = jiffies; - spin_lock(&conn->session->frwd_lock); - rc = iscsi_tcp_r2t_rsp(conn, task); - spin_unlock(&conn->session->frwd_lock); - } else - rc = ISCSI_ERR_PROTO; + break; + } + rc = iscsi_tcp_r2t_rsp(conn, hdr); break; case ISCSI_OP_LOGIN_RSP: case ISCSI_OP_TEXT_RSP: diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h index b3bbd10eb3f0..44a9554aea62 100644 --- a/include/scsi/libiscsi.h +++ b/include/scsi/libiscsi.h @@ -187,7 +187,7 @@ struct iscsi_conn { struct iscsi_task *task; /* xmit task in progress */ /* xmit */ - spinlock_t taskqueuelock; /* protects the next three lists */ + /* items must be added/deleted under frwd lock */ struct list_head mgmtqueue; /* mgmt (control) xmit queue */ struct list_head cmdqueue; /* data-path cmd queue */ struct list_head requeue; /* tasks needing another run */ @@ -332,7 +332,7 @@ struct iscsi_session { * cmdsn, queued_cmdsn * * session resources: * * - cmdpool kfifo_out , * - * - mgmtpool, */ + * - mgmtpool, queues */ spinlock_t back_lock; /* protects cmdsn_exp * * cmdsn_max, * * cmdpool kfifo_in */ -- cgit v1.2.3 From b4046922b3c0740ad50a6e9c59e12f4dc43946d4 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Sat, 6 Feb 2021 22:46:04 -0600 Subject: scsi: libiscsi: Add helper to calculate max SCSI cmds per session This patch just breaks out the code that calculates the number of SCSI cmds that will be used for a SCSI session. It also adds a check that we don't go over the host's can_queue value. Link: https://lore.kernel.org/r/20210207044608.27585-6-michael.christie@oracle.com Reviewed-by: Lee Duncan Signed-off-by: Mike Christie Signed-off-by: Martin K. Petersen --- drivers/scsi/libiscsi.c | 86 +++++++++++++++++++++++++++++++------------------ include/scsi/libiscsi.h | 2 ++ 2 files changed, 56 insertions(+), 32 deletions(-) (limited to 'include') diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index b271d3accd2a..f64e2077754c 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -2648,6 +2648,56 @@ void iscsi_pool_free(struct iscsi_pool *q) } EXPORT_SYMBOL_GPL(iscsi_pool_free); +int iscsi_host_get_max_scsi_cmds(struct Scsi_Host *shost, + uint16_t requested_cmds_max) +{ + int scsi_cmds, total_cmds = requested_cmds_max; + +check: + if (!total_cmds) + total_cmds = ISCSI_DEF_XMIT_CMDS_MAX; + /* + * The iscsi layer needs some tasks for nop handling and tmfs, + * so the cmds_max must at least be greater than ISCSI_MGMT_CMDS_MAX + * + 1 command for scsi IO. + */ + if (total_cmds < ISCSI_TOTAL_CMDS_MIN) { + printk(KERN_ERR "iscsi: invalid max cmds of %d. Must be a power of two that is at least %d.\n", + total_cmds, ISCSI_TOTAL_CMDS_MIN); + return -EINVAL; + } + + if (total_cmds > ISCSI_TOTAL_CMDS_MAX) { + printk(KERN_INFO "iscsi: invalid max cmds of %d. Must be a power of 2 less than or equal to %d. Using %d.\n", + requested_cmds_max, ISCSI_TOTAL_CMDS_MAX, + ISCSI_TOTAL_CMDS_MAX); + total_cmds = ISCSI_TOTAL_CMDS_MAX; + } + + if (!is_power_of_2(total_cmds)) { + total_cmds = rounddown_pow_of_two(total_cmds); + if (total_cmds < ISCSI_TOTAL_CMDS_MIN) { + printk(KERN_ERR "iscsi: invalid max cmds of %d. Must be a power of 2 greater than %d.\n", requested_cmds_max, ISCSI_TOTAL_CMDS_MIN); + return -EINVAL; + } + + printk(KERN_INFO "iscsi: invalid max cmds %d. Must be a power of 2. Rounding max cmds down to %d.\n", + requested_cmds_max, total_cmds); + } + + scsi_cmds = total_cmds - ISCSI_MGMT_CMDS_MAX; + if (shost->can_queue && scsi_cmds > shost->can_queue) { + total_cmds = shost->can_queue; + + printk(KERN_INFO "iscsi: requested max cmds %u is higher than driver limit. Using driver limit %u\n", + requested_cmds_max, shost->can_queue); + goto check; + } + + return scsi_cmds; +} +EXPORT_SYMBOL_GPL(iscsi_host_get_max_scsi_cmds); + /** * iscsi_host_add - add host to system * @shost: scsi host @@ -2801,7 +2851,7 @@ iscsi_session_setup(struct iscsi_transport *iscsit, struct Scsi_Host *shost, struct iscsi_host *ihost = shost_priv(shost); struct iscsi_session *session; struct iscsi_cls_session *cls_session; - int cmd_i, scsi_cmds, total_cmds = cmds_max; + int cmd_i, scsi_cmds; unsigned long flags; spin_lock_irqsave(&ihost->lock, flags); @@ -2812,37 +2862,9 @@ iscsi_session_setup(struct iscsi_transport *iscsit, struct Scsi_Host *shost, ihost->num_sessions++; spin_unlock_irqrestore(&ihost->lock, flags); - if (!total_cmds) - total_cmds = ISCSI_DEF_XMIT_CMDS_MAX; - /* - * The iscsi layer needs some tasks for nop handling and tmfs, - * so the cmds_max must at least be greater than ISCSI_MGMT_CMDS_MAX - * + 1 command for scsi IO. - */ - if (total_cmds < ISCSI_TOTAL_CMDS_MIN) { - printk(KERN_ERR "iscsi: invalid can_queue of %d. can_queue " - "must be a power of two that is at least %d.\n", - total_cmds, ISCSI_TOTAL_CMDS_MIN); + scsi_cmds = iscsi_host_get_max_scsi_cmds(shost, cmds_max); + if (scsi_cmds < 0) goto dec_session_count; - } - - if (total_cmds > ISCSI_TOTAL_CMDS_MAX) { - printk(KERN_ERR "iscsi: invalid can_queue of %d. can_queue " - "must be a power of 2 less than or equal to %d.\n", - cmds_max, ISCSI_TOTAL_CMDS_MAX); - total_cmds = ISCSI_TOTAL_CMDS_MAX; - } - - if (!is_power_of_2(total_cmds)) { - printk(KERN_ERR "iscsi: invalid can_queue of %d. can_queue " - "must be a power of 2.\n", total_cmds); - total_cmds = rounddown_pow_of_two(total_cmds); - if (total_cmds < ISCSI_TOTAL_CMDS_MIN) - goto dec_session_count; - printk(KERN_INFO "iscsi: Rounding can_queue to %d.\n", - total_cmds); - } - scsi_cmds = total_cmds - ISCSI_MGMT_CMDS_MAX; cls_session = iscsi_alloc_session(shost, iscsit, sizeof(struct iscsi_session) + @@ -2858,7 +2880,7 @@ iscsi_session_setup(struct iscsi_transport *iscsit, struct Scsi_Host *shost, session->lu_reset_timeout = 15; session->abort_timeout = 10; session->scsi_cmds_max = scsi_cmds; - session->cmds_max = total_cmds; + session->cmds_max = scsi_cmds + ISCSI_MGMT_CMDS_MAX; session->queued_cmdsn = session->cmdsn = initial_cmdsn; session->exp_cmdsn = initial_cmdsn + 1; session->max_cmdsn = initial_cmdsn + 1; diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h index 44a9554aea62..02f966e9358f 100644 --- a/include/scsi/libiscsi.h +++ b/include/scsi/libiscsi.h @@ -395,6 +395,8 @@ extern struct Scsi_Host *iscsi_host_alloc(struct scsi_host_template *sht, extern void iscsi_host_remove(struct Scsi_Host *shost); extern void iscsi_host_free(struct Scsi_Host *shost); extern int iscsi_target_alloc(struct scsi_target *starget); +extern int iscsi_host_get_max_scsi_cmds(struct Scsi_Host *shost, + uint16_t requested_cmds_max); /* * session management -- cgit v1.2.3 From bcbe6005eb18d2cd565f202d9351737061753894 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 20 Jan 2021 14:10:24 +0100 Subject: clk: remove zte zx driver The zte zx platform is getting removed, so this driver is no longer needed. Cc: Jun Nie Cc: Shawn Guo Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20210120131026.1721788-3-arnd@kernel.org Signed-off-by: Stephen Boyd --- .../devicetree/bindings/clock/zx296702-clk.txt | 34 - .../devicetree/bindings/clock/zx296718-clk.txt | 37 - drivers/clk/Makefile | 1 - drivers/clk/zte/Makefile | 4 - drivers/clk/zte/clk-zx296702.c | 741 -------------- drivers/clk/zte/clk-zx296718.c | 1074 -------------------- drivers/clk/zte/clk.c | 446 -------- drivers/clk/zte/clk.h | 174 ---- include/dt-bindings/clock/zx296702-clock.h | 180 ---- 9 files changed, 2691 deletions(-) delete mode 100644 Documentation/devicetree/bindings/clock/zx296702-clk.txt delete mode 100644 Documentation/devicetree/bindings/clock/zx296718-clk.txt delete mode 100644 drivers/clk/zte/Makefile delete mode 100644 drivers/clk/zte/clk-zx296702.c delete mode 100644 drivers/clk/zte/clk-zx296718.c delete mode 100644 drivers/clk/zte/clk.c delete mode 100644 drivers/clk/zte/clk.h delete mode 100644 include/dt-bindings/clock/zx296702-clock.h (limited to 'include') diff --git a/Documentation/devicetree/bindings/clock/zx296702-clk.txt b/Documentation/devicetree/bindings/clock/zx296702-clk.txt deleted file mode 100644 index 5c91c9e4f1be..000000000000 --- a/Documentation/devicetree/bindings/clock/zx296702-clk.txt +++ /dev/null @@ -1,34 +0,0 @@ -Device Tree Clock bindings for ZTE zx296702 - -This binding uses the common clock binding[1]. - -[1] Documentation/devicetree/bindings/clock/clock-bindings.txt - -Required properties: -- compatible : shall be one of the following: - "zte,zx296702-topcrm-clk": - zx296702 top clock selection, divider and gating - - "zte,zx296702-lsp0crpm-clk" and - "zte,zx296702-lsp1crpm-clk": - zx296702 device level clock selection and gating - -- reg: Address and length of the register set - -The clock consumer should specify the desired clock by having the clock -ID in its "clocks" phandle cell. See include/dt-bindings/clock/zx296702-clock.h -for the full list of zx296702 clock IDs. - - -topclk: topcrm@09800000 { - compatible = "zte,zx296702-topcrm-clk"; - reg = <0x09800000 0x1000>; - #clock-cells = <1>; -}; - -uart0: serial@09405000 { - compatible = "zte,zx296702-uart"; - reg = <0x09405000 0x1000>; - interrupts = ; - clocks = <&lsp1clk ZX296702_UART0_PCLK>; -}; diff --git a/Documentation/devicetree/bindings/clock/zx296718-clk.txt b/Documentation/devicetree/bindings/clock/zx296718-clk.txt deleted file mode 100644 index 3a46bf0b2540..000000000000 --- a/Documentation/devicetree/bindings/clock/zx296718-clk.txt +++ /dev/null @@ -1,37 +0,0 @@ -Device Tree Clock bindings for ZTE zx296718 - -This binding uses the common clock binding[1]. - -[1] Documentation/devicetree/bindings/clock/clock-bindings.txt - -Required properties: -- compatible : shall be one of the following: - "zte,zx296718-topcrm": - zx296718 top clock selection, divider and gating - - "zte,zx296718-lsp0crm" and - "zte,zx296718-lsp1crm": - zx296718 device level clock selection and gating - - "zte,zx296718-audiocrm": - zx296718 audio clock selection, divider and gating - -- reg: Address and length of the register set - -The clock consumer should specify the desired clock by having the clock -ID in its "clocks" phandle cell. See include/dt-bindings/clock/zx296718-clock.h -for the full list of zx296718 clock IDs. - - -topclk: topcrm@1461000 { - compatible = "zte,zx296718-topcrm-clk"; - reg = <0x01461000 0x1000>; - #clock-cells = <1>; -}; - -usbphy0:usb-phy0 { - compatible = "zte,zx296718-usb-phy"; - #phy-cells = <0>; - clocks = <&topclk USB20_PHY_CLK>; - clock-names = "phyclk"; -}; diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile index 3ea1b6efbfa1..789939da26dd 100644 --- a/drivers/clk/Makefile +++ b/drivers/clk/Makefile @@ -120,6 +120,5 @@ obj-y += versatile/ ifeq ($(CONFIG_COMMON_CLK), y) obj-$(CONFIG_X86) += x86/ endif -obj-$(CONFIG_ARCH_ZX) += zte/ obj-$(CONFIG_ARCH_ZYNQ) += zynq/ obj-$(CONFIG_COMMON_CLK_ZYNQMP) += zynqmp/ diff --git a/drivers/clk/zte/Makefile b/drivers/clk/zte/Makefile deleted file mode 100644 index f130643b695d..000000000000 --- a/drivers/clk/zte/Makefile +++ /dev/null @@ -1,4 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -obj-y := clk.o -obj-$(CONFIG_SOC_ZX296702) += clk-zx296702.o -obj-$(CONFIG_ARCH_ZX) += clk-zx296718.o diff --git a/drivers/clk/zte/clk-zx296702.c b/drivers/clk/zte/clk-zx296702.c deleted file mode 100644 index e846f2a34feb..000000000000 --- a/drivers/clk/zte/clk-zx296702.c +++ /dev/null @@ -1,741 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright 2014 Linaro Ltd. - * Copyright (C) 2014 ZTE Corporation. - */ - -#include -#include -#include -#include "clk.h" - -static DEFINE_SPINLOCK(reg_lock); - -static void __iomem *topcrm_base; -static void __iomem *lsp0crpm_base; -static void __iomem *lsp1crpm_base; - -static struct clk *topclk[ZX296702_TOPCLK_END]; -static struct clk *lsp0clk[ZX296702_LSP0CLK_END]; -static struct clk *lsp1clk[ZX296702_LSP1CLK_END]; - -static struct clk_onecell_data topclk_data; -static struct clk_onecell_data lsp0clk_data; -static struct clk_onecell_data lsp1clk_data; - -#define CLK_MUX (topcrm_base + 0x04) -#define CLK_DIV (topcrm_base + 0x08) -#define CLK_EN0 (topcrm_base + 0x0c) -#define CLK_EN1 (topcrm_base + 0x10) -#define VOU_LOCAL_CLKEN (topcrm_base + 0x68) -#define VOU_LOCAL_CLKSEL (topcrm_base + 0x70) -#define VOU_LOCAL_DIV2_SET (topcrm_base + 0x74) -#define CLK_MUX1 (topcrm_base + 0x8c) - -#define CLK_SDMMC1 (lsp0crpm_base + 0x0c) -#define CLK_GPIO (lsp0crpm_base + 0x2c) -#define CLK_SPDIF0 (lsp0crpm_base + 0x10) -#define SPDIF0_DIV (lsp0crpm_base + 0x14) -#define CLK_I2S0 (lsp0crpm_base + 0x18) -#define I2S0_DIV (lsp0crpm_base + 0x1c) -#define CLK_I2S1 (lsp0crpm_base + 0x20) -#define I2S1_DIV (lsp0crpm_base + 0x24) -#define CLK_I2S2 (lsp0crpm_base + 0x34) -#define I2S2_DIV (lsp0crpm_base + 0x38) - -#define CLK_UART0 (lsp1crpm_base + 0x20) -#define CLK_UART1 (lsp1crpm_base + 0x24) -#define CLK_SDMMC0 (lsp1crpm_base + 0x2c) -#define CLK_SPDIF1 (lsp1crpm_base + 0x30) -#define SPDIF1_DIV (lsp1crpm_base + 0x34) - -static const struct zx_pll_config pll_a9_config[] = { - { .rate = 700000000, .cfg0 = 0x800405d1, .cfg1 = 0x04555555 }, - { .rate = 800000000, .cfg0 = 0x80040691, .cfg1 = 0x04aaaaaa }, - { .rate = 900000000, .cfg0 = 0x80040791, .cfg1 = 0x04000000 }, - { .rate = 1000000000, .cfg0 = 0x80040851, .cfg1 = 0x04555555 }, - { .rate = 1100000000, .cfg0 = 0x80040911, .cfg1 = 0x04aaaaaa }, - { .rate = 1200000000, .cfg0 = 0x80040a11, .cfg1 = 0x04000000 }, -}; - -static const struct clk_div_table main_hlk_div[] = { - { .val = 1, .div = 2, }, - { .val = 3, .div = 4, }, - { /* sentinel */ } -}; - -static const struct clk_div_table a9_as1_aclk_divider[] = { - { .val = 0, .div = 1, }, - { .val = 1, .div = 2, }, - { .val = 3, .div = 4, }, - { /* sentinel */ } -}; - -static const struct clk_div_table sec_wclk_divider[] = { - { .val = 0, .div = 1, }, - { .val = 1, .div = 2, }, - { .val = 3, .div = 4, }, - { .val = 5, .div = 6, }, - { .val = 7, .div = 8, }, - { /* sentinel */ } -}; - -static const char * const matrix_aclk_sel[] = { - "pll_mm0_198M", - "osc", - "clk_148M5", - "pll_lsp_104M", -}; - -static const char * const a9_wclk_sel[] = { - "pll_a9", - "osc", - "clk_500", - "clk_250", -}; - -static const char * const a9_as1_aclk_sel[] = { - "clk_250", - "osc", - "pll_mm0_396M", - "pll_mac_333M", -}; - -static const char * const a9_trace_clkin_sel[] = { - "clk_74M25", - "pll_mm1_108M", - "clk_125", - "clk_148M5", -}; - -static const char * const decppu_aclk_sel[] = { - "clk_250", - "pll_mm0_198M", - "pll_lsp_104M", - "pll_audio_294M912", -}; - -static const char * const vou_main_wclk_sel[] = { - "clk_148M5", - "clk_74M25", - "clk_27", - "pll_mm1_54M", -}; - -static const char * const vou_scaler_wclk_sel[] = { - "clk_250", - "pll_mac_333M", - "pll_audio_294M912", - "pll_mm0_198M", -}; - -static const char * const r2d_wclk_sel[] = { - "pll_audio_294M912", - "pll_mac_333M", - "pll_a9_350M", - "pll_mm0_396M", -}; - -static const char * const ddr_wclk_sel[] = { - "pll_mac_333M", - "pll_ddr_266M", - "pll_audio_294M912", - "pll_mm0_198M", -}; - -static const char * const nand_wclk_sel[] = { - "pll_lsp_104M", - "osc", -}; - -static const char * const lsp_26_wclk_sel[] = { - "pll_lsp_26M", - "osc", -}; - -static const char * const vl0_sel[] = { - "vou_main_channel_div", - "vou_aux_channel_div", -}; - -static const char * const hdmi_sel[] = { - "vou_main_channel_wclk", - "vou_aux_channel_wclk", -}; - -static const char * const sdmmc0_wclk_sel[] = { - "lsp1_104M_wclk", - "lsp1_26M_wclk", -}; - -static const char * const sdmmc1_wclk_sel[] = { - "lsp0_104M_wclk", - "lsp0_26M_wclk", -}; - -static const char * const uart_wclk_sel[] = { - "lsp1_104M_wclk", - "lsp1_26M_wclk", -}; - -static const char * const spdif0_wclk_sel[] = { - "lsp0_104M_wclk", - "lsp0_26M_wclk", -}; - -static const char * const spdif1_wclk_sel[] = { - "lsp1_104M_wclk", - "lsp1_26M_wclk", -}; - -static const char * const i2s_wclk_sel[] = { - "lsp0_104M_wclk", - "lsp0_26M_wclk", -}; - -static inline struct clk *zx_divtbl(const char *name, const char *parent, - void __iomem *reg, u8 shift, u8 width, - const struct clk_div_table *table) -{ - return clk_register_divider_table(NULL, name, parent, 0, reg, shift, - width, 0, table, ®_lock); -} - -static inline struct clk *zx_div(const char *name, const char *parent, - void __iomem *reg, u8 shift, u8 width) -{ - return clk_register_divider(NULL, name, parent, 0, - reg, shift, width, 0, ®_lock); -} - -static inline struct clk *zx_mux(const char *name, const char * const *parents, - int num_parents, void __iomem *reg, u8 shift, u8 width) -{ - return clk_register_mux(NULL, name, parents, num_parents, - 0, reg, shift, width, 0, ®_lock); -} - -static inline struct clk *zx_gate(const char *name, const char *parent, - void __iomem *reg, u8 shift) -{ - return clk_register_gate(NULL, name, parent, CLK_IGNORE_UNUSED, - reg, shift, CLK_SET_RATE_PARENT, ®_lock); -} - -static void __init zx296702_top_clocks_init(struct device_node *np) -{ - struct clk **clk = topclk; - int i; - - topcrm_base = of_iomap(np, 0); - WARN_ON(!topcrm_base); - - clk[ZX296702_OSC] = - clk_register_fixed_rate(NULL, "osc", NULL, 0, 30000000); - clk[ZX296702_PLL_A9] = - clk_register_zx_pll("pll_a9", "osc", 0, topcrm_base - + 0x01c, pll_a9_config, - ARRAY_SIZE(pll_a9_config), ®_lock); - - /* TODO: pll_a9_350M look like changeble follow a9 pll */ - clk[ZX296702_PLL_A9_350M] = - clk_register_fixed_rate(NULL, "pll_a9_350M", "osc", 0, - 350000000); - clk[ZX296702_PLL_MAC_1000M] = - clk_register_fixed_rate(NULL, "pll_mac_1000M", "osc", 0, - 1000000000); - clk[ZX296702_PLL_MAC_333M] = - clk_register_fixed_rate(NULL, "pll_mac_333M", "osc", 0, - 333000000); - clk[ZX296702_PLL_MM0_1188M] = - clk_register_fixed_rate(NULL, "pll_mm0_1188M", "osc", 0, - 1188000000); - clk[ZX296702_PLL_MM0_396M] = - clk_register_fixed_rate(NULL, "pll_mm0_396M", "osc", 0, - 396000000); - clk[ZX296702_PLL_MM0_198M] = - clk_register_fixed_rate(NULL, "pll_mm0_198M", "osc", 0, - 198000000); - clk[ZX296702_PLL_MM1_108M] = - clk_register_fixed_rate(NULL, "pll_mm1_108M", "osc", 0, - 108000000); - clk[ZX296702_PLL_MM1_72M] = - clk_register_fixed_rate(NULL, "pll_mm1_72M", "osc", 0, - 72000000); - clk[ZX296702_PLL_MM1_54M] = - clk_register_fixed_rate(NULL, "pll_mm1_54M", "osc", 0, - 54000000); - clk[ZX296702_PLL_LSP_104M] = - clk_register_fixed_rate(NULL, "pll_lsp_104M", "osc", 0, - 104000000); - clk[ZX296702_PLL_LSP_26M] = - clk_register_fixed_rate(NULL, "pll_lsp_26M", "osc", 0, - 26000000); - clk[ZX296702_PLL_DDR_266M] = - clk_register_fixed_rate(NULL, "pll_ddr_266M", "osc", 0, - 266000000); - clk[ZX296702_PLL_AUDIO_294M912] = - clk_register_fixed_rate(NULL, "pll_audio_294M912", "osc", 0, - 294912000); - - /* bus clock */ - clk[ZX296702_MATRIX_ACLK] = - zx_mux("matrix_aclk", matrix_aclk_sel, - ARRAY_SIZE(matrix_aclk_sel), CLK_MUX, 2, 2); - clk[ZX296702_MAIN_HCLK] = - zx_divtbl("main_hclk", "matrix_aclk", CLK_DIV, 0, 2, - main_hlk_div); - clk[ZX296702_MAIN_PCLK] = - zx_divtbl("main_pclk", "matrix_aclk", CLK_DIV, 2, 2, - main_hlk_div); - - /* cpu clock */ - clk[ZX296702_CLK_500] = - clk_register_fixed_factor(NULL, "clk_500", "pll_mac_1000M", 0, - 1, 2); - clk[ZX296702_CLK_250] = - clk_register_fixed_factor(NULL, "clk_250", "pll_mac_1000M", 0, - 1, 4); - clk[ZX296702_CLK_125] = - clk_register_fixed_factor(NULL, "clk_125", "clk_250", 0, 1, 2); - clk[ZX296702_CLK_148M5] = - clk_register_fixed_factor(NULL, "clk_148M5", "pll_mm0_1188M", 0, - 1, 8); - clk[ZX296702_CLK_74M25] = - clk_register_fixed_factor(NULL, "clk_74M25", "pll_mm0_1188M", 0, - 1, 16); - clk[ZX296702_A9_WCLK] = - zx_mux("a9_wclk", a9_wclk_sel, ARRAY_SIZE(a9_wclk_sel), CLK_MUX, - 0, 2); - clk[ZX296702_A9_AS1_ACLK_MUX] = - zx_mux("a9_as1_aclk_mux", a9_as1_aclk_sel, - ARRAY_SIZE(a9_as1_aclk_sel), CLK_MUX, 4, 2); - clk[ZX296702_A9_TRACE_CLKIN_MUX] = - zx_mux("a9_trace_clkin_mux", a9_trace_clkin_sel, - ARRAY_SIZE(a9_trace_clkin_sel), CLK_MUX1, 0, 2); - clk[ZX296702_A9_AS1_ACLK_DIV] = - zx_divtbl("a9_as1_aclk_div", "a9_as1_aclk_mux", CLK_DIV, 4, 2, - a9_as1_aclk_divider); - - /* multi-media clock */ - clk[ZX296702_CLK_2] = - clk_register_fixed_factor(NULL, "clk_2", "pll_mm1_72M", 0, - 1, 36); - clk[ZX296702_CLK_27] = - clk_register_fixed_factor(NULL, "clk_27", "pll_mm1_54M", 0, - 1, 2); - clk[ZX296702_DECPPU_ACLK_MUX] = - zx_mux("decppu_aclk_mux", decppu_aclk_sel, - ARRAY_SIZE(decppu_aclk_sel), CLK_MUX, 6, 2); - clk[ZX296702_PPU_ACLK_MUX] = - zx_mux("ppu_aclk_mux", decppu_aclk_sel, - ARRAY_SIZE(decppu_aclk_sel), CLK_MUX, 8, 2); - clk[ZX296702_MALI400_ACLK_MUX] = - zx_mux("mali400_aclk_mux", decppu_aclk_sel, - ARRAY_SIZE(decppu_aclk_sel), CLK_MUX, 12, 2); - clk[ZX296702_VOU_ACLK_MUX] = - zx_mux("vou_aclk_mux", decppu_aclk_sel, - ARRAY_SIZE(decppu_aclk_sel), CLK_MUX, 10, 2); - clk[ZX296702_VOU_MAIN_WCLK_MUX] = - zx_mux("vou_main_wclk_mux", vou_main_wclk_sel, - ARRAY_SIZE(vou_main_wclk_sel), CLK_MUX, 14, 2); - clk[ZX296702_VOU_AUX_WCLK_MUX] = - zx_mux("vou_aux_wclk_mux", vou_main_wclk_sel, - ARRAY_SIZE(vou_main_wclk_sel), CLK_MUX, 16, 2); - clk[ZX296702_VOU_SCALER_WCLK_MUX] = - zx_mux("vou_scaler_wclk_mux", vou_scaler_wclk_sel, - ARRAY_SIZE(vou_scaler_wclk_sel), CLK_MUX, - 18, 2); - clk[ZX296702_R2D_ACLK_MUX] = - zx_mux("r2d_aclk_mux", decppu_aclk_sel, - ARRAY_SIZE(decppu_aclk_sel), CLK_MUX, 20, 2); - clk[ZX296702_R2D_WCLK_MUX] = - zx_mux("r2d_wclk_mux", r2d_wclk_sel, - ARRAY_SIZE(r2d_wclk_sel), CLK_MUX, 22, 2); - - /* other clock */ - clk[ZX296702_CLK_50] = - clk_register_fixed_factor(NULL, "clk_50", "pll_mac_1000M", - 0, 1, 20); - clk[ZX296702_CLK_25] = - clk_register_fixed_factor(NULL, "clk_25", "pll_mac_1000M", - 0, 1, 40); - clk[ZX296702_CLK_12] = - clk_register_fixed_factor(NULL, "clk_12", "pll_mm1_72M", - 0, 1, 6); - clk[ZX296702_CLK_16M384] = - clk_register_fixed_factor(NULL, "clk_16M384", - "pll_audio_294M912", 0, 1, 18); - clk[ZX296702_CLK_32K768] = - clk_register_fixed_factor(NULL, "clk_32K768", "clk_16M384", - 0, 1, 500); - clk[ZX296702_SEC_WCLK_DIV] = - zx_divtbl("sec_wclk_div", "pll_lsp_104M", CLK_DIV, 6, 3, - sec_wclk_divider); - clk[ZX296702_DDR_WCLK_MUX] = - zx_mux("ddr_wclk_mux", ddr_wclk_sel, - ARRAY_SIZE(ddr_wclk_sel), CLK_MUX, 24, 2); - clk[ZX296702_NAND_WCLK_MUX] = - zx_mux("nand_wclk_mux", nand_wclk_sel, - ARRAY_SIZE(nand_wclk_sel), CLK_MUX, 24, 2); - clk[ZX296702_LSP_26_WCLK_MUX] = - zx_mux("lsp_26_wclk_mux", lsp_26_wclk_sel, - ARRAY_SIZE(lsp_26_wclk_sel), CLK_MUX, 27, 1); - - /* gates */ - clk[ZX296702_A9_AS0_ACLK] = - zx_gate("a9_as0_aclk", "matrix_aclk", CLK_EN0, 0); - clk[ZX296702_A9_AS1_ACLK] = - zx_gate("a9_as1_aclk", "a9_as1_aclk_div", CLK_EN0, 1); - clk[ZX296702_A9_TRACE_CLKIN] = - zx_gate("a9_trace_clkin", "a9_trace_clkin_mux", CLK_EN0, 2); - clk[ZX296702_DECPPU_AXI_M_ACLK] = - zx_gate("decppu_axi_m_aclk", "decppu_aclk_mux", CLK_EN0, 3); - clk[ZX296702_DECPPU_AHB_S_HCLK] = - zx_gate("decppu_ahb_s_hclk", "main_hclk", CLK_EN0, 4); - clk[ZX296702_PPU_AXI_M_ACLK] = - zx_gate("ppu_axi_m_aclk", "ppu_aclk_mux", CLK_EN0, 5); - clk[ZX296702_PPU_AHB_S_HCLK] = - zx_gate("ppu_ahb_s_hclk", "main_hclk", CLK_EN0, 6); - clk[ZX296702_VOU_AXI_M_ACLK] = - zx_gate("vou_axi_m_aclk", "vou_aclk_mux", CLK_EN0, 7); - clk[ZX296702_VOU_APB_PCLK] = - zx_gate("vou_apb_pclk", "main_pclk", CLK_EN0, 8); - clk[ZX296702_VOU_MAIN_CHANNEL_WCLK] = - zx_gate("vou_main_channel_wclk", "vou_main_wclk_mux", - CLK_EN0, 9); - clk[ZX296702_VOU_AUX_CHANNEL_WCLK] = - zx_gate("vou_aux_channel_wclk", "vou_aux_wclk_mux", - CLK_EN0, 10); - clk[ZX296702_VOU_HDMI_OSCLK_CEC] = - zx_gate("vou_hdmi_osclk_cec", "clk_2", CLK_EN0, 11); - clk[ZX296702_VOU_SCALER_WCLK] = - zx_gate("vou_scaler_wclk", "vou_scaler_wclk_mux", CLK_EN0, 12); - clk[ZX296702_MALI400_AXI_M_ACLK] = - zx_gate("mali400_axi_m_aclk", "mali400_aclk_mux", CLK_EN0, 13); - clk[ZX296702_MALI400_APB_PCLK] = - zx_gate("mali400_apb_pclk", "main_pclk", CLK_EN0, 14); - clk[ZX296702_R2D_WCLK] = - zx_gate("r2d_wclk", "r2d_wclk_mux", CLK_EN0, 15); - clk[ZX296702_R2D_AXI_M_ACLK] = - zx_gate("r2d_axi_m_aclk", "r2d_aclk_mux", CLK_EN0, 16); - clk[ZX296702_R2D_AHB_HCLK] = - zx_gate("r2d_ahb_hclk", "main_hclk", CLK_EN0, 17); - clk[ZX296702_DDR3_AXI_S0_ACLK] = - zx_gate("ddr3_axi_s0_aclk", "matrix_aclk", CLK_EN0, 18); - clk[ZX296702_DDR3_APB_PCLK] = - zx_gate("ddr3_apb_pclk", "main_pclk", CLK_EN0, 19); - clk[ZX296702_DDR3_WCLK] = - zx_gate("ddr3_wclk", "ddr_wclk_mux", CLK_EN0, 20); - clk[ZX296702_USB20_0_AHB_HCLK] = - zx_gate("usb20_0_ahb_hclk", "main_hclk", CLK_EN0, 21); - clk[ZX296702_USB20_0_EXTREFCLK] = - zx_gate("usb20_0_extrefclk", "clk_12", CLK_EN0, 22); - clk[ZX296702_USB20_1_AHB_HCLK] = - zx_gate("usb20_1_ahb_hclk", "main_hclk", CLK_EN0, 23); - clk[ZX296702_USB20_1_EXTREFCLK] = - zx_gate("usb20_1_extrefclk", "clk_12", CLK_EN0, 24); - clk[ZX296702_USB20_2_AHB_HCLK] = - zx_gate("usb20_2_ahb_hclk", "main_hclk", CLK_EN0, 25); - clk[ZX296702_USB20_2_EXTREFCLK] = - zx_gate("usb20_2_extrefclk", "clk_12", CLK_EN0, 26); - clk[ZX296702_GMAC_AXI_M_ACLK] = - zx_gate("gmac_axi_m_aclk", "matrix_aclk", CLK_EN0, 27); - clk[ZX296702_GMAC_APB_PCLK] = - zx_gate("gmac_apb_pclk", "main_pclk", CLK_EN0, 28); - clk[ZX296702_GMAC_125_CLKIN] = - zx_gate("gmac_125_clkin", "clk_125", CLK_EN0, 29); - clk[ZX296702_GMAC_RMII_CLKIN] = - zx_gate("gmac_rmii_clkin", "clk_50", CLK_EN0, 30); - clk[ZX296702_GMAC_25M_CLK] = - zx_gate("gmac_25M_clk", "clk_25", CLK_EN0, 31); - clk[ZX296702_NANDFLASH_AHB_HCLK] = - zx_gate("nandflash_ahb_hclk", "main_hclk", CLK_EN1, 0); - clk[ZX296702_NANDFLASH_WCLK] = - zx_gate("nandflash_wclk", "nand_wclk_mux", CLK_EN1, 1); - clk[ZX296702_LSP0_APB_PCLK] = - zx_gate("lsp0_apb_pclk", "main_pclk", CLK_EN1, 2); - clk[ZX296702_LSP0_AHB_HCLK] = - zx_gate("lsp0_ahb_hclk", "main_hclk", CLK_EN1, 3); - clk[ZX296702_LSP0_26M_WCLK] = - zx_gate("lsp0_26M_wclk", "lsp_26_wclk_mux", CLK_EN1, 4); - clk[ZX296702_LSP0_104M_WCLK] = - zx_gate("lsp0_104M_wclk", "pll_lsp_104M", CLK_EN1, 5); - clk[ZX296702_LSP0_16M384_WCLK] = - zx_gate("lsp0_16M384_wclk", "clk_16M384", CLK_EN1, 6); - clk[ZX296702_LSP1_APB_PCLK] = - zx_gate("lsp1_apb_pclk", "main_pclk", CLK_EN1, 7); - /* FIXME: wclk enable bit is bit8. We hack it as reserved 31 for - * UART does not work after parent clk is disabled/enabled */ - clk[ZX296702_LSP1_26M_WCLK] = - zx_gate("lsp1_26M_wclk", "lsp_26_wclk_mux", CLK_EN1, 31); - clk[ZX296702_LSP1_104M_WCLK] = - zx_gate("lsp1_104M_wclk", "pll_lsp_104M", CLK_EN1, 9); - clk[ZX296702_LSP1_32K_CLK] = - zx_gate("lsp1_32K_clk", "clk_32K768", CLK_EN1, 10); - clk[ZX296702_AON_HCLK] = - zx_gate("aon_hclk", "main_hclk", CLK_EN1, 11); - clk[ZX296702_SYS_CTRL_PCLK] = - zx_gate("sys_ctrl_pclk", "main_pclk", CLK_EN1, 12); - clk[ZX296702_DMA_PCLK] = - zx_gate("dma_pclk", "main_pclk", CLK_EN1, 13); - clk[ZX296702_DMA_ACLK] = - zx_gate("dma_aclk", "matrix_aclk", CLK_EN1, 14); - clk[ZX296702_SEC_HCLK] = - zx_gate("sec_hclk", "main_hclk", CLK_EN1, 15); - clk[ZX296702_AES_WCLK] = - zx_gate("aes_wclk", "sec_wclk_div", CLK_EN1, 16); - clk[ZX296702_DES_WCLK] = - zx_gate("des_wclk", "sec_wclk_div", CLK_EN1, 17); - clk[ZX296702_IRAM_ACLK] = - zx_gate("iram_aclk", "matrix_aclk", CLK_EN1, 18); - clk[ZX296702_IROM_ACLK] = - zx_gate("irom_aclk", "matrix_aclk", CLK_EN1, 19); - clk[ZX296702_BOOT_CTRL_HCLK] = - zx_gate("boot_ctrl_hclk", "main_hclk", CLK_EN1, 20); - clk[ZX296702_EFUSE_CLK_30] = - zx_gate("efuse_clk_30", "osc", CLK_EN1, 21); - - /* TODO: add VOU Local clocks */ - clk[ZX296702_VOU_MAIN_CHANNEL_DIV] = - zx_div("vou_main_channel_div", "vou_main_channel_wclk", - VOU_LOCAL_DIV2_SET, 1, 1); - clk[ZX296702_VOU_AUX_CHANNEL_DIV] = - zx_div("vou_aux_channel_div", "vou_aux_channel_wclk", - VOU_LOCAL_DIV2_SET, 0, 1); - clk[ZX296702_VOU_TV_ENC_HD_DIV] = - zx_div("vou_tv_enc_hd_div", "vou_tv_enc_hd_mux", - VOU_LOCAL_DIV2_SET, 3, 1); - clk[ZX296702_VOU_TV_ENC_SD_DIV] = - zx_div("vou_tv_enc_sd_div", "vou_tv_enc_sd_mux", - VOU_LOCAL_DIV2_SET, 2, 1); - clk[ZX296702_VL0_MUX] = - zx_mux("vl0_mux", vl0_sel, ARRAY_SIZE(vl0_sel), - VOU_LOCAL_CLKSEL, 8, 1); - clk[ZX296702_VL1_MUX] = - zx_mux("vl1_mux", vl0_sel, ARRAY_SIZE(vl0_sel), - VOU_LOCAL_CLKSEL, 9, 1); - clk[ZX296702_VL2_MUX] = - zx_mux("vl2_mux", vl0_sel, ARRAY_SIZE(vl0_sel), - VOU_LOCAL_CLKSEL, 10, 1); - clk[ZX296702_GL0_MUX] = - zx_mux("gl0_mux", vl0_sel, ARRAY_SIZE(vl0_sel), - VOU_LOCAL_CLKSEL, 5, 1); - clk[ZX296702_GL1_MUX] = - zx_mux("gl1_mux", vl0_sel, ARRAY_SIZE(vl0_sel), - VOU_LOCAL_CLKSEL, 6, 1); - clk[ZX296702_GL2_MUX] = - zx_mux("gl2_mux", vl0_sel, ARRAY_SIZE(vl0_sel), - VOU_LOCAL_CLKSEL, 7, 1); - clk[ZX296702_WB_MUX] = - zx_mux("wb_mux", vl0_sel, ARRAY_SIZE(vl0_sel), - VOU_LOCAL_CLKSEL, 11, 1); - clk[ZX296702_HDMI_MUX] = - zx_mux("hdmi_mux", hdmi_sel, ARRAY_SIZE(hdmi_sel), - VOU_LOCAL_CLKSEL, 4, 1); - clk[ZX296702_VOU_TV_ENC_HD_MUX] = - zx_mux("vou_tv_enc_hd_mux", hdmi_sel, ARRAY_SIZE(hdmi_sel), - VOU_LOCAL_CLKSEL, 3, 1); - clk[ZX296702_VOU_TV_ENC_SD_MUX] = - zx_mux("vou_tv_enc_sd_mux", hdmi_sel, ARRAY_SIZE(hdmi_sel), - VOU_LOCAL_CLKSEL, 2, 1); - clk[ZX296702_VL0_CLK] = - zx_gate("vl0_clk", "vl0_mux", VOU_LOCAL_CLKEN, 8); - clk[ZX296702_VL1_CLK] = - zx_gate("vl1_clk", "vl1_mux", VOU_LOCAL_CLKEN, 9); - clk[ZX296702_VL2_CLK] = - zx_gate("vl2_clk", "vl2_mux", VOU_LOCAL_CLKEN, 10); - clk[ZX296702_GL0_CLK] = - zx_gate("gl0_clk", "gl0_mux", VOU_LOCAL_CLKEN, 5); - clk[ZX296702_GL1_CLK] = - zx_gate("gl1_clk", "gl1_mux", VOU_LOCAL_CLKEN, 6); - clk[ZX296702_GL2_CLK] = - zx_gate("gl2_clk", "gl2_mux", VOU_LOCAL_CLKEN, 7); - clk[ZX296702_WB_CLK] = - zx_gate("wb_clk", "wb_mux", VOU_LOCAL_CLKEN, 11); - clk[ZX296702_CL_CLK] = - zx_gate("cl_clk", "vou_main_channel_div", VOU_LOCAL_CLKEN, 12); - clk[ZX296702_MAIN_MIX_CLK] = - zx_gate("main_mix_clk", "vou_main_channel_div", - VOU_LOCAL_CLKEN, 4); - clk[ZX296702_AUX_MIX_CLK] = - zx_gate("aux_mix_clk", "vou_aux_channel_div", - VOU_LOCAL_CLKEN, 3); - clk[ZX296702_HDMI_CLK] = - zx_gate("hdmi_clk", "hdmi_mux", VOU_LOCAL_CLKEN, 2); - clk[ZX296702_VOU_TV_ENC_HD_DAC_CLK] = - zx_gate("vou_tv_enc_hd_dac_clk", "vou_tv_enc_hd_div", - VOU_LOCAL_CLKEN, 1); - clk[ZX296702_VOU_TV_ENC_SD_DAC_CLK] = - zx_gate("vou_tv_enc_sd_dac_clk", "vou_tv_enc_sd_div", - VOU_LOCAL_CLKEN, 0); - - /* CA9 PERIPHCLK = a9_wclk / 2 */ - clk[ZX296702_A9_PERIPHCLK] = - clk_register_fixed_factor(NULL, "a9_periphclk", "a9_wclk", - 0, 1, 2); - - for (i = 0; i < ARRAY_SIZE(topclk); i++) { - if (IS_ERR(clk[i])) { - pr_err("zx296702 clk %d: register failed with %ld\n", - i, PTR_ERR(clk[i])); - return; - } - } - - topclk_data.clks = topclk; - topclk_data.clk_num = ARRAY_SIZE(topclk); - of_clk_add_provider(np, of_clk_src_onecell_get, &topclk_data); -} -CLK_OF_DECLARE(zx296702_top_clk, "zte,zx296702-topcrm-clk", - zx296702_top_clocks_init); - -static void __init zx296702_lsp0_clocks_init(struct device_node *np) -{ - struct clk **clk = lsp0clk; - int i; - - lsp0crpm_base = of_iomap(np, 0); - WARN_ON(!lsp0crpm_base); - - /* SDMMC1 */ - clk[ZX296702_SDMMC1_WCLK_MUX] = - zx_mux("sdmmc1_wclk_mux", sdmmc1_wclk_sel, - ARRAY_SIZE(sdmmc1_wclk_sel), CLK_SDMMC1, 4, 1); - clk[ZX296702_SDMMC1_WCLK_DIV] = - zx_div("sdmmc1_wclk_div", "sdmmc1_wclk_mux", CLK_SDMMC1, 12, 4); - clk[ZX296702_SDMMC1_WCLK] = - zx_gate("sdmmc1_wclk", "sdmmc1_wclk_div", CLK_SDMMC1, 1); - clk[ZX296702_SDMMC1_PCLK] = - zx_gate("sdmmc1_pclk", "lsp0_apb_pclk", CLK_SDMMC1, 0); - - clk[ZX296702_GPIO_CLK] = - zx_gate("gpio_clk", "lsp0_apb_pclk", CLK_GPIO, 0); - - /* SPDIF */ - clk[ZX296702_SPDIF0_WCLK_MUX] = - zx_mux("spdif0_wclk_mux", spdif0_wclk_sel, - ARRAY_SIZE(spdif0_wclk_sel), CLK_SPDIF0, 4, 1); - clk[ZX296702_SPDIF0_WCLK] = - zx_gate("spdif0_wclk", "spdif0_wclk_mux", CLK_SPDIF0, 1); - clk[ZX296702_SPDIF0_PCLK] = - zx_gate("spdif0_pclk", "lsp0_apb_pclk", CLK_SPDIF0, 0); - - clk[ZX296702_SPDIF0_DIV] = - clk_register_zx_audio("spdif0_div", "spdif0_wclk", 0, - SPDIF0_DIV); - - /* I2S */ - clk[ZX296702_I2S0_WCLK_MUX] = - zx_mux("i2s0_wclk_mux", i2s_wclk_sel, - ARRAY_SIZE(i2s_wclk_sel), CLK_I2S0, 4, 1); - clk[ZX296702_I2S0_WCLK] = - zx_gate("i2s0_wclk", "i2s0_wclk_mux", CLK_I2S0, 1); - clk[ZX296702_I2S0_PCLK] = - zx_gate("i2s0_pclk", "lsp0_apb_pclk", CLK_I2S0, 0); - - clk[ZX296702_I2S0_DIV] = - clk_register_zx_audio("i2s0_div", "i2s0_wclk", 0, I2S0_DIV); - - clk[ZX296702_I2S1_WCLK_MUX] = - zx_mux("i2s1_wclk_mux", i2s_wclk_sel, - ARRAY_SIZE(i2s_wclk_sel), CLK_I2S1, 4, 1); - clk[ZX296702_I2S1_WCLK] = - zx_gate("i2s1_wclk", "i2s1_wclk_mux", CLK_I2S1, 1); - clk[ZX296702_I2S1_PCLK] = - zx_gate("i2s1_pclk", "lsp0_apb_pclk", CLK_I2S1, 0); - - clk[ZX296702_I2S1_DIV] = - clk_register_zx_audio("i2s1_div", "i2s1_wclk", 0, I2S1_DIV); - - clk[ZX296702_I2S2_WCLK_MUX] = - zx_mux("i2s2_wclk_mux", i2s_wclk_sel, - ARRAY_SIZE(i2s_wclk_sel), CLK_I2S2, 4, 1); - clk[ZX296702_I2S2_WCLK] = - zx_gate("i2s2_wclk", "i2s2_wclk_mux", CLK_I2S2, 1); - clk[ZX296702_I2S2_PCLK] = - zx_gate("i2s2_pclk", "lsp0_apb_pclk", CLK_I2S2, 0); - - clk[ZX296702_I2S2_DIV] = - clk_register_zx_audio("i2s2_div", "i2s2_wclk", 0, I2S2_DIV); - - for (i = 0; i < ARRAY_SIZE(lsp0clk); i++) { - if (IS_ERR(clk[i])) { - pr_err("zx296702 clk %d: register failed with %ld\n", - i, PTR_ERR(clk[i])); - return; - } - } - - lsp0clk_data.clks = lsp0clk; - lsp0clk_data.clk_num = ARRAY_SIZE(lsp0clk); - of_clk_add_provider(np, of_clk_src_onecell_get, &lsp0clk_data); -} -CLK_OF_DECLARE(zx296702_lsp0_clk, "zte,zx296702-lsp0crpm-clk", - zx296702_lsp0_clocks_init); - -static void __init zx296702_lsp1_clocks_init(struct device_node *np) -{ - struct clk **clk = lsp1clk; - int i; - - lsp1crpm_base = of_iomap(np, 0); - WARN_ON(!lsp1crpm_base); - - /* UART0 */ - clk[ZX296702_UART0_WCLK_MUX] = - zx_mux("uart0_wclk_mux", uart_wclk_sel, - ARRAY_SIZE(uart_wclk_sel), CLK_UART0, 4, 1); - /* FIXME: uart wclk enable bit is bit1 in. We hack it as reserved 31 for - * UART does not work after parent clk is disabled/enabled */ - clk[ZX296702_UART0_WCLK] = - zx_gate("uart0_wclk", "uart0_wclk_mux", CLK_UART0, 31); - clk[ZX296702_UART0_PCLK] = - zx_gate("uart0_pclk", "lsp1_apb_pclk", CLK_UART0, 0); - - /* UART1 */ - clk[ZX296702_UART1_WCLK_MUX] = - zx_mux("uart1_wclk_mux", uart_wclk_sel, - ARRAY_SIZE(uart_wclk_sel), CLK_UART1, 4, 1); - clk[ZX296702_UART1_WCLK] = - zx_gate("uart1_wclk", "uart1_wclk_mux", CLK_UART1, 1); - clk[ZX296702_UART1_PCLK] = - zx_gate("uart1_pclk", "lsp1_apb_pclk", CLK_UART1, 0); - - /* SDMMC0 */ - clk[ZX296702_SDMMC0_WCLK_MUX] = - zx_mux("sdmmc0_wclk_mux", sdmmc0_wclk_sel, - ARRAY_SIZE(sdmmc0_wclk_sel), CLK_SDMMC0, 4, 1); - clk[ZX296702_SDMMC0_WCLK_DIV] = - zx_div("sdmmc0_wclk_div", "sdmmc0_wclk_mux", CLK_SDMMC0, 12, 4); - clk[ZX296702_SDMMC0_WCLK] = - zx_gate("sdmmc0_wclk", "sdmmc0_wclk_div", CLK_SDMMC0, 1); - clk[ZX296702_SDMMC0_PCLK] = - zx_gate("sdmmc0_pclk", "lsp1_apb_pclk", CLK_SDMMC0, 0); - - clk[ZX296702_SPDIF1_WCLK_MUX] = - zx_mux("spdif1_wclk_mux", spdif1_wclk_sel, - ARRAY_SIZE(spdif1_wclk_sel), CLK_SPDIF1, 4, 1); - clk[ZX296702_SPDIF1_WCLK] = - zx_gate("spdif1_wclk", "spdif1_wclk_mux", CLK_SPDIF1, 1); - clk[ZX296702_SPDIF1_PCLK] = - zx_gate("spdif1_pclk", "lsp1_apb_pclk", CLK_SPDIF1, 0); - - clk[ZX296702_SPDIF1_DIV] = - clk_register_zx_audio("spdif1_div", "spdif1_wclk", 0, - SPDIF1_DIV); - - for (i = 0; i < ARRAY_SIZE(lsp1clk); i++) { - if (IS_ERR(clk[i])) { - pr_err("zx296702 clk %d: register failed with %ld\n", - i, PTR_ERR(clk[i])); - return; - } - } - - lsp1clk_data.clks = lsp1clk; - lsp1clk_data.clk_num = ARRAY_SIZE(lsp1clk); - of_clk_add_provider(np, of_clk_src_onecell_get, &lsp1clk_data); -} -CLK_OF_DECLARE(zx296702_lsp1_clk, "zte,zx296702-lsp1crpm-clk", - zx296702_lsp1_clocks_init); diff --git a/drivers/clk/zte/clk-zx296718.c b/drivers/clk/zte/clk-zx296718.c deleted file mode 100644 index dd7045bc48c1..000000000000 --- a/drivers/clk/zte/clk-zx296718.c +++ /dev/null @@ -1,1074 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2015 - 2016 ZTE Corporation. - * Copyright (C) 2016 Linaro Ltd. - */ -#include -#include -#include -#include -#include -#include - -#include -#include "clk.h" - -/* TOP CRM */ -#define TOP_CLK_MUX0 0x04 -#define TOP_CLK_MUX1 0x08 -#define TOP_CLK_MUX2 0x0c -#define TOP_CLK_MUX3 0x10 -#define TOP_CLK_MUX4 0x14 -#define TOP_CLK_MUX5 0x18 -#define TOP_CLK_MUX6 0x1c -#define TOP_CLK_MUX7 0x20 -#define TOP_CLK_MUX9 0x28 - - -#define TOP_CLK_GATE0 0x34 -#define TOP_CLK_GATE1 0x38 -#define TOP_CLK_GATE2 0x3c -#define TOP_CLK_GATE3 0x40 -#define TOP_CLK_GATE4 0x44 -#define TOP_CLK_GATE5 0x48 -#define TOP_CLK_GATE6 0x4c - -#define TOP_CLK_DIV0 0x58 - -#define PLL_CPU_REG 0x80 -#define PLL_VGA_REG 0xb0 -#define PLL_DDR_REG 0xa0 - -/* LSP0 CRM */ -#define LSP0_TIMER3_CLK 0x4 -#define LSP0_TIMER4_CLK 0x8 -#define LSP0_TIMER5_CLK 0xc -#define LSP0_UART3_CLK 0x10 -#define LSP0_UART1_CLK 0x14 -#define LSP0_UART2_CLK 0x18 -#define LSP0_SPIFC0_CLK 0x1c -#define LSP0_I2C4_CLK 0x20 -#define LSP0_I2C5_CLK 0x24 -#define LSP0_SSP0_CLK 0x28 -#define LSP0_SSP1_CLK 0x2c -#define LSP0_USIM0_CLK 0x30 -#define LSP0_GPIO_CLK 0x34 -#define LSP0_I2C3_CLK 0x38 - -/* LSP1 CRM */ -#define LSP1_UART4_CLK 0x08 -#define LSP1_UART5_CLK 0x0c -#define LSP1_PWM_CLK 0x10 -#define LSP1_I2C2_CLK 0x14 -#define LSP1_SSP2_CLK 0x1c -#define LSP1_SSP3_CLK 0x20 -#define LSP1_SSP4_CLK 0x24 -#define LSP1_USIM1_CLK 0x28 - -/* audio lsp */ -#define AUDIO_I2S0_DIV_CFG1 0x10 -#define AUDIO_I2S0_DIV_CFG2 0x14 -#define AUDIO_I2S0_CLK 0x18 -#define AUDIO_I2S1_DIV_CFG1 0x20 -#define AUDIO_I2S1_DIV_CFG2 0x24 -#define AUDIO_I2S1_CLK 0x28 -#define AUDIO_I2S2_DIV_CFG1 0x30 -#define AUDIO_I2S2_DIV_CFG2 0x34 -#define AUDIO_I2S2_CLK 0x38 -#define AUDIO_I2S3_DIV_CFG1 0x40 -#define AUDIO_I2S3_DIV_CFG2 0x44 -#define AUDIO_I2S3_CLK 0x48 -#define AUDIO_I2C0_CLK 0x50 -#define AUDIO_SPDIF0_DIV_CFG1 0x60 -#define AUDIO_SPDIF0_DIV_CFG2 0x64 -#define AUDIO_SPDIF0_CLK 0x68 -#define AUDIO_SPDIF1_DIV_CFG1 0x70 -#define AUDIO_SPDIF1_DIV_CFG2 0x74 -#define AUDIO_SPDIF1_CLK 0x78 -#define AUDIO_TIMER_CLK 0x80 -#define AUDIO_TDM_CLK 0x90 -#define AUDIO_TS_CLK 0xa0 - -static DEFINE_SPINLOCK(clk_lock); - -static const struct zx_pll_config pll_cpu_table[] = { - PLL_RATE(1312000000, 0x00103621, 0x04aaaaaa), - PLL_RATE(1407000000, 0x00103a21, 0x04aaaaaa), - PLL_RATE(1503000000, 0x00103e21, 0x04aaaaaa), - PLL_RATE(1600000000, 0x00104221, 0x04aaaaaa), -}; - -static const struct zx_pll_config pll_vga_table[] = { - PLL_RATE(36000000, 0x00102464, 0x04000000), /* 800x600@56 */ - PLL_RATE(40000000, 0x00102864, 0x04000000), /* 800x600@60 */ - PLL_RATE(49500000, 0x00103164, 0x04800000), /* 800x600@75 */ - PLL_RATE(50000000, 0x00103264, 0x04000000), /* 800x600@72 */ - PLL_RATE(56250000, 0x00103864, 0x04400000), /* 800x600@85 */ - PLL_RATE(65000000, 0x00104164, 0x04000000), /* 1024x768@60 */ - PLL_RATE(74375000, 0x00104a64, 0x04600000), /* 1280x720@60 */ - PLL_RATE(75000000, 0x00104b64, 0x04800000), /* 1024x768@70 */ - PLL_RATE(78750000, 0x00104e64, 0x04c00000), /* 1024x768@75 */ - PLL_RATE(85500000, 0x00105564, 0x04800000), /* 1360x768@60 */ - PLL_RATE(106500000, 0x00106a64, 0x04800000), /* 1440x900@60 */ - PLL_RATE(108000000, 0x00106c64, 0x04000000), /* 1280x1024@60 */ - PLL_RATE(110000000, 0x00106e64, 0x04000000), /* 1024x768@85 */ - PLL_RATE(135000000, 0x00105a44, 0x04000000), /* 1280x1024@75 */ - PLL_RATE(136750000, 0x00104462, 0x04600000), /* 1440x900@75 */ - PLL_RATE(148500000, 0x00104a62, 0x04400000), /* 1920x1080@60 */ - PLL_RATE(157000000, 0x00104e62, 0x04800000), /* 1440x900@85 */ - PLL_RATE(157500000, 0x00104e62, 0x04c00000), /* 1280x1024@85 */ - PLL_RATE(162000000, 0x00105162, 0x04000000), /* 1600x1200@60 */ - PLL_RATE(193250000, 0x00106062, 0x04a00000), /* 1920x1200@60 */ -}; - -PNAME(osc) = { - "osc24m", - "osc32k", -}; - -PNAME(dbg_wclk_p) = { - "clk334m", - "clk466m", - "clk396m", - "clk250m", -}; - -PNAME(a72_coreclk_p) = { - "osc24m", - "pll_mm0_1188m", - "pll_mm1_1296m", - "clk1000m", - "clk648m", - "clk1600m", - "pll_audio_1800m", - "pll_vga_1800m", -}; - -PNAME(cpu_periclk_p) = { - "osc24m", - "clk500m", - "clk594m", - "clk466m", - "clk294m", - "clk334m", - "clk250m", - "clk125m", -}; - -PNAME(a53_coreclk_p) = { - "osc24m", - "clk1000m", - "pll_mm0_1188m", - "clk648m", - "clk500m", - "clk800m", - "clk1600m", - "pll_audio_1800m", -}; - -PNAME(sec_wclk_p) = { - "osc24m", - "clk396m", - "clk334m", - "clk297m", - "clk250m", - "clk198m", - "clk148m5", - "clk99m", -}; - -PNAME(sd_nand_wclk_p) = { - "osc24m", - "clk49m5", - "clk99m", - "clk198m", - "clk167m", - "clk148m5", - "clk125m", - "clk216m", -}; - -PNAME(emmc_wclk_p) = { - "osc24m", - "clk198m", - "clk99m", - "clk396m", - "clk334m", - "clk297m", - "clk250m", - "clk148m5", -}; - -PNAME(clk32_p) = { - "osc32k", - "clk32k768", -}; - -PNAME(usb_ref24m_p) = { - "osc32k", - "clk32k768", -}; - -PNAME(sys_noc_alck_p) = { - "osc24m", - "clk250m", - "clk198m", - "clk148m5", - "clk108m", - "clk54m", - "clk216m", - "clk240m", -}; - -PNAME(vde_aclk_p) = { - "clk334m", - "clk594m", - "clk500m", - "clk432m", - "clk480m", - "clk297m", - "clk_vga", /*600MHz*/ - "clk294m", -}; - -PNAME(vce_aclk_p) = { - "clk334m", - "clk594m", - "clk500m", - "clk432m", - "clk396m", - "clk297m", - "clk_vga", /*600MHz*/ - "clk294m", -}; - -PNAME(hde_aclk_p) = { - "clk334m", - "clk594m", - "clk500m", - "clk432m", - "clk396m", - "clk297m", - "clk_vga", /*600MHz*/ - "clk294m", -}; - -PNAME(gpu_aclk_p) = { - "clk334m", - "clk648m", - "clk594m", - "clk500m", - "clk396m", - "clk297m", - "clk_vga", /*600MHz*/ - "clk294m", -}; - -PNAME(sappu_aclk_p) = { - "clk396m", - "clk500m", - "clk250m", - "clk148m5", -}; - -PNAME(sappu_wclk_p) = { - "clk198m", - "clk396m", - "clk334m", - "clk297m", - "clk250m", - "clk148m5", - "clk125m", - "clk99m", -}; - -PNAME(vou_aclk_p) = { - "clk334m", - "clk594m", - "clk500m", - "clk432m", - "clk396m", - "clk297m", - "clk_vga", /*600MHz*/ - "clk294m", -}; - -PNAME(vou_main_wclk_p) = { - "clk108m", - "clk594m", - "clk297m", - "clk148m5", - "clk74m25", - "clk54m", - "clk27m", - "clk_vga", -}; - -PNAME(vou_aux_wclk_p) = { - "clk108m", - "clk148m5", - "clk74m25", - "clk54m", - "clk27m", - "clk_vga", - "clk54m_mm0", - "clk" -}; - -PNAME(vou_ppu_wclk_p) = { - "clk334m", - "clk432m", - "clk396m", - "clk297m", - "clk250m", - "clk125m", - "clk198m", - "clk99m", -}; - -PNAME(vga_i2c_wclk_p) = { - "osc24m", - "clk99m", -}; - -PNAME(viu_m0_aclk_p) = { - "clk334m", - "clk432m", - "clk396m", - "clk297m", - "clk250m", - "clk125m", - "clk198m", - "osc24m", -}; - -PNAME(viu_m1_aclk_p) = { - "clk198m", - "clk250m", - "clk297m", - "clk125m", - "clk396m", - "clk334m", - "clk148m5", - "osc24m", -}; - -PNAME(viu_clk_p) = { - "clk198m", - "clk334m", - "clk297m", - "clk250m", - "clk396m", - "clk125m", - "clk99m", - "clk148m5", -}; - -PNAME(viu_jpeg_clk_p) = { - "clk334m", - "clk480m", - "clk432m", - "clk396m", - "clk297m", - "clk250m", - "clk125m", - "clk198m", -}; - -PNAME(ts_sys_clk_p) = { - "clk192m", - "clk167m", - "clk125m", - "clk99m", -}; - -PNAME(wdt_ares_p) = { - "osc24m", - "clk32k" -}; - -static struct clk_zx_pll zx296718_pll_clk[] = { - ZX296718_PLL("pll_cpu", "osc24m", PLL_CPU_REG, pll_cpu_table), - ZX296718_PLL("pll_vga", "osc24m", PLL_VGA_REG, pll_vga_table), -}; - -static struct zx_clk_fixed_factor top_ffactor_clk[] = { - FFACTOR(0, "clk4m", "osc24m", 1, 6, 0), - FFACTOR(0, "clk2m", "osc24m", 1, 12, 0), - /* pll cpu */ - FFACTOR(0, "clk1600m", "pll_cpu", 1, 1, CLK_SET_RATE_PARENT), - FFACTOR(0, "clk800m", "pll_cpu", 1, 2, CLK_SET_RATE_PARENT), - /* pll mac */ - FFACTOR(0, "clk25m", "pll_mac", 1, 40, 0), - FFACTOR(0, "clk125m", "pll_mac", 1, 8, 0), - FFACTOR(0, "clk250m", "pll_mac", 1, 4, 0), - FFACTOR(0, "clk50m", "pll_mac", 1, 20, 0), - FFACTOR(0, "clk500m", "pll_mac", 1, 2, 0), - FFACTOR(0, "clk1000m", "pll_mac", 1, 1, 0), - FFACTOR(0, "clk334m", "pll_mac", 1, 3, 0), - FFACTOR(0, "clk167m", "pll_mac", 1, 6, 0), - /* pll mm */ - FFACTOR(0, "clk54m_mm0", "pll_mm0", 1, 22, 0), - FFACTOR(0, "clk74m25", "pll_mm0", 1, 16, 0), - FFACTOR(0, "clk148m5", "pll_mm0", 1, 8, 0), - FFACTOR(0, "clk297m", "pll_mm0", 1, 4, 0), - FFACTOR(0, "clk594m", "pll_mm0", 1, 2, 0), - FFACTOR(0, "pll_mm0_1188m", "pll_mm0", 1, 1, 0), - FFACTOR(0, "clk396m", "pll_mm0", 1, 3, 0), - FFACTOR(0, "clk198m", "pll_mm0", 1, 6, 0), - FFACTOR(0, "clk99m", "pll_mm0", 1, 12, 0), - FFACTOR(0, "clk49m5", "pll_mm0", 1, 24, 0), - /* pll mm */ - FFACTOR(0, "clk324m", "pll_mm1", 1, 4, 0), - FFACTOR(0, "clk648m", "pll_mm1", 1, 2, 0), - FFACTOR(0, "pll_mm1_1296m", "pll_mm1", 1, 1, 0), - FFACTOR(0, "clk216m", "pll_mm1", 1, 6, 0), - FFACTOR(0, "clk432m", "pll_mm1", 1, 3, 0), - FFACTOR(0, "clk108m", "pll_mm1", 1, 12, 0), - FFACTOR(0, "clk72m", "pll_mm1", 1, 18, 0), - FFACTOR(0, "clk27m", "pll_mm1", 1, 48, 0), - FFACTOR(0, "clk54m", "pll_mm1", 1, 24, 0), - /* vga */ - FFACTOR(0, "pll_vga_1800m", "pll_vga", 1, 1, 0), - FFACTOR(0, "clk_vga", "pll_vga", 1, 1, CLK_SET_RATE_PARENT), - /* pll ddr */ - FFACTOR(0, "clk466m", "pll_ddr", 1, 2, 0), - - /* pll audio */ - FFACTOR(0, "pll_audio_1800m", "pll_audio", 1, 1, 0), - FFACTOR(0, "clk32k768", "pll_audio", 1, 27000, 0), - FFACTOR(0, "clk16m384", "pll_audio", 1, 54, 0), - FFACTOR(0, "clk294m", "pll_audio", 1, 3, 0), - - /* pll hsic*/ - FFACTOR(0, "clk240m", "pll_hsic", 1, 4, 0), - FFACTOR(0, "clk480m", "pll_hsic", 1, 2, 0), - FFACTOR(0, "clk192m", "pll_hsic", 1, 5, 0), - FFACTOR(0, "clk_pll_24m", "pll_hsic", 1, 40, 0), - FFACTOR(0, "emmc_mux_div2", "emmc_mux", 1, 2, CLK_SET_RATE_PARENT), -}; - -static const struct clk_div_table noc_div_table[] = { - { .val = 1, .div = 2, }, - { .val = 3, .div = 4, }, -}; -static struct zx_clk_div top_div_clk[] = { - DIV_T(0, "sys_noc_hclk", "sys_noc_aclk", TOP_CLK_DIV0, 0, 2, 0, noc_div_table), - DIV_T(0, "sys_noc_pclk", "sys_noc_aclk", TOP_CLK_DIV0, 4, 2, 0, noc_div_table), -}; - -static struct zx_clk_mux top_mux_clk[] = { - MUX(0, "dbg_mux", dbg_wclk_p, TOP_CLK_MUX0, 12, 2), - MUX(0, "a72_mux", a72_coreclk_p, TOP_CLK_MUX0, 8, 3), - MUX(0, "cpu_peri_mux", cpu_periclk_p, TOP_CLK_MUX0, 4, 3), - MUX_F(0, "a53_mux", a53_coreclk_p, TOP_CLK_MUX0, 0, 3, CLK_SET_RATE_PARENT, 0), - MUX(0, "sys_noc_aclk", sys_noc_alck_p, TOP_CLK_MUX1, 0, 3), - MUX(0, "sec_mux", sec_wclk_p, TOP_CLK_MUX2, 16, 3), - MUX(0, "sd1_mux", sd_nand_wclk_p, TOP_CLK_MUX2, 12, 3), - MUX(0, "sd0_mux", sd_nand_wclk_p, TOP_CLK_MUX2, 8, 3), - MUX(0, "emmc_mux", emmc_wclk_p, TOP_CLK_MUX2, 4, 3), - MUX(0, "nand_mux", sd_nand_wclk_p, TOP_CLK_MUX2, 0, 3), - MUX(0, "usb_ref24m_mux", usb_ref24m_p, TOP_CLK_MUX9, 16, 1), - MUX(0, "clk32k", clk32_p, TOP_CLK_MUX9, 12, 1), - MUX_F(0, "wdt_mux", wdt_ares_p, TOP_CLK_MUX9, 8, 1, CLK_SET_RATE_PARENT, 0), - MUX(0, "timer_mux", osc, TOP_CLK_MUX9, 4, 1), - MUX(0, "vde_mux", vde_aclk_p, TOP_CLK_MUX4, 0, 3), - MUX(0, "vce_mux", vce_aclk_p, TOP_CLK_MUX4, 4, 3), - MUX(0, "hde_mux", hde_aclk_p, TOP_CLK_MUX4, 8, 3), - MUX(0, "gpu_mux", gpu_aclk_p, TOP_CLK_MUX5, 0, 3), - MUX(0, "sappu_a_mux", sappu_aclk_p, TOP_CLK_MUX5, 4, 2), - MUX(0, "sappu_w_mux", sappu_wclk_p, TOP_CLK_MUX5, 8, 3), - MUX(0, "vou_a_mux", vou_aclk_p, TOP_CLK_MUX7, 0, 3), - MUX_F(0, "vou_main_w_mux", vou_main_wclk_p, TOP_CLK_MUX7, 4, 3, CLK_SET_RATE_PARENT, 0), - MUX_F(0, "vou_aux_w_mux", vou_aux_wclk_p, TOP_CLK_MUX7, 8, 3, CLK_SET_RATE_PARENT, 0), - MUX(0, "vou_ppu_w_mux", vou_ppu_wclk_p, TOP_CLK_MUX7, 12, 3), - MUX(0, "vga_i2c_mux", vga_i2c_wclk_p, TOP_CLK_MUX7, 16, 1), - MUX(0, "viu_m0_a_mux", viu_m0_aclk_p, TOP_CLK_MUX6, 0, 3), - MUX(0, "viu_m1_a_mux", viu_m1_aclk_p, TOP_CLK_MUX6, 4, 3), - MUX(0, "viu_w_mux", viu_clk_p, TOP_CLK_MUX6, 8, 3), - MUX(0, "viu_jpeg_w_mux", viu_jpeg_clk_p, TOP_CLK_MUX6, 12, 3), - MUX(0, "ts_sys_mux", ts_sys_clk_p, TOP_CLK_MUX6, 16, 2), -}; - -static struct zx_clk_gate top_gate_clk[] = { - GATE(CPU_DBG_GATE, "dbg_wclk", "dbg_mux", TOP_CLK_GATE0, 4, CLK_SET_RATE_PARENT, 0), - GATE(A72_GATE, "a72_coreclk", "a72_mux", TOP_CLK_GATE0, 3, CLK_SET_RATE_PARENT, 0), - GATE(CPU_PERI_GATE, "cpu_peri", "cpu_peri_mux", TOP_CLK_GATE0, 1, CLK_SET_RATE_PARENT, 0), - GATE(A53_GATE, "a53_coreclk", "a53_mux", TOP_CLK_GATE0, 0, CLK_SET_RATE_PARENT, 0), - GATE(SD1_WCLK, "sd1_wclk", "sd1_mux", TOP_CLK_GATE1, 13, CLK_SET_RATE_PARENT, 0), - GATE(SD0_WCLK, "sd0_wclk", "sd0_mux", TOP_CLK_GATE1, 9, CLK_SET_RATE_PARENT, 0), - GATE(EMMC_WCLK, "emmc_wclk", "emmc_mux_div2", TOP_CLK_GATE0, 5, CLK_SET_RATE_PARENT, 0), - GATE(EMMC_NAND_AXI, "emmc_nand_aclk", "sys_noc_aclk", TOP_CLK_GATE1, 4, CLK_SET_RATE_PARENT, 0), - GATE(NAND_WCLK, "nand_wclk", "nand_mux", TOP_CLK_GATE0, 1, CLK_SET_RATE_PARENT, 0), - GATE(EMMC_NAND_AHB, "emmc_nand_hclk", "sys_noc_hclk", TOP_CLK_GATE1, 0, CLK_SET_RATE_PARENT, 0), - GATE(0, "lsp1_pclk", "sys_noc_pclk", TOP_CLK_GATE2, 31, 0, 0), - GATE(LSP1_148M5, "lsp1_148m5", "clk148m5", TOP_CLK_GATE2, 30, 0, 0), - GATE(LSP1_99M, "lsp1_99m", "clk99m", TOP_CLK_GATE2, 29, 0, 0), - GATE(LSP1_24M, "lsp1_24m", "osc24m", TOP_CLK_GATE2, 28, 0, 0), - GATE(LSP0_74M25, "lsp0_74m25", "clk74m25", TOP_CLK_GATE2, 25, 0, 0), - GATE(0, "lsp0_pclk", "sys_noc_pclk", TOP_CLK_GATE2, 24, 0, 0), - GATE(LSP0_32K, "lsp0_32k", "osc32k", TOP_CLK_GATE2, 23, 0, 0), - GATE(LSP0_148M5, "lsp0_148m5", "clk148m5", TOP_CLK_GATE2, 22, 0, 0), - GATE(LSP0_99M, "lsp0_99m", "clk99m", TOP_CLK_GATE2, 21, 0, 0), - GATE(LSP0_24M, "lsp0_24m", "osc24m", TOP_CLK_GATE2, 20, 0, 0), - GATE(AUDIO_99M, "audio_99m", "clk99m", TOP_CLK_GATE5, 27, 0, 0), - GATE(AUDIO_24M, "audio_24m", "osc24m", TOP_CLK_GATE5, 28, 0, 0), - GATE(AUDIO_16M384, "audio_16m384", "clk16m384", TOP_CLK_GATE5, 29, 0, 0), - GATE(AUDIO_32K, "audio_32k", "clk32k", TOP_CLK_GATE5, 30, 0, 0), - GATE(WDT_WCLK, "wdt_wclk", "wdt_mux", TOP_CLK_GATE6, 9, CLK_SET_RATE_PARENT, 0), - GATE(TIMER_WCLK, "timer_wclk", "timer_mux", TOP_CLK_GATE6, 5, CLK_SET_RATE_PARENT, 0), - GATE(VDE_ACLK, "vde_aclk", "vde_mux", TOP_CLK_GATE3, 0, CLK_SET_RATE_PARENT, 0), - GATE(VCE_ACLK, "vce_aclk", "vce_mux", TOP_CLK_GATE3, 4, CLK_SET_RATE_PARENT, 0), - GATE(HDE_ACLK, "hde_aclk", "hde_mux", TOP_CLK_GATE3, 8, CLK_SET_RATE_PARENT, 0), - GATE(GPU_ACLK, "gpu_aclk", "gpu_mux", TOP_CLK_GATE3, 16, CLK_SET_RATE_PARENT, 0), - GATE(SAPPU_ACLK, "sappu_aclk", "sappu_a_mux", TOP_CLK_GATE3, 20, CLK_SET_RATE_PARENT, 0), - GATE(SAPPU_WCLK, "sappu_wclk", "sappu_w_mux", TOP_CLK_GATE3, 22, CLK_SET_RATE_PARENT, 0), - GATE(VOU_ACLK, "vou_aclk", "vou_a_mux", TOP_CLK_GATE4, 16, CLK_SET_RATE_PARENT, 0), - GATE(VOU_MAIN_WCLK, "vou_main_wclk", "vou_main_w_mux", TOP_CLK_GATE4, 18, CLK_SET_RATE_PARENT, 0), - GATE(VOU_AUX_WCLK, "vou_aux_wclk", "vou_aux_w_mux", TOP_CLK_GATE4, 19, CLK_SET_RATE_PARENT, 0), - GATE(VOU_PPU_WCLK, "vou_ppu_wclk", "vou_ppu_w_mux", TOP_CLK_GATE4, 20, CLK_SET_RATE_PARENT, 0), - GATE(MIPI_CFG_CLK, "mipi_cfg_clk", "osc24m", TOP_CLK_GATE4, 21, 0, 0), - GATE(VGA_I2C_WCLK, "vga_i2c_wclk", "vga_i2c_mux", TOP_CLK_GATE4, 23, CLK_SET_RATE_PARENT, 0), - GATE(MIPI_REF_CLK, "mipi_ref_clk", "clk27m", TOP_CLK_GATE4, 24, 0, 0), - GATE(HDMI_OSC_CEC, "hdmi_osc_cec", "clk2m", TOP_CLK_GATE4, 22, 0, 0), - GATE(HDMI_OSC_CLK, "hdmi_osc_clk", "clk240m", TOP_CLK_GATE4, 25, 0, 0), - GATE(HDMI_XCLK, "hdmi_xclk", "osc24m", TOP_CLK_GATE4, 26, 0, 0), - GATE(VIU_M0_ACLK, "viu_m0_aclk", "viu_m0_a_mux", TOP_CLK_GATE4, 0, CLK_SET_RATE_PARENT, 0), - GATE(VIU_M1_ACLK, "viu_m1_aclk", "viu_m1_a_mux", TOP_CLK_GATE4, 1, CLK_SET_RATE_PARENT, 0), - GATE(VIU_WCLK, "viu_wclk", "viu_w_mux", TOP_CLK_GATE4, 2, CLK_SET_RATE_PARENT, 0), - GATE(VIU_JPEG_WCLK, "viu_jpeg_wclk", "viu_jpeg_w_mux", TOP_CLK_GATE4, 3, CLK_SET_RATE_PARENT, 0), - GATE(VIU_CFG_CLK, "viu_cfg_clk", "osc24m", TOP_CLK_GATE4, 6, 0, 0), - GATE(TS_SYS_WCLK, "ts_sys_wclk", "ts_sys_mux", TOP_CLK_GATE5, 2, CLK_SET_RATE_PARENT, 0), - GATE(TS_SYS_108M, "ts_sys_108m", "clk108m", TOP_CLK_GATE5, 3, 0, 0), - GATE(USB20_HCLK, "usb20_hclk", "sys_noc_hclk", TOP_CLK_GATE2, 12, 0, 0), - GATE(USB20_PHY_CLK, "usb20_phy_clk", "usb_ref24m_mux", TOP_CLK_GATE2, 13, 0, 0), - GATE(USB21_HCLK, "usb21_hclk", "sys_noc_hclk", TOP_CLK_GATE2, 14, 0, 0), - GATE(USB21_PHY_CLK, "usb21_phy_clk", "usb_ref24m_mux", TOP_CLK_GATE2, 15, 0, 0), - GATE(GMAC_RMIICLK, "gmac_rmii_clk", "clk50m", TOP_CLK_GATE2, 3, 0, 0), - GATE(GMAC_PCLK, "gmac_pclk", "clk198m", TOP_CLK_GATE2, 1, 0, 0), - GATE(GMAC_ACLK, "gmac_aclk", "clk49m5", TOP_CLK_GATE2, 0, 0, 0), - GATE(GMAC_RFCLK, "gmac_refclk", "clk25m", TOP_CLK_GATE2, 4, 0, 0), - GATE(SD1_AHB, "sd1_hclk", "sys_noc_hclk", TOP_CLK_GATE1, 12, 0, 0), - GATE(SD0_AHB, "sd0_hclk", "sys_noc_hclk", TOP_CLK_GATE1, 8, 0, 0), - GATE(TEMPSENSOR_GATE, "tempsensor_gate", "clk4m", TOP_CLK_GATE5, 31, 0, 0), -}; - -static struct clk_hw_onecell_data top_hw_onecell_data = { - .num = TOP_NR_CLKS, - .hws = { - [TOP_NR_CLKS - 1] = NULL, - }, -}; - -static int __init top_clocks_init(struct device_node *np) -{ - void __iomem *reg_base; - int i, ret; - const char *name; - - reg_base = of_iomap(np, 0); - if (!reg_base) { - pr_err("%s: Unable to map clk base\n", __func__); - return -ENXIO; - } - - for (i = 0; i < ARRAY_SIZE(zx296718_pll_clk); i++) { - zx296718_pll_clk[i].reg_base += (uintptr_t)reg_base; - name = zx296718_pll_clk[i].hw.init->name; - ret = clk_hw_register(NULL, &zx296718_pll_clk[i].hw); - if (ret) - pr_warn("top clk %s init error!\n", name); - } - - for (i = 0; i < ARRAY_SIZE(top_ffactor_clk); i++) { - if (top_ffactor_clk[i].id) - top_hw_onecell_data.hws[top_ffactor_clk[i].id] = - &top_ffactor_clk[i].factor.hw; - - name = top_ffactor_clk[i].factor.hw.init->name; - ret = clk_hw_register(NULL, &top_ffactor_clk[i].factor.hw); - if (ret) - pr_warn("top clk %s init error!\n", name); - } - - for (i = 0; i < ARRAY_SIZE(top_mux_clk); i++) { - if (top_mux_clk[i].id) - top_hw_onecell_data.hws[top_mux_clk[i].id] = - &top_mux_clk[i].mux.hw; - - top_mux_clk[i].mux.reg += (uintptr_t)reg_base; - name = top_mux_clk[i].mux.hw.init->name; - ret = clk_hw_register(NULL, &top_mux_clk[i].mux.hw); - if (ret) - pr_warn("top clk %s init error!\n", name); - } - - for (i = 0; i < ARRAY_SIZE(top_gate_clk); i++) { - if (top_gate_clk[i].id) - top_hw_onecell_data.hws[top_gate_clk[i].id] = - &top_gate_clk[i].gate.hw; - - top_gate_clk[i].gate.reg += (uintptr_t)reg_base; - name = top_gate_clk[i].gate.hw.init->name; - ret = clk_hw_register(NULL, &top_gate_clk[i].gate.hw); - if (ret) - pr_warn("top clk %s init error!\n", name); - } - - for (i = 0; i < ARRAY_SIZE(top_div_clk); i++) { - if (top_div_clk[i].id) - top_hw_onecell_data.hws[top_div_clk[i].id] = - &top_div_clk[i].div.hw; - - top_div_clk[i].div.reg += (uintptr_t)reg_base; - name = top_div_clk[i].div.hw.init->name; - ret = clk_hw_register(NULL, &top_div_clk[i].div.hw); - if (ret) - pr_warn("top clk %s init error!\n", name); - } - - ret = of_clk_add_hw_provider(np, of_clk_hw_onecell_get, - &top_hw_onecell_data); - if (ret) { - pr_err("failed to register top clk provider: %d\n", ret); - return ret; - } - - return 0; -} - -static const struct clk_div_table common_even_div_table[] = { - { .val = 0, .div = 1, }, - { .val = 1, .div = 2, }, - { .val = 3, .div = 4, }, - { .val = 5, .div = 6, }, - { .val = 7, .div = 8, }, - { .val = 9, .div = 10, }, - { .val = 11, .div = 12, }, - { .val = 13, .div = 14, }, - { .val = 15, .div = 16, }, -}; - -static const struct clk_div_table common_div_table[] = { - { .val = 0, .div = 1, }, - { .val = 1, .div = 2, }, - { .val = 2, .div = 3, }, - { .val = 3, .div = 4, }, - { .val = 4, .div = 5, }, - { .val = 5, .div = 6, }, - { .val = 6, .div = 7, }, - { .val = 7, .div = 8, }, - { .val = 8, .div = 9, }, - { .val = 9, .div = 10, }, - { .val = 10, .div = 11, }, - { .val = 11, .div = 12, }, - { .val = 12, .div = 13, }, - { .val = 13, .div = 14, }, - { .val = 14, .div = 15, }, - { .val = 15, .div = 16, }, -}; - -PNAME(lsp0_wclk_common_p) = { - "lsp0_24m", - "lsp0_99m", -}; - -PNAME(lsp0_wclk_timer3_p) = { - "timer3_div", - "lsp0_32k" -}; - -PNAME(lsp0_wclk_timer4_p) = { - "timer4_div", - "lsp0_32k" -}; - -PNAME(lsp0_wclk_timer5_p) = { - "timer5_div", - "lsp0_32k" -}; - -PNAME(lsp0_wclk_spifc0_p) = { - "lsp0_148m5", - "lsp0_24m", - "lsp0_99m", - "lsp0_74m25" -}; - -PNAME(lsp0_wclk_ssp_p) = { - "lsp0_148m5", - "lsp0_99m", - "lsp0_24m", -}; - -static struct zx_clk_mux lsp0_mux_clk[] = { - MUX(0, "timer3_wclk_mux", lsp0_wclk_timer3_p, LSP0_TIMER3_CLK, 4, 1), - MUX(0, "timer4_wclk_mux", lsp0_wclk_timer4_p, LSP0_TIMER4_CLK, 4, 1), - MUX(0, "timer5_wclk_mux", lsp0_wclk_timer5_p, LSP0_TIMER5_CLK, 4, 1), - MUX(0, "uart3_wclk_mux", lsp0_wclk_common_p, LSP0_UART3_CLK, 4, 1), - MUX(0, "uart1_wclk_mux", lsp0_wclk_common_p, LSP0_UART1_CLK, 4, 1), - MUX(0, "uart2_wclk_mux", lsp0_wclk_common_p, LSP0_UART2_CLK, 4, 1), - MUX(0, "spifc0_wclk_mux", lsp0_wclk_spifc0_p, LSP0_SPIFC0_CLK, 4, 2), - MUX(0, "i2c4_wclk_mux", lsp0_wclk_common_p, LSP0_I2C4_CLK, 4, 1), - MUX(0, "i2c5_wclk_mux", lsp0_wclk_common_p, LSP0_I2C5_CLK, 4, 1), - MUX(0, "ssp0_wclk_mux", lsp0_wclk_ssp_p, LSP0_SSP0_CLK, 4, 1), - MUX(0, "ssp1_wclk_mux", lsp0_wclk_ssp_p, LSP0_SSP1_CLK, 4, 1), - MUX(0, "i2c3_wclk_mux", lsp0_wclk_common_p, LSP0_I2C3_CLK, 4, 1), -}; - -static struct zx_clk_gate lsp0_gate_clk[] = { - GATE(LSP0_TIMER3_WCLK, "timer3_wclk", "timer3_wclk_mux", LSP0_TIMER3_CLK, 1, CLK_SET_RATE_PARENT, 0), - GATE(LSP0_TIMER4_WCLK, "timer4_wclk", "timer4_wclk_mux", LSP0_TIMER4_CLK, 1, CLK_SET_RATE_PARENT, 0), - GATE(LSP0_TIMER5_WCLK, "timer5_wclk", "timer5_wclk_mux", LSP0_TIMER5_CLK, 1, CLK_SET_RATE_PARENT, 0), - GATE(LSP0_UART3_WCLK, "uart3_wclk", "uart3_wclk_mux", LSP0_UART3_CLK, 1, CLK_SET_RATE_PARENT, 0), - GATE(LSP0_UART1_WCLK, "uart1_wclk", "uart1_wclk_mux", LSP0_UART1_CLK, 1, CLK_SET_RATE_PARENT, 0), - GATE(LSP0_UART2_WCLK, "uart2_wclk", "uart2_wclk_mux", LSP0_UART2_CLK, 1, CLK_SET_RATE_PARENT, 0), - GATE(LSP0_SPIFC0_WCLK, "spifc0_wclk", "spifc0_wclk_mux", LSP0_SPIFC0_CLK, 1, CLK_SET_RATE_PARENT, 0), - GATE(LSP0_I2C4_WCLK, "i2c4_wclk", "i2c4_wclk_mux", LSP0_I2C4_CLK, 1, CLK_SET_RATE_PARENT, 0), - GATE(LSP0_I2C5_WCLK, "i2c5_wclk", "i2c5_wclk_mux", LSP0_I2C5_CLK, 1, CLK_SET_RATE_PARENT, 0), - GATE(LSP0_SSP0_WCLK, "ssp0_wclk", "ssp0_div", LSP0_SSP0_CLK, 1, CLK_SET_RATE_PARENT, 0), - GATE(LSP0_SSP1_WCLK, "ssp1_wclk", "ssp1_div", LSP0_SSP1_CLK, 1, CLK_SET_RATE_PARENT, 0), - GATE(LSP0_I2C3_WCLK, "i2c3_wclk", "i2c3_wclk_mux", LSP0_I2C3_CLK, 1, CLK_SET_RATE_PARENT, 0), -}; - -static struct zx_clk_div lsp0_div_clk[] = { - DIV_T(0, "timer3_div", "lsp0_24m", LSP0_TIMER3_CLK, 12, 4, 0, common_even_div_table), - DIV_T(0, "timer4_div", "lsp0_24m", LSP0_TIMER4_CLK, 12, 4, 0, common_even_div_table), - DIV_T(0, "timer5_div", "lsp0_24m", LSP0_TIMER5_CLK, 12, 4, 0, common_even_div_table), - DIV_T(0, "ssp0_div", "ssp0_wclk_mux", LSP0_SSP0_CLK, 12, 4, 0, common_even_div_table), - DIV_T(0, "ssp1_div", "ssp1_wclk_mux", LSP0_SSP1_CLK, 12, 4, 0, common_even_div_table), -}; - -static struct clk_hw_onecell_data lsp0_hw_onecell_data = { - .num = LSP0_NR_CLKS, - .hws = { - [LSP0_NR_CLKS - 1] = NULL, - }, -}; - -static int __init lsp0_clocks_init(struct device_node *np) -{ - void __iomem *reg_base; - int i, ret; - const char *name; - - reg_base = of_iomap(np, 0); - if (!reg_base) { - pr_err("%s: Unable to map clk base\n", __func__); - return -ENXIO; - } - - for (i = 0; i < ARRAY_SIZE(lsp0_mux_clk); i++) { - if (lsp0_mux_clk[i].id) - lsp0_hw_onecell_data.hws[lsp0_mux_clk[i].id] = - &lsp0_mux_clk[i].mux.hw; - - lsp0_mux_clk[i].mux.reg += (uintptr_t)reg_base; - name = lsp0_mux_clk[i].mux.hw.init->name; - ret = clk_hw_register(NULL, &lsp0_mux_clk[i].mux.hw); - if (ret) - pr_warn("lsp0 clk %s init error!\n", name); - } - - for (i = 0; i < ARRAY_SIZE(lsp0_gate_clk); i++) { - if (lsp0_gate_clk[i].id) - lsp0_hw_onecell_data.hws[lsp0_gate_clk[i].id] = - &lsp0_gate_clk[i].gate.hw; - - lsp0_gate_clk[i].gate.reg += (uintptr_t)reg_base; - name = lsp0_gate_clk[i].gate.hw.init->name; - ret = clk_hw_register(NULL, &lsp0_gate_clk[i].gate.hw); - if (ret) - pr_warn("lsp0 clk %s init error!\n", name); - } - - for (i = 0; i < ARRAY_SIZE(lsp0_div_clk); i++) { - if (lsp0_div_clk[i].id) - lsp0_hw_onecell_data.hws[lsp0_div_clk[i].id] = - &lsp0_div_clk[i].div.hw; - - lsp0_div_clk[i].div.reg += (uintptr_t)reg_base; - name = lsp0_div_clk[i].div.hw.init->name; - ret = clk_hw_register(NULL, &lsp0_div_clk[i].div.hw); - if (ret) - pr_warn("lsp0 clk %s init error!\n", name); - } - - ret = of_clk_add_hw_provider(np, of_clk_hw_onecell_get, - &lsp0_hw_onecell_data); - if (ret) { - pr_err("failed to register lsp0 clk provider: %d\n", ret); - return ret; - } - - return 0; -} - -PNAME(lsp1_wclk_common_p) = { - "lsp1_24m", - "lsp1_99m", -}; - -PNAME(lsp1_wclk_ssp_p) = { - "lsp1_148m5", - "lsp1_99m", - "lsp1_24m", -}; - -static struct zx_clk_mux lsp1_mux_clk[] = { - MUX(0, "uart4_wclk_mux", lsp1_wclk_common_p, LSP1_UART4_CLK, 4, 1), - MUX(0, "uart5_wclk_mux", lsp1_wclk_common_p, LSP1_UART5_CLK, 4, 1), - MUX(0, "pwm_wclk_mux", lsp1_wclk_common_p, LSP1_PWM_CLK, 4, 1), - MUX(0, "i2c2_wclk_mux", lsp1_wclk_common_p, LSP1_I2C2_CLK, 4, 1), - MUX(0, "ssp2_wclk_mux", lsp1_wclk_ssp_p, LSP1_SSP2_CLK, 4, 2), - MUX(0, "ssp3_wclk_mux", lsp1_wclk_ssp_p, LSP1_SSP3_CLK, 4, 2), - MUX(0, "ssp4_wclk_mux", lsp1_wclk_ssp_p, LSP1_SSP4_CLK, 4, 2), - MUX(0, "usim1_wclk_mux", lsp1_wclk_common_p, LSP1_USIM1_CLK, 4, 1), -}; - -static struct zx_clk_div lsp1_div_clk[] = { - DIV_T(0, "pwm_div", "pwm_wclk_mux", LSP1_PWM_CLK, 12, 4, CLK_SET_RATE_PARENT, common_div_table), - DIV_T(0, "ssp2_div", "ssp2_wclk_mux", LSP1_SSP2_CLK, 12, 4, CLK_SET_RATE_PARENT, common_even_div_table), - DIV_T(0, "ssp3_div", "ssp3_wclk_mux", LSP1_SSP3_CLK, 12, 4, CLK_SET_RATE_PARENT, common_even_div_table), - DIV_T(0, "ssp4_div", "ssp4_wclk_mux", LSP1_SSP4_CLK, 12, 4, CLK_SET_RATE_PARENT, common_even_div_table), -}; - -static struct zx_clk_gate lsp1_gate_clk[] = { - GATE(LSP1_UART4_WCLK, "lsp1_uart4_wclk", "uart4_wclk_mux", LSP1_UART4_CLK, 1, CLK_SET_RATE_PARENT, 0), - GATE(LSP1_UART5_WCLK, "lsp1_uart5_wclk", "uart5_wclk_mux", LSP1_UART5_CLK, 1, CLK_SET_RATE_PARENT, 0), - GATE(LSP1_PWM_WCLK, "lsp1_pwm_wclk", "pwm_div", LSP1_PWM_CLK, 1, CLK_SET_RATE_PARENT, 0), - GATE(LSP1_PWM_PCLK, "lsp1_pwm_pclk", "lsp1_pclk", LSP1_PWM_CLK, 0, 0, 0), - GATE(LSP1_I2C2_WCLK, "lsp1_i2c2_wclk", "i2c2_wclk_mux", LSP1_I2C2_CLK, 1, CLK_SET_RATE_PARENT, 0), - GATE(LSP1_SSP2_WCLK, "lsp1_ssp2_wclk", "ssp2_div", LSP1_SSP2_CLK, 1, CLK_SET_RATE_PARENT, 0), - GATE(LSP1_SSP3_WCLK, "lsp1_ssp3_wclk", "ssp3_div", LSP1_SSP3_CLK, 1, CLK_SET_RATE_PARENT, 0), - GATE(LSP1_SSP4_WCLK, "lsp1_ssp4_wclk", "ssp4_div", LSP1_SSP4_CLK, 1, CLK_SET_RATE_PARENT, 0), - GATE(LSP1_USIM1_WCLK, "lsp1_usim1_wclk", "usim1_wclk_mux", LSP1_USIM1_CLK, 1, CLK_SET_RATE_PARENT, 0), -}; - -static struct clk_hw_onecell_data lsp1_hw_onecell_data = { - .num = LSP1_NR_CLKS, - .hws = { - [LSP1_NR_CLKS - 1] = NULL, - }, -}; - -static int __init lsp1_clocks_init(struct device_node *np) -{ - void __iomem *reg_base; - int i, ret; - const char *name; - - reg_base = of_iomap(np, 0); - if (!reg_base) { - pr_err("%s: Unable to map clk base\n", __func__); - return -ENXIO; - } - - for (i = 0; i < ARRAY_SIZE(lsp1_mux_clk); i++) { - if (lsp1_mux_clk[i].id) - lsp1_hw_onecell_data.hws[lsp1_mux_clk[i].id] = - &lsp0_mux_clk[i].mux.hw; - - lsp1_mux_clk[i].mux.reg += (uintptr_t)reg_base; - name = lsp1_mux_clk[i].mux.hw.init->name; - ret = clk_hw_register(NULL, &lsp1_mux_clk[i].mux.hw); - if (ret) - pr_warn("lsp1 clk %s init error!\n", name); - } - - for (i = 0; i < ARRAY_SIZE(lsp1_gate_clk); i++) { - if (lsp1_gate_clk[i].id) - lsp1_hw_onecell_data.hws[lsp1_gate_clk[i].id] = - &lsp1_gate_clk[i].gate.hw; - - lsp1_gate_clk[i].gate.reg += (uintptr_t)reg_base; - name = lsp1_gate_clk[i].gate.hw.init->name; - ret = clk_hw_register(NULL, &lsp1_gate_clk[i].gate.hw); - if (ret) - pr_warn("lsp1 clk %s init error!\n", name); - } - - for (i = 0; i < ARRAY_SIZE(lsp1_div_clk); i++) { - if (lsp1_div_clk[i].id) - lsp1_hw_onecell_data.hws[lsp1_div_clk[i].id] = - &lsp1_div_clk[i].div.hw; - - lsp1_div_clk[i].div.reg += (uintptr_t)reg_base; - name = lsp1_div_clk[i].div.hw.init->name; - ret = clk_hw_register(NULL, &lsp1_div_clk[i].div.hw); - if (ret) - pr_warn("lsp1 clk %s init error!\n", name); - } - - ret = of_clk_add_hw_provider(np, of_clk_hw_onecell_get, - &lsp1_hw_onecell_data); - if (ret) { - pr_err("failed to register lsp1 clk provider: %d\n", ret); - return ret; - } - - return 0; -} - -PNAME(audio_wclk_common_p) = { - "audio_99m", - "audio_24m", -}; - -PNAME(audio_timer_p) = { - "audio_24m", - "audio_32k", -}; - -static struct zx_clk_mux audio_mux_clk[] = { - MUX(I2S0_WCLK_MUX, "i2s0_wclk_mux", audio_wclk_common_p, AUDIO_I2S0_CLK, 0, 1), - MUX(I2S1_WCLK_MUX, "i2s1_wclk_mux", audio_wclk_common_p, AUDIO_I2S1_CLK, 0, 1), - MUX(I2S2_WCLK_MUX, "i2s2_wclk_mux", audio_wclk_common_p, AUDIO_I2S2_CLK, 0, 1), - MUX(I2S3_WCLK_MUX, "i2s3_wclk_mux", audio_wclk_common_p, AUDIO_I2S3_CLK, 0, 1), - MUX(0, "i2c0_wclk_mux", audio_wclk_common_p, AUDIO_I2C0_CLK, 0, 1), - MUX(0, "spdif0_wclk_mux", audio_wclk_common_p, AUDIO_SPDIF0_CLK, 0, 1), - MUX(0, "spdif1_wclk_mux", audio_wclk_common_p, AUDIO_SPDIF1_CLK, 0, 1), - MUX(0, "timer_wclk_mux", audio_timer_p, AUDIO_TIMER_CLK, 0, 1), -}; - -static struct clk_zx_audio_divider audio_adiv_clk[] = { - AUDIO_DIV(0, "i2s0_wclk_div", "i2s0_wclk_mux", AUDIO_I2S0_DIV_CFG1), - AUDIO_DIV(0, "i2s1_wclk_div", "i2s1_wclk_mux", AUDIO_I2S1_DIV_CFG1), - AUDIO_DIV(0, "i2s2_wclk_div", "i2s2_wclk_mux", AUDIO_I2S2_DIV_CFG1), - AUDIO_DIV(0, "i2s3_wclk_div", "i2s3_wclk_mux", AUDIO_I2S3_DIV_CFG1), - AUDIO_DIV(0, "spdif0_wclk_div", "spdif0_wclk_mux", AUDIO_SPDIF0_DIV_CFG1), - AUDIO_DIV(0, "spdif1_wclk_div", "spdif1_wclk_mux", AUDIO_SPDIF1_DIV_CFG1), -}; - -static struct zx_clk_div audio_div_clk[] = { - DIV_T(0, "tdm_wclk_div", "audio_16m384", AUDIO_TDM_CLK, 8, 4, 0, common_div_table), -}; - -static struct zx_clk_gate audio_gate_clk[] = { - GATE(AUDIO_I2S0_WCLK, "i2s0_wclk", "i2s0_wclk_div", AUDIO_I2S0_CLK, 9, CLK_SET_RATE_PARENT, 0), - GATE(AUDIO_I2S1_WCLK, "i2s1_wclk", "i2s1_wclk_div", AUDIO_I2S1_CLK, 9, CLK_SET_RATE_PARENT, 0), - GATE(AUDIO_I2S2_WCLK, "i2s2_wclk", "i2s2_wclk_div", AUDIO_I2S2_CLK, 9, CLK_SET_RATE_PARENT, 0), - GATE(AUDIO_I2S3_WCLK, "i2s3_wclk", "i2s3_wclk_div", AUDIO_I2S3_CLK, 9, CLK_SET_RATE_PARENT, 0), - GATE(AUDIO_I2S0_PCLK, "i2s0_pclk", "clk49m5", AUDIO_I2S0_CLK, 8, 0, 0), - GATE(AUDIO_I2S1_PCLK, "i2s1_pclk", "clk49m5", AUDIO_I2S1_CLK, 8, 0, 0), - GATE(AUDIO_I2S2_PCLK, "i2s2_pclk", "clk49m5", AUDIO_I2S2_CLK, 8, 0, 0), - GATE(AUDIO_I2S3_PCLK, "i2s3_pclk", "clk49m5", AUDIO_I2S3_CLK, 8, 0, 0), - GATE(AUDIO_I2C0_WCLK, "i2c0_wclk", "i2c0_wclk_mux", AUDIO_I2C0_CLK, 9, CLK_SET_RATE_PARENT, 0), - GATE(AUDIO_SPDIF0_WCLK, "spdif0_wclk", "spdif0_wclk_div", AUDIO_SPDIF0_CLK, 9, CLK_SET_RATE_PARENT, 0), - GATE(AUDIO_SPDIF1_WCLK, "spdif1_wclk", "spdif1_wclk_div", AUDIO_SPDIF1_CLK, 9, CLK_SET_RATE_PARENT, 0), - GATE(AUDIO_TDM_WCLK, "tdm_wclk", "tdm_wclk_div", AUDIO_TDM_CLK, 17, CLK_SET_RATE_PARENT, 0), - GATE(AUDIO_TS_PCLK, "tempsensor_pclk", "clk49m5", AUDIO_TS_CLK, 1, 0, 0), -}; - -static struct clk_hw_onecell_data audio_hw_onecell_data = { - .num = AUDIO_NR_CLKS, - .hws = { - [AUDIO_NR_CLKS - 1] = NULL, - }, -}; - -static int __init audio_clocks_init(struct device_node *np) -{ - void __iomem *reg_base; - int i, ret; - const char *name; - - reg_base = of_iomap(np, 0); - if (!reg_base) { - pr_err("%s: Unable to map audio clk base\n", __func__); - return -ENXIO; - } - - for (i = 0; i < ARRAY_SIZE(audio_mux_clk); i++) { - if (audio_mux_clk[i].id) - audio_hw_onecell_data.hws[audio_mux_clk[i].id] = - &audio_mux_clk[i].mux.hw; - - audio_mux_clk[i].mux.reg += (uintptr_t)reg_base; - name = audio_mux_clk[i].mux.hw.init->name; - ret = clk_hw_register(NULL, &audio_mux_clk[i].mux.hw); - if (ret) - pr_warn("audio clk %s init error!\n", name); - } - - for (i = 0; i < ARRAY_SIZE(audio_adiv_clk); i++) { - if (audio_adiv_clk[i].id) - audio_hw_onecell_data.hws[audio_adiv_clk[i].id] = - &audio_adiv_clk[i].hw; - - audio_adiv_clk[i].reg_base += (uintptr_t)reg_base; - name = audio_adiv_clk[i].hw.init->name; - ret = clk_hw_register(NULL, &audio_adiv_clk[i].hw); - if (ret) - pr_warn("audio clk %s init error!\n", name); - } - - for (i = 0; i < ARRAY_SIZE(audio_div_clk); i++) { - if (audio_div_clk[i].id) - audio_hw_onecell_data.hws[audio_div_clk[i].id] = - &audio_div_clk[i].div.hw; - - audio_div_clk[i].div.reg += (uintptr_t)reg_base; - name = audio_div_clk[i].div.hw.init->name; - ret = clk_hw_register(NULL, &audio_div_clk[i].div.hw); - if (ret) - pr_warn("audio clk %s init error!\n", name); - } - - for (i = 0; i < ARRAY_SIZE(audio_gate_clk); i++) { - if (audio_gate_clk[i].id) - audio_hw_onecell_data.hws[audio_gate_clk[i].id] = - &audio_gate_clk[i].gate.hw; - - audio_gate_clk[i].gate.reg += (uintptr_t)reg_base; - name = audio_gate_clk[i].gate.hw.init->name; - ret = clk_hw_register(NULL, &audio_gate_clk[i].gate.hw); - if (ret) - pr_warn("audio clk %s init error!\n", name); - } - - ret = of_clk_add_hw_provider(np, of_clk_hw_onecell_get, - &audio_hw_onecell_data); - if (ret) { - pr_err("failed to register audio clk provider: %d\n", ret); - return ret; - } - - return 0; -} - -static const struct of_device_id zx_clkc_match_table[] = { - { .compatible = "zte,zx296718-topcrm", .data = &top_clocks_init }, - { .compatible = "zte,zx296718-lsp0crm", .data = &lsp0_clocks_init }, - { .compatible = "zte,zx296718-lsp1crm", .data = &lsp1_clocks_init }, - { .compatible = "zte,zx296718-audiocrm", .data = &audio_clocks_init }, - { } -}; - -static int zx_clkc_probe(struct platform_device *pdev) -{ - int (*init_fn)(struct device_node *np); - struct device_node *np = pdev->dev.of_node; - - init_fn = of_device_get_match_data(&pdev->dev); - if (!init_fn) { - dev_err(&pdev->dev, "Error: No device match found\n"); - return -ENODEV; - } - - return init_fn(np); -} - -static struct platform_driver zx_clk_driver = { - .probe = zx_clkc_probe, - .driver = { - .name = "zx296718-clkc", - .of_match_table = zx_clkc_match_table, - }, -}; - -static int __init zx_clk_init(void) -{ - return platform_driver_register(&zx_clk_driver); -} -core_initcall(zx_clk_init); diff --git a/drivers/clk/zte/clk.c b/drivers/clk/zte/clk.c deleted file mode 100644 index 8bda6d41ad3a..000000000000 --- a/drivers/clk/zte/clk.c +++ /dev/null @@ -1,446 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright 2014 Linaro Ltd. - * Copyright (C) 2014 ZTE Corporation. - */ - -#include -#include -#include -#include -#include -#include -#include -#include - -#include "clk.h" - -#define to_clk_zx_pll(_hw) container_of(_hw, struct clk_zx_pll, hw) -#define to_clk_zx_audio(_hw) container_of(_hw, struct clk_zx_audio, hw) - -#define CFG0_CFG1_OFFSET 4 -#define LOCK_FLAG 30 -#define POWER_DOWN 31 - -static int rate_to_idx(struct clk_zx_pll *zx_pll, unsigned long rate) -{ - const struct zx_pll_config *config = zx_pll->lookup_table; - int i; - - for (i = 0; i < zx_pll->count; i++) { - if (config[i].rate > rate) - return i > 0 ? i - 1 : 0; - - if (config[i].rate == rate) - return i; - } - - return i - 1; -} - -static int hw_to_idx(struct clk_zx_pll *zx_pll) -{ - const struct zx_pll_config *config = zx_pll->lookup_table; - u32 hw_cfg0, hw_cfg1; - int i; - - hw_cfg0 = readl_relaxed(zx_pll->reg_base); - hw_cfg1 = readl_relaxed(zx_pll->reg_base + CFG0_CFG1_OFFSET); - - /* For matching the value in lookup table */ - hw_cfg0 &= ~BIT(zx_pll->lock_bit); - - /* Check availability of pd_bit */ - if (zx_pll->pd_bit < 32) - hw_cfg0 |= BIT(zx_pll->pd_bit); - - for (i = 0; i < zx_pll->count; i++) { - if (hw_cfg0 == config[i].cfg0 && hw_cfg1 == config[i].cfg1) - return i; - } - - return -EINVAL; -} - -static unsigned long zx_pll_recalc_rate(struct clk_hw *hw, - unsigned long parent_rate) -{ - struct clk_zx_pll *zx_pll = to_clk_zx_pll(hw); - int idx; - - idx = hw_to_idx(zx_pll); - if (unlikely(idx == -EINVAL)) - return 0; - - return zx_pll->lookup_table[idx].rate; -} - -static long zx_pll_round_rate(struct clk_hw *hw, unsigned long rate, - unsigned long *prate) -{ - struct clk_zx_pll *zx_pll = to_clk_zx_pll(hw); - int idx; - - idx = rate_to_idx(zx_pll, rate); - - return zx_pll->lookup_table[idx].rate; -} - -static int zx_pll_set_rate(struct clk_hw *hw, unsigned long rate, - unsigned long parent_rate) -{ - /* Assume current cpu is not running on current PLL */ - struct clk_zx_pll *zx_pll = to_clk_zx_pll(hw); - const struct zx_pll_config *config; - int idx; - - idx = rate_to_idx(zx_pll, rate); - config = &zx_pll->lookup_table[idx]; - - writel_relaxed(config->cfg0, zx_pll->reg_base); - writel_relaxed(config->cfg1, zx_pll->reg_base + CFG0_CFG1_OFFSET); - - return 0; -} - -static int zx_pll_enable(struct clk_hw *hw) -{ - struct clk_zx_pll *zx_pll = to_clk_zx_pll(hw); - u32 reg; - - /* If pd_bit is not available, simply return success. */ - if (zx_pll->pd_bit > 31) - return 0; - - reg = readl_relaxed(zx_pll->reg_base); - writel_relaxed(reg & ~BIT(zx_pll->pd_bit), zx_pll->reg_base); - - return readl_relaxed_poll_timeout(zx_pll->reg_base, reg, - reg & BIT(zx_pll->lock_bit), 0, 100); -} - -static void zx_pll_disable(struct clk_hw *hw) -{ - struct clk_zx_pll *zx_pll = to_clk_zx_pll(hw); - u32 reg; - - if (zx_pll->pd_bit > 31) - return; - - reg = readl_relaxed(zx_pll->reg_base); - writel_relaxed(reg | BIT(zx_pll->pd_bit), zx_pll->reg_base); -} - -static int zx_pll_is_enabled(struct clk_hw *hw) -{ - struct clk_zx_pll *zx_pll = to_clk_zx_pll(hw); - u32 reg; - - reg = readl_relaxed(zx_pll->reg_base); - - return !(reg & BIT(zx_pll->pd_bit)); -} - -const struct clk_ops zx_pll_ops = { - .recalc_rate = zx_pll_recalc_rate, - .round_rate = zx_pll_round_rate, - .set_rate = zx_pll_set_rate, - .enable = zx_pll_enable, - .disable = zx_pll_disable, - .is_enabled = zx_pll_is_enabled, -}; -EXPORT_SYMBOL(zx_pll_ops); - -struct clk *clk_register_zx_pll(const char *name, const char *parent_name, - unsigned long flags, void __iomem *reg_base, - const struct zx_pll_config *lookup_table, - int count, spinlock_t *lock) -{ - struct clk_zx_pll *zx_pll; - struct clk *clk; - struct clk_init_data init; - - zx_pll = kzalloc(sizeof(*zx_pll), GFP_KERNEL); - if (!zx_pll) - return ERR_PTR(-ENOMEM); - - init.name = name; - init.ops = &zx_pll_ops; - init.flags = flags; - init.parent_names = parent_name ? &parent_name : NULL; - init.num_parents = parent_name ? 1 : 0; - - zx_pll->reg_base = reg_base; - zx_pll->lookup_table = lookup_table; - zx_pll->count = count; - zx_pll->lock_bit = LOCK_FLAG; - zx_pll->pd_bit = POWER_DOWN; - zx_pll->lock = lock; - zx_pll->hw.init = &init; - - clk = clk_register(NULL, &zx_pll->hw); - if (IS_ERR(clk)) - kfree(zx_pll); - - return clk; -} - -#define BPAR 1000000 -static u32 calc_reg(u32 parent_rate, u32 rate) -{ - u32 sel, integ, fra_div, tmp; - u64 tmp64 = (u64)parent_rate * BPAR; - - do_div(tmp64, rate); - integ = (u32)tmp64 / BPAR; - integ = integ >> 1; - - tmp = (u32)tmp64 % BPAR; - sel = tmp / BPAR; - - tmp = tmp % BPAR; - fra_div = tmp * 0xff / BPAR; - tmp = (sel << 24) | (integ << 16) | (0xff << 8) | fra_div; - - /* Set I2S integer divider as 1. This bit is reserved for SPDIF - * and do no harm. - */ - tmp |= BIT(28); - return tmp; -} - -static u32 calc_rate(u32 reg, u32 parent_rate) -{ - u32 sel, integ, fra_div, tmp; - u64 tmp64 = (u64)parent_rate * BPAR; - - tmp = reg; - sel = (tmp >> 24) & BIT(0); - integ = (tmp >> 16) & 0xff; - fra_div = tmp & 0xff; - - tmp = fra_div * BPAR; - tmp = tmp / 0xff; - tmp += sel * BPAR; - tmp += 2 * integ * BPAR; - do_div(tmp64, tmp); - - return (u32)tmp64; -} - -static unsigned long zx_audio_recalc_rate(struct clk_hw *hw, - unsigned long parent_rate) -{ - struct clk_zx_audio *zx_audio = to_clk_zx_audio(hw); - u32 reg; - - reg = readl_relaxed(zx_audio->reg_base); - return calc_rate(reg, parent_rate); -} - -static long zx_audio_round_rate(struct clk_hw *hw, unsigned long rate, - unsigned long *prate) -{ - u32 reg; - - if (rate * 2 > *prate) - return -EINVAL; - - reg = calc_reg(*prate, rate); - return calc_rate(reg, *prate); -} - -static int zx_audio_set_rate(struct clk_hw *hw, unsigned long rate, - unsigned long parent_rate) -{ - struct clk_zx_audio *zx_audio = to_clk_zx_audio(hw); - u32 reg; - - reg = calc_reg(parent_rate, rate); - writel_relaxed(reg, zx_audio->reg_base); - - return 0; -} - -#define ZX_AUDIO_EN BIT(25) -static int zx_audio_enable(struct clk_hw *hw) -{ - struct clk_zx_audio *zx_audio = to_clk_zx_audio(hw); - u32 reg; - - reg = readl_relaxed(zx_audio->reg_base); - writel_relaxed(reg & ~ZX_AUDIO_EN, zx_audio->reg_base); - return 0; -} - -static void zx_audio_disable(struct clk_hw *hw) -{ - struct clk_zx_audio *zx_audio = to_clk_zx_audio(hw); - u32 reg; - - reg = readl_relaxed(zx_audio->reg_base); - writel_relaxed(reg | ZX_AUDIO_EN, zx_audio->reg_base); -} - -static const struct clk_ops zx_audio_ops = { - .recalc_rate = zx_audio_recalc_rate, - .round_rate = zx_audio_round_rate, - .set_rate = zx_audio_set_rate, - .enable = zx_audio_enable, - .disable = zx_audio_disable, -}; - -struct clk *clk_register_zx_audio(const char *name, - const char * const parent_name, - unsigned long flags, - void __iomem *reg_base) -{ - struct clk_zx_audio *zx_audio; - struct clk *clk; - struct clk_init_data init; - - zx_audio = kzalloc(sizeof(*zx_audio), GFP_KERNEL); - if (!zx_audio) - return ERR_PTR(-ENOMEM); - - init.name = name; - init.ops = &zx_audio_ops; - init.flags = flags; - init.parent_names = parent_name ? &parent_name : NULL; - init.num_parents = parent_name ? 1 : 0; - - zx_audio->reg_base = reg_base; - zx_audio->hw.init = &init; - - clk = clk_register(NULL, &zx_audio->hw); - if (IS_ERR(clk)) - kfree(zx_audio); - - return clk; -} - -#define CLK_AUDIO_DIV_FRAC BIT(0) -#define CLK_AUDIO_DIV_INT BIT(1) -#define CLK_AUDIO_DIV_UNCOMMON BIT(1) - -#define CLK_AUDIO_DIV_FRAC_NSHIFT 16 -#define CLK_AUDIO_DIV_INT_FRAC_RE BIT(16) -#define CLK_AUDIO_DIV_INT_FRAC_MAX (0xffff) -#define CLK_AUDIO_DIV_INT_FRAC_MIN (0x2) -#define CLK_AUDIO_DIV_INT_INT_SHIFT 24 -#define CLK_AUDIO_DIV_INT_INT_WIDTH 4 - -struct zx_clk_audio_div_table { - unsigned long rate; - unsigned int int_reg; - unsigned int frac_reg; -}; - -#define to_clk_zx_audio_div(_hw) container_of(_hw, struct clk_zx_audio_divider, hw) - -static unsigned long audio_calc_rate(struct clk_zx_audio_divider *audio_div, - u32 reg_frac, u32 reg_int, - unsigned long parent_rate) -{ - unsigned long rate, m, n; - - m = reg_frac & 0xffff; - n = (reg_frac >> 16) & 0xffff; - - m = (reg_int & 0xffff) * n + m; - rate = (parent_rate * n) / m; - - return rate; -} - -static void audio_calc_reg(struct clk_zx_audio_divider *audio_div, - struct zx_clk_audio_div_table *div_table, - unsigned long rate, unsigned long parent_rate) -{ - unsigned int reg_int, reg_frac; - unsigned long m, n, div; - - reg_int = parent_rate / rate; - - if (reg_int > CLK_AUDIO_DIV_INT_FRAC_MAX) - reg_int = CLK_AUDIO_DIV_INT_FRAC_MAX; - else if (reg_int < CLK_AUDIO_DIV_INT_FRAC_MIN) - reg_int = 0; - m = parent_rate - rate * reg_int; - n = rate; - - div = gcd(m, n); - m = m / div; - n = n / div; - - if ((m >> 16) || (n >> 16)) { - if (m > n) { - n = n * 0xffff / m; - m = 0xffff; - } else { - m = m * 0xffff / n; - n = 0xffff; - } - } - reg_frac = m | (n << 16); - - div_table->rate = parent_rate * n / (reg_int * n + m); - div_table->int_reg = reg_int; - div_table->frac_reg = reg_frac; -} - -static unsigned long zx_audio_div_recalc_rate(struct clk_hw *hw, - unsigned long parent_rate) -{ - struct clk_zx_audio_divider *zx_audio_div = to_clk_zx_audio_div(hw); - u32 reg_frac, reg_int; - - reg_frac = readl_relaxed(zx_audio_div->reg_base); - reg_int = readl_relaxed(zx_audio_div->reg_base + 0x4); - - return audio_calc_rate(zx_audio_div, reg_frac, reg_int, parent_rate); -} - -static long zx_audio_div_round_rate(struct clk_hw *hw, unsigned long rate, - unsigned long *prate) -{ - struct clk_zx_audio_divider *zx_audio_div = to_clk_zx_audio_div(hw); - struct zx_clk_audio_div_table divt; - - audio_calc_reg(zx_audio_div, &divt, rate, *prate); - - return audio_calc_rate(zx_audio_div, divt.frac_reg, divt.int_reg, *prate); -} - -static int zx_audio_div_set_rate(struct clk_hw *hw, unsigned long rate, - unsigned long parent_rate) -{ - struct clk_zx_audio_divider *zx_audio_div = to_clk_zx_audio_div(hw); - struct zx_clk_audio_div_table divt; - unsigned int val; - - audio_calc_reg(zx_audio_div, &divt, rate, parent_rate); - if (divt.rate != rate) - pr_debug("the real rate is:%ld", divt.rate); - - writel_relaxed(divt.frac_reg, zx_audio_div->reg_base); - - val = readl_relaxed(zx_audio_div->reg_base + 0x4); - val &= ~0xffff; - val |= divt.int_reg | CLK_AUDIO_DIV_INT_FRAC_RE; - writel_relaxed(val, zx_audio_div->reg_base + 0x4); - - mdelay(1); - - val = readl_relaxed(zx_audio_div->reg_base + 0x4); - val &= ~CLK_AUDIO_DIV_INT_FRAC_RE; - writel_relaxed(val, zx_audio_div->reg_base + 0x4); - - return 0; -} - -const struct clk_ops zx_audio_div_ops = { - .recalc_rate = zx_audio_div_recalc_rate, - .round_rate = zx_audio_div_round_rate, - .set_rate = zx_audio_div_set_rate, -}; diff --git a/drivers/clk/zte/clk.h b/drivers/clk/zte/clk.h deleted file mode 100644 index aeaf2a380ba6..000000000000 --- a/drivers/clk/zte/clk.h +++ /dev/null @@ -1,174 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright 2015 Linaro Ltd. - * Copyright (C) 2014 ZTE Corporation. - */ - -#ifndef __ZTE_CLK_H -#define __ZTE_CLK_H -#include -#include - -#define PNAME(x) static const char *x[] - -struct zx_pll_config { - unsigned long rate; - u32 cfg0; - u32 cfg1; -}; - -struct clk_zx_pll { - struct clk_hw hw; - void __iomem *reg_base; - const struct zx_pll_config *lookup_table; /* order by rate asc */ - int count; - spinlock_t *lock; - u8 pd_bit; /* power down bit */ - u8 lock_bit; /* pll lock flag bit */ -}; - -#define PLL_RATE(_rate, _cfg0, _cfg1) \ -{ \ - .rate = _rate, \ - .cfg0 = _cfg0, \ - .cfg1 = _cfg1, \ -} - -#define ZX_PLL(_name, _parent, _reg, _table, _pd, _lock) \ -{ \ - .reg_base = (void __iomem *) _reg, \ - .lookup_table = _table, \ - .count = ARRAY_SIZE(_table), \ - .pd_bit = _pd, \ - .lock_bit = _lock, \ - .hw.init = CLK_HW_INIT(_name, _parent, &zx_pll_ops, \ - CLK_GET_RATE_NOCACHE), \ -} - -/* - * The pd_bit is not available on ZX296718, so let's pass something - * bigger than 31, e.g. 0xff, to indicate that. - */ -#define ZX296718_PLL(_name, _parent, _reg, _table) \ -ZX_PLL(_name, _parent, _reg, _table, 0xff, 30) - -struct zx_clk_gate { - struct clk_gate gate; - u16 id; -}; - -#define GATE(_id, _name, _parent, _reg, _bit, _flag, _gflags) \ -{ \ - .gate = { \ - .reg = (void __iomem *) _reg, \ - .bit_idx = (_bit), \ - .flags = _gflags, \ - .lock = &clk_lock, \ - .hw.init = CLK_HW_INIT(_name, \ - _parent, \ - &clk_gate_ops, \ - _flag | CLK_IGNORE_UNUSED), \ - }, \ - .id = _id, \ -} - -struct zx_clk_fixed_factor { - struct clk_fixed_factor factor; - u16 id; -}; - -#define FFACTOR(_id, _name, _parent, _mult, _div, _flag) \ -{ \ - .factor = { \ - .div = _div, \ - .mult = _mult, \ - .hw.init = CLK_HW_INIT(_name, \ - _parent, \ - &clk_fixed_factor_ops, \ - _flag), \ - }, \ - .id = _id, \ -} - -struct zx_clk_mux { - struct clk_mux mux; - u16 id; -}; - -#define MUX_F(_id, _name, _parent, _reg, _shift, _width, _flag, _mflag) \ -{ \ - .mux = { \ - .reg = (void __iomem *) _reg, \ - .mask = BIT(_width) - 1, \ - .shift = _shift, \ - .flags = _mflag, \ - .lock = &clk_lock, \ - .hw.init = CLK_HW_INIT_PARENTS(_name, \ - _parent, \ - &clk_mux_ops, \ - _flag), \ - }, \ - .id = _id, \ -} - -#define MUX(_id, _name, _parent, _reg, _shift, _width) \ -MUX_F(_id, _name, _parent, _reg, _shift, _width, 0, 0) - -struct zx_clk_div { - struct clk_divider div; - u16 id; -}; - -#define DIV_T(_id, _name, _parent, _reg, _shift, _width, _flag, _table) \ -{ \ - .div = { \ - .reg = (void __iomem *) _reg, \ - .shift = _shift, \ - .width = _width, \ - .flags = 0, \ - .table = _table, \ - .lock = &clk_lock, \ - .hw.init = CLK_HW_INIT(_name, \ - _parent, \ - &clk_divider_ops, \ - _flag), \ - }, \ - .id = _id, \ -} - -struct clk_zx_audio_divider { - struct clk_hw hw; - void __iomem *reg_base; - unsigned int rate_count; - spinlock_t *lock; - u16 id; -}; - -#define AUDIO_DIV(_id, _name, _parent, _reg) \ -{ \ - .reg_base = (void __iomem *) _reg, \ - .lock = &clk_lock, \ - .hw.init = CLK_HW_INIT(_name, \ - _parent, \ - &zx_audio_div_ops, \ - 0), \ - .id = _id, \ -} - -struct clk *clk_register_zx_pll(const char *name, const char *parent_name, - unsigned long flags, void __iomem *reg_base, - const struct zx_pll_config *lookup_table, int count, spinlock_t *lock); - -struct clk_zx_audio { - struct clk_hw hw; - void __iomem *reg_base; -}; - -struct clk *clk_register_zx_audio(const char *name, - const char * const parent_name, - unsigned long flags, void __iomem *reg_base); - -extern const struct clk_ops zx_pll_ops; -extern const struct clk_ops zx_audio_div_ops; - -#endif diff --git a/include/dt-bindings/clock/zx296702-clock.h b/include/dt-bindings/clock/zx296702-clock.h deleted file mode 100644 index e04126111aae..000000000000 --- a/include/dt-bindings/clock/zx296702-clock.h +++ /dev/null @@ -1,180 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright 2014 Linaro Ltd. - * Copyright (C) 2014 ZTE Corporation. - */ - -#ifndef __DT_BINDINGS_CLOCK_ZX296702_H -#define __DT_BINDINGS_CLOCK_ZX296702_H - -#define ZX296702_OSC 0 -#define ZX296702_PLL_A9 1 -#define ZX296702_PLL_A9_350M 2 -#define ZX296702_PLL_MAC_1000M 3 -#define ZX296702_PLL_MAC_333M 4 -#define ZX296702_PLL_MM0_1188M 5 -#define ZX296702_PLL_MM0_396M 6 -#define ZX296702_PLL_MM0_198M 7 -#define ZX296702_PLL_MM1_108M 8 -#define ZX296702_PLL_MM1_72M 9 -#define ZX296702_PLL_MM1_54M 10 -#define ZX296702_PLL_LSP_104M 11 -#define ZX296702_PLL_LSP_26M 12 -#define ZX296702_PLL_AUDIO_294M912 13 -#define ZX296702_PLL_DDR_266M 14 -#define ZX296702_CLK_148M5 15 -#define ZX296702_MATRIX_ACLK 16 -#define ZX296702_MAIN_HCLK 17 -#define ZX296702_MAIN_PCLK 18 -#define ZX296702_CLK_500 19 -#define ZX296702_CLK_250 20 -#define ZX296702_CLK_125 21 -#define ZX296702_CLK_74M25 22 -#define ZX296702_A9_WCLK 23 -#define ZX296702_A9_AS1_ACLK_MUX 24 -#define ZX296702_A9_TRACE_CLKIN_MUX 25 -#define ZX296702_A9_AS1_ACLK_DIV 26 -#define ZX296702_CLK_2 27 -#define ZX296702_CLK_27 28 -#define ZX296702_DECPPU_ACLK_MUX 29 -#define ZX296702_PPU_ACLK_MUX 30 -#define ZX296702_MALI400_ACLK_MUX 31 -#define ZX296702_VOU_ACLK_MUX 32 -#define ZX296702_VOU_MAIN_WCLK_MUX 33 -#define ZX296702_VOU_AUX_WCLK_MUX 34 -#define ZX296702_VOU_SCALER_WCLK_MUX 35 -#define ZX296702_R2D_ACLK_MUX 36 -#define ZX296702_R2D_WCLK_MUX 37 -#define ZX296702_CLK_50 38 -#define ZX296702_CLK_25 39 -#define ZX296702_CLK_12 40 -#define ZX296702_CLK_16M384 41 -#define ZX296702_CLK_32K768 42 -#define ZX296702_SEC_WCLK_DIV 43 -#define ZX296702_DDR_WCLK_MUX 44 -#define ZX296702_NAND_WCLK_MUX 45 -#define ZX296702_LSP_26_WCLK_MUX 46 -#define ZX296702_A9_AS0_ACLK 47 -#define ZX296702_A9_AS1_ACLK 48 -#define ZX296702_A9_TRACE_CLKIN 49 -#define ZX296702_DECPPU_AXI_M_ACLK 50 -#define ZX296702_DECPPU_AHB_S_HCLK 51 -#define ZX296702_PPU_AXI_M_ACLK 52 -#define ZX296702_PPU_AHB_S_HCLK 53 -#define ZX296702_VOU_AXI_M_ACLK 54 -#define ZX296702_VOU_APB_PCLK 55 -#define ZX296702_VOU_MAIN_CHANNEL_WCLK 56 -#define ZX296702_VOU_AUX_CHANNEL_WCLK 57 -#define ZX296702_VOU_HDMI_OSCLK_CEC 58 -#define ZX296702_VOU_SCALER_WCLK 59 -#define ZX296702_MALI400_AXI_M_ACLK 60 -#define ZX296702_MALI400_APB_PCLK 61 -#define ZX296702_R2D_WCLK 62 -#define ZX296702_R2D_AXI_M_ACLK 63 -#define ZX296702_R2D_AHB_HCLK 64 -#define ZX296702_DDR3_AXI_S0_ACLK 65 -#define ZX296702_DDR3_APB_PCLK 66 -#define ZX296702_DDR3_WCLK 67 -#define ZX296702_USB20_0_AHB_HCLK 68 -#define ZX296702_USB20_0_EXTREFCLK 69 -#define ZX296702_USB20_1_AHB_HCLK 70 -#define ZX296702_USB20_1_EXTREFCLK 71 -#define ZX296702_USB20_2_AHB_HCLK 72 -#define ZX296702_USB20_2_EXTREFCLK 73 -#define ZX296702_GMAC_AXI_M_ACLK 74 -#define ZX296702_GMAC_APB_PCLK 75 -#define ZX296702_GMAC_125_CLKIN 76 -#define ZX296702_GMAC_RMII_CLKIN 77 -#define ZX296702_GMAC_25M_CLK 78 -#define ZX296702_NANDFLASH_AHB_HCLK 79 -#define ZX296702_NANDFLASH_WCLK 80 -#define ZX296702_LSP0_APB_PCLK 81 -#define ZX296702_LSP0_AHB_HCLK 82 -#define ZX296702_LSP0_26M_WCLK 83 -#define ZX296702_LSP0_104M_WCLK 84 -#define ZX296702_LSP0_16M384_WCLK 85 -#define ZX296702_LSP1_APB_PCLK 86 -#define ZX296702_LSP1_26M_WCLK 87 -#define ZX296702_LSP1_104M_WCLK 88 -#define ZX296702_LSP1_32K_CLK 89 -#define ZX296702_AON_HCLK 90 -#define ZX296702_SYS_CTRL_PCLK 91 -#define ZX296702_DMA_PCLK 92 -#define ZX296702_DMA_ACLK 93 -#define ZX296702_SEC_HCLK 94 -#define ZX296702_AES_WCLK 95 -#define ZX296702_DES_WCLK 96 -#define ZX296702_IRAM_ACLK 97 -#define ZX296702_IROM_ACLK 98 -#define ZX296702_BOOT_CTRL_HCLK 99 -#define ZX296702_EFUSE_CLK_30 100 -#define ZX296702_VOU_MAIN_CHANNEL_DIV 101 -#define ZX296702_VOU_AUX_CHANNEL_DIV 102 -#define ZX296702_VOU_TV_ENC_HD_DIV 103 -#define ZX296702_VOU_TV_ENC_SD_DIV 104 -#define ZX296702_VL0_MUX 105 -#define ZX296702_VL1_MUX 106 -#define ZX296702_VL2_MUX 107 -#define ZX296702_GL0_MUX 108 -#define ZX296702_GL1_MUX 109 -#define ZX296702_GL2_MUX 110 -#define ZX296702_WB_MUX 111 -#define ZX296702_HDMI_MUX 112 -#define ZX296702_VOU_TV_ENC_HD_MUX 113 -#define ZX296702_VOU_TV_ENC_SD_MUX 114 -#define ZX296702_VL0_CLK 115 -#define ZX296702_VL1_CLK 116 -#define ZX296702_VL2_CLK 117 -#define ZX296702_GL0_CLK 118 -#define ZX296702_GL1_CLK 119 -#define ZX296702_GL2_CLK 120 -#define ZX296702_WB_CLK 121 -#define ZX296702_CL_CLK 122 -#define ZX296702_MAIN_MIX_CLK 123 -#define ZX296702_AUX_MIX_CLK 124 -#define ZX296702_HDMI_CLK 125 -#define ZX296702_VOU_TV_ENC_HD_DAC_CLK 126 -#define ZX296702_VOU_TV_ENC_SD_DAC_CLK 127 -#define ZX296702_A9_PERIPHCLK 128 -#define ZX296702_TOPCLK_END 129 - -#define ZX296702_SDMMC1_WCLK_MUX 0 -#define ZX296702_SDMMC1_WCLK_DIV 1 -#define ZX296702_SDMMC1_WCLK 2 -#define ZX296702_SDMMC1_PCLK 3 -#define ZX296702_SPDIF0_WCLK_MUX 4 -#define ZX296702_SPDIF0_WCLK 5 -#define ZX296702_SPDIF0_PCLK 6 -#define ZX296702_SPDIF0_DIV 7 -#define ZX296702_I2S0_WCLK_MUX 8 -#define ZX296702_I2S0_WCLK 9 -#define ZX296702_I2S0_PCLK 10 -#define ZX296702_I2S0_DIV 11 -#define ZX296702_I2S1_WCLK_MUX 12 -#define ZX296702_I2S1_WCLK 13 -#define ZX296702_I2S1_PCLK 14 -#define ZX296702_I2S1_DIV 15 -#define ZX296702_I2S2_WCLK_MUX 16 -#define ZX296702_I2S2_WCLK 17 -#define ZX296702_I2S2_PCLK 18 -#define ZX296702_I2S2_DIV 19 -#define ZX296702_GPIO_CLK 20 -#define ZX296702_LSP0CLK_END 21 - -#define ZX296702_UART0_WCLK_MUX 0 -#define ZX296702_UART0_WCLK 1 -#define ZX296702_UART0_PCLK 2 -#define ZX296702_UART1_WCLK_MUX 3 -#define ZX296702_UART1_WCLK 4 -#define ZX296702_UART1_PCLK 5 -#define ZX296702_SDMMC0_WCLK_MUX 6 -#define ZX296702_SDMMC0_WCLK_DIV 7 -#define ZX296702_SDMMC0_WCLK 8 -#define ZX296702_SDMMC0_PCLK 9 -#define ZX296702_SPDIF1_WCLK_MUX 10 -#define ZX296702_SPDIF1_WCLK 11 -#define ZX296702_SPDIF1_PCLK 12 -#define ZX296702_SPDIF1_DIV 13 -#define ZX296702_LSP1CLK_END 14 - -#endif /* __DT_BINDINGS_CLOCK_ZX296702_H */ -- cgit v1.2.3 From ee7294ba49bf8559b560b21629ed8153082c25cf Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 20 Jan 2021 14:10:26 +0100 Subject: clk: remove u300 driver The ST-Ericsson U300 platform is getting removed, so this driver is no longer needed. Cc: Linus Walleij Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20210120131026.1721788-5-arnd@kernel.org Reviewed-by: Linus Walleij Signed-off-by: Stephen Boyd --- .../bindings/clock/ste-u300-syscon-clock.txt | 80 -- drivers/clk/Makefile | 1 - drivers/clk/clk-u300.c | 1199 -------------------- include/linux/platform_data/clk-u300.h | 1 - 4 files changed, 1281 deletions(-) delete mode 100644 Documentation/devicetree/bindings/clock/ste-u300-syscon-clock.txt delete mode 100644 drivers/clk/clk-u300.c delete mode 100644 include/linux/platform_data/clk-u300.h (limited to 'include') diff --git a/Documentation/devicetree/bindings/clock/ste-u300-syscon-clock.txt b/Documentation/devicetree/bindings/clock/ste-u300-syscon-clock.txt deleted file mode 100644 index 7cafcb98ead7..000000000000 --- a/Documentation/devicetree/bindings/clock/ste-u300-syscon-clock.txt +++ /dev/null @@ -1,80 +0,0 @@ -Clock bindings for ST-Ericsson U300 System Controller Clocks - -Bindings for the gated system controller clocks: - -Required properties: -- compatible: must be "stericsson,u300-syscon-clk" -- #clock-cells: must be <0> -- clock-type: specifies the type of clock: - 0 = slow clock - 1 = fast clock - 2 = rest/remaining clock -- clock-id: specifies the clock in the type range - -Optional properties: -- clocks: parent clock(s) - -The available clocks per type are as follows: - -Type: ID: Clock: -------------------- -0 0 Slow peripheral bridge clock -0 1 UART0 clock -0 4 GPIO clock -0 6 RTC clock -0 7 Application timer clock -0 8 Access timer clock - -1 0 Fast peripheral bridge clock -1 1 I2C bus 0 clock -1 2 I2C bus 1 clock -1 5 MMC interface peripheral (silicon) clock -1 6 SPI clock - -2 3 CPU clock -2 4 DMA controller clock -2 5 External Memory Interface (EMIF) clock -2 6 NAND flask interface clock -2 8 XGAM graphics engine clock -2 9 Shared External Memory Interface (SEMI) clock -2 10 AHB Subsystem Bridge clock -2 12 Interrupt controller clock - -Example: - -gpio_clk: gpio_clk@13M { - #clock-cells = <0>; - compatible = "stericsson,u300-syscon-clk"; - clock-type = <0>; /* Slow */ - clock-id = <4>; - clocks = <&slow_clk>; -}; - -gpio: gpio@c0016000 { - compatible = "stericsson,gpio-coh901"; - (...) - clocks = <&gpio_clk>; -}; - - -Bindings for the MMC/SD card clock: - -Required properties: -- compatible: must be "stericsson,u300-syscon-mclk" -- #clock-cells: must be <0> - -Optional properties: -- clocks: parent clock(s) - -mmc_mclk: mmc_mclk { - #clock-cells = <0>; - compatible = "stericsson,u300-syscon-mclk"; - clocks = <&mmc_pclk>; -}; - -mmcsd: mmcsd@c0001000 { - compatible = "arm,pl18x", "arm,primecell"; - clocks = <&mmc_pclk>, <&mmc_mclk>; - clock-names = "apb_pclk", "mclk"; - (...) -}; diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile index 663414cef29a..2e4fc98ca1db 100644 --- a/drivers/clk/Makefile +++ b/drivers/clk/Makefile @@ -63,7 +63,6 @@ obj-$(CONFIG_COMMON_CLK_STM32F) += clk-stm32f4.o obj-$(CONFIG_COMMON_CLK_STM32H7) += clk-stm32h7.o obj-$(CONFIG_COMMON_CLK_STM32MP157) += clk-stm32mp1.o obj-$(CONFIG_CLK_TWL6040) += clk-twl6040.o -obj-$(CONFIG_ARCH_U300) += clk-u300.o obj-$(CONFIG_ARCH_VT8500) += clk-vt8500.o obj-$(CONFIG_COMMON_CLK_VC5) += clk-versaclock5.o obj-$(CONFIG_COMMON_CLK_WM831X) += clk-wm831x.o diff --git a/drivers/clk/clk-u300.c b/drivers/clk/clk-u300.c deleted file mode 100644 index e228c07c4c6e..000000000000 --- a/drivers/clk/clk-u300.c +++ /dev/null @@ -1,1199 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * U300 clock implementation - * Copyright (C) 2007-2012 ST-Ericsson AB - * Author: Linus Walleij - * Author: Jonas Aaberg - */ -#include -#include -#include -#include -#include -#include -#include -#include - -/* APP side SYSCON registers */ -/* CLK Control Register 16bit (R/W) */ -#define U300_SYSCON_CCR (0x0000) -#define U300_SYSCON_CCR_I2S1_USE_VCXO (0x0040) -#define U300_SYSCON_CCR_I2S0_USE_VCXO (0x0020) -#define U300_SYSCON_CCR_TURN_VCXO_ON (0x0008) -#define U300_SYSCON_CCR_CLKING_PERFORMANCE_MASK (0x0007) -#define U300_SYSCON_CCR_CLKING_PERFORMANCE_LOW_POWER (0x04) -#define U300_SYSCON_CCR_CLKING_PERFORMANCE_LOW (0x03) -#define U300_SYSCON_CCR_CLKING_PERFORMANCE_INTERMEDIATE (0x02) -#define U300_SYSCON_CCR_CLKING_PERFORMANCE_HIGH (0x01) -#define U300_SYSCON_CCR_CLKING_PERFORMANCE_BEST (0x00) -/* CLK Status Register 16bit (R/W) */ -#define U300_SYSCON_CSR (0x0004) -#define U300_SYSCON_CSR_PLL208_LOCK_IND (0x0002) -#define U300_SYSCON_CSR_PLL13_LOCK_IND (0x0001) -/* Reset lines for SLOW devices 16bit (R/W) */ -#define U300_SYSCON_RSR (0x0014) -#define U300_SYSCON_RSR_PPM_RESET_EN (0x0200) -#define U300_SYSCON_RSR_ACC_TMR_RESET_EN (0x0100) -#define U300_SYSCON_RSR_APP_TMR_RESET_EN (0x0080) -#define U300_SYSCON_RSR_RTC_RESET_EN (0x0040) -#define U300_SYSCON_RSR_KEYPAD_RESET_EN (0x0020) -#define U300_SYSCON_RSR_GPIO_RESET_EN (0x0010) -#define U300_SYSCON_RSR_EH_RESET_EN (0x0008) -#define U300_SYSCON_RSR_BTR_RESET_EN (0x0004) -#define U300_SYSCON_RSR_UART_RESET_EN (0x0002) -#define U300_SYSCON_RSR_SLOW_BRIDGE_RESET_EN (0x0001) -/* Reset lines for FAST devices 16bit (R/W) */ -#define U300_SYSCON_RFR (0x0018) -#define U300_SYSCON_RFR_UART1_RESET_ENABLE (0x0080) -#define U300_SYSCON_RFR_SPI_RESET_ENABLE (0x0040) -#define U300_SYSCON_RFR_MMC_RESET_ENABLE (0x0020) -#define U300_SYSCON_RFR_PCM_I2S1_RESET_ENABLE (0x0010) -#define U300_SYSCON_RFR_PCM_I2S0_RESET_ENABLE (0x0008) -#define U300_SYSCON_RFR_I2C1_RESET_ENABLE (0x0004) -#define U300_SYSCON_RFR_I2C0_RESET_ENABLE (0x0002) -#define U300_SYSCON_RFR_FAST_BRIDGE_RESET_ENABLE (0x0001) -/* Reset lines for the rest of the peripherals 16bit (R/W) */ -#define U300_SYSCON_RRR (0x001c) -#define U300_SYSCON_RRR_CDS_RESET_EN (0x4000) -#define U300_SYSCON_RRR_ISP_RESET_EN (0x2000) -#define U300_SYSCON_RRR_INTCON_RESET_EN (0x1000) -#define U300_SYSCON_RRR_MSPRO_RESET_EN (0x0800) -#define U300_SYSCON_RRR_XGAM_RESET_EN (0x0100) -#define U300_SYSCON_RRR_XGAM_VC_SYNC_RESET_EN (0x0080) -#define U300_SYSCON_RRR_NANDIF_RESET_EN (0x0040) -#define U300_SYSCON_RRR_EMIF_RESET_EN (0x0020) -#define U300_SYSCON_RRR_DMAC_RESET_EN (0x0010) -#define U300_SYSCON_RRR_CPU_RESET_EN (0x0008) -#define U300_SYSCON_RRR_APEX_RESET_EN (0x0004) -#define U300_SYSCON_RRR_AHB_RESET_EN (0x0002) -#define U300_SYSCON_RRR_AAIF_RESET_EN (0x0001) -/* Clock enable for SLOW peripherals 16bit (R/W) */ -#define U300_SYSCON_CESR (0x0020) -#define U300_SYSCON_CESR_PPM_CLK_EN (0x0200) -#define U300_SYSCON_CESR_ACC_TMR_CLK_EN (0x0100) -#define U300_SYSCON_CESR_APP_TMR_CLK_EN (0x0080) -#define U300_SYSCON_CESR_KEYPAD_CLK_EN (0x0040) -#define U300_SYSCON_CESR_GPIO_CLK_EN (0x0010) -#define U300_SYSCON_CESR_EH_CLK_EN (0x0008) -#define U300_SYSCON_CESR_BTR_CLK_EN (0x0004) -#define U300_SYSCON_CESR_UART_CLK_EN (0x0002) -#define U300_SYSCON_CESR_SLOW_BRIDGE_CLK_EN (0x0001) -/* Clock enable for FAST peripherals 16bit (R/W) */ -#define U300_SYSCON_CEFR (0x0024) -#define U300_SYSCON_CEFR_UART1_CLK_EN (0x0200) -#define U300_SYSCON_CEFR_I2S1_CORE_CLK_EN (0x0100) -#define U300_SYSCON_CEFR_I2S0_CORE_CLK_EN (0x0080) -#define U300_SYSCON_CEFR_SPI_CLK_EN (0x0040) -#define U300_SYSCON_CEFR_MMC_CLK_EN (0x0020) -#define U300_SYSCON_CEFR_I2S1_CLK_EN (0x0010) -#define U300_SYSCON_CEFR_I2S0_CLK_EN (0x0008) -#define U300_SYSCON_CEFR_I2C1_CLK_EN (0x0004) -#define U300_SYSCON_CEFR_I2C0_CLK_EN (0x0002) -#define U300_SYSCON_CEFR_FAST_BRIDGE_CLK_EN (0x0001) -/* Clock enable for the rest of the peripherals 16bit (R/W) */ -#define U300_SYSCON_CERR (0x0028) -#define U300_SYSCON_CERR_CDS_CLK_EN (0x2000) -#define U300_SYSCON_CERR_ISP_CLK_EN (0x1000) -#define U300_SYSCON_CERR_MSPRO_CLK_EN (0x0800) -#define U300_SYSCON_CERR_AHB_SUBSYS_BRIDGE_CLK_EN (0x0400) -#define U300_SYSCON_CERR_SEMI_CLK_EN (0x0200) -#define U300_SYSCON_CERR_XGAM_CLK_EN (0x0100) -#define U300_SYSCON_CERR_VIDEO_ENC_CLK_EN (0x0080) -#define U300_SYSCON_CERR_NANDIF_CLK_EN (0x0040) -#define U300_SYSCON_CERR_EMIF_CLK_EN (0x0020) -#define U300_SYSCON_CERR_DMAC_CLK_EN (0x0010) -#define U300_SYSCON_CERR_CPU_CLK_EN (0x0008) -#define U300_SYSCON_CERR_APEX_CLK_EN (0x0004) -#define U300_SYSCON_CERR_AHB_CLK_EN (0x0002) -#define U300_SYSCON_CERR_AAIF_CLK_EN (0x0001) -/* Single block clock enable 16bit (-/W) */ -#define U300_SYSCON_SBCER (0x002c) -#define U300_SYSCON_SBCER_PPM_CLK_EN (0x0009) -#define U300_SYSCON_SBCER_ACC_TMR_CLK_EN (0x0008) -#define U300_SYSCON_SBCER_APP_TMR_CLK_EN (0x0007) -#define U300_SYSCON_SBCER_KEYPAD_CLK_EN (0x0006) -#define U300_SYSCON_SBCER_GPIO_CLK_EN (0x0004) -#define U300_SYSCON_SBCER_EH_CLK_EN (0x0003) -#define U300_SYSCON_SBCER_BTR_CLK_EN (0x0002) -#define U300_SYSCON_SBCER_UART_CLK_EN (0x0001) -#define U300_SYSCON_SBCER_SLOW_BRIDGE_CLK_EN (0x0000) -#define U300_SYSCON_SBCER_UART1_CLK_EN (0x0019) -#define U300_SYSCON_SBCER_I2S1_CORE_CLK_EN (0x0018) -#define U300_SYSCON_SBCER_I2S0_CORE_CLK_EN (0x0017) -#define U300_SYSCON_SBCER_SPI_CLK_EN (0x0016) -#define U300_SYSCON_SBCER_MMC_CLK_EN (0x0015) -#define U300_SYSCON_SBCER_I2S1_CLK_EN (0x0014) -#define U300_SYSCON_SBCER_I2S0_CLK_EN (0x0013) -#define U300_SYSCON_SBCER_I2C1_CLK_EN (0x0012) -#define U300_SYSCON_SBCER_I2C0_CLK_EN (0x0011) -#define U300_SYSCON_SBCER_FAST_BRIDGE_CLK_EN (0x0010) -#define U300_SYSCON_SBCER_CDS_CLK_EN (0x002D) -#define U300_SYSCON_SBCER_ISP_CLK_EN (0x002C) -#define U300_SYSCON_SBCER_MSPRO_CLK_EN (0x002B) -#define U300_SYSCON_SBCER_AHB_SUBSYS_BRIDGE_CLK_EN (0x002A) -#define U300_SYSCON_SBCER_SEMI_CLK_EN (0x0029) -#define U300_SYSCON_SBCER_XGAM_CLK_EN (0x0028) -#define U300_SYSCON_SBCER_VIDEO_ENC_CLK_EN (0x0027) -#define U300_SYSCON_SBCER_NANDIF_CLK_EN (0x0026) -#define U300_SYSCON_SBCER_EMIF_CLK_EN (0x0025) -#define U300_SYSCON_SBCER_DMAC_CLK_EN (0x0024) -#define U300_SYSCON_SBCER_CPU_CLK_EN (0x0023) -#define U300_SYSCON_SBCER_APEX_CLK_EN (0x0022) -#define U300_SYSCON_SBCER_AHB_CLK_EN (0x0021) -#define U300_SYSCON_SBCER_AAIF_CLK_EN (0x0020) -/* Single block clock disable 16bit (-/W) */ -#define U300_SYSCON_SBCDR (0x0030) -/* Same values as above for SBCER */ -/* Clock force SLOW peripherals 16bit (R/W) */ -#define U300_SYSCON_CFSR (0x003c) -#define U300_SYSCON_CFSR_PPM_CLK_FORCE_EN (0x0200) -#define U300_SYSCON_CFSR_ACC_TMR_CLK_FORCE_EN (0x0100) -#define U300_SYSCON_CFSR_APP_TMR_CLK_FORCE_EN (0x0080) -#define U300_SYSCON_CFSR_KEYPAD_CLK_FORCE_EN (0x0020) -#define U300_SYSCON_CFSR_GPIO_CLK_FORCE_EN (0x0010) -#define U300_SYSCON_CFSR_EH_CLK_FORCE_EN (0x0008) -#define U300_SYSCON_CFSR_BTR_CLK_FORCE_EN (0x0004) -#define U300_SYSCON_CFSR_UART_CLK_FORCE_EN (0x0002) -#define U300_SYSCON_CFSR_SLOW_BRIDGE_CLK_FORCE_EN (0x0001) -/* Clock force FAST peripherals 16bit (R/W) */ -#define U300_SYSCON_CFFR (0x40) -/* Values not defined. Define if you want to use them. */ -/* Clock force the rest of the peripherals 16bit (R/W) */ -#define U300_SYSCON_CFRR (0x44) -#define U300_SYSCON_CFRR_CDS_CLK_FORCE_EN (0x2000) -#define U300_SYSCON_CFRR_ISP_CLK_FORCE_EN (0x1000) -#define U300_SYSCON_CFRR_MSPRO_CLK_FORCE_EN (0x0800) -#define U300_SYSCON_CFRR_AHB_SUBSYS_BRIDGE_CLK_FORCE_EN (0x0400) -#define U300_SYSCON_CFRR_SEMI_CLK_FORCE_EN (0x0200) -#define U300_SYSCON_CFRR_XGAM_CLK_FORCE_EN (0x0100) -#define U300_SYSCON_CFRR_VIDEO_ENC_CLK_FORCE_EN (0x0080) -#define U300_SYSCON_CFRR_NANDIF_CLK_FORCE_EN (0x0040) -#define U300_SYSCON_CFRR_EMIF_CLK_FORCE_EN (0x0020) -#define U300_SYSCON_CFRR_DMAC_CLK_FORCE_EN (0x0010) -#define U300_SYSCON_CFRR_CPU_CLK_FORCE_EN (0x0008) -#define U300_SYSCON_CFRR_APEX_CLK_FORCE_EN (0x0004) -#define U300_SYSCON_CFRR_AHB_CLK_FORCE_EN (0x0002) -#define U300_SYSCON_CFRR_AAIF_CLK_FORCE_EN (0x0001) -/* PLL208 Frequency Control 16bit (R/W) */ -#define U300_SYSCON_PFCR (0x48) -#define U300_SYSCON_PFCR_DPLL_MULT_NUM (0x000F) -/* Power Management Control 16bit (R/W) */ -#define U300_SYSCON_PMCR (0x50) -#define U300_SYSCON_PMCR_DCON_ENABLE (0x0002) -#define U300_SYSCON_PMCR_PWR_MGNT_ENABLE (0x0001) -/* Reset Out 16bit (R/W) */ -#define U300_SYSCON_RCR (0x6c) -#define U300_SYSCON_RCR_RESOUT0_RST_N_DISABLE (0x0001) -/* EMIF Slew Rate Control 16bit (R/W) */ -#define U300_SYSCON_SRCLR (0x70) -#define U300_SYSCON_SRCLR_MASK (0x03FF) -#define U300_SYSCON_SRCLR_VALUE (0x03FF) -#define U300_SYSCON_SRCLR_EMIF_1_SLRC_5_B (0x0200) -#define U300_SYSCON_SRCLR_EMIF_1_SLRC_5_A (0x0100) -#define U300_SYSCON_SRCLR_EMIF_1_SLRC_4_B (0x0080) -#define U300_SYSCON_SRCLR_EMIF_1_SLRC_4_A (0x0040) -#define U300_SYSCON_SRCLR_EMIF_1_SLRC_3_B (0x0020) -#define U300_SYSCON_SRCLR_EMIF_1_SLRC_3_A (0x0010) -#define U300_SYSCON_SRCLR_EMIF_1_SLRC_2_B (0x0008) -#define U300_SYSCON_SRCLR_EMIF_1_SLRC_2_A (0x0004) -#define U300_SYSCON_SRCLR_EMIF_1_SLRC_1_B (0x0002) -#define U300_SYSCON_SRCLR_EMIF_1_SLRC_1_A (0x0001) -/* EMIF Clock Control Register 16bit (R/W) */ -#define U300_SYSCON_ECCR (0x0078) -#define U300_SYSCON_ECCR_MASK (0x000F) -#define U300_SYSCON_ECCR_EMIF_1_STATIC_CLK_EN_N_DISABLE (0x0008) -#define U300_SYSCON_ECCR_EMIF_1_RET_OUT_CLK_EN_N_DISABLE (0x0004) -#define U300_SYSCON_ECCR_EMIF_MEMCLK_RET_EN_N_DISABLE (0x0002) -#define U300_SYSCON_ECCR_EMIF_SDRCLK_RET_EN_N_DISABLE (0x0001) -/* MMC/MSPRO frequency divider register 0 16bit (R/W) */ -#define U300_SYSCON_MMF0R (0x90) -#define U300_SYSCON_MMF0R_MASK (0x00FF) -#define U300_SYSCON_MMF0R_FREQ_0_HIGH_MASK (0x00F0) -#define U300_SYSCON_MMF0R_FREQ_0_LOW_MASK (0x000F) -/* MMC/MSPRO frequency divider register 1 16bit (R/W) */ -#define U300_SYSCON_MMF1R (0x94) -#define U300_SYSCON_MMF1R_MASK (0x00FF) -#define U300_SYSCON_MMF1R_FREQ_1_HIGH_MASK (0x00F0) -#define U300_SYSCON_MMF1R_FREQ_1_LOW_MASK (0x000F) -/* Clock control for the MMC and MSPRO blocks 16bit (R/W) */ -#define U300_SYSCON_MMCR (0x9C) -#define U300_SYSCON_MMCR_MASK (0x0003) -#define U300_SYSCON_MMCR_MMC_FB_CLK_SEL_ENABLE (0x0002) -#define U300_SYSCON_MMCR_MSPRO_FREQSEL_ENABLE (0x0001) -/* SYS_0_CLK_CONTROL first clock control 16bit (R/W) */ -#define U300_SYSCON_S0CCR (0x120) -#define U300_SYSCON_S0CCR_FIELD_MASK (0x43FF) -#define U300_SYSCON_S0CCR_CLOCK_REQ (0x4000) -#define U300_SYSCON_S0CCR_CLOCK_REQ_MONITOR (0x2000) -#define U300_SYSCON_S0CCR_CLOCK_INV (0x0200) -#define U300_SYSCON_S0CCR_CLOCK_FREQ_MASK (0x01E0) -#define U300_SYSCON_S0CCR_CLOCK_SELECT_MASK (0x001E) -#define U300_SYSCON_S0CCR_CLOCK_ENABLE (0x0001) -#define U300_SYSCON_S0CCR_SEL_MCLK (0x8 << 1) -#define U300_SYSCON_S0CCR_SEL_ACC_FSM_CLK (0xA << 1) -#define U300_SYSCON_S0CCR_SEL_PLL60_48_CLK (0xC << 1) -#define U300_SYSCON_S0CCR_SEL_PLL60_60_CLK (0xD << 1) -#define U300_SYSCON_S0CCR_SEL_ACC_PLL208_CLK (0xE << 1) -#define U300_SYSCON_S0CCR_SEL_APP_PLL13_CLK (0x0 << 1) -#define U300_SYSCON_S0CCR_SEL_APP_FSM_CLK (0x2 << 1) -#define U300_SYSCON_S0CCR_SEL_RTC_CLK (0x4 << 1) -#define U300_SYSCON_S0CCR_SEL_APP_PLL208_CLK (0x6 << 1) -/* SYS_1_CLK_CONTROL second clock control 16 bit (R/W) */ -#define U300_SYSCON_S1CCR (0x124) -#define U300_SYSCON_S1CCR_FIELD_MASK (0x43FF) -#define U300_SYSCON_S1CCR_CLOCK_REQ (0x4000) -#define U300_SYSCON_S1CCR_CLOCK_REQ_MONITOR (0x2000) -#define U300_SYSCON_S1CCR_CLOCK_INV (0x0200) -#define U300_SYSCON_S1CCR_CLOCK_FREQ_MASK (0x01E0) -#define U300_SYSCON_S1CCR_CLOCK_SELECT_MASK (0x001E) -#define U300_SYSCON_S1CCR_CLOCK_ENABLE (0x0001) -#define U300_SYSCON_S1CCR_SEL_MCLK (0x8 << 1) -#define U300_SYSCON_S1CCR_SEL_ACC_FSM_CLK (0xA << 1) -#define U300_SYSCON_S1CCR_SEL_PLL60_48_CLK (0xC << 1) -#define U300_SYSCON_S1CCR_SEL_PLL60_60_CLK (0xD << 1) -#define U300_SYSCON_S1CCR_SEL_ACC_PLL208_CLK (0xE << 1) -#define U300_SYSCON_S1CCR_SEL_ACC_PLL13_CLK (0x0 << 1) -#define U300_SYSCON_S1CCR_SEL_APP_FSM_CLK (0x2 << 1) -#define U300_SYSCON_S1CCR_SEL_RTC_CLK (0x4 << 1) -#define U300_SYSCON_S1CCR_SEL_APP_PLL208_CLK (0x6 << 1) -/* SYS_2_CLK_CONTROL third clock control 16 bit (R/W) */ -#define U300_SYSCON_S2CCR (0x128) -#define U300_SYSCON_S2CCR_FIELD_MASK (0xC3FF) -#define U300_SYSCON_S2CCR_CLK_STEAL (0x8000) -#define U300_SYSCON_S2CCR_CLOCK_REQ (0x4000) -#define U300_SYSCON_S2CCR_CLOCK_REQ_MONITOR (0x2000) -#define U300_SYSCON_S2CCR_CLOCK_INV (0x0200) -#define U300_SYSCON_S2CCR_CLOCK_FREQ_MASK (0x01E0) -#define U300_SYSCON_S2CCR_CLOCK_SELECT_MASK (0x001E) -#define U300_SYSCON_S2CCR_CLOCK_ENABLE (0x0001) -#define U300_SYSCON_S2CCR_SEL_MCLK (0x8 << 1) -#define U300_SYSCON_S2CCR_SEL_ACC_FSM_CLK (0xA << 1) -#define U300_SYSCON_S2CCR_SEL_PLL60_48_CLK (0xC << 1) -#define U300_SYSCON_S2CCR_SEL_PLL60_60_CLK (0xD << 1) -#define U300_SYSCON_S2CCR_SEL_ACC_PLL208_CLK (0xE << 1) -#define U300_SYSCON_S2CCR_SEL_ACC_PLL13_CLK (0x0 << 1) -#define U300_SYSCON_S2CCR_SEL_APP_FSM_CLK (0x2 << 1) -#define U300_SYSCON_S2CCR_SEL_RTC_CLK (0x4 << 1) -#define U300_SYSCON_S2CCR_SEL_APP_PLL208_CLK (0x6 << 1) -/* SC_PLL_IRQ_CONTROL 16bit (R/W) */ -#define U300_SYSCON_PICR (0x0130) -#define U300_SYSCON_PICR_MASK (0x00FF) -#define U300_SYSCON_PICR_FORCE_PLL208_LOCK_LOW_ENABLE (0x0080) -#define U300_SYSCON_PICR_FORCE_PLL208_LOCK_HIGH_ENABLE (0x0040) -#define U300_SYSCON_PICR_FORCE_PLL13_LOCK_LOW_ENABLE (0x0020) -#define U300_SYSCON_PICR_FORCE_PLL13_LOCK_HIGH_ENABLE (0x0010) -#define U300_SYSCON_PICR_IRQMASK_PLL13_UNLOCK_ENABLE (0x0008) -#define U300_SYSCON_PICR_IRQMASK_PLL13_LOCK_ENABLE (0x0004) -#define U300_SYSCON_PICR_IRQMASK_PLL208_UNLOCK_ENABLE (0x0002) -#define U300_SYSCON_PICR_IRQMASK_PLL208_LOCK_ENABLE (0x0001) -/* SC_PLL_IRQ_STATUS 16 bit (R/-) */ -#define U300_SYSCON_PISR (0x0134) -#define U300_SYSCON_PISR_MASK (0x000F) -#define U300_SYSCON_PISR_PLL13_UNLOCK_IND (0x0008) -#define U300_SYSCON_PISR_PLL13_LOCK_IND (0x0004) -#define U300_SYSCON_PISR_PLL208_UNLOCK_IND (0x0002) -#define U300_SYSCON_PISR_PLL208_LOCK_IND (0x0001) -/* SC_PLL_IRQ_CLEAR 16 bit (-/W) */ -#define U300_SYSCON_PICLR (0x0138) -#define U300_SYSCON_PICLR_MASK (0x000F) -#define U300_SYSCON_PICLR_RWMASK (0x0000) -#define U300_SYSCON_PICLR_PLL13_UNLOCK_SC (0x0008) -#define U300_SYSCON_PICLR_PLL13_LOCK_SC (0x0004) -#define U300_SYSCON_PICLR_PLL208_UNLOCK_SC (0x0002) -#define U300_SYSCON_PICLR_PLL208_LOCK_SC (0x0001) -/* Clock activity observability register 0 */ -#define U300_SYSCON_C0OAR (0x140) -#define U300_SYSCON_C0OAR_MASK (0xFFFF) -#define U300_SYSCON_C0OAR_VALUE (0xFFFF) -#define U300_SYSCON_C0OAR_BT_H_CLK (0x8000) -#define U300_SYSCON_C0OAR_ASPB_P_CLK (0x4000) -#define U300_SYSCON_C0OAR_APP_SEMI_H_CLK (0x2000) -#define U300_SYSCON_C0OAR_APP_SEMI_CLK (0x1000) -#define U300_SYSCON_C0OAR_APP_MMC_MSPRO_CLK (0x0800) -#define U300_SYSCON_C0OAR_APP_I2S1_CLK (0x0400) -#define U300_SYSCON_C0OAR_APP_I2S0_CLK (0x0200) -#define U300_SYSCON_C0OAR_APP_CPU_CLK (0x0100) -#define U300_SYSCON_C0OAR_APP_52_CLK (0x0080) -#define U300_SYSCON_C0OAR_APP_208_CLK (0x0040) -#define U300_SYSCON_C0OAR_APP_104_CLK (0x0020) -#define U300_SYSCON_C0OAR_APEX_CLK (0x0010) -#define U300_SYSCON_C0OAR_AHPB_M_H_CLK (0x0008) -#define U300_SYSCON_C0OAR_AHB_CLK (0x0004) -#define U300_SYSCON_C0OAR_AFPB_P_CLK (0x0002) -#define U300_SYSCON_C0OAR_AAIF_CLK (0x0001) -/* Clock activity observability register 1 */ -#define U300_SYSCON_C1OAR (0x144) -#define U300_SYSCON_C1OAR_MASK (0x3FFE) -#define U300_SYSCON_C1OAR_VALUE (0x3FFE) -#define U300_SYSCON_C1OAR_NFIF_F_CLK (0x2000) -#define U300_SYSCON_C1OAR_MSPRO_CLK (0x1000) -#define U300_SYSCON_C1OAR_MMC_P_CLK (0x0800) -#define U300_SYSCON_C1OAR_MMC_CLK (0x0400) -#define U300_SYSCON_C1OAR_KP_P_CLK (0x0200) -#define U300_SYSCON_C1OAR_I2C1_P_CLK (0x0100) -#define U300_SYSCON_C1OAR_I2C0_P_CLK (0x0080) -#define U300_SYSCON_C1OAR_GPIO_CLK (0x0040) -#define U300_SYSCON_C1OAR_EMIF_MPMC_CLK (0x0020) -#define U300_SYSCON_C1OAR_EMIF_H_CLK (0x0010) -#define U300_SYSCON_C1OAR_EVHIST_CLK (0x0008) -#define U300_SYSCON_C1OAR_PPM_CLK (0x0004) -#define U300_SYSCON_C1OAR_DMA_CLK (0x0002) -/* Clock activity observability register 2 */ -#define U300_SYSCON_C2OAR (0x148) -#define U300_SYSCON_C2OAR_MASK (0x0FFF) -#define U300_SYSCON_C2OAR_VALUE (0x0FFF) -#define U300_SYSCON_C2OAR_XGAM_CDI_CLK (0x0800) -#define U300_SYSCON_C2OAR_XGAM_CLK (0x0400) -#define U300_SYSCON_C2OAR_VC_H_CLK (0x0200) -#define U300_SYSCON_C2OAR_VC_CLK (0x0100) -#define U300_SYSCON_C2OAR_UA_P_CLK (0x0080) -#define U300_SYSCON_C2OAR_TMR1_CLK (0x0040) -#define U300_SYSCON_C2OAR_TMR0_CLK (0x0020) -#define U300_SYSCON_C2OAR_SPI_P_CLK (0x0010) -#define U300_SYSCON_C2OAR_PCM_I2S1_CORE_CLK (0x0008) -#define U300_SYSCON_C2OAR_PCM_I2S1_CLK (0x0004) -#define U300_SYSCON_C2OAR_PCM_I2S0_CORE_CLK (0x0002) -#define U300_SYSCON_C2OAR_PCM_I2S0_CLK (0x0001) - - -/* - * The clocking hierarchy currently looks like this. - * NOTE: the idea is NOT to show how the clocks are routed on the chip! - * The ideas is to show dependencies, so a clock higher up in the - * hierarchy has to be on in order for another clock to be on. Now, - * both CPU and DMA can actually be on top of the hierarchy, and that - * is not modeled currently. Instead we have the backbone AMBA bus on - * top. This bus cannot be programmed in any way but conceptually it - * needs to be active for the bridges and devices to transport data. - * - * Please be aware that a few clocks are hw controlled, which mean that - * the hw itself can turn on/off or change the rate of the clock when - * needed! - * - * AMBA bus - * | - * +- CPU - * +- FSMC NANDIF NAND Flash interface - * +- SEMI Shared Memory interface - * +- ISP Image Signal Processor (U335 only) - * +- CDS (U335 only) - * +- DMA Direct Memory Access Controller - * +- AAIF APP/ACC Interface (Mobile Scalable Link, MSL) - * +- APEX - * +- VIDEO_ENC AVE2/3 Video Encoder - * +- XGAM Graphics Accelerator Controller - * +- AHB - * | - * +- ahb:0 AHB Bridge - * | | - * | +- ahb:1 INTCON Interrupt controller - * | +- ahb:3 MSPRO Memory Stick Pro controller - * | +- ahb:4 EMIF External Memory interface - * | - * +- fast:0 FAST bridge - * | | - * | +- fast:1 MMCSD MMC/SD card reader controller - * | +- fast:2 I2S0 PCM I2S channel 0 controller - * | +- fast:3 I2S1 PCM I2S channel 1 controller - * | +- fast:4 I2C0 I2C channel 0 controller - * | +- fast:5 I2C1 I2C channel 1 controller - * | +- fast:6 SPI SPI controller - * | +- fast:7 UART1 Secondary UART (U335 only) - * | - * +- slow:0 SLOW bridge - * | - * +- slow:1 SYSCON (not possible to control) - * +- slow:2 WDOG Watchdog - * +- slow:3 UART0 primary UART - * +- slow:4 TIMER_APP Application timer - used in Linux - * +- slow:5 KEYPAD controller - * +- slow:6 GPIO controller - * +- slow:7 RTC controller - * +- slow:8 BT Bus Tracer (not used currently) - * +- slow:9 EH Event Handler (not used currently) - * +- slow:a TIMER_ACC Access style timer (not used currently) - * +- slow:b PPM (U335 only, what is that?) - */ - -/* Global syscon virtual base */ -static void __iomem *syscon_vbase; - -/** - * struct clk_syscon - U300 syscon clock - * @hw: corresponding clock hardware entry - * @hw_ctrld: whether this clock is hardware controlled (for refcount etc) - * and does not need any magic pokes to be enabled/disabled - * @reset: state holder, whether this block's reset line is asserted or not - * @res_reg: reset line enable/disable flag register - * @res_bit: bit for resetting or taking this consumer out of reset - * @en_reg: clock line enable/disable flag register - * @en_bit: bit for enabling/disabling this consumer clock line - * @clk_val: magic value to poke in the register to enable/disable - * this one clock - */ -struct clk_syscon { - struct clk_hw hw; - bool hw_ctrld; - bool reset; - void __iomem *res_reg; - u8 res_bit; - void __iomem *en_reg; - u8 en_bit; - u16 clk_val; -}; - -#define to_syscon(_hw) container_of(_hw, struct clk_syscon, hw) - -static DEFINE_SPINLOCK(syscon_resetreg_lock); - -/* - * Reset control functions. We remember if a block has been - * taken out of reset and don't remove the reset assertion again - * and vice versa. Currently we only remove resets so the - * enablement function is defined out. - */ -static void syscon_block_reset_enable(struct clk_syscon *sclk) -{ - unsigned long iflags; - u16 val; - - /* Not all blocks support resetting */ - if (!sclk->res_reg) - return; - spin_lock_irqsave(&syscon_resetreg_lock, iflags); - val = readw(sclk->res_reg); - val |= BIT(sclk->res_bit); - writew(val, sclk->res_reg); - spin_unlock_irqrestore(&syscon_resetreg_lock, iflags); - sclk->reset = true; -} - -static void syscon_block_reset_disable(struct clk_syscon *sclk) -{ - unsigned long iflags; - u16 val; - - /* Not all blocks support resetting */ - if (!sclk->res_reg) - return; - spin_lock_irqsave(&syscon_resetreg_lock, iflags); - val = readw(sclk->res_reg); - val &= ~BIT(sclk->res_bit); - writew(val, sclk->res_reg); - spin_unlock_irqrestore(&syscon_resetreg_lock, iflags); - sclk->reset = false; -} - -static int syscon_clk_prepare(struct clk_hw *hw) -{ - struct clk_syscon *sclk = to_syscon(hw); - - /* If the block is in reset, bring it out */ - if (sclk->reset) - syscon_block_reset_disable(sclk); - return 0; -} - -static void syscon_clk_unprepare(struct clk_hw *hw) -{ - struct clk_syscon *sclk = to_syscon(hw); - - /* Please don't force the console into reset */ - if (sclk->clk_val == U300_SYSCON_SBCER_UART_CLK_EN) - return; - /* When unpreparing, force block into reset */ - if (!sclk->reset) - syscon_block_reset_enable(sclk); -} - -static int syscon_clk_enable(struct clk_hw *hw) -{ - struct clk_syscon *sclk = to_syscon(hw); - - /* Don't touch the hardware controlled clocks */ - if (sclk->hw_ctrld) - return 0; - /* These cannot be controlled */ - if (sclk->clk_val == 0xFFFFU) - return 0; - - writew(sclk->clk_val, syscon_vbase + U300_SYSCON_SBCER); - return 0; -} - -static void syscon_clk_disable(struct clk_hw *hw) -{ - struct clk_syscon *sclk = to_syscon(hw); - - /* Don't touch the hardware controlled clocks */ - if (sclk->hw_ctrld) - return; - if (sclk->clk_val == 0xFFFFU) - return; - /* Please don't disable the console port */ - if (sclk->clk_val == U300_SYSCON_SBCER_UART_CLK_EN) - return; - - writew(sclk->clk_val, syscon_vbase + U300_SYSCON_SBCDR); -} - -static int syscon_clk_is_enabled(struct clk_hw *hw) -{ - struct clk_syscon *sclk = to_syscon(hw); - u16 val; - - /* If no enable register defined, it's always-on */ - if (!sclk->en_reg) - return 1; - - val = readw(sclk->en_reg); - val &= BIT(sclk->en_bit); - - return val ? 1 : 0; -} - -static u16 syscon_get_perf(void) -{ - u16 val; - - val = readw(syscon_vbase + U300_SYSCON_CCR); - val &= U300_SYSCON_CCR_CLKING_PERFORMANCE_MASK; - return val; -} - -static unsigned long -syscon_clk_recalc_rate(struct clk_hw *hw, - unsigned long parent_rate) -{ - struct clk_syscon *sclk = to_syscon(hw); - u16 perf = syscon_get_perf(); - - switch (sclk->clk_val) { - case U300_SYSCON_SBCER_FAST_BRIDGE_CLK_EN: - case U300_SYSCON_SBCER_I2C0_CLK_EN: - case U300_SYSCON_SBCER_I2C1_CLK_EN: - case U300_SYSCON_SBCER_MMC_CLK_EN: - case U300_SYSCON_SBCER_SPI_CLK_EN: - /* The FAST clocks have one progression */ - switch (perf) { - case U300_SYSCON_CCR_CLKING_PERFORMANCE_LOW_POWER: - case U300_SYSCON_CCR_CLKING_PERFORMANCE_LOW: - return 13000000; - default: - return parent_rate; /* 26 MHz */ - } - case U300_SYSCON_SBCER_DMAC_CLK_EN: - case U300_SYSCON_SBCER_NANDIF_CLK_EN: - case U300_SYSCON_SBCER_XGAM_CLK_EN: - /* AMBA interconnect peripherals */ - switch (perf) { - case U300_SYSCON_CCR_CLKING_PERFORMANCE_LOW_POWER: - case U300_SYSCON_CCR_CLKING_PERFORMANCE_LOW: - return 6500000; - case U300_SYSCON_CCR_CLKING_PERFORMANCE_INTERMEDIATE: - return 26000000; - default: - return parent_rate; /* 52 MHz */ - } - case U300_SYSCON_SBCER_SEMI_CLK_EN: - case U300_SYSCON_SBCER_EMIF_CLK_EN: - /* EMIF speeds */ - switch (perf) { - case U300_SYSCON_CCR_CLKING_PERFORMANCE_LOW_POWER: - case U300_SYSCON_CCR_CLKING_PERFORMANCE_LOW: - return 13000000; - case U300_SYSCON_CCR_CLKING_PERFORMANCE_INTERMEDIATE: - return 52000000; - default: - return 104000000; - } - case U300_SYSCON_SBCER_CPU_CLK_EN: - /* And the fast CPU clock */ - switch (perf) { - case U300_SYSCON_CCR_CLKING_PERFORMANCE_LOW_POWER: - case U300_SYSCON_CCR_CLKING_PERFORMANCE_LOW: - return 13000000; - case U300_SYSCON_CCR_CLKING_PERFORMANCE_INTERMEDIATE: - return 52000000; - case U300_SYSCON_CCR_CLKING_PERFORMANCE_HIGH: - return 104000000; - default: - return parent_rate; /* 208 MHz */ - } - default: - /* - * The SLOW clocks and default just inherit the rate of - * their parent (typically PLL13 13 MHz). - */ - return parent_rate; - } -} - -static long -syscon_clk_round_rate(struct clk_hw *hw, unsigned long rate, - unsigned long *prate) -{ - struct clk_syscon *sclk = to_syscon(hw); - - if (sclk->clk_val != U300_SYSCON_SBCER_CPU_CLK_EN) - return *prate; - /* We really only support setting the rate of the CPU clock */ - if (rate <= 13000000) - return 13000000; - if (rate <= 52000000) - return 52000000; - if (rate <= 104000000) - return 104000000; - return 208000000; -} - -static int syscon_clk_set_rate(struct clk_hw *hw, unsigned long rate, - unsigned long parent_rate) -{ - struct clk_syscon *sclk = to_syscon(hw); - u16 val; - - /* We only support setting the rate of the CPU clock */ - if (sclk->clk_val != U300_SYSCON_SBCER_CPU_CLK_EN) - return -EINVAL; - switch (rate) { - case 13000000: - val = U300_SYSCON_CCR_CLKING_PERFORMANCE_LOW_POWER; - break; - case 52000000: - val = U300_SYSCON_CCR_CLKING_PERFORMANCE_INTERMEDIATE; - break; - case 104000000: - val = U300_SYSCON_CCR_CLKING_PERFORMANCE_HIGH; - break; - case 208000000: - val = U300_SYSCON_CCR_CLKING_PERFORMANCE_BEST; - break; - default: - return -EINVAL; - } - val |= readw(syscon_vbase + U300_SYSCON_CCR) & - ~U300_SYSCON_CCR_CLKING_PERFORMANCE_MASK ; - writew(val, syscon_vbase + U300_SYSCON_CCR); - return 0; -} - -static const struct clk_ops syscon_clk_ops = { - .prepare = syscon_clk_prepare, - .unprepare = syscon_clk_unprepare, - .enable = syscon_clk_enable, - .disable = syscon_clk_disable, - .is_enabled = syscon_clk_is_enabled, - .recalc_rate = syscon_clk_recalc_rate, - .round_rate = syscon_clk_round_rate, - .set_rate = syscon_clk_set_rate, -}; - -static struct clk_hw * __init -syscon_clk_register(struct device *dev, const char *name, - const char *parent_name, unsigned long flags, - bool hw_ctrld, - void __iomem *res_reg, u8 res_bit, - void __iomem *en_reg, u8 en_bit, - u16 clk_val) -{ - struct clk_hw *hw; - struct clk_syscon *sclk; - struct clk_init_data init; - int ret; - - sclk = kzalloc(sizeof(*sclk), GFP_KERNEL); - if (!sclk) - return ERR_PTR(-ENOMEM); - - init.name = name; - init.ops = &syscon_clk_ops; - init.flags = flags; - init.parent_names = (parent_name ? &parent_name : NULL); - init.num_parents = (parent_name ? 1 : 0); - sclk->hw.init = &init; - sclk->hw_ctrld = hw_ctrld; - /* Assume the block is in reset at registration */ - sclk->reset = true; - sclk->res_reg = res_reg; - sclk->res_bit = res_bit; - sclk->en_reg = en_reg; - sclk->en_bit = en_bit; - sclk->clk_val = clk_val; - - hw = &sclk->hw; - ret = clk_hw_register(dev, hw); - if (ret) { - kfree(sclk); - hw = ERR_PTR(ret); - } - - return hw; -} - -#define U300_CLK_TYPE_SLOW 0 -#define U300_CLK_TYPE_FAST 1 -#define U300_CLK_TYPE_REST 2 - -/** - * struct u300_clock - defines the bits and pieces for a certain clock - * @type: the clock type, slow fast or rest - * @id: the bit in the slow/fast/rest register for this clock - * @hw_ctrld: whether the clock is hardware controlled - * @clk_val: a value to poke in the one-write enable/disable registers - */ -struct u300_clock { - u8 type; - u8 id; - bool hw_ctrld; - u16 clk_val; -}; - -static struct u300_clock const u300_clk_lookup[] __initconst = { - { - .type = U300_CLK_TYPE_REST, - .id = 3, - .hw_ctrld = true, - .clk_val = U300_SYSCON_SBCER_CPU_CLK_EN, - }, - { - .type = U300_CLK_TYPE_REST, - .id = 4, - .hw_ctrld = true, - .clk_val = U300_SYSCON_SBCER_DMAC_CLK_EN, - }, - { - .type = U300_CLK_TYPE_REST, - .id = 5, - .hw_ctrld = false, - .clk_val = U300_SYSCON_SBCER_EMIF_CLK_EN, - }, - { - .type = U300_CLK_TYPE_REST, - .id = 6, - .hw_ctrld = false, - .clk_val = U300_SYSCON_SBCER_NANDIF_CLK_EN, - }, - { - .type = U300_CLK_TYPE_REST, - .id = 8, - .hw_ctrld = true, - .clk_val = U300_SYSCON_SBCER_XGAM_CLK_EN, - }, - { - .type = U300_CLK_TYPE_REST, - .id = 9, - .hw_ctrld = false, - .clk_val = U300_SYSCON_SBCER_SEMI_CLK_EN, - }, - { - .type = U300_CLK_TYPE_REST, - .id = 10, - .hw_ctrld = true, - .clk_val = U300_SYSCON_SBCER_AHB_SUBSYS_BRIDGE_CLK_EN, - }, - { - .type = U300_CLK_TYPE_REST, - .id = 12, - .hw_ctrld = false, - /* INTCON: cannot be enabled, just taken out of reset */ - .clk_val = 0xFFFFU, - }, - { - .type = U300_CLK_TYPE_FAST, - .id = 0, - .hw_ctrld = true, - .clk_val = U300_SYSCON_SBCER_FAST_BRIDGE_CLK_EN, - }, - { - .type = U300_CLK_TYPE_FAST, - .id = 1, - .hw_ctrld = false, - .clk_val = U300_SYSCON_SBCER_I2C0_CLK_EN, - }, - { - .type = U300_CLK_TYPE_FAST, - .id = 2, - .hw_ctrld = false, - .clk_val = U300_SYSCON_SBCER_I2C1_CLK_EN, - }, - { - .type = U300_CLK_TYPE_FAST, - .id = 5, - .hw_ctrld = false, - .clk_val = U300_SYSCON_SBCER_MMC_CLK_EN, - }, - { - .type = U300_CLK_TYPE_FAST, - .id = 6, - .hw_ctrld = false, - .clk_val = U300_SYSCON_SBCER_SPI_CLK_EN, - }, - { - .type = U300_CLK_TYPE_SLOW, - .id = 0, - .hw_ctrld = true, - .clk_val = U300_SYSCON_SBCER_SLOW_BRIDGE_CLK_EN, - }, - { - .type = U300_CLK_TYPE_SLOW, - .id = 1, - .hw_ctrld = false, - .clk_val = U300_SYSCON_SBCER_UART_CLK_EN, - }, - { - .type = U300_CLK_TYPE_SLOW, - .id = 4, - .hw_ctrld = false, - .clk_val = U300_SYSCON_SBCER_GPIO_CLK_EN, - }, - { - .type = U300_CLK_TYPE_SLOW, - .id = 6, - .hw_ctrld = true, - /* No clock enable register bit */ - .clk_val = 0xFFFFU, - }, - { - .type = U300_CLK_TYPE_SLOW, - .id = 7, - .hw_ctrld = false, - .clk_val = U300_SYSCON_SBCER_APP_TMR_CLK_EN, - }, - { - .type = U300_CLK_TYPE_SLOW, - .id = 8, - .hw_ctrld = false, - .clk_val = U300_SYSCON_SBCER_ACC_TMR_CLK_EN, - }, -}; - -static void __init of_u300_syscon_clk_init(struct device_node *np) -{ - struct clk_hw *hw = ERR_PTR(-EINVAL); - const char *clk_name = np->name; - const char *parent_name; - void __iomem *res_reg; - void __iomem *en_reg; - u32 clk_type; - u32 clk_id; - int i; - - if (of_property_read_u32(np, "clock-type", &clk_type)) { - pr_err("%s: syscon clock \"%s\" missing clock-type property\n", - __func__, clk_name); - return; - } - if (of_property_read_u32(np, "clock-id", &clk_id)) { - pr_err("%s: syscon clock \"%s\" missing clock-id property\n", - __func__, clk_name); - return; - } - parent_name = of_clk_get_parent_name(np, 0); - - switch (clk_type) { - case U300_CLK_TYPE_SLOW: - res_reg = syscon_vbase + U300_SYSCON_RSR; - en_reg = syscon_vbase + U300_SYSCON_CESR; - break; - case U300_CLK_TYPE_FAST: - res_reg = syscon_vbase + U300_SYSCON_RFR; - en_reg = syscon_vbase + U300_SYSCON_CEFR; - break; - case U300_CLK_TYPE_REST: - res_reg = syscon_vbase + U300_SYSCON_RRR; - en_reg = syscon_vbase + U300_SYSCON_CERR; - break; - default: - pr_err("unknown clock type %x specified\n", clk_type); - return; - } - - for (i = 0; i < ARRAY_SIZE(u300_clk_lookup); i++) { - const struct u300_clock *u3clk = &u300_clk_lookup[i]; - - if (u3clk->type == clk_type && u3clk->id == clk_id) - hw = syscon_clk_register(NULL, clk_name, parent_name, - 0, u3clk->hw_ctrld, - res_reg, u3clk->id, - en_reg, u3clk->id, - u3clk->clk_val); - } - - if (!IS_ERR(hw)) { - of_clk_add_hw_provider(np, of_clk_hw_simple_get, hw); - - /* - * Some few system clocks - device tree does not - * represent clocks without a corresponding device node. - * for now we add these three clocks here. - */ - if (clk_type == U300_CLK_TYPE_REST && clk_id == 5) - clk_hw_register_clkdev(hw, NULL, "pl172"); - if (clk_type == U300_CLK_TYPE_REST && clk_id == 9) - clk_hw_register_clkdev(hw, NULL, "semi"); - if (clk_type == U300_CLK_TYPE_REST && clk_id == 12) - clk_hw_register_clkdev(hw, NULL, "intcon"); - } -} - -/** - * struct clk_mclk - U300 MCLK clock (MMC/SD clock) - * @hw: corresponding clock hardware entry - * @is_mspro: if this is the memory stick clock rather than MMC/SD - */ -struct clk_mclk { - struct clk_hw hw; - bool is_mspro; -}; - -#define to_mclk(_hw) container_of(_hw, struct clk_mclk, hw) - -static int mclk_clk_prepare(struct clk_hw *hw) -{ - struct clk_mclk *mclk = to_mclk(hw); - u16 val; - - /* The MMC and MSPRO clocks need some special set-up */ - if (!mclk->is_mspro) { - /* Set default MMC clock divisor to 18.9 MHz */ - writew(0x0054U, syscon_vbase + U300_SYSCON_MMF0R); - val = readw(syscon_vbase + U300_SYSCON_MMCR); - /* Disable the MMC feedback clock */ - val &= ~U300_SYSCON_MMCR_MMC_FB_CLK_SEL_ENABLE; - /* Disable MSPRO frequency */ - val &= ~U300_SYSCON_MMCR_MSPRO_FREQSEL_ENABLE; - writew(val, syscon_vbase + U300_SYSCON_MMCR); - } else { - val = readw(syscon_vbase + U300_SYSCON_MMCR); - /* Disable the MMC feedback clock */ - val &= ~U300_SYSCON_MMCR_MMC_FB_CLK_SEL_ENABLE; - /* Enable MSPRO frequency */ - val |= U300_SYSCON_MMCR_MSPRO_FREQSEL_ENABLE; - writew(val, syscon_vbase + U300_SYSCON_MMCR); - } - - return 0; -} - -static unsigned long -mclk_clk_recalc_rate(struct clk_hw *hw, - unsigned long parent_rate) -{ - u16 perf = syscon_get_perf(); - - switch (perf) { - case U300_SYSCON_CCR_CLKING_PERFORMANCE_LOW_POWER: - /* - * Here, the 208 MHz PLL gets shut down and the always - * on 13 MHz PLL used for RTC etc kicks into use - * instead. - */ - return 13000000; - case U300_SYSCON_CCR_CLKING_PERFORMANCE_LOW: - case U300_SYSCON_CCR_CLKING_PERFORMANCE_INTERMEDIATE: - case U300_SYSCON_CCR_CLKING_PERFORMANCE_HIGH: - case U300_SYSCON_CCR_CLKING_PERFORMANCE_BEST: - { - /* - * This clock is under program control. The register is - * divided in two nybbles, bit 7-4 gives cycles-1 to count - * high, bit 3-0 gives cycles-1 to count low. Distribute - * these with no more than 1 cycle difference between - * low and high and add low and high to get the actual - * divisor. The base PLL is 208 MHz. Writing 0x00 will - * divide by 1 and 1 so the highest frequency possible - * is 104 MHz. - * - * e.g. 0x54 => - * f = 208 / ((5+1) + (4+1)) = 208 / 11 = 18.9 MHz - */ - u16 val = readw(syscon_vbase + U300_SYSCON_MMF0R) & - U300_SYSCON_MMF0R_MASK; - switch (val) { - case 0x0054: - return 18900000; - case 0x0044: - return 20800000; - case 0x0043: - return 23100000; - case 0x0033: - return 26000000; - case 0x0032: - return 29700000; - case 0x0022: - return 34700000; - case 0x0021: - return 41600000; - case 0x0011: - return 52000000; - case 0x0000: - return 104000000; - default: - break; - } - } - default: - break; - } - return parent_rate; -} - -static long -mclk_clk_round_rate(struct clk_hw *hw, unsigned long rate, - unsigned long *prate) -{ - if (rate <= 18900000) - return 18900000; - if (rate <= 20800000) - return 20800000; - if (rate <= 23100000) - return 23100000; - if (rate <= 26000000) - return 26000000; - if (rate <= 29700000) - return 29700000; - if (rate <= 34700000) - return 34700000; - if (rate <= 41600000) - return 41600000; - /* Highest rate */ - return 52000000; -} - -static int mclk_clk_set_rate(struct clk_hw *hw, unsigned long rate, - unsigned long parent_rate) -{ - u16 val; - u16 reg; - - switch (rate) { - case 18900000: - val = 0x0054; - break; - case 20800000: - val = 0x0044; - break; - case 23100000: - val = 0x0043; - break; - case 26000000: - val = 0x0033; - break; - case 29700000: - val = 0x0032; - break; - case 34700000: - val = 0x0022; - break; - case 41600000: - val = 0x0021; - break; - case 52000000: - val = 0x0011; - break; - case 104000000: - val = 0x0000; - break; - default: - return -EINVAL; - } - - reg = readw(syscon_vbase + U300_SYSCON_MMF0R) & - ~U300_SYSCON_MMF0R_MASK; - writew(reg | val, syscon_vbase + U300_SYSCON_MMF0R); - return 0; -} - -static const struct clk_ops mclk_ops = { - .prepare = mclk_clk_prepare, - .recalc_rate = mclk_clk_recalc_rate, - .round_rate = mclk_clk_round_rate, - .set_rate = mclk_clk_set_rate, -}; - -static struct clk_hw * __init -mclk_clk_register(struct device *dev, const char *name, - const char *parent_name, bool is_mspro) -{ - struct clk_hw *hw; - struct clk_mclk *mclk; - struct clk_init_data init; - int ret; - - mclk = kzalloc(sizeof(*mclk), GFP_KERNEL); - if (!mclk) - return ERR_PTR(-ENOMEM); - - init.name = "mclk"; - init.ops = &mclk_ops; - init.flags = 0; - init.parent_names = (parent_name ? &parent_name : NULL); - init.num_parents = (parent_name ? 1 : 0); - mclk->hw.init = &init; - mclk->is_mspro = is_mspro; - - hw = &mclk->hw; - ret = clk_hw_register(dev, hw); - if (ret) { - kfree(mclk); - hw = ERR_PTR(ret); - } - - return hw; -} - -static void __init of_u300_syscon_mclk_init(struct device_node *np) -{ - struct clk_hw *hw; - const char *clk_name = np->name; - const char *parent_name; - - parent_name = of_clk_get_parent_name(np, 0); - hw = mclk_clk_register(NULL, clk_name, parent_name, false); - if (!IS_ERR(hw)) - of_clk_add_hw_provider(np, of_clk_hw_simple_get, hw); -} - -static const struct of_device_id u300_clk_match[] __initconst = { - { - .compatible = "fixed-clock", - .data = of_fixed_clk_setup, - }, - { - .compatible = "fixed-factor-clock", - .data = of_fixed_factor_clk_setup, - }, - { - .compatible = "stericsson,u300-syscon-clk", - .data = of_u300_syscon_clk_init, - }, - { - .compatible = "stericsson,u300-syscon-mclk", - .data = of_u300_syscon_mclk_init, - }, - {} -}; - - -void __init u300_clk_init(void __iomem *base) -{ - u16 val; - - syscon_vbase = base; - - /* Set system to run at PLL208, max performance, a known state. */ - val = readw(syscon_vbase + U300_SYSCON_CCR); - val &= ~U300_SYSCON_CCR_CLKING_PERFORMANCE_MASK; - writew(val, syscon_vbase + U300_SYSCON_CCR); - /* Wait for the PLL208 to lock if not locked in yet */ - while (!(readw(syscon_vbase + U300_SYSCON_CSR) & - U300_SYSCON_CSR_PLL208_LOCK_IND)); - - /* Power management enable */ - val = readw(syscon_vbase + U300_SYSCON_PMCR); - val |= U300_SYSCON_PMCR_PWR_MGNT_ENABLE; - writew(val, syscon_vbase + U300_SYSCON_PMCR); - - of_clk_init(u300_clk_match); -} diff --git a/include/linux/platform_data/clk-u300.h b/include/linux/platform_data/clk-u300.h deleted file mode 100644 index 8429e73911a1..000000000000 --- a/include/linux/platform_data/clk-u300.h +++ /dev/null @@ -1 +0,0 @@ -void __init u300_clk_init(void __iomem *base); -- cgit v1.2.3 From bf5c9cc8ad7fffd1f72df3baa5870449e4c16d1b Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Mon, 8 Feb 2021 08:37:05 +0100 Subject: mei: bus: change remove callback to return void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver core ignores the return value of mei_cl_device_remove() so passing an error value doesn't solve any problem. As most mei drivers' remove callbacks return 0 unconditionally and returning a different value doesn't have any effect, change this prototype to return void and return 0 unconditionally in mei_cl_device_remove(). The only driver that could return an error value is modified to emit an explicit warning in the error case. Acked-by: Guenter Roeck Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20210208073705.428185-3-uwe@kleine-koenig.org Signed-off-by: Greg Kroah-Hartman --- drivers/misc/mei/bus.c | 5 ++--- drivers/misc/mei/hdcp/mei_hdcp.c | 7 +++++-- drivers/nfc/microread/mei.c | 4 +--- drivers/nfc/pn544/mei.c | 4 +--- drivers/watchdog/mei_wdt.c | 4 +--- include/linux/mei_cl_bus.h | 2 +- 6 files changed, 11 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c index 393a41330a6b..580074e32599 100644 --- a/drivers/misc/mei/bus.c +++ b/drivers/misc/mei/bus.c @@ -881,17 +881,16 @@ static int mei_cl_device_remove(struct device *dev) { struct mei_cl_device *cldev = to_mei_cl_device(dev); struct mei_cl_driver *cldrv = to_mei_cl_driver(dev->driver); - int ret = 0; if (cldrv->remove) - ret = cldrv->remove(cldev); + cldrv->remove(cldev); mei_cldev_unregister_callbacks(cldev); mei_cl_bus_module_put(cldev); module_put(THIS_MODULE); - return ret; + return 0; } static ssize_t name_show(struct device *dev, struct device_attribute *a, diff --git a/drivers/misc/mei/hdcp/mei_hdcp.c b/drivers/misc/mei/hdcp/mei_hdcp.c index 9ae9669e46ea..8447ad4b7d47 100644 --- a/drivers/misc/mei/hdcp/mei_hdcp.c +++ b/drivers/misc/mei/hdcp/mei_hdcp.c @@ -845,16 +845,19 @@ enable_err_exit: return ret; } -static int mei_hdcp_remove(struct mei_cl_device *cldev) +static void mei_hdcp_remove(struct mei_cl_device *cldev) { struct i915_hdcp_comp_master *comp_master = mei_cldev_get_drvdata(cldev); + int ret; component_master_del(&cldev->dev, &mei_component_master_ops); kfree(comp_master); mei_cldev_set_drvdata(cldev, NULL); - return mei_cldev_disable(cldev); + ret = mei_cldev_disable(cldev); + if (ret) + dev_warn(&cldev->dev, "mei_cldev_disable() failed\n"); } #define MEI_UUID_HDCP GUID_INIT(0xB638AB7E, 0x94E2, 0x4EA2, 0xA5, \ diff --git a/drivers/nfc/microread/mei.c b/drivers/nfc/microread/mei.c index 5dad8847a9b3..8fa7771085eb 100644 --- a/drivers/nfc/microread/mei.c +++ b/drivers/nfc/microread/mei.c @@ -44,15 +44,13 @@ static int microread_mei_probe(struct mei_cl_device *cldev, return 0; } -static int microread_mei_remove(struct mei_cl_device *cldev) +static void microread_mei_remove(struct mei_cl_device *cldev) { struct nfc_mei_phy *phy = mei_cldev_get_drvdata(cldev); microread_remove(phy->hdev); nfc_mei_phy_free(phy); - - return 0; } static struct mei_cl_device_id microread_mei_tbl[] = { diff --git a/drivers/nfc/pn544/mei.c b/drivers/nfc/pn544/mei.c index 579bc599f545..5c10aac085a4 100644 --- a/drivers/nfc/pn544/mei.c +++ b/drivers/nfc/pn544/mei.c @@ -42,7 +42,7 @@ static int pn544_mei_probe(struct mei_cl_device *cldev, return 0; } -static int pn544_mei_remove(struct mei_cl_device *cldev) +static void pn544_mei_remove(struct mei_cl_device *cldev) { struct nfc_mei_phy *phy = mei_cldev_get_drvdata(cldev); @@ -51,8 +51,6 @@ static int pn544_mei_remove(struct mei_cl_device *cldev) pn544_hci_remove(phy->hdev); nfc_mei_phy_free(phy); - - return 0; } static struct mei_cl_device_id pn544_mei_tbl[] = { diff --git a/drivers/watchdog/mei_wdt.c b/drivers/watchdog/mei_wdt.c index 5391bf3e6b11..53165e49c298 100644 --- a/drivers/watchdog/mei_wdt.c +++ b/drivers/watchdog/mei_wdt.c @@ -619,7 +619,7 @@ err_out: return ret; } -static int mei_wdt_remove(struct mei_cl_device *cldev) +static void mei_wdt_remove(struct mei_cl_device *cldev) { struct mei_wdt *wdt = mei_cldev_get_drvdata(cldev); @@ -636,8 +636,6 @@ static int mei_wdt_remove(struct mei_cl_device *cldev) dbgfs_unregister(wdt); kfree(wdt); - - return 0; } #define MEI_UUID_WD UUID_LE(0x05B79A6F, 0x4628, 0x4D7F, \ diff --git a/include/linux/mei_cl_bus.h b/include/linux/mei_cl_bus.h index 959ad7d850b4..07f5ef8fc456 100644 --- a/include/linux/mei_cl_bus.h +++ b/include/linux/mei_cl_bus.h @@ -68,7 +68,7 @@ struct mei_cl_driver { int (*probe)(struct mei_cl_device *cldev, const struct mei_cl_device_id *id); - int (*remove)(struct mei_cl_device *cldev); + void (*remove)(struct mei_cl_device *cldev); }; int __mei_cldev_driver_register(struct mei_cl_driver *cldrv, -- cgit v1.2.3 From 9c5137aedd112f78a968bdd2325de2ea06df46c0 Mon Sep 17 00:00:00 2001 From: Shuo Liu Date: Sun, 7 Feb 2021 11:10:28 +0800 Subject: virt: acrn: Introduce VM management interfaces The VM management interfaces expose several VM operations to ACRN userspace via ioctls. For example, creating VM, starting VM, destroying VM and so on. The ACRN Hypervisor needs to exchange data with the ACRN userspace during the VM operations. HSM provides VM operation ioctls to the ACRN userspace and communicates with the ACRN Hypervisor for VM operations via hypercalls. HSM maintains a list of User VM. Each User VM will be bound to an existing file descriptor of /dev/acrn_hsm. The User VM will be destroyed when the file descriptor is closed. Cc: Zhi Wang Cc: Zhenyu Wang Cc: Yu Wang Cc: Reinette Chatre Cc: Greg Kroah-Hartman Reviewed-by: Zhi Wang Reviewed-by: Reinette Chatre Signed-off-by: Shuo Liu Link: https://lore.kernel.org/r/20210207031040.49576-7-shuo.a.liu@intel.com Signed-off-by: Greg Kroah-Hartman --- Documentation/userspace-api/ioctl/ioctl-number.rst | 1 + MAINTAINERS | 1 + drivers/virt/acrn/Makefile | 2 +- drivers/virt/acrn/acrn_drv.h | 21 +++++- drivers/virt/acrn/hsm.c | 76 ++++++++++++++++++++- drivers/virt/acrn/hypercall.h | 78 ++++++++++++++++++++++ drivers/virt/acrn/vm.c | 68 +++++++++++++++++++ include/uapi/linux/acrn.h | 58 ++++++++++++++++ 8 files changed, 301 insertions(+), 4 deletions(-) create mode 100644 drivers/virt/acrn/hypercall.h create mode 100644 drivers/virt/acrn/vm.c create mode 100644 include/uapi/linux/acrn.h (limited to 'include') diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst index 19d730f9d136..76c27dbae96b 100644 --- a/Documentation/userspace-api/ioctl/ioctl-number.rst +++ b/Documentation/userspace-api/ioctl/ioctl-number.rst @@ -320,6 +320,7 @@ Code Seq# Include File Comments 0xA0 all linux/sdp/sdp.h Industrial Device Project 0xA1 0 linux/vtpm_proxy.h TPM Emulator Proxy Driver +0xA2 all uapi/linux/acrn.h ACRN hypervisor 0xA3 80-8F Port ACL in development: 0xA3 90-9F linux/dtlk.h diff --git a/MAINTAINERS b/MAINTAINERS index 4ac781da514f..6b5990a28b44 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -443,6 +443,7 @@ S: Supported W: https://projectacrn.org F: Documentation/virt/acrn/ F: drivers/virt/acrn/ +F: include/uapi/linux/acrn.h AD1889 ALSA SOUND DRIVER L: linux-parisc@vger.kernel.org diff --git a/drivers/virt/acrn/Makefile b/drivers/virt/acrn/Makefile index 6920ed798aaf..cf8b4ed5e74e 100644 --- a/drivers/virt/acrn/Makefile +++ b/drivers/virt/acrn/Makefile @@ -1,3 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_ACRN_HSM) := acrn.o -acrn-y := hsm.o +acrn-y := hsm.o vm.o diff --git a/drivers/virt/acrn/acrn_drv.h b/drivers/virt/acrn/acrn_drv.h index 29eedd696327..e5aba86cad8c 100644 --- a/drivers/virt/acrn/acrn_drv.h +++ b/drivers/virt/acrn/acrn_drv.h @@ -3,16 +3,35 @@ #ifndef __ACRN_HSM_DRV_H #define __ACRN_HSM_DRV_H +#include +#include +#include #include +#include "hypercall.h" + +extern struct miscdevice acrn_dev; + #define ACRN_INVALID_VMID (0xffffU) +#define ACRN_VM_FLAG_DESTROYED 0U /** * struct acrn_vm - Properties of ACRN User VM. + * @list: Entry within global list of all VMs * @vmid: User VM ID + * @vcpu_num: Number of virtual CPUs in the VM + * @flags: Flags (ACRN_VM_FLAG_*) of the VM. This is VM flag management + * in HSM which is different from the &acrn_vm_creation.vm_flag. */ struct acrn_vm { - u16 vmid; + struct list_head list; + u16 vmid; + int vcpu_num; + unsigned long flags; }; +struct acrn_vm *acrn_vm_create(struct acrn_vm *vm, + struct acrn_vm_creation *vm_param); +int acrn_vm_destroy(struct acrn_vm *vm); + #endif /* __ACRN_HSM_DRV_H */ diff --git a/drivers/virt/acrn/hsm.c b/drivers/virt/acrn/hsm.c index a8dcb250649d..5fd933471683 100644 --- a/drivers/virt/acrn/hsm.c +++ b/drivers/virt/acrn/hsm.c @@ -9,7 +9,6 @@ * Yakui Zhao */ -#include #include #include #include @@ -38,10 +37,82 @@ static int acrn_dev_open(struct inode *inode, struct file *filp) return 0; } +/* + * HSM relies on hypercall layer of the ACRN hypervisor to do the + * sanity check against the input parameters. + */ +static long acrn_dev_ioctl(struct file *filp, unsigned int cmd, + unsigned long ioctl_param) +{ + struct acrn_vm *vm = filp->private_data; + struct acrn_vm_creation *vm_param; + int ret = 0; + + if (vm->vmid == ACRN_INVALID_VMID && cmd != ACRN_IOCTL_CREATE_VM) { + dev_dbg(acrn_dev.this_device, + "ioctl 0x%x: Invalid VM state!\n", cmd); + return -EINVAL; + } + + switch (cmd) { + case ACRN_IOCTL_CREATE_VM: + vm_param = memdup_user((void __user *)ioctl_param, + sizeof(struct acrn_vm_creation)); + if (IS_ERR(vm_param)) + return PTR_ERR(vm_param); + + if ((vm_param->reserved0 | vm_param->reserved1) != 0) + return -EINVAL; + + vm = acrn_vm_create(vm, vm_param); + if (!vm) { + ret = -EINVAL; + kfree(vm_param); + break; + } + + if (copy_to_user((void __user *)ioctl_param, vm_param, + sizeof(struct acrn_vm_creation))) { + acrn_vm_destroy(vm); + ret = -EFAULT; + } + + kfree(vm_param); + break; + case ACRN_IOCTL_START_VM: + ret = hcall_start_vm(vm->vmid); + if (ret < 0) + dev_dbg(acrn_dev.this_device, + "Failed to start VM %u!\n", vm->vmid); + break; + case ACRN_IOCTL_PAUSE_VM: + ret = hcall_pause_vm(vm->vmid); + if (ret < 0) + dev_dbg(acrn_dev.this_device, + "Failed to pause VM %u!\n", vm->vmid); + break; + case ACRN_IOCTL_RESET_VM: + ret = hcall_reset_vm(vm->vmid); + if (ret < 0) + dev_dbg(acrn_dev.this_device, + "Failed to restart VM %u!\n", vm->vmid); + break; + case ACRN_IOCTL_DESTROY_VM: + ret = acrn_vm_destroy(vm); + break; + default: + dev_dbg(acrn_dev.this_device, "Unknown IOCTL 0x%x!\n", cmd); + ret = -ENOTTY; + } + + return ret; +} + static int acrn_dev_release(struct inode *inode, struct file *filp) { struct acrn_vm *vm = filp->private_data; + acrn_vm_destroy(vm); kfree(vm); return 0; } @@ -50,9 +121,10 @@ static const struct file_operations acrn_fops = { .owner = THIS_MODULE, .open = acrn_dev_open, .release = acrn_dev_release, + .unlocked_ioctl = acrn_dev_ioctl, }; -static struct miscdevice acrn_dev = { +struct miscdevice acrn_dev = { .minor = MISC_DYNAMIC_MINOR, .name = "acrn_hsm", .fops = &acrn_fops, diff --git a/drivers/virt/acrn/hypercall.h b/drivers/virt/acrn/hypercall.h new file mode 100644 index 000000000000..426b66cadb1f --- /dev/null +++ b/drivers/virt/acrn/hypercall.h @@ -0,0 +1,78 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * ACRN HSM: hypercalls of ACRN Hypervisor + */ +#ifndef __ACRN_HSM_HYPERCALL_H +#define __ACRN_HSM_HYPERCALL_H +#include + +/* + * Hypercall IDs of the ACRN Hypervisor + */ +#define _HC_ID(x, y) (((x) << 24) | (y)) + +#define HC_ID 0x80UL + +#define HC_ID_VM_BASE 0x10UL +#define HC_CREATE_VM _HC_ID(HC_ID, HC_ID_VM_BASE + 0x00) +#define HC_DESTROY_VM _HC_ID(HC_ID, HC_ID_VM_BASE + 0x01) +#define HC_START_VM _HC_ID(HC_ID, HC_ID_VM_BASE + 0x02) +#define HC_PAUSE_VM _HC_ID(HC_ID, HC_ID_VM_BASE + 0x03) +#define HC_RESET_VM _HC_ID(HC_ID, HC_ID_VM_BASE + 0x05) + +/** + * hcall_create_vm() - Create a User VM + * @vminfo: Service VM GPA of info of User VM creation + * + * Return: 0 on success, <0 on failure + */ +static inline long hcall_create_vm(u64 vminfo) +{ + return acrn_hypercall1(HC_CREATE_VM, vminfo); +} + +/** + * hcall_start_vm() - Start a User VM + * @vmid: User VM ID + * + * Return: 0 on success, <0 on failure + */ +static inline long hcall_start_vm(u64 vmid) +{ + return acrn_hypercall1(HC_START_VM, vmid); +} + +/** + * hcall_pause_vm() - Pause a User VM + * @vmid: User VM ID + * + * Return: 0 on success, <0 on failure + */ +static inline long hcall_pause_vm(u64 vmid) +{ + return acrn_hypercall1(HC_PAUSE_VM, vmid); +} + +/** + * hcall_destroy_vm() - Destroy a User VM + * @vmid: User VM ID + * + * Return: 0 on success, <0 on failure + */ +static inline long hcall_destroy_vm(u64 vmid) +{ + return acrn_hypercall1(HC_DESTROY_VM, vmid); +} + +/** + * hcall_reset_vm() - Reset a User VM + * @vmid: User VM ID + * + * Return: 0 on success, <0 on failure + */ +static inline long hcall_reset_vm(u64 vmid) +{ + return acrn_hypercall1(HC_RESET_VM, vmid); +} + +#endif /* __ACRN_HSM_HYPERCALL_H */ diff --git a/drivers/virt/acrn/vm.c b/drivers/virt/acrn/vm.c new file mode 100644 index 000000000000..3f667ac8ac1e --- /dev/null +++ b/drivers/virt/acrn/vm.c @@ -0,0 +1,68 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * ACRN_HSM: Virtual Machine management + * + * Copyright (C) 2020 Intel Corporation. All rights reserved. + * + * Authors: + * Jason Chen CJ + * Yakui Zhao + */ +#include +#include +#include + +#include "acrn_drv.h" + +/* List of VMs */ +static LIST_HEAD(acrn_vm_list); +/* To protect acrn_vm_list */ +static DEFINE_MUTEX(acrn_vm_list_lock); + +struct acrn_vm *acrn_vm_create(struct acrn_vm *vm, + struct acrn_vm_creation *vm_param) +{ + int ret; + + ret = hcall_create_vm(virt_to_phys(vm_param)); + if (ret < 0 || vm_param->vmid == ACRN_INVALID_VMID) { + dev_err(acrn_dev.this_device, + "Failed to create VM! Error: %d\n", ret); + return NULL; + } + + vm->vmid = vm_param->vmid; + vm->vcpu_num = vm_param->vcpu_num; + + mutex_lock(&acrn_vm_list_lock); + list_add(&vm->list, &acrn_vm_list); + mutex_unlock(&acrn_vm_list_lock); + + dev_dbg(acrn_dev.this_device, "VM %u created.\n", vm->vmid); + return vm; +} + +int acrn_vm_destroy(struct acrn_vm *vm) +{ + int ret; + + if (vm->vmid == ACRN_INVALID_VMID || + test_and_set_bit(ACRN_VM_FLAG_DESTROYED, &vm->flags)) + return 0; + + /* Remove from global VM list */ + mutex_lock(&acrn_vm_list_lock); + list_del_init(&vm->list); + mutex_unlock(&acrn_vm_list_lock); + + ret = hcall_destroy_vm(vm->vmid); + if (ret < 0) { + dev_err(acrn_dev.this_device, + "Failed to destroy VM %u\n", vm->vmid); + clear_bit(ACRN_VM_FLAG_DESTROYED, &vm->flags); + return ret; + } + dev_dbg(acrn_dev.this_device, "VM %u destroyed.\n", vm->vmid); + vm->vmid = ACRN_INVALID_VMID; + return 0; +} diff --git a/include/uapi/linux/acrn.h b/include/uapi/linux/acrn.h new file mode 100644 index 000000000000..32521168075f --- /dev/null +++ b/include/uapi/linux/acrn.h @@ -0,0 +1,58 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Userspace interface for /dev/acrn_hsm - ACRN Hypervisor Service Module + * + * This file can be used by applications that need to communicate with the HSM + * via the ioctl interface. + * + * Copyright (C) 2021 Intel Corporation. All rights reserved. + */ + +#ifndef _UAPI_ACRN_H +#define _UAPI_ACRN_H + +#include +#include + +/** + * struct acrn_vm_creation - Info to create a User VM + * @vmid: User VM ID returned from the hypervisor + * @reserved0: Reserved and must be 0 + * @vcpu_num: Number of vCPU in the VM. Return from hypervisor. + * @reserved1: Reserved and must be 0 + * @uuid: UUID of the VM. Pass to hypervisor directly. + * @vm_flag: Flag of the VM creating. Pass to hypervisor directly. + * @ioreq_buf: Service VM GPA of I/O request buffer. Pass to + * hypervisor directly. + * @cpu_affinity: CPU affinity of the VM. Pass to hypervisor directly. + * It's a bitmap which indicates CPUs used by the VM. + */ +struct acrn_vm_creation { + __u16 vmid; + __u16 reserved0; + __u16 vcpu_num; + __u16 reserved1; + guid_t uuid; + __u64 vm_flag; + __u64 ioreq_buf; + __u64 cpu_affinity; +}; + +/* The ioctl type, documented in ioctl-number.rst */ +#define ACRN_IOCTL_TYPE 0xA2 + +/* + * Common IOCTL IDs definition for ACRN userspace + */ +#define ACRN_IOCTL_CREATE_VM \ + _IOWR(ACRN_IOCTL_TYPE, 0x10, struct acrn_vm_creation) +#define ACRN_IOCTL_DESTROY_VM \ + _IO(ACRN_IOCTL_TYPE, 0x11) +#define ACRN_IOCTL_START_VM \ + _IO(ACRN_IOCTL_TYPE, 0x12) +#define ACRN_IOCTL_PAUSE_VM \ + _IO(ACRN_IOCTL_TYPE, 0x13) +#define ACRN_IOCTL_RESET_VM \ + _IO(ACRN_IOCTL_TYPE, 0x15) + +#endif /* _UAPI_ACRN_H */ -- cgit v1.2.3 From 2ad2aaee1bc9568d0c146463483d2c926ef20055 Mon Sep 17 00:00:00 2001 From: Shuo Liu Date: Sun, 7 Feb 2021 11:10:29 +0800 Subject: virt: acrn: Introduce an ioctl to set vCPU registers state A virtual CPU of User VM has different context due to the different registers state. ACRN userspace needs to set the virtual CPU registers state (e.g. giving a initial registers state to a virtual BSP of a User VM). HSM provides an ioctl ACRN_IOCTL_SET_VCPU_REGS to do the virtual CPU registers state setting. The ioctl passes the registers state from ACRN userspace to the hypervisor directly. Cc: Zhi Wang Cc: Zhenyu Wang Cc: Yu Wang Cc: Reinette Chatre Cc: Greg Kroah-Hartman Reviewed-by: Zhi Wang Reviewed-by: Reinette Chatre Signed-off-by: Shuo Liu Link: https://lore.kernel.org/r/20210207031040.49576-8-shuo.a.liu@intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/virt/acrn/hsm.c | 34 +++++++++++- drivers/virt/acrn/hypercall.h | 13 +++++ include/uapi/linux/acrn.h | 119 ++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 165 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/virt/acrn/hsm.c b/drivers/virt/acrn/hsm.c index 5fd933471683..ee5cc7413239 100644 --- a/drivers/virt/acrn/hsm.c +++ b/drivers/virt/acrn/hsm.c @@ -9,6 +9,7 @@ * Yakui Zhao */ +#include #include #include #include @@ -46,7 +47,8 @@ static long acrn_dev_ioctl(struct file *filp, unsigned int cmd, { struct acrn_vm *vm = filp->private_data; struct acrn_vm_creation *vm_param; - int ret = 0; + struct acrn_vcpu_regs *cpu_regs; + int i, ret = 0; if (vm->vmid == ACRN_INVALID_VMID && cmd != ACRN_IOCTL_CREATE_VM) { dev_dbg(acrn_dev.this_device, @@ -100,6 +102,36 @@ static long acrn_dev_ioctl(struct file *filp, unsigned int cmd, case ACRN_IOCTL_DESTROY_VM: ret = acrn_vm_destroy(vm); break; + case ACRN_IOCTL_SET_VCPU_REGS: + cpu_regs = memdup_user((void __user *)ioctl_param, + sizeof(struct acrn_vcpu_regs)); + if (IS_ERR(cpu_regs)) + return PTR_ERR(cpu_regs); + + for (i = 0; i < ARRAY_SIZE(cpu_regs->reserved); i++) + if (cpu_regs->reserved[i]) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(cpu_regs->vcpu_regs.reserved_32); i++) + if (cpu_regs->vcpu_regs.reserved_32[i]) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(cpu_regs->vcpu_regs.reserved_64); i++) + if (cpu_regs->vcpu_regs.reserved_64[i]) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(cpu_regs->vcpu_regs.gdt.reserved); i++) + if (cpu_regs->vcpu_regs.gdt.reserved[i] | + cpu_regs->vcpu_regs.idt.reserved[i]) + return -EINVAL; + + ret = hcall_set_vcpu_regs(vm->vmid, virt_to_phys(cpu_regs)); + if (ret < 0) + dev_dbg(acrn_dev.this_device, + "Failed to set regs state of VM%u!\n", + vm->vmid); + kfree(cpu_regs); + break; default: dev_dbg(acrn_dev.this_device, "Unknown IOCTL 0x%x!\n", cmd); ret = -ENOTTY; diff --git a/drivers/virt/acrn/hypercall.h b/drivers/virt/acrn/hypercall.h index 426b66cadb1f..f29cfae08862 100644 --- a/drivers/virt/acrn/hypercall.h +++ b/drivers/virt/acrn/hypercall.h @@ -19,6 +19,7 @@ #define HC_START_VM _HC_ID(HC_ID, HC_ID_VM_BASE + 0x02) #define HC_PAUSE_VM _HC_ID(HC_ID, HC_ID_VM_BASE + 0x03) #define HC_RESET_VM _HC_ID(HC_ID, HC_ID_VM_BASE + 0x05) +#define HC_SET_VCPU_REGS _HC_ID(HC_ID, HC_ID_VM_BASE + 0x06) /** * hcall_create_vm() - Create a User VM @@ -75,4 +76,16 @@ static inline long hcall_reset_vm(u64 vmid) return acrn_hypercall1(HC_RESET_VM, vmid); } +/** + * hcall_set_vcpu_regs() - Set up registers of virtual CPU of a User VM + * @vmid: User VM ID + * @regs_state: Service VM GPA of registers state + * + * Return: 0 on success, <0 on failure + */ +static inline long hcall_set_vcpu_regs(u64 vmid, u64 regs_state) +{ + return acrn_hypercall2(HC_SET_VCPU_REGS, vmid, regs_state); +} + #endif /* __ACRN_HSM_HYPERCALL_H */ diff --git a/include/uapi/linux/acrn.h b/include/uapi/linux/acrn.h index 32521168075f..775c58bad026 100644 --- a/include/uapi/linux/acrn.h +++ b/include/uapi/linux/acrn.h @@ -38,6 +38,123 @@ struct acrn_vm_creation { __u64 cpu_affinity; }; +/** + * struct acrn_gp_regs - General registers of a User VM + * @rax: Value of register RAX + * @rcx: Value of register RCX + * @rdx: Value of register RDX + * @rbx: Value of register RBX + * @rsp: Value of register RSP + * @rbp: Value of register RBP + * @rsi: Value of register RSI + * @rdi: Value of register RDI + * @r8: Value of register R8 + * @r9: Value of register R9 + * @r10: Value of register R10 + * @r11: Value of register R11 + * @r12: Value of register R12 + * @r13: Value of register R13 + * @r14: Value of register R14 + * @r15: Value of register R15 + */ +struct acrn_gp_regs { + __le64 rax; + __le64 rcx; + __le64 rdx; + __le64 rbx; + __le64 rsp; + __le64 rbp; + __le64 rsi; + __le64 rdi; + __le64 r8; + __le64 r9; + __le64 r10; + __le64 r11; + __le64 r12; + __le64 r13; + __le64 r14; + __le64 r15; +}; + +/** + * struct acrn_descriptor_ptr - Segment descriptor table of a User VM. + * @limit: Limit field. + * @base: Base field. + * @reserved: Reserved and must be 0. + */ +struct acrn_descriptor_ptr { + __le16 limit; + __le64 base; + __le16 reserved[3]; +} __attribute__ ((__packed__)); + +/** + * struct acrn_regs - Registers structure of a User VM + * @gprs: General registers + * @gdt: Global Descriptor Table + * @idt: Interrupt Descriptor Table + * @rip: Value of register RIP + * @cs_base: Base of code segment selector + * @cr0: Value of register CR0 + * @cr4: Value of register CR4 + * @cr3: Value of register CR3 + * @ia32_efer: Value of IA32_EFER MSR + * @rflags: Value of regsiter RFLAGS + * @reserved_64: Reserved and must be 0 + * @cs_ar: Attribute field of code segment selector + * @cs_limit: Limit field of code segment selector + * @reserved_32: Reserved and must be 0 + * @cs_sel: Value of code segment selector + * @ss_sel: Value of stack segment selector + * @ds_sel: Value of data segment selector + * @es_sel: Value of extra segment selector + * @fs_sel: Value of FS selector + * @gs_sel: Value of GS selector + * @ldt_sel: Value of LDT descriptor selector + * @tr_sel: Value of TSS descriptor selector + */ +struct acrn_regs { + struct acrn_gp_regs gprs; + struct acrn_descriptor_ptr gdt; + struct acrn_descriptor_ptr idt; + + __le64 rip; + __le64 cs_base; + __le64 cr0; + __le64 cr4; + __le64 cr3; + __le64 ia32_efer; + __le64 rflags; + __le64 reserved_64[4]; + + __le32 cs_ar; + __le32 cs_limit; + __le32 reserved_32[3]; + + __le16 cs_sel; + __le16 ss_sel; + __le16 ds_sel; + __le16 es_sel; + __le16 fs_sel; + __le16 gs_sel; + __le16 ldt_sel; + __le16 tr_sel; +}; + +/** + * struct acrn_vcpu_regs - Info of vCPU registers state + * @vcpu_id: vCPU ID + * @reserved: Reserved and must be 0 + * @vcpu_regs: vCPU registers state + * + * This structure will be passed to hypervisor directly. + */ +struct acrn_vcpu_regs { + __u16 vcpu_id; + __u16 reserved[3]; + struct acrn_regs vcpu_regs; +}; + /* The ioctl type, documented in ioctl-number.rst */ #define ACRN_IOCTL_TYPE 0xA2 @@ -54,5 +171,7 @@ struct acrn_vm_creation { _IO(ACRN_IOCTL_TYPE, 0x13) #define ACRN_IOCTL_RESET_VM \ _IO(ACRN_IOCTL_TYPE, 0x15) +#define ACRN_IOCTL_SET_VCPU_REGS \ + _IOW(ACRN_IOCTL_TYPE, 0x16, struct acrn_vcpu_regs) #endif /* _UAPI_ACRN_H */ -- cgit v1.2.3 From 88f537d5e8ddc89c2622f4a2bc1eb28455e8339c Mon Sep 17 00:00:00 2001 From: Shuo Liu Date: Sun, 7 Feb 2021 11:10:30 +0800 Subject: virt: acrn: Introduce EPT mapping management The HSM provides hypervisor services to the ACRN userspace. While launching a User VM, ACRN userspace needs to allocate memory and request the ACRN Hypervisor to set up the EPT mapping for the VM. A mapping cache is introduced for accelerating the translation between the Service VM kernel virtual address and User VM physical address. >From the perspective of the hypervisor, the types of GPA of User VM can be listed as following: 1) RAM region, which is used by User VM as system ram. 2) MMIO region, which is recognized by User VM as MMIO. MMIO region is used to be utilized for devices emulation. Generally, User VM RAM regions mapping is set up before VM started and is released in the User VM destruction. MMIO regions mapping may be set and unset dynamically during User VM running. To achieve this, ioctls ACRN_IOCTL_SET_MEMSEG and ACRN_IOCTL_UNSET_MEMSEG are introduced in HSM. Cc: Zhi Wang Cc: Zhenyu Wang Cc: Yu Wang Cc: Reinette Chatre Cc: Greg Kroah-Hartman Reviewed-by: Zhi Wang Reviewed-by: Reinette Chatre Signed-off-by: Shuo Liu Link: https://lore.kernel.org/r/20210207031040.49576-9-shuo.a.liu@intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/virt/acrn/Makefile | 2 +- drivers/virt/acrn/acrn_drv.h | 96 +++++++++++-- drivers/virt/acrn/hsm.c | 15 +++ drivers/virt/acrn/hypercall.h | 14 ++ drivers/virt/acrn/mm.c | 306 ++++++++++++++++++++++++++++++++++++++++++ drivers/virt/acrn/vm.c | 4 + include/uapi/linux/acrn.h | 49 +++++++ 7 files changed, 476 insertions(+), 10 deletions(-) create mode 100644 drivers/virt/acrn/mm.c (limited to 'include') diff --git a/drivers/virt/acrn/Makefile b/drivers/virt/acrn/Makefile index cf8b4ed5e74e..38bc44b6edcd 100644 --- a/drivers/virt/acrn/Makefile +++ b/drivers/virt/acrn/Makefile @@ -1,3 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_ACRN_HSM) := acrn.o -acrn-y := hsm.o vm.o +acrn-y := hsm.o vm.o mm.o diff --git a/drivers/virt/acrn/acrn_drv.h b/drivers/virt/acrn/acrn_drv.h index e5aba86cad8c..e47a45280eea 100644 --- a/drivers/virt/acrn/acrn_drv.h +++ b/drivers/virt/acrn/acrn_drv.h @@ -12,26 +12,104 @@ extern struct miscdevice acrn_dev; +#define ACRN_MEM_MAPPING_MAX 256 + +#define ACRN_MEM_REGION_ADD 0 +#define ACRN_MEM_REGION_DEL 2 +/** + * struct vm_memory_region_op - Hypervisor memory operation + * @type: Operation type (ACRN_MEM_REGION_*) + * @attr: Memory attribute (ACRN_MEM_TYPE_* | ACRN_MEM_ACCESS_*) + * @user_vm_pa: Physical address of User VM to be mapped. + * @service_vm_pa: Physical address of Service VM to be mapped. + * @size: Size of this region. + * + * Structure containing needed information that is provided to ACRN Hypervisor + * to manage the EPT mappings of a single memory region of the User VM. Several + * &struct vm_memory_region_op can be batched to ACRN Hypervisor, see &struct + * vm_memory_region_batch. + */ +struct vm_memory_region_op { + u32 type; + u32 attr; + u64 user_vm_pa; + u64 service_vm_pa; + u64 size; +}; + +/** + * struct vm_memory_region_batch - A batch of vm_memory_region_op. + * @vmid: A User VM ID. + * @reserved: Reserved. + * @regions_num: The number of vm_memory_region_op. + * @regions_gpa: Physical address of a vm_memory_region_op array. + * + * HC_VM_SET_MEMORY_REGIONS uses this structure to manage EPT mappings of + * multiple memory regions of a User VM. A &struct vm_memory_region_batch + * contains multiple &struct vm_memory_region_op for batch processing in the + * ACRN Hypervisor. + */ +struct vm_memory_region_batch { + u16 vmid; + u16 reserved[3]; + u32 regions_num; + u64 regions_gpa; +}; + +/** + * struct vm_memory_mapping - Memory map between a User VM and the Service VM + * @pages: Pages in Service VM kernel. + * @npages: Number of pages. + * @service_vm_va: Virtual address in Service VM kernel. + * @user_vm_pa: Physical address in User VM. + * @size: Size of this memory region. + * + * HSM maintains memory mappings between a User VM GPA and the Service VM + * kernel VA for accelerating the User VM GPA translation. + */ +struct vm_memory_mapping { + struct page **pages; + int npages; + void *service_vm_va; + u64 user_vm_pa; + size_t size; +}; + #define ACRN_INVALID_VMID (0xffffU) #define ACRN_VM_FLAG_DESTROYED 0U /** * struct acrn_vm - Properties of ACRN User VM. - * @list: Entry within global list of all VMs - * @vmid: User VM ID - * @vcpu_num: Number of virtual CPUs in the VM - * @flags: Flags (ACRN_VM_FLAG_*) of the VM. This is VM flag management - * in HSM which is different from the &acrn_vm_creation.vm_flag. + * @list: Entry within global list of all VMs. + * @vmid: User VM ID. + * @vcpu_num: Number of virtual CPUs in the VM. + * @flags: Flags (ACRN_VM_FLAG_*) of the VM. This is VM + * flag management in HSM which is different + * from the &acrn_vm_creation.vm_flag. + * @regions_mapping_lock: Lock to protect &acrn_vm.regions_mapping and + * &acrn_vm.regions_mapping_count. + * @regions_mapping: Memory mappings of this VM. + * @regions_mapping_count: Number of memory mapping of this VM. */ struct acrn_vm { - struct list_head list; - u16 vmid; - int vcpu_num; - unsigned long flags; + struct list_head list; + u16 vmid; + int vcpu_num; + unsigned long flags; + struct mutex regions_mapping_lock; + struct vm_memory_mapping regions_mapping[ACRN_MEM_MAPPING_MAX]; + int regions_mapping_count; }; struct acrn_vm *acrn_vm_create(struct acrn_vm *vm, struct acrn_vm_creation *vm_param); int acrn_vm_destroy(struct acrn_vm *vm); +int acrn_mm_region_add(struct acrn_vm *vm, u64 user_gpa, u64 service_gpa, + u64 size, u32 mem_type, u32 mem_access_right); +int acrn_mm_region_del(struct acrn_vm *vm, u64 user_gpa, u64 size); +int acrn_vm_memseg_map(struct acrn_vm *vm, struct acrn_vm_memmap *memmap); +int acrn_vm_memseg_unmap(struct acrn_vm *vm, struct acrn_vm_memmap *memmap); +int acrn_vm_ram_map(struct acrn_vm *vm, struct acrn_vm_memmap *memmap); +void acrn_vm_all_ram_unmap(struct acrn_vm *vm); #endif /* __ACRN_HSM_DRV_H */ diff --git a/drivers/virt/acrn/hsm.c b/drivers/virt/acrn/hsm.c index ee5cc7413239..2c40d3dc5e94 100644 --- a/drivers/virt/acrn/hsm.c +++ b/drivers/virt/acrn/hsm.c @@ -48,6 +48,7 @@ static long acrn_dev_ioctl(struct file *filp, unsigned int cmd, struct acrn_vm *vm = filp->private_data; struct acrn_vm_creation *vm_param; struct acrn_vcpu_regs *cpu_regs; + struct acrn_vm_memmap memmap; int i, ret = 0; if (vm->vmid == ACRN_INVALID_VMID && cmd != ACRN_IOCTL_CREATE_VM) { @@ -132,6 +133,20 @@ static long acrn_dev_ioctl(struct file *filp, unsigned int cmd, vm->vmid); kfree(cpu_regs); break; + case ACRN_IOCTL_SET_MEMSEG: + if (copy_from_user(&memmap, (void __user *)ioctl_param, + sizeof(memmap))) + return -EFAULT; + + ret = acrn_vm_memseg_map(vm, &memmap); + break; + case ACRN_IOCTL_UNSET_MEMSEG: + if (copy_from_user(&memmap, (void __user *)ioctl_param, + sizeof(memmap))) + return -EFAULT; + + ret = acrn_vm_memseg_unmap(vm, &memmap); + break; default: dev_dbg(acrn_dev.this_device, "Unknown IOCTL 0x%x!\n", cmd); ret = -ENOTTY; diff --git a/drivers/virt/acrn/hypercall.h b/drivers/virt/acrn/hypercall.h index f29cfae08862..a1a70a071713 100644 --- a/drivers/virt/acrn/hypercall.h +++ b/drivers/virt/acrn/hypercall.h @@ -21,6 +21,9 @@ #define HC_RESET_VM _HC_ID(HC_ID, HC_ID_VM_BASE + 0x05) #define HC_SET_VCPU_REGS _HC_ID(HC_ID, HC_ID_VM_BASE + 0x06) +#define HC_ID_MEM_BASE 0x40UL +#define HC_VM_SET_MEMORY_REGIONS _HC_ID(HC_ID, HC_ID_MEM_BASE + 0x02) + /** * hcall_create_vm() - Create a User VM * @vminfo: Service VM GPA of info of User VM creation @@ -88,4 +91,15 @@ static inline long hcall_set_vcpu_regs(u64 vmid, u64 regs_state) return acrn_hypercall2(HC_SET_VCPU_REGS, vmid, regs_state); } +/** + * hcall_set_memory_regions() - Inform the hypervisor to set up EPT mappings + * @regions_pa: Service VM GPA of &struct vm_memory_region_batch + * + * Return: 0 on success, <0 on failure + */ +static inline long hcall_set_memory_regions(u64 regions_pa) +{ + return acrn_hypercall1(HC_VM_SET_MEMORY_REGIONS, regions_pa); +} + #endif /* __ACRN_HSM_HYPERCALL_H */ diff --git a/drivers/virt/acrn/mm.c b/drivers/virt/acrn/mm.c new file mode 100644 index 000000000000..c4f2e15c8a2b --- /dev/null +++ b/drivers/virt/acrn/mm.c @@ -0,0 +1,306 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * ACRN: Memory mapping management + * + * Copyright (C) 2020 Intel Corporation. All rights reserved. + * + * Authors: + * Fei Li + * Shuo Liu + */ + +#include +#include +#include + +#include "acrn_drv.h" + +static int modify_region(struct acrn_vm *vm, struct vm_memory_region_op *region) +{ + struct vm_memory_region_batch *regions; + int ret; + + regions = kzalloc(sizeof(*regions), GFP_KERNEL); + if (!regions) + return -ENOMEM; + + regions->vmid = vm->vmid; + regions->regions_num = 1; + regions->regions_gpa = virt_to_phys(region); + + ret = hcall_set_memory_regions(virt_to_phys(regions)); + if (ret < 0) + dev_dbg(acrn_dev.this_device, + "Failed to set memory region for VM[%u]!\n", vm->vmid); + + kfree(regions); + return ret; +} + +/** + * acrn_mm_region_add() - Set up the EPT mapping of a memory region. + * @vm: User VM. + * @user_gpa: A GPA of User VM. + * @service_gpa: A GPA of Service VM. + * @size: Size of the region. + * @mem_type: Combination of ACRN_MEM_TYPE_*. + * @mem_access_right: Combination of ACRN_MEM_ACCESS_*. + * + * Return: 0 on success, <0 on error. + */ +int acrn_mm_region_add(struct acrn_vm *vm, u64 user_gpa, u64 service_gpa, + u64 size, u32 mem_type, u32 mem_access_right) +{ + struct vm_memory_region_op *region; + int ret = 0; + + region = kzalloc(sizeof(*region), GFP_KERNEL); + if (!region) + return -ENOMEM; + + region->type = ACRN_MEM_REGION_ADD; + region->user_vm_pa = user_gpa; + region->service_vm_pa = service_gpa; + region->size = size; + region->attr = ((mem_type & ACRN_MEM_TYPE_MASK) | + (mem_access_right & ACRN_MEM_ACCESS_RIGHT_MASK)); + ret = modify_region(vm, region); + + dev_dbg(acrn_dev.this_device, + "%s: user-GPA[%pK] service-GPA[%pK] size[0x%llx].\n", + __func__, (void *)user_gpa, (void *)service_gpa, size); + kfree(region); + return ret; +} + +/** + * acrn_mm_region_del() - Del the EPT mapping of a memory region. + * @vm: User VM. + * @user_gpa: A GPA of the User VM. + * @size: Size of the region. + * + * Return: 0 on success, <0 for error. + */ +int acrn_mm_region_del(struct acrn_vm *vm, u64 user_gpa, u64 size) +{ + struct vm_memory_region_op *region; + int ret = 0; + + region = kzalloc(sizeof(*region), GFP_KERNEL); + if (!region) + return -ENOMEM; + + region->type = ACRN_MEM_REGION_DEL; + region->user_vm_pa = user_gpa; + region->service_vm_pa = 0UL; + region->size = size; + region->attr = 0U; + + ret = modify_region(vm, region); + + dev_dbg(acrn_dev.this_device, "%s: user-GPA[%pK] size[0x%llx].\n", + __func__, (void *)user_gpa, size); + kfree(region); + return ret; +} + +int acrn_vm_memseg_map(struct acrn_vm *vm, struct acrn_vm_memmap *memmap) +{ + int ret; + + if (memmap->type == ACRN_MEMMAP_RAM) + return acrn_vm_ram_map(vm, memmap); + + if (memmap->type != ACRN_MEMMAP_MMIO) { + dev_dbg(acrn_dev.this_device, + "Invalid memmap type: %u\n", memmap->type); + return -EINVAL; + } + + ret = acrn_mm_region_add(vm, memmap->user_vm_pa, + memmap->service_vm_pa, memmap->len, + ACRN_MEM_TYPE_UC, memmap->attr); + if (ret < 0) + dev_dbg(acrn_dev.this_device, + "Add memory region failed, VM[%u]!\n", vm->vmid); + + return ret; +} + +int acrn_vm_memseg_unmap(struct acrn_vm *vm, struct acrn_vm_memmap *memmap) +{ + int ret; + + if (memmap->type != ACRN_MEMMAP_MMIO) { + dev_dbg(acrn_dev.this_device, + "Invalid memmap type: %u\n", memmap->type); + return -EINVAL; + } + + ret = acrn_mm_region_del(vm, memmap->user_vm_pa, memmap->len); + if (ret < 0) + dev_dbg(acrn_dev.this_device, + "Del memory region failed, VM[%u]!\n", vm->vmid); + + return ret; +} + +/** + * acrn_vm_ram_map() - Create a RAM EPT mapping of User VM. + * @vm: The User VM pointer + * @memmap: Info of the EPT mapping + * + * Return: 0 on success, <0 for error. + */ +int acrn_vm_ram_map(struct acrn_vm *vm, struct acrn_vm_memmap *memmap) +{ + struct vm_memory_region_batch *regions_info; + int nr_pages, i = 0, order, nr_regions = 0; + struct vm_memory_mapping *region_mapping; + struct vm_memory_region_op *vm_region; + struct page **pages = NULL, *page; + void *remap_vaddr; + int ret, pinned; + u64 user_vm_pa; + + if (!vm || !memmap) + return -EINVAL; + + /* Get the page number of the map region */ + nr_pages = memmap->len >> PAGE_SHIFT; + pages = vzalloc(nr_pages * sizeof(struct page *)); + if (!pages) + return -ENOMEM; + + /* Lock the pages of user memory map region */ + pinned = pin_user_pages_fast(memmap->vma_base, + nr_pages, FOLL_WRITE | FOLL_LONGTERM, + pages); + if (pinned < 0) { + ret = pinned; + goto free_pages; + } else if (pinned != nr_pages) { + ret = -EFAULT; + goto put_pages; + } + + /* Create a kernel map for the map region */ + remap_vaddr = vmap(pages, nr_pages, VM_MAP, PAGE_KERNEL); + if (!remap_vaddr) { + ret = -ENOMEM; + goto put_pages; + } + + /* Record Service VM va <-> User VM pa mapping */ + mutex_lock(&vm->regions_mapping_lock); + region_mapping = &vm->regions_mapping[vm->regions_mapping_count]; + if (vm->regions_mapping_count < ACRN_MEM_MAPPING_MAX) { + region_mapping->pages = pages; + region_mapping->npages = nr_pages; + region_mapping->size = memmap->len; + region_mapping->service_vm_va = remap_vaddr; + region_mapping->user_vm_pa = memmap->user_vm_pa; + vm->regions_mapping_count++; + } else { + dev_warn(acrn_dev.this_device, + "Run out of memory mapping slots!\n"); + ret = -ENOMEM; + mutex_unlock(&vm->regions_mapping_lock); + goto unmap_no_count; + } + mutex_unlock(&vm->regions_mapping_lock); + + /* Calculate count of vm_memory_region_op */ + while (i < nr_pages) { + page = pages[i]; + VM_BUG_ON_PAGE(PageTail(page), page); + order = compound_order(page); + nr_regions++; + i += 1 << order; + } + + /* Prepare the vm_memory_region_batch */ + regions_info = kzalloc(sizeof(*regions_info) + + sizeof(*vm_region) * nr_regions, + GFP_KERNEL); + if (!regions_info) { + ret = -ENOMEM; + goto unmap_kernel_map; + } + + /* Fill each vm_memory_region_op */ + vm_region = (struct vm_memory_region_op *)(regions_info + 1); + regions_info->vmid = vm->vmid; + regions_info->regions_num = nr_regions; + regions_info->regions_gpa = virt_to_phys(vm_region); + user_vm_pa = memmap->user_vm_pa; + i = 0; + while (i < nr_pages) { + u32 region_size; + + page = pages[i]; + VM_BUG_ON_PAGE(PageTail(page), page); + order = compound_order(page); + region_size = PAGE_SIZE << order; + vm_region->type = ACRN_MEM_REGION_ADD; + vm_region->user_vm_pa = user_vm_pa; + vm_region->service_vm_pa = page_to_phys(page); + vm_region->size = region_size; + vm_region->attr = (ACRN_MEM_TYPE_WB & ACRN_MEM_TYPE_MASK) | + (memmap->attr & ACRN_MEM_ACCESS_RIGHT_MASK); + + vm_region++; + user_vm_pa += region_size; + i += 1 << order; + } + + /* Inform the ACRN Hypervisor to set up EPT mappings */ + ret = hcall_set_memory_regions(virt_to_phys(regions_info)); + if (ret < 0) { + dev_dbg(acrn_dev.this_device, + "Failed to set regions, VM[%u]!\n", vm->vmid); + goto unset_region; + } + kfree(regions_info); + + dev_dbg(acrn_dev.this_device, + "%s: VM[%u] service-GVA[%pK] user-GPA[%pK] size[0x%llx]\n", + __func__, vm->vmid, + remap_vaddr, (void *)memmap->user_vm_pa, memmap->len); + return ret; + +unset_region: + kfree(regions_info); +unmap_kernel_map: + mutex_lock(&vm->regions_mapping_lock); + vm->regions_mapping_count--; + mutex_unlock(&vm->regions_mapping_lock); +unmap_no_count: + vunmap(remap_vaddr); +put_pages: + for (i = 0; i < pinned; i++) + unpin_user_page(pages[i]); +free_pages: + vfree(pages); + return ret; +} + +/** + * acrn_vm_all_ram_unmap() - Destroy a RAM EPT mapping of User VM. + * @vm: The User VM + */ +void acrn_vm_all_ram_unmap(struct acrn_vm *vm) +{ + struct vm_memory_mapping *region_mapping; + int i, j; + + mutex_lock(&vm->regions_mapping_lock); + for (i = 0; i < vm->regions_mapping_count; i++) { + region_mapping = &vm->regions_mapping[i]; + vunmap(region_mapping->service_vm_va); + for (j = 0; j < region_mapping->npages; j++) + unpin_user_page(region_mapping->pages[j]); + vfree(region_mapping->pages); + } + mutex_unlock(&vm->regions_mapping_lock); +} diff --git a/drivers/virt/acrn/vm.c b/drivers/virt/acrn/vm.c index 3f667ac8ac1e..ff5df7acb551 100644 --- a/drivers/virt/acrn/vm.c +++ b/drivers/virt/acrn/vm.c @@ -31,6 +31,7 @@ struct acrn_vm *acrn_vm_create(struct acrn_vm *vm, return NULL; } + mutex_init(&vm->regions_mapping_lock); vm->vmid = vm_param->vmid; vm->vcpu_num = vm_param->vcpu_num; @@ -62,6 +63,9 @@ int acrn_vm_destroy(struct acrn_vm *vm) clear_bit(ACRN_VM_FLAG_DESTROYED, &vm->flags); return ret; } + + acrn_vm_all_ram_unmap(vm); + dev_dbg(acrn_dev.this_device, "VM %u destroyed.\n", vm->vmid); vm->vmid = ACRN_INVALID_VMID; return 0; diff --git a/include/uapi/linux/acrn.h b/include/uapi/linux/acrn.h index 775c58bad026..ec4c61e7c170 100644 --- a/include/uapi/linux/acrn.h +++ b/include/uapi/linux/acrn.h @@ -155,6 +155,50 @@ struct acrn_vcpu_regs { struct acrn_regs vcpu_regs; }; +#define ACRN_MEM_ACCESS_RIGHT_MASK 0x00000007U +#define ACRN_MEM_ACCESS_READ 0x00000001U +#define ACRN_MEM_ACCESS_WRITE 0x00000002U +#define ACRN_MEM_ACCESS_EXEC 0x00000004U +#define ACRN_MEM_ACCESS_RWX (ACRN_MEM_ACCESS_READ | \ + ACRN_MEM_ACCESS_WRITE | \ + ACRN_MEM_ACCESS_EXEC) + +#define ACRN_MEM_TYPE_MASK 0x000007C0U +#define ACRN_MEM_TYPE_WB 0x00000040U +#define ACRN_MEM_TYPE_WT 0x00000080U +#define ACRN_MEM_TYPE_UC 0x00000100U +#define ACRN_MEM_TYPE_WC 0x00000200U +#define ACRN_MEM_TYPE_WP 0x00000400U + +/* Memory mapping types */ +#define ACRN_MEMMAP_RAM 0 +#define ACRN_MEMMAP_MMIO 1 + +/** + * struct acrn_vm_memmap - A EPT memory mapping info for a User VM. + * @type: Type of the memory mapping (ACRM_MEMMAP_*). + * Pass to hypervisor directly. + * @attr: Attribute of the memory mapping. + * Pass to hypervisor directly. + * @user_vm_pa: Physical address of User VM. + * Pass to hypervisor directly. + * @service_vm_pa: Physical address of Service VM. + * Pass to hypervisor directly. + * @vma_base: VMA address of Service VM. Pass to hypervisor directly. + * @len: Length of the memory mapping. + * Pass to hypervisor directly. + */ +struct acrn_vm_memmap { + __u32 type; + __u32 attr; + __u64 user_vm_pa; + union { + __u64 service_vm_pa; + __u64 vma_base; + }; + __u64 len; +}; + /* The ioctl type, documented in ioctl-number.rst */ #define ACRN_IOCTL_TYPE 0xA2 @@ -174,4 +218,9 @@ struct acrn_vcpu_regs { #define ACRN_IOCTL_SET_VCPU_REGS \ _IOW(ACRN_IOCTL_TYPE, 0x16, struct acrn_vcpu_regs) +#define ACRN_IOCTL_SET_MEMSEG \ + _IOW(ACRN_IOCTL_TYPE, 0x41, struct acrn_vm_memmap) +#define ACRN_IOCTL_UNSET_MEMSEG \ + _IOW(ACRN_IOCTL_TYPE, 0x42, struct acrn_vm_memmap) + #endif /* _UAPI_ACRN_H */ -- cgit v1.2.3 From 72f293de3ff40b57db573c1bf623f494f3446f74 Mon Sep 17 00:00:00 2001 From: Shuo Liu Date: Sun, 7 Feb 2021 11:10:31 +0800 Subject: virt: acrn: Introduce I/O request management An I/O request of a User VM, which is constructed by the hypervisor, is distributed by the ACRN Hypervisor Service Module to an I/O client corresponding to the address range of the I/O request. For each User VM, there is a shared 4-KByte memory region used for I/O requests communication between the hypervisor and Service VM. An I/O request is a 256-byte structure buffer, which is 'struct acrn_io_request', that is filled by an I/O handler of the hypervisor when a trapped I/O access happens in a User VM. ACRN userspace in the Service VM first allocates a 4-KByte page and passes the GPA (Guest Physical Address) of the buffer to the hypervisor. The buffer is used as an array of 16 I/O request slots with each I/O request slot being 256 bytes. This array is indexed by vCPU ID. An I/O client, which is 'struct acrn_ioreq_client', is responsible for handling User VM I/O requests whose accessed GPA falls in a certain range. Multiple I/O clients can be associated with each User VM. There is a special client associated with each User VM, called the default client, that handles all I/O requests that do not fit into the range of any other I/O clients. The ACRN userspace acts as the default client for each User VM. The state transitions of a ACRN I/O request are as follows. FREE -> PENDING -> PROCESSING -> COMPLETE -> FREE -> ... FREE: this I/O request slot is empty PENDING: a valid I/O request is pending in this slot PROCESSING: the I/O request is being processed COMPLETE: the I/O request has been processed An I/O request in COMPLETE or FREE state is owned by the hypervisor. HSM and ACRN userspace are in charge of processing the others. The processing flow of I/O requests are listed as following: a) The I/O handler of the hypervisor will fill an I/O request with PENDING state when a trapped I/O access happens in a User VM. b) The hypervisor makes an upcall, which is a notification interrupt, to the Service VM. c) The upcall handler schedules a worker to dispatch I/O requests. d) The worker looks for the PENDING I/O requests, assigns them to different registered clients based on the address of the I/O accesses, updates their state to PROCESSING, and notifies the corresponding client to handle. e) The notified client handles the assigned I/O requests. f) The HSM updates I/O requests states to COMPLETE and notifies the hypervisor of the completion via hypercalls. Cc: Davidlohr Bueso Cc: Zhi Wang Cc: Zhenyu Wang Cc: Yu Wang Cc: Reinette Chatre Cc: Greg Kroah-Hartman Reviewed-by: Zhi Wang Reviewed-by: Reinette Chatre Acked-by: Davidlohr Bueso Signed-off-by: Shuo Liu Link: https://lore.kernel.org/r/20210207031040.49576-10-shuo.a.liu@intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/virt/acrn/Makefile | 2 +- drivers/virt/acrn/acrn_drv.h | 82 +++++++ drivers/virt/acrn/hsm.c | 43 +++- drivers/virt/acrn/hypercall.h | 28 +++ drivers/virt/acrn/ioreq.c | 521 ++++++++++++++++++++++++++++++++++++++++++ drivers/virt/acrn/vm.c | 27 ++- include/uapi/linux/acrn.h | 150 ++++++++++++ 7 files changed, 843 insertions(+), 10 deletions(-) create mode 100644 drivers/virt/acrn/ioreq.c (limited to 'include') diff --git a/drivers/virt/acrn/Makefile b/drivers/virt/acrn/Makefile index 38bc44b6edcd..21721cbf6a80 100644 --- a/drivers/virt/acrn/Makefile +++ b/drivers/virt/acrn/Makefile @@ -1,3 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_ACRN_HSM) := acrn.o -acrn-y := hsm.o vm.o mm.o +acrn-y := hsm.o vm.o mm.o ioreq.o diff --git a/drivers/virt/acrn/acrn_drv.h b/drivers/virt/acrn/acrn_drv.h index e47a45280eea..68bd8db6c8be 100644 --- a/drivers/virt/acrn/acrn_drv.h +++ b/drivers/virt/acrn/acrn_drv.h @@ -12,10 +12,15 @@ extern struct miscdevice acrn_dev; +#define ACRN_NAME_LEN 16 #define ACRN_MEM_MAPPING_MAX 256 #define ACRN_MEM_REGION_ADD 0 #define ACRN_MEM_REGION_DEL 2 + +struct acrn_vm; +struct acrn_ioreq_client; + /** * struct vm_memory_region_op - Hypervisor memory operation * @type: Operation type (ACRN_MEM_REGION_*) @@ -75,9 +80,63 @@ struct vm_memory_mapping { size_t size; }; +/** + * struct acrn_ioreq_buffer - Data for setting the ioreq buffer of User VM + * @ioreq_buf: The GPA of the IO request shared buffer of a VM + * + * The parameter for the HC_SET_IOREQ_BUFFER hypercall used to set up + * the shared I/O request buffer between Service VM and ACRN hypervisor. + */ +struct acrn_ioreq_buffer { + u64 ioreq_buf; +}; + +struct acrn_ioreq_range { + struct list_head list; + u32 type; + u64 start; + u64 end; +}; + +#define ACRN_IOREQ_CLIENT_DESTROYING 0U +typedef int (*ioreq_handler_t)(struct acrn_ioreq_client *client, + struct acrn_io_request *req); +/** + * struct acrn_ioreq_client - Structure of I/O client. + * @name: Client name + * @vm: The VM that the client belongs to + * @list: List node for this acrn_ioreq_client + * @is_default: If this client is the default one + * @flags: Flags (ACRN_IOREQ_CLIENT_*) + * @range_list: I/O ranges + * @range_lock: Lock to protect range_list + * @ioreqs_map: The pending I/O requests bitmap. + * @handler: I/O requests handler of this client + * @thread: The thread which executes the handler + * @wq: The wait queue for the handler thread parking + * @priv: Data for the thread + */ +struct acrn_ioreq_client { + char name[ACRN_NAME_LEN]; + struct acrn_vm *vm; + struct list_head list; + bool is_default; + unsigned long flags; + struct list_head range_list; + rwlock_t range_lock; + DECLARE_BITMAP(ioreqs_map, ACRN_IO_REQUEST_MAX); + ioreq_handler_t handler; + struct task_struct *thread; + wait_queue_head_t wq; + void *priv; +}; + #define ACRN_INVALID_VMID (0xffffU) #define ACRN_VM_FLAG_DESTROYED 0U +#define ACRN_VM_FLAG_CLEARING_IOREQ 1U +extern struct list_head acrn_vm_list; +extern rwlock_t acrn_vm_list_lock; /** * struct acrn_vm - Properties of ACRN User VM. * @list: Entry within global list of all VMs. @@ -90,6 +149,11 @@ struct vm_memory_mapping { * &acrn_vm.regions_mapping_count. * @regions_mapping: Memory mappings of this VM. * @regions_mapping_count: Number of memory mapping of this VM. + * @ioreq_clients_lock: Lock to protect ioreq_clients and default_client + * @ioreq_clients: The I/O request clients list of this VM + * @default_client: The default I/O request client + * @ioreq_buf: I/O request shared buffer + * @ioreq_page: The page of the I/O request shared buffer */ struct acrn_vm { struct list_head list; @@ -99,6 +163,11 @@ struct acrn_vm { struct mutex regions_mapping_lock; struct vm_memory_mapping regions_mapping[ACRN_MEM_MAPPING_MAX]; int regions_mapping_count; + spinlock_t ioreq_clients_lock; + struct list_head ioreq_clients; + struct acrn_ioreq_client *default_client; + struct acrn_io_request_buffer *ioreq_buf; + struct page *ioreq_page; }; struct acrn_vm *acrn_vm_create(struct acrn_vm *vm, @@ -112,4 +181,17 @@ int acrn_vm_memseg_unmap(struct acrn_vm *vm, struct acrn_vm_memmap *memmap); int acrn_vm_ram_map(struct acrn_vm *vm, struct acrn_vm_memmap *memmap); void acrn_vm_all_ram_unmap(struct acrn_vm *vm); +int acrn_ioreq_init(struct acrn_vm *vm, u64 buf_vma); +void acrn_ioreq_deinit(struct acrn_vm *vm); +int acrn_ioreq_intr_setup(void); +void acrn_ioreq_intr_remove(void); +void acrn_ioreq_request_clear(struct acrn_vm *vm); +int acrn_ioreq_client_wait(struct acrn_ioreq_client *client); +int acrn_ioreq_request_default_complete(struct acrn_vm *vm, u16 vcpu); +struct acrn_ioreq_client *acrn_ioreq_client_create(struct acrn_vm *vm, + ioreq_handler_t handler, + void *data, bool is_default, + const char *name); +void acrn_ioreq_client_destroy(struct acrn_ioreq_client *client); + #endif /* __ACRN_HSM_DRV_H */ diff --git a/drivers/virt/acrn/hsm.c b/drivers/virt/acrn/hsm.c index 2c40d3dc5e94..1cc0c612dc09 100644 --- a/drivers/virt/acrn/hsm.c +++ b/drivers/virt/acrn/hsm.c @@ -48,6 +48,7 @@ static long acrn_dev_ioctl(struct file *filp, unsigned int cmd, struct acrn_vm *vm = filp->private_data; struct acrn_vm_creation *vm_param; struct acrn_vcpu_regs *cpu_regs; + struct acrn_ioreq_notify notify; struct acrn_vm_memmap memmap; int i, ret = 0; @@ -147,6 +148,35 @@ static long acrn_dev_ioctl(struct file *filp, unsigned int cmd, ret = acrn_vm_memseg_unmap(vm, &memmap); break; + case ACRN_IOCTL_CREATE_IOREQ_CLIENT: + if (vm->default_client) + return -EEXIST; + if (!acrn_ioreq_client_create(vm, NULL, NULL, true, "acrndm")) + ret = -EINVAL; + break; + case ACRN_IOCTL_DESTROY_IOREQ_CLIENT: + if (vm->default_client) + acrn_ioreq_client_destroy(vm->default_client); + break; + case ACRN_IOCTL_ATTACH_IOREQ_CLIENT: + if (vm->default_client) + ret = acrn_ioreq_client_wait(vm->default_client); + else + ret = -ENODEV; + break; + case ACRN_IOCTL_NOTIFY_REQUEST_FINISH: + if (copy_from_user(¬ify, (void __user *)ioctl_param, + sizeof(struct acrn_ioreq_notify))) + return -EFAULT; + + if (notify.reserved != 0) + return -EINVAL; + + ret = acrn_ioreq_request_default_complete(vm, notify.vcpu); + break; + case ACRN_IOCTL_CLEAR_VM_IOREQ: + acrn_ioreq_request_clear(vm); + break; default: dev_dbg(acrn_dev.this_device, "Unknown IOCTL 0x%x!\n", cmd); ret = -ENOTTY; @@ -188,14 +218,23 @@ static int __init hsm_init(void) return -EPERM; ret = misc_register(&acrn_dev); - if (ret) + if (ret) { pr_err("Create misc dev failed!\n"); + return ret; + } - return ret; + ret = acrn_ioreq_intr_setup(); + if (ret) { + pr_err("Setup I/O request handler failed!\n"); + misc_deregister(&acrn_dev); + return ret; + } + return 0; } static void __exit hsm_exit(void) { + acrn_ioreq_intr_remove(); misc_deregister(&acrn_dev); } module_init(hsm_init); diff --git a/drivers/virt/acrn/hypercall.h b/drivers/virt/acrn/hypercall.h index a1a70a071713..5eba29e3ed38 100644 --- a/drivers/virt/acrn/hypercall.h +++ b/drivers/virt/acrn/hypercall.h @@ -21,6 +21,10 @@ #define HC_RESET_VM _HC_ID(HC_ID, HC_ID_VM_BASE + 0x05) #define HC_SET_VCPU_REGS _HC_ID(HC_ID, HC_ID_VM_BASE + 0x06) +#define HC_ID_IOREQ_BASE 0x30UL +#define HC_SET_IOREQ_BUFFER _HC_ID(HC_ID, HC_ID_IOREQ_BASE + 0x00) +#define HC_NOTIFY_REQUEST_FINISH _HC_ID(HC_ID, HC_ID_IOREQ_BASE + 0x01) + #define HC_ID_MEM_BASE 0x40UL #define HC_VM_SET_MEMORY_REGIONS _HC_ID(HC_ID, HC_ID_MEM_BASE + 0x02) @@ -91,6 +95,30 @@ static inline long hcall_set_vcpu_regs(u64 vmid, u64 regs_state) return acrn_hypercall2(HC_SET_VCPU_REGS, vmid, regs_state); } +/** + * hcall_set_ioreq_buffer() - Set up the shared buffer for I/O Requests. + * @vmid: User VM ID + * @buffer: Service VM GPA of the shared buffer + * + * Return: 0 on success, <0 on failure + */ +static inline long hcall_set_ioreq_buffer(u64 vmid, u64 buffer) +{ + return acrn_hypercall2(HC_SET_IOREQ_BUFFER, vmid, buffer); +} + +/** + * hcall_notify_req_finish() - Notify ACRN Hypervisor of I/O request completion. + * @vmid: User VM ID + * @vcpu: The vCPU which initiated the I/O request + * + * Return: 0 on success, <0 on failure + */ +static inline long hcall_notify_req_finish(u64 vmid, u64 vcpu) +{ + return acrn_hypercall2(HC_NOTIFY_REQUEST_FINISH, vmid, vcpu); +} + /** * hcall_set_memory_regions() - Inform the hypervisor to set up EPT mappings * @regions_pa: Service VM GPA of &struct vm_memory_region_batch diff --git a/drivers/virt/acrn/ioreq.c b/drivers/virt/acrn/ioreq.c new file mode 100644 index 000000000000..51cb41ef7c72 --- /dev/null +++ b/drivers/virt/acrn/ioreq.c @@ -0,0 +1,521 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * ACRN_HSM: Handle I/O requests + * + * Copyright (C) 2020 Intel Corporation. All rights reserved. + * + * Authors: + * Jason Chen CJ + * Fengwei Yin + */ + +#include +#include +#include +#include +#include + +#include + +#include "acrn_drv.h" + +static void ioreq_pause(void); +static void ioreq_resume(void); + +static void ioreq_dispatcher(struct work_struct *work); +static struct workqueue_struct *ioreq_wq; +static DECLARE_WORK(ioreq_work, ioreq_dispatcher); + +static inline bool has_pending_request(struct acrn_ioreq_client *client) +{ + return !bitmap_empty(client->ioreqs_map, ACRN_IO_REQUEST_MAX); +} + +static inline bool is_destroying(struct acrn_ioreq_client *client) +{ + return test_bit(ACRN_IOREQ_CLIENT_DESTROYING, &client->flags); +} + +static int ioreq_complete_request(struct acrn_vm *vm, u16 vcpu, + struct acrn_io_request *acrn_req) +{ + bool polling_mode; + int ret = 0; + + polling_mode = acrn_req->completion_polling; + /* Add barrier() to make sure the writes are done before completion */ + smp_store_release(&acrn_req->processed, ACRN_IOREQ_STATE_COMPLETE); + + /* + * To fulfill the requirement of real-time in several industry + * scenarios, like automotive, ACRN can run under the partition mode, + * in which User VMs and Service VM are bound to dedicated CPU cores. + * Polling mode of handling the I/O request is introduced to achieve a + * faster I/O request handling. In polling mode, the hypervisor polls + * I/O request's completion. Once an I/O request is marked as + * ACRN_IOREQ_STATE_COMPLETE, hypervisor resumes from the polling point + * to continue the I/O request flow. Thus, the completion notification + * from HSM of I/O request is not needed. Please note, + * completion_polling needs to be read before the I/O request being + * marked as ACRN_IOREQ_STATE_COMPLETE to avoid racing with the + * hypervisor. + */ + if (!polling_mode) { + ret = hcall_notify_req_finish(vm->vmid, vcpu); + if (ret < 0) + dev_err(acrn_dev.this_device, + "Notify I/O request finished failed!\n"); + } + + return ret; +} + +static int acrn_ioreq_complete_request(struct acrn_ioreq_client *client, + u16 vcpu, + struct acrn_io_request *acrn_req) +{ + int ret; + + if (vcpu >= client->vm->vcpu_num) + return -EINVAL; + + clear_bit(vcpu, client->ioreqs_map); + if (!acrn_req) { + acrn_req = (struct acrn_io_request *)client->vm->ioreq_buf; + acrn_req += vcpu; + } + + ret = ioreq_complete_request(client->vm, vcpu, acrn_req); + + return ret; +} + +int acrn_ioreq_request_default_complete(struct acrn_vm *vm, u16 vcpu) +{ + int ret = 0; + + spin_lock_bh(&vm->ioreq_clients_lock); + if (vm->default_client) + ret = acrn_ioreq_complete_request(vm->default_client, + vcpu, NULL); + spin_unlock_bh(&vm->ioreq_clients_lock); + + return ret; +} + +/* + * ioreq_task() is the execution entity of handler thread of an I/O client. + * The handler callback of the I/O client is called within the handler thread. + */ +static int ioreq_task(void *data) +{ + struct acrn_ioreq_client *client = data; + struct acrn_io_request *req; + unsigned long *ioreqs_map; + int vcpu, ret; + + /* + * Lockless access to ioreqs_map is safe, because + * 1) set_bit() and clear_bit() are atomic operations. + * 2) I/O requests arrives serialized. The access flow of ioreqs_map is: + * set_bit() - in ioreq_work handler + * Handler callback handles corresponding I/O request + * clear_bit() - in handler thread (include ACRN userspace) + * Mark corresponding I/O request completed + * Loop again if a new I/O request occurs + */ + ioreqs_map = client->ioreqs_map; + while (!kthread_should_stop()) { + acrn_ioreq_client_wait(client); + while (has_pending_request(client)) { + vcpu = find_first_bit(ioreqs_map, client->vm->vcpu_num); + req = client->vm->ioreq_buf->req_slot + vcpu; + ret = client->handler(client, req); + if (ret < 0) { + dev_err(acrn_dev.this_device, + "IO handle failure: %d\n", ret); + break; + } + acrn_ioreq_complete_request(client, vcpu, req); + } + } + + return 0; +} + +/* + * For the non-default I/O clients, give them chance to complete the current + * I/O requests if there are any. For the default I/O client, it is safe to + * clear all pending I/O requests because the clearing request is from ACRN + * userspace. + */ +void acrn_ioreq_request_clear(struct acrn_vm *vm) +{ + struct acrn_ioreq_client *client; + bool has_pending = false; + unsigned long vcpu; + int retry = 10; + + /* + * IO requests of this VM will be completed directly in + * acrn_ioreq_dispatch if ACRN_VM_FLAG_CLEARING_IOREQ flag is set. + */ + set_bit(ACRN_VM_FLAG_CLEARING_IOREQ, &vm->flags); + + /* + * acrn_ioreq_request_clear is only called in VM reset case. Simply + * wait 100ms in total for the IO requests' completion. + */ + do { + spin_lock_bh(&vm->ioreq_clients_lock); + list_for_each_entry(client, &vm->ioreq_clients, list) { + has_pending = has_pending_request(client); + if (has_pending) + break; + } + spin_unlock_bh(&vm->ioreq_clients_lock); + + if (has_pending) + schedule_timeout_interruptible(HZ / 100); + } while (has_pending && --retry > 0); + if (retry == 0) + dev_warn(acrn_dev.this_device, + "%s cannot flush pending request!\n", client->name); + + /* Clear all ioreqs belonging to the default client */ + spin_lock_bh(&vm->ioreq_clients_lock); + client = vm->default_client; + if (client) { + vcpu = find_next_bit(client->ioreqs_map, + ACRN_IO_REQUEST_MAX, 0); + while (vcpu < ACRN_IO_REQUEST_MAX) { + acrn_ioreq_complete_request(client, vcpu, NULL); + vcpu = find_next_bit(client->ioreqs_map, + ACRN_IO_REQUEST_MAX, vcpu + 1); + } + } + spin_unlock_bh(&vm->ioreq_clients_lock); + + /* Clear ACRN_VM_FLAG_CLEARING_IOREQ flag after the clearing */ + clear_bit(ACRN_VM_FLAG_CLEARING_IOREQ, &vm->flags); +} + +int acrn_ioreq_client_wait(struct acrn_ioreq_client *client) +{ + if (client->is_default) { + /* + * In the default client, a user space thread waits on the + * waitqueue. The is_destroying() check is used to notify user + * space the client is going to be destroyed. + */ + wait_event_interruptible(client->wq, + has_pending_request(client) || + is_destroying(client)); + if (is_destroying(client)) + return -ENODEV; + } else { + wait_event_interruptible(client->wq, + has_pending_request(client) || + kthread_should_stop()); + } + + return 0; +} + +static bool in_range(struct acrn_ioreq_range *range, + struct acrn_io_request *req) +{ + bool ret = false; + + if (range->type == req->type) { + switch (req->type) { + case ACRN_IOREQ_TYPE_MMIO: + if (req->reqs.mmio_request.address >= range->start && + (req->reqs.mmio_request.address + + req->reqs.mmio_request.size - 1) <= range->end) + ret = true; + break; + case ACRN_IOREQ_TYPE_PORTIO: + if (req->reqs.pio_request.address >= range->start && + (req->reqs.pio_request.address + + req->reqs.pio_request.size - 1) <= range->end) + ret = true; + break; + default: + break; + } + } + + return ret; +} + +static struct acrn_ioreq_client *find_ioreq_client(struct acrn_vm *vm, + struct acrn_io_request *req) +{ + struct acrn_ioreq_client *client, *found = NULL; + struct acrn_ioreq_range *range; + + lockdep_assert_held(&vm->ioreq_clients_lock); + + list_for_each_entry(client, &vm->ioreq_clients, list) { + read_lock_bh(&client->range_lock); + list_for_each_entry(range, &client->range_list, list) { + if (in_range(range, req)) { + found = client; + break; + } + } + read_unlock_bh(&client->range_lock); + if (found) + break; + } + return found ? found : vm->default_client; +} + +/** + * acrn_ioreq_client_create() - Create an ioreq client + * @vm: The VM that this client belongs to + * @handler: The ioreq_handler of ioreq client acrn_hsm will create a kernel + * thread and call the handler to handle I/O requests. + * @priv: Private data for the handler + * @is_default: If it is the default client + * @name: The name of ioreq client + * + * Return: acrn_ioreq_client pointer on success, NULL on error + */ +struct acrn_ioreq_client *acrn_ioreq_client_create(struct acrn_vm *vm, + ioreq_handler_t handler, + void *priv, bool is_default, + const char *name) +{ + struct acrn_ioreq_client *client; + + if (!handler && !is_default) { + dev_dbg(acrn_dev.this_device, + "Cannot create non-default client w/o handler!\n"); + return NULL; + } + client = kzalloc(sizeof(*client), GFP_KERNEL); + if (!client) + return NULL; + + client->handler = handler; + client->vm = vm; + client->priv = priv; + client->is_default = is_default; + if (name) + strncpy(client->name, name, sizeof(client->name) - 1); + rwlock_init(&client->range_lock); + INIT_LIST_HEAD(&client->range_list); + init_waitqueue_head(&client->wq); + + if (client->handler) { + client->thread = kthread_run(ioreq_task, client, "VM%u-%s", + client->vm->vmid, client->name); + if (IS_ERR(client->thread)) { + kfree(client); + return NULL; + } + } + + spin_lock_bh(&vm->ioreq_clients_lock); + if (is_default) + vm->default_client = client; + else + list_add(&client->list, &vm->ioreq_clients); + spin_unlock_bh(&vm->ioreq_clients_lock); + + dev_dbg(acrn_dev.this_device, "Created ioreq client %s.\n", name); + return client; +} + +/** + * acrn_ioreq_client_destroy() - Destroy an ioreq client + * @client: The ioreq client + */ +void acrn_ioreq_client_destroy(struct acrn_ioreq_client *client) +{ + struct acrn_ioreq_range *range, *next; + struct acrn_vm *vm = client->vm; + + dev_dbg(acrn_dev.this_device, + "Destroy ioreq client %s.\n", client->name); + ioreq_pause(); + set_bit(ACRN_IOREQ_CLIENT_DESTROYING, &client->flags); + if (client->is_default) + wake_up_interruptible(&client->wq); + else + kthread_stop(client->thread); + + spin_lock_bh(&vm->ioreq_clients_lock); + if (client->is_default) + vm->default_client = NULL; + else + list_del(&client->list); + spin_unlock_bh(&vm->ioreq_clients_lock); + + write_lock_bh(&client->range_lock); + list_for_each_entry_safe(range, next, &client->range_list, list) { + list_del(&range->list); + kfree(range); + } + write_unlock_bh(&client->range_lock); + kfree(client); + + ioreq_resume(); +} + +static int acrn_ioreq_dispatch(struct acrn_vm *vm) +{ + struct acrn_ioreq_client *client; + struct acrn_io_request *req; + int i; + + for (i = 0; i < vm->vcpu_num; i++) { + req = vm->ioreq_buf->req_slot + i; + + /* barrier the read of processed of acrn_io_request */ + if (smp_load_acquire(&req->processed) == + ACRN_IOREQ_STATE_PENDING) { + /* Complete the IO request directly in clearing stage */ + if (test_bit(ACRN_VM_FLAG_CLEARING_IOREQ, &vm->flags)) { + ioreq_complete_request(vm, i, req); + continue; + } + + spin_lock_bh(&vm->ioreq_clients_lock); + client = find_ioreq_client(vm, req); + if (!client) { + dev_err(acrn_dev.this_device, + "Failed to find ioreq client!\n"); + spin_unlock_bh(&vm->ioreq_clients_lock); + return -EINVAL; + } + if (!client->is_default) + req->kernel_handled = 1; + else + req->kernel_handled = 0; + /* + * Add barrier() to make sure the writes are done + * before setting ACRN_IOREQ_STATE_PROCESSING + */ + smp_store_release(&req->processed, + ACRN_IOREQ_STATE_PROCESSING); + set_bit(i, client->ioreqs_map); + wake_up_interruptible(&client->wq); + spin_unlock_bh(&vm->ioreq_clients_lock); + } + } + + return 0; +} + +static void ioreq_dispatcher(struct work_struct *work) +{ + struct acrn_vm *vm; + + read_lock(&acrn_vm_list_lock); + list_for_each_entry(vm, &acrn_vm_list, list) { + if (!vm->ioreq_buf) + break; + acrn_ioreq_dispatch(vm); + } + read_unlock(&acrn_vm_list_lock); +} + +static void ioreq_intr_handler(void) +{ + queue_work(ioreq_wq, &ioreq_work); +} + +static void ioreq_pause(void) +{ + /* Flush and unarm the handler to ensure no I/O requests pending */ + acrn_remove_intr_handler(); + drain_workqueue(ioreq_wq); +} + +static void ioreq_resume(void) +{ + /* Schedule after enabling in case other clients miss interrupt */ + acrn_setup_intr_handler(ioreq_intr_handler); + queue_work(ioreq_wq, &ioreq_work); +} + +int acrn_ioreq_intr_setup(void) +{ + acrn_setup_intr_handler(ioreq_intr_handler); + ioreq_wq = alloc_workqueue("ioreq_wq", + WQ_HIGHPRI | WQ_MEM_RECLAIM | WQ_UNBOUND, 1); + if (!ioreq_wq) { + dev_err(acrn_dev.this_device, "Failed to alloc workqueue!\n"); + acrn_remove_intr_handler(); + return -ENOMEM; + } + return 0; +} + +void acrn_ioreq_intr_remove(void) +{ + if (ioreq_wq) + destroy_workqueue(ioreq_wq); + acrn_remove_intr_handler(); +} + +int acrn_ioreq_init(struct acrn_vm *vm, u64 buf_vma) +{ + struct acrn_ioreq_buffer *set_buffer; + struct page *page; + int ret; + + if (vm->ioreq_buf) + return -EEXIST; + + set_buffer = kzalloc(sizeof(*set_buffer), GFP_KERNEL); + if (!set_buffer) + return -ENOMEM; + + ret = pin_user_pages_fast(buf_vma, 1, + FOLL_WRITE | FOLL_LONGTERM, &page); + if (unlikely(ret != 1) || !page) { + dev_err(acrn_dev.this_device, "Failed to pin ioreq page!\n"); + ret = -EFAULT; + goto free_buf; + } + + vm->ioreq_buf = page_address(page); + vm->ioreq_page = page; + set_buffer->ioreq_buf = page_to_phys(page); + ret = hcall_set_ioreq_buffer(vm->vmid, virt_to_phys(set_buffer)); + if (ret < 0) { + dev_err(acrn_dev.this_device, "Failed to init ioreq buffer!\n"); + unpin_user_page(page); + vm->ioreq_buf = NULL; + goto free_buf; + } + + dev_dbg(acrn_dev.this_device, + "Init ioreq buffer %pK!\n", vm->ioreq_buf); + ret = 0; +free_buf: + kfree(set_buffer); + return ret; +} + +void acrn_ioreq_deinit(struct acrn_vm *vm) +{ + struct acrn_ioreq_client *client, *next; + + dev_dbg(acrn_dev.this_device, + "Deinit ioreq buffer %pK!\n", vm->ioreq_buf); + /* Destroy all clients belonging to this VM */ + list_for_each_entry_safe(client, next, &vm->ioreq_clients, list) + acrn_ioreq_client_destroy(client); + if (vm->default_client) + acrn_ioreq_client_destroy(vm->default_client); + + if (vm->ioreq_buf && vm->ioreq_page) { + unpin_user_page(vm->ioreq_page); + vm->ioreq_buf = NULL; + } +} diff --git a/drivers/virt/acrn/vm.c b/drivers/virt/acrn/vm.c index ff5df7acb551..2bc649c7c1d3 100644 --- a/drivers/virt/acrn/vm.c +++ b/drivers/virt/acrn/vm.c @@ -15,9 +15,12 @@ #include "acrn_drv.h" /* List of VMs */ -static LIST_HEAD(acrn_vm_list); -/* To protect acrn_vm_list */ -static DEFINE_MUTEX(acrn_vm_list_lock); +LIST_HEAD(acrn_vm_list); +/* + * acrn_vm_list is read in a worker thread which dispatch I/O requests and + * is wrote in VM creation ioctl. Use the rwlock mechanism to protect it. + */ +DEFINE_RWLOCK(acrn_vm_list_lock); struct acrn_vm *acrn_vm_create(struct acrn_vm *vm, struct acrn_vm_creation *vm_param) @@ -32,12 +35,20 @@ struct acrn_vm *acrn_vm_create(struct acrn_vm *vm, } mutex_init(&vm->regions_mapping_lock); + INIT_LIST_HEAD(&vm->ioreq_clients); + spin_lock_init(&vm->ioreq_clients_lock); vm->vmid = vm_param->vmid; vm->vcpu_num = vm_param->vcpu_num; - mutex_lock(&acrn_vm_list_lock); + if (acrn_ioreq_init(vm, vm_param->ioreq_buf) < 0) { + hcall_destroy_vm(vm_param->vmid); + vm->vmid = ACRN_INVALID_VMID; + return NULL; + } + + write_lock_bh(&acrn_vm_list_lock); list_add(&vm->list, &acrn_vm_list); - mutex_unlock(&acrn_vm_list_lock); + write_unlock_bh(&acrn_vm_list_lock); dev_dbg(acrn_dev.this_device, "VM %u created.\n", vm->vmid); return vm; @@ -52,9 +63,11 @@ int acrn_vm_destroy(struct acrn_vm *vm) return 0; /* Remove from global VM list */ - mutex_lock(&acrn_vm_list_lock); + write_lock_bh(&acrn_vm_list_lock); list_del_init(&vm->list); - mutex_unlock(&acrn_vm_list_lock); + write_unlock_bh(&acrn_vm_list_lock); + + acrn_ioreq_deinit(vm); ret = hcall_destroy_vm(vm->vmid); if (ret < 0) { diff --git a/include/uapi/linux/acrn.h b/include/uapi/linux/acrn.h index ec4c61e7c170..b0f73ab5e4e8 100644 --- a/include/uapi/linux/acrn.h +++ b/include/uapi/linux/acrn.h @@ -14,6 +14,145 @@ #include #include +#define ACRN_IO_REQUEST_MAX 16 + +#define ACRN_IOREQ_STATE_PENDING 0 +#define ACRN_IOREQ_STATE_COMPLETE 1 +#define ACRN_IOREQ_STATE_PROCESSING 2 +#define ACRN_IOREQ_STATE_FREE 3 + +#define ACRN_IOREQ_TYPE_PORTIO 0 +#define ACRN_IOREQ_TYPE_MMIO 1 + +#define ACRN_IOREQ_DIR_READ 0 +#define ACRN_IOREQ_DIR_WRITE 1 + +/** + * struct acrn_mmio_request - Info of a MMIO I/O request + * @direction: Access direction of this request (ACRN_IOREQ_DIR_*) + * @reserved: Reserved for alignment and should be 0 + * @address: Access address of this MMIO I/O request + * @size: Access size of this MMIO I/O request + * @value: Read/write value of this MMIO I/O request + */ +struct acrn_mmio_request { + __u32 direction; + __u32 reserved; + __u64 address; + __u64 size; + __u64 value; +}; + +/** + * struct acrn_pio_request - Info of a PIO I/O request + * @direction: Access direction of this request (ACRN_IOREQ_DIR_*) + * @reserved: Reserved for alignment and should be 0 + * @address: Access address of this PIO I/O request + * @size: Access size of this PIO I/O request + * @value: Read/write value of this PIO I/O request + */ +struct acrn_pio_request { + __u32 direction; + __u32 reserved; + __u64 address; + __u64 size; + __u32 value; +}; + +/** + * struct acrn_io_request - 256-byte ACRN I/O request + * @type: Type of this request (ACRN_IOREQ_TYPE_*). + * @completion_polling: Polling flag. Hypervisor will poll completion of the + * I/O request if this flag set. + * @reserved0: Reserved fields. + * @reqs: Union of different types of request. Byte offset: 64. + * @reqs.pio_request: PIO request data of the I/O request. + * @reqs.mmio_request: MMIO request data of the I/O request. + * @reqs.data: Raw data of the I/O request. + * @reserved1: Reserved fields. + * @kernel_handled: Flag indicates this request need be handled in kernel. + * @processed: The status of this request (ACRN_IOREQ_STATE_*). + * + * The state transitions of ACRN I/O request: + * + * FREE -> PENDING -> PROCESSING -> COMPLETE -> FREE -> ... + * + * An I/O request in COMPLETE or FREE state is owned by the hypervisor. HSM and + * ACRN userspace are in charge of processing the others. + * + * On basis of the states illustrated above, a typical lifecycle of ACRN IO + * request would look like: + * + * Flow (assume the initial state is FREE) + * | + * | Service VM vCPU 0 Service VM vCPU x User vCPU y + * | + * | hypervisor: + * | fills in type, addr, etc. + * | pauses the User VM vCPU y + * | sets the state to PENDING (a) + * | fires an upcall to Service VM + * | + * | HSM: + * | scans for PENDING requests + * | sets the states to PROCESSING (b) + * | assigns the requests to clients (c) + * V + * | client: + * | scans for the assigned requests + * | handles the requests (d) + * | HSM: + * | sets states to COMPLETE + * | notifies the hypervisor + * | + * | hypervisor: + * | resumes User VM vCPU y (e) + * | + * | hypervisor: + * | post handling (f) + * V sets states to FREE + * + * Note that the procedures (a) to (f) in the illustration above require to be + * strictly processed in the order. One vCPU cannot trigger another request of + * I/O emulation before completing the previous one. + * + * Atomic and barriers are required when HSM and hypervisor accessing the state + * of &struct acrn_io_request. + * + */ +struct acrn_io_request { + __u32 type; + __u32 completion_polling; + __u32 reserved0[14]; + union { + struct acrn_pio_request pio_request; + struct acrn_mmio_request mmio_request; + __u64 data[8]; + } reqs; + __u32 reserved1; + __u32 kernel_handled; + __u32 processed; +} __attribute__((aligned(256))); + +struct acrn_io_request_buffer { + union { + struct acrn_io_request req_slot[ACRN_IO_REQUEST_MAX]; + __u8 reserved[4096]; + }; +}; + +/** + * struct acrn_ioreq_notify - The structure of ioreq completion notification + * @vmid: User VM ID + * @reserved: Reserved and should be 0 + * @vcpu: vCPU ID + */ +struct acrn_ioreq_notify { + __u16 vmid; + __u16 reserved; + __u32 vcpu; +}; + /** * struct acrn_vm_creation - Info to create a User VM * @vmid: User VM ID returned from the hypervisor @@ -218,6 +357,17 @@ struct acrn_vm_memmap { #define ACRN_IOCTL_SET_VCPU_REGS \ _IOW(ACRN_IOCTL_TYPE, 0x16, struct acrn_vcpu_regs) +#define ACRN_IOCTL_NOTIFY_REQUEST_FINISH \ + _IOW(ACRN_IOCTL_TYPE, 0x31, struct acrn_ioreq_notify) +#define ACRN_IOCTL_CREATE_IOREQ_CLIENT \ + _IO(ACRN_IOCTL_TYPE, 0x32) +#define ACRN_IOCTL_ATTACH_IOREQ_CLIENT \ + _IO(ACRN_IOCTL_TYPE, 0x33) +#define ACRN_IOCTL_DESTROY_IOREQ_CLIENT \ + _IO(ACRN_IOCTL_TYPE, 0x34) +#define ACRN_IOCTL_CLEAR_VM_IOREQ \ + _IO(ACRN_IOCTL_TYPE, 0x35) + #define ACRN_IOCTL_SET_MEMSEG \ _IOW(ACRN_IOCTL_TYPE, 0x41, struct acrn_vm_memmap) #define ACRN_IOCTL_UNSET_MEMSEG \ -- cgit v1.2.3 From 3c4c331667d4d9f1b5f3fdff9c4db36776da30ae Mon Sep 17 00:00:00 2001 From: Shuo Liu Date: Sun, 7 Feb 2021 11:10:32 +0800 Subject: virt: acrn: Introduce PCI configuration space PIO accesses combiner A User VM can access its virtual PCI configuration spaces via port IO approach, which has two following steps: 1) writes address into port 0xCF8 2) put/get data in/from port 0xCFC To distribute a complete PCI configuration space access one time, HSM need to combine such two accesses together. Combine two paired PIO I/O requests into one PCI I/O request and continue the I/O request distribution. Cc: Greg Kroah-Hartman Reviewed-by: Reinette Chatre Signed-off-by: Shuo Liu Link: https://lore.kernel.org/r/20210207031040.49576-11-shuo.a.liu@intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/virt/acrn/acrn_drv.h | 2 ++ drivers/virt/acrn/ioreq.c | 76 ++++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/acrn.h | 27 ++++++++++++++++ 3 files changed, 105 insertions(+) (limited to 'include') diff --git a/drivers/virt/acrn/acrn_drv.h b/drivers/virt/acrn/acrn_drv.h index 68bd8db6c8be..6c92a505fa20 100644 --- a/drivers/virt/acrn/acrn_drv.h +++ b/drivers/virt/acrn/acrn_drv.h @@ -154,6 +154,7 @@ extern rwlock_t acrn_vm_list_lock; * @default_client: The default I/O request client * @ioreq_buf: I/O request shared buffer * @ioreq_page: The page of the I/O request shared buffer + * @pci_conf_addr: Address of a PCI configuration access emulation */ struct acrn_vm { struct list_head list; @@ -168,6 +169,7 @@ struct acrn_vm { struct acrn_ioreq_client *default_client; struct acrn_io_request_buffer *ioreq_buf; struct page *ioreq_page; + u32 pci_conf_addr; }; struct acrn_vm *acrn_vm_create(struct acrn_vm *vm, diff --git a/drivers/virt/acrn/ioreq.c b/drivers/virt/acrn/ioreq.c index 51cb41ef7c72..d19c05582d38 100644 --- a/drivers/virt/acrn/ioreq.c +++ b/drivers/virt/acrn/ioreq.c @@ -222,6 +222,80 @@ int acrn_ioreq_client_wait(struct acrn_ioreq_client *client) return 0; } +static bool is_cfg_addr(struct acrn_io_request *req) +{ + return ((req->type == ACRN_IOREQ_TYPE_PORTIO) && + (req->reqs.pio_request.address == 0xcf8)); +} + +static bool is_cfg_data(struct acrn_io_request *req) +{ + return ((req->type == ACRN_IOREQ_TYPE_PORTIO) && + ((req->reqs.pio_request.address >= 0xcfc) && + (req->reqs.pio_request.address < (0xcfc + 4)))); +} + +/* The low 8-bit of supported pci_reg addr.*/ +#define PCI_LOWREG_MASK 0xFC +/* The high 4-bit of supported pci_reg addr */ +#define PCI_HIGHREG_MASK 0xF00 +/* Max number of supported functions */ +#define PCI_FUNCMAX 7 +/* Max number of supported slots */ +#define PCI_SLOTMAX 31 +/* Max number of supported buses */ +#define PCI_BUSMAX 255 +#define CONF1_ENABLE 0x80000000UL +/* + * A PCI configuration space access via PIO 0xCF8 and 0xCFC normally has two + * following steps: + * 1) writes address into 0xCF8 port + * 2) accesses data in/from 0xCFC + * This function combines such paired PCI configuration space I/O requests into + * one ACRN_IOREQ_TYPE_PCICFG type I/O request and continues the processing. + */ +static bool handle_cf8cfc(struct acrn_vm *vm, + struct acrn_io_request *req, u16 vcpu) +{ + int offset, pci_cfg_addr, pci_reg; + bool is_handled = false; + + if (is_cfg_addr(req)) { + WARN_ON(req->reqs.pio_request.size != 4); + if (req->reqs.pio_request.direction == ACRN_IOREQ_DIR_WRITE) + vm->pci_conf_addr = req->reqs.pio_request.value; + else + req->reqs.pio_request.value = vm->pci_conf_addr; + is_handled = true; + } else if (is_cfg_data(req)) { + if (!(vm->pci_conf_addr & CONF1_ENABLE)) { + if (req->reqs.pio_request.direction == + ACRN_IOREQ_DIR_READ) + req->reqs.pio_request.value = 0xffffffff; + is_handled = true; + } else { + offset = req->reqs.pio_request.address - 0xcfc; + + req->type = ACRN_IOREQ_TYPE_PCICFG; + pci_cfg_addr = vm->pci_conf_addr; + req->reqs.pci_request.bus = + (pci_cfg_addr >> 16) & PCI_BUSMAX; + req->reqs.pci_request.dev = + (pci_cfg_addr >> 11) & PCI_SLOTMAX; + req->reqs.pci_request.func = + (pci_cfg_addr >> 8) & PCI_FUNCMAX; + pci_reg = (pci_cfg_addr & PCI_LOWREG_MASK) + + ((pci_cfg_addr >> 16) & PCI_HIGHREG_MASK); + req->reqs.pci_request.reg = pci_reg + offset; + } + } + + if (is_handled) + ioreq_complete_request(vm, vcpu, req); + + return is_handled; +} + static bool in_range(struct acrn_ioreq_range *range, struct acrn_io_request *req) { @@ -382,6 +456,8 @@ static int acrn_ioreq_dispatch(struct acrn_vm *vm) ioreq_complete_request(vm, i, req); continue; } + if (handle_cf8cfc(vm, req, i)) + continue; spin_lock_bh(&vm->ioreq_clients_lock); client = find_ioreq_client(vm, req); diff --git a/include/uapi/linux/acrn.h b/include/uapi/linux/acrn.h index b0f73ab5e4e8..da40f7ad13d9 100644 --- a/include/uapi/linux/acrn.h +++ b/include/uapi/linux/acrn.h @@ -23,6 +23,7 @@ #define ACRN_IOREQ_TYPE_PORTIO 0 #define ACRN_IOREQ_TYPE_MMIO 1 +#define ACRN_IOREQ_TYPE_PCICFG 2 #define ACRN_IOREQ_DIR_READ 0 #define ACRN_IOREQ_DIR_WRITE 1 @@ -59,6 +60,30 @@ struct acrn_pio_request { __u32 value; }; +/** + * struct acrn_pci_request - Info of a PCI I/O request + * @direction: Access direction of this request (ACRN_IOREQ_DIR_*) + * @reserved: Reserved for alignment and should be 0 + * @size: Access size of this PCI I/O request + * @value: Read/write value of this PIO I/O request + * @bus: PCI bus value of this PCI I/O request + * @dev: PCI device value of this PCI I/O request + * @func: PCI function value of this PCI I/O request + * @reg: PCI config space offset of this PCI I/O request + * + * Need keep same header layout with &struct acrn_pio_request. + */ +struct acrn_pci_request { + __u32 direction; + __u32 reserved[3]; + __u64 size; + __u32 value; + __u32 bus; + __u32 dev; + __u32 func; + __u32 reg; +}; + /** * struct acrn_io_request - 256-byte ACRN I/O request * @type: Type of this request (ACRN_IOREQ_TYPE_*). @@ -67,6 +92,7 @@ struct acrn_pio_request { * @reserved0: Reserved fields. * @reqs: Union of different types of request. Byte offset: 64. * @reqs.pio_request: PIO request data of the I/O request. + * @reqs.pci_request: PCI configuration space request data of the I/O request. * @reqs.mmio_request: MMIO request data of the I/O request. * @reqs.data: Raw data of the I/O request. * @reserved1: Reserved fields. @@ -126,6 +152,7 @@ struct acrn_io_request { __u32 reserved0[14]; union { struct acrn_pio_request pio_request; + struct acrn_pci_request pci_request; struct acrn_mmio_request mmio_request; __u64 data[8]; } reqs; -- cgit v1.2.3 From ce011e1363a1fe43de0ca05abc394022ee4fefeb Mon Sep 17 00:00:00 2001 From: Shuo Liu Date: Sun, 7 Feb 2021 11:10:33 +0800 Subject: virt: acrn: Introduce interfaces for PCI device passthrough PCI device passthrough enables an OS in a virtual machine to directly access a PCI device in the host. It promises almost the native performance, which is required in performance-critical scenarios of ACRN. HSM provides the following ioctls: - Assign - ACRN_IOCTL_ASSIGN_PCIDEV Pass data struct acrn_pcidev from userspace to the hypervisor, and inform the hypervisor to assign a PCI device to a User VM. - De-assign - ACRN_IOCTL_DEASSIGN_PCIDEV Pass data struct acrn_pcidev from userspace to the hypervisor, and inform the hypervisor to de-assign a PCI device from a User VM. - Set a interrupt of a passthrough device - ACRN_IOCTL_SET_PTDEV_INTR Pass data struct acrn_ptdev_irq from userspace to the hypervisor, and inform the hypervisor to map a INTx interrupt of passthrough device of User VM. - Reset passthrough device interrupt - ACRN_IOCTL_RESET_PTDEV_INTR Pass data struct acrn_ptdev_irq from userspace to the hypervisor, and inform the hypervisor to unmap a INTx interrupt of passthrough device of User VM. Cc: Zhi Wang Cc: Zhenyu Wang Cc: Yu Wang Cc: Reinette Chatre Cc: Greg Kroah-Hartman Reviewed-by: Zhi Wang Reviewed-by: Reinette Chatre Signed-off-by: Shuo Liu Link: https://lore.kernel.org/r/20210207031040.49576-12-shuo.a.liu@intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/virt/acrn/hsm.c | 50 +++++++++++++++++++++++++++++++++++ drivers/virt/acrn/hypercall.h | 54 ++++++++++++++++++++++++++++++++++++++ include/uapi/linux/acrn.h | 61 +++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 165 insertions(+) (limited to 'include') diff --git a/drivers/virt/acrn/hsm.c b/drivers/virt/acrn/hsm.c index 1cc0c612dc09..94d70b1c1e5c 100644 --- a/drivers/virt/acrn/hsm.c +++ b/drivers/virt/acrn/hsm.c @@ -49,7 +49,9 @@ static long acrn_dev_ioctl(struct file *filp, unsigned int cmd, struct acrn_vm_creation *vm_param; struct acrn_vcpu_regs *cpu_regs; struct acrn_ioreq_notify notify; + struct acrn_ptdev_irq *irq_info; struct acrn_vm_memmap memmap; + struct acrn_pcidev *pcidev; int i, ret = 0; if (vm->vmid == ACRN_INVALID_VMID && cmd != ACRN_IOCTL_CREATE_VM) { @@ -148,6 +150,54 @@ static long acrn_dev_ioctl(struct file *filp, unsigned int cmd, ret = acrn_vm_memseg_unmap(vm, &memmap); break; + case ACRN_IOCTL_ASSIGN_PCIDEV: + pcidev = memdup_user((void __user *)ioctl_param, + sizeof(struct acrn_pcidev)); + if (IS_ERR(pcidev)) + return PTR_ERR(pcidev); + + ret = hcall_assign_pcidev(vm->vmid, virt_to_phys(pcidev)); + if (ret < 0) + dev_dbg(acrn_dev.this_device, + "Failed to assign pci device!\n"); + kfree(pcidev); + break; + case ACRN_IOCTL_DEASSIGN_PCIDEV: + pcidev = memdup_user((void __user *)ioctl_param, + sizeof(struct acrn_pcidev)); + if (IS_ERR(pcidev)) + return PTR_ERR(pcidev); + + ret = hcall_deassign_pcidev(vm->vmid, virt_to_phys(pcidev)); + if (ret < 0) + dev_dbg(acrn_dev.this_device, + "Failed to deassign pci device!\n"); + kfree(pcidev); + break; + case ACRN_IOCTL_SET_PTDEV_INTR: + irq_info = memdup_user((void __user *)ioctl_param, + sizeof(struct acrn_ptdev_irq)); + if (IS_ERR(irq_info)) + return PTR_ERR(irq_info); + + ret = hcall_set_ptdev_intr(vm->vmid, virt_to_phys(irq_info)); + if (ret < 0) + dev_dbg(acrn_dev.this_device, + "Failed to configure intr for ptdev!\n"); + kfree(irq_info); + break; + case ACRN_IOCTL_RESET_PTDEV_INTR: + irq_info = memdup_user((void __user *)ioctl_param, + sizeof(struct acrn_ptdev_irq)); + if (IS_ERR(irq_info)) + return PTR_ERR(irq_info); + + ret = hcall_reset_ptdev_intr(vm->vmid, virt_to_phys(irq_info)); + if (ret < 0) + dev_dbg(acrn_dev.this_device, + "Failed to reset intr for ptdev!\n"); + kfree(irq_info); + break; case ACRN_IOCTL_CREATE_IOREQ_CLIENT: if (vm->default_client) return -EEXIST; diff --git a/drivers/virt/acrn/hypercall.h b/drivers/virt/acrn/hypercall.h index 5eba29e3ed38..f448301832cf 100644 --- a/drivers/virt/acrn/hypercall.h +++ b/drivers/virt/acrn/hypercall.h @@ -28,6 +28,12 @@ #define HC_ID_MEM_BASE 0x40UL #define HC_VM_SET_MEMORY_REGIONS _HC_ID(HC_ID, HC_ID_MEM_BASE + 0x02) +#define HC_ID_PCI_BASE 0x50UL +#define HC_SET_PTDEV_INTR _HC_ID(HC_ID, HC_ID_PCI_BASE + 0x03) +#define HC_RESET_PTDEV_INTR _HC_ID(HC_ID, HC_ID_PCI_BASE + 0x04) +#define HC_ASSIGN_PCIDEV _HC_ID(HC_ID, HC_ID_PCI_BASE + 0x05) +#define HC_DEASSIGN_PCIDEV _HC_ID(HC_ID, HC_ID_PCI_BASE + 0x06) + /** * hcall_create_vm() - Create a User VM * @vminfo: Service VM GPA of info of User VM creation @@ -130,4 +136,52 @@ static inline long hcall_set_memory_regions(u64 regions_pa) return acrn_hypercall1(HC_VM_SET_MEMORY_REGIONS, regions_pa); } +/** + * hcall_assign_pcidev() - Assign a PCI device to a User VM + * @vmid: User VM ID + * @addr: Service VM GPA of the &struct acrn_pcidev + * + * Return: 0 on success, <0 on failure + */ +static inline long hcall_assign_pcidev(u64 vmid, u64 addr) +{ + return acrn_hypercall2(HC_ASSIGN_PCIDEV, vmid, addr); +} + +/** + * hcall_deassign_pcidev() - De-assign a PCI device from a User VM + * @vmid: User VM ID + * @addr: Service VM GPA of the &struct acrn_pcidev + * + * Return: 0 on success, <0 on failure + */ +static inline long hcall_deassign_pcidev(u64 vmid, u64 addr) +{ + return acrn_hypercall2(HC_DEASSIGN_PCIDEV, vmid, addr); +} + +/** + * hcall_set_ptdev_intr() - Configure an interrupt for an assigned PCI device. + * @vmid: User VM ID + * @irq: Service VM GPA of the &struct acrn_ptdev_irq + * + * Return: 0 on success, <0 on failure + */ +static inline long hcall_set_ptdev_intr(u64 vmid, u64 irq) +{ + return acrn_hypercall2(HC_SET_PTDEV_INTR, vmid, irq); +} + +/** + * hcall_reset_ptdev_intr() - Reset an interrupt for an assigned PCI device. + * @vmid: User VM ID + * @irq: Service VM GPA of the &struct acrn_ptdev_irq + * + * Return: 0 on success, <0 on failure + */ +static inline long hcall_reset_ptdev_intr(u64 vmid, u64 irq) +{ + return acrn_hypercall2(HC_RESET_PTDEV_INTR, vmid, irq); +} + #endif /* __ACRN_HSM_HYPERCALL_H */ diff --git a/include/uapi/linux/acrn.h b/include/uapi/linux/acrn.h index da40f7ad13d9..b25ca8c33b92 100644 --- a/include/uapi/linux/acrn.h +++ b/include/uapi/linux/acrn.h @@ -365,6 +365,58 @@ struct acrn_vm_memmap { __u64 len; }; +/* Type of interrupt of a passthrough device */ +#define ACRN_PTDEV_IRQ_INTX 0 +#define ACRN_PTDEV_IRQ_MSI 1 +#define ACRN_PTDEV_IRQ_MSIX 2 +/** + * struct acrn_ptdev_irq - Interrupt data of a passthrough device. + * @type: Type (ACRN_PTDEV_IRQ_*) + * @virt_bdf: Virtual Bus/Device/Function + * @phys_bdf: Physical Bus/Device/Function + * @intx: Info of interrupt + * @intx.virt_pin: Virtual IOAPIC pin + * @intx.phys_pin: Physical IOAPIC pin + * @intx.is_pic_pin: Is PIC pin or not + * + * This structure will be passed to hypervisor directly. + */ +struct acrn_ptdev_irq { + __u32 type; + __u16 virt_bdf; + __u16 phys_bdf; + + struct { + __u32 virt_pin; + __u32 phys_pin; + __u32 is_pic_pin; + } intx; +}; + +/* Type of PCI device assignment */ +#define ACRN_PTDEV_QUIRK_ASSIGN (1U << 0) + +#define ACRN_PCI_NUM_BARS 6 +/** + * struct acrn_pcidev - Info for assigning or de-assigning a PCI device + * @type: Type of the assignment + * @virt_bdf: Virtual Bus/Device/Function + * @phys_bdf: Physical Bus/Device/Function + * @intr_line: PCI interrupt line + * @intr_pin: PCI interrupt pin + * @bar: PCI BARs. + * + * This structure will be passed to hypervisor directly. + */ +struct acrn_pcidev { + __u32 type; + __u16 virt_bdf; + __u16 phys_bdf; + __u8 intr_line; + __u8 intr_pin; + __u32 bar[ACRN_PCI_NUM_BARS]; +}; + /* The ioctl type, documented in ioctl-number.rst */ #define ACRN_IOCTL_TYPE 0xA2 @@ -400,4 +452,13 @@ struct acrn_vm_memmap { #define ACRN_IOCTL_UNSET_MEMSEG \ _IOW(ACRN_IOCTL_TYPE, 0x42, struct acrn_vm_memmap) +#define ACRN_IOCTL_SET_PTDEV_INTR \ + _IOW(ACRN_IOCTL_TYPE, 0x53, struct acrn_ptdev_irq) +#define ACRN_IOCTL_RESET_PTDEV_INTR \ + _IOW(ACRN_IOCTL_TYPE, 0x54, struct acrn_ptdev_irq) +#define ACRN_IOCTL_ASSIGN_PCIDEV \ + _IOW(ACRN_IOCTL_TYPE, 0x55, struct acrn_pcidev) +#define ACRN_IOCTL_DEASSIGN_PCIDEV \ + _IOW(ACRN_IOCTL_TYPE, 0x56, struct acrn_pcidev) + #endif /* _UAPI_ACRN_H */ -- cgit v1.2.3 From c7cf8d27244f2ccdde30c79eb6314c943bbeac28 Mon Sep 17 00:00:00 2001 From: Shuo Liu Date: Sun, 7 Feb 2021 11:10:34 +0800 Subject: virt: acrn: Introduce interrupt injection interfaces ACRN userspace need to inject virtual interrupts into a User VM in devices emulation. HSM needs provide interfaces to do so. Introduce following interrupt injection interfaces: ioctl ACRN_IOCTL_SET_IRQLINE: Pass data from userspace to the hypervisor, and inform the hypervisor to inject a virtual IOAPIC GSI interrupt to a User VM. ioctl ACRN_IOCTL_INJECT_MSI: Pass data struct acrn_msi_entry from userspace to the hypervisor, and inform the hypervisor to inject a virtual MSI to a User VM. ioctl ACRN_IOCTL_VM_INTR_MONITOR: Set a 4-Kbyte aligned shared page for statistics information of interrupts of a User VM. Cc: Zhi Wang Cc: Zhenyu Wang Cc: Yu Wang Cc: Reinette Chatre Cc: Greg Kroah-Hartman Reviewed-by: Zhi Wang Reviewed-by: Reinette Chatre Signed-off-by: Shuo Liu Link: https://lore.kernel.org/r/20210207031040.49576-13-shuo.a.liu@intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/virt/acrn/acrn_drv.h | 4 ++++ drivers/virt/acrn/hsm.c | 40 ++++++++++++++++++++++++++++++++++++++++ drivers/virt/acrn/hypercall.h | 41 +++++++++++++++++++++++++++++++++++++++++ drivers/virt/acrn/vm.c | 36 ++++++++++++++++++++++++++++++++++++ include/uapi/linux/acrn.h | 17 +++++++++++++++++ 5 files changed, 138 insertions(+) (limited to 'include') diff --git a/drivers/virt/acrn/acrn_drv.h b/drivers/virt/acrn/acrn_drv.h index 6c92a505fa20..068f0be769f6 100644 --- a/drivers/virt/acrn/acrn_drv.h +++ b/drivers/virt/acrn/acrn_drv.h @@ -155,6 +155,7 @@ extern rwlock_t acrn_vm_list_lock; * @ioreq_buf: I/O request shared buffer * @ioreq_page: The page of the I/O request shared buffer * @pci_conf_addr: Address of a PCI configuration access emulation + * @monitor_page: Page of interrupt statistics of User VM */ struct acrn_vm { struct list_head list; @@ -170,6 +171,7 @@ struct acrn_vm { struct acrn_io_request_buffer *ioreq_buf; struct page *ioreq_page; u32 pci_conf_addr; + struct page *monitor_page; }; struct acrn_vm *acrn_vm_create(struct acrn_vm *vm, @@ -196,4 +198,6 @@ struct acrn_ioreq_client *acrn_ioreq_client_create(struct acrn_vm *vm, const char *name); void acrn_ioreq_client_destroy(struct acrn_ioreq_client *client); +int acrn_msi_inject(struct acrn_vm *vm, u64 msi_addr, u64 msi_data); + #endif /* __ACRN_HSM_DRV_H */ diff --git a/drivers/virt/acrn/hsm.c b/drivers/virt/acrn/hsm.c index 94d70b1c1e5c..419271f32be8 100644 --- a/drivers/virt/acrn/hsm.c +++ b/drivers/virt/acrn/hsm.c @@ -51,7 +51,9 @@ static long acrn_dev_ioctl(struct file *filp, unsigned int cmd, struct acrn_ioreq_notify notify; struct acrn_ptdev_irq *irq_info; struct acrn_vm_memmap memmap; + struct acrn_msi_entry *msi; struct acrn_pcidev *pcidev; + struct page *page; int i, ret = 0; if (vm->vmid == ACRN_INVALID_VMID && cmd != ACRN_IOCTL_CREATE_VM) { @@ -198,6 +200,44 @@ static long acrn_dev_ioctl(struct file *filp, unsigned int cmd, "Failed to reset intr for ptdev!\n"); kfree(irq_info); break; + case ACRN_IOCTL_SET_IRQLINE: + ret = hcall_set_irqline(vm->vmid, ioctl_param); + if (ret < 0) + dev_dbg(acrn_dev.this_device, + "Failed to set interrupt line!\n"); + break; + case ACRN_IOCTL_INJECT_MSI: + msi = memdup_user((void __user *)ioctl_param, + sizeof(struct acrn_msi_entry)); + if (IS_ERR(msi)) + return PTR_ERR(msi); + + ret = hcall_inject_msi(vm->vmid, virt_to_phys(msi)); + if (ret < 0) + dev_dbg(acrn_dev.this_device, + "Failed to inject MSI!\n"); + kfree(msi); + break; + case ACRN_IOCTL_VM_INTR_MONITOR: + ret = pin_user_pages_fast(ioctl_param, 1, + FOLL_WRITE | FOLL_LONGTERM, &page); + if (unlikely(ret != 1)) { + dev_dbg(acrn_dev.this_device, + "Failed to pin intr hdr buffer!\n"); + return -EFAULT; + } + + ret = hcall_vm_intr_monitor(vm->vmid, page_to_phys(page)); + if (ret < 0) { + unpin_user_page(page); + dev_dbg(acrn_dev.this_device, + "Failed to monitor intr data!\n"); + return ret; + } + if (vm->monitor_page) + unpin_user_page(vm->monitor_page); + vm->monitor_page = page; + break; case ACRN_IOCTL_CREATE_IOREQ_CLIENT: if (vm->default_client) return -EEXIST; diff --git a/drivers/virt/acrn/hypercall.h b/drivers/virt/acrn/hypercall.h index f448301832cf..a8813397a3fe 100644 --- a/drivers/virt/acrn/hypercall.h +++ b/drivers/virt/acrn/hypercall.h @@ -21,6 +21,11 @@ #define HC_RESET_VM _HC_ID(HC_ID, HC_ID_VM_BASE + 0x05) #define HC_SET_VCPU_REGS _HC_ID(HC_ID, HC_ID_VM_BASE + 0x06) +#define HC_ID_IRQ_BASE 0x20UL +#define HC_INJECT_MSI _HC_ID(HC_ID, HC_ID_IRQ_BASE + 0x03) +#define HC_VM_INTR_MONITOR _HC_ID(HC_ID, HC_ID_IRQ_BASE + 0x04) +#define HC_SET_IRQLINE _HC_ID(HC_ID, HC_ID_IRQ_BASE + 0x05) + #define HC_ID_IOREQ_BASE 0x30UL #define HC_SET_IOREQ_BUFFER _HC_ID(HC_ID, HC_ID_IOREQ_BASE + 0x00) #define HC_NOTIFY_REQUEST_FINISH _HC_ID(HC_ID, HC_ID_IOREQ_BASE + 0x01) @@ -101,6 +106,42 @@ static inline long hcall_set_vcpu_regs(u64 vmid, u64 regs_state) return acrn_hypercall2(HC_SET_VCPU_REGS, vmid, regs_state); } +/** + * hcall_inject_msi() - Deliver a MSI interrupt to a User VM + * @vmid: User VM ID + * @msi: Service VM GPA of MSI message + * + * Return: 0 on success, <0 on failure + */ +static inline long hcall_inject_msi(u64 vmid, u64 msi) +{ + return acrn_hypercall2(HC_INJECT_MSI, vmid, msi); +} + +/** + * hcall_vm_intr_monitor() - Set a shared page for User VM interrupt statistics + * @vmid: User VM ID + * @addr: Service VM GPA of the shared page + * + * Return: 0 on success, <0 on failure + */ +static inline long hcall_vm_intr_monitor(u64 vmid, u64 addr) +{ + return acrn_hypercall2(HC_VM_INTR_MONITOR, vmid, addr); +} + +/** + * hcall_set_irqline() - Set or clear an interrupt line + * @vmid: User VM ID + * @op: Service VM GPA of interrupt line operations + * + * Return: 0 on success, <0 on failure + */ +static inline long hcall_set_irqline(u64 vmid, u64 op) +{ + return acrn_hypercall2(HC_SET_IRQLINE, vmid, op); +} + /** * hcall_set_ioreq_buffer() - Set up the shared buffer for I/O Requests. * @vmid: User VM ID diff --git a/drivers/virt/acrn/vm.c b/drivers/virt/acrn/vm.c index 2bc649c7c1d3..db597f27690a 100644 --- a/drivers/virt/acrn/vm.c +++ b/drivers/virt/acrn/vm.c @@ -68,6 +68,10 @@ int acrn_vm_destroy(struct acrn_vm *vm) write_unlock_bh(&acrn_vm_list_lock); acrn_ioreq_deinit(vm); + if (vm->monitor_page) { + put_page(vm->monitor_page); + vm->monitor_page = NULL; + } ret = hcall_destroy_vm(vm->vmid); if (ret < 0) { @@ -83,3 +87,35 @@ int acrn_vm_destroy(struct acrn_vm *vm) vm->vmid = ACRN_INVALID_VMID; return 0; } + +/** + * acrn_inject_msi() - Inject a MSI interrupt into a User VM + * @vm: User VM + * @msi_addr: The MSI address + * @msi_data: The MSI data + * + * Return: 0 on success, <0 on error + */ +int acrn_msi_inject(struct acrn_vm *vm, u64 msi_addr, u64 msi_data) +{ + struct acrn_msi_entry *msi; + int ret; + + /* might be used in interrupt context, so use GFP_ATOMIC */ + msi = kzalloc(sizeof(*msi), GFP_ATOMIC); + if (!msi) + return -ENOMEM; + + /* + * msi_addr: addr[19:12] with dest vcpu id + * msi_data: data[7:0] with vector + */ + msi->msi_addr = msi_addr; + msi->msi_data = msi_data; + ret = hcall_inject_msi(vm->vmid, virt_to_phys(msi)); + if (ret < 0) + dev_err(acrn_dev.this_device, + "Failed to inject MSI to VM %u!\n", vm->vmid); + kfree(msi); + return ret; +} diff --git a/include/uapi/linux/acrn.h b/include/uapi/linux/acrn.h index b25ca8c33b92..b1c06b28ebdc 100644 --- a/include/uapi/linux/acrn.h +++ b/include/uapi/linux/acrn.h @@ -417,6 +417,16 @@ struct acrn_pcidev { __u32 bar[ACRN_PCI_NUM_BARS]; }; +/** + * struct acrn_msi_entry - Info for injecting a MSI interrupt to a VM + * @msi_addr: MSI addr[19:12] with dest vCPU ID + * @msi_data: MSI data[7:0] with vector + */ +struct acrn_msi_entry { + __u64 msi_addr; + __u64 msi_data; +}; + /* The ioctl type, documented in ioctl-number.rst */ #define ACRN_IOCTL_TYPE 0xA2 @@ -436,6 +446,13 @@ struct acrn_pcidev { #define ACRN_IOCTL_SET_VCPU_REGS \ _IOW(ACRN_IOCTL_TYPE, 0x16, struct acrn_vcpu_regs) +#define ACRN_IOCTL_INJECT_MSI \ + _IOW(ACRN_IOCTL_TYPE, 0x23, struct acrn_msi_entry) +#define ACRN_IOCTL_VM_INTR_MONITOR \ + _IOW(ACRN_IOCTL_TYPE, 0x24, unsigned long) +#define ACRN_IOCTL_SET_IRQLINE \ + _IOW(ACRN_IOCTL_TYPE, 0x25, __u64) + #define ACRN_IOCTL_NOTIFY_REQUEST_FINISH \ _IOW(ACRN_IOCTL_TYPE, 0x31, struct acrn_ioreq_notify) #define ACRN_IOCTL_CREATE_IOREQ_CLIENT \ -- cgit v1.2.3 From 3d679d5aec648f50e645702929890b9611998a0b Mon Sep 17 00:00:00 2001 From: Shuo Liu Date: Sun, 7 Feb 2021 11:10:35 +0800 Subject: virt: acrn: Introduce interfaces to query C-states and P-states allowed by hypervisor The C-states and P-states data are used to support CPU power management. The hypervisor controls C-states and P-states for a User VM. ACRN userspace need to query the data from the hypervisor to build ACPI tables for a User VM. HSM provides ioctls for ACRN userspace to query C-states and P-states data obtained from the hypervisor. Cc: Zhi Wang Cc: Zhenyu Wang Cc: Yu Wang Cc: Reinette Chatre Cc: Greg Kroah-Hartman Reviewed-by: Zhi Wang Reviewed-by: Reinette Chatre Signed-off-by: Shuo Liu Link: https://lore.kernel.org/r/20210207031040.49576-14-shuo.a.liu@intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/virt/acrn/hsm.c | 69 +++++++++++++++++++++++++++++++++++++++++++ drivers/virt/acrn/hypercall.h | 12 ++++++++ include/uapi/linux/acrn.h | 55 ++++++++++++++++++++++++++++++++++ 3 files changed, 136 insertions(+) (limited to 'include') diff --git a/drivers/virt/acrn/hsm.c b/drivers/virt/acrn/hsm.c index 419271f32be8..b7f2deddc3e7 100644 --- a/drivers/virt/acrn/hsm.c +++ b/drivers/virt/acrn/hsm.c @@ -38,6 +38,67 @@ static int acrn_dev_open(struct inode *inode, struct file *filp) return 0; } +static int pmcmd_ioctl(u64 cmd, void __user *uptr) +{ + struct acrn_pstate_data *px_data; + struct acrn_cstate_data *cx_data; + u64 *pm_info; + int ret = 0; + + switch (cmd & PMCMD_TYPE_MASK) { + case ACRN_PMCMD_GET_PX_CNT: + case ACRN_PMCMD_GET_CX_CNT: + pm_info = kmalloc(sizeof(u64), GFP_KERNEL); + if (!pm_info) + return -ENOMEM; + + ret = hcall_get_cpu_state(cmd, virt_to_phys(pm_info)); + if (ret < 0) { + kfree(pm_info); + break; + } + + if (copy_to_user(uptr, pm_info, sizeof(u64))) + ret = -EFAULT; + kfree(pm_info); + break; + case ACRN_PMCMD_GET_PX_DATA: + px_data = kmalloc(sizeof(*px_data), GFP_KERNEL); + if (!px_data) + return -ENOMEM; + + ret = hcall_get_cpu_state(cmd, virt_to_phys(px_data)); + if (ret < 0) { + kfree(px_data); + break; + } + + if (copy_to_user(uptr, px_data, sizeof(*px_data))) + ret = -EFAULT; + kfree(px_data); + break; + case ACRN_PMCMD_GET_CX_DATA: + cx_data = kmalloc(sizeof(*cx_data), GFP_KERNEL); + if (!cx_data) + return -ENOMEM; + + ret = hcall_get_cpu_state(cmd, virt_to_phys(cx_data)); + if (ret < 0) { + kfree(cx_data); + break; + } + + if (copy_to_user(uptr, cx_data, sizeof(*cx_data))) + ret = -EFAULT; + kfree(cx_data); + break; + default: + break; + } + + return ret; +} + /* * HSM relies on hypercall layer of the ACRN hypervisor to do the * sanity check against the input parameters. @@ -54,6 +115,7 @@ static long acrn_dev_ioctl(struct file *filp, unsigned int cmd, struct acrn_msi_entry *msi; struct acrn_pcidev *pcidev; struct page *page; + u64 cstate_cmd; int i, ret = 0; if (vm->vmid == ACRN_INVALID_VMID && cmd != ACRN_IOCTL_CREATE_VM) { @@ -267,6 +329,13 @@ static long acrn_dev_ioctl(struct file *filp, unsigned int cmd, case ACRN_IOCTL_CLEAR_VM_IOREQ: acrn_ioreq_request_clear(vm); break; + case ACRN_IOCTL_PM_GET_CPU_STATE: + if (copy_from_user(&cstate_cmd, (void *)ioctl_param, + sizeof(cstate_cmd))) + return -EFAULT; + + ret = pmcmd_ioctl(cstate_cmd, (void __user *)ioctl_param); + break; default: dev_dbg(acrn_dev.this_device, "Unknown IOCTL 0x%x!\n", cmd); ret = -ENOTTY; diff --git a/drivers/virt/acrn/hypercall.h b/drivers/virt/acrn/hypercall.h index a8813397a3fe..e640632366f0 100644 --- a/drivers/virt/acrn/hypercall.h +++ b/drivers/virt/acrn/hypercall.h @@ -39,6 +39,9 @@ #define HC_ASSIGN_PCIDEV _HC_ID(HC_ID, HC_ID_PCI_BASE + 0x05) #define HC_DEASSIGN_PCIDEV _HC_ID(HC_ID, HC_ID_PCI_BASE + 0x06) +#define HC_ID_PM_BASE 0x80UL +#define HC_PM_GET_CPU_STATE _HC_ID(HC_ID, HC_ID_PM_BASE + 0x00) + /** * hcall_create_vm() - Create a User VM * @vminfo: Service VM GPA of info of User VM creation @@ -225,4 +228,13 @@ static inline long hcall_reset_ptdev_intr(u64 vmid, u64 irq) return acrn_hypercall2(HC_RESET_PTDEV_INTR, vmid, irq); } +/* + * hcall_get_cpu_state() - Get P-states and C-states info from the hypervisor + * @state: Service VM GPA of buffer of P-states and C-states + */ +static inline long hcall_get_cpu_state(u64 cmd, u64 state) +{ + return acrn_hypercall2(HC_PM_GET_CPU_STATE, cmd, state); +} + #endif /* __ACRN_HSM_HYPERCALL_H */ diff --git a/include/uapi/linux/acrn.h b/include/uapi/linux/acrn.h index b1c06b28ebdc..e997d80a0cc7 100644 --- a/include/uapi/linux/acrn.h +++ b/include/uapi/linux/acrn.h @@ -427,6 +427,58 @@ struct acrn_msi_entry { __u64 msi_data; }; +struct acrn_acpi_generic_address { + __u8 space_id; + __u8 bit_width; + __u8 bit_offset; + __u8 access_size; + __u64 address; +} __attribute__ ((__packed__)); + +/** + * struct acrn_cstate_data - A C state package defined in ACPI + * @cx_reg: Register of the C state object + * @type: Type of the C state object + * @latency: The worst-case latency to enter and exit this C state + * @power: The average power consumption when in this C state + */ +struct acrn_cstate_data { + struct acrn_acpi_generic_address cx_reg; + __u8 type; + __u32 latency; + __u64 power; +}; + +/** + * struct acrn_pstate_data - A P state package defined in ACPI + * @core_frequency: CPU frequency (in MHz). + * @power: Power dissipation (in milliwatts). + * @transition_latency: The worst-case latency in microseconds that CPU is + * unavailable during a transition from any P state to + * this P state. + * @bus_master_latency: The worst-case latency in microseconds that Bus Masters + * are prevented from accessing memory during a transition + * from any P state to this P state. + * @control: The value to be written to Performance Control Register + * @status: Transition status. + */ +struct acrn_pstate_data { + __u64 core_frequency; + __u64 power; + __u64 transition_latency; + __u64 bus_master_latency; + __u64 control; + __u64 status; +}; + +#define PMCMD_TYPE_MASK 0x000000ff +enum acrn_pm_cmd_type { + ACRN_PMCMD_GET_PX_CNT, + ACRN_PMCMD_GET_PX_DATA, + ACRN_PMCMD_GET_CX_CNT, + ACRN_PMCMD_GET_CX_DATA, +}; + /* The ioctl type, documented in ioctl-number.rst */ #define ACRN_IOCTL_TYPE 0xA2 @@ -478,4 +530,7 @@ struct acrn_msi_entry { #define ACRN_IOCTL_DEASSIGN_PCIDEV \ _IOW(ACRN_IOCTL_TYPE, 0x56, struct acrn_pcidev) +#define ACRN_IOCTL_PM_GET_CPU_STATE \ + _IOWR(ACRN_IOCTL_TYPE, 0x60, __u64) + #endif /* _UAPI_ACRN_H */ -- cgit v1.2.3 From d8ad515156b66e7e79a6e4c814f997ee54eb47c7 Mon Sep 17 00:00:00 2001 From: Shuo Liu Date: Sun, 7 Feb 2021 11:10:37 +0800 Subject: virt: acrn: Introduce ioeventfd ioeventfd is a mechanism to register PIO/MMIO regions to trigger an eventfd signal when written to by a User VM. ACRN userspace can register any arbitrary I/O address with a corresponding eventfd and then pass the eventfd to a specific end-point of interest for handling. Vhost is a kernel-level virtio server which uses eventfd for signalling. To support vhost on ACRN, ioeventfd is introduced in HSM. A new I/O client dedicated to ioeventfd is associated with a User VM during VM creation. HSM provides ioctls to associate an I/O region with a eventfd. The I/O client signals a eventfd once its corresponding I/O region is matched with an I/O request. Cc: Zhi Wang Cc: Zhenyu Wang Cc: Yu Wang Cc: Reinette Chatre Cc: Greg Kroah-Hartman Reviewed-by: Zhi Wang Reviewed-by: Reinette Chatre Signed-off-by: Shuo Liu Link: https://lore.kernel.org/r/20210207031040.49576-16-shuo.a.liu@intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/virt/acrn/Kconfig | 1 + drivers/virt/acrn/Makefile | 2 +- drivers/virt/acrn/acrn_drv.h | 10 ++ drivers/virt/acrn/hsm.c | 11 ++ drivers/virt/acrn/ioeventfd.c | 273 ++++++++++++++++++++++++++++++++++++++++++ drivers/virt/acrn/vm.c | 2 + include/uapi/linux/acrn.h | 29 +++++ 7 files changed, 327 insertions(+), 1 deletion(-) create mode 100644 drivers/virt/acrn/ioeventfd.c (limited to 'include') diff --git a/drivers/virt/acrn/Kconfig b/drivers/virt/acrn/Kconfig index 36c80378c30c..3e1a61c9d8d8 100644 --- a/drivers/virt/acrn/Kconfig +++ b/drivers/virt/acrn/Kconfig @@ -2,6 +2,7 @@ config ACRN_HSM tristate "ACRN Hypervisor Service Module" depends on ACRN_GUEST + select EVENTFD help ACRN Hypervisor Service Module (HSM) is a kernel module which communicates with ACRN userspace through ioctls and talks to diff --git a/drivers/virt/acrn/Makefile b/drivers/virt/acrn/Makefile index 21721cbf6a80..755b583b32ca 100644 --- a/drivers/virt/acrn/Makefile +++ b/drivers/virt/acrn/Makefile @@ -1,3 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_ACRN_HSM) := acrn.o -acrn-y := hsm.o vm.o mm.o ioreq.o +acrn-y := hsm.o vm.o mm.o ioreq.o ioeventfd.o diff --git a/drivers/virt/acrn/acrn_drv.h b/drivers/virt/acrn/acrn_drv.h index 8a7d7721f505..e3f8190bd972 100644 --- a/drivers/virt/acrn/acrn_drv.h +++ b/drivers/virt/acrn/acrn_drv.h @@ -156,6 +156,9 @@ extern rwlock_t acrn_vm_list_lock; * @ioreq_page: The page of the I/O request shared buffer * @pci_conf_addr: Address of a PCI configuration access emulation * @monitor_page: Page of interrupt statistics of User VM + * @ioeventfds_lock: Lock to protect ioeventfds list + * @ioeventfds: List to link all hsm_ioeventfd + * @ioeventfd_client: I/O client for ioeventfds of the VM */ struct acrn_vm { struct list_head list; @@ -172,6 +175,9 @@ struct acrn_vm { struct page *ioreq_page; u32 pci_conf_addr; struct page *monitor_page; + struct mutex ioeventfds_lock; + struct list_head ioeventfds; + struct acrn_ioreq_client *ioeventfd_client; }; struct acrn_vm *acrn_vm_create(struct acrn_vm *vm, @@ -204,4 +210,8 @@ void acrn_ioreq_range_del(struct acrn_ioreq_client *client, int acrn_msi_inject(struct acrn_vm *vm, u64 msi_addr, u64 msi_data); +int acrn_ioeventfd_init(struct acrn_vm *vm); +int acrn_ioeventfd_config(struct acrn_vm *vm, struct acrn_ioeventfd *args); +void acrn_ioeventfd_deinit(struct acrn_vm *vm); + #endif /* __ACRN_HSM_DRV_H */ diff --git a/drivers/virt/acrn/hsm.c b/drivers/virt/acrn/hsm.c index b7f2deddc3e7..0b4e88b0b6bc 100644 --- a/drivers/virt/acrn/hsm.c +++ b/drivers/virt/acrn/hsm.c @@ -111,6 +111,7 @@ static long acrn_dev_ioctl(struct file *filp, unsigned int cmd, struct acrn_vcpu_regs *cpu_regs; struct acrn_ioreq_notify notify; struct acrn_ptdev_irq *irq_info; + struct acrn_ioeventfd ioeventfd; struct acrn_vm_memmap memmap; struct acrn_msi_entry *msi; struct acrn_pcidev *pcidev; @@ -336,6 +337,16 @@ static long acrn_dev_ioctl(struct file *filp, unsigned int cmd, ret = pmcmd_ioctl(cstate_cmd, (void __user *)ioctl_param); break; + case ACRN_IOCTL_IOEVENTFD: + if (copy_from_user(&ioeventfd, (void __user *)ioctl_param, + sizeof(ioeventfd))) + return -EFAULT; + + if (ioeventfd.reserved != 0) + return -EINVAL; + + ret = acrn_ioeventfd_config(vm, &ioeventfd); + break; default: dev_dbg(acrn_dev.this_device, "Unknown IOCTL 0x%x!\n", cmd); ret = -ENOTTY; diff --git a/drivers/virt/acrn/ioeventfd.c b/drivers/virt/acrn/ioeventfd.c new file mode 100644 index 000000000000..ac4037e9f947 --- /dev/null +++ b/drivers/virt/acrn/ioeventfd.c @@ -0,0 +1,273 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * ACRN HSM eventfd - use eventfd objects to signal expected I/O requests + * + * Copyright (C) 2020 Intel Corporation. All rights reserved. + * + * Authors: + * Shuo Liu + * Yakui Zhao + */ + +#include +#include + +#include "acrn_drv.h" + +/** + * struct hsm_ioeventfd - Properties of HSM ioeventfd + * @list: Entry within &acrn_vm.ioeventfds of ioeventfds of a VM + * @eventfd: Eventfd of the HSM ioeventfd + * @addr: Address of I/O range + * @data: Data for matching + * @length: Length of I/O range + * @type: Type of I/O range (ACRN_IOREQ_TYPE_MMIO/ACRN_IOREQ_TYPE_PORTIO) + * @wildcard: Data matching or not + */ +struct hsm_ioeventfd { + struct list_head list; + struct eventfd_ctx *eventfd; + u64 addr; + u64 data; + int length; + int type; + bool wildcard; +}; + +static inline int ioreq_type_from_flags(int flags) +{ + return flags & ACRN_IOEVENTFD_FLAG_PIO ? + ACRN_IOREQ_TYPE_PORTIO : ACRN_IOREQ_TYPE_MMIO; +} + +static void acrn_ioeventfd_shutdown(struct acrn_vm *vm, struct hsm_ioeventfd *p) +{ + lockdep_assert_held(&vm->ioeventfds_lock); + + eventfd_ctx_put(p->eventfd); + list_del(&p->list); + kfree(p); +} + +static bool hsm_ioeventfd_is_conflict(struct acrn_vm *vm, + struct hsm_ioeventfd *ioeventfd) +{ + struct hsm_ioeventfd *p; + + lockdep_assert_held(&vm->ioeventfds_lock); + + /* Either one is wildcard, the data matching will be skipped. */ + list_for_each_entry(p, &vm->ioeventfds, list) + if (p->eventfd == ioeventfd->eventfd && + p->addr == ioeventfd->addr && + p->type == ioeventfd->type && + (p->wildcard || ioeventfd->wildcard || + p->data == ioeventfd->data)) + return true; + + return false; +} + +/* + * Assign an eventfd to a VM and create a HSM ioeventfd associated with the + * eventfd. The properties of the HSM ioeventfd are built from a &struct + * acrn_ioeventfd. + */ +static int acrn_ioeventfd_assign(struct acrn_vm *vm, + struct acrn_ioeventfd *args) +{ + struct eventfd_ctx *eventfd; + struct hsm_ioeventfd *p; + int ret; + + /* Check for range overflow */ + if (args->addr + args->len < args->addr) + return -EINVAL; + + /* + * Currently, acrn_ioeventfd is used to support vhost. 1,2,4,8 width + * accesses can cover vhost's requirements. + */ + if (!(args->len == 1 || args->len == 2 || + args->len == 4 || args->len == 8)) + return -EINVAL; + + eventfd = eventfd_ctx_fdget(args->fd); + if (IS_ERR(eventfd)) + return PTR_ERR(eventfd); + + p = kzalloc(sizeof(*p), GFP_KERNEL); + if (!p) { + ret = -ENOMEM; + goto fail; + } + + INIT_LIST_HEAD(&p->list); + p->addr = args->addr; + p->length = args->len; + p->eventfd = eventfd; + p->type = ioreq_type_from_flags(args->flags); + + /* + * ACRN_IOEVENTFD_FLAG_DATAMATCH flag is set in virtio 1.0 support, the + * writing of notification register of each virtqueue may trigger the + * notification. There is no data matching requirement. + */ + if (args->flags & ACRN_IOEVENTFD_FLAG_DATAMATCH) + p->data = args->data; + else + p->wildcard = true; + + mutex_lock(&vm->ioeventfds_lock); + + if (hsm_ioeventfd_is_conflict(vm, p)) { + ret = -EEXIST; + goto unlock_fail; + } + + /* register the I/O range into ioreq client */ + ret = acrn_ioreq_range_add(vm->ioeventfd_client, p->type, + p->addr, p->addr + p->length - 1); + if (ret < 0) + goto unlock_fail; + + list_add_tail(&p->list, &vm->ioeventfds); + mutex_unlock(&vm->ioeventfds_lock); + + return 0; + +unlock_fail: + mutex_unlock(&vm->ioeventfds_lock); + kfree(p); +fail: + eventfd_ctx_put(eventfd); + return ret; +} + +static int acrn_ioeventfd_deassign(struct acrn_vm *vm, + struct acrn_ioeventfd *args) +{ + struct hsm_ioeventfd *p; + struct eventfd_ctx *eventfd; + + eventfd = eventfd_ctx_fdget(args->fd); + if (IS_ERR(eventfd)) + return PTR_ERR(eventfd); + + mutex_lock(&vm->ioeventfds_lock); + list_for_each_entry(p, &vm->ioeventfds, list) { + if (p->eventfd != eventfd) + continue; + + acrn_ioreq_range_del(vm->ioeventfd_client, p->type, + p->addr, p->addr + p->length - 1); + acrn_ioeventfd_shutdown(vm, p); + break; + } + mutex_unlock(&vm->ioeventfds_lock); + + eventfd_ctx_put(eventfd); + return 0; +} + +static struct hsm_ioeventfd *hsm_ioeventfd_match(struct acrn_vm *vm, u64 addr, + u64 data, int len, int type) +{ + struct hsm_ioeventfd *p = NULL; + + lockdep_assert_held(&vm->ioeventfds_lock); + + list_for_each_entry(p, &vm->ioeventfds, list) { + if (p->type == type && p->addr == addr && p->length >= len && + (p->wildcard || p->data == data)) + return p; + } + + return NULL; +} + +static int acrn_ioeventfd_handler(struct acrn_ioreq_client *client, + struct acrn_io_request *req) +{ + struct hsm_ioeventfd *p; + u64 addr, val; + int size; + + if (req->type == ACRN_IOREQ_TYPE_MMIO) { + /* + * I/O requests are dispatched by range check only, so a + * acrn_ioreq_client need process both READ and WRITE accesses + * of same range. READ accesses are safe to be ignored here + * because virtio PCI devices write the notify registers for + * notification. + */ + if (req->reqs.mmio_request.direction == ACRN_IOREQ_DIR_READ) { + /* reading does nothing and return 0 */ + req->reqs.mmio_request.value = 0; + return 0; + } + addr = req->reqs.mmio_request.address; + size = req->reqs.mmio_request.size; + val = req->reqs.mmio_request.value; + } else { + if (req->reqs.pio_request.direction == ACRN_IOREQ_DIR_READ) { + /* reading does nothing and return 0 */ + req->reqs.pio_request.value = 0; + return 0; + } + addr = req->reqs.pio_request.address; + size = req->reqs.pio_request.size; + val = req->reqs.pio_request.value; + } + + mutex_lock(&client->vm->ioeventfds_lock); + p = hsm_ioeventfd_match(client->vm, addr, val, size, req->type); + if (p) + eventfd_signal(p->eventfd, 1); + mutex_unlock(&client->vm->ioeventfds_lock); + + return 0; +} + +int acrn_ioeventfd_config(struct acrn_vm *vm, struct acrn_ioeventfd *args) +{ + int ret; + + if (args->flags & ACRN_IOEVENTFD_FLAG_DEASSIGN) + ret = acrn_ioeventfd_deassign(vm, args); + else + ret = acrn_ioeventfd_assign(vm, args); + + return ret; +} + +int acrn_ioeventfd_init(struct acrn_vm *vm) +{ + char name[ACRN_NAME_LEN]; + + mutex_init(&vm->ioeventfds_lock); + INIT_LIST_HEAD(&vm->ioeventfds); + snprintf(name, sizeof(name), "ioeventfd-%u", vm->vmid); + vm->ioeventfd_client = acrn_ioreq_client_create(vm, + acrn_ioeventfd_handler, + NULL, false, name); + if (!vm->ioeventfd_client) { + dev_err(acrn_dev.this_device, "Failed to create ioeventfd ioreq client!\n"); + return -EINVAL; + } + + dev_dbg(acrn_dev.this_device, "VM %u ioeventfd init.\n", vm->vmid); + return 0; +} + +void acrn_ioeventfd_deinit(struct acrn_vm *vm) +{ + struct hsm_ioeventfd *p, *next; + + dev_dbg(acrn_dev.this_device, "VM %u ioeventfd deinit.\n", vm->vmid); + acrn_ioreq_client_destroy(vm->ioeventfd_client); + mutex_lock(&vm->ioeventfds_lock); + list_for_each_entry_safe(p, next, &vm->ioeventfds, list) + acrn_ioeventfd_shutdown(vm, p); + mutex_unlock(&vm->ioeventfds_lock); +} diff --git a/drivers/virt/acrn/vm.c b/drivers/virt/acrn/vm.c index db597f27690a..2b322d956a8c 100644 --- a/drivers/virt/acrn/vm.c +++ b/drivers/virt/acrn/vm.c @@ -50,6 +50,7 @@ struct acrn_vm *acrn_vm_create(struct acrn_vm *vm, list_add(&vm->list, &acrn_vm_list); write_unlock_bh(&acrn_vm_list_lock); + acrn_ioeventfd_init(vm); dev_dbg(acrn_dev.this_device, "VM %u created.\n", vm->vmid); return vm; } @@ -67,6 +68,7 @@ int acrn_vm_destroy(struct acrn_vm *vm) list_del_init(&vm->list); write_unlock_bh(&acrn_vm_list_lock); + acrn_ioeventfd_deinit(vm); acrn_ioreq_deinit(vm); if (vm->monitor_page) { put_page(vm->monitor_page); diff --git a/include/uapi/linux/acrn.h b/include/uapi/linux/acrn.h index e997d80a0cc7..132c5ff95967 100644 --- a/include/uapi/linux/acrn.h +++ b/include/uapi/linux/acrn.h @@ -479,6 +479,32 @@ enum acrn_pm_cmd_type { ACRN_PMCMD_GET_CX_DATA, }; +#define ACRN_IOEVENTFD_FLAG_PIO 0x01 +#define ACRN_IOEVENTFD_FLAG_DATAMATCH 0x02 +#define ACRN_IOEVENTFD_FLAG_DEASSIGN 0x04 +/** + * struct acrn_ioeventfd - Data to operate a &struct hsm_ioeventfd + * @fd: The fd of eventfd associated with a hsm_ioeventfd + * @flags: Logical-OR of ACRN_IOEVENTFD_FLAG_* + * @addr: The start address of IO range of ioeventfd + * @len: The length of IO range of ioeventfd + * @reserved: Reserved and should be 0 + * @data: Data for data matching + * + * Without flag ACRN_IOEVENTFD_FLAG_DEASSIGN, ioctl ACRN_IOCTL_IOEVENTFD + * creates a &struct hsm_ioeventfd with properties originated from &struct + * acrn_ioeventfd. With flag ACRN_IOEVENTFD_FLAG_DEASSIGN, ioctl + * ACRN_IOCTL_IOEVENTFD destroys the &struct hsm_ioeventfd matching the fd. + */ +struct acrn_ioeventfd { + __u32 fd; + __u32 flags; + __u64 addr; + __u32 len; + __u32 reserved; + __u64 data; +}; + /* The ioctl type, documented in ioctl-number.rst */ #define ACRN_IOCTL_TYPE 0xA2 @@ -533,4 +559,7 @@ enum acrn_pm_cmd_type { #define ACRN_IOCTL_PM_GET_CPU_STATE \ _IOWR(ACRN_IOCTL_TYPE, 0x60, __u64) +#define ACRN_IOCTL_IOEVENTFD \ + _IOW(ACRN_IOCTL_TYPE, 0x70, struct acrn_ioeventfd) + #endif /* _UAPI_ACRN_H */ -- cgit v1.2.3 From aa3b483ff1d71c50b33db154048dff9a8f08ac71 Mon Sep 17 00:00:00 2001 From: Shuo Liu Date: Sun, 7 Feb 2021 11:10:38 +0800 Subject: virt: acrn: Introduce irqfd irqfd is a mechanism to inject a specific interrupt to a User VM using a decoupled eventfd mechanism. Vhost is a kernel-level virtio server which uses eventfd for interrupt injection. To support vhost on ACRN, irqfd is introduced in HSM. HSM provides ioctls to associate a virtual Message Signaled Interrupt (MSI) with an eventfd. The corresponding virtual MSI will be injected into a User VM once the eventfd got signal. Cc: Zhi Wang Cc: Zhenyu Wang Cc: Yu Wang Cc: Reinette Chatre Cc: Greg Kroah-Hartman Reviewed-by: Zhi Wang Reviewed-by: Reinette Chatre Signed-off-by: Shuo Liu Link: https://lore.kernel.org/r/20210207031040.49576-17-shuo.a.liu@intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/virt/acrn/Makefile | 2 +- drivers/virt/acrn/acrn_drv.h | 10 ++ drivers/virt/acrn/hsm.c | 7 ++ drivers/virt/acrn/irqfd.c | 235 +++++++++++++++++++++++++++++++++++++++++++ drivers/virt/acrn/vm.c | 3 + include/uapi/linux/acrn.h | 15 +++ 6 files changed, 271 insertions(+), 1 deletion(-) create mode 100644 drivers/virt/acrn/irqfd.c (limited to 'include') diff --git a/drivers/virt/acrn/Makefile b/drivers/virt/acrn/Makefile index 755b583b32ca..08ce641dcfa1 100644 --- a/drivers/virt/acrn/Makefile +++ b/drivers/virt/acrn/Makefile @@ -1,3 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_ACRN_HSM) := acrn.o -acrn-y := hsm.o vm.o mm.o ioreq.o ioeventfd.o +acrn-y := hsm.o vm.o mm.o ioreq.o ioeventfd.o irqfd.o diff --git a/drivers/virt/acrn/acrn_drv.h b/drivers/virt/acrn/acrn_drv.h index e3f8190bd972..1be54efa666c 100644 --- a/drivers/virt/acrn/acrn_drv.h +++ b/drivers/virt/acrn/acrn_drv.h @@ -159,6 +159,9 @@ extern rwlock_t acrn_vm_list_lock; * @ioeventfds_lock: Lock to protect ioeventfds list * @ioeventfds: List to link all hsm_ioeventfd * @ioeventfd_client: I/O client for ioeventfds of the VM + * @irqfds_lock: Lock to protect irqfds list + * @irqfds: List to link all hsm_irqfd + * @irqfd_wq: Workqueue for irqfd async shutdown */ struct acrn_vm { struct list_head list; @@ -178,6 +181,9 @@ struct acrn_vm { struct mutex ioeventfds_lock; struct list_head ioeventfds; struct acrn_ioreq_client *ioeventfd_client; + struct mutex irqfds_lock; + struct list_head irqfds; + struct workqueue_struct *irqfd_wq; }; struct acrn_vm *acrn_vm_create(struct acrn_vm *vm, @@ -214,4 +220,8 @@ int acrn_ioeventfd_init(struct acrn_vm *vm); int acrn_ioeventfd_config(struct acrn_vm *vm, struct acrn_ioeventfd *args); void acrn_ioeventfd_deinit(struct acrn_vm *vm); +int acrn_irqfd_init(struct acrn_vm *vm); +int acrn_irqfd_config(struct acrn_vm *vm, struct acrn_irqfd *args); +void acrn_irqfd_deinit(struct acrn_vm *vm); + #endif /* __ACRN_HSM_DRV_H */ diff --git a/drivers/virt/acrn/hsm.c b/drivers/virt/acrn/hsm.c index 0b4e88b0b6bc..93f6abe10fa6 100644 --- a/drivers/virt/acrn/hsm.c +++ b/drivers/virt/acrn/hsm.c @@ -115,6 +115,7 @@ static long acrn_dev_ioctl(struct file *filp, unsigned int cmd, struct acrn_vm_memmap memmap; struct acrn_msi_entry *msi; struct acrn_pcidev *pcidev; + struct acrn_irqfd irqfd; struct page *page; u64 cstate_cmd; int i, ret = 0; @@ -347,6 +348,12 @@ static long acrn_dev_ioctl(struct file *filp, unsigned int cmd, ret = acrn_ioeventfd_config(vm, &ioeventfd); break; + case ACRN_IOCTL_IRQFD: + if (copy_from_user(&irqfd, (void __user *)ioctl_param, + sizeof(irqfd))) + return -EFAULT; + ret = acrn_irqfd_config(vm, &irqfd); + break; default: dev_dbg(acrn_dev.this_device, "Unknown IOCTL 0x%x!\n", cmd); ret = -ENOTTY; diff --git a/drivers/virt/acrn/irqfd.c b/drivers/virt/acrn/irqfd.c new file mode 100644 index 000000000000..a8766d528e29 --- /dev/null +++ b/drivers/virt/acrn/irqfd.c @@ -0,0 +1,235 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * ACRN HSM irqfd: use eventfd objects to inject virtual interrupts + * + * Copyright (C) 2020 Intel Corporation. All rights reserved. + * + * Authors: + * Shuo Liu + * Yakui Zhao + */ + +#include +#include +#include +#include + +#include "acrn_drv.h" + +static LIST_HEAD(acrn_irqfd_clients); +static DEFINE_MUTEX(acrn_irqfds_mutex); + +/** + * struct hsm_irqfd - Properties of HSM irqfd + * @vm: Associated VM pointer + * @wait: Entry of wait-queue + * @shutdown: Async shutdown work + * @eventfd: Associated eventfd + * @list: Entry within &acrn_vm.irqfds of irqfds of a VM + * @pt: Structure for select/poll on the associated eventfd + * @msi: MSI data + */ +struct hsm_irqfd { + struct acrn_vm *vm; + wait_queue_entry_t wait; + struct work_struct shutdown; + struct eventfd_ctx *eventfd; + struct list_head list; + poll_table pt; + struct acrn_msi_entry msi; +}; + +static void acrn_irqfd_inject(struct hsm_irqfd *irqfd) +{ + struct acrn_vm *vm = irqfd->vm; + + acrn_msi_inject(vm, irqfd->msi.msi_addr, + irqfd->msi.msi_data); +} + +static void hsm_irqfd_shutdown(struct hsm_irqfd *irqfd) +{ + u64 cnt; + + lockdep_assert_held(&irqfd->vm->irqfds_lock); + + /* remove from wait queue */ + list_del_init(&irqfd->list); + eventfd_ctx_remove_wait_queue(irqfd->eventfd, &irqfd->wait, &cnt); + eventfd_ctx_put(irqfd->eventfd); + kfree(irqfd); +} + +static void hsm_irqfd_shutdown_work(struct work_struct *work) +{ + struct hsm_irqfd *irqfd; + struct acrn_vm *vm; + + irqfd = container_of(work, struct hsm_irqfd, shutdown); + vm = irqfd->vm; + mutex_lock(&vm->irqfds_lock); + if (!list_empty(&irqfd->list)) + hsm_irqfd_shutdown(irqfd); + mutex_unlock(&vm->irqfds_lock); +} + +/* Called with wqh->lock held and interrupts disabled */ +static int hsm_irqfd_wakeup(wait_queue_entry_t *wait, unsigned int mode, + int sync, void *key) +{ + unsigned long poll_bits = (unsigned long)key; + struct hsm_irqfd *irqfd; + struct acrn_vm *vm; + + irqfd = container_of(wait, struct hsm_irqfd, wait); + vm = irqfd->vm; + if (poll_bits & POLLIN) + /* An event has been signaled, inject an interrupt */ + acrn_irqfd_inject(irqfd); + + if (poll_bits & POLLHUP) + /* Do shutdown work in thread to hold wqh->lock */ + queue_work(vm->irqfd_wq, &irqfd->shutdown); + + return 0; +} + +static void hsm_irqfd_poll_func(struct file *file, wait_queue_head_t *wqh, + poll_table *pt) +{ + struct hsm_irqfd *irqfd; + + irqfd = container_of(pt, struct hsm_irqfd, pt); + add_wait_queue(wqh, &irqfd->wait); +} + +/* + * Assign an eventfd to a VM and create a HSM irqfd associated with the + * eventfd. The properties of the HSM irqfd are built from a &struct + * acrn_irqfd. + */ +static int acrn_irqfd_assign(struct acrn_vm *vm, struct acrn_irqfd *args) +{ + struct eventfd_ctx *eventfd = NULL; + struct hsm_irqfd *irqfd, *tmp; + unsigned int events; + struct fd f; + int ret = 0; + + irqfd = kzalloc(sizeof(*irqfd), GFP_KERNEL); + if (!irqfd) + return -ENOMEM; + + irqfd->vm = vm; + memcpy(&irqfd->msi, &args->msi, sizeof(args->msi)); + INIT_LIST_HEAD(&irqfd->list); + INIT_WORK(&irqfd->shutdown, hsm_irqfd_shutdown_work); + + f = fdget(args->fd); + if (!f.file) { + ret = -EBADF; + goto out; + } + + eventfd = eventfd_ctx_fileget(f.file); + if (IS_ERR(eventfd)) { + ret = PTR_ERR(eventfd); + goto fail; + } + + irqfd->eventfd = eventfd; + + /* + * Install custom wake-up handling to be notified whenever underlying + * eventfd is signaled. + */ + init_waitqueue_func_entry(&irqfd->wait, hsm_irqfd_wakeup); + init_poll_funcptr(&irqfd->pt, hsm_irqfd_poll_func); + + mutex_lock(&vm->irqfds_lock); + list_for_each_entry(tmp, &vm->irqfds, list) { + if (irqfd->eventfd != tmp->eventfd) + continue; + ret = -EBUSY; + mutex_unlock(&vm->irqfds_lock); + goto fail; + } + list_add_tail(&irqfd->list, &vm->irqfds); + mutex_unlock(&vm->irqfds_lock); + + /* Check the pending event in this stage */ + events = f.file->f_op->poll(f.file, &irqfd->pt); + + if (events & POLLIN) + acrn_irqfd_inject(irqfd); + + fdput(f); + return 0; +fail: + if (eventfd && !IS_ERR(eventfd)) + eventfd_ctx_put(eventfd); + + fdput(f); +out: + kfree(irqfd); + return ret; +} + +static int acrn_irqfd_deassign(struct acrn_vm *vm, + struct acrn_irqfd *args) +{ + struct hsm_irqfd *irqfd, *tmp; + struct eventfd_ctx *eventfd; + + eventfd = eventfd_ctx_fdget(args->fd); + if (IS_ERR(eventfd)) + return PTR_ERR(eventfd); + + mutex_lock(&vm->irqfds_lock); + list_for_each_entry_safe(irqfd, tmp, &vm->irqfds, list) { + if (irqfd->eventfd == eventfd) { + hsm_irqfd_shutdown(irqfd); + break; + } + } + mutex_unlock(&vm->irqfds_lock); + eventfd_ctx_put(eventfd); + + return 0; +} + +int acrn_irqfd_config(struct acrn_vm *vm, struct acrn_irqfd *args) +{ + int ret; + + if (args->flags & ACRN_IRQFD_FLAG_DEASSIGN) + ret = acrn_irqfd_deassign(vm, args); + else + ret = acrn_irqfd_assign(vm, args); + + return ret; +} + +int acrn_irqfd_init(struct acrn_vm *vm) +{ + INIT_LIST_HEAD(&vm->irqfds); + mutex_init(&vm->irqfds_lock); + vm->irqfd_wq = alloc_workqueue("acrn_irqfd-%u", 0, 0, vm->vmid); + if (!vm->irqfd_wq) + return -ENOMEM; + + dev_dbg(acrn_dev.this_device, "VM %u irqfd init.\n", vm->vmid); + return 0; +} + +void acrn_irqfd_deinit(struct acrn_vm *vm) +{ + struct hsm_irqfd *irqfd, *next; + + dev_dbg(acrn_dev.this_device, "VM %u irqfd deinit.\n", vm->vmid); + destroy_workqueue(vm->irqfd_wq); + mutex_lock(&vm->irqfds_lock); + list_for_each_entry_safe(irqfd, next, &vm->irqfds, list) + hsm_irqfd_shutdown(irqfd); + mutex_unlock(&vm->irqfds_lock); +} diff --git a/drivers/virt/acrn/vm.c b/drivers/virt/acrn/vm.c index 2b322d956a8c..7804a2492ad7 100644 --- a/drivers/virt/acrn/vm.c +++ b/drivers/virt/acrn/vm.c @@ -51,6 +51,7 @@ struct acrn_vm *acrn_vm_create(struct acrn_vm *vm, write_unlock_bh(&acrn_vm_list_lock); acrn_ioeventfd_init(vm); + acrn_irqfd_init(vm); dev_dbg(acrn_dev.this_device, "VM %u created.\n", vm->vmid); return vm; } @@ -69,7 +70,9 @@ int acrn_vm_destroy(struct acrn_vm *vm) write_unlock_bh(&acrn_vm_list_lock); acrn_ioeventfd_deinit(vm); + acrn_irqfd_deinit(vm); acrn_ioreq_deinit(vm); + if (vm->monitor_page) { put_page(vm->monitor_page); vm->monitor_page = NULL; diff --git a/include/uapi/linux/acrn.h b/include/uapi/linux/acrn.h index 132c5ff95967..353b2a2e4536 100644 --- a/include/uapi/linux/acrn.h +++ b/include/uapi/linux/acrn.h @@ -505,6 +505,19 @@ struct acrn_ioeventfd { __u64 data; }; +#define ACRN_IRQFD_FLAG_DEASSIGN 0x01 +/** + * struct acrn_irqfd - Data to operate a &struct hsm_irqfd + * @fd: The fd of eventfd associated with a hsm_irqfd + * @flags: Logical-OR of ACRN_IRQFD_FLAG_* + * @msi: Info of MSI associated with the irqfd + */ +struct acrn_irqfd { + __s32 fd; + __u32 flags; + struct acrn_msi_entry msi; +}; + /* The ioctl type, documented in ioctl-number.rst */ #define ACRN_IOCTL_TYPE 0xA2 @@ -561,5 +574,7 @@ struct acrn_ioeventfd { #define ACRN_IOCTL_IOEVENTFD \ _IOW(ACRN_IOCTL_TYPE, 0x70, struct acrn_ioeventfd) +#define ACRN_IOCTL_IRQFD \ + _IOW(ACRN_IOCTL_TYPE, 0x71, struct acrn_irqfd) #endif /* _UAPI_ACRN_H */ -- cgit v1.2.3 From cae5216387d18c888f9f38a0cf5be341a0af75a6 Mon Sep 17 00:00:00 2001 From: Vadim Pasternak Date: Mon, 8 Feb 2021 22:16:03 +0200 Subject: i2c: mux: mlxcpld: Get rid of adapter numbers enforcement Do not set the argument 'force_nr' of i2c_mux_add_adapter() routine, instead provide argument 'chan_id'. Rename mux ids array from 'adap_ids' to 'chan_ids'. The motivation is to prepare infrastructure to be able to: - Create only the child adapters which are actually needed - for which channel ids are specified. - To assign 'nrs' to these child adapters dynamically, with no 'nr' enforcement. Signed-off-by: Vadim Pasternak Acked-by: Peter Rosin Signed-off-by: Wolfram Sang --- drivers/i2c/muxes/i2c-mux-mlxcpld.c | 7 ++----- include/linux/platform_data/mlxcpld.h | 4 ++-- 2 files changed, 4 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/drivers/i2c/muxes/i2c-mux-mlxcpld.c b/drivers/i2c/muxes/i2c-mux-mlxcpld.c index 113ad84cdd94..e99a7ad09886 100644 --- a/drivers/i2c/muxes/i2c-mux-mlxcpld.c +++ b/drivers/i2c/muxes/i2c-mux-mlxcpld.c @@ -101,9 +101,8 @@ static int mlxcpld_mux_probe(struct platform_device *pdev) struct mlxcpld_mux_plat_data *pdata = dev_get_platdata(&pdev->dev); struct i2c_client *client = to_i2c_client(pdev->dev.parent); struct i2c_mux_core *muxc; - int num, force; struct mlxcpld_mux *data; - int err; + int num, err; if (!pdata) return -EINVAL; @@ -130,9 +129,7 @@ static int mlxcpld_mux_probe(struct platform_device *pdev) /* discard unconfigured channels */ break; - force = pdata->adap_ids[num]; - - err = i2c_mux_add_adapter(muxc, force, num, 0); + err = i2c_mux_add_adapter(muxc, 0, pdata->chan_ids[num], 0); if (err) goto virt_reg_failed; } diff --git a/include/linux/platform_data/mlxcpld.h b/include/linux/platform_data/mlxcpld.h index e6c18bf017dd..04d93c563c04 100644 --- a/include/linux/platform_data/mlxcpld.h +++ b/include/linux/platform_data/mlxcpld.h @@ -11,12 +11,12 @@ /* Platform data for the CPLD I2C multiplexers */ /* mlxcpld_mux_plat_data - per mux data, used with i2c_register_board_info - * @adap_ids - adapter array + * @chan_ids - channels array * @num_adaps - number of adapters * @sel_reg_addr - mux select register offset in CPLD space */ struct mlxcpld_mux_plat_data { - int *adap_ids; + int *chan_ids; int num_adaps; int sel_reg_addr; }; -- cgit v1.2.3 From c52a1c5f5db55c6a71110c2db9ae26b9f5269d20 Mon Sep 17 00:00:00 2001 From: Vadim Pasternak Date: Mon, 8 Feb 2021 22:16:04 +0200 Subject: i2c: mux: mlxcpld: Extend driver to support word address space devices Extend driver to allow I2C routing control through CPLD devices with word address space. Till now only CPLD devices with byte address space have been supported. Signed-off-by: Vadim Pasternak Reviewed-by: Michael Shych Acked-by: Peter Rosin Signed-off-by: Wolfram Sang --- drivers/i2c/muxes/i2c-mux-mlxcpld.c | 47 +++++++++++++++++++++++++++++------ include/linux/platform_data/mlxcpld.h | 2 ++ 2 files changed, 41 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/drivers/i2c/muxes/i2c-mux-mlxcpld.c b/drivers/i2c/muxes/i2c-mux-mlxcpld.c index e99a7ad09886..10767ad4adb4 100644 --- a/drivers/i2c/muxes/i2c-mux-mlxcpld.c +++ b/drivers/i2c/muxes/i2c-mux-mlxcpld.c @@ -63,19 +63,39 @@ static int mlxcpld_mux_reg_write(struct i2c_adapter *adap, struct mlxcpld_mux *mux, u32 val) { struct i2c_client *client = mux->client; - union i2c_smbus_data data = { .byte = val }; - - return __i2c_smbus_xfer(adap, client->addr, client->flags, - I2C_SMBUS_WRITE, mux->pdata.sel_reg_addr, - I2C_SMBUS_BYTE_DATA, &data); + union i2c_smbus_data data; + struct i2c_msg msg; + u8 buf[3]; + + switch (mux->pdata.reg_size) { + case 1: + data.byte = val; + return __i2c_smbus_xfer(adap, client->addr, client->flags, + I2C_SMBUS_WRITE, mux->pdata.sel_reg_addr, + I2C_SMBUS_BYTE_DATA, &data); + case 2: + buf[0] = mux->pdata.sel_reg_addr >> 8; + buf[1] = mux->pdata.sel_reg_addr; + buf[2] = val; + msg.addr = client->addr; + msg.buf = buf; + msg.len = mux->pdata.reg_size + 1; + msg.flags = 0; + return __i2c_transfer(adap, &msg, 1); + default: + return -EINVAL; + } } static int mlxcpld_mux_select_chan(struct i2c_mux_core *muxc, u32 chan) { struct mlxcpld_mux *mux = i2c_mux_priv(muxc); - u32 regval = chan + 1; + u32 regval = chan; int err = 0; + if (mux->pdata.reg_size == 1) + regval += 1; + /* Only select the channel if its different from the last channel */ if (mux->last_val != regval) { err = mlxcpld_mux_reg_write(muxc->parent, mux, regval); @@ -103,12 +123,23 @@ static int mlxcpld_mux_probe(struct platform_device *pdev) struct i2c_mux_core *muxc; struct mlxcpld_mux *data; int num, err; + u32 func; if (!pdata) return -EINVAL; - if (!i2c_check_functionality(client->adapter, - I2C_FUNC_SMBUS_WRITE_BYTE_DATA)) + switch (pdata->reg_size) { + case 1: + func = I2C_FUNC_SMBUS_WRITE_BYTE_DATA; + break; + case 2: + func = I2C_FUNC_I2C; + break; + default: + return -EINVAL; + } + + if (!i2c_check_functionality(client->adapter, func)) return -ENODEV; muxc = i2c_mux_alloc(client->adapter, &pdev->dev, CPLD_MUX_MAX_NCHANS, diff --git a/include/linux/platform_data/mlxcpld.h b/include/linux/platform_data/mlxcpld.h index 04d93c563c04..a7bee798d991 100644 --- a/include/linux/platform_data/mlxcpld.h +++ b/include/linux/platform_data/mlxcpld.h @@ -14,11 +14,13 @@ * @chan_ids - channels array * @num_adaps - number of adapters * @sel_reg_addr - mux select register offset in CPLD space + * @reg_size: register size in bytes */ struct mlxcpld_mux_plat_data { int *chan_ids; int num_adaps; int sel_reg_addr; + u8 reg_size; }; #endif /* _LINUX_I2C_MLXCPLD_H */ -- cgit v1.2.3 From a39bd92e92b96d05d676fb5c9493cf1c911d2a0a Mon Sep 17 00:00:00 2001 From: Vadim Pasternak Date: Mon, 8 Feb 2021 22:16:06 +0200 Subject: i2c: mux: mlxcpld: Add callback to notify mux creation completion Add notification to inform caller that mux objects array has been created. It allows to user, invoked platform device registration for "i2c-mux-mlxcpld" driver, to be notified that mux infrastructure is available, and thus some devices could be connected to this infrastructure. Signed-off-by: Vadim Pasternak Acked-by: Peter Rosin Signed-off-by: Wolfram Sang --- drivers/i2c/muxes/i2c-mux-mlxcpld.c | 4 ++++ include/linux/platform_data/mlxcpld.h | 5 +++++ 2 files changed, 9 insertions(+) (limited to 'include') diff --git a/drivers/i2c/muxes/i2c-mux-mlxcpld.c b/drivers/i2c/muxes/i2c-mux-mlxcpld.c index 5e0672f9979b..1a879f6a31ef 100644 --- a/drivers/i2c/muxes/i2c-mux-mlxcpld.c +++ b/drivers/i2c/muxes/i2c-mux-mlxcpld.c @@ -159,6 +159,10 @@ static int mlxcpld_mux_probe(struct platform_device *pdev) goto virt_reg_failed; } + /* Notify caller when all channels' adapters are created. */ + if (pdata->completion_notify) + pdata->completion_notify(pdata->handle, muxc->parent, muxc->adapter); + return 0; virt_reg_failed: diff --git a/include/linux/platform_data/mlxcpld.h b/include/linux/platform_data/mlxcpld.h index a7bee798d991..d7610b528856 100644 --- a/include/linux/platform_data/mlxcpld.h +++ b/include/linux/platform_data/mlxcpld.h @@ -15,12 +15,17 @@ * @num_adaps - number of adapters * @sel_reg_addr - mux select register offset in CPLD space * @reg_size: register size in bytes + * @handle: handle to be passed by callback + * @completion_notify: callback to notify when all the adapters are created */ struct mlxcpld_mux_plat_data { int *chan_ids; int num_adaps; int sel_reg_addr; u8 reg_size; + void *handle; + int (*completion_notify)(void *handle, struct i2c_adapter *parent, + struct i2c_adapter *adapters[]); }; #endif /* _LINUX_I2C_MLXCPLD_H */ -- cgit v1.2.3 From 1077d4367ab3b97f6db2f66c87289af863652215 Mon Sep 17 00:00:00 2001 From: Michal Simek Date: Wed, 3 Feb 2021 15:13:50 +0100 Subject: firmware: xilinx: Use explicit values for all enum values Based on discussion at https://lore.kernel.org/r/20200318125003.GA2727094@kroah.com we got recommendation to use explicit values for all enum values. The patch is following this recommendation. Signed-off-by: Michal Simek Link: https://lore.kernel.org/r/daeb67ded45d8a8f6a96717d1fb9c84439dd2ae8.1612361627.git.michal.simek@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 338 +++++++++++++++++------------------ 1 file changed, 169 insertions(+), 169 deletions(-) (limited to 'include') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 0a483249ff30..71177b17eee5 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -64,25 +64,25 @@ enum pm_api_id { PM_GET_API_VERSION = 1, PM_SYSTEM_SHUTDOWN = 12, PM_REQUEST_NODE = 13, - PM_RELEASE_NODE, - PM_SET_REQUIREMENT, + PM_RELEASE_NODE = 14, + PM_SET_REQUIREMENT = 15, PM_RESET_ASSERT = 17, - PM_RESET_GET_STATUS, + PM_RESET_GET_STATUS = 18, PM_PM_INIT_FINALIZE = 21, - PM_FPGA_LOAD, - PM_FPGA_GET_STATUS, + PM_FPGA_LOAD = 22, + PM_FPGA_GET_STATUS = 23, PM_GET_CHIPID = 24, PM_IOCTL = 34, - PM_QUERY_DATA, - PM_CLOCK_ENABLE, - PM_CLOCK_DISABLE, - PM_CLOCK_GETSTATE, - PM_CLOCK_SETDIVIDER, - PM_CLOCK_GETDIVIDER, - PM_CLOCK_SETRATE, - PM_CLOCK_GETRATE, - PM_CLOCK_SETPARENT, - PM_CLOCK_GETPARENT, + PM_QUERY_DATA = 35, + PM_CLOCK_ENABLE = 36, + PM_CLOCK_DISABLE = 37, + PM_CLOCK_GETSTATE = 38, + PM_CLOCK_SETDIVIDER = 39, + PM_CLOCK_GETDIVIDER = 40, + PM_CLOCK_SETRATE = 41, + PM_CLOCK_GETRATE = 42, + PM_CLOCK_SETPARENT = 43, + PM_CLOCK_GETPARENT = 44, PM_SECURE_AES = 47, PM_FEATURE_CHECK = 63, }; @@ -92,21 +92,21 @@ enum pm_ret_status { XST_PM_SUCCESS = 0, XST_PM_NO_FEATURE = 19, XST_PM_INTERNAL = 2000, - XST_PM_CONFLICT, - XST_PM_NO_ACCESS, - XST_PM_INVALID_NODE, - XST_PM_DOUBLE_REQ, - XST_PM_ABORT_SUSPEND, + XST_PM_CONFLICT = 2001, + XST_PM_NO_ACCESS = 2002, + XST_PM_INVALID_NODE = 2003, + XST_PM_DOUBLE_REQ = 2004, + XST_PM_ABORT_SUSPEND = 2005, XST_PM_MULT_USER = 2008, }; enum pm_ioctl_id { IOCTL_SD_DLL_RESET = 6, - IOCTL_SET_SD_TAPDELAY, - IOCTL_SET_PLL_FRAC_MODE, - IOCTL_GET_PLL_FRAC_MODE, - IOCTL_SET_PLL_FRAC_DATA, - IOCTL_GET_PLL_FRAC_DATA, + IOCTL_SET_SD_TAPDELAY = 7, + IOCTL_SET_PLL_FRAC_MODE = 8, + IOCTL_GET_PLL_FRAC_MODE = 9, + IOCTL_SET_PLL_FRAC_DATA = 10, + IOCTL_GET_PLL_FRAC_DATA = 11, IOCTL_WRITE_GGS = 12, IOCTL_READ_GGS = 13, IOCTL_WRITE_PGGS = 14, @@ -116,185 +116,185 @@ enum pm_ioctl_id { }; enum pm_query_id { - PM_QID_INVALID, - PM_QID_CLOCK_GET_NAME, - PM_QID_CLOCK_GET_TOPOLOGY, - PM_QID_CLOCK_GET_FIXEDFACTOR_PARAMS, - PM_QID_CLOCK_GET_PARENTS, - PM_QID_CLOCK_GET_ATTRIBUTES, + PM_QID_INVALID = 0, + PM_QID_CLOCK_GET_NAME = 1, + PM_QID_CLOCK_GET_TOPOLOGY = 2, + PM_QID_CLOCK_GET_FIXEDFACTOR_PARAMS = 3, + PM_QID_CLOCK_GET_PARENTS = 4, + PM_QID_CLOCK_GET_ATTRIBUTES = 5, PM_QID_CLOCK_GET_NUM_CLOCKS = 12, - PM_QID_CLOCK_GET_MAX_DIVISOR, + PM_QID_CLOCK_GET_MAX_DIVISOR = 13, }; enum zynqmp_pm_reset_action { - PM_RESET_ACTION_RELEASE, - PM_RESET_ACTION_ASSERT, - PM_RESET_ACTION_PULSE, + PM_RESET_ACTION_RELEASE = 0, + PM_RESET_ACTION_ASSERT = 1, + PM_RESET_ACTION_PULSE = 2, }; enum zynqmp_pm_reset { ZYNQMP_PM_RESET_START = 1000, ZYNQMP_PM_RESET_PCIE_CFG = ZYNQMP_PM_RESET_START, - ZYNQMP_PM_RESET_PCIE_BRIDGE, - ZYNQMP_PM_RESET_PCIE_CTRL, - ZYNQMP_PM_RESET_DP, - ZYNQMP_PM_RESET_SWDT_CRF, - ZYNQMP_PM_RESET_AFI_FM5, - ZYNQMP_PM_RESET_AFI_FM4, - ZYNQMP_PM_RESET_AFI_FM3, - ZYNQMP_PM_RESET_AFI_FM2, - ZYNQMP_PM_RESET_AFI_FM1, - ZYNQMP_PM_RESET_AFI_FM0, - ZYNQMP_PM_RESET_GDMA, - ZYNQMP_PM_RESET_GPU_PP1, - ZYNQMP_PM_RESET_GPU_PP0, - ZYNQMP_PM_RESET_GPU, - ZYNQMP_PM_RESET_GT, - ZYNQMP_PM_RESET_SATA, - ZYNQMP_PM_RESET_ACPU3_PWRON, - ZYNQMP_PM_RESET_ACPU2_PWRON, - ZYNQMP_PM_RESET_ACPU1_PWRON, - ZYNQMP_PM_RESET_ACPU0_PWRON, - ZYNQMP_PM_RESET_APU_L2, - ZYNQMP_PM_RESET_ACPU3, - ZYNQMP_PM_RESET_ACPU2, - ZYNQMP_PM_RESET_ACPU1, - ZYNQMP_PM_RESET_ACPU0, - ZYNQMP_PM_RESET_DDR, - ZYNQMP_PM_RESET_APM_FPD, - ZYNQMP_PM_RESET_SOFT, - ZYNQMP_PM_RESET_GEM0, - ZYNQMP_PM_RESET_GEM1, - ZYNQMP_PM_RESET_GEM2, - ZYNQMP_PM_RESET_GEM3, - ZYNQMP_PM_RESET_QSPI, - ZYNQMP_PM_RESET_UART0, - ZYNQMP_PM_RESET_UART1, - ZYNQMP_PM_RESET_SPI0, - ZYNQMP_PM_RESET_SPI1, - ZYNQMP_PM_RESET_SDIO0, - ZYNQMP_PM_RESET_SDIO1, - ZYNQMP_PM_RESET_CAN0, - ZYNQMP_PM_RESET_CAN1, - ZYNQMP_PM_RESET_I2C0, - ZYNQMP_PM_RESET_I2C1, - ZYNQMP_PM_RESET_TTC0, - ZYNQMP_PM_RESET_TTC1, - ZYNQMP_PM_RESET_TTC2, - ZYNQMP_PM_RESET_TTC3, - ZYNQMP_PM_RESET_SWDT_CRL, - ZYNQMP_PM_RESET_NAND, - ZYNQMP_PM_RESET_ADMA, - ZYNQMP_PM_RESET_GPIO, - ZYNQMP_PM_RESET_IOU_CC, - ZYNQMP_PM_RESET_TIMESTAMP, - ZYNQMP_PM_RESET_RPU_R50, - ZYNQMP_PM_RESET_RPU_R51, - ZYNQMP_PM_RESET_RPU_AMBA, - ZYNQMP_PM_RESET_OCM, - ZYNQMP_PM_RESET_RPU_PGE, - ZYNQMP_PM_RESET_USB0_CORERESET, - ZYNQMP_PM_RESET_USB1_CORERESET, - ZYNQMP_PM_RESET_USB0_HIBERRESET, - ZYNQMP_PM_RESET_USB1_HIBERRESET, - ZYNQMP_PM_RESET_USB0_APB, - ZYNQMP_PM_RESET_USB1_APB, - ZYNQMP_PM_RESET_IPI, - ZYNQMP_PM_RESET_APM_LPD, - ZYNQMP_PM_RESET_RTC, - ZYNQMP_PM_RESET_SYSMON, - ZYNQMP_PM_RESET_AFI_FM6, - ZYNQMP_PM_RESET_LPD_SWDT, - ZYNQMP_PM_RESET_FPD, - ZYNQMP_PM_RESET_RPU_DBG1, - ZYNQMP_PM_RESET_RPU_DBG0, - ZYNQMP_PM_RESET_DBG_LPD, - ZYNQMP_PM_RESET_DBG_FPD, - ZYNQMP_PM_RESET_APLL, - ZYNQMP_PM_RESET_DPLL, - ZYNQMP_PM_RESET_VPLL, - ZYNQMP_PM_RESET_IOPLL, - ZYNQMP_PM_RESET_RPLL, - ZYNQMP_PM_RESET_GPO3_PL_0, - ZYNQMP_PM_RESET_GPO3_PL_1, - ZYNQMP_PM_RESET_GPO3_PL_2, - ZYNQMP_PM_RESET_GPO3_PL_3, - ZYNQMP_PM_RESET_GPO3_PL_4, - ZYNQMP_PM_RESET_GPO3_PL_5, - ZYNQMP_PM_RESET_GPO3_PL_6, - ZYNQMP_PM_RESET_GPO3_PL_7, - ZYNQMP_PM_RESET_GPO3_PL_8, - ZYNQMP_PM_RESET_GPO3_PL_9, - ZYNQMP_PM_RESET_GPO3_PL_10, - ZYNQMP_PM_RESET_GPO3_PL_11, - ZYNQMP_PM_RESET_GPO3_PL_12, - ZYNQMP_PM_RESET_GPO3_PL_13, - ZYNQMP_PM_RESET_GPO3_PL_14, - ZYNQMP_PM_RESET_GPO3_PL_15, - ZYNQMP_PM_RESET_GPO3_PL_16, - ZYNQMP_PM_RESET_GPO3_PL_17, - ZYNQMP_PM_RESET_GPO3_PL_18, - ZYNQMP_PM_RESET_GPO3_PL_19, - ZYNQMP_PM_RESET_GPO3_PL_20, - ZYNQMP_PM_RESET_GPO3_PL_21, - ZYNQMP_PM_RESET_GPO3_PL_22, - ZYNQMP_PM_RESET_GPO3_PL_23, - ZYNQMP_PM_RESET_GPO3_PL_24, - ZYNQMP_PM_RESET_GPO3_PL_25, - ZYNQMP_PM_RESET_GPO3_PL_26, - ZYNQMP_PM_RESET_GPO3_PL_27, - ZYNQMP_PM_RESET_GPO3_PL_28, - ZYNQMP_PM_RESET_GPO3_PL_29, - ZYNQMP_PM_RESET_GPO3_PL_30, - ZYNQMP_PM_RESET_GPO3_PL_31, - ZYNQMP_PM_RESET_RPU_LS, - ZYNQMP_PM_RESET_PS_ONLY, - ZYNQMP_PM_RESET_PL, - ZYNQMP_PM_RESET_PS_PL0, - ZYNQMP_PM_RESET_PS_PL1, - ZYNQMP_PM_RESET_PS_PL2, - ZYNQMP_PM_RESET_PS_PL3, + ZYNQMP_PM_RESET_PCIE_BRIDGE = 1001, + ZYNQMP_PM_RESET_PCIE_CTRL = 1002, + ZYNQMP_PM_RESET_DP = 1003, + ZYNQMP_PM_RESET_SWDT_CRF = 1004, + ZYNQMP_PM_RESET_AFI_FM5 = 1005, + ZYNQMP_PM_RESET_AFI_FM4 = 1006, + ZYNQMP_PM_RESET_AFI_FM3 = 1007, + ZYNQMP_PM_RESET_AFI_FM2 = 1008, + ZYNQMP_PM_RESET_AFI_FM1 = 1009, + ZYNQMP_PM_RESET_AFI_FM0 = 1010, + ZYNQMP_PM_RESET_GDMA = 1011, + ZYNQMP_PM_RESET_GPU_PP1 = 1012, + ZYNQMP_PM_RESET_GPU_PP0 = 1013, + ZYNQMP_PM_RESET_GPU = 1014, + ZYNQMP_PM_RESET_GT = 1015, + ZYNQMP_PM_RESET_SATA = 1016, + ZYNQMP_PM_RESET_ACPU3_PWRON = 1017, + ZYNQMP_PM_RESET_ACPU2_PWRON = 1018, + ZYNQMP_PM_RESET_ACPU1_PWRON = 1019, + ZYNQMP_PM_RESET_ACPU0_PWRON = 1020, + ZYNQMP_PM_RESET_APU_L2 = 1021, + ZYNQMP_PM_RESET_ACPU3 = 1022, + ZYNQMP_PM_RESET_ACPU2 = 1023, + ZYNQMP_PM_RESET_ACPU1 = 1024, + ZYNQMP_PM_RESET_ACPU0 = 1025, + ZYNQMP_PM_RESET_DDR = 1026, + ZYNQMP_PM_RESET_APM_FPD = 1027, + ZYNQMP_PM_RESET_SOFT = 1028, + ZYNQMP_PM_RESET_GEM0 = 1029, + ZYNQMP_PM_RESET_GEM1 = 1030, + ZYNQMP_PM_RESET_GEM2 = 1031, + ZYNQMP_PM_RESET_GEM3 = 1032, + ZYNQMP_PM_RESET_QSPI = 1033, + ZYNQMP_PM_RESET_UART0 = 1034, + ZYNQMP_PM_RESET_UART1 = 1035, + ZYNQMP_PM_RESET_SPI0 = 1036, + ZYNQMP_PM_RESET_SPI1 = 1037, + ZYNQMP_PM_RESET_SDIO0 = 1038, + ZYNQMP_PM_RESET_SDIO1 = 1039, + ZYNQMP_PM_RESET_CAN0 = 1040, + ZYNQMP_PM_RESET_CAN1 = 1041, + ZYNQMP_PM_RESET_I2C0 = 1042, + ZYNQMP_PM_RESET_I2C1 = 1043, + ZYNQMP_PM_RESET_TTC0 = 1044, + ZYNQMP_PM_RESET_TTC1 = 1045, + ZYNQMP_PM_RESET_TTC2 = 1046, + ZYNQMP_PM_RESET_TTC3 = 1047, + ZYNQMP_PM_RESET_SWDT_CRL = 1048, + ZYNQMP_PM_RESET_NAND = 1049, + ZYNQMP_PM_RESET_ADMA = 1050, + ZYNQMP_PM_RESET_GPIO = 1051, + ZYNQMP_PM_RESET_IOU_CC = 1052, + ZYNQMP_PM_RESET_TIMESTAMP = 1053, + ZYNQMP_PM_RESET_RPU_R50 = 1054, + ZYNQMP_PM_RESET_RPU_R51 = 1055, + ZYNQMP_PM_RESET_RPU_AMBA = 1056, + ZYNQMP_PM_RESET_OCM = 1057, + ZYNQMP_PM_RESET_RPU_PGE = 1058, + ZYNQMP_PM_RESET_USB0_CORERESET = 1059, + ZYNQMP_PM_RESET_USB1_CORERESET = 1060, + ZYNQMP_PM_RESET_USB0_HIBERRESET = 1061, + ZYNQMP_PM_RESET_USB1_HIBERRESET = 1062, + ZYNQMP_PM_RESET_USB0_APB = 1063, + ZYNQMP_PM_RESET_USB1_APB = 1064, + ZYNQMP_PM_RESET_IPI = 1065, + ZYNQMP_PM_RESET_APM_LPD = 1066, + ZYNQMP_PM_RESET_RTC = 1067, + ZYNQMP_PM_RESET_SYSMON = 1068, + ZYNQMP_PM_RESET_AFI_FM6 = 1069, + ZYNQMP_PM_RESET_LPD_SWDT = 1070, + ZYNQMP_PM_RESET_FPD = 1071, + ZYNQMP_PM_RESET_RPU_DBG1 = 1072, + ZYNQMP_PM_RESET_RPU_DBG0 = 1073, + ZYNQMP_PM_RESET_DBG_LPD = 1074, + ZYNQMP_PM_RESET_DBG_FPD = 1075, + ZYNQMP_PM_RESET_APLL = 1076, + ZYNQMP_PM_RESET_DPLL = 1077, + ZYNQMP_PM_RESET_VPLL = 1078, + ZYNQMP_PM_RESET_IOPLL = 1079, + ZYNQMP_PM_RESET_RPLL = 1080, + ZYNQMP_PM_RESET_GPO3_PL_0 = 1081, + ZYNQMP_PM_RESET_GPO3_PL_1 = 1082, + ZYNQMP_PM_RESET_GPO3_PL_2 = 1083, + ZYNQMP_PM_RESET_GPO3_PL_3 = 1084, + ZYNQMP_PM_RESET_GPO3_PL_4 = 1085, + ZYNQMP_PM_RESET_GPO3_PL_5 = 1086, + ZYNQMP_PM_RESET_GPO3_PL_6 = 1087, + ZYNQMP_PM_RESET_GPO3_PL_7 = 1088, + ZYNQMP_PM_RESET_GPO3_PL_8 = 1089, + ZYNQMP_PM_RESET_GPO3_PL_9 = 1090, + ZYNQMP_PM_RESET_GPO3_PL_10 = 1091, + ZYNQMP_PM_RESET_GPO3_PL_11 = 1092, + ZYNQMP_PM_RESET_GPO3_PL_12 = 1093, + ZYNQMP_PM_RESET_GPO3_PL_13 = 1094, + ZYNQMP_PM_RESET_GPO3_PL_14 = 1095, + ZYNQMP_PM_RESET_GPO3_PL_15 = 1096, + ZYNQMP_PM_RESET_GPO3_PL_16 = 1097, + ZYNQMP_PM_RESET_GPO3_PL_17 = 1098, + ZYNQMP_PM_RESET_GPO3_PL_18 = 1099, + ZYNQMP_PM_RESET_GPO3_PL_19 = 1100, + ZYNQMP_PM_RESET_GPO3_PL_20 = 1101, + ZYNQMP_PM_RESET_GPO3_PL_21 = 1102, + ZYNQMP_PM_RESET_GPO3_PL_22 = 1103, + ZYNQMP_PM_RESET_GPO3_PL_23 = 1104, + ZYNQMP_PM_RESET_GPO3_PL_24 = 1105, + ZYNQMP_PM_RESET_GPO3_PL_25 = 1106, + ZYNQMP_PM_RESET_GPO3_PL_26 = 1107, + ZYNQMP_PM_RESET_GPO3_PL_27 = 1108, + ZYNQMP_PM_RESET_GPO3_PL_28 = 1109, + ZYNQMP_PM_RESET_GPO3_PL_29 = 1110, + ZYNQMP_PM_RESET_GPO3_PL_30 = 1111, + ZYNQMP_PM_RESET_GPO3_PL_31 = 1112, + ZYNQMP_PM_RESET_RPU_LS = 1113, + ZYNQMP_PM_RESET_PS_ONLY = 1114, + ZYNQMP_PM_RESET_PL = 1115, + ZYNQMP_PM_RESET_PS_PL0 = 1116, + ZYNQMP_PM_RESET_PS_PL1 = 1117, + ZYNQMP_PM_RESET_PS_PL2 = 1118, + ZYNQMP_PM_RESET_PS_PL3 = 1119, ZYNQMP_PM_RESET_END = ZYNQMP_PM_RESET_PS_PL3 }; enum zynqmp_pm_suspend_reason { SUSPEND_POWER_REQUEST = 201, - SUSPEND_ALERT, - SUSPEND_SYSTEM_SHUTDOWN, + SUSPEND_ALERT = 202, + SUSPEND_SYSTEM_SHUTDOWN = 203, }; enum zynqmp_pm_request_ack { ZYNQMP_PM_REQUEST_ACK_NO = 1, - ZYNQMP_PM_REQUEST_ACK_BLOCKING, - ZYNQMP_PM_REQUEST_ACK_NON_BLOCKING, + ZYNQMP_PM_REQUEST_ACK_BLOCKING = 2, + ZYNQMP_PM_REQUEST_ACK_NON_BLOCKING = 3, }; enum pm_node_id { NODE_SD_0 = 39, - NODE_SD_1, + NODE_SD_1 = 40, }; enum tap_delay_type { PM_TAPDELAY_INPUT = 0, - PM_TAPDELAY_OUTPUT, + PM_TAPDELAY_OUTPUT = 1, }; enum dll_reset_type { - PM_DLL_RESET_ASSERT, - PM_DLL_RESET_RELEASE, - PM_DLL_RESET_PULSE, + PM_DLL_RESET_ASSERT = 0, + PM_DLL_RESET_RELEASE = 1, + PM_DLL_RESET_PULSE = 2, }; enum zynqmp_pm_shutdown_type { - ZYNQMP_PM_SHUTDOWN_TYPE_SHUTDOWN, - ZYNQMP_PM_SHUTDOWN_TYPE_RESET, - ZYNQMP_PM_SHUTDOWN_TYPE_SETSCOPE_ONLY, + ZYNQMP_PM_SHUTDOWN_TYPE_SHUTDOWN = 0, + ZYNQMP_PM_SHUTDOWN_TYPE_RESET = 1, + ZYNQMP_PM_SHUTDOWN_TYPE_SETSCOPE_ONLY = 2, }; enum zynqmp_pm_shutdown_subtype { - ZYNQMP_PM_SHUTDOWN_SUBTYPE_SUBSYSTEM, - ZYNQMP_PM_SHUTDOWN_SUBTYPE_PS_ONLY, - ZYNQMP_PM_SHUTDOWN_SUBTYPE_SYSTEM, + ZYNQMP_PM_SHUTDOWN_SUBTYPE_SUBSYSTEM = 0, + ZYNQMP_PM_SHUTDOWN_SUBTYPE_PS_ONLY = 1, + ZYNQMP_PM_SHUTDOWN_SUBTYPE_SYSTEM = 2, }; /** -- cgit v1.2.3 From 2adc75fba3289455b9c4349dd6b95cfb7167b7ea Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Wed, 27 Jan 2021 22:23:29 +0100 Subject: vme: make remove callback return void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver core ignores the return value of struct bus_type::remove() because there is only little that can be done. To simplify the quest to make this function return void, let struct vme_driver::remove return void, too. There is only a single vme driver and it already returns 0 unconditionally in .remove(). Also fix the bus remove function to always return 0. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20210127212329.98517-1-uwe@kleine-koenig.org Signed-off-by: Greg Kroah-Hartman --- drivers/staging/vme/devices/vme_user.c | 4 +--- drivers/vme/vme.c | 4 ++-- include/linux/vme.h | 2 +- 3 files changed, 4 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/drivers/staging/vme/devices/vme_user.c b/drivers/staging/vme/devices/vme_user.c index fd0ea4dbcb91..35d7260e2271 100644 --- a/drivers/staging/vme/devices/vme_user.c +++ b/drivers/staging/vme/devices/vme_user.c @@ -689,7 +689,7 @@ err_dev: return err; } -static int vme_user_remove(struct vme_dev *dev) +static void vme_user_remove(struct vme_dev *dev) { int i; @@ -717,8 +717,6 @@ static int vme_user_remove(struct vme_dev *dev) /* Unregister the major and minor device numbers */ unregister_chrdev_region(MKDEV(VME_MAJOR, 0), VME_DEVS); - - return 0; } static struct vme_driver vme_user_driver = { diff --git a/drivers/vme/vme.c b/drivers/vme/vme.c index 54d7963c1078..1b15afea28ee 100644 --- a/drivers/vme/vme.c +++ b/drivers/vme/vme.c @@ -1997,9 +1997,9 @@ static int vme_bus_remove(struct device *dev) driver = dev->platform_data; if (driver->remove) - return driver->remove(vdev); + driver->remove(vdev); - return -ENODEV; + return 0; } struct bus_type vme_bus_type = { diff --git a/include/linux/vme.h b/include/linux/vme.h index 7e82bf500f01..b204a9b4be1b 100644 --- a/include/linux/vme.h +++ b/include/linux/vme.h @@ -122,7 +122,7 @@ struct vme_driver { const char *name; int (*match)(struct vme_dev *); int (*probe)(struct vme_dev *); - int (*remove)(struct vme_dev *); + void (*remove)(struct vme_dev *); struct device_driver driver; struct list_head devices; }; -- cgit v1.2.3 From 5c3db63abdb08d8f0ec2c609f7789a199d5c476f Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Fri, 5 Feb 2021 18:06:08 +0100 Subject: device.h: Remove bogus "the" in kerneldoc Remove the bogus word "the" from "...once the it is..." in the documentation describing the "dev_groups" member of the device_driver structure. Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20210205170608.1956223-1-geert@linux-m68k.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device/driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/device/driver.h b/include/linux/device/driver.h index ee7ba5b5417e..a498ebcf4993 100644 --- a/include/linux/device/driver.h +++ b/include/linux/device/driver.h @@ -75,7 +75,7 @@ enum probe_type { * @resume: Called to bring a device from sleep mode. * @groups: Default attributes that get created by the driver core * automatically. - * @dev_groups: Additional attributes attached to device instance once the + * @dev_groups: Additional attributes attached to device instance once * it is bound to the driver. * @pm: Power management operations of the device which matched * this driver. -- cgit v1.2.3 From 0566752c3e8681ec47fee37374cb38081d801e95 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Sun, 7 Feb 2021 14:05:43 +0100 Subject: uapi: map_to_7segment: Update example in documentation The device_attribute .show() and .store() methods gained an extra parameter in v2.6.13, but the example in the documentation for the 7-segment header file was never updated. Add the missing parameters. While at it, get rid of the (misspelled) deprecated symbolic permissions, and switch to DEVICE_ATTR_RW(), which was introduced in v3.11 Fixes: 54b6f35c99974e99 ("[PATCH] Driver core: change device_attribute callbacks") Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20210207130543.2128980-1-geert@linux-m68k.org Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/map_to_7segment.h | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/map_to_7segment.h b/include/uapi/linux/map_to_7segment.h index 13a06e5e966e..8b02088f96e3 100644 --- a/include/uapi/linux/map_to_7segment.h +++ b/include/uapi/linux/map_to_7segment.h @@ -45,17 +45,22 @@ * In device drivers it is recommended, if required, to make the char map * accessible via the sysfs interface using the following scheme: * - * static ssize_t show_map(struct device *dev, char *buf) { + * static ssize_t map_seg7_show(struct device *dev, + * struct device_attribute *attr, char *buf) + * { * memcpy(buf, &map_seg7, sizeof(map_seg7)); * return sizeof(map_seg7); * } - * static ssize_t store_map(struct device *dev, const char *buf, size_t cnt) { + * static ssize_t map_seg7_store(struct device *dev, + * struct device_attribute *attr, const char *buf, + * size_t cnt) + * { * if(cnt != sizeof(map_seg7)) * return -EINVAL; * memcpy(&map_seg7, buf, cnt); * return cnt; * } - * static DEVICE_ATTR(map_seg7, PERMS_RW, show_map, store_map); + * static DEVICE_ATTR_RW(map_seg7); * * History: * 2005-05-31 RFC linux-kernel@vger.kernel.org -- cgit v1.2.3 From dcd48b25c682106335d48c040eeaaf0ff5575c38 Mon Sep 17 00:00:00 2001 From: Remi Pommarel Date: Mon, 9 Mar 2020 22:01:57 +0100 Subject: clk: meson-axg: remove CLKID_MIPI_ENABLE CLKID_MIPI_ENABLE is not handled by the AXG clock driver anymore but by the MIPI/PCIe PHY driver. Signed-off-by: Remi Pommarel Signed-off-by: Jerome Brunet --- include/dt-bindings/clock/axg-clkc.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/dt-bindings/clock/axg-clkc.h b/include/dt-bindings/clock/axg-clkc.h index e2749dbc74b8..93752ea107e3 100644 --- a/include/dt-bindings/clock/axg-clkc.h +++ b/include/dt-bindings/clock/axg-clkc.h @@ -70,7 +70,6 @@ #define CLKID_HIFI_PLL 69 #define CLKID_PCIE_CML_EN0 79 #define CLKID_PCIE_CML_EN1 80 -#define CLKID_MIPI_ENABLE 81 #define CLKID_GEN_CLK 84 #define CLKID_VPU_0_SEL 92 #define CLKID_VPU_0 93 -- cgit v1.2.3 From 9528e0d9c10027ae80e2aab36e30a1f730b1bbf9 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Fri, 5 Feb 2021 14:26:37 -0800 Subject: driver core: fw_devlink: Detect supplier devices that will never be added During the initial parsing of firmware by fw_devlink, fw_devlink might infer that some supplier firmware nodes would get populated as devices. But the inference is not always correct. This patch tries to logically detect and fix such mistakes as boot progresses or more devices probe. fw_devlink makes a fundamental assumption that once a device binds to a driver, it will populate (i.e: add as struct devices) all the child firmware nodes that could be populated as devices (if they aren't populated already). So, whenever a device probes, we check all its child firmware nodes. If a child firmware node has a corresponding device populated, we don't modify the child node or its descendants. However, if a child firmware node has not been populated as a device, we delete all the fwnode links where the child node or its descendants are suppliers. This ensures that no other device is blocked on a firmware node that will never be populated as a device. We also mark such fwnodes as NOT_DEVICE, so that no new fwnode links are created with these nodes as suppliers. Fixes: e590474768f1 ("driver core: Set fw_devlink=on by default") Tested-by: Marek Szyprowski Acked-by: Rafael J. Wysocki Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20210205222644.2357303-2-saravanak@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 31 ++++++++++++++++++++++++++++--- include/linux/fwnode.h | 2 ++ 2 files changed, 30 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/base/core.c b/drivers/base/core.c index 484a942884ba..c95b1daabac7 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -148,6 +148,21 @@ void fwnode_links_purge(struct fwnode_handle *fwnode) fwnode_links_purge_consumers(fwnode); } +static void fw_devlink_purge_absent_suppliers(struct fwnode_handle *fwnode) +{ + struct fwnode_handle *child; + + /* Don't purge consumer links of an added child */ + if (fwnode->dev) + return; + + fwnode->flags |= FWNODE_FLAG_NOT_DEVICE; + fwnode_links_purge_consumers(fwnode); + + fwnode_for_each_available_child_node(fwnode, child) + fw_devlink_purge_absent_suppliers(child); +} + #ifdef CONFIG_SRCU static DEFINE_MUTEX(device_links_lock); DEFINE_STATIC_SRCU(device_links_srcu); @@ -1154,12 +1169,22 @@ void device_links_driver_bound(struct device *dev) LIST_HEAD(sync_list); /* - * If a device probes successfully, it's expected to have created all + * If a device binds successfully, it's expected to have created all * the device links it needs to or make new device links as it needs - * them. So, it no longer needs to wait on any suppliers. + * them. So, fw_devlink no longer needs to create device links to any + * of the device's suppliers. + * + * Also, if a child firmware node of this bound device is not added as + * a device by now, assume it is never going to be added and make sure + * other devices don't defer probe indefinitely by waiting for such a + * child device. */ - if (dev->fwnode && dev->fwnode->dev == dev) + if (dev->fwnode && dev->fwnode->dev == dev) { + struct fwnode_handle *child; fwnode_links_purge_suppliers(dev->fwnode); + fwnode_for_each_available_child_node(dev->fwnode, child) + fw_devlink_purge_absent_suppliers(child); + } device_remove_file(dev, &dev_attr_waiting_for_supplier); device_links_write_lock(); diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index fde4ad97564c..21082f11473f 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -19,8 +19,10 @@ struct device; * fwnode link flags * * LINKS_ADDED: The fwnode has already be parsed to add fwnode links. + * NOT_DEVICE: The fwnode will never be populated as a struct device. */ #define FWNODE_FLAG_LINKS_ADDED BIT(0) +#define FWNODE_FLAG_NOT_DEVICE BIT(1) struct fwnode_handle { struct fwnode_handle *secondary; -- cgit v1.2.3 From 19d0f5f6bff878277783fd98fef4ae2441d6a1d8 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Fri, 5 Feb 2021 14:26:39 -0800 Subject: driver core: Add fw_devlink.strict kernel param This param allows forcing all dependencies to be treated as mandatory. This will be useful for boards in which all optional dependencies like IOMMUs and DMAs need to be treated as mandatory dependencies. Tested-by: Marek Szyprowski Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20210205222644.2357303-4-saravanak@google.com Signed-off-by: Greg Kroah-Hartman --- Documentation/admin-guide/kernel-parameters.txt | 5 +++++ drivers/base/core.c | 12 ++++++++++++ include/linux/fwnode.h | 1 + 3 files changed, 18 insertions(+) (limited to 'include') diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index a10b545c2070..692b63644133 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1433,6 +1433,11 @@ to enforce probe and suspend/resume ordering. rpm -- Like "on", but also use to order runtime PM. + fw_devlink.strict= + [KNL] Treat all inferred dependencies as mandatory + dependencies. This only applies for fw_devlink=on|rpm. + Format: + gamecon.map[2|3]= [HW,JOY] Multisystem joystick and NES/SNES/PSX pad support via parallel port (up to 5 devices per port) diff --git a/drivers/base/core.c b/drivers/base/core.c index c95b1daabac7..f466ab4f1c35 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -1521,6 +1521,13 @@ static int __init fw_devlink_setup(char *arg) } early_param("fw_devlink", fw_devlink_setup); +static bool fw_devlink_strict; +static int __init fw_devlink_strict_setup(char *arg) +{ + return strtobool(arg, &fw_devlink_strict); +} +early_param("fw_devlink.strict", fw_devlink_strict_setup); + u32 fw_devlink_get_flags(void) { return fw_devlink_flags; @@ -1531,6 +1538,11 @@ static bool fw_devlink_is_permissive(void) return fw_devlink_flags == FW_DEVLINK_FLAGS_PERMISSIVE; } +bool fw_devlink_is_strict(void) +{ + return fw_devlink_strict && !fw_devlink_is_permissive(); +} + static void fw_devlink_parse_fwnode(struct fwnode_handle *fwnode) { if (fwnode->flags & FWNODE_FLAG_LINKS_ADDED) diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index 21082f11473f..d5caefe39d93 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -162,6 +162,7 @@ static inline void fwnode_init(struct fwnode_handle *fwnode, } extern u32 fw_devlink_get_flags(void); +extern bool fw_devlink_is_strict(void); int fwnode_link_add(struct fwnode_handle *con, struct fwnode_handle *sup); void fwnode_links_purge(struct fwnode_handle *fwnode); -- cgit v1.2.3 From 74c782cff77b3533290148df1fa6f8c7db5e60d5 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Fri, 5 Feb 2021 14:26:41 -0800 Subject: driver core: fw_devlink: Handle suppliers that don't use driver core Device links only work between devices that use the driver core to match and bind a driver to a device. So, add an API for frameworks to let the driver core know that a fwnode has been initialized by a driver without using the driver core. Then use this information to make sure that fw_devlink doesn't make the consumers wait indefinitely on suppliers that'll never bind to a driver. Tested-by: Marek Szyprowski Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20210205222644.2357303-6-saravanak@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 15 +++++++++++++++ include/linux/fwnode.h | 19 +++++++++++++++++-- 2 files changed, 32 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/base/core.c b/drivers/base/core.c index f466ab4f1c35..ea710b33bda6 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -1636,6 +1636,17 @@ static int fw_devlink_create_devlink(struct device *con, sup_dev = get_dev_from_fwnode(sup_handle); if (sup_dev) { + /* + * If it's one of those drivers that don't actually bind to + * their device using driver core, then don't wait on this + * supplier device indefinitely. + */ + if (sup_dev->links.status == DL_DEV_NO_DRIVER && + sup_handle->flags & FWNODE_FLAG_INITIALIZED) { + ret = -EINVAL; + goto out; + } + /* * If this fails, it is due to cycles in device links. Just * give up on this link and treat it as invalid. @@ -1655,6 +1666,10 @@ static int fw_devlink_create_devlink(struct device *con, goto out; } + /* Supplier that's already initialized without a struct device. */ + if (sup_handle->flags & FWNODE_FLAG_INITIALIZED) + return -EINVAL; + /* * DL_FLAG_SYNC_STATE_ONLY doesn't block probing and supports * cycles. So cycle detection isn't necessary and shouldn't be diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index d5caefe39d93..dfefd43a737c 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -11,6 +11,7 @@ #include #include +#include struct fwnode_operations; struct device; @@ -18,11 +19,13 @@ struct device; /* * fwnode link flags * - * LINKS_ADDED: The fwnode has already be parsed to add fwnode links. - * NOT_DEVICE: The fwnode will never be populated as a struct device. + * LINKS_ADDED: The fwnode has already be parsed to add fwnode links. + * NOT_DEVICE: The fwnode will never be populated as a struct device. + * INITIALIZED: The hardware corresponding to fwnode has been initialized. */ #define FWNODE_FLAG_LINKS_ADDED BIT(0) #define FWNODE_FLAG_NOT_DEVICE BIT(1) +#define FWNODE_FLAG_INITIALIZED BIT(2) struct fwnode_handle { struct fwnode_handle *secondary; @@ -161,6 +164,18 @@ static inline void fwnode_init(struct fwnode_handle *fwnode, INIT_LIST_HEAD(&fwnode->suppliers); } +static inline void fwnode_dev_initialized(struct fwnode_handle *fwnode, + bool initialized) +{ + if (IS_ERR_OR_NULL(fwnode)) + return; + + if (initialized) + fwnode->flags |= FWNODE_FLAG_INITIALIZED; + else + fwnode->flags &= ~FWNODE_FLAG_INITIALIZED; +} + extern u32 fw_devlink_get_flags(void); extern bool fw_devlink_is_strict(void); int fwnode_link_add(struct fwnode_handle *con, struct fwnode_handle *sup); -- cgit v1.2.3 From ef3c67b6454b8f542f50387ad481633ae30874ac Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 25 Jan 2021 21:39:48 +0200 Subject: mfd: intel_msic: Remove driver for deprecated platform Intel Moorestown and Medfield are quite old Intel Atom based 32-bit platforms, which were in limited use in some Android phones, tablets and consumer electronics more than eight years ago. There are no bugs or problems ever reported outside from Intel for breaking any of that platforms for years. It seems no real users exists who run more or less fresh kernel on it. Commit 05f4434bc130 ("ASoC: Intel: remove mfld_machine") is also in align with this theory. Due to above and to reduce a burden of supporting outdated drivers, remove the support for outdated platforms completely. Signed-off-by: Andy Shevchenko Acked-by: Mika Westerberg Acked-by: Linus Walleij Acked-by: Lee Jones Signed-off-by: Rafael J. Wysocki --- MAINTAINERS | 2 - arch/x86/include/asm/intel_scu_ipc_legacy.h | 12 - drivers/mfd/Kconfig | 9 - drivers/mfd/Makefile | 1 - drivers/mfd/intel_msic.c | 425 -------------------------- include/linux/mfd/intel_msic.h | 453 ---------------------------- 6 files changed, 902 deletions(-) delete mode 100644 drivers/mfd/intel_msic.c delete mode 100644 include/linux/mfd/intel_msic.h (limited to 'include') diff --git a/MAINTAINERS b/MAINTAINERS index 904eaa52f5f8..8fdb7fe27537 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9098,9 +9098,7 @@ F: drivers/gpio/gpio-*cove.c INTEL PMIC MULTIFUNCTION DEVICE DRIVERS M: Andy Shevchenko S: Maintained -F: drivers/mfd/intel_msic.c F: drivers/mfd/intel_soc_pmic* -F: include/linux/mfd/intel_msic.h F: include/linux/mfd/intel_soc_pmic* INTEL PMT DRIVER diff --git a/arch/x86/include/asm/intel_scu_ipc_legacy.h b/arch/x86/include/asm/intel_scu_ipc_legacy.h index 2232197c24f8..f8b87d8face7 100644 --- a/arch/x86/include/asm/intel_scu_ipc_legacy.h +++ b/arch/x86/include/asm/intel_scu_ipc_legacy.h @@ -16,24 +16,12 @@ /* Don't call these in new code - they will be removed eventually */ -/* Read single register */ -static inline int intel_scu_ipc_ioread8(u16 addr, u8 *data) -{ - return intel_scu_ipc_dev_ioread8(NULL, addr, data); -} - /* Read a vector */ static inline int intel_scu_ipc_readv(u16 *addr, u8 *data, int len) { return intel_scu_ipc_dev_readv(NULL, addr, data, len); } -/* Write single register */ -static inline int intel_scu_ipc_iowrite8(u16 addr, u8 data) -{ - return intel_scu_ipc_dev_iowrite8(NULL, addr, data); -} - /* Write a vector */ static inline int intel_scu_ipc_writev(u16 *addr, u8 *data, int len) { diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index bdfce7b15621..2dc58a92251b 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -659,15 +659,6 @@ config MFD_INTEL_LPSS_PCI I2C, SPI and HS-UART starting from Intel Sunrisepoint (Intel Skylake PCH) in PCI mode. -config MFD_INTEL_MSIC - bool "Intel MSIC" - depends on INTEL_SCU - select MFD_CORE - help - Select this option to enable access to Intel MSIC (Avatele - Passage) chip. This chip embeds audio, battery, GPIO, etc. - devices used in Intel Medfield platforms. - config MFD_INTEL_PMC_BXT tristate "Intel PMC Driver for Broxton" depends on X86 diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile index 14fdb188af02..be19bc799073 100644 --- a/drivers/mfd/Makefile +++ b/drivers/mfd/Makefile @@ -214,7 +214,6 @@ obj-$(CONFIG_MFD_ATMEL_SMC) += atmel-smc.o obj-$(CONFIG_MFD_INTEL_LPSS) += intel-lpss.o obj-$(CONFIG_MFD_INTEL_LPSS_PCI) += intel-lpss-pci.o obj-$(CONFIG_MFD_INTEL_LPSS_ACPI) += intel-lpss-acpi.o -obj-$(CONFIG_MFD_INTEL_MSIC) += intel_msic.o obj-$(CONFIG_MFD_INTEL_PMC_BXT) += intel_pmc_bxt.o obj-$(CONFIG_MFD_INTEL_PMT) += intel_pmt.o obj-$(CONFIG_MFD_PALMAS) += palmas.o diff --git a/drivers/mfd/intel_msic.c b/drivers/mfd/intel_msic.c deleted file mode 100644 index daa772f8146b..000000000000 --- a/drivers/mfd/intel_msic.c +++ /dev/null @@ -1,425 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Driver for Intel MSIC - * - * Copyright (C) 2011, Intel Corporation - * Author: Mika Westerberg - */ - -#include -#include -#include -#include -#include -#include -#include -#include - -#include - -#define MSIC_VENDOR(id) ((id >> 6) & 3) -#define MSIC_VERSION(id) (id & 0x3f) -#define MSIC_MAJOR(id) ('A' + ((id >> 3) & 7)) -#define MSIC_MINOR(id) (id & 7) - -/* - * MSIC interrupt tree is readable from SRAM at INTEL_MSIC_IRQ_PHYS_BASE. - * Since IRQ block starts from address 0x002 we need to subtract that from - * the actual IRQ status register address. - */ -#define MSIC_IRQ_STATUS(x) (INTEL_MSIC_IRQ_PHYS_BASE + ((x) - 2)) -#define MSIC_IRQ_STATUS_ACCDET MSIC_IRQ_STATUS(INTEL_MSIC_ACCDET) - -/* - * The SCU hardware has limitation of 16 bytes per read/write buffer on - * Medfield. - */ -#define SCU_IPC_RWBUF_LIMIT 16 - -/** - * struct intel_msic - an MSIC MFD instance - * @pdev: pointer to the platform device - * @vendor: vendor ID - * @version: chip version - * @irq_base: base address of the mapped MSIC SRAM interrupt tree - */ -struct intel_msic { - struct platform_device *pdev; - unsigned vendor; - unsigned version; - void __iomem *irq_base; -}; - -static const struct resource msic_touch_resources[] = { - DEFINE_RES_IRQ(0), -}; - -static const struct resource msic_adc_resources[] = { - DEFINE_RES_IRQ(0), -}; - -static const struct resource msic_battery_resources[] = { - DEFINE_RES_IRQ(0), -}; - -static const struct resource msic_gpio_resources[] = { - DEFINE_RES_IRQ(0), -}; - -static const struct resource msic_audio_resources[] = { - DEFINE_RES_IRQ_NAMED(0, "IRQ"), - /* - * We will pass IRQ_BASE to the driver now but this can be removed - * when/if the driver starts to use intel_msic_irq_read(). - */ - DEFINE_RES_MEM_NAMED(MSIC_IRQ_STATUS_ACCDET, 1, "IRQ_BASE"), -}; - -static const struct resource msic_hdmi_resources[] = { - DEFINE_RES_IRQ(0), -}; - -static const struct resource msic_thermal_resources[] = { - DEFINE_RES_IRQ(0), -}; - -static const struct resource msic_power_btn_resources[] = { - DEFINE_RES_IRQ(0), -}; - -static const struct resource msic_ocd_resources[] = { - DEFINE_RES_IRQ(0), -}; - -/* - * Devices that are part of the MSIC and are available via firmware - * populated SFI DEVS table. - */ -static struct mfd_cell msic_devs[] = { - [INTEL_MSIC_BLOCK_TOUCH] = { - .name = "msic_touch", - .num_resources = ARRAY_SIZE(msic_touch_resources), - .resources = msic_touch_resources, - }, - [INTEL_MSIC_BLOCK_ADC] = { - .name = "msic_adc", - .num_resources = ARRAY_SIZE(msic_adc_resources), - .resources = msic_adc_resources, - }, - [INTEL_MSIC_BLOCK_BATTERY] = { - .name = "msic_battery", - .num_resources = ARRAY_SIZE(msic_battery_resources), - .resources = msic_battery_resources, - }, - [INTEL_MSIC_BLOCK_GPIO] = { - .name = "msic_gpio", - .num_resources = ARRAY_SIZE(msic_gpio_resources), - .resources = msic_gpio_resources, - }, - [INTEL_MSIC_BLOCK_AUDIO] = { - .name = "msic_audio", - .num_resources = ARRAY_SIZE(msic_audio_resources), - .resources = msic_audio_resources, - }, - [INTEL_MSIC_BLOCK_HDMI] = { - .name = "msic_hdmi", - .num_resources = ARRAY_SIZE(msic_hdmi_resources), - .resources = msic_hdmi_resources, - }, - [INTEL_MSIC_BLOCK_THERMAL] = { - .name = "msic_thermal", - .num_resources = ARRAY_SIZE(msic_thermal_resources), - .resources = msic_thermal_resources, - }, - [INTEL_MSIC_BLOCK_POWER_BTN] = { - .name = "msic_power_btn", - .num_resources = ARRAY_SIZE(msic_power_btn_resources), - .resources = msic_power_btn_resources, - }, - [INTEL_MSIC_BLOCK_OCD] = { - .name = "msic_ocd", - .num_resources = ARRAY_SIZE(msic_ocd_resources), - .resources = msic_ocd_resources, - }, -}; - -/* - * Other MSIC related devices which are not directly available via SFI DEVS - * table. These can be pseudo devices, regulators etc. which are needed for - * different purposes. - * - * These devices appear only after the MSIC driver itself is initialized so - * we can guarantee that the SCU IPC interface is ready. - */ -static const struct mfd_cell msic_other_devs[] = { - /* Audio codec in the MSIC */ - { - .id = -1, - .name = "sn95031", - }, -}; - -/** - * intel_msic_reg_read - read a single MSIC register - * @reg: register to read - * @val: register value is placed here - * - * Read a single register from MSIC. Returns %0 on success and negative - * errno in case of failure. - * - * Function may sleep. - */ -int intel_msic_reg_read(unsigned short reg, u8 *val) -{ - return intel_scu_ipc_ioread8(reg, val); -} -EXPORT_SYMBOL_GPL(intel_msic_reg_read); - -/** - * intel_msic_reg_write - write a single MSIC register - * @reg: register to write - * @val: value to write to that register - * - * Write a single MSIC register. Returns 0 on success and negative - * errno in case of failure. - * - * Function may sleep. - */ -int intel_msic_reg_write(unsigned short reg, u8 val) -{ - return intel_scu_ipc_iowrite8(reg, val); -} -EXPORT_SYMBOL_GPL(intel_msic_reg_write); - -/** - * intel_msic_reg_update - update a single MSIC register - * @reg: register to update - * @val: value to write to the register - * @mask: specifies which of the bits are updated (%0 = don't update, - * %1 = update) - * - * Perform an update to a register @reg. @mask is used to specify which - * bits are updated. Returns %0 in case of success and negative errno in - * case of failure. - * - * Function may sleep. - */ -int intel_msic_reg_update(unsigned short reg, u8 val, u8 mask) -{ - return intel_scu_ipc_update_register(reg, val, mask); -} -EXPORT_SYMBOL_GPL(intel_msic_reg_update); - -/** - * intel_msic_bulk_read - read an array of registers - * @reg: array of register addresses to read - * @buf: array where the read values are placed - * @count: number of registers to read - * - * Function reads @count registers from the MSIC using addresses passed in - * @reg. Read values are placed in @buf. Reads are performed atomically - * wrt. MSIC. - * - * Returns %0 in case of success and negative errno in case of failure. - * - * Function may sleep. - */ -int intel_msic_bulk_read(unsigned short *reg, u8 *buf, size_t count) -{ - if (WARN_ON(count > SCU_IPC_RWBUF_LIMIT)) - return -EINVAL; - - return intel_scu_ipc_readv(reg, buf, count); -} -EXPORT_SYMBOL_GPL(intel_msic_bulk_read); - -/** - * intel_msic_bulk_write - write an array of values to the MSIC registers - * @reg: array of registers to write - * @buf: values to write to each register - * @count: number of registers to write - * - * Function writes @count registers in @buf to MSIC. Writes are performed - * atomically wrt MSIC. Returns %0 in case of success and negative errno in - * case of failure. - * - * Function may sleep. - */ -int intel_msic_bulk_write(unsigned short *reg, u8 *buf, size_t count) -{ - if (WARN_ON(count > SCU_IPC_RWBUF_LIMIT)) - return -EINVAL; - - return intel_scu_ipc_writev(reg, buf, count); -} -EXPORT_SYMBOL_GPL(intel_msic_bulk_write); - -/** - * intel_msic_irq_read - read a register from an MSIC interrupt tree - * @msic: MSIC instance - * @reg: interrupt register (between %INTEL_MSIC_IRQLVL1 and - * %INTEL_MSIC_RESETIRQ2) - * @val: value of the register is placed here - * - * This function can be used by an MSIC subdevice interrupt handler to read - * a register value from the MSIC interrupt tree. In this way subdevice - * drivers don't have to map in the interrupt tree themselves but can just - * call this function instead. - * - * Function doesn't sleep and is callable from interrupt context. - * - * Returns %-EINVAL if @reg is outside of the allowed register region. - */ -int intel_msic_irq_read(struct intel_msic *msic, unsigned short reg, u8 *val) -{ - if (WARN_ON(reg < INTEL_MSIC_IRQLVL1 || reg > INTEL_MSIC_RESETIRQ2)) - return -EINVAL; - - *val = readb(msic->irq_base + (reg - INTEL_MSIC_IRQLVL1)); - return 0; -} -EXPORT_SYMBOL_GPL(intel_msic_irq_read); - -static int intel_msic_init_devices(struct intel_msic *msic) -{ - struct platform_device *pdev = msic->pdev; - struct intel_msic_platform_data *pdata = dev_get_platdata(&pdev->dev); - int ret, i; - - if (pdata->gpio) { - struct mfd_cell *cell = &msic_devs[INTEL_MSIC_BLOCK_GPIO]; - - cell->platform_data = pdata->gpio; - cell->pdata_size = sizeof(*pdata->gpio); - } - - if (pdata->ocd) { - unsigned gpio = pdata->ocd->gpio; - - ret = devm_gpio_request_one(&pdev->dev, gpio, - GPIOF_IN, "ocd_gpio"); - if (ret) { - dev_err(&pdev->dev, "failed to register OCD GPIO\n"); - return ret; - } - - ret = gpio_to_irq(gpio); - if (ret < 0) { - dev_err(&pdev->dev, "no IRQ number for OCD GPIO\n"); - return ret; - } - - /* Update the IRQ number for the OCD */ - pdata->irq[INTEL_MSIC_BLOCK_OCD] = ret; - } - - for (i = 0; i < ARRAY_SIZE(msic_devs); i++) { - if (!pdata->irq[i]) - continue; - - ret = mfd_add_devices(&pdev->dev, -1, &msic_devs[i], 1, NULL, - pdata->irq[i], NULL); - if (ret) - goto fail; - } - - ret = mfd_add_devices(&pdev->dev, 0, msic_other_devs, - ARRAY_SIZE(msic_other_devs), NULL, 0, NULL); - if (ret) - goto fail; - - return 0; - -fail: - mfd_remove_devices(&pdev->dev); - - return ret; -} - -static void intel_msic_remove_devices(struct intel_msic *msic) -{ - struct platform_device *pdev = msic->pdev; - - mfd_remove_devices(&pdev->dev); -} - -static int intel_msic_probe(struct platform_device *pdev) -{ - struct intel_msic_platform_data *pdata = dev_get_platdata(&pdev->dev); - struct intel_msic *msic; - struct resource *res; - u8 id0, id1; - int ret; - - if (!pdata) { - dev_err(&pdev->dev, "no platform data passed\n"); - return -EINVAL; - } - - /* First validate that we have an MSIC in place */ - ret = intel_scu_ipc_ioread8(INTEL_MSIC_ID0, &id0); - if (ret) { - dev_err(&pdev->dev, "failed to identify the MSIC chip (ID0)\n"); - return -ENXIO; - } - - ret = intel_scu_ipc_ioread8(INTEL_MSIC_ID1, &id1); - if (ret) { - dev_err(&pdev->dev, "failed to identify the MSIC chip (ID1)\n"); - return -ENXIO; - } - - if (MSIC_VENDOR(id0) != MSIC_VENDOR(id1)) { - dev_err(&pdev->dev, "invalid vendor ID: %x, %x\n", id0, id1); - return -ENXIO; - } - - msic = devm_kzalloc(&pdev->dev, sizeof(*msic), GFP_KERNEL); - if (!msic) - return -ENOMEM; - - msic->vendor = MSIC_VENDOR(id0); - msic->version = MSIC_VERSION(id0); - msic->pdev = pdev; - - /* - * Map in the MSIC interrupt tree area in SRAM. This is exposed to - * the clients via intel_msic_irq_read(). - */ - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - msic->irq_base = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(msic->irq_base)) - return PTR_ERR(msic->irq_base); - - platform_set_drvdata(pdev, msic); - - ret = intel_msic_init_devices(msic); - if (ret) { - dev_err(&pdev->dev, "failed to initialize MSIC devices\n"); - return ret; - } - - dev_info(&pdev->dev, "Intel MSIC version %c%d (vendor %#x)\n", - MSIC_MAJOR(msic->version), MSIC_MINOR(msic->version), - msic->vendor); - - return 0; -} - -static int intel_msic_remove(struct platform_device *pdev) -{ - struct intel_msic *msic = platform_get_drvdata(pdev); - - intel_msic_remove_devices(msic); - - return 0; -} - -static struct platform_driver intel_msic_driver = { - .probe = intel_msic_probe, - .remove = intel_msic_remove, - .driver = { - .name = "intel_msic", - }, -}; -builtin_platform_driver(intel_msic_driver); diff --git a/include/linux/mfd/intel_msic.h b/include/linux/mfd/intel_msic.h deleted file mode 100644 index 317e8608cf41..000000000000 --- a/include/linux/mfd/intel_msic.h +++ /dev/null @@ -1,453 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Core interface for Intel MSIC - * - * Copyright (C) 2011, Intel Corporation - * Author: Mika Westerberg - */ - -#ifndef __LINUX_MFD_INTEL_MSIC_H__ -#define __LINUX_MFD_INTEL_MSIC_H__ - -/* ID */ -#define INTEL_MSIC_ID0 0x000 /* RO */ -#define INTEL_MSIC_ID1 0x001 /* RO */ - -/* IRQ */ -#define INTEL_MSIC_IRQLVL1 0x002 -#define INTEL_MSIC_ADC1INT 0x003 -#define INTEL_MSIC_CCINT 0x004 -#define INTEL_MSIC_PWRSRCINT 0x005 -#define INTEL_MSIC_PWRSRCINT1 0x006 -#define INTEL_MSIC_CHRINT 0x007 -#define INTEL_MSIC_CHRINT1 0x008 -#define INTEL_MSIC_RTCIRQ 0x009 -#define INTEL_MSIC_GPIO0LVIRQ 0x00a -#define INTEL_MSIC_GPIO1LVIRQ 0x00b -#define INTEL_MSIC_GPIOHVIRQ 0x00c -#define INTEL_MSIC_VRINT 0x00d -#define INTEL_MSIC_OCAUDIO 0x00e -#define INTEL_MSIC_ACCDET 0x00f -#define INTEL_MSIC_RESETIRQ1 0x010 -#define INTEL_MSIC_RESETIRQ2 0x011 -#define INTEL_MSIC_MADC1INT 0x012 -#define INTEL_MSIC_MCCINT 0x013 -#define INTEL_MSIC_MPWRSRCINT 0x014 -#define INTEL_MSIC_MPWRSRCINT1 0x015 -#define INTEL_MSIC_MCHRINT 0x016 -#define INTEL_MSIC_MCHRINT1 0x017 -#define INTEL_MSIC_RTCIRQMASK 0x018 -#define INTEL_MSIC_GPIO0LVIRQMASK 0x019 -#define INTEL_MSIC_GPIO1LVIRQMASK 0x01a -#define INTEL_MSIC_GPIOHVIRQMASK 0x01b -#define INTEL_MSIC_VRINTMASK 0x01c -#define INTEL_MSIC_OCAUDIOMASK 0x01d -#define INTEL_MSIC_ACCDETMASK 0x01e -#define INTEL_MSIC_RESETIRQ1MASK 0x01f -#define INTEL_MSIC_RESETIRQ2MASK 0x020 -#define INTEL_MSIC_IRQLVL1MSK 0x021 -#define INTEL_MSIC_PBCONFIG 0x03e -#define INTEL_MSIC_PBSTATUS 0x03f /* RO */ - -/* GPIO */ -#define INTEL_MSIC_GPIO0LV7CTLO 0x040 -#define INTEL_MSIC_GPIO0LV6CTLO 0x041 -#define INTEL_MSIC_GPIO0LV5CTLO 0x042 -#define INTEL_MSIC_GPIO0LV4CTLO 0x043 -#define INTEL_MSIC_GPIO0LV3CTLO 0x044 -#define INTEL_MSIC_GPIO0LV2CTLO 0x045 -#define INTEL_MSIC_GPIO0LV1CTLO 0x046 -#define INTEL_MSIC_GPIO0LV0CTLO 0x047 -#define INTEL_MSIC_GPIO1LV7CTLOS 0x048 -#define INTEL_MSIC_GPIO1LV6CTLO 0x049 -#define INTEL_MSIC_GPIO1LV5CTLO 0x04a -#define INTEL_MSIC_GPIO1LV4CTLO 0x04b -#define INTEL_MSIC_GPIO1LV3CTLO 0x04c -#define INTEL_MSIC_GPIO1LV2CTLO 0x04d -#define INTEL_MSIC_GPIO1LV1CTLO 0x04e -#define INTEL_MSIC_GPIO1LV0CTLO 0x04f -#define INTEL_MSIC_GPIO0LV7CTLI 0x050 -#define INTEL_MSIC_GPIO0LV6CTLI 0x051 -#define INTEL_MSIC_GPIO0LV5CTLI 0x052 -#define INTEL_MSIC_GPIO0LV4CTLI 0x053 -#define INTEL_MSIC_GPIO0LV3CTLI 0x054 -#define INTEL_MSIC_GPIO0LV2CTLI 0x055 -#define INTEL_MSIC_GPIO0LV1CTLI 0x056 -#define INTEL_MSIC_GPIO0LV0CTLI 0x057 -#define INTEL_MSIC_GPIO1LV7CTLIS 0x058 -#define INTEL_MSIC_GPIO1LV6CTLI 0x059 -#define INTEL_MSIC_GPIO1LV5CTLI 0x05a -#define INTEL_MSIC_GPIO1LV4CTLI 0x05b -#define INTEL_MSIC_GPIO1LV3CTLI 0x05c -#define INTEL_MSIC_GPIO1LV2CTLI 0x05d -#define INTEL_MSIC_GPIO1LV1CTLI 0x05e -#define INTEL_MSIC_GPIO1LV0CTLI 0x05f -#define INTEL_MSIC_PWM0CLKDIV1 0x061 -#define INTEL_MSIC_PWM0CLKDIV0 0x062 -#define INTEL_MSIC_PWM1CLKDIV1 0x063 -#define INTEL_MSIC_PWM1CLKDIV0 0x064 -#define INTEL_MSIC_PWM2CLKDIV1 0x065 -#define INTEL_MSIC_PWM2CLKDIV0 0x066 -#define INTEL_MSIC_PWM0DUTYCYCLE 0x067 -#define INTEL_MSIC_PWM1DUTYCYCLE 0x068 -#define INTEL_MSIC_PWM2DUTYCYCLE 0x069 -#define INTEL_MSIC_GPIO0HV3CTLO 0x06d -#define INTEL_MSIC_GPIO0HV2CTLO 0x06e -#define INTEL_MSIC_GPIO0HV1CTLO 0x06f -#define INTEL_MSIC_GPIO0HV0CTLO 0x070 -#define INTEL_MSIC_GPIO1HV3CTLO 0x071 -#define INTEL_MSIC_GPIO1HV2CTLO 0x072 -#define INTEL_MSIC_GPIO1HV1CTLO 0x073 -#define INTEL_MSIC_GPIO1HV0CTLO 0x074 -#define INTEL_MSIC_GPIO0HV3CTLI 0x075 -#define INTEL_MSIC_GPIO0HV2CTLI 0x076 -#define INTEL_MSIC_GPIO0HV1CTLI 0x077 -#define INTEL_MSIC_GPIO0HV0CTLI 0x078 -#define INTEL_MSIC_GPIO1HV3CTLI 0x079 -#define INTEL_MSIC_GPIO1HV2CTLI 0x07a -#define INTEL_MSIC_GPIO1HV1CTLI 0x07b -#define INTEL_MSIC_GPIO1HV0CTLI 0x07c - -/* SVID */ -#define INTEL_MSIC_SVIDCTRL0 0x080 -#define INTEL_MSIC_SVIDCTRL1 0x081 -#define INTEL_MSIC_SVIDCTRL2 0x082 -#define INTEL_MSIC_SVIDTXLASTPKT3 0x083 /* RO */ -#define INTEL_MSIC_SVIDTXLASTPKT2 0x084 /* RO */ -#define INTEL_MSIC_SVIDTXLASTPKT1 0x085 /* RO */ -#define INTEL_MSIC_SVIDTXLASTPKT0 0x086 /* RO */ -#define INTEL_MSIC_SVIDPKTOUTBYTE3 0x087 -#define INTEL_MSIC_SVIDPKTOUTBYTE2 0x088 -#define INTEL_MSIC_SVIDPKTOUTBYTE1 0x089 -#define INTEL_MSIC_SVIDPKTOUTBYTE0 0x08a -#define INTEL_MSIC_SVIDRXVPDEBUG1 0x08b -#define INTEL_MSIC_SVIDRXVPDEBUG0 0x08c -#define INTEL_MSIC_SVIDRXLASTPKT3 0x08d /* RO */ -#define INTEL_MSIC_SVIDRXLASTPKT2 0x08e /* RO */ -#define INTEL_MSIC_SVIDRXLASTPKT1 0x08f /* RO */ -#define INTEL_MSIC_SVIDRXLASTPKT0 0x090 /* RO */ -#define INTEL_MSIC_SVIDRXCHKSTATUS3 0x091 /* RO */ -#define INTEL_MSIC_SVIDRXCHKSTATUS2 0x092 /* RO */ -#define INTEL_MSIC_SVIDRXCHKSTATUS1 0x093 /* RO */ -#define INTEL_MSIC_SVIDRXCHKSTATUS0 0x094 /* RO */ - -/* VREG */ -#define INTEL_MSIC_VCCLATCH 0x0c0 -#define INTEL_MSIC_VNNLATCH 0x0c1 -#define INTEL_MSIC_VCCCNT 0x0c2 -#define INTEL_MSIC_SMPSRAMP 0x0c3 -#define INTEL_MSIC_VNNCNT 0x0c4 -#define INTEL_MSIC_VNNAONCNT 0x0c5 -#define INTEL_MSIC_VCC122AONCNT 0x0c6 -#define INTEL_MSIC_V180AONCNT 0x0c7 -#define INTEL_MSIC_V500CNT 0x0c8 -#define INTEL_MSIC_VIHFCNT 0x0c9 -#define INTEL_MSIC_LDORAMP1 0x0ca -#define INTEL_MSIC_LDORAMP2 0x0cb -#define INTEL_MSIC_VCC108AONCNT 0x0cc -#define INTEL_MSIC_VCC108ASCNT 0x0cd -#define INTEL_MSIC_VCC108CNT 0x0ce -#define INTEL_MSIC_VCCA100ASCNT 0x0cf -#define INTEL_MSIC_VCCA100CNT 0x0d0 -#define INTEL_MSIC_VCC180AONCNT 0x0d1 -#define INTEL_MSIC_VCC180CNT 0x0d2 -#define INTEL_MSIC_VCC330CNT 0x0d3 -#define INTEL_MSIC_VUSB330CNT 0x0d4 -#define INTEL_MSIC_VCCSDIOCNT 0x0d5 -#define INTEL_MSIC_VPROG1CNT 0x0d6 -#define INTEL_MSIC_VPROG2CNT 0x0d7 -#define INTEL_MSIC_VEMMCSCNT 0x0d8 -#define INTEL_MSIC_VEMMC1CNT 0x0d9 -#define INTEL_MSIC_VEMMC2CNT 0x0da -#define INTEL_MSIC_VAUDACNT 0x0db -#define INTEL_MSIC_VHSPCNT 0x0dc -#define INTEL_MSIC_VHSNCNT 0x0dd -#define INTEL_MSIC_VHDMICNT 0x0de -#define INTEL_MSIC_VOTGCNT 0x0df -#define INTEL_MSIC_V1P35CNT 0x0e0 -#define INTEL_MSIC_V330AONCNT 0x0e1 - -/* RESET */ -#define INTEL_MSIC_CHIPCNTRL 0x100 /* WO */ -#define INTEL_MSIC_ERCONFIG 0x101 - -/* BURST */ -#define INTEL_MSIC_BATCURRENTLIMIT12 0x102 -#define INTEL_MSIC_BATTIMELIMIT12 0x103 -#define INTEL_MSIC_BATTIMELIMIT3 0x104 -#define INTEL_MSIC_BATTIMEDB 0x105 -#define INTEL_MSIC_BRSTCONFIGOUTPUTS 0x106 -#define INTEL_MSIC_BRSTCONFIGACTIONS 0x107 -#define INTEL_MSIC_BURSTCONTROLSTATUS 0x108 - -/* RTC */ -#define INTEL_MSIC_RTCB1 0x140 /* RO */ -#define INTEL_MSIC_RTCB2 0x141 /* RO */ -#define INTEL_MSIC_RTCB3 0x142 /* RO */ -#define INTEL_MSIC_RTCB4 0x143 /* RO */ -#define INTEL_MSIC_RTCOB1 0x144 -#define INTEL_MSIC_RTCOB2 0x145 -#define INTEL_MSIC_RTCOB3 0x146 -#define INTEL_MSIC_RTCOB4 0x147 -#define INTEL_MSIC_RTCAB1 0x148 -#define INTEL_MSIC_RTCAB2 0x149 -#define INTEL_MSIC_RTCAB3 0x14a -#define INTEL_MSIC_RTCAB4 0x14b -#define INTEL_MSIC_RTCWAB1 0x14c -#define INTEL_MSIC_RTCWAB2 0x14d -#define INTEL_MSIC_RTCWAB3 0x14e -#define INTEL_MSIC_RTCWAB4 0x14f -#define INTEL_MSIC_RTCSC1 0x150 -#define INTEL_MSIC_RTCSC2 0x151 -#define INTEL_MSIC_RTCSC3 0x152 -#define INTEL_MSIC_RTCSC4 0x153 -#define INTEL_MSIC_RTCSTATUS 0x154 /* RO */ -#define INTEL_MSIC_RTCCONFIG1 0x155 -#define INTEL_MSIC_RTCCONFIG2 0x156 - -/* CHARGER */ -#define INTEL_MSIC_BDTIMER 0x180 -#define INTEL_MSIC_BATTRMV 0x181 -#define INTEL_MSIC_VBUSDET 0x182 -#define INTEL_MSIC_VBUSDET1 0x183 -#define INTEL_MSIC_ADPHVDET 0x184 -#define INTEL_MSIC_ADPLVDET 0x185 -#define INTEL_MSIC_ADPDETDBDM 0x186 -#define INTEL_MSIC_LOWBATTDET 0x187 -#define INTEL_MSIC_CHRCTRL 0x188 -#define INTEL_MSIC_CHRCVOLTAGE 0x189 -#define INTEL_MSIC_CHRCCURRENT 0x18a -#define INTEL_MSIC_SPCHARGER 0x18b -#define INTEL_MSIC_CHRTTIME 0x18c -#define INTEL_MSIC_CHRCTRL1 0x18d -#define INTEL_MSIC_PWRSRCLMT 0x18e -#define INTEL_MSIC_CHRSTWDT 0x18f -#define INTEL_MSIC_WDTWRITE 0x190 /* WO */ -#define INTEL_MSIC_CHRSAFELMT 0x191 -#define INTEL_MSIC_SPWRSRCINT 0x192 /* RO */ -#define INTEL_MSIC_SPWRSRCINT1 0x193 /* RO */ -#define INTEL_MSIC_CHRLEDPWM 0x194 -#define INTEL_MSIC_CHRLEDCTRL 0x195 - -/* ADC */ -#define INTEL_MSIC_ADC1CNTL1 0x1c0 -#define INTEL_MSIC_ADC1CNTL2 0x1c1 -#define INTEL_MSIC_ADC1CNTL3 0x1c2 -#define INTEL_MSIC_ADC1OFFSETH 0x1c3 /* RO */ -#define INTEL_MSIC_ADC1OFFSETL 0x1c4 /* RO */ -#define INTEL_MSIC_ADC1ADDR0 0x1c5 -#define INTEL_MSIC_ADC1ADDR1 0x1c6 -#define INTEL_MSIC_ADC1ADDR2 0x1c7 -#define INTEL_MSIC_ADC1ADDR3 0x1c8 -#define INTEL_MSIC_ADC1ADDR4 0x1c9 -#define INTEL_MSIC_ADC1ADDR5 0x1ca -#define INTEL_MSIC_ADC1ADDR6 0x1cb -#define INTEL_MSIC_ADC1ADDR7 0x1cc -#define INTEL_MSIC_ADC1ADDR8 0x1cd -#define INTEL_MSIC_ADC1ADDR9 0x1ce -#define INTEL_MSIC_ADC1ADDR10 0x1cf -#define INTEL_MSIC_ADC1ADDR11 0x1d0 -#define INTEL_MSIC_ADC1ADDR12 0x1d1 -#define INTEL_MSIC_ADC1ADDR13 0x1d2 -#define INTEL_MSIC_ADC1ADDR14 0x1d3 -#define INTEL_MSIC_ADC1SNS0H 0x1d4 /* RO */ -#define INTEL_MSIC_ADC1SNS0L 0x1d5 /* RO */ -#define INTEL_MSIC_ADC1SNS1H 0x1d6 /* RO */ -#define INTEL_MSIC_ADC1SNS1L 0x1d7 /* RO */ -#define INTEL_MSIC_ADC1SNS2H 0x1d8 /* RO */ -#define INTEL_MSIC_ADC1SNS2L 0x1d9 /* RO */ -#define INTEL_MSIC_ADC1SNS3H 0x1da /* RO */ -#define INTEL_MSIC_ADC1SNS3L 0x1db /* RO */ -#define INTEL_MSIC_ADC1SNS4H 0x1dc /* RO */ -#define INTEL_MSIC_ADC1SNS4L 0x1dd /* RO */ -#define INTEL_MSIC_ADC1SNS5H 0x1de /* RO */ -#define INTEL_MSIC_ADC1SNS5L 0x1df /* RO */ -#define INTEL_MSIC_ADC1SNS6H 0x1e0 /* RO */ -#define INTEL_MSIC_ADC1SNS6L 0x1e1 /* RO */ -#define INTEL_MSIC_ADC1SNS7H 0x1e2 /* RO */ -#define INTEL_MSIC_ADC1SNS7L 0x1e3 /* RO */ -#define INTEL_MSIC_ADC1SNS8H 0x1e4 /* RO */ -#define INTEL_MSIC_ADC1SNS8L 0x1e5 /* RO */ -#define INTEL_MSIC_ADC1SNS9H 0x1e6 /* RO */ -#define INTEL_MSIC_ADC1SNS9L 0x1e7 /* RO */ -#define INTEL_MSIC_ADC1SNS10H 0x1e8 /* RO */ -#define INTEL_MSIC_ADC1SNS10L 0x1e9 /* RO */ -#define INTEL_MSIC_ADC1SNS11H 0x1ea /* RO */ -#define INTEL_MSIC_ADC1SNS11L 0x1eb /* RO */ -#define INTEL_MSIC_ADC1SNS12H 0x1ec /* RO */ -#define INTEL_MSIC_ADC1SNS12L 0x1ed /* RO */ -#define INTEL_MSIC_ADC1SNS13H 0x1ee /* RO */ -#define INTEL_MSIC_ADC1SNS13L 0x1ef /* RO */ -#define INTEL_MSIC_ADC1SNS14H 0x1f0 /* RO */ -#define INTEL_MSIC_ADC1SNS14L 0x1f1 /* RO */ -#define INTEL_MSIC_ADC1BV0H 0x1f2 /* RO */ -#define INTEL_MSIC_ADC1BV0L 0x1f3 /* RO */ -#define INTEL_MSIC_ADC1BV1H 0x1f4 /* RO */ -#define INTEL_MSIC_ADC1BV1L 0x1f5 /* RO */ -#define INTEL_MSIC_ADC1BV2H 0x1f6 /* RO */ -#define INTEL_MSIC_ADC1BV2L 0x1f7 /* RO */ -#define INTEL_MSIC_ADC1BV3H 0x1f8 /* RO */ -#define INTEL_MSIC_ADC1BV3L 0x1f9 /* RO */ -#define INTEL_MSIC_ADC1BI0H 0x1fa /* RO */ -#define INTEL_MSIC_ADC1BI0L 0x1fb /* RO */ -#define INTEL_MSIC_ADC1BI1H 0x1fc /* RO */ -#define INTEL_MSIC_ADC1BI1L 0x1fd /* RO */ -#define INTEL_MSIC_ADC1BI2H 0x1fe /* RO */ -#define INTEL_MSIC_ADC1BI2L 0x1ff /* RO */ -#define INTEL_MSIC_ADC1BI3H 0x200 /* RO */ -#define INTEL_MSIC_ADC1BI3L 0x201 /* RO */ -#define INTEL_MSIC_CCCNTL 0x202 -#define INTEL_MSIC_CCOFFSETH 0x203 /* RO */ -#define INTEL_MSIC_CCOFFSETL 0x204 /* RO */ -#define INTEL_MSIC_CCADCHA 0x205 /* RO */ -#define INTEL_MSIC_CCADCLA 0x206 /* RO */ - -/* AUDIO */ -#define INTEL_MSIC_AUDPLLCTRL 0x240 -#define INTEL_MSIC_DMICBUF0123 0x241 -#define INTEL_MSIC_DMICBUF45 0x242 -#define INTEL_MSIC_DMICGPO 0x244 -#define INTEL_MSIC_DMICMUX 0x245 -#define INTEL_MSIC_DMICCLK 0x246 -#define INTEL_MSIC_MICBIAS 0x247 -#define INTEL_MSIC_ADCCONFIG 0x248 -#define INTEL_MSIC_MICAMP1 0x249 -#define INTEL_MSIC_MICAMP2 0x24a -#define INTEL_MSIC_NOISEMUX 0x24b -#define INTEL_MSIC_AUDIOMUX12 0x24c -#define INTEL_MSIC_AUDIOMUX34 0x24d -#define INTEL_MSIC_AUDIOSINC 0x24e -#define INTEL_MSIC_AUDIOTXEN 0x24f -#define INTEL_MSIC_HSEPRXCTRL 0x250 -#define INTEL_MSIC_IHFRXCTRL 0x251 -#define INTEL_MSIC_VOICETXVOL 0x252 -#define INTEL_MSIC_SIDETONEVOL 0x253 -#define INTEL_MSIC_MUSICSHARVOL 0x254 -#define INTEL_MSIC_VOICETXCTRL 0x255 -#define INTEL_MSIC_HSMIXER 0x256 -#define INTEL_MSIC_DACCONFIG 0x257 -#define INTEL_MSIC_SOFTMUTE 0x258 -#define INTEL_MSIC_HSLVOLCTRL 0x259 -#define INTEL_MSIC_HSRVOLCTRL 0x25a -#define INTEL_MSIC_IHFLVOLCTRL 0x25b -#define INTEL_MSIC_IHFRVOLCTRL 0x25c -#define INTEL_MSIC_DRIVEREN 0x25d -#define INTEL_MSIC_LINEOUTCTRL 0x25e -#define INTEL_MSIC_VIB1CTRL1 0x25f -#define INTEL_MSIC_VIB1CTRL2 0x260 -#define INTEL_MSIC_VIB1CTRL3 0x261 -#define INTEL_MSIC_VIB1SPIPCM_1 0x262 -#define INTEL_MSIC_VIB1SPIPCM_2 0x263 -#define INTEL_MSIC_VIB1CTRL5 0x264 -#define INTEL_MSIC_VIB2CTRL1 0x265 -#define INTEL_MSIC_VIB2CTRL2 0x266 -#define INTEL_MSIC_VIB2CTRL3 0x267 -#define INTEL_MSIC_VIB2SPIPCM_1 0x268 -#define INTEL_MSIC_VIB2SPIPCM_2 0x269 -#define INTEL_MSIC_VIB2CTRL5 0x26a -#define INTEL_MSIC_BTNCTRL1 0x26b -#define INTEL_MSIC_BTNCTRL2 0x26c -#define INTEL_MSIC_PCM1TXSLOT01 0x26d -#define INTEL_MSIC_PCM1TXSLOT23 0x26e -#define INTEL_MSIC_PCM1TXSLOT45 0x26f -#define INTEL_MSIC_PCM1RXSLOT0123 0x270 -#define INTEL_MSIC_PCM1RXSLOT045 0x271 -#define INTEL_MSIC_PCM2TXSLOT01 0x272 -#define INTEL_MSIC_PCM2TXSLOT23 0x273 -#define INTEL_MSIC_PCM2TXSLOT45 0x274 -#define INTEL_MSIC_PCM2RXSLOT01 0x275 -#define INTEL_MSIC_PCM2RXSLOT23 0x276 -#define INTEL_MSIC_PCM2RXSLOT45 0x277 -#define INTEL_MSIC_PCM1CTRL1 0x278 -#define INTEL_MSIC_PCM1CTRL2 0x279 -#define INTEL_MSIC_PCM1CTRL3 0x27a -#define INTEL_MSIC_PCM2CTRL1 0x27b -#define INTEL_MSIC_PCM2CTRL2 0x27c - -/* HDMI */ -#define INTEL_MSIC_HDMIPUEN 0x280 -#define INTEL_MSIC_HDMISTATUS 0x281 /* RO */ - -/* Physical address of the start of the MSIC interrupt tree in SRAM */ -#define INTEL_MSIC_IRQ_PHYS_BASE 0xffff7fc0 - -/** - * struct intel_msic_gpio_pdata - platform data for the MSIC GPIO driver - * @gpio_base: base number for the GPIOs - */ -struct intel_msic_gpio_pdata { - unsigned gpio_base; -}; - -/** - * struct intel_msic_ocd_pdata - platform data for the MSIC OCD driver - * @gpio: GPIO number used for OCD interrupts - * - * The MSIC MFD driver converts @gpio into an IRQ number and passes it to - * the OCD driver as %IORESOURCE_IRQ. - */ -struct intel_msic_ocd_pdata { - unsigned gpio; -}; - -/* MSIC embedded blocks (subdevices) */ -enum intel_msic_block { - INTEL_MSIC_BLOCK_TOUCH, - INTEL_MSIC_BLOCK_ADC, - INTEL_MSIC_BLOCK_BATTERY, - INTEL_MSIC_BLOCK_GPIO, - INTEL_MSIC_BLOCK_AUDIO, - INTEL_MSIC_BLOCK_HDMI, - INTEL_MSIC_BLOCK_THERMAL, - INTEL_MSIC_BLOCK_POWER_BTN, - INTEL_MSIC_BLOCK_OCD, - - INTEL_MSIC_BLOCK_LAST, -}; - -/** - * struct intel_msic_platform_data - platform data for the MSIC driver - * @irq: array of interrupt numbers, one per device. If @irq is set to %0 - * for a given block, the corresponding platform device is not - * created. For devices which don't have an interrupt, use %0xff - * (this is same as in SFI spec). - * @gpio: platform data for the MSIC GPIO driver - * @ocd: platform data for the MSIC OCD driver - * - * Once the MSIC driver is initialized, the register interface is ready to - * use. All the platform devices for subdevices are created after the - * register interface is ready so that we can guarantee its availability to - * the subdevice drivers. - * - * Interrupt numbers are passed to the subdevices via %IORESOURCE_IRQ - * resources of the created platform device. - */ -struct intel_msic_platform_data { - int irq[INTEL_MSIC_BLOCK_LAST]; - struct intel_msic_gpio_pdata *gpio; - struct intel_msic_ocd_pdata *ocd; -}; - -struct intel_msic; - -extern int intel_msic_reg_read(unsigned short reg, u8 *val); -extern int intel_msic_reg_write(unsigned short reg, u8 val); -extern int intel_msic_reg_update(unsigned short reg, u8 val, u8 mask); -extern int intel_msic_bulk_read(unsigned short *reg, u8 *buf, size_t count); -extern int intel_msic_bulk_write(unsigned short *reg, u8 *buf, size_t count); - -/* - * pdev_to_intel_msic - gets an MSIC instance from the platform device - * @pdev: platform device pointer - * - * The client drivers need to have pointer to the MSIC instance if they - * want to call intel_msic_irq_read(). This macro can be used for - * convenience to get the MSIC pointer from @pdev where needed. This is - * _only_ valid for devices which are managed by the MSIC. - */ -#define pdev_to_intel_msic(pdev) (dev_get_drvdata(pdev->dev.parent)) - -extern int intel_msic_irq_read(struct intel_msic *msic, unsigned short reg, - u8 *val); - -#endif /* __LINUX_MFD_INTEL_MSIC_H__ */ -- cgit v1.2.3 From c10983e14e8f5d7c8dab0415e0cb7fe8d10aa9e3 Mon Sep 17 00:00:00 2001 From: Luben Tuikov Date: Wed, 20 Jan 2021 15:09:59 -0500 Subject: drm/scheduler: Job timeout handler returns status (v3) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch does not change current behaviour. The driver's job timeout handler now returns status indicating back to the DRM layer whether the device (GPU) is no longer available, such as after it's been unplugged, or whether all is normal, i.e. current behaviour. All drivers which make use of the drm_sched_backend_ops' .timedout_job() callback have been accordingly renamed and return the would've-been default value of DRM_GPU_SCHED_STAT_NOMINAL to restart the task's timeout timer--this is the old behaviour, and is preserved by this patch. v2: Use enum as the status of a driver's job timeout callback method. v3: Return scheduler/device information, rather than task information. Cc: Alexander Deucher Cc: Andrey Grodzovsky Cc: Christian König Cc: Daniel Vetter Cc: Lucas Stach Cc: Russell King Cc: Christian Gmeiner Cc: Qiang Yu Cc: Rob Herring Cc: Tomeu Vizoso Cc: Steven Price Cc: Alyssa Rosenzweig Cc: Eric Anholt Reported-by: kernel test robot Signed-off-by: Luben Tuikov Acked-by: Alyssa Rosenzweig Acked-by: Christian König Acked-by: Steven Price Signed-off-by: Christian König Link: https://patchwork.freedesktop.org/patch/415095/ (cherry picked from commit a6a1f036c74e3d2a3a56b3140492c7c3ecb879f3) Signed-off-by: Maarten Lankhorst --- drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 6 ++++-- drivers/gpu/drm/etnaviv/etnaviv_sched.c | 7 ++++++- drivers/gpu/drm/lima/lima_sched.c | 4 +++- drivers/gpu/drm/panfrost/panfrost_job.c | 9 ++++++--- drivers/gpu/drm/scheduler/sched_main.c | 4 +--- drivers/gpu/drm/v3d/v3d_sched.c | 32 +++++++++++++++++--------------- include/drm/gpu_scheduler.h | 18 +++++++++++++++--- 7 files changed, 52 insertions(+), 28 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index ff48101bab55..759b34799221 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -28,7 +28,7 @@ #include "amdgpu.h" #include "amdgpu_trace.h" -static void amdgpu_job_timedout(struct drm_sched_job *s_job) +static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job) { struct amdgpu_ring *ring = to_amdgpu_ring(s_job->sched); struct amdgpu_job *job = to_amdgpu_job(s_job); @@ -41,7 +41,7 @@ static void amdgpu_job_timedout(struct drm_sched_job *s_job) amdgpu_ring_soft_recovery(ring, job->vmid, s_job->s_fence->parent)) { DRM_ERROR("ring %s timeout, but soft recovered\n", s_job->sched->name); - return; + return DRM_GPU_SCHED_STAT_NOMINAL; } amdgpu_vm_get_task_info(ring->adev, job->pasid, &ti); @@ -53,10 +53,12 @@ static void amdgpu_job_timedout(struct drm_sched_job *s_job) if (amdgpu_device_should_recover_gpu(ring->adev)) { amdgpu_device_gpu_recover(ring->adev, job); + return DRM_GPU_SCHED_STAT_NOMINAL; } else { drm_sched_suspend_timeout(&ring->sched); if (amdgpu_sriov_vf(adev)) adev->virt.tdr_debug = true; + return DRM_GPU_SCHED_STAT_NOMINAL; } } diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c index cd46c882269c..2a9439cbb0fb 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c @@ -82,7 +82,8 @@ static struct dma_fence *etnaviv_sched_run_job(struct drm_sched_job *sched_job) return fence; } -static void etnaviv_sched_timedout_job(struct drm_sched_job *sched_job) +static enum drm_gpu_sched_stat etnaviv_sched_timedout_job(struct drm_sched_job + *sched_job) { struct etnaviv_gem_submit *submit = to_etnaviv_submit(sched_job); struct etnaviv_gpu *gpu = submit->gpu; @@ -120,9 +121,13 @@ static void etnaviv_sched_timedout_job(struct drm_sched_job *sched_job) drm_sched_resubmit_jobs(&gpu->sched); + drm_sched_start(&gpu->sched, true); + return DRM_GPU_SCHED_STAT_NOMINAL; + out_no_timeout: /* restart scheduler after GPU is usable again */ drm_sched_start(&gpu->sched, true); + return DRM_GPU_SCHED_STAT_NOMINAL; } static void etnaviv_sched_free_job(struct drm_sched_job *sched_job) diff --git a/drivers/gpu/drm/lima/lima_sched.c b/drivers/gpu/drm/lima/lima_sched.c index 63b4c5643f9c..6e4273852712 100644 --- a/drivers/gpu/drm/lima/lima_sched.c +++ b/drivers/gpu/drm/lima/lima_sched.c @@ -415,7 +415,7 @@ out: mutex_unlock(&dev->error_task_list_lock); } -static void lima_sched_timedout_job(struct drm_sched_job *job) +static enum drm_gpu_sched_stat lima_sched_timedout_job(struct drm_sched_job *job) { struct lima_sched_pipe *pipe = to_lima_pipe(job->sched); struct lima_sched_task *task = to_lima_task(job); @@ -449,6 +449,8 @@ static void lima_sched_timedout_job(struct drm_sched_job *job) drm_sched_resubmit_jobs(&pipe->base); drm_sched_start(&pipe->base, true); + + return DRM_GPU_SCHED_STAT_NOMINAL; } static void lima_sched_free_job(struct drm_sched_job *job) diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c index 04e6f6f9b742..0a83eefa49c4 100644 --- a/drivers/gpu/drm/panfrost/panfrost_job.c +++ b/drivers/gpu/drm/panfrost/panfrost_job.c @@ -432,7 +432,8 @@ static void panfrost_scheduler_start(struct panfrost_queue_state *queue) mutex_unlock(&queue->lock); } -static void panfrost_job_timedout(struct drm_sched_job *sched_job) +static enum drm_gpu_sched_stat panfrost_job_timedout(struct drm_sched_job + *sched_job) { struct panfrost_job *job = to_panfrost_job(sched_job); struct panfrost_device *pfdev = job->pfdev; @@ -443,7 +444,7 @@ static void panfrost_job_timedout(struct drm_sched_job *sched_job) * spurious. Bail out. */ if (dma_fence_is_signaled(job->done_fence)) - return; + return DRM_GPU_SCHED_STAT_NOMINAL; dev_err(pfdev->dev, "gpu sched timeout, js=%d, config=0x%x, status=0x%x, head=0x%x, tail=0x%x, sched_job=%p", js, @@ -455,11 +456,13 @@ static void panfrost_job_timedout(struct drm_sched_job *sched_job) /* Scheduler is already stopped, nothing to do. */ if (!panfrost_scheduler_stop(&pfdev->js->queue[js], sched_job)) - return; + return DRM_GPU_SCHED_STAT_NOMINAL; /* Schedule a reset if there's no reset in progress. */ if (!atomic_xchg(&pfdev->reset.pending, 1)) schedule_work(&pfdev->reset.work); + + return DRM_GPU_SCHED_STAT_NOMINAL; } static const struct drm_sched_backend_ops panfrost_sched_ops = { diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index 92637b70c9bf..73fccc54268b 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -527,7 +527,7 @@ void drm_sched_start(struct drm_gpu_scheduler *sched, bool full_recovery) EXPORT_SYMBOL(drm_sched_start); /** - * drm_sched_resubmit_jobs - helper to relunch job from pending ring list + * drm_sched_resubmit_jobs - helper to relaunch jobs from the pending list * * @sched: scheduler instance * @@ -561,8 +561,6 @@ void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched) } else { s_job->s_fence->parent = fence; } - - } } EXPORT_SYMBOL(drm_sched_resubmit_jobs); diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c index 452682e2209f..ef2338a294ca 100644 --- a/drivers/gpu/drm/v3d/v3d_sched.c +++ b/drivers/gpu/drm/v3d/v3d_sched.c @@ -259,7 +259,7 @@ v3d_cache_clean_job_run(struct drm_sched_job *sched_job) return NULL; } -static void +static enum drm_gpu_sched_status v3d_gpu_reset_for_timeout(struct v3d_dev *v3d, struct drm_sched_job *sched_job) { enum v3d_queue q; @@ -285,6 +285,8 @@ v3d_gpu_reset_for_timeout(struct v3d_dev *v3d, struct drm_sched_job *sched_job) } mutex_unlock(&v3d->reset_lock); + + return DRM_GPU_SCHED_STAT_NOMINAL; } /* If the current address or return address have changed, then the GPU @@ -292,7 +294,7 @@ v3d_gpu_reset_for_timeout(struct v3d_dev *v3d, struct drm_sched_job *sched_job) * could fail if the GPU got in an infinite loop in the CL, but that * is pretty unlikely outside of an i-g-t testcase. */ -static void +static enum drm_task_status v3d_cl_job_timedout(struct drm_sched_job *sched_job, enum v3d_queue q, u32 *timedout_ctca, u32 *timedout_ctra) { @@ -304,39 +306,39 @@ v3d_cl_job_timedout(struct drm_sched_job *sched_job, enum v3d_queue q, if (*timedout_ctca != ctca || *timedout_ctra != ctra) { *timedout_ctca = ctca; *timedout_ctra = ctra; - return; + return DRM_GPU_SCHED_STAT_NOMINAL; } - v3d_gpu_reset_for_timeout(v3d, sched_job); + return v3d_gpu_reset_for_timeout(v3d, sched_job); } -static void +static enum drm_task_status v3d_bin_job_timedout(struct drm_sched_job *sched_job) { struct v3d_bin_job *job = to_bin_job(sched_job); - v3d_cl_job_timedout(sched_job, V3D_BIN, - &job->timedout_ctca, &job->timedout_ctra); + return v3d_cl_job_timedout(sched_job, V3D_BIN, + &job->timedout_ctca, &job->timedout_ctra); } -static void +static enum drm_task_status v3d_render_job_timedout(struct drm_sched_job *sched_job) { struct v3d_render_job *job = to_render_job(sched_job); - v3d_cl_job_timedout(sched_job, V3D_RENDER, - &job->timedout_ctca, &job->timedout_ctra); + return v3d_cl_job_timedout(sched_job, V3D_RENDER, + &job->timedout_ctca, &job->timedout_ctra); } -static void +static enum drm_task_status v3d_generic_job_timedout(struct drm_sched_job *sched_job) { struct v3d_job *job = to_v3d_job(sched_job); - v3d_gpu_reset_for_timeout(job->v3d, sched_job); + return v3d_gpu_reset_for_timeout(job->v3d, sched_job); } -static void +static enum drm_task_status v3d_csd_job_timedout(struct drm_sched_job *sched_job) { struct v3d_csd_job *job = to_csd_job(sched_job); @@ -348,10 +350,10 @@ v3d_csd_job_timedout(struct drm_sched_job *sched_job) */ if (job->timedout_batches != batches) { job->timedout_batches = batches; - return; + return DRM_GPU_SCHED_STAT_NOMINAL; } - v3d_gpu_reset_for_timeout(v3d, sched_job); + return v3d_gpu_reset_for_timeout(v3d, sched_job); } static const struct drm_sched_backend_ops v3d_bin_sched_ops = { diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index 975e8a67947f..ce6a383ed99f 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -206,6 +206,12 @@ static inline bool drm_sched_invalidate_job(struct drm_sched_job *s_job, return s_job && atomic_inc_return(&s_job->karma) > threshold; } +enum drm_gpu_sched_stat { + DRM_GPU_SCHED_STAT_NONE, /* Reserve 0 */ + DRM_GPU_SCHED_STAT_NOMINAL, + DRM_GPU_SCHED_STAT_ENODEV, +}; + /** * struct drm_sched_backend_ops * @@ -230,10 +236,16 @@ struct drm_sched_backend_ops { struct dma_fence *(*run_job)(struct drm_sched_job *sched_job); /** - * @timedout_job: Called when a job has taken too long to execute, - * to trigger GPU recovery. + * @timedout_job: Called when a job has taken too long to execute, + * to trigger GPU recovery. + * + * Return DRM_GPU_SCHED_STAT_NOMINAL, when all is normal, + * and the underlying driver has started or completed recovery. + * + * Return DRM_GPU_SCHED_STAT_ENODEV, if the device is no longer + * available, i.e. has been unplugged. */ - void (*timedout_job)(struct drm_sched_job *sched_job); + enum drm_gpu_sched_stat (*timedout_job)(struct drm_sched_job *sched_job); /** * @free_job: Called once the job's finished fence has been signaled -- cgit v1.2.3 From 81d88ce55092edf1a1f928efb373f289c6b90efd Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 24 Nov 2020 16:38:40 +0100 Subject: dma-mapping: remove the {alloc,free}_noncoherent methods It turns out allowing non-contigous allocations here was a rather bad idea, as we'll now need to define ways to get the pages for mmaping or dma_buf sharing. Revert this change and stick to the original concept. A different API for the use case of non-contigous allocations will be added back later. Signed-off-by: Christoph Hellwig Reviewed-by: Tomasz Figa Tested-by: Ricardo Ribalda :wq --- Documentation/core-api/dma-api.rst | 64 +++++++++++++------------------------- drivers/iommu/dma-iommu.c | 30 ------------------ include/linux/dma-map-ops.h | 5 --- include/linux/dma-mapping.h | 17 +++++++--- kernel/dma/mapping.c | 40 ------------------------ 5 files changed, 35 insertions(+), 121 deletions(-) (limited to 'include') diff --git a/Documentation/core-api/dma-api.rst b/Documentation/core-api/dma-api.rst index 75cb757bbff0..e6d23f117308 100644 --- a/Documentation/core-api/dma-api.rst +++ b/Documentation/core-api/dma-api.rst @@ -528,16 +528,14 @@ an I/O device, you should not be using this part of the API. :: - void * - dma_alloc_noncoherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, enum dma_data_direction dir, - gfp_t gfp) + struct page * + dma_alloc_pages(struct device *dev, size_t size, dma_addr_t *dma_handle, + enum dma_data_direction dir, gfp_t gfp) -This routine allocates a region of bytes of consistent memory. It -returns a pointer to the allocated region (in the processor's virtual address -space) or NULL if the allocation failed. The returned memory may or may not -be in the kernel direct mapping. Drivers must not call virt_to_page on -the returned memory region. +This routine allocates a region of bytes of non-coherent memory. It +returns a pointer to first struct page for the region, or NULL if the +allocation failed. The resulting struct page can be used for everything a +struct page is suitable for. It also returns a which may be cast to an unsigned integer the same width as the bus and given to the device as the DMA address base of @@ -558,51 +556,33 @@ reused. :: void - dma_free_noncoherent(struct device *dev, size_t size, void *cpu_addr, + dma_free_pages(struct device *dev, size_t size, struct page *page, dma_addr_t dma_handle, enum dma_data_direction dir) -Free a region of memory previously allocated using dma_alloc_noncoherent(). -dev, size and dma_handle and dir must all be the same as those passed into -dma_alloc_noncoherent(). cpu_addr must be the virtual address returned by -dma_alloc_noncoherent(). +Free a region of memory previously allocated using dma_alloc_pages(). +dev, size, dma_handle and dir must all be the same as those passed into +dma_alloc_pages(). page must be the pointer returned by dma_alloc_pages(). :: - struct page * - dma_alloc_pages(struct device *dev, size_t size, dma_addr_t *dma_handle, - enum dma_data_direction dir, gfp_t gfp) - -This routine allocates a region of bytes of non-coherent memory. It -returns a pointer to first struct page for the region, or NULL if the -allocation failed. The resulting struct page can be used for everything a -struct page is suitable for. - -It also returns a which may be cast to an unsigned integer the -same width as the bus and given to the device as the DMA address base of -the region. - -The dir parameter specified if data is read and/or written by the device, -see dma_map_single() for details. - -The gfp parameter allows the caller to specify the ``GFP_`` flags (see -kmalloc()) for the allocation, but rejects flags used to specify a memory -zone such as GFP_DMA or GFP_HIGHMEM. + void * + dma_alloc_noncoherent(struct device *dev, size_t size, + dma_addr_t *dma_handle, enum dma_data_direction dir, + gfp_t gfp) -Before giving the memory to the device, dma_sync_single_for_device() needs -to be called, and before reading memory written by the device, -dma_sync_single_for_cpu(), just like for streaming DMA mappings that are -reused. +This routine is a convenient wrapper around dma_alloc_pages that returns the +kernel virtual address for the allocated memory instead of the page structure. :: void - dma_free_pages(struct device *dev, size_t size, struct page *page, + dma_free_noncoherent(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_handle, enum dma_data_direction dir) -Free a region of memory previously allocated using dma_alloc_pages(). -dev, size and dma_handle and dir must all be the same as those passed into -dma_alloc_noncoherent(). page must be the pointer returned by -dma_alloc_pages(). +Free a region of memory previously allocated using dma_alloc_noncoherent(). +dev, size, dma_handle and dir must all be the same as those passed into +dma_alloc_noncoherent(). cpu_addr must be the virtual address returned by +dma_alloc_noncoherent(). :: diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 4078358ed66e..255533faf905 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -1197,34 +1197,6 @@ static void *iommu_dma_alloc(struct device *dev, size_t size, return cpu_addr; } -#ifdef CONFIG_DMA_REMAP -static void *iommu_dma_alloc_noncoherent(struct device *dev, size_t size, - dma_addr_t *handle, enum dma_data_direction dir, gfp_t gfp) -{ - if (!gfpflags_allow_blocking(gfp)) { - struct page *page; - - page = dma_common_alloc_pages(dev, size, handle, dir, gfp); - if (!page) - return NULL; - return page_address(page); - } - - return iommu_dma_alloc_remap(dev, size, handle, gfp | __GFP_ZERO, - PAGE_KERNEL, 0); -} - -static void iommu_dma_free_noncoherent(struct device *dev, size_t size, - void *cpu_addr, dma_addr_t handle, enum dma_data_direction dir) -{ - __iommu_dma_unmap(dev, handle, size); - __iommu_dma_free(dev, size, cpu_addr); -} -#else -#define iommu_dma_alloc_noncoherent NULL -#define iommu_dma_free_noncoherent NULL -#endif /* CONFIG_DMA_REMAP */ - static int iommu_dma_mmap(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs) @@ -1295,8 +1267,6 @@ static const struct dma_map_ops iommu_dma_ops = { .free = iommu_dma_free, .alloc_pages = dma_common_alloc_pages, .free_pages = dma_common_free_pages, - .alloc_noncoherent = iommu_dma_alloc_noncoherent, - .free_noncoherent = iommu_dma_free_noncoherent, .mmap = iommu_dma_mmap, .get_sgtable = iommu_dma_get_sgtable, .map_page = iommu_dma_map_page, diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h index 70fcd0f610ea..11e02537b9e0 100644 --- a/include/linux/dma-map-ops.h +++ b/include/linux/dma-map-ops.h @@ -22,11 +22,6 @@ struct dma_map_ops { gfp_t gfp); void (*free_pages)(struct device *dev, size_t size, struct page *vaddr, dma_addr_t dma_handle, enum dma_data_direction dir); - void *(*alloc_noncoherent)(struct device *dev, size_t size, - dma_addr_t *dma_handle, enum dma_data_direction dir, - gfp_t gfp); - void (*free_noncoherent)(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_handle, enum dma_data_direction dir); int (*mmap)(struct device *, struct vm_area_struct *, void *, dma_addr_t, size_t, unsigned long attrs); diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 2e49996a8f39..fbfa3f5abd94 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -263,10 +263,19 @@ struct page *dma_alloc_pages(struct device *dev, size_t size, dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp); void dma_free_pages(struct device *dev, size_t size, struct page *page, dma_addr_t dma_handle, enum dma_data_direction dir); -void *dma_alloc_noncoherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp); -void dma_free_noncoherent(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_handle, enum dma_data_direction dir); + +static inline void *dma_alloc_noncoherent(struct device *dev, size_t size, + dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp) +{ + struct page *page = dma_alloc_pages(dev, size, dma_handle, dir, gfp); + return page ? page_address(page) : NULL; +} + +static inline void dma_free_noncoherent(struct device *dev, size_t size, + void *vaddr, dma_addr_t dma_handle, enum dma_data_direction dir) +{ + dma_free_pages(dev, size, virt_to_page(vaddr), dma_handle, dir); +} static inline dma_addr_t dma_map_single_attrs(struct device *dev, void *ptr, size_t size, enum dma_data_direction dir, unsigned long attrs) diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index f87a89d08654..68992e35c8c3 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -515,46 +515,6 @@ void dma_free_pages(struct device *dev, size_t size, struct page *page, } EXPORT_SYMBOL_GPL(dma_free_pages); -void *dma_alloc_noncoherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp) -{ - const struct dma_map_ops *ops = get_dma_ops(dev); - void *vaddr; - - if (!ops || !ops->alloc_noncoherent) { - struct page *page; - - page = dma_alloc_pages(dev, size, dma_handle, dir, gfp); - if (!page) - return NULL; - return page_address(page); - } - - size = PAGE_ALIGN(size); - vaddr = ops->alloc_noncoherent(dev, size, dma_handle, dir, gfp); - if (vaddr) - debug_dma_map_page(dev, virt_to_page(vaddr), 0, size, dir, - *dma_handle); - return vaddr; -} -EXPORT_SYMBOL_GPL(dma_alloc_noncoherent); - -void dma_free_noncoherent(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_handle, enum dma_data_direction dir) -{ - const struct dma_map_ops *ops = get_dma_ops(dev); - - if (!ops || !ops->free_noncoherent) { - dma_free_pages(dev, size, virt_to_page(vaddr), dma_handle, dir); - return; - } - - size = PAGE_ALIGN(size); - debug_dma_unmap_page(dev, dma_handle, size, dir); - ops->free_noncoherent(dev, size, vaddr, dma_handle, dir); -} -EXPORT_SYMBOL_GPL(dma_free_noncoherent); - int dma_supported(struct device *dev, u64 mask) { const struct dma_map_ops *ops = get_dma_ops(dev); -- cgit v1.2.3 From 1746fd4416ed5510fe9fdd6a93e49a436187b680 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Mon, 8 Feb 2021 15:09:23 -0500 Subject: tracepoints: Remove unnecessary "data_args" macro parameter While working on a clean up that would restructure the difference between architectures that have static calls vs those that do not, I was stumbling over the "data_args" parameter that includes "__data" in the arguments. The issue was that one version didn't even need it, while the other one did. Instead of injecting a "__data = NULL;" into the macro for the unneeded version, just remove it completely. The original idea behind data_args is that there may be a case of a tracepoint with no arguments. But this is considered bad practice, and all tracepoints should pass something to that location (that's what tracepoints were created for). Link: https://lkml.kernel.org/r/20210208201050.768074128@goodmis.org Acked-by: Peter Zijlstra (Intel) Signed-off-by: Steven Rostedt (VMware) --- include/linux/tracepoint.h | 31 +++++++++++-------------------- 1 file changed, 11 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 966ed8980327..42bb5b753b33 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -160,13 +160,8 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) /* * it_func[0] is never NULL because there is at least one element in the array * when the array itself is non NULL. - * - * Note, the proto and args passed in includes "__data" as the first parameter. - * The reason for this is to handle the "void" prototype. If a tracepoint - * has a "void" prototype, then it is invalid to declare a function - * as "(void *, void)". */ -#define __DO_TRACE(name, proto, args, cond, rcuidle) \ +#define __DO_TRACE(name, args, cond, rcuidle) \ do { \ struct tracepoint_func *it_func_ptr; \ int __maybe_unused __idx = 0; \ @@ -194,7 +189,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) rcu_dereference_raw((&__tracepoint_##name)->funcs); \ if (it_func_ptr) { \ __data = (it_func_ptr)->data; \ - __DO_TRACE_CALL(name)(args); \ + __DO_TRACE_CALL(name)(__data, args); \ } \ \ if (rcuidle) { \ @@ -206,17 +201,16 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) } while (0) #ifndef MODULE -#define __DECLARE_TRACE_RCU(name, proto, args, cond, data_proto, data_args) \ +#define __DECLARE_TRACE_RCU(name, proto, args, cond) \ static inline void trace_##name##_rcuidle(proto) \ { \ if (static_key_false(&__tracepoint_##name.key)) \ __DO_TRACE(name, \ - TP_PROTO(data_proto), \ - TP_ARGS(data_args), \ + TP_ARGS(args), \ TP_CONDITION(cond), 1); \ } #else -#define __DECLARE_TRACE_RCU(name, proto, args, cond, data_proto, data_args) +#define __DECLARE_TRACE_RCU(name, proto, args, cond) #endif /* @@ -231,7 +225,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) * even when this tracepoint is off. This code has no purpose other than * poking RCU a bit. */ -#define __DECLARE_TRACE(name, proto, args, cond, data_proto, data_args) \ +#define __DECLARE_TRACE(name, proto, args, cond, data_proto) \ extern int __traceiter_##name(data_proto); \ DECLARE_STATIC_CALL(tp_func_##name, __traceiter_##name); \ extern struct tracepoint __tracepoint_##name; \ @@ -239,8 +233,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) { \ if (static_key_false(&__tracepoint_##name.key)) \ __DO_TRACE(name, \ - TP_PROTO(data_proto), \ - TP_ARGS(data_args), \ + TP_ARGS(args), \ TP_CONDITION(cond), 0); \ if (IS_ENABLED(CONFIG_LOCKDEP) && (cond)) { \ rcu_read_lock_sched_notrace(); \ @@ -249,7 +242,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) } \ } \ __DECLARE_TRACE_RCU(name, PARAMS(proto), PARAMS(args), \ - PARAMS(cond), PARAMS(data_proto), PARAMS(data_args)) \ + PARAMS(cond)) \ static inline int \ register_trace_##name(void (*probe)(data_proto), void *data) \ { \ @@ -332,7 +325,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) #else /* !TRACEPOINTS_ENABLED */ -#define __DECLARE_TRACE(name, proto, args, cond, data_proto, data_args) \ +#define __DECLARE_TRACE(name, proto, args, cond, data_proto) \ static inline void trace_##name(proto) \ { } \ static inline void trace_##name##_rcuidle(proto) \ @@ -412,14 +405,12 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) #define DECLARE_TRACE(name, proto, args) \ __DECLARE_TRACE(name, PARAMS(proto), PARAMS(args), \ cpu_online(raw_smp_processor_id()), \ - PARAMS(void *__data, proto), \ - PARAMS(__data, args)) + PARAMS(void *__data, proto)) #define DECLARE_TRACE_CONDITION(name, proto, args, cond) \ __DECLARE_TRACE(name, PARAMS(proto), PARAMS(args), \ cpu_online(raw_smp_processor_id()) && (PARAMS(cond)), \ - PARAMS(void *__data, proto), \ - PARAMS(__data, args)) + PARAMS(void *__data, proto)) #define TRACE_EVENT_FLAGS(event, flag) -- cgit v1.2.3 From d9a1be1be331fc857d3fe29f86c3a305950b35a9 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Mon, 8 Feb 2021 15:09:24 -0500 Subject: tracepoints: Do not punish non static call users With static calls, a tracepoint can call the callback directly if there is only one callback registered to that tracepoint. When there is more than one, the static call will call the tracepoint's "iterator" function, which needs to reload the tracepoint's "funcs" array again, as it could have changed since the first time it was loaded. But an arch without static calls is punished by having to load the tracepoint's "funcs" array twice. Once in the DO_TRACE macro, and once again in the iterator macro. For archs without static calls, there's no reason to load the array macro in the first place, since the iterator function will do it anyway. Change the __DO_TRACE_CALL() macro to do the load and call of the tracepoints funcs array only for architectures with static calls, and just call the iterator function directly for architectures without static calls. Link: https://lkml.kernel.org/r/20210208201050.909329787@goodmis.org Acked-by: Peter Zijlstra (Intel) Signed-off-by: Steven Rostedt (VMware) --- include/linux/tracepoint.h | 23 +++++++++++++---------- 1 file changed, 13 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 42bb5b753b33..2aad1c10821a 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -152,9 +152,19 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) #ifdef TRACEPOINTS_ENABLED #ifdef CONFIG_HAVE_STATIC_CALL -#define __DO_TRACE_CALL(name) static_call(tp_func_##name) +#define __DO_TRACE_CALL(name, args) \ + do { \ + struct tracepoint_func *it_func_ptr; \ + void *__data; \ + it_func_ptr = \ + rcu_dereference_raw((&__tracepoint_##name)->funcs); \ + if (it_func_ptr) { \ + __data = (it_func_ptr)->data; \ + static_call(tp_func_##name)(__data, args); \ + } \ + } while (0) #else -#define __DO_TRACE_CALL(name) __traceiter_##name +#define __DO_TRACE_CALL(name, args) __traceiter_##name(NULL, args) #endif /* CONFIG_HAVE_STATIC_CALL */ /* @@ -163,9 +173,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) */ #define __DO_TRACE(name, args, cond, rcuidle) \ do { \ - struct tracepoint_func *it_func_ptr; \ int __maybe_unused __idx = 0; \ - void *__data; \ \ if (!(cond)) \ return; \ @@ -185,12 +193,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) rcu_irq_enter_irqson(); \ } \ \ - it_func_ptr = \ - rcu_dereference_raw((&__tracepoint_##name)->funcs); \ - if (it_func_ptr) { \ - __data = (it_func_ptr)->data; \ - __DO_TRACE_CALL(name)(__data, args); \ - } \ + __DO_TRACE_CALL(name, TP_ARGS(args)); \ \ if (rcuidle) { \ rcu_irq_exit_irqson(); \ -- cgit v1.2.3 From 7211f0a25781ace5f79b272318b4c60b5dcfd413 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 4 Feb 2021 14:30:04 -0500 Subject: tracepoints: Code clean up Restructure the code a bit to make it simpler, fix some formatting problems and add READ_ONCE/WRITE_ONCE to make sure there's no compiler load/store tearing to the variables that can be accessed across CPUs. Started with Mathieu Desnoyers's patch: Link: https://lore.kernel.org/lkml/20210203175741.20665-1-mathieu.desnoyers@efficios.com/ And will keep his signature, but I will take the responsibility of this being correct, and keep the authorship. Link: https://lkml.kernel.org/r/20210204143004.61126582@gandalf.local.home Signed-off-by: Mathieu Desnoyers Signed-off-by: Steven Rostedt (VMware) --- include/linux/tracepoint.h | 2 +- kernel/tracepoint.c | 91 ++++++++++++++++++---------------------------- 2 files changed, 36 insertions(+), 57 deletions(-) (limited to 'include') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 2aad1c10821a..9cfb099da58f 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -305,7 +305,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) rcu_dereference_raw((&__tracepoint_##_name)->funcs); \ if (it_func_ptr) { \ do { \ - it_func = (it_func_ptr)->func; \ + it_func = READ_ONCE((it_func_ptr)->func); \ __data = (it_func_ptr)->data; \ ((void(*)(void *, proto))(it_func))(__data, args); \ } while ((++it_func_ptr)->func); \ diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index e8f20ae29c18..9f478d29b926 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -136,9 +136,9 @@ func_add(struct tracepoint_func **funcs, struct tracepoint_func *tp_func, int prio) { struct tracepoint_func *old, *new; - int nr_probes = 0; - int stub_funcs = 0; - int pos = -1; + int iter_probes; /* Iterate over old probe array. */ + int nr_probes = 0; /* Counter for probes */ + int pos = -1; /* Insertion position into new array */ if (WARN_ON(!tp_func->func)) return ERR_PTR(-EINVAL); @@ -147,54 +147,38 @@ func_add(struct tracepoint_func **funcs, struct tracepoint_func *tp_func, old = *funcs; if (old) { /* (N -> N+1), (N != 0, 1) probes */ - for (nr_probes = 0; old[nr_probes].func; nr_probes++) { - /* Insert before probes of lower priority */ - if (pos < 0 && old[nr_probes].prio < prio) - pos = nr_probes; - if (old[nr_probes].func == tp_func->func && - old[nr_probes].data == tp_func->data) + for (iter_probes = 0; old[iter_probes].func; iter_probes++) { + if (old[iter_probes].func == tp_stub_func) + continue; /* Skip stub functions. */ + if (old[iter_probes].func == tp_func->func && + old[iter_probes].data == tp_func->data) return ERR_PTR(-EEXIST); - if (old[nr_probes].func == tp_stub_func) - stub_funcs++; + nr_probes++; } } - /* + 2 : one for new probe, one for NULL func - stub functions */ - new = allocate_probes(nr_probes + 2 - stub_funcs); + /* + 2 : one for new probe, one for NULL func */ + new = allocate_probes(nr_probes + 2); if (new == NULL) return ERR_PTR(-ENOMEM); if (old) { - if (stub_funcs) { - /* Need to copy one at a time to remove stubs */ - int probes = 0; - - pos = -1; - for (nr_probes = 0; old[nr_probes].func; nr_probes++) { - if (old[nr_probes].func == tp_stub_func) - continue; - if (pos < 0 && old[nr_probes].prio < prio) - pos = probes++; - new[probes++] = old[nr_probes]; - } - nr_probes = probes; - if (pos < 0) - pos = probes; - else - nr_probes--; /* Account for insertion */ - - } else if (pos < 0) { - pos = nr_probes; - memcpy(new, old, nr_probes * sizeof(struct tracepoint_func)); - } else { - /* Copy higher priority probes ahead of the new probe */ - memcpy(new, old, pos * sizeof(struct tracepoint_func)); - /* Copy the rest after it. */ - memcpy(new + pos + 1, old + pos, - (nr_probes - pos) * sizeof(struct tracepoint_func)); + nr_probes = 0; + for (iter_probes = 0; old[iter_probes].func; iter_probes++) { + if (old[iter_probes].func == tp_stub_func) + continue; + /* Insert before probes of lower priority */ + if (pos < 0 && old[iter_probes].prio < prio) + pos = nr_probes++; + new[nr_probes++] = old[iter_probes]; } - } else + if (pos < 0) + pos = nr_probes++; + /* nr_probes now points to the end of the new array */ + } else { pos = 0; + nr_probes = 1; /* must point at end of array */ + } new[pos] = *tp_func; - new[nr_probes + 1].func = NULL; + new[nr_probes].func = NULL; *funcs = new; debug_print_probes(*funcs); return old; @@ -237,11 +221,12 @@ static void *func_remove(struct tracepoint_func **funcs, /* + 1 for NULL */ new = allocate_probes(nr_probes - nr_del + 1); if (new) { - for (i = 0; old[i].func; i++) - if ((old[i].func != tp_func->func - || old[i].data != tp_func->data) - && old[i].func != tp_stub_func) + for (i = 0; old[i].func; i++) { + if ((old[i].func != tp_func->func || + old[i].data != tp_func->data) && + old[i].func != tp_stub_func) new[j++] = old[i]; + } new[nr_probes - nr_del].func = NULL; *funcs = new; } else { @@ -249,17 +234,11 @@ static void *func_remove(struct tracepoint_func **funcs, * Failed to allocate, replace the old function * with calls to tp_stub_func. */ - for (i = 0; old[i].func; i++) + for (i = 0; old[i].func; i++) { if (old[i].func == tp_func->func && - old[i].data == tp_func->data) { - old[i].func = tp_stub_func; - /* Set the prio to the next event. */ - if (old[i + 1].func) - old[i].prio = - old[i + 1].prio; - else - old[i].prio = -1; - } + old[i].data == tp_func->data) + WRITE_ONCE(old[i].func, tp_stub_func); + } *funcs = old; } } -- cgit v1.2.3 From a1320e0c2fc834264fa2125ef5c40670dbb5b736 Mon Sep 17 00:00:00 2001 From: Jinyang He Date: Thu, 4 Feb 2021 11:34:31 +0800 Subject: ftrace: Remove unused ftrace_force_update() ftrace_force_update() is committed by Commit e1c08bdd9fa7 ("ftrace: force recording") and removed by Commit cb7be3b2fc2c ("ftrace: remove daemon"). Remove it in header file. Link: https://lkml.kernel.org/r/1612409671-8249-1-git-send-email-hejinyang@loongson.cn Signed-off-by: Jinyang He Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 9a8ce28e4485..86e5028bfa20 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -485,7 +485,6 @@ struct dyn_ftrace { struct dyn_arch_ftrace arch; }; -int ftrace_force_update(void); int ftrace_set_filter_ip(struct ftrace_ops *ops, unsigned long ip, int remove, int reset); int ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf, @@ -740,7 +739,6 @@ extern void ftrace_disable_daemon(void); extern void ftrace_enable_daemon(void); #else /* CONFIG_DYNAMIC_FTRACE */ static inline int skip_trace(unsigned long ip) { return 0; } -static inline int ftrace_force_update(void) { return 0; } static inline void ftrace_disable_daemon(void) { } static inline void ftrace_enable_daemon(void) { } static inline void ftrace_module_init(struct module *mod) { } -- cgit v1.2.3 From 8f1fc1c15329a9d53bde5636e85ca98ece2ec7bd Mon Sep 17 00:00:00 2001 From: Martin Hundebøll Date: Mon, 8 Feb 2021 16:01:57 +0100 Subject: PCI: Add Silicom Denmark vendor ID MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Update pci_ids.h with the vendor ID for Silicom Denmark. The define is going to be referenced in driver(s) for FPGA accelerated smart NICs. Link: https://lore.kernel.org/r/20210208150158.2877414-1-mhu@silicom.dk Signed-off-by: Martin Hundebøll Signed-off-by: Bjorn Helgaas Reviewed-by: Tom Rix Reviewed-by: Krzysztof Wilczyński --- include/linux/pci_ids.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index d8156a5dbee8..aae07d512ca6 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2588,6 +2588,8 @@ #define PCI_VENDOR_ID_REDHAT 0x1b36 +#define PCI_VENDOR_ID_SILICOM_DENMARK 0x1c2c + #define PCI_VENDOR_ID_AMAZON_ANNAPURNA_LABS 0x1c36 #define PCI_VENDOR_ID_CIRCUITCO 0x1cc8 -- cgit v1.2.3 From e2183fb135a7f62d317aa1c61eb3d1919080edba Mon Sep 17 00:00:00 2001 From: Maarten Lankhorst Date: Wed, 10 Feb 2021 14:24:39 +0100 Subject: Revert "drm/scheduler: Job timeout handler returns status (v3)" This reverts commit c10983e14e8f5d7c8dab0415e0cb7fe8d10aa9e3. This commit is not meant for drm-misc-next-fixes, and was accidentally cherry picked over. Signed-off-by: Maarten Lankhorst --- drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 6 ++---- drivers/gpu/drm/etnaviv/etnaviv_sched.c | 7 +------ drivers/gpu/drm/lima/lima_sched.c | 4 +--- drivers/gpu/drm/panfrost/panfrost_job.c | 9 +++------ drivers/gpu/drm/scheduler/sched_main.c | 4 +++- drivers/gpu/drm/v3d/v3d_sched.c | 32 +++++++++++++++----------------- include/drm/gpu_scheduler.h | 18 +++--------------- 7 files changed, 28 insertions(+), 52 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index 759b34799221..ff48101bab55 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -28,7 +28,7 @@ #include "amdgpu.h" #include "amdgpu_trace.h" -static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job) +static void amdgpu_job_timedout(struct drm_sched_job *s_job) { struct amdgpu_ring *ring = to_amdgpu_ring(s_job->sched); struct amdgpu_job *job = to_amdgpu_job(s_job); @@ -41,7 +41,7 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job) amdgpu_ring_soft_recovery(ring, job->vmid, s_job->s_fence->parent)) { DRM_ERROR("ring %s timeout, but soft recovered\n", s_job->sched->name); - return DRM_GPU_SCHED_STAT_NOMINAL; + return; } amdgpu_vm_get_task_info(ring->adev, job->pasid, &ti); @@ -53,12 +53,10 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job) if (amdgpu_device_should_recover_gpu(ring->adev)) { amdgpu_device_gpu_recover(ring->adev, job); - return DRM_GPU_SCHED_STAT_NOMINAL; } else { drm_sched_suspend_timeout(&ring->sched); if (amdgpu_sriov_vf(adev)) adev->virt.tdr_debug = true; - return DRM_GPU_SCHED_STAT_NOMINAL; } } diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c index 2a9439cbb0fb..cd46c882269c 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c @@ -82,8 +82,7 @@ static struct dma_fence *etnaviv_sched_run_job(struct drm_sched_job *sched_job) return fence; } -static enum drm_gpu_sched_stat etnaviv_sched_timedout_job(struct drm_sched_job - *sched_job) +static void etnaviv_sched_timedout_job(struct drm_sched_job *sched_job) { struct etnaviv_gem_submit *submit = to_etnaviv_submit(sched_job); struct etnaviv_gpu *gpu = submit->gpu; @@ -121,13 +120,9 @@ static enum drm_gpu_sched_stat etnaviv_sched_timedout_job(struct drm_sched_job drm_sched_resubmit_jobs(&gpu->sched); - drm_sched_start(&gpu->sched, true); - return DRM_GPU_SCHED_STAT_NOMINAL; - out_no_timeout: /* restart scheduler after GPU is usable again */ drm_sched_start(&gpu->sched, true); - return DRM_GPU_SCHED_STAT_NOMINAL; } static void etnaviv_sched_free_job(struct drm_sched_job *sched_job) diff --git a/drivers/gpu/drm/lima/lima_sched.c b/drivers/gpu/drm/lima/lima_sched.c index 20dafa62980f..5cc20b403a25 100644 --- a/drivers/gpu/drm/lima/lima_sched.c +++ b/drivers/gpu/drm/lima/lima_sched.c @@ -415,7 +415,7 @@ out: mutex_unlock(&dev->error_task_list_lock); } -static enum drm_gpu_sched_stat lima_sched_timedout_job(struct drm_sched_job *job) +static void lima_sched_timedout_job(struct drm_sched_job *job) { struct lima_sched_pipe *pipe = to_lima_pipe(job->sched); struct lima_sched_task *task = to_lima_task(job); @@ -449,8 +449,6 @@ static enum drm_gpu_sched_stat lima_sched_timedout_job(struct drm_sched_job *job drm_sched_resubmit_jobs(&pipe->base); drm_sched_start(&pipe->base, true); - - return DRM_GPU_SCHED_STAT_NOMINAL; } static void lima_sched_free_job(struct drm_sched_job *job) diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c index 0a83eefa49c4..04e6f6f9b742 100644 --- a/drivers/gpu/drm/panfrost/panfrost_job.c +++ b/drivers/gpu/drm/panfrost/panfrost_job.c @@ -432,8 +432,7 @@ static void panfrost_scheduler_start(struct panfrost_queue_state *queue) mutex_unlock(&queue->lock); } -static enum drm_gpu_sched_stat panfrost_job_timedout(struct drm_sched_job - *sched_job) +static void panfrost_job_timedout(struct drm_sched_job *sched_job) { struct panfrost_job *job = to_panfrost_job(sched_job); struct panfrost_device *pfdev = job->pfdev; @@ -444,7 +443,7 @@ static enum drm_gpu_sched_stat panfrost_job_timedout(struct drm_sched_job * spurious. Bail out. */ if (dma_fence_is_signaled(job->done_fence)) - return DRM_GPU_SCHED_STAT_NOMINAL; + return; dev_err(pfdev->dev, "gpu sched timeout, js=%d, config=0x%x, status=0x%x, head=0x%x, tail=0x%x, sched_job=%p", js, @@ -456,13 +455,11 @@ static enum drm_gpu_sched_stat panfrost_job_timedout(struct drm_sched_job /* Scheduler is already stopped, nothing to do. */ if (!panfrost_scheduler_stop(&pfdev->js->queue[js], sched_job)) - return DRM_GPU_SCHED_STAT_NOMINAL; + return; /* Schedule a reset if there's no reset in progress. */ if (!atomic_xchg(&pfdev->reset.pending, 1)) schedule_work(&pfdev->reset.work); - - return DRM_GPU_SCHED_STAT_NOMINAL; } static const struct drm_sched_backend_ops panfrost_sched_ops = { diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index 73fccc54268b..92637b70c9bf 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -527,7 +527,7 @@ void drm_sched_start(struct drm_gpu_scheduler *sched, bool full_recovery) EXPORT_SYMBOL(drm_sched_start); /** - * drm_sched_resubmit_jobs - helper to relaunch jobs from the pending list + * drm_sched_resubmit_jobs - helper to relunch job from pending ring list * * @sched: scheduler instance * @@ -561,6 +561,8 @@ void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched) } else { s_job->s_fence->parent = fence; } + + } } EXPORT_SYMBOL(drm_sched_resubmit_jobs); diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c index ef2338a294ca..452682e2209f 100644 --- a/drivers/gpu/drm/v3d/v3d_sched.c +++ b/drivers/gpu/drm/v3d/v3d_sched.c @@ -259,7 +259,7 @@ v3d_cache_clean_job_run(struct drm_sched_job *sched_job) return NULL; } -static enum drm_gpu_sched_status +static void v3d_gpu_reset_for_timeout(struct v3d_dev *v3d, struct drm_sched_job *sched_job) { enum v3d_queue q; @@ -285,8 +285,6 @@ v3d_gpu_reset_for_timeout(struct v3d_dev *v3d, struct drm_sched_job *sched_job) } mutex_unlock(&v3d->reset_lock); - - return DRM_GPU_SCHED_STAT_NOMINAL; } /* If the current address or return address have changed, then the GPU @@ -294,7 +292,7 @@ v3d_gpu_reset_for_timeout(struct v3d_dev *v3d, struct drm_sched_job *sched_job) * could fail if the GPU got in an infinite loop in the CL, but that * is pretty unlikely outside of an i-g-t testcase. */ -static enum drm_task_status +static void v3d_cl_job_timedout(struct drm_sched_job *sched_job, enum v3d_queue q, u32 *timedout_ctca, u32 *timedout_ctra) { @@ -306,39 +304,39 @@ v3d_cl_job_timedout(struct drm_sched_job *sched_job, enum v3d_queue q, if (*timedout_ctca != ctca || *timedout_ctra != ctra) { *timedout_ctca = ctca; *timedout_ctra = ctra; - return DRM_GPU_SCHED_STAT_NOMINAL; + return; } - return v3d_gpu_reset_for_timeout(v3d, sched_job); + v3d_gpu_reset_for_timeout(v3d, sched_job); } -static enum drm_task_status +static void v3d_bin_job_timedout(struct drm_sched_job *sched_job) { struct v3d_bin_job *job = to_bin_job(sched_job); - return v3d_cl_job_timedout(sched_job, V3D_BIN, - &job->timedout_ctca, &job->timedout_ctra); + v3d_cl_job_timedout(sched_job, V3D_BIN, + &job->timedout_ctca, &job->timedout_ctra); } -static enum drm_task_status +static void v3d_render_job_timedout(struct drm_sched_job *sched_job) { struct v3d_render_job *job = to_render_job(sched_job); - return v3d_cl_job_timedout(sched_job, V3D_RENDER, - &job->timedout_ctca, &job->timedout_ctra); + v3d_cl_job_timedout(sched_job, V3D_RENDER, + &job->timedout_ctca, &job->timedout_ctra); } -static enum drm_task_status +static void v3d_generic_job_timedout(struct drm_sched_job *sched_job) { struct v3d_job *job = to_v3d_job(sched_job); - return v3d_gpu_reset_for_timeout(job->v3d, sched_job); + v3d_gpu_reset_for_timeout(job->v3d, sched_job); } -static enum drm_task_status +static void v3d_csd_job_timedout(struct drm_sched_job *sched_job) { struct v3d_csd_job *job = to_csd_job(sched_job); @@ -350,10 +348,10 @@ v3d_csd_job_timedout(struct drm_sched_job *sched_job) */ if (job->timedout_batches != batches) { job->timedout_batches = batches; - return DRM_GPU_SCHED_STAT_NOMINAL; + return; } - return v3d_gpu_reset_for_timeout(v3d, sched_job); + v3d_gpu_reset_for_timeout(v3d, sched_job); } static const struct drm_sched_backend_ops v3d_bin_sched_ops = { diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index ce6a383ed99f..975e8a67947f 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -206,12 +206,6 @@ static inline bool drm_sched_invalidate_job(struct drm_sched_job *s_job, return s_job && atomic_inc_return(&s_job->karma) > threshold; } -enum drm_gpu_sched_stat { - DRM_GPU_SCHED_STAT_NONE, /* Reserve 0 */ - DRM_GPU_SCHED_STAT_NOMINAL, - DRM_GPU_SCHED_STAT_ENODEV, -}; - /** * struct drm_sched_backend_ops * @@ -236,16 +230,10 @@ struct drm_sched_backend_ops { struct dma_fence *(*run_job)(struct drm_sched_job *sched_job); /** - * @timedout_job: Called when a job has taken too long to execute, - * to trigger GPU recovery. - * - * Return DRM_GPU_SCHED_STAT_NOMINAL, when all is normal, - * and the underlying driver has started or completed recovery. - * - * Return DRM_GPU_SCHED_STAT_ENODEV, if the device is no longer - * available, i.e. has been unplugged. + * @timedout_job: Called when a job has taken too long to execute, + * to trigger GPU recovery. */ - enum drm_gpu_sched_stat (*timedout_job)(struct drm_sched_job *sched_job); + void (*timedout_job)(struct drm_sched_job *sched_job); /** * @free_job: Called once the job's finished fence has been signaled -- cgit v1.2.3 From 1852ebd1354201cf4ab9564947ff2a17a918b294 Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Wed, 10 Feb 2021 21:27:56 +1100 Subject: of: irq: make a stub for of_irq_parse_one() Signed-off-by: Stephen Rothwell Link: https://lore.kernel.org/r/20210210214720.02e6a6be@canb.auug.org.au Signed-off-by: Greg Kroah-Hartman --- include/linux/of_irq.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h index e8b78139f78c..f898d838d201 100644 --- a/include/linux/of_irq.h +++ b/include/linux/of_irq.h @@ -33,8 +33,6 @@ static inline int of_irq_parse_oldworld(struct device_node *device, int index, #endif /* CONFIG_PPC32 && CONFIG_PPC_PMAC */ extern int of_irq_parse_raw(const __be32 *addr, struct of_phandle_args *out_irq); -extern int of_irq_parse_one(struct device_node *device, int index, - struct of_phandle_args *out_irq); extern unsigned int irq_create_of_mapping(struct of_phandle_args *irq_data); extern int of_irq_to_resource(struct device_node *dev, int index, struct resource *r); @@ -42,6 +40,8 @@ extern int of_irq_to_resource(struct device_node *dev, int index, extern void of_irq_init(const struct of_device_id *matches); #ifdef CONFIG_OF_IRQ +extern int of_irq_parse_one(struct device_node *device, int index, + struct of_phandle_args *out_irq); extern int of_irq_count(struct device_node *dev); extern int of_irq_get(struct device_node *dev, int index); extern int of_irq_get_byname(struct device_node *dev, const char *name); @@ -57,6 +57,11 @@ extern struct irq_domain *of_msi_map_get_device_domain(struct device *dev, extern void of_msi_configure(struct device *dev, struct device_node *np); u32 of_msi_map_id(struct device *dev, struct device_node *msi_np, u32 id_in); #else +static inline int of_irq_parse_one(struct device_node *device, int index, + struct of_phandle_args *out_irq) +{ + return 0; +} static inline int of_irq_count(struct device_node *dev) { return 0; -- cgit v1.2.3 From f31e3386a4e92ba6eda7328cb508462956c94c64 Mon Sep 17 00:00:00 2001 From: Lakshmi Ramasubramanian Date: Thu, 4 Feb 2021 09:49:51 -0800 Subject: ima: Free IMA measurement buffer after kexec syscall IMA allocates kernel virtual memory to carry forward the measurement list, from the current kernel to the next kernel on kexec system call, in ima_add_kexec_buffer() function. This buffer is not freed before completing the kexec system call resulting in memory leak. Add ima_buffer field in "struct kimage" to store the virtual address of the buffer allocated for the IMA measurement list. Free the memory allocated for the IMA measurement list in kimage_file_post_load_cleanup() function. Signed-off-by: Lakshmi Ramasubramanian Suggested-by: Tyler Hicks Reviewed-by: Thiago Jung Bauermann Reviewed-by: Tyler Hicks Fixes: 7b8589cc29e7 ("ima: on soft reboot, save the measurement list") Signed-off-by: Mimi Zohar --- include/linux/kexec.h | 5 +++++ kernel/kexec_file.c | 5 +++++ security/integrity/ima/ima_kexec.c | 2 ++ 3 files changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 9e93bef52968..5f61389f5f36 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -300,6 +300,11 @@ struct kimage { /* Information for loading purgatory */ struct purgatory_info purgatory_info; #endif + +#ifdef CONFIG_IMA_KEXEC + /* Virtual address of IMA measurement buffer for kexec syscall */ + void *ima_buffer; +#endif }; /* kexec interface functions */ diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index b02086d70492..5c3447cf7ad5 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -166,6 +166,11 @@ void kimage_file_post_load_cleanup(struct kimage *image) vfree(pi->sechdrs); pi->sechdrs = NULL; +#ifdef CONFIG_IMA_KEXEC + vfree(image->ima_buffer); + image->ima_buffer = NULL; +#endif /* CONFIG_IMA_KEXEC */ + /* See if architecture has anything to cleanup post load */ arch_kimage_file_post_load_cleanup(image); diff --git a/security/integrity/ima/ima_kexec.c b/security/integrity/ima/ima_kexec.c index 206ddcaa5c67..e29bea3dd4cc 100644 --- a/security/integrity/ima/ima_kexec.c +++ b/security/integrity/ima/ima_kexec.c @@ -129,6 +129,8 @@ void ima_add_kexec_buffer(struct kimage *image) return; } + image->ima_buffer = kexec_buffer; + pr_debug("kexec measurement buffer for the loaded kernel at 0x%lx.\n", kbuf.mem); } -- cgit v1.2.3 From cd1a41ceba8a4caef4d18a3a14d6d0f8c656efe4 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 10 Feb 2021 00:40:52 +0100 Subject: softirq: Move __ARCH_HAS_DO_SOFTIRQ to Kconfig To prepare for inlining do_softirq_own_stack() replace __ARCH_HAS_DO_SOFTIRQ with a Kconfig switch and select it in the affected architectures. This allows in the next step to move the function prototype and the inline stub into a seperate asm-generic header file which is required to avoid include recursion. Signed-off-by: Thomas Gleixner Reviewed-by: Kees Cook Link: https://lore.kernel.org/r/20210210002513.181713427@linutronix.de --- arch/Kconfig | 6 ++++++ arch/parisc/Kconfig | 1 + arch/parisc/include/asm/hardirq.h | 4 ---- arch/powerpc/Kconfig | 1 + arch/powerpc/include/asm/irq.h | 2 -- arch/s390/Kconfig | 1 + arch/s390/include/asm/hardirq.h | 1 - arch/sh/Kconfig | 1 + arch/sh/include/asm/irq.h | 1 - arch/sparc/Kconfig | 1 + arch/sparc/include/asm/irq_64.h | 1 - arch/x86/Kconfig | 1 + arch/x86/include/asm/irq.h | 2 -- include/linux/interrupt.h | 2 +- 14 files changed, 13 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/arch/Kconfig b/arch/Kconfig index 24862d15f3a3..7eab9d0a4b43 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -759,6 +759,12 @@ config HAVE_IRQ_EXIT_ON_IRQ_STACK This spares a stack switch and improves cache usage on softirq processing. +config HAVE_SOFTIRQ_ON_OWN_STACK + bool + help + Architecture provides a function to run __do_softirq() on a + seperate stack. + config PGTABLE_LEVELS int default 2 diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 78b17621ee4a..7cd88c0a9a32 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -63,6 +63,7 @@ config PARISC select HAVE_FTRACE_MCOUNT_RECORD if HAVE_DYNAMIC_FTRACE select HAVE_KPROBES_ON_FTRACE select HAVE_DYNAMIC_FTRACE_WITH_REGS + select HAVE_SOFTIRQ_ON_OWN_STACK if IRQSTACKS select SET_FS help diff --git a/arch/parisc/include/asm/hardirq.h b/arch/parisc/include/asm/hardirq.h index fad29aa6f45f..1e4fbd0fd944 100644 --- a/arch/parisc/include/asm/hardirq.h +++ b/arch/parisc/include/asm/hardirq.h @@ -12,10 +12,6 @@ #include #include -#ifdef CONFIG_IRQSTACKS -#define __ARCH_HAS_DO_SOFTIRQ -#endif - typedef struct { unsigned int __softirq_pending; unsigned int kernel_stack_usage; diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 107bb4319e0e..888d1ad436ce 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -237,6 +237,7 @@ config PPC select MMU_GATHER_PAGE_SIZE select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RELIABLE_STACKTRACE if PPC_BOOK3S_64 && CPU_LITTLE_ENDIAN + select HAVE_SOFTIRQ_ON_OWN_STACK select HAVE_SYSCALL_TRACEPOINTS select HAVE_VIRT_CPU_ACCOUNTING select HAVE_IRQ_TIME_ACCOUNTING diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h index 4f983ca4030a..f3f264e441a7 100644 --- a/arch/powerpc/include/asm/irq.h +++ b/arch/powerpc/include/asm/irq.h @@ -37,8 +37,6 @@ extern int distribute_irqs; struct pt_regs; -#define __ARCH_HAS_DO_SOFTIRQ - #if defined(CONFIG_BOOKE) || defined(CONFIG_40x) /* * Per-cpu stacks for handling critical, debug and machine check diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index c72874f09741..e00c02ab5706 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -182,6 +182,7 @@ config S390 select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RELIABLE_STACKTRACE select HAVE_RSEQ + select HAVE_SOFTIRQ_ON_OWN_STACK select HAVE_SYSCALL_TRACEPOINTS select HAVE_VIRT_CPU_ACCOUNTING select HAVE_VIRT_CPU_ACCOUNTING_IDLE diff --git a/arch/s390/include/asm/hardirq.h b/arch/s390/include/asm/hardirq.h index dfbc3c6c0674..58668ffb5488 100644 --- a/arch/s390/include/asm/hardirq.h +++ b/arch/s390/include/asm/hardirq.h @@ -18,7 +18,6 @@ #define or_softirq_pending(x) (S390_lowcore.softirq_pending |= (x)) #define __ARCH_IRQ_STAT -#define __ARCH_HAS_DO_SOFTIRQ #define __ARCH_IRQ_EXIT_IRQS_DISABLED static inline void ack_bad_irq(unsigned int irq) diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 5fa580219a86..b49d5e033e29 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -56,6 +56,7 @@ config SUPERH select HAVE_PERF_EVENTS select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_UID16 + select HAVE_SOFTIRQ_ON_OWN_STACK if IRQSTACKS select HAVE_STACKPROTECTOR select HAVE_SYSCALL_TRACEPOINTS select IRQ_FORCED_THREADING diff --git a/arch/sh/include/asm/irq.h b/arch/sh/include/asm/irq.h index 6d44c32ef047..839551ce398c 100644 --- a/arch/sh/include/asm/irq.h +++ b/arch/sh/include/asm/irq.h @@ -51,7 +51,6 @@ asmlinkage int do_IRQ(unsigned int irq, struct pt_regs *regs); #ifdef CONFIG_IRQSTACKS extern void irq_ctx_init(int cpu); extern void irq_ctx_exit(int cpu); -# define __ARCH_HAS_DO_SOFTIRQ #else # define irq_ctx_init(cpu) do { } while (0) # define irq_ctx_exit(cpu) do { } while (0) diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index c9c34dc52b7d..f0d22d530645 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -97,6 +97,7 @@ config SPARC64 select ARCH_HAS_PTE_SPECIAL select PCI_DOMAINS if PCI select ARCH_HAS_GIGANTIC_PAGE + select HAVE_SOFTIRQ_ON_OWN_STACK config ARCH_PROC_KCORE_TEXT def_bool y diff --git a/arch/sparc/include/asm/irq_64.h b/arch/sparc/include/asm/irq_64.h index 4d748e93b974..154df2cf19f4 100644 --- a/arch/sparc/include/asm/irq_64.h +++ b/arch/sparc/include/asm/irq_64.h @@ -93,7 +93,6 @@ void arch_trigger_cpumask_backtrace(const struct cpumask *mask, extern void *hardirq_stack[NR_CPUS]; extern void *softirq_stack[NR_CPUS]; -#define __ARCH_HAS_DO_SOFTIRQ #define NO_IRQ 0xffffffff diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index e17ce871bb19..019e0e1a5ee0 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -221,6 +221,7 @@ config X86 select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RELIABLE_STACKTRACE if X86_64 && (UNWINDER_FRAME_POINTER || UNWINDER_ORC) && STACK_VALIDATION select HAVE_FUNCTION_ARG_ACCESS_API + select HAVE_SOFTIRQ_ON_OWN_STACK select HAVE_STACKPROTECTOR if CC_HAS_SANE_STACKPROTECTOR select HAVE_STACK_VALIDATION if X86_64 select HAVE_STATIC_CALL diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h index 528c8a71fe7f..f70d2ca3887e 100644 --- a/arch/x86/include/asm/irq.h +++ b/arch/x86/include/asm/irq.h @@ -25,8 +25,6 @@ static inline int irq_canonicalize(int irq) extern int irq_init_percpu_irqstack(unsigned int cpu); -#define __ARCH_HAS_DO_SOFTIRQ - struct irq_desc; extern void fixup_irqs(void); diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index bb8ff9083e7d..f0b918f393a2 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -569,7 +569,7 @@ struct softirq_action asmlinkage void do_softirq(void); asmlinkage void __do_softirq(void); -#ifdef __ARCH_HAS_DO_SOFTIRQ +#ifdef CONFIG_HAVE_SOFTIRQ_ON_OWN_STACK void do_softirq_own_stack(void); #else static inline void do_softirq_own_stack(void) -- cgit v1.2.3 From db1cc7aede37eb9235759131ddfefd9c0ea5136f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 10 Feb 2021 00:40:53 +0100 Subject: softirq: Move do_softirq_own_stack() to generic asm header To avoid include recursion hell move the do_softirq_own_stack() related content into a generic asm header and include it from all places in arch/ which need the prototype. This allows architectures to provide an inline implementation of do_softirq_own_stack() without introducing a lot of #ifdeffery all over the place. Signed-off-by: Thomas Gleixner Reviewed-by: Kees Cook Link: https://lore.kernel.org/r/20210210002513.289960691@linutronix.de --- arch/parisc/kernel/irq.c | 1 + arch/powerpc/kernel/irq.c | 1 + arch/s390/kernel/irq.c | 1 + arch/sh/kernel/irq.c | 1 + arch/sparc/kernel/irq_64.c | 1 + arch/x86/kernel/irq_32.c | 1 + arch/x86/kernel/irq_64.c | 1 + include/asm-generic/Kbuild | 1 + include/asm-generic/softirq_stack.h | 14 ++++++++++++++ include/linux/interrupt.h | 9 --------- kernel/softirq.c | 2 ++ 11 files changed, 24 insertions(+), 9 deletions(-) create mode 100644 include/asm-generic/softirq_stack.h (limited to 'include') diff --git a/arch/parisc/kernel/irq.c b/arch/parisc/kernel/irq.c index 49cd6d2caefb..1632d525ad64 100644 --- a/arch/parisc/kernel/irq.c +++ b/arch/parisc/kernel/irq.c @@ -17,6 +17,7 @@ #include #include +#include #include #include diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 6b1eca53e36c..96296d3383a7 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -65,6 +65,7 @@ #include #include #include +#include #ifdef CONFIG_PPC64 #include diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c index f8a8b9428ae2..a1a2f75f3c09 100644 --- a/arch/s390/kernel/irq.c +++ b/arch/s390/kernel/irq.c @@ -27,6 +27,7 @@ #include #include #include +#include #include "entry.h" DEFINE_PER_CPU_SHARED_ALIGNED(struct irq_stat, irq_stat); diff --git a/arch/sh/kernel/irq.c b/arch/sh/kernel/irq.c index ab5f790b0cd2..ef0f0827cf57 100644 --- a/arch/sh/kernel/irq.c +++ b/arch/sh/kernel/irq.c @@ -20,6 +20,7 @@ #include #include #include +#include atomic_t irq_err_count; diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c index 3ec9f1402aad..c8848bb681a1 100644 --- a/arch/sparc/kernel/irq_64.c +++ b/arch/sparc/kernel/irq_64.c @@ -42,6 +42,7 @@ #include #include #include +#include #include "entry.h" #include "cpumap.h" diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index 0b79efc87be5..044902d5a3c4 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -22,6 +22,7 @@ #include #include +#include #ifdef CONFIG_DEBUG_STACKOVERFLOW diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index b88fdb9686e6..f335c3910834 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -20,6 +20,7 @@ #include #include +#include #include #include #include diff --git a/include/asm-generic/Kbuild b/include/asm-generic/Kbuild index 267f6dfb8960..bd684188e2dc 100644 --- a/include/asm-generic/Kbuild +++ b/include/asm-generic/Kbuild @@ -51,6 +51,7 @@ mandatory-y += sections.h mandatory-y += serial.h mandatory-y += shmparam.h mandatory-y += simd.h +mandatory-y += softirq_stack.h mandatory-y += switch_to.h mandatory-y += timex.h mandatory-y += tlbflush.h diff --git a/include/asm-generic/softirq_stack.h b/include/asm-generic/softirq_stack.h new file mode 100644 index 000000000000..eceeecf6a5bd --- /dev/null +++ b/include/asm-generic/softirq_stack.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef __ASM_GENERIC_SOFTIRQ_STACK_H +#define __ASM_GENERIC_SOFTIRQ_STACK_H + +#ifdef CONFIG_HAVE_SOFTIRQ_ON_OWN_STACK +void do_softirq_own_stack(void); +#else +static inline void do_softirq_own_stack(void) +{ + __do_softirq(); +} +#endif + +#endif diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index f0b918f393a2..967e25767153 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -569,15 +569,6 @@ struct softirq_action asmlinkage void do_softirq(void); asmlinkage void __do_softirq(void); -#ifdef CONFIG_HAVE_SOFTIRQ_ON_OWN_STACK -void do_softirq_own_stack(void); -#else -static inline void do_softirq_own_stack(void) -{ - __do_softirq(); -} -#endif - extern void open_softirq(int nr, void (*action)(struct softirq_action *)); extern void softirq_init(void); extern void __raise_softirq_irqoff(unsigned int nr); diff --git a/kernel/softirq.c b/kernel/softirq.c index 9d71046ea247..9908ec4a9bfe 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -26,6 +26,8 @@ #include #include +#include + #define CREATE_TRACE_POINTS #include -- cgit v1.2.3 From 8c0381f55bbf70a3b8ab24e4f5ac62125c44c804 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Wed, 10 Feb 2021 12:00:49 -0800 Subject: of: irq: Fix the return value for of_irq_parse_one() stub When commit 1852ebd13542 ("of: irq: make a stub for of_irq_parse_one()") added a stub for of_irq_parse_one() it set the return value to 0. Return value of 0 in this instance means the call succeeded and the out_irq pointer was filled with valid data. So, fix it to return an error value. Fixes: 1852ebd13542 ("of: irq: make a stub for of_irq_parse_one()") Acked-by: Stephen Rothwell Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20210210200050.4106032-1-saravanak@google.com Signed-off-by: Greg Kroah-Hartman --- include/linux/of_irq.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h index f898d838d201..aaf219bd0354 100644 --- a/include/linux/of_irq.h +++ b/include/linux/of_irq.h @@ -60,7 +60,7 @@ u32 of_msi_map_id(struct device *dev, struct device_node *msi_np, u32 id_in); static inline int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_args *out_irq) { - return 0; + return -EINVAL; } static inline int of_irq_count(struct device_node *dev) { -- cgit v1.2.3 From f11e2bc682cc197e33bfd118178cadb61326dc0e Mon Sep 17 00:00:00 2001 From: Daniel Thompson Date: Wed, 10 Feb 2021 14:25:25 +0000 Subject: kgdb: Remove kgdb_schedule_breakpoint() To the very best of my knowledge there has never been any in-tree code that calls this function. It exists largely to support an out-of-tree driver that provides kgdb-over-ethernet using the netpoll API. kgdboe has been out-of-tree for more than 10 years and I don't recall any serious attempt to upstream it at any point in the last five. At this stage it looks better to stop carrying this code in the kernel and integrate the code into the out-of-tree driver instead. The long term trajectory for the kernel looks likely to include effort to remove or reduce the use of tasklets (something that has also been true for the last 10 years). Thus the main real reason for this patch is to make explicit that the in-tree kgdb features do not require tasklets. Signed-off-by: Daniel Thompson Link: https://lore.kernel.org/r/20210210142525.2876648-1-daniel.thompson@linaro.org Reviewed-by: Douglas Anderson Acked-by: Davidlohr Bueso Acked-by: Jason Wessel --- include/linux/kgdb.h | 1 - kernel/debug/debug_core.c | 26 -------------------------- 2 files changed, 27 deletions(-) (limited to 'include') diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index 0d6cf64c8bb1..0444b44bd156 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -325,7 +325,6 @@ extern char *kgdb_mem2hex(char *mem, char *buf, int count); extern int kgdb_hex2mem(char *buf, char *mem, int count); extern int kgdb_isremovedbreak(unsigned long addr); -extern void kgdb_schedule_breakpoint(void); extern int kgdb_has_hit_break(unsigned long addr); extern int diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index 7f22c1c0ffe8..b636d517c02c 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -119,7 +119,6 @@ static DEFINE_RAW_SPINLOCK(dbg_slave_lock); */ static atomic_t masters_in_kgdb; static atomic_t slaves_in_kgdb; -static atomic_t kgdb_break_tasklet_var; atomic_t kgdb_setting_breakpoint; struct task_struct *kgdb_usethread; @@ -1084,31 +1083,6 @@ static void kgdb_unregister_callbacks(void) } } -/* - * There are times a tasklet needs to be used vs a compiled in - * break point so as to cause an exception outside a kgdb I/O module, - * such as is the case with kgdboe, where calling a breakpoint in the - * I/O driver itself would be fatal. - */ -static void kgdb_tasklet_bpt(unsigned long ing) -{ - kgdb_breakpoint(); - atomic_set(&kgdb_break_tasklet_var, 0); -} - -static DECLARE_TASKLET_OLD(kgdb_tasklet_breakpoint, kgdb_tasklet_bpt); - -void kgdb_schedule_breakpoint(void) -{ - if (atomic_read(&kgdb_break_tasklet_var) || - atomic_read(&kgdb_active) != -1 || - atomic_read(&kgdb_setting_breakpoint)) - return; - atomic_inc(&kgdb_break_tasklet_var); - tasklet_schedule(&kgdb_tasklet_breakpoint); -} -EXPORT_SYMBOL_GPL(kgdb_schedule_breakpoint); - /** * kgdb_register_io_module - register KGDB IO module * @new_dbg_io_ops: the io ops vector -- cgit v1.2.3 From f7684f5a048febd2a7bc98ee81d6dce52f7268b8 Mon Sep 17 00:00:00 2001 From: Frieder Schrempf Date: Thu, 11 Feb 2021 11:55:30 +0100 Subject: regulator: pca9450: Enable system reset on WDOG_B assertion By default the PCA9450 doesn't handle the assertion of the WDOG_B signal, but this is required to guarantee that things like software resets triggered by the watchdog work reliably. As we don't want to rely on the bootloader to enable this, we tell the PMIC to issue a cold reset in case the WDOG_B signal is asserted (WDOG_B_CFG = 10), just as the NXP U-Boot code does. Signed-off-by: Frieder Schrempf Link: https://lore.kernel.org/r/20210211105534.38972-3-frieder.schrempf@kontron.de Signed-off-by: Mark Brown --- drivers/regulator/pca9450-regulator.c | 8 ++++++++ include/linux/regulator/pca9450.h | 7 +++++++ 2 files changed, 15 insertions(+) (limited to 'include') diff --git a/drivers/regulator/pca9450-regulator.c b/drivers/regulator/pca9450-regulator.c index 1bba8fdcb7b7..833d398c6aa2 100644 --- a/drivers/regulator/pca9450-regulator.c +++ b/drivers/regulator/pca9450-regulator.c @@ -797,6 +797,14 @@ static int pca9450_i2c_probe(struct i2c_client *i2c, return ret; } + /* Set reset behavior on assertion of WDOG_B signal */ + ret = regmap_update_bits(pca9450->regmap, PCA9450_REG_RESET_CTRL, + WDOG_B_CFG_MASK, WDOG_B_CFG_COLD_LDO12); + if (ret) { + dev_err(&i2c->dev, "Failed to set WDOG_B reset behavior\n"); + return ret; + } + /* * The driver uses the LDO5CTRL_H register to control the LDO5 regulator. * This is only valid if the SD_VSEL input of the PMIC is high. Let's diff --git a/include/linux/regulator/pca9450.h b/include/linux/regulator/pca9450.h index 1bbd3014f906..ccdb5320a240 100644 --- a/include/linux/regulator/pca9450.h +++ b/include/linux/regulator/pca9450.h @@ -216,4 +216,11 @@ enum { #define IRQ_THERM_105 0x02 #define IRQ_THERM_125 0x01 +/* PCA9450_REG_RESET_CTRL bits */ +#define WDOG_B_CFG_MASK 0xC0 +#define WDOG_B_CFG_NONE 0x00 +#define WDOG_B_CFG_WARM 0x40 +#define WDOG_B_CFG_COLD_LDO12 0x80 +#define WDOG_B_CFG_COLD 0xC0 + #endif /* __LINUX_REG_PCA9450_H__ */ -- cgit v1.2.3 From 7bdcc48f4e80b01fd6057dfd382236a5b8123b61 Mon Sep 17 00:00:00 2001 From: Satya Tangirala Date: Mon, 1 Feb 2021 05:10:15 +0000 Subject: block/keyslot-manager: Introduce passthrough keyslot manager The device mapper may map over devices that have inline encryption capabilities, and to make use of those capabilities, the DM device must itself advertise those inline encryption capabilities. One way to do this would be to have the DM device set up a keyslot manager with a "sufficiently large" number of keyslots, but that would use a lot of memory. Also, the DM device itself has no "keyslots", and it doesn't make much sense to talk about "programming a key into a DM device's keyslot manager", so all that extra memory used to represent those keyslots is just wasted. All a DM device really needs to be able to do is advertise the crypto capabilities of the underlying devices in a coherent manner and expose a way to evict keys from the underlying devices. There are also devices with inline encryption hardware that do not have a limited number of keyslots. One can send a raw encryption key along with a bio to these devices (as opposed to typical inline encryption hardware that require users to first program a raw encryption key into a keyslot, and send the index of that keyslot along with the bio). These devices also only need the same things from the keyslot manager that DM devices need - a way to advertise crypto capabilities and potentially a way to expose a function to evict keys from hardware. So we introduce a "passthrough" keyslot manager that provides a way to represent a keyslot manager that doesn't have just a limited number of keyslots, and for which do not require keys to be programmed into keyslots. DM devices can set up a passthrough keyslot manager in their request queues, and advertise appropriate crypto capabilities based on those of the underlying devices. Blk-crypto does not attempt to program keys into any keyslots in the passthrough keyslot manager. Instead, if/when the bio is resubmitted to the underlying device, blk-crypto will try to program the key into the underlying device's keyslot manager. Signed-off-by: Satya Tangirala Reviewed-by: Eric Biggers Acked-by: Jens Axboe Signed-off-by: Mike Snitzer --- block/keyslot-manager.c | 39 +++++++++++++++++++++++++++++++++++++++ include/linux/keyslot-manager.h | 2 ++ 2 files changed, 41 insertions(+) (limited to 'include') diff --git a/block/keyslot-manager.c b/block/keyslot-manager.c index 86f8195d8039..ac7ce83a76e8 100644 --- a/block/keyslot-manager.c +++ b/block/keyslot-manager.c @@ -62,6 +62,11 @@ static inline void blk_ksm_hw_exit(struct blk_keyslot_manager *ksm) pm_runtime_put_sync(ksm->dev); } +static inline bool blk_ksm_is_passthrough(struct blk_keyslot_manager *ksm) +{ + return ksm->num_slots == 0; +} + /** * blk_ksm_init() - Initialize a keyslot manager * @ksm: The keyslot_manager to initialize. @@ -205,6 +210,10 @@ blk_status_t blk_ksm_get_slot_for_key(struct blk_keyslot_manager *ksm, int err; *slot_ptr = NULL; + + if (blk_ksm_is_passthrough(ksm)) + return BLK_STS_OK; + down_read(&ksm->lock); slot = blk_ksm_find_and_grab_keyslot(ksm, key); up_read(&ksm->lock); @@ -325,6 +334,16 @@ int blk_ksm_evict_key(struct blk_keyslot_manager *ksm, struct blk_ksm_keyslot *slot; int err = 0; + if (blk_ksm_is_passthrough(ksm)) { + if (ksm->ksm_ll_ops.keyslot_evict) { + blk_ksm_hw_enter(ksm); + err = ksm->ksm_ll_ops.keyslot_evict(ksm, key, -1); + blk_ksm_hw_exit(ksm); + return err; + } + return 0; + } + blk_ksm_hw_enter(ksm); slot = blk_ksm_find_keyslot(ksm, key); if (!slot) @@ -360,6 +379,9 @@ void blk_ksm_reprogram_all_keys(struct blk_keyslot_manager *ksm) { unsigned int slot; + if (blk_ksm_is_passthrough(ksm)) + return; + /* This is for device initialization, so don't resume the device */ down_write(&ksm->lock); for (slot = 0; slot < ksm->num_slots; slot++) { @@ -401,3 +423,20 @@ void blk_ksm_unregister(struct request_queue *q) { q->ksm = NULL; } + +/** + * blk_ksm_init_passthrough() - Init a passthrough keyslot manager + * @ksm: The keyslot manager to init + * + * Initialize a passthrough keyslot manager. + * Called by e.g. storage drivers to set up a keyslot manager in their + * request_queue, when the storage driver wants to manage its keys by itself. + * This is useful for inline encryption hardware that doesn't have the concept + * of keyslots, and for layered devices. + */ +void blk_ksm_init_passthrough(struct blk_keyslot_manager *ksm) +{ + memset(ksm, 0, sizeof(*ksm)); + init_rwsem(&ksm->lock); +} +EXPORT_SYMBOL_GPL(blk_ksm_init_passthrough); diff --git a/include/linux/keyslot-manager.h b/include/linux/keyslot-manager.h index 18f3f5346843..323e15dd6fa7 100644 --- a/include/linux/keyslot-manager.h +++ b/include/linux/keyslot-manager.h @@ -103,4 +103,6 @@ void blk_ksm_reprogram_all_keys(struct blk_keyslot_manager *ksm); void blk_ksm_destroy(struct blk_keyslot_manager *ksm); +void blk_ksm_init_passthrough(struct blk_keyslot_manager *ksm); + #endif /* __LINUX_KEYSLOT_MANAGER_H */ -- cgit v1.2.3 From d3b17a243790a34bd63fcef3fde63e29e2744938 Mon Sep 17 00:00:00 2001 From: Satya Tangirala Date: Mon, 1 Feb 2021 05:10:16 +0000 Subject: block/keyslot-manager: Introduce functions for device mapper support Introduce blk_ksm_update_capabilities() to update the capabilities of a keyslot manager (ksm) in-place. The pointer to a ksm in a device's request queue may not be easily replaced, because upper layers like the filesystem might access it (e.g. for programming keys/checking capabilities) at the same time the device wants to replace that request queue's ksm (and free the old ksm's memory). This function allows the device to update the capabilities of the ksm in its request queue directly. Devices can safely update the ksm this way without any synchronization with upper layers *only* if the updated (new) ksm continues to support all the crypto capabilities that the old ksm did (see description below for blk_ksm_is_superset() for why this is so). Also introduce blk_ksm_is_superset() which checks whether one ksm's capabilities are a (not necessarily strict) superset of another ksm's. The blk-crypto framework requires that crypto capabilities that were advertised when a bio was created continue to be supported by the device until that bio is ended - in practice this probably means that a device's advertised crypto capabilities can *never* "shrink" (since there's no synchronization between bio creation and when a device may want to change its advertised capabilities) - so a previously advertised crypto capability must always continue to be supported. This function can be used to check that a new ksm is a valid replacement for an old ksm. Signed-off-by: Satya Tangirala Reviewed-by: Eric Biggers Acked-by: Jens Axboe Signed-off-by: Mike Snitzer --- block/keyslot-manager.c | 107 ++++++++++++++++++++++++++++++++++++++++ include/linux/keyslot-manager.h | 9 ++++ 2 files changed, 116 insertions(+) (limited to 'include') diff --git a/block/keyslot-manager.c b/block/keyslot-manager.c index ac7ce83a76e8..9f9494b80148 100644 --- a/block/keyslot-manager.c +++ b/block/keyslot-manager.c @@ -424,6 +424,113 @@ void blk_ksm_unregister(struct request_queue *q) q->ksm = NULL; } +/** + * blk_ksm_intersect_modes() - restrict supported modes by child device + * @parent: The keyslot manager for parent device + * @child: The keyslot manager for child device, or NULL + * + * Clear any crypto mode support bits in @parent that aren't set in @child. + * If @child is NULL, then all parent bits are cleared. + * + * Only use this when setting up the keyslot manager for a layered device, + * before it's been exposed yet. + */ +void blk_ksm_intersect_modes(struct blk_keyslot_manager *parent, + const struct blk_keyslot_manager *child) +{ + if (child) { + unsigned int i; + + parent->max_dun_bytes_supported = + min(parent->max_dun_bytes_supported, + child->max_dun_bytes_supported); + for (i = 0; i < ARRAY_SIZE(child->crypto_modes_supported); + i++) { + parent->crypto_modes_supported[i] &= + child->crypto_modes_supported[i]; + } + } else { + parent->max_dun_bytes_supported = 0; + memset(parent->crypto_modes_supported, 0, + sizeof(parent->crypto_modes_supported)); + } +} +EXPORT_SYMBOL_GPL(blk_ksm_intersect_modes); + +/** + * blk_ksm_is_superset() - Check if a KSM supports a superset of crypto modes + * and DUN bytes that another KSM supports. Here, + * "superset" refers to the mathematical meaning of the + * word - i.e. if two KSMs have the *same* capabilities, + * they *are* considered supersets of each other. + * @ksm_superset: The KSM that we want to verify is a superset + * @ksm_subset: The KSM that we want to verify is a subset + * + * Return: True if @ksm_superset supports a superset of the crypto modes and DUN + * bytes that @ksm_subset supports. + */ +bool blk_ksm_is_superset(struct blk_keyslot_manager *ksm_superset, + struct blk_keyslot_manager *ksm_subset) +{ + int i; + + if (!ksm_subset) + return true; + + if (!ksm_superset) + return false; + + for (i = 0; i < ARRAY_SIZE(ksm_superset->crypto_modes_supported); i++) { + if (ksm_subset->crypto_modes_supported[i] & + (~ksm_superset->crypto_modes_supported[i])) { + return false; + } + } + + if (ksm_subset->max_dun_bytes_supported > + ksm_superset->max_dun_bytes_supported) { + return false; + } + + return true; +} +EXPORT_SYMBOL_GPL(blk_ksm_is_superset); + +/** + * blk_ksm_update_capabilities() - Update the restrictions of a KSM to those of + * another KSM + * @target_ksm: The KSM whose restrictions to update. + * @reference_ksm: The KSM to whose restrictions this function will update + * @target_ksm's restrictions to. + * + * Blk-crypto requires that crypto capabilities that were + * advertised when a bio was created continue to be supported by the + * device until that bio is ended. This is turn means that a device cannot + * shrink its advertised crypto capabilities without any explicit + * synchronization with upper layers. So if there's no such explicit + * synchronization, @reference_ksm must support all the crypto capabilities that + * @target_ksm does + * (i.e. we need blk_ksm_is_superset(@reference_ksm, @target_ksm) == true). + * + * Note also that as long as the crypto capabilities are being expanded, the + * order of updates becoming visible is not important because it's alright + * for blk-crypto to see stale values - they only cause blk-crypto to + * believe that a crypto capability isn't supported when it actually is (which + * might result in blk-crypto-fallback being used if available, or the bio being + * failed). + */ +void blk_ksm_update_capabilities(struct blk_keyslot_manager *target_ksm, + struct blk_keyslot_manager *reference_ksm) +{ + memcpy(target_ksm->crypto_modes_supported, + reference_ksm->crypto_modes_supported, + sizeof(target_ksm->crypto_modes_supported)); + + target_ksm->max_dun_bytes_supported = + reference_ksm->max_dun_bytes_supported; +} +EXPORT_SYMBOL_GPL(blk_ksm_update_capabilities); + /** * blk_ksm_init_passthrough() - Init a passthrough keyslot manager * @ksm: The keyslot manager to init diff --git a/include/linux/keyslot-manager.h b/include/linux/keyslot-manager.h index 323e15dd6fa7..164568f52be7 100644 --- a/include/linux/keyslot-manager.h +++ b/include/linux/keyslot-manager.h @@ -103,6 +103,15 @@ void blk_ksm_reprogram_all_keys(struct blk_keyslot_manager *ksm); void blk_ksm_destroy(struct blk_keyslot_manager *ksm); +void blk_ksm_intersect_modes(struct blk_keyslot_manager *parent, + const struct blk_keyslot_manager *child); + void blk_ksm_init_passthrough(struct blk_keyslot_manager *ksm); +bool blk_ksm_is_superset(struct blk_keyslot_manager *ksm_superset, + struct blk_keyslot_manager *ksm_subset); + +void blk_ksm_update_capabilities(struct blk_keyslot_manager *target_ksm, + struct blk_keyslot_manager *reference_ksm); + #endif /* __LINUX_KEYSLOT_MANAGER_H */ -- cgit v1.2.3 From aa6ce87a768226802f9a231b3909fe81c503852c Mon Sep 17 00:00:00 2001 From: Satya Tangirala Date: Mon, 1 Feb 2021 05:10:17 +0000 Subject: dm: add support for passing through inline crypto support Update the device-mapper core to support exposing the inline crypto support of the underlying device(s) through the device-mapper device. This works by creating a "passthrough keyslot manager" for the dm device, which declares support for encryption settings which all underlying devices support. When a supported setting is used, the bio cloning code handles cloning the crypto context to the bios for all the underlying devices. When an unsupported setting is used, the blk-crypto fallback is used as usual. Crypto support on each underlying device is ignored unless the corresponding dm target opts into exposing it. This is needed because for inline crypto to semantically operate on the original bio, the data must not be transformed by the dm target. Thus, targets like dm-linear can expose crypto support of the underlying device, but targets like dm-crypt can't. (dm-crypt could use inline crypto itself, though.) A DM device's table can only be changed if the "new" inline encryption capabilities are a (*not* necessarily strict) superset of the "old" inline encryption capabilities. Attempts to make changes to the table that result in some inline encryption capability becoming no longer supported will be rejected. For the sake of clarity, key eviction from underlying devices will be handled in a future patch. Co-developed-by: Eric Biggers Signed-off-by: Eric Biggers Signed-off-by: Satya Tangirala Signed-off-by: Mike Snitzer --- drivers/md/dm-core.h | 5 ++ drivers/md/dm-table.c | 162 ++++++++++++++++++++++++++++++++++++++++++ drivers/md/dm.c | 18 ++++- include/linux/device-mapper.h | 11 +++ include/uapi/linux/dm-ioctl.h | 4 +- 5 files changed, 197 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h index 086d293c2b03..bf3e66f39a4a 100644 --- a/drivers/md/dm-core.h +++ b/drivers/md/dm-core.h @@ -13,6 +13,7 @@ #include #include #include +#include #include @@ -162,6 +163,10 @@ struct dm_table { void *event_context; struct dm_md_mempools *mempools; + +#ifdef CONFIG_BLK_INLINE_ENCRYPTION + struct blk_keyslot_manager *ksm; +#endif }; static inline struct completion *dm_get_completion_from_kobject(struct kobject *kobj) diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 2bc256d61550..8c4ed3ec9409 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -187,6 +187,8 @@ static void free_devices(struct list_head *devices, struct mapped_device *md) } } +static void dm_table_destroy_keyslot_manager(struct dm_table *t); + void dm_table_destroy(struct dm_table *t) { unsigned int i; @@ -215,6 +217,8 @@ void dm_table_destroy(struct dm_table *t) dm_free_md_mempools(t->mempools); + dm_table_destroy_keyslot_manager(t); + kfree(t); } @@ -1203,6 +1207,157 @@ static int dm_table_register_integrity(struct dm_table *t) return 0; } +#ifdef CONFIG_BLK_INLINE_ENCRYPTION + +struct dm_keyslot_manager { + struct blk_keyslot_manager ksm; + struct mapped_device *md; +}; + +static int device_intersect_crypto_modes(struct dm_target *ti, + struct dm_dev *dev, sector_t start, + sector_t len, void *data) +{ + struct blk_keyslot_manager *parent = data; + struct blk_keyslot_manager *child = bdev_get_queue(dev->bdev)->ksm; + + blk_ksm_intersect_modes(parent, child); + return 0; +} + +void dm_destroy_keyslot_manager(struct blk_keyslot_manager *ksm) +{ + struct dm_keyslot_manager *dksm = container_of(ksm, + struct dm_keyslot_manager, + ksm); + + if (!ksm) + return; + + blk_ksm_destroy(ksm); + kfree(dksm); +} + +static void dm_table_destroy_keyslot_manager(struct dm_table *t) +{ + dm_destroy_keyslot_manager(t->ksm); + t->ksm = NULL; +} + +/* + * Constructs and initializes t->ksm with a keyslot manager that + * represents the common set of crypto capabilities of the devices + * described by the dm_table. However, if the constructed keyslot + * manager does not support a superset of the crypto capabilities + * supported by the current keyslot manager of the mapped_device, + * it returns an error instead, since we don't support restricting + * crypto capabilities on table changes. Finally, if the constructed + * keyslot manager doesn't actually support any crypto modes at all, + * it just returns NULL. + */ +static int dm_table_construct_keyslot_manager(struct dm_table *t) +{ + struct dm_keyslot_manager *dksm; + struct blk_keyslot_manager *ksm; + struct dm_target *ti; + unsigned int i; + bool ksm_is_empty = true; + + dksm = kmalloc(sizeof(*dksm), GFP_KERNEL); + if (!dksm) + return -ENOMEM; + dksm->md = t->md; + + ksm = &dksm->ksm; + blk_ksm_init_passthrough(ksm); + ksm->max_dun_bytes_supported = UINT_MAX; + memset(ksm->crypto_modes_supported, 0xFF, + sizeof(ksm->crypto_modes_supported)); + + for (i = 0; i < dm_table_get_num_targets(t); i++) { + ti = dm_table_get_target(t, i); + + if (!dm_target_passes_crypto(ti->type)) { + blk_ksm_intersect_modes(ksm, NULL); + break; + } + if (!ti->type->iterate_devices) + continue; + ti->type->iterate_devices(ti, device_intersect_crypto_modes, + ksm); + } + + if (t->md->queue && !blk_ksm_is_superset(ksm, t->md->queue->ksm)) { + DMWARN("Inline encryption capabilities of new DM table were more restrictive than the old table's. This is not supported!"); + dm_destroy_keyslot_manager(ksm); + return -EINVAL; + } + + /* + * If the new KSM doesn't actually support any crypto modes, we may as + * well represent it with a NULL ksm. + */ + ksm_is_empty = true; + for (i = 0; i < ARRAY_SIZE(ksm->crypto_modes_supported); i++) { + if (ksm->crypto_modes_supported[i]) { + ksm_is_empty = false; + break; + } + } + + if (ksm_is_empty) { + dm_destroy_keyslot_manager(ksm); + ksm = NULL; + } + + /* + * t->ksm is only set temporarily while the table is being set + * up, and it gets set to NULL after the capabilities have + * been transferred to the request_queue. + */ + t->ksm = ksm; + + return 0; +} + +static void dm_update_keyslot_manager(struct request_queue *q, + struct dm_table *t) +{ + if (!t->ksm) + return; + + /* Make the ksm less restrictive */ + if (!q->ksm) { + blk_ksm_register(t->ksm, q); + } else { + blk_ksm_update_capabilities(q->ksm, t->ksm); + dm_destroy_keyslot_manager(t->ksm); + } + t->ksm = NULL; +} + +#else /* CONFIG_BLK_INLINE_ENCRYPTION */ + +static int dm_table_construct_keyslot_manager(struct dm_table *t) +{ + return 0; +} + +void dm_destroy_keyslot_manager(struct blk_keyslot_manager *ksm) +{ +} + +static void dm_table_destroy_keyslot_manager(struct dm_table *t) +{ +} + +static void dm_update_keyslot_manager(struct request_queue *q, + struct dm_table *t) +{ +} + +#endif /* !CONFIG_BLK_INLINE_ENCRYPTION */ + /* * Prepares the table for use by building the indices, * setting the type, and allocating mempools. @@ -1229,6 +1384,12 @@ int dm_table_complete(struct dm_table *t) return r; } + r = dm_table_construct_keyslot_manager(t); + if (r) { + DMERR("could not construct keyslot manager."); + return r; + } + r = dm_table_alloc_md_mempools(t, t->md); if (r) DMERR("unable to allocate mempools"); @@ -1863,6 +2024,7 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, } #endif + dm_update_keyslot_manager(q, t); blk_queue_update_readahead(q); } diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 64fda1429e39..7021aea82aa4 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -28,6 +28,7 @@ #include #include #include +#include #define DM_MSG_PREFIX "core" @@ -1722,6 +1723,19 @@ static const struct dax_operations dm_dax_ops; static void dm_wq_work(struct work_struct *work); +#ifdef CONFIG_BLK_INLINE_ENCRYPTION +static void dm_queue_destroy_keyslot_manager(struct request_queue *q) +{ + dm_destroy_keyslot_manager(q->ksm); +} + +#else /* CONFIG_BLK_INLINE_ENCRYPTION */ + +static inline void dm_queue_destroy_keyslot_manager(struct request_queue *q) +{ +} +#endif /* !CONFIG_BLK_INLINE_ENCRYPTION */ + static void cleanup_mapped_device(struct mapped_device *md) { if (md->wq) @@ -1743,8 +1757,10 @@ static void cleanup_mapped_device(struct mapped_device *md) put_disk(md->disk); } - if (md->queue) + if (md->queue) { + dm_queue_destroy_keyslot_manager(md->queue); blk_cleanup_queue(md->queue); + } cleanup_srcu_struct(&md->io_barrier); diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 61a66fb8ebb3..47588130ef5e 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -257,6 +257,12 @@ struct target_type { #define DM_TARGET_NOWAIT 0x00000080 #define dm_target_supports_nowait(type) ((type)->features & DM_TARGET_NOWAIT) +/* + * A target supports passing through inline crypto support. + */ +#define DM_TARGET_PASSES_CRYPTO 0x00000100 +#define dm_target_passes_crypto(type) ((type)->features & DM_TARGET_PASSES_CRYPTO) + struct dm_target { struct dm_table *table; struct target_type *type; @@ -533,6 +539,11 @@ void dm_table_run_md_queue_async(struct dm_table *t); struct dm_table *dm_swap_table(struct mapped_device *md, struct dm_table *t); +/* + * Table keyslot manager functions + */ +void dm_destroy_keyslot_manager(struct blk_keyslot_manager *ksm); + /* * A wrapper around vmalloc. */ diff --git a/include/uapi/linux/dm-ioctl.h b/include/uapi/linux/dm-ioctl.h index 4933b6b67b85..fcff6669137b 100644 --- a/include/uapi/linux/dm-ioctl.h +++ b/include/uapi/linux/dm-ioctl.h @@ -272,9 +272,9 @@ enum { #define DM_DEV_SET_GEOMETRY _IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl) #define DM_VERSION_MAJOR 4 -#define DM_VERSION_MINOR 43 +#define DM_VERSION_MINOR 44 #define DM_VERSION_PATCHLEVEL 0 -#define DM_VERSION_EXTRA "-ioctl (2020-10-01)" +#define DM_VERSION_EXTRA "-ioctl (2021-02-01)" /* Status bits */ #define DM_READONLY_FLAG (1 << 0) /* In/Out */ -- cgit v1.2.3 From e3290b9491ff5b7ee40f9e0a4c06821988a2a2bf Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Wed, 10 Feb 2021 17:38:30 -0500 Subject: dm: simplify target code conditional on CONFIG_BLK_DEV_ZONED Allow removal of CONFIG_BLK_DEV_ZONED conditionals in target_type definition of various targets. Suggested-by: Eric Biggers Signed-off-by: Mike Snitzer --- drivers/md/dm-crypt.c | 6 ++---- drivers/md/dm-flakey.c | 6 ++---- drivers/md/dm-linear.c | 7 ++----- include/linux/device-mapper.h | 16 ++++++++++++++-- 4 files changed, 20 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index ee20b586f526..ae0f0a4e3689 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -3134,7 +3134,6 @@ static int crypt_ctr_optional(struct dm_target *ti, unsigned int argc, char **ar } #ifdef CONFIG_BLK_DEV_ZONED - static int crypt_report_zones(struct dm_target *ti, struct dm_report_zones_args *args, unsigned int nr_zones) { @@ -3145,7 +3144,8 @@ static int crypt_report_zones(struct dm_target *ti, return blkdev_report_zones(cc->dev->bdev, sector, nr_zones, dm_report_zones_cb, args); } - +#else +#define crypt_report_zones NULL #endif /* @@ -3580,10 +3580,8 @@ static struct target_type crypt_target = { .module = THIS_MODULE, .ctr = crypt_ctr, .dtr = crypt_dtr, -#ifdef CONFIG_BLK_DEV_ZONED .features = DM_TARGET_ZONED_HM, .report_zones = crypt_report_zones, -#endif .map = crypt_map, .status = crypt_status, .postsuspend = crypt_postsuspend, diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c index 30c6bc151213..b7fee9936f05 100644 --- a/drivers/md/dm-flakey.c +++ b/drivers/md/dm-flakey.c @@ -469,6 +469,8 @@ static int flakey_report_zones(struct dm_target *ti, return blkdev_report_zones(fc->dev->bdev, sector, nr_zones, dm_report_zones_cb, args); } +#else +#define flakey_report_zones NULL #endif static int flakey_iterate_devices(struct dm_target *ti, iterate_devices_callout_fn fn, void *data) @@ -481,12 +483,8 @@ static int flakey_iterate_devices(struct dm_target *ti, iterate_devices_callout_ static struct target_type flakey_target = { .name = "flakey", .version = {1, 5, 0}, -#ifdef CONFIG_BLK_DEV_ZONED .features = DM_TARGET_ZONED_HM | DM_TARGET_PASSES_CRYPTO, .report_zones = flakey_report_zones, -#else - .features = DM_TARGET_PASSES_CRYPTO, -#endif .module = THIS_MODULE, .ctr = flakey_ctr, .dtr = flakey_dtr, diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c index fc9c4272c10d..92db0f5e7f28 100644 --- a/drivers/md/dm-linear.c +++ b/drivers/md/dm-linear.c @@ -146,6 +146,8 @@ static int linear_report_zones(struct dm_target *ti, return blkdev_report_zones(lc->dev->bdev, sector, nr_zones, dm_report_zones_cb, args); } +#else +#define linear_report_zones NULL #endif static int linear_iterate_devices(struct dm_target *ti, @@ -227,14 +229,9 @@ static int linear_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff, static struct target_type linear_target = { .name = "linear", .version = {1, 4, 0}, -#ifdef CONFIG_BLK_DEV_ZONED .features = DM_TARGET_PASSES_INTEGRITY | DM_TARGET_NOWAIT | DM_TARGET_ZONED_HM | DM_TARGET_PASSES_CRYPTO, .report_zones = linear_report_zones, -#else - .features = DM_TARGET_PASSES_INTEGRITY | DM_TARGET_NOWAIT | - DM_TARGET_PASSES_CRYPTO, -#endif .module = THIS_MODULE, .ctr = linear_ctr, .dtr = linear_dtr, diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 47588130ef5e..c98d847b0f0b 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -93,9 +93,18 @@ typedef int (*dm_message_fn) (struct dm_target *ti, unsigned argc, char **argv, typedef int (*dm_prepare_ioctl_fn) (struct dm_target *ti, struct block_device **bdev); +#ifdef CONFIG_BLK_DEV_ZONED typedef int (*dm_report_zones_fn) (struct dm_target *ti, struct dm_report_zones_args *args, unsigned int nr_zones); +#else +/* + * Define dm_report_zones_fn so that targets can assign to NULL if + * CONFIG_BLK_DEV_ZONED disabled. Otherwise each target needs to do + * awkward #ifdefs in their target_type, etc. + */ +typedef int (*dm_report_zones_fn) (struct dm_target *dummy); +#endif /* * These iteration functions are typically used to check (and combine) @@ -187,9 +196,7 @@ struct target_type { dm_status_fn status; dm_message_fn message; dm_prepare_ioctl_fn prepare_ioctl; -#ifdef CONFIG_BLK_DEV_ZONED dm_report_zones_fn report_zones; -#endif dm_busy_fn busy; dm_iterate_devices_fn iterate_devices; dm_io_hints_fn io_hints; @@ -248,8 +255,13 @@ struct target_type { /* * Indicates that a target supports host-managed zoned block devices. */ +#ifdef CONFIG_BLK_DEV_ZONED #define DM_TARGET_ZONED_HM 0x00000040 #define dm_target_supports_zoned_hm(type) ((type)->features & DM_TARGET_ZONED_HM) +#else +#define DM_TARGET_ZONED_HM 0x00000000 +#define dm_target_supports_zoned_hm(type) (false) +#endif /* * A target handles REQ_NOWAIT -- cgit v1.2.3 From a666e5c05e7c4aaabb2c5d58117b0946803d03d2 Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Wed, 10 Feb 2021 15:26:23 -0500 Subject: dm: fix deadlock when swapping to encrypted device The system would deadlock when swapping to a dm-crypt device. The reason is that for each incoming write bio, dm-crypt allocates memory that holds encrypted data. These excessive allocations exhaust all the memory and the result is either deadlock or OOM trigger. This patch limits the number of in-flight swap bios, so that the memory consumed by dm-crypt is limited. The limit is enforced if the target set the "limit_swap_bios" variable and if the bio has REQ_SWAP set. Non-swap bios are not affected becuase taking the semaphore would cause performance degradation. This is similar to request-based drivers - they will also block when the number of requests is over the limit. Signed-off-by: Mikulas Patocka Cc: stable@vger.kernel.org Signed-off-by: Mike Snitzer --- drivers/md/dm-core.h | 4 +++ drivers/md/dm-crypt.c | 1 + drivers/md/dm.c | 60 +++++++++++++++++++++++++++++++++++++++++++ include/linux/device-mapper.h | 5 ++++ 4 files changed, 70 insertions(+) (limited to 'include') diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h index bf3e66f39a4a..5953ff2bd260 100644 --- a/drivers/md/dm-core.h +++ b/drivers/md/dm-core.h @@ -103,6 +103,10 @@ struct mapped_device { /* kobject and completion */ struct dm_kobject_holder kobj_holder; + int swap_bios; + struct semaphore swap_bios_semaphore; + struct mutex swap_bios_lock; + struct dm_stats stats; /* for blk-mq request-based DM support */ diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index ae0f0a4e3689..11c105ecd165 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -3342,6 +3342,7 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) wake_up_process(cc->write_thread); ti->num_flush_bios = 1; + ti->limit_swap_bios = true; return 0; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 7021aea82aa4..50b693d776d6 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -153,6 +153,16 @@ EXPORT_SYMBOL_GPL(dm_bio_get_target_bio_nr); #define DM_NUMA_NODE NUMA_NO_NODE static int dm_numa_node = DM_NUMA_NODE; +#define DEFAULT_SWAP_BIOS (8 * 1048576 / PAGE_SIZE) +static int swap_bios = DEFAULT_SWAP_BIOS; +static int get_swap_bios(void) +{ + int latch = READ_ONCE(swap_bios); + if (unlikely(latch <= 0)) + latch = DEFAULT_SWAP_BIOS; + return latch; +} + /* * For mempools pre-allocation at the table loading time. */ @@ -974,6 +984,11 @@ void disable_write_zeroes(struct mapped_device *md) limits->max_write_zeroes_sectors = 0; } +static bool swap_bios_limit(struct dm_target *ti, struct bio *bio) +{ + return unlikely((bio->bi_opf & REQ_SWAP) != 0) && unlikely(ti->limit_swap_bios); +} + static void clone_endio(struct bio *bio) { blk_status_t error = bio->bi_status; @@ -1025,6 +1040,11 @@ static void clone_endio(struct bio *bio) } } + if (unlikely(swap_bios_limit(tio->ti, bio))) { + struct mapped_device *md = io->md; + up(&md->swap_bios_semaphore); + } + free_tio(tio); dec_pending(io, error); } @@ -1258,6 +1278,22 @@ void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors) } EXPORT_SYMBOL_GPL(dm_accept_partial_bio); +static noinline void __set_swap_bios_limit(struct mapped_device *md, int latch) +{ + mutex_lock(&md->swap_bios_lock); + while (latch < md->swap_bios) { + cond_resched(); + down(&md->swap_bios_semaphore); + md->swap_bios--; + } + while (latch > md->swap_bios) { + cond_resched(); + up(&md->swap_bios_semaphore); + md->swap_bios++; + } + mutex_unlock(&md->swap_bios_lock); +} + static blk_qc_t __map_bio(struct dm_target_io *tio) { int r; @@ -1277,6 +1313,14 @@ static blk_qc_t __map_bio(struct dm_target_io *tio) atomic_inc(&io->io_count); sector = clone->bi_iter.bi_sector; + if (unlikely(swap_bios_limit(ti, clone))) { + struct mapped_device *md = io->md; + int latch = get_swap_bios(); + if (unlikely(latch != md->swap_bios)) + __set_swap_bios_limit(md, latch); + down(&md->swap_bios_semaphore); + } + r = ti->type->map(ti, clone); switch (r) { case DM_MAPIO_SUBMITTED: @@ -1287,10 +1331,18 @@ static blk_qc_t __map_bio(struct dm_target_io *tio) ret = submit_bio_noacct(clone); break; case DM_MAPIO_KILL: + if (unlikely(swap_bios_limit(ti, clone))) { + struct mapped_device *md = io->md; + up(&md->swap_bios_semaphore); + } free_tio(tio); dec_pending(io, BLK_STS_IOERR); break; case DM_MAPIO_REQUEUE: + if (unlikely(swap_bios_limit(ti, clone))) { + struct mapped_device *md = io->md; + up(&md->swap_bios_semaphore); + } free_tio(tio); dec_pending(io, BLK_STS_DM_REQUEUE); break; @@ -1767,6 +1819,7 @@ static void cleanup_mapped_device(struct mapped_device *md) mutex_destroy(&md->suspend_lock); mutex_destroy(&md->type_lock); mutex_destroy(&md->table_devices_lock); + mutex_destroy(&md->swap_bios_lock); dm_mq_cleanup_mapped_device(md); } @@ -1834,6 +1887,10 @@ static struct mapped_device *alloc_dev(int minor) init_waitqueue_head(&md->eventq); init_completion(&md->kobj_holder.completion); + md->swap_bios = get_swap_bios(); + sema_init(&md->swap_bios_semaphore, md->swap_bios); + mutex_init(&md->swap_bios_lock); + md->disk->major = _major; md->disk->first_minor = minor; md->disk->fops = &dm_blk_dops; @@ -3117,6 +3174,9 @@ MODULE_PARM_DESC(reserved_bio_based_ios, "Reserved IOs in bio-based mempools"); module_param(dm_numa_node, int, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(dm_numa_node, "NUMA node for DM device memory allocations"); +module_param(swap_bios, int, S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(swap_bios, "Maximum allowed inflight swap IOs"); + MODULE_DESCRIPTION(DM_NAME " driver"); MODULE_AUTHOR("Joe Thornber "); MODULE_LICENSE("GPL"); diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index c98d847b0f0b..7f4ac87c0b32 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -343,6 +343,11 @@ struct dm_target { * whether or not its underlying devices have support. */ bool discards_supported:1; + + /* + * Set if we need to limit the number of in-flight bios when swapping. + */ + bool limit_swap_bios:1; }; void *dm_per_bio_data(struct bio *bio, size_t data_size); -- cgit v1.2.3 From 539cf68cd51bfcd2987ce1c44e628e9da69de7c8 Mon Sep 17 00:00:00 2001 From: Pratyush Yadav Date: Thu, 4 Feb 2021 19:42:17 +0530 Subject: spi: spi-mem: add spi_mem_dtr_supports_op() spi_mem_default_supports_op() rejects DTR ops by default to ensure that the controller drivers that haven't been updated with DTR support continue to reject them. It also makes sure that controllers that don't support DTR mode at all (which is most of them at the moment) also reject them. This means that controller drivers that want to support DTR mode can't use spi_mem_default_supports_op(). Driver authors have to roll their own supports_op() function and mimic the buswidth checks. See spi-cadence-quadspi.c for example. Or even worse, driver authors might skip it completely or get it wrong. Add spi_mem_dtr_supports_op(). It provides a basic sanity check for DTR ops and performs the buswidth requirement check. Move the logic for checking buswidth in spi_mem_default_supports_op() to a separate function so the logic is not repeated twice. Signed-off-by: Pratyush Yadav Reviewed-by: Miquel Raynal Link: https://lore.kernel.org/r/20210204141218.32229-1-p.yadav@ti.com Signed-off-by: Mark Brown --- drivers/spi/spi-mem.c | 22 +++++++++++++++++++--- include/linux/spi/spi-mem.h | 9 +++++++++ 2 files changed, 28 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/spi/spi-mem.c b/drivers/spi/spi-mem.c index c64371ce6c38..dc713b0c3c4d 100644 --- a/drivers/spi/spi-mem.c +++ b/drivers/spi/spi-mem.c @@ -137,8 +137,8 @@ static int spi_check_buswidth_req(struct spi_mem *mem, u8 buswidth, bool tx) return -ENOTSUPP; } -bool spi_mem_default_supports_op(struct spi_mem *mem, - const struct spi_mem_op *op) +static bool spi_mem_check_buswidth(struct spi_mem *mem, + const struct spi_mem_op *op) { if (spi_check_buswidth_req(mem, op->cmd.buswidth, true)) return false; @@ -156,13 +156,29 @@ bool spi_mem_default_supports_op(struct spi_mem *mem, op->data.dir == SPI_MEM_DATA_OUT)) return false; + return true; +} + +bool spi_mem_dtr_supports_op(struct spi_mem *mem, + const struct spi_mem_op *op) +{ + if (op->cmd.nbytes != 2) + return false; + + return spi_mem_check_buswidth(mem, op); +} +EXPORT_SYMBOL_GPL(spi_mem_dtr_supports_op); + +bool spi_mem_default_supports_op(struct spi_mem *mem, + const struct spi_mem_op *op) +{ if (op->cmd.dtr || op->addr.dtr || op->dummy.dtr || op->data.dtr) return false; if (op->cmd.nbytes != 1) return false; - return true; + return spi_mem_check_buswidth(mem, op); } EXPORT_SYMBOL_GPL(spi_mem_default_supports_op); diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h index 159463cc659c..2b65c9edc34e 100644 --- a/include/linux/spi/spi-mem.h +++ b/include/linux/spi/spi-mem.h @@ -311,6 +311,9 @@ void spi_controller_dma_unmap_mem_op_data(struct spi_controller *ctlr, bool spi_mem_default_supports_op(struct spi_mem *mem, const struct spi_mem_op *op); +bool spi_mem_dtr_supports_op(struct spi_mem *mem, + const struct spi_mem_op *op); + #else static inline int spi_controller_dma_map_mem_op_data(struct spi_controller *ctlr, @@ -334,6 +337,12 @@ bool spi_mem_default_supports_op(struct spi_mem *mem, return false; } +static inline +bool spi_mem_dtr_supports_op(struct spi_mem *mem, + const struct spi_mem_op *op) +{ + return false; +} #endif /* CONFIG_SPI_MEM */ int spi_mem_adjust_op_size(struct spi_mem *mem, struct spi_mem_op *op); -- cgit v1.2.3 From 53abf3fe831756261f399dad03ccc07235296acf Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Thu, 11 Feb 2021 10:20:36 -0700 Subject: coresight: etm-perf: Clarify comment on perf options In theory, the options should be arbitrary values and are neutral for any ETM version; so far perf tool uses ETMv3.5/PTM ETMCR config bits except for register's bit definitions, also uses as options. This can introduce confusion, especially if we want to add a new option but the new option is not supported by ETMv3.5/PTM ETMCR. But on the other hand, we cannot change options since these options are generic CoreSight PMU ABI. For easier maintenance and avoid confusion, this patch refines the comment to clarify perf options, and gives out the background info for these bits are coming from ETMv3.5/PTM. Afterwards, we should take these options as general knobs, and if there have any confliction with ETMv3.5/PTM, should consider to define saperate macros for ETMv3.5/PTM ETMCR config bits. Suggested-by: Suzuki K Poulose Reviewed-by: Suzuki K Poulose Signed-off-by: Leo Yan Signed-off-by: Mathieu Poirier Link: https://lore.kernel.org/r/20210206150833.42120-2-leo.yan@linaro.org Link: https://lore.kernel.org/r/20210211172038.2483517-2-mathieu.poirier@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/coresight/coresight-etm-perf.c | 5 ++++- include/linux/coresight-pmu.h | 17 ++++++++++++----- 2 files changed, 16 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c index bdc34ca449f7..465ef1aa8c82 100644 --- a/drivers/hwtracing/coresight/coresight-etm-perf.c +++ b/drivers/hwtracing/coresight/coresight-etm-perf.c @@ -27,7 +27,10 @@ static bool etm_perf_up; static DEFINE_PER_CPU(struct perf_output_handle, ctx_handle); static DEFINE_PER_CPU(struct coresight_device *, csdev_src); -/* ETMv3.5/PTM's ETMCR is 'config' */ +/* + * The PMU formats were orignally for ETMv3.5/PTM's ETMCR 'config'; + * now take them as general formats and apply on all ETMs. + */ PMU_FORMAT_ATTR(cycacc, "config:" __stringify(ETM_OPT_CYCACC)); PMU_FORMAT_ATTR(contextid, "config:" __stringify(ETM_OPT_CTXTID)); PMU_FORMAT_ATTR(timestamp, "config:" __stringify(ETM_OPT_TS)); diff --git a/include/linux/coresight-pmu.h b/include/linux/coresight-pmu.h index b0e35eec6499..5dc47cfdcf07 100644 --- a/include/linux/coresight-pmu.h +++ b/include/linux/coresight-pmu.h @@ -10,11 +10,18 @@ #define CORESIGHT_ETM_PMU_NAME "cs_etm" #define CORESIGHT_ETM_PMU_SEED 0x10 -/* ETMv3.5/PTM's ETMCR config bit */ -#define ETM_OPT_CYCACC 12 -#define ETM_OPT_CTXTID 14 -#define ETM_OPT_TS 28 -#define ETM_OPT_RETSTK 29 +/* + * Below are the definition of bit offsets for perf option, and works as + * arbitrary values for all ETM versions. + * + * Most of them are orignally from ETMv3.5/PTM's ETMCR config, therefore, + * ETMv3.5/PTM doesn't define ETMCR config bits with prefix "ETM3_" and + * directly use below macros as config bits. + */ +#define ETM_OPT_CYCACC 12 +#define ETM_OPT_CTXTID 14 +#define ETM_OPT_TS 28 +#define ETM_OPT_RETSTK 29 /* ETMv4 CONFIGR programming bits for the ETM OPTs */ #define ETM4_CFG_BIT_CYCACC 4 -- cgit v1.2.3 From 88f11864cf1d1324f620059ec747d74b72d9d736 Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Thu, 11 Feb 2021 10:20:37 -0700 Subject: coresight: etm-perf: Support PID tracing for kernel at EL2 When the kernel is running at EL2, the PID is stored in CONTEXTIDR_EL2. So, tracing CONTEXTIDR_EL1 doesn't give us the pid of the process. Thus we should trace the VMID with VMIDOPT set to trace CONTEXTIDR_EL2 instead of CONTEXTIDR_EL1. Given that we have an existing config option "contextid" and this will be useful for tracing virtual machines (when we get to support virtualization). So instead, this patch extends option CTXTID with an extra bit ETM_OPT_CTXTID2 (bit 15), thus on an EL2 kernel, we will have another bit available for the perf tool: ETM_OPT_CTXTID is for kernel running in EL1, ETM_OPT_CTXTID2 is used when kernel runs in EL2 with VHE enabled. The tool must be backward compatible for users, i.e, "contextid" today traces PID and that should remain the same; for this purpose, the perf tool is updated to automatically set corresponding bit for the "contextid" config, therefore, the user doesn't have to bother which EL the kernel is running. i.e, perf record -e cs_etm/contextid/u -- will always do the "pid" tracing, independent of the kernel EL. The driver parses the format "contextid", which traces CONTEXTIDR_EL1 for ETM_OPT_CTXTID (on EL1 kernel) and traces CONTEXTIDR_EL2 for ETM_OPT_CTXTID2 (on EL2 kernel). Besides the enhancement for format "contexid", extra two formats are introduced: "contextid1" and "contextid2". This considers to support tracing both CONTEXTIDR_EL1 and CONTEXTIDR_EL2 when the kernel is running at EL2. Finally, the PMU formats are defined as follow: "contextid1": Available on both EL1 kernel and EL2 kernel. When the kernel is running at EL1, "contextid1" enables the PID tracing; when the kernel is running at EL2, this enables tracing the PID of guest applications. "contextid2": Only usable when the kernel is running at EL2. When selected, enables PID tracing on EL2 kernel. "contextid": Will be an alias for the option that enables PID tracing. I.e, contextid == contextid1, on EL1 kernel. contextid == contextid2, on EL2 kernel. Cc: Mathieu Poirier Cc: Al Grant Cc: Mike Leach Cc: Leo Yan Reviewed-by: Mike Leach Signed-off-by: Suzuki K Poulose [ Added two config formats: contextid1, contextid2 ] Signed-off-by: Leo Yan Signed-off-by: Mathieu Poirier Link: https://lore.kernel.org/r/20210206150833.42120-4-leo.yan@linaro.org Link: https://lore.kernel.org/r/20210211172038.2483517-3-mathieu.poirier@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/coresight/coresight-etm-perf.c | 27 +++++++++++++++++++++- drivers/hwtracing/coresight/coresight-etm4x-core.c | 13 +++++++++++ include/linux/coresight-pmu.h | 3 +++ 3 files changed, 42 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c index 465ef1aa8c82..0f603b4094f2 100644 --- a/drivers/hwtracing/coresight/coresight-etm-perf.c +++ b/drivers/hwtracing/coresight/coresight-etm-perf.c @@ -32,15 +32,40 @@ static DEFINE_PER_CPU(struct coresight_device *, csdev_src); * now take them as general formats and apply on all ETMs. */ PMU_FORMAT_ATTR(cycacc, "config:" __stringify(ETM_OPT_CYCACC)); -PMU_FORMAT_ATTR(contextid, "config:" __stringify(ETM_OPT_CTXTID)); +/* contextid1 enables tracing CONTEXTIDR_EL1 for ETMv4 */ +PMU_FORMAT_ATTR(contextid1, "config:" __stringify(ETM_OPT_CTXTID)); +/* contextid2 enables tracing CONTEXTIDR_EL2 for ETMv4 */ +PMU_FORMAT_ATTR(contextid2, "config:" __stringify(ETM_OPT_CTXTID2)); PMU_FORMAT_ATTR(timestamp, "config:" __stringify(ETM_OPT_TS)); PMU_FORMAT_ATTR(retstack, "config:" __stringify(ETM_OPT_RETSTK)); /* Sink ID - same for all ETMs */ PMU_FORMAT_ATTR(sinkid, "config2:0-31"); +/* + * contextid always traces the "PID". The PID is in CONTEXTIDR_EL1 + * when the kernel is running at EL1; when the kernel is at EL2, + * the PID is in CONTEXTIDR_EL2. + */ +static ssize_t format_attr_contextid_show(struct device *dev, + struct device_attribute *attr, + char *page) +{ + int pid_fmt = ETM_OPT_CTXTID; + +#if defined(CONFIG_CORESIGHT_SOURCE_ETM4X) + pid_fmt = is_kernel_in_hyp_mode() ? ETM_OPT_CTXTID2 : ETM_OPT_CTXTID; +#endif + return sprintf(page, "config:%d\n", pid_fmt); +} + +struct device_attribute format_attr_contextid = + __ATTR(contextid, 0444, format_attr_contextid_show, NULL); + static struct attribute *etm_config_formats_attr[] = { &format_attr_cycacc.attr, &format_attr_contextid.attr, + &format_attr_contextid1.attr, + &format_attr_contextid2.attr, &format_attr_timestamp.attr, &format_attr_retstack.attr, &format_attr_sinkid.attr, diff --git a/drivers/hwtracing/coresight/coresight-etm4x-core.c b/drivers/hwtracing/coresight/coresight-etm4x-core.c index c8ecd91e289e..15016f757828 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x-core.c +++ b/drivers/hwtracing/coresight/coresight-etm4x-core.c @@ -550,6 +550,19 @@ static int etm4_parse_event_config(struct etmv4_drvdata *drvdata, /* bit[6], Context ID tracing bit */ config->cfg |= BIT(ETM4_CFG_BIT_CTXTID); + /* + * If set bit ETM_OPT_CTXTID2 in perf config, this asks to trace VMID + * for recording CONTEXTIDR_EL2. Do not enable VMID tracing if the + * kernel is not running in EL2. + */ + if (attr->config & BIT(ETM_OPT_CTXTID2)) { + if (!is_kernel_in_hyp_mode()) { + ret = -EINVAL; + goto out; + } + config->cfg |= BIT(ETM4_CFG_BIT_VMID) | BIT(ETM4_CFG_BIT_VMID_OPT); + } + /* return stack - enable if selected and supported */ if ((attr->config & BIT(ETM_OPT_RETSTK)) && drvdata->retstack) /* bit[12], Return stack enable bit */ diff --git a/include/linux/coresight-pmu.h b/include/linux/coresight-pmu.h index 5dc47cfdcf07..4ac5c081af93 100644 --- a/include/linux/coresight-pmu.h +++ b/include/linux/coresight-pmu.h @@ -20,14 +20,17 @@ */ #define ETM_OPT_CYCACC 12 #define ETM_OPT_CTXTID 14 +#define ETM_OPT_CTXTID2 15 #define ETM_OPT_TS 28 #define ETM_OPT_RETSTK 29 /* ETMv4 CONFIGR programming bits for the ETM OPTs */ #define ETM4_CFG_BIT_CYCACC 4 #define ETM4_CFG_BIT_CTXTID 6 +#define ETM4_CFG_BIT_VMID 7 #define ETM4_CFG_BIT_TS 11 #define ETM4_CFG_BIT_RETSTK 12 +#define ETM4_CFG_BIT_VMID_OPT 15 static inline int coresight_get_trace_id(int cpu) { -- cgit v1.2.3 From f2ad937b62d984fd1ede3994798fe39f5fabc8d7 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Tue, 26 Jan 2021 12:45:38 +0000 Subject: clk: spear: Move prototype to accessible header MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fixes the following W=1 kernel build warning(s): drivers/clk/spear/spear1310_clock.c:385:13: warning: no previous prototype for ‘spear1310_clk_init’ [-Wmissing-prototypes] drivers/clk/spear/spear1340_clock.c:442:13: warning: no previous prototype for ‘spear1340_clk_init’ [-Wmissing-prototypes] Cc: Viresh Kumar Cc: Shiraz Hashim Cc: Russell King Cc: Rajeev Kumar Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20210126124540.3320214-20-lee.jones@linaro.org Acked-by: Viresh Kumar Signed-off-by: Stephen Boyd --- arch/arm/mach-spear/generic.h | 12 ------------ arch/arm/mach-spear/spear13xx.c | 1 + drivers/clk/spear/spear1310_clock.c | 1 + drivers/clk/spear/spear1340_clock.c | 1 + include/linux/clk/spear.h | 23 +++++++++++++++++++++++ 5 files changed, 26 insertions(+), 12 deletions(-) create mode 100644 include/linux/clk/spear.h (limited to 'include') diff --git a/arch/arm/mach-spear/generic.h b/arch/arm/mach-spear/generic.h index 25b4c5e66e39..8ec2b92dca19 100644 --- a/arch/arm/mach-spear/generic.h +++ b/arch/arm/mach-spear/generic.h @@ -43,16 +43,4 @@ void spear13xx_cpu_die(unsigned int cpu); extern const struct smp_operations spear13xx_smp_ops; -#ifdef CONFIG_MACH_SPEAR1310 -void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base); -#else -static inline void spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base) {} -#endif - -#ifdef CONFIG_MACH_SPEAR1340 -void __init spear1340_clk_init(void __iomem *misc_base); -#else -static inline void spear1340_clk_init(void __iomem *misc_base) {} -#endif - #endif /* __MACH_GENERIC_H */ diff --git a/arch/arm/mach-spear/spear13xx.c b/arch/arm/mach-spear/spear13xx.c index 31c43cabf362..74d1ca2a529a 100644 --- a/arch/arm/mach-spear/spear13xx.c +++ b/arch/arm/mach-spear/spear13xx.c @@ -15,6 +15,7 @@ #include #include +#include #include #include #include diff --git a/drivers/clk/spear/spear1310_clock.c b/drivers/clk/spear/spear1310_clock.c index 591248c9a88e..8c8974866789 100644 --- a/drivers/clk/spear/spear1310_clock.c +++ b/drivers/clk/spear/spear1310_clock.c @@ -12,6 +12,7 @@ */ #include +#include #include #include #include diff --git a/drivers/clk/spear/spear1340_clock.c b/drivers/clk/spear/spear1340_clock.c index 9163bbb46411..c0dc94355c87 100644 --- a/drivers/clk/spear/spear1340_clock.c +++ b/drivers/clk/spear/spear1340_clock.c @@ -12,6 +12,7 @@ */ #include +#include #include #include #include diff --git a/include/linux/clk/spear.h b/include/linux/clk/spear.h new file mode 100644 index 000000000000..a64d034ceddd --- /dev/null +++ b/include/linux/clk/spear.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2020 STMicroelectronics - All Rights Reserved + * + * Author: Lee Jones + */ + +#ifndef __LINUX_CLK_SPEAR_H +#define __LINUX_CLK_SPEAR_H + +#ifdef CONFIG_MACH_SPEAR1310 +void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base); +#else +static inline void spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base) {} +#endif + +#ifdef CONFIG_MACH_SPEAR1340 +void __init spear1340_clk_init(void __iomem *misc_base); +#else +static inline void spear1340_clk_init(void __iomem *misc_base) {} +#endif + +#endif -- cgit v1.2.3 From efbbdaa22bb78761bff8dfdde027ad04bedd47ce Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 15 Oct 2020 23:55:07 +0900 Subject: tracing: Show real address for trace event arguments To help debugging kernel, show real address for trace event arguments in tracefs/trace{,pipe} instead of hashed pointer value. Since ftrace human-readable format uses vsprintf(), all %p are translated to hash values instead of pointer address. However, when debugging the kernel, raw address value gives a hint when comparing with the memory mapping in the kernel. (Those are sometimes used with crash log, which is not hashed too) So converting %p with %px when calling trace_seq_printf(). Moreover, this is not improving the security because the tracefs can be used only by root user and the raw address values are readable from tracefs/percpu/cpu*/trace_pipe_raw file. Link: https://lkml.kernel.org/r/160277370703.29307.5134475491761971203.stgit@devnote2 Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_events.h | 4 +++ include/trace/trace_events.h | 2 +- kernel/trace/trace.c | 71 +++++++++++++++++++++++++++++++++++++++++++- kernel/trace/trace.h | 2 ++ kernel/trace/trace_output.c | 12 +++++++- 5 files changed, 88 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 5d1eeac4bfbe..7077fec653bb 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -55,6 +55,8 @@ struct trace_event; int trace_raw_output_prep(struct trace_iterator *iter, struct trace_event *event); +extern __printf(2, 3) +void trace_event_printf(struct trace_iterator *iter, const char *fmt, ...); /* * The trace entry - the most basic unit of tracing. This is what @@ -87,6 +89,8 @@ struct trace_iterator { unsigned long iter_flags; void *temp; /* temp holder */ unsigned int temp_size; + char *fmt; /* modified format holder */ + unsigned int fmt_size; /* trace_seq for __print_flags() and __print_symbolic() etc. */ struct trace_seq tmp_seq; diff --git a/include/trace/trace_events.h b/include/trace/trace_events.h index 7785961d82ba..e6a8b3febc49 100644 --- a/include/trace/trace_events.h +++ b/include/trace/trace_events.h @@ -364,7 +364,7 @@ trace_raw_output_##call(struct trace_iterator *iter, int flags, \ if (ret != TRACE_TYPE_HANDLED) \ return ret; \ \ - trace_seq_printf(s, print); \ + trace_event_printf(iter, print); \ \ return trace_handle_return(s); \ } \ diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index b79bcacdd6f9..39f8a537196e 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3530,6 +3530,62 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, return next; } +#define STATIC_FMT_BUF_SIZE 128 +static char static_fmt_buf[STATIC_FMT_BUF_SIZE]; + +static char *trace_iter_expand_format(struct trace_iterator *iter) +{ + char *tmp; + + if (iter->fmt == static_fmt_buf) + return NULL; + + tmp = krealloc(iter->fmt, iter->fmt_size + STATIC_FMT_BUF_SIZE, + GFP_KERNEL); + if (tmp) { + iter->fmt_size += STATIC_FMT_BUF_SIZE; + iter->fmt = tmp; + } + + return tmp; +} + +const char *trace_event_format(struct trace_iterator *iter, const char *fmt) +{ + const char *p, *new_fmt; + char *q; + + if (WARN_ON_ONCE(!fmt)) + return fmt; + + p = fmt; + new_fmt = q = iter->fmt; + while (*p) { + if (unlikely(q - new_fmt + 3 > iter->fmt_size)) { + if (!trace_iter_expand_format(iter)) + return fmt; + + q += iter->fmt - new_fmt; + new_fmt = iter->fmt; + } + + *q++ = *p++; + + /* Replace %p with %px */ + if (p[-1] == '%') { + if (p[0] == '%') { + *q++ = *p++; + } else if (p[0] == 'p' && !isalnum(p[1])) { + *q++ = *p++; + *q++ = 'x'; + } + } + } + *q = '\0'; + + return new_fmt; +} + #define STATIC_TEMP_BUF_SIZE 128 static char static_temp_buf[STATIC_TEMP_BUF_SIZE] __aligned(4); @@ -4322,6 +4378,16 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot) if (iter->temp) iter->temp_size = 128; + /* + * trace_event_printf() may need to modify given format + * string to replace %p with %px so that it shows real address + * instead of hash value. However, that is only for the event + * tracing, other tracer may not need. Defer the allocation + * until it is needed. + */ + iter->fmt = NULL; + iter->fmt_size = 0; + /* * We make a copy of the current tracer to avoid concurrent * changes on it while we are reading. @@ -4473,6 +4539,7 @@ static int tracing_release(struct inode *inode, struct file *file) mutex_destroy(&iter->mutex); free_cpumask_var(iter->started); + kfree(iter->fmt); kfree(iter->temp); kfree(iter->trace); kfree(iter->buffer_iter); @@ -9331,9 +9398,11 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) /* Simulate the iterator */ trace_init_global_iter(&iter); - /* Can not use kmalloc for iter.temp */ + /* Can not use kmalloc for iter.temp and iter.fmt */ iter.temp = static_temp_buf; iter.temp_size = STATIC_TEMP_BUF_SIZE; + iter.fmt = static_fmt_buf; + iter.fmt_size = STATIC_FMT_BUF_SIZE; for_each_tracing_cpu(cpu) { atomic_inc(&per_cpu_ptr(iter.array_buffer->data, cpu)->disabled); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index a9e13bd5a41b..6c3ea6f95e68 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -581,6 +581,8 @@ struct trace_entry *trace_find_next_entry(struct trace_iterator *iter, void trace_buffer_unlock_commit_nostack(struct trace_buffer *buffer, struct ring_buffer_event *event); +const char *trace_event_format(struct trace_iterator *iter, const char *fmt); + int trace_empty(struct trace_iterator *iter); void *trace_find_next_entry_inc(struct trace_iterator *iter); diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 92b1575ae0ca..61255bad7e01 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -312,13 +312,23 @@ int trace_raw_output_prep(struct trace_iterator *iter, } EXPORT_SYMBOL(trace_raw_output_prep); +void trace_event_printf(struct trace_iterator *iter, const char *fmt, ...) +{ + va_list ap; + + va_start(ap, fmt); + trace_seq_vprintf(&iter->seq, trace_event_format(iter, fmt), ap); + va_end(ap); +} +EXPORT_SYMBOL(trace_event_printf); + static int trace_output_raw(struct trace_iterator *iter, char *name, char *fmt, va_list ap) { struct trace_seq *s = &iter->seq; trace_seq_printf(s, "%s: ", name); - trace_seq_vprintf(s, fmt, ap); + trace_seq_vprintf(s, trace_event_format(iter, fmt), ap); return trace_handle_return(s); } -- cgit v1.2.3 From 1600cbcf6944dee9f87f52cbceb0b6895c29efd0 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 15 Oct 2020 23:55:16 +0900 Subject: tracing: Update the stage 3 of trace event macro comment Update the comment of the 3rd stage of trace event macro expansion code. Now there are 2 macros makes different trace_raw_output_() functions. Link: https://lkml.kernel.org/r/160277371605.29307.8586817119278606720.stgit@devnote2 Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/trace/trace_events.h | 29 ++++++++++++++++++++--------- 1 file changed, 20 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/trace/trace_events.h b/include/trace/trace_events.h index e6a8b3febc49..8268bf747d6f 100644 --- a/include/trace/trace_events.h +++ b/include/trace/trace_events.h @@ -231,9 +231,11 @@ TRACE_MAKE_SYSTEM_STR(); * { * struct trace_seq *s = &iter->seq; * struct trace_event_raw_ *field; <-- defined in stage 1 - * struct trace_entry *entry; * struct trace_seq *p = &iter->tmp_seq; - * int ret; + * + * -------(for event)------- + * + * struct trace_entry *entry; * * entry = iter->ent; * @@ -245,14 +247,23 @@ TRACE_MAKE_SYSTEM_STR(); * field = (typeof(field))entry; * * trace_seq_init(p); - * ret = trace_seq_printf(s, "%s: ", ); - * if (ret) - * ret = trace_seq_printf(s, "\n"); - * if (!ret) - * return TRACE_TYPE_PARTIAL_LINE; + * return trace_output_call(iter, , "\n"); * - * return TRACE_TYPE_HANDLED; - * } + * ------(or, for event class)------ + * + * int ret; + * + * field = (typeof(field))iter->ent; + * + * ret = trace_raw_output_prep(iter, trace_event); + * if (ret != TRACE_TYPE_HANDLED) + * return ret; + * + * trace_event_printf(iter, "\n"); + * + * return trace_handle_return(s); + * ------- + * } * * This is the method used to print the raw event to the trace * output format. Note, this is not needed if the data is read -- cgit v1.2.3 From c294554111a835598b557db789d9ad2379b512a2 Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Fri, 12 Feb 2021 10:00:23 +0200 Subject: regulator: bd718x7, bd71828, Fix dvs voltage levels The ROHM BD718x7 and BD71828 drivers support setting HW state specific voltages from device-tree. This is used also by various in-tree DTS files. These drivers do incorrectly try to compose bit-map using enum values. By a chance this works for first two valid levels having values 1 and 2 - but setting values for the rest of the levels do indicate capability of setting values for first levels as well. Luckily the regulators which support setting values for SUSPEND/LPSR do usually also support setting values for RUN and IDLE too - thus this has not been such a fatal issue. Fix this by defining the old enum values as bits and fixing the parsing code. This allows keeping existing IC specific drivers intact and only slightly changing the rohm-regulator.c Fixes: 21b72156ede8b ("regulator: bd718x7: Split driver to common and bd718x7 specific parts") Signed-off-by: Matti Vaittinen Acked-by: Lee Jones Link: https://lore.kernel.org/r/20210212080023.GA880728@localhost.localdomain Signed-off-by: Mark Brown --- drivers/regulator/rohm-regulator.c | 9 ++++++--- include/linux/mfd/rohm-generic.h | 14 ++++++-------- 2 files changed, 12 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/drivers/regulator/rohm-regulator.c b/drivers/regulator/rohm-regulator.c index 399002383b28..5c558b153d55 100644 --- a/drivers/regulator/rohm-regulator.c +++ b/drivers/regulator/rohm-regulator.c @@ -52,9 +52,12 @@ int rohm_regulator_set_dvs_levels(const struct rohm_dvs_config *dvs, char *prop; unsigned int reg, mask, omask, oreg = desc->enable_reg; - for (i = 0; i < ROHM_DVS_LEVEL_MAX && !ret; i++) { - if (dvs->level_map & (1 << i)) { - switch (i + 1) { + for (i = 0; i < ROHM_DVS_LEVEL_VALID_AMOUNT && !ret; i++) { + int bit; + + bit = BIT(i); + if (dvs->level_map & bit) { + switch (bit) { case ROHM_DVS_LEVEL_RUN: prop = "rohm,dvs-run-voltage"; reg = dvs->run_reg; diff --git a/include/linux/mfd/rohm-generic.h b/include/linux/mfd/rohm-generic.h index 4283b5b33e04..2b85b9deb03a 100644 --- a/include/linux/mfd/rohm-generic.h +++ b/include/linux/mfd/rohm-generic.h @@ -20,14 +20,12 @@ struct rohm_regmap_dev { struct regmap *regmap; }; -enum { - ROHM_DVS_LEVEL_UNKNOWN, - ROHM_DVS_LEVEL_RUN, - ROHM_DVS_LEVEL_IDLE, - ROHM_DVS_LEVEL_SUSPEND, - ROHM_DVS_LEVEL_LPSR, - ROHM_DVS_LEVEL_MAX = ROHM_DVS_LEVEL_LPSR, -}; +#define ROHM_DVS_LEVEL_RUN BIT(0) +#define ROHM_DVS_LEVEL_IDLE BIT(1) +#define ROHM_DVS_LEVEL_SUSPEND BIT(2) +#define ROHM_DVS_LEVEL_LPSR BIT(3) +#define ROHM_DVS_LEVEL_VALID_AMOUNT 4 +#define ROHM_DVS_LEVEL_UNKNOWN 0 /** * struct rohm_dvs_config - dynamic voltage scaling register descriptions -- cgit v1.2.3 From f9ab49184af093f0bf6c0e6583f5b25da2c09ff5 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Sat, 23 Jan 2021 21:10:27 +0100 Subject: blk-mq: Use llist_head for blk_cpu_done With llist_head it is possible to avoid the locking (the irq-off region) when items are added. This makes it possible to add items on a remote CPU without additional locking. llist_add() returns true if the list was previously empty. This can be used to invoke the SMP function call / raise sofirq only if the first item was added (otherwise it is already pending). This simplifies the code a little and reduces the IRQ-off regions. blk_mq_raise_softirq() needs a preempt-disable section to ensure the request is enqueued on the same CPU as the softirq is raised. Some callers (USB-storage) invoke this path in preemptible context. Reviewed-by: Christoph Hellwig Reviewed-by: Daniel Wagner Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Jens Axboe --- block/blk-mq.c | 97 +++++++++++++++++++++----------------------------- include/linux/blkdev.h | 2 +- 2 files changed, 42 insertions(+), 57 deletions(-) (limited to 'include') diff --git a/block/blk-mq.c b/block/blk-mq.c index 90348ae51846..463de2981df8 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -41,7 +41,7 @@ #include "blk-mq-sched.h" #include "blk-rq-qos.h" -static DEFINE_PER_CPU(struct list_head, blk_cpu_done); +static DEFINE_PER_CPU(struct llist_head, blk_cpu_done); static void blk_mq_poll_stats_start(struct request_queue *q); static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb); @@ -567,68 +567,29 @@ void blk_mq_end_request(struct request *rq, blk_status_t error) } EXPORT_SYMBOL(blk_mq_end_request); -/* - * Softirq action handler - move entries to local list and loop over them - * while passing them to the queue registered handler. - */ -static __latent_entropy void blk_done_softirq(struct softirq_action *h) +static void blk_complete_reqs(struct llist_head *list) { - struct list_head *cpu_list, local_list; - - local_irq_disable(); - cpu_list = this_cpu_ptr(&blk_cpu_done); - list_replace_init(cpu_list, &local_list); - local_irq_enable(); - - while (!list_empty(&local_list)) { - struct request *rq; + struct llist_node *entry = llist_reverse_order(llist_del_all(list)); + struct request *rq, *next; - rq = list_entry(local_list.next, struct request, ipi_list); - list_del_init(&rq->ipi_list); + llist_for_each_entry_safe(rq, next, entry, ipi_list) rq->q->mq_ops->complete(rq); - } } -static void blk_mq_trigger_softirq(struct request *rq) +static __latent_entropy void blk_done_softirq(struct softirq_action *h) { - struct list_head *list; - unsigned long flags; - - local_irq_save(flags); - list = this_cpu_ptr(&blk_cpu_done); - list_add_tail(&rq->ipi_list, list); - - /* - * If the list only contains our just added request, signal a raise of - * the softirq. If there are already entries there, someone already - * raised the irq but it hasn't run yet. - */ - if (list->next == &rq->ipi_list) - raise_softirq_irqoff(BLOCK_SOFTIRQ); - local_irq_restore(flags); + blk_complete_reqs(this_cpu_ptr(&blk_cpu_done)); } static int blk_softirq_cpu_dead(unsigned int cpu) { - /* - * If a CPU goes away, splice its entries to the current CPU - * and trigger a run of the softirq - */ - local_irq_disable(); - list_splice_init(&per_cpu(blk_cpu_done, cpu), - this_cpu_ptr(&blk_cpu_done)); - raise_softirq_irqoff(BLOCK_SOFTIRQ); - local_irq_enable(); - + blk_complete_reqs(&per_cpu(blk_cpu_done, cpu)); return 0; } - static void __blk_mq_complete_request_remote(void *data) { - struct request *rq = data; - - blk_mq_trigger_softirq(rq); + __raise_softirq_irqoff(BLOCK_SOFTIRQ); } static inline bool blk_mq_complete_need_ipi(struct request *rq) @@ -657,6 +618,30 @@ static inline bool blk_mq_complete_need_ipi(struct request *rq) return cpu_online(rq->mq_ctx->cpu); } +static void blk_mq_complete_send_ipi(struct request *rq) +{ + struct llist_head *list; + unsigned int cpu; + + cpu = rq->mq_ctx->cpu; + list = &per_cpu(blk_cpu_done, cpu); + if (llist_add(&rq->ipi_list, list)) { + INIT_CSD(&rq->csd, __blk_mq_complete_request_remote, rq); + smp_call_function_single_async(cpu, &rq->csd); + } +} + +static void blk_mq_raise_softirq(struct request *rq) +{ + struct llist_head *list; + + preempt_disable(); + list = this_cpu_ptr(&blk_cpu_done); + if (llist_add(&rq->ipi_list, list)) + raise_softirq(BLOCK_SOFTIRQ); + preempt_enable(); +} + bool blk_mq_complete_request_remote(struct request *rq) { WRITE_ONCE(rq->state, MQ_RQ_COMPLETE); @@ -669,15 +654,15 @@ bool blk_mq_complete_request_remote(struct request *rq) return false; if (blk_mq_complete_need_ipi(rq)) { - INIT_CSD(&rq->csd, __blk_mq_complete_request_remote, rq); - smp_call_function_single_async(rq->mq_ctx->cpu, &rq->csd); - } else { - if (rq->q->nr_hw_queues > 1) - return false; - blk_mq_trigger_softirq(rq); + blk_mq_complete_send_ipi(rq); + return true; } - return true; + if (rq->q->nr_hw_queues == 1) { + blk_mq_raise_softirq(rq); + return true; + } + return false; } EXPORT_SYMBOL_GPL(blk_mq_complete_request_remote); @@ -3892,7 +3877,7 @@ static int __init blk_mq_init(void) int i; for_each_possible_cpu(i) - INIT_LIST_HEAD(&per_cpu(blk_cpu_done, i)); + init_llist_head(&per_cpu(blk_cpu_done, i)); open_softirq(BLOCK_SOFTIRQ, blk_done_softirq); cpuhp_setup_state_nocalls(CPUHP_BLOCK_SOFTIRQ_DEAD, diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f94ee3089e01..89a444c5a583 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -153,7 +153,7 @@ struct request { */ union { struct hlist_node hash; /* merge hash */ - struct list_head ipi_list; + struct llist_node ipi_list; }; /* -- cgit v1.2.3 From 83c4a4eec06a8fc46fc68c437424f9c89e4d9c72 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Thu, 11 Feb 2021 17:27:44 -0600 Subject: of: Remove of_dev_{get,put}() of_dev_get() and of_dev_put are just wrappers for get_device()/put_device() on a platform_device. There's also already platform_device_{get,put}() wrappers for this purpose. Let's update the few users and remove of_dev_{get,put}(). Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: "David S. Miller" Cc: Jakub Kicinski Cc: Frank Rowand Cc: Patrice Chotard Cc: Felipe Balbi Cc: Julia Lawall Cc: Gilles Muller Cc: Nicolas Palix Cc: Michal Marek Cc: linuxppc-dev@lists.ozlabs.org Cc: netdev@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-usb@vger.kernel.org Cc: cocci@systeme.lip6.fr Signed-off-by: Rob Herring Reviewed-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20210211232745.1498137-2-robh@kernel.org --- arch/powerpc/platforms/pseries/ibmebus.c | 4 ++-- drivers/net/ethernet/ibm/emac/core.c | 15 ++++++++------- drivers/of/device.c | 21 --------------------- drivers/of/platform.c | 4 ++-- drivers/of/unittest.c | 2 +- drivers/usb/dwc3/dwc3-st.c | 2 +- include/linux/of_device.h | 3 --- scripts/coccinelle/free/put_device.cocci | 1 - 8 files changed, 14 insertions(+), 38 deletions(-) (limited to 'include') diff --git a/arch/powerpc/platforms/pseries/ibmebus.c b/arch/powerpc/platforms/pseries/ibmebus.c index 8c6e509f6967..a15ab33646b3 100644 --- a/arch/powerpc/platforms/pseries/ibmebus.c +++ b/arch/powerpc/platforms/pseries/ibmebus.c @@ -355,12 +355,12 @@ static int ibmebus_bus_device_probe(struct device *dev) if (!drv->probe) return error; - of_dev_get(of_dev); + get_device(dev); if (of_driver_match_device(dev, dev->driver)) error = drv->probe(of_dev); if (error) - of_dev_put(of_dev); + put_device(dev); return error; } diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c index c00b9097eeea..471be6ec7e8a 100644 --- a/drivers/net/ethernet/ibm/emac/core.c +++ b/drivers/net/ethernet/ibm/emac/core.c @@ -38,6 +38,7 @@ #include #include #include +#include #include #include @@ -2390,11 +2391,11 @@ static int emac_check_deps(struct emac_instance *dev, static void emac_put_deps(struct emac_instance *dev) { - of_dev_put(dev->mal_dev); - of_dev_put(dev->zmii_dev); - of_dev_put(dev->rgmii_dev); - of_dev_put(dev->mdio_dev); - of_dev_put(dev->tah_dev); + platform_device_put(dev->mal_dev); + platform_device_put(dev->zmii_dev); + platform_device_put(dev->rgmii_dev); + platform_device_put(dev->mdio_dev); + platform_device_put(dev->tah_dev); } static int emac_of_bus_notify(struct notifier_block *nb, unsigned long action, @@ -2435,7 +2436,7 @@ static int emac_wait_deps(struct emac_instance *dev) for (i = 0; i < EMAC_DEP_COUNT; i++) { of_node_put(deps[i].node); if (err) - of_dev_put(deps[i].ofdev); + platform_device_put(deps[i].ofdev); } if (err == 0) { dev->mal_dev = deps[EMAC_DEP_MAL_IDX].ofdev; @@ -2444,7 +2445,7 @@ static int emac_wait_deps(struct emac_instance *dev) dev->tah_dev = deps[EMAC_DEP_TAH_IDX].ofdev; dev->mdio_dev = deps[EMAC_DEP_MDIO_IDX].ofdev; } - of_dev_put(deps[EMAC_DEP_PREV_IDX].ofdev); + platform_device_put(deps[EMAC_DEP_PREV_IDX].ofdev); return err; } diff --git a/drivers/of/device.c b/drivers/of/device.c index aedfaaafd3e7..9a748855b39d 100644 --- a/drivers/of/device.c +++ b/drivers/of/device.c @@ -33,27 +33,6 @@ const struct of_device_id *of_match_device(const struct of_device_id *matches, } EXPORT_SYMBOL(of_match_device); -struct platform_device *of_dev_get(struct platform_device *dev) -{ - struct device *tmp; - - if (!dev) - return NULL; - tmp = get_device(&dev->dev); - if (tmp) - return to_platform_device(tmp); - else - return NULL; -} -EXPORT_SYMBOL(of_dev_get); - -void of_dev_put(struct platform_device *dev) -{ - if (dev) - put_device(&dev->dev); -} -EXPORT_SYMBOL(of_dev_put); - int of_device_add(struct platform_device *ofdev) { BUG_ON(ofdev->dev.of_node == NULL); diff --git a/drivers/of/platform.c b/drivers/of/platform.c index 79bd5f5a1bf1..020bf860c72c 100644 --- a/drivers/of/platform.c +++ b/drivers/of/platform.c @@ -687,7 +687,7 @@ static int of_platform_notify(struct notifier_block *nb, pdev_parent = of_find_device_by_node(rd->dn->parent); pdev = of_platform_device_create(rd->dn, NULL, pdev_parent ? &pdev_parent->dev : NULL); - of_dev_put(pdev_parent); + platform_device_put(pdev_parent); if (pdev == NULL) { pr_err("%s: failed to create for '%pOF'\n", @@ -712,7 +712,7 @@ static int of_platform_notify(struct notifier_block *nb, of_platform_device_destroy(&pdev->dev, &children_left); /* and put the reference of the find */ - of_dev_put(pdev); + platform_device_put(pdev); break; } diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c index eb51bc147440..eb100627c186 100644 --- a/drivers/of/unittest.c +++ b/drivers/of/unittest.c @@ -1286,7 +1286,7 @@ static void __init of_unittest_platform_populate(void) unittest(pdev, "Could not create device for node '%pOFn'\n", grandchild); - of_dev_put(pdev); + platform_device_put(pdev); } } diff --git a/drivers/usb/dwc3/dwc3-st.c b/drivers/usb/dwc3/dwc3-st.c index e733be840545..b06b7092b1a2 100644 --- a/drivers/usb/dwc3/dwc3-st.c +++ b/drivers/usb/dwc3/dwc3-st.c @@ -274,7 +274,7 @@ static int st_dwc3_probe(struct platform_device *pdev) dwc3_data->dr_mode = usb_get_dr_mode(&child_pdev->dev); of_node_put(child); - of_dev_put(child_pdev); + platform_device_put(child_pdev); /* * Configure the USB port as device or host according to the static diff --git a/include/linux/of_device.h b/include/linux/of_device.h index 937f32f6aecb..d7a407dfeecb 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -26,9 +26,6 @@ static inline int of_driver_match_device(struct device *dev, return of_match_device(drv->of_match_table, dev) != NULL; } -extern struct platform_device *of_dev_get(struct platform_device *dev); -extern void of_dev_put(struct platform_device *dev); - extern int of_device_add(struct platform_device *pdev); extern int of_device_register(struct platform_device *ofdev); extern void of_device_unregister(struct platform_device *ofdev); diff --git a/scripts/coccinelle/free/put_device.cocci b/scripts/coccinelle/free/put_device.cocci index 120921366e84..f09f1e79bfa6 100644 --- a/scripts/coccinelle/free/put_device.cocci +++ b/scripts/coccinelle/free/put_device.cocci @@ -21,7 +21,6 @@ id = of_find_device_by_node@p1(x) if (id == NULL || ...) { ... return ...; } ... when != put_device(&id->dev) when != platform_device_put(id) - when != of_dev_put(id) when != if (id) { ... put_device(&id->dev) ... } when != e1 = (T)id when != e1 = (T)(&id->dev) -- cgit v1.2.3 From cb8be8b4b27f6eea88268d6991175df1a27e557e Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Thu, 11 Feb 2021 17:27:45 -0600 Subject: driver core: platform: Drop of_device_node_put() wrapper of_device_node_put() is just a wrapper for of_node_put(). The platform driver core is already polluted with of_node pointers and the only 'get' already uses of_node_get() (though typically the get would happen in of_device_alloc()). Cc: "Rafael J. Wysocki" Cc: Frank Rowand Signed-off-by: Rob Herring Reviewed-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20210211232745.1498137-3-robh@kernel.org --- drivers/base/platform.c | 2 +- include/linux/of_device.h | 7 ------- 2 files changed, 1 insertion(+), 8 deletions(-) (limited to 'include') diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 95fd1549f87d..9d5171e5f967 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -571,7 +571,7 @@ static void platform_device_release(struct device *dev) struct platform_object *pa = container_of(dev, struct platform_object, pdev.dev); - of_device_node_put(&pa->pdev.dev); + of_node_put(pa->pdev.dev.of_node); kfree(pa->pdev.dev.platform_data); kfree(pa->pdev.mfd_cell); kfree(pa->pdev.resource); diff --git a/include/linux/of_device.h b/include/linux/of_device.h index d7a407dfeecb..1d7992a02e36 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -38,11 +38,6 @@ extern int of_device_request_module(struct device *dev); extern void of_device_uevent(struct device *dev, struct kobj_uevent_env *env); extern int of_device_uevent_modalias(struct device *dev, struct kobj_uevent_env *env); -static inline void of_device_node_put(struct device *dev) -{ - of_node_put(dev->of_node); -} - static inline struct device_node *of_cpu_device_node_get(int cpu) { struct device *cpu_dev; @@ -94,8 +89,6 @@ static inline int of_device_uevent_modalias(struct device *dev, return -ENODEV; } -static inline void of_device_node_put(struct device *dev) { } - static inline const struct of_device_id *of_match_device( const struct of_device_id *matches, const struct device *dev) { -- cgit v1.2.3 From 258e0815e2b1706e87c0d874211097aa8a7aa52f Mon Sep 17 00:00:00 2001 From: Dennis Zhou Date: Sun, 14 Feb 2021 17:16:33 +0000 Subject: percpu: fix clang modpost section mismatch pcpu_build_alloc_info() is an __init function that makes a call to cpumask_clear_cpu(). With CONFIG_GCOV_PROFILE_ALL enabled, the inline heuristics are modified and such cpumask_clear_cpu() which is marked inline doesn't get inlined. Because it works on mask in __initdata, modpost throws a section mismatch error. Arnd sent a patch with the flatten attribute as an alternative [2]. I've added it to compiler_attributes.h. modpost complaint: WARNING: modpost: vmlinux.o(.text+0x735425): Section mismatch in reference from the function cpumask_clear_cpu() to the variable .init.data:pcpu_build_alloc_info.mask The function cpumask_clear_cpu() references the variable __initdata pcpu_build_alloc_info.mask. This is often because cpumask_clear_cpu lacks a __initdata annotation or the annotation of pcpu_build_alloc_info.mask is wrong. clang output: mm/percpu.c:2724:5: remark: cpumask_clear_cpu not inlined into pcpu_build_alloc_info because too costly to inline (cost=725, threshold=325) [-Rpass-missed=inline] [1] https://lore.kernel.org/linux-mm/202012220454.9F6Bkz9q-lkp@intel.com/ [2] https://lore.kernel.org/lkml/CAK8P3a2ZWfNeXKSm8K_SUhhwkor17jFo3xApLXjzfPqX0eUDUA@mail.gmail.com/ Reported-by: kernel test robot Cc: Arnd Bergmann Cc: Nick Desaulniers Signed-off-by: Dennis Zhou --- include/linux/compiler_attributes.h | 6 ++++++ mm/percpu.c | 2 +- 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index ea5e04e75845..c043b8d2b17b 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -210,6 +210,12 @@ # define fallthrough do {} while (0) /* fallthrough */ #endif +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#Common-Function-Attributes + * clang: https://clang.llvm.org/docs/AttributeReference.html#flatten + */ +# define __flatten __attribute__((flatten)) + /* * Note the missing underscores. * diff --git a/mm/percpu.c b/mm/percpu.c index 80f8f885a990..6596a0a4286e 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -2663,7 +2663,7 @@ early_param("percpu_alloc", percpu_alloc_setup); * On success, pointer to the new allocation_info is returned. On * failure, ERR_PTR value is returned. */ -static struct pcpu_alloc_info * __init pcpu_build_alloc_info( +static struct pcpu_alloc_info * __init __flatten pcpu_build_alloc_info( size_t reserved_size, size_t dyn_size, size_t atom_size, pcpu_fc_cpu_distance_fn_t cpu_distance_fn) -- cgit v1.2.3 From 1d895931cb427b4275f3ca4ffebe1f12c6ce2e4e Mon Sep 17 00:00:00 2001 From: Daniel Palmer Date: Thu, 11 Feb 2021 14:22:00 +0900 Subject: dt-bindings: clk: mstar msc313 mpll binding header Simple header to document the relationship between the MPLL outputs and which divider they come from. Output 0 is missing because it should not be consumed. Signed-off-by: Daniel Palmer Acked-by: Rob Herring Link: https://lore.kernel.org/r/20210211052206.2955988-2-daniel@0x0f.com Signed-off-by: Stephen Boyd --- MAINTAINERS | 1 + include/dt-bindings/clock/mstar-msc313-mpll.h | 19 +++++++++++++++++++ 2 files changed, 20 insertions(+) create mode 100644 include/dt-bindings/clock/mstar-msc313-mpll.h (limited to 'include') diff --git a/MAINTAINERS b/MAINTAINERS index 546aa66428c9..ac03c7a0066b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2150,6 +2150,7 @@ F: Documentation/devicetree/bindings/gpio/mstar,msc313-gpio.yaml F: arch/arm/boot/dts/mstar-* F: arch/arm/mach-mstar/ F: drivers/gpio/gpio-msc313.c +F: include/dt-bindings/clock/mstar-* F: include/dt-bindings/gpio/msc313-gpio.h ARM/NEC MOBILEPRO 900/c MACHINE SUPPORT diff --git a/include/dt-bindings/clock/mstar-msc313-mpll.h b/include/dt-bindings/clock/mstar-msc313-mpll.h new file mode 100644 index 000000000000..1b30b02317b6 --- /dev/null +++ b/include/dt-bindings/clock/mstar-msc313-mpll.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause */ +/* + * Output definitions for the MStar/SigmaStar MPLL + * + * Copyright (C) 2020 Daniel Palmer + */ + +#ifndef _DT_BINDINGS_CLOCK_MSTAR_MSC313_MPLL_H +#define _DT_BINDINGS_CLOCK_MSTAR_MSC313_MPLL_H + +#define MSTAR_MSC313_MPLL_DIV2 1 +#define MSTAR_MSC313_MPLL_DIV3 2 +#define MSTAR_MSC313_MPLL_DIV4 3 +#define MSTAR_MSC313_MPLL_DIV5 4 +#define MSTAR_MSC313_MPLL_DIV6 5 +#define MSTAR_MSC313_MPLL_DIV7 6 +#define MSTAR_MSC313_MPLL_DIV10 7 + +#endif -- cgit v1.2.3 From 0b9266d295cee170509539635b8d572abe5267af Mon Sep 17 00:00:00 2001 From: Daniel Palmer Date: Thu, 11 Feb 2021 14:22:02 +0900 Subject: clk: fixed: add devm helper for clk_hw_register_fixed_factor() Add a devm helper for clk_hw_register_fixed_factor() so that drivers that internally register fixed factor clocks for things like dividers don't need to manually unregister them on remove or if probe fails. Signed-off-by: Daniel Palmer Link: https://lore.kernel.org/r/20210211052206.2955988-4-daniel@0x0f.com Signed-off-by: Stephen Boyd --- drivers/clk/clk-fixed-factor.c | 39 +++++++++++++++++++++++++++++++++------ include/linux/clk-provider.h | 4 +++- 2 files changed, 36 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/drivers/clk/clk-fixed-factor.c b/drivers/clk/clk-fixed-factor.c index 910e6e74ae90..4f7bf3929d6d 100644 --- a/drivers/clk/clk-fixed-factor.c +++ b/drivers/clk/clk-fixed-factor.c @@ -64,10 +64,16 @@ const struct clk_ops clk_fixed_factor_ops = { }; EXPORT_SYMBOL_GPL(clk_fixed_factor_ops); +static void devm_clk_hw_register_fixed_factor_release(struct device *dev, void *res) +{ + clk_hw_unregister_fixed_factor(&((struct clk_fixed_factor *)res)->hw); +} + static struct clk_hw * __clk_hw_register_fixed_factor(struct device *dev, struct device_node *np, const char *name, const char *parent_name, int index, - unsigned long flags, unsigned int mult, unsigned int div) + unsigned long flags, unsigned int mult, unsigned int div, + bool devm) { struct clk_fixed_factor *fix; struct clk_init_data init = { }; @@ -75,7 +81,15 @@ __clk_hw_register_fixed_factor(struct device *dev, struct device_node *np, struct clk_hw *hw; int ret; - fix = kmalloc(sizeof(*fix), GFP_KERNEL); + /* You can't use devm without a dev */ + if (devm && !dev) + return ERR_PTR(-EINVAL); + + if (devm) + fix = devres_alloc(devm_clk_hw_register_fixed_factor_release, + sizeof(*fix), GFP_KERNEL); + else + fix = kmalloc(sizeof(*fix), GFP_KERNEL); if (!fix) return ERR_PTR(-ENOMEM); @@ -99,9 +113,13 @@ __clk_hw_register_fixed_factor(struct device *dev, struct device_node *np, else ret = of_clk_hw_register(np, hw); if (ret) { - kfree(fix); + if (devm) + devres_free(fix); + else + kfree(fix); hw = ERR_PTR(ret); - } + } else if (devm) + devres_add(dev, fix); return hw; } @@ -111,7 +129,7 @@ struct clk_hw *clk_hw_register_fixed_factor(struct device *dev, unsigned int mult, unsigned int div) { return __clk_hw_register_fixed_factor(dev, NULL, name, parent_name, -1, - flags, mult, div); + flags, mult, div, false); } EXPORT_SYMBOL_GPL(clk_hw_register_fixed_factor); @@ -153,6 +171,15 @@ void clk_hw_unregister_fixed_factor(struct clk_hw *hw) } EXPORT_SYMBOL_GPL(clk_hw_unregister_fixed_factor); +struct clk_hw *devm_clk_hw_register_fixed_factor(struct device *dev, + const char *name, const char *parent_name, unsigned long flags, + unsigned int mult, unsigned int div) +{ + return __clk_hw_register_fixed_factor(dev, NULL, name, parent_name, -1, + flags, mult, div, true); +} +EXPORT_SYMBOL_GPL(devm_clk_hw_register_fixed_factor); + #ifdef CONFIG_OF static const struct of_device_id set_rate_parent_matches[] = { { .compatible = "allwinner,sun4i-a10-pll3-2x-clk" }, @@ -185,7 +212,7 @@ static struct clk_hw *_of_fixed_factor_clk_setup(struct device_node *node) flags |= CLK_SET_RATE_PARENT; hw = __clk_hw_register_fixed_factor(NULL, node, clk_name, NULL, 0, - flags, mult, div); + flags, mult, div, false); if (IS_ERR(hw)) { /* * Clear OF_POPULATED flag so that clock registration can be diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index e4316890661a..58f6fe866ae9 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -941,7 +941,9 @@ struct clk_hw *clk_hw_register_fixed_factor(struct device *dev, const char *name, const char *parent_name, unsigned long flags, unsigned int mult, unsigned int div); void clk_hw_unregister_fixed_factor(struct clk_hw *hw); - +struct clk_hw *devm_clk_hw_register_fixed_factor(struct device *dev, + const char *name, const char *parent_name, unsigned long flags, + unsigned int mult, unsigned int div); /** * struct clk_fractional_divider - adjustable fractional divider clock * -- cgit v1.2.3 From 5db3ae8b33de627ac3a73b7a772e5ae9f8c31da9 Mon Sep 17 00:00:00 2001 From: Martin Botka Date: Wed, 13 Jan 2021 19:38:11 +0100 Subject: clk: qcom: Add SDM660 Multimedia Clock Controller (MMCC) driver Add a driver for the multimedia clock controller found on SDM660 based devices. This should allow most multimedia device drivers to probe and control their clocks. Signed-off-by: Martin Botka Co-developed-by: Konrad Dybcio Signed-off-by: Konrad Dybcio [angelogioacchino.delregno@somainline.org: Cleaned up SDM630 clock fixups] Signed-off-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20210113183817.447866-4-angelogioacchino.delregno@somainline.org [sboyd@kernel.org: Silence NULL pointer sparse warnings] Signed-off-by: Stephen Boyd --- drivers/clk/qcom/Kconfig | 9 + drivers/clk/qcom/Makefile | 1 + drivers/clk/qcom/mmcc-sdm660.c | 2864 ++++++++++++++++++++++++++ include/dt-bindings/clock/qcom,mmcc-sdm660.h | 162 ++ 4 files changed, 3036 insertions(+) create mode 100644 drivers/clk/qcom/mmcc-sdm660.c create mode 100644 include/dt-bindings/clock/qcom,mmcc-sdm660.h (limited to 'include') diff --git a/drivers/clk/qcom/Kconfig b/drivers/clk/qcom/Kconfig index 7e754d8fda08..f514881686d3 100644 --- a/drivers/clk/qcom/Kconfig +++ b/drivers/clk/qcom/Kconfig @@ -392,6 +392,15 @@ config SDM_GCC_660 Say Y if you want to use peripheral devices such as UART, SPI, i2C, USB, UFS, SDDC, PCIe, etc. +config SDM_MMCC_660 + tristate "SDM660 Multimedia Clock Controller" + select SDM_GCC_660 + select QCOM_GDSC + help + Support for the multimedia clock controller on SDM660 devices. + Say Y if you want to support multimedia devices such as display, + graphics, video encode/decode, camera, etc. + config QCS_TURING_404 tristate "QCS404 Turing Clock Controller" help diff --git a/drivers/clk/qcom/Makefile b/drivers/clk/qcom/Makefile index 3d64c0f91e79..a01cd4076ce3 100644 --- a/drivers/clk/qcom/Makefile +++ b/drivers/clk/qcom/Makefile @@ -65,6 +65,7 @@ obj-$(CONFIG_SC_VIDEOCC_7180) += videocc-sc7180.o obj-$(CONFIG_SDM_CAMCC_845) += camcc-sdm845.o obj-$(CONFIG_SDM_DISPCC_845) += dispcc-sdm845.o obj-$(CONFIG_SDM_GCC_660) += gcc-sdm660.o +obj-$(CONFIG_SDM_MMCC_660) += mmcc-sdm660.o obj-$(CONFIG_SDM_GCC_845) += gcc-sdm845.o obj-$(CONFIG_SDM_GPUCC_845) += gpucc-sdm845.o obj-$(CONFIG_SDM_LPASSCC_845) += lpasscc-sdm845.o diff --git a/drivers/clk/qcom/mmcc-sdm660.c b/drivers/clk/qcom/mmcc-sdm660.c new file mode 100644 index 000000000000..941993bc610d --- /dev/null +++ b/drivers/clk/qcom/mmcc-sdm660.c @@ -0,0 +1,2864 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2020, The Linux Foundation. All rights reserved. + * Copyright (c) 2020, Martin Botka + * Copyright (c) 2020, Konrad Dybcio + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +#include + +#include "common.h" +#include "clk-regmap.h" +#include "clk-regmap-divider.h" +#include "clk-alpha-pll.h" +#include "clk-rcg.h" +#include "clk-branch.h" +#include "reset.h" +#include "gdsc.h" + +enum { + P_XO, + P_DSI0PLL_BYTE, + P_DSI0PLL, + P_DSI1PLL_BYTE, + P_DSI1PLL, + P_GPLL0, + P_GPLL0_DIV, + P_MMPLL0, + P_MMPLL10, + P_MMPLL3, + P_MMPLL4, + P_MMPLL5, + P_MMPLL6, + P_MMPLL7, + P_MMPLL8, + P_SLEEP_CLK, + P_DP_PHY_PLL_LINK_CLK, + P_DP_PHY_PLL_VCO_DIV, +}; + +static const struct parent_map mmcc_xo_mmpll0_mmpll4_mmpll7_mmpll8_gpll0_gpll0_div_map[] = { + { P_XO, 0 }, + { P_MMPLL0, 1 }, + { P_MMPLL4, 2 }, + { P_MMPLL7, 3 }, + { P_MMPLL8, 4 }, + { P_GPLL0, 5 }, + { P_GPLL0_DIV, 6 }, +}; + +/* Voteable PLL */ +static struct clk_alpha_pll mmpll0 = { + .offset = 0xc000, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .clkr = { + .enable_reg = 0x1f0, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "mmpll0", + .parent_data = &(const struct clk_parent_data){ + .fw_name = "xo", + }, + .num_parents = 1, + .ops = &clk_alpha_pll_ops, + }, + }, +}; + +static struct clk_alpha_pll mmpll6 = { + .offset = 0xf0, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .clkr = { + .enable_reg = 0x1f0, + .enable_mask = BIT(2), + .hw.init = &(struct clk_init_data){ + .name = "mmpll6", + .parent_data = &(const struct clk_parent_data){ + .fw_name = "xo", + }, + .num_parents = 1, + .ops = &clk_alpha_pll_ops, + }, + }, +}; + +/* APSS controlled PLLs */ +static struct pll_vco vco[] = { + { 1000000000, 2000000000, 0 }, + { 750000000, 1500000000, 1 }, + { 500000000, 1000000000, 2 }, + { 250000000, 500000000, 3 }, +}; + +static struct pll_vco mmpll3_vco[] = { + { 750000000, 1500000000, 1 }, +}; + +static const struct alpha_pll_config mmpll10_config = { + .l = 0x1e, + .config_ctl_val = 0x00004289, + .main_output_mask = 0x1, +}; + +static struct clk_alpha_pll mmpll10 = { + .offset = 0x190, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .clkr = { + .hw.init = &(struct clk_init_data){ + .name = "mmpll10", + .parent_data = &(const struct clk_parent_data){ + .fw_name = "xo", + }, + .num_parents = 1, + .ops = &clk_alpha_pll_ops, + }, + }, +}; + +static const struct alpha_pll_config mmpll3_config = { + .l = 0x2e, + .config_ctl_val = 0x4001055b, + .vco_val = 0x1 << 20, + .vco_mask = 0x3 << 20, + .main_output_mask = 0x1, +}; + +static struct clk_alpha_pll mmpll3 = { + .offset = 0x0, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .vco_table = mmpll3_vco, + .num_vco = ARRAY_SIZE(mmpll3_vco), + .clkr = { + .hw.init = &(struct clk_init_data){ + .name = "mmpll3", + .parent_data = &(const struct clk_parent_data){ + .fw_name = "xo", + }, + .num_parents = 1, + .ops = &clk_alpha_pll_ops, + }, + }, +}; + +static const struct alpha_pll_config mmpll4_config = { + .l = 0x28, + .config_ctl_val = 0x4001055b, + .vco_val = 0x2 << 20, + .vco_mask = 0x3 << 20, + .main_output_mask = 0x1, +}; + +static struct clk_alpha_pll mmpll4 = { + .offset = 0x50, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .vco_table = vco, + .num_vco = ARRAY_SIZE(vco), + .clkr = { + .hw.init = &(struct clk_init_data){ + .name = "mmpll4", + .parent_data = &(const struct clk_parent_data){ + .fw_name = "xo", + }, + .num_parents = 1, + .ops = &clk_alpha_pll_ops, + }, + }, +}; + +static const struct alpha_pll_config mmpll5_config = { + .l = 0x2a, + .config_ctl_val = 0x4001055b, + .alpha_hi = 0xf8, + .alpha_en_mask = BIT(24), + .vco_val = 0x2 << 20, + .vco_mask = 0x3 << 20, + .main_output_mask = 0x1, +}; + +static struct clk_alpha_pll mmpll5 = { + .offset = 0xa0, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .vco_table = vco, + .num_vco = ARRAY_SIZE(vco), + .clkr = { + .hw.init = &(struct clk_init_data){ + .name = "mmpll5", + .parent_data = &(const struct clk_parent_data){ + .fw_name = "xo", + }, + .num_parents = 1, + .ops = &clk_alpha_pll_ops, + }, + }, +}; + +static const struct alpha_pll_config mmpll7_config = { + .l = 0x32, + .config_ctl_val = 0x4001055b, + .vco_val = 0x2 << 20, + .vco_mask = 0x3 << 20, + .main_output_mask = 0x1, +}; + +static struct clk_alpha_pll mmpll7 = { + .offset = 0x140, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .vco_table = vco, + .num_vco = ARRAY_SIZE(vco), + .clkr = { + .hw.init = &(struct clk_init_data){ + .name = "mmpll7", + .parent_data = &(const struct clk_parent_data){ + .fw_name = "xo", + }, + .num_parents = 1, + .ops = &clk_alpha_pll_ops, + }, + }, +}; + +static const struct alpha_pll_config mmpll8_config = { + .l = 0x30, + .alpha_hi = 0x70, + .alpha_en_mask = BIT(24), + .config_ctl_val = 0x4001055b, + .vco_val = 0x2 << 20, + .vco_mask = 0x3 << 20, + .main_output_mask = 0x1, +}; + +static struct clk_alpha_pll mmpll8 = { + .offset = 0x1c0, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .vco_table = vco, + .num_vco = ARRAY_SIZE(vco), + .clkr = { + .hw.init = &(struct clk_init_data){ + .name = "mmpll8", + .parent_data = &(const struct clk_parent_data){ + .fw_name = "xo", + }, + .num_parents = 1, + .ops = &clk_alpha_pll_ops, + }, + }, +}; + +static const struct clk_parent_data mmcc_xo_mmpll0_mmpll4_mmpll7_mmpll8_gpll0_gpll0_div[] = { + { .fw_name = "xo" }, + { .hw = &mmpll0.clkr.hw }, + { .hw = &mmpll4.clkr.hw }, + { .hw = &mmpll7.clkr.hw }, + { .hw = &mmpll8.clkr.hw }, + { .fw_name = "gpll0" }, + { .fw_name = "gpll0_div" }, +}; + +static const struct parent_map mmcc_xo_dsibyte_map[] = { + { P_XO, 0 }, + { P_DSI0PLL_BYTE, 1 }, + { P_DSI1PLL_BYTE, 2 }, +}; + +static const struct clk_parent_data mmcc_xo_dsibyte[] = { + { .fw_name = "xo" }, + { .fw_name = "dsi0pllbyte" }, + { .fw_name = "dsi1pllbyte" }, +}; + +static const struct parent_map mmcc_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div_map[] = { + { P_XO, 0 }, + { P_MMPLL0, 1 }, + { P_MMPLL4, 2 }, + { P_MMPLL7, 3 }, + { P_MMPLL10, 4 }, + { P_GPLL0, 5 }, + { P_GPLL0_DIV, 6 }, +}; + +static const struct clk_parent_data mmcc_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div[] = { + { .fw_name = "xo" }, + { .hw = &mmpll0.clkr.hw }, + { .hw = &mmpll4.clkr.hw }, + { .hw = &mmpll7.clkr.hw }, + { .hw = &mmpll10.clkr.hw }, + { .fw_name = "gpll0" }, + { .fw_name = "gpll0_div" }, +}; + +static const struct parent_map mmcc_xo_mmpll4_mmpll7_mmpll10_sleep_gpll0_gpll0_div_map[] = { + { P_XO, 0 }, + { P_MMPLL4, 1 }, + { P_MMPLL7, 2 }, + { P_MMPLL10, 3 }, + { P_SLEEP_CLK, 4 }, + { P_GPLL0, 5 }, + { P_GPLL0_DIV, 6 }, +}; + +static const struct clk_parent_data mmcc_xo_mmpll4_mmpll7_mmpll10_sleep_gpll0_gpll0_div[] = { + { .fw_name = "xo" }, + { .hw = &mmpll4.clkr.hw }, + { .hw = &mmpll7.clkr.hw }, + { .hw = &mmpll10.clkr.hw }, + { .fw_name = "sleep_clk" }, + { .fw_name = "gpll0" }, + { .fw_name = "gpll0_div" }, +}; + +static const struct parent_map mmcc_xo_mmpll0_mmpll7_mmpll10_sleep_gpll0_gpll0_div_map[] = { + { P_XO, 0 }, + { P_MMPLL0, 1 }, + { P_MMPLL7, 2 }, + { P_MMPLL10, 3 }, + { P_SLEEP_CLK, 4 }, + { P_GPLL0, 5 }, + { P_GPLL0_DIV, 6 }, +}; + +static const struct clk_parent_data mmcc_xo_mmpll0_mmpll7_mmpll10_sleep_gpll0_gpll0_div[] = { + { .fw_name = "xo" }, + { .hw = &mmpll0.clkr.hw }, + { .hw = &mmpll7.clkr.hw }, + { .hw = &mmpll10.clkr.hw }, + { .fw_name = "sleep_clk" }, + { .fw_name = "gpll0" }, + { .fw_name = "gpll0_div" }, +}; + +static const struct parent_map mmcc_xo_gpll0_gpll0_div_map[] = { + { P_XO, 0 }, + { P_GPLL0, 5 }, + { P_GPLL0_DIV, 6 }, +}; + +static const struct clk_parent_data mmcc_xo_gpll0_gpll0_div[] = { + { .fw_name = "xo" }, + { .fw_name = "gpll0" }, + { .fw_name = "gpll0_div" }, +}; + +static const struct parent_map mmcc_xo_dplink_dpvco_map[] = { + { P_XO, 0 }, + { P_DP_PHY_PLL_LINK_CLK, 1 }, + { P_DP_PHY_PLL_VCO_DIV, 2 }, +}; + +static const struct clk_parent_data mmcc_xo_dplink_dpvco[] = { + { .fw_name = "xo" }, + { .fw_name = "dp_link_2x_clk_divsel_five" }, + { .fw_name = "dp_vco_divided_clk_src_mux" }, +}; + +static const struct parent_map mmcc_xo_mmpll0_mmpll5_mmpll7_gpll0_gpll0_div_map[] = { + { P_XO, 0 }, + { P_MMPLL0, 1 }, + { P_MMPLL5, 2 }, + { P_MMPLL7, 3 }, + { P_GPLL0, 5 }, + { P_GPLL0_DIV, 6 }, +}; + +static const struct clk_parent_data mmcc_xo_mmpll0_mmpll5_mmpll7_gpll0_gpll0_div[] = { + { .fw_name = "xo" }, + { .hw = &mmpll0.clkr.hw }, + { .hw = &mmpll5.clkr.hw }, + { .hw = &mmpll7.clkr.hw }, + { .fw_name = "gpll0" }, + { .fw_name = "gpll0_div" }, +}; + +static const struct parent_map mmcc_xo_dsi0pll_dsi1pll_map[] = { + { P_XO, 0 }, + { P_DSI0PLL, 1 }, + { P_DSI1PLL, 2 }, +}; + +static const struct clk_parent_data mmcc_xo_dsi0pll_dsi1pll[] = { + { .fw_name = "xo" }, + { .fw_name = "dsi0pll" }, + { .fw_name = "dsi1pll" }, +}; + +static const struct parent_map mmcc_mmpll0_mmpll4_mmpll7_mmpll10_mmpll6_gpll0_map[] = { + { P_XO, 0 }, + { P_MMPLL0, 1 }, + { P_MMPLL4, 2 }, + { P_MMPLL7, 3 }, + { P_MMPLL10, 4 }, + { P_MMPLL6, 5 }, + { P_GPLL0, 6 }, +}; + +static const struct clk_parent_data mmcc_mmpll0_mmpll4_mmpll7_mmpll10_mmpll6_gpll0[] = { + { .fw_name = "xo" }, + { .hw = &mmpll0.clkr.hw }, + { .hw = &mmpll4.clkr.hw }, + { .hw = &mmpll7.clkr.hw }, + { .hw = &mmpll10.clkr.hw }, + { .hw = &mmpll6.clkr.hw }, + { .fw_name = "gpll0" }, +}; + +static const struct parent_map mmcc_xo_mmpll0_gpll0_gpll0_div_map[] = { + { P_XO, 0 }, + { P_MMPLL0, 1 }, + { P_GPLL0, 5 }, + { P_GPLL0_DIV, 6 }, +}; + +static const struct clk_parent_data mmcc_xo_mmpll0_gpll0_gpll0_div[] = { + { .fw_name = "xo" }, + { .hw = &mmpll0.clkr.hw }, + { .fw_name = "gpll0" }, + { .fw_name = "gpll0_div" }, +}; + +static const struct parent_map mmcc_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_mmpll6_map[] = { + { P_XO, 0 }, + { P_MMPLL0, 1 }, + { P_MMPLL4, 2 }, + { P_MMPLL7, 3 }, + { P_MMPLL10, 4 }, + { P_GPLL0, 5 }, + { P_MMPLL6, 6 }, +}; + +static const struct clk_parent_data mmcc_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_mmpll6[] = { + { .fw_name = "xo" }, + { .hw = &mmpll0.clkr.hw }, + { .hw = &mmpll4.clkr.hw }, + { .hw = &mmpll7.clkr.hw }, + { .hw = &mmpll10.clkr.hw }, + { .fw_name = "gpll0" }, + { .hw = &mmpll6.clkr.hw }, +}; + +static const struct parent_map mmcc_xo_mmpll0_mmpll8_mmpll3_mmpll6_gpll0_mmpll7_map[] = { + { P_XO, 0 }, + { P_MMPLL0, 1 }, + { P_MMPLL8, 2 }, + { P_MMPLL3, 3 }, + { P_MMPLL6, 4 }, + { P_GPLL0, 5 }, + { P_MMPLL7, 6 }, +}; + +static const struct clk_parent_data mmcc_xo_mmpll0_mmpll8_mmpll3_mmpll6_gpll0_mmpll7[] = { + { .fw_name = "xo" }, + { .hw = &mmpll0.clkr.hw }, + { .hw = &mmpll8.clkr.hw }, + { .hw = &mmpll3.clkr.hw }, + { .hw = &mmpll6.clkr.hw }, + { .fw_name = "gpll0" }, + { .hw = &mmpll7.clkr.hw }, +}; + +static const struct freq_tbl ftbl_ahb_clk_src[] = { + F(19200000, P_XO, 1, 0, 0), + F(40000000, P_GPLL0_DIV, 7.5, 0, 0), + F(80800000, P_MMPLL0, 10, 0, 0), + { } +}; + +static struct clk_rcg2 ahb_clk_src = { + .cmd_rcgr = 0x5000, + .mnd_width = 0, + .hid_width = 5, + .parent_map = mmcc_xo_mmpll0_gpll0_gpll0_div_map, + .freq_tbl = ftbl_ahb_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "ahb_clk_src", + .parent_data = mmcc_xo_mmpll0_gpll0_gpll0_div, + .num_parents = 4, + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 byte0_clk_src = { + .cmd_rcgr = 0x2120, + .mnd_width = 0, + .hid_width = 5, + .parent_map = mmcc_xo_dsibyte_map, + .clkr.hw.init = &(struct clk_init_data){ + .name = "byte0_clk_src", + .parent_data = mmcc_xo_dsibyte, + .num_parents = 3, + .ops = &clk_byte2_ops, + .flags = CLK_SET_RATE_PARENT | CLK_GET_RATE_NOCACHE, + }, +}; + +static struct clk_rcg2 byte1_clk_src = { + .cmd_rcgr = 0x2140, + .mnd_width = 0, + .hid_width = 5, + .parent_map = mmcc_xo_dsibyte_map, + .clkr.hw.init = &(struct clk_init_data){ + .name = "byte1_clk_src", + .parent_data = mmcc_xo_dsibyte, + .num_parents = 3, + .ops = &clk_byte2_ops, + .flags = CLK_SET_RATE_PARENT | CLK_GET_RATE_NOCACHE, + }, +}; + +static const struct freq_tbl ftbl_camss_gp0_clk_src[] = { + F(10000, P_XO, 16, 1, 120), + F(24000, P_XO, 16, 1, 50), + F(6000000, P_GPLL0_DIV, 10, 1, 5), + F(12000000, P_GPLL0_DIV, 10, 2, 5), + F(13043478, P_GPLL0_DIV, 1, 1, 23), + F(24000000, P_GPLL0_DIV, 1, 2, 25), + F(50000000, P_GPLL0_DIV, 6, 0, 0), + F(100000000, P_GPLL0_DIV, 3, 0, 0), + F(200000000, P_GPLL0, 3, 0, 0), + { } +}; + +static struct clk_rcg2 camss_gp0_clk_src = { + .cmd_rcgr = 0x3420, + .mnd_width = 8, + .hid_width = 5, + .parent_map = mmcc_xo_mmpll0_mmpll7_mmpll10_sleep_gpll0_gpll0_div_map, + .freq_tbl = ftbl_camss_gp0_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "camss_gp0_clk_src", + .parent_data = mmcc_xo_mmpll0_mmpll7_mmpll10_sleep_gpll0_gpll0_div, + .num_parents = 7, + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 camss_gp1_clk_src = { + .cmd_rcgr = 0x3450, + .mnd_width = 8, + .hid_width = 5, + .parent_map = mmcc_xo_mmpll0_mmpll7_mmpll10_sleep_gpll0_gpll0_div_map, + .freq_tbl = ftbl_camss_gp0_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "camss_gp1_clk_src", + .parent_data = mmcc_xo_mmpll0_mmpll7_mmpll10_sleep_gpll0_gpll0_div, + .num_parents = 7, + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_cci_clk_src[] = { + F(37500000, P_GPLL0_DIV, 8, 0, 0), + F(50000000, P_GPLL0_DIV, 6, 0, 0), + F(100000000, P_GPLL0, 6, 0, 0), + { } +}; + +static struct clk_rcg2 cci_clk_src = { + .cmd_rcgr = 0x3300, + .mnd_width = 8, + .hid_width = 5, + .parent_map = mmcc_xo_mmpll0_mmpll7_mmpll10_sleep_gpll0_gpll0_div_map, + .freq_tbl = ftbl_cci_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "cci_clk_src", + .parent_data = mmcc_xo_mmpll0_mmpll7_mmpll10_sleep_gpll0_gpll0_div, + .num_parents = 7, + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_cpp_clk_src[] = { + F(120000000, P_GPLL0, 5, 0, 0), + F(256000000, P_MMPLL4, 3, 0, 0), + F(384000000, P_MMPLL4, 2, 0, 0), + F(480000000, P_MMPLL7, 2, 0, 0), + F(540000000, P_MMPLL6, 2, 0, 0), + F(576000000, P_MMPLL10, 1, 0, 0), + { } +}; + +static struct clk_rcg2 cpp_clk_src = { + .cmd_rcgr = 0x3640, + .mnd_width = 0, + .hid_width = 5, + .parent_map = mmcc_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_mmpll6_map, + .freq_tbl = ftbl_cpp_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "cpp_clk_src", + .parent_data = mmcc_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_mmpll6, + .num_parents = 7, + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_csi0_clk_src[] = { + F(100000000, P_GPLL0_DIV, 3, 0, 0), + F(200000000, P_GPLL0, 3, 0, 0), + F(310000000, P_MMPLL8, 3, 0, 0), + F(404000000, P_MMPLL0, 2, 0, 0), + F(465000000, P_MMPLL8, 2, 0, 0), + { } +}; + +static struct clk_rcg2 csi0_clk_src = { + .cmd_rcgr = 0x3090, + .mnd_width = 0, + .hid_width = 5, + .parent_map = mmcc_xo_mmpll0_mmpll4_mmpll7_mmpll8_gpll0_gpll0_div_map, + .freq_tbl = ftbl_csi0_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "csi0_clk_src", + .parent_data = mmcc_xo_mmpll0_mmpll4_mmpll7_mmpll8_gpll0_gpll0_div, + .num_parents = 7, + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_csi0phytimer_clk_src[] = { + F(100000000, P_GPLL0_DIV, 3, 0, 0), + F(200000000, P_GPLL0, 3, 0, 0), + F(269333333, P_MMPLL0, 3, 0, 0), + { } +}; + +static struct clk_rcg2 csi0phytimer_clk_src = { + .cmd_rcgr = 0x3000, + .mnd_width = 0, + .hid_width = 5, + .parent_map = mmcc_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div_map, + .freq_tbl = ftbl_csi0phytimer_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "csi0phytimer_clk_src", + .parent_data = mmcc_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div, + .num_parents = 7, + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 csi1_clk_src = { + .cmd_rcgr = 0x3100, + .mnd_width = 0, + .hid_width = 5, + .parent_map = mmcc_xo_mmpll0_mmpll4_mmpll7_mmpll8_gpll0_gpll0_div_map, + .freq_tbl = ftbl_csi0_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "csi1_clk_src", + .parent_data = mmcc_xo_mmpll0_mmpll4_mmpll7_mmpll8_gpll0_gpll0_div, + .num_parents = 7, + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 csi1phytimer_clk_src = { + .cmd_rcgr = 0x3030, + .mnd_width = 0, + .hid_width = 5, + .parent_map = mmcc_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div_map, + .freq_tbl = ftbl_csi0phytimer_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "csi1phytimer_clk_src", + .parent_data = mmcc_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div, + .num_parents = 7, + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 csi2_clk_src = { + .cmd_rcgr = 0x3160, + .mnd_width = 0, + .hid_width = 5, + .parent_map = mmcc_xo_mmpll0_mmpll4_mmpll7_mmpll8_gpll0_gpll0_div_map, + .freq_tbl = ftbl_csi0_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "csi2_clk_src", + .parent_data = mmcc_xo_mmpll0_mmpll4_mmpll7_mmpll8_gpll0_gpll0_div, + .num_parents = 7, + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 csi2phytimer_clk_src = { + .cmd_rcgr = 0x3060, + .mnd_width = 0, + .hid_width = 5, + .parent_map = mmcc_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div_map, + .freq_tbl = ftbl_csi0phytimer_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "csi2phytimer_clk_src", + .parent_data = mmcc_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div, + .num_parents = 7, + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 csi3_clk_src = { + .cmd_rcgr = 0x31c0, + .mnd_width = 0, + .hid_width = 5, + .parent_map = mmcc_xo_mmpll0_mmpll4_mmpll7_mmpll8_gpll0_gpll0_div_map, + .freq_tbl = ftbl_csi0_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "csi3_clk_src", + .parent_data = mmcc_xo_mmpll0_mmpll4_mmpll7_mmpll8_gpll0_gpll0_div, + .num_parents = 7, + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_csiphy_clk_src[] = { + F(100000000, P_GPLL0_DIV, 3, 0, 0), + F(200000000, P_GPLL0, 3, 0, 0), + F(269333333, P_MMPLL0, 3, 0, 0), + F(320000000, P_MMPLL7, 3, 0, 0), + { } +}; + +static struct clk_rcg2 csiphy_clk_src = { + .cmd_rcgr = 0x3800, + .mnd_width = 0, + .hid_width = 5, + .parent_map = mmcc_xo_mmpll0_mmpll4_mmpll7_mmpll8_gpll0_gpll0_div_map, + .freq_tbl = ftbl_csiphy_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "csiphy_clk_src", + .parent_data = mmcc_xo_mmpll0_mmpll4_mmpll7_mmpll8_gpll0_gpll0_div, + .num_parents = 7, + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_dp_aux_clk_src[] = { + F(19200000, P_XO, 1, 0, 0), + { } +}; + +static struct clk_rcg2 dp_aux_clk_src = { + .cmd_rcgr = 0x2260, + .mnd_width = 0, + .hid_width = 5, + .parent_map = mmcc_xo_gpll0_gpll0_div_map, + .freq_tbl = ftbl_dp_aux_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "dp_aux_clk_src", + .parent_data = mmcc_xo_gpll0_gpll0_div, + .num_parents = 3, + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_dp_crypto_clk_src[] = { + F(101250000, P_DP_PHY_PLL_VCO_DIV, 4, 0, 0), + F(168750000, P_DP_PHY_PLL_VCO_DIV, 4, 0, 0), + F(337500000, P_DP_PHY_PLL_VCO_DIV, 4, 0, 0), + { } +}; + +static struct clk_rcg2 dp_crypto_clk_src = { + .cmd_rcgr = 0x2220, + .mnd_width = 8, + .hid_width = 5, + .parent_map = mmcc_xo_dplink_dpvco_map, + .freq_tbl = ftbl_dp_crypto_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "dp_crypto_clk_src", + .parent_data = mmcc_xo_dplink_dpvco, + .num_parents = 3, + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_dp_gtc_clk_src[] = { + F(40000000, P_GPLL0_DIV, 7.5, 0, 0), + F(60000000, P_GPLL0, 10, 0, 0), + { } +}; + +static struct clk_rcg2 dp_gtc_clk_src = { + .cmd_rcgr = 0x2280, + .mnd_width = 0, + .hid_width = 5, + .parent_map = mmcc_xo_gpll0_gpll0_div_map, + .freq_tbl = ftbl_dp_gtc_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "dp_gtc_clk_src", + .parent_data = mmcc_xo_gpll0_gpll0_div, + .num_parents = 3, + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_dp_link_clk_src[] = { + F(162000000, P_DP_PHY_PLL_LINK_CLK, 2, 0, 0), + F(270000000, P_DP_PHY_PLL_LINK_CLK, 2, 0, 0), + F(540000000, P_DP_PHY_PLL_LINK_CLK, 2, 0, 0), + { } +}; + +static struct clk_rcg2 dp_link_clk_src = { + .cmd_rcgr = 0x2200, + .mnd_width = 0, + .hid_width = 5, + .parent_map = mmcc_xo_dplink_dpvco_map, + .freq_tbl = ftbl_dp_link_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "dp_link_clk_src", + .parent_data = mmcc_xo_dplink_dpvco, + .num_parents = 3, + .ops = &clk_rcg2_ops, + .flags = CLK_GET_RATE_NOCACHE | CLK_SET_RATE_PARENT, + }, +}; + +static struct clk_rcg2 dp_pixel_clk_src = { + .cmd_rcgr = 0x2240, + .mnd_width = 16, + .hid_width = 5, + .parent_map = mmcc_xo_dplink_dpvco_map, + .clkr.hw.init = &(struct clk_init_data){ + .name = "dp_pixel_clk_src", + .parent_data = mmcc_xo_dplink_dpvco, + .num_parents = 3, + .ops = &clk_dp_ops, + .flags = CLK_GET_RATE_NOCACHE | CLK_SET_RATE_PARENT, + }, +}; + +static struct clk_rcg2 esc0_clk_src = { + .cmd_rcgr = 0x2160, + .mnd_width = 0, + .hid_width = 5, + .parent_map = mmcc_xo_dsibyte_map, + .clkr.hw.init = &(struct clk_init_data){ + .name = "esc0_clk_src", + .parent_data = mmcc_xo_dsibyte, + .num_parents = 3, + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 esc1_clk_src = { + .cmd_rcgr = 0x2180, + .mnd_width = 0, + .hid_width = 5, + .parent_map = mmcc_xo_dsibyte_map, + .clkr.hw.init = &(struct clk_init_data){ + .name = "esc1_clk_src", + .parent_data = mmcc_xo_dsibyte, + .num_parents = 3, + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_jpeg0_clk_src[] = { + F(66666667, P_GPLL0_DIV, 4.5, 0, 0), + F(133333333, P_GPLL0, 4.5, 0, 0), + F(219428571, P_MMPLL4, 3.5, 0, 0), + F(320000000, P_MMPLL7, 3, 0, 0), + F(480000000, P_MMPLL7, 2, 0, 0), + { } +}; + +static struct clk_rcg2 jpeg0_clk_src = { + .cmd_rcgr = 0x3500, + .mnd_width = 0, + .hid_width = 5, + .parent_map = mmcc_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div_map, + .freq_tbl = ftbl_jpeg0_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "jpeg0_clk_src", + .parent_data = mmcc_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div, + .num_parents = 7, + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_mclk0_clk_src[] = { + F(4800000, P_XO, 4, 0, 0), + F(6000000, P_GPLL0_DIV, 10, 1, 5), + F(8000000, P_GPLL0_DIV, 1, 2, 75), + F(9600000, P_XO, 2, 0, 0), + F(16666667, P_GPLL0_DIV, 2, 1, 9), + F(19200000, P_XO, 1, 0, 0), + F(24000000, P_MMPLL10, 1, 1, 24), + F(33333333, P_GPLL0_DIV, 1, 1, 9), + F(48000000, P_GPLL0, 1, 2, 25), + F(66666667, P_GPLL0, 1, 1, 9), + { } +}; + +static struct clk_rcg2 mclk0_clk_src = { + .cmd_rcgr = 0x3360, + .mnd_width = 8, + .hid_width = 5, + .parent_map = mmcc_xo_mmpll4_mmpll7_mmpll10_sleep_gpll0_gpll0_div_map, + .freq_tbl = ftbl_mclk0_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "mclk0_clk_src", + .parent_data = mmcc_xo_mmpll4_mmpll7_mmpll10_sleep_gpll0_gpll0_div, + .num_parents = 7, + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 mclk1_clk_src = { + .cmd_rcgr = 0x3390, + .mnd_width = 8, + .hid_width = 5, + .parent_map = mmcc_xo_mmpll4_mmpll7_mmpll10_sleep_gpll0_gpll0_div_map, + .freq_tbl = ftbl_mclk0_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "mclk1_clk_src", + .parent_data = mmcc_xo_mmpll4_mmpll7_mmpll10_sleep_gpll0_gpll0_div, + .num_parents = 7, + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 mclk2_clk_src = { + .cmd_rcgr = 0x33c0, + .mnd_width = 8, + .hid_width = 5, + .parent_map = mmcc_xo_mmpll4_mmpll7_mmpll10_sleep_gpll0_gpll0_div_map, + .freq_tbl = ftbl_mclk0_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "mclk2_clk_src", + .parent_data = mmcc_xo_mmpll4_mmpll7_mmpll10_sleep_gpll0_gpll0_div, + .num_parents = 7, + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 mclk3_clk_src = { + .cmd_rcgr = 0x33f0, + .mnd_width = 8, + .hid_width = 5, + .parent_map = mmcc_xo_mmpll4_mmpll7_mmpll10_sleep_gpll0_gpll0_div_map, + .freq_tbl = ftbl_mclk0_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "mclk3_clk_src", + .parent_data = mmcc_xo_mmpll4_mmpll7_mmpll10_sleep_gpll0_gpll0_div, + .num_parents = 7, + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_mdp_clk_src[] = { + F(100000000, P_GPLL0_DIV, 3, 0, 0), + F(150000000, P_GPLL0_DIV, 2, 0, 0), + F(171428571, P_GPLL0, 3.5, 0, 0), + F(200000000, P_GPLL0, 3, 0, 0), + F(275000000, P_MMPLL5, 3, 0, 0), + F(300000000, P_GPLL0, 2, 0, 0), + F(330000000, P_MMPLL5, 2.5, 0, 0), + F(412500000, P_MMPLL5, 2, 0, 0), + { } +}; + +static struct clk_rcg2 mdp_clk_src = { + .cmd_rcgr = 0x2040, + .mnd_width = 0, + .hid_width = 5, + .parent_map = mmcc_xo_mmpll0_mmpll5_mmpll7_gpll0_gpll0_div_map, + .freq_tbl = ftbl_mdp_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "mdp_clk_src", + .parent_data = mmcc_xo_mmpll0_mmpll5_mmpll7_gpll0_gpll0_div, + .num_parents = 6, + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 pclk0_clk_src = { + .cmd_rcgr = 0x2000, + .mnd_width = 8, + .hid_width = 5, + .parent_map = mmcc_xo_dsi0pll_dsi1pll_map, + .clkr.hw.init = &(struct clk_init_data){ + .name = "pclk0_clk_src", + .parent_data = mmcc_xo_dsi0pll_dsi1pll, + .num_parents = 3, + .ops = &clk_pixel_ops, + .flags = CLK_SET_RATE_PARENT | CLK_GET_RATE_NOCACHE, + }, +}; + +static struct clk_rcg2 pclk1_clk_src = { + .cmd_rcgr = 0x2020, + .mnd_width = 8, + .hid_width = 5, + .parent_map = mmcc_xo_dsi0pll_dsi1pll_map, + .clkr.hw.init = &(struct clk_init_data){ + .name = "pclk1_clk_src", + .parent_data = mmcc_xo_dsi0pll_dsi1pll, + .num_parents = 3, + .ops = &clk_pixel_ops, + .flags = CLK_SET_RATE_PARENT | CLK_GET_RATE_NOCACHE, + }, +}; + +static const struct freq_tbl ftbl_rot_clk_src[] = { + F(171428571, P_GPLL0, 3.5, 0, 0), + F(275000000, P_MMPLL5, 3, 0, 0), + F(300000000, P_GPLL0, 2, 0, 0), + F(330000000, P_MMPLL5, 2.5, 0, 0), + F(412500000, P_MMPLL5, 2, 0, 0), + { } +}; + +static struct clk_rcg2 rot_clk_src = { + .cmd_rcgr = 0x21a0, + .mnd_width = 0, + .hid_width = 5, + .parent_map = mmcc_xo_mmpll0_mmpll5_mmpll7_gpll0_gpll0_div_map, + .freq_tbl = ftbl_rot_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "rot_clk_src", + .parent_data = mmcc_xo_mmpll0_mmpll5_mmpll7_gpll0_gpll0_div, + .num_parents = 6, + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_vfe0_clk_src[] = { + F(120000000, P_GPLL0, 5, 0, 0), + F(200000000, P_GPLL0, 3, 0, 0), + F(256000000, P_MMPLL4, 3, 0, 0), + F(300000000, P_GPLL0, 2, 0, 0), + F(404000000, P_MMPLL0, 2, 0, 0), + F(480000000, P_MMPLL7, 2, 0, 0), + F(540000000, P_MMPLL6, 2, 0, 0), + F(576000000, P_MMPLL10, 1, 0, 0), + { } +}; + +static struct clk_rcg2 vfe0_clk_src = { + .cmd_rcgr = 0x3600, + .mnd_width = 0, + .hid_width = 5, + .parent_map = mmcc_mmpll0_mmpll4_mmpll7_mmpll10_mmpll6_gpll0_map, + .freq_tbl = ftbl_vfe0_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "vfe0_clk_src", + .parent_data = mmcc_mmpll0_mmpll4_mmpll7_mmpll10_mmpll6_gpll0, + .num_parents = 7, + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 vfe1_clk_src = { + .cmd_rcgr = 0x3620, + .mnd_width = 0, + .hid_width = 5, + .parent_map = mmcc_mmpll0_mmpll4_mmpll7_mmpll10_mmpll6_gpll0_map, + .freq_tbl = ftbl_vfe0_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "vfe1_clk_src", + .parent_data = mmcc_mmpll0_mmpll4_mmpll7_mmpll10_mmpll6_gpll0, + .num_parents = 7, + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_video_core_clk_src[] = { + F(133333333, P_GPLL0, 4.5, 0, 0), + F(269333333, P_MMPLL0, 3, 0, 0), + F(320000000, P_MMPLL7, 3, 0, 0), + F(404000000, P_MMPLL0, 2, 0, 0), + F(441600000, P_MMPLL3, 2, 0, 0), + F(518400000, P_MMPLL3, 2, 0, 0), + { } +}; + +static struct clk_rcg2 video_core_clk_src = { + .cmd_rcgr = 0x1000, + .mnd_width = 0, + .hid_width = 5, + .parent_map = mmcc_xo_mmpll0_mmpll8_mmpll3_mmpll6_gpll0_mmpll7_map, + .freq_tbl = ftbl_video_core_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "video_core_clk_src", + .parent_data = mmcc_xo_mmpll0_mmpll8_mmpll3_mmpll6_gpll0_mmpll7, + .num_parents = 7, + .ops = &clk_rcg2_ops, + .flags = CLK_IS_CRITICAL, + }, +}; + +static struct clk_rcg2 vsync_clk_src = { + .cmd_rcgr = 0x2080, + .mnd_width = 0, + .hid_width = 5, + .parent_map = mmcc_xo_gpll0_gpll0_div_map, + .freq_tbl = ftbl_dp_aux_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "vsync_clk_src", + .parent_data = mmcc_xo_gpll0_gpll0_div, + .num_parents = 3, + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_branch bimc_smmu_ahb_clk = { + .halt_reg = 0xe004, + .halt_check = BRANCH_VOTED, + .hwcg_reg = 0xe004, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0xe004, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "bimc_smmu_ahb_clk", + .parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch bimc_smmu_axi_clk = { + .halt_reg = 0xe008, + .halt_check = BRANCH_VOTED, + .hwcg_reg = 0xe008, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0xe008, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "bimc_smmu_axi_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_ahb_clk = { + .halt_reg = 0x348c, + .halt_check = BRANCH_HALT, + .hwcg_reg = 0x348c, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x348c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_ahb_clk", + .parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_cci_ahb_clk = { + .halt_reg = 0x3348, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3348, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_cci_ahb_clk", + .parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_cci_clk = { + .halt_reg = 0x3344, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3344, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_cci_clk", + .parent_hws = (const struct clk_hw *[]){ &cci_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_cpp_ahb_clk = { + .halt_reg = 0x36b4, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x36b4, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_cpp_ahb_clk", + .parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_cpp_axi_clk = { + .halt_reg = 0x36c4, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x36c4, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_cpp_axi_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_cpp_clk = { + .halt_reg = 0x36b0, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x36b0, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_cpp_clk", + .parent_hws = (const struct clk_hw *[]){ &cpp_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_cpp_vbif_ahb_clk = { + .halt_reg = 0x36c8, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x36c8, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_cpp_vbif_ahb_clk", + .parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_csi0_ahb_clk = { + .halt_reg = 0x30bc, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x30bc, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_csi0_ahb_clk", + .parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_csi0_clk = { + .halt_reg = 0x30b4, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x30b4, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_csi0_clk", + .parent_hws = (const struct clk_hw *[]){ &csi0_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_csi0phytimer_clk = { + .halt_reg = 0x3024, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3024, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_csi0phytimer_clk", + .parent_hws = (const struct clk_hw *[]){ &csi0phytimer_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_csi0pix_clk = { + .halt_reg = 0x30e4, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x30e4, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_csi0pix_clk", + .parent_hws = (const struct clk_hw *[]){ &csi0_clk_src.clkr.hw }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_csi0rdi_clk = { + .halt_reg = 0x30d4, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x30d4, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_csi0rdi_clk", + .parent_hws = (const struct clk_hw *[]){ &csi0_clk_src.clkr.hw }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_csi1_ahb_clk = { + .halt_reg = 0x3128, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3128, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_csi1_ahb_clk", + .parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_csi1_clk = { + .halt_reg = 0x3124, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3124, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_csi1_clk", + .parent_hws = (const struct clk_hw *[]){ &csi1_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_csi1phytimer_clk = { + .halt_reg = 0x3054, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3054, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_csi1phytimer_clk", + .parent_hws = (const struct clk_hw *[]){ &csi1phytimer_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_csi1pix_clk = { + .halt_reg = 0x3154, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3154, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_csi1pix_clk", + .parent_hws = (const struct clk_hw *[]){ &csi1_clk_src.clkr.hw }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_csi1rdi_clk = { + .halt_reg = 0x3144, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3144, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_csi1rdi_clk", + .parent_hws = (const struct clk_hw *[]){ &csi1_clk_src.clkr.hw }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_csi2_ahb_clk = { + .halt_reg = 0x3188, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3188, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_csi2_ahb_clk", + .parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_csi2_clk = { + .halt_reg = 0x3184, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3184, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_csi2_clk", + .parent_hws = (const struct clk_hw *[]){ &csi2_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_csi2phytimer_clk = { + .halt_reg = 0x3084, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3084, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_csi2phytimer_clk", + .parent_hws = (const struct clk_hw *[]){ &csi2phytimer_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_csi2pix_clk = { + .halt_reg = 0x31b4, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x31b4, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_csi2pix_clk", + .parent_hws = (const struct clk_hw *[]){ &csi2_clk_src.clkr.hw }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_csi2rdi_clk = { + .halt_reg = 0x31a4, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x31a4, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_csi2rdi_clk", + .parent_hws = (const struct clk_hw *[]){ &csi2_clk_src.clkr.hw }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_csi3_ahb_clk = { + .halt_reg = 0x31e8, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x31e8, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_csi3_ahb_clk", + .parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_csi3_clk = { + .halt_reg = 0x31e4, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x31e4, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_csi3_clk", + .parent_hws = (const struct clk_hw *[]){ &csi3_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_csi3pix_clk = { + .halt_reg = 0x3214, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3214, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_csi3pix_clk", + .parent_hws = (const struct clk_hw *[]){ &csi3_clk_src.clkr.hw }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_csi3rdi_clk = { + .halt_reg = 0x3204, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3204, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_csi3rdi_clk", + .parent_hws = (const struct clk_hw *[]){ &csi3_clk_src.clkr.hw }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_csi_vfe0_clk = { + .halt_reg = 0x3704, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3704, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_csi_vfe0_clk", + .parent_hws = (const struct clk_hw *[]){ &vfe0_clk_src.clkr.hw }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_csi_vfe1_clk = { + .halt_reg = 0x3714, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3714, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_csi_vfe1_clk", + .parent_hws = (const struct clk_hw *[]){ &vfe1_clk_src.clkr.hw }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_csiphy0_clk = { + .halt_reg = 0x3740, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3740, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_csiphy0_clk", + .parent_hws = (const struct clk_hw *[]){ &csiphy_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_csiphy1_clk = { + .halt_reg = 0x3744, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3744, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_csiphy1_clk", + .parent_hws = (const struct clk_hw *[]){ &csiphy_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_csiphy2_clk = { + .halt_reg = 0x3748, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3748, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_csiphy2_clk", + .parent_hws = (const struct clk_hw *[]){ &csiphy_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + + +static struct clk_branch camss_cphy_csid0_clk = { + .halt_reg = 0x3730, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3730, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_cphy_csid0_clk", + .parent_hws = (const struct clk_hw *[]){ &camss_csiphy0_clk.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_cphy_csid1_clk = { + .halt_reg = 0x3734, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3734, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_cphy_csid1_clk", + .parent_hws = (const struct clk_hw *[]){ &camss_csiphy1_clk.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_cphy_csid2_clk = { + .halt_reg = 0x3738, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3738, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_cphy_csid2_clk", + .parent_hws = (const struct clk_hw *[]){ &camss_csiphy2_clk.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_cphy_csid3_clk = { + .halt_reg = 0x373c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x373c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_cphy_csid3_clk", + .parent_hws = (const struct clk_hw *[]){ &csiphy_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_gp0_clk = { + .halt_reg = 0x3444, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3444, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_gp0_clk", + .parent_hws = (const struct clk_hw *[]){ &camss_gp0_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_gp1_clk = { + .halt_reg = 0x3474, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3474, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_gp1_clk", + .parent_hws = (const struct clk_hw *[]){ &camss_gp1_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_ispif_ahb_clk = { + .halt_reg = 0x3224, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3224, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_ispif_ahb_clk", + .parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_jpeg0_clk = { + .halt_reg = 0x35a8, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x35a8, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_jpeg0_clk", + .parent_hws = (const struct clk_hw *[]){ &jpeg0_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_jpeg_ahb_clk = { + .halt_reg = 0x35b4, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x35b4, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_jpeg_ahb_clk", + .parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_jpeg_axi_clk = { + .halt_reg = 0x35b8, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x35b8, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_jpeg_axi_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch throttle_camss_axi_clk = { + .halt_reg = 0x3c3c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3c3c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "throttle_camss_axi_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_mclk0_clk = { + .halt_reg = 0x3384, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3384, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_mclk0_clk", + .parent_hws = (const struct clk_hw *[]){ &mclk0_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_mclk1_clk = { + .halt_reg = 0x33b4, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x33b4, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_mclk1_clk", + .parent_hws = (const struct clk_hw *[]){ &mclk1_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_mclk2_clk = { + .halt_reg = 0x33e4, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x33e4, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_mclk2_clk", + .parent_hws = (const struct clk_hw *[]){ &mclk2_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_mclk3_clk = { + .halt_reg = 0x3414, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3414, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_mclk3_clk", + .parent_hws = (const struct clk_hw *[]){ &mclk3_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_micro_ahb_clk = { + .halt_reg = 0x3494, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3494, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_micro_ahb_clk", + .parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_top_ahb_clk = { + .halt_reg = 0x3484, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3484, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_top_ahb_clk", + .parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_vfe0_ahb_clk = { + .halt_reg = 0x3668, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3668, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_vfe0_ahb_clk", + .parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_vfe0_clk = { + .halt_reg = 0x36a8, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x36a8, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_vfe0_clk", + .parent_hws = (const struct clk_hw *[]){ &vfe0_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_vfe0_stream_clk = { + .halt_reg = 0x3720, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3720, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_vfe0_stream_clk", + .parent_hws = (const struct clk_hw *[]){ &vfe0_clk_src.clkr.hw }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_vfe1_ahb_clk = { + .halt_reg = 0x3678, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3678, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_vfe1_ahb_clk", + .parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_vfe1_clk = { + .halt_reg = 0x36ac, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x36ac, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_vfe1_clk", + .parent_hws = (const struct clk_hw *[]){ &vfe1_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_vfe1_stream_clk = { + .halt_reg = 0x3724, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3724, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_vfe1_stream_clk", + .parent_hws = (const struct clk_hw *[]){ &vfe1_clk_src.clkr.hw }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_vfe_vbif_ahb_clk = { + .halt_reg = 0x36b8, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x36b8, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_vfe_vbif_ahb_clk", + .parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch camss_vfe_vbif_axi_clk = { + .halt_reg = 0x36bc, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x36bc, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "camss_vfe_vbif_axi_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch csiphy_ahb2crif_clk = { + .halt_reg = 0x374c, + .halt_check = BRANCH_HALT, + .hwcg_reg = 0x374c, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x374c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "csiphy_ahb2crif_clk", + .parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch mdss_ahb_clk = { + .halt_reg = 0x2308, + .halt_check = BRANCH_HALT, + .hwcg_reg = 0x8a004, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x2308, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "mdss_ahb_clk", + .parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw }, + .flags = CLK_SET_RATE_PARENT, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static const struct freq_tbl ftbl_axi_clk_src[] = { + F(75000000, P_GPLL0, 8, 0, 0), + F(171428571, P_GPLL0, 3.5, 0, 0), + F(240000000, P_GPLL0, 2.5, 0, 0), + F(323200000, P_MMPLL0, 2.5, 0, 0), + F(406000000, P_MMPLL0, 2, 0, 0), + { } +}; + +/* RO to linux */ +static struct clk_rcg2 axi_clk_src = { + .cmd_rcgr = 0xd000, + .hid_width = 5, + .parent_map = mmcc_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div_map, + .freq_tbl = ftbl_axi_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "axi_clk_src", + .parent_data = mmcc_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div, + .num_parents = 7, + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_branch mdss_axi_clk = { + .halt_reg = 0x2310, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x2310, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "mdss_axi_clk", + .parent_hws = (const struct clk_hw *[]){ &axi_clk_src.clkr.hw }, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch throttle_mdss_axi_clk = { + .halt_reg = 0x246c, + .halt_check = BRANCH_HALT, + .hwcg_reg = 0x246c, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x246c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "throttle_mdss_axi_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch mdss_byte0_clk = { + .halt_reg = 0x233c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x233c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "mdss_byte0_clk", + .parent_hws = (const struct clk_hw *[]){ &byte0_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_regmap_div mdss_byte0_intf_div_clk = { + .reg = 0x237c, + .shift = 0, + .width = 2, + /* + * NOTE: Op does not work for div-3. Current assumption is that div-3 + * is not a recommended setting for this divider. + */ + .clkr = { + .hw.init = &(struct clk_init_data){ + .name = "mdss_byte0_intf_div_clk", + .parent_hws = (const struct clk_hw *[]){ &byte0_clk_src.clkr.hw }, + .num_parents = 1, + .ops = &clk_regmap_div_ops, + .flags = CLK_GET_RATE_NOCACHE, + }, + }, +}; + +static struct clk_branch mdss_byte0_intf_clk = { + .halt_reg = 0x2374, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x2374, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "mdss_byte0_intf_clk", + .parent_hws = (const struct clk_hw *[]){ &mdss_byte0_intf_div_clk.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT | CLK_GET_RATE_NOCACHE, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch mdss_byte1_clk = { + .halt_reg = 0x2340, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x2340, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "mdss_byte1_clk", + .parent_hws = (const struct clk_hw *[]){ &byte1_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_regmap_div mdss_byte1_intf_div_clk = { + .reg = 0x2380, + .shift = 0, + .width = 2, + /* + * NOTE: Op does not work for div-3. Current assumption is that div-3 + * is not a recommended setting for this divider. + */ + .clkr = { + .hw.init = &(struct clk_init_data){ + .name = "mdss_byte1_intf_div_clk", + .parent_hws = (const struct clk_hw *[]){ &byte1_clk_src.clkr.hw }, + .num_parents = 1, + .ops = &clk_regmap_div_ops, + .flags = CLK_GET_RATE_NOCACHE, + }, + }, +}; + +static struct clk_branch mdss_byte1_intf_clk = { + .halt_reg = 0x2378, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x2378, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "mdss_byte1_intf_clk", + .parent_hws = (const struct clk_hw *[]){ &mdss_byte1_intf_div_clk.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT | CLK_GET_RATE_NOCACHE, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch mdss_dp_aux_clk = { + .halt_reg = 0x2364, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x2364, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "mdss_dp_aux_clk", + .parent_hws = (const struct clk_hw *[]){ &dp_aux_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch mdss_dp_crypto_clk = { + .halt_reg = 0x235c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x235c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "mdss_dp_crypto_clk", + .parent_hws = (const struct clk_hw *[]){ &dp_crypto_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch mdss_dp_gtc_clk = { + .halt_reg = 0x2368, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x2368, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "mdss_dp_gtc_clk", + .parent_hws = (const struct clk_hw *[]){ &dp_gtc_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch mdss_dp_link_clk = { + .halt_reg = 0x2354, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x2354, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "mdss_dp_link_clk", + .parent_hws = (const struct clk_hw *[]){ &dp_link_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_GET_RATE_NOCACHE | CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +/* Reset state of MDSS_DP_LINK_INTF_DIV is 0x3 (div-4) */ +static struct clk_branch mdss_dp_link_intf_clk = { + .halt_reg = 0x2358, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x2358, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "mdss_dp_link_intf_clk", + .parent_hws = (const struct clk_hw *[]){ &dp_link_clk_src.clkr.hw }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch mdss_dp_pixel_clk = { + .halt_reg = 0x2360, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x2360, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "mdss_dp_pixel_clk", + .parent_hws = (const struct clk_hw *[]){ &dp_pixel_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_GET_RATE_NOCACHE | CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch mdss_esc0_clk = { + .halt_reg = 0x2344, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x2344, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "mdss_esc0_clk", + .parent_hws = (const struct clk_hw *[]){ &esc0_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch mdss_esc1_clk = { + .halt_reg = 0x2348, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x2348, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "mdss_esc1_clk", + .parent_hws = (const struct clk_hw *[]){ &esc1_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch mdss_hdmi_dp_ahb_clk = { + .halt_reg = 0x230c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x230c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "mdss_hdmi_dp_ahb_clk", + .parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch mdss_mdp_clk = { + .halt_reg = 0x231c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x231c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "mdss_mdp_clk", + .parent_hws = (const struct clk_hw *[]){ &mdp_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch mdss_pclk0_clk = { + .halt_reg = 0x2314, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x2314, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "mdss_pclk0_clk", + .parent_hws = (const struct clk_hw *[]){ &pclk0_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch mdss_pclk1_clk = { + .halt_reg = 0x2318, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x2318, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "mdss_pclk1_clk", + .parent_hws = (const struct clk_hw *[]){ &pclk1_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch mdss_rot_clk = { + .halt_reg = 0x2350, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x2350, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "mdss_rot_clk", + .parent_hws = (const struct clk_hw *[]){ &rot_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch mdss_vsync_clk = { + .halt_reg = 0x2328, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x2328, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "mdss_vsync_clk", + .parent_hws = (const struct clk_hw *[]){ &vsync_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch mnoc_ahb_clk = { + .halt_reg = 0x5024, + .halt_check = BRANCH_VOTED, + .clkr = { + .enable_reg = 0x5024, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "mnoc_ahb_clk", + .parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch misc_ahb_clk = { + .halt_reg = 0x328, + .halt_check = BRANCH_HALT, + .hwcg_reg = 0x328, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x328, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "misc_ahb_clk", + /* + * Dependency to be enabled before the branch is + * enabled. + */ + .parent_hws = (const struct clk_hw *[]){ &mnoc_ahb_clk.clkr.hw }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch misc_cxo_clk = { + .halt_reg = 0x324, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x324, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "misc_cxo_clk", + .parent_data = &(const struct clk_parent_data){ + .fw_name = "xo", + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch snoc_dvm_axi_clk = { + .halt_reg = 0xe040, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0xe040, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "snoc_dvm_axi_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch video_ahb_clk = { + .halt_reg = 0x1030, + .halt_check = BRANCH_HALT, + .hwcg_reg = 0x1030, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x1030, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "video_ahb_clk", + .parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch video_axi_clk = { + .halt_reg = 0x1034, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x1034, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "video_axi_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch throttle_video_axi_clk = { + .halt_reg = 0x118c, + .halt_check = BRANCH_HALT, + .hwcg_reg = 0x118c, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x118c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "throttle_video_axi_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch video_core_clk = { + .halt_reg = 0x1028, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x1028, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "video_core_clk", + .parent_hws = (const struct clk_hw *[]){ &video_core_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch video_subcore0_clk = { + .halt_reg = 0x1048, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x1048, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "video_subcore0_clk", + .parent_hws = (const struct clk_hw *[]){ &video_core_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT | CLK_GET_RATE_NOCACHE, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct gdsc venus_gdsc = { + .gdscr = 0x1024, + .pd = { + .name = "venus", + }, + .pwrsts = PWRSTS_OFF_ON, +}; + +static struct gdsc venus_core0_gdsc = { + .gdscr = 0x1040, + .pd = { + .name = "venus_core0", + }, + .parent = &venus_gdsc.pd, + .pwrsts = PWRSTS_OFF_ON, +}; + +static struct gdsc mdss_gdsc = { + .gdscr = 0x2304, + .pd = { + .name = "mdss", + }, + .cxcs = (unsigned int []){ 0x2040 }, + .cxc_count = 1, + .pwrsts = PWRSTS_OFF_ON, +}; + +static struct gdsc camss_top_gdsc = { + .gdscr = 0x34a0, + .pd = { + .name = "camss_top", + }, + .pwrsts = PWRSTS_OFF_ON, +}; + +static struct gdsc camss_vfe0_gdsc = { + .gdscr = 0x3664, + .pd = { + .name = "camss_vfe0", + }, + .parent = &camss_top_gdsc.pd, + .pwrsts = PWRSTS_OFF_ON, +}; + +static struct gdsc camss_vfe1_gdsc = { + .gdscr = 0x3674, + .pd = { + .name = "camss_vfe1_gdsc", + }, + .parent = &camss_top_gdsc.pd, + .pwrsts = PWRSTS_OFF_ON, +}; + +static struct gdsc camss_cpp_gdsc = { + .gdscr = 0x36d4, + .pd = { + .name = "camss_cpp", + }, + .parent = &camss_top_gdsc.pd, + .pwrsts = PWRSTS_OFF_ON, +}; + +/* This GDSC seems to hang the whole multimedia subsystem. +static struct gdsc bimc_smmu_gdsc = { + .gdscr = 0xe020, + .gds_hw_ctrl = 0xe024, + .pd = { + .name = "bimc_smmu", + }, + .pwrsts = PWRSTS_OFF_ON, + .parent = &bimc_smmu_gdsc.pd, + .flags = HW_CTRL, +}; +*/ + +static struct clk_regmap *mmcc_660_clocks[] = { + [AHB_CLK_SRC] = &ahb_clk_src.clkr, + [BYTE0_CLK_SRC] = &byte0_clk_src.clkr, + [BYTE1_CLK_SRC] = &byte1_clk_src.clkr, + [CAMSS_GP0_CLK_SRC] = &camss_gp0_clk_src.clkr, + [CAMSS_GP1_CLK_SRC] = &camss_gp1_clk_src.clkr, + [CCI_CLK_SRC] = &cci_clk_src.clkr, + [CPP_CLK_SRC] = &cpp_clk_src.clkr, + [CSI0_CLK_SRC] = &csi0_clk_src.clkr, + [CSI0PHYTIMER_CLK_SRC] = &csi0phytimer_clk_src.clkr, + [CSI1_CLK_SRC] = &csi1_clk_src.clkr, + [CSI1PHYTIMER_CLK_SRC] = &csi1phytimer_clk_src.clkr, + [CSI2_CLK_SRC] = &csi2_clk_src.clkr, + [CSI2PHYTIMER_CLK_SRC] = &csi2phytimer_clk_src.clkr, + [CSI3_CLK_SRC] = &csi3_clk_src.clkr, + [CSIPHY_CLK_SRC] = &csiphy_clk_src.clkr, + [DP_AUX_CLK_SRC] = &dp_aux_clk_src.clkr, + [DP_CRYPTO_CLK_SRC] = &dp_crypto_clk_src.clkr, + [DP_GTC_CLK_SRC] = &dp_gtc_clk_src.clkr, + [DP_LINK_CLK_SRC] = &dp_link_clk_src.clkr, + [DP_PIXEL_CLK_SRC] = &dp_pixel_clk_src.clkr, + [ESC0_CLK_SRC] = &esc0_clk_src.clkr, + [ESC1_CLK_SRC] = &esc1_clk_src.clkr, + [JPEG0_CLK_SRC] = &jpeg0_clk_src.clkr, + [MCLK0_CLK_SRC] = &mclk0_clk_src.clkr, + [MCLK1_CLK_SRC] = &mclk1_clk_src.clkr, + [MCLK2_CLK_SRC] = &mclk2_clk_src.clkr, + [MCLK3_CLK_SRC] = &mclk3_clk_src.clkr, + [MDP_CLK_SRC] = &mdp_clk_src.clkr, + [MMPLL0_PLL] = &mmpll0.clkr, + [MMPLL10_PLL] = &mmpll10.clkr, + [MMPLL3_PLL] = &mmpll3.clkr, + [MMPLL4_PLL] = &mmpll4.clkr, + [MMPLL5_PLL] = &mmpll5.clkr, + [MMPLL6_PLL] = &mmpll6.clkr, + [MMPLL7_PLL] = &mmpll7.clkr, + [MMPLL8_PLL] = &mmpll8.clkr, + [BIMC_SMMU_AHB_CLK] = &bimc_smmu_ahb_clk.clkr, + [BIMC_SMMU_AXI_CLK] = &bimc_smmu_axi_clk.clkr, + [CAMSS_AHB_CLK] = &camss_ahb_clk.clkr, + [CAMSS_CCI_AHB_CLK] = &camss_cci_ahb_clk.clkr, + [CAMSS_CCI_CLK] = &camss_cci_clk.clkr, + [CAMSS_CPHY_CSID0_CLK] = &camss_cphy_csid0_clk.clkr, + [CAMSS_CPHY_CSID1_CLK] = &camss_cphy_csid1_clk.clkr, + [CAMSS_CPHY_CSID2_CLK] = &camss_cphy_csid2_clk.clkr, + [CAMSS_CPHY_CSID3_CLK] = &camss_cphy_csid3_clk.clkr, + [CAMSS_CPP_AHB_CLK] = &camss_cpp_ahb_clk.clkr, + [CAMSS_CPP_AXI_CLK] = &camss_cpp_axi_clk.clkr, + [CAMSS_CPP_CLK] = &camss_cpp_clk.clkr, + [CAMSS_CPP_VBIF_AHB_CLK] = &camss_cpp_vbif_ahb_clk.clkr, + [CAMSS_CSI0_AHB_CLK] = &camss_csi0_ahb_clk.clkr, + [CAMSS_CSI0_CLK] = &camss_csi0_clk.clkr, + [CAMSS_CSI0PHYTIMER_CLK] = &camss_csi0phytimer_clk.clkr, + [CAMSS_CSI0PIX_CLK] = &camss_csi0pix_clk.clkr, + [CAMSS_CSI0RDI_CLK] = &camss_csi0rdi_clk.clkr, + [CAMSS_CSI1_AHB_CLK] = &camss_csi1_ahb_clk.clkr, + [CAMSS_CSI1_CLK] = &camss_csi1_clk.clkr, + [CAMSS_CSI1PHYTIMER_CLK] = &camss_csi1phytimer_clk.clkr, + [CAMSS_CSI1PIX_CLK] = &camss_csi1pix_clk.clkr, + [CAMSS_CSI1RDI_CLK] = &camss_csi1rdi_clk.clkr, + [CAMSS_CSI2_AHB_CLK] = &camss_csi2_ahb_clk.clkr, + [CAMSS_CSI2_CLK] = &camss_csi2_clk.clkr, + [CAMSS_CSI2PHYTIMER_CLK] = &camss_csi2phytimer_clk.clkr, + [CAMSS_CSI2PIX_CLK] = &camss_csi2pix_clk.clkr, + [CAMSS_CSI2RDI_CLK] = &camss_csi2rdi_clk.clkr, + [CAMSS_CSI3_AHB_CLK] = &camss_csi3_ahb_clk.clkr, + [CAMSS_CSI3_CLK] = &camss_csi3_clk.clkr, + [CAMSS_CSI3PIX_CLK] = &camss_csi3pix_clk.clkr, + [CAMSS_CSI3RDI_CLK] = &camss_csi3rdi_clk.clkr, + [CAMSS_CSI_VFE0_CLK] = &camss_csi_vfe0_clk.clkr, + [CAMSS_CSI_VFE1_CLK] = &camss_csi_vfe1_clk.clkr, + [CAMSS_CSIPHY0_CLK] = &camss_csiphy0_clk.clkr, + [CAMSS_CSIPHY1_CLK] = &camss_csiphy1_clk.clkr, + [CAMSS_CSIPHY2_CLK] = &camss_csiphy2_clk.clkr, + [CAMSS_GP0_CLK] = &camss_gp0_clk.clkr, + [CAMSS_GP1_CLK] = &camss_gp1_clk.clkr, + [CAMSS_ISPIF_AHB_CLK] = &camss_ispif_ahb_clk.clkr, + [CAMSS_JPEG0_CLK] = &camss_jpeg0_clk.clkr, + [CAMSS_JPEG_AHB_CLK] = &camss_jpeg_ahb_clk.clkr, + [CAMSS_JPEG_AXI_CLK] = &camss_jpeg_axi_clk.clkr, + [CAMSS_MCLK0_CLK] = &camss_mclk0_clk.clkr, + [CAMSS_MCLK1_CLK] = &camss_mclk1_clk.clkr, + [CAMSS_MCLK2_CLK] = &camss_mclk2_clk.clkr, + [CAMSS_MCLK3_CLK] = &camss_mclk3_clk.clkr, + [CAMSS_MICRO_AHB_CLK] = &camss_micro_ahb_clk.clkr, + [CAMSS_TOP_AHB_CLK] = &camss_top_ahb_clk.clkr, + [CAMSS_VFE0_AHB_CLK] = &camss_vfe0_ahb_clk.clkr, + [CAMSS_VFE0_CLK] = &camss_vfe0_clk.clkr, + [CAMSS_VFE0_STREAM_CLK] = &camss_vfe0_stream_clk.clkr, + [CAMSS_VFE1_AHB_CLK] = &camss_vfe1_ahb_clk.clkr, + [CAMSS_VFE1_CLK] = &camss_vfe1_clk.clkr, + [CAMSS_VFE1_STREAM_CLK] = &camss_vfe1_stream_clk.clkr, + [CAMSS_VFE_VBIF_AHB_CLK] = &camss_vfe_vbif_ahb_clk.clkr, + [CAMSS_VFE_VBIF_AXI_CLK] = &camss_vfe_vbif_axi_clk.clkr, + [CSIPHY_AHB2CRIF_CLK] = &csiphy_ahb2crif_clk.clkr, + [MDSS_AHB_CLK] = &mdss_ahb_clk.clkr, + [MDSS_AXI_CLK] = &mdss_axi_clk.clkr, + [MDSS_BYTE0_CLK] = &mdss_byte0_clk.clkr, + [MDSS_BYTE0_INTF_CLK] = &mdss_byte0_intf_clk.clkr, + [MDSS_BYTE0_INTF_DIV_CLK] = &mdss_byte0_intf_div_clk.clkr, + [MDSS_BYTE1_CLK] = &mdss_byte1_clk.clkr, + [MDSS_BYTE1_INTF_CLK] = &mdss_byte1_intf_clk.clkr, + [MDSS_DP_AUX_CLK] = &mdss_dp_aux_clk.clkr, + [MDSS_DP_CRYPTO_CLK] = &mdss_dp_crypto_clk.clkr, + [MDSS_DP_GTC_CLK] = &mdss_dp_gtc_clk.clkr, + [MDSS_DP_LINK_CLK] = &mdss_dp_link_clk.clkr, + [MDSS_DP_LINK_INTF_CLK] = &mdss_dp_link_intf_clk.clkr, + [MDSS_DP_PIXEL_CLK] = &mdss_dp_pixel_clk.clkr, + [MDSS_ESC0_CLK] = &mdss_esc0_clk.clkr, + [MDSS_ESC1_CLK] = &mdss_esc1_clk.clkr, + [MDSS_HDMI_DP_AHB_CLK] = &mdss_hdmi_dp_ahb_clk.clkr, + [MDSS_MDP_CLK] = &mdss_mdp_clk.clkr, + [MDSS_PCLK0_CLK] = &mdss_pclk0_clk.clkr, + [MDSS_PCLK1_CLK] = &mdss_pclk1_clk.clkr, + [MDSS_ROT_CLK] = &mdss_rot_clk.clkr, + [MDSS_VSYNC_CLK] = &mdss_vsync_clk.clkr, + [MISC_AHB_CLK] = &misc_ahb_clk.clkr, + [MISC_CXO_CLK] = &misc_cxo_clk.clkr, + [MNOC_AHB_CLK] = &mnoc_ahb_clk.clkr, + [SNOC_DVM_AXI_CLK] = &snoc_dvm_axi_clk.clkr, + [THROTTLE_CAMSS_AXI_CLK] = &throttle_camss_axi_clk.clkr, + [THROTTLE_MDSS_AXI_CLK] = &throttle_mdss_axi_clk.clkr, + [THROTTLE_VIDEO_AXI_CLK] = &throttle_video_axi_clk.clkr, + [VIDEO_AHB_CLK] = &video_ahb_clk.clkr, + [VIDEO_AXI_CLK] = &video_axi_clk.clkr, + [VIDEO_CORE_CLK] = &video_core_clk.clkr, + [VIDEO_SUBCORE0_CLK] = &video_subcore0_clk.clkr, + [PCLK0_CLK_SRC] = &pclk0_clk_src.clkr, + [PCLK1_CLK_SRC] = &pclk1_clk_src.clkr, + [ROT_CLK_SRC] = &rot_clk_src.clkr, + [VFE0_CLK_SRC] = &vfe0_clk_src.clkr, + [VFE1_CLK_SRC] = &vfe1_clk_src.clkr, + [VIDEO_CORE_CLK_SRC] = &video_core_clk_src.clkr, + [VSYNC_CLK_SRC] = &vsync_clk_src.clkr, + [MDSS_BYTE1_INTF_DIV_CLK] = &mdss_byte1_intf_div_clk.clkr, + [AXI_CLK_SRC] = &axi_clk_src.clkr, +}; + +static struct gdsc *mmcc_sdm660_gdscs[] = { + [VENUS_GDSC] = &venus_gdsc, + [VENUS_CORE0_GDSC] = &venus_core0_gdsc, + [MDSS_GDSC] = &mdss_gdsc, + [CAMSS_TOP_GDSC] = &camss_top_gdsc, + [CAMSS_VFE0_GDSC] = &camss_vfe0_gdsc, + [CAMSS_VFE1_GDSC] = &camss_vfe1_gdsc, + [CAMSS_CPP_GDSC] = &camss_cpp_gdsc, +}; + +static const struct qcom_reset_map mmcc_660_resets[] = { + [CAMSS_MICRO_BCR] = { 0x3490 }, +}; + +static const struct regmap_config mmcc_660_regmap_config = { + .reg_bits = 32, + .reg_stride = 4, + .val_bits = 32, + .max_register = 0x40000, + .fast_io = true, +}; + +static const struct qcom_cc_desc mmcc_660_desc = { + .config = &mmcc_660_regmap_config, + .clks = mmcc_660_clocks, + .num_clks = ARRAY_SIZE(mmcc_660_clocks), + .resets = mmcc_660_resets, + .num_resets = ARRAY_SIZE(mmcc_660_resets), + .gdscs = mmcc_sdm660_gdscs, + .num_gdscs = ARRAY_SIZE(mmcc_sdm660_gdscs), +}; + +static const struct of_device_id mmcc_660_match_table[] = { + { .compatible = "qcom,mmcc-sdm660" }, + { .compatible = "qcom,mmcc-sdm630", .data = (void *)1UL }, + { } +}; +MODULE_DEVICE_TABLE(of, mmcc_660_match_table); + +static void sdm630_clock_override(void) +{ + /* SDM630 has only one DSI */ + mmcc_660_desc.clks[BYTE1_CLK_SRC] = NULL; + mmcc_660_desc.clks[MDSS_BYTE1_CLK] = NULL; + mmcc_660_desc.clks[MDSS_BYTE1_INTF_DIV_CLK] = NULL; + mmcc_660_desc.clks[MDSS_BYTE1_INTF_CLK] = NULL; + mmcc_660_desc.clks[ESC1_CLK_SRC] = NULL; + mmcc_660_desc.clks[MDSS_ESC1_CLK] = NULL; + mmcc_660_desc.clks[PCLK1_CLK_SRC] = NULL; + mmcc_660_desc.clks[MDSS_PCLK1_CLK] = NULL; +} + +static int mmcc_660_probe(struct platform_device *pdev) +{ + const struct of_device_id *id; + struct regmap *regmap; + bool is_sdm630; + + id = of_match_device(mmcc_660_match_table, &pdev->dev); + if (!id) + return -ENODEV; + is_sdm630 = !!(id->data); + + regmap = qcom_cc_map(pdev, &mmcc_660_desc); + if (IS_ERR(regmap)) + return PTR_ERR(regmap); + + if (is_sdm630) + sdm630_clock_override(); + + clk_alpha_pll_configure(&mmpll3, regmap, &mmpll3_config); + clk_alpha_pll_configure(&mmpll4, regmap, &mmpll4_config); + clk_alpha_pll_configure(&mmpll5, regmap, &mmpll5_config); + clk_alpha_pll_configure(&mmpll7, regmap, &mmpll7_config); + clk_alpha_pll_configure(&mmpll8, regmap, &mmpll8_config); + clk_alpha_pll_configure(&mmpll10, regmap, &mmpll10_config); + + return qcom_cc_really_probe(pdev, &mmcc_660_desc, regmap); +} + +static struct platform_driver mmcc_660_driver = { + .probe = mmcc_660_probe, + .driver = { + .name = "mmcc-sdm660", + .of_match_table = mmcc_660_match_table, + }, +}; +module_platform_driver(mmcc_660_driver); + +MODULE_DESCRIPTION("Qualcomm SDM630/SDM660 MMCC driver"); +MODULE_LICENSE("GPL v2"); diff --git a/include/dt-bindings/clock/qcom,mmcc-sdm660.h b/include/dt-bindings/clock/qcom,mmcc-sdm660.h new file mode 100644 index 000000000000..f9dbc21cb5c7 --- /dev/null +++ b/include/dt-bindings/clock/qcom,mmcc-sdm660.h @@ -0,0 +1,162 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2020, The Linux Foundation. All rights reserved. + */ + +#ifndef _DT_BINDINGS_CLK_MSM_MMCC_660_H +#define _DT_BINDINGS_CLK_MSM_MMCC_660_H + +#define AHB_CLK_SRC 0 +#define BYTE0_CLK_SRC 1 +#define BYTE1_CLK_SRC 2 +#define CAMSS_GP0_CLK_SRC 3 +#define CAMSS_GP1_CLK_SRC 4 +#define CCI_CLK_SRC 5 +#define CPP_CLK_SRC 6 +#define CSI0_CLK_SRC 7 +#define CSI0PHYTIMER_CLK_SRC 8 +#define CSI1_CLK_SRC 9 +#define CSI1PHYTIMER_CLK_SRC 10 +#define CSI2_CLK_SRC 11 +#define CSI2PHYTIMER_CLK_SRC 12 +#define CSI3_CLK_SRC 13 +#define CSIPHY_CLK_SRC 14 +#define DP_AUX_CLK_SRC 15 +#define DP_CRYPTO_CLK_SRC 16 +#define DP_GTC_CLK_SRC 17 +#define DP_LINK_CLK_SRC 18 +#define DP_PIXEL_CLK_SRC 19 +#define ESC0_CLK_SRC 20 +#define ESC1_CLK_SRC 21 +#define JPEG0_CLK_SRC 22 +#define MCLK0_CLK_SRC 23 +#define MCLK1_CLK_SRC 24 +#define MCLK2_CLK_SRC 25 +#define MCLK3_CLK_SRC 26 +#define MDP_CLK_SRC 27 +#define MMPLL0_PLL 28 +#define MMPLL10_PLL 29 +#define MMPLL1_PLL 30 +#define MMPLL3_PLL 31 +#define MMPLL4_PLL 32 +#define MMPLL5_PLL 33 +#define MMPLL6_PLL 34 +#define MMPLL7_PLL 35 +#define MMPLL8_PLL 36 +#define BIMC_SMMU_AHB_CLK 37 +#define BIMC_SMMU_AXI_CLK 38 +#define CAMSS_AHB_CLK 39 +#define CAMSS_CCI_AHB_CLK 40 +#define CAMSS_CCI_CLK 41 +#define CAMSS_CPHY_CSID0_CLK 42 +#define CAMSS_CPHY_CSID1_CLK 43 +#define CAMSS_CPHY_CSID2_CLK 44 +#define CAMSS_CPHY_CSID3_CLK 45 +#define CAMSS_CPP_AHB_CLK 46 +#define CAMSS_CPP_AXI_CLK 47 +#define CAMSS_CPP_CLK 48 +#define CAMSS_CPP_VBIF_AHB_CLK 49 +#define CAMSS_CSI0_AHB_CLK 50 +#define CAMSS_CSI0_CLK 51 +#define CAMSS_CSI0PHYTIMER_CLK 52 +#define CAMSS_CSI0PIX_CLK 53 +#define CAMSS_CSI0RDI_CLK 54 +#define CAMSS_CSI1_AHB_CLK 55 +#define CAMSS_CSI1_CLK 56 +#define CAMSS_CSI1PHYTIMER_CLK 57 +#define CAMSS_CSI1PIX_CLK 58 +#define CAMSS_CSI1RDI_CLK 59 +#define CAMSS_CSI2_AHB_CLK 60 +#define CAMSS_CSI2_CLK 61 +#define CAMSS_CSI2PHYTIMER_CLK 62 +#define CAMSS_CSI2PIX_CLK 63 +#define CAMSS_CSI2RDI_CLK 64 +#define CAMSS_CSI3_AHB_CLK 65 +#define CAMSS_CSI3_CLK 66 +#define CAMSS_CSI3PIX_CLK 67 +#define CAMSS_CSI3RDI_CLK 68 +#define CAMSS_CSI_VFE0_CLK 69 +#define CAMSS_CSI_VFE1_CLK 70 +#define CAMSS_CSIPHY0_CLK 71 +#define CAMSS_CSIPHY1_CLK 72 +#define CAMSS_CSIPHY2_CLK 73 +#define CAMSS_GP0_CLK 74 +#define CAMSS_GP1_CLK 75 +#define CAMSS_ISPIF_AHB_CLK 76 +#define CAMSS_JPEG0_CLK 77 +#define CAMSS_JPEG_AHB_CLK 78 +#define CAMSS_JPEG_AXI_CLK 79 +#define CAMSS_MCLK0_CLK 80 +#define CAMSS_MCLK1_CLK 81 +#define CAMSS_MCLK2_CLK 82 +#define CAMSS_MCLK3_CLK 83 +#define CAMSS_MICRO_AHB_CLK 84 +#define CAMSS_TOP_AHB_CLK 85 +#define CAMSS_VFE0_AHB_CLK 86 +#define CAMSS_VFE0_CLK 87 +#define CAMSS_VFE0_STREAM_CLK 88 +#define CAMSS_VFE1_AHB_CLK 89 +#define CAMSS_VFE1_CLK 90 +#define CAMSS_VFE1_STREAM_CLK 91 +#define CAMSS_VFE_VBIF_AHB_CLK 92 +#define CAMSS_VFE_VBIF_AXI_CLK 93 +#define CSIPHY_AHB2CRIF_CLK 94 +#define CXO_CLK 95 +#define MDSS_AHB_CLK 96 +#define MDSS_AXI_CLK 97 +#define MDSS_BYTE0_CLK 98 +#define MDSS_BYTE0_INTF_CLK 99 +#define MDSS_BYTE0_INTF_DIV_CLK 100 +#define MDSS_BYTE1_CLK 101 +#define MDSS_BYTE1_INTF_CLK 102 +#define MDSS_DP_AUX_CLK 103 +#define MDSS_DP_CRYPTO_CLK 104 +#define MDSS_DP_GTC_CLK 105 +#define MDSS_DP_LINK_CLK 106 +#define MDSS_DP_LINK_INTF_CLK 107 +#define MDSS_DP_PIXEL_CLK 108 +#define MDSS_ESC0_CLK 109 +#define MDSS_ESC1_CLK 110 +#define MDSS_HDMI_DP_AHB_CLK 111 +#define MDSS_MDP_CLK 112 +#define MDSS_PCLK0_CLK 113 +#define MDSS_PCLK1_CLK 114 +#define MDSS_ROT_CLK 115 +#define MDSS_VSYNC_CLK 116 +#define MISC_AHB_CLK 117 +#define MISC_CXO_CLK 118 +#define MNOC_AHB_CLK 119 +#define SNOC_DVM_AXI_CLK 120 +#define THROTTLE_CAMSS_AHB_CLK 121 +#define THROTTLE_CAMSS_AXI_CLK 122 +#define THROTTLE_MDSS_AHB_CLK 123 +#define THROTTLE_MDSS_AXI_CLK 124 +#define THROTTLE_VIDEO_AHB_CLK 125 +#define THROTTLE_VIDEO_AXI_CLK 126 +#define VIDEO_AHB_CLK 127 +#define VIDEO_AXI_CLK 128 +#define VIDEO_CORE_CLK 129 +#define VIDEO_SUBCORE0_CLK 130 +#define PCLK0_CLK_SRC 131 +#define PCLK1_CLK_SRC 132 +#define ROT_CLK_SRC 133 +#define VFE0_CLK_SRC 134 +#define VFE1_CLK_SRC 135 +#define VIDEO_CORE_CLK_SRC 136 +#define VSYNC_CLK_SRC 137 +#define MDSS_BYTE1_INTF_DIV_CLK 138 +#define AXI_CLK_SRC 139 + +#define VENUS_GDSC 0 +#define VENUS_CORE0_GDSC 1 +#define MDSS_GDSC 2 +#define CAMSS_TOP_GDSC 3 +#define CAMSS_VFE0_GDSC 4 +#define CAMSS_VFE1_GDSC 5 +#define CAMSS_CPP_GDSC 6 +#define BIMC_SMMU_GDSC 7 + +#define CAMSS_MICRO_BCR 0 + +#endif + -- cgit v1.2.3 From 79b5d1fc93a1f114a0974a076b5a25ca64b37b0f Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Wed, 13 Jan 2021 19:38:16 +0100 Subject: clk: qcom: Add SDM660 GPU Clock Controller (GPUCC) driver The GPUCC manages the clocks for the Adreno GPU found on the SDM630, SDM636, SDM660 SoCs. Signed-off-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20210113183817.447866-9-angelogioacchino.delregno@somainline.org Signed-off-by: Stephen Boyd --- drivers/clk/qcom/Kconfig | 9 + drivers/clk/qcom/Makefile | 1 + drivers/clk/qcom/gpucc-sdm660.c | 349 ++++++++++++++++++++++++++ include/dt-bindings/clock/qcom,gpucc-sdm660.h | 28 +++ 4 files changed, 387 insertions(+) create mode 100644 drivers/clk/qcom/gpucc-sdm660.c create mode 100644 include/dt-bindings/clock/qcom,gpucc-sdm660.h (limited to 'include') diff --git a/drivers/clk/qcom/Kconfig b/drivers/clk/qcom/Kconfig index f514881686d3..2f9ec28f1224 100644 --- a/drivers/clk/qcom/Kconfig +++ b/drivers/clk/qcom/Kconfig @@ -401,6 +401,15 @@ config SDM_MMCC_660 Say Y if you want to support multimedia devices such as display, graphics, video encode/decode, camera, etc. +config SDM_GPUCC_660 + tristate "SDM660 Graphics Clock Controller" + select SDM_GCC_660 + select QCOM_GDSC + help + Support for the graphics clock controller on SDM630/636/660 devices. + Say Y if you want to support graphics controller devices and + functionality such as 3D graphics + config QCS_TURING_404 tristate "QCS404 Turing Clock Controller" help diff --git a/drivers/clk/qcom/Makefile b/drivers/clk/qcom/Makefile index a01cd4076ce3..9d1b87980633 100644 --- a/drivers/clk/qcom/Makefile +++ b/drivers/clk/qcom/Makefile @@ -66,6 +66,7 @@ obj-$(CONFIG_SDM_CAMCC_845) += camcc-sdm845.o obj-$(CONFIG_SDM_DISPCC_845) += dispcc-sdm845.o obj-$(CONFIG_SDM_GCC_660) += gcc-sdm660.o obj-$(CONFIG_SDM_MMCC_660) += mmcc-sdm660.o +obj-$(CONFIG_SDM_GPUCC_660) += gpucc-sdm660.o obj-$(CONFIG_SDM_GCC_845) += gcc-sdm845.o obj-$(CONFIG_SDM_GPUCC_845) += gpucc-sdm845.o obj-$(CONFIG_SDM_LPASSCC_845) += lpasscc-sdm845.o diff --git a/drivers/clk/qcom/gpucc-sdm660.c b/drivers/clk/qcom/gpucc-sdm660.c new file mode 100644 index 000000000000..1ebcceb3a50d --- /dev/null +++ b/drivers/clk/qcom/gpucc-sdm660.c @@ -0,0 +1,349 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2020, The Linux Foundation. All rights reserved. + * Copyright (c) 2020, AngeloGioacchino Del Regno + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "clk-alpha-pll.h" +#include "common.h" +#include "clk-regmap.h" +#include "clk-pll.h" +#include "clk-rcg.h" +#include "clk-branch.h" +#include "gdsc.h" +#include "reset.h" + +enum { + P_GPU_XO, + P_CORE_BI_PLL_TEST_SE, + P_GPLL0_OUT_MAIN, + P_GPLL0_OUT_MAIN_DIV, + P_GPU_PLL0_PLL_OUT_MAIN, + P_GPU_PLL1_PLL_OUT_MAIN, +}; + +static struct clk_branch gpucc_cxo_clk = { + .halt_reg = 0x1020, + .clkr = { + .enable_reg = 0x1020, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gpucc_cxo_clk", + .parent_data = &(const struct clk_parent_data){ + .fw_name = "xo", + .name = "xo" + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_IS_CRITICAL, + }, + }, +}; + +static struct pll_vco gpu_vco[] = { + { 1000000000, 2000000000, 0 }, + { 500000000, 1000000000, 2 }, + { 250000000, 500000000, 3 }, +}; + +static struct clk_alpha_pll gpu_pll0_pll_out_main = { + .offset = 0x0, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .vco_table = gpu_vco, + .num_vco = ARRAY_SIZE(gpu_vco), + .clkr.hw.init = &(struct clk_init_data){ + .name = "gpu_pll0_pll_out_main", + .parent_data = &(const struct clk_parent_data){ + .hw = &gpucc_cxo_clk.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_alpha_pll_ops, + }, +}; + +static struct clk_alpha_pll gpu_pll1_pll_out_main = { + .offset = 0x40, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .vco_table = gpu_vco, + .num_vco = ARRAY_SIZE(gpu_vco), + .clkr.hw.init = &(struct clk_init_data){ + .name = "gpu_pll1_pll_out_main", + .parent_data = &(const struct clk_parent_data){ + .hw = &gpucc_cxo_clk.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_alpha_pll_ops, + }, +}; + +static const struct parent_map gpucc_parent_map_1[] = { + { P_GPU_XO, 0 }, + { P_GPU_PLL0_PLL_OUT_MAIN, 1 }, + { P_GPU_PLL1_PLL_OUT_MAIN, 3 }, + { P_GPLL0_OUT_MAIN, 5 }, +}; + +static const struct clk_parent_data gpucc_parent_data_1[] = { + { .hw = &gpucc_cxo_clk.clkr.hw }, + { .hw = &gpu_pll0_pll_out_main.clkr.hw }, + { .hw = &gpu_pll1_pll_out_main.clkr.hw }, + { .fw_name = "gcc_gpu_gpll0_clk", .name = "gcc_gpu_gpll0_clk" }, +}; + +static struct clk_rcg2_gfx3d gfx3d_clk_src = { + .div = 2, + .rcg = { + .cmd_rcgr = 0x1070, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gpucc_parent_map_1, + .clkr.hw.init = &(struct clk_init_data){ + .name = "gfx3d_clk_src", + .parent_data = gpucc_parent_data_1, + .num_parents = 4, + .ops = &clk_gfx3d_ops, + .flags = CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE, + }, + }, + .hws = (struct clk_hw*[]){ + &gpucc_cxo_clk.clkr.hw, + &gpu_pll0_pll_out_main.clkr.hw, + &gpu_pll1_pll_out_main.clkr.hw, + } +}; + +static struct clk_branch gpucc_gfx3d_clk = { + .halt_reg = 0x1098, + .halt_check = BRANCH_HALT, + .hwcg_reg = 0x1098, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x1098, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gpucc_gfx3d_clk", + .parent_data = &(const struct clk_parent_data){ + .hw = &gfx3d_clk_src.rcg.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + }, + }, +}; + +static const struct parent_map gpucc_parent_map_0[] = { + { P_GPU_XO, 0 }, + { P_GPLL0_OUT_MAIN, 5 }, + { P_GPLL0_OUT_MAIN_DIV, 6 }, +}; + +static const struct clk_parent_data gpucc_parent_data_0[] = { + { .hw = &gpucc_cxo_clk.clkr.hw }, + { .fw_name = "gcc_gpu_gpll0_clk", .name = "gcc_gpu_gpll0_clk" }, + { .fw_name = "gcc_gpu_gpll0_div_clk", .name = "gcc_gpu_gpll0_div_clk" }, +}; + +static const struct freq_tbl ftbl_rbbmtimer_clk_src[] = { + F(19200000, P_GPU_XO, 1, 0, 0), + { } +}; + +static struct clk_rcg2 rbbmtimer_clk_src = { + .cmd_rcgr = 0x10b0, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gpucc_parent_map_0, + .freq_tbl = ftbl_rbbmtimer_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "rbbmtimer_clk_src", + .parent_data = gpucc_parent_data_0, + .num_parents = 3, + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_rbcpr_clk_src[] = { + F(19200000, P_GPU_XO, 1, 0, 0), + F(50000000, P_GPLL0_OUT_MAIN_DIV, 6, 0, 0), + { } +}; + +static struct clk_rcg2 rbcpr_clk_src = { + .cmd_rcgr = 0x1030, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gpucc_parent_map_0, + .freq_tbl = ftbl_rbcpr_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "rbcpr_clk_src", + .parent_data = gpucc_parent_data_0, + .num_parents = 3, + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_branch gpucc_rbbmtimer_clk = { + .halt_reg = 0x10d0, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x10d0, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gpucc_rbbmtimer_clk", + .parent_names = (const char *[]){ + "rbbmtimer_clk_src", + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpucc_rbcpr_clk = { + .halt_reg = 0x1054, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x1054, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gpucc_rbcpr_clk", + .parent_names = (const char *[]){ + "rbcpr_clk_src", + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct gdsc gpu_cx_gdsc = { + .gdscr = 0x1004, + .gds_hw_ctrl = 0x1008, + .pd = { + .name = "gpu_cx", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE, +}; + +static struct gdsc gpu_gx_gdsc = { + .gdscr = 0x1094, + .clamp_io_ctrl = 0x130, + .resets = (unsigned int []){ GPU_GX_BCR }, + .reset_count = 1, + .cxcs = (unsigned int []){ 0x1098 }, + .cxc_count = 1, + .pd = { + .name = "gpu_gx", + }, + .parent = &gpu_cx_gdsc.pd, + .pwrsts = PWRSTS_OFF | PWRSTS_ON | PWRSTS_RET, + .flags = CLAMP_IO | SW_RESET | AON_RESET | NO_RET_PERIPH, +}; + +static struct gdsc *gpucc_sdm660_gdscs[] = { + [GPU_CX_GDSC] = &gpu_cx_gdsc, + [GPU_GX_GDSC] = &gpu_gx_gdsc, +}; + +static const struct qcom_reset_map gpucc_sdm660_resets[] = { + [GPU_CX_BCR] = { 0x1000 }, + [RBCPR_BCR] = { 0x1050 }, + [GPU_GX_BCR] = { 0x1090 }, + [SPDM_BCR] = { 0x10E0 }, +}; + +static struct clk_regmap *gpucc_sdm660_clocks[] = { + [GPUCC_CXO_CLK] = &gpucc_cxo_clk.clkr, + [GPU_PLL0_PLL] = &gpu_pll0_pll_out_main.clkr, + [GPU_PLL1_PLL] = &gpu_pll1_pll_out_main.clkr, + [GFX3D_CLK_SRC] = &gfx3d_clk_src.rcg.clkr, + [RBCPR_CLK_SRC] = &rbcpr_clk_src.clkr, + [RBBMTIMER_CLK_SRC] = &rbbmtimer_clk_src.clkr, + [GPUCC_RBCPR_CLK] = &gpucc_rbcpr_clk.clkr, + [GPUCC_GFX3D_CLK] = &gpucc_gfx3d_clk.clkr, + [GPUCC_RBBMTIMER_CLK] = &gpucc_rbbmtimer_clk.clkr, +}; + +static const struct regmap_config gpucc_660_regmap_config = { + .reg_bits = 32, + .reg_stride = 4, + .val_bits = 32, + .max_register = 0x9034, + .fast_io = true, +}; + +static const struct qcom_cc_desc gpucc_sdm660_desc = { + .config = &gpucc_660_regmap_config, + .clks = gpucc_sdm660_clocks, + .num_clks = ARRAY_SIZE(gpucc_sdm660_clocks), + .resets = gpucc_sdm660_resets, + .num_resets = ARRAY_SIZE(gpucc_sdm660_resets), + .gdscs = gpucc_sdm660_gdscs, + .num_gdscs = ARRAY_SIZE(gpucc_sdm660_gdscs), +}; + +static const struct of_device_id gpucc_sdm660_match_table[] = { + { .compatible = "qcom,gpucc-sdm660" }, + { .compatible = "qcom,gpucc-sdm630" }, + { } +}; +MODULE_DEVICE_TABLE(of, gpucc_sdm660_match_table); + +static int gpucc_sdm660_probe(struct platform_device *pdev) +{ + struct regmap *regmap; + struct alpha_pll_config gpu_pll_config = { + .config_ctl_val = 0x4001055b, + .alpha = 0xaaaaab00, + .alpha_en_mask = BIT(24), + .vco_val = 0x2 << 20, + .vco_mask = 0x3 << 20, + .main_output_mask = 0x1, + }; + + regmap = qcom_cc_map(pdev, &gpucc_sdm660_desc); + if (IS_ERR(regmap)) + return PTR_ERR(regmap); + + /* 800MHz configuration for GPU PLL0 */ + gpu_pll_config.l = 0x29; + gpu_pll_config.alpha_hi = 0xaa; + clk_alpha_pll_configure(&gpu_pll0_pll_out_main, regmap, &gpu_pll_config); + + /* 740MHz configuration for GPU PLL1 */ + gpu_pll_config.l = 0x26; + gpu_pll_config.alpha_hi = 0x8a; + clk_alpha_pll_configure(&gpu_pll1_pll_out_main, regmap, &gpu_pll_config); + + return qcom_cc_really_probe(pdev, &gpucc_sdm660_desc, regmap); +} + +static struct platform_driver gpucc_sdm660_driver = { + .probe = gpucc_sdm660_probe, + .driver = { + .name = "gpucc-sdm660", + .of_match_table = gpucc_sdm660_match_table, + }, +}; +module_platform_driver(gpucc_sdm660_driver); + +MODULE_DESCRIPTION("Qualcomm SDM630/SDM660 GPUCC Driver"); +MODULE_LICENSE("GPL v2"); diff --git a/include/dt-bindings/clock/qcom,gpucc-sdm660.h b/include/dt-bindings/clock/qcom,gpucc-sdm660.h new file mode 100644 index 000000000000..7ea3e53df58c --- /dev/null +++ b/include/dt-bindings/clock/qcom,gpucc-sdm660.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2020, The Linux Foundation. All rights reserved. + * Copyright (c) 2020, AngeloGioacchino Del Regno + */ + +#ifndef _DT_BINDINGS_CLK_SDM_GPUCC_660_H +#define _DT_BINDINGS_CLK_SDM_GPUCC_660_H + +#define GPUCC_CXO_CLK 0 +#define GPU_PLL0_PLL 1 +#define GPU_PLL1_PLL 2 +#define GFX3D_CLK_SRC 3 +#define RBCPR_CLK_SRC 4 +#define RBBMTIMER_CLK_SRC 5 +#define GPUCC_RBCPR_CLK 6 +#define GPUCC_GFX3D_CLK 7 +#define GPUCC_RBBMTIMER_CLK 8 + +#define GPU_CX_GDSC 0 +#define GPU_GX_GDSC 1 + +#define GPU_CX_BCR 0 +#define GPU_GX_BCR 1 +#define RBCPR_BCR 2 +#define SPDM_BCR 3 + +#endif -- cgit v1.2.3 From 3fade948fbb3ccd30f6b06c474d0d084dffecb64 Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Wed, 10 Feb 2021 21:46:49 +0530 Subject: clk: qcom: gcc-sm8350: add gdsc Add the GDSC found in GCC for SM8350 SoC Signed-off-by: Vinod Koul Link: https://lore.kernel.org/r/20210210161649.431741-1-vkoul@kernel.org Signed-off-by: Stephen Boyd --- drivers/clk/qcom/gcc-sm8350.c | 100 ++++++++++++++++++++++++++++ include/dt-bindings/clock/qcom,gcc-sm8350.h | 12 ++++ 2 files changed, 112 insertions(+) (limited to 'include') diff --git a/drivers/clk/qcom/gcc-sm8350.c b/drivers/clk/qcom/gcc-sm8350.c index a16c08651206..1c23b9f84900 100644 --- a/drivers/clk/qcom/gcc-sm8350.c +++ b/drivers/clk/qcom/gcc-sm8350.c @@ -16,6 +16,7 @@ #include "clk-regmap.h" #include "clk-regmap-divider.h" #include "clk-regmap-mux.h" +#include "gdsc.h" #include "reset.h" enum { @@ -3452,6 +3453,90 @@ static struct clk_branch gcc_video_axi1_clk = { }, }; +static struct gdsc pcie_0_gdsc = { + .gdscr = 0x6b004, + .pd = { + .name = "pcie_0_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, +}; + +static struct gdsc pcie_1_gdsc = { + .gdscr = 0x8d004, + .pd = { + .name = "pcie_1_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, +}; + +static struct gdsc ufs_card_gdsc = { + .gdscr = 0x75004, + .pd = { + .name = "ufs_card_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, +}; + +static struct gdsc ufs_phy_gdsc = { + .gdscr = 0x77004, + .pd = { + .name = "ufs_phy_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, +}; + +static struct gdsc usb30_prim_gdsc = { + .gdscr = 0xf004, + .pd = { + .name = "usb30_prim_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, +}; + +static struct gdsc usb30_sec_gdsc = { + .gdscr = 0x10004, + .pd = { + .name = "usb30_sec_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, +}; + +static struct gdsc hlos1_vote_mmnoc_mmu_tbu_hf0_gdsc = { + .gdscr = 0x7d050, + .pd = { + .name = "hlos1_vote_mmnoc_mmu_tbu_hf0_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE, +}; + +static struct gdsc hlos1_vote_mmnoc_mmu_tbu_hf1_gdsc = { + .gdscr = 0x7d058, + .pd = { + .name = "hlos1_vote_mmnoc_mmu_tbu_hf1_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE, +}; + +static struct gdsc hlos1_vote_mmnoc_mmu_tbu_sf0_gdsc = { + .gdscr = 0x7d054, + .pd = { + .name = "hlos1_vote_mmnoc_mmu_tbu_sf0_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE, +}; + +static struct gdsc hlos1_vote_mmnoc_mmu_tbu_sf1_gdsc = { + .gdscr = 0x7d06c, + .pd = { + .name = "hlos1_vote_mmnoc_mmu_tbu_sf1_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE, +}; + static struct clk_regmap *gcc_sm8350_clocks[] = { [GCC_AGGRE_NOC_PCIE_0_AXI_CLK] = &gcc_aggre_noc_pcie_0_axi_clk.clkr, [GCC_AGGRE_NOC_PCIE_1_AXI_CLK] = &gcc_aggre_noc_pcie_1_axi_clk.clkr, @@ -3646,6 +3731,19 @@ static struct clk_regmap *gcc_sm8350_clocks[] = { [GCC_VIDEO_AXI1_CLK] = &gcc_video_axi1_clk.clkr, }; +static struct gdsc *gcc_sm8350_gdscs[] = { + [PCIE_0_GDSC] = &pcie_0_gdsc, + [PCIE_1_GDSC] = &pcie_1_gdsc, + [UFS_CARD_GDSC] = &ufs_card_gdsc, + [UFS_PHY_GDSC] = &ufs_phy_gdsc, + [USB30_PRIM_GDSC] = &usb30_prim_gdsc, + [USB30_SEC_GDSC] = &usb30_sec_gdsc, + [HLOS1_VOTE_MMNOC_MMU_TBU_HF0_GDSC] = &hlos1_vote_mmnoc_mmu_tbu_hf0_gdsc, + [HLOS1_VOTE_MMNOC_MMU_TBU_HF1_GDSC] = &hlos1_vote_mmnoc_mmu_tbu_hf1_gdsc, + [HLOS1_VOTE_MMNOC_MMU_TBU_SF0_GDSC] = &hlos1_vote_mmnoc_mmu_tbu_sf0_gdsc, + [HLOS1_VOTE_MMNOC_MMU_TBU_SF1_GDSC] = &hlos1_vote_mmnoc_mmu_tbu_sf1_gdsc, +}; + static const struct qcom_reset_map gcc_sm8350_resets[] = { [GCC_CAMERA_BCR] = { 0x26000 }, [GCC_DISPLAY_BCR] = { 0x27000 }, @@ -3724,6 +3822,8 @@ static const struct qcom_cc_desc gcc_sm8350_desc = { .num_clks = ARRAY_SIZE(gcc_sm8350_clocks), .resets = gcc_sm8350_resets, .num_resets = ARRAY_SIZE(gcc_sm8350_resets), + .gdscs = gcc_sm8350_gdscs, + .num_gdscs = ARRAY_SIZE(gcc_sm8350_gdscs), }; static const struct of_device_id gcc_sm8350_match_table[] = { diff --git a/include/dt-bindings/clock/qcom,gcc-sm8350.h b/include/dt-bindings/clock/qcom,gcc-sm8350.h index 1331da65f669..f6be3da5f781 100644 --- a/include/dt-bindings/clock/qcom,gcc-sm8350.h +++ b/include/dt-bindings/clock/qcom,gcc-sm8350.h @@ -251,4 +251,16 @@ #define GCC_VIDEO_AXI1_CLK_ARES 36 #define GCC_VIDEO_BCR 37 +/* GCC power domains */ +#define PCIE_0_GDSC 0 +#define PCIE_1_GDSC 1 +#define UFS_CARD_GDSC 2 +#define UFS_PHY_GDSC 3 +#define USB30_PRIM_GDSC 4 +#define USB30_SEC_GDSC 5 +#define HLOS1_VOTE_MMNOC_MMU_TBU_HF0_GDSC 6 +#define HLOS1_VOTE_MMNOC_MMU_TBU_HF1_GDSC 7 +#define HLOS1_VOTE_MMNOC_MMU_TBU_SF0_GDSC 8 +#define HLOS1_VOTE_MMNOC_MMU_TBU_SF1_GDSC 9 + #endif -- cgit v1.2.3 From 87a3d523b38ca17e05eea6a8634b94a3ea0f5337 Mon Sep 17 00:00:00 2001 From: Taniya Das Date: Wed, 10 Feb 2021 23:56:18 +0530 Subject: dt-bindings: clock: Add SC7280 GCC clock binding Add device tree bindings for global clock subsystem clock controller for Qualcomm Technology Inc's SC7280 SoCs. Signed-off-by: Taniya Das Link: https://lore.kernel.org/r/1612981579-17391-2-git-send-email-tdas@codeaurora.org Signed-off-by: Stephen Boyd --- .../devicetree/bindings/clock/qcom,gcc-sc7280.yaml | 92 +++++++++ include/dt-bindings/clock/qcom,gcc-sc7280.h | 226 +++++++++++++++++++++ 2 files changed, 318 insertions(+) create mode 100644 Documentation/devicetree/bindings/clock/qcom,gcc-sc7280.yaml create mode 100644 include/dt-bindings/clock/qcom,gcc-sc7280.h (limited to 'include') diff --git a/Documentation/devicetree/bindings/clock/qcom,gcc-sc7280.yaml b/Documentation/devicetree/bindings/clock/qcom,gcc-sc7280.yaml new file mode 100644 index 000000000000..5693b8997570 --- /dev/null +++ b/Documentation/devicetree/bindings/clock/qcom,gcc-sc7280.yaml @@ -0,0 +1,92 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/clock/qcom,gcc-sc7280.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Qualcomm Global Clock & Reset Controller Binding for SC7280 + +maintainers: + - Taniya Das + +description: | + Qualcomm global clock control module which supports the clocks, resets and + power domains on SC7280. + + See also: + - dt-bindings/clock/qcom,gcc-sc7280.h + +properties: + compatible: + const: qcom,gcc-sc7280 + + clocks: + items: + - description: Board XO source + - description: Board active XO source + - description: Sleep clock source + - description: PCIE-0 pipe clock source + - description: PCIE-1 pipe clock source + - description: USF phy rx symbol 0 clock source + - description: USF phy rx symbol 1 clock source + - description: USF phy tx symbol 0 clock source + - description: USB30 phy wrapper pipe clock source + + clock-names: + items: + - const: bi_tcxo + - const: bi_tcxo_ao + - const: sleep_clk + - const: pcie_0_pipe_clk + - const: pcie_1_pipe_clk + - const: ufs_phy_rx_symbol_0_clk + - const: ufs_phy_rx_symbol_1_clk + - const: ufs_phy_tx_symbol_0_clk + - const: usb3_phy_wrapper_gcc_usb30_pipe_clk + + '#clock-cells': + const: 1 + + '#reset-cells': + const: 1 + + '#power-domain-cells': + const: 1 + + reg: + maxItems: 1 + +required: + - compatible + - clocks + - clock-names + - reg + - '#clock-cells' + - '#reset-cells' + - '#power-domain-cells' + +additionalProperties: false + +examples: + - | + #include + clock-controller@100000 { + compatible = "qcom,gcc-sc7280"; + reg = <0x00100000 0x1f0000>; + clocks = <&rpmhcc RPMH_CXO_CLK>, + <&rpmhcc RPMH_CXO_CLK_A>, + <&sleep_clk>, + <&pcie_0_pipe_clk>, <&pcie_1_pipe_clk>, + <&ufs_phy_rx_symbol_0_clk>, <&ufs_phy_rx_symbol_1_clk>, + <&ufs_phy_tx_symbol_0_clk>, + <&usb3_phy_wrapper_gcc_usb30_pipe_clk>; + + clock-names = "bi_tcxo", "bi_tcxo_ao", "sleep_clk", "pcie_0_pipe_clk", + "pcie_1_pipe_clk", "ufs_phy_rx_symbol_0_clk", + "ufs_phy_rx_symbol_1_clk", "ufs_phy_tx_symbol_0_clk", + "usb3_phy_wrapper_gcc_usb30_pipe_clk"; + #clock-cells = <1>; + #reset-cells = <1>; + #power-domain-cells = <1>; + }; +... diff --git a/include/dt-bindings/clock/qcom,gcc-sc7280.h b/include/dt-bindings/clock/qcom,gcc-sc7280.h new file mode 100644 index 000000000000..4394f15111c6 --- /dev/null +++ b/include/dt-bindings/clock/qcom,gcc-sc7280.h @@ -0,0 +1,226 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2020-2021, The Linux Foundation. All rights reserved. + */ + +#ifndef _DT_BINDINGS_CLK_QCOM_GCC_SC7280_H +#define _DT_BINDINGS_CLK_QCOM_GCC_SC7280_H + +/* GCC clocks */ +#define GCC_GPLL0 0 +#define GCC_GPLL0_OUT_EVEN 1 +#define GCC_GPLL0_OUT_ODD 2 +#define GCC_GPLL1 3 +#define GCC_GPLL10 4 +#define GCC_GPLL4 5 +#define GCC_GPLL9 6 +#define GCC_AGGRE_NOC_PCIE_0_AXI_CLK 7 +#define GCC_AGGRE_NOC_PCIE_1_AXI_CLK 8 +#define GCC_AGGRE_UFS_PHY_AXI_CLK 9 +#define GCC_AGGRE_USB3_PRIM_AXI_CLK 10 +#define GCC_CAMERA_AHB_CLK 11 +#define GCC_CAMERA_HF_AXI_CLK 12 +#define GCC_CAMERA_SF_AXI_CLK 13 +#define GCC_CAMERA_XO_CLK 14 +#define GCC_CFG_NOC_USB3_PRIM_AXI_CLK 15 +#define GCC_CFG_NOC_USB3_SEC_AXI_CLK 16 +#define GCC_CPUSS_AHB_CLK 17 +#define GCC_CPUSS_AHB_CLK_SRC 18 +#define GCC_CPUSS_AHB_POSTDIV_CLK_SRC 19 +#define GCC_DDRSS_GPU_AXI_CLK 20 +#define GCC_DDRSS_PCIE_SF_CLK 21 +#define GCC_DISP_AHB_CLK 22 +#define GCC_DISP_GPLL0_CLK_SRC 23 +#define GCC_DISP_HF_AXI_CLK 24 +#define GCC_DISP_SF_AXI_CLK 25 +#define GCC_DISP_XO_CLK 26 +#define GCC_GP1_CLK 27 +#define GCC_GP1_CLK_SRC 28 +#define GCC_GP2_CLK 29 +#define GCC_GP2_CLK_SRC 30 +#define GCC_GP3_CLK 31 +#define GCC_GP3_CLK_SRC 32 +#define GCC_GPU_CFG_AHB_CLK 33 +#define GCC_GPU_GPLL0_CLK_SRC 34 +#define GCC_GPU_GPLL0_DIV_CLK_SRC 35 +#define GCC_GPU_IREF_EN 36 +#define GCC_GPU_MEMNOC_GFX_CLK 37 +#define GCC_GPU_SNOC_DVM_GFX_CLK 38 +#define GCC_PCIE0_PHY_RCHNG_CLK 39 +#define GCC_PCIE1_PHY_RCHNG_CLK 40 +#define GCC_PCIE_0_AUX_CLK 41 +#define GCC_PCIE_0_AUX_CLK_SRC 42 +#define GCC_PCIE_0_CFG_AHB_CLK 43 +#define GCC_PCIE_0_MSTR_AXI_CLK 44 +#define GCC_PCIE_0_PHY_RCHNG_CLK_SRC 45 +#define GCC_PCIE_0_PIPE_CLK 46 +#define GCC_PCIE_0_PIPE_CLK_SRC 47 +#define GCC_PCIE_0_SLV_AXI_CLK 48 +#define GCC_PCIE_0_SLV_Q2A_AXI_CLK 49 +#define GCC_PCIE_1_AUX_CLK 50 +#define GCC_PCIE_1_AUX_CLK_SRC 51 +#define GCC_PCIE_1_CFG_AHB_CLK 52 +#define GCC_PCIE_1_MSTR_AXI_CLK 53 +#define GCC_PCIE_1_PHY_RCHNG_CLK_SRC 54 +#define GCC_PCIE_1_PIPE_CLK 55 +#define GCC_PCIE_1_PIPE_CLK_SRC 56 +#define GCC_PCIE_1_SLV_AXI_CLK 57 +#define GCC_PCIE_1_SLV_Q2A_AXI_CLK 58 +#define GCC_PCIE_THROTTLE_CORE_CLK 59 +#define GCC_PDM2_CLK 60 +#define GCC_PDM2_CLK_SRC 61 +#define GCC_PDM_AHB_CLK 62 +#define GCC_PDM_XO4_CLK 63 +#define GCC_QMIP_CAMERA_NRT_AHB_CLK 64 +#define GCC_QMIP_CAMERA_RT_AHB_CLK 65 +#define GCC_QMIP_DISP_AHB_CLK 66 +#define GCC_QMIP_VIDEO_VCODEC_AHB_CLK 67 +#define GCC_QUPV3_WRAP0_CORE_2X_CLK 68 +#define GCC_QUPV3_WRAP0_CORE_CLK 69 +#define GCC_QUPV3_WRAP0_S0_CLK 70 +#define GCC_QUPV3_WRAP0_S0_CLK_SRC 71 +#define GCC_QUPV3_WRAP0_S1_CLK 72 +#define GCC_QUPV3_WRAP0_S1_CLK_SRC 73 +#define GCC_QUPV3_WRAP0_S2_CLK 74 +#define GCC_QUPV3_WRAP0_S2_CLK_SRC 75 +#define GCC_QUPV3_WRAP0_S3_CLK 76 +#define GCC_QUPV3_WRAP0_S3_CLK_SRC 77 +#define GCC_QUPV3_WRAP0_S4_CLK 78 +#define GCC_QUPV3_WRAP0_S4_CLK_SRC 79 +#define GCC_QUPV3_WRAP0_S5_CLK 80 +#define GCC_QUPV3_WRAP0_S5_CLK_SRC 81 +#define GCC_QUPV3_WRAP0_S6_CLK 82 +#define GCC_QUPV3_WRAP0_S6_CLK_SRC 83 +#define GCC_QUPV3_WRAP0_S7_CLK 84 +#define GCC_QUPV3_WRAP0_S7_CLK_SRC 85 +#define GCC_QUPV3_WRAP1_CORE_2X_CLK 86 +#define GCC_QUPV3_WRAP1_CORE_CLK 87 +#define GCC_QUPV3_WRAP1_S0_CLK 88 +#define GCC_QUPV3_WRAP1_S0_CLK_SRC 89 +#define GCC_QUPV3_WRAP1_S1_CLK 90 +#define GCC_QUPV3_WRAP1_S1_CLK_SRC 91 +#define GCC_QUPV3_WRAP1_S2_CLK 92 +#define GCC_QUPV3_WRAP1_S2_CLK_SRC 93 +#define GCC_QUPV3_WRAP1_S3_CLK 94 +#define GCC_QUPV3_WRAP1_S3_CLK_SRC 95 +#define GCC_QUPV3_WRAP1_S4_CLK 96 +#define GCC_QUPV3_WRAP1_S4_CLK_SRC 97 +#define GCC_QUPV3_WRAP1_S5_CLK 98 +#define GCC_QUPV3_WRAP1_S5_CLK_SRC 99 +#define GCC_QUPV3_WRAP1_S6_CLK 100 +#define GCC_QUPV3_WRAP1_S6_CLK_SRC 101 +#define GCC_QUPV3_WRAP1_S7_CLK 102 +#define GCC_QUPV3_WRAP1_S7_CLK_SRC 103 +#define GCC_QUPV3_WRAP_0_M_AHB_CLK 104 +#define GCC_QUPV3_WRAP_0_S_AHB_CLK 105 +#define GCC_QUPV3_WRAP_1_M_AHB_CLK 106 +#define GCC_QUPV3_WRAP_1_S_AHB_CLK 107 +#define GCC_SDCC1_AHB_CLK 108 +#define GCC_SDCC1_APPS_CLK 109 +#define GCC_SDCC1_APPS_CLK_SRC 110 +#define GCC_SDCC1_ICE_CORE_CLK 111 +#define GCC_SDCC1_ICE_CORE_CLK_SRC 112 +#define GCC_SDCC2_AHB_CLK 113 +#define GCC_SDCC2_APPS_CLK 114 +#define GCC_SDCC2_APPS_CLK_SRC 115 +#define GCC_SDCC4_AHB_CLK 116 +#define GCC_SDCC4_APPS_CLK 117 +#define GCC_SDCC4_APPS_CLK_SRC 118 +#define GCC_SYS_NOC_CPUSS_AHB_CLK 119 +#define GCC_THROTTLE_PCIE_AHB_CLK 120 +#define GCC_TITAN_NRT_THROTTLE_CORE_CLK 121 +#define GCC_TITAN_RT_THROTTLE_CORE_CLK 122 +#define GCC_UFS_1_CLKREF_EN 123 +#define GCC_UFS_PHY_AHB_CLK 124 +#define GCC_UFS_PHY_AXI_CLK 125 +#define GCC_UFS_PHY_AXI_CLK_SRC 126 +#define GCC_UFS_PHY_ICE_CORE_CLK 127 +#define GCC_UFS_PHY_ICE_CORE_CLK_SRC 128 +#define GCC_UFS_PHY_PHY_AUX_CLK 129 +#define GCC_UFS_PHY_PHY_AUX_CLK_SRC 130 +#define GCC_UFS_PHY_RX_SYMBOL_0_CLK 131 +#define GCC_UFS_PHY_RX_SYMBOL_0_CLK_SRC 132 +#define GCC_UFS_PHY_RX_SYMBOL_1_CLK 133 +#define GCC_UFS_PHY_RX_SYMBOL_1_CLK_SRC 134 +#define GCC_UFS_PHY_TX_SYMBOL_0_CLK 135 +#define GCC_UFS_PHY_TX_SYMBOL_0_CLK_SRC 136 +#define GCC_UFS_PHY_UNIPRO_CORE_CLK 137 +#define GCC_UFS_PHY_UNIPRO_CORE_CLK_SRC 138 +#define GCC_USB30_PRIM_MASTER_CLK 139 +#define GCC_USB30_PRIM_MASTER_CLK_SRC 140 +#define GCC_USB30_PRIM_MOCK_UTMI_CLK 141 +#define GCC_USB30_PRIM_MOCK_UTMI_CLK_SRC 142 +#define GCC_USB30_PRIM_MOCK_UTMI_POSTDIV_CLK_SRC 143 +#define GCC_USB30_PRIM_SLEEP_CLK 144 +#define GCC_USB30_SEC_MASTER_CLK 145 +#define GCC_USB30_SEC_MASTER_CLK_SRC 146 +#define GCC_USB30_SEC_MOCK_UTMI_CLK 147 +#define GCC_USB30_SEC_MOCK_UTMI_CLK_SRC 148 +#define GCC_USB30_SEC_MOCK_UTMI_POSTDIV_CLK_SRC 149 +#define GCC_USB30_SEC_SLEEP_CLK 150 +#define GCC_USB3_PRIM_PHY_AUX_CLK 151 +#define GCC_USB3_PRIM_PHY_AUX_CLK_SRC 152 +#define GCC_USB3_PRIM_PHY_COM_AUX_CLK 153 +#define GCC_USB3_PRIM_PHY_PIPE_CLK 154 +#define GCC_USB3_PRIM_PHY_PIPE_CLK_SRC 155 +#define GCC_USB3_SEC_PHY_AUX_CLK 156 +#define GCC_USB3_SEC_PHY_AUX_CLK_SRC 157 +#define GCC_USB3_SEC_PHY_COM_AUX_CLK 158 +#define GCC_USB3_SEC_PHY_PIPE_CLK 159 +#define GCC_USB3_SEC_PHY_PIPE_CLK_SRC 160 +#define GCC_VIDEO_AHB_CLK 161 +#define GCC_VIDEO_AXI0_CLK 162 +#define GCC_VIDEO_MVP_THROTTLE_CORE_CLK 163 +#define GCC_VIDEO_XO_CLK 164 +#define GCC_GPLL0_MAIN_DIV_CDIV 165 +#define GCC_QSPI_CNOC_PERIPH_AHB_CLK 166 +#define GCC_QSPI_CORE_CLK 167 +#define GCC_QSPI_CORE_CLK_SRC 168 +#define GCC_CFG_NOC_LPASS_CLK 169 +#define GCC_MSS_GPLL0_MAIN_DIV_CLK_SRC 170 +#define GCC_MSS_CFG_AHB_CLK 171 +#define GCC_MSS_OFFLINE_AXI_CLK 172 +#define GCC_MSS_SNOC_AXI_CLK 173 +#define GCC_MSS_Q6_MEMNOC_AXI_CLK 174 +#define GCC_MSS_Q6SS_BOOT_CLK_SRC 175 +#define GCC_AGGRE_USB3_SEC_AXI_CLK 176 +#define GCC_AGGRE_NOC_PCIE_TBU_CLK 177 +#define GCC_AGGRE_NOC_PCIE_CENTER_SF_AXI_CLK 178 +#define GCC_PCIE_CLKREF_EN 179 +#define GCC_WPSS_AHB_CLK 180 +#define GCC_WPSS_AHB_BDG_MST_CLK 181 +#define GCC_WPSS_RSCP_CLK 182 +#define GCC_EDP_CLKREF_EN 183 +#define GCC_SEC_CTRL_CLK_SRC 184 + +/* GCC power domains */ +#define GCC_PCIE_0_GDSC 0 +#define GCC_PCIE_1_GDSC 1 +#define GCC_UFS_PHY_GDSC 2 +#define GCC_USB30_PRIM_GDSC 3 +#define GCC_USB30_SEC_GDSC 4 +#define HLOS1_VOTE_MMNOC_MMU_TBU_HF0_GDSC 5 +#define HLOS1_VOTE_MMNOC_MMU_TBU_HF1_GDSC 6 +#define HLOS1_VOTE_MMNOC_MMU_TBU_SF0_GDSC 7 +#define HLOS1_VOTE_TURING_MMU_TBU0_GDSC 8 +#define HLOS1_VOTE_TURING_MMU_TBU1_GDSC 9 + +/* GCC resets */ +#define GCC_PCIE_0_BCR 0 +#define GCC_PCIE_0_PHY_BCR 1 +#define GCC_PCIE_1_BCR 2 +#define GCC_PCIE_1_PHY_BCR 3 +#define GCC_QUSB2PHY_PRIM_BCR 4 +#define GCC_QUSB2PHY_SEC_BCR 5 +#define GCC_SDCC1_BCR 6 +#define GCC_SDCC2_BCR 7 +#define GCC_SDCC4_BCR 8 +#define GCC_UFS_PHY_BCR 9 +#define GCC_USB30_PRIM_BCR 10 +#define GCC_USB30_SEC_BCR 11 +#define GCC_USB3_DP_PHY_PRIM_BCR 12 +#define GCC_USB3_PHY_PRIM_BCR 13 +#define GCC_USB3PHY_PHY_PRIM_BCR 14 +#define GCC_USB_PHY_CFG_AHB2PHY_BCR 15 + +#endif -- cgit v1.2.3 From f61d3f0c6912c54f6a468318907a5c554e116516 Mon Sep 17 00:00:00 2001 From: Kent Gibson Date: Tue, 19 Jan 2021 21:57:27 +0800 Subject: gpio: uapi: fix line info flags description The description of the flags field of the struct gpio_v2_line_info mentions "the GPIO lines" while the info only applies to an individual GPIO line. This was accidentally changed from "the GPIO line" during formatting improvements. Reword to "this GPIO line" to clarify and to be consistent with other struct gpio_v2_line_info fields. Fixes: 2cc522d3931b ("gpio: uapi: kernel-doc formatting improvements") Signed-off-by: Kent Gibson Signed-off-by: Bartosz Golaszewski --- include/uapi/linux/gpio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/gpio.h b/include/uapi/linux/gpio.h index e4eb0b8c5cf9..7a6f7948a7df 100644 --- a/include/uapi/linux/gpio.h +++ b/include/uapi/linux/gpio.h @@ -212,7 +212,7 @@ struct gpio_v2_line_request { * @offset: the local offset on this GPIO chip, fill this in when * requesting the line information from the kernel * @num_attrs: the number of attributes in @attrs - * @flags: flags for the GPIO lines, with values from &enum + * @flags: flags for this GPIO line, with values from &enum * gpio_v2_line_flag, such as %GPIO_V2_LINE_FLAG_ACTIVE_LOW, * %GPIO_V2_LINE_FLAG_OUTPUT etc, added together. * @attrs: the configuration attributes associated with the line -- cgit v1.2.3 From b2498cb87c4ba87580e5975e049d589b6786ff75 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 22 Jan 2021 14:38:52 +0200 Subject: gpio: aggregator: Use compound literal from the header Instead of doing it in place, convert GPIO_LOOKUP_IDX() and GPIO_HOG() to be compund literals that's allow to use them as rvalue in assignments. Due to above conversion, use compound literal from the header in the gpio-aggregator.c. Signed-off-by: Andy Shevchenko Reviewed-by: Geert Uytterhoeven --- drivers/gpio/gpio-aggregator.c | 3 +-- include/linux/gpio/machine.h | 4 ++-- 2 files changed, 3 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/gpio/gpio-aggregator.c b/drivers/gpio/gpio-aggregator.c index 40a081b095fb..13e473c97ce4 100644 --- a/drivers/gpio/gpio-aggregator.c +++ b/drivers/gpio/gpio-aggregator.c @@ -72,8 +72,7 @@ static int aggr_add_gpio(struct gpio_aggregator *aggr, const char *key, if (!lookups) return -ENOMEM; - lookups->table[*n] = - (struct gpiod_lookup)GPIO_LOOKUP_IDX(key, hwnum, NULL, *n, 0); + lookups->table[*n] = GPIO_LOOKUP_IDX(key, hwnum, NULL, *n, 0); (*n)++; memset(&lookups->table[*n], 0, sizeof(lookups->table[*n])); diff --git a/include/linux/gpio/machine.h b/include/linux/gpio/machine.h index 781a053abbb9..d755e529c1e3 100644 --- a/include/linux/gpio/machine.h +++ b/include/linux/gpio/machine.h @@ -75,7 +75,7 @@ struct gpiod_hog { * gpiod_get_index() */ #define GPIO_LOOKUP_IDX(_key, _chip_hwnum, _con_id, _idx, _flags) \ -{ \ +(struct gpiod_lookup) { \ .key = _key, \ .chip_hwnum = _chip_hwnum, \ .con_id = _con_id, \ @@ -87,7 +87,7 @@ struct gpiod_hog { * Simple definition of a single GPIO hog in an array. */ #define GPIO_HOG(_chip_label, _chip_hwnum, _line_name, _lflags, _dflags) \ -{ \ +(struct gpiod_hog) { \ .chip_label = _chip_label, \ .chip_hwnum = _chip_hwnum, \ .line_name = _line_name, \ -- cgit v1.2.3 From 50f9a6c254c60bbad4cde050dbc39b46b61f7a5d Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Thu, 4 Feb 2021 13:43:57 +0100 Subject: gpio: uapi: use the preferred SPDX license identifier GPL-2.0 license identifier is deprecated. User-space projects that want to include the kernel header with their source-code will be unable to become fully REUSE compliant due to the reuse tool complaining about deprecated licenses. Change the SPDX identifier to GPL-2.0-only. Signed-off-by: Bartosz Golaszewski --- include/uapi/linux/gpio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/gpio.h b/include/uapi/linux/gpio.h index 7a6f7948a7df..eaaea3d8e6b4 100644 --- a/include/uapi/linux/gpio.h +++ b/include/uapi/linux/gpio.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ /* * - userspace ABI for the GPIO character devices * -- cgit v1.2.3 From 4590d98f5a4f466d17e5c81d7c9fc796da9a8cee Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 11 Feb 2021 15:40:02 +0200 Subject: sfi: Remove framework for deprecated firmware SFI-based platforms are gone. So does this framework. This removes mention of SFI through the drivers and other code as well. Signed-off-by: Andy Shevchenko Reviewed-by: Hans de Goede Acked-by: Linus Walleij Signed-off-by: Rafael J. Wysocki --- Documentation/ABI/testing/sysfs-firmware-sfi | 15 - Documentation/ABI/testing/sysfs-platform-kim | 2 +- MAINTAINERS | 7 - arch/x86/Kconfig | 7 +- arch/x86/include/asm/intel-mid.h | 37 -- arch/x86/include/asm/intel_scu_ipc_legacy.h | 58 +-- arch/x86/include/asm/platform_sst_audio.h | 2 - arch/x86/kernel/apic/io_apic.c | 4 +- arch/x86/kernel/setup.c | 2 - arch/x86/pci/mmconfig-shared.c | 6 +- arch/x86/platform/Makefile | 1 - arch/x86/platform/intel-mid/Makefile | 5 - arch/x86/platform/intel-mid/device_libs/Makefile | 23 - .../intel-mid/device_libs/platform_bcm43xx.c | 101 ---- .../intel-mid/device_libs/platform_bma023.c | 16 - .../platform/intel-mid/device_libs/platform_bt.c | 101 ---- .../intel-mid/device_libs/platform_emc1403.c | 39 -- .../intel-mid/device_libs/platform_gpio_keys.c | 81 ---- .../intel-mid/device_libs/platform_lis331.c | 37 -- .../intel-mid/device_libs/platform_max7315.c | 77 --- .../intel-mid/device_libs/platform_mpu3050.c | 32 -- .../intel-mid/device_libs/platform_mrfld_pinctrl.c | 39 -- .../intel-mid/device_libs/platform_mrfld_rtc.c | 44 -- .../intel-mid/device_libs/platform_mrfld_sd.c | 43 -- .../intel-mid/device_libs/platform_mrfld_spidev.c | 50 -- .../intel-mid/device_libs/platform_pcal9555a.c | 95 ---- .../intel-mid/device_libs/platform_tc35876x.c | 42 -- .../intel-mid/device_libs/platform_tca6416.c | 53 --- arch/x86/platform/intel-mid/intel-mid.c | 1 - arch/x86/platform/intel-mid/sfi.c | 419 ----------------- arch/x86/platform/sfi/Makefile | 2 - arch/x86/platform/sfi/sfi.c | 100 ---- drivers/Makefile | 2 +- drivers/platform/x86/intel_scu_pcidrv.c | 22 +- drivers/sfi/Kconfig | 18 - drivers/sfi/Makefile | 4 - drivers/sfi/sfi_acpi.c | 214 --------- drivers/sfi/sfi_core.c | 522 --------------------- drivers/sfi/sfi_core.h | 81 ---- include/linux/sfi.h | 210 --------- include/linux/sfi_acpi.h | 93 ---- init/main.c | 2 - 42 files changed, 14 insertions(+), 2695 deletions(-) delete mode 100644 Documentation/ABI/testing/sysfs-firmware-sfi delete mode 100644 arch/x86/platform/intel-mid/device_libs/Makefile delete mode 100644 arch/x86/platform/intel-mid/device_libs/platform_bcm43xx.c delete mode 100644 arch/x86/platform/intel-mid/device_libs/platform_bma023.c delete mode 100644 arch/x86/platform/intel-mid/device_libs/platform_bt.c delete mode 100644 arch/x86/platform/intel-mid/device_libs/platform_emc1403.c delete mode 100644 arch/x86/platform/intel-mid/device_libs/platform_gpio_keys.c delete mode 100644 arch/x86/platform/intel-mid/device_libs/platform_lis331.c delete mode 100644 arch/x86/platform/intel-mid/device_libs/platform_max7315.c delete mode 100644 arch/x86/platform/intel-mid/device_libs/platform_mpu3050.c delete mode 100644 arch/x86/platform/intel-mid/device_libs/platform_mrfld_pinctrl.c delete mode 100644 arch/x86/platform/intel-mid/device_libs/platform_mrfld_rtc.c delete mode 100644 arch/x86/platform/intel-mid/device_libs/platform_mrfld_sd.c delete mode 100644 arch/x86/platform/intel-mid/device_libs/platform_mrfld_spidev.c delete mode 100644 arch/x86/platform/intel-mid/device_libs/platform_pcal9555a.c delete mode 100644 arch/x86/platform/intel-mid/device_libs/platform_tc35876x.c delete mode 100644 arch/x86/platform/intel-mid/device_libs/platform_tca6416.c delete mode 100644 arch/x86/platform/intel-mid/sfi.c delete mode 100644 arch/x86/platform/sfi/Makefile delete mode 100644 arch/x86/platform/sfi/sfi.c delete mode 100644 drivers/sfi/Kconfig delete mode 100644 drivers/sfi/Makefile delete mode 100644 drivers/sfi/sfi_acpi.c delete mode 100644 drivers/sfi/sfi_core.c delete mode 100644 drivers/sfi/sfi_core.h delete mode 100644 include/linux/sfi.h delete mode 100644 include/linux/sfi_acpi.h (limited to 'include') diff --git a/Documentation/ABI/testing/sysfs-firmware-sfi b/Documentation/ABI/testing/sysfs-firmware-sfi deleted file mode 100644 index 5210e0f06ddb..000000000000 --- a/Documentation/ABI/testing/sysfs-firmware-sfi +++ /dev/null @@ -1,15 +0,0 @@ -What: /sys/firmware/sfi/tables/ -Date: May 2010 -Contact: Len Brown -Description: - SFI defines a number of small static memory tables - so the kernel can get platform information from firmware. - - The tables are defined in the latest SFI specification: - http://simplefirmware.org/documentation - - While the tables are used by the kernel, user-space - can observe them this way:: - - # cd /sys/firmware/sfi/tables - # cat $TABLENAME > $TABLENAME.bin diff --git a/Documentation/ABI/testing/sysfs-platform-kim b/Documentation/ABI/testing/sysfs-platform-kim index a7f81de68046..6a52d6d2b601 100644 --- a/Documentation/ABI/testing/sysfs-platform-kim +++ b/Documentation/ABI/testing/sysfs-platform-kim @@ -7,7 +7,7 @@ Description: is connected. example: "/dev/ttyS0". The device name flows down to architecture specific board - initialization file from the SFI/ATAGS bootloader + initialization file from the ATAGS bootloader firmware. The name exposed is read from the user-space dameon and opens the device when install is requested. diff --git a/MAINTAINERS b/MAINTAINERS index 8fdb7fe27537..fd41b96d71bb 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -16234,13 +16234,6 @@ S: Maintained F: Documentation/fb/sm712fb.rst F: drivers/video/fbdev/sm712* -SIMPLE FIRMWARE INTERFACE (SFI) -S: Obsolete -W: http://simplefirmware.org/ -F: arch/x86/platform/sfi/ -F: drivers/sfi/ -F: include/linux/sfi*.h - SIMPLEFB FB DRIVER M: Hans de Goede L: linux-fbdev@vger.kernel.org diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index cc73f98c3e42..7f5b77055266 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -444,7 +444,7 @@ config X86_X2APIC If you don't know what to do here, say N. config X86_MPPARSE - bool "Enable MPS table" if ACPI || SFI + bool "Enable MPS table" if ACPI default y depends on X86_LOCAL_APIC help @@ -603,7 +603,6 @@ config X86_INTEL_MID depends on PCI depends on X86_64 || (PCI_GOANY && X86_32) depends on X86_IO_APIC - select SFI select I2C select DW_APB_TIMER select APB_TIMER @@ -2457,8 +2456,6 @@ source "kernel/power/Kconfig" source "drivers/acpi/Kconfig" -source "drivers/sfi/Kconfig" - config X86_APM_BOOT def_bool y depends on APM @@ -2645,7 +2642,7 @@ config PCI_DIRECT config PCI_MMCONFIG bool "Support mmconfig PCI config space access" if X86_64 default y - depends on PCI && (ACPI || SFI || JAILHOUSE_GUEST) + depends on PCI && (ACPI || JAILHOUSE_GUEST) depends on X86_64 || (PCI_GOANY || PCI_GOMMCONFIG) config PCI_OLPC diff --git a/arch/x86/include/asm/intel-mid.h b/arch/x86/include/asm/intel-mid.h index 7bda0587cf70..6306fe3e5c4a 100644 --- a/arch/x86/include/asm/intel-mid.h +++ b/arch/x86/include/asm/intel-mid.h @@ -7,7 +7,6 @@ #ifndef _ASM_X86_INTEL_MID_H #define _ASM_X86_INTEL_MID_H -#include #include #include @@ -22,39 +21,6 @@ extern void intel_mid_pwr_power_off(void); extern int intel_mid_pwr_get_lss_id(struct pci_dev *pdev); -extern int get_gpio_by_name(const char *name); - -/* - * Here defines the array of devices platform data that IAFW would export - * through SFI "DEVS" table, we use name and type to match the device and - * its platform data. - */ -struct devs_id { - char name[SFI_NAME_LEN + 1]; - u8 type; - u8 delay; - void *(*get_platform_data)(void *info); -}; - -#define sfi_device(i) \ - static const struct devs_id *const __intel_mid_sfi_##i##_dev __used \ - __section(".x86_intel_mid_dev.init") = &i - -/** -* struct mid_sd_board_info - template for SD device creation -* @name: identifies the driver -* @bus_num: board-specific identifier for a given SD controller -* @max_clk: the maximum frequency device supports -* @platform_data: the particular data stored there is driver-specific -*/ -struct mid_sd_board_info { - char name[SFI_NAME_LEN]; - int bus_num; - unsigned short addr; - u32 max_clk; - void *platform_data; -}; - /* * Medfield is the follow-up of Moorestown, it combines two chip solution into * one. Other than that it also added always-on and constant tsc and lapic @@ -99,7 +65,4 @@ static inline void intel_scu_devices_destroy(void) { } /* FSB 83MHz */ #define BSEL_SOC_FUSE_111 0x7 -/* The offset for the mapping of global gpio pin to irq */ -#define INTEL_MID_IRQ_OFFSET 0x100 - #endif /* _ASM_X86_INTEL_MID_H */ diff --git a/arch/x86/include/asm/intel_scu_ipc_legacy.h b/arch/x86/include/asm/intel_scu_ipc_legacy.h index f8b87d8face7..fa529e5ec142 100644 --- a/arch/x86/include/asm/intel_scu_ipc_legacy.h +++ b/arch/x86/include/asm/intel_scu_ipc_legacy.h @@ -2,73 +2,17 @@ #ifndef _ASM_X86_INTEL_SCU_IPC_LEGACY_H_ #define _ASM_X86_INTEL_SCU_IPC_LEGACY_H_ -#include - -#define IPCMSG_INDIRECT_READ 0x02 -#define IPCMSG_INDIRECT_WRITE 0x05 +#include #define IPCMSG_COLD_OFF 0x80 /* Only for Tangier */ - -#define IPCMSG_WARM_RESET 0xF0 #define IPCMSG_COLD_RESET 0xF1 -#define IPCMSG_SOFT_RESET 0xF2 -#define IPCMSG_COLD_BOOT 0xF3 /* Don't call these in new code - they will be removed eventually */ -/* Read a vector */ -static inline int intel_scu_ipc_readv(u16 *addr, u8 *data, int len) -{ - return intel_scu_ipc_dev_readv(NULL, addr, data, len); -} - -/* Write a vector */ -static inline int intel_scu_ipc_writev(u16 *addr, u8 *data, int len) -{ - return intel_scu_ipc_dev_writev(NULL, addr, data, len); -} - -/* Update single register based on the mask */ -static inline int intel_scu_ipc_update_register(u16 addr, u8 data, u8 mask) -{ - return intel_scu_ipc_dev_update(NULL, addr, data, mask); -} - /* Issue commands to the SCU with or without data */ static inline int intel_scu_ipc_simple_command(int cmd, int sub) { return intel_scu_ipc_dev_simple_command(NULL, cmd, sub); } -static inline int intel_scu_ipc_command(int cmd, int sub, u32 *in, int inlen, - u32 *out, int outlen) -{ - /* New API takes both inlen and outlen as bytes so convert here */ - size_t inbytes = inlen * sizeof(u32); - size_t outbytes = outlen * sizeof(u32); - - return intel_scu_ipc_dev_command_with_size(NULL, cmd, sub, in, inbytes, - inlen, out, outbytes); -} - -extern struct blocking_notifier_head intel_scu_notifier; - -static inline void intel_scu_notifier_add(struct notifier_block *nb) -{ - blocking_notifier_chain_register(&intel_scu_notifier, nb); -} - -static inline void intel_scu_notifier_remove(struct notifier_block *nb) -{ - blocking_notifier_chain_unregister(&intel_scu_notifier, nb); -} - -static inline int intel_scu_notifier_post(unsigned long v, void *p) -{ - return blocking_notifier_call_chain(&intel_scu_notifier, v, p); -} - -#define SCU_AVAILABLE 1 -#define SCU_DOWN 2 - #endif diff --git a/arch/x86/include/asm/platform_sst_audio.h b/arch/x86/include/asm/platform_sst_audio.h index 16b9f220bdeb..40f92270515b 100644 --- a/arch/x86/include/asm/platform_sst_audio.h +++ b/arch/x86/include/asm/platform_sst_audio.h @@ -10,8 +10,6 @@ #ifndef _PLATFORM_SST_AUDIO_H_ #define _PLATFORM_SST_AUDIO_H_ -#include - #define MAX_NUM_STREAMS_MRFLD 25 #define MAX_NUM_STREAMS MAX_NUM_STREAMS_MRFLD diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index e4ab4804b20d..c3b60c37c728 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -198,7 +198,7 @@ static int __init parse_noapic(char *str) } early_param("noapic", parse_noapic); -/* Will be called in mpparse/acpi/sfi codes for saving IRQ info */ +/* Will be called in mpparse/ACPI codes for saving IRQ info */ void mp_save_irq(struct mpc_intsrc *m) { int i; @@ -2863,7 +2863,7 @@ int mp_register_ioapic(int id, u32 address, u32 gsi_base, /* * If mp_register_ioapic() is called during early boot stage when - * walking ACPI/SFI/DT tables, it's too early to create irqdomain, + * walking ACPI/DT tables, it's too early to create irqdomain, * we are still using bootmem allocator. So delay it to setup_IO_APIC(). */ if (hotplug) { diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 740f3bdb3f61..d883176ef2ce 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -16,7 +16,6 @@ #include #include #include -#include #include #include #include @@ -1185,7 +1184,6 @@ void __init setup_arch(char **cmdline_p) * Read APIC and some other early information from ACPI tables. */ acpi_boot_init(); - sfi_init(); x86_dtb_init(); /* diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c index 234998f196d4..de6bf0e7e8f8 100644 --- a/arch/x86/pci/mmconfig-shared.c +++ b/arch/x86/pci/mmconfig-shared.c @@ -11,9 +11,9 @@ * themselves. */ +#include #include #include -#include #include #include #include @@ -665,7 +665,7 @@ void __init pci_mmcfg_early_init(void) if (pci_mmcfg_check_hostbridge()) known_bridge = 1; else - acpi_sfi_table_parse(ACPI_SIG_MCFG, pci_parse_mcfg); + acpi_table_parse(ACPI_SIG_MCFG, pci_parse_mcfg); __pci_mmcfg_init(1); set_apei_filter(); @@ -683,7 +683,7 @@ void __init pci_mmcfg_late_init(void) /* MMCONFIG hasn't been enabled yet, try again */ if (pci_probe & PCI_PROBE_MASK & ~PCI_PROBE_MMCONF) { - acpi_sfi_table_parse(ACPI_SIG_MCFG, pci_parse_mcfg); + acpi_table_parse(ACPI_SIG_MCFG, pci_parse_mcfg); __pci_mmcfg_init(0); } } diff --git a/arch/x86/platform/Makefile b/arch/x86/platform/Makefile index d0e835470d01..d1f5228225d9 100644 --- a/arch/x86/platform/Makefile +++ b/arch/x86/platform/Makefile @@ -11,6 +11,5 @@ obj-y += intel-mid/ obj-y += intel-quark/ obj-y += olpc/ obj-y += scx200/ -obj-y += sfi/ obj-y += ts5500/ obj-y += uv/ diff --git a/arch/x86/platform/intel-mid/Makefile b/arch/x86/platform/intel-mid/Makefile index 5794e661050c..ddfc08783fb8 100644 --- a/arch/x86/platform/intel-mid/Makefile +++ b/arch/x86/platform/intel-mid/Makefile @@ -1,7 +1,2 @@ # SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_X86_INTEL_MID) += intel-mid.o pwr.o - -# SFI specific code -ifdef CONFIG_X86_INTEL_MID -obj-$(CONFIG_SFI) += sfi.o device_libs/ -endif diff --git a/arch/x86/platform/intel-mid/device_libs/Makefile b/arch/x86/platform/intel-mid/device_libs/Makefile deleted file mode 100644 index 4d008b053ac8..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/Makefile +++ /dev/null @@ -1,23 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -# Family-Level Interface Shim (FLIS) -obj-$(subst m,y,$(CONFIG_PINCTRL_MERRIFIELD)) += platform_mrfld_pinctrl.o -# SDHCI Devices -obj-$(subst m,y,$(CONFIG_MMC_SDHCI_PCI)) += platform_mrfld_sd.o -# WiFi + BT -obj-$(subst m,y,$(CONFIG_BRCMFMAC_SDIO)) += platform_bcm43xx.o -obj-$(subst m,y,$(CONFIG_BT_HCIUART_BCM)) += platform_bt.o -# SPI Devices -obj-$(subst m,y,$(CONFIG_SPI_SPIDEV)) += platform_mrfld_spidev.o -# I2C Devices -obj-$(subst m,y,$(CONFIG_SENSORS_EMC1403)) += platform_emc1403.o -obj-$(subst m,y,$(CONFIG_SENSORS_LIS3LV02D)) += platform_lis331.o -obj-$(subst m,y,$(CONFIG_MPU3050_I2C)) += platform_mpu3050.o -obj-$(subst m,y,$(CONFIG_INPUT_BMA150)) += platform_bma023.o -obj-$(subst m,y,$(CONFIG_DRM_MEDFIELD)) += platform_tc35876x.o -# I2C GPIO Expanders -obj-$(subst m,y,$(CONFIG_GPIO_PCA953X)) += platform_max7315.o -obj-$(subst m,y,$(CONFIG_GPIO_PCA953X)) += platform_pcal9555a.o -obj-$(subst m,y,$(CONFIG_GPIO_PCA953X)) += platform_tca6416.o -# MISC Devices -obj-$(subst m,y,$(CONFIG_KEYBOARD_GPIO)) += platform_gpio_keys.o -obj-$(subst m,y,$(CONFIG_RTC_DRV_CMOS)) += platform_mrfld_rtc.o diff --git a/arch/x86/platform/intel-mid/device_libs/platform_bcm43xx.c b/arch/x86/platform/intel-mid/device_libs/platform_bcm43xx.c deleted file mode 100644 index 564c47c53f3a..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_bcm43xx.c +++ /dev/null @@ -1,101 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * platform_bcm43xx.c: bcm43xx platform data initialization file - * - * (C) Copyright 2016 Intel Corporation - * Author: Andy Shevchenko - */ - -#include -#include -#include -#include -#include - -#include - -#define WLAN_SFI_GPIO_IRQ_NAME "WLAN-interrupt" -#define WLAN_SFI_GPIO_ENABLE_NAME "WLAN-enable" - -#define WLAN_DEV_NAME "0000:00:01.3" - -static struct regulator_consumer_supply bcm43xx_vmmc_supply = { - .dev_name = WLAN_DEV_NAME, - .supply = "vmmc", -}; - -static struct regulator_init_data bcm43xx_vmmc_data = { - .constraints = { - .valid_ops_mask = REGULATOR_CHANGE_STATUS, - }, - .num_consumer_supplies = 1, - .consumer_supplies = &bcm43xx_vmmc_supply, -}; - -static struct fixed_voltage_config bcm43xx_vmmc = { - .supply_name = "bcm43xx-vmmc-regulator", - /* - * Announce 2.0V here to be compatible with SDIO specification. The - * real voltage and signaling are still 1.8V. - */ - .microvolts = 2000000, /* 1.8V */ - .startup_delay = 250 * 1000, /* 250ms */ - .enabled_at_boot = 0, /* disabled at boot */ - .init_data = &bcm43xx_vmmc_data, -}; - -static struct platform_device bcm43xx_vmmc_regulator = { - .name = "reg-fixed-voltage", - .id = PLATFORM_DEVID_AUTO, - .dev = { - .platform_data = &bcm43xx_vmmc, - }, -}; - -static struct gpiod_lookup_table bcm43xx_vmmc_gpio_table = { - .dev_id = "reg-fixed-voltage.0", - .table = { - GPIO_LOOKUP("0000:00:0c.0", -1, NULL, GPIO_ACTIVE_LOW), - {} - }, -}; - -static int __init bcm43xx_regulator_register(void) -{ - struct gpiod_lookup_table *table = &bcm43xx_vmmc_gpio_table; - struct gpiod_lookup *lookup = table->table; - int ret; - - lookup[0].chip_hwnum = get_gpio_by_name(WLAN_SFI_GPIO_ENABLE_NAME); - gpiod_add_lookup_table(table); - - ret = platform_device_register(&bcm43xx_vmmc_regulator); - if (ret) { - pr_err("%s: vmmc regulator register failed\n", __func__); - return ret; - } - - return 0; -} - -static void __init *bcm43xx_platform_data(void *info) -{ - int ret; - - ret = bcm43xx_regulator_register(); - if (ret) - return NULL; - - pr_info("Using generic wifi platform data\n"); - - /* For now it's empty */ - return NULL; -} - -static const struct devs_id bcm43xx_clk_vmmc_dev_id __initconst = { - .name = "bcm43xx_clk_vmmc", - .type = SFI_DEV_TYPE_SD, - .get_platform_data = &bcm43xx_platform_data, -}; - -sfi_device(bcm43xx_clk_vmmc_dev_id); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_bma023.c b/arch/x86/platform/intel-mid/device_libs/platform_bma023.c deleted file mode 100644 index 32912a17f68e..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_bma023.c +++ /dev/null @@ -1,16 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * platform_bma023.c: bma023 platform data initialization file - * - * (C) Copyright 2013 Intel Corporation - */ - -#include - -static const struct devs_id bma023_dev_id __initconst = { - .name = "bma023", - .type = SFI_DEV_TYPE_I2C, - .delay = 1, -}; - -sfi_device(bma023_dev_id); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_bt.c b/arch/x86/platform/intel-mid/device_libs/platform_bt.c deleted file mode 100644 index 31dda18bb370..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_bt.c +++ /dev/null @@ -1,101 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Bluetooth platform data initialization file - * - * (C) Copyright 2017 Intel Corporation - * Author: Andy Shevchenko - */ - -#include -#include -#include - -#include -#include -#include - -struct bt_sfi_data { - struct device *dev; - const char *name; - int (*setup)(struct bt_sfi_data *ddata); -}; - -static struct gpiod_lookup_table tng_bt_sfi_gpio_table = { - .dev_id = "hci_bcm", - .table = { - GPIO_LOOKUP("0000:00:0c.0", -1, "device-wakeup", GPIO_ACTIVE_HIGH), - GPIO_LOOKUP("0000:00:0c.0", -1, "shutdown", GPIO_ACTIVE_HIGH), - GPIO_LOOKUP("0000:00:0c.0", -1, "host-wakeup", GPIO_ACTIVE_HIGH), - { }, - }, -}; - -#define TNG_BT_SFI_GPIO_DEVICE_WAKEUP "bt_wakeup" -#define TNG_BT_SFI_GPIO_SHUTDOWN "BT-reset" -#define TNG_BT_SFI_GPIO_HOST_WAKEUP "bt_uart_enable" - -static int __init tng_bt_sfi_setup(struct bt_sfi_data *ddata) -{ - struct gpiod_lookup_table *table = &tng_bt_sfi_gpio_table; - struct gpiod_lookup *lookup = table->table; - struct pci_dev *pdev; - - /* Connected to /dev/ttyS0 */ - pdev = pci_get_domain_bus_and_slot(0, 0, PCI_DEVFN(4, 1)); - if (!pdev) - return -ENODEV; - - ddata->dev = &pdev->dev; - ddata->name = table->dev_id; - - lookup[0].chip_hwnum = get_gpio_by_name(TNG_BT_SFI_GPIO_DEVICE_WAKEUP); - lookup[1].chip_hwnum = get_gpio_by_name(TNG_BT_SFI_GPIO_SHUTDOWN); - lookup[2].chip_hwnum = get_gpio_by_name(TNG_BT_SFI_GPIO_HOST_WAKEUP); - - gpiod_add_lookup_table(table); - return 0; -} - -static struct bt_sfi_data tng_bt_sfi_data __initdata = { - .setup = tng_bt_sfi_setup, -}; - -static const struct x86_cpu_id bt_sfi_cpu_ids[] = { - X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT_MID, &tng_bt_sfi_data), - {} -}; - -static int __init bt_sfi_init(void) -{ - struct platform_device_info info; - struct platform_device *pdev; - const struct x86_cpu_id *id; - struct bt_sfi_data *ddata; - int ret; - - id = x86_match_cpu(bt_sfi_cpu_ids); - if (!id) - return -ENODEV; - - ddata = (struct bt_sfi_data *)id->driver_data; - if (!ddata) - return -ENODEV; - - ret = ddata->setup(ddata); - if (ret) - return ret; - - memset(&info, 0, sizeof(info)); - info.fwnode = ddata->dev->fwnode; - info.parent = ddata->dev; - info.name = ddata->name, - info.id = PLATFORM_DEVID_NONE, - - pdev = platform_device_register_full(&info); - if (IS_ERR(pdev)) - return PTR_ERR(pdev); - - dev_info(ddata->dev, "Registered Bluetooth device: %s\n", ddata->name); - return 0; -} -device_initcall(bt_sfi_init); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_emc1403.c b/arch/x86/platform/intel-mid/device_libs/platform_emc1403.c deleted file mode 100644 index a2508582a0b1..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_emc1403.c +++ /dev/null @@ -1,39 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * platform_emc1403.c: emc1403 platform data initialization file - * - * (C) Copyright 2013 Intel Corporation - * Author: Sathyanarayanan Kuppuswamy - */ - -#include -#include -#include -#include - -static void __init *emc1403_platform_data(void *info) -{ - static short intr2nd_pdata; - struct i2c_board_info *i2c_info = info; - int intr = get_gpio_by_name("thermal_int"); - int intr2nd = get_gpio_by_name("thermal_alert"); - - if (intr < 0) - return NULL; - if (intr2nd < 0) - return NULL; - - i2c_info->irq = intr + INTEL_MID_IRQ_OFFSET; - intr2nd_pdata = intr2nd + INTEL_MID_IRQ_OFFSET; - - return &intr2nd_pdata; -} - -static const struct devs_id emc1403_dev_id __initconst = { - .name = "emc1403", - .type = SFI_DEV_TYPE_I2C, - .delay = 1, - .get_platform_data = &emc1403_platform_data, -}; - -sfi_device(emc1403_dev_id); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_gpio_keys.c b/arch/x86/platform/intel-mid/device_libs/platform_gpio_keys.c deleted file mode 100644 index d9435d2196a4..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_gpio_keys.c +++ /dev/null @@ -1,81 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * platform_gpio_keys.c: gpio_keys platform data initialization file - * - * (C) Copyright 2013 Intel Corporation - * Author: Sathyanarayanan Kuppuswamy - */ - -#include -#include -#include -#include -#include -#include -#include - -#define DEVICE_NAME "gpio-keys" - -/* - * we will search these buttons in SFI GPIO table (by name) - * and register them dynamically. Please add all possible - * buttons here, we will shrink them if no GPIO found. - */ -static struct gpio_keys_button gpio_button[] = { - {KEY_POWER, -1, 1, "power_btn", EV_KEY, 0, 3000}, - {KEY_PROG1, -1, 1, "prog_btn1", EV_KEY, 0, 20}, - {KEY_PROG2, -1, 1, "prog_btn2", EV_KEY, 0, 20}, - {SW_LID, -1, 1, "lid_switch", EV_SW, 0, 20}, - {KEY_VOLUMEUP, -1, 1, "vol_up", EV_KEY, 0, 20}, - {KEY_VOLUMEDOWN, -1, 1, "vol_down", EV_KEY, 0, 20}, - {KEY_MUTE, -1, 1, "mute_enable", EV_KEY, 0, 20}, - {KEY_VOLUMEUP, -1, 1, "volume_up", EV_KEY, 0, 20}, - {KEY_VOLUMEDOWN, -1, 1, "volume_down", EV_KEY, 0, 20}, - {KEY_CAMERA, -1, 1, "camera_full", EV_KEY, 0, 20}, - {KEY_CAMERA_FOCUS, -1, 1, "camera_half", EV_KEY, 0, 20}, - {SW_KEYPAD_SLIDE, -1, 1, "MagSw1", EV_SW, 0, 20}, - {SW_KEYPAD_SLIDE, -1, 1, "MagSw2", EV_SW, 0, 20}, -}; - -static struct gpio_keys_platform_data gpio_keys = { - .buttons = gpio_button, - .rep = 1, - .nbuttons = -1, /* will fill it after search */ -}; - -static struct platform_device pb_device = { - .name = DEVICE_NAME, - .id = -1, - .dev = { - .platform_data = &gpio_keys, - }, -}; - -/* - * Shrink the non-existent buttons, register the gpio button - * device if there is some - */ -static int __init pb_keys_init(void) -{ - struct gpio_keys_button *gb = gpio_button; - int i, good = 0; - - for (i = 0; i < ARRAY_SIZE(gpio_button); i++) { - gb[i].gpio = get_gpio_by_name(gb[i].desc); - pr_debug("info[%2d]: name = %s, gpio = %d\n", i, gb[i].desc, - gb[i].gpio); - if (gb[i].gpio < 0) - continue; - - if (i != good) - gb[good] = gb[i]; - good++; - } - - if (good) { - gpio_keys.nbuttons = good; - return platform_device_register(&pb_device); - } - return 0; -} -late_initcall(pb_keys_init); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_lis331.c b/arch/x86/platform/intel-mid/device_libs/platform_lis331.c deleted file mode 100644 index a4485cd638c6..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_lis331.c +++ /dev/null @@ -1,37 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * platform_lis331.c: lis331 platform data initialization file - * - * (C) Copyright 2013 Intel Corporation - * Author: Sathyanarayanan Kuppuswamy - */ - -#include -#include -#include - -static void __init *lis331dl_platform_data(void *info) -{ - static short intr2nd_pdata; - struct i2c_board_info *i2c_info = info; - int intr = get_gpio_by_name("accel_int"); - int intr2nd = get_gpio_by_name("accel_2"); - - if (intr < 0) - return NULL; - if (intr2nd < 0) - return NULL; - - i2c_info->irq = intr + INTEL_MID_IRQ_OFFSET; - intr2nd_pdata = intr2nd + INTEL_MID_IRQ_OFFSET; - - return &intr2nd_pdata; -} - -static const struct devs_id lis331dl_dev_id __initconst = { - .name = "i2c_accel", - .type = SFI_DEV_TYPE_I2C, - .get_platform_data = &lis331dl_platform_data, -}; - -sfi_device(lis331dl_dev_id); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_max7315.c b/arch/x86/platform/intel-mid/device_libs/platform_max7315.c deleted file mode 100644 index e9287c3184da..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_max7315.c +++ /dev/null @@ -1,77 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * platform_max7315.c: max7315 platform data initialization file - * - * (C) Copyright 2013 Intel Corporation - * Author: Sathyanarayanan Kuppuswamy - */ - -#include -#include -#include -#include -#include - -#define MAX7315_NUM 2 - -static void __init *max7315_platform_data(void *info) -{ - static struct pca953x_platform_data max7315_pdata[MAX7315_NUM]; - static int nr; - struct pca953x_platform_data *max7315 = &max7315_pdata[nr]; - struct i2c_board_info *i2c_info = info; - int gpio_base, intr; - char base_pin_name[SFI_NAME_LEN + 1]; - char intr_pin_name[SFI_NAME_LEN + 1]; - - if (nr == MAX7315_NUM) { - pr_err("too many max7315s, we only support %d\n", - MAX7315_NUM); - return NULL; - } - /* we have several max7315 on the board, we only need load several - * instances of the same pca953x driver to cover them - */ - strcpy(i2c_info->type, "max7315"); - if (nr++) { - snprintf(base_pin_name, sizeof(base_pin_name), - "max7315_%d_base", nr); - snprintf(intr_pin_name, sizeof(intr_pin_name), - "max7315_%d_int", nr); - } else { - strcpy(base_pin_name, "max7315_base"); - strcpy(intr_pin_name, "max7315_int"); - } - - gpio_base = get_gpio_by_name(base_pin_name); - intr = get_gpio_by_name(intr_pin_name); - - if (gpio_base < 0) - return NULL; - max7315->gpio_base = gpio_base; - if (intr != -1) { - i2c_info->irq = intr + INTEL_MID_IRQ_OFFSET; - max7315->irq_base = gpio_base + INTEL_MID_IRQ_OFFSET; - } else { - i2c_info->irq = -1; - max7315->irq_base = -1; - } - return max7315; -} - -static const struct devs_id max7315_dev_id __initconst = { - .name = "i2c_max7315", - .type = SFI_DEV_TYPE_I2C, - .delay = 1, - .get_platform_data = &max7315_platform_data, -}; - -static const struct devs_id max7315_2_dev_id __initconst = { - .name = "i2c_max7315_2", - .type = SFI_DEV_TYPE_I2C, - .delay = 1, - .get_platform_data = &max7315_platform_data, -}; - -sfi_device(max7315_dev_id); -sfi_device(max7315_2_dev_id); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_mpu3050.c b/arch/x86/platform/intel-mid/device_libs/platform_mpu3050.c deleted file mode 100644 index 28a182713934..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_mpu3050.c +++ /dev/null @@ -1,32 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * platform_mpu3050.c: mpu3050 platform data initialization file - * - * (C) Copyright 2013 Intel Corporation - * Author: Sathyanarayanan Kuppuswamy - */ - -#include -#include -#include - -static void *mpu3050_platform_data(void *info) -{ - struct i2c_board_info *i2c_info = info; - int intr = get_gpio_by_name("mpu3050_int"); - - if (intr < 0) - return NULL; - - i2c_info->irq = intr + INTEL_MID_IRQ_OFFSET; - return NULL; -} - -static const struct devs_id mpu3050_dev_id __initconst = { - .name = "mpu3050", - .type = SFI_DEV_TYPE_I2C, - .delay = 1, - .get_platform_data = &mpu3050_platform_data, -}; - -sfi_device(mpu3050_dev_id); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_pinctrl.c b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_pinctrl.c deleted file mode 100644 index 605e1f94ad89..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_pinctrl.c +++ /dev/null @@ -1,39 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Intel Merrifield FLIS platform device initialization file - * - * Copyright (C) 2016, Intel Corporation - * - * Author: Andy Shevchenko - */ - -#include -#include -#include - -#include - -#define FLIS_BASE_ADDR 0xff0c0000 -#define FLIS_LENGTH 0x8000 - -static struct resource mrfld_pinctrl_mmio_resource = { - .start = FLIS_BASE_ADDR, - .end = FLIS_BASE_ADDR + FLIS_LENGTH - 1, - .flags = IORESOURCE_MEM, -}; - -static struct platform_device mrfld_pinctrl_device = { - .name = "pinctrl-merrifield", - .id = PLATFORM_DEVID_NONE, - .resource = &mrfld_pinctrl_mmio_resource, - .num_resources = 1, -}; - -static int __init mrfld_pinctrl_init(void) -{ - if (intel_mid_identify_cpu() == INTEL_MID_CPU_CHIP_TANGIER) - return platform_device_register(&mrfld_pinctrl_device); - - return -ENODEV; -} -arch_initcall(mrfld_pinctrl_init); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_rtc.c b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_rtc.c deleted file mode 100644 index 40e9808a9634..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_rtc.c +++ /dev/null @@ -1,44 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Intel Merrifield legacy RTC initialization file - * - * (C) Copyright 2017 Intel Corporation - * - * Author: Andy Shevchenko - */ - -#include - -#include -#include -#include -#include -#include - -static int __init mrfld_legacy_rtc_alloc_irq(void) -{ - struct irq_alloc_info info; - int ret; - - if (!x86_platform.legacy.rtc) - return -ENODEV; - - ioapic_set_alloc_attr(&info, NUMA_NO_NODE, 1, 0); - ret = mp_map_gsi_to_irq(RTC_IRQ, IOAPIC_MAP_ALLOC, &info); - if (ret < 0) { - pr_info("Failed to allocate RTC interrupt. Disabling RTC\n"); - x86_platform.legacy.rtc = 0; - return ret; - } - - return 0; -} - -static int __init mrfld_legacy_rtc_init(void) -{ - if (intel_mid_identify_cpu() != INTEL_MID_CPU_CHIP_TANGIER) - return -ENODEV; - - return mrfld_legacy_rtc_alloc_irq(); -} -arch_initcall(mrfld_legacy_rtc_init); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_sd.c b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_sd.c deleted file mode 100644 index fe3b7ff975f3..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_sd.c +++ /dev/null @@ -1,43 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * SDHCI platform data initilisation file - * - * (C) Copyright 2016 Intel Corporation - * Author: Andy Shevchenko - */ - -#include -#include - -#include - -#include - -#define INTEL_MRFLD_SD 2 -#define INTEL_MRFLD_SD_CD_GPIO 77 - -static struct sdhci_pci_data mrfld_sdhci_pci_data = { - .rst_n_gpio = -EINVAL, - .cd_gpio = INTEL_MRFLD_SD_CD_GPIO, -}; - -static struct sdhci_pci_data * -mrfld_sdhci_pci_get_data(struct pci_dev *pdev, int slotno) -{ - unsigned int func = PCI_FUNC(pdev->devfn); - - if (func == INTEL_MRFLD_SD) - return &mrfld_sdhci_pci_data; - - return NULL; -} - -static int __init mrfld_sd_init(void) -{ - if (intel_mid_identify_cpu() != INTEL_MID_CPU_CHIP_TANGIER) - return -ENODEV; - - sdhci_pci_get_data = mrfld_sdhci_pci_get_data; - return 0; -} -arch_initcall(mrfld_sd_init); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_spidev.c b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_spidev.c deleted file mode 100644 index b828f4fd40be..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_spidev.c +++ /dev/null @@ -1,50 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * spidev platform data initialization file - * - * (C) Copyright 2014, 2016 Intel Corporation - * Authors: Andy Shevchenko - * Dan O'Donovan - */ - -#include -#include -#include -#include -#include - -#include - -#define MRFLD_SPI_DEFAULT_DMA_BURST 8 -#define MRFLD_SPI_DEFAULT_TIMEOUT 500 - -/* GPIO pin for spidev chipselect */ -#define MRFLD_SPIDEV_GPIO_CS 111 - -static struct pxa2xx_spi_chip spidev_spi_chip = { - .dma_burst_size = MRFLD_SPI_DEFAULT_DMA_BURST, - .timeout = MRFLD_SPI_DEFAULT_TIMEOUT, - .gpio_cs = MRFLD_SPIDEV_GPIO_CS, -}; - -static void __init *spidev_platform_data(void *info) -{ - struct spi_board_info *spi_info = info; - - if (intel_mid_identify_cpu() != INTEL_MID_CPU_CHIP_TANGIER) - return ERR_PTR(-ENODEV); - - spi_info->mode = SPI_MODE_0; - spi_info->controller_data = &spidev_spi_chip; - - return NULL; -} - -static const struct devs_id spidev_dev_id __initconst = { - .name = "spidev", - .type = SFI_DEV_TYPE_SPI, - .delay = 0, - .get_platform_data = &spidev_platform_data, -}; - -sfi_device(spidev_dev_id); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_pcal9555a.c b/arch/x86/platform/intel-mid/device_libs/platform_pcal9555a.c deleted file mode 100644 index 5609d8da3978..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_pcal9555a.c +++ /dev/null @@ -1,95 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * PCAL9555a platform data initialization file - * - * Copyright (C) 2016, Intel Corporation - * - * Authors: Andy Shevchenko - * Dan O'Donovan - */ - -#include -#include -#include -#include -#include - -#include - -#define PCAL9555A_NUM 4 - -static struct pca953x_platform_data pcal9555a_pdata[PCAL9555A_NUM]; -static int nr; - -static void __init *pcal9555a_platform_data(void *info) -{ - struct i2c_board_info *i2c_info = info; - char *type = i2c_info->type; - struct pca953x_platform_data *pcal9555a; - char base_pin_name[SFI_NAME_LEN + 1]; - char intr_pin_name[SFI_NAME_LEN + 1]; - int gpio_base, intr; - - snprintf(base_pin_name, sizeof(base_pin_name), "%s_base", type); - snprintf(intr_pin_name, sizeof(intr_pin_name), "%s_int", type); - - gpio_base = get_gpio_by_name(base_pin_name); - intr = get_gpio_by_name(intr_pin_name); - - /* Check if the SFI record valid */ - if (gpio_base == -1) - return NULL; - - if (nr >= PCAL9555A_NUM) { - pr_err("%s: Too many instances, only %d supported\n", __func__, - PCAL9555A_NUM); - return NULL; - } - - pcal9555a = &pcal9555a_pdata[nr++]; - pcal9555a->gpio_base = gpio_base; - - if (intr >= 0) { - i2c_info->irq = intr + INTEL_MID_IRQ_OFFSET; - pcal9555a->irq_base = gpio_base + INTEL_MID_IRQ_OFFSET; - } else { - i2c_info->irq = -1; - pcal9555a->irq_base = -1; - } - - strcpy(type, "pcal9555a"); - return pcal9555a; -} - -static const struct devs_id pcal9555a_1_dev_id __initconst = { - .name = "pcal9555a-1", - .type = SFI_DEV_TYPE_I2C, - .delay = 1, - .get_platform_data = &pcal9555a_platform_data, -}; - -static const struct devs_id pcal9555a_2_dev_id __initconst = { - .name = "pcal9555a-2", - .type = SFI_DEV_TYPE_I2C, - .delay = 1, - .get_platform_data = &pcal9555a_platform_data, -}; - -static const struct devs_id pcal9555a_3_dev_id __initconst = { - .name = "pcal9555a-3", - .type = SFI_DEV_TYPE_I2C, - .delay = 1, - .get_platform_data = &pcal9555a_platform_data, -}; - -static const struct devs_id pcal9555a_4_dev_id __initconst = { - .name = "pcal9555a-4", - .type = SFI_DEV_TYPE_I2C, - .delay = 1, - .get_platform_data = &pcal9555a_platform_data, -}; - -sfi_device(pcal9555a_1_dev_id); -sfi_device(pcal9555a_2_dev_id); -sfi_device(pcal9555a_3_dev_id); -sfi_device(pcal9555a_4_dev_id); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_tc35876x.c b/arch/x86/platform/intel-mid/device_libs/platform_tc35876x.c deleted file mode 100644 index 139738bbdd36..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_tc35876x.c +++ /dev/null @@ -1,42 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * platform_tc35876x.c: tc35876x platform data initialization file - * - * (C) Copyright 2013 Intel Corporation - * Author: Sathyanarayanan Kuppuswamy - */ - -#include -#include - -static struct gpiod_lookup_table tc35876x_gpio_table = { - .dev_id = "i2c_disp_brig", - .table = { - GPIO_LOOKUP("0000:00:0c.0", -1, "bridge-reset", GPIO_ACTIVE_HIGH), - GPIO_LOOKUP("0000:00:0c.0", -1, "bl-en", GPIO_ACTIVE_HIGH), - GPIO_LOOKUP("0000:00:0c.0", -1, "vadd", GPIO_ACTIVE_HIGH), - { }, - }, -}; - -/*tc35876x DSI_LVDS bridge chip and panel platform data*/ -static void *tc35876x_platform_data(void *data) -{ - struct gpiod_lookup_table *table = &tc35876x_gpio_table; - struct gpiod_lookup *lookup = table->table; - - lookup[0].chip_hwnum = get_gpio_by_name("LCMB_RXEN"); - lookup[1].chip_hwnum = get_gpio_by_name("6S6P_BL_EN"); - lookup[2].chip_hwnum = get_gpio_by_name("EN_VREG_LCD_V3P3"); - gpiod_add_lookup_table(table); - - return NULL; -} - -static const struct devs_id tc35876x_dev_id __initconst = { - .name = "i2c_disp_brig", - .type = SFI_DEV_TYPE_I2C, - .get_platform_data = &tc35876x_platform_data, -}; - -sfi_device(tc35876x_dev_id); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_tca6416.c b/arch/x86/platform/intel-mid/device_libs/platform_tca6416.c deleted file mode 100644 index e689d8f61059..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_tca6416.c +++ /dev/null @@ -1,53 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * platform_tca6416.c: tca6416 platform data initialization file - * - * (C) Copyright 2013 Intel Corporation - * Author: Sathyanarayanan Kuppuswamy - */ - -#include -#include -#include -#include - -#define TCA6416_NAME "tca6416" -#define TCA6416_BASE "tca6416_base" -#define TCA6416_INTR "tca6416_int" - -static void *tca6416_platform_data(void *info) -{ - static struct pca953x_platform_data tca6416; - struct i2c_board_info *i2c_info = info; - int gpio_base, intr; - char base_pin_name[SFI_NAME_LEN + 1]; - char intr_pin_name[SFI_NAME_LEN + 1]; - - strcpy(i2c_info->type, TCA6416_NAME); - strcpy(base_pin_name, TCA6416_BASE); - strcpy(intr_pin_name, TCA6416_INTR); - - gpio_base = get_gpio_by_name(base_pin_name); - intr = get_gpio_by_name(intr_pin_name); - - if (gpio_base < 0) - return NULL; - tca6416.gpio_base = gpio_base; - if (intr >= 0) { - i2c_info->irq = intr + INTEL_MID_IRQ_OFFSET; - tca6416.irq_base = gpio_base + INTEL_MID_IRQ_OFFSET; - } else { - i2c_info->irq = -1; - tca6416.irq_base = -1; - } - return &tca6416; -} - -static const struct devs_id tca6416_dev_id __initconst = { - .name = "tca6416", - .type = SFI_DEV_TYPE_I2C, - .delay = 1, - .get_platform_data = &tca6416_platform_data, -}; - -sfi_device(tca6416_dev_id); diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c index 864b0c158b2f..2c044e260b4b 100644 --- a/arch/x86/platform/intel-mid/intel-mid.c +++ b/arch/x86/platform/intel-mid/intel-mid.c @@ -14,7 +14,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/x86/platform/intel-mid/sfi.c b/arch/x86/platform/intel-mid/sfi.c deleted file mode 100644 index 63ae342ffb12..000000000000 --- a/arch/x86/platform/intel-mid/sfi.c +++ /dev/null @@ -1,419 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * intel_mid_sfi.c: Intel MID SFI initialization code - * - * (C) Copyright 2013 Intel Corporation - * Author: Sathyanarayanan Kuppuswamy - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#define SFI_SIG_OEM0 "OEM0" -#define MAX_IPCDEVS 24 -#define MAX_SCU_SPI 24 -#define MAX_SCU_I2C 24 - -static struct platform_device *ipc_devs[MAX_IPCDEVS]; -static struct spi_board_info *spi_devs[MAX_SCU_SPI]; -static struct i2c_board_info *i2c_devs[MAX_SCU_I2C]; -static struct sfi_gpio_table_entry *gpio_table; -static int ipc_next_dev; -static int spi_next_dev; -static int i2c_next_dev; -static int i2c_bus[MAX_SCU_I2C]; -static int gpio_num_entry; - -struct blocking_notifier_head intel_scu_notifier = - BLOCKING_NOTIFIER_INIT(intel_scu_notifier); -EXPORT_SYMBOL_GPL(intel_scu_notifier); - -#define intel_mid_sfi_get_pdata(dev, priv) \ - ((dev)->get_platform_data ? (dev)->get_platform_data(priv) : NULL) - -/* - * Parsing GPIO table first, since the DEVS table will need this table - * to map the pin name to the actual pin. - */ -static int __init sfi_parse_gpio(struct sfi_table_header *table) -{ - struct sfi_table_simple *sb; - struct sfi_gpio_table_entry *pentry; - int num, i; - - if (gpio_table) - return 0; - sb = (struct sfi_table_simple *)table; - num = SFI_GET_NUM_ENTRIES(sb, struct sfi_gpio_table_entry); - pentry = (struct sfi_gpio_table_entry *)sb->pentry; - - gpio_table = kmemdup(pentry, num * sizeof(*pentry), GFP_KERNEL); - if (!gpio_table) - return -1; - gpio_num_entry = num; - - pr_debug("GPIO pin info:\n"); - for (i = 0; i < num; i++, pentry++) - pr_debug("info[%2d]: controller = %16.16s, pin_name = %16.16s," - " pin = %d\n", i, - pentry->controller_name, - pentry->pin_name, - pentry->pin_no); - return 0; -} - -int get_gpio_by_name(const char *name) -{ - struct sfi_gpio_table_entry *pentry = gpio_table; - int i; - - if (!pentry) - return -1; - for (i = 0; i < gpio_num_entry; i++, pentry++) { - if (!strncmp(name, pentry->pin_name, SFI_NAME_LEN)) - return pentry->pin_no; - } - return -EINVAL; -} - -static void __init intel_scu_ipc_device_register(struct platform_device *pdev) -{ - if (ipc_next_dev == MAX_IPCDEVS) - pr_err("too many SCU IPC devices"); - else - ipc_devs[ipc_next_dev++] = pdev; -} - -static void __init intel_scu_spi_device_register(struct spi_board_info *sdev) -{ - struct spi_board_info *new_dev; - - if (spi_next_dev == MAX_SCU_SPI) { - pr_err("too many SCU SPI devices"); - return; - } - - new_dev = kzalloc(sizeof(*sdev), GFP_KERNEL); - if (!new_dev) { - pr_err("failed to alloc mem for delayed spi dev %s\n", - sdev->modalias); - return; - } - *new_dev = *sdev; - - spi_devs[spi_next_dev++] = new_dev; -} - -static void __init intel_scu_i2c_device_register(int bus, - struct i2c_board_info *idev) -{ - struct i2c_board_info *new_dev; - - if (i2c_next_dev == MAX_SCU_I2C) { - pr_err("too many SCU I2C devices"); - return; - } - - new_dev = kzalloc(sizeof(*idev), GFP_KERNEL); - if (!new_dev) { - pr_err("failed to alloc mem for delayed i2c dev %s\n", - idev->type); - return; - } - *new_dev = *idev; - - i2c_bus[i2c_next_dev] = bus; - i2c_devs[i2c_next_dev++] = new_dev; -} - -/* Called by IPC driver */ -void intel_scu_devices_create(void) -{ - int i; - - for (i = 0; i < ipc_next_dev; i++) - platform_device_add(ipc_devs[i]); - - for (i = 0; i < spi_next_dev; i++) - spi_register_board_info(spi_devs[i], 1); - - for (i = 0; i < i2c_next_dev; i++) { - struct i2c_adapter *adapter; - struct i2c_client *client; - - adapter = i2c_get_adapter(i2c_bus[i]); - if (adapter) { - client = i2c_new_client_device(adapter, i2c_devs[i]); - if (IS_ERR(client)) - pr_err("can't create i2c device %s\n", - i2c_devs[i]->type); - } else - i2c_register_board_info(i2c_bus[i], i2c_devs[i], 1); - } - intel_scu_notifier_post(SCU_AVAILABLE, NULL); -} -EXPORT_SYMBOL_GPL(intel_scu_devices_create); - -/* Called by IPC driver */ -void intel_scu_devices_destroy(void) -{ - int i; - - intel_scu_notifier_post(SCU_DOWN, NULL); - - for (i = 0; i < ipc_next_dev; i++) - platform_device_del(ipc_devs[i]); -} -EXPORT_SYMBOL_GPL(intel_scu_devices_destroy); - -static void __init install_irq_resource(struct platform_device *pdev, int irq) -{ - /* Single threaded */ - static struct resource res __initdata = { - .name = "IRQ", - .flags = IORESOURCE_IRQ, - }; - res.start = irq; - platform_device_add_resources(pdev, &res, 1); -} - -static void __init sfi_handle_ipc_dev(struct sfi_device_table_entry *pentry, - struct devs_id *dev) -{ - struct platform_device *pdev; - void *pdata = NULL; - - pr_debug("IPC bus, name = %16.16s, irq = 0x%2x\n", - pentry->name, pentry->irq); - - /* - * We need to call platform init of IPC devices to fill misc_pdata - * structure. It will be used in msic_init for initialization. - */ - pdata = intel_mid_sfi_get_pdata(dev, pentry); - if (IS_ERR(pdata)) - return; - - pdev = platform_device_alloc(pentry->name, 0); - if (pdev == NULL) { - pr_err("out of memory for SFI platform device '%s'.\n", - pentry->name); - return; - } - install_irq_resource(pdev, pentry->irq); - - pdev->dev.platform_data = pdata; - if (dev->delay) - intel_scu_ipc_device_register(pdev); - else - platform_device_add(pdev); -} - -static void __init sfi_handle_spi_dev(struct sfi_device_table_entry *pentry, - struct devs_id *dev) -{ - struct spi_board_info spi_info; - void *pdata = NULL; - - memset(&spi_info, 0, sizeof(spi_info)); - strncpy(spi_info.modalias, pentry->name, SFI_NAME_LEN); - spi_info.irq = ((pentry->irq == (u8)0xff) ? 0 : pentry->irq); - spi_info.bus_num = pentry->host_num; - spi_info.chip_select = pentry->addr; - spi_info.max_speed_hz = pentry->max_freq; - pr_debug("SPI bus=%d, name=%16.16s, irq=0x%2x, max_freq=%d, cs=%d\n", - spi_info.bus_num, - spi_info.modalias, - spi_info.irq, - spi_info.max_speed_hz, - spi_info.chip_select); - - pdata = intel_mid_sfi_get_pdata(dev, &spi_info); - if (IS_ERR(pdata)) - return; - - spi_info.platform_data = pdata; - if (dev->delay) - intel_scu_spi_device_register(&spi_info); - else - spi_register_board_info(&spi_info, 1); -} - -static void __init sfi_handle_i2c_dev(struct sfi_device_table_entry *pentry, - struct devs_id *dev) -{ - struct i2c_board_info i2c_info; - void *pdata = NULL; - - memset(&i2c_info, 0, sizeof(i2c_info)); - strncpy(i2c_info.type, pentry->name, SFI_NAME_LEN); - i2c_info.irq = ((pentry->irq == (u8)0xff) ? 0 : pentry->irq); - i2c_info.addr = pentry->addr; - pr_debug("I2C bus = %d, name = %16.16s, irq = 0x%2x, addr = 0x%x\n", - pentry->host_num, - i2c_info.type, - i2c_info.irq, - i2c_info.addr); - pdata = intel_mid_sfi_get_pdata(dev, &i2c_info); - i2c_info.platform_data = pdata; - if (IS_ERR(pdata)) - return; - - if (dev->delay) - intel_scu_i2c_device_register(pentry->host_num, &i2c_info); - else - i2c_register_board_info(pentry->host_num, &i2c_info, 1); -} - -static void __init sfi_handle_sd_dev(struct sfi_device_table_entry *pentry, - struct devs_id *dev) -{ - struct mid_sd_board_info sd_info; - void *pdata; - - memset(&sd_info, 0, sizeof(sd_info)); - strncpy(sd_info.name, pentry->name, SFI_NAME_LEN); - sd_info.bus_num = pentry->host_num; - sd_info.max_clk = pentry->max_freq; - sd_info.addr = pentry->addr; - pr_debug("SD bus = %d, name = %16.16s, max_clk = %d, addr = 0x%x\n", - sd_info.bus_num, - sd_info.name, - sd_info.max_clk, - sd_info.addr); - pdata = intel_mid_sfi_get_pdata(dev, &sd_info); - if (IS_ERR(pdata)) - return; - - /* Nothing we can do with this for now */ - sd_info.platform_data = pdata; - - pr_debug("Successfully registered %16.16s", sd_info.name); -} - -extern struct devs_id *const __x86_intel_mid_dev_start[], - *const __x86_intel_mid_dev_end[]; - -static struct devs_id __init *get_device_id(u8 type, char *name) -{ - struct devs_id *const *dev_table; - - for (dev_table = __x86_intel_mid_dev_start; - dev_table < __x86_intel_mid_dev_end; dev_table++) { - struct devs_id *dev = *dev_table; - if (dev->type == type && - !strncmp(dev->name, name, SFI_NAME_LEN)) { - return dev; - } - } - - return NULL; -} - -static int __init sfi_parse_devs(struct sfi_table_header *table) -{ - struct sfi_table_simple *sb; - struct sfi_device_table_entry *pentry; - struct devs_id *dev = NULL; - int num, i, ret; - int polarity; - struct irq_alloc_info info; - - sb = (struct sfi_table_simple *)table; - num = SFI_GET_NUM_ENTRIES(sb, struct sfi_device_table_entry); - pentry = (struct sfi_device_table_entry *)sb->pentry; - - for (i = 0; i < num; i++, pentry++) { - int irq = pentry->irq; - - if (irq != (u8)0xff) { /* native RTE case */ - /* these SPI2 devices are not exposed to system as PCI - * devices, but they have separate RTE entry in IOAPIC - * so we have to enable them one by one here - */ - if (intel_mid_identify_cpu() == - INTEL_MID_CPU_CHIP_TANGIER) { - if (!strncmp(pentry->name, "r69001-ts-i2c", 13)) - /* active low */ - polarity = 1; - else if (!strncmp(pentry->name, - "synaptics_3202", 14)) - /* active low */ - polarity = 1; - else if (irq == 41) - /* fast_int_1 */ - polarity = 1; - else - /* active high */ - polarity = 0; - } else { - /* PNW and CLV go with active low */ - polarity = 1; - } - - ioapic_set_alloc_attr(&info, NUMA_NO_NODE, 1, polarity); - ret = mp_map_gsi_to_irq(irq, IOAPIC_MAP_ALLOC, &info); - WARN_ON(ret < 0); - } - - dev = get_device_id(pentry->type, pentry->name); - - if (!dev) - continue; - - switch (pentry->type) { - case SFI_DEV_TYPE_IPC: - sfi_handle_ipc_dev(pentry, dev); - break; - case SFI_DEV_TYPE_SPI: - sfi_handle_spi_dev(pentry, dev); - break; - case SFI_DEV_TYPE_I2C: - sfi_handle_i2c_dev(pentry, dev); - break; - case SFI_DEV_TYPE_SD: - sfi_handle_sd_dev(pentry, dev); - break; - case SFI_DEV_TYPE_UART: - case SFI_DEV_TYPE_HSI: - default: - break; - } - } - return 0; -} - -static int __init intel_mid_platform_init(void) -{ - sfi_table_parse(SFI_SIG_GPIO, NULL, NULL, sfi_parse_gpio); - sfi_table_parse(SFI_SIG_DEVS, NULL, NULL, sfi_parse_devs); - return 0; -} -arch_initcall(intel_mid_platform_init); diff --git a/arch/x86/platform/sfi/Makefile b/arch/x86/platform/sfi/Makefile deleted file mode 100644 index 4eba24c2af67..000000000000 --- a/arch/x86/platform/sfi/Makefile +++ /dev/null @@ -1,2 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -obj-$(CONFIG_SFI) += sfi.o diff --git a/arch/x86/platform/sfi/sfi.c b/arch/x86/platform/sfi/sfi.c deleted file mode 100644 index 6259563760f9..000000000000 --- a/arch/x86/platform/sfi/sfi.c +++ /dev/null @@ -1,100 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * sfi.c - x86 architecture SFI support. - * - * Copyright (c) 2009, Intel Corporation. - */ - -#define KMSG_COMPONENT "SFI" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt - -#include -#include -#include -#include - -#include -#include -#include -#include -#include - -#ifdef CONFIG_X86_LOCAL_APIC -static unsigned long sfi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE; - -/* All CPUs enumerated by SFI must be present and enabled */ -static void __init mp_sfi_register_lapic(u8 id) -{ - if (MAX_LOCAL_APIC - id <= 0) { - pr_warn("Processor #%d invalid (max %d)\n", id, MAX_LOCAL_APIC); - return; - } - - pr_info("registering lapic[%d]\n", id); - - generic_processor_info(id, GET_APIC_VERSION(apic_read(APIC_LVR))); -} - -static int __init sfi_parse_cpus(struct sfi_table_header *table) -{ - struct sfi_table_simple *sb; - struct sfi_cpu_table_entry *pentry; - int i; - int cpu_num; - - sb = (struct sfi_table_simple *)table; - cpu_num = SFI_GET_NUM_ENTRIES(sb, struct sfi_cpu_table_entry); - pentry = (struct sfi_cpu_table_entry *)sb->pentry; - - for (i = 0; i < cpu_num; i++) { - mp_sfi_register_lapic(pentry->apic_id); - pentry++; - } - - smp_found_config = 1; - return 0; -} -#endif /* CONFIG_X86_LOCAL_APIC */ - -#ifdef CONFIG_X86_IO_APIC - -static int __init sfi_parse_ioapic(struct sfi_table_header *table) -{ - struct sfi_table_simple *sb; - struct sfi_apic_table_entry *pentry; - int i, num; - struct ioapic_domain_cfg cfg = { - .type = IOAPIC_DOMAIN_STRICT, - .ops = &mp_ioapic_irqdomain_ops, - }; - - sb = (struct sfi_table_simple *)table; - num = SFI_GET_NUM_ENTRIES(sb, struct sfi_apic_table_entry); - pentry = (struct sfi_apic_table_entry *)sb->pentry; - - for (i = 0; i < num; i++) { - mp_register_ioapic(i, pentry->phys_addr, gsi_top, &cfg); - pentry++; - } - - WARN(pic_mode, KERN_WARNING - "SFI: pic_mod shouldn't be 1 when IOAPIC table is present\n"); - pic_mode = 0; - return 0; -} -#endif /* CONFIG_X86_IO_APIC */ - -/* - * sfi_platform_init(): register lapics & io-apics - */ -int __init sfi_platform_init(void) -{ -#ifdef CONFIG_X86_LOCAL_APIC - register_lapic_address(sfi_lapic_addr); - sfi_table_parse(SFI_SIG_CPUS, NULL, NULL, sfi_parse_cpus); -#endif -#ifdef CONFIG_X86_IO_APIC - sfi_table_parse(SFI_SIG_APIC, NULL, NULL, sfi_parse_ioapic); -#endif - return 0; -} diff --git a/drivers/Makefile b/drivers/Makefile index fd11b9ac4cc3..b2af1514a6b3 100644 --- a/drivers/Makefile +++ b/drivers/Makefile @@ -27,7 +27,7 @@ obj-y += idle/ obj-y += char/ipmi/ obj-$(CONFIG_ACPI) += acpi/ -obj-$(CONFIG_SFI) += sfi/ + # PnP must come after ACPI since it will eventually need to check if acpi # was used and do nothing if so obj-$(CONFIG_PNP) += pnp/ diff --git a/drivers/platform/x86/intel_scu_pcidrv.c b/drivers/platform/x86/intel_scu_pcidrv.c index 8c5fd8240da9..80abc708e4f2 100644 --- a/drivers/platform/x86/intel_scu_pcidrv.c +++ b/drivers/platform/x86/intel_scu_pcidrv.c @@ -17,7 +17,6 @@ static int intel_scu_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { - void (*setup_fn)(void) = (void (*)(void))id->driver_data; struct intel_scu_ipc_data scu_data = {}; struct intel_scu_ipc_dev *scu; int ret; @@ -30,27 +29,14 @@ static int intel_scu_pci_probe(struct pci_dev *pdev, scu_data.irq = pdev->irq; scu = intel_scu_ipc_register(&pdev->dev, &scu_data); - if (IS_ERR(scu)) - return PTR_ERR(scu); - - if (setup_fn) - setup_fn(); - return 0; -} - -static void intel_mid_scu_setup(void) -{ - intel_scu_devices_create(); + return PTR_ERR_OR_ZERO(scu); } static const struct pci_device_id pci_ids[] = { - { PCI_VDEVICE(INTEL, 0x080e), - .driver_data = (kernel_ulong_t)intel_mid_scu_setup }, - { PCI_VDEVICE(INTEL, 0x08ea), - .driver_data = (kernel_ulong_t)intel_mid_scu_setup }, + { PCI_VDEVICE(INTEL, 0x080e) }, + { PCI_VDEVICE(INTEL, 0x08ea) }, { PCI_VDEVICE(INTEL, 0x0a94) }, - { PCI_VDEVICE(INTEL, 0x11a0), - .driver_data = (kernel_ulong_t)intel_mid_scu_setup }, + { PCI_VDEVICE(INTEL, 0x11a0) }, { PCI_VDEVICE(INTEL, 0x1a94) }, { PCI_VDEVICE(INTEL, 0x5a94) }, {} diff --git a/drivers/sfi/Kconfig b/drivers/sfi/Kconfig deleted file mode 100644 index 3d0b64db214e..000000000000 --- a/drivers/sfi/Kconfig +++ /dev/null @@ -1,18 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -# -# SFI Configuration -# - -menuconfig SFI - bool "SFI (Simple Firmware Interface) Support" - help - The Simple Firmware Interface (SFI) provides a lightweight method - for platform firmware to pass information to the operating system - via static tables in memory. Kernel SFI support is required to - boot on SFI-only platforms. Currently, all SFI-only platforms are - based on the 2nd generation Intel Atom processor platform, - code-named Moorestown. - - For more information, see http://simplefirmware.org - - Say 'Y' here to enable the kernel to boot on SFI-only platforms. diff --git a/drivers/sfi/Makefile b/drivers/sfi/Makefile deleted file mode 100644 index ca9436b12386..000000000000 --- a/drivers/sfi/Makefile +++ /dev/null @@ -1,4 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -obj-y += sfi_acpi.o -obj-y += sfi_core.o - diff --git a/drivers/sfi/sfi_acpi.c b/drivers/sfi/sfi_acpi.c deleted file mode 100644 index d277b36eb389..000000000000 --- a/drivers/sfi/sfi_acpi.c +++ /dev/null @@ -1,214 +0,0 @@ -/* sfi_acpi.c Simple Firmware Interface - ACPI extensions */ - -/* - - This file is provided under a dual BSD/GPLv2 license. When using or - redistributing this file, you may do so under either license. - - GPL LICENSE SUMMARY - - Copyright(c) 2009 Intel Corporation. All rights reserved. - - This program is free software; you can redistribute it and/or modify - it under the terms of version 2 of the GNU General Public License as - published by the Free Software Foundation. - - This program is distributed in the hope that it will be useful, but - WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - General Public License for more details. - - You should have received a copy of the GNU General Public License - along with this program; if not, write to the Free Software - Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - The full GNU General Public License is included in this distribution - in the file called LICENSE.GPL. - - BSD LICENSE - - Copyright(c) 2009 Intel Corporation. All rights reserved. - - Redistribution and use in source and binary forms, with or without - modification, are permitted provided that the following conditions - are met: - - * Redistributions of source code must retain the above copyright - notice, this list of conditions and the following disclaimer. - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in - the documentation and/or other materials provided with the - distribution. - * Neither the name of Intel Corporation nor the names of its - contributors may be used to endorse or promote products derived - from this software without specific prior written permission. - - THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT - LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, - DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY - THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE - OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - -*/ - -#define KMSG_COMPONENT "SFI" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt - -#include -#include -#include "sfi_core.h" - -/* - * SFI can access ACPI-defined tables via an optional ACPI XSDT. - * - * This allows re-use, and avoids re-definition, of standard tables. - * For example, the "MCFG" table is defined by PCI, reserved by ACPI, - * and is expected to be present many SFI-only systems. - */ - -static struct acpi_table_xsdt *xsdt_va __read_mostly; - -#define XSDT_GET_NUM_ENTRIES(ptable, entry_type) \ - ((ptable->header.length - sizeof(struct acpi_table_header)) / \ - (sizeof(entry_type))) - -static inline struct sfi_table_header *acpi_to_sfi_th( - struct acpi_table_header *th) -{ - return (struct sfi_table_header *)th; -} - -static inline struct acpi_table_header *sfi_to_acpi_th( - struct sfi_table_header *th) -{ - return (struct acpi_table_header *)th; -} - -/* - * sfi_acpi_parse_xsdt() - * - * Parse the ACPI XSDT for later access by sfi_acpi_table_parse(). - */ -static int __init sfi_acpi_parse_xsdt(struct sfi_table_header *th) -{ - struct sfi_table_key key = SFI_ANY_KEY; - int tbl_cnt, i; - void *ret; - - xsdt_va = (struct acpi_table_xsdt *)th; - tbl_cnt = XSDT_GET_NUM_ENTRIES(xsdt_va, u64); - for (i = 0; i < tbl_cnt; i++) { - ret = sfi_check_table(xsdt_va->table_offset_entry[i], &key); - if (IS_ERR(ret)) { - disable_sfi(); - return -1; - } - } - - return 0; -} - -int __init sfi_acpi_init(void) -{ - struct sfi_table_key xsdt_key = { .sig = SFI_SIG_XSDT }; - - sfi_table_parse(SFI_SIG_XSDT, NULL, NULL, sfi_acpi_parse_xsdt); - - /* Only call the get_table to keep the table mapped */ - xsdt_va = (struct acpi_table_xsdt *)sfi_get_table(&xsdt_key); - return 0; -} - -static struct acpi_table_header *sfi_acpi_get_table(struct sfi_table_key *key) -{ - u32 tbl_cnt, i; - void *ret; - - tbl_cnt = XSDT_GET_NUM_ENTRIES(xsdt_va, u64); - for (i = 0; i < tbl_cnt; i++) { - ret = sfi_check_table(xsdt_va->table_offset_entry[i], key); - if (!IS_ERR(ret) && ret) - return sfi_to_acpi_th(ret); - } - - return NULL; -} - -static void sfi_acpi_put_table(struct acpi_table_header *table) -{ - sfi_put_table(acpi_to_sfi_th(table)); -} - -/* - * sfi_acpi_table_parse() - * - * Find specified table in XSDT, run handler on it and return its return value - */ -int sfi_acpi_table_parse(char *signature, char *oem_id, char *oem_table_id, - int(*handler)(struct acpi_table_header *)) -{ - struct acpi_table_header *table = NULL; - struct sfi_table_key key; - int ret = 0; - - if (sfi_disabled) - return -1; - - key.sig = signature; - key.oem_id = oem_id; - key.oem_table_id = oem_table_id; - - table = sfi_acpi_get_table(&key); - if (!table) - return -EINVAL; - - ret = handler(table); - sfi_acpi_put_table(table); - return ret; -} - -static ssize_t sfi_acpi_table_show(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, - loff_t offset, size_t count) -{ - struct sfi_table_attr *tbl_attr = - container_of(bin_attr, struct sfi_table_attr, attr); - struct acpi_table_header *th = NULL; - struct sfi_table_key key; - ssize_t cnt; - - key.sig = tbl_attr->name; - key.oem_id = NULL; - key.oem_table_id = NULL; - - th = sfi_acpi_get_table(&key); - if (!th) - return 0; - - cnt = memory_read_from_buffer(buf, count, &offset, - th, th->length); - sfi_acpi_put_table(th); - - return cnt; -} - - -void __init sfi_acpi_sysfs_init(void) -{ - u32 tbl_cnt, i; - struct sfi_table_attr *tbl_attr; - - tbl_cnt = XSDT_GET_NUM_ENTRIES(xsdt_va, u64); - for (i = 0; i < tbl_cnt; i++) { - tbl_attr = - sfi_sysfs_install_table(xsdt_va->table_offset_entry[i]); - tbl_attr->attr.read = sfi_acpi_table_show; - } - - return; -} diff --git a/drivers/sfi/sfi_core.c b/drivers/sfi/sfi_core.c deleted file mode 100644 index a5136901dd8a..000000000000 --- a/drivers/sfi/sfi_core.c +++ /dev/null @@ -1,522 +0,0 @@ -/* sfi_core.c Simple Firmware Interface - core internals */ - -/* - - This file is provided under a dual BSD/GPLv2 license. When using or - redistributing this file, you may do so under either license. - - GPL LICENSE SUMMARY - - Copyright(c) 2009 Intel Corporation. All rights reserved. - - This program is free software; you can redistribute it and/or modify - it under the terms of version 2 of the GNU General Public License as - published by the Free Software Foundation. - - This program is distributed in the hope that it will be useful, but - WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - General Public License for more details. - - You should have received a copy of the GNU General Public License - along with this program; if not, write to the Free Software - Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - The full GNU General Public License is included in this distribution - in the file called LICENSE.GPL. - - BSD LICENSE - - Copyright(c) 2009 Intel Corporation. All rights reserved. - - Redistribution and use in source and binary forms, with or without - modification, are permitted provided that the following conditions - are met: - - * Redistributions of source code must retain the above copyright - notice, this list of conditions and the following disclaimer. - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in - the documentation and/or other materials provided with the - distribution. - * Neither the name of Intel Corporation nor the names of its - contributors may be used to endorse or promote products derived - from this software without specific prior written permission. - - THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT - LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, - DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY - THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE - OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - -*/ - -#define KMSG_COMPONENT "SFI" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "sfi_core.h" - -#define ON_SAME_PAGE(addr1, addr2) \ - (((unsigned long)(addr1) & PAGE_MASK) == \ - ((unsigned long)(addr2) & PAGE_MASK)) -#define TABLE_ON_PAGE(page, table, size) (ON_SAME_PAGE(page, table) && \ - ON_SAME_PAGE(page, table + size)) - -int sfi_disabled __read_mostly; -EXPORT_SYMBOL(sfi_disabled); - -static u64 syst_pa __read_mostly; -static struct sfi_table_simple *syst_va __read_mostly; - -/* - * FW creates and saves the SFI tables in memory. When these tables get - * used, they may need to be mapped to virtual address space, and the mapping - * can happen before or after the memremap() is ready, so a flag is needed - * to indicating this - */ -static u32 sfi_use_memremap __read_mostly; - -/* - * sfi_un/map_memory calls early_memremap/memunmap which is a __init function - * and introduces section mismatch. So use __ref to make it calm. - */ -static void __iomem * __ref sfi_map_memory(u64 phys, u32 size) -{ - if (!phys || !size) - return NULL; - - if (sfi_use_memremap) - return memremap(phys, size, MEMREMAP_WB); - else - return early_memremap(phys, size); -} - -static void __ref sfi_unmap_memory(void __iomem *virt, u32 size) -{ - if (!virt || !size) - return; - - if (sfi_use_memremap) - memunmap(virt); - else - early_memunmap(virt, size); -} - -static void sfi_print_table_header(unsigned long long pa, - struct sfi_table_header *header) -{ - pr_info("%4.4s %llX, %04X (v%d %6.6s %8.8s)\n", - header->sig, pa, - header->len, header->rev, header->oem_id, - header->oem_table_id); -} - -/* - * sfi_verify_table() - * Sanity check table lengh, calculate checksum - */ -static int sfi_verify_table(struct sfi_table_header *table) -{ - - u8 checksum = 0; - u8 *puchar = (u8 *)table; - u32 length = table->len; - - /* Sanity check table length against arbitrary 1MB limit */ - if (length > 0x100000) { - pr_err("Invalid table length 0x%x\n", length); - return -1; - } - - while (length--) - checksum += *puchar++; - - if (checksum) { - pr_err("Checksum %2.2X should be %2.2X\n", - table->csum, table->csum - checksum); - return -1; - } - return 0; -} - -/* - * sfi_map_table() - * - * Return address of mapped table - * Check for common case that we can re-use mapping to SYST, - * which requires syst_pa, syst_va to be initialized. - */ -static struct sfi_table_header *sfi_map_table(u64 pa) -{ - struct sfi_table_header *th; - u32 length; - - if (!TABLE_ON_PAGE(syst_pa, pa, sizeof(struct sfi_table_header))) - th = sfi_map_memory(pa, sizeof(struct sfi_table_header)); - else - th = (void *)syst_va + (pa - syst_pa); - - /* If table fits on same page as its header, we are done */ - if (TABLE_ON_PAGE(th, th, th->len)) - return th; - - /* Entire table does not fit on same page as SYST */ - length = th->len; - if (!TABLE_ON_PAGE(syst_pa, pa, sizeof(struct sfi_table_header))) - sfi_unmap_memory(th, sizeof(struct sfi_table_header)); - - return sfi_map_memory(pa, length); -} - -/* - * sfi_unmap_table() - * - * Undoes effect of sfi_map_table() by unmapping table - * if it did not completely fit on same page as SYST. - */ -static void sfi_unmap_table(struct sfi_table_header *th) -{ - if (!TABLE_ON_PAGE(syst_va, th, th->len)) - sfi_unmap_memory(th, TABLE_ON_PAGE(th, th, th->len) ? - sizeof(*th) : th->len); -} - -static int sfi_table_check_key(struct sfi_table_header *th, - struct sfi_table_key *key) -{ - - if (strncmp(th->sig, key->sig, SFI_SIGNATURE_SIZE) - || (key->oem_id && strncmp(th->oem_id, - key->oem_id, SFI_OEM_ID_SIZE)) - || (key->oem_table_id && strncmp(th->oem_table_id, - key->oem_table_id, SFI_OEM_TABLE_ID_SIZE))) - return -1; - - return 0; -} - -/* - * This function will be used in 2 cases: - * 1. used to enumerate and verify the tables addressed by SYST/XSDT, - * thus no signature will be given (in kernel boot phase) - * 2. used to parse one specific table, signature must exist, and - * the mapped virt address will be returned, and the virt space - * will be released by call sfi_put_table() later - * - * This two cases are from two different functions with two different - * sections and causes section mismatch warning. So use __ref to tell - * modpost not to make any noise. - * - * Return value: - * NULL: when can't find a table matching the key - * ERR_PTR(error): error value - * virt table address: when a matched table is found - */ -struct sfi_table_header * - __ref sfi_check_table(u64 pa, struct sfi_table_key *key) -{ - struct sfi_table_header *th; - void *ret = NULL; - - th = sfi_map_table(pa); - if (!th) - return ERR_PTR(-ENOMEM); - - if (!key->sig) { - sfi_print_table_header(pa, th); - if (sfi_verify_table(th)) - ret = ERR_PTR(-EINVAL); - } else { - if (!sfi_table_check_key(th, key)) - return th; /* Success */ - } - - sfi_unmap_table(th); - return ret; -} - -/* - * sfi_get_table() - * - * Search SYST for the specified table with the signature in - * the key, and return the mapped table - */ -struct sfi_table_header *sfi_get_table(struct sfi_table_key *key) -{ - struct sfi_table_header *th; - u32 tbl_cnt, i; - - tbl_cnt = SFI_GET_NUM_ENTRIES(syst_va, u64); - for (i = 0; i < tbl_cnt; i++) { - th = sfi_check_table(syst_va->pentry[i], key); - if (!IS_ERR(th) && th) - return th; - } - - return NULL; -} - -void sfi_put_table(struct sfi_table_header *th) -{ - sfi_unmap_table(th); -} - -/* Find table with signature, run handler on it */ -int sfi_table_parse(char *signature, char *oem_id, char *oem_table_id, - sfi_table_handler handler) -{ - struct sfi_table_header *table = NULL; - struct sfi_table_key key; - int ret = -EINVAL; - - if (sfi_disabled || !handler || !signature) - goto exit; - - key.sig = signature; - key.oem_id = oem_id; - key.oem_table_id = oem_table_id; - - table = sfi_get_table(&key); - if (!table) - goto exit; - - ret = handler(table); - sfi_put_table(table); -exit: - return ret; -} -EXPORT_SYMBOL_GPL(sfi_table_parse); - -/* - * sfi_parse_syst() - * Checksum all the tables in SYST and print their headers - * - * success: set syst_va, return 0 - */ -static int __init sfi_parse_syst(void) -{ - struct sfi_table_key key = SFI_ANY_KEY; - int tbl_cnt, i; - void *ret; - - syst_va = sfi_map_memory(syst_pa, sizeof(struct sfi_table_simple)); - if (!syst_va) - return -ENOMEM; - - tbl_cnt = SFI_GET_NUM_ENTRIES(syst_va, u64); - for (i = 0; i < tbl_cnt; i++) { - ret = sfi_check_table(syst_va->pentry[i], &key); - if (IS_ERR(ret)) - return PTR_ERR(ret); - } - - return 0; -} - -/* - * The OS finds the System Table by searching 16-byte boundaries between - * physical address 0x000E0000 and 0x000FFFFF. The OS shall search this region - * starting at the low address and shall stop searching when the 1st valid SFI - * System Table is found. - * - * success: set syst_pa, return 0 - * fail: return -1 - */ -static __init int sfi_find_syst(void) -{ - unsigned long offset, len; - void *start; - - len = SFI_SYST_SEARCH_END - SFI_SYST_SEARCH_BEGIN; - start = sfi_map_memory(SFI_SYST_SEARCH_BEGIN, len); - if (!start) - return -1; - - for (offset = 0; offset < len; offset += 16) { - struct sfi_table_header *syst_hdr; - - syst_hdr = start + offset; - if (strncmp(syst_hdr->sig, SFI_SIG_SYST, - SFI_SIGNATURE_SIZE)) - continue; - - if (syst_hdr->len > PAGE_SIZE) - continue; - - sfi_print_table_header(SFI_SYST_SEARCH_BEGIN + offset, - syst_hdr); - - if (sfi_verify_table(syst_hdr)) - continue; - - /* - * Enforce SFI spec mandate that SYST reside within a page. - */ - if (!ON_SAME_PAGE(syst_pa, syst_pa + syst_hdr->len)) { - pr_info("SYST 0x%llx + 0x%x crosses page\n", - syst_pa, syst_hdr->len); - continue; - } - - /* Success */ - syst_pa = SFI_SYST_SEARCH_BEGIN + offset; - sfi_unmap_memory(start, len); - return 0; - } - - sfi_unmap_memory(start, len); - return -1; -} - -static struct kobject *sfi_kobj; -static struct kobject *tables_kobj; - -static ssize_t sfi_table_show(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, char *buf, - loff_t offset, size_t count) -{ - struct sfi_table_attr *tbl_attr = - container_of(bin_attr, struct sfi_table_attr, attr); - struct sfi_table_header *th = NULL; - struct sfi_table_key key; - ssize_t cnt; - - key.sig = tbl_attr->name; - key.oem_id = NULL; - key.oem_table_id = NULL; - - if (strncmp(SFI_SIG_SYST, tbl_attr->name, SFI_SIGNATURE_SIZE)) { - th = sfi_get_table(&key); - if (!th) - return 0; - - cnt = memory_read_from_buffer(buf, count, &offset, - th, th->len); - sfi_put_table(th); - } else - cnt = memory_read_from_buffer(buf, count, &offset, - syst_va, syst_va->header.len); - - return cnt; -} - -struct sfi_table_attr __init *sfi_sysfs_install_table(u64 pa) -{ - struct sfi_table_attr *tbl_attr; - struct sfi_table_header *th; - int ret; - - tbl_attr = kzalloc(sizeof(struct sfi_table_attr), GFP_KERNEL); - if (!tbl_attr) - return NULL; - - th = sfi_map_table(pa); - if (!th || !th->sig[0]) { - kfree(tbl_attr); - return NULL; - } - - sysfs_attr_init(&tbl_attr->attr.attr); - memcpy(tbl_attr->name, th->sig, SFI_SIGNATURE_SIZE); - - tbl_attr->attr.size = 0; - tbl_attr->attr.read = sfi_table_show; - tbl_attr->attr.attr.name = tbl_attr->name; - tbl_attr->attr.attr.mode = 0400; - - ret = sysfs_create_bin_file(tables_kobj, - &tbl_attr->attr); - if (ret) { - kfree(tbl_attr); - tbl_attr = NULL; - } - - sfi_unmap_table(th); - return tbl_attr; -} - -static int __init sfi_sysfs_init(void) -{ - int tbl_cnt, i; - - if (sfi_disabled) - return 0; - - sfi_kobj = kobject_create_and_add("sfi", firmware_kobj); - if (!sfi_kobj) - return 0; - - tables_kobj = kobject_create_and_add("tables", sfi_kobj); - if (!tables_kobj) { - kobject_put(sfi_kobj); - return 0; - } - - sfi_sysfs_install_table(syst_pa); - - tbl_cnt = SFI_GET_NUM_ENTRIES(syst_va, u64); - - for (i = 0; i < tbl_cnt; i++) - sfi_sysfs_install_table(syst_va->pentry[i]); - - sfi_acpi_sysfs_init(); - kobject_uevent(sfi_kobj, KOBJ_ADD); - kobject_uevent(tables_kobj, KOBJ_ADD); - pr_info("SFI sysfs interfaces init success\n"); - return 0; -} - -void __init sfi_init(void) -{ - if (!acpi_disabled) - disable_sfi(); - - if (sfi_disabled) - return; - - pr_info("Simple Firmware Interface v0.81 http://simplefirmware.org\n"); - - if (sfi_find_syst() || sfi_parse_syst() || sfi_platform_init()) - disable_sfi(); - - return; -} - -void __init sfi_init_late(void) -{ - int length; - - if (sfi_disabled) - return; - - length = syst_va->header.len; - sfi_unmap_memory(syst_va, sizeof(struct sfi_table_simple)); - - /* Use memremap now after it is ready */ - sfi_use_memremap = 1; - syst_va = sfi_map_memory(syst_pa, length); - - sfi_acpi_init(); -} - -/* - * The reason we put it here because we need wait till the /sys/firmware - * is setup, then our interface can be registered in /sys/firmware/sfi - */ -core_initcall(sfi_sysfs_init); diff --git a/drivers/sfi/sfi_core.h b/drivers/sfi/sfi_core.h deleted file mode 100644 index 1d5cfe854cf7..000000000000 --- a/drivers/sfi/sfi_core.h +++ /dev/null @@ -1,81 +0,0 @@ -/* sfi_core.h Simple Firmware Interface, internal header */ - -/* - - This file is provided under a dual BSD/GPLv2 license. When using or - redistributing this file, you may do so under either license. - - GPL LICENSE SUMMARY - - Copyright(c) 2009 Intel Corporation. All rights reserved. - - This program is free software; you can redistribute it and/or modify - it under the terms of version 2 of the GNU General Public License as - published by the Free Software Foundation. - - This program is distributed in the hope that it will be useful, but - WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - General Public License for more details. - - You should have received a copy of the GNU General Public License - along with this program; if not, write to the Free Software - Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - The full GNU General Public License is included in this distribution - in the file called LICENSE.GPL. - - BSD LICENSE - - Copyright(c) 2009 Intel Corporation. All rights reserved. - - Redistribution and use in source and binary forms, with or without - modification, are permitted provided that the following conditions - are met: - - * Redistributions of source code must retain the above copyright - notice, this list of conditions and the following disclaimer. - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in - the documentation and/or other materials provided with the - distribution. - * Neither the name of Intel Corporation nor the names of its - contributors may be used to endorse or promote products derived - from this software without specific prior written permission. - - THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT - LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, - DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY - THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE - OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - -*/ - -#include - -struct sfi_table_key{ - char *sig; - char *oem_id; - char *oem_table_id; -}; - -/* sysfs interface */ -struct sfi_table_attr { - struct bin_attribute attr; - char name[8]; -}; - -#define SFI_ANY_KEY { .sig = NULL, .oem_id = NULL, .oem_table_id = NULL } - -extern int __init sfi_acpi_init(void); -extern struct sfi_table_header *sfi_check_table(u64 paddr, - struct sfi_table_key *key); -struct sfi_table_header *sfi_get_table(struct sfi_table_key *key); -extern void sfi_put_table(struct sfi_table_header *table); -extern struct sfi_table_attr __init *sfi_sysfs_install_table(u64 pa); -extern void __init sfi_acpi_sysfs_init(void); diff --git a/include/linux/sfi.h b/include/linux/sfi.h deleted file mode 100644 index e0e1597ef9e6..000000000000 --- a/include/linux/sfi.h +++ /dev/null @@ -1,210 +0,0 @@ -/* sfi.h Simple Firmware Interface */ - -/* - - This file is provided under a dual BSD/GPLv2 license. When using or - redistributing this file, you may do so under either license. - - GPL LICENSE SUMMARY - - Copyright(c) 2009 Intel Corporation. All rights reserved. - - This program is free software; you can redistribute it and/or modify - it under the terms of version 2 of the GNU General Public License as - published by the Free Software Foundation. - - This program is distributed in the hope that it will be useful, but - WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - General Public License for more details. - - You should have received a copy of the GNU General Public License - along with this program; if not, write to the Free Software - Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - The full GNU General Public License is included in this distribution - in the file called LICENSE.GPL. - - BSD LICENSE - - Copyright(c) 2009 Intel Corporation. All rights reserved. - - Redistribution and use in source and binary forms, with or without - modification, are permitted provided that the following conditions - are met: - - * Redistributions of source code must retain the above copyright - notice, this list of conditions and the following disclaimer. - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in - the documentation and/or other materials provided with the - distribution. - * Neither the name of Intel Corporation nor the names of its - contributors may be used to endorse or promote products derived - from this software without specific prior written permission. - - THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT - LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, - DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY - THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE - OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - -*/ - -#ifndef _LINUX_SFI_H -#define _LINUX_SFI_H - -#include -#include - -/* Table signatures reserved by the SFI specification */ -#define SFI_SIG_SYST "SYST" -#define SFI_SIG_FREQ "FREQ" -#define SFI_SIG_IDLE "IDLE" -#define SFI_SIG_CPUS "CPUS" -#define SFI_SIG_MTMR "MTMR" -#define SFI_SIG_MRTC "MRTC" -#define SFI_SIG_MMAP "MMAP" -#define SFI_SIG_APIC "APIC" -#define SFI_SIG_XSDT "XSDT" -#define SFI_SIG_WAKE "WAKE" -#define SFI_SIG_DEVS "DEVS" -#define SFI_SIG_GPIO "GPIO" - -#define SFI_SIGNATURE_SIZE 4 -#define SFI_OEM_ID_SIZE 6 -#define SFI_OEM_TABLE_ID_SIZE 8 - -#define SFI_NAME_LEN 16 - -#define SFI_SYST_SEARCH_BEGIN 0x000E0000 -#define SFI_SYST_SEARCH_END 0x000FFFFF - -#define SFI_GET_NUM_ENTRIES(ptable, entry_type) \ - ((ptable->header.len - sizeof(struct sfi_table_header)) / \ - (sizeof(entry_type))) -/* - * Table structures must be byte-packed to match the SFI specification, - * as they are provided by the BIOS. - */ -struct sfi_table_header { - char sig[SFI_SIGNATURE_SIZE]; - u32 len; - u8 rev; - u8 csum; - char oem_id[SFI_OEM_ID_SIZE]; - char oem_table_id[SFI_OEM_TABLE_ID_SIZE]; -} __packed; - -struct sfi_table_simple { - struct sfi_table_header header; - u64 pentry[1]; -} __packed; - -/* Comply with UEFI spec 2.1 */ -struct sfi_mem_entry { - u32 type; - u64 phys_start; - u64 virt_start; - u64 pages; - u64 attrib; -} __packed; - -struct sfi_cpu_table_entry { - u32 apic_id; -} __packed; - -struct sfi_cstate_table_entry { - u32 hint; /* MWAIT hint */ - u32 latency; /* latency in ms */ -} __packed; - -struct sfi_apic_table_entry { - u64 phys_addr; /* phy base addr for APIC reg */ -} __packed; - -struct sfi_freq_table_entry { - u32 freq_mhz; /* in MHZ */ - u32 latency; /* transition latency in ms */ - u32 ctrl_val; /* value to write to PERF_CTL */ -} __packed; - -struct sfi_wake_table_entry { - u64 phys_addr; /* pointer to where the wake vector locates */ -} __packed; - -struct sfi_timer_table_entry { - u64 phys_addr; /* phy base addr for the timer */ - u32 freq_hz; /* in HZ */ - u32 irq; -} __packed; - -struct sfi_rtc_table_entry { - u64 phys_addr; /* phy base addr for the RTC */ - u32 irq; -} __packed; - -struct sfi_device_table_entry { - u8 type; /* bus type, I2C, SPI or ...*/ -#define SFI_DEV_TYPE_SPI 0 -#define SFI_DEV_TYPE_I2C 1 -#define SFI_DEV_TYPE_UART 2 -#define SFI_DEV_TYPE_HSI 3 -#define SFI_DEV_TYPE_IPC 4 -#define SFI_DEV_TYPE_SD 5 - - u8 host_num; /* attached to host 0, 1...*/ - u16 addr; - u8 irq; - u32 max_freq; - char name[SFI_NAME_LEN]; -} __packed; - -struct sfi_gpio_table_entry { - char controller_name[SFI_NAME_LEN]; - u16 pin_no; - char pin_name[SFI_NAME_LEN]; -} __packed; - -typedef int (*sfi_table_handler) (struct sfi_table_header *table); - -#ifdef CONFIG_SFI -extern void __init sfi_init(void); -extern int __init sfi_platform_init(void); -extern void __init sfi_init_late(void); -extern int sfi_table_parse(char *signature, char *oem_id, char *oem_table_id, - sfi_table_handler handler); - -extern int sfi_disabled; -static inline void disable_sfi(void) -{ - sfi_disabled = 1; -} - -#else /* !CONFIG_SFI */ - -static inline void sfi_init(void) -{ -} - -static inline void sfi_init_late(void) -{ -} - -#define sfi_disabled 0 - -static inline int sfi_table_parse(char *signature, char *oem_id, - char *oem_table_id, - sfi_table_handler handler) -{ - return -1; -} - -#endif /* !CONFIG_SFI */ - -#endif /*_LINUX_SFI_H*/ diff --git a/include/linux/sfi_acpi.h b/include/linux/sfi_acpi.h deleted file mode 100644 index a6e555cbe05c..000000000000 --- a/include/linux/sfi_acpi.h +++ /dev/null @@ -1,93 +0,0 @@ -/* sfi.h Simple Firmware Interface */ - -/* - - This file is provided under a dual BSD/GPLv2 license. When using or - redistributing this file, you may do so under either license. - - GPL LICENSE SUMMARY - - Copyright(c) 2009 Intel Corporation. All rights reserved. - - This program is free software; you can redistribute it and/or modify - it under the terms of version 2 of the GNU General Public License as - published by the Free Software Foundation. - - This program is distributed in the hope that it will be useful, but - WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - General Public License for more details. - - You should have received a copy of the GNU General Public License - along with this program; if not, write to the Free Software - Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - The full GNU General Public License is included in this distribution - in the file called LICENSE.GPL. - - BSD LICENSE - - Copyright(c) 2009 Intel Corporation. All rights reserved. - - Redistribution and use in source and binary forms, with or without - modification, are permitted provided that the following conditions - are met: - - * Redistributions of source code must retain the above copyright - notice, this list of conditions and the following disclaimer. - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in - the documentation and/or other materials provided with the - distribution. - * Neither the name of Intel Corporation nor the names of its - contributors may be used to endorse or promote products derived - from this software without specific prior written permission. - - THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT - LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, - DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY - THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE - OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - -*/ - -#ifndef _LINUX_SFI_ACPI_H -#define _LINUX_SFI_ACPI_H - -#include -#include - -#ifdef CONFIG_SFI -extern int sfi_acpi_table_parse(char *signature, char *oem_id, - char *oem_table_id, - int (*handler)(struct acpi_table_header *)); - -static inline int __init acpi_sfi_table_parse(char *signature, - int (*handler)(struct acpi_table_header *)) -{ - if (!acpi_table_parse(signature, handler)) - return 0; - - return sfi_acpi_table_parse(signature, NULL, NULL, handler); -} -#else /* !CONFIG_SFI */ -static inline int sfi_acpi_table_parse(char *signature, char *oem_id, - char *oem_table_id, - int (*handler)(struct acpi_table_header *)) -{ - return -1; -} - -static inline int __init acpi_sfi_table_parse(char *signature, - int (*handler)(struct acpi_table_header *)) -{ - return acpi_table_parse(signature, handler); -} -#endif /* !CONFIG_SFI */ - -#endif /*_LINUX_SFI_ACPI_H*/ diff --git a/init/main.c b/init/main.c index a626e78dbf06..e9933cbf60d4 100644 --- a/init/main.c +++ b/init/main.c @@ -74,7 +74,6 @@ #include #include #include -#include #include #include #include @@ -1054,7 +1053,6 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void) acpi_subsystem_init(); arch_post_acpi_subsys_init(); - sfi_init_late(); kcsan_init(); /* Do the rest non-__init'ed, we're now alive */ -- cgit v1.2.3 From ca66dca5eda6bd16b7b27fed2a034f2396df5627 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Fri, 5 Feb 2021 03:01:18 +0300 Subject: thermal: qcom: add support for adc-tm5 PMIC thermal monitor Add support for Thermal Monitoring part of PMIC5. This part is closely coupled with ADC, using it's channels directly. ADC-TM support generating interrupts on ADC value crossing low or high voltage bounds, which is used to support thermal trip points. Signed-off-by: Dmitry Baryshkov Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20210205000118.493610-3-dmitry.baryshkov@linaro.org --- drivers/iio/adc/qcom-vadc-common.c | 50 +++ drivers/thermal/qcom/Kconfig | 11 + drivers/thermal/qcom/Makefile | 1 + drivers/thermal/qcom/qcom-spmi-adc-tm5.c | 623 +++++++++++++++++++++++++++++++ include/linux/iio/adc/qcom-vadc-common.h | 3 + 5 files changed, 688 insertions(+) create mode 100644 drivers/thermal/qcom/qcom-spmi-adc-tm5.c (limited to 'include') diff --git a/drivers/iio/adc/qcom-vadc-common.c b/drivers/iio/adc/qcom-vadc-common.c index 8682cf1e213f..14723896aab2 100644 --- a/drivers/iio/adc/qcom-vadc-common.c +++ b/drivers/iio/adc/qcom-vadc-common.c @@ -368,6 +368,28 @@ static int qcom_vadc_map_voltage_temp(const struct vadc_map_pt *pts, return 0; } +static s32 qcom_vadc_map_temp_voltage(const struct vadc_map_pt *pts, + u32 tablesize, int input) +{ + u32 i = 0; + + /* + * Table must be sorted, find the interval of 'y' which contains value + * 'input' and map it to proper 'x' value + */ + while (i < tablesize && pts[i].y < input) + i++; + + if (i == 0) + return pts[0].x; + if (i == tablesize) + return pts[tablesize - 1].x; + + /* interpolate linearly */ + return fixp_linear_interpolate(pts[i - 1].y, pts[i - 1].x, + pts[i].y, pts[i].x, input); +} + static void qcom_vadc_scale_calib(const struct vadc_linear_graph *calib_graph, u16 adc_code, bool absolute, @@ -463,6 +485,21 @@ static int qcom_vadc_scale_chg_temp(const struct vadc_linear_graph *calib_graph, return 0; } +/* convert voltage to ADC code, using 1.875V reference */ +static u16 qcom_vadc_scale_voltage_code(s32 voltage, + const struct vadc_prescale_ratio *prescale, + const u32 full_scale_code_volt, + unsigned int factor) +{ + s64 volt = voltage; + s64 adc_vdd_ref_mv = 1875; /* reference voltage */ + + volt *= prescale->num * factor * full_scale_code_volt; + volt = div64_s64(volt, (s64)prescale->den * adc_vdd_ref_mv * 1000); + + return volt; +} + static int qcom_vadc_scale_code_voltage_factor(u16 adc_code, const struct vadc_prescale_ratio *prescale, const struct adc5_data *data, @@ -627,6 +664,19 @@ int qcom_vadc_scale(enum vadc_scale_fn_type scaletype, } EXPORT_SYMBOL(qcom_vadc_scale); +u16 qcom_adc_tm5_temp_volt_scale(unsigned int prescale_ratio, + u32 full_scale_code_volt, int temp) +{ + const struct vadc_prescale_ratio *prescale = &adc5_prescale_ratios[prescale_ratio]; + s32 voltage; + + voltage = qcom_vadc_map_temp_voltage(adcmap_100k_104ef_104fb_1875_vref, + ARRAY_SIZE(adcmap_100k_104ef_104fb_1875_vref), + temp); + return qcom_vadc_scale_voltage_code(voltage, prescale, full_scale_code_volt, 1000); +} +EXPORT_SYMBOL(qcom_adc_tm5_temp_volt_scale); + int qcom_adc5_hw_scale(enum vadc_scale_fn_type scaletype, unsigned int prescale_ratio, const struct adc5_data *data, diff --git a/drivers/thermal/qcom/Kconfig b/drivers/thermal/qcom/Kconfig index aa9c1d80fae4..8d5ac2df26dc 100644 --- a/drivers/thermal/qcom/Kconfig +++ b/drivers/thermal/qcom/Kconfig @@ -10,6 +10,17 @@ config QCOM_TSENS Also able to set threshold temperature for both hot and cold and update when a threshold is reached. +config QCOM_SPMI_ADC_TM5 + tristate "Qualcomm SPMI PMIC Thermal Monitor ADC5" + depends on OF && SPMI && IIO + select REGMAP_SPMI + select QCOM_VADC_COMMON + help + This enables the thermal driver for the ADC thermal monitoring + device. It shows up as a thermal zone with multiple trip points. + Thermal client sets threshold temperature for both warm and cool and + gets updated when a threshold is reached. + config QCOM_SPMI_TEMP_ALARM tristate "Qualcomm SPMI PMIC Temperature Alarm" depends on OF && SPMI && IIO diff --git a/drivers/thermal/qcom/Makefile b/drivers/thermal/qcom/Makefile index ec86eef7f6a6..252ea7d9da0b 100644 --- a/drivers/thermal/qcom/Makefile +++ b/drivers/thermal/qcom/Makefile @@ -3,4 +3,5 @@ obj-$(CONFIG_QCOM_TSENS) += qcom_tsens.o qcom_tsens-y += tsens.o tsens-v2.o tsens-v1.o tsens-v0_1.o \ tsens-8960.o +obj-$(CONFIG_QCOM_SPMI_ADC_TM5) += qcom-spmi-adc-tm5.o obj-$(CONFIG_QCOM_SPMI_TEMP_ALARM) += qcom-spmi-temp-alarm.o diff --git a/drivers/thermal/qcom/qcom-spmi-adc-tm5.c b/drivers/thermal/qcom/qcom-spmi-adc-tm5.c new file mode 100644 index 000000000000..a2014375587d --- /dev/null +++ b/drivers/thermal/qcom/qcom-spmi-adc-tm5.c @@ -0,0 +1,623 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2020 Linaro Limited + * + * Based on original driver: + * Copyright (c) 2012-2020, The Linux Foundation. All rights reserved. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * Thermal monitoring block consists of 8 (ADC_TM5_NUM_CHANNELS) channels. Each + * channel is programmed to use one of ADC channels for voltage comparison. + * Voltages are programmed using ADC codes, so we have to convert temp to + * voltage and then to ADC code value. + * + * Configuration of TM channels must match configuration of corresponding ADC + * channels. + */ + +#define ADC5_MAX_CHANNEL 0xc0 +#define ADC_TM5_NUM_CHANNELS 8 + +#define ADC_TM5_STATUS_LOW 0x0a + +#define ADC_TM5_STATUS_HIGH 0x0b + +#define ADC_TM5_NUM_BTM 0x0f + +#define ADC_TM5_ADC_DIG_PARAM 0x42 + +#define ADC_TM5_FAST_AVG_CTL (ADC_TM5_ADC_DIG_PARAM + 1) +#define ADC_TM5_FAST_AVG_EN BIT(7) + +#define ADC_TM5_MEAS_INTERVAL_CTL (ADC_TM5_ADC_DIG_PARAM + 2) +#define ADC_TM5_TIMER1 3 /* 3.9ms */ + +#define ADC_TM5_MEAS_INTERVAL_CTL2 (ADC_TM5_ADC_DIG_PARAM + 3) +#define ADC_TM5_MEAS_INTERVAL_CTL2_MASK 0xf0 +#define ADC_TM5_TIMER2 10 /* 1 second */ +#define ADC_TM5_MEAS_INTERVAL_CTL3_MASK 0xf +#define ADC_TM5_TIMER3 4 /* 4 second */ + +#define ADC_TM_EN_CTL1 0x46 +#define ADC_TM_EN BIT(7) +#define ADC_TM_CONV_REQ 0x47 +#define ADC_TM_CONV_REQ_EN BIT(7) + +#define ADC_TM5_M_CHAN_BASE 0x60 + +#define ADC_TM5_M_ADC_CH_SEL_CTL(n) (ADC_TM5_M_CHAN_BASE + ((n) * 8) + 0) +#define ADC_TM5_M_LOW_THR0(n) (ADC_TM5_M_CHAN_BASE + ((n) * 8) + 1) +#define ADC_TM5_M_LOW_THR1(n) (ADC_TM5_M_CHAN_BASE + ((n) * 8) + 2) +#define ADC_TM5_M_HIGH_THR0(n) (ADC_TM5_M_CHAN_BASE + ((n) * 8) + 3) +#define ADC_TM5_M_HIGH_THR1(n) (ADC_TM5_M_CHAN_BASE + ((n) * 8) + 4) +#define ADC_TM5_M_MEAS_INTERVAL_CTL(n) (ADC_TM5_M_CHAN_BASE + ((n) * 8) + 5) +#define ADC_TM5_M_CTL(n) (ADC_TM5_M_CHAN_BASE + ((n) * 8) + 6) +#define ADC_TM5_M_CTL_HW_SETTLE_DELAY_MASK 0xf +#define ADC_TM5_M_CTL_CAL_SEL_MASK 0x30 +#define ADC_TM5_M_CTL_CAL_VAL 0x40 +#define ADC_TM5_M_EN(n) (ADC_TM5_M_CHAN_BASE + ((n) * 8) + 7) +#define ADC_TM5_M_MEAS_EN BIT(7) +#define ADC_TM5_M_HIGH_THR_INT_EN BIT(1) +#define ADC_TM5_M_LOW_THR_INT_EN BIT(0) + +enum adc5_timer_select { + ADC5_TIMER_SEL_1 = 0, + ADC5_TIMER_SEL_2, + ADC5_TIMER_SEL_3, + ADC5_TIMER_SEL_NONE, +}; + +struct adc_tm5_data { + const u32 full_scale_code_volt; + unsigned int *decimation; + unsigned int *hw_settle; +}; + +enum adc_tm5_cal_method { + ADC_TM5_NO_CAL = 0, + ADC_TM5_RATIOMETRIC_CAL, + ADC_TM5_ABSOLUTE_CAL +}; + +struct adc_tm5_chip; + +/** + * struct adc_tm5_channel - ADC Thermal Monitoring channel data. + * @channel: channel number. + * @adc_channel: corresponding ADC channel number. + * @cal_method: calibration method. + * @prescale: channel scaling performed on the input signal. + * @hw_settle_time: the time between AMUX being configured and the + * start of conversion. + * @iio: IIO channel instance used by this channel. + * @chip: ADC TM chip instance. + * @tzd: thermal zone device used by this channel. + */ +struct adc_tm5_channel { + unsigned int channel; + unsigned int adc_channel; + enum adc_tm5_cal_method cal_method; + unsigned int prescale; + unsigned int hw_settle_time; + struct iio_channel *iio; + struct adc_tm5_chip *chip; + struct thermal_zone_device *tzd; +}; + +/** + * struct adc_tm5_chip - ADC Thermal Monitoring properties + * @regmap: SPMI ADC5 Thermal Monitoring peripheral register map field. + * @dev: SPMI ADC5 device. + * @data: software configuration data. + * @channels: array of ADC TM channel data. + * @nchannels: amount of channels defined/allocated + * @decimation: sampling rate supported for the channel. + * @avg_samples: ability to provide single result from the ADC + * that is an average of multiple measurements. + * @base: base address of TM registers. + */ +struct adc_tm5_chip { + struct regmap *regmap; + struct device *dev; + const struct adc_tm5_data *data; + struct adc_tm5_channel *channels; + unsigned int nchannels; + unsigned int decimation; + unsigned int avg_samples; + u16 base; +}; + +static const struct adc_tm5_data adc_tm5_data_pmic = { + .full_scale_code_volt = 0x70e4, + .decimation = (unsigned int []) { 250, 420, 840 }, + .hw_settle = (unsigned int []) { 15, 100, 200, 300, 400, 500, 600, 700, + 1000, 2000, 4000, 8000, 16000, 32000, + 64000, 128000 }, +}; + +static int adc_tm5_read(struct adc_tm5_chip *adc_tm, u16 offset, u8 *data, int len) +{ + return regmap_bulk_read(adc_tm->regmap, adc_tm->base + offset, data, len); +} + +static int adc_tm5_write(struct adc_tm5_chip *adc_tm, u16 offset, u8 *data, int len) +{ + return regmap_bulk_write(adc_tm->regmap, adc_tm->base + offset, data, len); +} + +static int adc_tm5_reg_update(struct adc_tm5_chip *adc_tm, u16 offset, u8 mask, u8 val) +{ + return regmap_write_bits(adc_tm->regmap, adc_tm->base + offset, mask, val); +} + +static irqreturn_t adc_tm5_isr(int irq, void *data) +{ + struct adc_tm5_chip *chip = data; + u8 status_low, status_high, ctl; + int ret, i; + + ret = adc_tm5_read(chip, ADC_TM5_STATUS_LOW, &status_low, sizeof(status_low)); + if (unlikely(ret)) { + dev_err(chip->dev, "read status low failed: %d\n", ret); + return IRQ_HANDLED; + } + + ret = adc_tm5_read(chip, ADC_TM5_STATUS_HIGH, &status_high, sizeof(status_high)); + if (unlikely(ret)) { + dev_err(chip->dev, "read status high failed: %d\n", ret); + return IRQ_HANDLED; + } + + for (i = 0; i < chip->nchannels; i++) { + bool upper_set = false, lower_set = false; + unsigned int ch = chip->channels[i].channel; + + /* No TZD, we warned at the boot time */ + if (!chip->channels[i].tzd) + continue; + + ret = adc_tm5_read(chip, ADC_TM5_M_EN(ch), &ctl, sizeof(ctl)); + if (unlikely(ret)) { + dev_err(chip->dev, "ctl read failed: %d, channel %d\n", ret, i); + continue; + } + + if (!(ctl & ADC_TM5_M_MEAS_EN)) + continue; + + lower_set = (status_low & BIT(ch)) && + (ctl & ADC_TM5_M_LOW_THR_INT_EN); + + upper_set = (status_high & BIT(ch)) && + (ctl & ADC_TM5_M_HIGH_THR_INT_EN); + + if (upper_set || lower_set) + thermal_zone_device_update(chip->channels[i].tzd, + THERMAL_EVENT_UNSPECIFIED); + } + + return IRQ_HANDLED; +} + +static int adc_tm5_get_temp(void *data, int *temp) +{ + struct adc_tm5_channel *channel = data; + int ret; + + if (!channel || !channel->iio) + return -EINVAL; + + ret = iio_read_channel_processed(channel->iio, temp); + if (ret < 0) + return ret; + + if (ret != IIO_VAL_INT) + return -EINVAL; + + return 0; +} + +static int adc_tm5_disable_channel(struct adc_tm5_channel *channel) +{ + struct adc_tm5_chip *chip = channel->chip; + unsigned int reg = ADC_TM5_M_EN(channel->channel); + + return adc_tm5_reg_update(chip, reg, + ADC_TM5_M_MEAS_EN | + ADC_TM5_M_HIGH_THR_INT_EN | + ADC_TM5_M_LOW_THR_INT_EN, + 0); +} + +static int adc_tm5_enable(struct adc_tm5_chip *chip) +{ + int ret; + u8 data; + + data = ADC_TM_EN; + ret = adc_tm5_write(chip, ADC_TM_EN_CTL1, &data, sizeof(data)); + if (ret < 0) { + dev_err(chip->dev, "adc-tm enable failed\n"); + return ret; + } + + data = ADC_TM_CONV_REQ_EN; + ret = adc_tm5_write(chip, ADC_TM_CONV_REQ, &data, sizeof(data)); + if (ret < 0) { + dev_err(chip->dev, "adc-tm request conversion failed\n"); + return ret; + } + + return 0; +} + +static int adc_tm5_configure(struct adc_tm5_channel *channel, int low, int high) +{ + struct adc_tm5_chip *chip = channel->chip; + u8 buf[8]; + u16 reg = ADC_TM5_M_ADC_CH_SEL_CTL(channel->channel); + int ret; + + ret = adc_tm5_read(chip, reg, buf, sizeof(buf)); + if (ret) { + dev_err(chip->dev, "channel %d params read failed: %d\n", channel->channel, ret); + return ret; + } + + buf[0] = channel->adc_channel; + + /* High temperature corresponds to low voltage threshold */ + if (high != INT_MAX) { + u16 adc_code = qcom_adc_tm5_temp_volt_scale(channel->prescale, + chip->data->full_scale_code_volt, high); + + buf[1] = adc_code & 0xff; + buf[2] = adc_code >> 8; + buf[7] |= ADC_TM5_M_LOW_THR_INT_EN; + } else { + buf[7] &= ~ADC_TM5_M_LOW_THR_INT_EN; + } + + /* Low temperature corresponds to high voltage threshold */ + if (low != -INT_MAX) { + u16 adc_code = qcom_adc_tm5_temp_volt_scale(channel->prescale, + chip->data->full_scale_code_volt, low); + + buf[3] = adc_code & 0xff; + buf[4] = adc_code >> 8; + buf[7] |= ADC_TM5_M_HIGH_THR_INT_EN; + } else { + buf[7] &= ~ADC_TM5_M_HIGH_THR_INT_EN; + } + + buf[5] = ADC5_TIMER_SEL_2; + + /* Set calibration select, hw_settle delay */ + buf[6] &= ~ADC_TM5_M_CTL_HW_SETTLE_DELAY_MASK; + buf[6] |= FIELD_PREP(ADC_TM5_M_CTL_HW_SETTLE_DELAY_MASK, channel->hw_settle_time); + buf[6] &= ~ADC_TM5_M_CTL_CAL_SEL_MASK; + buf[6] |= FIELD_PREP(ADC_TM5_M_CTL_CAL_SEL_MASK, channel->cal_method); + + buf[7] |= ADC_TM5_M_MEAS_EN; + + ret = adc_tm5_write(chip, reg, buf, sizeof(buf)); + if (ret) { + dev_err(chip->dev, "channel %d params write failed: %d\n", channel->channel, ret); + return ret; + } + + return adc_tm5_enable(chip); +} + +static int adc_tm5_set_trips(void *data, int low, int high) +{ + struct adc_tm5_channel *channel = data; + struct adc_tm5_chip *chip; + int ret; + + if (!channel) + return -EINVAL; + + chip = channel->chip; + dev_dbg(chip->dev, "%d:low(mdegC):%d, high(mdegC):%d\n", + channel->channel, low, high); + + if (high == INT_MAX && low <= -INT_MAX) + ret = adc_tm5_disable_channel(channel); + else + ret = adc_tm5_configure(channel, low, high); + + return ret; +} + +static struct thermal_zone_of_device_ops adc_tm5_ops = { + .get_temp = adc_tm5_get_temp, + .set_trips = adc_tm5_set_trips, +}; + +static int adc_tm5_register_tzd(struct adc_tm5_chip *adc_tm) +{ + unsigned int i; + struct thermal_zone_device *tzd; + + for (i = 0; i < adc_tm->nchannels; i++) { + adc_tm->channels[i].chip = adc_tm; + + tzd = devm_thermal_zone_of_sensor_register(adc_tm->dev, + adc_tm->channels[i].channel, + &adc_tm->channels[i], + &adc_tm5_ops); + if (IS_ERR(tzd)) { + dev_err(adc_tm->dev, "Error registering TZ zone for channel %d: %ld\n", + adc_tm->channels[i].channel, PTR_ERR(tzd)); + return PTR_ERR(tzd); + } + adc_tm->channels[i].tzd = tzd; + } + + return 0; +} + +static int adc_tm5_init(struct adc_tm5_chip *chip) +{ + u8 buf[4], channels_available; + int ret; + unsigned int i; + + for (i = 0; i < chip->nchannels; i++) { + if (chip->channels[i].channel >= channels_available) { + dev_err(chip->dev, "Invalid channel %d\n", chip->channels[i].channel); + return -EINVAL; + } + } + + ret = adc_tm5_read(chip, ADC_TM5_NUM_BTM, + &channels_available, sizeof(channels_available)); + if (ret) { + dev_err(chip->dev, "read failed for BTM channels\n"); + return ret; + } + + buf[0] = chip->decimation; + buf[1] = chip->avg_samples | ADC_TM5_FAST_AVG_EN; + buf[2] = ADC_TM5_TIMER1; + buf[3] = FIELD_PREP(ADC_TM5_MEAS_INTERVAL_CTL2_MASK, ADC_TM5_TIMER2) | + FIELD_PREP(ADC_TM5_MEAS_INTERVAL_CTL3_MASK, ADC_TM5_TIMER3); + + ret = adc_tm5_write(chip, ADC_TM5_ADC_DIG_PARAM, buf, sizeof(buf)); + if (ret) { + dev_err(chip->dev, "block write failed: %d\n", ret); + return ret; + } + + return ret; +} + +static int adc_tm5_get_dt_channel_data(struct adc_tm5_chip *adc_tm, + struct adc_tm5_channel *channel, + struct device_node *node) +{ + const char *name = node->name; + u32 chan, value, varr[2]; + int ret; + struct device *dev = adc_tm->dev; + struct of_phandle_args args; + + ret = of_property_read_u32(node, "reg", &chan); + if (ret) { + dev_err(dev, "%s: invalid channel number %d\n", name, ret); + return ret; + } + + if (chan >= ADC_TM5_NUM_CHANNELS) { + dev_err(dev, "%s: channel number too big: %d\n", name, chan); + return -EINVAL; + } + + channel->channel = chan; + + /* + * We are tied to PMIC's ADC controller, which always use single + * argument for channel number. So don't bother parsing + * #io-channel-cells, just enforce cell_count = 1. + */ + ret = of_parse_phandle_with_fixed_args(node, "io-channels", 1, 0, &args); + if (ret < 0) { + dev_err(dev, "%s: error parsing ADC channel number %d: %d\n", name, chan, ret); + return ret; + } + of_node_put(args.np); + + if (args.args_count != 1 || args.args[0] >= ADC5_MAX_CHANNEL) { + dev_err(dev, "%s: invalid ADC channel number %d\n", name, chan); + return ret; + } + channel->adc_channel = args.args[0]; + + channel->iio = devm_of_iio_channel_get_by_name(adc_tm->dev, node, NULL); + if (IS_ERR(channel->iio)) { + ret = PTR_ERR(channel->iio); + if (ret != -EPROBE_DEFER) + dev_err(dev, "%s: error getting channel: %d\n", name, ret); + return ret; + } + + ret = of_property_read_u32_array(node, "qcom,pre-scaling", varr, 2); + if (!ret) { + ret = qcom_adc5_prescaling_from_dt(varr[0], varr[1]); + if (ret < 0) { + dev_err(dev, "%s: invalid pre-scaling <%d %d>\n", + name, varr[0], varr[1]); + return ret; + } + channel->prescale = ret; + } else { + /* 1:1 prescale is index 0 */ + channel->prescale = 0; + } + + ret = of_property_read_u32(node, "qcom,hw-settle-time-us", &value); + if (!ret) { + ret = qcom_adc5_hw_settle_time_from_dt(value, adc_tm->data->hw_settle); + if (ret < 0) { + dev_err(dev, "%s invalid hw-settle-time-us %d us\n", + name, value); + return ret; + } + channel->hw_settle_time = ret; + } else { + channel->hw_settle_time = VADC_DEF_HW_SETTLE_TIME; + } + + if (of_property_read_bool(node, "qcom,ratiometric")) + channel->cal_method = ADC_TM5_RATIOMETRIC_CAL; + else + channel->cal_method = ADC_TM5_ABSOLUTE_CAL; + + return 0; +} + +static int adc_tm5_get_dt_data(struct adc_tm5_chip *adc_tm, struct device_node *node) +{ + struct adc_tm5_channel *channels; + struct device_node *child; + u32 value; + int ret; + struct device *dev = adc_tm->dev; + + adc_tm->nchannels = of_get_available_child_count(node); + if (!adc_tm->nchannels) + return -EINVAL; + + adc_tm->channels = devm_kcalloc(dev, adc_tm->nchannels, + sizeof(*adc_tm->channels), GFP_KERNEL); + if (!adc_tm->channels) + return -ENOMEM; + + channels = adc_tm->channels; + + adc_tm->data = of_device_get_match_data(dev); + if (!adc_tm->data) + adc_tm->data = &adc_tm5_data_pmic; + + ret = of_property_read_u32(node, "qcom,decimation", &value); + if (!ret) { + ret = qcom_adc5_decimation_from_dt(value, adc_tm->data->decimation); + if (ret < 0) { + dev_err(dev, "invalid decimation %d\n", value); + return ret; + } + adc_tm->decimation = ret; + } else { + adc_tm->decimation = ADC5_DECIMATION_DEFAULT; + } + + ret = of_property_read_u32(node, "qcom,avg-samples", &value); + if (!ret) { + ret = qcom_adc5_avg_samples_from_dt(value); + if (ret < 0) { + dev_err(dev, "invalid avg-samples %d\n", value); + return ret; + } + adc_tm->avg_samples = ret; + } else { + adc_tm->avg_samples = VADC_DEF_AVG_SAMPLES; + } + + for_each_available_child_of_node(node, child) { + ret = adc_tm5_get_dt_channel_data(adc_tm, channels, child); + if (ret) { + of_node_put(child); + return ret; + } + + channels++; + } + + return 0; +} + +static int adc_tm5_probe(struct platform_device *pdev) +{ + struct device_node *node = pdev->dev.of_node; + struct device *dev = &pdev->dev; + struct adc_tm5_chip *adc_tm; + struct regmap *regmap; + int ret, irq; + u32 reg; + + regmap = dev_get_regmap(dev->parent, NULL); + if (!regmap) + return -ENODEV; + + ret = of_property_read_u32(node, "reg", ®); + if (ret) + return ret; + + adc_tm = devm_kzalloc(&pdev->dev, sizeof(*adc_tm), GFP_KERNEL); + if (!adc_tm) + return -ENOMEM; + + adc_tm->regmap = regmap; + adc_tm->dev = dev; + adc_tm->base = reg; + + irq = platform_get_irq(pdev, 0); + if (irq < 0) { + dev_err(dev, "get_irq failed: %d\n", irq); + return irq; + } + + ret = adc_tm5_get_dt_data(adc_tm, node); + if (ret) { + dev_err(dev, "get dt data failed: %d\n", ret); + return ret; + } + + ret = adc_tm5_init(adc_tm); + if (ret) { + dev_err(dev, "adc-tm init failed\n"); + return ret; + } + + ret = adc_tm5_register_tzd(adc_tm); + if (ret) { + dev_err(dev, "tzd register failed\n"); + return ret; + } + + return devm_request_threaded_irq(dev, irq, NULL, adc_tm5_isr, + IRQF_ONESHOT, "pm-adc-tm5", adc_tm); +} + +static const struct of_device_id adc_tm5_match_table[] = { + { + .compatible = "qcom,spmi-adc-tm5", + .data = &adc_tm5_data_pmic, + }, + { } +}; +MODULE_DEVICE_TABLE(of, adc_tm5_match_table); + +static struct platform_driver adc_tm5_driver = { + .driver = { + .name = "qcom-spmi-adc-tm5", + .of_match_table = adc_tm5_match_table, + }, + .probe = adc_tm5_probe, +}; +module_platform_driver(adc_tm5_driver); + +MODULE_DESCRIPTION("SPMI PMIC Thermal Monitor ADC driver"); +MODULE_LICENSE("GPL v2"); diff --git a/include/linux/iio/adc/qcom-vadc-common.h b/include/linux/iio/adc/qcom-vadc-common.h index 58216124d89d..33f60f43e1aa 100644 --- a/include/linux/iio/adc/qcom-vadc-common.h +++ b/include/linux/iio/adc/qcom-vadc-common.h @@ -158,6 +158,9 @@ int qcom_adc5_hw_scale(enum vadc_scale_fn_type scaletype, const struct adc5_data *data, u16 adc_code, int *result_mdec); +u16 qcom_adc_tm5_temp_volt_scale(unsigned int prescale_ratio, + u32 full_scale_code_volt, int temp); + int qcom_adc5_prescaling_from_dt(u32 num, u32 den); int qcom_adc5_hw_settle_time_from_dt(u32 value, const unsigned int *hw_settle); -- cgit v1.2.3 From aec6c60a01d3a3170242d6a99372a388e1136dc6 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Sat, 16 Jan 2021 08:35:42 +0900 Subject: kbuild: check the minimum compiler version in Kconfig Paul Gortmaker reported a regression in the GCC version check. [1] If you use GCC 4.8, the build breaks before showing the error message "error Sorry, your version of GCC is too old - please use 4.9 or newer." I do not want to apply his fix-up since it implies we would not be able to remove any cc-option test. Anyway, I admit checking the GCC version in is too late. Almost at the same time, Linus also suggested to move the compiler version error to Kconfig time. [2] I unified the two similar scripts, gcc-version.sh and clang-version.sh into cc-version.sh. The old scripts invoked the compiler multiple times (3 times for gcc-version.sh, 4 times for clang-version.sh). I refactored the code so the new one invokes the compiler just once, and also tried my best to use shell-builtin commands where possible. The new script runs faster. $ time ./scripts/clang-version.sh clang 120000 real 0m0.029s user 0m0.012s sys 0m0.021s $ time ./scripts/cc-version.sh clang Clang 120000 real 0m0.009s user 0m0.006s sys 0m0.004s cc-version.sh also shows an error message if the compiler is too old: $ make defconfig CC=clang-9 *** Default configuration is based on 'x86_64_defconfig' *** *** Compiler is too old. *** Your Clang version: 9.0.1 *** Minimum Clang version: 10.0.1 *** scripts/Kconfig.include:46: Sorry, this compiler is not supported. make[1]: *** [scripts/kconfig/Makefile:81: defconfig] Error 1 make: *** [Makefile:602: defconfig] Error 2 The new script takes care of ICC because we have although I am not sure if building the kernel with ICC is well-supported. [1]: https://lore.kernel.org/r/20210110190807.134996-1-paul.gortmaker@windriver.com [2]: https://lore.kernel.org/r/CAHk-=wh-+TMHPTFo1qs-MYyK7tZh-OQovA=pP3=e06aCVp6_kA@mail.gmail.com Fixes: 87de84c9140e ("kbuild: remove cc-option test of -Werror=date-time") Reported-by: Paul Gortmaker Suggested-by: Linus Torvalds Reviewed-by: Nick Desaulniers Tested-by: Nick Desaulniers Reviewed-by: Nathan Chancellor Tested-by: Nathan Chancellor Reviewed-by: Miguel Ojeda Tested-by: Miguel Ojeda Tested-by: Sedat Dilek Signed-off-by: Masahiro Yamada --- MAINTAINERS | 1 - include/linux/compiler-clang.h | 10 ------ include/linux/compiler-gcc.h | 11 ------ init/Kconfig | 9 ++--- scripts/Kconfig.include | 6 ++++ scripts/cc-version.sh | 82 ++++++++++++++++++++++++++++++++++++++++++ scripts/clang-version.sh | 19 ---------- scripts/gcc-version.sh | 20 ----------- 8 files changed, 93 insertions(+), 65 deletions(-) create mode 100755 scripts/cc-version.sh delete mode 100755 scripts/clang-version.sh delete mode 100755 scripts/gcc-version.sh (limited to 'include') diff --git a/MAINTAINERS b/MAINTAINERS index 667d03852191..df820969be1f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4314,7 +4314,6 @@ C: irc://chat.freenode.net/clangbuiltlinux F: Documentation/kbuild/llvm.rst F: include/linux/compiler-clang.h F: scripts/clang-tools/ -F: scripts/clang-version.sh F: scripts/lld-version.sh K: \b(?i:clang|llvm)\b diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index 98cff1b4b088..04c0a5a717f7 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -3,16 +3,6 @@ #error "Please don't include directly, include instead." #endif -#define CLANG_VERSION (__clang_major__ * 10000 \ - + __clang_minor__ * 100 \ - + __clang_patchlevel__) - -#if CLANG_VERSION < 100001 -#ifndef __BPF_TRACING__ -# error Sorry, your version of Clang is too old - please use 10.0.1 or newer. -#endif -#endif - /* Compiler specific definitions for Clang compiler */ /* same as gcc, this was present in clang-2.6 so we can assume it works diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 555ab0fddbef..48750243db4c 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -10,17 +10,6 @@ + __GNUC_MINOR__ * 100 \ + __GNUC_PATCHLEVEL__) -/* https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58145 */ -#if GCC_VERSION < 40900 -# error Sorry, your version of GCC is too old - please use 4.9 or newer. -#elif defined(CONFIG_ARM64) && GCC_VERSION < 50100 -/* - * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=63293 - * https://lore.kernel.org/r/20210107111841.GN1551@shell.armlinux.org.uk - */ -# error Sorry, your version of GCC is too old - please use 5.1 or newer. -#endif - /* * This macro obfuscates arithmetic on a variable address so that gcc * shouldn't recognize the original var, and make assumptions about it. diff --git a/init/Kconfig b/init/Kconfig index 29ad68325028..7bcfa24524c2 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -26,11 +26,11 @@ config CC_VERSION_TEXT and then every file will be rebuilt. config CC_IS_GCC - def_bool $(success,echo "$(CC_VERSION_TEXT)" | grep -q gcc) + def_bool $(success,test "$(cc-name)" = GCC) config GCC_VERSION int - default $(shell,$(srctree)/scripts/gcc-version.sh $(CC)) if CC_IS_GCC + default $(cc-version) if CC_IS_GCC default 0 config LD_VERSION @@ -38,14 +38,15 @@ config LD_VERSION default $(shell,$(LD) --version | $(srctree)/scripts/ld-version.sh) config CC_IS_CLANG - def_bool $(success,echo "$(CC_VERSION_TEXT)" | grep -q clang) + def_bool $(success,test "$(cc-name)" = Clang) config LD_IS_LLD def_bool $(success,$(LD) -v | head -n 1 | grep -q LLD) config CLANG_VERSION int - default $(shell,$(srctree)/scripts/clang-version.sh $(CC)) + default $(cc-version) if CC_IS_CLANG + default 0 config LLD_VERSION int diff --git a/scripts/Kconfig.include b/scripts/Kconfig.include index a5fe72c504ff..0228cb9c74aa 100644 --- a/scripts/Kconfig.include +++ b/scripts/Kconfig.include @@ -39,6 +39,12 @@ as-instr = $(success,printf "%b\n" "$(1)" | $(CC) $(CLANG_FLAGS) -c -x assembler $(error-if,$(failure,command -v $(CC)),compiler '$(CC)' not found) $(error-if,$(failure,command -v $(LD)),linker '$(LD)' not found) +# Get the compiler name, version, and error out if it is not supported. +cc-info := $(shell,$(srctree)/scripts/cc-version.sh $(CC)) +$(error-if,$(success,test -z "$(cc-info)"),Sorry$(comma) this compiler is not supported.) +cc-name := $(shell,set -- $(cc-info) && echo $1) +cc-version := $(shell,set -- $(cc-info) && echo $2) + # Fail if the linker is gold as it's not capable of linking the kernel proper $(error-if,$(success, $(LD) -v | grep -q gold), gold linker '$(LD)' not supported) diff --git a/scripts/cc-version.sh b/scripts/cc-version.sh new file mode 100755 index 000000000000..3f2ee885b116 --- /dev/null +++ b/scripts/cc-version.sh @@ -0,0 +1,82 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# Print the compiler name and its version in a 5 or 6-digit form. +# Also, perform the minimum version check. + +set -e + +# When you raise the minimum compiler version, please update +# Documentation/process/changes.rst as well. +gcc_min_version=4.9.0 +clang_min_version=10.0.1 +icc_min_version=16.0.3 # temporary + +# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=63293 +# https://lore.kernel.org/r/20210107111841.GN1551@shell.armlinux.org.uk +if [ "$SRCARCH" = arm64 ]; then + gcc_min_version=5.1.0 +fi + +# Print the compiler name and some version components. +get_compiler_info() +{ + cat <<- EOF | "$@" -E -P -x c - 2>/dev/null + #if defined(__clang__) + Clang __clang_major__ __clang_minor__ __clang_patchlevel__ + #elif defined(__INTEL_COMPILER) + ICC __INTEL_COMPILER __INTEL_COMPILER_UPDATE + #elif defined(__GNUC__) + GCC __GNUC__ __GNUC_MINOR__ __GNUC_PATCHLEVEL__ + #else + unknown + #endif + EOF +} + +# Convert the version string x.y.z to a canonical 5 or 6-digit form. +get_canonical_version() +{ + IFS=. + set -- $1 + echo $((10000 * $1 + 100 * $2 + $3)) +} + +# $@ instead of $1 because multiple words might be given, e.g. CC="ccache gcc". +orig_args="$@" +set -- $(get_compiler_info "$@") + +name=$1 + +case "$name" in +GCC) + version=$2.$3.$4 + min_version=$gcc_min_version + ;; +Clang) + version=$2.$3.$4 + min_version=$clang_min_version + ;; +ICC) + version=$(($2 / 100)).$(($2 % 100)).$3 + min_version=$icc_min_version + ;; +*) + echo "$orig_args: unknown compiler" >&2 + exit 1 + ;; +esac + +cversion=$(get_canonical_version $version) +min_cversion=$(get_canonical_version $min_version) + +if [ "$cversion" -lt "$min_cversion" ]; then + echo >&2 "***" + echo >&2 "*** Compiler is too old." + echo >&2 "*** Your $name version: $version" + echo >&2 "*** Minimum $name version: $min_version" + echo >&2 "***" + exit 1 +fi + +echo $name $cversion diff --git a/scripts/clang-version.sh b/scripts/clang-version.sh deleted file mode 100755 index 6fabf0695761..000000000000 --- a/scripts/clang-version.sh +++ /dev/null @@ -1,19 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0 -# -# clang-version clang-command -# -# Print the compiler version of `clang-command' in a 5 or 6-digit form -# such as `50001' for clang-5.0.1 etc. - -compiler="$*" - -if ! ( $compiler --version | grep -q clang) ; then - echo 0 - exit 1 -fi - -MAJOR=$(echo __clang_major__ | $compiler -E -x c - | tail -n 1) -MINOR=$(echo __clang_minor__ | $compiler -E -x c - | tail -n 1) -PATCHLEVEL=$(echo __clang_patchlevel__ | $compiler -E -x c - | tail -n 1) -printf "%d%02d%02d\\n" $MAJOR $MINOR $PATCHLEVEL diff --git a/scripts/gcc-version.sh b/scripts/gcc-version.sh deleted file mode 100755 index ae353432539b..000000000000 --- a/scripts/gcc-version.sh +++ /dev/null @@ -1,20 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0 -# -# gcc-version gcc-command -# -# Print the gcc version of `gcc-command' in a 5 or 6-digit form -# such as `29503' for gcc-2.95.3, `30301' for gcc-3.3.1, etc. - -compiler="$*" - -if [ ${#compiler} -eq 0 ]; then - echo "Error: No compiler specified." >&2 - printf "Usage:\n\t$0 \n" >&2 - exit 1 -fi - -MAJOR=$(echo __GNUC__ | $compiler -E -x c - | tail -n 1) -MINOR=$(echo __GNUC_MINOR__ | $compiler -E -x c - | tail -n 1) -PATCHLEVEL=$(echo __GNUC_PATCHLEVEL__ | $compiler -E -x c - | tail -n 1) -printf "%d%02d%02d\\n" $MAJOR $MINOR $PATCHLEVEL -- cgit v1.2.3 From 3c4fa46b30c551b1df2fb1574a684f68bc22067c Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Fri, 5 Feb 2021 12:22:18 -0800 Subject: vmlinux.lds.h: add DWARF v5 sections We expect toolchains to produce these new debug info sections as part of DWARF v5. Add explicit placements to prevent the linker warnings from --orphan-section=warn. Compilers may produce such sections with explicit -gdwarf-5, or based on the implicit default version of DWARF when -g is used via DEBUG_INFO. This implicit default changes over time, and has changed to DWARF v5 with GCC 11. .debug_sup was mentioned in review, but without compilers producing it today, let's wait to add it until it becomes necessary. Cc: stable@vger.kernel.org Link: https://bugzilla.redhat.com/show_bug.cgi?id=1922707 Reported-by: Chris Murphy Suggested-by: Fangrui Song Reviewed-by: Nathan Chancellor Reviewed-by: Mark Wielaard Tested-by: Sedat Dilek Signed-off-by: Nick Desaulniers Signed-off-by: Masahiro Yamada --- include/asm-generic/vmlinux.lds.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index b2b3d81b1535..b3d4ceaf19ed 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -828,8 +828,13 @@ /* DWARF 4 */ \ .debug_types 0 : { *(.debug_types) } \ /* DWARF 5 */ \ + .debug_addr 0 : { *(.debug_addr) } \ + .debug_line_str 0 : { *(.debug_line_str) } \ + .debug_loclists 0 : { *(.debug_loclists) } \ .debug_macro 0 : { *(.debug_macro) } \ - .debug_addr 0 : { *(.debug_addr) } + .debug_names 0 : { *(.debug_names) } \ + .debug_rnglists 0 : { *(.debug_rnglists) } \ + .debug_str_offsets 0 : { *(.debug_str_offsets) } /* Stabs debugging sections. */ #define STABS_DEBUG \ -- cgit v1.2.3 From 88a686728b3739d3598851e729c0e81f194e5c53 Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Fri, 12 Feb 2021 11:29:24 -0500 Subject: kbuild: simplify access to the kernel's version Instead of storing the version in a single integer and having various kernel (and userspace) code how it's constructed, export individual (major, patchlevel, sublevel) components and simplify kernel code that uses it. This should also make it easier on userspace. Signed-off-by: Sasha Levin Acked-by: Greg Kroah-Hartman Signed-off-by: Masahiro Yamada --- Makefile | 5 ++++- drivers/net/ethernet/mellanox/mlx5/core/main.c | 4 ++-- drivers/usb/core/hcd.c | 4 ++-- drivers/usb/gadget/udc/aspeed-vhub/hub.c | 4 ++-- include/linux/usb/composite.h | 4 ++-- kernel/sys.c | 2 +- 6 files changed, 13 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/Makefile b/Makefile index 12607d389148..1fdd44fe1659 100644 --- a/Makefile +++ b/Makefile @@ -1255,7 +1255,10 @@ define filechk_version.h expr $(VERSION) \* 65536 + 0$(PATCHLEVEL) \* 256 + $(SUBLEVEL)); \ fi; \ echo '#define KERNEL_VERSION(a,b,c) (((a) << 16) + ((b) << 8) + \ - ((c) > 255 ? 255 : (c)))' + ((c) > 255 ? 255 : (c)))'; \ + echo \#define LINUX_VERSION_MAJOR $(VERSION); \ + echo \#define LINUX_VERSION_PATCHLEVEL $(PATCHLEVEL); \ + echo \#define LINUX_VERSION_SUBLEVEL $(SUBLEVEL) endef $(version_h): FORCE diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index ca6f2fc39ea0..29f886263dc5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -235,8 +235,8 @@ static void mlx5_set_driver_version(struct mlx5_core_dev *dev) remaining_size = max_t(int, 0, driver_ver_sz - strlen(string)); snprintf(string + strlen(string), remaining_size, "%u.%u.%u", - (u8)((LINUX_VERSION_CODE >> 16) & 0xff), (u8)((LINUX_VERSION_CODE >> 8) & 0xff), - (u16)(LINUX_VERSION_CODE & 0xffff)); + LINUX_VERSION_MAJOR, LINUX_VERSION_PATCHLEVEL, + LINUX_VERSION_SUBLEVEL); /*Send the command*/ MLX5_SET(set_driver_version_in, in, opcode, diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index ad5a0f405a75..3f0381344221 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -111,8 +111,8 @@ DECLARE_WAIT_QUEUE_HEAD(usb_kill_urb_queue); */ /*-------------------------------------------------------------------------*/ -#define KERNEL_REL bin2bcd(((LINUX_VERSION_CODE >> 16) & 0x0ff)) -#define KERNEL_VER bin2bcd(((LINUX_VERSION_CODE >> 8) & 0x0ff)) +#define KERNEL_REL bin2bcd(LINUX_VERSION_MAJOR) +#define KERNEL_VER bin2bcd(LINUX_VERSION_PATCHLEVEL) /* usb 3.1 root hub device descriptor */ static const u8 usb31_rh_dev_descriptor[18] = { diff --git a/drivers/usb/gadget/udc/aspeed-vhub/hub.c b/drivers/usb/gadget/udc/aspeed-vhub/hub.c index bfd8e77788e2..5c7dea5e0ff1 100644 --- a/drivers/usb/gadget/udc/aspeed-vhub/hub.c +++ b/drivers/usb/gadget/udc/aspeed-vhub/hub.c @@ -46,8 +46,8 @@ * - Make vid/did overridable * - make it look like usb1 if usb1 mode forced */ -#define KERNEL_REL bin2bcd(((LINUX_VERSION_CODE >> 16) & 0x0ff)) -#define KERNEL_VER bin2bcd(((LINUX_VERSION_CODE >> 8) & 0x0ff)) +#define KERNEL_REL bin2bcd(LINUX_VERSION_MAJOR) +#define KERNEL_VER bin2bcd(LINUX_VERSION_PATCHLEVEL) enum { AST_VHUB_STR_INDEX_MAX = 4, diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index a2d229ab63ba..7531ce723374 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -573,8 +573,8 @@ static inline u16 get_default_bcdDevice(void) { u16 bcdDevice; - bcdDevice = bin2bcd((LINUX_VERSION_CODE >> 16 & 0xff)) << 8; - bcdDevice |= bin2bcd((LINUX_VERSION_CODE >> 8 & 0xff)); + bcdDevice = bin2bcd(LINUX_VERSION_MAJOR) << 8; + bcdDevice |= bin2bcd(LINUX_VERSION_PATCHLEVEL); return bcdDevice; } diff --git a/kernel/sys.c b/kernel/sys.c index 51f00fe20e4d..c2225bd405d5 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1243,7 +1243,7 @@ static int override_release(char __user *release, size_t len) break; rest++; } - v = ((LINUX_VERSION_CODE >> 8) & 0xff) + 60; + v = LINUX_VERSION_PATCHLEVEL + 60; copy = clamp_t(size_t, len, 1, sizeof(buf)); copy = scnprintf(buf, copy, "2.6.%u%s", v, rest); ret = copy_to_user(release, buf, copy + 1); -- cgit v1.2.3 From aab73d9524026caa14aab17fa9b750a6539fd49f Mon Sep 17 00:00:00 2001 From: James Bottomley Date: Wed, 13 Jan 2021 15:26:33 -0800 Subject: tpm: add sysfs exports for all banks of PCR registers Create sysfs per hash groups with 24 PCR files in them one group, named pcr-, for each agile hash of the TPM. The files are plugged in to a PCR read function which is TPM version agnostic, so this works also for TPM 1.2 but the hash is only sha1 in that case. Note: the macros used to create the hashes emit spurious checkpatch warnings. Do not try to "fix" them as checkpatch recommends, otherwise they'll break. Signed-off-by: James Bottomley Reviewed-by: Jerry Snitselaar Tested-by: Thiago Jung Bauermann Tested-by: Jarkko Sakkinen Reviewed-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen --- drivers/char/tpm/tpm-sysfs.c | 179 +++++++++++++++++++++++++++++++++++++++++++ include/linux/tpm.h | 9 ++- 2 files changed, 187 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/char/tpm/tpm-sysfs.c b/drivers/char/tpm/tpm-sysfs.c index e2ff0b273a0f..63f03cfb8e6a 100644 --- a/drivers/char/tpm/tpm-sysfs.c +++ b/drivers/char/tpm/tpm-sysfs.c @@ -337,11 +337,190 @@ static const struct attribute_group tpm2_dev_group = { .attrs = tpm2_dev_attrs, }; +struct tpm_pcr_attr { + int alg_id; + int pcr; + struct device_attribute attr; +}; + +#define to_tpm_pcr_attr(a) container_of(a, struct tpm_pcr_attr, attr) + +static ssize_t pcr_value_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct tpm_pcr_attr *ha = to_tpm_pcr_attr(attr); + struct tpm_chip *chip = to_tpm_chip(dev); + struct tpm_digest digest; + int i; + int digest_size = 0; + int rc; + char *str = buf; + + for (i = 0; i < chip->nr_allocated_banks; i++) + if (ha->alg_id == chip->allocated_banks[i].alg_id) + digest_size = chip->allocated_banks[i].digest_size; + /* should never happen */ + if (!digest_size) + return -EINVAL; + + digest.alg_id = ha->alg_id; + rc = tpm_pcr_read(chip, ha->pcr, &digest); + if (rc) + return rc; + for (i = 0; i < digest_size; i++) + str += sprintf(str, "%02X", digest.digest[i]); + str += sprintf(str, "\n"); + + return str - buf; +} + +/* + * The following set of defines represents all the magic to build + * the per hash attribute groups for displaying each bank of PCRs. + * The only slight problem with this approach is that every PCR is + * hard coded to be present, so you don't know if an PCR is missing + * until a cat of the file returns -EINVAL + * + * Also note you must ignore checkpatch warnings in this macro + * code. This is deep macro magic that checkpatch.pl doesn't + * understand. + */ + +/* Note, this must match TPM2_PLATFORM_PCR which is fixed at 24. */ +#define _TPM_HELPER(_alg, _hash, F) \ + F(_alg, _hash, 0) \ + F(_alg, _hash, 1) \ + F(_alg, _hash, 2) \ + F(_alg, _hash, 3) \ + F(_alg, _hash, 4) \ + F(_alg, _hash, 5) \ + F(_alg, _hash, 6) \ + F(_alg, _hash, 7) \ + F(_alg, _hash, 8) \ + F(_alg, _hash, 9) \ + F(_alg, _hash, 10) \ + F(_alg, _hash, 11) \ + F(_alg, _hash, 12) \ + F(_alg, _hash, 13) \ + F(_alg, _hash, 14) \ + F(_alg, _hash, 15) \ + F(_alg, _hash, 16) \ + F(_alg, _hash, 17) \ + F(_alg, _hash, 18) \ + F(_alg, _hash, 19) \ + F(_alg, _hash, 20) \ + F(_alg, _hash, 21) \ + F(_alg, _hash, 22) \ + F(_alg, _hash, 23) + +/* ignore checkpatch warning about trailing ; in macro. */ +#define PCR_ATTR(_alg, _hash, _pcr) \ + static struct tpm_pcr_attr dev_attr_pcr_##_hash##_##_pcr = { \ + .alg_id = _alg, \ + .pcr = _pcr, \ + .attr = { \ + .attr = { \ + .name = __stringify(_pcr), \ + .mode = 0444 \ + }, \ + .show = pcr_value_show \ + } \ + }; + +#define PCR_ATTRS(_alg, _hash) \ + _TPM_HELPER(_alg, _hash, PCR_ATTR) + +/* ignore checkpatch warning about trailing , in macro. */ +#define PCR_ATTR_VAL(_alg, _hash, _pcr) \ + &dev_attr_pcr_##_hash##_##_pcr.attr.attr, + +#define PCR_ATTR_GROUP_ARRAY(_alg, _hash) \ + static struct attribute *pcr_group_attrs_##_hash[] = { \ + _TPM_HELPER(_alg, _hash, PCR_ATTR_VAL) \ + NULL \ + } + +#define PCR_ATTR_GROUP(_alg, _hash) \ + static struct attribute_group pcr_group_##_hash = { \ + .name = "pcr-" __stringify(_hash), \ + .attrs = pcr_group_attrs_##_hash \ + } + +#define PCR_ATTR_BUILD(_alg, _hash) \ + PCR_ATTRS(_alg, _hash) \ + PCR_ATTR_GROUP_ARRAY(_alg, _hash); \ + PCR_ATTR_GROUP(_alg, _hash) +/* + * End of macro structure to build an attribute group containing 24 + * PCR value files for each supported hash algorithm + */ + +/* + * The next set of macros implements the cleverness for each hash to + * build a static attribute group called pcr_group_ which can be + * added to chip->groups[]. + * + * The first argument is the TPM algorithm id and the second is the + * hash used as both the suffix and the group name. Note: the group + * name is a directory in the top level tpm class with the name + * pcr-, so it must not clash with any other names already + * in the sysfs directory. + */ +PCR_ATTR_BUILD(TPM_ALG_SHA1, sha1); +PCR_ATTR_BUILD(TPM_ALG_SHA256, sha256); +PCR_ATTR_BUILD(TPM_ALG_SHA384, sha384); +PCR_ATTR_BUILD(TPM_ALG_SHA512, sha512); +PCR_ATTR_BUILD(TPM_ALG_SM3_256, sm3); + + void tpm_sysfs_add_device(struct tpm_chip *chip) { + int i; + WARN_ON(chip->groups_cnt != 0); + if (chip->flags & TPM_CHIP_FLAG_TPM2) chip->groups[chip->groups_cnt++] = &tpm2_dev_group; else chip->groups[chip->groups_cnt++] = &tpm1_dev_group; + + /* add one group for each bank hash */ + for (i = 0; i < chip->nr_allocated_banks; i++) { + switch (chip->allocated_banks[i].alg_id) { + case TPM_ALG_SHA1: + chip->groups[chip->groups_cnt++] = &pcr_group_sha1; + break; + case TPM_ALG_SHA256: + chip->groups[chip->groups_cnt++] = &pcr_group_sha256; + break; + case TPM_ALG_SHA384: + chip->groups[chip->groups_cnt++] = &pcr_group_sha384; + break; + case TPM_ALG_SHA512: + chip->groups[chip->groups_cnt++] = &pcr_group_sha512; + break; + case TPM_ALG_SM3_256: + chip->groups[chip->groups_cnt++] = &pcr_group_sm3; + break; + default: + /* + * If triggers, send a patch to add both a + * PCR_ATTR_BUILD() macro above for the + * missing algorithm as well as an additional + * case in this switch statement. + */ + dev_err(&chip->dev, + "TPM with unsupported bank algorithm 0x%04x", + chip->allocated_banks[i].alg_id); + break; + } + } + + /* + * This will only trigger if someone has added an additional + * hash to the tpm_algorithms enum without incrementing + * TPM_MAX_HASHES. + */ + WARN_ON(chip->groups_cnt > TPM_MAX_HASHES + 1); } diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 8f4ff39f51e7..ae2482510f8c 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -31,6 +31,7 @@ struct tpm_chip; struct trusted_key_payload; struct trusted_key_options; +/* if you add a new hash to this, increment TPM_MAX_HASHES below */ enum tpm_algorithms { TPM_ALG_ERROR = 0x0000, TPM_ALG_SHA1 = 0x0004, @@ -42,6 +43,12 @@ enum tpm_algorithms { TPM_ALG_SM3_256 = 0x0012, }; +/* + * maximum number of hashing algorithms a TPM can have. This is + * basically a count of every hash in tpm_algorithms above + */ +#define TPM_MAX_HASHES 5 + struct tpm_digest { u16 alg_id; u8 digest[TPM_MAX_DIGEST_SIZE]; @@ -146,7 +153,7 @@ struct tpm_chip { struct dentry *bios_dir[TPM_NUM_EVENT_LOG_FILES]; - const struct attribute_group *groups[3]; + const struct attribute_group *groups[3 + TPM_MAX_HASHES]; unsigned int groups_cnt; u32 nr_allocated_banks; -- cgit v1.2.3 From 8c657a0590de585b1115847c17b34a58025f2f4b Mon Sep 17 00:00:00 2001 From: Jarkko Sakkinen Date: Fri, 29 Jan 2021 01:56:21 +0200 Subject: KEYS: trusted: Reserve TPM for seal and unseal operations When TPM 2.0 trusted keys code was moved to the trusted keys subsystem, the operations were unwrapped from tpm_try_get_ops() and tpm_put_ops(), which are used to take temporarily the ownership of the TPM chip. The ownership is only taken inside tpm_send(), but this is not sufficient, as in the key load TPM2_CC_LOAD, TPM2_CC_UNSEAL and TPM2_FLUSH_CONTEXT need to be done as a one single atom. Take the TPM chip ownership before sending anything with tpm_try_get_ops() and tpm_put_ops(), and use tpm_transmit_cmd() to send TPM commands instead of tpm_send(), reverting back to the old behaviour. Fixes: 2e19e10131a0 ("KEYS: trusted: Move TPM2 trusted keys code") Reported-by: "James E.J. Bottomley" Cc: stable@vger.kernel.org Cc: David Howells Cc: Mimi Zohar Cc: Sumit Garg Acked-by Sumit Garg Tested-by: Mimi Zohar Signed-off-by: Jarkko Sakkinen --- drivers/char/tpm/tpm.h | 4 ---- include/linux/tpm.h | 5 ++++- security/keys/trusted-keys/trusted_tpm2.c | 22 ++++++++++++++++++---- 3 files changed, 22 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h index 947d1db0a5cc..283f78211c3a 100644 --- a/drivers/char/tpm/tpm.h +++ b/drivers/char/tpm/tpm.h @@ -164,8 +164,6 @@ extern const struct file_operations tpmrm_fops; extern struct idr dev_nums_idr; ssize_t tpm_transmit(struct tpm_chip *chip, u8 *buf, size_t bufsiz); -ssize_t tpm_transmit_cmd(struct tpm_chip *chip, struct tpm_buf *buf, - size_t min_rsp_body_length, const char *desc); int tpm_get_timeouts(struct tpm_chip *); int tpm_auto_startup(struct tpm_chip *chip); @@ -194,8 +192,6 @@ static inline void tpm_msleep(unsigned int delay_msec) int tpm_chip_start(struct tpm_chip *chip); void tpm_chip_stop(struct tpm_chip *chip); struct tpm_chip *tpm_find_get_ops(struct tpm_chip *chip); -__must_check int tpm_try_get_ops(struct tpm_chip *chip); -void tpm_put_ops(struct tpm_chip *chip); struct tpm_chip *tpm_chip_alloc(struct device *dev, const struct tpm_class_ops *ops); diff --git a/include/linux/tpm.h b/include/linux/tpm.h index ae2482510f8c..543aa3b1dedc 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -404,6 +404,10 @@ static inline u32 tpm2_rc_value(u32 rc) #if defined(CONFIG_TCG_TPM) || defined(CONFIG_TCG_TPM_MODULE) extern int tpm_is_tpm2(struct tpm_chip *chip); +extern __must_check int tpm_try_get_ops(struct tpm_chip *chip); +extern void tpm_put_ops(struct tpm_chip *chip); +extern ssize_t tpm_transmit_cmd(struct tpm_chip *chip, struct tpm_buf *buf, + size_t min_rsp_body_length, const char *desc); extern int tpm_pcr_read(struct tpm_chip *chip, u32 pcr_idx, struct tpm_digest *digest); extern int tpm_pcr_extend(struct tpm_chip *chip, u32 pcr_idx, @@ -417,7 +421,6 @@ static inline int tpm_is_tpm2(struct tpm_chip *chip) { return -ENODEV; } - static inline int tpm_pcr_read(struct tpm_chip *chip, int pcr_idx, struct tpm_digest *digest) { diff --git a/security/keys/trusted-keys/trusted_tpm2.c b/security/keys/trusted-keys/trusted_tpm2.c index 08ec7f48f01d..e2a0ed5d02f0 100644 --- a/security/keys/trusted-keys/trusted_tpm2.c +++ b/security/keys/trusted-keys/trusted_tpm2.c @@ -83,6 +83,12 @@ int tpm2_seal_trusted(struct tpm_chip *chip, if (rc) return rc; + rc = tpm_buf_init(&buf, TPM2_ST_SESSIONS, TPM2_CC_CREATE); + if (rc) { + tpm_put_ops(chip); + return rc; + } + tpm_buf_append_u32(&buf, options->keyhandle); tpm2_buf_append_auth(&buf, TPM2_RS_PW, NULL /* nonce */, 0, @@ -130,7 +136,7 @@ int tpm2_seal_trusted(struct tpm_chip *chip, goto out; } - rc = tpm_send(chip, buf.data, tpm_buf_length(&buf)); + rc = tpm_transmit_cmd(chip, &buf, 4, "sealing data"); if (rc) goto out; @@ -157,6 +163,7 @@ out: rc = -EPERM; } + tpm_put_ops(chip); return rc; } @@ -211,7 +218,7 @@ static int tpm2_load_cmd(struct tpm_chip *chip, goto out; } - rc = tpm_send(chip, buf.data, tpm_buf_length(&buf)); + rc = tpm_transmit_cmd(chip, &buf, 4, "loading blob"); if (!rc) *blob_handle = be32_to_cpup( (__be32 *) &buf.data[TPM_HEADER_SIZE]); @@ -260,7 +267,7 @@ static int tpm2_unseal_cmd(struct tpm_chip *chip, options->blobauth /* hmac */, TPM_DIGEST_SIZE); - rc = tpm_send(chip, buf.data, tpm_buf_length(&buf)); + rc = tpm_transmit_cmd(chip, &buf, 6, "unsealing"); if (rc > 0) rc = -EPERM; @@ -304,12 +311,19 @@ int tpm2_unseal_trusted(struct tpm_chip *chip, u32 blob_handle; int rc; - rc = tpm2_load_cmd(chip, payload, options, &blob_handle); + rc = tpm_try_get_ops(chip); if (rc) return rc; + rc = tpm2_load_cmd(chip, payload, options, &blob_handle); + if (rc) + goto out; + rc = tpm2_unseal_cmd(chip, payload, options, blob_handle); tpm2_flush_context(chip, blob_handle); +out: + tpm_put_ops(chip); + return rc; } -- cgit v1.2.3 From bfe3911a91047557eb0e620f95a370aee6a248c7 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Fri, 5 Feb 2021 22:00:12 +0000 Subject: kcmp: Support selection of SYS_kcmp without CHECKPOINT_RESTORE Userspace has discovered the functionality offered by SYS_kcmp and has started to depend upon it. In particular, Mesa uses SYS_kcmp for os_same_file_description() in order to identify when two fd (e.g. device or dmabuf) point to the same struct file. Since they depend on it for core functionality, lift SYS_kcmp out of the non-default CONFIG_CHECKPOINT_RESTORE into the selectable syscall category. Rasmus Villemoes also pointed out that systemd uses SYS_kcmp to deduplicate the per-service file descriptor store. Note that some distributions such as Ubuntu are already enabling CHECKPOINT_RESTORE in their configs and so, by extension, SYS_kcmp. References: https://gitlab.freedesktop.org/drm/intel/-/issues/3046 Signed-off-by: Chris Wilson Cc: Kees Cook Cc: Andy Lutomirski Cc: Will Drewry Cc: Andrew Morton Cc: Dave Airlie Cc: Daniel Vetter Cc: Lucas Stach Cc: Rasmus Villemoes Cc: Cyrill Gorcunov Cc: stable@vger.kernel.org Acked-by: Daniel Vetter # DRM depends on kcmp Acked-by: Rasmus Villemoes # systemd uses kcmp Reviewed-by: Cyrill Gorcunov Reviewed-by: Kees Cook Acked-by: Thomas Zimmermann Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210205220012.1983-1-chris@chris-wilson.co.uk --- drivers/gpu/drm/Kconfig | 3 +++ fs/eventpoll.c | 4 ++-- include/linux/eventpoll.h | 2 +- init/Kconfig | 11 +++++++++++ kernel/Makefile | 2 +- tools/testing/selftests/seccomp/seccomp_bpf.c | 2 +- 6 files changed, 19 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index 0973f408d75f..af6c6d214d91 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -15,6 +15,9 @@ menuconfig DRM select I2C_ALGOBIT select DMA_SHARED_BUFFER select SYNC_FILE +# gallium uses SYS_kcmp for os_same_file_description() to de-duplicate +# device and dmabuf fd. Let's make sure that is available for our userspace. + select KCMP help Kernel-level support for the Direct Rendering Infrastructure (DRI) introduced in XFree86 4.0. If you say Y here, you need to select diff --git a/fs/eventpoll.c b/fs/eventpoll.c index a829af074eb5..3196474cbe24 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -979,7 +979,7 @@ static struct epitem *ep_find(struct eventpoll *ep, struct file *file, int fd) return epir; } -#ifdef CONFIG_CHECKPOINT_RESTORE +#ifdef CONFIG_KCMP static struct epitem *ep_find_tfd(struct eventpoll *ep, int tfd, unsigned long toff) { struct rb_node *rbp; @@ -1021,7 +1021,7 @@ struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, return file_raw; } -#endif /* CONFIG_CHECKPOINT_RESTORE */ +#endif /* CONFIG_KCMP */ /** * Adds a new entry to the tail of the list in a lockless way, i.e. diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h index 0350393465d4..593322c946e6 100644 --- a/include/linux/eventpoll.h +++ b/include/linux/eventpoll.h @@ -18,7 +18,7 @@ struct file; #ifdef CONFIG_EPOLL -#ifdef CONFIG_CHECKPOINT_RESTORE +#ifdef CONFIG_KCMP struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, unsigned long toff); #endif diff --git a/init/Kconfig b/init/Kconfig index 29ad68325028..b7d3c6a12196 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1193,6 +1193,7 @@ endif # NAMESPACES config CHECKPOINT_RESTORE bool "Checkpoint/restore support" select PROC_CHILDREN + select KCMP default n help Enables additional kernel features in a sake of checkpoint/restore. @@ -1736,6 +1737,16 @@ config ARCH_HAS_MEMBARRIER_CALLBACKS config ARCH_HAS_MEMBARRIER_SYNC_CORE bool +config KCMP + bool "Enable kcmp() system call" if EXPERT + help + Enable the kernel resource comparison system call. It provides + user-space with the ability to compare two processes to see if they + share a common resource, such as a file descriptor or even virtual + memory space. + + If unsure, say N. + config RSEQ bool "Enable rseq() system call" if EXPERT default y diff --git a/kernel/Makefile b/kernel/Makefile index aa7368c7eabf..320f1f3941b7 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -51,7 +51,7 @@ obj-y += livepatch/ obj-y += dma/ obj-y += entry/ -obj-$(CONFIG_CHECKPOINT_RESTORE) += kcmp.o +obj-$(CONFIG_KCMP) += kcmp.o obj-$(CONFIG_FREEZER) += freezer.o obj-$(CONFIG_PROFILING) += profile.o obj-$(CONFIG_STACKTRACE) += stacktrace.o diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 26c72f2b61b1..1b6c7d33c4ff 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -315,7 +315,7 @@ TEST(kcmp) ret = __filecmp(getpid(), getpid(), 1, 1); EXPECT_EQ(ret, 0); if (ret != 0 && errno == ENOSYS) - SKIP(return, "Kernel does not support kcmp() (missing CONFIG_CHECKPOINT_RESTORE?)"); + SKIP(return, "Kernel does not support kcmp() (missing CONFIG_KCMP?)"); } TEST(mode_strict_support) -- cgit v1.2.3 From afd56e78dd179d5638333bb407d9f7da2863381a Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Fri, 22 Jan 2021 15:41:14 +0100 Subject: libceph: deprecate [no]cephx_require_signatures options These options were introduced in 3.19 with support for message signing and are rather useless, as explained in commit a51983e4dd2d ("libceph: add nocephx_sign_messages option"). Deprecate them. In case there is someone out there with a cluster that lacks support for MSG_AUTH feature (very unlikely but has to be considered since we haven't formally raised the bar from argonaut to bobtail yet), make nocephx_sign_messages also waive MSG_AUTH requirement. This is probably how it should have been done in the first place -- if we aren't going to sign, requiring the signing feature makes no sense. Signed-off-by: Ilya Dryomov Reviewed-by: Jeff Layton --- include/linux/ceph/libceph.h | 7 +++---- net/ceph/ceph_common.c | 11 +++++------ 2 files changed, 8 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index eb9008bb3992..409d8c29bc4f 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -32,10 +32,9 @@ #define CEPH_OPT_NOSHARE (1<<1) /* don't share client with other sbs */ #define CEPH_OPT_MYIP (1<<2) /* specified my ip */ #define CEPH_OPT_NOCRC (1<<3) /* no data crc on writes (msgr1) */ -#define CEPH_OPT_NOMSGAUTH (1<<4) /* don't require msg signing feat */ -#define CEPH_OPT_TCP_NODELAY (1<<5) /* TCP_NODELAY on TCP sockets */ -#define CEPH_OPT_NOMSGSIGN (1<<6) /* don't sign msgs (msgr1) */ -#define CEPH_OPT_ABORT_ON_FULL (1<<7) /* abort w/ ENOSPC when full */ +#define CEPH_OPT_TCP_NODELAY (1<<4) /* TCP_NODELAY on TCP sockets */ +#define CEPH_OPT_NOMSGSIGN (1<<5) /* don't sign msgs (msgr1) */ +#define CEPH_OPT_ABORT_ON_FULL (1<<6) /* abort w/ ENOSPC when full */ #define CEPH_OPT_DEFAULT (CEPH_OPT_TCP_NODELAY) diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index 271287c5ec12..bec181181d41 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -307,7 +307,8 @@ static const struct constant_table ceph_param_ms_mode[] = { static const struct fs_parameter_spec ceph_parameters[] = { fsparam_flag ("abort_on_full", Opt_abort_on_full), - fsparam_flag_no ("cephx_require_signatures", Opt_cephx_require_signatures), + __fsparam (NULL, "cephx_require_signatures", Opt_cephx_require_signatures, + fs_param_neg_with_no|fs_param_deprecated, NULL), fsparam_flag_no ("cephx_sign_messages", Opt_cephx_sign_messages), fsparam_flag_no ("crc", Opt_crc), fsparam_string ("crush_location", Opt_crush_location), @@ -596,9 +597,9 @@ int ceph_parse_param(struct fs_parameter *param, struct ceph_options *opt, break; case Opt_cephx_require_signatures: if (!result.negated) - opt->flags &= ~CEPH_OPT_NOMSGAUTH; + warn_plog(&log, "Ignoring cephx_require_signatures"); else - opt->flags |= CEPH_OPT_NOMSGAUTH; + warn_plog(&log, "Ignoring nocephx_require_signatures, use nocephx_sign_messages"); break; case Opt_cephx_sign_messages: if (!result.negated) @@ -686,8 +687,6 @@ int ceph_print_client_options(struct seq_file *m, struct ceph_client *client, seq_puts(m, "noshare,"); if (opt->flags & CEPH_OPT_NOCRC) seq_puts(m, "nocrc,"); - if (opt->flags & CEPH_OPT_NOMSGAUTH) - seq_puts(m, "nocephx_require_signatures,"); if (opt->flags & CEPH_OPT_NOMSGSIGN) seq_puts(m, "nocephx_sign_messages,"); if ((opt->flags & CEPH_OPT_TCP_NODELAY) == 0) @@ -756,7 +755,7 @@ struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private) client->supported_features = CEPH_FEATURES_SUPPORTED_DEFAULT; client->required_features = CEPH_FEATURES_REQUIRED_DEFAULT; - if (!ceph_test_opt(client, NOMSGAUTH)) + if (!ceph_test_opt(client, NOMSGSIGN)) client->required_features |= CEPH_FEATURE_MSG_AUTH; /* msgr */ -- cgit v1.2.3 From e0a912e8ddbaa0536352dd8318845cdfdbab7bab Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 16 Feb 2021 12:17:22 -0500 Subject: SUNRPC: Use TCP_CORK to optimise send performance on the server Use a counter to keep track of how many requests are queued behind the xprt->xpt_mutex, and keep TCP_CORK set until the queue is empty. Signed-off-by: Trond Myklebust Link: https://lore.kernel.org/linux-nfs/20210213202532.23146-1-trondmy@kernel.org/T/#u Signed-off-by: Chuck Lever --- include/linux/sunrpc/svcsock.h | 2 ++ net/sunrpc/svcsock.c | 8 +++++++- 2 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h index b7ac7fe68306..bcc555c7ae9c 100644 --- a/include/linux/sunrpc/svcsock.h +++ b/include/linux/sunrpc/svcsock.h @@ -35,6 +35,8 @@ struct svc_sock { /* Total length of the data (not including fragment headers) * received so far in the fragments making up this rpc: */ u32 sk_datalen; + /* Number of queued send requests */ + atomic_t sk_sendqlen; struct page * sk_pages[RPCSVC_MAXPAGES]; /* received data */ }; diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 5a809c64dc7b..231f510a4830 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -1171,18 +1171,23 @@ static int svc_tcp_sendto(struct svc_rqst *rqstp) svc_tcp_release_rqst(rqstp); + atomic_inc(&svsk->sk_sendqlen); mutex_lock(&xprt->xpt_mutex); if (svc_xprt_is_dead(xprt)) goto out_notconn; + tcp_sock_set_cork(svsk->sk_sk, true); err = svc_tcp_sendmsg(svsk->sk_sock, &msg, xdr, marker, &sent); xdr_free_bvec(xdr); trace_svcsock_tcp_send(xprt, err < 0 ? err : sent); if (err < 0 || sent != (xdr->len + sizeof(marker))) goto out_close; + if (atomic_dec_and_test(&svsk->sk_sendqlen)) + tcp_sock_set_cork(svsk->sk_sk, false); mutex_unlock(&xprt->xpt_mutex); return sent; out_notconn: + atomic_dec(&svsk->sk_sendqlen); mutex_unlock(&xprt->xpt_mutex); return -ENOTCONN; out_close: @@ -1192,6 +1197,7 @@ out_close: (err < 0) ? err : sent, xdr->len); set_bit(XPT_CLOSE, &xprt->xpt_flags); svc_xprt_enqueue(xprt); + atomic_dec(&svsk->sk_sendqlen); mutex_unlock(&xprt->xpt_mutex); return -EAGAIN; } @@ -1261,7 +1267,7 @@ static void svc_tcp_init(struct svc_sock *svsk, struct svc_serv *serv) svsk->sk_datalen = 0; memset(&svsk->sk_pages[0], 0, sizeof(svsk->sk_pages)); - tcp_sk(sk)->nonagle |= TCP_NAGLE_OFF; + tcp_sock_set_nodelay(sk); set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); switch (sk->sk_state) { -- cgit v1.2.3 From 633d61021298f690f823ff51bcdab906e3644fe1 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Thu, 28 Jan 2021 18:46:47 +0000 Subject: RDMA/ipoib: Remove racy Subnet Manager sendonly join checks When a system receives a REREG event from the SM, then the SM information in the kernel is marked as invalid and a request is sent to the SM to update the information. The SM information is invalid in that time period. However, receiving a REREG also occurs simultaneously in user space applications that are now trying to rejoin the multicast groups. Some of those may be sendonly multicast groups which are then failing. If the SM information is invalid then ib_sa_sendonly_fullmem_support() returns false. That is wrong because it just means that we do not know yet if the potentially new SM supports sendonly joins. Sendonly join was introduced in 2015 and all the Subnet managers have supported it ever since. So there is no point in checking if a subnet manager supports it. Should an old opensm get a request for a sendonly join then the request will fail. The code that is removed here accomodated that situation and fell back to a full join. Falling back to a full join is problematic in itself. The reason to use the sendonly join was to reduce the traffic on the Infiniband fabric otherwise one could have just stayed with the regular join. So this patch may cause users of very old opensms to discover that lots of traffic needlessly crosses their IB fabrics. Link: https://lore.kernel.org/r/alpine.DEB.2.22.394.2101281845160.13303@www.lameter.com Signed-off-by: Christoph Lameter Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/cma.c | 11 ----------- drivers/infiniband/core/sa_query.c | 24 ------------------------ drivers/infiniband/ulp/ipoib/ipoib.h | 1 - drivers/infiniband/ulp/ipoib/ipoib_main.c | 2 -- drivers/infiniband/ulp/ipoib/ipoib_multicast.c | 13 +------------ include/rdma/ib_sa.h | 4 ---- 6 files changed, 1 insertion(+), 54 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index c51b84b2d2f3..58ee7004c8d8 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -4542,17 +4542,6 @@ static int cma_join_ib_multicast(struct rdma_id_private *id_priv, rec.pkey = cpu_to_be16(ib_addr_get_pkey(dev_addr)); rec.join_state = mc->join_state; - if ((rec.join_state == BIT(SENDONLY_FULLMEMBER_JOIN)) && - (!ib_sa_sendonly_fullmem_support(&sa_client, - id_priv->id.device, - id_priv->id.port_num))) { - dev_warn( - &id_priv->id.device->dev, - "RDMA CM: port %u Unable to multicast join: SM doesn't support Send Only Full Member option\n", - id_priv->id.port_num); - return -EOPNOTSUPP; - } - comp_mask = IB_SA_MCMEMBER_REC_MGID | IB_SA_MCMEMBER_REC_PORT_GID | IB_SA_MCMEMBER_REC_PKEY | IB_SA_MCMEMBER_REC_JOIN_STATE | IB_SA_MCMEMBER_REC_QKEY | IB_SA_MCMEMBER_REC_SL | diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c index 5bd047042e68..9ef1a355131b 100644 --- a/drivers/infiniband/core/sa_query.c +++ b/drivers/infiniband/core/sa_query.c @@ -1951,30 +1951,6 @@ err1: } EXPORT_SYMBOL(ib_sa_guid_info_rec_query); -bool ib_sa_sendonly_fullmem_support(struct ib_sa_client *client, - struct ib_device *device, - u8 port_num) -{ - struct ib_sa_device *sa_dev = ib_get_client_data(device, &sa_client); - struct ib_sa_port *port; - bool ret = false; - unsigned long flags; - - if (!sa_dev) - return ret; - - port = &sa_dev->port[port_num - sa_dev->start_port]; - - spin_lock_irqsave(&port->classport_lock, flags); - if ((port->classport_info.valid) && - (port->classport_info.data.type == RDMA_CLASS_PORT_INFO_IB)) - ret = ib_get_cpi_capmask2(&port->classport_info.data.ib) - & IB_SA_CAP_MASK2_SENDONLY_FULL_MEM_SUPPORT; - spin_unlock_irqrestore(&port->classport_lock, flags); - return ret; -} -EXPORT_SYMBOL(ib_sa_sendonly_fullmem_support); - struct ib_classport_info_context { struct completion done; struct ib_sa_query *sa_query; diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h index 3440dc48d02c..179ff1d068e5 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib.h +++ b/drivers/infiniband/ulp/ipoib/ipoib.h @@ -413,7 +413,6 @@ struct ipoib_dev_priv { u64 hca_caps; struct ipoib_ethtool_st ethtool; unsigned int max_send_sge; - bool sm_fullmember_sendonly_support; const struct net_device_ops *rn_ops; }; diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index a6f413491321..e16b40c09f82 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -141,8 +141,6 @@ int ipoib_open(struct net_device *dev) set_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags); - priv->sm_fullmember_sendonly_support = false; - if (ipoib_ib_dev_open(dev)) { if (!test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags)) return 0; diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c index e3e4447c0f51..5b3154503bf4 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c @@ -333,15 +333,6 @@ void ipoib_mcast_carrier_on_task(struct work_struct *work) ipoib_dbg(priv, "Keeping carrier off until IB port is active\n"); return; } - /* - * Check if can send sendonly MCG's with sendonly-fullmember join state. - * It done here after the successfully join to the broadcast group, - * because the broadcast group must always be joined first and is always - * re-joined if the SM changes substantially. - */ - priv->sm_fullmember_sendonly_support = - ib_sa_sendonly_fullmem_support(&ipoib_sa_client, - priv->ca, priv->port); /* * Take rtnl_lock to avoid racing with ipoib_stop() and * turning the carrier back on while a device is being @@ -537,9 +528,7 @@ static int ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast) * most closely emulates the behavior, from a user space * application perspective, of Ethernet multicast operation. */ - if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags) && - priv->sm_fullmember_sendonly_support) - /* SM supports sendonly-fullmember, otherwise fallback to full-member */ + if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)) rec.join_state = SENDONLY_FULLMEMBER_JOIN; } spin_unlock_irq(&priv->lock); diff --git a/include/rdma/ib_sa.h b/include/rdma/ib_sa.h index 693285e76f13..4c52c2fd22a1 100644 --- a/include/rdma/ib_sa.h +++ b/include/rdma/ib_sa.h @@ -547,10 +547,6 @@ int ib_sa_guid_info_rec_query(struct ib_sa_client *client, void *context), void *context, struct ib_sa_query **sa_query); -bool ib_sa_sendonly_fullmem_support(struct ib_sa_client *client, - struct ib_device *device, - u8 port_num); - static inline bool sa_path_is_roce(struct sa_path_rec *rec) { return ((rec->rec_type == SA_PATH_REC_TYPE_ROCE_V1) || -- cgit v1.2.3 From 7232c132d13aafd178ba18c1099b2cb98d104b8c Mon Sep 17 00:00:00 2001 From: Tal Gilboa Date: Thu, 11 Feb 2021 10:55:49 +0200 Subject: RDMA/mlx5: Allow CQ creation without attached EQs The traditional DevX CQ creation flow goes through mlx5_core_create_cq() which checks that the given EQN corresponds to an existing EQ and attaches a devx handler to the EQN for the CQ. In some cases the EQ will not be a kernel EQ, but will be controlled by modify CQ, don't block creating these just because the EQN can't be found in the kernel. Link: https://lore.kernel.org/r/20210211085549.1277674-1-leon@kernel.org Signed-off-by: Tal Gilboa Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/mlx5/devx.c | 13 ++++++++++++- include/linux/mlx5/mlx5_ifc.h | 5 +++-- 2 files changed, 15 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c index e39661db0d2f..ebc2a4355fa5 100644 --- a/drivers/infiniband/hw/mlx5/devx.c +++ b/drivers/infiniband/hw/mlx5/devx.c @@ -1439,6 +1439,16 @@ out: rcu_read_unlock(); } +static bool is_apu_thread_cq(struct mlx5_ib_dev *dev, const void *in) +{ + if (!MLX5_CAP_GEN(dev->mdev, apu) || + !MLX5_GET(cqc, MLX5_ADDR_OF(create_cq_in, in, cq_context), + apu_thread_cq)) + return false; + + return true; +} + static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_OBJ_CREATE)( struct uverbs_attr_bundle *attrs) { @@ -1492,7 +1502,8 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_OBJ_CREATE)( obj->flags |= DEVX_OBJ_FLAGS_DCT; err = mlx5_core_create_dct(dev, &obj->core_dct, cmd_in, cmd_in_len, cmd_out, cmd_out_len); - } else if (opcode == MLX5_CMD_OP_CREATE_CQ) { + } else if (opcode == MLX5_CMD_OP_CREATE_CQ && + !is_apu_thread_cq(dev, cmd_in)) { obj->flags |= DEVX_OBJ_FLAGS_CQ; obj->core_cq.comp = devx_cq_comp; err = mlx5_core_create_cq(dev->mdev, &obj->core_cq, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index cf692fc17f41..768e097c633b 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1634,7 +1634,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 sf_set_partition[0x1]; u8 reserved_at_682[0x1]; u8 log_max_sf[0x5]; - u8 reserved_at_688[0x8]; + u8 apu[0x1]; + u8 reserved_at_689[0x7]; u8 log_min_sf_size[0x8]; u8 max_num_sf_partitions[0x8]; @@ -3816,7 +3817,7 @@ struct mlx5_ifc_cqc_bits { u8 status[0x4]; u8 reserved_at_4[0x2]; u8 dbr_umem_valid[0x1]; - u8 reserved_at_7[0x1]; + u8 apu_thread_cq[0x1]; u8 cqe_sz[0x3]; u8 cc[0x1]; u8 reserved_at_c[0x1]; -- cgit v1.2.3 From 75cfb200cd081d23eb7eaa68deba9e0ab9320070 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 12 Feb 2021 16:49:47 -0500 Subject: NFS: 'flags' field should be unsigned in struct nfs_server The mount flags are all unsigned integers, so we should not be storing them in a signed field. Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- include/linux/nfs_fs_sb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 38e60ec742df..962e8313f007 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -142,7 +142,7 @@ struct nfs_server { struct nlm_host *nlm_host; /* NLM client handle */ struct nfs_iostats __percpu *io_stats; /* I/O statistics */ atomic_long_t writeback; /* number of writeback pages */ - int flags; /* various flags */ + unsigned int flags; /* various flags */ /* The following are for internal use only. Also see uapi/linux/nfs_mount.h */ #define NFS_MOUNT_LOOKUP_CACHE_NONEG 0x10000 -- cgit v1.2.3 From ed7bcdb374d20fab9e9dc36853a6735c047ad1b1 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 12 Feb 2021 16:49:48 -0500 Subject: NFS: Add support for eager writes Support eager writing to the server, meaning that we write the data to cache on the server, and wait for that to complete. This ensures that we see ENOSPC errors immediately. Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- fs/nfs/file.c | 19 +++++++++++++++++-- fs/nfs/write.c | 17 ++++++++++++----- include/linux/nfs_fs_sb.h | 2 ++ 3 files changed, 31 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 03fd1dcc96bd..16ad5050e046 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -606,8 +606,8 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); - unsigned long written = 0; - ssize_t result; + unsigned int mntflags = NFS_SERVER(inode)->flags; + ssize_t result, written; errseq_t since; int error; @@ -648,6 +648,21 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from) written = result; iocb->ki_pos += written; + + if (mntflags & NFS_MOUNT_WRITE_EAGER) { + result = filemap_fdatawrite_range(file->f_mapping, + iocb->ki_pos - written, + iocb->ki_pos - 1); + if (result < 0) + goto out; + } + if (mntflags & NFS_MOUNT_WRITE_WAIT) { + result = filemap_fdatawait_range(file->f_mapping, + iocb->ki_pos - written, + iocb->ki_pos - 1); + if (result < 0) + goto out; + } result = generic_write_sync(iocb, written); if (result < 0) goto out; diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 6193350356a8..82bdcb982186 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -712,16 +712,23 @@ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc) { struct inode *inode = mapping->host; struct nfs_pageio_descriptor pgio; - struct nfs_io_completion *ioc; + struct nfs_io_completion *ioc = NULL; + unsigned int mntflags = NFS_SERVER(inode)->flags; + int priority = 0; int err; nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGES); - ioc = nfs_io_completion_alloc(GFP_KERNEL); - if (ioc) - nfs_io_completion_init(ioc, nfs_io_completion_commit, inode); + if (!(mntflags & NFS_MOUNT_WRITE_EAGER) || wbc->for_kupdate || + wbc->for_background || wbc->for_sync || wbc->for_reclaim) { + ioc = nfs_io_completion_alloc(GFP_KERNEL); + if (ioc) + nfs_io_completion_init(ioc, nfs_io_completion_commit, + inode); + priority = wb_priority(wbc); + } - nfs_pageio_init_write(&pgio, inode, wb_priority(wbc), false, + nfs_pageio_init_write(&pgio, inode, priority, false, &nfs_async_write_completion_ops); pgio.pg_io_completion = ioc; err = write_cache_pages(mapping, wbc, nfs_writepages_callback, &pgio); diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 962e8313f007..6f76b32a0238 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -153,6 +153,8 @@ struct nfs_server { #define NFS_MOUNT_LOCAL_FCNTL 0x200000 #define NFS_MOUNT_SOFTERR 0x400000 #define NFS_MOUNT_SOFTREVAL 0x800000 +#define NFS_MOUNT_WRITE_EAGER 0x01000000 +#define NFS_MOUNT_WRITE_WAIT 0x02000000 unsigned int caps; /* server capabilities */ unsigned int rsize; /* read size */ -- cgit v1.2.3 From 1f975074634a63f014e2b7e76852ee6d6005a91d Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Fri, 12 Feb 2021 18:10:43 +0100 Subject: libnvdimm: Make remove callback return void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit All drivers return 0 in their remove callback and the driver core ignores the return value of nvdimm_bus_remove() anyhow. So simplify by changing the driver remove callback to return void and return 0 unconditionally to the upper layer. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20210212171043.2136580-2-u.kleine-koenig@pengutronix.de Signed-off-by: Dan Williams --- drivers/dax/pmem/compat.c | 3 +-- drivers/nvdimm/blk.c | 3 +-- drivers/nvdimm/bus.c | 13 +++++-------- drivers/nvdimm/dimm.c | 4 +--- drivers/nvdimm/pmem.c | 4 +--- drivers/nvdimm/region.c | 4 +--- include/linux/nd.h | 2 +- 7 files changed, 11 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/drivers/dax/pmem/compat.c b/drivers/dax/pmem/compat.c index 863c114fd88c..d81dc35fd65d 100644 --- a/drivers/dax/pmem/compat.c +++ b/drivers/dax/pmem/compat.c @@ -41,10 +41,9 @@ static int dax_pmem_compat_release(struct device *dev, void *data) return 0; } -static int dax_pmem_compat_remove(struct device *dev) +static void dax_pmem_compat_remove(struct device *dev) { device_for_each_child(dev, NULL, dax_pmem_compat_release); - return 0; } static struct nd_device_driver dax_pmem_compat_driver = { diff --git a/drivers/nvdimm/blk.c b/drivers/nvdimm/blk.c index 22e5617b2cea..8a53728e13e6 100644 --- a/drivers/nvdimm/blk.c +++ b/drivers/nvdimm/blk.c @@ -310,11 +310,10 @@ static int nd_blk_probe(struct device *dev) return nsblk_attach_disk(nsblk); } -static int nd_blk_remove(struct device *dev) +static void nd_blk_remove(struct device *dev) { if (is_nd_btt(dev)) nvdimm_namespace_detach_btt(to_nd_btt(dev)); - return 0; } static struct nd_device_driver nd_blk_driver = { diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index 2304c6183822..48f0985ca8a0 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -113,18 +113,17 @@ static int nvdimm_bus_remove(struct device *dev) struct nd_device_driver *nd_drv = to_nd_device_driver(dev->driver); struct module *provider = to_bus_provider(dev); struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev); - int rc = 0; if (nd_drv->remove) { debug_nvdimm_lock(dev); - rc = nd_drv->remove(dev); + nd_drv->remove(dev); debug_nvdimm_unlock(dev); } - dev_dbg(&nvdimm_bus->dev, "%s.remove(%s) = %d\n", dev->driver->name, - dev_name(dev), rc); + dev_dbg(&nvdimm_bus->dev, "%s.remove(%s)\n", dev->driver->name, + dev_name(dev)); module_put(provider); - return rc; + return 0; } static void nvdimm_bus_shutdown(struct device *dev) @@ -427,7 +426,7 @@ static void free_badrange_list(struct list_head *badrange_list) list_del_init(badrange_list); } -static int nd_bus_remove(struct device *dev) +static void nd_bus_remove(struct device *dev) { struct nvdimm_bus *nvdimm_bus = to_nvdimm_bus(dev); @@ -446,8 +445,6 @@ static int nd_bus_remove(struct device *dev) spin_unlock(&nvdimm_bus->badrange.lock); nvdimm_bus_destroy_ndctl(nvdimm_bus); - - return 0; } static int nd_bus_probe(struct device *dev) diff --git a/drivers/nvdimm/dimm.c b/drivers/nvdimm/dimm.c index 94be3ae1d29f..91d9163ee303 100644 --- a/drivers/nvdimm/dimm.c +++ b/drivers/nvdimm/dimm.c @@ -113,7 +113,7 @@ static int nvdimm_probe(struct device *dev) return rc; } -static int nvdimm_remove(struct device *dev) +static void nvdimm_remove(struct device *dev) { struct nvdimm_drvdata *ndd = dev_get_drvdata(dev); @@ -121,8 +121,6 @@ static int nvdimm_remove(struct device *dev) dev_set_drvdata(dev, NULL); nvdimm_bus_unlock(dev); put_ndd(ndd); - - return 0; } static struct nd_device_driver nvdimm_driver = { diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 875076b0ea6c..062f0f22bac9 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -564,7 +564,7 @@ static int nd_pmem_probe(struct device *dev) return pmem_attach_disk(dev, ndns); } -static int nd_pmem_remove(struct device *dev) +static void nd_pmem_remove(struct device *dev) { struct pmem_device *pmem = dev_get_drvdata(dev); @@ -579,8 +579,6 @@ static int nd_pmem_remove(struct device *dev) pmem->bb_state = NULL; } nvdimm_flush(to_nd_region(dev->parent), NULL); - - return 0; } static void nd_pmem_shutdown(struct device *dev) diff --git a/drivers/nvdimm/region.c b/drivers/nvdimm/region.c index bfce87ed72ab..e0c34120df37 100644 --- a/drivers/nvdimm/region.c +++ b/drivers/nvdimm/region.c @@ -87,7 +87,7 @@ static int child_unregister(struct device *dev, void *data) return 0; } -static int nd_region_remove(struct device *dev) +static void nd_region_remove(struct device *dev) { struct nd_region *nd_region = to_nd_region(dev); @@ -108,8 +108,6 @@ static int nd_region_remove(struct device *dev) */ sysfs_put(nd_region->bb_state); nd_region->bb_state = NULL; - - return 0; } static int child_notify(struct device *dev, void *data) diff --git a/include/linux/nd.h b/include/linux/nd.h index 55c735997805..cec526c8043d 100644 --- a/include/linux/nd.h +++ b/include/linux/nd.h @@ -26,7 +26,7 @@ struct nd_device_driver { struct device_driver drv; unsigned long type; int (*probe)(struct device *dev); - int (*remove)(struct device *dev); + void (*remove)(struct device *dev); void (*shutdown)(struct device *dev); void (*notify)(struct device *dev, enum nvdimm_event event); }; -- cgit v1.2.3 From 4cdadfd5e0a70017fec735b7b6d7f2f731842dc6 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 16 Feb 2021 20:09:50 -0800 Subject: cxl/mem: Introduce a driver for CXL-2.0-Type-3 endpoints The CXL.mem protocol allows a device to act as a provider of "System RAM" and/or "Persistent Memory" that is fully coherent as if the memory was attached to the typical CPU memory controller. With the CXL-2.0 specification a PCI endpoint can implement a "Type-3" device interface and give the operating system control over "Host Managed Device Memory". See section 2.3 Type 3 CXL Device. The memory range exported by the device may optionally be described by the platform firmware memory map, or by infrastructure like LIBNVDIMM to provision persistent memory capacity from one, or more, CXL.mem devices. A pre-requisite for Linux-managed memory-capacity provisioning is this cxl_mem driver that can speak the mailbox protocol defined in section 8.2.8.4 Mailbox Registers. For now just land the initial driver boiler-plate and Documentation/ infrastructure. Signed-off-by: Ben Widawsky Reviewed-by: Jonathan Cameron Acked-by: David Rientjes (v1) Cc: Jonathan Corbet Link: https://www.computeexpresslink.org/download-the-specification Link: https://lore.kernel.org/r/20210217040958.1354670-2-ben.widawsky@intel.com Signed-off-by: Dan Williams --- Documentation/driver-api/cxl/index.rst | 12 +++++ Documentation/driver-api/cxl/memory-devices.rst | 15 ++++++ Documentation/driver-api/index.rst | 1 + drivers/Kconfig | 1 + drivers/Makefile | 1 + drivers/cxl/Kconfig | 35 ++++++++++++++ drivers/cxl/Makefile | 4 ++ drivers/cxl/mem.c | 62 +++++++++++++++++++++++++ drivers/cxl/pci.h | 17 +++++++ include/linux/pci_ids.h | 1 + 10 files changed, 149 insertions(+) create mode 100644 Documentation/driver-api/cxl/index.rst create mode 100644 Documentation/driver-api/cxl/memory-devices.rst create mode 100644 drivers/cxl/Kconfig create mode 100644 drivers/cxl/Makefile create mode 100644 drivers/cxl/mem.c create mode 100644 drivers/cxl/pci.h (limited to 'include') diff --git a/Documentation/driver-api/cxl/index.rst b/Documentation/driver-api/cxl/index.rst new file mode 100644 index 000000000000..036e49553542 --- /dev/null +++ b/Documentation/driver-api/cxl/index.rst @@ -0,0 +1,12 @@ +.. SPDX-License-Identifier: GPL-2.0 + +==================== +Compute Express Link +==================== + +.. toctree:: + :maxdepth: 1 + + memory-devices + +.. only:: subproject and html diff --git a/Documentation/driver-api/cxl/memory-devices.rst b/Documentation/driver-api/cxl/memory-devices.rst new file mode 100644 index 000000000000..71617e9002f1 --- /dev/null +++ b/Documentation/driver-api/cxl/memory-devices.rst @@ -0,0 +1,15 @@ +.. SPDX-License-Identifier: GPL-2.0 +.. include:: + +=================================== +Compute Express Link Memory Devices +=================================== + +A Compute Express Link Memory Device is a CXL component that implements the +CXL.mem protocol. It contains some amount of volatile memory, persistent memory, +or both. It is enumerated as a PCI device for configuration and passing +messages over an MMIO mailbox. Its contribution to the System Physical +Address space is handled via HDM (Host Managed Device Memory) decoders +that optionally define a device's contribution to an interleaved address +range across multiple devices underneath a host-bridge or interleaved +across host-bridges. diff --git a/Documentation/driver-api/index.rst b/Documentation/driver-api/index.rst index 2456d0a97ed8..d246a18fd78f 100644 --- a/Documentation/driver-api/index.rst +++ b/Documentation/driver-api/index.rst @@ -35,6 +35,7 @@ available subsections can be seen below. usb/index firewire pci/index + cxl/index spi i2c ipmb diff --git a/drivers/Kconfig b/drivers/Kconfig index dcecc9f6e33f..62c753a73651 100644 --- a/drivers/Kconfig +++ b/drivers/Kconfig @@ -6,6 +6,7 @@ menu "Device Drivers" source "drivers/amba/Kconfig" source "drivers/eisa/Kconfig" source "drivers/pci/Kconfig" +source "drivers/cxl/Kconfig" source "drivers/pcmcia/Kconfig" source "drivers/rapidio/Kconfig" diff --git a/drivers/Makefile b/drivers/Makefile index fd11b9ac4cc3..678ea810410f 100644 --- a/drivers/Makefile +++ b/drivers/Makefile @@ -73,6 +73,7 @@ obj-$(CONFIG_NVM) += lightnvm/ obj-y += base/ block/ misc/ mfd/ nfc/ obj-$(CONFIG_LIBNVDIMM) += nvdimm/ obj-$(CONFIG_DAX) += dax/ +obj-$(CONFIG_CXL_BUS) += cxl/ obj-$(CONFIG_DMA_SHARED_BUFFER) += dma-buf/ obj-$(CONFIG_NUBUS) += nubus/ obj-y += macintosh/ diff --git a/drivers/cxl/Kconfig b/drivers/cxl/Kconfig new file mode 100644 index 000000000000..9e80b311e928 --- /dev/null +++ b/drivers/cxl/Kconfig @@ -0,0 +1,35 @@ +# SPDX-License-Identifier: GPL-2.0-only +menuconfig CXL_BUS + tristate "CXL (Compute Express Link) Devices Support" + depends on PCI + help + CXL is a bus that is electrically compatible with PCI Express, but + layers three protocols on that signalling (CXL.io, CXL.cache, and + CXL.mem). The CXL.cache protocol allows devices to hold cachelines + locally, the CXL.mem protocol allows devices to be fully coherent + memory targets, the CXL.io protocol is equivalent to PCI Express. + Say 'y' to enable support for the configuration and management of + devices supporting these protocols. + +if CXL_BUS + +config CXL_MEM + tristate "CXL.mem: Memory Devices" + help + The CXL.mem protocol allows a device to act as a provider of + "System RAM" and/or "Persistent Memory" that is fully coherent + as if the memory was attached to the typical CPU memory + controller. + + Say 'y/m' to enable a driver (named "cxl_mem.ko" when built as + a module) that will attach to CXL.mem devices for + configuration, provisioning, and health monitoring. This + driver is required for dynamic provisioning of CXL.mem + attached memory which is a prerequisite for persistent memory + support. Typically volatile memory is mapped by platform + firmware and included in the platform memory map, but in some + cases the OS is responsible for mapping that memory. See + Chapter 2.3 Type 3 CXL Device in the CXL 2.0 specification. + + If unsure say 'm'. +endif diff --git a/drivers/cxl/Makefile b/drivers/cxl/Makefile new file mode 100644 index 000000000000..4a30f7c3fc4a --- /dev/null +++ b/drivers/cxl/Makefile @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_CXL_MEM) += cxl_mem.o + +cxl_mem-y := mem.o diff --git a/drivers/cxl/mem.c b/drivers/cxl/mem.c new file mode 100644 index 000000000000..ce33c5ee77c9 --- /dev/null +++ b/drivers/cxl/mem.c @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright(c) 2020 Intel Corporation. All rights reserved. */ +#include +#include +#include +#include "pci.h" + +static int cxl_mem_dvsec(struct pci_dev *pdev, int dvsec) +{ + int pos; + + pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_DVSEC); + if (!pos) + return 0; + + while (pos) { + u16 vendor, id; + + pci_read_config_word(pdev, pos + PCI_DVSEC_HEADER1, &vendor); + pci_read_config_word(pdev, pos + PCI_DVSEC_HEADER2, &id); + if (vendor == PCI_DVSEC_VENDOR_ID_CXL && dvsec == id) + return pos; + + pos = pci_find_next_ext_capability(pdev, pos, + PCI_EXT_CAP_ID_DVSEC); + } + + return 0; +} + +static int cxl_mem_probe(struct pci_dev *pdev, const struct pci_device_id *id) +{ + struct device *dev = &pdev->dev; + int regloc; + + regloc = cxl_mem_dvsec(pdev, PCI_DVSEC_ID_CXL_REGLOC_OFFSET); + if (!regloc) { + dev_err(dev, "register location dvsec not found\n"); + return -ENXIO; + } + + return 0; +} + +static const struct pci_device_id cxl_mem_pci_tbl[] = { + /* PCI class code for CXL.mem Type-3 Devices */ + { PCI_DEVICE_CLASS((PCI_CLASS_MEMORY_CXL << 8 | CXL_MEMORY_PROGIF), ~0)}, + { /* terminate list */ }, +}; +MODULE_DEVICE_TABLE(pci, cxl_mem_pci_tbl); + +static struct pci_driver cxl_mem_driver = { + .name = KBUILD_MODNAME, + .id_table = cxl_mem_pci_tbl, + .probe = cxl_mem_probe, + .driver = { + .probe_type = PROBE_PREFER_ASYNCHRONOUS, + }, +}; + +MODULE_LICENSE("GPL v2"); +module_pci_driver(cxl_mem_driver); diff --git a/drivers/cxl/pci.h b/drivers/cxl/pci.h new file mode 100644 index 000000000000..e464bea3f4d3 --- /dev/null +++ b/drivers/cxl/pci.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright(c) 2020 Intel Corporation. All rights reserved. */ +#ifndef __CXL_PCI_H__ +#define __CXL_PCI_H__ + +#define CXL_MEMORY_PROGIF 0x10 + +/* + * See section 8.1 Configuration Space Registers in the CXL 2.0 + * Specification + */ +#define PCI_DVSEC_VENDOR_ID_CXL 0x1E98 +#define PCI_DVSEC_ID_CXL 0x0 + +#define PCI_DVSEC_ID_CXL_REGLOC_OFFSET 0x8 + +#endif /* __CXL_PCI_H__ */ diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index d8156a5dbee8..766260a9b247 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -51,6 +51,7 @@ #define PCI_BASE_CLASS_MEMORY 0x05 #define PCI_CLASS_MEMORY_RAM 0x0500 #define PCI_CLASS_MEMORY_FLASH 0x0501 +#define PCI_CLASS_MEMORY_CXL 0x0502 #define PCI_CLASS_MEMORY_OTHER 0x0580 #define PCI_BASE_CLASS_BRIDGE 0x06 -- cgit v1.2.3 From 583fa5e71caeb79e04e477e9837e2f7fa53b71e4 Mon Sep 17 00:00:00 2001 From: Ben Widawsky Date: Tue, 16 Feb 2021 20:09:53 -0800 Subject: cxl/mem: Add basic IOCTL interface Add a straightforward IOCTL that provides a mechanism for userspace to query the supported memory device commands. CXL commands as they appear to userspace are described as part of the UAPI kerneldoc. The command list returned via this IOCTL will contain the full set of commands that the driver supports, however, some of those commands may not be available for use by userspace. Memory device commands first appear in the CXL 2.0 specification. They are submitted through a mailbox mechanism specified in the CXL 2.0 specification. The send command allows userspace to issue mailbox commands directly to the hardware. The list of available commands to send are the output of the query command. The driver verifies basic properties of the command and possibly inspect the input (or output) payload to determine whether or not the command is allowed (or might taint the kernel). Reported-by: kernel test robot # bug in earlier revision Reported-by: Stephen Rothwell Signed-off-by: Ben Widawsky Reviewed-by: Dan Williams (v2) Cc: Al Viro Link: https://lore.kernel.org/r/20210217040958.1354670-5-ben.widawsky@intel.com Signed-off-by: Dan Williams --- .clang-format | 1 + Documentation/driver-api/cxl/memory-devices.rst | 12 + Documentation/userspace-api/ioctl/ioctl-number.rst | 1 + drivers/cxl/mem.c | 283 ++++++++++++++++++++- include/uapi/linux/cxl_mem.h | 156 ++++++++++++ 5 files changed, 452 insertions(+), 1 deletion(-) create mode 100644 include/uapi/linux/cxl_mem.h (limited to 'include') diff --git a/.clang-format b/.clang-format index 10dc5a9a61b3..3f11c8901b43 100644 --- a/.clang-format +++ b/.clang-format @@ -109,6 +109,7 @@ ForEachMacros: - 'css_for_each_child' - 'css_for_each_descendant_post' - 'css_for_each_descendant_pre' + - 'cxl_for_each_cmd' - 'device_for_each_child_node' - 'dma_fence_chain_for_each' - 'do_for_each_ftrace_op' diff --git a/Documentation/driver-api/cxl/memory-devices.rst b/Documentation/driver-api/cxl/memory-devices.rst index 1fef2c0a167d..1bad466f9167 100644 --- a/Documentation/driver-api/cxl/memory-devices.rst +++ b/Documentation/driver-api/cxl/memory-devices.rst @@ -32,3 +32,15 @@ CXL Bus ------- .. kernel-doc:: drivers/cxl/bus.c :doc: cxl bus + +External Interfaces +=================== + +CXL IOCTL Interface +------------------- + +.. kernel-doc:: include/uapi/linux/cxl_mem.h + :doc: UAPI + +.. kernel-doc:: include/uapi/linux/cxl_mem.h + :internal: diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst index a4c75a28c839..6eb8e634664d 100644 --- a/Documentation/userspace-api/ioctl/ioctl-number.rst +++ b/Documentation/userspace-api/ioctl/ioctl-number.rst @@ -352,6 +352,7 @@ Code Seq# Include File Comments 0xCC 00-0F drivers/misc/ibmvmc.h pseries VMC driver 0xCD 01 linux/reiserfs_fs.h +0xCE 01-02 uapi/linux/cxl_mem.h Compute Express Link Memory Devices 0xCF 02 fs/cifs/ioctl.c 0xDB 00-0F drivers/char/mwave/mwavepub.h 0xDD 00-3F ZFCP device driver see drivers/s390/scsi/ diff --git a/drivers/cxl/mem.c b/drivers/cxl/mem.c index 1c0195b07063..aa8f843fcca1 100644 --- a/drivers/cxl/mem.c +++ b/drivers/cxl/mem.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* Copyright(c) 2020 Intel Corporation. All rights reserved. */ +#include #include #include #include @@ -40,6 +41,7 @@ #define CXL_MAILBOX_TIMEOUT_MS (2 * HZ) enum opcode { + CXL_MBOX_OP_INVALID = 0x0000, CXL_MBOX_OP_IDENTIFY = 0x4000, CXL_MBOX_OP_MAX = 0x10000 }; @@ -95,6 +97,49 @@ struct cxl_memdev { static int cxl_mem_major; static DEFINE_IDA(cxl_memdev_ida); +/** + * struct cxl_mem_command - Driver representation of a memory device command + * @info: Command information as it exists for the UAPI + * @opcode: The actual bits used for the mailbox protocol + * + * The cxl_mem_command is the driver's internal representation of commands that + * are supported by the driver. Some of these commands may not be supported by + * the hardware. The driver will use @info to validate the fields passed in by + * the user then submit the @opcode to the hardware. + * + * See struct cxl_command_info. + */ +struct cxl_mem_command { + struct cxl_command_info info; + enum opcode opcode; +}; + +#define CXL_CMD(_id, sin, sout) \ + [CXL_MEM_COMMAND_ID_##_id] = { \ + .info = { \ + .id = CXL_MEM_COMMAND_ID_##_id, \ + .size_in = sin, \ + .size_out = sout, \ + }, \ + .opcode = CXL_MBOX_OP_##_id, \ + } + +/* + * This table defines the supported mailbox commands for the driver. This table + * is made up of a UAPI structure. Non-negative values as parameters in the + * table will be validated against the user's input. For example, if size_in is + * 0, and the user passed in 1, it is an error. + */ +static struct cxl_mem_command mem_commands[] = { + CXL_CMD(IDENTIFY, 0, 0x43), +}; + +#define cxl_for_each_cmd(cmd) \ + for ((cmd) = &mem_commands[0]; \ + ((cmd) - mem_commands) < ARRAY_SIZE(mem_commands); (cmd)++) + +#define cxl_cmd_count ARRAY_SIZE(mem_commands) + static int cxl_mem_wait_for_doorbell(struct cxl_mem *cxlm) { const unsigned long start = jiffies; @@ -324,6 +369,242 @@ static void cxl_mem_mbox_put(struct cxl_mem *cxlm) mutex_unlock(&cxlm->mbox_mutex); } +/** + * handle_mailbox_cmd_from_user() - Dispatch a mailbox command for userspace. + * @cxlm: The CXL memory device to communicate with. + * @cmd: The validated command. + * @in_payload: Pointer to userspace's input payload. + * @out_payload: Pointer to userspace's output payload. + * @size_out: (Input) Max payload size to copy out. + * (Output) Payload size hardware generated. + * @retval: Hardware generated return code from the operation. + * + * Return: + * * %0 - Mailbox transaction succeeded. This implies the mailbox + * protocol completed successfully not that the operation itself + * was successful. + * * %-ENOMEM - Couldn't allocate a bounce buffer. + * * %-EFAULT - Something happened with copy_to/from_user. + * * %-EINTR - Mailbox acquisition interrupted. + * * %-EXXX - Transaction level failures. + * + * Creates the appropriate mailbox command and dispatches it on behalf of a + * userspace request. The input and output payloads are copied between + * userspace. + * + * See cxl_send_cmd(). + */ +static int handle_mailbox_cmd_from_user(struct cxl_mem *cxlm, + const struct cxl_mem_command *cmd, + u64 in_payload, u64 out_payload, + s32 *size_out, u32 *retval) +{ + struct device *dev = &cxlm->pdev->dev; + struct mbox_cmd mbox_cmd = { + .opcode = cmd->opcode, + .size_in = cmd->info.size_in, + .size_out = cmd->info.size_out, + }; + int rc; + + if (cmd->info.size_out) { + mbox_cmd.payload_out = kvzalloc(cmd->info.size_out, GFP_KERNEL); + if (!mbox_cmd.payload_out) + return -ENOMEM; + } + + if (cmd->info.size_in) { + mbox_cmd.payload_in = vmemdup_user(u64_to_user_ptr(in_payload), + cmd->info.size_in); + if (IS_ERR(mbox_cmd.payload_in)) + return PTR_ERR(mbox_cmd.payload_in); + } + + rc = cxl_mem_mbox_get(cxlm); + if (rc) + goto out; + + dev_dbg(dev, + "Submitting %s command for user\n" + "\topcode: %x\n" + "\tsize: %ub\n", + cxl_command_names[cmd->info.id].name, mbox_cmd.opcode, + cmd->info.size_in); + + rc = __cxl_mem_mbox_send_cmd(cxlm, &mbox_cmd); + cxl_mem_mbox_put(cxlm); + if (rc) + goto out; + + /* + * @size_out contains the max size that's allowed to be written back out + * to userspace. While the payload may have written more output than + * this it will have to be ignored. + */ + if (mbox_cmd.size_out) { + dev_WARN_ONCE(dev, mbox_cmd.size_out > *size_out, + "Invalid return size\n"); + if (copy_to_user(u64_to_user_ptr(out_payload), + mbox_cmd.payload_out, mbox_cmd.size_out)) { + rc = -EFAULT; + goto out; + } + } + + *size_out = mbox_cmd.size_out; + *retval = mbox_cmd.return_code; + +out: + kvfree(mbox_cmd.payload_in); + kvfree(mbox_cmd.payload_out); + return rc; +} + +/** + * cxl_validate_cmd_from_user() - Check fields for CXL_MEM_SEND_COMMAND. + * @cxlm: &struct cxl_mem device whose mailbox will be used. + * @send_cmd: &struct cxl_send_command copied in from userspace. + * @out_cmd: Sanitized and populated &struct cxl_mem_command. + * + * Return: + * * %0 - @out_cmd is ready to send. + * * %-ENOTTY - Invalid command specified. + * * %-EINVAL - Reserved fields or invalid values were used. + * * %-ENOMEM - Input or output buffer wasn't sized properly. + * + * The result of this command is a fully validated command in @out_cmd that is + * safe to send to the hardware. + * + * See handle_mailbox_cmd_from_user() + */ +static int cxl_validate_cmd_from_user(struct cxl_mem *cxlm, + const struct cxl_send_command *send_cmd, + struct cxl_mem_command *out_cmd) +{ + const struct cxl_command_info *info; + struct cxl_mem_command *c; + + if (send_cmd->id == 0 || send_cmd->id >= CXL_MEM_COMMAND_ID_MAX) + return -ENOTTY; + + /* + * The user can never specify an input payload larger than what hardware + * supports, but output can be arbitrarily large (simply write out as + * much data as the hardware provides). + */ + if (send_cmd->in.size > cxlm->payload_size) + return -EINVAL; + + if (send_cmd->flags & ~CXL_MEM_COMMAND_FLAG_MASK) + return -EINVAL; + + if (send_cmd->rsvd) + return -EINVAL; + + if (send_cmd->in.rsvd || send_cmd->out.rsvd) + return -EINVAL; + + /* Convert user's command into the internal representation */ + c = &mem_commands[send_cmd->id]; + info = &c->info; + + /* Check the input buffer is the expected size */ + if (info->size_in >= 0 && info->size_in != send_cmd->in.size) + return -ENOMEM; + + /* Check the output buffer is at least large enough */ + if (info->size_out >= 0 && send_cmd->out.size < info->size_out) + return -ENOMEM; + + memcpy(out_cmd, c, sizeof(*c)); + out_cmd->info.size_in = send_cmd->in.size; + /* + * XXX: out_cmd->info.size_out will be controlled by the driver, and the + * specified number of bytes @send_cmd->out.size will be copied back out + * to userspace. + */ + + return 0; +} + +static int cxl_query_cmd(struct cxl_memdev *cxlmd, + struct cxl_mem_query_commands __user *q) +{ + struct device *dev = &cxlmd->dev; + struct cxl_mem_command *cmd; + u32 n_commands; + int j = 0; + + dev_dbg(dev, "Query IOCTL\n"); + + if (get_user(n_commands, &q->n_commands)) + return -EFAULT; + + /* returns the total number if 0 elements are requested. */ + if (n_commands == 0) + return put_user(cxl_cmd_count, &q->n_commands); + + /* + * otherwise, return max(n_commands, total commands) cxl_command_info + * structures. + */ + cxl_for_each_cmd(cmd) { + const struct cxl_command_info *info = &cmd->info; + + if (copy_to_user(&q->commands[j++], info, sizeof(*info))) + return -EFAULT; + + if (j == n_commands) + break; + } + + return 0; +} + +static int cxl_send_cmd(struct cxl_memdev *cxlmd, + struct cxl_send_command __user *s) +{ + struct cxl_mem *cxlm = cxlmd->cxlm; + struct device *dev = &cxlmd->dev; + struct cxl_send_command send; + struct cxl_mem_command c; + int rc; + + dev_dbg(dev, "Send IOCTL\n"); + + if (copy_from_user(&send, s, sizeof(send))) + return -EFAULT; + + rc = cxl_validate_cmd_from_user(cxlmd->cxlm, &send, &c); + if (rc) + return rc; + + /* Prepare to handle a full payload for variable sized output */ + if (c.info.size_out < 0) + c.info.size_out = cxlm->payload_size; + + rc = handle_mailbox_cmd_from_user(cxlm, &c, send.in.payload, + send.out.payload, &send.out.size, + &send.retval); + if (rc) + return rc; + + return copy_to_user(s, &send, sizeof(send)); +} + +static long __cxl_memdev_ioctl(struct cxl_memdev *cxlmd, unsigned int cmd, + unsigned long arg) +{ + switch (cmd) { + case CXL_MEM_QUERY_COMMANDS: + return cxl_query_cmd(cxlmd, (void __user *)arg); + case CXL_MEM_SEND_COMMAND: + return cxl_send_cmd(cxlmd, (void __user *)arg); + default: + return -ENOTTY; + } +} + static long cxl_memdev_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { @@ -337,7 +618,7 @@ static long cxl_memdev_ioctl(struct file *file, unsigned int cmd, if (!percpu_ref_tryget_live(&cxlmd->ops_active)) return -ENXIO; - /* TODO: ioctl body */ + rc = __cxl_memdev_ioctl(cxlmd, cmd, arg); percpu_ref_put(&cxlmd->ops_active); diff --git a/include/uapi/linux/cxl_mem.h b/include/uapi/linux/cxl_mem.h new file mode 100644 index 000000000000..887781dc3b6c --- /dev/null +++ b/include/uapi/linux/cxl_mem.h @@ -0,0 +1,156 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * CXL IOCTLs for Memory Devices + */ + +#ifndef _UAPI_CXL_MEM_H_ +#define _UAPI_CXL_MEM_H_ + +#include + +/** + * DOC: UAPI + * + * Not all of all commands that the driver supports are always available for use + * by userspace. Userspace must check the results from the QUERY command in + * order to determine the live set of commands. + */ + +#define CXL_MEM_QUERY_COMMANDS _IOR(0xCE, 1, struct cxl_mem_query_commands) +#define CXL_MEM_SEND_COMMAND _IOWR(0xCE, 2, struct cxl_send_command) + +#define CXL_CMDS \ + ___C(INVALID, "Invalid Command"), \ + ___C(IDENTIFY, "Identify Command"), \ + ___C(MAX, "invalid / last command") + +#define ___C(a, b) CXL_MEM_COMMAND_ID_##a +enum { CXL_CMDS }; + +#undef ___C +#define ___C(a, b) { b } +static const struct { + const char *name; +} cxl_command_names[] = { CXL_CMDS }; + +/* + * Here's how this actually breaks out: + * cxl_command_names[] = { + * [CXL_MEM_COMMAND_ID_INVALID] = { "Invalid Command" }, + * [CXL_MEM_COMMAND_ID_IDENTIFY] = { "Identify Command" }, + * ... + * [CXL_MEM_COMMAND_ID_MAX] = { "invalid / last command" }, + * }; + */ + +#undef ___C + +/** + * struct cxl_command_info - Command information returned from a query. + * @id: ID number for the command. + * @flags: Flags that specify command behavior. + * @size_in: Expected input size, or -1 if variable length. + * @size_out: Expected output size, or -1 if variable length. + * + * Represents a single command that is supported by both the driver and the + * hardware. This is returned as part of an array from the query ioctl. The + * following would be a command that takes a variable length input and returns 0 + * bytes of output. + * + * - @id = 10 + * - @flags = 0 + * - @size_in = -1 + * - @size_out = 0 + * + * See struct cxl_mem_query_commands. + */ +struct cxl_command_info { + __u32 id; + + __u32 flags; +#define CXL_MEM_COMMAND_FLAG_MASK GENMASK(0, 0) + + __s32 size_in; + __s32 size_out; +}; + +/** + * struct cxl_mem_query_commands - Query supported commands. + * @n_commands: In/out parameter. When @n_commands is > 0, the driver will + * return min(num_support_commands, n_commands). When @n_commands + * is 0, driver will return the number of total supported commands. + * @rsvd: Reserved for future use. + * @commands: Output array of supported commands. This array must be allocated + * by userspace to be at least min(num_support_commands, @n_commands) + * + * Allow userspace to query the available commands supported by both the driver, + * and the hardware. Commands that aren't supported by either the driver, or the + * hardware are not returned in the query. + * + * Examples: + * + * - { .n_commands = 0 } // Get number of supported commands + * - { .n_commands = 15, .commands = buf } // Return first 15 (or less) + * supported commands + * + * See struct cxl_command_info. + */ +struct cxl_mem_query_commands { + /* + * Input: Number of commands to return (space allocated by user) + * Output: Number of commands supported by the driver/hardware + * + * If n_commands is 0, kernel will only return number of commands and + * not try to populate commands[], thus allowing userspace to know how + * much space to allocate + */ + __u32 n_commands; + __u32 rsvd; + + struct cxl_command_info __user commands[]; /* out: supported commands */ +}; + +/** + * struct cxl_send_command - Send a command to a memory device. + * @id: The command to send to the memory device. This must be one of the + * commands returned by the query command. + * @flags: Flags for the command (input). + * @rsvd: Must be zero. + * @retval: Return value from the memory device (output). + * @in: Parameters associated with input payload. + * @in.size: Size of the payload to provide to the device (input). + * @in.rsvd: Must be zero. + * @in.payload: Pointer to memory for payload input, payload is little endian. + * @out: Parameters associated with output payload. + * @out.size: Size of the payload received from the device (input/output). This + * field is filled in by userspace to let the driver know how much + * space was allocated for output. It is populated by the driver to + * let userspace know how large the output payload actually was. + * @out.rsvd: Must be zero. + * @out.payload: Pointer to memory for payload output, payload is little endian. + * + * Mechanism for userspace to send a command to the hardware for processing. The + * driver will do basic validation on the command sizes. In some cases even the + * payload may be introspected. Userspace is required to allocate large enough + * buffers for size_out which can be variable length in certain situations. + */ +struct cxl_send_command { + __u32 id; + __u32 flags; + __u32 rsvd; + __u32 retval; + + struct { + __s32 size; + __u32 rsvd; + __u64 payload; + } in; + + struct { + __s32 size; + __u32 rsvd; + __u64 payload; + } out; +}; + +#endif -- cgit v1.2.3 From 13237183c735f5cba4ae26bc782c613ae0d4e4d3 Mon Sep 17 00:00:00 2001 From: Ben Widawsky Date: Tue, 16 Feb 2021 20:09:54 -0800 Subject: cxl/mem: Add a "RAW" send command The CXL memory device send interface will have a number of supported commands. The raw command is not such a command. Raw commands allow userspace to send a specified opcode to the underlying hardware and bypass all driver checks on the command. The primary use for this command is to [begrudgingly] allow undocumented vendor specific hardware commands. While not the main motivation, it also allows prototyping new hardware commands without a driver patch and rebuild. While this all sounds very powerful it comes with a couple of caveats: 1. Bug reports using raw commands will not get the same level of attention as bug reports using supported commands (via taint). 2. Supported commands will be rejected by the RAW command. With this comes new debugfs knob to allow full access to your toes with your weapon of choice. Signed-off-by: Ben Widawsky Reviewed-by: Dan Williams (v2) Reviewed-by: Jonathan Cameron Cc: Ariel Sibley Link: https://lore.kernel.org/r/20210217040958.1354670-6-ben.widawsky@intel.com Signed-off-by: Dan Williams --- drivers/cxl/Kconfig | 18 ++++++ drivers/cxl/mem.c | 132 +++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/cxl_mem.h | 12 +++- 3 files changed, 161 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/cxl/Kconfig b/drivers/cxl/Kconfig index 9e80b311e928..97dc4d751651 100644 --- a/drivers/cxl/Kconfig +++ b/drivers/cxl/Kconfig @@ -32,4 +32,22 @@ config CXL_MEM Chapter 2.3 Type 3 CXL Device in the CXL 2.0 specification. If unsure say 'm'. + +config CXL_MEM_RAW_COMMANDS + bool "RAW Command Interface for Memory Devices" + depends on CXL_MEM + help + Enable CXL RAW command interface. + + The CXL driver ioctl interface may assign a kernel ioctl command + number for each specification defined opcode. At any given point in + time the number of opcodes that the specification defines and a device + may implement may exceed the kernel's set of associated ioctl function + numbers. The mismatch is either by omission, specification is too new, + or by design. When prototyping new hardware, or developing / debugging + the driver it is useful to be able to submit any possible command to + the hardware, even commands that may crash the kernel due to their + potential impact to memory currently in use by the kernel. + + If developing CXL hardware or the driver say Y, otherwise say N. endif diff --git a/drivers/cxl/mem.c b/drivers/cxl/mem.c index aa8f843fcca1..5319412e245c 100644 --- a/drivers/cxl/mem.c +++ b/drivers/cxl/mem.c @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0-only /* Copyright(c) 2020 Intel Corporation. All rights reserved. */ #include +#include +#include #include #include #include @@ -42,7 +44,14 @@ enum opcode { CXL_MBOX_OP_INVALID = 0x0000, + CXL_MBOX_OP_RAW = CXL_MBOX_OP_INVALID, + CXL_MBOX_OP_ACTIVATE_FW = 0x0202, CXL_MBOX_OP_IDENTIFY = 0x4000, + CXL_MBOX_OP_SET_PARTITION_INFO = 0x4101, + CXL_MBOX_OP_SET_LSA = 0x4103, + CXL_MBOX_OP_SET_SHUTDOWN_STATE = 0x4204, + CXL_MBOX_OP_SCAN_MEDIA = 0x4304, + CXL_MBOX_OP_GET_SCAN_MEDIA = 0x4305, CXL_MBOX_OP_MAX = 0x10000 }; @@ -96,6 +105,8 @@ struct cxl_memdev { static int cxl_mem_major; static DEFINE_IDA(cxl_memdev_ida); +static struct dentry *cxl_debugfs; +static bool cxl_raw_allow_all; /** * struct cxl_mem_command - Driver representation of a memory device command @@ -132,6 +143,49 @@ struct cxl_mem_command { */ static struct cxl_mem_command mem_commands[] = { CXL_CMD(IDENTIFY, 0, 0x43), +#ifdef CONFIG_CXL_MEM_RAW_COMMANDS + CXL_CMD(RAW, ~0, ~0), +#endif +}; + +/* + * Commands that RAW doesn't permit. The rationale for each: + * + * CXL_MBOX_OP_ACTIVATE_FW: Firmware activation requires adjustment / + * coordination of transaction timeout values at the root bridge level. + * + * CXL_MBOX_OP_SET_PARTITION_INFO: The device memory map may change live + * and needs to be coordinated with HDM updates. + * + * CXL_MBOX_OP_SET_LSA: The label storage area may be cached by the + * driver and any writes from userspace invalidates those contents. + * + * CXL_MBOX_OP_SET_SHUTDOWN_STATE: Set shutdown state assumes no writes + * to the device after it is marked clean, userspace can not make that + * assertion. + * + * CXL_MBOX_OP_[GET_]SCAN_MEDIA: The kernel provides a native error list that + * is kept up to date with patrol notifications and error management. + */ +static u16 cxl_disabled_raw_commands[] = { + CXL_MBOX_OP_ACTIVATE_FW, + CXL_MBOX_OP_SET_PARTITION_INFO, + CXL_MBOX_OP_SET_LSA, + CXL_MBOX_OP_SET_SHUTDOWN_STATE, + CXL_MBOX_OP_SCAN_MEDIA, + CXL_MBOX_OP_GET_SCAN_MEDIA, +}; + +/* + * Command sets that RAW doesn't permit. All opcodes in this set are + * disabled because they pass plain text security payloads over the + * user/kernel boundary. This functionality is intended to be wrapped + * behind the keys ABI which allows for encrypted payloads in the UAPI + */ +static u8 security_command_sets[] = { + 0x44, /* Sanitize */ + 0x45, /* Persistent Memory Data-at-rest Security */ + 0x46, /* Security Passthrough */ }; #define cxl_for_each_cmd(cmd) \ @@ -162,6 +216,16 @@ static int cxl_mem_wait_for_doorbell(struct cxl_mem *cxlm) return 0; } +static bool cxl_is_security_command(u16 opcode) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(security_command_sets); i++) + if (security_command_sets[i] == (opcode >> 8)) + return true; + return false; +} + static void cxl_mem_mbox_timeout(struct cxl_mem *cxlm, struct mbox_cmd *mbox_cmd) { @@ -431,6 +495,9 @@ static int handle_mailbox_cmd_from_user(struct cxl_mem *cxlm, cxl_command_names[cmd->info.id].name, mbox_cmd.opcode, cmd->info.size_in); + dev_WARN_ONCE(dev, cmd->info.id == CXL_MEM_COMMAND_ID_RAW, + "raw command path used\n"); + rc = __cxl_mem_mbox_send_cmd(cxlm, &mbox_cmd); cxl_mem_mbox_put(cxlm); if (rc) @@ -460,6 +527,29 @@ out: return rc; } +static bool cxl_mem_raw_command_allowed(u16 opcode) +{ + int i; + + if (!IS_ENABLED(CONFIG_CXL_MEM_RAW_COMMANDS)) + return false; + + if (security_locked_down(LOCKDOWN_NONE)) + return false; + + if (cxl_raw_allow_all) + return true; + + if (cxl_is_security_command(opcode)) + return false; + + for (i = 0; i < ARRAY_SIZE(cxl_disabled_raw_commands); i++) + if (cxl_disabled_raw_commands[i] == opcode) + return false; + + return true; +} + /** * cxl_validate_cmd_from_user() - Check fields for CXL_MEM_SEND_COMMAND. * @cxlm: &struct cxl_mem device whose mailbox will be used. @@ -471,6 +561,7 @@ out: * * %-ENOTTY - Invalid command specified. * * %-EINVAL - Reserved fields or invalid values were used. * * %-ENOMEM - Input or output buffer wasn't sized properly. + * * %-EPERM - Attempted to use a protected command. * * The result of this command is a fully validated command in @out_cmd that is * safe to send to the hardware. @@ -495,6 +586,40 @@ static int cxl_validate_cmd_from_user(struct cxl_mem *cxlm, if (send_cmd->in.size > cxlm->payload_size) return -EINVAL; + /* + * Checks are bypassed for raw commands but a WARN/taint will occur + * later in the callchain + */ + if (send_cmd->id == CXL_MEM_COMMAND_ID_RAW) { + const struct cxl_mem_command temp = { + .info = { + .id = CXL_MEM_COMMAND_ID_RAW, + .flags = 0, + .size_in = send_cmd->in.size, + .size_out = send_cmd->out.size, + }, + .opcode = send_cmd->raw.opcode + }; + + if (send_cmd->raw.rsvd) + return -EINVAL; + + /* + * Unlike supported commands, the output size of RAW commands + * gets passed along without further checking, so it must be + * validated here. + */ + if (send_cmd->out.size > cxlm->payload_size) + return -EINVAL; + + if (!cxl_mem_raw_command_allowed(send_cmd->raw.opcode)) + return -EPERM; + + memcpy(out_cmd, &temp, sizeof(temp)); + + return 0; + } + if (send_cmd->flags & ~CXL_MEM_COMMAND_FLAG_MASK) return -EINVAL; @@ -1166,6 +1291,7 @@ static struct pci_driver cxl_mem_driver = { static __init int cxl_mem_init(void) { + struct dentry *mbox_debugfs; dev_t devt; int rc; @@ -1182,11 +1308,17 @@ static __init int cxl_mem_init(void) return rc; } + cxl_debugfs = debugfs_create_dir("cxl", NULL); + mbox_debugfs = debugfs_create_dir("mbox", cxl_debugfs); + debugfs_create_bool("raw_allow_all", 0600, mbox_debugfs, + &cxl_raw_allow_all); + return 0; } static __exit void cxl_mem_exit(void) { + debugfs_remove_recursive(cxl_debugfs); pci_unregister_driver(&cxl_mem_driver); unregister_chrdev_region(MKDEV(cxl_mem_major, 0), CXL_MEM_MAX_DEVS); } diff --git a/include/uapi/linux/cxl_mem.h b/include/uapi/linux/cxl_mem.h index 887781dc3b6c..c316028730e7 100644 --- a/include/uapi/linux/cxl_mem.h +++ b/include/uapi/linux/cxl_mem.h @@ -22,6 +22,7 @@ #define CXL_CMDS \ ___C(INVALID, "Invalid Command"), \ ___C(IDENTIFY, "Identify Command"), \ + ___C(RAW, "Raw device command"), \ ___C(MAX, "invalid / last command") #define ___C(a, b) CXL_MEM_COMMAND_ID_##a @@ -115,6 +116,9 @@ struct cxl_mem_query_commands { * @id: The command to send to the memory device. This must be one of the * commands returned by the query command. * @flags: Flags for the command (input). + * @raw: Special fields for raw commands + * @raw.opcode: Opcode passed to hardware when using the RAW command. + * @raw.rsvd: Must be zero. * @rsvd: Must be zero. * @retval: Return value from the memory device (output). * @in: Parameters associated with input payload. @@ -137,7 +141,13 @@ struct cxl_mem_query_commands { struct cxl_send_command { __u32 id; __u32 flags; - __u32 rsvd; + union { + struct { + __u16 opcode; + __u16 rsvd; + } raw; + __u32 rsvd; + }; __u32 retval; struct { -- cgit v1.2.3 From 472b1ce6e9d6396ab3f11fc5101c6b63b934a018 Mon Sep 17 00:00:00 2001 From: Ben Widawsky Date: Tue, 16 Feb 2021 20:09:55 -0800 Subject: cxl/mem: Enable commands via CEL CXL devices identified by the memory-device class code must implement the Device Command Interface (described in 8.2.9 of the CXL 2.0 spec). While the driver already maintains a list of commands it supports, there is still a need to be able to distinguish between commands that the driver knows about from commands that are optionally supported by the hardware. The Command Effects Log (CEL) is specified in the CXL 2.0 specification. The CEL is one of two types of logs, the other being vendor specific. They are distinguished in hardware/spec via UUID. The CEL is useful for 2 things: 1. Determine which optional commands are supported by the CXL device. 2. Enumerate any vendor specific commands The CEL is used by the driver to determine which commands are available in the hardware and therefore which commands userspace is allowed to execute. The set of enabled commands might be a subset of commands which are advertised in UAPI via CXL_MEM_SEND_COMMAND IOCTL. With the CEL enabling comes a internal flag to indicate a base set of commands that are enabled regardless of CEL. Such commands are required for basic interaction with the hardware and thus can be useful in debug cases, for example if the CEL is corrupted. The implementation leaves the statically defined table of commands and supplements it with a bitmap to determine commands that are enabled. This organization was chosen for the following reasons: - Smaller memory footprint. Doesn't need a table per device. - Reduce memory allocation complexity. - Fixed command IDs to opcode mapping for all devices makes development and debugging easier. - Certain helpers are easily achievable, like cxl_for_each_cmd(). Signed-off-by: Ben Widawsky Reviewed-by: Dan Williams (v2) Reviewed-by: Jonathan Cameron (v3) Link: https://lore.kernel.org/r/20210217040958.1354670-7-ben.widawsky@intel.com Signed-off-by: Dan Williams --- drivers/cxl/cxl.h | 2 + drivers/cxl/mem.c | 223 +++++++++++++++++++++++++++++++++++++++++-- include/uapi/linux/cxl_mem.h | 1 + 3 files changed, 219 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h index 8fd4a177fe25..6f14838c2d25 100644 --- a/drivers/cxl/cxl.h +++ b/drivers/cxl/cxl.h @@ -69,6 +69,7 @@ struct cxl_memdev; * (CXL 2.0 8.2.8.4.3 Mailbox Capabilities Register) * @mbox_mutex: Mutex to synchronize mailbox access. * @firmware_version: Firmware version for the memory device. + * @enabled_commands: Hardware commands found enabled in CEL. * @pmem_range: Persistent memory capacity information. * @ram_range: Volatile memory capacity information. */ @@ -84,6 +85,7 @@ struct cxl_mem { size_t payload_size; struct mutex mbox_mutex; /* Protects device mailbox and firmware */ char firmware_version[0x10]; + unsigned long *enabled_cmds; struct range pmem_range; struct range ram_range; diff --git a/drivers/cxl/mem.c b/drivers/cxl/mem.c index 5319412e245c..e31b3045e231 100644 --- a/drivers/cxl/mem.c +++ b/drivers/cxl/mem.c @@ -46,6 +46,8 @@ enum opcode { CXL_MBOX_OP_INVALID = 0x0000, CXL_MBOX_OP_RAW = CXL_MBOX_OP_INVALID, CXL_MBOX_OP_ACTIVATE_FW = 0x0202, + CXL_MBOX_OP_GET_SUPPORTED_LOGS = 0x0400, + CXL_MBOX_OP_GET_LOG = 0x0401, CXL_MBOX_OP_IDENTIFY = 0x4000, CXL_MBOX_OP_SET_PARTITION_INFO = 0x4101, CXL_MBOX_OP_SET_LSA = 0x4103, @@ -108,10 +110,28 @@ static DEFINE_IDA(cxl_memdev_ida); static struct dentry *cxl_debugfs; static bool cxl_raw_allow_all; +enum { + CEL_UUID, + VENDOR_DEBUG_UUID, +}; + +/* See CXL 2.0 Table 170. Get Log Input Payload */ +static const uuid_t log_uuid[] = { + [CEL_UUID] = UUID_INIT(0xda9c0b5, 0xbf41, 0x4b78, 0x8f, 0x79, 0x96, + 0xb1, 0x62, 0x3b, 0x3f, 0x17), + [VENDOR_DEBUG_UUID] = UUID_INIT(0xe1819d9, 0x11a9, 0x400c, 0x81, 0x1f, + 0xd6, 0x07, 0x19, 0x40, 0x3d, 0x86), +}; + /** * struct cxl_mem_command - Driver representation of a memory device command * @info: Command information as it exists for the UAPI * @opcode: The actual bits used for the mailbox protocol + * @flags: Set of flags effecting driver behavior. + * + * * %CXL_CMD_FLAG_FORCE_ENABLE: In cases of error, commands with this flag + * will be enabled by the driver regardless of what hardware may have + * advertised. * * The cxl_mem_command is the driver's internal representation of commands that * are supported by the driver. Some of these commands may not be supported by @@ -123,9 +143,12 @@ static bool cxl_raw_allow_all; struct cxl_mem_command { struct cxl_command_info info; enum opcode opcode; + u32 flags; +#define CXL_CMD_FLAG_NONE 0 +#define CXL_CMD_FLAG_FORCE_ENABLE BIT(0) }; -#define CXL_CMD(_id, sin, sout) \ +#define CXL_CMD(_id, sin, sout, _flags) \ [CXL_MEM_COMMAND_ID_##_id] = { \ .info = { \ .id = CXL_MEM_COMMAND_ID_##_id, \ @@ -133,6 +156,7 @@ struct cxl_mem_command { .size_out = sout, \ }, \ .opcode = CXL_MBOX_OP_##_id, \ + .flags = _flags, \ } /* @@ -142,10 +166,11 @@ struct cxl_mem_command { * 0, and the user passed in 1, it is an error. */ static struct cxl_mem_command mem_commands[] = { - CXL_CMD(IDENTIFY, 0, 0x43), + CXL_CMD(IDENTIFY, 0, 0x43, CXL_CMD_FLAG_FORCE_ENABLE), #ifdef CONFIG_CXL_MEM_RAW_COMMANDS - CXL_CMD(RAW, ~0, ~0), + CXL_CMD(RAW, ~0, ~0, 0), #endif + CXL_CMD(GET_SUPPORTED_LOGS, 0, ~0, CXL_CMD_FLAG_FORCE_ENABLE), }; /* @@ -633,6 +658,10 @@ static int cxl_validate_cmd_from_user(struct cxl_mem *cxlm, c = &mem_commands[send_cmd->id]; info = &c->info; + /* Check that the command is enabled for hardware */ + if (!test_bit(info->id, cxlm->enabled_cmds)) + return -ENOTTY; + /* Check the input buffer is the expected size */ if (info->size_in >= 0 && info->size_in != send_cmd->in.size) return -ENOMEM; @@ -757,6 +786,17 @@ static const struct file_operations cxl_memdev_fops = { .llseek = noop_llseek, }; +static inline struct cxl_mem_command *cxl_mem_find_command(u16 opcode) +{ + struct cxl_mem_command *c; + + cxl_for_each_cmd(c) + if (c->opcode == opcode) + return c; + + return NULL; +} + /** * cxl_mem_mbox_send_cmd() - Send a mailbox command to a memory device. * @cxlm: The CXL memory device to communicate with. @@ -777,9 +817,7 @@ static const struct file_operations cxl_memdev_fops = { * * Mailbox commands may execute successfully yet the device itself reported an * error. While this distinction can be useful for commands from userspace, the - * kernel will only be able to use results when both are successful. It's - * expected that all callers of this function know exactly the size of the data - * they will consume from the hardware. + * kernel will only be able to use results when both are successful. * * See __cxl_mem_mbox_send_cmd() */ @@ -787,6 +825,7 @@ static int cxl_mem_mbox_send_cmd(struct cxl_mem *cxlm, u16 opcode, void *in, size_t in_size, void *out, size_t out_size) { + const struct cxl_mem_command *cmd = cxl_mem_find_command(opcode); struct mbox_cmd mbox_cmd = { .opcode = opcode, .payload_in = in, @@ -812,7 +851,11 @@ static int cxl_mem_mbox_send_cmd(struct cxl_mem *cxlm, u16 opcode, if (mbox_cmd.return_code != CXL_MBOX_SUCCESS) return -ENXIO; - if (mbox_cmd.size_out != out_size) + /* + * Variable sized commands can't be validated and so it's up to the + * caller to do that if they wish. + */ + if (cmd->info.size_out >= 0 && mbox_cmd.size_out != out_size) return -EIO; return 0; @@ -947,6 +990,14 @@ static struct cxl_mem *cxl_mem_create(struct pci_dev *pdev, u32 reg_lo, mutex_init(&cxlm->mbox_mutex); cxlm->pdev = pdev; cxlm->regs = regs + offset; + cxlm->enabled_cmds = + devm_kmalloc_array(dev, BITS_TO_LONGS(cxl_cmd_count), + sizeof(unsigned long), + GFP_KERNEL | __GFP_ZERO); + if (!cxlm->enabled_cmds) { + dev_err(dev, "No memory available for bitmap\n"); + return NULL; + } dev_dbg(dev, "Mapped CXL Memory Device resource\n"); return cxlm; @@ -1166,6 +1217,160 @@ err_ref: return rc; } +static int cxl_xfer_log(struct cxl_mem *cxlm, uuid_t *uuid, u32 size, u8 *out) +{ + u32 remaining = size; + u32 offset = 0; + + while (remaining) { + u32 xfer_size = min_t(u32, remaining, cxlm->payload_size); + struct cxl_mbox_get_log { + uuid_t uuid; + __le32 offset; + __le32 length; + } __packed log = { + .uuid = *uuid, + .offset = cpu_to_le32(offset), + .length = cpu_to_le32(xfer_size) + }; + int rc; + + rc = cxl_mem_mbox_send_cmd(cxlm, CXL_MBOX_OP_GET_LOG, &log, + sizeof(log), out, xfer_size); + if (rc < 0) + return rc; + + out += xfer_size; + remaining -= xfer_size; + offset += xfer_size; + } + + return 0; +} + +/** + * cxl_walk_cel() - Walk through the Command Effects Log. + * @cxlm: Device. + * @size: Length of the Command Effects Log. + * @cel: CEL + * + * Iterate over each entry in the CEL and determine if the driver supports the + * command. If so, the command is enabled for the device and can be used later. + */ +static void cxl_walk_cel(struct cxl_mem *cxlm, size_t size, u8 *cel) +{ + struct cel_entry { + __le16 opcode; + __le16 effect; + } __packed * cel_entry; + const int cel_entries = size / sizeof(*cel_entry); + int i; + + cel_entry = (struct cel_entry *)cel; + + for (i = 0; i < cel_entries; i++) { + u16 opcode = le16_to_cpu(cel_entry[i].opcode); + struct cxl_mem_command *cmd = cxl_mem_find_command(opcode); + + if (!cmd) { + dev_dbg(&cxlm->pdev->dev, + "Opcode 0x%04x unsupported by driver", opcode); + continue; + } + + set_bit(cmd->info.id, cxlm->enabled_cmds); + } +} + +struct cxl_mbox_get_supported_logs { + __le16 entries; + u8 rsvd[6]; + struct gsl_entry { + uuid_t uuid; + __le32 size; + } __packed entry[]; +} __packed; + +static struct cxl_mbox_get_supported_logs *cxl_get_gsl(struct cxl_mem *cxlm) +{ + struct cxl_mbox_get_supported_logs *ret; + int rc; + + ret = kvmalloc(cxlm->payload_size, GFP_KERNEL); + if (!ret) + return ERR_PTR(-ENOMEM); + + rc = cxl_mem_mbox_send_cmd(cxlm, CXL_MBOX_OP_GET_SUPPORTED_LOGS, NULL, + 0, ret, cxlm->payload_size); + if (rc < 0) { + kvfree(ret); + return ERR_PTR(rc); + } + + return ret; +} + +/** + * cxl_mem_enumerate_cmds() - Enumerate commands for a device. + * @cxlm: The device. + * + * Returns 0 if enumerate completed successfully. + * + * CXL devices have optional support for certain commands. This function will + * determine the set of supported commands for the hardware and update the + * enabled_cmds bitmap in the @cxlm. + */ +static int cxl_mem_enumerate_cmds(struct cxl_mem *cxlm) +{ + struct cxl_mbox_get_supported_logs *gsl; + struct device *dev = &cxlm->pdev->dev; + struct cxl_mem_command *cmd; + int i, rc; + + gsl = cxl_get_gsl(cxlm); + if (IS_ERR(gsl)) + return PTR_ERR(gsl); + + rc = -ENOENT; + for (i = 0; i < le16_to_cpu(gsl->entries); i++) { + u32 size = le32_to_cpu(gsl->entry[i].size); + uuid_t uuid = gsl->entry[i].uuid; + u8 *log; + + dev_dbg(dev, "Found LOG type %pU of size %d", &uuid, size); + + if (!uuid_equal(&uuid, &log_uuid[CEL_UUID])) + continue; + + log = kvmalloc(size, GFP_KERNEL); + if (!log) { + rc = -ENOMEM; + goto out; + } + + rc = cxl_xfer_log(cxlm, &uuid, size, log); + if (rc) { + kvfree(log); + goto out; + } + + cxl_walk_cel(cxlm, size, log); + kvfree(log); + + /* In case CEL was bogus, enable some default commands. */ + cxl_for_each_cmd(cmd) + if (cmd->flags & CXL_CMD_FLAG_FORCE_ENABLE) + set_bit(cmd->info.id, cxlm->enabled_cmds); + + /* Found the required CEL */ + rc = 0; + } + +out: + kvfree(gsl); + return rc; +} + /** * cxl_mem_identify() - Send the IDENTIFY command to the device. * @cxlm: The device to identify. @@ -1266,6 +1471,10 @@ static int cxl_mem_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (rc) return rc; + rc = cxl_mem_enumerate_cmds(cxlm); + if (rc) + return rc; + rc = cxl_mem_identify(cxlm); if (rc) return rc; diff --git a/include/uapi/linux/cxl_mem.h b/include/uapi/linux/cxl_mem.h index c316028730e7..59227f82a4c1 100644 --- a/include/uapi/linux/cxl_mem.h +++ b/include/uapi/linux/cxl_mem.h @@ -23,6 +23,7 @@ ___C(INVALID, "Invalid Command"), \ ___C(IDENTIFY, "Identify Command"), \ ___C(RAW, "Raw device command"), \ + ___C(GET_SUPPORTED_LOGS, "Get Supported Logs"), \ ___C(MAX, "invalid / last command") #define ___C(a, b) CXL_MEM_COMMAND_ID_##a -- cgit v1.2.3 From 57ee605b976c30a86613648935d255bbe704aeab Mon Sep 17 00:00:00 2001 From: Ben Widawsky Date: Tue, 16 Feb 2021 20:09:56 -0800 Subject: cxl/mem: Add set of informational commands Add initial set of formal commands beyond basic identify and command enumeration. Signed-off-by: Ben Widawsky Reviewed-by: Dan Williams Reviewed-by: Jonathan Cameron (v2) Link: https://lore.kernel.org/r/20210217040958.1354670-8-ben.widawsky@intel.com Signed-off-by: Dan Williams --- drivers/cxl/mem.c | 9 +++++++++ include/uapi/linux/cxl_mem.h | 5 +++++ 2 files changed, 14 insertions(+) (limited to 'include') diff --git a/drivers/cxl/mem.c b/drivers/cxl/mem.c index e31b3045e231..6d7d3870b5da 100644 --- a/drivers/cxl/mem.c +++ b/drivers/cxl/mem.c @@ -45,12 +45,16 @@ enum opcode { CXL_MBOX_OP_INVALID = 0x0000, CXL_MBOX_OP_RAW = CXL_MBOX_OP_INVALID, + CXL_MBOX_OP_GET_FW_INFO = 0x0200, CXL_MBOX_OP_ACTIVATE_FW = 0x0202, CXL_MBOX_OP_GET_SUPPORTED_LOGS = 0x0400, CXL_MBOX_OP_GET_LOG = 0x0401, CXL_MBOX_OP_IDENTIFY = 0x4000, + CXL_MBOX_OP_GET_PARTITION_INFO = 0x4100, CXL_MBOX_OP_SET_PARTITION_INFO = 0x4101, + CXL_MBOX_OP_GET_LSA = 0x4102, CXL_MBOX_OP_SET_LSA = 0x4103, + CXL_MBOX_OP_GET_HEALTH_INFO = 0x4200, CXL_MBOX_OP_SET_SHUTDOWN_STATE = 0x4204, CXL_MBOX_OP_SCAN_MEDIA = 0x4304, CXL_MBOX_OP_GET_SCAN_MEDIA = 0x4305, @@ -171,6 +175,11 @@ static struct cxl_mem_command mem_commands[] = { CXL_CMD(RAW, ~0, ~0, 0), #endif CXL_CMD(GET_SUPPORTED_LOGS, 0, ~0, CXL_CMD_FLAG_FORCE_ENABLE), + CXL_CMD(GET_FW_INFO, 0, 0x50, 0), + CXL_CMD(GET_PARTITION_INFO, 0, 0x20, 0), + CXL_CMD(GET_LSA, 0x8, ~0, 0), + CXL_CMD(GET_HEALTH_INFO, 0, 0x12, 0), + CXL_CMD(GET_LOG, 0x18, ~0, CXL_CMD_FLAG_FORCE_ENABLE), }; /* diff --git a/include/uapi/linux/cxl_mem.h b/include/uapi/linux/cxl_mem.h index 59227f82a4c1..3155382dfc9b 100644 --- a/include/uapi/linux/cxl_mem.h +++ b/include/uapi/linux/cxl_mem.h @@ -24,6 +24,11 @@ ___C(IDENTIFY, "Identify Command"), \ ___C(RAW, "Raw device command"), \ ___C(GET_SUPPORTED_LOGS, "Get Supported Logs"), \ + ___C(GET_FW_INFO, "Get FW Info"), \ + ___C(GET_PARTITION_INFO, "Get Partition Information"), \ + ___C(GET_LSA, "Get Label Storage Area"), \ + ___C(GET_HEALTH_INFO, "Get Health Info"), \ + ___C(GET_LOG, "Get Log"), \ ___C(MAX, "invalid / last command") #define ___C(a, b) CXL_MEM_COMMAND_ID_##a -- cgit v1.2.3 From fade5cad9339a627c5ad029e3577582b6292df03 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Fri, 15 Jan 2021 13:46:03 +0800 Subject: initrd: Add the preprocessor guard in initrd.h Add the preprocessor guard in initrd.h to prevent possible build error from the multiple inclusion of same header file multiple time. Signed-off-by: Kefeng Wang Signed-off-by: Palmer Dabbelt --- include/linux/initrd.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/initrd.h b/include/linux/initrd.h index 8db6f8c8030b..fc30ac30e10e 100644 --- a/include/linux/initrd.h +++ b/include/linux/initrd.h @@ -1,5 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_INITRD_H +#define __LINUX_INITRD_H + #define INITRD_MINOR 250 /* shouldn't collide with /dev/ram* too soon ... */ /* starting block # of image */ @@ -24,3 +27,5 @@ extern char __initramfs_start[]; extern unsigned long __initramfs_size; void console_on_rootfs(void); + +#endif /* __LINUX_INITRD_H */ -- cgit v1.2.3 From c72160fe05fb978ad859ba053c4462c2bb960b13 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Fri, 15 Jan 2021 13:46:04 +0800 Subject: initramfs: Provide a common initrd reserve function Some architectures(eg, ARM and riscv) have similar logic to check and reserve the memory of initrd, let's provide a common function reserve_initrd_mem() to reduce duplicated code. Signed-off-by: Kefeng Wang Signed-off-by: Palmer Dabbelt --- include/linux/initrd.h | 6 ++++++ init/initramfs.c | 45 +++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 51 insertions(+) (limited to 'include') diff --git a/include/linux/initrd.h b/include/linux/initrd.h index fc30ac30e10e..85c15717af34 100644 --- a/include/linux/initrd.h +++ b/include/linux/initrd.h @@ -18,6 +18,12 @@ extern int initrd_below_start_ok; extern unsigned long initrd_start, initrd_end; extern void free_initrd_mem(unsigned long, unsigned long); +#ifdef CONFIG_BLK_DEV_INITRD +extern void __init reserve_initrd_mem(void); +#else +static inline void __init reserve_initrd_mem(void) {} +#endif + extern phys_addr_t phys_initrd_start; extern unsigned long phys_initrd_size; diff --git a/init/initramfs.c b/init/initramfs.c index 55b74d7e5260..f75c89e9d602 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -535,6 +535,51 @@ extern unsigned long __initramfs_size; #include #include +void __init reserve_initrd_mem(void) +{ + phys_addr_t start; + unsigned long size; + + /* Ignore the virtul address computed during device tree parsing */ + initrd_start = initrd_end = 0; + + if (!phys_initrd_size) + return; + /* + * Round the memory region to page boundaries as per free_initrd_mem() + * This allows us to detect whether the pages overlapping the initrd + * are in use, but more importantly, reserves the entire set of pages + * as we don't want these pages allocated for other purposes. + */ + start = round_down(phys_initrd_start, PAGE_SIZE); + size = phys_initrd_size + (phys_initrd_start - start); + size = round_up(size, PAGE_SIZE); + + if (!memblock_is_region_memory(start, size)) { + pr_err("INITRD: 0x%08llx+0x%08lx is not a memory region", + (u64)start, size); + goto disable; + } + + if (memblock_is_region_reserved(start, size)) { + pr_err("INITRD: 0x%08llx+0x%08lx overlaps in-use memory region\n", + (u64)start, size); + goto disable; + } + + memblock_reserve(start, size); + /* Now convert initrd to virtual addresses */ + initrd_start = (unsigned long)__va(phys_initrd_start); + initrd_end = initrd_start + phys_initrd_size; + initrd_below_start_ok = 1; + + return; +disable: + pr_cont(" - disabling initrd\n"); + initrd_start = 0; + initrd_end = 0; +} + void __weak __init free_initrd_mem(unsigned long start, unsigned long end) { #ifdef CONFIG_ARCH_KEEP_MEMBLOCK -- cgit v1.2.3 From af0bfab907a011e146304d20d81dddce4e4d62d0 Mon Sep 17 00:00:00 2001 From: Abanoub Sameh Date: Fri, 11 Dec 2020 22:42:08 +0200 Subject: leds: led-core: Get rid of enum led_brightness This gets rid of enum led_brightness in the main led files, because it is deprecated, and an unsigned int can be used instead. We can get rid of led_brightness completely and patches can also be supplied for the other drivers' files. Signed-off-by: Abanoub Sameh Signed-off-by: Pavel Machek --- drivers/leds/led-class.c | 3 +-- drivers/leds/led-core.c | 20 +++++++------------- drivers/leds/leds.h | 6 ++---- include/linux/leds.h | 12 +++++------- 4 files changed, 15 insertions(+), 26 deletions(-) (limited to 'include') diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c index 131ca83f5fb3..2e495ff67856 100644 --- a/drivers/leds/led-class.c +++ b/drivers/leds/led-class.c @@ -145,8 +145,7 @@ static void led_remove_brightness_hw_changed(struct led_classdev *led_cdev) device_remove_file(led_cdev->dev, &dev_attr_brightness_hw_changed); } -void led_classdev_notify_brightness_hw_changed(struct led_classdev *led_cdev, - enum led_brightness brightness) +void led_classdev_notify_brightness_hw_changed(struct led_classdev *led_cdev, unsigned int brightness) { if (WARN_ON(!led_cdev->brightness_hw_changed_kn)) return; diff --git a/drivers/leds/led-core.c b/drivers/leds/led-core.c index c4e780bdb385..8eb8054ef9c6 100644 --- a/drivers/leds/led-core.c +++ b/drivers/leds/led-core.c @@ -39,8 +39,7 @@ const char * const led_colors[LED_COLOR_ID_MAX] = { }; EXPORT_SYMBOL_GPL(led_colors); -static int __led_set_brightness(struct led_classdev *led_cdev, - enum led_brightness value) +static int __led_set_brightness(struct led_classdev *led_cdev, unsigned int value) { if (!led_cdev->brightness_set) return -ENOTSUPP; @@ -50,8 +49,7 @@ static int __led_set_brightness(struct led_classdev *led_cdev, return 0; } -static int __led_set_brightness_blocking(struct led_classdev *led_cdev, - enum led_brightness value) +static int __led_set_brightness_blocking(struct led_classdev *led_cdev, unsigned int value) { if (!led_cdev->brightness_set_blocking) return -ENOTSUPP; @@ -240,8 +238,7 @@ void led_stop_software_blink(struct led_classdev *led_cdev) } EXPORT_SYMBOL_GPL(led_stop_software_blink); -void led_set_brightness(struct led_classdev *led_cdev, - enum led_brightness brightness) +void led_set_brightness(struct led_classdev *led_cdev, unsigned int brightness) { /* * If software blink is active, delay brightness setting @@ -253,7 +250,7 @@ void led_set_brightness(struct led_classdev *led_cdev, * work queue task to avoid problems in case we are called * from hard irq context. */ - if (brightness == LED_OFF) { + if (!brightness) { set_bit(LED_BLINK_DISABLE, &led_cdev->work_flags); schedule_work(&led_cdev->set_brightness_work); } else { @@ -268,8 +265,7 @@ void led_set_brightness(struct led_classdev *led_cdev, } EXPORT_SYMBOL_GPL(led_set_brightness); -void led_set_brightness_nopm(struct led_classdev *led_cdev, - enum led_brightness value) +void led_set_brightness_nopm(struct led_classdev *led_cdev, unsigned int value) { /* Use brightness_set op if available, it is guaranteed not to sleep */ if (!__led_set_brightness(led_cdev, value)) @@ -281,8 +277,7 @@ void led_set_brightness_nopm(struct led_classdev *led_cdev, } EXPORT_SYMBOL_GPL(led_set_brightness_nopm); -void led_set_brightness_nosleep(struct led_classdev *led_cdev, - enum led_brightness value) +void led_set_brightness_nosleep(struct led_classdev *led_cdev, unsigned int value) { led_cdev->brightness = min(value, led_cdev->max_brightness); @@ -293,8 +288,7 @@ void led_set_brightness_nosleep(struct led_classdev *led_cdev, } EXPORT_SYMBOL_GPL(led_set_brightness_nosleep); -int led_set_brightness_sync(struct led_classdev *led_cdev, - enum led_brightness value) +int led_set_brightness_sync(struct led_classdev *led_cdev, unsigned int value) { if (led_cdev->blink_delay_on || led_cdev->blink_delay_off) return -EBUSY; diff --git a/drivers/leds/leds.h b/drivers/leds/leds.h index 2d9eb48bbed9..345062ccabda 100644 --- a/drivers/leds/leds.h +++ b/drivers/leds/leds.h @@ -19,10 +19,8 @@ static inline int led_get_brightness(struct led_classdev *led_cdev) void led_init_core(struct led_classdev *led_cdev); void led_stop_software_blink(struct led_classdev *led_cdev); -void led_set_brightness_nopm(struct led_classdev *led_cdev, - enum led_brightness value); -void led_set_brightness_nosleep(struct led_classdev *led_cdev, - enum led_brightness value); +void led_set_brightness_nopm(struct led_classdev *led_cdev, unsigned int value); +void led_set_brightness_nosleep(struct led_classdev *led_cdev, unsigned int value); ssize_t led_trigger_read(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t pos, size_t count); diff --git a/include/linux/leds.h b/include/linux/leds.h index 6a8d6409c993..329fd914cf24 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -63,8 +63,8 @@ struct led_hw_trigger_type { struct led_classdev { const char *name; - enum led_brightness brightness; - enum led_brightness max_brightness; + unsigned int brightness; + unsigned int max_brightness; int flags; /* Lower 16 bits reflect status */ @@ -253,8 +253,7 @@ void led_blink_set_oneshot(struct led_classdev *led_cdev, * software blink timer that implements blinking when the * hardware doesn't. This function is guaranteed not to sleep. */ -void led_set_brightness(struct led_classdev *led_cdev, - enum led_brightness brightness); +void led_set_brightness(struct led_classdev *led_cdev, unsigned int brightness); /** * led_set_brightness_sync - set LED brightness synchronously @@ -267,8 +266,7 @@ void led_set_brightness(struct led_classdev *led_cdev, * * Returns: 0 on success or negative error value on failure */ -int led_set_brightness_sync(struct led_classdev *led_cdev, - enum led_brightness value); +int led_set_brightness_sync(struct led_classdev *led_cdev, unsigned int value); /** * led_update_brightness - update LED brightness @@ -565,7 +563,7 @@ static inline void ledtrig_cpu(enum cpu_led_event evt) #ifdef CONFIG_LEDS_BRIGHTNESS_HW_CHANGED void led_classdev_notify_brightness_hw_changed( - struct led_classdev *led_cdev, enum led_brightness brightness); + struct led_classdev *led_cdev, unsigned int brightness); #else static inline void led_classdev_notify_brightness_hw_changed( struct led_classdev *led_cdev, enum led_brightness brightness) { } -- cgit v1.2.3 From 8e5c38a33c84935d66cfcf23c96960b6c4b484ef Mon Sep 17 00:00:00 2001 From: Gene Chen Date: Mon, 21 Dec 2020 18:45:50 +0800 Subject: leds: flash: Add flash registration with undefined CONFIG_LEDS_CLASS_FLASH Add flash registration with undefined CONFIG_LEDS_CLASS_FLASH, and move the same registration functions outside of #ifdef block. Signed-off-by: Gene Chen Acked-by: Jacek Anaszewski Signed-off-by: Pavel Machek --- include/linux/led-class-flash.h | 42 ++++++++++++++++++++++++++++++++--------- 1 file changed, 33 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/led-class-flash.h b/include/linux/led-class-flash.h index 21a3358a1731..612b4cab3819 100644 --- a/include/linux/led-class-flash.h +++ b/include/linux/led-class-flash.h @@ -85,6 +85,7 @@ static inline struct led_classdev_flash *lcdev_to_flcdev( return container_of(lcdev, struct led_classdev_flash, led_cdev); } +#if IS_ENABLED(CONFIG_LEDS_CLASS_FLASH) /** * led_classdev_flash_register_ext - register a new object of LED class with * init data and with support for flash LEDs @@ -98,12 +99,6 @@ int led_classdev_flash_register_ext(struct device *parent, struct led_classdev_flash *fled_cdev, struct led_init_data *init_data); -static inline int led_classdev_flash_register(struct device *parent, - struct led_classdev_flash *fled_cdev) -{ - return led_classdev_flash_register_ext(parent, fled_cdev, NULL); -} - /** * led_classdev_flash_unregister - unregisters an object of led_classdev class * with support for flash LEDs @@ -118,15 +113,44 @@ int devm_led_classdev_flash_register_ext(struct device *parent, struct led_init_data *init_data); +void devm_led_classdev_flash_unregister(struct device *parent, + struct led_classdev_flash *fled_cdev); + +#else + +static inline int led_classdev_flash_register_ext(struct device *parent, + struct led_classdev_flash *fled_cdev, + struct led_init_data *init_data) +{ + return 0; +} + +static inline void led_classdev_flash_unregister(struct led_classdev_flash *fled_cdev) {}; +static inline int devm_led_classdev_flash_register_ext(struct device *parent, + struct led_classdev_flash *fled_cdev, + struct led_init_data *init_data) +{ + return 0; +} + +static inline void devm_led_classdev_flash_unregister(struct device *parent, + struct led_classdev_flash *fled_cdev) +{}; + +#endif /* IS_ENABLED(CONFIG_LEDS_CLASS_FLASH) */ + +static inline int led_classdev_flash_register(struct device *parent, + struct led_classdev_flash *fled_cdev) +{ + return led_classdev_flash_register_ext(parent, fled_cdev, NULL); +} + static inline int devm_led_classdev_flash_register(struct device *parent, struct led_classdev_flash *fled_cdev) { return devm_led_classdev_flash_register_ext(parent, fled_cdev, NULL); } -void devm_led_classdev_flash_unregister(struct device *parent, - struct led_classdev_flash *fled_cdev); - /** * led_set_flash_strobe - setup flash strobe * @fled_cdev: the flash LED to set strobe on -- cgit v1.2.3 From 6039b7e87be0b350a5f8fc135adfb5d1f4ba66ad Mon Sep 17 00:00:00 2001 From: Gene Chen Date: Mon, 21 Dec 2020 18:45:51 +0800 Subject: leds: flash: Fix multicolor no-ops registration by return 0 Fix multicolor no-ops registration by return 0, and move the same registration functions outside of #ifdef block. Signed-off-by: Gene Chen Acked-by: Jacek Anaszewski Signed-off-by: Pavel Machek --- include/linux/led-class-multicolor.h | 42 +++++++++++++----------------------- 1 file changed, 15 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/include/linux/led-class-multicolor.h b/include/linux/led-class-multicolor.h index 5116f9a866cc..210d57bcd767 100644 --- a/include/linux/led-class-multicolor.h +++ b/include/linux/led-class-multicolor.h @@ -44,12 +44,6 @@ int led_classdev_multicolor_register_ext(struct device *parent, struct led_classdev_mc *mcled_cdev, struct led_init_data *init_data); -static inline int led_classdev_multicolor_register(struct device *parent, - struct led_classdev_mc *mcled_cdev) -{ - return led_classdev_multicolor_register_ext(parent, mcled_cdev, NULL); -} - /** * led_classdev_multicolor_unregister - unregisters an object of led_classdev * class with support for multicolor LEDs @@ -68,13 +62,6 @@ int devm_led_classdev_multicolor_register_ext(struct device *parent, struct led_classdev_mc *mcled_cdev, struct led_init_data *init_data); -static inline int devm_led_classdev_multicolor_register(struct device *parent, - struct led_classdev_mc *mcled_cdev) -{ - return devm_led_classdev_multicolor_register_ext(parent, mcled_cdev, - NULL); -} - void devm_led_classdev_multicolor_unregister(struct device *parent, struct led_classdev_mc *mcled_cdev); #else @@ -83,27 +70,33 @@ static inline int led_classdev_multicolor_register_ext(struct device *parent, struct led_classdev_mc *mcled_cdev, struct led_init_data *init_data) { - return -EINVAL; -} - -static inline int led_classdev_multicolor_register(struct device *parent, - struct led_classdev_mc *mcled_cdev) -{ - return led_classdev_multicolor_register_ext(parent, mcled_cdev, NULL); + return 0; } static inline void led_classdev_multicolor_unregister(struct led_classdev_mc *mcled_cdev) {}; static inline int led_mc_calc_color_components(struct led_classdev_mc *mcled_cdev, enum led_brightness brightness) { - return -EINVAL; + return 0; } static inline int devm_led_classdev_multicolor_register_ext(struct device *parent, struct led_classdev_mc *mcled_cdev, struct led_init_data *init_data) { - return -EINVAL; + return 0; +} + +static inline void devm_led_classdev_multicolor_unregister(struct device *parent, + struct led_classdev_mc *mcled_cdev) +{}; + +#endif /* IS_ENABLED(CONFIG_LEDS_CLASS_MULTICOLOR) */ + +static inline int led_classdev_multicolor_register(struct device *parent, + struct led_classdev_mc *mcled_cdev) +{ + return led_classdev_multicolor_register_ext(parent, mcled_cdev, NULL); } static inline int devm_led_classdev_multicolor_register(struct device *parent, @@ -113,9 +106,4 @@ static inline int devm_led_classdev_multicolor_register(struct device *parent, NULL); } -static inline void devm_led_classdev_multicolor_unregister(struct device *parent, - struct led_classdev_mc *mcled_cdev) -{}; - -#endif /* IS_ENABLED(CONFIG_LEDS_CLASS_MULTICOLOR) */ #endif /* _LINUX_MULTICOLOR_LEDS_H_INCLUDED */ -- cgit v1.2.3 From 36950f2da1ea4cb683be174f6f581e25b2d33e71 Mon Sep 17 00:00:00 2001 From: Jianxiong Gao Date: Mon, 1 Feb 2021 10:30:15 -0800 Subject: driver core: add a min_align_mask field to struct device_dma_parameters Some devices rely on the address offset in a page to function correctly (NVMe driver as an example). These devices may use a different page size than the Linux kernel. The address offset has to be preserved upon mapping, and in order to do so, we need to record the page_offset_mask first. Signed-off-by: Jianxiong Gao Signed-off-by: Christoph Hellwig Acked-by: Greg Kroah-Hartman Signed-off-by: Konrad Rzeszutek Wilk --- include/linux/device.h | 1 + include/linux/dma-mapping.h | 16 ++++++++++++++++ 2 files changed, 17 insertions(+) (limited to 'include') diff --git a/include/linux/device.h b/include/linux/device.h index 1779f90eeb4c..7960bf516dd7 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -291,6 +291,7 @@ struct device_dma_parameters { * sg limitations. */ unsigned int max_segment_size; + unsigned int min_align_mask; unsigned long segment_boundary_mask; }; diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 2e49996a8f39..9c26225754e7 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -500,6 +500,22 @@ static inline int dma_set_seg_boundary(struct device *dev, unsigned long mask) return -EIO; } +static inline unsigned int dma_get_min_align_mask(struct device *dev) +{ + if (dev->dma_parms) + return dev->dma_parms->min_align_mask; + return 0; +} + +static inline int dma_set_min_align_mask(struct device *dev, + unsigned int min_align_mask) +{ + if (WARN_ON_ONCE(!dev->dma_parms)) + return -EIO; + dev->dma_parms->min_align_mask = min_align_mask; + return 0; +} + static inline int dma_get_cache_alignment(void) { #ifdef ARCH_DMA_MINALIGN -- cgit v1.2.3 From b5d7ccb7aac3895c2138fe0980a109116ce15eff Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 5 Feb 2021 11:18:40 +0100 Subject: swiotlb: add a IO_TLB_SIZE define Add a new IO_TLB_SIZE define instead open coding it using IO_TLB_SHIFT all over. Signed-off-by: Christoph Hellwig Acked-by: Jianxiong Gao Tested-by: Jianxiong Gao Signed-off-by: Konrad Rzeszutek Wilk --- include/linux/swiotlb.h | 1 + kernel/dma/swiotlb.c | 14 +++++++------- 2 files changed, 8 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index d9c9fc9ca5d2..5857a937c637 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -29,6 +29,7 @@ enum swiotlb_force { * controllable. */ #define IO_TLB_SHIFT 11 +#define IO_TLB_SIZE (1 << IO_TLB_SHIFT) /* default to 64MB */ #define IO_TLB_DEFAULT_SIZE (64UL<<20) diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 7c42df6e6100..768187d0e17e 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -171,7 +171,7 @@ void __init swiotlb_adjust_size(unsigned long new_size) * adjust/expand SWIOTLB size for their use. */ if (!io_tlb_nslabs) { - size = ALIGN(new_size, 1 << IO_TLB_SHIFT); + size = ALIGN(new_size, IO_TLB_SIZE); io_tlb_nslabs = size >> IO_TLB_SHIFT; io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE); @@ -491,20 +491,20 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t orig_addr, tbl_dma_addr &= mask; - offset_slots = ALIGN(tbl_dma_addr, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT; + offset_slots = ALIGN(tbl_dma_addr, IO_TLB_SIZE) >> IO_TLB_SHIFT; /* * Carefully handle integer overflow which can occur when mask == ~0UL. */ max_slots = mask + 1 - ? ALIGN(mask + 1, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT + ? ALIGN(mask + 1, IO_TLB_SIZE) >> IO_TLB_SHIFT : 1UL << (BITS_PER_LONG - IO_TLB_SHIFT); /* * For mappings greater than or equal to a page, we limit the stride * (and hence alignment) to a page size. */ - nslots = ALIGN(alloc_size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT; + nslots = ALIGN(alloc_size, IO_TLB_SIZE) >> IO_TLB_SHIFT; if (alloc_size >= PAGE_SIZE) stride = (1 << (PAGE_SHIFT - IO_TLB_SHIFT)); else @@ -598,7 +598,7 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, enum dma_data_direction dir, unsigned long attrs) { unsigned long flags; - int i, count, nslots = ALIGN(alloc_size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT; + int i, count, nslots = ALIGN(alloc_size, IO_TLB_SIZE) >> IO_TLB_SHIFT; int index = (tlb_addr - io_tlb_start) >> IO_TLB_SHIFT; phys_addr_t orig_addr = io_tlb_orig_addr[index]; @@ -649,7 +649,7 @@ void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr, if (orig_addr == INVALID_PHYS_ADDR) return; - orig_addr += (unsigned long)tlb_addr & ((1 << IO_TLB_SHIFT) - 1); + orig_addr += (unsigned long)tlb_addr & (IO_TLB_SIZE - 1); switch (target) { case SYNC_FOR_CPU: @@ -707,7 +707,7 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size, size_t swiotlb_max_mapping_size(struct device *dev) { - return ((size_t)1 << IO_TLB_SHIFT) * IO_TLB_SEGSIZE; + return ((size_t)IO_TLB_SIZE) * IO_TLB_SEGSIZE; } bool is_swiotlb_active(void) -- cgit v1.2.3 From 5aa75ed5b93f086c455a3c67239b0471ff5a1526 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 16 Feb 2021 12:56:50 -0700 Subject: io_uring: tie async worker side to the task context Move it outside of the io_ring_ctx, and tie it to the io_uring task context. Signed-off-by: Jens Axboe --- fs/io_uring.c | 84 ++++++++++++++++++++---------------------------- include/linux/io_uring.h | 1 + 2 files changed, 35 insertions(+), 50 deletions(-) (limited to 'include') diff --git a/fs/io_uring.c b/fs/io_uring.c index d6c2ff6124fd..31402a19fca6 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -366,9 +366,6 @@ struct io_ring_ctx { struct io_rings *rings; - /* IO offload */ - struct io_wq *io_wq; - /* * For SQPOLL usage - we hold a reference to the parent task, so we * have access to the ->files @@ -1634,10 +1631,11 @@ static struct io_kiocb *__io_queue_async_work(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; struct io_kiocb *link = io_prep_linked_timeout(req); + struct io_uring_task *tctx = req->task->io_uring; trace_io_uring_queue_async_work(ctx, io_wq_is_hashed(&req->work), req, &req->work, req->flags); - io_wq_enqueue(ctx->io_wq, &req->work); + io_wq_enqueue(tctx->io_wq, &req->work); return link; } @@ -5960,12 +5958,15 @@ static bool io_cancel_cb(struct io_wq_work *work, void *data) return req->user_data == (unsigned long) data; } -static int io_async_cancel_one(struct io_ring_ctx *ctx, void *sqe_addr) +static int io_async_cancel_one(struct io_uring_task *tctx, void *sqe_addr) { enum io_wq_cancel cancel_ret; int ret = 0; - cancel_ret = io_wq_cancel_cb(ctx->io_wq, io_cancel_cb, sqe_addr, false); + if (!tctx->io_wq) + return -ENOENT; + + cancel_ret = io_wq_cancel_cb(tctx->io_wq, io_cancel_cb, sqe_addr, false); switch (cancel_ret) { case IO_WQ_CANCEL_OK: ret = 0; @@ -5988,7 +5989,8 @@ static void io_async_find_and_cancel(struct io_ring_ctx *ctx, unsigned long flags; int ret; - ret = io_async_cancel_one(ctx, (void *) (unsigned long) sqe_addr); + ret = io_async_cancel_one(req->task->io_uring, + (void *) (unsigned long) sqe_addr); if (ret != -ENOENT) { spin_lock_irqsave(&ctx->completion_lock, flags); goto done; @@ -7537,16 +7539,6 @@ static void io_sq_thread_stop(struct io_ring_ctx *ctx) } } -static void io_finish_async(struct io_ring_ctx *ctx) -{ - io_sq_thread_stop(ctx); - - if (ctx->io_wq) { - io_wq_destroy(ctx->io_wq); - ctx->io_wq = NULL; - } -} - #if defined(CONFIG_UNIX) /* * Ensure the UNIX gc is aware of our file set, so we are certain that @@ -8105,11 +8097,10 @@ static struct io_wq_work *io_free_work(struct io_wq_work *work) return req ? &req->work : NULL; } -static int io_init_wq_offload(struct io_ring_ctx *ctx) +static struct io_wq *io_init_wq_offload(struct io_ring_ctx *ctx) { struct io_wq_data data; unsigned int concurrency; - int ret = 0; data.user = ctx->user; data.free_work = io_free_work; @@ -8118,16 +8109,11 @@ static int io_init_wq_offload(struct io_ring_ctx *ctx) /* Do QD, or 4 * CPUS, whatever is smallest */ concurrency = min(ctx->sq_entries, 4 * num_online_cpus()); - ctx->io_wq = io_wq_create(concurrency, &data); - if (IS_ERR(ctx->io_wq)) { - ret = PTR_ERR(ctx->io_wq); - ctx->io_wq = NULL; - } - - return ret; + return io_wq_create(concurrency, &data); } -static int io_uring_alloc_task_context(struct task_struct *task) +static int io_uring_alloc_task_context(struct task_struct *task, + struct io_ring_ctx *ctx) { struct io_uring_task *tctx; int ret; @@ -8142,6 +8128,14 @@ static int io_uring_alloc_task_context(struct task_struct *task) return ret; } + tctx->io_wq = io_init_wq_offload(ctx); + if (IS_ERR(tctx->io_wq)) { + ret = PTR_ERR(tctx->io_wq); + percpu_counter_destroy(&tctx->inflight); + kfree(tctx); + return ret; + } + xa_init(&tctx->xa); init_waitqueue_head(&tctx->wait); tctx->last = NULL; @@ -8214,7 +8208,7 @@ static int io_sq_offload_create(struct io_ring_ctx *ctx, ctx->sq_thread_idle = HZ; if (sqd->thread) - goto done; + return 0; if (p->flags & IORING_SETUP_SQ_AFF) { int cpu = p->sq_thread_cpu; @@ -8236,7 +8230,7 @@ static int io_sq_offload_create(struct io_ring_ctx *ctx, sqd->thread = NULL; goto err; } - ret = io_uring_alloc_task_context(sqd->thread); + ret = io_uring_alloc_task_context(sqd->thread, ctx); if (ret) goto err; } else if (p->flags & IORING_SETUP_SQ_AFF) { @@ -8245,14 +8239,9 @@ static int io_sq_offload_create(struct io_ring_ctx *ctx, goto err; } -done: - ret = io_init_wq_offload(ctx); - if (ret) - goto err; - return 0; err: - io_finish_async(ctx); + io_sq_thread_stop(ctx); return ret; } @@ -8727,7 +8716,7 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx) mutex_lock(&ctx->uring_lock); mutex_unlock(&ctx->uring_lock); - io_finish_async(ctx); + io_sq_thread_stop(ctx); io_sqe_buffers_unregister(ctx); if (ctx->sqo_task) { @@ -8870,13 +8859,6 @@ static void io_ring_exit_work(struct work_struct *work) io_ring_ctx_free(ctx); } -static bool io_cancel_ctx_cb(struct io_wq_work *work, void *data) -{ - struct io_kiocb *req = container_of(work, struct io_kiocb, work); - - return req->ctx == data; -} - static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) { mutex_lock(&ctx->uring_lock); @@ -8895,9 +8877,6 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) io_kill_timeouts(ctx, NULL, NULL); io_poll_remove_all(ctx, NULL, NULL); - if (ctx->io_wq) - io_wq_cancel_cb(ctx->io_wq, io_cancel_ctx_cb, ctx, true); - /* if we failed setting up the ctx, we might not have any rings */ io_iopoll_try_reap_events(ctx); @@ -8976,13 +8955,14 @@ static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx, struct files_struct *files) { struct io_task_cancel cancel = { .task = task, .files = files, }; + struct io_uring_task *tctx = current->io_uring; while (1) { enum io_wq_cancel cret; bool ret = false; - if (ctx->io_wq) { - cret = io_wq_cancel_cb(ctx->io_wq, io_cancel_task_cb, + if (tctx && tctx->io_wq) { + cret = io_wq_cancel_cb(tctx->io_wq, io_cancel_task_cb, &cancel, true); ret |= (cret != IO_WQ_CANCEL_NOTFOUND); } @@ -9094,7 +9074,7 @@ static int io_uring_add_task_file(struct io_ring_ctx *ctx, struct file *file) int ret; if (unlikely(!tctx)) { - ret = io_uring_alloc_task_context(current); + ret = io_uring_alloc_task_context(current, ctx); if (unlikely(ret)) return ret; tctx = current->io_uring; @@ -9164,8 +9144,12 @@ void __io_uring_files_cancel(struct files_struct *files) io_uring_cancel_task_requests(file->private_data, files); atomic_dec(&tctx->in_idle); - if (files) + if (files) { io_uring_remove_task_files(tctx); + } else if (tctx->io_wq && current->flags & PF_EXITING) { + io_wq_destroy(tctx->io_wq); + tctx->io_wq = NULL; + } } static s64 tctx_inflight(struct io_uring_task *tctx) diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 2eb6d19de336..0e95398998b6 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -36,6 +36,7 @@ struct io_uring_task { struct xarray xa; struct wait_queue_head wait; struct file *last; + void *io_wq; struct percpu_counter inflight; struct io_identity __identity; struct io_identity *identity; -- cgit v1.2.3 From 3bfe6106693b6b4ba175ad1f929c4660b8f59ca8 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 16 Feb 2021 14:15:30 -0700 Subject: io-wq: fork worker threads from original task Instead of using regular kthread kernel threads, create kernel threads that are like a real thread that the task would create. This ensures that we get all the context that we need, without having to carry that state around. This greatly reduces the code complexity, and the risk of missing state for a given request type. With the move away from kthread, we can also dump everything related to assigned state to the new threads. Signed-off-by: Jens Axboe --- fs/io-wq.c | 301 +++++++++++++++++--------------------------------- fs/io-wq.h | 3 +- fs/io_uring.c | 7 ++ include/linux/sched.h | 3 + 4 files changed, 116 insertions(+), 198 deletions(-) (limited to 'include') diff --git a/fs/io-wq.c b/fs/io-wq.c index ec7f1106b659..b53f569b5b4e 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -13,12 +13,9 @@ #include #include #include -#include #include -#include -#include -#include #include +#include #include "../kernel/sched/sched.h" #include "io-wq.h" @@ -57,13 +54,6 @@ struct io_worker { spinlock_t lock; struct rcu_head rcu; - struct mm_struct *mm; -#ifdef CONFIG_BLK_CGROUP - struct cgroup_subsys_state *blkcg_css; -#endif - const struct cred *cur_creds; - const struct cred *saved_creds; - struct nsproxy *restore_nsproxy; }; #if BITS_PER_LONG == 64 @@ -122,6 +112,8 @@ struct io_wq { struct completion done; struct hlist_node cpuhp_node; + + pid_t task_pid; }; static enum cpuhp_state io_wq_online; @@ -137,61 +129,6 @@ static void io_worker_release(struct io_worker *worker) wake_up_process(worker->task); } -/* - * Note: drops the wqe->lock if returning true! The caller must re-acquire - * the lock in that case. Some callers need to restart handling if this - * happens, so we can't just re-acquire the lock on behalf of the caller. - */ -static bool __io_worker_unuse(struct io_wqe *wqe, struct io_worker *worker) -{ - bool dropped_lock = false; - - if (worker->saved_creds) { - revert_creds(worker->saved_creds); - worker->cur_creds = worker->saved_creds = NULL; - } - - if (current->files) { - __acquire(&wqe->lock); - raw_spin_unlock_irq(&wqe->lock); - dropped_lock = true; - - task_lock(current); - current->files = NULL; - current->nsproxy = worker->restore_nsproxy; - task_unlock(current); - } - - if (current->fs) - current->fs = NULL; - - /* - * If we have an active mm, we need to drop the wq lock before unusing - * it. If we do, return true and let the caller retry the idle loop. - */ - if (worker->mm) { - if (!dropped_lock) { - __acquire(&wqe->lock); - raw_spin_unlock_irq(&wqe->lock); - dropped_lock = true; - } - __set_current_state(TASK_RUNNING); - kthread_unuse_mm(worker->mm); - mmput(worker->mm); - worker->mm = NULL; - } - -#ifdef CONFIG_BLK_CGROUP - if (worker->blkcg_css) { - kthread_associate_blkcg(NULL); - worker->blkcg_css = NULL; - } -#endif - if (current->signal->rlim[RLIMIT_FSIZE].rlim_cur != RLIM_INFINITY) - current->signal->rlim[RLIMIT_FSIZE].rlim_cur = RLIM_INFINITY; - return dropped_lock; -} - static inline struct io_wqe_acct *io_work_get_acct(struct io_wqe *wqe, struct io_wq_work *work) { @@ -237,10 +174,6 @@ static void io_worker_exit(struct io_worker *worker) raw_spin_lock_irq(&wqe->lock); hlist_nulls_del_rcu(&worker->nulls_node); list_del_rcu(&worker->all_list); - if (__io_worker_unuse(wqe, worker)) { - __release(&wqe->lock); - raw_spin_lock_irq(&wqe->lock); - } acct->nr_workers--; raw_spin_unlock_irq(&wqe->lock); @@ -323,14 +256,7 @@ static void io_wqe_dec_running(struct io_worker *worker) static void io_worker_start(struct io_worker *worker) { - allow_kernel_signal(SIGINT); - - current->flags |= PF_IO_WORKER; - current->fs = NULL; - current->files = NULL; - worker->flags |= (IO_WORKER_F_UP | IO_WORKER_F_RUNNING); - worker->restore_nsproxy = current->nsproxy; io_wqe_inc_running(worker); } @@ -387,7 +313,7 @@ static bool __io_worker_idle(struct io_wqe *wqe, struct io_worker *worker) hlist_nulls_add_head_rcu(&worker->nulls_node, &wqe->free_list); } - return __io_worker_unuse(wqe, worker); + return false; } static inline unsigned int io_get_work_hash(struct io_wq_work *work) @@ -426,96 +352,23 @@ static struct io_wq_work *io_get_next_work(struct io_wqe *wqe) return NULL; } -static void io_wq_switch_mm(struct io_worker *worker, struct io_wq_work *work) +static void io_flush_signals(void) { - if (worker->mm) { - kthread_unuse_mm(worker->mm); - mmput(worker->mm); - worker->mm = NULL; + if (unlikely(test_tsk_thread_flag(current, TIF_NOTIFY_SIGNAL))) { + if (current->task_works) + task_work_run(); + clear_tsk_thread_flag(current, TIF_NOTIFY_SIGNAL); } - - if (mmget_not_zero(work->identity->mm)) { - kthread_use_mm(work->identity->mm); - worker->mm = work->identity->mm; - return; - } - - /* failed grabbing mm, ensure work gets cancelled */ - work->flags |= IO_WQ_WORK_CANCEL; -} - -static inline void io_wq_switch_blkcg(struct io_worker *worker, - struct io_wq_work *work) -{ -#ifdef CONFIG_BLK_CGROUP - if (!(work->flags & IO_WQ_WORK_BLKCG)) - return; - if (work->identity->blkcg_css != worker->blkcg_css) { - kthread_associate_blkcg(work->identity->blkcg_css); - worker->blkcg_css = work->identity->blkcg_css; - } -#endif -} - -static void io_wq_switch_creds(struct io_worker *worker, - struct io_wq_work *work) -{ - const struct cred *old_creds = override_creds(work->identity->creds); - - worker->cur_creds = work->identity->creds; - if (worker->saved_creds) - put_cred(old_creds); /* creds set by previous switch */ - else - worker->saved_creds = old_creds; -} - -static void io_impersonate_work(struct io_worker *worker, - struct io_wq_work *work) -{ - if ((work->flags & IO_WQ_WORK_FILES) && - current->files != work->identity->files) { - task_lock(current); - current->files = work->identity->files; - current->nsproxy = work->identity->nsproxy; - task_unlock(current); - if (!work->identity->files) { - /* failed grabbing files, ensure work gets cancelled */ - work->flags |= IO_WQ_WORK_CANCEL; - } - } - if ((work->flags & IO_WQ_WORK_FS) && current->fs != work->identity->fs) - current->fs = work->identity->fs; - if ((work->flags & IO_WQ_WORK_MM) && work->identity->mm != worker->mm) - io_wq_switch_mm(worker, work); - if ((work->flags & IO_WQ_WORK_CREDS) && - worker->cur_creds != work->identity->creds) - io_wq_switch_creds(worker, work); - if (work->flags & IO_WQ_WORK_FSIZE) - current->signal->rlim[RLIMIT_FSIZE].rlim_cur = work->identity->fsize; - else if (current->signal->rlim[RLIMIT_FSIZE].rlim_cur != RLIM_INFINITY) - current->signal->rlim[RLIMIT_FSIZE].rlim_cur = RLIM_INFINITY; - io_wq_switch_blkcg(worker, work); -#ifdef CONFIG_AUDIT - current->loginuid = work->identity->loginuid; - current->sessionid = work->identity->sessionid; -#endif } static void io_assign_current_work(struct io_worker *worker, struct io_wq_work *work) { if (work) { - /* flush pending signals before assigning new work */ - if (signal_pending(current)) - flush_signals(current); + io_flush_signals(); cond_resched(); } -#ifdef CONFIG_AUDIT - current->loginuid = KUIDT_INIT(AUDIT_UID_UNSET); - current->sessionid = AUDIT_SID_UNSET; -#endif - spin_lock_irq(&worker->lock); worker->cur_work = work; spin_unlock_irq(&worker->lock); @@ -556,7 +409,6 @@ get_next: unsigned int hash = io_get_work_hash(work); next_hashed = wq_next_work(work); - io_impersonate_work(worker, work); wq->do_work(work); io_assign_current_work(worker, NULL); @@ -608,10 +460,11 @@ loop: goto loop; } raw_spin_unlock_irq(&wqe->lock); - if (signal_pending(current)) - flush_signals(current); + io_flush_signals(); if (schedule_timeout(WORKER_IDLE_TIMEOUT)) continue; + if (fatal_signal_pending(current)) + break; /* timed out, exit unless we're the fixed worker */ if (test_bit(IO_WQ_BIT_EXIT, &wq->state) || !(worker->flags & IO_WORKER_F_FIXED)) @@ -635,8 +488,10 @@ loop: */ void io_wq_worker_running(struct task_struct *tsk) { - struct io_worker *worker = kthread_data(tsk); + struct io_worker *worker = tsk->pf_io_worker; + if (!worker) + return; if (!(worker->flags & IO_WORKER_F_UP)) return; if (worker->flags & IO_WORKER_F_RUNNING) @@ -652,9 +507,10 @@ void io_wq_worker_running(struct task_struct *tsk) */ void io_wq_worker_sleeping(struct task_struct *tsk) { - struct io_worker *worker = kthread_data(tsk); - struct io_wqe *wqe = worker->wqe; + struct io_worker *worker = tsk->pf_io_worker; + if (!worker) + return; if (!(worker->flags & IO_WORKER_F_UP)) return; if (!(worker->flags & IO_WORKER_F_RUNNING)) @@ -662,32 +518,27 @@ void io_wq_worker_sleeping(struct task_struct *tsk) worker->flags &= ~IO_WORKER_F_RUNNING; - raw_spin_lock_irq(&wqe->lock); + raw_spin_lock_irq(&worker->wqe->lock); io_wqe_dec_running(worker); - raw_spin_unlock_irq(&wqe->lock); + raw_spin_unlock_irq(&worker->wqe->lock); } -static bool create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index) +static int task_thread(void *data, int index) { + struct io_worker *worker = data; + struct io_wqe *wqe = worker->wqe; struct io_wqe_acct *acct = &wqe->acct[index]; - struct io_worker *worker; + struct io_wq *wq = wqe->wq; + char buf[TASK_COMM_LEN]; - worker = kzalloc_node(sizeof(*worker), GFP_KERNEL, wqe->node); - if (!worker) - return false; + sprintf(buf, "iou-wrk-%d", wq->task_pid); + set_task_comm(current, buf); - refcount_set(&worker->ref, 1); - worker->nulls_node.pprev = NULL; - worker->wqe = wqe; - spin_lock_init(&worker->lock); + current->pf_io_worker = worker; + worker->task = current; - worker->task = kthread_create_on_node(io_wqe_worker, worker, wqe->node, - "io_wqe_worker-%d/%d", index, wqe->node); - if (IS_ERR(worker->task)) { - kfree(worker); - return false; - } - kthread_bind_mask(worker->task, cpumask_of_node(wqe->node)); + set_cpus_allowed_ptr(current, cpumask_of_node(wqe->node)); + current->flags |= PF_NO_SETAFFINITY; raw_spin_lock_irq(&wqe->lock); hlist_nulls_add_head_rcu(&worker->nulls_node, &wqe->free_list); @@ -703,8 +554,58 @@ static bool create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index) if (index == IO_WQ_ACCT_UNBOUND) atomic_inc(&wq->user->processes); + io_wqe_worker(data); + do_exit(0); +} + +static int task_thread_bound(void *data) +{ + return task_thread(data, IO_WQ_ACCT_BOUND); +} + +static int task_thread_unbound(void *data) +{ + return task_thread(data, IO_WQ_ACCT_UNBOUND); +} + +static pid_t fork_thread(int (*fn)(void *), void *arg) +{ + unsigned long flags = CLONE_FS|CLONE_FILES|CLONE_SIGHAND|CLONE_THREAD| + CLONE_IO|SIGCHLD; + struct kernel_clone_args args = { + .flags = ((lower_32_bits(flags) | CLONE_VM | + CLONE_UNTRACED) & ~CSIGNAL), + .exit_signal = (lower_32_bits(flags) & CSIGNAL), + .stack = (unsigned long)fn, + .stack_size = (unsigned long)arg, + }; + + return kernel_clone(&args); +} + +static bool create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index) +{ + struct io_worker *worker; + pid_t pid; + + worker = kzalloc_node(sizeof(*worker), GFP_KERNEL, wqe->node); + if (!worker) + return false; + + refcount_set(&worker->ref, 1); + worker->nulls_node.pprev = NULL; + worker->wqe = wqe; + spin_lock_init(&worker->lock); + + if (index == IO_WQ_ACCT_BOUND) + pid = fork_thread(task_thread_bound, worker); + else + pid = fork_thread(task_thread_unbound, worker); + if (pid < 0) { + kfree(worker); + return false; + } refcount_inc(&wq->refs); - wake_up_process(worker->task); return true; } @@ -756,12 +657,17 @@ static bool io_wq_worker_wake(struct io_worker *worker, void *data) static int io_wq_manager(void *data) { struct io_wq *wq = data; + char buf[TASK_COMM_LEN]; int node; - refcount_set(&wq->refs, 1); + sprintf(buf, "iou-mgr-%d", wq->task_pid); + set_task_comm(current, buf); + current->flags |= PF_IO_WORKER; + wq->manager = current; + complete(&wq->done); - while (!kthread_should_stop()) { + while (!test_bit(IO_WQ_BIT_EXIT, &wq->state)) { for_each_node(node) { struct io_wqe *wqe = wq->wqes[node]; bool fork_worker[2] = { false, false }; @@ -782,11 +688,13 @@ static int io_wq_manager(void *data) } set_current_state(TASK_INTERRUPTIBLE); schedule_timeout(HZ); + if (fatal_signal_pending(current)) + set_bit(IO_WQ_BIT_EXIT, &wq->state); } if (refcount_dec_and_test(&wq->refs)) { complete(&wq->done); - return 0; + do_exit(0); } /* if ERROR is set and we get here, we have workers to wake */ if (test_bit(IO_WQ_BIT_ERROR, &wq->state)) { @@ -795,7 +703,7 @@ static int io_wq_manager(void *data) io_wq_for_each_worker(wq->wqes[node], io_wq_worker_wake, NULL); rcu_read_unlock(); } - return 0; + do_exit(0); } static bool io_wq_can_queue(struct io_wqe *wqe, struct io_wqe_acct *acct, @@ -919,7 +827,7 @@ static bool io_wq_worker_cancel(struct io_worker *worker, void *data) spin_lock_irqsave(&worker->lock, flags); if (worker->cur_work && match->fn(worker->cur_work, match->data)) { - send_sig(SIGINT, worker->task, 1); + set_notify_signal(worker->task); match->nr_running++; } spin_unlock_irqrestore(&worker->lock, flags); @@ -1075,22 +983,21 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data) INIT_LIST_HEAD(&wqe->all_list); } + wq->task_pid = current->pid; init_completion(&wq->done); + refcount_set(&wq->refs, 1); - wq->manager = kthread_create(io_wq_manager, wq, "io_wq_manager"); - if (!IS_ERR(wq->manager)) { - wake_up_process(wq->manager); + current->flags |= PF_IO_WORKER; + ret = fork_thread(io_wq_manager, wq); + current->flags &= ~PF_IO_WORKER; + if (ret >= 0) { wait_for_completion(&wq->done); - if (test_bit(IO_WQ_BIT_ERROR, &wq->state)) { - ret = -ENOMEM; - goto err; - } reinit_completion(&wq->done); return wq; } - ret = PTR_ERR(wq->manager); - complete(&wq->done); + if (refcount_dec_and_test(&wq->refs)) + complete(&wq->done); err: cpuhp_state_remove_instance_nocalls(io_wq_online, &wq->cpuhp_node); for_each_node(node) @@ -1110,7 +1017,7 @@ void io_wq_destroy(struct io_wq *wq) set_bit(IO_WQ_BIT_EXIT, &wq->state); if (wq->manager) - kthread_stop(wq->manager); + wake_up_process(wq->manager); rcu_read_lock(); for_each_node(node) diff --git a/fs/io-wq.h b/fs/io-wq.h index d2cf284b4641..83d56adabd16 100644 --- a/fs/io-wq.h +++ b/fs/io-wq.h @@ -137,6 +137,7 @@ static inline void io_wq_worker_running(struct task_struct *tsk) static inline bool io_wq_current_is_worker(void) { - return in_task() && (current->flags & PF_IO_WORKER); + return in_task() && (current->flags & PF_IO_WORKER) && + current->pf_io_worker; } #endif diff --git a/fs/io_uring.c b/fs/io_uring.c index 31402a19fca6..9d22ec9d9406 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1633,6 +1633,9 @@ static struct io_kiocb *__io_queue_async_work(struct io_kiocb *req) struct io_kiocb *link = io_prep_linked_timeout(req); struct io_uring_task *tctx = req->task->io_uring; + BUG_ON(!tctx); + BUG_ON(!tctx->io_wq); + trace_io_uring_queue_async_work(ctx, io_wq_is_hashed(&req->work), req, &req->work, req->flags); io_wq_enqueue(tctx->io_wq, &req->work); @@ -9240,6 +9243,10 @@ static int io_uring_flush(struct file *file, void *data) struct io_uring_task *tctx = current->io_uring; struct io_ring_ctx *ctx = file->private_data; + /* Ignore helper thread files exit */ + if (current->flags & PF_IO_WORKER) + return 0; + if (fatal_signal_pending(current) || (current->flags & PF_EXITING)) { io_uring_cancel_task_requests(ctx, NULL); io_req_caches_free(ctx, current); diff --git a/include/linux/sched.h b/include/linux/sched.h index 26f499810dfa..ef00bb22164c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -895,6 +895,9 @@ struct task_struct { /* CLONE_CHILD_CLEARTID: */ int __user *clear_child_tid; + /* PF_IO_WORKER */ + void *pf_io_worker; + u64 utime; u64 stime; #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME -- cgit v1.2.3 From 4379bf8bd70b5de6bba7d53015b0c36c57a634ee Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 15 Feb 2021 13:40:22 -0700 Subject: io_uring: remove io_identity We are no longer grabbing state, so no need to maintain an IO identity that we COW if there are changes. Signed-off-by: Jens Axboe --- fs/io-wq.c | 26 ++++++++++++ fs/io-wq.h | 2 +- fs/io_uring.c | 104 ++++++++++++----------------------------------- include/linux/io_uring.h | 19 --------- 4 files changed, 52 insertions(+), 99 deletions(-) (limited to 'include') diff --git a/fs/io-wq.c b/fs/io-wq.c index 41042119bf0f..acc67ed3a52c 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -53,6 +53,9 @@ struct io_worker { struct io_wq_work *cur_work; spinlock_t lock; + const struct cred *cur_creds; + const struct cred *saved_creds; + struct rcu_head rcu; }; @@ -171,6 +174,11 @@ static void io_worker_exit(struct io_worker *worker) worker->flags = 0; preempt_enable(); + if (worker->saved_creds) { + revert_creds(worker->saved_creds); + worker->cur_creds = worker->saved_creds = NULL; + } + raw_spin_lock_irq(&wqe->lock); hlist_nulls_del_rcu(&worker->nulls_node); list_del_rcu(&worker->all_list); @@ -312,6 +320,10 @@ static void __io_worker_idle(struct io_wqe *wqe, struct io_worker *worker) worker->flags |= IO_WORKER_F_FREE; hlist_nulls_add_head_rcu(&worker->nulls_node, &wqe->free_list); } + if (worker->saved_creds) { + revert_creds(worker->saved_creds); + worker->cur_creds = worker->saved_creds = NULL; + } } static inline unsigned int io_get_work_hash(struct io_wq_work *work) @@ -359,6 +371,18 @@ static void io_flush_signals(void) } } +static void io_wq_switch_creds(struct io_worker *worker, + struct io_wq_work *work) +{ + const struct cred *old_creds = override_creds(work->creds); + + worker->cur_creds = work->creds; + if (worker->saved_creds) + put_cred(old_creds); /* creds set by previous switch */ + else + worker->saved_creds = old_creds; +} + static void io_assign_current_work(struct io_worker *worker, struct io_wq_work *work) { @@ -407,6 +431,8 @@ get_next: unsigned int hash = io_get_work_hash(work); next_hashed = wq_next_work(work); + if (work->creds && worker->cur_creds != work->creds) + io_wq_switch_creds(worker, work); wq->do_work(work); io_assign_current_work(worker, NULL); diff --git a/fs/io-wq.h b/fs/io-wq.h index bbe05dd54716..584f0bd5a83d 100644 --- a/fs/io-wq.h +++ b/fs/io-wq.h @@ -78,7 +78,7 @@ static inline void wq_list_del(struct io_wq_work_list *list, struct io_wq_work { struct io_wq_work_node list; - struct io_identity *identity; + const struct cred *creds; unsigned flags; }; diff --git a/fs/io_uring.c b/fs/io_uring.c index 6e88295758b5..6d851033e48d 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1094,7 +1094,7 @@ static bool io_match_task(struct io_kiocb *head, continue; if (req->file && req->file->f_op == &io_uring_fops) return true; - if (req->work.identity->files == files) + if (req->task->files == files) return true; } return false; @@ -1218,31 +1218,6 @@ static inline void req_set_fail_links(struct io_kiocb *req) req->flags |= REQ_F_FAIL_LINK; } -/* - * None of these are dereferenced, they are simply used to check if any of - * them have changed. If we're under current and check they are still the - * same, we're fine to grab references to them for actual out-of-line use. - */ -static void io_init_identity(struct io_identity *id) -{ - id->files = current->files; - id->mm = current->mm; -#ifdef CONFIG_BLK_CGROUP - rcu_read_lock(); - id->blkcg_css = blkcg_css(); - rcu_read_unlock(); -#endif - id->creds = current_cred(); - id->nsproxy = current->nsproxy; - id->fs = current->fs; - id->fsize = rlimit(RLIMIT_FSIZE); -#ifdef CONFIG_AUDIT - id->loginuid = current->loginuid; - id->sessionid = current->sessionid; -#endif - refcount_set(&id->count, 1); -} - static inline void __io_req_init_async(struct io_kiocb *req) { memset(&req->work, 0, sizeof(req->work)); @@ -1255,17 +1230,10 @@ static inline void __io_req_init_async(struct io_kiocb *req) */ static inline void io_req_init_async(struct io_kiocb *req) { - struct io_uring_task *tctx = current->io_uring; - if (req->flags & REQ_F_WORK_INITIALIZED) return; __io_req_init_async(req); - - /* Grab a ref if this isn't our static identity */ - req->work.identity = tctx->identity; - if (tctx->identity != &tctx->__identity) - refcount_inc(&req->work.identity->count); } static void io_ring_ctx_ref_free(struct percpu_ref *ref) @@ -1350,19 +1318,15 @@ static bool req_need_defer(struct io_kiocb *req, u32 seq) return false; } -static void io_put_identity(struct io_uring_task *tctx, struct io_kiocb *req) -{ - if (req->work.identity == &tctx->__identity) - return; - if (refcount_dec_and_test(&req->work.identity->count)) - kfree(req->work.identity); -} - static void io_req_clean_work(struct io_kiocb *req) { if (!(req->flags & REQ_F_WORK_INITIALIZED)) return; + if (req->work.creds) { + put_cred(req->work.creds); + req->work.creds = NULL; + } if (req->flags & REQ_F_INFLIGHT) { struct io_ring_ctx *ctx = req->ctx; struct io_uring_task *tctx = req->task->io_uring; @@ -1377,7 +1341,6 @@ static void io_req_clean_work(struct io_kiocb *req) } req->flags &= ~REQ_F_WORK_INITIALIZED; - io_put_identity(req->task->io_uring, req); } static void io_req_track_inflight(struct io_kiocb *req) @@ -1411,6 +1374,8 @@ static void io_prep_async_work(struct io_kiocb *req) if (def->unbound_nonreg_file) req->work.flags |= IO_WQ_WORK_UNBOUND; } + if (!req->work.creds) + req->work.creds = get_current_cred(); } static void io_prep_async_link(struct io_kiocb *req) @@ -6376,9 +6341,9 @@ static void __io_queue_sqe(struct io_kiocb *req) const struct cred *old_creds = NULL; int ret; - if ((req->flags & REQ_F_WORK_INITIALIZED) && - req->work.identity->creds != current_cred()) - old_creds = override_creds(req->work.identity->creds); + if ((req->flags & REQ_F_WORK_INITIALIZED) && req->work.creds && + req->work.creds != current_cred()) + old_creds = override_creds(req->work.creds); ret = io_issue_sqe(req, IO_URING_F_NONBLOCK|IO_URING_F_COMPLETE_DEFER); @@ -6508,16 +6473,11 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, id = READ_ONCE(sqe->personality); if (id) { - struct io_identity *iod; - - iod = idr_find(&ctx->personality_idr, id); - if (unlikely(!iod)) - return -EINVAL; - refcount_inc(&iod->count); - __io_req_init_async(req); - get_cred(iod->creds); - req->work.identity = iod; + req->work.creds = idr_find(&ctx->personality_idr, id); + if (unlikely(!req->work.creds)) + return -EINVAL; + get_cred(req->work.creds); } state = &ctx->submit_state; @@ -7936,8 +7896,6 @@ static int io_uring_alloc_task_context(struct task_struct *task, tctx->last = NULL; atomic_set(&tctx->in_idle, 0); tctx->sqpoll = false; - io_init_identity(&tctx->__identity); - tctx->identity = &tctx->__identity; task->io_uring = tctx; spin_lock_init(&tctx->task_lock); INIT_WQ_LIST(&tctx->task_list); @@ -7951,9 +7909,6 @@ void __io_uring_free(struct task_struct *tsk) struct io_uring_task *tctx = tsk->io_uring; WARN_ON_ONCE(!xa_empty(&tctx->xa)); - WARN_ON_ONCE(refcount_read(&tctx->identity->count) != 1); - if (tctx->identity != &tctx->__identity) - kfree(tctx->identity); percpu_counter_destroy(&tctx->inflight); kfree(tctx); tsk->io_uring = NULL; @@ -8593,13 +8548,11 @@ static int io_uring_fasync(int fd, struct file *file, int on) static int io_unregister_personality(struct io_ring_ctx *ctx, unsigned id) { - struct io_identity *iod; + const struct cred *creds; - iod = idr_remove(&ctx->personality_idr, id); - if (iod) { - put_cred(iod->creds); - if (refcount_dec_and_test(&iod->count)) - kfree(iod); + creds = idr_remove(&ctx->personality_idr, id); + if (creds) { + put_cred(creds); return 0; } @@ -9300,8 +9253,7 @@ out_fput: #ifdef CONFIG_PROC_FS static int io_uring_show_cred(int id, void *p, void *data) { - struct io_identity *iod = p; - const struct cred *cred = iod->creds; + const struct cred *cred = p; struct seq_file *m = data; struct user_namespace *uns = seq_user_ns(m); struct group_info *gi; @@ -9732,21 +9684,15 @@ out: static int io_register_personality(struct io_ring_ctx *ctx) { - struct io_identity *id; + const struct cred *creds; int ret; - id = kmalloc(sizeof(*id), GFP_KERNEL); - if (unlikely(!id)) - return -ENOMEM; - - io_init_identity(id); - id->creds = get_current_cred(); + creds = get_current_cred(); - ret = idr_alloc_cyclic(&ctx->personality_idr, id, 1, USHRT_MAX, GFP_KERNEL); - if (ret < 0) { - put_cred(id->creds); - kfree(id); - } + ret = idr_alloc_cyclic(&ctx->personality_idr, (void *) creds, 1, + USHRT_MAX, GFP_KERNEL); + if (ret < 0) + put_cred(creds); return ret; } diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 0e95398998b6..c48fcbdc2ea8 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -5,23 +5,6 @@ #include #include -struct io_identity { - struct files_struct *files; - struct mm_struct *mm; -#ifdef CONFIG_BLK_CGROUP - struct cgroup_subsys_state *blkcg_css; -#endif - const struct cred *creds; - struct nsproxy *nsproxy; - struct fs_struct *fs; - unsigned long fsize; -#ifdef CONFIG_AUDIT - kuid_t loginuid; - unsigned int sessionid; -#endif - refcount_t count; -}; - struct io_wq_work_node { struct io_wq_work_node *next; }; @@ -38,8 +21,6 @@ struct io_uring_task { struct file *last; void *io_wq; struct percpu_counter inflight; - struct io_identity __identity; - struct io_identity *identity; atomic_t in_idle; bool sqpoll; -- cgit v1.2.3 From 2596b6ae412be3d29632efc63976a2132032e620 Mon Sep 17 00:00:00 2001 From: Pavel Tatashin Date: Fri, 19 Feb 2021 14:51:42 -0500 Subject: kexec: move machine_kexec_post_load() to public interface The kernel test robot reports the following compiler warning: | arch/arm64/kernel/machine_kexec.c:62:5: warning: no previous prototype for | function 'machine_kexec_post_load' [-Wmissing-prototypes] | int machine_kexec_post_load(struct kimage *kimage) Fix it by moving the declaration of machine_kexec_post_load() from kexec_internal.h to the public header instead. Reported-by: kernel test robot Link: https://lore.kernel.org/linux-arm-kernel/202102030727.gqTokACH-lkp@intel.com Signed-off-by: Pavel Tatashin Link: https://lore.kernel.org/r/20210219195142.13571-1-pasha.tatashin@soleen.com Fixes: 4c3c31230c91 ("arm64: kexec: move relocation function setup") Signed-off-by: Will Deacon --- include/linux/kexec.h | 2 ++ kernel/kexec_internal.h | 2 -- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 9e93bef52968..3671b845cf28 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -309,6 +309,8 @@ extern void machine_kexec_cleanup(struct kimage *image); extern int kernel_kexec(void); extern struct page *kimage_alloc_control_pages(struct kimage *image, unsigned int order); +int machine_kexec_post_load(struct kimage *image); + extern void __crash_kexec(struct pt_regs *); extern void crash_kexec(struct pt_regs *); int kexec_should_crash(struct task_struct *); diff --git a/kernel/kexec_internal.h b/kernel/kexec_internal.h index 39d30ccf8d87..48aaf2ac0d0d 100644 --- a/kernel/kexec_internal.h +++ b/kernel/kexec_internal.h @@ -13,8 +13,6 @@ void kimage_terminate(struct kimage *image); int kimage_is_destination_range(struct kimage *image, unsigned long start, unsigned long end); -int machine_kexec_post_load(struct kimage *image); - extern struct mutex kexec_mutex; #ifdef CONFIG_KEXEC_FILE -- cgit v1.2.3 From 9fb407179c6fd910005040bebb040094ef959b6c Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Sun, 21 Feb 2021 18:28:05 -0800 Subject: block: Remove unused blk_pm_*() function definitions Commit a1ce35fa4985 ("block: remove dead elevator code") removed the last callers of blk_pm_requeue_request(), blk_pm_add_request() and blk_pm_put_request(). Hence remove the definitions of these functions. Removing these functions removes all users of the struct request nr_pending member. Hence also remove 'nr_pending'. Note: 'nr_pending' is no longer used since commit 7cedffec8e75 ("block: Make blk_get_request() block for non-PM requests while suspended"). Cc: Alan Stern Cc: Christoph Hellwig Signed-off-by: Bart Van Assche Reviewed-by: Chaitanya Kulkarni Signed-off-by: Jens Axboe --- block/blk-pm.h | 38 -------------------------------------- include/linux/blkdev.h | 1 - 2 files changed, 39 deletions(-) (limited to 'include') diff --git a/block/blk-pm.h b/block/blk-pm.h index a2283cc9f716..8a5a0d4b357f 100644 --- a/block/blk-pm.h +++ b/block/blk-pm.h @@ -21,31 +21,6 @@ static inline void blk_pm_mark_last_busy(struct request *rq) if (rq->q->dev && !(rq->rq_flags & RQF_PM)) pm_runtime_mark_last_busy(rq->q->dev); } - -static inline void blk_pm_requeue_request(struct request *rq) -{ - lockdep_assert_held(&rq->q->queue_lock); - - if (rq->q->dev && !(rq->rq_flags & RQF_PM)) - rq->q->nr_pending--; -} - -static inline void blk_pm_add_request(struct request_queue *q, - struct request *rq) -{ - lockdep_assert_held(&q->queue_lock); - - if (q->dev && !(rq->rq_flags & RQF_PM)) - q->nr_pending++; -} - -static inline void blk_pm_put_request(struct request *rq) -{ - lockdep_assert_held(&rq->q->queue_lock); - - if (rq->q->dev && !(rq->rq_flags & RQF_PM)) - --rq->q->nr_pending; -} #else static inline int blk_pm_resume_queue(const bool pm, struct request_queue *q) { @@ -55,19 +30,6 @@ static inline int blk_pm_resume_queue(const bool pm, struct request_queue *q) static inline void blk_pm_mark_last_busy(struct request *rq) { } - -static inline void blk_pm_requeue_request(struct request *rq) -{ -} - -static inline void blk_pm_add_request(struct request_queue *q, - struct request *rq) -{ -} - -static inline void blk_pm_put_request(struct request *rq) -{ -} #endif #endif /* _BLOCK_BLK_PM_H_ */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 9149f4a5adb3..f2e0697258b8 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -462,7 +462,6 @@ struct request_queue { #ifdef CONFIG_PM struct device *dev; enum rpm_status rpm_status; - unsigned int nr_pending; #endif /* -- cgit v1.2.3 From 179d1600723670dc0d6ae8ce572e0e2c44b64763 Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Sun, 21 Feb 2021 21:29:55 -0800 Subject: block: remove superfluous param in blk_fill_rwbs() The last parameter for the function blk_fill_rwbs() was added in 5782138e47 ("tracing/events: convert block trace points to TRACE_EVENT()") in order to signal read request and use of that parameter was replaced with using switch case REQ_OP_READ with 1b9a9ab78b0 ("blktrace: use op accessors"), but the parameter was never removed. Remove the unused parameter and adjust the respective call sites. Fixes: 1b9a9ab78b0 ("blktrace: use op accessors") Signed-off-by: Chaitanya Kulkarni Reviewed-by: Johannes Thumshirn Reviewed-by: Damien Le Moal Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blktrace_api.h | 2 +- include/trace/events/bcache.h | 10 +++++----- include/trace/events/block.h | 16 ++++++++-------- kernel/trace/blktrace.c | 2 +- 4 files changed, 15 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 05556573b896..11484f1d19a1 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -119,7 +119,7 @@ struct compat_blk_user_trace_setup { #endif -extern void blk_fill_rwbs(char *rwbs, unsigned int op, int bytes); +extern void blk_fill_rwbs(char *rwbs, unsigned int op); static inline sector_t blk_rq_trace_sector(struct request *rq) { diff --git a/include/trace/events/bcache.h b/include/trace/events/bcache.h index e41c611d6d3b..899fdacf57b9 100644 --- a/include/trace/events/bcache.h +++ b/include/trace/events/bcache.h @@ -28,7 +28,7 @@ DECLARE_EVENT_CLASS(bcache_request, __entry->sector = bio->bi_iter.bi_sector; __entry->orig_sector = bio->bi_iter.bi_sector - 16; __entry->nr_sector = bio->bi_iter.bi_size >> 9; - blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size); + blk_fill_rwbs(__entry->rwbs, bio->bi_opf); ), TP_printk("%d,%d %s %llu + %u (from %d,%d @ %llu)", @@ -102,7 +102,7 @@ DECLARE_EVENT_CLASS(bcache_bio, __entry->dev = bio_dev(bio); __entry->sector = bio->bi_iter.bi_sector; __entry->nr_sector = bio->bi_iter.bi_size >> 9; - blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size); + blk_fill_rwbs(__entry->rwbs, bio->bi_opf); ), TP_printk("%d,%d %s %llu + %u", @@ -137,7 +137,7 @@ TRACE_EVENT(bcache_read, __entry->dev = bio_dev(bio); __entry->sector = bio->bi_iter.bi_sector; __entry->nr_sector = bio->bi_iter.bi_size >> 9; - blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size); + blk_fill_rwbs(__entry->rwbs, bio->bi_opf); __entry->cache_hit = hit; __entry->bypass = bypass; ), @@ -168,7 +168,7 @@ TRACE_EVENT(bcache_write, __entry->inode = inode; __entry->sector = bio->bi_iter.bi_sector; __entry->nr_sector = bio->bi_iter.bi_size >> 9; - blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size); + blk_fill_rwbs(__entry->rwbs, bio->bi_opf); __entry->writeback = writeback; __entry->bypass = bypass; ), @@ -238,7 +238,7 @@ TRACE_EVENT(bcache_journal_write, __entry->sector = bio->bi_iter.bi_sector; __entry->nr_sector = bio->bi_iter.bi_size >> 9; __entry->nr_keys = keys; - blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size); + blk_fill_rwbs(__entry->rwbs, bio->bi_opf); ), TP_printk("%d,%d %s %llu + %u keys %u", diff --git a/include/trace/events/block.h b/include/trace/events/block.h index 0d782663a005..879cba8bdfca 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -89,7 +89,7 @@ TRACE_EVENT(block_rq_requeue, __entry->sector = blk_rq_trace_sector(rq); __entry->nr_sector = blk_rq_trace_nr_sectors(rq); - blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, blk_rq_bytes(rq)); + blk_fill_rwbs(__entry->rwbs, rq->cmd_flags); __get_str(cmd)[0] = '\0'; ), @@ -133,7 +133,7 @@ TRACE_EVENT(block_rq_complete, __entry->nr_sector = nr_bytes >> 9; __entry->error = error; - blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, nr_bytes); + blk_fill_rwbs(__entry->rwbs, rq->cmd_flags); __get_str(cmd)[0] = '\0'; ), @@ -166,7 +166,7 @@ DECLARE_EVENT_CLASS(block_rq, __entry->nr_sector = blk_rq_trace_nr_sectors(rq); __entry->bytes = blk_rq_bytes(rq); - blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, blk_rq_bytes(rq)); + blk_fill_rwbs(__entry->rwbs, rq->cmd_flags); __get_str(cmd)[0] = '\0'; memcpy(__entry->comm, current->comm, TASK_COMM_LEN); ), @@ -249,7 +249,7 @@ TRACE_EVENT(block_bio_complete, __entry->sector = bio->bi_iter.bi_sector; __entry->nr_sector = bio_sectors(bio); __entry->error = blk_status_to_errno(bio->bi_status); - blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size); + blk_fill_rwbs(__entry->rwbs, bio->bi_opf); ), TP_printk("%d,%d %s %llu + %u [%d]", @@ -276,7 +276,7 @@ DECLARE_EVENT_CLASS(block_bio, __entry->dev = bio_dev(bio); __entry->sector = bio->bi_iter.bi_sector; __entry->nr_sector = bio_sectors(bio); - blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size); + blk_fill_rwbs(__entry->rwbs, bio->bi_opf); memcpy(__entry->comm, current->comm, TASK_COMM_LEN); ), @@ -433,7 +433,7 @@ TRACE_EVENT(block_split, __entry->dev = bio_dev(bio); __entry->sector = bio->bi_iter.bi_sector; __entry->new_sector = new_sector; - blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size); + blk_fill_rwbs(__entry->rwbs, bio->bi_opf); memcpy(__entry->comm, current->comm, TASK_COMM_LEN); ), @@ -474,7 +474,7 @@ TRACE_EVENT(block_bio_remap, __entry->nr_sector = bio_sectors(bio); __entry->old_dev = dev; __entry->old_sector = from; - blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size); + blk_fill_rwbs(__entry->rwbs, bio->bi_opf); ), TP_printk("%d,%d %s %llu + %u <- (%d,%d) %llu", @@ -518,7 +518,7 @@ TRACE_EVENT(block_rq_remap, __entry->old_dev = dev; __entry->old_sector = from; __entry->nr_bios = blk_rq_count_bios(rq); - blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, blk_rq_bytes(rq)); + blk_fill_rwbs(__entry->rwbs, rq->cmd_flags); ), TP_printk("%d,%d %s %llu + %u <- (%d,%d) %llu %u", diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 9e9ee4945043..8a2591c7aa41 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -1867,7 +1867,7 @@ void blk_trace_remove_sysfs(struct device *dev) #ifdef CONFIG_EVENT_TRACING -void blk_fill_rwbs(char *rwbs, unsigned int op, int bytes) +void blk_fill_rwbs(char *rwbs, unsigned int op) { int i = 0; -- cgit v1.2.3 From 1f83bb4b491472310ae7aeca505ed3725149906c Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Sun, 21 Feb 2021 21:29:56 -0800 Subject: blktrace: add blk_fill_rwbs documentation comment blk_fill_rwbs() is an expoted function, add kernel style documentation comment. Signed-off-by: Chaitanya Kulkarni Reviewed-by: Johannes Thumshirn Reviewed-by: Damien Le Moal Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blktrace_api.h | 2 +- kernel/trace/blktrace.c | 10 ++++++++++ 2 files changed, 11 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 11484f1d19a1..e17d04abf6a3 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -119,7 +119,7 @@ struct compat_blk_user_trace_setup { #endif -extern void blk_fill_rwbs(char *rwbs, unsigned int op); +void blk_fill_rwbs(char *rwbs, unsigned int op); static inline sector_t blk_rq_trace_sector(struct request *rq) { diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 8a2591c7aa41..d7ebef83771c 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -1867,6 +1867,16 @@ void blk_trace_remove_sysfs(struct device *dev) #ifdef CONFIG_EVENT_TRACING +/** + * blk_fill_rwbs - Fill the buffer rwbs by mapping op to character string. + * @rwbs buffer to be filled + * @op: REQ_OP_XXX for the tracepoint + * + * Description: + * Maps the REQ_OP_XXX to character and fills the buffer provided by the + * caller with resulting string. + * + **/ void blk_fill_rwbs(char *rwbs, unsigned int op) { int i = 0; -- cgit v1.2.3 From c7ff651960a6ef11cef55479658aff504c34872f Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Sun, 21 Feb 2021 21:29:57 -0800 Subject: blktrace: fix blk_rq_issue documentation The commit 881245dcff29 ("Add DocBook documentation for the block tracepoints.") added the comment for blk_rq_issue() tracepoint. Remove the duplicate word from the tracepoint documentation. Fixes: 881245dcff29 ("Add DocBook documentation for the block tracepoints.") Signed-off-by: Chaitanya Kulkarni Reviewed-by: Johannes Thumshirn Reviewed-by: Damien Le Moal Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/trace/events/block.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/block.h b/include/trace/events/block.h index 879cba8bdfca..004cfe34ef37 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -196,7 +196,7 @@ DEFINE_EVENT(block_rq, block_rq_insert, /** * block_rq_issue - issue pending block IO request operation to device driver - * @rq: block IO operation operation request + * @rq: block IO operation request * * Called when block operation request @rq from queue @q is sent to a * device driver for processing. -- cgit v1.2.3 From b0719245098c27b36a9b52969af0300ae6219591 Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Sun, 21 Feb 2021 21:29:58 -0800 Subject: blktrace: fix blk_rq_merge documentation The commit f3bdc62fd82e ("blktrace: Provide event for request merging") added the comment for blk_rq_merge() tracepoint. Remove the duplicate word from the tracepoint documentation. Fixes: f3bdc62fd82e ("blktrace: Provide event for request merging") Signed-off-by: Chaitanya Kulkarni Reviewed-by: Johannes Thumshirn Reviewed-by: Damien Le Moal Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/trace/events/block.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/block.h b/include/trace/events/block.h index 004cfe34ef37..cc5ab96a7471 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -210,7 +210,7 @@ DEFINE_EVENT(block_rq, block_rq_issue, /** * block_rq_merge - merge request with another one in the elevator - * @rq: block IO operation operation request + * @rq: block IO operation request * * Called when block operation request @rq from queue @q is merged to another * request queued in the elevator. -- cgit v1.2.3 From 4a42d848db9544e3108875390886dc490d9c101e Mon Sep 17 00:00:00 2001 From: David Stevens Date: Mon, 22 Feb 2021 11:45:22 +0900 Subject: KVM: x86/mmu: Consider the hva in mmu_notifier retry Track the range being invalidated by mmu_notifier and skip page fault retries if the fault address is not affected by the in-progress invalidation. Handle concurrent invalidations by finding the minimal range which includes all ranges being invalidated. Although the combined range may include unrelated addresses and cannot be shrunk as individual invalidation operations complete, it is unlikely the marginal gains of proper range tracking are worth the additional complexity. The primary benefit of this change is the reduction in the likelihood of extreme latency when handing a page fault due to another thread having been preempted while modifying host virtual addresses. Signed-off-by: David Stevens Message-Id: <20210222024522.1751719-3-stevensd@google.com> Signed-off-by: Paolo Bonzini --- arch/powerpc/kvm/book3s_64_mmu_hv.c | 2 +- arch/powerpc/kvm/book3s_64_mmu_radix.c | 2 +- arch/x86/kvm/mmu/mmu.c | 23 +++++++++++++++++------ arch/x86/kvm/mmu/paging_tmpl.h | 14 +++++++++++--- include/linux/kvm_host.h | 25 ++++++++++++++++++++++++- virt/kvm/kvm_main.c | 29 +++++++++++++++++++++++++---- 6 files changed, 79 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 38ea396a23d6..8e06cd3f759c 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -590,7 +590,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_vcpu *vcpu, } else { /* Call KVM generic code to do the slow-path check */ pfn = __gfn_to_pfn_memslot(memslot, gfn, false, NULL, - writing, &write_ok); + writing, &write_ok, NULL); if (is_error_noslot_pfn(pfn)) return -EFAULT; page = NULL; diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index bb35490400e9..e603de7ade52 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -822,7 +822,7 @@ int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu, /* Call KVM generic code to do the slow-path check */ pfn = __gfn_to_pfn_memslot(memslot, gfn, false, NULL, - writing, upgrade_p); + writing, upgrade_p, NULL); if (is_error_noslot_pfn(pfn)) return -EFAULT; page = NULL; diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 752b4b7ab01b..d75524bc8423 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -2734,6 +2734,13 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep) if (sp->role.level > PG_LEVEL_4K) return; + /* + * If addresses are being invalidated, skip prefetching to avoid + * accidentally prefetching those addresses. + */ + if (unlikely(vcpu->kvm->mmu_notifier_count)) + return; + __direct_pte_prefetch(vcpu, sp, sptep); } @@ -3640,8 +3647,8 @@ static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, } static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, - gpa_t cr2_or_gpa, kvm_pfn_t *pfn, bool write, - bool *writable) + gpa_t cr2_or_gpa, kvm_pfn_t *pfn, hva_t *hva, + bool write, bool *writable) { struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); bool async; @@ -3654,7 +3661,8 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, } async = false; - *pfn = __gfn_to_pfn_memslot(slot, gfn, false, &async, write, writable); + *pfn = __gfn_to_pfn_memslot(slot, gfn, false, &async, + write, writable, hva); if (!async) return false; /* *pfn has correct page already */ @@ -3668,7 +3676,8 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, return true; } - *pfn = __gfn_to_pfn_memslot(slot, gfn, false, NULL, write, writable); + *pfn = __gfn_to_pfn_memslot(slot, gfn, false, NULL, + write, writable, hva); return false; } @@ -3681,6 +3690,7 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, gfn_t gfn = gpa >> PAGE_SHIFT; unsigned long mmu_seq; kvm_pfn_t pfn; + hva_t hva; int r; if (page_fault_handle_page_track(vcpu, error_code, gfn)) @@ -3699,7 +3709,8 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, mmu_seq = vcpu->kvm->mmu_notifier_seq; smp_rmb(); - if (try_async_pf(vcpu, prefault, gfn, gpa, &pfn, write, &map_writable)) + if (try_async_pf(vcpu, prefault, gfn, gpa, &pfn, &hva, + write, &map_writable)) return RET_PF_RETRY; if (handle_abnormal_pfn(vcpu, is_tdp ? 0 : gpa, gfn, pfn, ACC_ALL, &r)) @@ -3712,7 +3723,7 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, else write_lock(&vcpu->kvm->mmu_lock); - if (!is_noslot_pfn(pfn) && mmu_notifier_retry(vcpu->kvm, mmu_seq)) + if (!is_noslot_pfn(pfn) && mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, hva)) goto out_unlock; r = make_mmu_pages_available(vcpu); if (r) diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 5844d3979bb8..55d7b473ac44 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -601,6 +601,13 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw, if (sp->role.level > PG_LEVEL_4K) return; + /* + * If addresses are being invalidated, skip prefetching to avoid + * accidentally prefetching those addresses. + */ + if (unlikely(vcpu->kvm->mmu_notifier_count)) + return; + if (sp->role.direct) return __direct_pte_prefetch(vcpu, sp, sptep); @@ -790,6 +797,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code, struct guest_walker walker; int r; kvm_pfn_t pfn; + hva_t hva; unsigned long mmu_seq; bool map_writable, is_self_change_mapping; int max_level; @@ -840,8 +848,8 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code, mmu_seq = vcpu->kvm->mmu_notifier_seq; smp_rmb(); - if (try_async_pf(vcpu, prefault, walker.gfn, addr, &pfn, write_fault, - &map_writable)) + if (try_async_pf(vcpu, prefault, walker.gfn, addr, &pfn, &hva, + write_fault, &map_writable)) return RET_PF_RETRY; if (handle_abnormal_pfn(vcpu, addr, walker.gfn, pfn, walker.pte_access, &r)) @@ -869,7 +877,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code, r = RET_PF_RETRY; write_lock(&vcpu->kvm->mmu_lock); - if (!is_noslot_pfn(pfn) && mmu_notifier_retry(vcpu->kvm, mmu_seq)) + if (!is_noslot_pfn(pfn) && mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, hva)) goto out_unlock; kvm_mmu_audit(vcpu, AUDIT_PRE_PAGE_FAULT); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index e126ebda36d0..1b65e7204344 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -506,6 +507,8 @@ struct kvm { struct mmu_notifier mmu_notifier; unsigned long mmu_notifier_seq; long mmu_notifier_count; + unsigned long mmu_notifier_range_start; + unsigned long mmu_notifier_range_end; #endif long tlbs_dirty; struct list_head devices; @@ -733,7 +736,7 @@ kvm_pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn); kvm_pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn); kvm_pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, bool atomic, bool *async, bool write_fault, - bool *writable); + bool *writable, hva_t *hva); void kvm_release_pfn_clean(kvm_pfn_t pfn); void kvm_release_pfn_dirty(kvm_pfn_t pfn); @@ -1207,6 +1210,26 @@ static inline int mmu_notifier_retry(struct kvm *kvm, unsigned long mmu_seq) return 1; return 0; } + +static inline int mmu_notifier_retry_hva(struct kvm *kvm, + unsigned long mmu_seq, + unsigned long hva) +{ + lockdep_assert_held(&kvm->mmu_lock); + /* + * If mmu_notifier_count is non-zero, then the range maintained by + * kvm_mmu_notifier_invalidate_range_start contains all addresses that + * might be being invalidated. Note that it may include some false + * positives, due to shortcuts when handing concurrent invalidations. + */ + if (unlikely(kvm->mmu_notifier_count) && + hva >= kvm->mmu_notifier_range_start && + hva < kvm->mmu_notifier_range_end) + return 1; + if (kvm->mmu_notifier_seq != mmu_seq) + return 1; + return 0; +} #endif #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 001b9de4e727..383df23514b9 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -486,6 +486,24 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, * count is also read inside the mmu_lock critical section. */ kvm->mmu_notifier_count++; + if (likely(kvm->mmu_notifier_count == 1)) { + kvm->mmu_notifier_range_start = range->start; + kvm->mmu_notifier_range_end = range->end; + } else { + /* + * Fully tracking multiple concurrent ranges has dimishing + * returns. Keep things simple and just find the minimal range + * which includes the current and new ranges. As there won't be + * enough information to subtract a range after its invalidate + * completes, any ranges invalidated concurrently will + * accumulate and persist until all outstanding invalidates + * complete. + */ + kvm->mmu_notifier_range_start = + min(kvm->mmu_notifier_range_start, range->start); + kvm->mmu_notifier_range_end = + max(kvm->mmu_notifier_range_end, range->end); + } need_tlb_flush = kvm_unmap_hva_range(kvm, range->start, range->end, range->flags); /* we've to flush the tlb before the pages can be freed */ @@ -2023,10 +2041,13 @@ exit: kvm_pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, bool atomic, bool *async, bool write_fault, - bool *writable) + bool *writable, hva_t *hva) { unsigned long addr = __gfn_to_hva_many(slot, gfn, NULL, write_fault); + if (hva) + *hva = addr; + if (addr == KVM_HVA_ERR_RO_BAD) { if (writable) *writable = false; @@ -2054,19 +2075,19 @@ kvm_pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault, bool *writable) { return __gfn_to_pfn_memslot(gfn_to_memslot(kvm, gfn), gfn, false, NULL, - write_fault, writable); + write_fault, writable, NULL); } EXPORT_SYMBOL_GPL(gfn_to_pfn_prot); kvm_pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn) { - return __gfn_to_pfn_memslot(slot, gfn, false, NULL, true, NULL); + return __gfn_to_pfn_memslot(slot, gfn, false, NULL, true, NULL, NULL); } EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot); kvm_pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn) { - return __gfn_to_pfn_memslot(slot, gfn, true, NULL, true, NULL); + return __gfn_to_pfn_memslot(slot, gfn, true, NULL, true, NULL, NULL); } EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot_atomic); -- cgit v1.2.3 From c6ca7616f7d5c2ce166280107ba74db1d528fcb7 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Wed, 10 Feb 2021 14:02:14 +0900 Subject: clk: Add RISC-V Canaan Kendryte K210 clock driver Add a clock provider driver for the Canaan Kendryte K210 RISC-V SoC. This new driver with the compatible string "canaan,k210-clk" implements support for the full clock structure of the K210 SoC. Since it is required for the correct operation of the SoC, this driver is selected by default for compilation when the SOC_CANAAN option is selected. With this change, the k210-sysctl driver is turned into a simple platform driver which enables its power bus clock and triggers populating its child nodes. The sysctl driver retains the SOC early initialization code, but the implementation now relies on the new function k210_clk_early_init() provided by the new clk-k210 driver. The clock structure implemented and many of the coding ideas for the driver come from the work by Sean Anderson on the K210 support for the U-Boot project. Cc: Stephen Boyd Cc: Michael Turquette Cc: linux-clk@vger.kernel.org Signed-off-by: Damien Le Moal Reviewed-by: Stephen Boyd Signed-off-by: Palmer Dabbelt --- drivers/clk/Kconfig | 7 + drivers/clk/Makefile | 1 + drivers/clk/clk-k210.c | 1007 ++++++++++++++++++++++++++++++++++++++ drivers/soc/canaan/Kconfig | 18 +- drivers/soc/canaan/Makefile | 2 +- drivers/soc/canaan/k210-sysctl.c | 205 ++------ include/soc/canaan/k210-sysctl.h | 2 + 7 files changed, 1064 insertions(+), 178 deletions(-) create mode 100644 drivers/clk/clk-k210.c (limited to 'include') diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig index 85856cff506c..78f6288d5226 100644 --- a/drivers/clk/Kconfig +++ b/drivers/clk/Kconfig @@ -368,6 +368,13 @@ config COMMON_CLK_FIXED_MMIO help Support for Memory Mapped IO Fixed clocks +config COMMON_CLK_K210 + bool "Clock driver for the Canaan Kendryte K210 SoC" + depends on OF && RISCV && SOC_CANAAN + default SOC_CANAAN + help + Support for the Canaan Kendryte K210 RISC-V SoC clocks. + source "drivers/clk/actions/Kconfig" source "drivers/clk/analogbits/Kconfig" source "drivers/clk/baikal-t1/Kconfig" diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile index dbdc590e7de3..5f8f9f135df5 100644 --- a/drivers/clk/Makefile +++ b/drivers/clk/Makefile @@ -37,6 +37,7 @@ obj-$(CONFIG_COMMON_CLK_ASPEED) += clk-aspeed.o obj-$(CONFIG_MACH_ASPEED_G6) += clk-ast2600.o obj-$(CONFIG_ARCH_HIGHBANK) += clk-highbank.o obj-$(CONFIG_CLK_HSDK) += clk-hsdk-pll.o +obj-$(CONFIG_COMMON_CLK_K210) += clk-k210.o obj-$(CONFIG_COMMON_CLK_LOCHNAGAR) += clk-lochnagar.o obj-$(CONFIG_COMMON_CLK_MAX77686) += clk-max77686.o obj-$(CONFIG_COMMON_CLK_MAX9485) += clk-max9485.o diff --git a/drivers/clk/clk-k210.c b/drivers/clk/clk-k210.c new file mode 100644 index 000000000000..6c84abf5b2e3 --- /dev/null +++ b/drivers/clk/clk-k210.c @@ -0,0 +1,1007 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) 2019-20 Sean Anderson + * Copyright (c) 2019 Western Digital Corporation or its affiliates. + */ +#define pr_fmt(fmt) "k210-clk: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +struct k210_sysclk; + +struct k210_clk { + int id; + struct k210_sysclk *ksc; + struct clk_hw hw; +}; + +struct k210_clk_cfg { + const char *name; + u8 gate_reg; + u8 gate_bit; + u8 div_reg; + u8 div_shift; + u8 div_width; + u8 div_type; + u8 mux_reg; + u8 mux_bit; +}; + +enum k210_clk_div_type { + K210_DIV_NONE, + K210_DIV_ONE_BASED, + K210_DIV_DOUBLE_ONE_BASED, + K210_DIV_POWER_OF_TWO, +}; + +#define K210_GATE(_reg, _bit) \ + .gate_reg = (_reg), \ + .gate_bit = (_bit) + +#define K210_DIV(_reg, _shift, _width, _type) \ + .div_reg = (_reg), \ + .div_shift = (_shift), \ + .div_width = (_width), \ + .div_type = (_type) + +#define K210_MUX(_reg, _bit) \ + .mux_reg = (_reg), \ + .mux_bit = (_bit) + +static struct k210_clk_cfg k210_clk_cfgs[K210_NUM_CLKS] = { + /* Gated clocks, no mux, no divider */ + [K210_CLK_CPU] = { + .name = "cpu", + K210_GATE(K210_SYSCTL_EN_CENT, 0) + }, + [K210_CLK_DMA] = { + .name = "dma", + K210_GATE(K210_SYSCTL_EN_PERI, 1) + }, + [K210_CLK_FFT] = { + .name = "fft", + K210_GATE(K210_SYSCTL_EN_PERI, 4) + }, + [K210_CLK_GPIO] = { + .name = "gpio", + K210_GATE(K210_SYSCTL_EN_PERI, 5) + }, + [K210_CLK_UART1] = { + .name = "uart1", + K210_GATE(K210_SYSCTL_EN_PERI, 16) + }, + [K210_CLK_UART2] = { + .name = "uart2", + K210_GATE(K210_SYSCTL_EN_PERI, 17) + }, + [K210_CLK_UART3] = { + .name = "uart3", + K210_GATE(K210_SYSCTL_EN_PERI, 18) + }, + [K210_CLK_FPIOA] = { + .name = "fpioa", + K210_GATE(K210_SYSCTL_EN_PERI, 20) + }, + [K210_CLK_SHA] = { + .name = "sha", + K210_GATE(K210_SYSCTL_EN_PERI, 26) + }, + [K210_CLK_AES] = { + .name = "aes", + K210_GATE(K210_SYSCTL_EN_PERI, 19) + }, + [K210_CLK_OTP] = { + .name = "otp", + K210_GATE(K210_SYSCTL_EN_PERI, 27) + }, + [K210_CLK_RTC] = { + .name = "rtc", + K210_GATE(K210_SYSCTL_EN_PERI, 29) + }, + + /* Gated divider clocks */ + [K210_CLK_SRAM0] = { + .name = "sram0", + K210_GATE(K210_SYSCTL_EN_CENT, 1), + K210_DIV(K210_SYSCTL_THR0, 0, 4, K210_DIV_ONE_BASED) + }, + [K210_CLK_SRAM1] = { + .name = "sram1", + K210_GATE(K210_SYSCTL_EN_CENT, 2), + K210_DIV(K210_SYSCTL_THR0, 4, 4, K210_DIV_ONE_BASED) + }, + [K210_CLK_ROM] = { + .name = "rom", + K210_GATE(K210_SYSCTL_EN_PERI, 0), + K210_DIV(K210_SYSCTL_THR0, 16, 4, K210_DIV_ONE_BASED) + }, + [K210_CLK_DVP] = { + .name = "dvp", + K210_GATE(K210_SYSCTL_EN_PERI, 3), + K210_DIV(K210_SYSCTL_THR0, 12, 4, K210_DIV_ONE_BASED) + }, + [K210_CLK_APB0] = { + .name = "apb0", + K210_GATE(K210_SYSCTL_EN_CENT, 3), + K210_DIV(K210_SYSCTL_SEL0, 3, 3, K210_DIV_ONE_BASED) + }, + [K210_CLK_APB1] = { + .name = "apb1", + K210_GATE(K210_SYSCTL_EN_CENT, 4), + K210_DIV(K210_SYSCTL_SEL0, 6, 3, K210_DIV_ONE_BASED) + }, + [K210_CLK_APB2] = { + .name = "apb2", + K210_GATE(K210_SYSCTL_EN_CENT, 5), + K210_DIV(K210_SYSCTL_SEL0, 9, 3, K210_DIV_ONE_BASED) + }, + [K210_CLK_AI] = { + .name = "ai", + K210_GATE(K210_SYSCTL_EN_PERI, 2), + K210_DIV(K210_SYSCTL_THR0, 8, 4, K210_DIV_ONE_BASED) + }, + [K210_CLK_SPI0] = { + .name = "spi0", + K210_GATE(K210_SYSCTL_EN_PERI, 6), + K210_DIV(K210_SYSCTL_THR1, 0, 8, K210_DIV_DOUBLE_ONE_BASED) + }, + [K210_CLK_SPI1] = { + .name = "spi1", + K210_GATE(K210_SYSCTL_EN_PERI, 7), + K210_DIV(K210_SYSCTL_THR1, 8, 8, K210_DIV_DOUBLE_ONE_BASED) + }, + [K210_CLK_SPI2] = { + .name = "spi2", + K210_GATE(K210_SYSCTL_EN_PERI, 8), + K210_DIV(K210_SYSCTL_THR1, 16, 8, K210_DIV_DOUBLE_ONE_BASED) + }, + [K210_CLK_I2C0] = { + .name = "i2c0", + K210_GATE(K210_SYSCTL_EN_PERI, 13), + K210_DIV(K210_SYSCTL_THR5, 8, 8, K210_DIV_DOUBLE_ONE_BASED) + }, + [K210_CLK_I2C1] = { + .name = "i2c1", + K210_GATE(K210_SYSCTL_EN_PERI, 14), + K210_DIV(K210_SYSCTL_THR5, 16, 8, K210_DIV_DOUBLE_ONE_BASED) + }, + [K210_CLK_I2C2] = { + .name = "i2c2", + K210_GATE(K210_SYSCTL_EN_PERI, 15), + K210_DIV(K210_SYSCTL_THR5, 24, 8, K210_DIV_DOUBLE_ONE_BASED) + }, + [K210_CLK_WDT0] = { + .name = "wdt0", + K210_GATE(K210_SYSCTL_EN_PERI, 24), + K210_DIV(K210_SYSCTL_THR6, 0, 8, K210_DIV_DOUBLE_ONE_BASED) + }, + [K210_CLK_WDT1] = { + .name = "wdt1", + K210_GATE(K210_SYSCTL_EN_PERI, 25), + K210_DIV(K210_SYSCTL_THR6, 8, 8, K210_DIV_DOUBLE_ONE_BASED) + }, + [K210_CLK_I2S0] = { + .name = "i2s0", + K210_GATE(K210_SYSCTL_EN_PERI, 10), + K210_DIV(K210_SYSCTL_THR3, 0, 16, K210_DIV_DOUBLE_ONE_BASED) + }, + [K210_CLK_I2S1] = { + .name = "i2s1", + K210_GATE(K210_SYSCTL_EN_PERI, 11), + K210_DIV(K210_SYSCTL_THR3, 16, 16, K210_DIV_DOUBLE_ONE_BASED) + }, + [K210_CLK_I2S2] = { + .name = "i2s2", + K210_GATE(K210_SYSCTL_EN_PERI, 12), + K210_DIV(K210_SYSCTL_THR4, 0, 16, K210_DIV_DOUBLE_ONE_BASED) + }, + + /* Divider clocks, no gate, no mux */ + [K210_CLK_I2S0_M] = { + .name = "i2s0_m", + K210_DIV(K210_SYSCTL_THR4, 16, 8, K210_DIV_DOUBLE_ONE_BASED) + }, + [K210_CLK_I2S1_M] = { + .name = "i2s1_m", + K210_DIV(K210_SYSCTL_THR4, 24, 8, K210_DIV_DOUBLE_ONE_BASED) + }, + [K210_CLK_I2S2_M] = { + .name = "i2s2_m", + K210_DIV(K210_SYSCTL_THR4, 0, 8, K210_DIV_DOUBLE_ONE_BASED) + }, + + /* Muxed gated divider clocks */ + [K210_CLK_SPI3] = { + .name = "spi3", + K210_GATE(K210_SYSCTL_EN_PERI, 9), + K210_DIV(K210_SYSCTL_THR1, 24, 8, K210_DIV_DOUBLE_ONE_BASED), + K210_MUX(K210_SYSCTL_SEL0, 12) + }, + [K210_CLK_TIMER0] = { + .name = "timer0", + K210_GATE(K210_SYSCTL_EN_PERI, 21), + K210_DIV(K210_SYSCTL_THR2, 0, 8, K210_DIV_DOUBLE_ONE_BASED), + K210_MUX(K210_SYSCTL_SEL0, 13) + }, + [K210_CLK_TIMER1] = { + .name = "timer1", + K210_GATE(K210_SYSCTL_EN_PERI, 22), + K210_DIV(K210_SYSCTL_THR2, 8, 8, K210_DIV_DOUBLE_ONE_BASED), + K210_MUX(K210_SYSCTL_SEL0, 14) + }, + [K210_CLK_TIMER2] = { + .name = "timer2", + K210_GATE(K210_SYSCTL_EN_PERI, 23), + K210_DIV(K210_SYSCTL_THR2, 16, 8, K210_DIV_DOUBLE_ONE_BASED), + K210_MUX(K210_SYSCTL_SEL0, 15) + }, +}; + +/* + * PLL control register bits. + */ +#define K210_PLL_CLKR GENMASK(3, 0) +#define K210_PLL_CLKF GENMASK(9, 4) +#define K210_PLL_CLKOD GENMASK(13, 10) +#define K210_PLL_BWADJ GENMASK(19, 14) +#define K210_PLL_RESET (1 << 20) +#define K210_PLL_PWRD (1 << 21) +#define K210_PLL_INTFB (1 << 22) +#define K210_PLL_BYPASS (1 << 23) +#define K210_PLL_TEST (1 << 24) +#define K210_PLL_EN (1 << 25) +#define K210_PLL_SEL GENMASK(27, 26) /* PLL2 only */ + +/* + * PLL lock register bits. + */ +#define K210_PLL_LOCK 0 +#define K210_PLL_CLEAR_SLIP 2 +#define K210_PLL_TEST_OUT 3 + +/* + * Clock selector register bits. + */ +#define K210_ACLK_SEL BIT(0) +#define K210_ACLK_DIV GENMASK(2, 1) + +/* + * PLLs. + */ +enum k210_pll_id { + K210_PLL0, K210_PLL1, K210_PLL2, K210_PLL_NUM +}; + +struct k210_pll { + enum k210_pll_id id; + struct k210_sysclk *ksc; + void __iomem *base; + void __iomem *reg; + void __iomem *lock; + u8 lock_shift; + u8 lock_width; + struct clk_hw hw; +}; +#define to_k210_pll(_hw) container_of(_hw, struct k210_pll, hw) + +/* + * PLLs configuration: by default PLL0 runs at 780 MHz and PLL1 at 299 MHz. + * The first 2 SRAM banks depend on ACLK/CPU clock which is by default PLL0 + * rate divided by 2. Set PLL1 to 390 MHz so that the third SRAM bank has the + * same clock as the first 2. + */ +struct k210_pll_cfg { + u32 reg; + u8 lock_shift; + u8 lock_width; + u32 r; + u32 f; + u32 od; + u32 bwadj; +}; + +static struct k210_pll_cfg k210_plls_cfg[] = { + { K210_SYSCTL_PLL0, 0, 2, 0, 59, 1, 59 }, /* 780 MHz */ + { K210_SYSCTL_PLL1, 8, 1, 0, 59, 3, 59 }, /* 390 MHz */ + { K210_SYSCTL_PLL2, 16, 1, 0, 22, 1, 22 }, /* 299 MHz */ +}; + +/** + * struct k210_sysclk - sysclk driver data + * @regs: system controller registers start address + * @clk_lock: clock setting spinlock + * @plls: SoC PLLs descriptors + * @aclk: ACLK clock + * @clks: All other clocks + */ +struct k210_sysclk { + void __iomem *regs; + spinlock_t clk_lock; + struct k210_pll plls[K210_PLL_NUM]; + struct clk_hw aclk; + struct k210_clk clks[K210_NUM_CLKS]; +}; + +#define to_k210_sysclk(_hw) container_of(_hw, struct k210_sysclk, aclk) + +/* + * Set ACLK parent selector: 0 for IN0, 1 for PLL0. + */ +static void k210_aclk_set_selector(void __iomem *regs, u8 sel) +{ + u32 reg = readl(regs + K210_SYSCTL_SEL0); + + if (sel) + reg |= K210_ACLK_SEL; + else + reg &= K210_ACLK_SEL; + writel(reg, regs + K210_SYSCTL_SEL0); +} + +static void k210_init_pll(void __iomem *regs, enum k210_pll_id pllid, + struct k210_pll *pll) +{ + pll->id = pllid; + pll->reg = regs + k210_plls_cfg[pllid].reg; + pll->lock = regs + K210_SYSCTL_PLL_LOCK; + pll->lock_shift = k210_plls_cfg[pllid].lock_shift; + pll->lock_width = k210_plls_cfg[pllid].lock_width; +} + +static void k210_pll_wait_for_lock(struct k210_pll *pll) +{ + u32 reg, mask = GENMASK(pll->lock_shift + pll->lock_width - 1, + pll->lock_shift); + + while (true) { + reg = readl(pll->lock); + if ((reg & mask) == mask) + break; + + reg |= BIT(pll->lock_shift + K210_PLL_CLEAR_SLIP); + writel(reg, pll->lock); + } +} + +static bool k210_pll_hw_is_enabled(struct k210_pll *pll) +{ + u32 reg = readl(pll->reg); + u32 mask = K210_PLL_PWRD | K210_PLL_EN; + + if (reg & K210_PLL_RESET) + return false; + + return (reg & mask) == mask; +} + +static void k210_pll_enable_hw(void __iomem *regs, struct k210_pll *pll) +{ + struct k210_pll_cfg *pll_cfg = &k210_plls_cfg[pll->id]; + u32 reg; + + if (k210_pll_hw_is_enabled(pll)) + return; + + /* + * For PLL0, we need to re-parent ACLK to IN0 to keep the CPU cores and + * SRAM running. + */ + if (pll->id == K210_PLL0) + k210_aclk_set_selector(regs, 0); + + /* Set PLL factors */ + reg = readl(pll->reg); + reg &= ~GENMASK(19, 0); + reg |= FIELD_PREP(K210_PLL_CLKR, pll_cfg->r); + reg |= FIELD_PREP(K210_PLL_CLKF, pll_cfg->f); + reg |= FIELD_PREP(K210_PLL_CLKOD, pll_cfg->od); + reg |= FIELD_PREP(K210_PLL_BWADJ, pll_cfg->bwadj); + reg |= K210_PLL_PWRD; + writel(reg, pll->reg); + + /* + * Reset the PLL: ensure reset is low before asserting it. + * The magic NOPs come from the Kendryte reference SDK. + */ + reg &= ~K210_PLL_RESET; + writel(reg, pll->reg); + reg |= K210_PLL_RESET; + writel(reg, pll->reg); + nop(); + nop(); + reg &= ~K210_PLL_RESET; + writel(reg, pll->reg); + + k210_pll_wait_for_lock(pll); + + reg &= ~K210_PLL_BYPASS; + reg |= K210_PLL_EN; + writel(reg, pll->reg); + + if (pll->id == K210_PLL0) + k210_aclk_set_selector(regs, 1); +} + +static int k210_pll_enable(struct clk_hw *hw) +{ + struct k210_pll *pll = to_k210_pll(hw); + struct k210_sysclk *ksc = pll->ksc; + unsigned long flags; + + spin_lock_irqsave(&ksc->clk_lock, flags); + + k210_pll_enable_hw(ksc->regs, pll); + + spin_unlock_irqrestore(&ksc->clk_lock, flags); + + return 0; +} + +static void k210_pll_disable(struct clk_hw *hw) +{ + struct k210_pll *pll = to_k210_pll(hw); + struct k210_sysclk *ksc = pll->ksc; + unsigned long flags; + u32 reg; + + /* + * Bypassing before powering off is important so child clocks do not + * stop working. This is especially important for pll0, the indirect + * parent of the cpu clock. + */ + spin_lock_irqsave(&ksc->clk_lock, flags); + reg = readl(pll->reg); + reg |= K210_PLL_BYPASS; + writel(reg, pll->reg); + + reg &= ~K210_PLL_PWRD; + reg &= ~K210_PLL_EN; + writel(reg, pll->reg); + spin_unlock_irqrestore(&ksc->clk_lock, flags); +} + +static int k210_pll_is_enabled(struct clk_hw *hw) +{ + return k210_pll_hw_is_enabled(to_k210_pll(hw)); +} + +static unsigned long k210_pll_get_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct k210_pll *pll = to_k210_pll(hw); + u32 reg = readl(pll->reg); + u32 r, f, od; + + if (reg & K210_PLL_BYPASS) + return parent_rate; + + if (!(reg & K210_PLL_PWRD)) + return 0; + + r = FIELD_GET(K210_PLL_CLKR, reg) + 1; + f = FIELD_GET(K210_PLL_CLKF, reg) + 1; + od = FIELD_GET(K210_PLL_CLKOD, reg) + 1; + + return (u64)parent_rate * f / (r * od); +} + +static const struct clk_ops k210_pll_ops = { + .enable = k210_pll_enable, + .disable = k210_pll_disable, + .is_enabled = k210_pll_is_enabled, + .recalc_rate = k210_pll_get_rate, +}; + +static int k210_pll2_set_parent(struct clk_hw *hw, u8 index) +{ + struct k210_pll *pll = to_k210_pll(hw); + struct k210_sysclk *ksc = pll->ksc; + unsigned long flags; + u32 reg; + + spin_lock_irqsave(&ksc->clk_lock, flags); + + reg = readl(pll->reg); + reg &= ~K210_PLL_SEL; + reg |= FIELD_PREP(K210_PLL_SEL, index); + writel(reg, pll->reg); + + spin_unlock_irqrestore(&ksc->clk_lock, flags); + + return 0; +} + +static u8 k210_pll2_get_parent(struct clk_hw *hw) +{ + struct k210_pll *pll = to_k210_pll(hw); + u32 reg = readl(pll->reg); + + return FIELD_GET(K210_PLL_SEL, reg); +} + +static const struct clk_ops k210_pll2_ops = { + .enable = k210_pll_enable, + .disable = k210_pll_disable, + .is_enabled = k210_pll_is_enabled, + .recalc_rate = k210_pll_get_rate, + .set_parent = k210_pll2_set_parent, + .get_parent = k210_pll2_get_parent, +}; + +static int __init k210_register_pll(struct device_node *np, + struct k210_sysclk *ksc, + enum k210_pll_id pllid, const char *name, + int num_parents, const struct clk_ops *ops) +{ + struct k210_pll *pll = &ksc->plls[pllid]; + struct clk_init_data init = {}; + const struct clk_parent_data parent_data[] = { + { /* .index = 0 for in0 */ }, + { .hw = &ksc->plls[K210_PLL0].hw }, + { .hw = &ksc->plls[K210_PLL1].hw }, + }; + + init.name = name; + init.parent_data = parent_data; + init.num_parents = num_parents; + init.ops = ops; + + pll->hw.init = &init; + pll->ksc = ksc; + + return of_clk_hw_register(np, &pll->hw); +} + +static int __init k210_register_plls(struct device_node *np, + struct k210_sysclk *ksc) +{ + int i, ret; + + for (i = 0; i < K210_PLL_NUM; i++) + k210_init_pll(ksc->regs, i, &ksc->plls[i]); + + /* PLL0 and PLL1 only have IN0 as parent */ + ret = k210_register_pll(np, ksc, K210_PLL0, "pll0", 1, &k210_pll_ops); + if (ret) { + pr_err("%pOFP: register PLL0 failed\n", np); + return ret; + } + ret = k210_register_pll(np, ksc, K210_PLL1, "pll1", 1, &k210_pll_ops); + if (ret) { + pr_err("%pOFP: register PLL1 failed\n", np); + return ret; + } + + /* PLL2 has IN0, PLL0 and PLL1 as parents */ + ret = k210_register_pll(np, ksc, K210_PLL2, "pll2", 3, &k210_pll2_ops); + if (ret) { + pr_err("%pOFP: register PLL2 failed\n", np); + return ret; + } + + return 0; +} + +static int k210_aclk_set_parent(struct clk_hw *hw, u8 index) +{ + struct k210_sysclk *ksc = to_k210_sysclk(hw); + unsigned long flags; + + spin_lock_irqsave(&ksc->clk_lock, flags); + + k210_aclk_set_selector(ksc->regs, index); + + spin_unlock_irqrestore(&ksc->clk_lock, flags); + + return 0; +} + +static u8 k210_aclk_get_parent(struct clk_hw *hw) +{ + struct k210_sysclk *ksc = to_k210_sysclk(hw); + u32 sel; + + sel = readl(ksc->regs + K210_SYSCTL_SEL0) & K210_ACLK_SEL; + + return sel ? 1 : 0; +} + +static unsigned long k210_aclk_get_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct k210_sysclk *ksc = to_k210_sysclk(hw); + u32 reg = readl(ksc->regs + K210_SYSCTL_SEL0); + unsigned int shift; + + if (!(reg & 0x1)) + return parent_rate; + + shift = FIELD_GET(K210_ACLK_DIV, reg); + + return parent_rate / (2UL << shift); +} + +static const struct clk_ops k210_aclk_ops = { + .set_parent = k210_aclk_set_parent, + .get_parent = k210_aclk_get_parent, + .recalc_rate = k210_aclk_get_rate, +}; + +/* + * ACLK has IN0 and PLL0 as parents. + */ +static int __init k210_register_aclk(struct device_node *np, + struct k210_sysclk *ksc) +{ + struct clk_init_data init = {}; + const struct clk_parent_data parent_data[] = { + { /* .index = 0 for in0 */ }, + { .hw = &ksc->plls[K210_PLL0].hw }, + }; + int ret; + + init.name = "aclk"; + init.parent_data = parent_data; + init.num_parents = 2; + init.ops = &k210_aclk_ops; + ksc->aclk.init = &init; + + ret = of_clk_hw_register(np, &ksc->aclk); + if (ret) { + pr_err("%pOFP: register aclk failed\n", np); + return ret; + } + + return 0; +} + +#define to_k210_clk(_hw) container_of(_hw, struct k210_clk, hw) + +static int k210_clk_enable(struct clk_hw *hw) +{ + struct k210_clk *kclk = to_k210_clk(hw); + struct k210_sysclk *ksc = kclk->ksc; + struct k210_clk_cfg *cfg = &k210_clk_cfgs[kclk->id]; + unsigned long flags; + u32 reg; + + if (!cfg->gate_reg) + return 0; + + spin_lock_irqsave(&ksc->clk_lock, flags); + reg = readl(ksc->regs + cfg->gate_reg); + reg |= BIT(cfg->gate_bit); + writel(reg, ksc->regs + cfg->gate_reg); + spin_unlock_irqrestore(&ksc->clk_lock, flags); + + return 0; +} + +static void k210_clk_disable(struct clk_hw *hw) +{ + struct k210_clk *kclk = to_k210_clk(hw); + struct k210_sysclk *ksc = kclk->ksc; + struct k210_clk_cfg *cfg = &k210_clk_cfgs[kclk->id]; + unsigned long flags; + u32 reg; + + if (!cfg->gate_reg) + return; + + spin_lock_irqsave(&ksc->clk_lock, flags); + reg = readl(ksc->regs + cfg->gate_reg); + reg &= ~BIT(cfg->gate_bit); + writel(reg, ksc->regs + cfg->gate_reg); + spin_unlock_irqrestore(&ksc->clk_lock, flags); +} + +static int k210_clk_set_parent(struct clk_hw *hw, u8 index) +{ + struct k210_clk *kclk = to_k210_clk(hw); + struct k210_sysclk *ksc = kclk->ksc; + struct k210_clk_cfg *cfg = &k210_clk_cfgs[kclk->id]; + unsigned long flags; + u32 reg; + + spin_lock_irqsave(&ksc->clk_lock, flags); + reg = readl(ksc->regs + cfg->mux_reg); + if (index) + reg |= BIT(cfg->mux_bit); + else + reg &= ~BIT(cfg->mux_bit); + spin_unlock_irqrestore(&ksc->clk_lock, flags); + + return 0; +} + +static u8 k210_clk_get_parent(struct clk_hw *hw) +{ + struct k210_clk *kclk = to_k210_clk(hw); + struct k210_sysclk *ksc = kclk->ksc; + struct k210_clk_cfg *cfg = &k210_clk_cfgs[kclk->id]; + unsigned long flags; + u32 reg, idx; + + spin_lock_irqsave(&ksc->clk_lock, flags); + reg = readl(ksc->regs + cfg->mux_reg); + idx = (reg & BIT(cfg->mux_bit)) ? 1 : 0; + spin_unlock_irqrestore(&ksc->clk_lock, flags); + + return idx; +} + +static unsigned long k210_clk_get_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct k210_clk *kclk = to_k210_clk(hw); + struct k210_sysclk *ksc = kclk->ksc; + struct k210_clk_cfg *cfg = &k210_clk_cfgs[kclk->id]; + u32 reg, div_val; + + if (!cfg->div_reg) + return parent_rate; + + reg = readl(ksc->regs + cfg->div_reg); + div_val = (reg >> cfg->div_shift) & GENMASK(cfg->div_width - 1, 0); + + switch (cfg->div_type) { + case K210_DIV_ONE_BASED: + return parent_rate / (div_val + 1); + case K210_DIV_DOUBLE_ONE_BASED: + return parent_rate / ((div_val + 1) * 2); + case K210_DIV_POWER_OF_TWO: + return parent_rate / (2UL << div_val); + case K210_DIV_NONE: + default: + return 0; + } +} + +static const struct clk_ops k210_clk_mux_ops = { + .enable = k210_clk_enable, + .disable = k210_clk_disable, + .set_parent = k210_clk_set_parent, + .get_parent = k210_clk_get_parent, + .recalc_rate = k210_clk_get_rate, +}; + +static const struct clk_ops k210_clk_ops = { + .enable = k210_clk_enable, + .disable = k210_clk_disable, + .recalc_rate = k210_clk_get_rate, +}; + +static void __init k210_register_clk(struct device_node *np, + struct k210_sysclk *ksc, int id, + const struct clk_parent_data *parent_data, + int num_parents, unsigned long flags) +{ + struct k210_clk *kclk = &ksc->clks[id]; + struct clk_init_data init = {}; + int ret; + + init.name = k210_clk_cfgs[id].name; + init.flags = flags; + init.parent_data = parent_data; + init.num_parents = num_parents; + if (num_parents > 1) + init.ops = &k210_clk_mux_ops; + else + init.ops = &k210_clk_ops; + + kclk->id = id; + kclk->ksc = ksc; + kclk->hw.init = &init; + + ret = of_clk_hw_register(np, &kclk->hw); + if (ret) { + pr_err("%pOFP: register clock %s failed\n", + np, k210_clk_cfgs[id].name); + kclk->id = -1; + } +} + +/* + * All muxed clocks have IN0 and PLL0 as parents. + */ +static inline void __init k210_register_mux_clk(struct device_node *np, + struct k210_sysclk *ksc, int id) +{ + const struct clk_parent_data parent_data[2] = { + { /* .index = 0 for in0 */ }, + { .hw = &ksc->plls[K210_PLL0].hw } + }; + + k210_register_clk(np, ksc, id, parent_data, 2, 0); +} + +static inline void __init k210_register_in0_child(struct device_node *np, + struct k210_sysclk *ksc, int id) +{ + const struct clk_parent_data parent_data = { + /* .index = 0 for in0 */ + }; + + k210_register_clk(np, ksc, id, &parent_data, 1, 0); +} + +static inline void __init k210_register_pll_child(struct device_node *np, + struct k210_sysclk *ksc, int id, + enum k210_pll_id pllid, + unsigned long flags) +{ + const struct clk_parent_data parent_data = { + .hw = &ksc->plls[pllid].hw, + }; + + k210_register_clk(np, ksc, id, &parent_data, 1, flags); +} + +static inline void __init k210_register_aclk_child(struct device_node *np, + struct k210_sysclk *ksc, int id, + unsigned long flags) +{ + const struct clk_parent_data parent_data = { + .hw = &ksc->aclk, + }; + + k210_register_clk(np, ksc, id, &parent_data, 1, flags); +} + +static inline void __init k210_register_clk_child(struct device_node *np, + struct k210_sysclk *ksc, int id, + int parent_id) +{ + const struct clk_parent_data parent_data = { + .hw = &ksc->clks[parent_id].hw, + }; + + k210_register_clk(np, ksc, id, &parent_data, 1, 0); +} + +static struct clk_hw *k210_clk_hw_onecell_get(struct of_phandle_args *clkspec, + void *data) +{ + struct k210_sysclk *ksc = data; + unsigned int idx = clkspec->args[0]; + + if (idx >= K210_NUM_CLKS) + return ERR_PTR(-EINVAL); + + return &ksc->clks[idx].hw; +} + +static void __init k210_clk_init(struct device_node *np) +{ + struct device_node *sysctl_np; + struct k210_sysclk *ksc; + int i, ret; + + ksc = kzalloc(sizeof(*ksc), GFP_KERNEL); + if (!ksc) + return; + + spin_lock_init(&ksc->clk_lock); + sysctl_np = of_get_parent(np); + ksc->regs = of_iomap(sysctl_np, 0); + of_node_put(sysctl_np); + if (!ksc->regs) { + pr_err("%pOFP: failed to map registers\n", np); + return; + } + + ret = k210_register_plls(np, ksc); + if (ret) + return; + + ret = k210_register_aclk(np, ksc); + if (ret) + return; + + /* + * Critical clocks: there are no consumers of the SRAM clocks, + * including the AI clock for the third SRAM bank. The CPU clock + * is only referenced by the uarths serial device and so would be + * disabled if the serial console is disabled to switch to another + * console. Mark all these clocks as critical so that they are never + * disabled by the core clock management. + */ + k210_register_aclk_child(np, ksc, K210_CLK_CPU, CLK_IS_CRITICAL); + k210_register_aclk_child(np, ksc, K210_CLK_SRAM0, CLK_IS_CRITICAL); + k210_register_aclk_child(np, ksc, K210_CLK_SRAM1, CLK_IS_CRITICAL); + k210_register_pll_child(np, ksc, K210_CLK_AI, K210_PLL1, + CLK_IS_CRITICAL); + + /* Clocks with aclk as source */ + k210_register_aclk_child(np, ksc, K210_CLK_DMA, 0); + k210_register_aclk_child(np, ksc, K210_CLK_FFT, 0); + k210_register_aclk_child(np, ksc, K210_CLK_ROM, 0); + k210_register_aclk_child(np, ksc, K210_CLK_DVP, 0); + k210_register_aclk_child(np, ksc, K210_CLK_APB0, 0); + k210_register_aclk_child(np, ksc, K210_CLK_APB1, 0); + k210_register_aclk_child(np, ksc, K210_CLK_APB2, 0); + + /* Clocks with PLL0 as source */ + k210_register_pll_child(np, ksc, K210_CLK_SPI0, K210_PLL0, 0); + k210_register_pll_child(np, ksc, K210_CLK_SPI1, K210_PLL0, 0); + k210_register_pll_child(np, ksc, K210_CLK_SPI2, K210_PLL0, 0); + k210_register_pll_child(np, ksc, K210_CLK_I2C0, K210_PLL0, 0); + k210_register_pll_child(np, ksc, K210_CLK_I2C1, K210_PLL0, 0); + k210_register_pll_child(np, ksc, K210_CLK_I2C2, K210_PLL0, 0); + + /* Clocks with PLL2 as source */ + k210_register_pll_child(np, ksc, K210_CLK_I2S0, K210_PLL2, 0); + k210_register_pll_child(np, ksc, K210_CLK_I2S1, K210_PLL2, 0); + k210_register_pll_child(np, ksc, K210_CLK_I2S2, K210_PLL2, 0); + k210_register_pll_child(np, ksc, K210_CLK_I2S0_M, K210_PLL2, 0); + k210_register_pll_child(np, ksc, K210_CLK_I2S1_M, K210_PLL2, 0); + k210_register_pll_child(np, ksc, K210_CLK_I2S2_M, K210_PLL2, 0); + + /* Clocks with IN0 as source */ + k210_register_in0_child(np, ksc, K210_CLK_WDT0); + k210_register_in0_child(np, ksc, K210_CLK_WDT1); + k210_register_in0_child(np, ksc, K210_CLK_RTC); + + /* Clocks with APB0 as source */ + k210_register_clk_child(np, ksc, K210_CLK_GPIO, K210_CLK_APB0); + k210_register_clk_child(np, ksc, K210_CLK_UART1, K210_CLK_APB0); + k210_register_clk_child(np, ksc, K210_CLK_UART2, K210_CLK_APB0); + k210_register_clk_child(np, ksc, K210_CLK_UART3, K210_CLK_APB0); + k210_register_clk_child(np, ksc, K210_CLK_FPIOA, K210_CLK_APB0); + k210_register_clk_child(np, ksc, K210_CLK_SHA, K210_CLK_APB0); + + /* Clocks with APB1 as source */ + k210_register_clk_child(np, ksc, K210_CLK_AES, K210_CLK_APB1); + k210_register_clk_child(np, ksc, K210_CLK_OTP, K210_CLK_APB1); + + /* Mux clocks with in0 or pll0 as source */ + k210_register_mux_clk(np, ksc, K210_CLK_SPI3); + k210_register_mux_clk(np, ksc, K210_CLK_TIMER0); + k210_register_mux_clk(np, ksc, K210_CLK_TIMER1); + k210_register_mux_clk(np, ksc, K210_CLK_TIMER2); + + /* Check for registration errors */ + for (i = 0; i < K210_NUM_CLKS; i++) { + if (ksc->clks[i].id != i) + return; + } + + ret = of_clk_add_hw_provider(np, k210_clk_hw_onecell_get, ksc); + if (ret) { + pr_err("%pOFP: add clock provider failed %d\n", np, ret); + return; + } + + pr_info("%pOFP: CPU running at %lu MHz\n", + np, clk_hw_get_rate(&ksc->clks[K210_CLK_CPU].hw) / 1000000); +} + +CLK_OF_DECLARE(k210_clk, "canaan,k210-clk", k210_clk_init); + +/* + * Enable PLL1 to be able to use the AI SRAM. + */ +void __init k210_clk_early_init(void __iomem *regs) +{ + struct k210_pll pll1; + + /* Make sure ACLK selector is set to PLL0 */ + k210_aclk_set_selector(regs, 1); + + /* Startup PLL1 to enable the aisram bank for general memory use */ + k210_init_pll(regs, K210_PLL1, &pll1); + k210_pll_enable_hw(regs, &pll1); +} diff --git a/drivers/soc/canaan/Kconfig b/drivers/soc/canaan/Kconfig index 5232d13f07e5..8179b69518b4 100644 --- a/drivers/soc/canaan/Kconfig +++ b/drivers/soc/canaan/Kconfig @@ -1,14 +1,12 @@ # SPDX-License-Identifier: GPL-2.0 -if SOC_CANAAN - -config K210_SYSCTL +config SOC_K210_SYSCTL bool "Canaan Kendryte K210 SoC system controller" - default y - depends on RISCV + depends on RISCV && SOC_CANAAN && OF + default SOC_CANAAN + select PM + select SIMPLE_PM_BUS + select SYSCON + select MFD_SYSCON help - Enables controlling the K210 various clocks and to enable - general purpose use of the extra 2MB of SRAM normally - reserved for the AI engine. - -endif + Canaan Kendryte K210 SoC system controller driver. diff --git a/drivers/soc/canaan/Makefile b/drivers/soc/canaan/Makefile index 002d9ce95c0d..570280ad7967 100644 --- a/drivers/soc/canaan/Makefile +++ b/drivers/soc/canaan/Makefile @@ -1,3 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 -obj-$(CONFIG_K210_SYSCTL) += k210-sysctl.o +obj-$(CONFIG_SOC_K210_SYSCTL) += k210-sysctl.o diff --git a/drivers/soc/canaan/k210-sysctl.c b/drivers/soc/canaan/k210-sysctl.c index 60b474c33d45..27a346c406bc 100644 --- a/drivers/soc/canaan/k210-sysctl.c +++ b/drivers/soc/canaan/k210-sysctl.c @@ -3,165 +3,45 @@ * Copyright (c) 2019 Christoph Hellwig. * Copyright (c) 2019 Western Digital Corporation or its affiliates. */ -#include #include -#include #include -#include -#include -#include +#include +#include #include #include -#define K210_SYSCTL_CLK0_FREQ 26000000UL - -/* Registers base address */ -#define K210_SYSCTL_SYSCTL_BASE_ADDR 0x50440000ULL - -/* Register bits */ -/* K210_SYSCTL_PLL1: clkr: 4bits, clkf1: 6bits, clkod: 4bits, bwadj: 4bits */ -#define PLL_RESET (1 << 20) -#define PLL_PWR (1 << 21) -#define PLL_BYPASS (1 << 23) -#define PLL_OUT_EN (1 << 25) -/* K210_SYSCTL_PLL_LOCK */ -#define PLL1_LOCK1 (1 << 8) -#define PLL1_LOCK2 (1 << 9) -#define PLL1_SLIP_CLEAR (1 << 10) -/* K210_SYSCTL_SEL0 */ -#define CLKSEL_ACLK (1 << 0) -/* K210_SYSCTL_CLKEN_CENT */ -#define CLKEN_CPU (1 << 0) -#define CLKEN_SRAM0 (1 << 1) -#define CLKEN_SRAM1 (1 << 2) -/* K210_SYSCTL_EN_PERI */ -#define CLKEN_ROM (1 << 0) -#define CLKEN_TIMER0 (1 << 21) -#define CLKEN_RTC (1 << 29) - -struct k210_sysctl { - void __iomem *regs; - struct clk_hw hw; -}; - -static void k210_set_bits(u32 val, void __iomem *reg) -{ - writel(readl(reg) | val, reg); -} - -static void k210_clear_bits(u32 val, void __iomem *reg) -{ - writel(readl(reg) & ~val, reg); -} - -static void k210_pll1_enable(void __iomem *regs) -{ - u32 val; - - val = readl(regs + K210_SYSCTL_PLL1); - val &= ~GENMASK(19, 0); /* clkr1 = 0 */ - val |= FIELD_PREP(GENMASK(9, 4), 0x3B); /* clkf1 = 59 */ - val |= FIELD_PREP(GENMASK(13, 10), 0x3); /* clkod1 = 3 */ - val |= FIELD_PREP(GENMASK(19, 14), 0x3B); /* bwadj1 = 59 */ - writel(val, regs + K210_SYSCTL_PLL1); - - k210_clear_bits(PLL_BYPASS, regs + K210_SYSCTL_PLL1); - k210_set_bits(PLL_PWR, regs + K210_SYSCTL_PLL1); - - /* - * Reset the pll. The magic NOPs come from the Kendryte reference SDK. - */ - k210_clear_bits(PLL_RESET, regs + K210_SYSCTL_PLL1); - k210_set_bits(PLL_RESET, regs + K210_SYSCTL_PLL1); - nop(); - nop(); - k210_clear_bits(PLL_RESET, regs + K210_SYSCTL_PLL1); - - for (;;) { - val = readl(regs + K210_SYSCTL_PLL_LOCK); - if (val & PLL1_LOCK2) - break; - writel(val | PLL1_SLIP_CLEAR, regs + K210_SYSCTL_PLL_LOCK); - } - - k210_set_bits(PLL_OUT_EN, regs + K210_SYSCTL_PLL1); -} - -static unsigned long k210_sysctl_clk_recalc_rate(struct clk_hw *hw, - unsigned long parent_rate) -{ - struct k210_sysctl *s = container_of(hw, struct k210_sysctl, hw); - u32 clksel0, pll0; - u64 pll0_freq, clkr0, clkf0, clkod0; - - /* - * If the clock selector is not set, use the base frequency. - * Otherwise, use PLL0 frequency with a frequency divisor. - */ - clksel0 = readl(s->regs + K210_SYSCTL_SEL0); - if (!(clksel0 & CLKSEL_ACLK)) - return K210_SYSCTL_CLK0_FREQ; - - /* - * Get PLL0 frequency: - * freq = base frequency * clkf0 / (clkr0 * clkod0) - */ - pll0 = readl(s->regs + K210_SYSCTL_PLL0); - clkr0 = 1 + FIELD_GET(GENMASK(3, 0), pll0); - clkf0 = 1 + FIELD_GET(GENMASK(9, 4), pll0); - clkod0 = 1 + FIELD_GET(GENMASK(13, 10), pll0); - pll0_freq = clkf0 * K210_SYSCTL_CLK0_FREQ / (clkr0 * clkod0); - - /* Get the frequency divisor from the clock selector */ - return pll0_freq / (2ULL << FIELD_GET(0x00000006, clksel0)); -} - -static const struct clk_ops k210_sysctl_clk_ops = { - .recalc_rate = k210_sysctl_clk_recalc_rate, -}; - -static const struct clk_init_data k210_clk_init_data = { - .name = "k210-sysctl-pll1", - .ops = &k210_sysctl_clk_ops, -}; - static int k210_sysctl_probe(struct platform_device *pdev) { - struct k210_sysctl *s; - int error; - - pr_info("Kendryte K210 SoC sysctl\n"); - - s = devm_kzalloc(&pdev->dev, sizeof(*s), GFP_KERNEL); - if (!s) - return -ENOMEM; - - s->regs = devm_ioremap_resource(&pdev->dev, - platform_get_resource(pdev, IORESOURCE_MEM, 0)); - if (IS_ERR(s->regs)) - return PTR_ERR(s->regs); - - s->hw.init = &k210_clk_init_data; - error = devm_clk_hw_register(&pdev->dev, &s->hw); - if (error) { - dev_err(&pdev->dev, "failed to register clk"); - return error; + struct device *dev = &pdev->dev; + struct clk *pclk; + int ret; + + dev_info(dev, "K210 system controller\n"); + + /* Get power bus clock */ + pclk = devm_clk_get(dev, NULL); + if (IS_ERR(pclk)) + return dev_err_probe(dev, PTR_ERR(pclk), + "Get bus clock failed\n"); + + ret = clk_prepare_enable(pclk); + if (ret) { + dev_err(dev, "Enable bus clock failed\n"); + return ret; } - error = devm_of_clk_add_hw_provider(&pdev->dev, of_clk_hw_simple_get, - &s->hw); - if (error) { - dev_err(&pdev->dev, "adding clk provider failed\n"); - return error; - } + /* Populate children */ + ret = devm_of_platform_populate(dev); + if (ret) + dev_err(dev, "Populate platform failed %d\n", ret); - return 0; + return ret; } static const struct of_device_id k210_sysctl_of_match[] = { - { .compatible = "kendryte,k210-sysctl", }, - {} + { .compatible = "canaan,k210-sysctl", }, + { /* sentinel */ }, }; static struct platform_driver k210_sysctl_driver = { @@ -171,12 +51,13 @@ static struct platform_driver k210_sysctl_driver = { }, .probe = k210_sysctl_probe, }; +builtin_platform_driver(k210_sysctl_driver); -static int __init k210_sysctl_init(void) -{ - return platform_driver_register(&k210_sysctl_driver); -} -core_initcall(k210_sysctl_init); +/* + * System controller registers base address and size. + */ +#define K210_SYSCTL_BASE_ADDR 0x50440000ULL +#define K210_SYSCTL_BASE_SIZE 0x1000 /* * This needs to be called very early during initialization, given that @@ -184,24 +65,14 @@ core_initcall(k210_sysctl_init); */ static void __init k210_soc_early_init(const void *fdt) { - void __iomem *regs; - - regs = ioremap(K210_SYSCTL_SYSCTL_BASE_ADDR, 0x1000); - if (!regs) - panic("K210 sysctl ioremap"); - - /* Enable PLL1 to make the KPU SRAM useable */ - k210_pll1_enable(regs); - - k210_set_bits(PLL_OUT_EN, regs + K210_SYSCTL_PLL0); + void __iomem *sysctl_base; - k210_set_bits(CLKEN_CPU | CLKEN_SRAM0 | CLKEN_SRAM1, - regs + K210_SYSCTL_EN_CENT); - k210_set_bits(CLKEN_ROM | CLKEN_TIMER0 | CLKEN_RTC, - regs + K210_SYSCTL_EN_PERI); + sysctl_base = ioremap(K210_SYSCTL_BASE_ADDR, K210_SYSCTL_BASE_SIZE); + if (!sysctl_base) + panic("k210-sysctl: ioremap failed"); - k210_set_bits(CLKSEL_ACLK, regs + K210_SYSCTL_SEL0); + k210_clk_early_init(sysctl_base); - iounmap(regs); + iounmap(sysctl_base); } -SOC_EARLY_INIT_DECLARE(generic_k210, "kendryte,k210", k210_soc_early_init); +SOC_EARLY_INIT_DECLARE(k210_soc, "canaan,kendryte-k210", k210_soc_early_init); diff --git a/include/soc/canaan/k210-sysctl.h b/include/soc/canaan/k210-sysctl.h index 2e037db68f35..0c2b2c2dabca 100644 --- a/include/soc/canaan/k210-sysctl.h +++ b/include/soc/canaan/k210-sysctl.h @@ -38,4 +38,6 @@ #define K210_SYSCTL_DMA_SEL1 0x68 /* DMA handshake selector 1 */ #define K210_SYSCTL_POWER_SEL 0x6C /* IO Power Mode Select controller */ +void k210_clk_early_init(void __iomem *regs); + #endif -- cgit v1.2.3 From 67d96729a9e789ecfddb0f701e5ec18389758dab Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Wed, 10 Feb 2021 14:02:23 +0900 Subject: riscv: Update Canaan Kendryte K210 device tree Update the Canaan Kendryte K210 base device tree k210.dtsi to define all supported peripherals of the SoC, their clocks and reset lines. The device tree file k210.dts is renamed to k210_generic.dts and becomes the default value selection of the configuration option SOC_CANAAN_K210_DTB_BUILTIN_SOURCE. No device beside the serial console is defined by this device tree. This makes this generic device tree suitable for use with a builtin initramfs with all known K210 based boards. These changes result in the K210_CLK_ACLK clock ID to be unused and removed from the dt-bindings k210-clk.h header file. Most updates to the k210.dtsi file come from Sean Anderson's work on U-Boot support for the K210. Cc: Rob Herring Cc: devicetree@vger.kernel.org Signed-off-by: Damien Le Moal Reviewed-by: Rob Herring Signed-off-by: Palmer Dabbelt --- arch/riscv/Kconfig.socs | 2 +- arch/riscv/boot/dts/canaan/k210.dts | 23 -- arch/riscv/boot/dts/canaan/k210.dtsi | 395 ++++++++++++++++++++++++++-- arch/riscv/boot/dts/canaan/k210_generic.dts | 46 ++++ include/dt-bindings/clock/k210-clk.h | 1 - 5 files changed, 414 insertions(+), 53 deletions(-) delete mode 100644 arch/riscv/boot/dts/canaan/k210.dts create mode 100644 arch/riscv/boot/dts/canaan/k210_generic.dts (limited to 'include') diff --git a/arch/riscv/Kconfig.socs b/arch/riscv/Kconfig.socs index 6402746c68f3..7efcece8896c 100644 --- a/arch/riscv/Kconfig.socs +++ b/arch/riscv/Kconfig.socs @@ -51,7 +51,7 @@ config SOC_CANAAN_K210_DTB_SOURCE string "Source file for the Canaan Kendryte K210 builtin DTB" depends on SOC_CANAAN depends on SOC_CANAAN_K210_DTB_BUILTIN - default "k210" + default "k210_generic" help Base name (without suffix, relative to arch/riscv/boot/dts/canaan) for the DTS file that will be used to produce the DTB linked into the diff --git a/arch/riscv/boot/dts/canaan/k210.dts b/arch/riscv/boot/dts/canaan/k210.dts deleted file mode 100644 index 0d1f28fce6b2..000000000000 --- a/arch/riscv/boot/dts/canaan/k210.dts +++ /dev/null @@ -1,23 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0+ -/* - * Copyright (C) 2020 Western Digital Corporation or its affiliates. - */ - -/dts-v1/; - -#include "k210.dtsi" - -/ { - model = "Kendryte K210 generic"; - compatible = "kendryte,k210"; - - chosen { - bootargs = "earlycon console=ttySIF0"; - stdout-path = "serial0"; - }; -}; - -&uarths0 { - status = "okay"; -}; - diff --git a/arch/riscv/boot/dts/canaan/k210.dtsi b/arch/riscv/boot/dts/canaan/k210.dtsi index 354b263195a3..5e8ca8142482 100644 --- a/arch/riscv/boot/dts/canaan/k210.dtsi +++ b/arch/riscv/boot/dts/canaan/k210.dtsi @@ -1,9 +1,11 @@ // SPDX-License-Identifier: GPL-2.0+ /* - * Copyright (C) 2019 Sean Anderson + * Copyright (C) 2019-20 Sean Anderson * Copyright (C) 2020 Western Digital Corporation or its affiliates. */ #include +#include +#include / { /* @@ -12,14 +14,17 @@ */ #address-cells = <1>; #size-cells = <1>; - compatible = "kendryte,k210"; + compatible = "canaan,kendryte-k210"; aliases { serial0 = &uarths0; + serial1 = &uart1; + serial2 = &uart2; + serial3 = &uart3; }; /* - * The K210 has an sv39 MMU following the priviledge specification v1.9. + * The K210 has an sv39 MMU following the privileged specification v1.9. * Since this is a non-ratified draft specification, the kernel does not * support it and the K210 support enabled only for the !MMU case. * Be consistent with this by setting the CPUs MMU type to "none". @@ -30,14 +35,14 @@ timebase-frequency = <7800000>; cpu0: cpu@0 { device_type = "cpu"; + compatible = "canaan,k210", "riscv"; reg = <0>; - compatible = "kendryte,k210", "sifive,rocket0", "riscv"; riscv,isa = "rv64imafdc"; - mmu-type = "none"; - i-cache-size = <0x8000>; + mmu-type = "riscv,none"; i-cache-block-size = <64>; - d-cache-size = <0x8000>; + i-cache-size = <0x8000>; d-cache-block-size = <64>; + d-cache-size = <0x8000>; cpu0_intc: interrupt-controller { #interrupt-cells = <1>; interrupt-controller; @@ -46,14 +51,14 @@ }; cpu1: cpu@1 { device_type = "cpu"; + compatible = "canaan,k210", "riscv"; reg = <1>; - compatible = "kendryte,k210", "sifive,rocket0", "riscv"; riscv,isa = "rv64imafdc"; - mmu-type = "none"; - i-cache-size = <0x8000>; + mmu-type = "riscv,none"; i-cache-block-size = <64>; - d-cache-size = <0x8000>; + i-cache-size = <0x8000>; d-cache-block-size = <64>; + d-cache-size = <0x8000>; cpu1_intc: interrupt-controller { #interrupt-cells = <1>; interrupt-controller; @@ -64,10 +69,15 @@ sram: memory@80000000 { device_type = "memory"; + compatible = "canaan,k210-sram"; reg = <0x80000000 0x400000>, <0x80400000 0x200000>, <0x80600000 0x200000>; reg-names = "sram0", "sram1", "aisram"; + clocks = <&sysclk K210_CLK_SRAM0>, + <&sysclk K210_CLK_SRAM1>, + <&sysclk K210_CLK_AI>; + clock-names = "sram0", "sram1", "aisram"; }; clocks { @@ -81,40 +91,369 @@ soc { #address-cells = <1>; #size-cells = <1>; - compatible = "kendryte,k210-soc", "simple-bus"; + compatible = "simple-bus"; ranges; interrupt-parent = <&plic0>; - sysctl: sysctl@50440000 { - compatible = "kendryte,k210-sysctl", "simple-mfd"; - reg = <0x50440000 0x1000>; - #clock-cells = <1>; + rom0: nvmem@1000 { + reg = <0x1000 0x1000>; + read-only; }; - clint0: clint@2000000 { - #interrupt-cells = <1>; - compatible = "riscv,clint0"; + clint0: timer@2000000 { + compatible = "canaan,k210-clint", "sifive,clint0"; reg = <0x2000000 0xC000>; - interrupts-extended = <&cpu0_intc 3 &cpu0_intc 7 - &cpu1_intc 3 &cpu1_intc 7>; + interrupts-extended = <&cpu0_intc 3 &cpu0_intc 7 + &cpu1_intc 3 &cpu1_intc 7>; }; plic0: interrupt-controller@c000000 { #interrupt-cells = <1>; - interrupt-controller; - compatible = "kendryte,k210-plic0", "riscv,plic0"; + #address-cells = <0>; + compatible = "canaan,k210-plic", "sifive,plic-1.0.0"; reg = <0xC000000 0x4000000>; - interrupts-extended = <&cpu0_intc 11>, <&cpu0_intc 0xffffffff>, - <&cpu1_intc 11>, <&cpu1_intc 0xffffffff>; + interrupt-controller; + interrupts-extended = <&cpu0_intc 11 &cpu1_intc 11>; riscv,ndev = <65>; - riscv,max-priority = <7>; }; uarths0: serial@38000000 { - compatible = "kendryte,k210-uarths", "sifive,uart0"; + compatible = "canaan,k210-uarths", "sifive,uart0"; reg = <0x38000000 0x1000>; interrupts = <33>; - clocks = <&sysctl K210_CLK_CPU>; + clocks = <&sysclk K210_CLK_CPU>; + }; + + gpio0: gpio-controller@38001000 { + #interrupt-cells = <2>; + #gpio-cells = <2>; + compatible = "canaan,k210-gpiohs", "sifive,gpio0"; + reg = <0x38001000 0x1000>; + interrupt-controller; + interrupts = <34 35 36 37 38 39 40 41 + 42 43 44 45 46 47 48 49 + 50 51 52 53 54 55 56 57 + 58 59 60 61 62 63 64 65>; + gpio-controller; + ngpios = <32>; + }; + + dmac0: dma-controller@50000000 { + compatible = "snps,axi-dma-1.01a"; + reg = <0x50000000 0x1000>; + interrupts = <27 28 29 30 31 32>; + #dma-cells = <1>; + clocks = <&sysclk K210_CLK_DMA>, <&sysclk K210_CLK_DMA>; + clock-names = "core-clk", "cfgr-clk"; + resets = <&sysrst K210_RST_DMA>; + dma-channels = <6>; + snps,dma-masters = <2>; + snps,priority = <0 1 2 3 4 5>; + snps,data-width = <5>; + snps,block-size = <0x200000 0x200000 0x200000 + 0x200000 0x200000 0x200000>; + snps,axi-max-burst-len = <256>; + }; + + apb0: bus@50200000 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "simple-pm-bus"; + ranges; + clocks = <&sysclk K210_CLK_APB0>; + + gpio1: gpio@50200000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "snps,dw-apb-gpio"; + reg = <0x50200000 0x80>; + clocks = <&sysclk K210_CLK_APB0>, + <&sysclk K210_CLK_GPIO>; + clock-names = "bus", "db"; + resets = <&sysrst K210_RST_GPIO>; + + gpio1_0: gpio-port@0 { + #gpio-cells = <2>; + #interrupt-cells = <2>; + compatible = "snps,dw-apb-gpio-port"; + reg = <0>; + interrupt-controller; + interrupts = <23>; + gpio-controller; + ngpios = <8>; + }; + }; + + uart1: serial@50210000 { + compatible = "snps,dw-apb-uart"; + reg = <0x50210000 0x100>; + interrupts = <11>; + clocks = <&sysclk K210_CLK_UART1>, + <&sysclk K210_CLK_APB0>; + clock-names = "baudclk", "apb_pclk"; + resets = <&sysrst K210_RST_UART1>; + reg-io-width = <4>; + reg-shift = <2>; + dcd-override; + dsr-override; + cts-override; + ri-override; + }; + + uart2: serial@50220000 { + compatible = "snps,dw-apb-uart"; + reg = <0x50220000 0x100>; + interrupts = <12>; + clocks = <&sysclk K210_CLK_UART2>, + <&sysclk K210_CLK_APB0>; + clock-names = "baudclk", "apb_pclk"; + resets = <&sysrst K210_RST_UART2>; + reg-io-width = <4>; + reg-shift = <2>; + dcd-override; + dsr-override; + cts-override; + ri-override; + }; + + uart3: serial@50230000 { + compatible = "snps,dw-apb-uart"; + reg = <0x50230000 0x100>; + interrupts = <13>; + clocks = <&sysclk K210_CLK_UART3>, + <&sysclk K210_CLK_APB0>; + clock-names = "baudclk", "apb_pclk"; + resets = <&sysrst K210_RST_UART3>; + reg-io-width = <4>; + reg-shift = <2>; + dcd-override; + dsr-override; + cts-override; + ri-override; + }; + + spi2: spi@50240000 { + compatible = "canaan,k210-spi"; + spi-slave; + reg = <0x50240000 0x100>; + #address-cells = <0>; + #size-cells = <0>; + interrupts = <3>; + clocks = <&sysclk K210_CLK_SPI2>, + <&sysclk K210_CLK_APB0>; + clock-names = "ssi_clk", "pclk"; + resets = <&sysrst K210_RST_SPI2>; + spi-max-frequency = <25000000>; + }; + + i2s0: i2s@50250000 { + compatible = "snps,designware-i2s"; + reg = <0x50250000 0x200>; + interrupts = <5>; + clocks = <&sysclk K210_CLK_I2S0>; + clock-names = "i2sclk"; + resets = <&sysrst K210_RST_I2S0>; + }; + + i2s1: i2s@50260000 { + compatible = "snps,designware-i2s"; + reg = <0x50260000 0x200>; + interrupts = <6>; + clocks = <&sysclk K210_CLK_I2S1>; + clock-names = "i2sclk"; + resets = <&sysrst K210_RST_I2S1>; + }; + + i2s2: i2s@50270000 { + compatible = "snps,designware-i2s"; + reg = <0x50270000 0x200>; + interrupts = <7>; + clocks = <&sysclk K210_CLK_I2S2>; + clock-names = "i2sclk"; + resets = <&sysrst K210_RST_I2S2>; + }; + + i2c0: i2c@50280000 { + compatible = "snps,designware-i2c"; + reg = <0x50280000 0x100>; + interrupts = <8>; + clocks = <&sysclk K210_CLK_I2C0>, + <&sysclk K210_CLK_APB0>; + clock-names = "ref", "pclk"; + resets = <&sysrst K210_RST_I2C0>; + }; + + i2c1: i2c@50290000 { + compatible = "snps,designware-i2c"; + reg = <0x50290000 0x100>; + interrupts = <9>; + clocks = <&sysclk K210_CLK_I2C1>, + <&sysclk K210_CLK_APB0>; + clock-names = "ref", "pclk"; + resets = <&sysrst K210_RST_I2C1>; + }; + + i2c2: i2c@502a0000 { + compatible = "snps,designware-i2c"; + reg = <0x502A0000 0x100>; + interrupts = <10>; + clocks = <&sysclk K210_CLK_I2C2>, + <&sysclk K210_CLK_APB0>; + clock-names = "ref", "pclk"; + resets = <&sysrst K210_RST_I2C2>; + }; + + fpioa: pinmux@502b0000 { + compatible = "canaan,k210-fpioa"; + reg = <0x502B0000 0x100>; + clocks = <&sysclk K210_CLK_FPIOA>, + <&sysclk K210_CLK_APB0>; + clock-names = "ref", "pclk"; + resets = <&sysrst K210_RST_FPIOA>; + canaan,k210-sysctl-power = <&sysctl 108>; + }; + + timer0: timer@502d0000 { + compatible = "snps,dw-apb-timer"; + reg = <0x502D0000 0x100>; + interrupts = <14 15>; + clocks = <&sysclk K210_CLK_TIMER0>, + <&sysclk K210_CLK_APB0>; + clock-names = "timer", "pclk"; + resets = <&sysrst K210_RST_TIMER0>; + }; + + timer1: timer@502e0000 { + compatible = "snps,dw-apb-timer"; + reg = <0x502E0000 0x100>; + interrupts = <16 17>; + clocks = <&sysclk K210_CLK_TIMER1>, + <&sysclk K210_CLK_APB0>; + clock-names = "timer", "pclk"; + resets = <&sysrst K210_RST_TIMER1>; + }; + + timer2: timer@502f0000 { + compatible = "snps,dw-apb-timer"; + reg = <0x502F0000 0x100>; + interrupts = <18 19>; + clocks = <&sysclk K210_CLK_TIMER2>, + <&sysclk K210_CLK_APB0>; + clock-names = "timer", "pclk"; + resets = <&sysrst K210_RST_TIMER2>; + }; + }; + + apb1: bus@50400000 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "simple-pm-bus"; + ranges; + clocks = <&sysclk K210_CLK_APB1>; + + wdt0: watchdog@50400000 { + compatible = "snps,dw-wdt"; + reg = <0x50400000 0x100>; + interrupts = <21>; + clocks = <&sysclk K210_CLK_WDT0>, + <&sysclk K210_CLK_APB1>; + clock-names = "tclk", "pclk"; + resets = <&sysrst K210_RST_WDT0>; + }; + + wdt1: watchdog@50410000 { + compatible = "snps,dw-wdt"; + reg = <0x50410000 0x100>; + interrupts = <22>; + clocks = <&sysclk K210_CLK_WDT1>, + <&sysclk K210_CLK_APB1>; + clock-names = "tclk", "pclk"; + resets = <&sysrst K210_RST_WDT1>; + }; + + sysctl: syscon@50440000 { + compatible = "canaan,k210-sysctl", + "syscon", "simple-mfd"; + reg = <0x50440000 0x100>; + clocks = <&sysclk K210_CLK_APB1>; + clock-names = "pclk"; + + sysclk: clock-controller { + #clock-cells = <1>; + compatible = "canaan,k210-clk"; + clocks = <&in0>; + }; + + sysrst: reset-controller { + compatible = "canaan,k210-rst"; + #reset-cells = <1>; + }; + + reboot: syscon-reboot { + compatible = "syscon-reboot"; + regmap = <&sysctl>; + offset = <48>; + mask = <1>; + value = <1>; + }; + }; + }; + + apb2: bus@52000000 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "simple-pm-bus"; + ranges; + clocks = <&sysclk K210_CLK_APB2>; + + spi0: spi@52000000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "canaan,k210-spi"; + reg = <0x52000000 0x100>; + interrupts = <1>; + clocks = <&sysclk K210_CLK_SPI0>, + <&sysclk K210_CLK_APB2>; + clock-names = "ssi_clk", "pclk"; + resets = <&sysrst K210_RST_SPI0>; + reset-names = "spi"; + spi-max-frequency = <25000000>; + num-cs = <4>; + reg-io-width = <4>; + }; + + spi1: spi@53000000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "canaan,k210-spi"; + reg = <0x53000000 0x100>; + interrupts = <2>; + clocks = <&sysclk K210_CLK_SPI1>, + <&sysclk K210_CLK_APB2>; + clock-names = "ssi_clk", "pclk"; + resets = <&sysrst K210_RST_SPI1>; + reset-names = "spi"; + spi-max-frequency = <25000000>; + num-cs = <4>; + reg-io-width = <4>; + }; + + spi3: spi@54000000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "snps,dwc-ssi-1.01a"; + reg = <0x54000000 0x200>; + interrupts = <4>; + clocks = <&sysclk K210_CLK_SPI3>, + <&sysclk K210_CLK_APB2>; + clock-names = "ssi_clk", "pclk"; + resets = <&sysrst K210_RST_SPI3>; + reset-names = "spi"; + /* Could possibly go up to 200 MHz */ + spi-max-frequency = <100000000>; + num-cs = <4>; + reg-io-width = <4>; + }; }; }; }; diff --git a/arch/riscv/boot/dts/canaan/k210_generic.dts b/arch/riscv/boot/dts/canaan/k210_generic.dts new file mode 100644 index 000000000000..396c8ca4d24d --- /dev/null +++ b/arch/riscv/boot/dts/canaan/k210_generic.dts @@ -0,0 +1,46 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright (C) 2019-20 Sean Anderson + * Copyright (C) 2020 Western Digital Corporation or its affiliates. + */ + +/dts-v1/; + +#include "k210.dtsi" + +#include +#include + +/ { + model = "Kendryte K210 generic"; + compatible = "canaan,kendryte-k210"; + + chosen { + bootargs = "earlycon console=ttySIF0"; + stdout-path = "serial0:115200n8"; + }; +}; + +&fpioa { + pinctrl-0 = <&jtag_pins>; + pinctrl-names = "default"; + status = "okay"; + + jtag_pins: jtag-pinmux { + pinmux = , + , + , + ; + }; + + uarths_pins: uarths-pinmux { + pinmux = , + ; + }; +}; + +&uarths0 { + pinctrl-0 = <&uarths_pins>; + pinctrl-names = "default"; + status = "okay"; +}; diff --git a/include/dt-bindings/clock/k210-clk.h b/include/dt-bindings/clock/k210-clk.h index a48176ad3c23..b2de702cbf75 100644 --- a/include/dt-bindings/clock/k210-clk.h +++ b/include/dt-bindings/clock/k210-clk.h @@ -9,7 +9,6 @@ /* * Kendryte K210 SoC clock identifiers (arbitrary values). */ -#define K210_CLK_ACLK 0 #define K210_CLK_CPU 0 #define K210_CLK_SRAM0 1 #define K210_CLK_SRAM1 2 -- cgit v1.2.3 From 1c73e0c5e54d5f7d77f422a10b03ebe61eaed5ad Mon Sep 17 00:00:00 2001 From: Aleksandr Miloserdov Date: Tue, 9 Feb 2021 10:22:01 +0300 Subject: scsi: target: core: Add cmd length set before cmd complete TCM doesn't properly handle underflow case for service actions. One way to prevent it is to always complete command with target_complete_cmd_with_length(), however it requires access to data_sg, which is not always available. This change introduces target_set_cmd_data_length() function which allows to set command data length before completing it. Link: https://lore.kernel.org/r/20210209072202.41154-2-a.miloserdov@yadro.com Reviewed-by: Roman Bolshakov Reviewed-by: Bodo Stroesser Signed-off-by: Aleksandr Miloserdov Signed-off-by: Martin K. Petersen --- drivers/target/target_core_transport.c | 15 +++++++++++---- include/target/target_core_backend.h | 1 + 2 files changed, 12 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 93ea17cbad79..5ecb9f18a53d 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -879,11 +879,9 @@ void target_complete_cmd(struct se_cmd *cmd, u8 scsi_status) } EXPORT_SYMBOL(target_complete_cmd); -void target_complete_cmd_with_length(struct se_cmd *cmd, u8 scsi_status, int length) +void target_set_cmd_data_length(struct se_cmd *cmd, int length) { - if ((scsi_status == SAM_STAT_GOOD || - cmd->se_cmd_flags & SCF_TREAT_READ_AS_NORMAL) && - length < cmd->data_length) { + if (length < cmd->data_length) { if (cmd->se_cmd_flags & SCF_UNDERFLOW_BIT) { cmd->residual_count += cmd->data_length - length; } else { @@ -893,6 +891,15 @@ void target_complete_cmd_with_length(struct se_cmd *cmd, u8 scsi_status, int len cmd->data_length = length; } +} +EXPORT_SYMBOL(target_set_cmd_data_length); + +void target_complete_cmd_with_length(struct se_cmd *cmd, u8 scsi_status, int length) +{ + if (scsi_status == SAM_STAT_GOOD || + cmd->se_cmd_flags & SCF_TREAT_READ_AS_NORMAL) { + target_set_cmd_data_length(cmd, length); + } target_complete_cmd(cmd, scsi_status); } diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h index 6336780d83a7..ce2fba49c95d 100644 --- a/include/target/target_core_backend.h +++ b/include/target/target_core_backend.h @@ -72,6 +72,7 @@ int transport_backend_register(const struct target_backend_ops *); void target_backend_unregister(const struct target_backend_ops *); void target_complete_cmd(struct se_cmd *, u8); +void target_set_cmd_data_length(struct se_cmd *, int); void target_complete_cmd_with_length(struct se_cmd *, u8, int); void transport_copy_sense_to_cmd(struct se_cmd *, unsigned char *); -- cgit v1.2.3 From faf7f3fdd151a03df68de3cb90bb5c394a6774c2 Mon Sep 17 00:00:00 2001 From: Philip Chen Date: Mon, 22 Feb 2021 21:01:26 -0800 Subject: dt-bindings: input: Create macros for cros-ec keymap In Chrome OS, the keyboard matrix can be split to two groups: The keymap for the top row keys can be customized based on OEM preference, while the keymap for the other keys is generic/fixed across boards. This patch creates marcos for the keymaps of these two groups, making it easier to reuse the generic portion of keymap when we override the keymap in the board-specific dts for custom top row design. Signed-off-by: Philip Chen Acked-by: Rob Herring Reviewed-by: Stephen Boyd Link: https://lore.kernel.org/r/20210115143555.v6.1.Iaa8a60cf2ed4b7ad5e2fbb4ad76a1c600ee36113@changeid Signed-off-by: Dmitry Torokhov --- include/dt-bindings/input/cros-ec-keyboard.h | 103 +++++++++++++++++++++++++++ 1 file changed, 103 insertions(+) create mode 100644 include/dt-bindings/input/cros-ec-keyboard.h (limited to 'include') diff --git a/include/dt-bindings/input/cros-ec-keyboard.h b/include/dt-bindings/input/cros-ec-keyboard.h new file mode 100644 index 000000000000..a37a8c570121 --- /dev/null +++ b/include/dt-bindings/input/cros-ec-keyboard.h @@ -0,0 +1,103 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * This header provides the constants of the standard Chrome OS key matrix + * for cros-ec keyboard-controller bindings. + * + * Copyright (c) 2021 Google, Inc + */ + +#ifndef _CROS_EC_KEYBOARD_H +#define _CROS_EC_KEYBOARD_H + +#define CROS_STD_TOP_ROW_KEYMAP \ + MATRIX_KEY(0x00, 0x02, KEY_F1) \ + MATRIX_KEY(0x03, 0x02, KEY_F2) \ + MATRIX_KEY(0x02, 0x02, KEY_F3) \ + MATRIX_KEY(0x01, 0x02, KEY_F4) \ + MATRIX_KEY(0x03, 0x04, KEY_F5) \ + MATRIX_KEY(0x02, 0x04, KEY_F6) \ + MATRIX_KEY(0x01, 0x04, KEY_F7) \ + MATRIX_KEY(0x02, 0x09, KEY_F8) \ + MATRIX_KEY(0x01, 0x09, KEY_F9) \ + MATRIX_KEY(0x00, 0x04, KEY_F10) \ + MATRIX_KEY(0x03, 0x09, KEY_F13) + +#define CROS_STD_MAIN_KEYMAP \ + MATRIX_KEY(0x00, 0x01, KEY_LEFTMETA) \ + MATRIX_KEY(0x00, 0x03, KEY_B) \ + MATRIX_KEY(0x00, 0x05, KEY_RO) \ + MATRIX_KEY(0x00, 0x06, KEY_N) \ + MATRIX_KEY(0x00, 0x08, KEY_EQUAL) \ + MATRIX_KEY(0x00, 0x0a, KEY_RIGHTALT) \ + MATRIX_KEY(0x01, 0x01, KEY_ESC) \ + MATRIX_KEY(0x01, 0x03, KEY_G) \ + MATRIX_KEY(0x01, 0x06, KEY_H) \ + MATRIX_KEY(0x01, 0x08, KEY_APOSTROPHE) \ + MATRIX_KEY(0x01, 0x0b, KEY_BACKSPACE) \ + MATRIX_KEY(0x01, 0x0c, KEY_HENKAN) \ + \ + MATRIX_KEY(0x02, 0x00, KEY_LEFTCTRL) \ + MATRIX_KEY(0x02, 0x01, KEY_TAB) \ + MATRIX_KEY(0x02, 0x03, KEY_T) \ + MATRIX_KEY(0x02, 0x05, KEY_RIGHTBRACE) \ + MATRIX_KEY(0x02, 0x06, KEY_Y) \ + MATRIX_KEY(0x02, 0x07, KEY_102ND) \ + MATRIX_KEY(0x02, 0x08, KEY_LEFTBRACE) \ + MATRIX_KEY(0x02, 0x0a, KEY_YEN) \ + \ + MATRIX_KEY(0x03, 0x00, KEY_LEFTMETA) \ + MATRIX_KEY(0x03, 0x01, KEY_GRAVE) \ + MATRIX_KEY(0x03, 0x03, KEY_5) \ + MATRIX_KEY(0x03, 0x06, KEY_6) \ + MATRIX_KEY(0x03, 0x08, KEY_MINUS) \ + MATRIX_KEY(0x03, 0x0b, KEY_BACKSLASH) \ + MATRIX_KEY(0x03, 0x0c, KEY_MUHENKAN) \ + \ + MATRIX_KEY(0x04, 0x00, KEY_RIGHTCTRL) \ + MATRIX_KEY(0x04, 0x01, KEY_A) \ + MATRIX_KEY(0x04, 0x02, KEY_D) \ + MATRIX_KEY(0x04, 0x03, KEY_F) \ + MATRIX_KEY(0x04, 0x04, KEY_S) \ + MATRIX_KEY(0x04, 0x05, KEY_K) \ + MATRIX_KEY(0x04, 0x06, KEY_J) \ + MATRIX_KEY(0x04, 0x08, KEY_SEMICOLON) \ + MATRIX_KEY(0x04, 0x09, KEY_L) \ + MATRIX_KEY(0x04, 0x0a, KEY_BACKSLASH) \ + MATRIX_KEY(0x04, 0x0b, KEY_ENTER) \ + \ + MATRIX_KEY(0x05, 0x01, KEY_Z) \ + MATRIX_KEY(0x05, 0x02, KEY_C) \ + MATRIX_KEY(0x05, 0x03, KEY_V) \ + MATRIX_KEY(0x05, 0x04, KEY_X) \ + MATRIX_KEY(0x05, 0x05, KEY_COMMA) \ + MATRIX_KEY(0x05, 0x06, KEY_M) \ + MATRIX_KEY(0x05, 0x07, KEY_LEFTSHIFT) \ + MATRIX_KEY(0x05, 0x08, KEY_SLASH) \ + MATRIX_KEY(0x05, 0x09, KEY_DOT) \ + MATRIX_KEY(0x05, 0x0b, KEY_SPACE) \ + \ + MATRIX_KEY(0x06, 0x01, KEY_1) \ + MATRIX_KEY(0x06, 0x02, KEY_3) \ + MATRIX_KEY(0x06, 0x03, KEY_4) \ + MATRIX_KEY(0x06, 0x04, KEY_2) \ + MATRIX_KEY(0x06, 0x05, KEY_8) \ + MATRIX_KEY(0x06, 0x06, KEY_7) \ + MATRIX_KEY(0x06, 0x08, KEY_0) \ + MATRIX_KEY(0x06, 0x09, KEY_9) \ + MATRIX_KEY(0x06, 0x0a, KEY_LEFTALT) \ + MATRIX_KEY(0x06, 0x0b, KEY_DOWN) \ + MATRIX_KEY(0x06, 0x0c, KEY_RIGHT) \ + \ + MATRIX_KEY(0x07, 0x01, KEY_Q) \ + MATRIX_KEY(0x07, 0x02, KEY_E) \ + MATRIX_KEY(0x07, 0x03, KEY_R) \ + MATRIX_KEY(0x07, 0x04, KEY_W) \ + MATRIX_KEY(0x07, 0x05, KEY_I) \ + MATRIX_KEY(0x07, 0x06, KEY_U) \ + MATRIX_KEY(0x07, 0x07, KEY_RIGHTSHIFT) \ + MATRIX_KEY(0x07, 0x08, KEY_P) \ + MATRIX_KEY(0x07, 0x09, KEY_O) \ + MATRIX_KEY(0x07, 0x0b, KEY_UP) \ + MATRIX_KEY(0x07, 0x0c, KEY_LEFT) + +#endif /* _CROS_EC_KEYBOARD_H */ -- cgit v1.2.3 From 3d283f0b076442354f301461bece737d3c109a1b Mon Sep 17 00:00:00 2001 From: Philip Chen Date: Mon, 22 Feb 2021 21:11:07 -0800 Subject: dt-bindings: input: Fix the keymap for LOCK key Decouple LOCK from F13 and directly map the LOCK key (KSI3/KSO9) to KEY_SLEEP action key code. Signed-off-by: Philip Chen Reviewed-by: Stephen Boyd Acked-by: Rob Herring Link: https://lore.kernel.org/r/20210115143555.v6.3.I96134907488f41f358d03f3c1b08194f9547e670@changeid Signed-off-by: Dmitry Torokhov --- include/dt-bindings/input/cros-ec-keyboard.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/dt-bindings/input/cros-ec-keyboard.h b/include/dt-bindings/input/cros-ec-keyboard.h index a37a8c570121..f0ae03634a96 100644 --- a/include/dt-bindings/input/cros-ec-keyboard.h +++ b/include/dt-bindings/input/cros-ec-keyboard.h @@ -19,8 +19,7 @@ MATRIX_KEY(0x01, 0x04, KEY_F7) \ MATRIX_KEY(0x02, 0x09, KEY_F8) \ MATRIX_KEY(0x01, 0x09, KEY_F9) \ - MATRIX_KEY(0x00, 0x04, KEY_F10) \ - MATRIX_KEY(0x03, 0x09, KEY_F13) + MATRIX_KEY(0x00, 0x04, KEY_F10) #define CROS_STD_MAIN_KEYMAP \ MATRIX_KEY(0x00, 0x01, KEY_LEFTMETA) \ @@ -50,6 +49,7 @@ MATRIX_KEY(0x03, 0x03, KEY_5) \ MATRIX_KEY(0x03, 0x06, KEY_6) \ MATRIX_KEY(0x03, 0x08, KEY_MINUS) \ + MATRIX_KEY(0x03, 0x09, KEY_SLEEP) \ MATRIX_KEY(0x03, 0x0b, KEY_BACKSLASH) \ MATRIX_KEY(0x03, 0x0c, KEY_MUHENKAN) \ \ -- cgit v1.2.3 From 49387f628840eac1e7e1113f4f2c150cdecf88c7 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Tue, 23 Feb 2021 11:36:21 +0000 Subject: vmlinux.lds.h: catch even more instrumentation symbols into .data LKP caught another bunch of orphaned instrumentation symbols [0]: mipsel-linux-ld: warning: orphan section `.data.$LPBX1' from `init/main.o' being placed in section `.data.$LPBX1' mipsel-linux-ld: warning: orphan section `.data.$LPBX0' from `init/main.o' being placed in section `.data.$LPBX0' mipsel-linux-ld: warning: orphan section `.data.$LPBX1' from `init/do_mounts.o' being placed in section `.data.$LPBX1' mipsel-linux-ld: warning: orphan section `.data.$LPBX0' from `init/do_mounts.o' being placed in section `.data.$LPBX0' mipsel-linux-ld: warning: orphan section `.data.$LPBX1' from `init/do_mounts_initrd.o' being placed in section `.data.$LPBX1' mipsel-linux-ld: warning: orphan section `.data.$LPBX0' from `init/do_mounts_initrd.o' being placed in section `.data.$LPBX0' mipsel-linux-ld: warning: orphan section `.data.$LPBX1' from `init/initramfs.o' being placed in section `.data.$LPBX1' mipsel-linux-ld: warning: orphan section `.data.$LPBX0' from `init/initramfs.o' being placed in section `.data.$LPBX0' mipsel-linux-ld: warning: orphan section `.data.$LPBX1' from `init/calibrate.o' being placed in section `.data.$LPBX1' mipsel-linux-ld: warning: orphan section `.data.$LPBX0' from `init/calibrate.o' being placed in section `.data.$LPBX0' [...] Soften the wildcard to .data.$L* to grab these ones into .data too. [0] https://lore.kernel.org/lkml/202102231519.lWPLPveV-lkp@intel.com Reported-by: kernel test robot Signed-off-by: Alexander Lobakin Signed-off-by: Thomas Bogendoerfer --- include/asm-generic/vmlinux.lds.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 83537e5ee78f..ecfb54e9fda5 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -95,7 +95,7 @@ */ #ifdef CONFIG_LD_DEAD_CODE_DATA_ELIMINATION #define TEXT_MAIN .text .text.[0-9a-zA-Z_]* -#define DATA_MAIN .data .data.[0-9a-zA-Z_]* .data..L* .data..compoundliteral* .data.$__unnamed_* .data.$Lubsan_* +#define DATA_MAIN .data .data.[0-9a-zA-Z_]* .data..L* .data..compoundliteral* .data.$__unnamed_* .data.$L* #define SDATA_MAIN .sdata .sdata.[0-9a-zA-Z_]* #define RODATA_MAIN .rodata .rodata.[0-9a-zA-Z_]* .rodata..L* #define BSS_MAIN .bss .bss.[0-9a-zA-Z_]* .bss..compoundliteral* -- cgit v1.2.3 From fd70a406a344e084ac680c3f14e71d37d6023883 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Tue, 5 Jan 2021 12:31:59 +0200 Subject: vdpa: Extend routine to accept vdpa device name In a subsequent patch, when user initiated command creates a vdpa device, the user chooses the name of the vdpa device. To support it, extend the device allocation API to consider this name specified by the caller driver. Signed-off-by: Parav Pandit Reviewed-by: Eli Cohen Acked-by: Jason Wang Link: https://lore.kernel.org/r/20210105103203.82508-3-parav@nvidia.com Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/ifcvf/ifcvf_main.c | 2 +- drivers/vdpa/mlx5/net/mlx5_vnet.c | 2 +- drivers/vdpa/vdpa.c | 36 ++++++++++++++++++++++++++++++++---- drivers/vdpa/vdpa_sim/vdpa_sim.c | 2 +- include/linux/vdpa.h | 7 +++---- 5 files changed, 38 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c index fa1af301cf55..7c8bbfcf6c3e 100644 --- a/drivers/vdpa/ifcvf/ifcvf_main.c +++ b/drivers/vdpa/ifcvf/ifcvf_main.c @@ -432,7 +432,7 @@ static int ifcvf_probe(struct pci_dev *pdev, const struct pci_device_id *id) adapter = vdpa_alloc_device(struct ifcvf_adapter, vdpa, dev, &ifc_vdpa_ops, - IFCVF_MAX_QUEUE_PAIRS * 2); + IFCVF_MAX_QUEUE_PAIRS * 2, NULL); if (adapter == NULL) { IFCVF_ERR(pdev, "Failed to allocate vDPA structure"); return -ENOMEM; diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index b5fe6d2ad22f..dc88559a8d49 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -1982,7 +1982,7 @@ static int mlx5v_probe(struct auxiliary_device *adev, max_vqs = min_t(u32, max_vqs, MLX5_MAX_SUPPORTED_VQS); ndev = vdpa_alloc_device(struct mlx5_vdpa_net, mvdev.vdev, mdev->device, &mlx5_vdpa_ops, - 2 * mlx5_vdpa_max_qps(max_vqs)); + 2 * mlx5_vdpa_max_qps(max_vqs), NULL); if (IS_ERR(ndev)) return PTR_ERR(ndev); diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index c0825650c055..7414bbd9057c 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -12,6 +12,8 @@ #include #include +/* A global mutex that protects vdpa management device and device level operations. */ +static DEFINE_MUTEX(vdpa_dev_mutex); static DEFINE_IDA(vdpa_index_ida); static int vdpa_dev_probe(struct device *d) @@ -63,6 +65,7 @@ static void vdpa_release_dev(struct device *d) * @config: the bus operations that is supported by this device * @nvqs: number of virtqueues supported by this device * @size: size of the parent structure that contains private data + * @name: name of the vdpa device; optional. * * Driver should use vdpa_alloc_device() wrapper macro instead of * using this directly. @@ -72,8 +75,7 @@ static void vdpa_release_dev(struct device *d) */ struct vdpa_device *__vdpa_alloc_device(struct device *parent, const struct vdpa_config_ops *config, - int nvqs, - size_t size) + int nvqs, size_t size, const char *name) { struct vdpa_device *vdev; int err = -EINVAL; @@ -101,7 +103,10 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent, vdev->features_valid = false; vdev->nvqs = nvqs; - err = dev_set_name(&vdev->dev, "vdpa%u", vdev->index); + if (name) + err = dev_set_name(&vdev->dev, "%s", name); + else + err = dev_set_name(&vdev->dev, "vdpa%u", vdev->index); if (err) goto err_name; @@ -118,6 +123,13 @@ err: } EXPORT_SYMBOL_GPL(__vdpa_alloc_device); +static int vdpa_name_match(struct device *dev, const void *data) +{ + struct vdpa_device *vdev = container_of(dev, struct vdpa_device, dev); + + return (strcmp(dev_name(&vdev->dev), data) == 0); +} + /** * vdpa_register_device - register a vDPA device * Callers must have a succeed call of vdpa_alloc_device() before. @@ -127,7 +139,21 @@ EXPORT_SYMBOL_GPL(__vdpa_alloc_device); */ int vdpa_register_device(struct vdpa_device *vdev) { - return device_add(&vdev->dev); + struct device *dev; + int err; + + mutex_lock(&vdpa_dev_mutex); + dev = bus_find_device(&vdpa_bus, NULL, dev_name(&vdev->dev), vdpa_name_match); + if (dev) { + put_device(dev); + err = -EEXIST; + goto name_err; + } + + err = device_add(&vdev->dev); +name_err: + mutex_unlock(&vdpa_dev_mutex); + return err; } EXPORT_SYMBOL_GPL(vdpa_register_device); @@ -137,7 +163,9 @@ EXPORT_SYMBOL_GPL(vdpa_register_device); */ void vdpa_unregister_device(struct vdpa_device *vdev) { + mutex_lock(&vdpa_dev_mutex); device_unregister(&vdev->dev); + mutex_unlock(&vdpa_dev_mutex); } EXPORT_SYMBOL_GPL(vdpa_unregister_device); diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c index b3fcc67bfdf0..db1636a99ba4 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c @@ -235,7 +235,7 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr) ops = &vdpasim_config_ops; vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, - dev_attr->nvqs); + dev_attr->nvqs, NULL); if (!vdpasim) goto err_alloc; diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 0fefeb976877..5700baa22356 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -245,15 +245,14 @@ struct vdpa_config_ops { struct vdpa_device *__vdpa_alloc_device(struct device *parent, const struct vdpa_config_ops *config, - int nvqs, - size_t size); + int nvqs, size_t size, const char *name); -#define vdpa_alloc_device(dev_struct, member, parent, config, nvqs) \ +#define vdpa_alloc_device(dev_struct, member, parent, config, nvqs, name) \ container_of(__vdpa_alloc_device( \ parent, config, nvqs, \ sizeof(dev_struct) + \ BUILD_BUG_ON_ZERO(offsetof( \ - dev_struct, member))), \ + dev_struct, member)), name), \ dev_struct, member) int vdpa_register_device(struct vdpa_device *vdev); -- cgit v1.2.3 From 33b347503f014ebf76257327cbc7001c6b721956 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Tue, 5 Jan 2021 12:32:00 +0200 Subject: vdpa: Define vdpa mgmt device, ops and a netlink interface To add one or more VDPA devices, define a management device which allows adding or removing vdpa device. A management device defines set of callbacks to manage vdpa devices. To begin with, it defines add and remove callbacks through which a user defined vdpa device can be added or removed. A unique management device is identified by its unique handle identified by management device name and optionally the bus name. Hence, introduce routine through which driver can register a management device and its callback operations for adding and remove a vdpa device. Introduce vdpa netlink socket family so that user can query management device and its attributes. Example of show vdpa management device which allows creating vdpa device of networking class (device id = 0x1) of virtio specification 1.1 section 5.1.1. $ vdpa mgmtdev show vdpasim_net: supported_classes: net Example of showing vdpa management device in JSON format. $ vdpa mgmtdev show -jp { "show": { "vdpasim_net": { "supported_classes": [ "net" ] } } } Signed-off-by: Parav Pandit Reviewed-by: Eli Cohen Reviewed-by: Jason Wang Link: https://lore.kernel.org/r/20210105103203.82508-4-parav@nvidia.com Signed-off-by: Michael S. Tsirkin Including a bugfix: vpda: correctly size vdpa_nl_policy We need to ensure last entry of vdpa_nl_policy[] is zero, otherwise out-of-bounds access is hurting us. Signed-off-by: Eric Dumazet Reported-by: syzbot Cc: Parav Pandit Cc: Eli Cohen Cc: Jason Wang Cc: Michael S. Tsirkin Link: https://lore.kernel.org/r/20210210134911.4119555-1-eric.dumazet@gmail.com Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/Kconfig | 1 + drivers/vdpa/vdpa.c | 213 +++++++++++++++++++++++++++++++++++++++++++++- include/linux/vdpa.h | 31 +++++++ include/uapi/linux/vdpa.h | 31 +++++++ 4 files changed, 275 insertions(+), 1 deletion(-) create mode 100644 include/uapi/linux/vdpa.h (limited to 'include') diff --git a/drivers/vdpa/Kconfig b/drivers/vdpa/Kconfig index 92a6396f8a73..ffd1e098bfd2 100644 --- a/drivers/vdpa/Kconfig +++ b/drivers/vdpa/Kconfig @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only menuconfig VDPA tristate "vDPA drivers" + depends on NET help Enable this module to support vDPA device that uses a datapath which complies with virtio specifications with diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index 7414bbd9057c..586e66b7f671 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -11,11 +11,17 @@ #include #include #include +#include +#include +#include +static LIST_HEAD(mdev_head); /* A global mutex that protects vdpa management device and device level operations. */ static DEFINE_MUTEX(vdpa_dev_mutex); static DEFINE_IDA(vdpa_index_ida); +static struct genl_family vdpa_nl_family; + static int vdpa_dev_probe(struct device *d) { struct vdpa_device *vdev = dev_to_vdpa(d); @@ -195,13 +201,218 @@ void vdpa_unregister_driver(struct vdpa_driver *drv) } EXPORT_SYMBOL_GPL(vdpa_unregister_driver); +/** + * vdpa_mgmtdev_register - register a vdpa management device + * + * @mdev: Pointer to vdpa management device + * vdpa_mgmtdev_register() register a vdpa management device which supports + * vdpa device management. + */ +int vdpa_mgmtdev_register(struct vdpa_mgmt_dev *mdev) +{ + if (!mdev->device || !mdev->ops || !mdev->ops->dev_add || !mdev->ops->dev_del) + return -EINVAL; + + INIT_LIST_HEAD(&mdev->list); + mutex_lock(&vdpa_dev_mutex); + list_add_tail(&mdev->list, &mdev_head); + mutex_unlock(&vdpa_dev_mutex); + return 0; +} +EXPORT_SYMBOL_GPL(vdpa_mgmtdev_register); + +void vdpa_mgmtdev_unregister(struct vdpa_mgmt_dev *mdev) +{ + mutex_lock(&vdpa_dev_mutex); + list_del(&mdev->list); + mutex_unlock(&vdpa_dev_mutex); +} +EXPORT_SYMBOL_GPL(vdpa_mgmtdev_unregister); + +static bool mgmtdev_handle_match(const struct vdpa_mgmt_dev *mdev, + const char *busname, const char *devname) +{ + /* Bus name is optional for simulated management device, so ignore the + * device with bus if bus attribute is provided. + */ + if ((busname && !mdev->device->bus) || (!busname && mdev->device->bus)) + return false; + + if (!busname && strcmp(dev_name(mdev->device), devname) == 0) + return true; + + if (busname && (strcmp(mdev->device->bus->name, busname) == 0) && + (strcmp(dev_name(mdev->device), devname) == 0)) + return true; + + return false; +} + +static struct vdpa_mgmt_dev *vdpa_mgmtdev_get_from_attr(struct nlattr **attrs) +{ + struct vdpa_mgmt_dev *mdev; + const char *busname = NULL; + const char *devname; + + if (!attrs[VDPA_ATTR_MGMTDEV_DEV_NAME]) + return ERR_PTR(-EINVAL); + devname = nla_data(attrs[VDPA_ATTR_MGMTDEV_DEV_NAME]); + if (attrs[VDPA_ATTR_MGMTDEV_BUS_NAME]) + busname = nla_data(attrs[VDPA_ATTR_MGMTDEV_BUS_NAME]); + + list_for_each_entry(mdev, &mdev_head, list) { + if (mgmtdev_handle_match(mdev, busname, devname)) + return mdev; + } + return ERR_PTR(-ENODEV); +} + +static int vdpa_nl_mgmtdev_handle_fill(struct sk_buff *msg, const struct vdpa_mgmt_dev *mdev) +{ + if (mdev->device->bus && + nla_put_string(msg, VDPA_ATTR_MGMTDEV_BUS_NAME, mdev->device->bus->name)) + return -EMSGSIZE; + if (nla_put_string(msg, VDPA_ATTR_MGMTDEV_DEV_NAME, dev_name(mdev->device))) + return -EMSGSIZE; + return 0; +} + +static int vdpa_mgmtdev_fill(const struct vdpa_mgmt_dev *mdev, struct sk_buff *msg, + u32 portid, u32 seq, int flags) +{ + u64 supported_classes = 0; + void *hdr; + int i = 0; + int err; + + hdr = genlmsg_put(msg, portid, seq, &vdpa_nl_family, flags, VDPA_CMD_MGMTDEV_NEW); + if (!hdr) + return -EMSGSIZE; + err = vdpa_nl_mgmtdev_handle_fill(msg, mdev); + if (err) + goto msg_err; + + while (mdev->id_table[i].device) { + supported_classes |= BIT(mdev->id_table[i].device); + i++; + } + + if (nla_put_u64_64bit(msg, VDPA_ATTR_MGMTDEV_SUPPORTED_CLASSES, + supported_classes, VDPA_ATTR_UNSPEC)) { + err = -EMSGSIZE; + goto msg_err; + } + + genlmsg_end(msg, hdr); + return 0; + +msg_err: + genlmsg_cancel(msg, hdr); + return err; +} + +static int vdpa_nl_cmd_mgmtdev_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct vdpa_mgmt_dev *mdev; + struct sk_buff *msg; + int err; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + mutex_lock(&vdpa_dev_mutex); + mdev = vdpa_mgmtdev_get_from_attr(info->attrs); + if (IS_ERR(mdev)) { + mutex_unlock(&vdpa_dev_mutex); + NL_SET_ERR_MSG_MOD(info->extack, "Fail to find the specified mgmt device"); + err = PTR_ERR(mdev); + goto out; + } + + err = vdpa_mgmtdev_fill(mdev, msg, info->snd_portid, info->snd_seq, 0); + mutex_unlock(&vdpa_dev_mutex); + if (err) + goto out; + err = genlmsg_reply(msg, info); + return err; + +out: + nlmsg_free(msg); + return err; +} + +static int +vdpa_nl_cmd_mgmtdev_get_dumpit(struct sk_buff *msg, struct netlink_callback *cb) +{ + struct vdpa_mgmt_dev *mdev; + int start = cb->args[0]; + int idx = 0; + int err; + + mutex_lock(&vdpa_dev_mutex); + list_for_each_entry(mdev, &mdev_head, list) { + if (idx < start) { + idx++; + continue; + } + err = vdpa_mgmtdev_fill(mdev, msg, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI); + if (err) + goto out; + idx++; + } +out: + mutex_unlock(&vdpa_dev_mutex); + cb->args[0] = idx; + return msg->len; +} + +static const struct nla_policy vdpa_nl_policy[VDPA_ATTR_MAX + 1] = { + [VDPA_ATTR_MGMTDEV_BUS_NAME] = { .type = NLA_NUL_STRING }, + [VDPA_ATTR_MGMTDEV_DEV_NAME] = { .type = NLA_STRING }, +}; + +static const struct genl_ops vdpa_nl_ops[] = { + { + .cmd = VDPA_CMD_MGMTDEV_GET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = vdpa_nl_cmd_mgmtdev_get_doit, + .dumpit = vdpa_nl_cmd_mgmtdev_get_dumpit, + }, +}; + +static struct genl_family vdpa_nl_family __ro_after_init = { + .name = VDPA_GENL_NAME, + .version = VDPA_GENL_VERSION, + .maxattr = VDPA_ATTR_MAX, + .policy = vdpa_nl_policy, + .netnsok = false, + .module = THIS_MODULE, + .ops = vdpa_nl_ops, + .n_ops = ARRAY_SIZE(vdpa_nl_ops), +}; + static int vdpa_init(void) { - return bus_register(&vdpa_bus); + int err; + + err = bus_register(&vdpa_bus); + if (err) + return err; + err = genl_register_family(&vdpa_nl_family); + if (err) + goto err; + return 0; + +err: + bus_unregister(&vdpa_bus); + return err; } static void __exit vdpa_exit(void) { + genl_unregister_family(&vdpa_nl_family); bus_unregister(&vdpa_bus); ida_destroy(&vdpa_index_ida); } diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 5700baa22356..6b8b4222bca6 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -35,6 +35,8 @@ struct vdpa_vq_state { u16 avail_index; }; +struct vdpa_mgmt_dev; + /** * vDPA device - representation of a vDPA device * @dev: underlying device @@ -335,4 +337,33 @@ static inline void vdpa_get_config(struct vdpa_device *vdev, unsigned offset, ops->get_config(vdev, offset, buf, len); } +/** + * vdpa_mgmtdev_ops - vdpa device ops + * @dev_add: Add a vdpa device using alloc and register + * @mdev: parent device to use for device addition + * @name: name of the new vdpa device + * Driver need to add a new device using _vdpa_register_device() + * after fully initializing the vdpa device. Driver must return 0 + * on success or appropriate error code. + * @dev_del: Remove a vdpa device using unregister + * @mdev: parent device to use for device removal + * @dev: vdpa device to remove + * Driver need to remove the specified device by calling + * _vdpa_unregister_device(). + */ +struct vdpa_mgmtdev_ops { + int (*dev_add)(struct vdpa_mgmt_dev *mdev, const char *name); + void (*dev_del)(struct vdpa_mgmt_dev *mdev, struct vdpa_device *dev); +}; + +struct vdpa_mgmt_dev { + struct device *device; + const struct vdpa_mgmtdev_ops *ops; + const struct virtio_device_id *id_table; /* supported ids */ + struct list_head list; +}; + +int vdpa_mgmtdev_register(struct vdpa_mgmt_dev *mdev); +void vdpa_mgmtdev_unregister(struct vdpa_mgmt_dev *mdev); + #endif /* _LINUX_VDPA_H */ diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h new file mode 100644 index 000000000000..d44d82e567b1 --- /dev/null +++ b/include/uapi/linux/vdpa.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +/* + * vdpa device management interface + * Copyright (c) 2020 Mellanox Technologies Ltd. All rights reserved. + */ + +#ifndef _UAPI_LINUX_VDPA_H_ +#define _UAPI_LINUX_VDPA_H_ + +#define VDPA_GENL_NAME "vdpa" +#define VDPA_GENL_VERSION 0x1 + +enum vdpa_command { + VDPA_CMD_UNSPEC, + VDPA_CMD_MGMTDEV_NEW, + VDPA_CMD_MGMTDEV_GET, /* can dump */ +}; + +enum vdpa_attr { + VDPA_ATTR_UNSPEC, + + /* bus name (optional) + dev name together make the parent device handle */ + VDPA_ATTR_MGMTDEV_BUS_NAME, /* string */ + VDPA_ATTR_MGMTDEV_DEV_NAME, /* string */ + VDPA_ATTR_MGMTDEV_SUPPORTED_CLASSES, /* u64 */ + + /* new attributes must be added above here */ + VDPA_ATTR_MAX, +}; + +#endif -- cgit v1.2.3 From 903f7bcaedb84ca47998e609015a34ddde93742e Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Tue, 5 Jan 2021 12:32:01 +0200 Subject: vdpa: Enable a user to add and delete a vdpa device Add the ability to add and delete a vdpa device. Examples: Create a vdpa device of type network named "foo2" from the management device vdpasim: $ vdpa dev add mgmtdev vdpasim_net name foo2 Delete the vdpa device after its use: $ vdpa dev del foo2 Signed-off-by: Parav Pandit Reviewed-by: Eli Cohen Reviewed-by: Jason Wang Link: https://lore.kernel.org/r/20210105103203.82508-5-parav@nvidia.com Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa.c | 143 ++++++++++++++++++++++++++++++++++++++++++---- include/linux/vdpa.h | 6 ++ include/uapi/linux/vdpa.h | 4 ++ 3 files changed, 143 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index 586e66b7f671..f1228189814f 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -136,6 +136,37 @@ static int vdpa_name_match(struct device *dev, const void *data) return (strcmp(dev_name(&vdev->dev), data) == 0); } +static int __vdpa_register_device(struct vdpa_device *vdev) +{ + struct device *dev; + + lockdep_assert_held(&vdpa_dev_mutex); + dev = bus_find_device(&vdpa_bus, NULL, dev_name(&vdev->dev), vdpa_name_match); + if (dev) { + put_device(dev); + return -EEXIST; + } + return device_add(&vdev->dev); +} + +/** + * _vdpa_register_device - register a vDPA device with vdpa lock held + * Caller must have a succeed call of vdpa_alloc_device() before. + * Caller must invoke this routine in the management device dev_add() + * callback after setting up valid mgmtdev for this vdpa device. + * @vdev: the vdpa device to be registered to vDPA bus + * + * Returns an error when fail to add device to vDPA bus + */ +int _vdpa_register_device(struct vdpa_device *vdev) +{ + if (!vdev->mdev) + return -EINVAL; + + return __vdpa_register_device(vdev); +} +EXPORT_SYMBOL_GPL(_vdpa_register_device); + /** * vdpa_register_device - register a vDPA device * Callers must have a succeed call of vdpa_alloc_device() before. @@ -145,24 +176,29 @@ static int vdpa_name_match(struct device *dev, const void *data) */ int vdpa_register_device(struct vdpa_device *vdev) { - struct device *dev; int err; mutex_lock(&vdpa_dev_mutex); - dev = bus_find_device(&vdpa_bus, NULL, dev_name(&vdev->dev), vdpa_name_match); - if (dev) { - put_device(dev); - err = -EEXIST; - goto name_err; - } - - err = device_add(&vdev->dev); -name_err: + err = __vdpa_register_device(vdev); mutex_unlock(&vdpa_dev_mutex); return err; } EXPORT_SYMBOL_GPL(vdpa_register_device); +/** + * _vdpa_unregister_device - unregister a vDPA device + * Caller must invoke this routine as part of management device dev_del() + * callback. + * @vdev: the vdpa device to be unregisted from vDPA bus + */ +void _vdpa_unregister_device(struct vdpa_device *vdev) +{ + lockdep_assert_held(&vdpa_dev_mutex); + WARN_ON(!vdev->mdev); + device_unregister(&vdev->dev); +} +EXPORT_SYMBOL_GPL(_vdpa_unregister_device); + /** * vdpa_unregister_device - unregister a vDPA device * @vdev: the vdpa device to be unregisted from vDPA bus @@ -221,10 +257,25 @@ int vdpa_mgmtdev_register(struct vdpa_mgmt_dev *mdev) } EXPORT_SYMBOL_GPL(vdpa_mgmtdev_register); +static int vdpa_match_remove(struct device *dev, void *data) +{ + struct vdpa_device *vdev = container_of(dev, struct vdpa_device, dev); + struct vdpa_mgmt_dev *mdev = vdev->mdev; + + if (mdev == data) + mdev->ops->dev_del(mdev, vdev); + return 0; +} + void vdpa_mgmtdev_unregister(struct vdpa_mgmt_dev *mdev) { mutex_lock(&vdpa_dev_mutex); + list_del(&mdev->list); + + /* Filter out all the entries belong to this management device and delete it. */ + bus_for_each_dev(&vdpa_bus, NULL, mdev, vdpa_match_remove); + mutex_unlock(&vdpa_dev_mutex); } EXPORT_SYMBOL_GPL(vdpa_mgmtdev_unregister); @@ -368,9 +419,69 @@ out: return msg->len; } +static int vdpa_nl_cmd_dev_add_set_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct vdpa_mgmt_dev *mdev; + const char *name; + int err = 0; + + if (!info->attrs[VDPA_ATTR_DEV_NAME]) + return -EINVAL; + + name = nla_data(info->attrs[VDPA_ATTR_DEV_NAME]); + + mutex_lock(&vdpa_dev_mutex); + mdev = vdpa_mgmtdev_get_from_attr(info->attrs); + if (IS_ERR(mdev)) { + NL_SET_ERR_MSG_MOD(info->extack, "Fail to find the specified management device"); + err = PTR_ERR(mdev); + goto err; + } + + err = mdev->ops->dev_add(mdev, name); +err: + mutex_unlock(&vdpa_dev_mutex); + return err; +} + +static int vdpa_nl_cmd_dev_del_set_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct vdpa_mgmt_dev *mdev; + struct vdpa_device *vdev; + struct device *dev; + const char *name; + int err = 0; + + if (!info->attrs[VDPA_ATTR_DEV_NAME]) + return -EINVAL; + name = nla_data(info->attrs[VDPA_ATTR_DEV_NAME]); + + mutex_lock(&vdpa_dev_mutex); + dev = bus_find_device(&vdpa_bus, NULL, name, vdpa_name_match); + if (!dev) { + NL_SET_ERR_MSG_MOD(info->extack, "device not found"); + err = -ENODEV; + goto dev_err; + } + vdev = container_of(dev, struct vdpa_device, dev); + if (!vdev->mdev) { + NL_SET_ERR_MSG_MOD(info->extack, "Only user created device can be deleted by user"); + err = -EINVAL; + goto mdev_err; + } + mdev = vdev->mdev; + mdev->ops->dev_del(mdev, vdev); +mdev_err: + put_device(dev); +dev_err: + mutex_unlock(&vdpa_dev_mutex); + return err; +} + static const struct nla_policy vdpa_nl_policy[VDPA_ATTR_MAX + 1] = { [VDPA_ATTR_MGMTDEV_BUS_NAME] = { .type = NLA_NUL_STRING }, [VDPA_ATTR_MGMTDEV_DEV_NAME] = { .type = NLA_STRING }, + [VDPA_ATTR_DEV_NAME] = { .type = NLA_STRING }, }; static const struct genl_ops vdpa_nl_ops[] = { @@ -380,6 +491,18 @@ static const struct genl_ops vdpa_nl_ops[] = { .doit = vdpa_nl_cmd_mgmtdev_get_doit, .dumpit = vdpa_nl_cmd_mgmtdev_get_dumpit, }, + { + .cmd = VDPA_CMD_DEV_NEW, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = vdpa_nl_cmd_dev_add_set_doit, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = VDPA_CMD_DEV_DEL, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = vdpa_nl_cmd_dev_del_set_doit, + .flags = GENL_ADMIN_PERM, + }, }; static struct genl_family vdpa_nl_family __ro_after_init = { diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 6b8b4222bca6..4ab5494503a8 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -45,6 +45,8 @@ struct vdpa_mgmt_dev; * @index: device index * @features_valid: were features initialized? for legacy guests * @nvqs: maximum number of supported virtqueues + * @mdev: management device pointer; caller must setup when registering device as part + * of dev_add() mgmtdev ops callback before invoking _vdpa_register_device(). */ struct vdpa_device { struct device dev; @@ -53,6 +55,7 @@ struct vdpa_device { unsigned int index; bool features_valid; int nvqs; + struct vdpa_mgmt_dev *mdev; }; /** @@ -260,6 +263,9 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent, int vdpa_register_device(struct vdpa_device *vdev); void vdpa_unregister_device(struct vdpa_device *vdev); +int _vdpa_register_device(struct vdpa_device *vdev); +void _vdpa_unregister_device(struct vdpa_device *vdev); + /** * vdpa_driver - operations for a vDPA driver * @driver: underlying device driver diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h index d44d82e567b1..bb4a1f00eb1c 100644 --- a/include/uapi/linux/vdpa.h +++ b/include/uapi/linux/vdpa.h @@ -14,6 +14,8 @@ enum vdpa_command { VDPA_CMD_UNSPEC, VDPA_CMD_MGMTDEV_NEW, VDPA_CMD_MGMTDEV_GET, /* can dump */ + VDPA_CMD_DEV_NEW, + VDPA_CMD_DEV_DEL, }; enum vdpa_attr { @@ -24,6 +26,8 @@ enum vdpa_attr { VDPA_ATTR_MGMTDEV_DEV_NAME, /* string */ VDPA_ATTR_MGMTDEV_SUPPORTED_CLASSES, /* u64 */ + VDPA_ATTR_DEV_NAME, /* string */ + /* new attributes must be added above here */ VDPA_ATTR_MAX, }; -- cgit v1.2.3 From bc0d90ee021f1baecd6aaa010d787eb373aa74dd Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Tue, 5 Jan 2021 12:32:02 +0200 Subject: vdpa: Enable user to query vdpa device info Enable user to query vdpa device information. $ vdpa dev add mgmtdev vdpasim_net name foo2 Show the newly created vdpa device by its name: $ vdpa dev show foo2 foo2: type network mgmtdev vdpasim_net vendor_id 0 max_vqs 2 max_vq_size 256 $ vdpa dev show foo2 -jp { "dev": { "foo2": { "type": "network", "mgmtdev": "vdpasim_net", "vendor_id": 0, "max_vqs": 2, "max_vq_size": 256 } } } Signed-off-by: Parav Pandit Reviewed-by: Eli Cohen Reviewed-by: Jason Wang Link: https://lore.kernel.org/r/20210105103203.82508-6-parav@nvidia.com Including a memory leak fix: Link: https://lore.kernel.org/r/20210217060614.59561-1-parav@nvidia.com Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa.c | 131 ++++++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/vdpa.h | 5 ++ 2 files changed, 136 insertions(+) (limited to 'include') diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index f1228189814f..da67f07e24fd 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -478,6 +478,131 @@ dev_err: return err; } +static int +vdpa_dev_fill(struct vdpa_device *vdev, struct sk_buff *msg, u32 portid, u32 seq, + int flags, struct netlink_ext_ack *extack) +{ + u16 max_vq_size; + u32 device_id; + u32 vendor_id; + void *hdr; + int err; + + hdr = genlmsg_put(msg, portid, seq, &vdpa_nl_family, flags, VDPA_CMD_DEV_NEW); + if (!hdr) + return -EMSGSIZE; + + err = vdpa_nl_mgmtdev_handle_fill(msg, vdev->mdev); + if (err) + goto msg_err; + + device_id = vdev->config->get_device_id(vdev); + vendor_id = vdev->config->get_vendor_id(vdev); + max_vq_size = vdev->config->get_vq_num_max(vdev); + + err = -EMSGSIZE; + if (nla_put_string(msg, VDPA_ATTR_DEV_NAME, dev_name(&vdev->dev))) + goto msg_err; + if (nla_put_u32(msg, VDPA_ATTR_DEV_ID, device_id)) + goto msg_err; + if (nla_put_u32(msg, VDPA_ATTR_DEV_VENDOR_ID, vendor_id)) + goto msg_err; + if (nla_put_u32(msg, VDPA_ATTR_DEV_MAX_VQS, vdev->nvqs)) + goto msg_err; + if (nla_put_u16(msg, VDPA_ATTR_DEV_MAX_VQ_SIZE, max_vq_size)) + goto msg_err; + + genlmsg_end(msg, hdr); + return 0; + +msg_err: + genlmsg_cancel(msg, hdr); + return err; +} + +static int vdpa_nl_cmd_dev_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct vdpa_device *vdev; + struct sk_buff *msg; + const char *devname; + struct device *dev; + int err; + + if (!info->attrs[VDPA_ATTR_DEV_NAME]) + return -EINVAL; + devname = nla_data(info->attrs[VDPA_ATTR_DEV_NAME]); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + mutex_lock(&vdpa_dev_mutex); + dev = bus_find_device(&vdpa_bus, NULL, devname, vdpa_name_match); + if (!dev) { + NL_SET_ERR_MSG_MOD(info->extack, "device not found"); + err = -ENODEV; + goto err; + } + vdev = container_of(dev, struct vdpa_device, dev); + if (!vdev->mdev) { + err = -EINVAL; + goto mdev_err; + } + err = vdpa_dev_fill(vdev, msg, info->snd_portid, info->snd_seq, 0, info->extack); + if (!err) + err = genlmsg_reply(msg, info); +mdev_err: + put_device(dev); +err: + mutex_unlock(&vdpa_dev_mutex); + if (err) + nlmsg_free(msg); + return err; +} + +struct vdpa_dev_dump_info { + struct sk_buff *msg; + struct netlink_callback *cb; + int start_idx; + int idx; +}; + +static int vdpa_dev_dump(struct device *dev, void *data) +{ + struct vdpa_device *vdev = container_of(dev, struct vdpa_device, dev); + struct vdpa_dev_dump_info *info = data; + int err; + + if (!vdev->mdev) + return 0; + if (info->idx < info->start_idx) { + info->idx++; + return 0; + } + err = vdpa_dev_fill(vdev, info->msg, NETLINK_CB(info->cb->skb).portid, + info->cb->nlh->nlmsg_seq, NLM_F_MULTI, info->cb->extack); + if (err) + return err; + + info->idx++; + return 0; +} + +static int vdpa_nl_cmd_dev_get_dumpit(struct sk_buff *msg, struct netlink_callback *cb) +{ + struct vdpa_dev_dump_info info; + + info.msg = msg; + info.cb = cb; + info.start_idx = cb->args[0]; + info.idx = 0; + + mutex_lock(&vdpa_dev_mutex); + bus_for_each_dev(&vdpa_bus, NULL, &info, vdpa_dev_dump); + mutex_unlock(&vdpa_dev_mutex); + cb->args[0] = info.idx; + return msg->len; +} + static const struct nla_policy vdpa_nl_policy[VDPA_ATTR_MAX + 1] = { [VDPA_ATTR_MGMTDEV_BUS_NAME] = { .type = NLA_NUL_STRING }, [VDPA_ATTR_MGMTDEV_DEV_NAME] = { .type = NLA_STRING }, @@ -503,6 +628,12 @@ static const struct genl_ops vdpa_nl_ops[] = { .doit = vdpa_nl_cmd_dev_del_set_doit, .flags = GENL_ADMIN_PERM, }, + { + .cmd = VDPA_CMD_DEV_GET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = vdpa_nl_cmd_dev_get_doit, + .dumpit = vdpa_nl_cmd_dev_get_dumpit, + }, }; static struct genl_family vdpa_nl_family __ro_after_init = { diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h index bb4a1f00eb1c..66a41e4ec163 100644 --- a/include/uapi/linux/vdpa.h +++ b/include/uapi/linux/vdpa.h @@ -16,6 +16,7 @@ enum vdpa_command { VDPA_CMD_MGMTDEV_GET, /* can dump */ VDPA_CMD_DEV_NEW, VDPA_CMD_DEV_DEL, + VDPA_CMD_DEV_GET, /* can dump */ }; enum vdpa_attr { @@ -27,6 +28,10 @@ enum vdpa_attr { VDPA_ATTR_MGMTDEV_SUPPORTED_CLASSES, /* u64 */ VDPA_ATTR_DEV_NAME, /* string */ + VDPA_ATTR_DEV_ID, /* u32 */ + VDPA_ATTR_DEV_VENDOR_ID, /* u32 */ + VDPA_ATTR_DEV_MAX_VQS, /* u32 */ + VDPA_ATTR_DEV_MAX_VQ_SIZE, /* u16 */ /* new attributes must be added above here */ VDPA_ATTR_MAX, -- cgit v1.2.3 From fd502729fbbf6a76fdb7acae4506486bfbb7c4f6 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Mon, 4 Jan 2021 14:55:00 +0800 Subject: virtio-pci: introduce modern device module Signed-off-by: Jason Wang Link: https://lore.kernel.org/r/20210104065503.199631-17-jasowang@redhat.com Including a bugfix: virtio: don't prompt CONFIG_VIRTIO_PCI_MODERN Cc: Arnd Bergmann Cc: Anders Roxell Cc: Guenter Roeck Reported-by: Naresh Kamboju Fixes: 86b87c9d858b6 ("virtio-pci: introduce modern device module") Signed-off-by: Jason Wang Acked-by: Arnd Bergmann Link: https://lore.kernel.org/r/20210223061905.422659-2-jasowang@redhat.com Signed-off-by: Michael S. Tsirkin --- drivers/virtio/Kconfig | 9 + drivers/virtio/Makefile | 1 + drivers/virtio/virtio_pci_common.h | 27 +- drivers/virtio/virtio_pci_modern.c | 617 --------------------------------- drivers/virtio/virtio_pci_modern_dev.c | 599 ++++++++++++++++++++++++++++++++ include/linux/virtio_pci_modern.h | 111 ++++++ 6 files changed, 721 insertions(+), 643 deletions(-) create mode 100644 drivers/virtio/virtio_pci_modern_dev.c create mode 100644 include/linux/virtio_pci_modern.h (limited to 'include') diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig index 7b41130d3f35..ce1b3f6ec325 100644 --- a/drivers/virtio/Kconfig +++ b/drivers/virtio/Kconfig @@ -12,6 +12,14 @@ config ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS This option is selected if the architecture may need to enforce VIRTIO_F_ACCESS_PLATFORM +config VIRTIO_PCI_LIB + tristate + help + Modern PCI device implementation. This module implements the + basic probe and control for devices which are based on modern + PCI device with possible vendor specific extensions. Any + module that selects this module must depend on PCI. + menuconfig VIRTIO_MENU bool "Virtio drivers" default y @@ -21,6 +29,7 @@ if VIRTIO_MENU config VIRTIO_PCI tristate "PCI driver for virtio devices" depends on PCI + select VIRTIO_PCI_LIB select VIRTIO help This driver provides support for virtio based paravirtual device diff --git a/drivers/virtio/Makefile b/drivers/virtio/Makefile index 591e6f72aa54..699bbea0465f 100644 --- a/drivers/virtio/Makefile +++ b/drivers/virtio/Makefile @@ -1,5 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_VIRTIO) += virtio.o virtio_ring.o +obj-$(CONFIG_VIRTIO_PCI_LIB) += virtio_pci_modern_dev.o obj-$(CONFIG_VIRTIO_MMIO) += virtio_mmio.o obj-$(CONFIG_VIRTIO_PCI) += virtio_pci.o virtio_pci-y := virtio_pci_modern.o virtio_pci_common.o diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h index f35ff5b6b467..beec047a8f8d 100644 --- a/drivers/virtio/virtio_pci_common.h +++ b/drivers/virtio/virtio_pci_common.h @@ -25,6 +25,7 @@ #include #include #include +#include #include #include @@ -39,32 +40,6 @@ struct virtio_pci_vq_info { unsigned msix_vector; }; -struct virtio_pci_modern_device { - struct pci_dev *pci_dev; - - struct virtio_pci_common_cfg __iomem *common; - /* Device-specific data (non-legacy mode) */ - void __iomem *device; - /* Base of vq notifications (non-legacy mode). */ - void __iomem *notify_base; - /* Where to read and clear interrupt */ - u8 __iomem *isr; - - /* So we can sanity-check accesses. */ - size_t notify_len; - size_t device_len; - - /* Capability for when we need to map notifications per-vq. */ - int notify_map_cap; - - /* Multiply queue_notify_off by this value. (non-legacy mode). */ - u32 notify_offset_multiplier; - - int modern_bars; - - struct virtio_device_id id; -}; - /* Our device structure */ struct virtio_pci_device { struct virtio_device vdev; diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c index a5e3a5e40323..fbd4ebc00eb6 100644 --- a/drivers/virtio/virtio_pci_modern.c +++ b/drivers/virtio/virtio_pci_modern.c @@ -19,158 +19,6 @@ #define VIRTIO_RING_NO_LEGACY #include "virtio_pci_common.h" -/* - * Type-safe wrappers for io accesses. - * Use these to enforce at compile time the following spec requirement: - * - * The driver MUST access each field using the “natural” access - * method, i.e. 32-bit accesses for 32-bit fields, 16-bit accesses - * for 16-bit fields and 8-bit accesses for 8-bit fields. - */ -static inline u8 vp_ioread8(const u8 __iomem *addr) -{ - return ioread8(addr); -} -static inline u16 vp_ioread16 (const __le16 __iomem *addr) -{ - return ioread16(addr); -} - -static inline u32 vp_ioread32(const __le32 __iomem *addr) -{ - return ioread32(addr); -} - -static inline void vp_iowrite8(u8 value, u8 __iomem *addr) -{ - iowrite8(value, addr); -} - -static inline void vp_iowrite16(u16 value, __le16 __iomem *addr) -{ - iowrite16(value, addr); -} - -static inline void vp_iowrite32(u32 value, __le32 __iomem *addr) -{ - iowrite32(value, addr); -} - -static void vp_iowrite64_twopart(u64 val, - __le32 __iomem *lo, __le32 __iomem *hi) -{ - vp_iowrite32((u32)val, lo); - vp_iowrite32(val >> 32, hi); -} - -/* - * vp_modern_map_capability - map a part of virtio pci capability - * @mdev: the modern virtio-pci device - * @off: offset of the capability - * @minlen: minimal length of the capability - * @align: align requirement - * @start: start from the capability - * @size: map size - * @len: the length that is actually mapped - * - * Returns the io address of for the part of the capability - */ -void __iomem *vp_modern_map_capability(struct virtio_pci_modern_device *mdev, int off, - size_t minlen, - u32 align, - u32 start, u32 size, - size_t *len) -{ - struct pci_dev *dev = mdev->pci_dev; - u8 bar; - u32 offset, length; - void __iomem *p; - - pci_read_config_byte(dev, off + offsetof(struct virtio_pci_cap, - bar), - &bar); - pci_read_config_dword(dev, off + offsetof(struct virtio_pci_cap, offset), - &offset); - pci_read_config_dword(dev, off + offsetof(struct virtio_pci_cap, length), - &length); - - if (length <= start) { - dev_err(&dev->dev, - "virtio_pci: bad capability len %u (>%u expected)\n", - length, start); - return NULL; - } - - if (length - start < minlen) { - dev_err(&dev->dev, - "virtio_pci: bad capability len %u (>=%zu expected)\n", - length, minlen); - return NULL; - } - - length -= start; - - if (start + offset < offset) { - dev_err(&dev->dev, - "virtio_pci: map wrap-around %u+%u\n", - start, offset); - return NULL; - } - - offset += start; - - if (offset & (align - 1)) { - dev_err(&dev->dev, - "virtio_pci: offset %u not aligned to %u\n", - offset, align); - return NULL; - } - - if (length > size) - length = size; - - if (len) - *len = length; - - if (minlen + offset < minlen || - minlen + offset > pci_resource_len(dev, bar)) { - dev_err(&dev->dev, - "virtio_pci: map virtio %zu@%u " - "out of range on bar %i length %lu\n", - minlen, offset, - bar, (unsigned long)pci_resource_len(dev, bar)); - return NULL; - } - - p = pci_iomap_range(dev, bar, offset, length); - if (!p) - dev_err(&dev->dev, - "virtio_pci: unable to map virtio %u@%u on bar %i\n", - length, offset, bar); - return p; -} - -/* - * vp_modern_get_features - get features from device - * @mdev: the modern virtio-pci device - * - * Returns the features read from the device - */ -static u64 vp_modern_get_features(struct virtio_pci_modern_device *mdev) -{ - struct virtio_pci_common_cfg __iomem *cfg = mdev->common; - - u64 features; - - vp_iowrite32(0, &cfg->device_feature_select); - features = vp_ioread32(&cfg->device_feature); - vp_iowrite32(1, &cfg->device_feature_select); - features |= ((u64)vp_ioread32(&cfg->device_feature) << 32); - - return features; -} - -/* virtio config->get_features() implementation */ static u64 vp_get_features(struct virtio_device *vdev) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); @@ -188,149 +36,6 @@ static void vp_transport_features(struct virtio_device *vdev, u64 features) __virtio_set_bit(vdev, VIRTIO_F_SR_IOV); } -/* - * vp_modern_set_features - set features to device - * @mdev: the modern virtio-pci device - * @features: the features set to device - */ -static void vp_modern_set_features(struct virtio_pci_modern_device *mdev, - u64 features) -{ - struct virtio_pci_common_cfg __iomem *cfg = mdev->common; - - vp_iowrite32(0, &cfg->guest_feature_select); - vp_iowrite32((u32)features, &cfg->guest_feature); - vp_iowrite32(1, &cfg->guest_feature_select); - vp_iowrite32(features >> 32, &cfg->guest_feature); -} - -/* - * vp_modern_queue_vector - set the MSIX vector for a specific virtqueue - * @mdev: the modern virtio-pci device - * @index: queue index - * @vector: the config vector - * - * Returns the config vector read from the device - */ -static u16 vp_modern_queue_vector(struct virtio_pci_modern_device *mdev, - u16 index, u16 vector) -{ - struct virtio_pci_common_cfg __iomem *cfg = mdev->common; - - vp_iowrite16(index, &cfg->queue_select); - vp_iowrite16(vector, &cfg->queue_msix_vector); - /* Flush the write out to device */ - return vp_ioread16(&cfg->queue_msix_vector); -} - -/* - * vp_modern_queue_address - set the virtqueue address - * @mdev: the modern virtio-pci device - * @index: the queue index - * @desc_addr: address of the descriptor area - * @driver_addr: address of the driver area - * @device_addr: address of the device area - */ -static void vp_modern_queue_address(struct virtio_pci_modern_device *mdev, - u16 index, u64 desc_addr, u64 driver_addr, - u64 device_addr) -{ - struct virtio_pci_common_cfg __iomem *cfg = mdev->common; - - vp_iowrite16(index, &cfg->queue_select); - - vp_iowrite64_twopart(desc_addr, &cfg->queue_desc_lo, - &cfg->queue_desc_hi); - vp_iowrite64_twopart(driver_addr, &cfg->queue_avail_lo, - &cfg->queue_avail_hi); - vp_iowrite64_twopart(device_addr, &cfg->queue_used_lo, - &cfg->queue_used_hi); -} - -/* - * vp_modern_set_queue_enable - enable a virtqueue - * @mdev: the modern virtio-pci device - * @index: the queue index - * @enable: whether the virtqueue is enable or not - */ -static void vp_modern_set_queue_enable(struct virtio_pci_modern_device *mdev, - u16 index, bool enable) -{ - vp_iowrite16(index, &mdev->common->queue_select); - vp_iowrite16(enable, &mdev->common->queue_enable); -} - -/* - * vp_modern_get_queue_enable - enable a virtqueue - * @mdev: the modern virtio-pci device - * @index: the queue index - * - * Returns whether a virtqueue is enabled or not - */ -static bool vp_modern_get_queue_enable(struct virtio_pci_modern_device *mdev, - u16 index) -{ - vp_iowrite16(index, &mdev->common->queue_select); - - return vp_ioread16(&mdev->common->queue_enable); -} - -/* - * vp_modern_set_queue_size - set size for a virtqueue - * @mdev: the modern virtio-pci device - * @index: the queue index - * @size: the size of the virtqueue - */ -static void vp_modern_set_queue_size(struct virtio_pci_modern_device *mdev, - u16 index, u16 size) -{ - vp_iowrite16(index, &mdev->common->queue_select); - vp_iowrite16(size, &mdev->common->queue_size); - -} - -/* - * vp_modern_get_queue_size - get size for a virtqueue - * @mdev: the modern virtio-pci device - * @index: the queue index - * - * Returns the size of the virtqueue - */ -static u16 vp_modern_get_queue_size(struct virtio_pci_modern_device *mdev, - u16 index) -{ - vp_iowrite16(index, &mdev->common->queue_select); - - return vp_ioread16(&mdev->common->queue_size); - -} - -/* - * vp_modern_get_num_queues - get the number of virtqueues - * @mdev: the modern virtio-pci device - * - * Returns the number of virtqueues - */ -static u16 vp_modern_get_num_queues(struct virtio_pci_modern_device *mdev) -{ - return vp_ioread16(&mdev->common->num_queues); -} - -/* - * vp_modern_get_queue_notify_off - get notification offset for a virtqueue - * @mdev: the modern virtio-pci device - * @index: the queue index - * - * Returns the notification offset for a virtqueue - */ -static u16 vp_modern_get_queue_notify_off(struct virtio_pci_modern_device *mdev, - u16 index) -{ - vp_iowrite16(index, &mdev->common->queue_select); - - return vp_ioread16(&mdev->common->queue_notify_off); -} - /* virtio config->finalize_features() implementation */ static int vp_finalize_features(struct virtio_device *vdev) { @@ -429,19 +134,6 @@ static void vp_set(struct virtio_device *vdev, unsigned offset, } } -/* - * vp_modern_generation - get the device genreation - * @mdev: the modern virtio-pci device - * - * Returns the genreation read from device - */ -static u32 vp_modern_generation(struct virtio_pci_modern_device *mdev) -{ - struct virtio_pci_common_cfg __iomem *cfg = mdev->common; - - return vp_ioread8(&cfg->config_generation); -} - static u32 vp_generation(struct virtio_device *vdev) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); @@ -449,19 +141,6 @@ static u32 vp_generation(struct virtio_device *vdev) return vp_modern_generation(&vp_dev->mdev); } -/* - * vp_modern_get_status - get the device status - * @mdev: the modern virtio-pci device - * - * Returns the status read from device - */ -static u8 vp_modern_get_status(struct virtio_pci_modern_device *mdev) -{ - struct virtio_pci_common_cfg __iomem *cfg = mdev->common; - - return vp_ioread8(&cfg->device_status); -} - /* config->{get,set}_status() implementations */ static u8 vp_get_status(struct virtio_device *vdev) { @@ -470,19 +149,6 @@ static u8 vp_get_status(struct virtio_device *vdev) return vp_modern_get_status(&vp_dev->mdev); } -/* - * vp_modern_set_status - set status to device - * @mdev: the modern virtio-pci device - * @status: the status set to device - */ -static void vp_modern_set_status(struct virtio_pci_modern_device *mdev, - u8 status) -{ - struct virtio_pci_common_cfg __iomem *cfg = mdev->common; - - vp_iowrite8(status, &cfg->device_status); -} - static void vp_set_status(struct virtio_device *vdev, u8 status) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); @@ -510,25 +176,6 @@ static void vp_reset(struct virtio_device *vdev) vp_synchronize_vectors(vdev); } -/* - * vp_modern_config_vector - set the vector for config interrupt - * @mdev: the modern virtio-pci device - * @vector: the config vector - * - * Returns the config vector read from the device - */ -static u16 vp_modern_config_vector(struct virtio_pci_modern_device *mdev, - u16 vector) -{ - struct virtio_pci_common_cfg __iomem *cfg = mdev->common; - - /* Setup the vector used for configuration events */ - vp_iowrite16(vector, &cfg->msix_config); - /* Verify we had enough resources to assign the vector */ - /* Will also flush the write out to device */ - return vp_ioread16(&cfg->msix_config); -} - static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector) { return vp_modern_config_vector(&vp_dev->mdev, vector); @@ -789,253 +436,6 @@ static const struct virtio_config_ops virtio_pci_config_ops = { .get_shm_region = vp_get_shm_region, }; -/** - * virtio_pci_find_capability - walk capabilities to find device info. - * @dev: the pci device - * @cfg_type: the VIRTIO_PCI_CAP_* value we seek - * @ioresource_types: IORESOURCE_MEM and/or IORESOURCE_IO. - * @bars: the bitmask of BARs - * - * Returns offset of the capability, or 0. - */ -static inline int virtio_pci_find_capability(struct pci_dev *dev, u8 cfg_type, - u32 ioresource_types, int *bars) -{ - int pos; - - for (pos = pci_find_capability(dev, PCI_CAP_ID_VNDR); - pos > 0; - pos = pci_find_next_capability(dev, pos, PCI_CAP_ID_VNDR)) { - u8 type, bar; - pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap, - cfg_type), - &type); - pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap, - bar), - &bar); - - /* Ignore structures with reserved BAR values */ - if (bar > 0x5) - continue; - - if (type == cfg_type) { - if (pci_resource_len(dev, bar) && - pci_resource_flags(dev, bar) & ioresource_types) { - *bars |= (1 << bar); - return pos; - } - } - } - return 0; -} - -/* This is part of the ABI. Don't screw with it. */ -static inline void check_offsets(void) -{ - /* Note: disk space was harmed in compilation of this function. */ - BUILD_BUG_ON(VIRTIO_PCI_CAP_VNDR != - offsetof(struct virtio_pci_cap, cap_vndr)); - BUILD_BUG_ON(VIRTIO_PCI_CAP_NEXT != - offsetof(struct virtio_pci_cap, cap_next)); - BUILD_BUG_ON(VIRTIO_PCI_CAP_LEN != - offsetof(struct virtio_pci_cap, cap_len)); - BUILD_BUG_ON(VIRTIO_PCI_CAP_CFG_TYPE != - offsetof(struct virtio_pci_cap, cfg_type)); - BUILD_BUG_ON(VIRTIO_PCI_CAP_BAR != - offsetof(struct virtio_pci_cap, bar)); - BUILD_BUG_ON(VIRTIO_PCI_CAP_OFFSET != - offsetof(struct virtio_pci_cap, offset)); - BUILD_BUG_ON(VIRTIO_PCI_CAP_LENGTH != - offsetof(struct virtio_pci_cap, length)); - BUILD_BUG_ON(VIRTIO_PCI_NOTIFY_CAP_MULT != - offsetof(struct virtio_pci_notify_cap, - notify_off_multiplier)); - BUILD_BUG_ON(VIRTIO_PCI_COMMON_DFSELECT != - offsetof(struct virtio_pci_common_cfg, - device_feature_select)); - BUILD_BUG_ON(VIRTIO_PCI_COMMON_DF != - offsetof(struct virtio_pci_common_cfg, device_feature)); - BUILD_BUG_ON(VIRTIO_PCI_COMMON_GFSELECT != - offsetof(struct virtio_pci_common_cfg, - guest_feature_select)); - BUILD_BUG_ON(VIRTIO_PCI_COMMON_GF != - offsetof(struct virtio_pci_common_cfg, guest_feature)); - BUILD_BUG_ON(VIRTIO_PCI_COMMON_MSIX != - offsetof(struct virtio_pci_common_cfg, msix_config)); - BUILD_BUG_ON(VIRTIO_PCI_COMMON_NUMQ != - offsetof(struct virtio_pci_common_cfg, num_queues)); - BUILD_BUG_ON(VIRTIO_PCI_COMMON_STATUS != - offsetof(struct virtio_pci_common_cfg, device_status)); - BUILD_BUG_ON(VIRTIO_PCI_COMMON_CFGGENERATION != - offsetof(struct virtio_pci_common_cfg, config_generation)); - BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_SELECT != - offsetof(struct virtio_pci_common_cfg, queue_select)); - BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_SIZE != - offsetof(struct virtio_pci_common_cfg, queue_size)); - BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_MSIX != - offsetof(struct virtio_pci_common_cfg, queue_msix_vector)); - BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_ENABLE != - offsetof(struct virtio_pci_common_cfg, queue_enable)); - BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_NOFF != - offsetof(struct virtio_pci_common_cfg, queue_notify_off)); - BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_DESCLO != - offsetof(struct virtio_pci_common_cfg, queue_desc_lo)); - BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_DESCHI != - offsetof(struct virtio_pci_common_cfg, queue_desc_hi)); - BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_AVAILLO != - offsetof(struct virtio_pci_common_cfg, queue_avail_lo)); - BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_AVAILHI != - offsetof(struct virtio_pci_common_cfg, queue_avail_hi)); - BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_USEDLO != - offsetof(struct virtio_pci_common_cfg, queue_used_lo)); - BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_USEDHI != - offsetof(struct virtio_pci_common_cfg, queue_used_hi)); -} - -/* - * vp_modern_probe: probe the modern virtio pci device, note that the - * caller is required to enable PCI device before calling this function. - * @mdev: the modern virtio-pci device - * - * Return 0 on succeed otherwise fail - */ -static int vp_modern_probe(struct virtio_pci_modern_device *mdev) -{ - struct pci_dev *pci_dev = mdev->pci_dev; - int err, common, isr, notify, device; - u32 notify_length; - u32 notify_offset; - - check_offsets(); - - mdev->pci_dev = pci_dev; - - /* We only own devices >= 0x1000 and <= 0x107f: leave the rest. */ - if (pci_dev->device < 0x1000 || pci_dev->device > 0x107f) - return -ENODEV; - - if (pci_dev->device < 0x1040) { - /* Transitional devices: use the PCI subsystem device id as - * virtio device id, same as legacy driver always did. - */ - mdev->id.device = pci_dev->subsystem_device; - } else { - /* Modern devices: simply use PCI device id, but start from 0x1040. */ - mdev->id.device = pci_dev->device - 0x1040; - } - mdev->id.vendor = pci_dev->subsystem_vendor; - - /* check for a common config: if not, use legacy mode (bar 0). */ - common = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_COMMON_CFG, - IORESOURCE_IO | IORESOURCE_MEM, - &mdev->modern_bars); - if (!common) { - dev_info(&pci_dev->dev, - "virtio_pci: leaving for legacy driver\n"); - return -ENODEV; - } - - /* If common is there, these should be too... */ - isr = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_ISR_CFG, - IORESOURCE_IO | IORESOURCE_MEM, - &mdev->modern_bars); - notify = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_NOTIFY_CFG, - IORESOURCE_IO | IORESOURCE_MEM, - &mdev->modern_bars); - if (!isr || !notify) { - dev_err(&pci_dev->dev, - "virtio_pci: missing capabilities %i/%i/%i\n", - common, isr, notify); - return -EINVAL; - } - - err = dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(64)); - if (err) - err = dma_set_mask_and_coherent(&pci_dev->dev, - DMA_BIT_MASK(32)); - if (err) - dev_warn(&pci_dev->dev, "Failed to enable 64-bit or 32-bit DMA. Trying to continue, but this might not work.\n"); - - /* Device capability is only mandatory for devices that have - * device-specific configuration. - */ - device = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_DEVICE_CFG, - IORESOURCE_IO | IORESOURCE_MEM, - &mdev->modern_bars); - - err = pci_request_selected_regions(pci_dev, mdev->modern_bars, - "virtio-pci-modern"); - if (err) - return err; - - err = -EINVAL; - mdev->common = vp_modern_map_capability(mdev, common, - sizeof(struct virtio_pci_common_cfg), 4, - 0, sizeof(struct virtio_pci_common_cfg), - NULL); - if (!mdev->common) - goto err_map_common; - mdev->isr = vp_modern_map_capability(mdev, isr, sizeof(u8), 1, - 0, 1, - NULL); - if (!mdev->isr) - goto err_map_isr; - - /* Read notify_off_multiplier from config space. */ - pci_read_config_dword(pci_dev, - notify + offsetof(struct virtio_pci_notify_cap, - notify_off_multiplier), - &mdev->notify_offset_multiplier); - /* Read notify length and offset from config space. */ - pci_read_config_dword(pci_dev, - notify + offsetof(struct virtio_pci_notify_cap, - cap.length), - ¬ify_length); - - pci_read_config_dword(pci_dev, - notify + offsetof(struct virtio_pci_notify_cap, - cap.offset), - ¬ify_offset); - - /* We don't know how many VQs we'll map, ahead of the time. - * If notify length is small, map it all now. - * Otherwise, map each VQ individually later. - */ - if ((u64)notify_length + (notify_offset % PAGE_SIZE) <= PAGE_SIZE) { - mdev->notify_base = vp_modern_map_capability(mdev, notify, - 2, 2, - 0, notify_length, - &mdev->notify_len); - if (!mdev->notify_base) - goto err_map_notify; - } else { - mdev->notify_map_cap = notify; - } - - /* Again, we don't know how much we should map, but PAGE_SIZE - * is more than enough for all existing devices. - */ - if (device) { - mdev->device = vp_modern_map_capability(mdev, device, 0, 4, - 0, PAGE_SIZE, - &mdev->device_len); - if (!mdev->device) - goto err_map_device; - } - - return 0; - -err_map_device: - if (mdev->notify_base) - pci_iounmap(pci_dev, mdev->notify_base); -err_map_notify: - pci_iounmap(pci_dev, mdev->isr); -err_map_isr: - pci_iounmap(pci_dev, mdev->common); -err_map_common: - return err; -} - /* the PCI probing function */ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev) { @@ -1063,23 +463,6 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev) return 0; } -/* - * vp_modern_probe: remove and cleanup the modern virtio pci device - * @mdev: the modern virtio-pci device - */ -static void vp_modern_remove(struct virtio_pci_modern_device *mdev) -{ - struct pci_dev *pci_dev = mdev->pci_dev; - - if (mdev->device) - pci_iounmap(pci_dev, mdev->device); - if (mdev->notify_base) - pci_iounmap(pci_dev, mdev->notify_base); - pci_iounmap(pci_dev, mdev->isr); - pci_iounmap(pci_dev, mdev->common); - pci_release_selected_regions(pci_dev, mdev->modern_bars); -} - void virtio_pci_modern_remove(struct virtio_pci_device *vp_dev) { struct virtio_pci_modern_device *mdev = &vp_dev->mdev; diff --git a/drivers/virtio/virtio_pci_modern_dev.c b/drivers/virtio/virtio_pci_modern_dev.c new file mode 100644 index 000000000000..cbd667496bb1 --- /dev/null +++ b/drivers/virtio/virtio_pci_modern_dev.c @@ -0,0 +1,599 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include +#include +#include + +/* + * vp_modern_map_capability - map a part of virtio pci capability + * @mdev: the modern virtio-pci device + * @off: offset of the capability + * @minlen: minimal length of the capability + * @align: align requirement + * @start: start from the capability + * @size: map size + * @len: the length that is actually mapped + * + * Returns the io address of for the part of the capability + */ +void __iomem *vp_modern_map_capability(struct virtio_pci_modern_device *mdev, int off, + size_t minlen, + u32 align, + u32 start, u32 size, + size_t *len) +{ + struct pci_dev *dev = mdev->pci_dev; + u8 bar; + u32 offset, length; + void __iomem *p; + + pci_read_config_byte(dev, off + offsetof(struct virtio_pci_cap, + bar), + &bar); + pci_read_config_dword(dev, off + offsetof(struct virtio_pci_cap, offset), + &offset); + pci_read_config_dword(dev, off + offsetof(struct virtio_pci_cap, length), + &length); + + if (length <= start) { + dev_err(&dev->dev, + "virtio_pci: bad capability len %u (>%u expected)\n", + length, start); + return NULL; + } + + if (length - start < minlen) { + dev_err(&dev->dev, + "virtio_pci: bad capability len %u (>=%zu expected)\n", + length, minlen); + return NULL; + } + + length -= start; + + if (start + offset < offset) { + dev_err(&dev->dev, + "virtio_pci: map wrap-around %u+%u\n", + start, offset); + return NULL; + } + + offset += start; + + if (offset & (align - 1)) { + dev_err(&dev->dev, + "virtio_pci: offset %u not aligned to %u\n", + offset, align); + return NULL; + } + + if (length > size) + length = size; + + if (len) + *len = length; + + if (minlen + offset < minlen || + minlen + offset > pci_resource_len(dev, bar)) { + dev_err(&dev->dev, + "virtio_pci: map virtio %zu@%u " + "out of range on bar %i length %lu\n", + minlen, offset, + bar, (unsigned long)pci_resource_len(dev, bar)); + return NULL; + } + + p = pci_iomap_range(dev, bar, offset, length); + if (!p) + dev_err(&dev->dev, + "virtio_pci: unable to map virtio %u@%u on bar %i\n", + length, offset, bar); + return p; +} +EXPORT_SYMBOL_GPL(vp_modern_map_capability); + +/** + * virtio_pci_find_capability - walk capabilities to find device info. + * @dev: the pci device + * @cfg_type: the VIRTIO_PCI_CAP_* value we seek + * @ioresource_types: IORESOURCE_MEM and/or IORESOURCE_IO. + * @bars: the bitmask of BARs + * + * Returns offset of the capability, or 0. + */ +static inline int virtio_pci_find_capability(struct pci_dev *dev, u8 cfg_type, + u32 ioresource_types, int *bars) +{ + int pos; + + for (pos = pci_find_capability(dev, PCI_CAP_ID_VNDR); + pos > 0; + pos = pci_find_next_capability(dev, pos, PCI_CAP_ID_VNDR)) { + u8 type, bar; + pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap, + cfg_type), + &type); + pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap, + bar), + &bar); + + /* Ignore structures with reserved BAR values */ + if (bar > 0x5) + continue; + + if (type == cfg_type) { + if (pci_resource_len(dev, bar) && + pci_resource_flags(dev, bar) & ioresource_types) { + *bars |= (1 << bar); + return pos; + } + } + } + return 0; +} + +/* This is part of the ABI. Don't screw with it. */ +static inline void check_offsets(void) +{ + /* Note: disk space was harmed in compilation of this function. */ + BUILD_BUG_ON(VIRTIO_PCI_CAP_VNDR != + offsetof(struct virtio_pci_cap, cap_vndr)); + BUILD_BUG_ON(VIRTIO_PCI_CAP_NEXT != + offsetof(struct virtio_pci_cap, cap_next)); + BUILD_BUG_ON(VIRTIO_PCI_CAP_LEN != + offsetof(struct virtio_pci_cap, cap_len)); + BUILD_BUG_ON(VIRTIO_PCI_CAP_CFG_TYPE != + offsetof(struct virtio_pci_cap, cfg_type)); + BUILD_BUG_ON(VIRTIO_PCI_CAP_BAR != + offsetof(struct virtio_pci_cap, bar)); + BUILD_BUG_ON(VIRTIO_PCI_CAP_OFFSET != + offsetof(struct virtio_pci_cap, offset)); + BUILD_BUG_ON(VIRTIO_PCI_CAP_LENGTH != + offsetof(struct virtio_pci_cap, length)); + BUILD_BUG_ON(VIRTIO_PCI_NOTIFY_CAP_MULT != + offsetof(struct virtio_pci_notify_cap, + notify_off_multiplier)); + BUILD_BUG_ON(VIRTIO_PCI_COMMON_DFSELECT != + offsetof(struct virtio_pci_common_cfg, + device_feature_select)); + BUILD_BUG_ON(VIRTIO_PCI_COMMON_DF != + offsetof(struct virtio_pci_common_cfg, device_feature)); + BUILD_BUG_ON(VIRTIO_PCI_COMMON_GFSELECT != + offsetof(struct virtio_pci_common_cfg, + guest_feature_select)); + BUILD_BUG_ON(VIRTIO_PCI_COMMON_GF != + offsetof(struct virtio_pci_common_cfg, guest_feature)); + BUILD_BUG_ON(VIRTIO_PCI_COMMON_MSIX != + offsetof(struct virtio_pci_common_cfg, msix_config)); + BUILD_BUG_ON(VIRTIO_PCI_COMMON_NUMQ != + offsetof(struct virtio_pci_common_cfg, num_queues)); + BUILD_BUG_ON(VIRTIO_PCI_COMMON_STATUS != + offsetof(struct virtio_pci_common_cfg, device_status)); + BUILD_BUG_ON(VIRTIO_PCI_COMMON_CFGGENERATION != + offsetof(struct virtio_pci_common_cfg, config_generation)); + BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_SELECT != + offsetof(struct virtio_pci_common_cfg, queue_select)); + BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_SIZE != + offsetof(struct virtio_pci_common_cfg, queue_size)); + BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_MSIX != + offsetof(struct virtio_pci_common_cfg, queue_msix_vector)); + BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_ENABLE != + offsetof(struct virtio_pci_common_cfg, queue_enable)); + BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_NOFF != + offsetof(struct virtio_pci_common_cfg, queue_notify_off)); + BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_DESCLO != + offsetof(struct virtio_pci_common_cfg, queue_desc_lo)); + BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_DESCHI != + offsetof(struct virtio_pci_common_cfg, queue_desc_hi)); + BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_AVAILLO != + offsetof(struct virtio_pci_common_cfg, queue_avail_lo)); + BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_AVAILHI != + offsetof(struct virtio_pci_common_cfg, queue_avail_hi)); + BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_USEDLO != + offsetof(struct virtio_pci_common_cfg, queue_used_lo)); + BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_USEDHI != + offsetof(struct virtio_pci_common_cfg, queue_used_hi)); +} + +/* + * vp_modern_probe: probe the modern virtio pci device, note that the + * caller is required to enable PCI device before calling this function. + * @mdev: the modern virtio-pci device + * + * Return 0 on succeed otherwise fail + */ +int vp_modern_probe(struct virtio_pci_modern_device *mdev) +{ + struct pci_dev *pci_dev = mdev->pci_dev; + int err, common, isr, notify, device; + u32 notify_length; + u32 notify_offset; + + check_offsets(); + + mdev->pci_dev = pci_dev; + + /* We only own devices >= 0x1000 and <= 0x107f: leave the rest. */ + if (pci_dev->device < 0x1000 || pci_dev->device > 0x107f) + return -ENODEV; + + if (pci_dev->device < 0x1040) { + /* Transitional devices: use the PCI subsystem device id as + * virtio device id, same as legacy driver always did. + */ + mdev->id.device = pci_dev->subsystem_device; + } else { + /* Modern devices: simply use PCI device id, but start from 0x1040. */ + mdev->id.device = pci_dev->device - 0x1040; + } + mdev->id.vendor = pci_dev->subsystem_vendor; + + /* check for a common config: if not, use legacy mode (bar 0). */ + common = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_COMMON_CFG, + IORESOURCE_IO | IORESOURCE_MEM, + &mdev->modern_bars); + if (!common) { + dev_info(&pci_dev->dev, + "virtio_pci: leaving for legacy driver\n"); + return -ENODEV; + } + + /* If common is there, these should be too... */ + isr = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_ISR_CFG, + IORESOURCE_IO | IORESOURCE_MEM, + &mdev->modern_bars); + notify = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_NOTIFY_CFG, + IORESOURCE_IO | IORESOURCE_MEM, + &mdev->modern_bars); + if (!isr || !notify) { + dev_err(&pci_dev->dev, + "virtio_pci: missing capabilities %i/%i/%i\n", + common, isr, notify); + return -EINVAL; + } + + err = dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(64)); + if (err) + err = dma_set_mask_and_coherent(&pci_dev->dev, + DMA_BIT_MASK(32)); + if (err) + dev_warn(&pci_dev->dev, "Failed to enable 64-bit or 32-bit DMA. Trying to continue, but this might not work.\n"); + + /* Device capability is only mandatory for devices that have + * device-specific configuration. + */ + device = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_DEVICE_CFG, + IORESOURCE_IO | IORESOURCE_MEM, + &mdev->modern_bars); + + err = pci_request_selected_regions(pci_dev, mdev->modern_bars, + "virtio-pci-modern"); + if (err) + return err; + + err = -EINVAL; + mdev->common = vp_modern_map_capability(mdev, common, + sizeof(struct virtio_pci_common_cfg), 4, + 0, sizeof(struct virtio_pci_common_cfg), + NULL); + if (!mdev->common) + goto err_map_common; + mdev->isr = vp_modern_map_capability(mdev, isr, sizeof(u8), 1, + 0, 1, + NULL); + if (!mdev->isr) + goto err_map_isr; + + /* Read notify_off_multiplier from config space. */ + pci_read_config_dword(pci_dev, + notify + offsetof(struct virtio_pci_notify_cap, + notify_off_multiplier), + &mdev->notify_offset_multiplier); + /* Read notify length and offset from config space. */ + pci_read_config_dword(pci_dev, + notify + offsetof(struct virtio_pci_notify_cap, + cap.length), + ¬ify_length); + + pci_read_config_dword(pci_dev, + notify + offsetof(struct virtio_pci_notify_cap, + cap.offset), + ¬ify_offset); + + /* We don't know how many VQs we'll map, ahead of the time. + * If notify length is small, map it all now. + * Otherwise, map each VQ individually later. + */ + if ((u64)notify_length + (notify_offset % PAGE_SIZE) <= PAGE_SIZE) { + mdev->notify_base = vp_modern_map_capability(mdev, notify, + 2, 2, + 0, notify_length, + &mdev->notify_len); + if (!mdev->notify_base) + goto err_map_notify; + } else { + mdev->notify_map_cap = notify; + } + + /* Again, we don't know how much we should map, but PAGE_SIZE + * is more than enough for all existing devices. + */ + if (device) { + mdev->device = vp_modern_map_capability(mdev, device, 0, 4, + 0, PAGE_SIZE, + &mdev->device_len); + if (!mdev->device) + goto err_map_device; + } + + return 0; + +err_map_device: + if (mdev->notify_base) + pci_iounmap(pci_dev, mdev->notify_base); +err_map_notify: + pci_iounmap(pci_dev, mdev->isr); +err_map_isr: + pci_iounmap(pci_dev, mdev->common); +err_map_common: + return err; +} +EXPORT_SYMBOL_GPL(vp_modern_probe); + +/* + * vp_modern_probe: remove and cleanup the modern virtio pci device + * @mdev: the modern virtio-pci device + */ +void vp_modern_remove(struct virtio_pci_modern_device *mdev) +{ + struct pci_dev *pci_dev = mdev->pci_dev; + + if (mdev->device) + pci_iounmap(pci_dev, mdev->device); + if (mdev->notify_base) + pci_iounmap(pci_dev, mdev->notify_base); + pci_iounmap(pci_dev, mdev->isr); + pci_iounmap(pci_dev, mdev->common); + pci_release_selected_regions(pci_dev, mdev->modern_bars); +} +EXPORT_SYMBOL_GPL(vp_modern_remove); + +/* + * vp_modern_get_features - get features from device + * @mdev: the modern virtio-pci device + * + * Returns the features read from the device + */ +u64 vp_modern_get_features(struct virtio_pci_modern_device *mdev) +{ + struct virtio_pci_common_cfg __iomem *cfg = mdev->common; + + u64 features; + + vp_iowrite32(0, &cfg->device_feature_select); + features = vp_ioread32(&cfg->device_feature); + vp_iowrite32(1, &cfg->device_feature_select); + features |= ((u64)vp_ioread32(&cfg->device_feature) << 32); + + return features; +} +EXPORT_SYMBOL_GPL(vp_modern_get_features); + +/* + * vp_modern_set_features - set features to device + * @mdev: the modern virtio-pci device + * @features: the features set to device + */ +void vp_modern_set_features(struct virtio_pci_modern_device *mdev, + u64 features) +{ + struct virtio_pci_common_cfg __iomem *cfg = mdev->common; + + vp_iowrite32(0, &cfg->guest_feature_select); + vp_iowrite32((u32)features, &cfg->guest_feature); + vp_iowrite32(1, &cfg->guest_feature_select); + vp_iowrite32(features >> 32, &cfg->guest_feature); +} +EXPORT_SYMBOL_GPL(vp_modern_set_features); + +/* + * vp_modern_generation - get the device genreation + * @mdev: the modern virtio-pci device + * + * Returns the genreation read from device + */ +u32 vp_modern_generation(struct virtio_pci_modern_device *mdev) +{ + struct virtio_pci_common_cfg __iomem *cfg = mdev->common; + + return vp_ioread8(&cfg->config_generation); +} +EXPORT_SYMBOL_GPL(vp_modern_generation); + +/* + * vp_modern_get_status - get the device status + * @mdev: the modern virtio-pci device + * + * Returns the status read from device + */ +u8 vp_modern_get_status(struct virtio_pci_modern_device *mdev) +{ + struct virtio_pci_common_cfg __iomem *cfg = mdev->common; + + return vp_ioread8(&cfg->device_status); +} +EXPORT_SYMBOL_GPL(vp_modern_get_status); + +/* + * vp_modern_set_status - set status to device + * @mdev: the modern virtio-pci device + * @status: the status set to device + */ +void vp_modern_set_status(struct virtio_pci_modern_device *mdev, + u8 status) +{ + struct virtio_pci_common_cfg __iomem *cfg = mdev->common; + + vp_iowrite8(status, &cfg->device_status); +} +EXPORT_SYMBOL_GPL(vp_modern_set_status); + +/* + * vp_modern_queue_vector - set the MSIX vector for a specific virtqueue + * @mdev: the modern virtio-pci device + * @index: queue index + * @vector: the config vector + * + * Returns the config vector read from the device + */ +u16 vp_modern_queue_vector(struct virtio_pci_modern_device *mdev, + u16 index, u16 vector) +{ + struct virtio_pci_common_cfg __iomem *cfg = mdev->common; + + vp_iowrite16(index, &cfg->queue_select); + vp_iowrite16(vector, &cfg->queue_msix_vector); + /* Flush the write out to device */ + return vp_ioread16(&cfg->queue_msix_vector); +} +EXPORT_SYMBOL_GPL(vp_modern_queue_vector); + +/* + * vp_modern_config_vector - set the vector for config interrupt + * @mdev: the modern virtio-pci device + * @vector: the config vector + * + * Returns the config vector read from the device + */ +u16 vp_modern_config_vector(struct virtio_pci_modern_device *mdev, + u16 vector) +{ + struct virtio_pci_common_cfg __iomem *cfg = mdev->common; + + /* Setup the vector used for configuration events */ + vp_iowrite16(vector, &cfg->msix_config); + /* Verify we had enough resources to assign the vector */ + /* Will also flush the write out to device */ + return vp_ioread16(&cfg->msix_config); +} +EXPORT_SYMBOL_GPL(vp_modern_config_vector); + +/* + * vp_modern_queue_address - set the virtqueue address + * @mdev: the modern virtio-pci device + * @index: the queue index + * @desc_addr: address of the descriptor area + * @driver_addr: address of the driver area + * @device_addr: address of the device area + */ +void vp_modern_queue_address(struct virtio_pci_modern_device *mdev, + u16 index, u64 desc_addr, u64 driver_addr, + u64 device_addr) +{ + struct virtio_pci_common_cfg __iomem *cfg = mdev->common; + + vp_iowrite16(index, &cfg->queue_select); + + vp_iowrite64_twopart(desc_addr, &cfg->queue_desc_lo, + &cfg->queue_desc_hi); + vp_iowrite64_twopart(driver_addr, &cfg->queue_avail_lo, + &cfg->queue_avail_hi); + vp_iowrite64_twopart(device_addr, &cfg->queue_used_lo, + &cfg->queue_used_hi); +} +EXPORT_SYMBOL_GPL(vp_modern_queue_address); + +/* + * vp_modern_set_queue_enable - enable a virtqueue + * @mdev: the modern virtio-pci device + * @index: the queue index + * @enable: whether the virtqueue is enable or not + */ +void vp_modern_set_queue_enable(struct virtio_pci_modern_device *mdev, + u16 index, bool enable) +{ + vp_iowrite16(index, &mdev->common->queue_select); + vp_iowrite16(enable, &mdev->common->queue_enable); +} +EXPORT_SYMBOL_GPL(vp_modern_set_queue_enable); + +/* + * vp_modern_get_queue_enable - enable a virtqueue + * @mdev: the modern virtio-pci device + * @index: the queue index + * + * Returns whether a virtqueue is enabled or not + */ +bool vp_modern_get_queue_enable(struct virtio_pci_modern_device *mdev, + u16 index) +{ + vp_iowrite16(index, &mdev->common->queue_select); + + return vp_ioread16(&mdev->common->queue_enable); +} +EXPORT_SYMBOL_GPL(vp_modern_get_queue_enable); + +/* + * vp_modern_set_queue_size - set size for a virtqueue + * @mdev: the modern virtio-pci device + * @index: the queue index + * @size: the size of the virtqueue + */ +void vp_modern_set_queue_size(struct virtio_pci_modern_device *mdev, + u16 index, u16 size) +{ + vp_iowrite16(index, &mdev->common->queue_select); + vp_iowrite16(size, &mdev->common->queue_size); + +} +EXPORT_SYMBOL_GPL(vp_modern_set_queue_size); + +/* + * vp_modern_get_queue_size - get size for a virtqueue + * @mdev: the modern virtio-pci device + * @index: the queue index + * + * Returns the size of the virtqueue + */ +u16 vp_modern_get_queue_size(struct virtio_pci_modern_device *mdev, + u16 index) +{ + vp_iowrite16(index, &mdev->common->queue_select); + + return vp_ioread16(&mdev->common->queue_size); + +} +EXPORT_SYMBOL_GPL(vp_modern_get_queue_size); + +/* + * vp_modern_get_num_queues - get the number of virtqueues + * @mdev: the modern virtio-pci device + * + * Returns the number of virtqueues + */ +u16 vp_modern_get_num_queues(struct virtio_pci_modern_device *mdev) +{ + return vp_ioread16(&mdev->common->num_queues); +} +EXPORT_SYMBOL_GPL(vp_modern_get_num_queues); + +/* + * vp_modern_get_queue_notify_off - get notification offset for a virtqueue + * @mdev: the modern virtio-pci device + * @index: the queue index + * + * Returns the notification offset for a virtqueue + */ +u16 vp_modern_get_queue_notify_off(struct virtio_pci_modern_device *mdev, + u16 index) +{ + vp_iowrite16(index, &mdev->common->queue_select); + + return vp_ioread16(&mdev->common->queue_notify_off); +} +EXPORT_SYMBOL_GPL(vp_modern_get_queue_notify_off); + +MODULE_VERSION("0.1"); +MODULE_DESCRIPTION("Modern Virtio PCI Device"); +MODULE_AUTHOR("Jason Wang "); +MODULE_LICENSE("GPL"); diff --git a/include/linux/virtio_pci_modern.h b/include/linux/virtio_pci_modern.h new file mode 100644 index 000000000000..f26acbeec965 --- /dev/null +++ b/include/linux/virtio_pci_modern.h @@ -0,0 +1,111 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_VIRTIO_PCI_MODERN_H +#define _LINUX_VIRTIO_PCI_MODERN_H + +#include +#include + +struct virtio_pci_modern_device { + struct pci_dev *pci_dev; + + struct virtio_pci_common_cfg __iomem *common; + /* Device-specific data (non-legacy mode) */ + void __iomem *device; + /* Base of vq notifications (non-legacy mode). */ + void __iomem *notify_base; + /* Where to read and clear interrupt */ + u8 __iomem *isr; + + /* So we can sanity-check accesses. */ + size_t notify_len; + size_t device_len; + + /* Capability for when we need to map notifications per-vq. */ + int notify_map_cap; + + /* Multiply queue_notify_off by this value. (non-legacy mode). */ + u32 notify_offset_multiplier; + + int modern_bars; + + struct virtio_device_id id; +}; + +/* + * Type-safe wrappers for io accesses. + * Use these to enforce at compile time the following spec requirement: + * + * The driver MUST access each field using the “natural” access + * method, i.e. 32-bit accesses for 32-bit fields, 16-bit accesses + * for 16-bit fields and 8-bit accesses for 8-bit fields. + */ +static inline u8 vp_ioread8(const u8 __iomem *addr) +{ + return ioread8(addr); +} +static inline u16 vp_ioread16 (const __le16 __iomem *addr) +{ + return ioread16(addr); +} + +static inline u32 vp_ioread32(const __le32 __iomem *addr) +{ + return ioread32(addr); +} + +static inline void vp_iowrite8(u8 value, u8 __iomem *addr) +{ + iowrite8(value, addr); +} + +static inline void vp_iowrite16(u16 value, __le16 __iomem *addr) +{ + iowrite16(value, addr); +} + +static inline void vp_iowrite32(u32 value, __le32 __iomem *addr) +{ + iowrite32(value, addr); +} + +static inline void vp_iowrite64_twopart(u64 val, + __le32 __iomem *lo, + __le32 __iomem *hi) +{ + vp_iowrite32((u32)val, lo); + vp_iowrite32(val >> 32, hi); +} + +u64 vp_modern_get_features(struct virtio_pci_modern_device *mdev); +void vp_modern_set_features(struct virtio_pci_modern_device *mdev, + u64 features); +u32 vp_modern_generation(struct virtio_pci_modern_device *mdev); +u8 vp_modern_get_status(struct virtio_pci_modern_device *mdev); +void vp_modern_set_status(struct virtio_pci_modern_device *mdev, + u8 status); +u16 vp_modern_queue_vector(struct virtio_pci_modern_device *mdev, + u16 idx, u16 vector); +u16 vp_modern_config_vector(struct virtio_pci_modern_device *mdev, + u16 vector); +void vp_modern_queue_address(struct virtio_pci_modern_device *mdev, + u16 index, u64 desc_addr, u64 driver_addr, + u64 device_addr); +void vp_modern_set_queue_enable(struct virtio_pci_modern_device *mdev, + u16 idx, bool enable); +bool vp_modern_get_queue_enable(struct virtio_pci_modern_device *mdev, + u16 idx); +void vp_modern_set_queue_size(struct virtio_pci_modern_device *mdev, + u16 idx, u16 size); +u16 vp_modern_get_queue_size(struct virtio_pci_modern_device *mdev, + u16 idx); +u16 vp_modern_get_num_queues(struct virtio_pci_modern_device *mdev); +u16 vp_modern_get_queue_notify_off(struct virtio_pci_modern_device *mdev, + u16 idx); +void __iomem *vp_modern_map_capability(struct virtio_pci_modern_device *mdev, int off, + size_t minlen, + u32 align, + u32 start, u32 size, + size_t *len); +int vp_modern_probe(struct virtio_pci_modern_device *mdev); +void vp_modern_remove(struct virtio_pci_modern_device *mdev); +#endif -- cgit v1.2.3 From 06f45fe96fcd81531b0bcb2a6115da563ae6dbd6 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Fri, 19 Feb 2021 16:40:28 +0100 Subject: xen/events: add per-xenbus device event statistics and settings Add syfs nodes for each xenbus device showing event statistics (number of events and spurious events, number of associated event channels) and for setting a spurious event threshold in case a frontend is sending too many events without being rogue on purpose. Signed-off-by: Juergen Gross Reviewed-by: Boris Ostrovsky Link: https://lore.kernel.org/r/20210219154030.10892-7-jgross@suse.com Signed-off-by: Boris Ostrovsky --- Documentation/ABI/testing/sysfs-devices-xenbus | 41 ++++++++++++++++ drivers/xen/events/events_base.c | 27 ++++++++++- drivers/xen/xenbus/xenbus_probe.c | 66 ++++++++++++++++++++++++++ include/xen/xenbus.h | 7 +++ 4 files changed, 139 insertions(+), 2 deletions(-) create mode 100644 Documentation/ABI/testing/sysfs-devices-xenbus (limited to 'include') diff --git a/Documentation/ABI/testing/sysfs-devices-xenbus b/Documentation/ABI/testing/sysfs-devices-xenbus new file mode 100644 index 000000000000..fd796cb4f315 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-devices-xenbus @@ -0,0 +1,41 @@ +What: /sys/devices/*/xenbus/event_channels +Date: February 2021 +Contact: Xen Developers mailing list +Description: + Number of Xen event channels associated with a kernel based + paravirtualized device frontend or backend. + +What: /sys/devices/*/xenbus/events +Date: February 2021 +Contact: Xen Developers mailing list +Description: + Total number of Xen events received for a Xen pv device + frontend or backend. + +What: /sys/devices/*/xenbus/jiffies_eoi_delayed +Date: February 2021 +Contact: Xen Developers mailing list +Description: + Summed up time in jiffies the EOI of an interrupt for a Xen + pv device has been delayed in order to avoid stalls due to + event storms. This value rising is a first sign for a rogue + other end of the pv device. + +What: /sys/devices/*/xenbus/spurious_events +Date: February 2021 +Contact: Xen Developers mailing list +Description: + Number of events received for a Xen pv device which did not + require any action. Too many spurious events in a row will + trigger delayed EOI processing. + +What: /sys/devices/*/xenbus/spurious_threshold +Date: February 2021 +Contact: Xen Developers mailing list +Description: + Controls the tolerated number of subsequent spurious events + before delayed EOI processing is triggered for a Xen pv + device. Default is 1. This can be modified in case the other + end of the pv device is issuing spurious events on a regular + basis and is known not to be malicious on purpose. Raising + the value for such cases can improve pv device performance. diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index b249f2d6b0cc..adb7260e94b2 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -323,6 +323,8 @@ static int xen_irq_info_evtchn_setup(unsigned irq, ret = xen_irq_info_common_setup(info, irq, IRQT_EVTCHN, evtchn, 0); info->u.interdomain = dev; + if (dev) + atomic_inc(&dev->event_channels); return ret; } @@ -568,18 +570,28 @@ static void xen_irq_lateeoi_locked(struct irq_info *info, bool spurious) return; if (spurious) { + struct xenbus_device *dev = info->u.interdomain; + unsigned int threshold = 1; + + if (dev && dev->spurious_threshold) + threshold = dev->spurious_threshold; + if ((1 << info->spurious_cnt) < (HZ << 2)) { if (info->spurious_cnt != 0xFF) info->spurious_cnt++; } - if (info->spurious_cnt > 1) { - delay = 1 << (info->spurious_cnt - 2); + if (info->spurious_cnt > threshold) { + delay = 1 << (info->spurious_cnt - 1 - threshold); if (delay > HZ) delay = HZ; if (!info->eoi_time) info->eoi_cpu = smp_processor_id(); info->eoi_time = get_jiffies_64() + delay; + if (dev) + atomic_add(delay, &dev->jiffies_eoi_delayed); } + if (dev) + atomic_inc(&dev->spurious_events); } else { info->spurious_cnt = 0; } @@ -908,6 +920,7 @@ static void __unbind_from_irq(unsigned int irq) if (VALID_EVTCHN(evtchn)) { unsigned int cpu = cpu_from_irq(irq); + struct xenbus_device *dev; xen_evtchn_close(evtchn); @@ -918,6 +931,11 @@ static void __unbind_from_irq(unsigned int irq) case IRQT_IPI: per_cpu(ipi_to_irq, cpu)[ipi_from_irq(irq)] = -1; break; + case IRQT_EVTCHN: + dev = info->u.interdomain; + if (dev) + atomic_dec(&dev->event_channels); + break; default: break; } @@ -1581,6 +1599,7 @@ void handle_irq_for_port(evtchn_port_t port, struct evtchn_loop_ctrl *ctrl) { int irq; struct irq_info *info; + struct xenbus_device *dev; irq = get_evtchn_to_irq(port); if (irq == -1) @@ -1610,6 +1629,10 @@ void handle_irq_for_port(evtchn_port_t port, struct evtchn_loop_ctrl *ctrl) info = info_for_irq(irq); + dev = (info->type == IRQT_EVTCHN) ? info->u.interdomain : NULL; + if (dev) + atomic_inc(&dev->events); + if (ctrl->defer_eoi) { info->eoi_cpu = smp_processor_id(); info->irq_epoch = __this_cpu_read(irq_epoch); diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c index 8a75092bb148..97f0d234482d 100644 --- a/drivers/xen/xenbus/xenbus_probe.c +++ b/drivers/xen/xenbus/xenbus_probe.c @@ -206,6 +206,65 @@ void xenbus_otherend_changed(struct xenbus_watch *watch, } EXPORT_SYMBOL_GPL(xenbus_otherend_changed); +#define XENBUS_SHOW_STAT(name) \ +static ssize_t show_##name(struct device *_dev, \ + struct device_attribute *attr, \ + char *buf) \ +{ \ + struct xenbus_device *dev = to_xenbus_device(_dev); \ + \ + return sprintf(buf, "%d\n", atomic_read(&dev->name)); \ +} \ +static DEVICE_ATTR(name, 0444, show_##name, NULL) + +XENBUS_SHOW_STAT(event_channels); +XENBUS_SHOW_STAT(events); +XENBUS_SHOW_STAT(spurious_events); +XENBUS_SHOW_STAT(jiffies_eoi_delayed); + +static ssize_t show_spurious_threshold(struct device *_dev, + struct device_attribute *attr, + char *buf) +{ + struct xenbus_device *dev = to_xenbus_device(_dev); + + return sprintf(buf, "%d\n", dev->spurious_threshold); +} + +static ssize_t set_spurious_threshold(struct device *_dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct xenbus_device *dev = to_xenbus_device(_dev); + unsigned int val; + ssize_t ret; + + ret = kstrtouint(buf, 0, &val); + if (ret) + return ret; + + dev->spurious_threshold = val; + + return count; +} + +static DEVICE_ATTR(spurious_threshold, 0644, show_spurious_threshold, + set_spurious_threshold); + +static struct attribute *xenbus_attrs[] = { + &dev_attr_event_channels.attr, + &dev_attr_events.attr, + &dev_attr_spurious_events.attr, + &dev_attr_jiffies_eoi_delayed.attr, + &dev_attr_spurious_threshold.attr, + NULL +}; + +static const struct attribute_group xenbus_group = { + .name = "xenbus", + .attrs = xenbus_attrs, +}; + int xenbus_dev_probe(struct device *_dev) { struct xenbus_device *dev = to_xenbus_device(_dev); @@ -253,6 +312,11 @@ int xenbus_dev_probe(struct device *_dev) return err; } + dev->spurious_threshold = 1; + if (sysfs_create_group(&dev->dev.kobj, &xenbus_group)) + dev_warn(&dev->dev, "sysfs_create_group on %s failed.\n", + dev->nodename); + return 0; fail_put: module_put(drv->driver.owner); @@ -269,6 +333,8 @@ int xenbus_dev_remove(struct device *_dev) DPRINTK("%s", dev->nodename); + sysfs_remove_group(&dev->dev.kobj, &xenbus_group); + free_otherend_watch(dev); if (drv->remove) { diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h index bf3cfc7c35d0..0b1386073d49 100644 --- a/include/xen/xenbus.h +++ b/include/xen/xenbus.h @@ -88,6 +88,13 @@ struct xenbus_device { struct completion down; struct work_struct work; struct semaphore reclaim_sem; + + /* Event channel based statistics and settings. */ + atomic_t event_channels; + atomic_t events; + atomic_t spurious_events; + atomic_t jiffies_eoi_delayed; + unsigned int spurious_threshold; }; static inline struct xenbus_device *to_xenbus_device(struct device *dev) -- cgit v1.2.3 From c0ea57608b691d6cde8aff23e11f9858a86b5918 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 16 Feb 2021 16:52:47 +0100 Subject: blktrace: remove debugfs file dentries from struct blk_trace These debugfs dentries do not need to be saved for anything as the whole directory and everything in it is properly cleaned up when the parent directory is removed. So remove them from struct blk_trace and don't save them when created as it's not necessary. Cc: Jens Axboe Cc: Steven Rostedt Cc: Ingo Molnar Cc: linux-block@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Greg Kroah-Hartman Signed-off-by: Jens Axboe --- include/linux/blktrace_api.h | 2 -- kernel/trace/blktrace.c | 8 ++------ 2 files changed, 2 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index e17d04abf6a3..a083e15df608 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -23,8 +23,6 @@ struct blk_trace { u32 pid; u32 dev; struct dentry *dir; - struct dentry *dropped_file; - struct dentry *msg_file; struct list_head running_list; atomic_t dropped; }; diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index d7ebef83771c..0c8690d9f6cd 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -311,8 +311,6 @@ record_it: static void blk_trace_free(struct blk_trace *bt) { - debugfs_remove(bt->msg_file); - debugfs_remove(bt->dropped_file); relay_close(bt->rchan); debugfs_remove(bt->dir); free_percpu(bt->sequence); @@ -544,10 +542,8 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, INIT_LIST_HEAD(&bt->running_list); ret = -EIO; - bt->dropped_file = debugfs_create_file("dropped", 0444, dir, bt, - &blk_dropped_fops); - - bt->msg_file = debugfs_create_file("msg", 0222, dir, bt, &blk_msg_fops); + debugfs_create_file("dropped", 0444, dir, bt, &blk_dropped_fops); + debugfs_create_file("msg", 0222, dir, bt, &blk_msg_fops); bt->rchan = relay_open("trace", dir, buts->buf_size, buts->buf_nr, &blk_relay_callbacks, bt); -- cgit v1.2.3 From ee576c47db60432c37e54b1e2b43a8ca6d3a8dca Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Tue, 23 Feb 2021 14:18:58 +0100 Subject: net: icmp: pass zeroed opts from icmp{,v6}_ndo_send before sending The icmp{,v6}_send functions make all sorts of use of skb->cb, casting it with IPCB or IP6CB, assuming the skb to have come directly from the inet layer. But when the packet comes from the ndo layer, especially when forwarded, there's no telling what might be in skb->cb at that point. As a result, the icmp sending code risks reading bogus memory contents, which can result in nasty stack overflows such as this one reported by a user: panic+0x108/0x2ea __stack_chk_fail+0x14/0x20 __icmp_send+0x5bd/0x5c0 icmp_ndo_send+0x148/0x160 In icmp_send, skb->cb is cast with IPCB and an ip_options struct is read from it. The optlen parameter there is of particular note, as it can induce writes beyond bounds. There are quite a few ways that can happen in __ip_options_echo. For example: // sptr/skb are attacker-controlled skb bytes sptr = skb_network_header(skb); // dptr/dopt points to stack memory allocated by __icmp_send dptr = dopt->__data; // sopt is the corrupt skb->cb in question if (sopt->rr) { optlen = sptr[sopt->rr+1]; // corrupt skb->cb + skb->data soffset = sptr[sopt->rr+2]; // corrupt skb->cb + skb->data // this now writes potentially attacker-controlled data, over // flowing the stack: memcpy(dptr, sptr+sopt->rr, optlen); } In the icmpv6_send case, the story is similar, but not as dire, as only IP6CB(skb)->iif and IP6CB(skb)->dsthao are used. The dsthao case is worse than the iif case, but it is passed to ipv6_find_tlv, which does a bit of bounds checking on the value. This is easy to simulate by doing a `memset(skb->cb, 0x41, sizeof(skb->cb));` before calling icmp{,v6}_ndo_send, and it's only by good fortune and the rarity of icmp sending from that context that we've avoided reports like this until now. For example, in KASAN: BUG: KASAN: stack-out-of-bounds in __ip_options_echo+0xa0e/0x12b0 Write of size 38 at addr ffff888006f1f80e by task ping/89 CPU: 2 PID: 89 Comm: ping Not tainted 5.10.0-rc7-debug+ #5 Call Trace: dump_stack+0x9a/0xcc print_address_description.constprop.0+0x1a/0x160 __kasan_report.cold+0x20/0x38 kasan_report+0x32/0x40 check_memory_region+0x145/0x1a0 memcpy+0x39/0x60 __ip_options_echo+0xa0e/0x12b0 __icmp_send+0x744/0x1700 Actually, out of the 4 drivers that do this, only gtp zeroed the cb for the v4 case, while the rest did not. So this commit actually removes the gtp-specific zeroing, while putting the code where it belongs in the shared infrastructure of icmp{,v6}_ndo_send. This commit fixes the issue by passing an empty IPCB or IP6CB along to the functions that actually do the work. For the icmp_send, this was already trivial, thanks to __icmp_send providing the plumbing function. For icmpv6_send, this required a tiny bit of refactoring to make it behave like the v4 case, after which it was straight forward. Fixes: a2b78e9b2cac ("sunvnet: generate ICMP PTMUD messages for smaller port MTUs") Reported-by: SinYu Reviewed-by: Willem de Bruijn Link: https://lore.kernel.org/netdev/CAF=yD-LOF116aHub6RMe8vB8ZpnrrnoTdqhobEx+bvoA8AsP0w@mail.gmail.com/T/ Signed-off-by: Jason A. Donenfeld Link: https://lore.kernel.org/r/20210223131858.72082-1-Jason@zx2c4.com Signed-off-by: Jakub Kicinski --- drivers/net/gtp.c | 1 - include/linux/icmpv6.h | 26 ++++++++++++++++++++------ include/linux/ipv6.h | 1 - include/net/icmp.h | 6 +++++- net/ipv4/icmp.c | 5 +++-- net/ipv6/icmp.c | 18 +++++++++--------- net/ipv6/ip6_icmp.c | 12 +++++++----- 7 files changed, 44 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 9a70f05baf6e..39c00f050fbd 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -543,7 +543,6 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev, if (!skb_is_gso(skb) && (iph->frag_off & htons(IP_DF)) && mtu < ntohs(iph->tot_len)) { netdev_dbg(dev, "packet too big, fragmentation needed\n"); - memset(IPCB(skb), 0, sizeof(*IPCB(skb))); icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); goto err_rt; diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h index 452d8978ffc7..9055cb380ee2 100644 --- a/include/linux/icmpv6.h +++ b/include/linux/icmpv6.h @@ -3,6 +3,7 @@ #define _LINUX_ICMPV6_H #include +#include #include static inline struct icmp6hdr *icmp6_hdr(const struct sk_buff *skb) @@ -15,13 +16,16 @@ static inline struct icmp6hdr *icmp6_hdr(const struct sk_buff *skb) #if IS_ENABLED(CONFIG_IPV6) typedef void ip6_icmp_send_t(struct sk_buff *skb, u8 type, u8 code, __u32 info, - const struct in6_addr *force_saddr); + const struct in6_addr *force_saddr, + const struct inet6_skb_parm *parm); void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, - const struct in6_addr *force_saddr); + const struct in6_addr *force_saddr, + const struct inet6_skb_parm *parm); #if IS_BUILTIN(CONFIG_IPV6) -static inline void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) +static inline void __icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, + const struct inet6_skb_parm *parm) { - icmp6_send(skb, type, code, info, NULL); + icmp6_send(skb, type, code, info, NULL, parm); } static inline int inet6_register_icmp_sender(ip6_icmp_send_t *fn) { @@ -34,18 +38,28 @@ static inline int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn) return 0; } #else -extern void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info); +extern void __icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, + const struct inet6_skb_parm *parm); extern int inet6_register_icmp_sender(ip6_icmp_send_t *fn); extern int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn); #endif +static inline void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) +{ + __icmpv6_send(skb, type, code, info, IP6CB(skb)); +} + int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type, unsigned int data_len); #if IS_ENABLED(CONFIG_NF_NAT) void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info); #else -#define icmpv6_ndo_send icmpv6_send +static inline void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info) +{ + struct inet6_skb_parm parm = { 0 }; + __icmpv6_send(skb_in, type, code, info, &parm); +} #endif #else diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 9d1f29f0c512..70b2ad3b9884 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -85,7 +85,6 @@ struct ipv6_params { __s32 autoconf; }; extern struct ipv6_params ipv6_defaults; -#include #include #include diff --git a/include/net/icmp.h b/include/net/icmp.h index 9ac2d2672a93..fd84adc47963 100644 --- a/include/net/icmp.h +++ b/include/net/icmp.h @@ -46,7 +46,11 @@ static inline void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 #if IS_ENABLED(CONFIG_NF_NAT) void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info); #else -#define icmp_ndo_send icmp_send +static inline void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info) +{ + struct ip_options opts = { 0 }; + __icmp_send(skb_in, type, code, info, &opts); +} #endif int icmp_rcv(struct sk_buff *skb); diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 396b492c804f..616e2dc1c8fa 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -775,13 +775,14 @@ EXPORT_SYMBOL(__icmp_send); void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info) { struct sk_buff *cloned_skb = NULL; + struct ip_options opts = { 0 }; enum ip_conntrack_info ctinfo; struct nf_conn *ct; __be32 orig_ip; ct = nf_ct_get(skb_in, &ctinfo); if (!ct || !(ct->status & IPS_SRC_NAT)) { - icmp_send(skb_in, type, code, info); + __icmp_send(skb_in, type, code, info, &opts); return; } @@ -796,7 +797,7 @@ void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info) orig_ip = ip_hdr(skb_in)->saddr; ip_hdr(skb_in)->saddr = ct->tuplehash[0].tuple.src.u3.ip; - icmp_send(skb_in, type, code, info); + __icmp_send(skb_in, type, code, info, &opts); ip_hdr(skb_in)->saddr = orig_ip; out: consume_skb(cloned_skb); diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index f3d05866692e..fd1f896115c1 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -331,10 +331,9 @@ static int icmpv6_getfrag(void *from, char *to, int offset, int len, int odd, st } #if IS_ENABLED(CONFIG_IPV6_MIP6) -static void mip6_addr_swap(struct sk_buff *skb) +static void mip6_addr_swap(struct sk_buff *skb, const struct inet6_skb_parm *opt) { struct ipv6hdr *iph = ipv6_hdr(skb); - struct inet6_skb_parm *opt = IP6CB(skb); struct ipv6_destopt_hao *hao; struct in6_addr tmp; int off; @@ -351,7 +350,7 @@ static void mip6_addr_swap(struct sk_buff *skb) } } #else -static inline void mip6_addr_swap(struct sk_buff *skb) {} +static inline void mip6_addr_swap(struct sk_buff *skb, const struct inet6_skb_parm *opt) {} #endif static struct dst_entry *icmpv6_route_lookup(struct net *net, @@ -446,7 +445,8 @@ static int icmp6_iif(const struct sk_buff *skb) * Send an ICMP message in response to a packet in error */ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, - const struct in6_addr *force_saddr) + const struct in6_addr *force_saddr, + const struct inet6_skb_parm *parm) { struct inet6_dev *idev = NULL; struct ipv6hdr *hdr = ipv6_hdr(skb); @@ -542,7 +542,7 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, if (!(skb->dev->flags & IFF_LOOPBACK) && !icmpv6_global_allow(net, type)) goto out_bh_enable; - mip6_addr_swap(skb); + mip6_addr_swap(skb, parm); sk = icmpv6_xmit_lock(net); if (!sk) @@ -559,7 +559,7 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, /* select a more meaningful saddr from input if */ struct net_device *in_netdev; - in_netdev = dev_get_by_index(net, IP6CB(skb)->iif); + in_netdev = dev_get_by_index(net, parm->iif); if (in_netdev) { ipv6_dev_get_saddr(net, in_netdev, &fl6.daddr, inet6_sk(sk)->srcprefs, @@ -640,7 +640,7 @@ EXPORT_SYMBOL(icmp6_send); */ void icmpv6_param_prob(struct sk_buff *skb, u8 code, int pos) { - icmp6_send(skb, ICMPV6_PARAMPROB, code, pos, NULL); + icmp6_send(skb, ICMPV6_PARAMPROB, code, pos, NULL, IP6CB(skb)); kfree_skb(skb); } @@ -697,10 +697,10 @@ int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type, } if (type == ICMP_TIME_EXCEEDED) icmp6_send(skb2, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, - info, &temp_saddr); + info, &temp_saddr, IP6CB(skb2)); else icmp6_send(skb2, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, - info, &temp_saddr); + info, &temp_saddr, IP6CB(skb2)); if (rt) ip6_rt_put(rt); diff --git a/net/ipv6/ip6_icmp.c b/net/ipv6/ip6_icmp.c index 70c8c2f36c98..9e3574880cb0 100644 --- a/net/ipv6/ip6_icmp.c +++ b/net/ipv6/ip6_icmp.c @@ -33,23 +33,25 @@ int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn) } EXPORT_SYMBOL(inet6_unregister_icmp_sender); -void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) +void __icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, + const struct inet6_skb_parm *parm) { ip6_icmp_send_t *send; rcu_read_lock(); send = rcu_dereference(ip6_icmp_send); if (send) - send(skb, type, code, info, NULL); + send(skb, type, code, info, NULL, parm); rcu_read_unlock(); } -EXPORT_SYMBOL(icmpv6_send); +EXPORT_SYMBOL(__icmpv6_send); #endif #if IS_ENABLED(CONFIG_NF_NAT) #include void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info) { + struct inet6_skb_parm parm = { 0 }; struct sk_buff *cloned_skb = NULL; enum ip_conntrack_info ctinfo; struct in6_addr orig_ip; @@ -57,7 +59,7 @@ void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info) ct = nf_ct_get(skb_in, &ctinfo); if (!ct || !(ct->status & IPS_SRC_NAT)) { - icmpv6_send(skb_in, type, code, info); + __icmpv6_send(skb_in, type, code, info, &parm); return; } @@ -72,7 +74,7 @@ void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info) orig_ip = ipv6_hdr(skb_in)->saddr; ipv6_hdr(skb_in)->saddr = ct->tuplehash[0].tuple.src.u3.in6; - icmpv6_send(skb_in, type, code, info); + __icmpv6_send(skb_in, type, code, info, &parm); ipv6_hdr(skb_in)->saddr = orig_ip; out: consume_skb(cloned_skb); -- cgit v1.2.3 From fa8fef0e104a23efe568b835d9e7e188d1d97610 Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Tue, 2 Feb 2021 01:27:55 +0530 Subject: PCI: endpoint: Add helper API to get the 'next' unreserved BAR Add an API to get the next unreserved BAR starting from a given BAR number that can be used by the endpoint function. Link: https://lore.kernel.org/r/20210201195809.7342-4-kishon@ti.com Signed-off-by: Kishon Vijay Abraham I Signed-off-by: Lorenzo Pieralisi Signed-off-by: Bjorn Helgaas --- drivers/pci/endpoint/pci-epc-core.c | 26 ++++++++++++++++++++++---- include/linux/pci-epc.h | 2 ++ 2 files changed, 24 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/pci/endpoint/pci-epc-core.c b/drivers/pci/endpoint/pci-epc-core.c index 25e57672e1a1..1afe5d9afb0d 100644 --- a/drivers/pci/endpoint/pci-epc-core.c +++ b/drivers/pci/endpoint/pci-epc-core.c @@ -87,17 +87,36 @@ EXPORT_SYMBOL_GPL(pci_epc_get); * pci_epc_get_first_free_bar() - helper to get first unreserved BAR * @epc_features: pci_epc_features structure that holds the reserved bar bitmap * - * Invoke to get the first unreserved BAR that can be used for endpoint + * Invoke to get the first unreserved BAR that can be used by the endpoint * function. For any incorrect value in reserved_bar return '0'. */ unsigned int pci_epc_get_first_free_bar(const struct pci_epc_features *epc_features) +{ + return pci_epc_get_next_free_bar(epc_features, BAR_0); +} +EXPORT_SYMBOL_GPL(pci_epc_get_first_free_bar); + +/** + * pci_epc_get_next_free_bar() - helper to get unreserved BAR starting from @bar + * @epc_features: pci_epc_features structure that holds the reserved bar bitmap + * @bar: the starting BAR number from where unreserved BAR should be searched + * + * Invoke to get the next unreserved BAR starting from @bar that can be used + * for endpoint function. For any incorrect value in reserved_bar return '0'. + */ +unsigned int pci_epc_get_next_free_bar(const struct pci_epc_features + *epc_features, enum pci_barno bar) { unsigned long free_bar; if (!epc_features) return 0; + /* If 'bar - 1' is a 64-bit BAR, move to the next BAR */ + if ((epc_features->bar_fixed_64bit << 1) & 1 << bar) + bar++; + /* Find if the reserved BAR is also a 64-bit BAR */ free_bar = epc_features->reserved_bar & epc_features->bar_fixed_64bit; @@ -105,14 +124,13 @@ unsigned int pci_epc_get_first_free_bar(const struct pci_epc_features free_bar <<= 1; free_bar |= epc_features->reserved_bar; - /* Now find the free BAR */ - free_bar = ffz(free_bar); + free_bar = find_next_zero_bit(&free_bar, 6, bar); if (free_bar > 5) return 0; return free_bar; } -EXPORT_SYMBOL_GPL(pci_epc_get_first_free_bar); +EXPORT_SYMBOL_GPL(pci_epc_get_next_free_bar); /** * pci_epc_get_features() - get the features supported by EPC diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h index cc66bec8be90..cfe9b427e6b7 100644 --- a/include/linux/pci-epc.h +++ b/include/linux/pci-epc.h @@ -203,6 +203,8 @@ const struct pci_epc_features *pci_epc_get_features(struct pci_epc *epc, u8 func_no); unsigned int pci_epc_get_first_free_bar(const struct pci_epc_features *epc_features); +unsigned int pci_epc_get_next_free_bar(const struct pci_epc_features + *epc_features, enum pci_barno bar); struct pci_epc *pci_epc_get(const char *epc_name); void pci_epc_put(struct pci_epc *epc); -- cgit v1.2.3 From 0e27aeccfa3d1bab7c6a29fb8e6fcedbad7b09a8 Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Tue, 2 Feb 2021 01:27:56 +0530 Subject: PCI: endpoint: Make *_free_bar() to return error codes on failure Modify pci_epc_get_next_free_bar() and pci_epc_get_first_free_bar() to return error values if there are no free BARs available. Link: https://lore.kernel.org/r/20210201195809.7342-5-kishon@ti.com Signed-off-by: Kishon Vijay Abraham I Signed-off-by: Lorenzo Pieralisi Signed-off-by: Bjorn Helgaas --- drivers/pci/endpoint/functions/pci-epf-test.c | 2 ++ drivers/pci/endpoint/pci-epc-core.c | 12 ++++++------ include/linux/pci-epc.h | 8 ++++---- include/linux/pci-epf.h | 1 + 4 files changed, 13 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/drivers/pci/endpoint/functions/pci-epf-test.c b/drivers/pci/endpoint/functions/pci-epf-test.c index e4e51d884553..7a1f3abfde48 100644 --- a/drivers/pci/endpoint/functions/pci-epf-test.c +++ b/drivers/pci/endpoint/functions/pci-epf-test.c @@ -834,6 +834,8 @@ static int pci_epf_test_bind(struct pci_epf *epf) linkup_notifier = epc_features->linkup_notifier; core_init_notifier = epc_features->core_init_notifier; test_reg_bar = pci_epc_get_first_free_bar(epc_features); + if (test_reg_bar < 0) + return -EINVAL; pci_epf_configure_bar(epf, epc_features); } diff --git a/drivers/pci/endpoint/pci-epc-core.c b/drivers/pci/endpoint/pci-epc-core.c index 1afe5d9afb0d..ea7e7465ce7a 100644 --- a/drivers/pci/endpoint/pci-epc-core.c +++ b/drivers/pci/endpoint/pci-epc-core.c @@ -90,8 +90,8 @@ EXPORT_SYMBOL_GPL(pci_epc_get); * Invoke to get the first unreserved BAR that can be used by the endpoint * function. For any incorrect value in reserved_bar return '0'. */ -unsigned int pci_epc_get_first_free_bar(const struct pci_epc_features - *epc_features) +enum pci_barno +pci_epc_get_first_free_bar(const struct pci_epc_features *epc_features) { return pci_epc_get_next_free_bar(epc_features, BAR_0); } @@ -105,13 +105,13 @@ EXPORT_SYMBOL_GPL(pci_epc_get_first_free_bar); * Invoke to get the next unreserved BAR starting from @bar that can be used * for endpoint function. For any incorrect value in reserved_bar return '0'. */ -unsigned int pci_epc_get_next_free_bar(const struct pci_epc_features - *epc_features, enum pci_barno bar) +enum pci_barno pci_epc_get_next_free_bar(const struct pci_epc_features + *epc_features, enum pci_barno bar) { unsigned long free_bar; if (!epc_features) - return 0; + return BAR_0; /* If 'bar - 1' is a 64-bit BAR, move to the next BAR */ if ((epc_features->bar_fixed_64bit << 1) & 1 << bar) @@ -126,7 +126,7 @@ unsigned int pci_epc_get_next_free_bar(const struct pci_epc_features free_bar = find_next_zero_bit(&free_bar, 6, bar); if (free_bar > 5) - return 0; + return NO_BAR; return free_bar; } diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h index cfe9b427e6b7..88d311bad984 100644 --- a/include/linux/pci-epc.h +++ b/include/linux/pci-epc.h @@ -201,10 +201,10 @@ int pci_epc_start(struct pci_epc *epc); void pci_epc_stop(struct pci_epc *epc); const struct pci_epc_features *pci_epc_get_features(struct pci_epc *epc, u8 func_no); -unsigned int pci_epc_get_first_free_bar(const struct pci_epc_features - *epc_features); -unsigned int pci_epc_get_next_free_bar(const struct pci_epc_features - *epc_features, enum pci_barno bar); +enum pci_barno +pci_epc_get_first_free_bar(const struct pci_epc_features *epc_features); +enum pci_barno pci_epc_get_next_free_bar(const struct pci_epc_features + *epc_features, enum pci_barno bar); struct pci_epc *pci_epc_get(const char *epc_name); void pci_epc_put(struct pci_epc *epc); diff --git a/include/linux/pci-epf.h b/include/linux/pci-epf.h index 6644ff3b0702..fa3aca43eb19 100644 --- a/include/linux/pci-epf.h +++ b/include/linux/pci-epf.h @@ -21,6 +21,7 @@ enum pci_notify_event { }; enum pci_barno { + NO_BAR = -1, BAR_0, BAR_1, BAR_2, -- cgit v1.2.3 From 7e5a51ebb321537c4209cdd0c54c4c19b3ef960d Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Tue, 2 Feb 2021 01:27:57 +0530 Subject: PCI: endpoint: Remove unused pci_epf_match_device() Remove unused pci_epf_match_device() function added in pci-epf-core.c Link: https://lore.kernel.org/r/20210201195809.7342-6-kishon@ti.com Signed-off-by: Kishon Vijay Abraham I Signed-off-by: Lorenzo Pieralisi Signed-off-by: Bjorn Helgaas --- drivers/pci/endpoint/pci-epf-core.c | 16 ---------------- include/linux/pci-epf.h | 2 -- 2 files changed, 18 deletions(-) (limited to 'include') diff --git a/drivers/pci/endpoint/pci-epf-core.c b/drivers/pci/endpoint/pci-epf-core.c index c977cf9dce56..e44a317a2a2a 100644 --- a/drivers/pci/endpoint/pci-epf-core.c +++ b/drivers/pci/endpoint/pci-epf-core.c @@ -282,22 +282,6 @@ struct pci_epf *pci_epf_create(const char *name) } EXPORT_SYMBOL_GPL(pci_epf_create); -const struct pci_epf_device_id * -pci_epf_match_device(const struct pci_epf_device_id *id, struct pci_epf *epf) -{ - if (!id || !epf) - return NULL; - - while (*id->name) { - if (strcmp(epf->name, id->name) == 0) - return id; - id++; - } - - return NULL; -} -EXPORT_SYMBOL_GPL(pci_epf_match_device); - static void pci_epf_dev_release(struct device *dev) { struct pci_epf *epf = to_pci_epf(dev); diff --git a/include/linux/pci-epf.h b/include/linux/pci-epf.h index fa3aca43eb19..f373a134ac04 100644 --- a/include/linux/pci-epf.h +++ b/include/linux/pci-epf.h @@ -165,8 +165,6 @@ static inline void *epf_get_drvdata(struct pci_epf *epf) return dev_get_drvdata(&epf->dev); } -const struct pci_epf_device_id * -pci_epf_match_device(const struct pci_epf_device_id *id, struct pci_epf *epf); struct pci_epf *pci_epf_create(const char *name); void pci_epf_destroy(struct pci_epf *epf); int __pci_epf_register_driver(struct pci_epf_driver *driver, -- cgit v1.2.3 From 63840ff5322373d665b2b9c59cd64233d5f0691e Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Tue, 2 Feb 2021 01:27:58 +0530 Subject: PCI: endpoint: Add support to associate secondary EPC with EPF In the case of standard endpoint functions, only one endpoint controller (EPC) will be associated with an endpoint function (EPF). However for providing NTB (non transparent bridge) functionality, two EPCs should be associated with a single EPF. Add support to associate secondary EPC with EPF. This is in preparation for adding NTB endpoint function driver. Link: https://lore.kernel.org/r/20210201195809.7342-7-kishon@ti.com Signed-off-by: Kishon Vijay Abraham I Signed-off-by: Lorenzo Pieralisi Signed-off-by: Bjorn Helgaas --- drivers/pci/endpoint/functions/pci-epf-test.c | 11 ++++-- drivers/pci/endpoint/pci-ep-cfs.c | 6 +-- drivers/pci/endpoint/pci-epc-core.c | 47 ++++++++++++++++------ drivers/pci/endpoint/pci-epf-core.c | 57 +++++++++++++++++++-------- include/linux/pci-epc.h | 25 +++++++++++- include/linux/pci-epf.h | 17 +++++++- 6 files changed, 125 insertions(+), 38 deletions(-) (limited to 'include') diff --git a/drivers/pci/endpoint/functions/pci-epf-test.c b/drivers/pci/endpoint/functions/pci-epf-test.c index 7a1f3abfde48..c0ac4e9cbe72 100644 --- a/drivers/pci/endpoint/functions/pci-epf-test.c +++ b/drivers/pci/endpoint/functions/pci-epf-test.c @@ -619,7 +619,8 @@ static void pci_epf_test_unbind(struct pci_epf *epf) if (epf_test->reg[bar]) { pci_epc_clear_bar(epc, epf->func_no, epf_bar); - pci_epf_free_space(epf, epf_test->reg[bar], bar); + pci_epf_free_space(epf, epf_test->reg[bar], bar, + PRIMARY_INTERFACE); } } } @@ -651,7 +652,8 @@ static int pci_epf_test_set_bar(struct pci_epf *epf) ret = pci_epc_set_bar(epc, epf->func_no, epf_bar); if (ret) { - pci_epf_free_space(epf, epf_test->reg[bar], bar); + pci_epf_free_space(epf, epf_test->reg[bar], bar, + PRIMARY_INTERFACE); dev_err(dev, "Failed to set BAR%d\n", bar); if (bar == test_reg_bar) return ret; @@ -771,7 +773,7 @@ static int pci_epf_test_alloc_space(struct pci_epf *epf) } base = pci_epf_alloc_space(epf, test_reg_size, test_reg_bar, - epc_features->align); + epc_features->align, PRIMARY_INTERFACE); if (!base) { dev_err(dev, "Failed to allocated register space\n"); return -ENOMEM; @@ -789,7 +791,8 @@ static int pci_epf_test_alloc_space(struct pci_epf *epf) continue; base = pci_epf_alloc_space(epf, bar_size[bar], bar, - epc_features->align); + epc_features->align, + PRIMARY_INTERFACE); if (!base) dev_err(dev, "Failed to allocate space for BAR%d\n", bar); diff --git a/drivers/pci/endpoint/pci-ep-cfs.c b/drivers/pci/endpoint/pci-ep-cfs.c index 3710adf51912..6ca9e2f92460 100644 --- a/drivers/pci/endpoint/pci-ep-cfs.c +++ b/drivers/pci/endpoint/pci-ep-cfs.c @@ -94,13 +94,13 @@ static int pci_epc_epf_link(struct config_item *epc_item, struct pci_epc *epc = epc_group->epc; struct pci_epf *epf = epf_group->epf; - ret = pci_epc_add_epf(epc, epf); + ret = pci_epc_add_epf(epc, epf, PRIMARY_INTERFACE); if (ret) return ret; ret = pci_epf_bind(epf); if (ret) { - pci_epc_remove_epf(epc, epf); + pci_epc_remove_epf(epc, epf, PRIMARY_INTERFACE); return ret; } @@ -120,7 +120,7 @@ static void pci_epc_epf_unlink(struct config_item *epc_item, epc = epc_group->epc; epf = epf_group->epf; pci_epf_unbind(epf); - pci_epc_remove_epf(epc, epf); + pci_epc_remove_epf(epc, epf, PRIMARY_INTERFACE); } static struct configfs_item_operations pci_epc_item_ops = { diff --git a/drivers/pci/endpoint/pci-epc-core.c b/drivers/pci/endpoint/pci-epc-core.c index ea7e7465ce7a..3693eca5b030 100644 --- a/drivers/pci/endpoint/pci-epc-core.c +++ b/drivers/pci/endpoint/pci-epc-core.c @@ -493,21 +493,28 @@ EXPORT_SYMBOL_GPL(pci_epc_write_header); * pci_epc_add_epf() - bind PCI endpoint function to an endpoint controller * @epc: the EPC device to which the endpoint function should be added * @epf: the endpoint function to be added + * @type: Identifies if the EPC is connected to the primary or secondary + * interface of EPF * * A PCI endpoint device can have one or more functions. In the case of PCIe, * the specification allows up to 8 PCIe endpoint functions. Invoke * pci_epc_add_epf() to add a PCI endpoint function to an endpoint controller. */ -int pci_epc_add_epf(struct pci_epc *epc, struct pci_epf *epf) +int pci_epc_add_epf(struct pci_epc *epc, struct pci_epf *epf, + enum pci_epc_interface_type type) { + struct list_head *list; u32 func_no; int ret = 0; - if (epf->epc) + if (IS_ERR_OR_NULL(epc)) + return -EINVAL; + + if (type == PRIMARY_INTERFACE && epf->epc) return -EBUSY; - if (IS_ERR(epc)) - return -EINVAL; + if (type == SECONDARY_INTERFACE && epf->sec_epc) + return -EBUSY; mutex_lock(&epc->lock); func_no = find_first_zero_bit(&epc->function_num_map, @@ -524,11 +531,17 @@ int pci_epc_add_epf(struct pci_epc *epc, struct pci_epf *epf) } set_bit(func_no, &epc->function_num_map); - epf->func_no = func_no; - epf->epc = epc; - - list_add_tail(&epf->list, &epc->pci_epf); + if (type == PRIMARY_INTERFACE) { + epf->func_no = func_no; + epf->epc = epc; + list = &epf->list; + } else { + epf->sec_epc_func_no = func_no; + epf->sec_epc = epc; + list = &epf->sec_epc_list; + } + list_add_tail(list, &epc->pci_epf); ret: mutex_unlock(&epc->lock); @@ -543,14 +556,26 @@ EXPORT_SYMBOL_GPL(pci_epc_add_epf); * * Invoke to remove PCI endpoint function from the endpoint controller. */ -void pci_epc_remove_epf(struct pci_epc *epc, struct pci_epf *epf) +void pci_epc_remove_epf(struct pci_epc *epc, struct pci_epf *epf, + enum pci_epc_interface_type type) { + struct list_head *list; + u32 func_no = 0; + if (!epc || IS_ERR(epc) || !epf) return; + if (type == PRIMARY_INTERFACE) { + func_no = epf->func_no; + list = &epf->list; + } else { + func_no = epf->sec_epc_func_no; + list = &epf->sec_epc_list; + } + mutex_lock(&epc->lock); - clear_bit(epf->func_no, &epc->function_num_map); - list_del(&epf->list); + clear_bit(func_no, &epc->function_num_map); + list_del(list); epf->epc = NULL; mutex_unlock(&epc->lock); } diff --git a/drivers/pci/endpoint/pci-epf-core.c b/drivers/pci/endpoint/pci-epf-core.c index e44a317a2a2a..79329ec6373c 100644 --- a/drivers/pci/endpoint/pci-epf-core.c +++ b/drivers/pci/endpoint/pci-epf-core.c @@ -74,24 +74,37 @@ EXPORT_SYMBOL_GPL(pci_epf_bind); * @epf: the EPF device from whom to free the memory * @addr: the virtual address of the PCI EPF register space * @bar: the BAR number corresponding to the register space + * @type: Identifies if the allocated space is for primary EPC or secondary EPC * * Invoke to free the allocated PCI EPF register space. */ -void pci_epf_free_space(struct pci_epf *epf, void *addr, enum pci_barno bar) +void pci_epf_free_space(struct pci_epf *epf, void *addr, enum pci_barno bar, + enum pci_epc_interface_type type) { struct device *dev = epf->epc->dev.parent; + struct pci_epf_bar *epf_bar; + struct pci_epc *epc; if (!addr) return; - dma_free_coherent(dev, epf->bar[bar].size, addr, - epf->bar[bar].phys_addr); + if (type == PRIMARY_INTERFACE) { + epc = epf->epc; + epf_bar = epf->bar; + } else { + epc = epf->sec_epc; + epf_bar = epf->sec_epc_bar; + } + + dev = epc->dev.parent; + dma_free_coherent(dev, epf_bar[bar].size, addr, + epf_bar[bar].phys_addr); - epf->bar[bar].phys_addr = 0; - epf->bar[bar].addr = NULL; - epf->bar[bar].size = 0; - epf->bar[bar].barno = 0; - epf->bar[bar].flags = 0; + epf_bar[bar].phys_addr = 0; + epf_bar[bar].addr = NULL; + epf_bar[bar].size = 0; + epf_bar[bar].barno = 0; + epf_bar[bar].flags = 0; } EXPORT_SYMBOL_GPL(pci_epf_free_space); @@ -101,15 +114,18 @@ EXPORT_SYMBOL_GPL(pci_epf_free_space); * @size: the size of the memory that has to be allocated * @bar: the BAR number corresponding to the allocated register space * @align: alignment size for the allocation region + * @type: Identifies if the allocation is for primary EPC or secondary EPC * * Invoke to allocate memory for the PCI EPF register space. */ void *pci_epf_alloc_space(struct pci_epf *epf, size_t size, enum pci_barno bar, - size_t align) + size_t align, enum pci_epc_interface_type type) { - void *space; - struct device *dev = epf->epc->dev.parent; + struct pci_epf_bar *epf_bar; dma_addr_t phys_addr; + struct pci_epc *epc; + struct device *dev; + void *space; if (size < 128) size = 128; @@ -119,17 +135,26 @@ void *pci_epf_alloc_space(struct pci_epf *epf, size_t size, enum pci_barno bar, else size = roundup_pow_of_two(size); + if (type == PRIMARY_INTERFACE) { + epc = epf->epc; + epf_bar = epf->bar; + } else { + epc = epf->sec_epc; + epf_bar = epf->sec_epc_bar; + } + + dev = epc->dev.parent; space = dma_alloc_coherent(dev, size, &phys_addr, GFP_KERNEL); if (!space) { dev_err(dev, "failed to allocate mem space\n"); return NULL; } - epf->bar[bar].phys_addr = phys_addr; - epf->bar[bar].addr = space; - epf->bar[bar].size = size; - epf->bar[bar].barno = bar; - epf->bar[bar].flags |= upper_32_bits(size) ? + epf_bar[bar].phys_addr = phys_addr; + epf_bar[bar].addr = space; + epf_bar[bar].size = size; + epf_bar[bar].barno = bar; + epf_bar[bar].flags |= upper_32_bits(size) ? PCI_BASE_ADDRESS_MEM_TYPE_64 : PCI_BASE_ADDRESS_MEM_TYPE_32; diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h index 88d311bad984..d9cb3944fb87 100644 --- a/include/linux/pci-epc.h +++ b/include/linux/pci-epc.h @@ -13,6 +13,12 @@ struct pci_epc; +enum pci_epc_interface_type { + UNKNOWN_INTERFACE = -1, + PRIMARY_INTERFACE, + SECONDARY_INTERFACE, +}; + enum pci_epc_irq_type { PCI_EPC_IRQ_UNKNOWN, PCI_EPC_IRQ_LEGACY, @@ -20,6 +26,19 @@ enum pci_epc_irq_type { PCI_EPC_IRQ_MSIX, }; +static inline const char * +pci_epc_interface_string(enum pci_epc_interface_type type) +{ + switch (type) { + case PRIMARY_INTERFACE: + return "primary"; + case SECONDARY_INTERFACE: + return "secondary"; + default: + return "UNKNOWN interface"; + } +} + /** * struct pci_epc_ops - set of function pointers for performing EPC operations * @write_header: ops to populate configuration space header @@ -175,10 +194,12 @@ __pci_epc_create(struct device *dev, const struct pci_epc_ops *ops, struct module *owner); void devm_pci_epc_destroy(struct device *dev, struct pci_epc *epc); void pci_epc_destroy(struct pci_epc *epc); -int pci_epc_add_epf(struct pci_epc *epc, struct pci_epf *epf); +int pci_epc_add_epf(struct pci_epc *epc, struct pci_epf *epf, + enum pci_epc_interface_type type); void pci_epc_linkup(struct pci_epc *epc); void pci_epc_init_notify(struct pci_epc *epc); -void pci_epc_remove_epf(struct pci_epc *epc, struct pci_epf *epf); +void pci_epc_remove_epf(struct pci_epc *epc, struct pci_epf *epf, + enum pci_epc_interface_type type); int pci_epc_write_header(struct pci_epc *epc, u8 func_no, struct pci_epf_header *hdr); int pci_epc_set_bar(struct pci_epc *epc, u8 func_no, diff --git a/include/linux/pci-epf.h b/include/linux/pci-epf.h index f373a134ac04..1dc66824f5a8 100644 --- a/include/linux/pci-epf.h +++ b/include/linux/pci-epf.h @@ -14,6 +14,7 @@ #include struct pci_epf; +enum pci_epc_interface_type; enum pci_notify_event { CORE_INIT, @@ -119,6 +120,11 @@ struct pci_epf_bar { * @list: to add pci_epf as a list of PCI endpoint functions to pci_epc * @nb: notifier block to notify EPF of any EPC events (like linkup) * @lock: mutex to protect pci_epf_ops + * @sec_epc: the secondary EPC device to which this EPF device is bound + * @sec_epc_list: to add pci_epf as list of PCI endpoint functions to secondary + * EPC device + * @sec_epc_bar: represents the BAR of EPF device associated with secondary EPC + * @sec_epc_func_no: unique (physical) function number within the secondary EPC */ struct pci_epf { struct device dev; @@ -135,6 +141,12 @@ struct pci_epf { struct notifier_block nb; /* mutex to protect against concurrent access of pci_epf_ops */ struct mutex lock; + + /* Below members are to attach secondary EPC to an endpoint function */ + struct pci_epc *sec_epc; + struct list_head sec_epc_list; + struct pci_epf_bar sec_epc_bar[6]; + u8 sec_epc_func_no; }; /** @@ -171,8 +183,9 @@ int __pci_epf_register_driver(struct pci_epf_driver *driver, struct module *owner); void pci_epf_unregister_driver(struct pci_epf_driver *driver); void *pci_epf_alloc_space(struct pci_epf *epf, size_t size, enum pci_barno bar, - size_t align); -void pci_epf_free_space(struct pci_epf *epf, void *addr, enum pci_barno bar); + size_t align, enum pci_epc_interface_type type); +void pci_epf_free_space(struct pci_epf *epf, void *addr, enum pci_barno bar, + enum pci_epc_interface_type type); int pci_epf_bind(struct pci_epf *epf); void pci_epf_unbind(struct pci_epf *epf); #endif /* __LINUX_PCI_EPF_H */ -- cgit v1.2.3 From 87d5972e476f6c4e98a0abce713c54c6f40661b0 Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Tue, 2 Feb 2021 01:28:00 +0530 Subject: PCI: endpoint: Add pci_epc_ops to map MSI IRQ Add pci_epc_ops to map physical address to MSI address and return MSI data. The physical address is an address in the outbound region. This is required to implement doorbell functionality of NTB (non-transparent bridge) wherein EPC on either side of the interface (primary and secondary) can directly write to the physical address (in outbound region) of the other interface to ring doorbell using MSI. Link: https://lore.kernel.org/r/20210201195809.7342-9-kishon@ti.com Signed-off-by: Kishon Vijay Abraham I Signed-off-by: Lorenzo Pieralisi Signed-off-by: Bjorn Helgaas --- drivers/pci/endpoint/pci-epc-core.c | 41 +++++++++++++++++++++++++++++++++++++ include/linux/pci-epc.h | 8 ++++++++ 2 files changed, 49 insertions(+) (limited to 'include') diff --git a/drivers/pci/endpoint/pci-epc-core.c b/drivers/pci/endpoint/pci-epc-core.c index 3693eca5b030..cc8f9eb2b177 100644 --- a/drivers/pci/endpoint/pci-epc-core.c +++ b/drivers/pci/endpoint/pci-epc-core.c @@ -230,6 +230,47 @@ int pci_epc_raise_irq(struct pci_epc *epc, u8 func_no, } EXPORT_SYMBOL_GPL(pci_epc_raise_irq); +/** + * pci_epc_map_msi_irq() - Map physical address to MSI address and return + * MSI data + * @epc: the EPC device which has the MSI capability + * @func_no: the physical endpoint function number in the EPC device + * @phys_addr: the physical address of the outbound region + * @interrupt_num: the MSI interrupt number + * @entry_size: Size of Outbound address region for each interrupt + * @msi_data: the data that should be written in order to raise MSI interrupt + * with interrupt number as 'interrupt num' + * @msi_addr_offset: Offset of MSI address from the aligned outbound address + * to which the MSI address is mapped + * + * Invoke to map physical address to MSI address and return MSI data. The + * physical address should be an address in the outbound region. This is + * required to implement doorbell functionality of NTB wherein EPC on either + * side of the interface (primary and secondary) can directly write to the + * physical address (in outbound region) of the other interface to ring + * doorbell. + */ +int pci_epc_map_msi_irq(struct pci_epc *epc, u8 func_no, phys_addr_t phys_addr, + u8 interrupt_num, u32 entry_size, u32 *msi_data, + u32 *msi_addr_offset) +{ + int ret; + + if (IS_ERR_OR_NULL(epc)) + return -EINVAL; + + if (!epc->ops->map_msi_irq) + return -EINVAL; + + mutex_lock(&epc->lock); + ret = epc->ops->map_msi_irq(epc, func_no, phys_addr, interrupt_num, + entry_size, msi_data, msi_addr_offset); + mutex_unlock(&epc->lock); + + return ret; +} +EXPORT_SYMBOL_GPL(pci_epc_map_msi_irq); + /** * pci_epc_get_msi() - get the number of MSI interrupt numbers allocated * @epc: the EPC device to which MSI interrupts was requested diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h index d9cb3944fb87..b82c9b100e97 100644 --- a/include/linux/pci-epc.h +++ b/include/linux/pci-epc.h @@ -55,6 +55,7 @@ pci_epc_interface_string(enum pci_epc_interface_type type) * @get_msix: ops to get the number of MSI-X interrupts allocated by the RC * from the MSI-X capability register * @raise_irq: ops to raise a legacy, MSI or MSI-X interrupt + * @map_msi_irq: ops to map physical address to MSI address and return MSI data * @start: ops to start the PCI link * @stop: ops to stop the PCI link * @owner: the module owner containing the ops @@ -77,6 +78,10 @@ struct pci_epc_ops { int (*get_msix)(struct pci_epc *epc, u8 func_no); int (*raise_irq)(struct pci_epc *epc, u8 func_no, enum pci_epc_irq_type type, u16 interrupt_num); + int (*map_msi_irq)(struct pci_epc *epc, u8 func_no, + phys_addr_t phys_addr, u8 interrupt_num, + u32 entry_size, u32 *msi_data, + u32 *msi_addr_offset); int (*start)(struct pci_epc *epc); void (*stop)(struct pci_epc *epc); const struct pci_epc_features* (*get_features)(struct pci_epc *epc, @@ -216,6 +221,9 @@ int pci_epc_get_msi(struct pci_epc *epc, u8 func_no); int pci_epc_set_msix(struct pci_epc *epc, u8 func_no, u16 interrupts, enum pci_barno, u32 offset); int pci_epc_get_msix(struct pci_epc *epc, u8 func_no); +int pci_epc_map_msi_irq(struct pci_epc *epc, u8 func_no, + phys_addr_t phys_addr, u8 interrupt_num, + u32 entry_size, u32 *msi_data, u32 *msi_addr_offset); int pci_epc_raise_irq(struct pci_epc *epc, u8 func_no, enum pci_epc_irq_type type, u16 interrupt_num); int pci_epc_start(struct pci_epc *epc); -- cgit v1.2.3 From 256ae475201b16fd69e00dd6c2d14035e4ea5745 Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Tue, 2 Feb 2021 01:28:01 +0530 Subject: PCI: endpoint: Add pci_epf_ops to expose function-specific attrs In addition to the attributes that are generic across function drivers documented in Documentation/PCI/endpoint/pci-endpoint-cfs.rst, there could be function-specific attributes that has to be exposed by the function driver to be configured by the user. Add ->add_cfs() in pci_epf_ops to be populated by the function driver if it has to expose any function-specific attributes and pci_epf_type_add_cfs() to be invoked by pci-ep-cfs.c when sub-directory to main function directory is created. Link: https://lore.kernel.org/r/20210201195809.7342-10-kishon@ti.com Signed-off-by: Kishon Vijay Abraham I Signed-off-by: Lorenzo Pieralisi Signed-off-by: Bjorn Helgaas --- drivers/pci/endpoint/pci-epf-core.c | 32 ++++++++++++++++++++++++++++++++ include/linux/pci-epf.h | 5 +++++ 2 files changed, 37 insertions(+) (limited to 'include') diff --git a/drivers/pci/endpoint/pci-epf-core.c b/drivers/pci/endpoint/pci-epf-core.c index 79329ec6373c..7646c8660d42 100644 --- a/drivers/pci/endpoint/pci-epf-core.c +++ b/drivers/pci/endpoint/pci-epf-core.c @@ -20,6 +20,38 @@ static DEFINE_MUTEX(pci_epf_mutex); static struct bus_type pci_epf_bus_type; static const struct device_type pci_epf_type; +/** + * pci_epf_type_add_cfs() - Help function drivers to expose function specific + * attributes in configfs + * @epf: the EPF device that has to be configured using configfs + * @group: the parent configfs group (corresponding to entries in + * pci_epf_device_id) + * + * Invoke to expose function specific attributes in configfs. If the function + * driver does not have anything to expose (attributes configured by user), + * return NULL. + */ +struct config_group *pci_epf_type_add_cfs(struct pci_epf *epf, + struct config_group *group) +{ + struct config_group *epf_type_group; + + if (!epf->driver) { + dev_err(&epf->dev, "epf device not bound to driver\n"); + return NULL; + } + + if (!epf->driver->ops->add_cfs) + return NULL; + + mutex_lock(&epf->lock); + epf_type_group = epf->driver->ops->add_cfs(epf, group); + mutex_unlock(&epf->lock); + + return epf_type_group; +} +EXPORT_SYMBOL_GPL(pci_epf_type_add_cfs); + /** * pci_epf_unbind() - Notify the function driver that the binding between the * EPF device and EPC device has been lost diff --git a/include/linux/pci-epf.h b/include/linux/pci-epf.h index 1dc66824f5a8..b241e7dd171f 100644 --- a/include/linux/pci-epf.h +++ b/include/linux/pci-epf.h @@ -62,10 +62,13 @@ struct pci_epf_header { * @bind: ops to perform when a EPC device has been bound to EPF device * @unbind: ops to perform when a binding has been lost between a EPC device * and EPF device + * @add_cfs: ops to initialize function specific configfs attributes */ struct pci_epf_ops { int (*bind)(struct pci_epf *epf); void (*unbind)(struct pci_epf *epf); + struct config_group *(*add_cfs)(struct pci_epf *epf, + struct config_group *group); }; /** @@ -188,4 +191,6 @@ void pci_epf_free_space(struct pci_epf *epf, void *addr, enum pci_barno bar, enum pci_epc_interface_type type); int pci_epf_bind(struct pci_epf *epf); void pci_epf_unbind(struct pci_epf *epf); +struct config_group *pci_epf_type_add_cfs(struct pci_epf *epf, + struct config_group *group); #endif /* __LINUX_PCI_EPF_H */ -- cgit v1.2.3 From 38ad827e3bc0f0e94628ee1d8dc31e778d9be40f Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Tue, 2 Feb 2021 01:28:02 +0530 Subject: PCI: endpoint: Allow user to create sub-directory of 'EPF Device' directory Documentation/PCI/endpoint/pci-endpoint-cfs.rst explains how a user has to create a directory in-order to create a 'EPF Device' that can be configured/probed by 'EPF Driver'. Allow user to create a sub-directory of 'EPF Device' directory for any function specific attributes that has to be exposed to the user. Link: https://lore.kernel.org/r/20210201195809.7342-11-kishon@ti.com Signed-off-by: Kishon Vijay Abraham I Signed-off-by: Lorenzo Pieralisi Signed-off-by: Bjorn Helgaas --- drivers/pci/endpoint/pci-ep-cfs.c | 23 +++++++++++++++++++++++ include/linux/pci-epf.h | 3 +++ 2 files changed, 26 insertions(+) (limited to 'include') diff --git a/drivers/pci/endpoint/pci-ep-cfs.c b/drivers/pci/endpoint/pci-ep-cfs.c index 8f750961d6ab..f3a8b833b479 100644 --- a/drivers/pci/endpoint/pci-ep-cfs.c +++ b/drivers/pci/endpoint/pci-ep-cfs.c @@ -490,7 +490,29 @@ static struct configfs_item_operations pci_epf_ops = { .release = pci_epf_release, }; +static struct config_group *pci_epf_type_make(struct config_group *group, + const char *name) +{ + struct pci_epf_group *epf_group = to_pci_epf_group(&group->cg_item); + struct config_group *epf_type_group; + + epf_type_group = pci_epf_type_add_cfs(epf_group->epf, group); + return epf_type_group; +} + +static void pci_epf_type_drop(struct config_group *group, + struct config_item *item) +{ + config_item_put(item); +} + +static struct configfs_group_operations pci_epf_type_group_ops = { + .make_group = &pci_epf_type_make, + .drop_item = &pci_epf_type_drop, +}; + static const struct config_item_type pci_epf_type = { + .ct_group_ops = &pci_epf_type_group_ops, .ct_item_ops = &pci_epf_ops, .ct_attrs = pci_epf_attrs, .ct_owner = THIS_MODULE, @@ -553,6 +575,7 @@ static struct config_group *pci_epf_make(struct config_group *group, goto free_name; } + epf->group = &epf_group->group; epf_group->epf = epf; kfree(epf_name); diff --git a/include/linux/pci-epf.h b/include/linux/pci-epf.h index b241e7dd171f..6833e2160ef1 100644 --- a/include/linux/pci-epf.h +++ b/include/linux/pci-epf.h @@ -9,6 +9,7 @@ #ifndef __LINUX_PCI_EPF_H #define __LINUX_PCI_EPF_H +#include #include #include #include @@ -128,6 +129,7 @@ struct pci_epf_bar { * EPC device * @sec_epc_bar: represents the BAR of EPF device associated with secondary EPC * @sec_epc_func_no: unique (physical) function number within the secondary EPC + * @group: configfs group associated with the EPF device */ struct pci_epf { struct device dev; @@ -150,6 +152,7 @@ struct pci_epf { struct list_head sec_epc_list; struct pci_epf_bar sec_epc_bar[6]; u8 sec_epc_func_no; + struct config_group *group; }; /** -- cgit v1.2.3 From 599f86872f9ce8a0a0bd111a23442b18e8ee7059 Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Tue, 2 Feb 2021 01:28:06 +0530 Subject: PCI: Add TI J721E device to PCI IDs Add TI J721E device to the PCI ID database. Since this device has a configurable PCIe endpoint, it could be used with different drivers. Link: https://lore.kernel.org/r/20210201195809.7342-15-kishon@ti.com Signed-off-by: Kishon Vijay Abraham I Signed-off-by: Lorenzo Pieralisi Signed-off-by: Bjorn Helgaas --- drivers/misc/pci_endpoint_test.c | 1 - include/linux/pci_ids.h | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/misc/pci_endpoint_test.c b/drivers/misc/pci_endpoint_test.c index eff481ce08ee..1b2868ca4f2a 100644 --- a/drivers/misc/pci_endpoint_test.c +++ b/drivers/misc/pci_endpoint_test.c @@ -68,7 +68,6 @@ #define PCI_ENDPOINT_TEST_FLAGS 0x2c #define FLAG_USE_DMA BIT(0) -#define PCI_DEVICE_ID_TI_J721E 0xb00d #define PCI_DEVICE_ID_TI_AM654 0xb00c #define PCI_DEVICE_ID_LS1088A 0x80c0 diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index d8156a5dbee8..f968fcda338e 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -881,6 +881,7 @@ #define PCI_DEVICE_ID_TI_X620 0xac8d #define PCI_DEVICE_ID_TI_X420 0xac8e #define PCI_DEVICE_ID_TI_XX20_FM 0xac8f +#define PCI_DEVICE_ID_TI_J721E 0xb00d #define PCI_DEVICE_ID_TI_DRA74x 0xb500 #define PCI_DEVICE_ID_TI_DRA72x 0xb501 -- cgit v1.2.3 From cf6acb8bdb1d829b85a4daa2944bf9e71c93f4b9 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Mon, 22 Feb 2021 18:01:54 +0100 Subject: s390/cpumf: Add support for complete counter set extraction Add support to the CPU Measurement counter facility device driver to extract complete counter sets per CPU and per counter set from user space. This includes a new device named /dev/hwctr and support for the device driver functions open, close and ioctl. Other functions are not supported. The ioctl command supports 3 subcommands: S390_HWCTR_START: enables counter sets on a list of CPUs. S390_HWCTR_STOP: disables counter sets on a list of CPUs. S390_HWCTR_READ: reads counter sets on a list of CPUs. The ioctl(..., S390_HWCTR_READ, ...) is the only subcommand which returns data. It requires member data_bytes to be positive and indicates the maximum amount of data available to store counter set data. The other ioctl() subcommands do not use this member and it should be set to zero. The S390_HWCTR_READ subcommand returns the following data: The cpuset data is flattened using the following scheme, stored in member data: 0x0 0x8 0xc 0x10 0x10 0x18 0x20 0x28 0xU-1 +---------+-----+---------+-----+---------+-----+-----+------+------+ | no_cpus | cpu | no_sets | set | no_cnts | cv1 | cv2 | .... | cv_n | +---------+-----+---------+-----+---------+-----+-----+------+------+ 0xU 0xU+4 0xU+8 0xU+10 0xV-1 +-----+---------+-----+-----+------+------+ | set | no_cnts | cv1 | cv2 | .... | cv_n | +-----+---------+-----+-----+------+------+ 0xV 0xV+4 0xV+8 0xV+c +-----+---------+-----+---------+-----+-----+------+------+ | cpu | no_sets | set | no_cnts | cv1 | cv2 | .... | cv_n | +-----+---------+-----+---------+-----+-----+------+------+ U and V denote arbitrary hexadezimal addresses. The first integer represents the number of CPUs data was extracted from. This is followed by CPU number and number of counter sets extracted. Both are two integer values. This is followed by the set identifer and number of counters extracted. Both are two integer values. This is followed by the counter values, each element is eight bytes in size. The S390_HWCTR_READ ioctl subcommand is also limited to one call per minute. This ensures that an application does not read out the counter sets too often and reduces the overall CPU performance. The complete counter set extraction is an expensive operation. Reviewed-by: Sumanth Korikkar Signed-off-by: Thomas Richter Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/include/uapi/asm/perf_cpum_cf_diag.h | 51 +++ arch/s390/kernel/perf_cpum_cf_diag.c | 548 +++++++++++++++++++++++-- include/linux/cpuhotplug.h | 1 + 3 files changed, 577 insertions(+), 23 deletions(-) create mode 100644 arch/s390/include/uapi/asm/perf_cpum_cf_diag.h (limited to 'include') diff --git a/arch/s390/include/uapi/asm/perf_cpum_cf_diag.h b/arch/s390/include/uapi/asm/perf_cpum_cf_diag.h new file mode 100644 index 000000000000..3d8284b95f87 --- /dev/null +++ b/arch/s390/include/uapi/asm/perf_cpum_cf_diag.h @@ -0,0 +1,51 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Copyright IBM Corp. 2021 + * Interface implementation for communication with the CPU Measurement + * counter facility device driver. + * + * Author(s): Thomas Richter + * + * Define for ioctl() commands to communicate with the CPU Measurement + * counter facility device driver. + */ + +#ifndef _PERF_CPUM_CF_DIAG_H +#define _PERF_CPUM_CF_DIAG_H + +#include +#include + +#define S390_HWCTR_DEVICE "hwctr" +#define S390_HWCTR_START_VERSION 1 + +struct s390_ctrset_start { /* Set CPUs to operate on */ + __u64 version; /* Version of interface */ + __u64 data_bytes; /* # of bytes required */ + __u64 cpumask_len; /* Length of CPU mask in bytes */ + __u64 *cpumask; /* Pointer to CPU mask */ + __u64 counter_sets; /* Bit mask of counter sets to get */ +}; + +struct s390_ctrset_setdata { /* Counter set data */ + __u32 set; /* Counter set number */ + __u32 no_cnts; /* # of counters stored in cv[] */ + __u64 cv[0]; /* Counter values (variable length) */ +}; + +struct s390_ctrset_cpudata { /* Counter set data per CPU */ + __u32 cpu_nr; /* CPU number */ + __u32 no_sets; /* # of counters sets in data[] */ + struct s390_ctrset_setdata data[0]; +}; + +struct s390_ctrset_read { /* Structure to get all ctr sets */ + __u64 no_cpus; /* Total # of CPUs data taken from */ + struct s390_ctrset_cpudata data[0]; +}; + +#define S390_HWCTR_MAGIC 'C' /* Random magic # for ioctls */ +#define S390_HWCTR_START _IOWR(S390_HWCTR_MAGIC, 1, struct s390_ctrset_start) +#define S390_HWCTR_STOP _IO(S390_HWCTR_MAGIC, 2) +#define S390_HWCTR_READ _IOWR(S390_HWCTR_MAGIC, 3, struct s390_ctrset_read) +#endif diff --git a/arch/s390/kernel/perf_cpum_cf_diag.c b/arch/s390/kernel/perf_cpum_cf_diag.c index b5c86fb70d63..db4877bbb9aa 100644 --- a/arch/s390/kernel/perf_cpum_cf_diag.c +++ b/arch/s390/kernel/perf_cpum_cf_diag.c @@ -2,7 +2,7 @@ /* * Performance event support for s390x - CPU-measurement Counter Sets * - * Copyright IBM Corp. 2019 + * Copyright IBM Corp. 2019, 2021 * Author(s): Hendrik Brueckner * Thomas Richer */ @@ -17,6 +17,8 @@ #include #include #include +#include +#include #include #include @@ -24,15 +26,20 @@ #include #include -#define CF_DIAG_CTRSET_DEF 0xfeef /* Counter set header mark */ +#include +#define CF_DIAG_CTRSET_DEF 0xfeef /* Counter set header mark */ +#define CF_DIAG_MIN_INTERVAL 60 /* Minimum counter set read */ + /* interval in seconds */ +static unsigned long cf_diag_interval = CF_DIAG_MIN_INTERVAL; static unsigned int cf_diag_cpu_speed; static debug_info_t *cf_diag_dbg; -struct cf_diag_csd { /* Counter set data per CPU */ +struct cf_diag_csd { /* Counter set data per CPU */ size_t used; /* Bytes used in data/start */ unsigned char start[PAGE_SIZE]; /* Counter set at event start */ unsigned char data[PAGE_SIZE]; /* Counter set at event delete */ + unsigned int sets; /* # Counter set saved in data */ }; static DEFINE_PER_CPU(struct cf_diag_csd, cf_diag_csd); @@ -178,18 +185,35 @@ static void cf_diag_disable(struct pmu *pmu) /* Number of perf events counting hardware events */ static atomic_t cf_diag_events = ATOMIC_INIT(0); +/* Used to avoid races in calling reserve/release_cpumf_hardware */ +static DEFINE_MUTEX(cf_diag_reserve_mutex); /* Release the PMU if event is the last perf event */ static void cf_diag_perf_event_destroy(struct perf_event *event) { debug_sprintf_event(cf_diag_dbg, 5, "%s event %p cpu %d cf_diag_events %d\n", - __func__, event, event->cpu, + __func__, event, smp_processor_id(), atomic_read(&cf_diag_events)); if (atomic_dec_return(&cf_diag_events) == 0) __kernel_cpumcf_end(); } +static int get_authctrsets(void) +{ + struct cpu_cf_events *cpuhw; + unsigned long auth = 0; + enum cpumf_ctr_set i; + + cpuhw = &get_cpu_var(cpu_cf_events); + for (i = CPUMF_CTR_SET_BASIC; i < CPUMF_CTR_SET_MAX; ++i) { + if (cpuhw->info.auth_ctl & cpumf_ctr_ctl[i]) + auth |= cpumf_ctr_ctl[i]; + } + put_cpu_var(cpu_cf_events); + return auth; +} + /* Setup the event. Test for authorized counter sets and only include counter * sets which are authorized at the time of the setup. Including unauthorized * counter sets result in specification exception (and panic). @@ -197,15 +221,12 @@ static void cf_diag_perf_event_destroy(struct perf_event *event) static int __hw_perf_event_init(struct perf_event *event) { struct perf_event_attr *attr = &event->attr; - struct cpu_cf_events *cpuhw; - enum cpumf_ctr_set i; int err = 0; debug_sprintf_event(cf_diag_dbg, 5, "%s event %p cpu %d\n", __func__, event, event->cpu); event->hw.config = attr->config; - event->hw.config_base = 0; /* Add all authorized counter sets to config_base. The * the hardware init function is either called per-cpu or just once @@ -215,11 +236,7 @@ static int __hw_perf_event_init(struct perf_event *event) * Checking the authorization on any CPU is fine as the hardware * applies the same authorization settings to all CPUs. */ - cpuhw = &get_cpu_var(cpu_cf_events); - for (i = CPUMF_CTR_SET_BASIC; i < CPUMF_CTR_SET_MAX; ++i) - if (cpuhw->info.auth_ctl & cpumf_ctr_ctl[i]) - event->hw.config_base |= cpumf_ctr_ctl[i]; - put_cpu_var(cpu_cf_events); + event->hw.config_base = get_authctrsets(); /* No authorized counter sets, nothing to count/sample */ if (!event->hw.config_base) { @@ -237,6 +254,25 @@ out: return err; } +/* Return 0 if the CPU-measurement counter facility is currently free + * and an error otherwise. + */ +static int cf_diag_perf_event_inuse(void) +{ + int err = 0; + + if (!atomic_inc_not_zero(&cf_diag_events)) { + mutex_lock(&cf_diag_reserve_mutex); + if (atomic_read(&cf_diag_events) == 0 && + __kernel_cpumcf_begin()) + err = -EBUSY; + else + err = atomic_inc_return(&cf_diag_events); + mutex_unlock(&cf_diag_reserve_mutex); + } + return err; +} + static int cf_diag_event_init(struct perf_event *event) { struct perf_event_attr *attr = &event->attr; @@ -264,13 +300,9 @@ static int cf_diag_event_init(struct perf_event *event) } /* Initialize for using the CPU-measurement counter facility */ - if (atomic_inc_return(&cf_diag_events) == 1) { - if (__kernel_cpumcf_begin()) { - atomic_dec(&cf_diag_events); - err = -EBUSY; - goto out; - } - } + err = cf_diag_perf_event_inuse(); + if (err < 0) + goto out; event->destroy = cf_diag_perf_event_destroy; err = __hw_perf_event_init(event); @@ -599,6 +631,8 @@ static void cf_diag_del(struct perf_event *event, int flags) cpuhw->flags &= ~PMU_F_IN_USE; } +/* Default counter set events and format attribute groups */ + CPUMF_EVENT_ATTR(CF_DIAG, CF_DIAG, PERF_EVENT_CPUM_CF_DIAG); static struct attribute *cf_diag_events_attr[] = { @@ -663,6 +697,452 @@ static void cf_diag_get_cpu_speed(void) } } +/* Code to create device and file I/O operations */ +static atomic_t ctrset_opencnt = ATOMIC_INIT(0); /* Excl. access */ + +static int cf_diag_open(struct inode *inode, struct file *file) +{ + int err = 0; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + if (atomic_xchg(&ctrset_opencnt, 1)) + return -EBUSY; + + /* Avoid concurrent access with perf_event_open() system call */ + mutex_lock(&cf_diag_reserve_mutex); + if (atomic_read(&cf_diag_events) || __kernel_cpumcf_begin()) + err = -EBUSY; + mutex_unlock(&cf_diag_reserve_mutex); + if (err) { + atomic_set(&ctrset_opencnt, 0); + return err; + } + file->private_data = NULL; + debug_sprintf_event(cf_diag_dbg, 2, "%s\n", __func__); + /* nonseekable_open() never fails */ + return nonseekable_open(inode, file); +} + +/* Variables for ioctl() interface support */ +static DEFINE_MUTEX(cf_diag_ctrset_mutex); +static struct cf_diag_ctrset { + unsigned long ctrset; /* Bit mask of counter set to read */ + cpumask_t mask; /* CPU mask to read from */ + time64_t lastread; /* Epoch counter set last read */ +} cf_diag_ctrset; + +static void cf_diag_ctrset_clear(void) +{ + cpumask_clear(&cf_diag_ctrset.mask); + cf_diag_ctrset.ctrset = 0; +} + +static void cf_diag_release_cpu(void *p) +{ + struct cpu_cf_events *cpuhw = this_cpu_ptr(&cpu_cf_events); + + debug_sprintf_event(cf_diag_dbg, 3, "%s cpu %d\n", __func__, + smp_processor_id()); + lcctl(0); /* Reset counter sets */ + cpuhw->state = 0; /* Save state in CPU hardware state */ +} + +/* Release function is also called when application gets terminated without + * doing a proper ioctl(..., S390_HWCTR_STOP, ...) command. + * Since only one application is allowed to open the device, simple stop all + * CPU counter sets. + */ +static int cf_diag_release(struct inode *inode, struct file *file) +{ + on_each_cpu(cf_diag_release_cpu, NULL, 1); + cf_diag_ctrset_clear(); + atomic_set(&ctrset_opencnt, 0); + __kernel_cpumcf_end(); + debug_sprintf_event(cf_diag_dbg, 2, "%s\n", __func__); + return 0; +} + +struct cf_diag_call_on_cpu_parm { /* Parm struct for smp_call_on_cpu */ + unsigned int sets; /* Counter set bit mask */ + atomic_t cpus_ack; /* # CPUs successfully executed func */ +}; + +static int cf_diag_all_copy(unsigned long arg, cpumask_t *mask) +{ + struct s390_ctrset_read __user *ctrset_read; + unsigned int cpu, cpus, rc; + void __user *uptr; + + ctrset_read = (struct s390_ctrset_read __user *)arg; + uptr = ctrset_read->data; + for_each_cpu(cpu, mask) { + struct cf_diag_csd *csd = per_cpu_ptr(&cf_diag_csd, cpu); + struct s390_ctrset_cpudata __user *ctrset_cpudata; + + ctrset_cpudata = uptr; + debug_sprintf_event(cf_diag_dbg, 5, "%s cpu %d used %zd\n", + __func__, cpu, csd->used); + rc = put_user(cpu, &ctrset_cpudata->cpu_nr); + rc |= put_user(csd->sets, &ctrset_cpudata->no_sets); + rc |= copy_to_user(ctrset_cpudata->data, csd->data, csd->used); + if (rc) + return -EFAULT; + uptr += sizeof(struct s390_ctrset_cpudata) + csd->used; + cond_resched(); + } + cpus = cpumask_weight(mask); + if (put_user(cpus, &ctrset_read->no_cpus)) + return -EFAULT; + debug_sprintf_event(cf_diag_dbg, 5, "%s copied %ld\n", + __func__, uptr - (void __user *)ctrset_read->data); + return 0; +} + +static size_t cf_diag_cpuset_read(struct s390_ctrset_setdata *p, int ctrset, + int ctrset_size, size_t room) +{ + size_t need = 0; + int rc = -1; + + need = sizeof(*p) + sizeof(u64) * ctrset_size; + debug_sprintf_event(cf_diag_dbg, 5, + "%s room %zd need %zd set %#x set_size %d\n", + __func__, room, need, ctrset, ctrset_size); + if (need <= room) { + p->set = cpumf_ctr_ctl[ctrset]; + p->no_cnts = ctrset_size; + rc = ctr_stcctm(ctrset, ctrset_size, (u64 *)p->cv); + if (rc == 3) /* Nothing stored */ + need = 0; + } + debug_sprintf_event(cf_diag_dbg, 5, "%s need %zd rc %d\n", __func__, + need, rc); + return need; +} + +/* Read all counter sets. Since the perf_event_open() system call with + * event cpum_cf_diag/.../ is blocked when this interface is active, reuse + * the perf_event_open() data buffer to store the counter sets. + */ +static void cf_diag_cpu_read(void *parm) +{ + struct cpu_cf_events *cpuhw = this_cpu_ptr(&cpu_cf_events); + struct cf_diag_csd *csd = this_cpu_ptr(&cf_diag_csd); + struct cf_diag_call_on_cpu_parm *p = parm; + int set, set_size; + size_t space; + + debug_sprintf_event(cf_diag_dbg, 5, + "%s new %#x flags %#x state %#llx\n", + __func__, p->sets, cpuhw->flags, + cpuhw->state); + /* No data saved yet */ + csd->used = 0; + csd->sets = 0; + memset(csd->data, 0, sizeof(csd->data)); + + /* Scan the counter sets */ + for (set = CPUMF_CTR_SET_BASIC; set < CPUMF_CTR_SET_MAX; ++set) { + struct s390_ctrset_setdata *sp = (void *)csd->data + csd->used; + + if (!(p->sets & cpumf_ctr_ctl[set])) + continue; /* Counter set not in list */ + set_size = cf_diag_ctrset_size(set, &cpuhw->info); + space = sizeof(csd->data) - csd->used; + space = cf_diag_cpuset_read(sp, set, set_size, space); + if (space) { + csd->used += space; + csd->sets += 1; + } + debug_sprintf_event(cf_diag_dbg, 5, "%s sp %px space %zd\n", + __func__, sp, space); + } + debug_sprintf_event(cf_diag_dbg, 5, "%s sets %d used %zd\n", __func__, + csd->sets, csd->used); +} + +static int cf_diag_all_read(unsigned long arg) +{ + struct cf_diag_call_on_cpu_parm p; + cpumask_var_t mask; + time64_t now; + int rc = 0; + + debug_sprintf_event(cf_diag_dbg, 5, "%s\n", __func__); + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; + now = ktime_get_seconds(); + if (cf_diag_ctrset.lastread + cf_diag_interval > now) { + debug_sprintf_event(cf_diag_dbg, 5, "%s now %lld " + " lastread %lld\n", __func__, now, + cf_diag_ctrset.lastread); + rc = -EAGAIN; + goto out; + } else { + cf_diag_ctrset.lastread = now; + } + p.sets = cf_diag_ctrset.ctrset; + cpumask_and(mask, &cf_diag_ctrset.mask, cpu_online_mask); + on_each_cpu_mask(mask, cf_diag_cpu_read, &p, 1); + rc = cf_diag_all_copy(arg, mask); +out: + free_cpumask_var(mask); + debug_sprintf_event(cf_diag_dbg, 5, "%s rc %d\n", __func__, rc); + return rc; +} + +/* Stop all counter sets via ioctl interface */ +static void cf_diag_ioctl_off(void *parm) +{ + struct cpu_cf_events *cpuhw = this_cpu_ptr(&cpu_cf_events); + struct cf_diag_call_on_cpu_parm *p = parm; + int rc; + + debug_sprintf_event(cf_diag_dbg, 5, + "%s new %#x flags %#x state %#llx\n", + __func__, p->sets, cpuhw->flags, + cpuhw->state); + + ctr_set_multiple_disable(&cpuhw->state, p->sets); + ctr_set_multiple_stop(&cpuhw->state, p->sets); + rc = lcctl(cpuhw->state); /* Stop counter sets */ + if (!cpuhw->state) + cpuhw->flags &= ~PMU_F_IN_USE; + debug_sprintf_event(cf_diag_dbg, 5, + "%s rc %d flags %#x state %#llx\n", __func__, + rc, cpuhw->flags, cpuhw->state); +} + +/* Start counter sets on particular CPU */ +static void cf_diag_ioctl_on(void *parm) +{ + struct cpu_cf_events *cpuhw = this_cpu_ptr(&cpu_cf_events); + struct cf_diag_call_on_cpu_parm *p = parm; + int rc; + + debug_sprintf_event(cf_diag_dbg, 5, + "%s new %#x flags %#x state %#llx\n", + __func__, p->sets, cpuhw->flags, + cpuhw->state); + + if (!(cpuhw->flags & PMU_F_IN_USE)) + cpuhw->state = 0; + cpuhw->flags |= PMU_F_IN_USE; + rc = lcctl(cpuhw->state); /* Reset unused counter sets */ + ctr_set_multiple_enable(&cpuhw->state, p->sets); + ctr_set_multiple_start(&cpuhw->state, p->sets); + rc |= lcctl(cpuhw->state); /* Start counter sets */ + if (!rc) + atomic_inc(&p->cpus_ack); + debug_sprintf_event(cf_diag_dbg, 5, "%s rc %d state %#llx\n", + __func__, rc, cpuhw->state); +} + +static int cf_diag_all_stop(void) +{ + struct cf_diag_call_on_cpu_parm p = { + .sets = cf_diag_ctrset.ctrset, + }; + cpumask_var_t mask; + + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; + cpumask_and(mask, &cf_diag_ctrset.mask, cpu_online_mask); + on_each_cpu_mask(mask, cf_diag_ioctl_off, &p, 1); + free_cpumask_var(mask); + return 0; +} + +static int cf_diag_all_start(void) +{ + struct cf_diag_call_on_cpu_parm p = { + .sets = cf_diag_ctrset.ctrset, + .cpus_ack = ATOMIC_INIT(0), + }; + cpumask_var_t mask; + int rc = 0; + + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; + cpumask_and(mask, &cf_diag_ctrset.mask, cpu_online_mask); + on_each_cpu_mask(mask, cf_diag_ioctl_on, &p, 1); + if (atomic_read(&p.cpus_ack) != cpumask_weight(mask)) { + on_each_cpu_mask(mask, cf_diag_ioctl_off, &p, 1); + rc = -EIO; + } + free_cpumask_var(mask); + return rc; +} + +/* Return the maximum required space for all possible CPUs in case one + * CPU will be onlined during the START, READ, STOP cycles. + * To find out the size of the counter sets, any one CPU will do. They + * all have the same counter sets. + */ +static size_t cf_diag_needspace(unsigned int sets) +{ + struct cpu_cf_events *cpuhw = this_cpu_ptr(&cpu_cf_events); + size_t bytes = 0; + int i; + + for (i = CPUMF_CTR_SET_BASIC; i < CPUMF_CTR_SET_MAX; ++i) { + if (!(sets & cpumf_ctr_ctl[i])) + continue; + bytes += cf_diag_ctrset_size(i, &cpuhw->info) * sizeof(u64) + + sizeof(((struct s390_ctrset_setdata *)0)->set) + + sizeof(((struct s390_ctrset_setdata *)0)->no_cnts); + } + bytes = sizeof(((struct s390_ctrset_read *)0)->no_cpus) + nr_cpu_ids * + (bytes + sizeof(((struct s390_ctrset_cpudata *)0)->cpu_nr) + + sizeof(((struct s390_ctrset_cpudata *)0)->no_sets)); + debug_sprintf_event(cf_diag_dbg, 5, "%s bytes %ld\n", __func__, + bytes); + return bytes; +} + +static long cf_diag_ioctl_read(unsigned long arg) +{ + struct s390_ctrset_read read; + int ret = 0; + + debug_sprintf_event(cf_diag_dbg, 5, "%s\n", __func__); + if (copy_from_user(&read, (char __user *)arg, sizeof(read))) + return -EFAULT; + ret = cf_diag_all_read(arg); + debug_sprintf_event(cf_diag_dbg, 5, "%s ret %d\n", __func__, ret); + return ret; +} + +static long cf_diag_ioctl_stop(void) +{ + int ret; + + debug_sprintf_event(cf_diag_dbg, 5, "%s\n", __func__); + ret = cf_diag_all_stop(); + cf_diag_ctrset_clear(); + debug_sprintf_event(cf_diag_dbg, 5, "%s ret %d\n", __func__, ret); + return ret; +} + +static long cf_diag_ioctl_start(unsigned long arg) +{ + struct s390_ctrset_start __user *ustart; + struct s390_ctrset_start start; + void __user *umask; + unsigned int len; + int ret = 0; + size_t need; + + if (cf_diag_ctrset.ctrset) + return -EBUSY; + ustart = (struct s390_ctrset_start __user *)arg; + if (copy_from_user(&start, ustart, sizeof(start))) + return -EFAULT; + if (start.version != S390_HWCTR_START_VERSION) + return -EINVAL; + if (start.counter_sets & ~(cpumf_ctr_ctl[CPUMF_CTR_SET_BASIC] | + cpumf_ctr_ctl[CPUMF_CTR_SET_USER] | + cpumf_ctr_ctl[CPUMF_CTR_SET_CRYPTO] | + cpumf_ctr_ctl[CPUMF_CTR_SET_EXT] | + cpumf_ctr_ctl[CPUMF_CTR_SET_MT_DIAG])) + return -EINVAL; /* Invalid counter set */ + if (!start.counter_sets) + return -EINVAL; /* No counter set at all? */ + cpumask_clear(&cf_diag_ctrset.mask); + len = min_t(u64, start.cpumask_len, cpumask_size()); + umask = (void __user *)start.cpumask; + if (copy_from_user(&cf_diag_ctrset.mask, umask, len)) + return -EFAULT; + if (cpumask_empty(&cf_diag_ctrset.mask)) + return -EINVAL; + need = cf_diag_needspace(start.counter_sets); + if (put_user(need, &ustart->data_bytes)) + ret = -EFAULT; + if (ret) + goto out; + cf_diag_ctrset.ctrset = start.counter_sets; + ret = cf_diag_all_start(); +out: + if (ret) + cf_diag_ctrset_clear(); + debug_sprintf_event(cf_diag_dbg, 2, "%s sets %#lx need %ld ret %d\n", + __func__, cf_diag_ctrset.ctrset, need, ret); + return ret; +} + +static long cf_diag_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + int ret; + + debug_sprintf_event(cf_diag_dbg, 2, "%s cmd %#x arg %lx\n", __func__, + cmd, arg); + get_online_cpus(); + mutex_lock(&cf_diag_ctrset_mutex); + switch (cmd) { + case S390_HWCTR_START: + ret = cf_diag_ioctl_start(arg); + break; + case S390_HWCTR_STOP: + ret = cf_diag_ioctl_stop(); + break; + case S390_HWCTR_READ: + ret = cf_diag_ioctl_read(arg); + break; + default: + ret = -ENOTTY; + break; + } + mutex_unlock(&cf_diag_ctrset_mutex); + put_online_cpus(); + debug_sprintf_event(cf_diag_dbg, 2, "%s ret %d\n", __func__, ret); + return ret; +} + +static const struct file_operations cf_diag_fops = { + .owner = THIS_MODULE, + .open = cf_diag_open, + .release = cf_diag_release, + .unlocked_ioctl = cf_diag_ioctl, + .compat_ioctl = cf_diag_ioctl, + .llseek = no_llseek +}; + +static struct miscdevice cf_diag_dev = { + .name = S390_HWCTR_DEVICE, + .minor = MISC_DYNAMIC_MINOR, + .fops = &cf_diag_fops, +}; + +static int cf_diag_online_cpu(unsigned int cpu) +{ + struct cf_diag_call_on_cpu_parm p; + + mutex_lock(&cf_diag_ctrset_mutex); + if (!cf_diag_ctrset.ctrset) + goto out; + p.sets = cf_diag_ctrset.ctrset; + cf_diag_ioctl_on(&p); +out: + mutex_unlock(&cf_diag_ctrset_mutex); + return 0; +} + +static int cf_diag_offline_cpu(unsigned int cpu) +{ + struct cf_diag_call_on_cpu_parm p; + + mutex_lock(&cf_diag_ctrset_mutex); + if (!cf_diag_ctrset.ctrset) + goto out; + p.sets = cf_diag_ctrset.ctrset; + cf_diag_ioctl_off(&p); +out: + mutex_unlock(&cf_diag_ctrset_mutex); + return 0; +} + /* Initialize the counter set PMU to generate complete counter set data as * event raw data. This relies on the CPU Measurement Counter Facility device * already being loaded and initialized. @@ -685,21 +1165,43 @@ static int __init cf_diag_init(void) return -ENOMEM; } + rc = misc_register(&cf_diag_dev); + if (rc) { + pr_err("Registration of /dev/" S390_HWCTR_DEVICE + "failed rc=%d\n", rc); + goto out; + } + /* Setup s390dbf facility */ cf_diag_dbg = debug_register(KMSG_COMPONENT, 2, 1, 128); if (!cf_diag_dbg) { pr_err("Registration of s390dbf(cpum_cf_diag) failed\n"); - return -ENOMEM; + rc = -ENOMEM; + goto out_dbf; } debug_register_view(cf_diag_dbg, &debug_sprintf_view); rc = perf_pmu_register(&cf_diag, "cpum_cf_diag", -1); if (rc) { - debug_unregister_view(cf_diag_dbg, &debug_sprintf_view); - debug_unregister(cf_diag_dbg); pr_err("Registration of PMU(cpum_cf_diag) failed with rc=%i\n", rc); + goto out_perf; } + rc = cpuhp_setup_state_nocalls(CPUHP_AP_PERF_S390_CFD_ONLINE, + "perf/s390/cfd:online", + cf_diag_online_cpu, cf_diag_offline_cpu); + if (!rc) + goto out; + + pr_err("Registration of CPUHP_AP_PERF_S390_CFD_ONLINE failed rc=%i\n", + rc); + perf_pmu_unregister(&cf_diag); +out_perf: + debug_unregister_view(cf_diag_dbg, &debug_sprintf_view); + debug_unregister(cf_diag_dbg); +out_dbf: + misc_deregister(&cf_diag_dev); +out: return rc; } -arch_initcall(cf_diag_init); +device_initcall(cf_diag_init); diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index ee09a39627d6..9129ba231423 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -168,6 +168,7 @@ enum cpuhp_state { CPUHP_AP_PERF_X86_CQM_ONLINE, CPUHP_AP_PERF_X86_CSTATE_ONLINE, CPUHP_AP_PERF_S390_CF_ONLINE, + CPUHP_AP_PERF_S390_CFD_ONLINE, CPUHP_AP_PERF_S390_SF_ONLINE, CPUHP_AP_PERF_ARM_CCI_ONLINE, CPUHP_AP_PERF_ARM_CCN_ONLINE, -- cgit v1.2.3 From e54937963fa249595824439dc839c948188dea83 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 17 Feb 2021 10:14:21 -0700 Subject: net: remove cmsg restriction from io_uring based send/recvmsg calls No need to restrict these anymore, as the worker threads are direct clones of the original task. Hence we know for a fact that we can support anything that the regular task can. Since the only user of proto_ops->flags was to flag PROTO_CMSG_DATA_ONLY, kill the member and the flag definition too. Signed-off-by: Jens Axboe --- include/linux/net.h | 3 --- net/ipv4/af_inet.c | 1 - net/ipv6/af_inet6.c | 1 - net/socket.c | 10 ---------- 4 files changed, 15 deletions(-) (limited to 'include') diff --git a/include/linux/net.h b/include/linux/net.h index 9e2324efc26a..ba736b457a06 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -42,8 +42,6 @@ struct net; #define SOCK_PASSCRED 3 #define SOCK_PASSSEC 4 -#define PROTO_CMSG_DATA_ONLY 0x0001 - #ifndef ARCH_HAS_SOCKET_TYPES /** * enum sock_type - Socket types @@ -138,7 +136,6 @@ typedef int (*sk_read_actor_t)(read_descriptor_t *, struct sk_buff *, struct proto_ops { int family; - unsigned int flags; struct module *owner; int (*release) (struct socket *sock); int (*bind) (struct socket *sock, diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index a02ce89b56b5..1355e6c0d567 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1021,7 +1021,6 @@ static int inet_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned lon const struct proto_ops inet_stream_ops = { .family = PF_INET, - .flags = PROTO_CMSG_DATA_ONLY, .owner = THIS_MODULE, .release = inet_release, .bind = inet_bind, diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 1fb75f01756c..802f5111805a 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -665,7 +665,6 @@ int inet6_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, const struct proto_ops inet6_stream_ops = { .family = PF_INET6, - .flags = PROTO_CMSG_DATA_ONLY, .owner = THIS_MODULE, .release = inet6_release, .bind = inet6_bind, diff --git a/net/socket.c b/net/socket.c index 7f0617ab5437..90a60899aae5 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2411,10 +2411,6 @@ static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg, long __sys_sendmsg_sock(struct socket *sock, struct msghdr *msg, unsigned int flags) { - /* disallow ancillary data requests from this path */ - if (msg->msg_control || msg->msg_controllen) - return -EINVAL; - return ____sys_sendmsg(sock, msg, flags, NULL, 0); } @@ -2623,12 +2619,6 @@ long __sys_recvmsg_sock(struct socket *sock, struct msghdr *msg, struct user_msghdr __user *umsg, struct sockaddr __user *uaddr, unsigned int flags) { - if (msg->msg_control || msg->msg_controllen) { - /* disallow ancillary data reqs unless cmsg is plain data */ - if (!(sock->ops->flags & PROTO_CMSG_DATA_ONLY)) - return -EINVAL; - } - return ____sys_recvmsg(sock, msg, umsg, uaddr, flags, 0); } -- cgit v1.2.3 From 1c0aa1fae1acb77c5f9917adb0e4cb4500b9f3a6 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 20 Feb 2021 11:55:28 -0700 Subject: io_uring: flag new native workers with IORING_FEAT_NATIVE_WORKERS A few reasons to do this: - The naming of the manager and worker have changed. That's a user visible change, so makes sense to flag it. - Opening certain files that use ->signal (like /proc/self or /dev/tty) now works, and the flag tells the application upfront that this is the case. - Related to the above, using signalfd will now work as well. Signed-off-by: Jens Axboe --- fs/io_uring.c | 2 +- include/uapi/linux/io_uring.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/fs/io_uring.c b/fs/io_uring.c index 378cf79e66c9..cf9a5fa1ad03 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -9467,7 +9467,7 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p, IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS | IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL | IORING_FEAT_POLL_32BITS | IORING_FEAT_SQPOLL_NONFIXED | - IORING_FEAT_EXT_ARG; + IORING_FEAT_EXT_ARG | IORING_FEAT_NATIVE_WORKERS; if (copy_to_user(params, p, sizeof(*p))) { ret = -EFAULT; diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index ac4e1738a9af..2514eb6b1cf2 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -262,6 +262,7 @@ struct io_uring_params { #define IORING_FEAT_POLL_32BITS (1U << 6) #define IORING_FEAT_SQPOLL_NONFIXED (1U << 7) #define IORING_FEAT_EXT_ARG (1U << 8) +#define IORING_FEAT_NATIVE_WORKERS (1U << 9) /* * io_uring_register(2) opcodes and arguments -- cgit v1.2.3 From 8a378fb096a7f02943c72a428bbfd0029260efb6 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 23 Feb 2021 12:27:49 -0700 Subject: io_uring: ensure io-wq context is always destroyed for tasks If the task ends up doing no IO, the context list is empty and we don't call into __io_uring_files_cancel() when the task exits. This can cause a leak of the io-wq structures. Ensure we always call __io_uring_files_cancel(), even if the task context list is empty. Fixes: 5aa75ed5b93f ("io_uring: tie async worker side to the task context") Signed-off-by: Jens Axboe --- fs/io_uring.c | 7 ++++--- include/linux/io_uring.h | 2 +- 2 files changed, 5 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/fs/io_uring.c b/fs/io_uring.c index e62ad6bde569..0a435a6f265a 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -8800,9 +8800,10 @@ void __io_uring_files_cancel(struct files_struct *files) if (files) { io_uring_remove_task_files(tctx); - } else if (tctx->io_wq && current->flags & PF_EXITING) { - io_wq_destroy(tctx->io_wq); - tctx->io_wq = NULL; + if (tctx->io_wq) { + io_wq_destroy(tctx->io_wq); + tctx->io_wq = NULL; + } } } diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index c48fcbdc2ea8..51ede771cd99 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -43,7 +43,7 @@ static inline void io_uring_task_cancel(void) } static inline void io_uring_files_cancel(struct files_struct *files) { - if (current->io_uring && !xa_empty(¤t->io_uring->xa)) + if (current->io_uring) __io_uring_files_cancel(files); } static inline void io_uring_free(struct task_struct *tsk) -- cgit v1.2.3 From 6120484ef2bd4ffea7d2f11d2f06167b8f848349 Mon Sep 17 00:00:00 2001 From: Maximilian Luz Date: Thu, 11 Feb 2021 21:17:01 +0100 Subject: ACPI: platform: Fix file references in comment The referenced files are named slightly different. Replace '-' with '_' and drop the .rst ending. Signed-off-by: Maximilian Luz Reviewed-by: Hans de Goede Signed-off-by: Rafael J. Wysocki --- include/linux/platform_profile.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/platform_profile.h b/include/linux/platform_profile.h index a26542d53058..b4794027e759 100644 --- a/include/linux/platform_profile.h +++ b/include/linux/platform_profile.h @@ -12,9 +12,8 @@ #include /* - * If more options are added please update profile_names - * array in platform-profile.c and sysfs-platform-profile.rst - * documentation. + * If more options are added please update profile_names array in + * platform_profile.c and sysfs-platform_profile documentation. */ enum platform_profile_option { -- cgit v1.2.3 From 6c0b5e3fc6b536b125a66dfee103f3bc26d386f6 Mon Sep 17 00:00:00 2001 From: Maximilian Luz Date: Thu, 11 Feb 2021 21:17:02 +0100 Subject: ACPI: platform: Add balanced-performance platform profile Some devices, including most Microsoft Surface devices, have a platform profile somewhere inbetween balanced and performance. More specifically, adding this profile allows the following mapping on Surface devices: Vendor Name Platform Profile ------------------------------------------ Battery Saver low-power Recommended balanced Better Performance balanced-performance Best Performance performance Suggested-by: Hans de Goede Signed-off-by: Maximilian Luz Reviewed-by: Hans de Goede Signed-off-by: Rafael J. Wysocki --- Documentation/ABI/testing/sysfs-platform_profile | 18 +++++++++++------- drivers/acpi/platform_profile.c | 1 + include/linux/platform_profile.h | 1 + 3 files changed, 13 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/Documentation/ABI/testing/sysfs-platform_profile b/Documentation/ABI/testing/sysfs-platform_profile index 9d6b89b66cca..dae9c8941905 100644 --- a/Documentation/ABI/testing/sysfs-platform_profile +++ b/Documentation/ABI/testing/sysfs-platform_profile @@ -5,13 +5,17 @@ Description: This file contains a space-separated list of profiles supported for Drivers must use the following standard profile-names: - ============ ============================================ - low-power Low power consumption - cool Cooler operation - quiet Quieter operation - balanced Balance between low power consumption and performance - performance High performance operation - ============ ============================================ + ==================== ======================================== + low-power Low power consumption + cool Cooler operation + quiet Quieter operation + balanced Balance between low power consumption + and performance + balanced-performance Balance between performance and low + power consumption with a slight bias + towards performance + performance High performance operation + ==================== ======================================== Userspace may expect drivers to offer more than one of these standard profile names. diff --git a/drivers/acpi/platform_profile.c b/drivers/acpi/platform_profile.c index 4a59c5993bde..dd2fbf38e414 100644 --- a/drivers/acpi/platform_profile.c +++ b/drivers/acpi/platform_profile.c @@ -17,6 +17,7 @@ static const char * const profile_names[] = { [PLATFORM_PROFILE_COOL] = "cool", [PLATFORM_PROFILE_QUIET] = "quiet", [PLATFORM_PROFILE_BALANCED] = "balanced", + [PLATFORM_PROFILE_BALANCED_PERFORMANCE] = "balanced-performance", [PLATFORM_PROFILE_PERFORMANCE] = "performance", }; static_assert(ARRAY_SIZE(profile_names) == PLATFORM_PROFILE_LAST); diff --git a/include/linux/platform_profile.h b/include/linux/platform_profile.h index b4794027e759..a6329003aee7 100644 --- a/include/linux/platform_profile.h +++ b/include/linux/platform_profile.h @@ -21,6 +21,7 @@ enum platform_profile_option { PLATFORM_PROFILE_COOL, PLATFORM_PROFILE_QUIET, PLATFORM_PROFILE_BALANCED, + PLATFORM_PROFILE_BALANCED_PERFORMANCE, PLATFORM_PROFILE_PERFORMANCE, PLATFORM_PROFILE_LAST, /*must always be last */ }; -- cgit v1.2.3 From abf4451b340b09f797c87341b3010f95af9215c0 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Tue, 19 Jan 2021 20:45:08 +0000 Subject: dma-buf: heaps: Rework heap allocation hooks to return struct dma_buf instead of fd MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Every heap needs to create a dmabuf and then export it to a fd via dma_buf_fd(), so to consolidate things a bit, have the heaps just return a struct dmabuf * and let the top level dma_heap_buffer_alloc() call handle creating the fd via dma_buf_fd(). Cc: Sumit Semwal Cc: Liam Mark Cc: Laura Abbott Cc: Brian Starkey Cc: Hridya Valsaraju Cc: Suren Baghdasaryan Cc: Sandeep Patil Cc: Daniel Mentz Cc: Chris Goldsworthy Cc: Ørjan Eide Cc: Robin Murphy Cc: Ezequiel Garcia Cc: Simon Ser Cc: James Jones Cc: linux-media@vger.kernel.org Cc: dri-devel@lists.freedesktop.org Signed-off-by: John Stultz Signed-off-by: Sumit Semwal [sumits: minor reword of commit message] Link: https://patchwork.freedesktop.org/patch/msgid/20210119204508.9256-3-john.stultz@linaro.org (cherry picked from commit c7f59e3dd60313071a989227dcb69094f499d310) Signed-off-by: Sumit Semwal --- drivers/dma-buf/dma-heap.c | 14 +++++++++++++- drivers/dma-buf/heaps/cma_heap.c | 22 +++++++--------------- drivers/dma-buf/heaps/system_heap.c | 21 +++++++-------------- include/linux/dma-heap.h | 12 ++++++------ 4 files changed, 33 insertions(+), 36 deletions(-) (limited to 'include') diff --git a/drivers/dma-buf/dma-heap.c b/drivers/dma-buf/dma-heap.c index afd22c9dbdcf..6b5db954569f 100644 --- a/drivers/dma-buf/dma-heap.c +++ b/drivers/dma-buf/dma-heap.c @@ -52,6 +52,9 @@ static int dma_heap_buffer_alloc(struct dma_heap *heap, size_t len, unsigned int fd_flags, unsigned int heap_flags) { + struct dma_buf *dmabuf; + int fd; + /* * Allocations from all heaps have to begin * and end on page boundaries. @@ -60,7 +63,16 @@ static int dma_heap_buffer_alloc(struct dma_heap *heap, size_t len, if (!len) return -EINVAL; - return heap->ops->allocate(heap, len, fd_flags, heap_flags); + dmabuf = heap->ops->allocate(heap, len, fd_flags, heap_flags); + if (IS_ERR(dmabuf)) + return PTR_ERR(dmabuf); + + fd = dma_buf_fd(dmabuf, fd_flags); + if (fd < 0) { + dma_buf_put(dmabuf); + /* just return, as put will call release and that will free */ + } + return fd; } static int dma_heap_open(struct inode *inode, struct file *file) diff --git a/drivers/dma-buf/heaps/cma_heap.c b/drivers/dma-buf/heaps/cma_heap.c index 364fc2f3e499..5d64eccd21d6 100644 --- a/drivers/dma-buf/heaps/cma_heap.c +++ b/drivers/dma-buf/heaps/cma_heap.c @@ -271,10 +271,10 @@ static const struct dma_buf_ops cma_heap_buf_ops = { .release = cma_heap_dma_buf_release, }; -static int cma_heap_allocate(struct dma_heap *heap, - unsigned long len, - unsigned long fd_flags, - unsigned long heap_flags) +static struct dma_buf *cma_heap_allocate(struct dma_heap *heap, + unsigned long len, + unsigned long fd_flags, + unsigned long heap_flags) { struct cma_heap *cma_heap = dma_heap_get_drvdata(heap); struct cma_heap_buffer *buffer; @@ -289,7 +289,7 @@ static int cma_heap_allocate(struct dma_heap *heap, buffer = kzalloc(sizeof(*buffer), GFP_KERNEL); if (!buffer) - return -ENOMEM; + return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&buffer->attachments); mutex_init(&buffer->lock); @@ -348,15 +348,7 @@ static int cma_heap_allocate(struct dma_heap *heap, ret = PTR_ERR(dmabuf); goto free_pages; } - - ret = dma_buf_fd(dmabuf, fd_flags); - if (ret < 0) { - dma_buf_put(dmabuf); - /* just return, as put will call release and that will free */ - return ret; - } - - return ret; + return dmabuf; free_pages: kfree(buffer->pages); @@ -365,7 +357,7 @@ free_cma: free_buffer: kfree(buffer); - return ret; + return ERR_PTR(ret); } static const struct dma_heap_ops cma_heap_ops = { diff --git a/drivers/dma-buf/heaps/system_heap.c b/drivers/dma-buf/heaps/system_heap.c index 405351aad2a8..29e49ac17251 100644 --- a/drivers/dma-buf/heaps/system_heap.c +++ b/drivers/dma-buf/heaps/system_heap.c @@ -331,10 +331,10 @@ static struct page *alloc_largest_available(unsigned long size, return NULL; } -static int system_heap_allocate(struct dma_heap *heap, - unsigned long len, - unsigned long fd_flags, - unsigned long heap_flags) +static struct dma_buf *system_heap_allocate(struct dma_heap *heap, + unsigned long len, + unsigned long fd_flags, + unsigned long heap_flags) { struct system_heap_buffer *buffer; DEFINE_DMA_BUF_EXPORT_INFO(exp_info); @@ -349,7 +349,7 @@ static int system_heap_allocate(struct dma_heap *heap, buffer = kzalloc(sizeof(*buffer), GFP_KERNEL); if (!buffer) - return -ENOMEM; + return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&buffer->attachments); mutex_init(&buffer->lock); @@ -399,14 +399,7 @@ static int system_heap_allocate(struct dma_heap *heap, ret = PTR_ERR(dmabuf); goto free_pages; } - - ret = dma_buf_fd(dmabuf, fd_flags); - if (ret < 0) { - dma_buf_put(dmabuf); - /* just return, as put will call release and that will free */ - return ret; - } - return ret; + return dmabuf; free_pages: for_each_sgtable_sg(table, sg, i) { @@ -420,7 +413,7 @@ free_buffer: __free_pages(page, compound_order(page)); kfree(buffer); - return ret; + return ERR_PTR(ret); } static const struct dma_heap_ops system_heap_ops = { diff --git a/include/linux/dma-heap.h b/include/linux/dma-heap.h index 454e354d1ffb..5bc5c946af58 100644 --- a/include/linux/dma-heap.h +++ b/include/linux/dma-heap.h @@ -16,15 +16,15 @@ struct dma_heap; /** * struct dma_heap_ops - ops to operate on a given heap - * @allocate: allocate dmabuf and return fd + * @allocate: allocate dmabuf and return struct dma_buf ptr * - * allocate returns dmabuf fd on success, -errno on error. + * allocate returns dmabuf on success, ERR_PTR(-errno) on error. */ struct dma_heap_ops { - int (*allocate)(struct dma_heap *heap, - unsigned long len, - unsigned long fd_flags, - unsigned long heap_flags); + struct dma_buf *(*allocate)(struct dma_heap *heap, + unsigned long len, + unsigned long fd_flags, + unsigned long heap_flags); }; /** -- cgit v1.2.3 From f588f0c69e0e645225e4ebc1aff8f9677583a056 Mon Sep 17 00:00:00 2001 From: Veera Sundaram Sankaran Date: Fri, 15 Jan 2021 16:31:46 -0800 Subject: dma-fence: allow signaling drivers to set fence timestamp Some drivers have hardware capability to get the precise HW timestamp of certain events based on which the fences are triggered. The delta between the event HW timestamp & current HW reference timestamp can be used to calculate the timestamp in kernel's CLOCK_MONOTONIC time domain. This allows it to set accurate timestamp factoring out any software and IRQ latencies. Add a timestamp variant of fence signal function, dma_fence_signal_timestamp to allow drivers to update the precise timestamp for fences. Changes in v2: - Add a new fence signal variant instead of modifying fence struct Changes in v3: - Add timestamp domain information to commit-text and dma_fence_signal_timestamp documentation Signed-off-by: Veera Sundaram Sankaran Reviewed-by: John Stultz Signed-off-by: Sumit Semwal [sumits: minor parenthesis alignment] Link: https://patchwork.freedesktop.org/patch/msgid/1610757107-11892-1-git-send-email-veeras@codeaurora.org (cherry picked from commit 5a164ac4dbd21b82bcdc03186d40e455ff467fdc) Signed-off-by: Sumit Semwal --- drivers/dma-buf/dma-fence.c | 70 ++++++++++++++++++++++++++++++++++++++++----- include/linux/dma-fence.h | 3 ++ 2 files changed, 66 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c index 7475e09b0680..d64fc03929be 100644 --- a/drivers/dma-buf/dma-fence.c +++ b/drivers/dma-buf/dma-fence.c @@ -312,22 +312,25 @@ void __dma_fence_might_wait(void) /** - * dma_fence_signal_locked - signal completion of a fence + * dma_fence_signal_timestamp_locked - signal completion of a fence * @fence: the fence to signal + * @timestamp: fence signal timestamp in kernel's CLOCK_MONOTONIC time domain * * Signal completion for software callbacks on a fence, this will unblock * dma_fence_wait() calls and run all the callbacks added with * dma_fence_add_callback(). Can be called multiple times, but since a fence * can only go from the unsignaled to the signaled state and not back, it will - * only be effective the first time. + * only be effective the first time. Set the timestamp provided as the fence + * signal timestamp. * - * Unlike dma_fence_signal(), this function must be called with &dma_fence.lock - * held. + * Unlike dma_fence_signal_timestamp(), this function must be called with + * &dma_fence.lock held. * * Returns 0 on success and a negative error value when @fence has been * signalled already. */ -int dma_fence_signal_locked(struct dma_fence *fence) +int dma_fence_signal_timestamp_locked(struct dma_fence *fence, + ktime_t timestamp) { struct dma_fence_cb *cur, *tmp; struct list_head cb_list; @@ -341,7 +344,7 @@ int dma_fence_signal_locked(struct dma_fence *fence) /* Stash the cb_list before replacing it with the timestamp */ list_replace(&fence->cb_list, &cb_list); - fence->timestamp = ktime_get(); + fence->timestamp = timestamp; set_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags); trace_dma_fence_signaled(fence); @@ -352,6 +355,59 @@ int dma_fence_signal_locked(struct dma_fence *fence) return 0; } +EXPORT_SYMBOL(dma_fence_signal_timestamp_locked); + +/** + * dma_fence_signal_timestamp - signal completion of a fence + * @fence: the fence to signal + * @timestamp: fence signal timestamp in kernel's CLOCK_MONOTONIC time domain + * + * Signal completion for software callbacks on a fence, this will unblock + * dma_fence_wait() calls and run all the callbacks added with + * dma_fence_add_callback(). Can be called multiple times, but since a fence + * can only go from the unsignaled to the signaled state and not back, it will + * only be effective the first time. Set the timestamp provided as the fence + * signal timestamp. + * + * Returns 0 on success and a negative error value when @fence has been + * signalled already. + */ +int dma_fence_signal_timestamp(struct dma_fence *fence, ktime_t timestamp) +{ + unsigned long flags; + int ret; + + if (!fence) + return -EINVAL; + + spin_lock_irqsave(fence->lock, flags); + ret = dma_fence_signal_timestamp_locked(fence, timestamp); + spin_unlock_irqrestore(fence->lock, flags); + + return ret; +} +EXPORT_SYMBOL(dma_fence_signal_timestamp); + +/** + * dma_fence_signal_locked - signal completion of a fence + * @fence: the fence to signal + * + * Signal completion for software callbacks on a fence, this will unblock + * dma_fence_wait() calls and run all the callbacks added with + * dma_fence_add_callback(). Can be called multiple times, but since a fence + * can only go from the unsignaled to the signaled state and not back, it will + * only be effective the first time. + * + * Unlike dma_fence_signal(), this function must be called with &dma_fence.lock + * held. + * + * Returns 0 on success and a negative error value when @fence has been + * signalled already. + */ +int dma_fence_signal_locked(struct dma_fence *fence) +{ + return dma_fence_signal_timestamp_locked(fence, ktime_get()); +} EXPORT_SYMBOL(dma_fence_signal_locked); /** @@ -379,7 +435,7 @@ int dma_fence_signal(struct dma_fence *fence) tmp = dma_fence_begin_signalling(); spin_lock_irqsave(fence->lock, flags); - ret = dma_fence_signal_locked(fence); + ret = dma_fence_signal_timestamp_locked(fence, ktime_get()); spin_unlock_irqrestore(fence->lock, flags); dma_fence_end_signalling(tmp); diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index 09e23adb351d..9f12efaaa93a 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -372,6 +372,9 @@ static inline void __dma_fence_might_wait(void) {} int dma_fence_signal(struct dma_fence *fence); int dma_fence_signal_locked(struct dma_fence *fence); +int dma_fence_signal_timestamp(struct dma_fence *fence, ktime_t timestamp); +int dma_fence_signal_timestamp_locked(struct dma_fence *fence, + ktime_t timestamp); signed long dma_fence_default_wait(struct dma_fence *fence, bool intr, signed long timeout); int dma_fence_add_callback(struct dma_fence *fence, -- cgit v1.2.3 From 583065c7aa23d4bb0c298222c1128353a2007c9c Mon Sep 17 00:00:00 2001 From: Veera Sundaram Sankaran Date: Fri, 15 Jan 2021 16:31:47 -0800 Subject: drm/drm_vblank: set the dma-fence timestamp during send_vblank_event The explicit out-fences in crtc are signaled as part of vblank event, indicating all framebuffers present on the Atomic Commit request are scanned out on the screen. Though the fence signal and the vblank event notification happens at the same time, triggered by the same hardware vsync event, the timestamp set in both are different. With drivers supporting precise vblank timestamp the difference between the two timestamps would be even higher. This might have an impact on use-mode frameworks using these fence timestamps for purposes other than simple buffer usage. For instance, the Android framework [1] uses the retire-fences as an alternative to vblank when frame-updates are in progress. Set the fence timestamp during send vblank event using a new drm_send_event_timestamp_locked variant to avoid discrepancies. [1] https://android.googlesource.com/platform/frameworks/native/+/master/ services/surfaceflinger/Scheduler/Scheduler.cpp#397 Changes in v2: - Use drm_send_event_timestamp_locked to update fence timestamp - add more information to commit text Changes in v3: - use same backend helper function for variants of drm_send_event to avoid code duplications Changes in v4: - remove WARN_ON from drm_send_event_timestamp_locked Signed-off-by: Veera Sundaram Sankaran Reviewed-by: John Stultz Signed-off-by: Sumit Semwal [sumits: minor parenthesis alignment correction] Link: https://patchwork.freedesktop.org/patch/msgid/1610757107-11892-2-git-send-email-veeras@codeaurora.org (cherry picked from commit a78e7a51d2fa9d2f482b462be4299784c884d988) Signed-off-by: Sumit Semwal --- drivers/gpu/drm/drm_file.c | 68 ++++++++++++++++++++++++++++++++++++-------- drivers/gpu/drm/drm_vblank.c | 9 +++++- include/drm/drm_file.h | 3 ++ 3 files changed, 67 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c index 6b116bfd747c..7efbccffc2ea 100644 --- a/drivers/gpu/drm/drm_file.c +++ b/drivers/gpu/drm/drm_file.c @@ -775,20 +775,19 @@ void drm_event_cancel_free(struct drm_device *dev, EXPORT_SYMBOL(drm_event_cancel_free); /** - * drm_send_event_locked - send DRM event to file descriptor + * drm_send_event_helper - send DRM event to file descriptor * @dev: DRM device * @e: DRM event to deliver + * @timestamp: timestamp to set for the fence event in kernel's CLOCK_MONOTONIC + * time domain * - * This function sends the event @e, initialized with drm_event_reserve_init(), - * to its associated userspace DRM file. Callers must already hold - * &drm_device.event_lock, see drm_send_event() for the unlocked version. - * - * Note that the core will take care of unlinking and disarming events when the - * corresponding DRM file is closed. Drivers need not worry about whether the - * DRM file for this event still exists and can call this function upon - * completion of the asynchronous work unconditionally. + * This helper function sends the event @e, initialized with + * drm_event_reserve_init(), to its associated userspace DRM file. + * The timestamp variant of dma_fence_signal is used when the caller + * sends a valid timestamp. */ -void drm_send_event_locked(struct drm_device *dev, struct drm_pending_event *e) +void drm_send_event_helper(struct drm_device *dev, + struct drm_pending_event *e, ktime_t timestamp) { assert_spin_locked(&dev->event_lock); @@ -799,7 +798,10 @@ void drm_send_event_locked(struct drm_device *dev, struct drm_pending_event *e) } if (e->fence) { - dma_fence_signal(e->fence); + if (timestamp) + dma_fence_signal_timestamp(e->fence, timestamp); + else + dma_fence_signal(e->fence); dma_fence_put(e->fence); } @@ -814,6 +816,48 @@ void drm_send_event_locked(struct drm_device *dev, struct drm_pending_event *e) wake_up_interruptible_poll(&e->file_priv->event_wait, EPOLLIN | EPOLLRDNORM); } + +/** + * drm_send_event_timestamp_locked - send DRM event to file descriptor + * @dev: DRM device + * @e: DRM event to deliver + * @timestamp: timestamp to set for the fence event in kernel's CLOCK_MONOTONIC + * time domain + * + * This function sends the event @e, initialized with drm_event_reserve_init(), + * to its associated userspace DRM file. Callers must already hold + * &drm_device.event_lock. + * + * Note that the core will take care of unlinking and disarming events when the + * corresponding DRM file is closed. Drivers need not worry about whether the + * DRM file for this event still exists and can call this function upon + * completion of the asynchronous work unconditionally. + */ +void drm_send_event_timestamp_locked(struct drm_device *dev, + struct drm_pending_event *e, ktime_t timestamp) +{ + drm_send_event_helper(dev, e, timestamp); +} +EXPORT_SYMBOL(drm_send_event_timestamp_locked); + +/** + * drm_send_event_locked - send DRM event to file descriptor + * @dev: DRM device + * @e: DRM event to deliver + * + * This function sends the event @e, initialized with drm_event_reserve_init(), + * to its associated userspace DRM file. Callers must already hold + * &drm_device.event_lock, see drm_send_event() for the unlocked version. + * + * Note that the core will take care of unlinking and disarming events when the + * corresponding DRM file is closed. Drivers need not worry about whether the + * DRM file for this event still exists and can call this function upon + * completion of the asynchronous work unconditionally. + */ +void drm_send_event_locked(struct drm_device *dev, struct drm_pending_event *e) +{ + drm_send_event_helper(dev, e, 0); +} EXPORT_SYMBOL(drm_send_event_locked); /** @@ -836,7 +880,7 @@ void drm_send_event(struct drm_device *dev, struct drm_pending_event *e) unsigned long irqflags; spin_lock_irqsave(&dev->event_lock, irqflags); - drm_send_event_locked(dev, e); + drm_send_event_helper(dev, e, 0); spin_unlock_irqrestore(&dev->event_lock, irqflags); } EXPORT_SYMBOL(drm_send_event); diff --git a/drivers/gpu/drm/drm_vblank.c b/drivers/gpu/drm/drm_vblank.c index 30912d8f82a5..893165eeddf3 100644 --- a/drivers/gpu/drm/drm_vblank.c +++ b/drivers/gpu/drm/drm_vblank.c @@ -1006,7 +1006,14 @@ static void send_vblank_event(struct drm_device *dev, break; } trace_drm_vblank_event_delivered(e->base.file_priv, e->pipe, seq); - drm_send_event_locked(dev, &e->base); + /* + * Use the same timestamp for any associated fence signal to avoid + * mismatch in timestamps for vsync & fence events triggered by the + * same HW event. Frameworks like SurfaceFlinger in Android expects the + * retire-fence timestamp to match exactly with HW vsync as it uses it + * for its software vsync modeling. + */ + drm_send_event_timestamp_locked(dev, &e->base, now); } /** diff --git a/include/drm/drm_file.h b/include/drm/drm_file.h index 716990bace10..b81b3bfb08c8 100644 --- a/include/drm/drm_file.h +++ b/include/drm/drm_file.h @@ -399,6 +399,9 @@ void drm_event_cancel_free(struct drm_device *dev, struct drm_pending_event *p); void drm_send_event_locked(struct drm_device *dev, struct drm_pending_event *e); void drm_send_event(struct drm_device *dev, struct drm_pending_event *e); +void drm_send_event_timestamp_locked(struct drm_device *dev, + struct drm_pending_event *e, + ktime_t timestamp); struct file *mock_drm_getfile(struct drm_minor *minor, unsigned int flags); -- cgit v1.2.3 From 3544de8ee6e4817278b15fe08658de49abf58954 Mon Sep 17 00:00:00 2001 From: Jacob Wen Date: Wed, 24 Feb 2021 12:00:55 -0800 Subject: mm, tracing: record slab name for kmem_cache_free() Currently, a trace record generated by the RCU core is as below. ... kmem_cache_free: call_site=rcu_core+0x1fd/0x610 ptr=00000000f3b49a66 It doesn't tell us what the RCU core has freed. This patch adds the slab name to trace_kmem_cache_free(). The new format is as follows. ... kmem_cache_free: call_site=rcu_core+0x1fd/0x610 ptr=0000000037f79c8d name=dentry ... kmem_cache_free: call_site=rcu_core+0x1fd/0x610 ptr=00000000f78cb7b5 name=sock_inode_cache ... kmem_cache_free: call_site=rcu_core+0x1fd/0x610 ptr=0000000018768985 name=pool_workqueue ... kmem_cache_free: call_site=rcu_core+0x1fd/0x610 ptr=000000006a6cb484 name=radix_tree_node We can use it to understand what the RCU core is going to free. For example, some users maybe interested in when the RCU core starts freeing reclaimable slabs like dentry to reduce memory pressure. Link: https://lkml.kernel.org/r/20201216072804.8838-1-jian.w.wen@oracle.com Signed-off-by: Jacob Wen Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Steven Rostedt Cc: "Paul E. McKenney" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/kmem.h | 24 ++++++++++++++++-------- mm/slab.c | 2 +- mm/slob.c | 2 +- mm/slub.c | 2 +- 4 files changed, 19 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h index f65b1f6db22d..40845b0d5dad 100644 --- a/include/trace/events/kmem.h +++ b/include/trace/events/kmem.h @@ -115,7 +115,7 @@ DEFINE_EVENT(kmem_alloc_node, kmem_cache_alloc_node, TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node) ); -DECLARE_EVENT_CLASS(kmem_free, +TRACE_EVENT(kfree, TP_PROTO(unsigned long call_site, const void *ptr), @@ -135,18 +135,26 @@ DECLARE_EVENT_CLASS(kmem_free, (void *)__entry->call_site, __entry->ptr) ); -DEFINE_EVENT(kmem_free, kfree, +TRACE_EVENT(kmem_cache_free, - TP_PROTO(unsigned long call_site, const void *ptr), + TP_PROTO(unsigned long call_site, const void *ptr, const char *name), - TP_ARGS(call_site, ptr) -); + TP_ARGS(call_site, ptr, name), -DEFINE_EVENT(kmem_free, kmem_cache_free, + TP_STRUCT__entry( + __field( unsigned long, call_site ) + __field( const void *, ptr ) + __field( const char *, name ) + ), - TP_PROTO(unsigned long call_site, const void *ptr), + TP_fast_assign( + __entry->call_site = call_site; + __entry->ptr = ptr; + __entry->name = name; + ), - TP_ARGS(call_site, ptr) + TP_printk("call_site=%pS ptr=%p name=%s", + (void *)__entry->call_site, __entry->ptr, __entry->name) ); TRACE_EVENT(mm_page_free, diff --git a/mm/slab.c b/mm/slab.c index dcc55e78f353..2ed27849d1f2 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -3717,7 +3717,7 @@ void kmem_cache_free(struct kmem_cache *cachep, void *objp) __cache_free(cachep, objp, _RET_IP_); local_irq_restore(flags); - trace_kmem_cache_free(_RET_IP_, objp); + trace_kmem_cache_free(_RET_IP_, objp, cachep->name); } EXPORT_SYMBOL(kmem_cache_free); diff --git a/mm/slob.c b/mm/slob.c index ef87ada8705d..0578429b991b 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -673,7 +673,7 @@ void kmem_cache_free(struct kmem_cache *c, void *b) __kmem_cache_free(b, c->size); } - trace_kmem_cache_free(_RET_IP_, b); + trace_kmem_cache_free(_RET_IP_, b, c->name); } EXPORT_SYMBOL(kmem_cache_free); diff --git a/mm/slub.c b/mm/slub.c index f5baf429654f..f4dc70228861 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -3157,7 +3157,7 @@ void kmem_cache_free(struct kmem_cache *s, void *x) if (!s) return; slab_free(s, virt_to_head_page(x), x, NULL, 1, _RET_IP_); - trace_kmem_cache_free(_RET_IP_, x); + trace_kmem_cache_free(_RET_IP_, x, s->name); } EXPORT_SYMBOL(kmem_cache_free); -- cgit v1.2.3 From 1f7ef657740344541645349a8bece90cbff898f5 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Wed, 24 Feb 2021 12:01:42 -0800 Subject: mm/filemap: remove unused parameter and change to void type for replace_page_cache_page() Since commit 74d609585d8b ("page cache: Add and replace pages using the XArray") was merged, the replace_page_cache_page() can not fail and always return 0, we can remove the redundant return value and void it. Moreover remove the unused gfp_mask. Link: https://lkml.kernel.org/r/609c30e5274ba15d8b90c872fd0d8ac437a9b2bb.1610071401.git.baolin.wang@linux.alibaba.com Signed-off-by: Baolin Wang Cc: Matthew Wilcox Cc: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fuse/dev.c | 6 +----- include/linux/pagemap.h | 2 +- mm/filemap.c | 7 +------ 3 files changed, 3 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 588f8d1240aa..c6636b4c4ccf 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -844,11 +844,7 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep) if (WARN_ON(PageMlocked(oldpage))) goto out_fallback_unlock; - err = replace_page_cache_page(oldpage, newpage, GFP_KERNEL); - if (err) { - unlock_page(newpage); - goto out_put_old; - } + replace_page_cache_page(oldpage, newpage); get_page(newpage); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index d5570deff400..74e466e5a2ba 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -757,7 +757,7 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); extern void delete_from_page_cache(struct page *page); extern void __delete_from_page_cache(struct page *page, void *shadow); -int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask); +void replace_page_cache_page(struct page *old, struct page *new); void delete_from_page_cache_batch(struct address_space *mapping, struct pagevec *pvec); diff --git a/mm/filemap.c b/mm/filemap.c index 6ff2a3fb0dc7..7dfed3454a2e 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -777,7 +777,6 @@ EXPORT_SYMBOL(file_write_and_wait_range); * replace_page_cache_page - replace a pagecache page with a new one * @old: page to be replaced * @new: page to replace with - * @gfp_mask: allocation mode * * This function replaces a page in the pagecache with a new one. On * success it acquires the pagecache reference for the new page and @@ -786,10 +785,8 @@ EXPORT_SYMBOL(file_write_and_wait_range); * caller must do that. * * The remove + add is atomic. This function cannot fail. - * - * Return: %0 */ -int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) +void replace_page_cache_page(struct page *old, struct page *new) { struct address_space *mapping = old->mapping; void (*freepage)(struct page *) = mapping->a_ops->freepage; @@ -824,8 +821,6 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) if (freepage) freepage(old); put_page(old); - - return 0; } EXPORT_SYMBOL_GPL(replace_page_cache_page); -- cgit v1.2.3 From 4805462598113f350838d612d0895db2dbb3992b Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 24 Feb 2021 12:02:02 -0800 Subject: mm/filemap: pass a sleep state to put_and_wait_on_page_locked This is prep work for the next patch, but I think at least one of the current callers would prefer a killable sleep to an uninterruptible one. Link: https://lkml.kernel.org/r/20210122160140.223228-6-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Kent Overstreet Reviewed-by: Christoph Hellwig Cc: Miaohe Lin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 3 +-- mm/filemap.c | 7 +++++-- mm/huge_memory.c | 4 ++-- mm/migrate.c | 4 ++-- 4 files changed, 10 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 74e466e5a2ba..bd629d676a27 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -681,8 +681,7 @@ static inline int wait_on_page_locked_killable(struct page *page) return wait_on_page_bit_killable(compound_head(page), PG_locked); } -extern void put_and_wait_on_page_locked(struct page *page); - +int put_and_wait_on_page_locked(struct page *page, int state); void wait_on_page_writeback(struct page *page); extern void end_page_writeback(struct page *page); void wait_for_stable_page(struct page *page); diff --git a/mm/filemap.c b/mm/filemap.c index 4fce9735e172..389a20eec9b8 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1384,20 +1384,23 @@ static int wait_on_page_locked_async(struct page *page, /** * put_and_wait_on_page_locked - Drop a reference and wait for it to be unlocked * @page: The page to wait for. + * @state: The sleep state (TASK_KILLABLE, TASK_UNINTERRUPTIBLE, etc). * * The caller should hold a reference on @page. They expect the page to * become unlocked relatively soon, but do not wish to hold up migration * (for example) by holding the reference while waiting for the page to * come unlocked. After this function returns, the caller should not * dereference @page. + * + * Return: 0 if the page was unlocked or -EINTR if interrupted by a signal. */ -void put_and_wait_on_page_locked(struct page *page) +int put_and_wait_on_page_locked(struct page *page, int state) { wait_queue_head_t *q; page = compound_head(page); q = page_waitqueue(page); - wait_on_page_bit_common(q, page, PG_locked, TASK_UNINTERRUPTIBLE, DROP); + return wait_on_page_bit_common(q, page, PG_locked, state, DROP); } /** diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 91ca9b103ee5..f655137536eb 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1439,7 +1439,7 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd) if (!get_page_unless_zero(page)) goto out_unlock; spin_unlock(vmf->ptl); - put_and_wait_on_page_locked(page); + put_and_wait_on_page_locked(page, TASK_UNINTERRUPTIBLE); goto out; } @@ -1475,7 +1475,7 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd) if (!get_page_unless_zero(page)) goto out_unlock; spin_unlock(vmf->ptl); - put_and_wait_on_page_locked(page); + put_and_wait_on_page_locked(page, TASK_UNINTERRUPTIBLE); goto out; } diff --git a/mm/migrate.c b/mm/migrate.c index 20ca887ea769..4ec727adfaa2 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -331,7 +331,7 @@ void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, if (!get_page_unless_zero(page)) goto out; pte_unmap_unlock(ptep, ptl); - put_and_wait_on_page_locked(page); + put_and_wait_on_page_locked(page, TASK_UNINTERRUPTIBLE); return; out: pte_unmap_unlock(ptep, ptl); @@ -365,7 +365,7 @@ void pmd_migration_entry_wait(struct mm_struct *mm, pmd_t *pmd) if (!get_page_unless_zero(page)) goto unlock; spin_unlock(ptl); - put_and_wait_on_page_locked(page); + put_and_wait_on_page_locked(page, TASK_UNINTERRUPTIBLE); return; unlock: spin_unlock(ptl); -- cgit v1.2.3 From 87fa0f3eb267eed966ee194907bc15376c1b758f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 24 Feb 2021 12:02:42 -0800 Subject: mm/filemap: rename generic_file_buffered_read to filemap_read Rename generic_file_buffered_read to match the naming of filemap_fault, also update the written parameter to a more descriptive name and improve the kerneldoc comment. Link: https://lkml.kernel.org/r/20210122160140.223228-18-willy@infradead.org Signed-off-by: Christoph Hellwig Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Kent Overstreet Cc: Miaohe Lin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/btrfs/file.c | 2 +- include/linux/fs.h | 4 ++-- mm/filemap.c | 35 ++++++++++++++++------------------- 3 files changed, 19 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index be9e3900cce8..bf2c51a9607a 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -3634,7 +3634,7 @@ static ssize_t btrfs_file_read_iter(struct kiocb *iocb, struct iov_iter *to) return ret; } - return generic_file_buffered_read(iocb, to, ret); + return filemap_read(iocb, to, ret); } const struct file_operations btrfs_file_operations = { diff --git a/include/linux/fs.h b/include/linux/fs.h index 418b772d6eca..ec8f3ddf4a6a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3080,8 +3080,8 @@ extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *); extern int generic_write_check_limits(struct file *file, loff_t pos, loff_t *count); extern int generic_file_rw_checks(struct file *file_in, struct file *file_out); -extern ssize_t generic_file_buffered_read(struct kiocb *iocb, - struct iov_iter *to, ssize_t already_read); +ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *to, + ssize_t already_read); extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *); extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *); diff --git a/mm/filemap.c b/mm/filemap.c index 1358cb061fd6..28c290da22c1 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2394,23 +2394,20 @@ err: } /** - * generic_file_buffered_read - generic file read routine - * @iocb: the iocb to read - * @iter: data destination - * @written: already copied + * filemap_read - Read data from the page cache. + * @iocb: The iocb to read. + * @iter: Destination for the data. + * @already_read: Number of bytes already read by the caller. * - * This is a generic file read routine, and uses the - * mapping->a_ops->readpage() function for the actual low-level stuff. + * Copies data from the page cache. If the data is not currently present, + * uses the readahead and readpage address_space operations to fetch it. * - * This is really ugly. But the goto's actually try to clarify some - * of the logic when it comes to error handling etc. - * - * Return: - * * total number of bytes copied, including those the were already @written - * * negative error code if nothing was copied + * Return: Total number of bytes copied, including those already read by + * the caller. If an error happens before any bytes are copied, returns + * a negative error number. */ -ssize_t generic_file_buffered_read(struct kiocb *iocb, - struct iov_iter *iter, ssize_t written) +ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter, + ssize_t already_read) { struct file *filp = iocb->ki_filp; struct file_ra_state *ra = &filp->f_ra; @@ -2437,7 +2434,7 @@ ssize_t generic_file_buffered_read(struct kiocb *iocb, * can no longer safely return -EIOCBQUEUED. Hence mark * an async read NOWAIT at that point. */ - if ((iocb->ki_flags & IOCB_WAITQ) && written) + if ((iocb->ki_flags & IOCB_WAITQ) && already_read) iocb->ki_flags |= IOCB_NOWAIT; error = filemap_get_pages(iocb, iter, &pvec); @@ -2497,7 +2494,7 @@ ssize_t generic_file_buffered_read(struct kiocb *iocb, copied = copy_page_to_iter(page, offset, bytes, iter); - written += copied; + already_read += copied; iocb->ki_pos += copied; ra->prev_pos = iocb->ki_pos; @@ -2514,9 +2511,9 @@ put_pages: file_accessed(filp); - return written ? written : error; + return already_read ? already_read : error; } -EXPORT_SYMBOL_GPL(generic_file_buffered_read); +EXPORT_SYMBOL_GPL(filemap_read); /** * generic_file_read_iter - generic filesystem read routine @@ -2591,7 +2588,7 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) goto out; } - retval = generic_file_buffered_read(iocb, iter, retval); + retval = filemap_read(iocb, iter, retval); out: return retval; } -- cgit v1.2.3 From 2e9bd483159939ed2c0704b914294653c8341d25 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Wed, 24 Feb 2021 12:03:11 -0800 Subject: mm: memcg/slab: pre-allocate obj_cgroups for slab caches with SLAB_ACCOUNT In general it's unknown in advance if a slab page will contain accounted objects or not. In order to avoid memory waste, an obj_cgroup vector is allocated dynamically when a need to account of a new object arises. Such approach is memory efficient, but requires an expensive cmpxchg() to set up the memcg/objcgs pointer, because an allocation can race with a different allocation on another cpu. But in some common cases it's known for sure that a slab page will contain accounted objects: if the page belongs to a slab cache with a SLAB_ACCOUNT flag set. It includes such popular objects like vm_area_struct, anon_vma, task_struct, etc. In such cases we can pre-allocate the objcgs vector and simple assign it to the page without any atomic operations, because at this early stage the page is not visible to anyone else. A very simplistic benchmark (allocating 10000000 64-bytes objects in a row) shows ~15% win. In the real life it seems that most workloads are not very sensitive to the speed of (accounted) slab allocations. [guro@fb.com: open-code set_page_objcgs() and add some comments, by Johannes] Link: https://lkml.kernel.org/r/20201113001926.GA2934489@carbon.dhcp.thefacebook.com [akpm@linux-foundation.org: fix it for mm-slub-call-account_slab_page-after-slab-page-initialization-fix.patch] Link: https://lkml.kernel.org/r/20201110195753.530157-2-guro@fb.com Signed-off-by: Roman Gushchin Acked-by: Johannes Weiner Reviewed-by: Shakeel Butt Cc: Michal Hocko Cc: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 19 ------------------- mm/memcontrol.c | 23 +++++++++++++++++++---- mm/slab.c | 2 +- mm/slab.h | 14 ++++++++++---- mm/slub.c | 2 +- 5 files changed, 31 insertions(+), 29 deletions(-) (limited to 'include') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index eeb0b52203e9..7a4dd1cb19fe 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -475,19 +475,6 @@ static inline struct obj_cgroup **page_objcgs_check(struct page *page) return (struct obj_cgroup **)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); } -/* - * set_page_objcgs - associate a page with a object cgroups vector - * @page: a pointer to the page struct - * @objcgs: a pointer to the object cgroups vector - * - * Atomically associates a page with a vector of object cgroups. - */ -static inline bool set_page_objcgs(struct page *page, - struct obj_cgroup **objcgs) -{ - return !cmpxchg(&page->memcg_data, 0, (unsigned long)objcgs | - MEMCG_DATA_OBJCGS); -} #else static inline struct obj_cgroup **page_objcgs(struct page *page) { @@ -498,12 +485,6 @@ static inline struct obj_cgroup **page_objcgs_check(struct page *page) { return NULL; } - -static inline bool set_page_objcgs(struct page *page, - struct obj_cgroup **objcgs) -{ - return true; -} #endif static __always_inline bool memcg_stat_item_in_bytes(int idx) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 0b9bd354e97e..60ce452e42e6 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2935,9 +2935,10 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg) #ifdef CONFIG_MEMCG_KMEM int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s, - gfp_t gfp) + gfp_t gfp, bool new_page) { unsigned int objects = objs_per_slab_page(s, page); + unsigned long memcg_data; void *vec; vec = kcalloc_node(objects, sizeof(struct obj_cgroup *), gfp, @@ -2945,11 +2946,25 @@ int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s, if (!vec) return -ENOMEM; - if (!set_page_objcgs(page, vec)) + memcg_data = (unsigned long) vec | MEMCG_DATA_OBJCGS; + if (new_page) { + /* + * If the slab page is brand new and nobody can yet access + * it's memcg_data, no synchronization is required and + * memcg_data can be simply assigned. + */ + page->memcg_data = memcg_data; + } else if (cmpxchg(&page->memcg_data, 0, memcg_data)) { + /* + * If the slab page is already in use, somebody can allocate + * and assign obj_cgroups in parallel. In this case the existing + * objcg vector should be reused. + */ kfree(vec); - else - kmemleak_not_leak(vec); + return 0; + } + kmemleak_not_leak(vec); return 0; } diff --git a/mm/slab.c b/mm/slab.c index cdad64b2836d..9c9e0c255c4b 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -1379,7 +1379,7 @@ static struct page *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, return NULL; } - account_slab_page(page, cachep->gfporder, cachep); + account_slab_page(page, cachep->gfporder, cachep, flags); __SetPageSlab(page); /* Record if ALLOC_NO_WATERMARKS was set when allocating the slab */ if (sk_memalloc_socks() && page_is_pfmemalloc(page)) diff --git a/mm/slab.h b/mm/slab.h index 48dc466a3791..076582f58f68 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -238,7 +238,7 @@ static inline bool kmem_cache_debug_flags(struct kmem_cache *s, slab_flags_t fla #ifdef CONFIG_MEMCG_KMEM int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s, - gfp_t gfp); + gfp_t gfp, bool new_page); static inline void memcg_free_page_obj_cgroups(struct page *page) { @@ -315,7 +315,8 @@ static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s, page = virt_to_head_page(p[i]); if (!page_objcgs(page) && - memcg_alloc_page_obj_cgroups(page, s, flags)) { + memcg_alloc_page_obj_cgroups(page, s, flags, + false)) { obj_cgroup_uncharge(objcg, obj_full_size(s)); continue; } @@ -379,7 +380,8 @@ static inline struct mem_cgroup *memcg_from_slab_obj(void *ptr) } static inline int memcg_alloc_page_obj_cgroups(struct page *page, - struct kmem_cache *s, gfp_t gfp) + struct kmem_cache *s, gfp_t gfp, + bool new_page) { return 0; } @@ -420,8 +422,12 @@ static inline struct kmem_cache *virt_to_cache(const void *obj) } static __always_inline void account_slab_page(struct page *page, int order, - struct kmem_cache *s) + struct kmem_cache *s, + gfp_t gfp) { + if (memcg_kmem_enabled() && (s->flags & SLAB_ACCOUNT)) + memcg_alloc_page_obj_cgroups(page, s, gfp, true); + mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s), PAGE_SIZE << order); } diff --git a/mm/slub.c b/mm/slub.c index e0fef8f8d4bf..ca566361561e 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1785,7 +1785,7 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) page->objects = oo_objects(oo); - account_slab_page(page, oo_order(oo), s); + account_slab_page(page, oo_order(oo), s, flags); page->slab_cache = s; __SetPageSlab(page); -- cgit v1.2.3 From f3344adf38bdb3107d40483dd9501215ad40edce Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Wed, 24 Feb 2021 12:03:15 -0800 Subject: mm: memcontrol: optimize per-lruvec stats counter memory usage The vmstat threshold is 32 (MEMCG_CHARGE_BATCH), Actually the threshold can be as big as MEMCG_CHARGE_BATCH * PAGE_SIZE. It still fits into s32. So introduce struct batched_lruvec_stat to optimize memory usage. The size of struct lruvec_stat is 304 bytes on 64 bit systems. As it is a per-cpu structure. So with this patch, we can save 304 / 2 * ncpu bytes per-memcg per-node where ncpu is the number of the possible CPU. If there are c memory cgroup (include dying cgroup) and n NUMA node in the system. Finally, we can save (152 * ncpu * c * n) bytes. [akpm@linux-foundation.org: fix typo in comment] Link: https://lkml.kernel.org/r/20201210042121.39665-1-songmuchun@bytedance.com Signed-off-by: Muchun Song Reviewed-by: Shakeel Butt Cc: Johannes Weiner Cc: Michal Hocko Cc: Vladimir Davydov Cc: Shakeel Butt Cc: Roman Gushchin Cc: Stephen Rothwell Cc: Chris Down Cc: Yafang Shao Cc: Wei Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 14 ++++++++++++-- mm/memcontrol.c | 10 +++++++++- 2 files changed, 21 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 7a4dd1cb19fe..41bbf71edd9f 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -92,6 +92,10 @@ struct lruvec_stat { long count[NR_VM_NODE_STAT_ITEMS]; }; +struct batched_lruvec_stat { + s32 count[NR_VM_NODE_STAT_ITEMS]; +}; + /* * Bitmap of shrinker::id corresponding to memcg-aware shrinkers, * which have elements charged to this memcg. @@ -107,11 +111,17 @@ struct memcg_shrinker_map { struct mem_cgroup_per_node { struct lruvec lruvec; - /* Legacy local VM stats */ + /* + * Legacy local VM stats. This should be struct lruvec_stat and + * cannot be optimized to struct batched_lruvec_stat. Because + * the threshold of the lruvec_stat_cpu can be as big as + * MEMCG_CHARGE_BATCH * PAGE_SIZE. It can fit into s32. But this + * filed has no upper limit. + */ struct lruvec_stat __percpu *lruvec_stat_local; /* Subtree VM stats (batched updates) */ - struct lruvec_stat __percpu *lruvec_stat_cpu; + struct batched_lruvec_stat __percpu *lruvec_stat_cpu; atomic_long_t lruvec_stat[NR_VM_NODE_STAT_ITEMS]; unsigned long lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS]; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 60ce452e42e6..b259e7d8ce41 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5208,7 +5208,7 @@ static int alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node) return 1; } - pn->lruvec_stat_cpu = alloc_percpu_gfp(struct lruvec_stat, + pn->lruvec_stat_cpu = alloc_percpu_gfp(struct batched_lruvec_stat, GFP_KERNEL_ACCOUNT); if (!pn->lruvec_stat_cpu) { free_percpu(pn->lruvec_stat_local); @@ -7093,6 +7093,14 @@ static int __init mem_cgroup_init(void) { int cpu, node; + /* + * Currently s32 type (can refer to struct batched_lruvec_stat) is + * used for per-memcg-per-cpu caching of per-node statistics. In order + * to work fine, we should make sure that the overfill threshold can't + * exceed S32_MAX / PAGE_SIZE. + */ + BUILD_BUG_ON(MEMCG_CHARGE_BATCH > S32_MAX / PAGE_SIZE); + cpuhp_setup_state_nocalls(CPUHP_MM_MEMCQ_DEAD, "mm/memctrl:dead", NULL, memcg_hotplug_cpu_dead); -- cgit v1.2.3 From 69473e5de87389be6c0fa4a5d574a50c8f904fb3 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Wed, 24 Feb 2021 12:03:23 -0800 Subject: mm: memcontrol: convert NR_ANON_THPS account to pages Currently we use struct per_cpu_nodestat to cache the vmstat counters, which leads to inaccurate statistics especially THP vmstat counters. In the systems with hundreds of processors it can be GBs of memory. For example, for a 96 CPUs system, the threshold is the maximum number of 125. And the per cpu counters can cache 23.4375 GB in total. The THP page is already a form of batched addition (it will add 512 worth of memory in one go) so skipping the batching seems like sensible. Although every THP stats update overflows the per-cpu counter, resorting to atomic global updates. But it can make the statistics more accuracy for the THP vmstat counters. So we convert the NR_ANON_THPS account to pages. This patch is consistent with 8f182270dfec ("mm/swap.c: flush lru pvecs on compound page arrival"). Doing this also can make the unit of vmstat counters more unified. Finally, the unit of the vmstat counters are pages, kB and bytes. The B/KB suffix can tell us that the unit is bytes or kB. The rest which is without suffix are pages. Link: https://lkml.kernel.org/r/20201228164110.2838-3-songmuchun@bytedance.com Signed-off-by: Muchun Song Cc: Greg Kroah-Hartman Cc: Rafael. J. Wysocki Cc: Alexey Dobriyan Cc: Johannes Weiner Cc: Vladimir Davydov Cc: Hugh Dickins Cc: Shakeel Butt Cc: Roman Gushchin Cc: Sami Tolvanen Cc: Feng Tang Cc: NeilBrown Cc: Joonsoo Kim Cc: Randy Dunlap Cc: Michal Hocko Cc: Pankaj Gupta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/node.c | 15 +++++++++------ fs/proc/meminfo.c | 2 +- include/linux/mmzone.h | 13 +++++++++++++ mm/huge_memory.c | 3 ++- mm/memcontrol.c | 20 ++++++-------------- mm/page_alloc.c | 2 +- mm/rmap.c | 6 +++--- mm/vmstat.c | 11 +++++++++-- 8 files changed, 44 insertions(+), 28 deletions(-) (limited to 'include') diff --git a/drivers/base/node.c b/drivers/base/node.c index 04f71c7bc3f8..6da0c3508bc9 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -461,8 +461,7 @@ static ssize_t node_read_meminfo(struct device *dev, nid, K(sunreclaimable) #ifdef CONFIG_TRANSPARENT_HUGEPAGE , - nid, K(node_page_state(pgdat, NR_ANON_THPS) * - HPAGE_PMD_NR), + nid, K(node_page_state(pgdat, NR_ANON_THPS)), nid, K(node_page_state(pgdat, NR_SHMEM_THPS) * HPAGE_PMD_NR), nid, K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED) * @@ -519,10 +518,14 @@ static ssize_t node_read_vmstat(struct device *dev, sum_zone_numa_state(nid, i)); #endif - for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) - len += sysfs_emit_at(buf, len, "%s %lu\n", - node_stat_name(i), - node_page_state_pages(pgdat, i)); + for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) { + unsigned long pages = node_page_state_pages(pgdat, i); + + if (vmstat_item_print_in_thp(i)) + pages /= HPAGE_PMD_NR; + len += sysfs_emit_at(buf, len, "%s %lu\n", node_stat_name(i), + pages); + } return len; } diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index d6fc74619625..a635c8a84ddf 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -129,7 +129,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v) #ifdef CONFIG_TRANSPARENT_HUGEPAGE show_val_kb(m, "AnonHugePages: ", - global_node_page_state(NR_ANON_THPS) * HPAGE_PMD_NR); + global_node_page_state(NR_ANON_THPS)); show_val_kb(m, "ShmemHugePages: ", global_node_page_state(NR_SHMEM_THPS) * HPAGE_PMD_NR); show_val_kb(m, "ShmemPmdMapped: ", diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index b593316bff3d..67d50ef5dd20 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -209,6 +209,19 @@ enum node_stat_item { NR_VM_NODE_STAT_ITEMS }; +/* + * Returns true if the item should be printed in THPs (/proc/vmstat + * currently prints number of anon, file and shmem THPs. But the item + * is charged in pages). + */ +static __always_inline bool vmstat_item_print_in_thp(enum node_stat_item item) +{ + if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) + return false; + + return item == NR_ANON_THPS; +} + /* * Returns true if the value is measured in bytes (most vmstat values are * measured in pages). This defines the API part, the internal representation diff --git a/mm/huge_memory.c b/mm/huge_memory.c index f655137536eb..3691e863070a 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2176,7 +2176,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, lock_page_memcg(page); if (atomic_add_negative(-1, compound_mapcount_ptr(page))) { /* Last compound_mapcount is gone. */ - __dec_lruvec_page_state(page, NR_ANON_THPS); + __mod_lruvec_page_state(page, NR_ANON_THPS, + -HPAGE_PMD_NR); if (TestClearPageDoubleMap(page)) { /* No need in mapcount reference anymore */ for (i = 0; i < HPAGE_PMD_NR; i++) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index e31e47e7bab2..b2405f049006 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1533,7 +1533,7 @@ static struct memory_stat memory_stats[] = { * on some architectures, the macro of HPAGE_PMD_SIZE is not * constant(e.g. powerpc). */ - { "anon_thp", 0, NR_ANON_THPS }, + { "anon_thp", PAGE_SIZE, NR_ANON_THPS }, { "file_thp", 0, NR_FILE_THPS }, { "shmem_thp", 0, NR_SHMEM_THPS }, #endif @@ -1566,8 +1566,7 @@ static int __init memory_stats_init(void) for (i = 0; i < ARRAY_SIZE(memory_stats); i++) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE - if (memory_stats[i].idx == NR_ANON_THPS || - memory_stats[i].idx == NR_FILE_THPS || + if (memory_stats[i].idx == NR_FILE_THPS || memory_stats[i].idx == NR_SHMEM_THPS) memory_stats[i].ratio = HPAGE_PMD_SIZE; #endif @@ -4087,10 +4086,6 @@ static int memcg_stat_show(struct seq_file *m, void *v) if (memcg1_stats[i] == MEMCG_SWAP && !do_memsw_account()) continue; nr = memcg_page_state_local(memcg, memcg1_stats[i]); -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - if (memcg1_stats[i] == NR_ANON_THPS) - nr *= HPAGE_PMD_NR; -#endif seq_printf(m, "%s %lu\n", memcg1_stat_names[i], nr * PAGE_SIZE); } @@ -4121,10 +4116,6 @@ static int memcg_stat_show(struct seq_file *m, void *v) if (memcg1_stats[i] == MEMCG_SWAP && !do_memsw_account()) continue; nr = memcg_page_state(memcg, memcg1_stats[i]); -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - if (memcg1_stats[i] == NR_ANON_THPS) - nr *= HPAGE_PMD_NR; -#endif seq_printf(m, "total_%s %llu\n", memcg1_stat_names[i], (u64)nr * PAGE_SIZE); } @@ -5652,10 +5643,11 @@ static int mem_cgroup_move_account(struct page *page, __mod_lruvec_state(from_vec, NR_ANON_MAPPED, -nr_pages); __mod_lruvec_state(to_vec, NR_ANON_MAPPED, nr_pages); if (PageTransHuge(page)) { - __dec_lruvec_state(from_vec, NR_ANON_THPS); - __inc_lruvec_state(to_vec, NR_ANON_THPS); + __mod_lruvec_state(from_vec, NR_ANON_THPS, + -nr_pages); + __mod_lruvec_state(to_vec, NR_ANON_THPS, + nr_pages); } - } } else { __mod_lruvec_state(from_vec, NR_FILE_PAGES, -nr_pages); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index ef5070fed76b..2e2e47f8714b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5587,7 +5587,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) K(node_page_state(pgdat, NR_SHMEM_THPS) * HPAGE_PMD_NR), K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED) * HPAGE_PMD_NR), - K(node_page_state(pgdat, NR_ANON_THPS) * HPAGE_PMD_NR), + K(node_page_state(pgdat, NR_ANON_THPS)), #endif K(node_page_state(pgdat, NR_WRITEBACK_TEMP)), node_page_state(pgdat, NR_KERNEL_STACK_KB), diff --git a/mm/rmap.c b/mm/rmap.c index 08c56aaf72eb..c4d5c63cfd29 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1144,7 +1144,7 @@ void do_page_add_anon_rmap(struct page *page, * disabled. */ if (compound) - __inc_lruvec_page_state(page, NR_ANON_THPS); + __mod_lruvec_page_state(page, NR_ANON_THPS, nr); __mod_lruvec_page_state(page, NR_ANON_MAPPED, nr); } @@ -1186,7 +1186,7 @@ void page_add_new_anon_rmap(struct page *page, if (hpage_pincount_available(page)) atomic_set(compound_pincount_ptr(page), 0); - __inc_lruvec_page_state(page, NR_ANON_THPS); + __mod_lruvec_page_state(page, NR_ANON_THPS, nr); } else { /* Anon THP always mapped first with PMD */ VM_BUG_ON_PAGE(PageTransCompound(page), page); @@ -1292,7 +1292,7 @@ static void page_remove_anon_compound_rmap(struct page *page) if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) return; - __dec_lruvec_page_state(page, NR_ANON_THPS); + __mod_lruvec_page_state(page, NR_ANON_THPS, -thp_nr_pages(page)); if (TestClearPageDoubleMap(page)) { /* diff --git a/mm/vmstat.c b/mm/vmstat.c index f8942160fc95..07dc0af50cf0 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1619,8 +1619,12 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, if (is_zone_first_populated(pgdat, zone)) { seq_printf(m, "\n per-node stats"); for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) { + unsigned long pages = node_page_state_pages(pgdat, i); + + if (vmstat_item_print_in_thp(i)) + pages /= HPAGE_PMD_NR; seq_printf(m, "\n %-12s %lu", node_stat_name(i), - node_page_state_pages(pgdat, i)); + pages); } } seq_printf(m, @@ -1740,8 +1744,11 @@ static void *vmstat_start(struct seq_file *m, loff_t *pos) v += NR_VM_NUMA_STAT_ITEMS; #endif - for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) + for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) { v[i] = global_node_page_state_pages(i); + if (vmstat_item_print_in_thp(i)) + v[i] /= HPAGE_PMD_NR; + } v += NR_VM_NODE_STAT_ITEMS; global_dirty_limits(v + NR_DIRTY_BG_THRESHOLD, -- cgit v1.2.3 From bf9ecead53c89d3d2cf60acbc460174ebbcf0027 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Wed, 24 Feb 2021 12:03:27 -0800 Subject: mm: memcontrol: convert NR_FILE_THPS account to pages Currently we use struct per_cpu_nodestat to cache the vmstat counters, which leads to inaccurate statistics especially THP vmstat counters. In the systems with if hundreds of processors it can be GBs of memory. For example, for a 96 CPUs system, the threshold is the maximum number of 125. And the per cpu counters can cache 23.4375 GB in total. The THP page is already a form of batched addition (it will add 512 worth of memory in one go) so skipping the batching seems like sensible. Although every THP stats update overflows the per-cpu counter, resorting to atomic global updates. But it can make the statistics more accuracy for the THP vmstat counters. So we convert the NR_FILE_THPS account to pages. This patch is consistent with 8f182270dfec ("mm/swap.c: flush lru pvecs on compound page arrival"). Doing this also can make the unit of vmstat counters more unified. Finally, the unit of the vmstat counters are pages, kB and bytes. The B/KB suffix can tell us that the unit is bytes or kB. The rest which is without suffix are pages. Link: https://lkml.kernel.org/r/20201228164110.2838-4-songmuchun@bytedance.com Signed-off-by: Muchun Song Cc: Alexey Dobriyan Cc: Feng Tang Cc: Greg Kroah-Hartman Cc: Hugh Dickins Cc: Johannes Weiner Cc: Joonsoo Kim Cc: Michal Hocko Cc: NeilBrown Cc: Pankaj Gupta Cc: Rafael. J. Wysocki Cc: Randy Dunlap Cc: Roman Gushchin Cc: Sami Tolvanen Cc: Shakeel Butt Cc: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/node.c | 3 +-- fs/proc/meminfo.c | 2 +- include/linux/mmzone.h | 3 ++- mm/filemap.c | 2 +- mm/huge_memory.c | 5 ++++- mm/khugepaged.c | 4 +++- mm/memcontrol.c | 5 ++--- 7 files changed, 14 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/drivers/base/node.c b/drivers/base/node.c index 6da0c3508bc9..d5952f754911 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -466,8 +466,7 @@ static ssize_t node_read_meminfo(struct device *dev, HPAGE_PMD_NR), nid, K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED) * HPAGE_PMD_NR), - nid, K(node_page_state(pgdat, NR_FILE_THPS) * - HPAGE_PMD_NR), + nid, K(node_page_state(pgdat, NR_FILE_THPS)), nid, K(node_page_state(pgdat, NR_FILE_PMDMAPPED) * HPAGE_PMD_NR) #endif diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index a635c8a84ddf..7ea4679880c8 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -135,7 +135,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v) show_val_kb(m, "ShmemPmdMapped: ", global_node_page_state(NR_SHMEM_PMDMAPPED) * HPAGE_PMD_NR); show_val_kb(m, "FileHugePages: ", - global_node_page_state(NR_FILE_THPS) * HPAGE_PMD_NR); + global_node_page_state(NR_FILE_THPS)); show_val_kb(m, "FilePmdMapped: ", global_node_page_state(NR_FILE_PMDMAPPED) * HPAGE_PMD_NR); #endif diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 67d50ef5dd20..b751a9898bb6 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -219,7 +219,8 @@ static __always_inline bool vmstat_item_print_in_thp(enum node_stat_item item) if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) return false; - return item == NR_ANON_THPS; + return item == NR_ANON_THPS || + item == NR_FILE_THPS; } /* diff --git a/mm/filemap.c b/mm/filemap.c index 820d81901eae..9efe059e2b58 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -208,7 +208,7 @@ static void unaccount_page_cache_page(struct address_space *mapping, if (PageTransHuge(page)) __dec_lruvec_page_state(page, NR_SHMEM_THPS); } else if (PageTransHuge(page)) { - __dec_lruvec_page_state(page, NR_FILE_THPS); + __mod_lruvec_page_state(page, NR_FILE_THPS, -nr); filemap_nr_thps_dec(mapping); } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 3691e863070a..77181faa2340 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2752,10 +2752,13 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) } spin_unlock(&ds_queue->split_queue_lock); if (mapping) { + int nr = thp_nr_pages(head); + if (PageSwapBacked(head)) __dec_lruvec_page_state(head, NR_SHMEM_THPS); else - __dec_lruvec_page_state(head, NR_FILE_THPS); + __mod_lruvec_page_state(head, NR_FILE_THPS, + -nr); } __split_huge_page(page, list, end); diff --git a/mm/khugepaged.c b/mm/khugepaged.c index fb0fdaec34d5..c427fe2ca7ff 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1643,6 +1643,7 @@ static void collapse_file(struct mm_struct *mm, XA_STATE_ORDER(xas, &mapping->i_pages, start, HPAGE_PMD_ORDER); int nr_none = 0, result = SCAN_SUCCEED; bool is_shmem = shmem_file(file); + int nr; VM_BUG_ON(!IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && !is_shmem); VM_BUG_ON(start & (HPAGE_PMD_NR - 1)); @@ -1854,11 +1855,12 @@ out_unlock: put_page(page); goto xa_unlocked; } + nr = thp_nr_pages(new_page); if (is_shmem) __inc_lruvec_page_state(new_page, NR_SHMEM_THPS); else { - __inc_lruvec_page_state(new_page, NR_FILE_THPS); + __mod_lruvec_page_state(new_page, NR_FILE_THPS, nr); filemap_nr_thps_inc(mapping); } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index b2405f049006..fc552f57d3fb 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1534,7 +1534,7 @@ static struct memory_stat memory_stats[] = { * constant(e.g. powerpc). */ { "anon_thp", PAGE_SIZE, NR_ANON_THPS }, - { "file_thp", 0, NR_FILE_THPS }, + { "file_thp", PAGE_SIZE, NR_FILE_THPS }, { "shmem_thp", 0, NR_SHMEM_THPS }, #endif { "inactive_anon", PAGE_SIZE, NR_INACTIVE_ANON }, @@ -1566,8 +1566,7 @@ static int __init memory_stats_init(void) for (i = 0; i < ARRAY_SIZE(memory_stats); i++) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE - if (memory_stats[i].idx == NR_FILE_THPS || - memory_stats[i].idx == NR_SHMEM_THPS) + if (memory_stats[i].idx == NR_SHMEM_THPS) memory_stats[i].ratio = HPAGE_PMD_SIZE; #endif VM_BUG_ON(!memory_stats[i].ratio); -- cgit v1.2.3 From 57b2847d3c1dc154923578efb47a12302a57d700 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Wed, 24 Feb 2021 12:03:31 -0800 Subject: mm: memcontrol: convert NR_SHMEM_THPS account to pages Currently we use struct per_cpu_nodestat to cache the vmstat counters, which leads to inaccurate statistics especially THP vmstat counters. In the systems with hundreds of processors it can be GBs of memory. For example, for a 96 CPUs system, the threshold is the maximum number of 125. And the per cpu counters can cache 23.4375 GB in total. The THP page is already a form of batched addition (it will add 512 worth of memory in one go) so skipping the batching seems like sensible. Although every THP stats update overflows the per-cpu counter, resorting to atomic global updates. But it can make the statistics more accuracy for the THP vmstat counters. So we convert the NR_SHMEM_THPS account to pages. This patch is consistent with 8f182270dfec ("mm/swap.c: flush lru pvecs on compound page arrival"). Doing this also can make the unit of vmstat counters more unified. Finally, the unit of the vmstat counters are pages, kB and bytes. The B/KB suffix can tell us that the unit is bytes or kB. The rest which is without suffix are pages. Link: https://lkml.kernel.org/r/20201228164110.2838-5-songmuchun@bytedance.com Signed-off-by: Muchun Song Cc: Alexey Dobriyan Cc: Feng Tang Cc: Greg Kroah-Hartman Cc: Hugh Dickins Cc: Johannes Weiner Cc: Joonsoo Kim Cc: Michal Hocko Cc: NeilBrown Cc: Pankaj Gupta Cc: Rafael. J. Wysocki Cc: Randy Dunlap Cc: Roman Gushchin Cc: Sami Tolvanen Cc: Shakeel Butt Cc: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/node.c | 3 +-- fs/proc/meminfo.c | 2 +- include/linux/mmzone.h | 3 ++- mm/filemap.c | 2 +- mm/huge_memory.c | 3 ++- mm/khugepaged.c | 2 +- mm/memcontrol.c | 26 ++------------------------ mm/page_alloc.c | 2 +- mm/shmem.c | 2 +- 9 files changed, 12 insertions(+), 33 deletions(-) (limited to 'include') diff --git a/drivers/base/node.c b/drivers/base/node.c index d5952f754911..6d5ac6ffb6e1 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -462,8 +462,7 @@ static ssize_t node_read_meminfo(struct device *dev, #ifdef CONFIG_TRANSPARENT_HUGEPAGE , nid, K(node_page_state(pgdat, NR_ANON_THPS)), - nid, K(node_page_state(pgdat, NR_SHMEM_THPS) * - HPAGE_PMD_NR), + nid, K(node_page_state(pgdat, NR_SHMEM_THPS)), nid, K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED) * HPAGE_PMD_NR), nid, K(node_page_state(pgdat, NR_FILE_THPS)), diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index 7ea4679880c8..cfb107eaa3e6 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -131,7 +131,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v) show_val_kb(m, "AnonHugePages: ", global_node_page_state(NR_ANON_THPS)); show_val_kb(m, "ShmemHugePages: ", - global_node_page_state(NR_SHMEM_THPS) * HPAGE_PMD_NR); + global_node_page_state(NR_SHMEM_THPS)); show_val_kb(m, "ShmemPmdMapped: ", global_node_page_state(NR_SHMEM_PMDMAPPED) * HPAGE_PMD_NR); show_val_kb(m, "FileHugePages: ", diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index b751a9898bb6..788837f40b38 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -220,7 +220,8 @@ static __always_inline bool vmstat_item_print_in_thp(enum node_stat_item item) return false; return item == NR_ANON_THPS || - item == NR_FILE_THPS; + item == NR_FILE_THPS || + item == NR_SHMEM_THPS; } /* diff --git a/mm/filemap.c b/mm/filemap.c index 9efe059e2b58..46a8b9e82434 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -206,7 +206,7 @@ static void unaccount_page_cache_page(struct address_space *mapping, if (PageSwapBacked(page)) { __mod_lruvec_page_state(page, NR_SHMEM, -nr); if (PageTransHuge(page)) - __dec_lruvec_page_state(page, NR_SHMEM_THPS); + __mod_lruvec_page_state(page, NR_SHMEM_THPS, -nr); } else if (PageTransHuge(page)) { __mod_lruvec_page_state(page, NR_FILE_THPS, -nr); filemap_nr_thps_dec(mapping); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 77181faa2340..86a3015ba54f 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2755,7 +2755,8 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) int nr = thp_nr_pages(head); if (PageSwapBacked(head)) - __dec_lruvec_page_state(head, NR_SHMEM_THPS); + __mod_lruvec_page_state(head, NR_SHMEM_THPS, + -nr); else __mod_lruvec_page_state(head, NR_FILE_THPS, -nr); diff --git a/mm/khugepaged.c b/mm/khugepaged.c index c427fe2ca7ff..75e246f680f4 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1858,7 +1858,7 @@ out_unlock: nr = thp_nr_pages(new_page); if (is_shmem) - __inc_lruvec_page_state(new_page, NR_SHMEM_THPS); + __mod_lruvec_page_state(new_page, NR_SHMEM_THPS, nr); else { __mod_lruvec_page_state(new_page, NR_FILE_THPS, nr); filemap_nr_thps_inc(mapping); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index fc552f57d3fb..d3a0c59210e7 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1516,7 +1516,7 @@ struct memory_stat { unsigned int idx; }; -static struct memory_stat memory_stats[] = { +static const struct memory_stat memory_stats[] = { { "anon", PAGE_SIZE, NR_ANON_MAPPED }, { "file", PAGE_SIZE, NR_FILE_PAGES }, { "kernel_stack", 1024, NR_KERNEL_STACK_KB }, @@ -1528,14 +1528,9 @@ static struct memory_stat memory_stats[] = { { "file_dirty", PAGE_SIZE, NR_FILE_DIRTY }, { "file_writeback", PAGE_SIZE, NR_WRITEBACK }, #ifdef CONFIG_TRANSPARENT_HUGEPAGE - /* - * The ratio will be initialized in memory_stats_init(). Because - * on some architectures, the macro of HPAGE_PMD_SIZE is not - * constant(e.g. powerpc). - */ { "anon_thp", PAGE_SIZE, NR_ANON_THPS }, { "file_thp", PAGE_SIZE, NR_FILE_THPS }, - { "shmem_thp", 0, NR_SHMEM_THPS }, + { "shmem_thp", PAGE_SIZE, NR_SHMEM_THPS }, #endif { "inactive_anon", PAGE_SIZE, NR_INACTIVE_ANON }, { "active_anon", PAGE_SIZE, NR_ACTIVE_ANON }, @@ -1560,23 +1555,6 @@ static struct memory_stat memory_stats[] = { { "workingset_nodereclaim", 1, WORKINGSET_NODERECLAIM }, }; -static int __init memory_stats_init(void) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(memory_stats); i++) { -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - if (memory_stats[i].idx == NR_SHMEM_THPS) - memory_stats[i].ratio = HPAGE_PMD_SIZE; -#endif - VM_BUG_ON(!memory_stats[i].ratio); - VM_BUG_ON(memory_stats[i].idx >= MEMCG_NR_STAT); - } - - return 0; -} -pure_initcall(memory_stats_init); - static char *memory_stat_format(struct mem_cgroup *memcg) { struct seq_buf s; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 2e2e47f8714b..df292d8e659b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5584,7 +5584,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) K(node_page_state(pgdat, NR_WRITEBACK)), K(node_page_state(pgdat, NR_SHMEM)), #ifdef CONFIG_TRANSPARENT_HUGEPAGE - K(node_page_state(pgdat, NR_SHMEM_THPS) * HPAGE_PMD_NR), + K(node_page_state(pgdat, NR_SHMEM_THPS)), K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED) * HPAGE_PMD_NR), K(node_page_state(pgdat, NR_ANON_THPS)), diff --git a/mm/shmem.c b/mm/shmem.c index 7924b3bf46fb..ff741d229701 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -713,7 +713,7 @@ next: } if (PageTransHuge(page)) { count_vm_event(THP_FILE_ALLOC); - __inc_lruvec_page_state(page, NR_SHMEM_THPS); + __mod_lruvec_page_state(page, NR_SHMEM_THPS, nr); } mapping->nrpages += nr; __mod_lruvec_page_state(page, NR_FILE_PAGES, nr); -- cgit v1.2.3 From a1528e21f8915e16252cda1137fe29672c918361 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Wed, 24 Feb 2021 12:03:35 -0800 Subject: mm: memcontrol: convert NR_SHMEM_PMDMAPPED account to pages Currently we use struct per_cpu_nodestat to cache the vmstat counters, which leads to inaccurate statistics especially THP vmstat counters. In the systems with hundreds of processors it can be GBs of memory. For example, for a 96 CPUs system, the threshold is the maximum number of 125. And the per cpu counters can cache 23.4375 GB in total. The THP page is already a form of batched addition (it will add 512 worth of memory in one go) so skipping the batching seems like sensible. Although every THP stats update overflows the per-cpu counter, resorting to atomic global updates. But it can make the statistics more accuracy for the THP vmstat counters. So we convert the NR_SHMEM_PMDMAPPED account to pages. This patch is consistent with 8f182270dfec ("mm/swap.c: flush lru pvecs on compound page arrival"). Doing this also can make the unit of vmstat counters more unified. Finally, the unit of the vmstat counters are pages, kB and bytes. The B/KB suffix can tell us that the unit is bytes or kB. The rest which is without suffix are pages. Link: https://lkml.kernel.org/r/20201228164110.2838-6-songmuchun@bytedance.com Signed-off-by: Muchun Song Cc: Alexey Dobriyan Cc: Feng Tang Cc: Greg Kroah-Hartman Cc: Hugh Dickins Cc: Johannes Weiner Cc: Joonsoo Kim Cc: Michal Hocko Cc: NeilBrown Cc: Pankaj Gupta Cc: Rafael. J. Wysocki Cc: Randy Dunlap Cc: Roman Gushchin Cc: Sami Tolvanen Cc: Shakeel Butt Cc: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/node.c | 3 +-- fs/proc/meminfo.c | 2 +- include/linux/mmzone.h | 3 ++- mm/page_alloc.c | 3 +-- mm/rmap.c | 14 ++++++++++---- 5 files changed, 15 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/drivers/base/node.c b/drivers/base/node.c index 6d5ac6ffb6e1..7a66aefe4e46 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -463,8 +463,7 @@ static ssize_t node_read_meminfo(struct device *dev, , nid, K(node_page_state(pgdat, NR_ANON_THPS)), nid, K(node_page_state(pgdat, NR_SHMEM_THPS)), - nid, K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED) * - HPAGE_PMD_NR), + nid, K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED)), nid, K(node_page_state(pgdat, NR_FILE_THPS)), nid, K(node_page_state(pgdat, NR_FILE_PMDMAPPED) * HPAGE_PMD_NR) diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index cfb107eaa3e6..c61f440570f9 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -133,7 +133,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v) show_val_kb(m, "ShmemHugePages: ", global_node_page_state(NR_SHMEM_THPS)); show_val_kb(m, "ShmemPmdMapped: ", - global_node_page_state(NR_SHMEM_PMDMAPPED) * HPAGE_PMD_NR); + global_node_page_state(NR_SHMEM_PMDMAPPED)); show_val_kb(m, "FileHugePages: ", global_node_page_state(NR_FILE_THPS)); show_val_kb(m, "FilePmdMapped: ", diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 788837f40b38..7bdbfeeb5c8c 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -221,7 +221,8 @@ static __always_inline bool vmstat_item_print_in_thp(enum node_stat_item item) return item == NR_ANON_THPS || item == NR_FILE_THPS || - item == NR_SHMEM_THPS; + item == NR_SHMEM_THPS || + item == NR_SHMEM_PMDMAPPED; } /* diff --git a/mm/page_alloc.c b/mm/page_alloc.c index df292d8e659b..069561aadc7b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5585,8 +5585,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) K(node_page_state(pgdat, NR_SHMEM)), #ifdef CONFIG_TRANSPARENT_HUGEPAGE K(node_page_state(pgdat, NR_SHMEM_THPS)), - K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED) - * HPAGE_PMD_NR), + K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED)), K(node_page_state(pgdat, NR_ANON_THPS)), #endif K(node_page_state(pgdat, NR_WRITEBACK_TEMP)), diff --git a/mm/rmap.c b/mm/rmap.c index c4d5c63cfd29..1c1b576c0627 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1211,14 +1211,17 @@ void page_add_file_rmap(struct page *page, bool compound) VM_BUG_ON_PAGE(compound && !PageTransHuge(page), page); lock_page_memcg(page); if (compound && PageTransHuge(page)) { - for (i = 0, nr = 0; i < thp_nr_pages(page); i++) { + int nr_pages = thp_nr_pages(page); + + for (i = 0, nr = 0; i < nr_pages; i++) { if (atomic_inc_and_test(&page[i]._mapcount)) nr++; } if (!atomic_inc_and_test(compound_mapcount_ptr(page))) goto out; if (PageSwapBacked(page)) - __inc_node_page_state(page, NR_SHMEM_PMDMAPPED); + __mod_lruvec_page_state(page, NR_SHMEM_PMDMAPPED, + nr_pages); else __inc_node_page_state(page, NR_FILE_PMDMAPPED); } else { @@ -1252,14 +1255,17 @@ static void page_remove_file_rmap(struct page *page, bool compound) /* page still mapped by someone else? */ if (compound && PageTransHuge(page)) { - for (i = 0, nr = 0; i < thp_nr_pages(page); i++) { + int nr_pages = thp_nr_pages(page); + + for (i = 0, nr = 0; i < nr_pages; i++) { if (atomic_add_negative(-1, &page[i]._mapcount)) nr++; } if (!atomic_add_negative(-1, compound_mapcount_ptr(page))) return; if (PageSwapBacked(page)) - __dec_node_page_state(page, NR_SHMEM_PMDMAPPED); + __mod_lruvec_page_state(page, NR_SHMEM_PMDMAPPED, + -nr_pages); else __dec_node_page_state(page, NR_FILE_PMDMAPPED); } else { -- cgit v1.2.3 From 380780e71895ae301505ffcec8f954ab3666a4c7 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Wed, 24 Feb 2021 12:03:39 -0800 Subject: mm: memcontrol: convert NR_FILE_PMDMAPPED account to pages Currently we use struct per_cpu_nodestat to cache the vmstat counters, which leads to inaccurate statistics especially THP vmstat counters. In the systems with hundreds of processors it can be GBs of memory. For example, for a 96 CPUs system, the threshold is the maximum number of 125. And the per cpu counters can cache 23.4375 GB in total. The THP page is already a form of batched addition (it will add 512 worth of memory in one go) so skipping the batching seems like sensible. Although every THP stats update overflows the per-cpu counter, resorting to atomic global updates. But it can make the statistics more accuracy for the THP vmstat counters. So we convert the NR_FILE_PMDMAPPED account to pages. This patch is consistent with 8f182270dfec ("mm/swap.c: flush lru pvecs on compound page arrival"). Doing this also can make the unit of vmstat counters more unified. Finally, the unit of the vmstat counters are pages, kB and bytes. The B/KB suffix can tell us that the unit is bytes or kB. The rest which is without suffix are pages. Link: https://lkml.kernel.org/r/20201228164110.2838-7-songmuchun@bytedance.com Signed-off-by: Muchun Song Cc: Alexey Dobriyan Cc: Feng Tang Cc: Greg Kroah-Hartman Cc: Hugh Dickins Cc: Johannes Weiner Cc: Joonsoo Kim Cc: Michal Hocko Cc: NeilBrown Cc: Pankaj Gupta Cc: Rafael. J. Wysocki Cc: Randy Dunlap Cc: Roman Gushchin Cc: Sami Tolvanen Cc: Shakeel Butt Cc: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/node.c | 3 +-- fs/proc/meminfo.c | 2 +- include/linux/mmzone.h | 3 ++- mm/rmap.c | 6 ++++-- 4 files changed, 8 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/drivers/base/node.c b/drivers/base/node.c index 7a66aefe4e46..d02d86aec19f 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -465,8 +465,7 @@ static ssize_t node_read_meminfo(struct device *dev, nid, K(node_page_state(pgdat, NR_SHMEM_THPS)), nid, K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED)), nid, K(node_page_state(pgdat, NR_FILE_THPS)), - nid, K(node_page_state(pgdat, NR_FILE_PMDMAPPED) * - HPAGE_PMD_NR) + nid, K(node_page_state(pgdat, NR_FILE_PMDMAPPED)) #endif ); len += hugetlb_report_node_meminfo(buf, len, nid); diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index c61f440570f9..6fa761c9cc78 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -137,7 +137,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v) show_val_kb(m, "FileHugePages: ", global_node_page_state(NR_FILE_THPS)); show_val_kb(m, "FilePmdMapped: ", - global_node_page_state(NR_FILE_PMDMAPPED) * HPAGE_PMD_NR); + global_node_page_state(NR_FILE_PMDMAPPED)); #endif #ifdef CONFIG_CMA diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 7bdbfeeb5c8c..66d68e5d5a0f 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -222,7 +222,8 @@ static __always_inline bool vmstat_item_print_in_thp(enum node_stat_item item) return item == NR_ANON_THPS || item == NR_FILE_THPS || item == NR_SHMEM_THPS || - item == NR_SHMEM_PMDMAPPED; + item == NR_SHMEM_PMDMAPPED || + item == NR_FILE_PMDMAPPED; } /* diff --git a/mm/rmap.c b/mm/rmap.c index 1c1b576c0627..5ebf16fae4b9 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1223,7 +1223,8 @@ void page_add_file_rmap(struct page *page, bool compound) __mod_lruvec_page_state(page, NR_SHMEM_PMDMAPPED, nr_pages); else - __inc_node_page_state(page, NR_FILE_PMDMAPPED); + __mod_lruvec_page_state(page, NR_FILE_PMDMAPPED, + nr_pages); } else { if (PageTransCompound(page) && page_mapping(page)) { VM_WARN_ON_ONCE(!PageLocked(page)); @@ -1267,7 +1268,8 @@ static void page_remove_file_rmap(struct page *page, bool compound) __mod_lruvec_page_state(page, NR_SHMEM_PMDMAPPED, -nr_pages); else - __dec_node_page_state(page, NR_FILE_PMDMAPPED); + __mod_lruvec_page_state(page, NR_FILE_PMDMAPPED, + -nr_pages); } else { if (!atomic_add_negative(-1, &page->_mapcount)) return; -- cgit v1.2.3 From b6038942480e574c697ea1a80019bbe586c1d654 Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Wed, 24 Feb 2021 12:03:55 -0800 Subject: mm: memcg: add swapcache stat for memcg v2 This patch adds swapcache stat for the cgroup v2. The swapcache represents the memory that is accounted against both the memory and the swap limit of the cgroup. The main motivation behind exposing the swapcache stat is for enabling users to gracefully migrate from cgroup v1's memsw counter to cgroup v2's memory and swap counters. Cgroup v1's memsw limit allows users to limit the memory+swap usage of a workload but without control on the exact proportion of memory and swap. Cgroup v2 provides separate limits for memory and swap which enables more control on the exact usage of memory and swap individually for the workload. With some little subtleties, the v1's memsw limit can be switched with the sum of the v2's memory and swap limits. However the alternative for memsw usage is not yet available in cgroup v2. Exposing per-cgroup swapcache stat enables that alternative. Adding the memory usage and swap usage and subtracting the swapcache will approximate the memsw usage. This will help in the transparent migration of the workloads depending on memsw usage and limit to v2' memory and swap counters. The reasons these applications are still interested in this approximate memsw usage are: (1) these applications are not really interested in two separate memory and swap usage metrics. A single usage metric is more simple to use and reason about for them. (2) The memsw usage metric hides the underlying system's swap setup from the applications. Applications with multiple instances running in a datacenter with heterogeneous systems (some have swap and some don't) will keep seeing a consistent view of their usage. [akpm@linux-foundation.org: fix CONFIG_SWAP=n build] Link: https://lkml.kernel.org/r/20210108155813.2914586-3-shakeelb@google.com Signed-off-by: Shakeel Butt Acked-by: Michal Hocko Reviewed-by: Roman Gushchin Cc: Johannes Weiner Cc: Muchun Song Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/cgroup-v2.rst | 4 ++++ drivers/base/node.c | 6 ++++++ include/linux/mmzone.h | 3 +++ include/linux/swap.h | 6 +++++- mm/memcontrol.c | 3 +++ mm/migrate.c | 6 ++++++ mm/swap_state.c | 28 ++-------------------------- mm/vmstat.c | 3 +++ 8 files changed, 32 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index c513eafaddea..9acc57f68f31 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1299,6 +1299,10 @@ PAGE_SIZE multiple when read back. Amount of cached filesystem data that was modified and is currently being written back to disk + swapcached + Amount of swap cached in memory. The swapcache is accounted + against both memory and swap usage. + anon_thp Amount of memory used in anonymous mappings backed by transparent hugepages diff --git a/drivers/base/node.c b/drivers/base/node.c index d02d86aec19f..f449dbb2c746 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -372,14 +372,19 @@ static ssize_t node_read_meminfo(struct device *dev, struct pglist_data *pgdat = NODE_DATA(nid); struct sysinfo i; unsigned long sreclaimable, sunreclaimable; + unsigned long swapcached = 0; si_meminfo_node(&i, nid); sreclaimable = node_page_state_pages(pgdat, NR_SLAB_RECLAIMABLE_B); sunreclaimable = node_page_state_pages(pgdat, NR_SLAB_UNRECLAIMABLE_B); +#ifdef CONFIG_SWAP + swapcached = node_page_state_pages(pgdat, NR_SWAPCACHE); +#endif len = sysfs_emit_at(buf, len, "Node %d MemTotal: %8lu kB\n" "Node %d MemFree: %8lu kB\n" "Node %d MemUsed: %8lu kB\n" + "Node %d SwapCached: %8lu kB\n" "Node %d Active: %8lu kB\n" "Node %d Inactive: %8lu kB\n" "Node %d Active(anon): %8lu kB\n" @@ -391,6 +396,7 @@ static ssize_t node_read_meminfo(struct device *dev, nid, K(i.totalram), nid, K(i.freeram), nid, K(i.totalram - i.freeram), + nid, K(swapcached), nid, K(node_page_state(pgdat, NR_ACTIVE_ANON) + node_page_state(pgdat, NR_ACTIVE_FILE)), nid, K(node_page_state(pgdat, NR_INACTIVE_ANON) + diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 66d68e5d5a0f..fc99e9241846 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -206,6 +206,9 @@ enum node_stat_item { NR_KERNEL_SCS_KB, /* measured in KiB */ #endif NR_PAGETABLE, /* used for pagetables */ +#ifdef CONFIG_SWAP + NR_SWAPCACHE, +#endif NR_VM_NODE_STAT_ITEMS }; diff --git a/include/linux/swap.h b/include/linux/swap.h index 3f1f7ae0fbe9..0d64a2bc7e00 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -408,7 +408,11 @@ extern struct address_space *swapper_spaces[]; #define swap_address_space(entry) \ (&swapper_spaces[swp_type(entry)][swp_offset(entry) \ >> SWAP_ADDRESS_SPACE_SHIFT]) -extern unsigned long total_swapcache_pages(void); +static inline unsigned long total_swapcache_pages(void) +{ + return global_node_page_state(NR_SWAPCACHE); +} + extern void show_swap_cache_info(void); extern int add_to_swap(struct page *page); extern void *get_shadow_from_swap_cache(swp_entry_t entry); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 5435b370c929..58edfb6614b8 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1521,6 +1521,9 @@ static const struct memory_stat memory_stats[] = { { "file_mapped", NR_FILE_MAPPED }, { "file_dirty", NR_FILE_DIRTY }, { "file_writeback", NR_WRITEBACK }, +#ifdef CONFIG_SWAP + { "swapcached", NR_SWAPCACHE }, +#endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE { "anon_thp", NR_ANON_THPS }, { "file_thp", NR_FILE_THPS }, diff --git a/mm/migrate.c b/mm/migrate.c index 4ec727adfaa2..62b81d5257aa 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -500,6 +500,12 @@ int migrate_page_move_mapping(struct address_space *mapping, __mod_lruvec_state(old_lruvec, NR_SHMEM, -nr); __mod_lruvec_state(new_lruvec, NR_SHMEM, nr); } +#ifdef CONFIG_SWAP + if (PageSwapCache(page)) { + __mod_lruvec_state(old_lruvec, NR_SWAPCACHE, -nr); + __mod_lruvec_state(new_lruvec, NR_SWAPCACHE, nr); + } +#endif if (dirty && mapping_can_writeback(mapping)) { __mod_lruvec_state(old_lruvec, NR_FILE_DIRTY, -nr); __mod_zone_page_state(oldzone, NR_ZONE_WRITE_PENDING, -nr); diff --git a/mm/swap_state.c b/mm/swap_state.c index 807b00eae969..c1a648d9092b 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -68,32 +68,6 @@ static struct { unsigned long find_total; } swap_cache_info; -unsigned long total_swapcache_pages(void) -{ - unsigned int i, j, nr; - unsigned long ret = 0; - struct address_space *spaces; - struct swap_info_struct *si; - - for (i = 0; i < MAX_SWAPFILES; i++) { - swp_entry_t entry = swp_entry(i, 1); - - /* Avoid get_swap_device() to warn for bad swap entry */ - if (!swp_swap_info(entry)) - continue; - /* Prevent swapoff to free swapper_spaces */ - si = get_swap_device(entry); - if (!si) - continue; - nr = nr_swapper_spaces[i]; - spaces = swapper_spaces[i]; - for (j = 0; j < nr; j++) - ret += spaces[j].nrpages; - put_swap_device(si); - } - return ret; -} - static atomic_t swapin_readahead_hits = ATOMIC_INIT(4); void show_swap_cache_info(void) @@ -163,6 +137,7 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry, address_space->nrexceptional -= nr_shadows; address_space->nrpages += nr; __mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, nr); + __mod_lruvec_page_state(page, NR_SWAPCACHE, nr); ADD_CACHE_INFO(add_total, nr); unlock: xas_unlock_irq(&xas); @@ -203,6 +178,7 @@ void __delete_from_swap_cache(struct page *page, address_space->nrexceptional += nr; address_space->nrpages -= nr; __mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, -nr); + __mod_lruvec_page_state(page, NR_SWAPCACHE, -nr); ADD_CACHE_INFO(del_total, nr); } diff --git a/mm/vmstat.c b/mm/vmstat.c index 07dc0af50cf0..a0e949542204 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1215,6 +1215,9 @@ const char * const vmstat_text[] = { "nr_shadow_call_stack", #endif "nr_page_table_pages", +#ifdef CONFIG_SWAP + "nr_swapcached", +#endif /* enum writeback_stat_item counters */ "nr_dirty_threshold", -- cgit v1.2.3 From c1a660dea3fa616420606f1e206e6d22f7e05c30 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Wed, 24 Feb 2021 12:03:58 -0800 Subject: mm: kmem: make __memcg_kmem_(un)charge static I've noticed that __memcg_kmem_charge() and __memcg_kmem_uncharge() are not used anywhere except memcontrol.c. Yet they are not declared as non-static and are declared in memcontrol.h. This patch makes them static. Link: https://lkml.kernel.org/r/20210108020332.4096911-1-guro@fb.com Signed-off-by: Roman Gushchin Reviewed-by: Shakeel Butt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 3 --- mm/memcontrol.c | 11 ++++++++--- 2 files changed, 8 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 41bbf71edd9f..7a38a1517a05 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1592,9 +1592,6 @@ static inline void memcg_set_shrinker_bit(struct mem_cgroup *memcg, #endif #ifdef CONFIG_MEMCG_KMEM -int __memcg_kmem_charge(struct mem_cgroup *memcg, gfp_t gfp, - unsigned int nr_pages); -void __memcg_kmem_uncharge(struct mem_cgroup *memcg, unsigned int nr_pages); int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order); void __memcg_kmem_uncharge_page(struct page *page, int order); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 58edfb6614b8..dce5291525a5 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -255,6 +255,11 @@ struct cgroup_subsys_state *vmpressure_to_css(struct vmpressure *vmpr) #ifdef CONFIG_MEMCG_KMEM extern spinlock_t css_set_lock; +static int __memcg_kmem_charge(struct mem_cgroup *memcg, gfp_t gfp, + unsigned int nr_pages); +static void __memcg_kmem_uncharge(struct mem_cgroup *memcg, + unsigned int nr_pages); + static void obj_cgroup_release(struct percpu_ref *ref) { struct obj_cgroup *objcg = container_of(ref, struct obj_cgroup, refcnt); @@ -3087,8 +3092,8 @@ static void memcg_free_cache_id(int id) * * Returns 0 on success, an error code on failure. */ -int __memcg_kmem_charge(struct mem_cgroup *memcg, gfp_t gfp, - unsigned int nr_pages) +static int __memcg_kmem_charge(struct mem_cgroup *memcg, gfp_t gfp, + unsigned int nr_pages) { struct page_counter *counter; int ret; @@ -3120,7 +3125,7 @@ int __memcg_kmem_charge(struct mem_cgroup *memcg, gfp_t gfp, * @memcg: memcg to uncharge * @nr_pages: number of pages to uncharge */ -void __memcg_kmem_uncharge(struct mem_cgroup *memcg, unsigned int nr_pages) +static void __memcg_kmem_uncharge(struct mem_cgroup *memcg, unsigned int nr_pages) { if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) page_counter_uncharge(&memcg->kmem, nr_pages); -- cgit v1.2.3 From 802f1d522d5fdaefc2b935141bc8fe03d43a99ab Mon Sep 17 00:00:00 2001 From: Feng Tang Date: Wed, 24 Feb 2021 12:04:01 -0800 Subject: mm: page_counter: re-layout structure to reduce false sharing MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When checking a memory cgroup related performance regression [1], from the perf c2c profiling data, we found high false sharing for accessing 'usage' and 'parent'. On 64 bit system, the 'usage' and 'parent' are close to each other, and easy to be in one cacheline (for cacheline size == 64+ B). 'usage' is usally written, while 'parent' is usually read as the cgroup's hierarchical counting nature. So move the 'parent' to the end of the structure to make sure they are in different cache lines. Following are some performance data with the patch, against v5.11-rc1. [ In the data, A means a platform with 2 sockets 48C/96T, B is a platform of 4 sockests 72C/144T, and if a %stddev will be shown bigger than 2%, P100/P50 means number of test tasks equals to 100%/50% of nr_cpu] will-it-scale/malloc1 --------------------- v5.11-rc1 v5.11-rc1+patch A-P100 15782 ± 2% -0.1% 15765 ± 3% will-it-scale.per_process_ops A-P50 21511 +8.9% 23432 will-it-scale.per_process_ops B-P100 9155 +2.2% 9357 will-it-scale.per_process_ops B-P50 10967 +7.1% 11751 ± 2% will-it-scale.per_process_ops will-it-scale/pagefault2 ------------------------ v5.11-rc1 v5.11-rc1+patch A-P100 79028 +3.0% 81411 will-it-scale.per_process_ops A-P50 183960 ± 2% +4.4% 192078 ± 2% will-it-scale.per_process_ops B-P100 85966 +9.9% 94467 ± 3% will-it-scale.per_process_ops B-P50 198195 +9.8% 217526 will-it-scale.per_process_ops fio (4k/1M is block size) ------------------------- v5.11-rc1 v5.11-rc1+patch A-P50-r-4k 16881 ± 2% +1.2% 17081 ± 2% fio.read_bw_MBps A-P50-w-4k 3931 +4.5% 4111 ± 2% fio.write_bw_MBps A-P50-r-1M 15178 -0.2% 15154 fio.read_bw_MBps A-P50-w-1M 3924 +0.1% 3929 fio.write_bw_MBps [1].https://lore.kernel.org/lkml/20201102091543.GM31092@shao2-debian/ Link: https://lkml.kernel.org/r/1611040814-33449-1-git-send-email-feng.tang@intel.com Signed-off-by: Feng Tang Reviewed-by: Roman Gushchin Reviewed-by: Shakeel Butt Acked-by: Johannes Weiner Acked-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_counter.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h index 85bd413e784e..679591301994 100644 --- a/include/linux/page_counter.h +++ b/include/linux/page_counter.h @@ -12,7 +12,6 @@ struct page_counter { unsigned long low; unsigned long high; unsigned long max; - struct page_counter *parent; /* effective memory.min and memory.min usage tracking */ unsigned long emin; @@ -27,6 +26,14 @@ struct page_counter { /* legacy */ unsigned long watermark; unsigned long failcnt; + + /* + * 'parent' is placed here to be far from 'usage' to reduce + * cache false sharing, as 'usage' is written mostly while + * parent is frequently read for cgroup's hierarchical + * counting nature. + */ + struct page_counter *parent; }; #if BITS_PER_LONG == 32 -- cgit v1.2.3 From 6eeb104e114cb6b7391c2d69ff873403858c1f35 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 24 Feb 2021 12:04:15 -0800 Subject: fs: buffer: use raw page_memcg() on locked page alloc_page_buffers() currently uses get_mem_cgroup_from_page() for charging the buffers to the page owner, which does an rcu-protected page->memcg lookup and acquires a reference. But buffer allocation has the page lock held throughout, which pins the page to the memcg and thereby the memcg - neither rcu nor holding an extra reference during the allocation are necessary. Use a raw page_memcg() instead. This was the last user of get_mem_cgroup_from_page(), delete it. Link: https://lkml.kernel.org/r/20210209190126.97842-1-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Reported-by: Muchun Song Reviewed-by: Shakeel Butt Acked-by: Roman Gushchin Acked-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/buffer.c | 4 ++-- include/linux/memcontrol.h | 7 ------- mm/memcontrol.c | 23 ----------------------- 3 files changed, 2 insertions(+), 32 deletions(-) (limited to 'include') diff --git a/fs/buffer.c b/fs/buffer.c index f1c3a5b27a90..0cb7ffd4977c 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -847,7 +847,8 @@ struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size, if (retry) gfp |= __GFP_NOFAIL; - memcg = get_mem_cgroup_from_page(page); + /* The page lock pins the memcg */ + memcg = page_memcg(page); old_memcg = set_active_memcg(memcg); head = NULL; @@ -868,7 +869,6 @@ struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size, } out: set_active_memcg(old_memcg); - mem_cgroup_put(memcg); return head; /* * In case anything failed, we just free everything we got. diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 7a38a1517a05..e6dc793d587d 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -680,8 +680,6 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm); -struct mem_cgroup *get_mem_cgroup_from_page(struct page *page); - struct lruvec *lock_page_lruvec(struct page *page); struct lruvec *lock_page_lruvec_irq(struct page *page); struct lruvec *lock_page_lruvec_irqsave(struct page *page, @@ -1191,11 +1189,6 @@ static inline struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm) return NULL; } -static inline struct mem_cgroup *get_mem_cgroup_from_page(struct page *page) -{ - return NULL; -} - static inline void mem_cgroup_put(struct mem_cgroup *memcg) { } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 8c035846c7a4..7fdc001ce15f 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1047,29 +1047,6 @@ struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm) } EXPORT_SYMBOL(get_mem_cgroup_from_mm); -/** - * get_mem_cgroup_from_page: Obtain a reference on given page's memcg. - * @page: page from which memcg should be extracted. - * - * Obtain a reference on page->memcg and returns it if successful. Otherwise - * root_mem_cgroup is returned. - */ -struct mem_cgroup *get_mem_cgroup_from_page(struct page *page) -{ - struct mem_cgroup *memcg = page_memcg(page); - - if (mem_cgroup_disabled()) - return NULL; - - rcu_read_lock(); - /* Page should not get uncharged and freed memcg under us. */ - if (!memcg || WARN_ON_ONCE(!css_tryget(&memcg->css))) - memcg = root_mem_cgroup; - rcu_read_unlock(); - return memcg; -} -EXPORT_SYMBOL(get_mem_cgroup_from_page); - static __always_inline struct mem_cgroup *active_memcg(void) { if (in_interrupt()) -- cgit v1.2.3 From 027b37b552f326aa94ef06c7ea77088b16c41e6e Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Wed, 24 Feb 2021 12:05:46 -0800 Subject: kasan: move _RET_IP_ to inline wrappers Generic mm functions that call KASAN annotations that might report a bug pass _RET_IP_ to them as an argument. This allows KASAN to include the name of the function that called the mm function in its report's header. Now that KASAN has inline wrappers for all of its annotations, move _RET_IP_ to those wrappers to simplify annotation call sites. Link: https://linux-review.googlesource.com/id/I8fb3c06d49671305ee184175a39591bc26647a67 Link: https://lkml.kernel.org/r/5c1490eddf20b436b8c4eeea83fce47687d5e4a4.1610733117.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Reviewed-by: Marco Elver Reviewed-by: Alexander Potapenko Cc: Andrey Ryabinin Cc: Branislav Rankov Cc: Catalin Marinas Cc: Dmitry Vyukov Cc: Evgenii Stepanov Cc: Kevin Brodsky Cc: Peter Collingbourne Cc: Vincenzo Frascino Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kasan.h | 20 +++++++++----------- mm/mempool.c | 2 +- mm/slab.c | 2 +- mm/slub.c | 4 ++-- 4 files changed, 13 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 0aea9e2a2a01..a7254186558a 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -185,19 +185,18 @@ static __always_inline void * __must_check kasan_init_slab_obj( } bool __kasan_slab_free(struct kmem_cache *s, void *object, unsigned long ip); -static __always_inline bool kasan_slab_free(struct kmem_cache *s, void *object, - unsigned long ip) +static __always_inline bool kasan_slab_free(struct kmem_cache *s, void *object) { if (kasan_enabled()) - return __kasan_slab_free(s, object, ip); + return __kasan_slab_free(s, object, _RET_IP_); return false; } void __kasan_slab_free_mempool(void *ptr, unsigned long ip); -static __always_inline void kasan_slab_free_mempool(void *ptr, unsigned long ip) +static __always_inline void kasan_slab_free_mempool(void *ptr) { if (kasan_enabled()) - __kasan_slab_free_mempool(ptr, ip); + __kasan_slab_free_mempool(ptr, _RET_IP_); } void * __must_check __kasan_slab_alloc(struct kmem_cache *s, @@ -241,10 +240,10 @@ static __always_inline void * __must_check kasan_krealloc(const void *object, } void __kasan_kfree_large(void *ptr, unsigned long ip); -static __always_inline void kasan_kfree_large(void *ptr, unsigned long ip) +static __always_inline void kasan_kfree_large(void *ptr) { if (kasan_enabled()) - __kasan_kfree_large(ptr, ip); + __kasan_kfree_large(ptr, _RET_IP_); } bool kasan_save_enable_multi_shot(void); @@ -277,12 +276,11 @@ static inline void *kasan_init_slab_obj(struct kmem_cache *cache, { return (void *)object; } -static inline bool kasan_slab_free(struct kmem_cache *s, void *object, - unsigned long ip) +static inline bool kasan_slab_free(struct kmem_cache *s, void *object) { return false; } -static inline void kasan_slab_free_mempool(void *ptr, unsigned long ip) {} +static inline void kasan_slab_free_mempool(void *ptr) {} static inline void *kasan_slab_alloc(struct kmem_cache *s, void *object, gfp_t flags) { @@ -302,7 +300,7 @@ static inline void *kasan_krealloc(const void *object, size_t new_size, { return (void *)object; } -static inline void kasan_kfree_large(void *ptr, unsigned long ip) {} +static inline void kasan_kfree_large(void *ptr) {} #endif /* CONFIG_KASAN */ diff --git a/mm/mempool.c b/mm/mempool.c index 624ed51b060f..79959fac27d7 100644 --- a/mm/mempool.c +++ b/mm/mempool.c @@ -104,7 +104,7 @@ static inline void poison_element(mempool_t *pool, void *element) static __always_inline void kasan_poison_element(mempool_t *pool, void *element) { if (pool->alloc == mempool_alloc_slab || pool->alloc == mempool_kmalloc) - kasan_slab_free_mempool(element, _RET_IP_); + kasan_slab_free_mempool(element); else if (pool->alloc == mempool_alloc_pages) kasan_free_pages(element, (unsigned long)pool->pool_data); } diff --git a/mm/slab.c b/mm/slab.c index 9c9e0c255c4b..35c68d99d460 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -3420,7 +3420,7 @@ static __always_inline void __cache_free(struct kmem_cache *cachep, void *objp, memset(objp, 0, cachep->object_size); /* Put the object into the quarantine, don't touch it for now. */ - if (kasan_slab_free(cachep, objp, _RET_IP_)) + if (kasan_slab_free(cachep, objp)) return; /* Use KCSAN to help debug racy use-after-free. */ diff --git a/mm/slub.c b/mm/slub.c index 046d7194acaf..b2833ce85c92 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1528,7 +1528,7 @@ static inline void *kmalloc_large_node_hook(void *ptr, size_t size, gfp_t flags) static __always_inline void kfree_hook(void *x) { kmemleak_free(x); - kasan_kfree_large(x, _RET_IP_); + kasan_kfree_large(x); } static __always_inline bool slab_free_hook(struct kmem_cache *s, void *x) @@ -1558,7 +1558,7 @@ static __always_inline bool slab_free_hook(struct kmem_cache *s, void *x) KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ASSERT); /* KASAN might put x into memory quarantine, delaying its reuse */ - return kasan_slab_free(s, x, _RET_IP_); + return kasan_slab_free(s, x); } static inline bool slab_free_freelist_hook(struct kmem_cache *s, -- cgit v1.2.3 From 611806b4bf8dd97a4f3d73f5cf3c2c7730c51eb2 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Wed, 24 Feb 2021 12:05:50 -0800 Subject: kasan: fix bug detection via ksize for HW_TAGS mode The currently existing kasan_check_read/write() annotations are intended to be used for kernel modules that have KASAN compiler instrumentation disabled. Thus, they are only relevant for the software KASAN modes that rely on compiler instrumentation. However there's another use case for these annotations: ksize() checks that the object passed to it is indeed accessible before unpoisoning the whole object. This is currently done via __kasan_check_read(), which is compiled away for the hardware tag-based mode that doesn't rely on compiler instrumentation. This leads to KASAN missing detecting some memory corruptions. Provide another annotation called kasan_check_byte() that is available for all KASAN modes. As the implementation rename and reuse kasan_check_invalid_free(). Use this new annotation in ksize(). To avoid having ksize() as the top frame in the reported stack trace pass _RET_IP_ to __kasan_check_byte(). Also add a new ksize_uaf() test that checks that a use-after-free is detected via ksize() itself, and via plain accesses that happen later. Link: https://linux-review.googlesource.com/id/Iaabf771881d0f9ce1b969f2a62938e99d3308ec5 Link: https://lkml.kernel.org/r/f32ad74a60b28d8402482a38476f02bb7600f620.1610733117.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Reviewed-by: Marco Elver Reviewed-by: Alexander Potapenko Cc: Andrey Ryabinin Cc: Branislav Rankov Cc: Catalin Marinas Cc: Dmitry Vyukov Cc: Evgenii Stepanov Cc: Kevin Brodsky Cc: Peter Collingbourne Cc: Vincenzo Frascino Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kasan-checks.h | 6 ++++++ include/linux/kasan.h | 17 +++++++++++++++++ lib/test_kasan.c | 20 ++++++++++++++++++++ mm/kasan/common.c | 11 ++++++++++- mm/kasan/generic.c | 4 ++-- mm/kasan/kasan.h | 10 +++++----- mm/kasan/sw_tags.c | 6 +++--- mm/slab_common.c | 16 +++++++++------- 8 files changed, 72 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/linux/kasan-checks.h b/include/linux/kasan-checks.h index ca5e89fb10d3..3d6d22a25bdc 100644 --- a/include/linux/kasan-checks.h +++ b/include/linux/kasan-checks.h @@ -4,6 +4,12 @@ #include +/* + * The annotations present in this file are only relevant for the software + * KASAN modes that rely on compiler instrumentation, and will be optimized + * away for the hardware tag-based KASAN mode. Use kasan_check_byte() instead. + */ + /* * __kasan_check_*: Always available when KASAN is enabled. This may be used * even in compilation units that selectively disable KASAN, but must use KASAN diff --git a/include/linux/kasan.h b/include/linux/kasan.h index a7254186558a..7eaf2d9effb4 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -246,6 +246,19 @@ static __always_inline void kasan_kfree_large(void *ptr) __kasan_kfree_large(ptr, _RET_IP_); } +/* + * Unlike kasan_check_read/write(), kasan_check_byte() is performed even for + * the hardware tag-based mode that doesn't rely on compiler instrumentation. + */ +bool __kasan_check_byte(const void *addr, unsigned long ip); +static __always_inline bool kasan_check_byte(const void *addr) +{ + if (kasan_enabled()) + return __kasan_check_byte(addr, _RET_IP_); + return true; +} + + bool kasan_save_enable_multi_shot(void); void kasan_restore_multi_shot(bool enabled); @@ -301,6 +314,10 @@ static inline void *kasan_krealloc(const void *object, size_t new_size, return (void *)object; } static inline void kasan_kfree_large(void *ptr) {} +static inline bool kasan_check_byte(const void *address) +{ + return true; +} #endif /* CONFIG_KASAN */ diff --git a/lib/test_kasan.c b/lib/test_kasan.c index e59f185b8075..3f771fabd0ec 100644 --- a/lib/test_kasan.c +++ b/lib/test_kasan.c @@ -496,6 +496,7 @@ static void kasan_global_oob(struct kunit *test) KUNIT_EXPECT_KASAN_FAIL(test, *(volatile char *)p); } +/* Check that ksize() makes the whole object accessible. */ static void ksize_unpoisons_memory(struct kunit *test) { char *ptr; @@ -514,6 +515,24 @@ static void ksize_unpoisons_memory(struct kunit *test) kfree(ptr); } +/* + * Check that a use-after-free is detected by ksize() and via normal accesses + * after it. + */ +static void ksize_uaf(struct kunit *test) +{ + char *ptr; + int size = 128 - KASAN_GRANULE_SIZE; + + ptr = kmalloc(size, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr); + kfree(ptr); + + KUNIT_EXPECT_KASAN_FAIL(test, ksize(ptr)); + KUNIT_EXPECT_KASAN_FAIL(test, kasan_int_result = *ptr); + KUNIT_EXPECT_KASAN_FAIL(test, kasan_int_result = *(ptr + size)); +} + static void kasan_stack_oob(struct kunit *test) { char stack_array[10]; @@ -907,6 +926,7 @@ static struct kunit_case kasan_kunit_test_cases[] = { KUNIT_CASE(kasan_alloca_oob_left), KUNIT_CASE(kasan_alloca_oob_right), KUNIT_CASE(ksize_unpoisons_memory), + KUNIT_CASE(ksize_uaf), KUNIT_CASE(kmem_cache_double_free), KUNIT_CASE(kmem_cache_invalid_free), KUNIT_CASE(kasan_memchr), diff --git a/mm/kasan/common.c b/mm/kasan/common.c index eedc3e0fe365..b18189ef3a92 100644 --- a/mm/kasan/common.c +++ b/mm/kasan/common.c @@ -345,7 +345,7 @@ static bool ____kasan_slab_free(struct kmem_cache *cache, void *object, if (unlikely(cache->flags & SLAB_TYPESAFE_BY_RCU)) return false; - if (kasan_check_invalid_free(tagged_object)) { + if (!kasan_byte_accessible(tagged_object)) { kasan_report_invalid_free(tagged_object, ip); return true; } @@ -490,3 +490,12 @@ void __kasan_kfree_large(void *ptr, unsigned long ip) kasan_report_invalid_free(ptr, ip); /* The object will be poisoned by kasan_free_pages(). */ } + +bool __kasan_check_byte(const void *address, unsigned long ip) +{ + if (!kasan_byte_accessible(address)) { + kasan_report((unsigned long)address, 1, false, ip); + return false; + } + return true; +} diff --git a/mm/kasan/generic.c b/mm/kasan/generic.c index acab8862dc67..3f17a1218055 100644 --- a/mm/kasan/generic.c +++ b/mm/kasan/generic.c @@ -185,11 +185,11 @@ bool kasan_check_range(unsigned long addr, size_t size, bool write, return check_region_inline(addr, size, write, ret_ip); } -bool kasan_check_invalid_free(void *addr) +bool kasan_byte_accessible(const void *addr) { s8 shadow_byte = READ_ONCE(*(s8 *)kasan_mem_to_shadow(addr)); - return shadow_byte < 0 || shadow_byte >= KASAN_GRANULE_SIZE; + return shadow_byte >= 0 && shadow_byte < KASAN_GRANULE_SIZE; } void kasan_cache_shrink(struct kmem_cache *cache) diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index 1298b79f9518..cc14b6e6c14c 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -341,20 +341,20 @@ static inline void kasan_unpoison(const void *address, size_t size) round_up(size, KASAN_GRANULE_SIZE), get_tag(address)); } -static inline bool kasan_check_invalid_free(void *addr) +static inline bool kasan_byte_accessible(const void *addr) { u8 ptr_tag = get_tag(addr); - u8 mem_tag = hw_get_mem_tag(addr); + u8 mem_tag = hw_get_mem_tag((void *)addr); - return (mem_tag == KASAN_TAG_INVALID) || - (ptr_tag != KASAN_TAG_KERNEL && ptr_tag != mem_tag); + return (mem_tag != KASAN_TAG_INVALID) && + (ptr_tag == KASAN_TAG_KERNEL || ptr_tag == mem_tag); } #else /* CONFIG_KASAN_HW_TAGS */ void kasan_poison(const void *address, size_t size, u8 value); void kasan_unpoison(const void *address, size_t size); -bool kasan_check_invalid_free(void *addr); +bool kasan_byte_accessible(const void *addr); #endif /* CONFIG_KASAN_HW_TAGS */ diff --git a/mm/kasan/sw_tags.c b/mm/kasan/sw_tags.c index cc271fceb5d5..94c2d33be333 100644 --- a/mm/kasan/sw_tags.c +++ b/mm/kasan/sw_tags.c @@ -118,13 +118,13 @@ bool kasan_check_range(unsigned long addr, size_t size, bool write, return true; } -bool kasan_check_invalid_free(void *addr) +bool kasan_byte_accessible(const void *addr) { u8 tag = get_tag(addr); u8 shadow_byte = READ_ONCE(*(u8 *)kasan_mem_to_shadow(kasan_reset_tag(addr))); - return (shadow_byte == KASAN_TAG_INVALID) || - (tag != KASAN_TAG_KERNEL && tag != shadow_byte); + return (shadow_byte != KASAN_TAG_INVALID) && + (tag == KASAN_TAG_KERNEL || tag == shadow_byte); } #define DEFINE_HWASAN_LOAD_STORE(size) \ diff --git a/mm/slab_common.c b/mm/slab_common.c index 5be7825ad3ce..7c8298c17145 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -1218,19 +1218,21 @@ size_t ksize(const void *objp) size_t size; /* - * We need to check that the pointed to object is valid, and only then - * unpoison the shadow memory below. We use __kasan_check_read(), to - * generate a more useful report at the time ksize() is called (rather - * than later where behaviour is undefined due to potential - * use-after-free or double-free). + * We need to first check that the pointer to the object is valid, and + * only then unpoison the memory. The report printed from ksize() is + * more useful, then when it's printed later when the behaviour could + * be undefined due to a potential use-after-free or double-free. * - * If the pointed to memory is invalid we return 0, to avoid users of + * We use kasan_check_byte(), which is supported for the hardware + * tag-based KASAN mode, unlike kasan_check_read/write(). + * + * If the pointed to memory is invalid, we return 0 to avoid users of * ksize() writing to and potentially corrupting the memory region. * * We want to perform the check before __ksize(), to avoid potentially * crashing in __ksize() due to accessing invalid metadata. */ - if (unlikely(ZERO_OR_NULL_PTR(objp)) || !__kasan_check_read(objp, 1)) + if (unlikely(ZERO_OR_NULL_PTR(objp)) || !kasan_check_byte(objp)) return 0; size = __ksize(objp); -- cgit v1.2.3 From 93f503c3fcd168a43e4a6c875fe2cfafaf8439dc Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Wed, 24 Feb 2021 12:06:10 -0800 Subject: mm: fix prototype warning from kernel test robot Patch series "mm: clean up names and parameters of memmap_init_xxxx functions", v5. This patchset corrects inappropriate function names of memmap_init_xxx, and simplify parameters of functions in the code flow. And also fix a prototype warning reported by lkp. This patch (of 5); Kernel test robot calling make with 'W=1' is triggering warning like below for memmap_init_zone() function. mm/page_alloc.c:6259:23: warning: no previous prototype for 'memmap_init_zone' [-Wmissing-prototypes] 6259 | void __meminit __weak memmap_init_zone(unsigned long size, int nid, | ^~~~~~~~~~~~~~~~ Fix it by adding the function declaration in include/linux/mm.h. Since memmap_init_zone() has a generic version with '__weak', the declaratoin in ia64 header file can be simply removed. Link: https://lkml.kernel.org/r/20210122135956.5946-1-bhe@redhat.com Link: https://lkml.kernel.org/r/20210122135956.5946-2-bhe@redhat.com Signed-off-by: Baoquan He Reported-by: kernel test robot Reviewed-by: Mike Rapoport Reviewed-by: David Hildenbrand Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/include/asm/pgtable.h | 6 ------ include/linux/mm.h | 2 ++ 2 files changed, 2 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/arch/ia64/include/asm/pgtable.h b/arch/ia64/include/asm/pgtable.h index 779b6972aa84..9b4efe89e62d 100644 --- a/arch/ia64/include/asm/pgtable.h +++ b/arch/ia64/include/asm/pgtable.h @@ -517,12 +517,6 @@ extern struct page *zero_page_memmap_ptr; __changed; \ }) #endif - -# ifdef CONFIG_VIRTUAL_MEM_MAP - /* arch mem_map init routine is needed due to holes in a virtual mem_map */ - extern void memmap_init (unsigned long size, int nid, unsigned long zone, - unsigned long start_pfn); -# endif /* CONFIG_VIRTUAL_MEM_MAP */ # endif /* !__ASSEMBLY__ */ /* diff --git a/include/linux/mm.h b/include/linux/mm.h index 7deb7168104d..1c1eabdf112c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2408,6 +2408,8 @@ extern void set_dma_reserve(unsigned long new_dma_reserve); extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long, unsigned long, enum meminit_context, struct vmem_altmap *, int migratetype); +extern void memmap_init(unsigned long size, int nid, + unsigned long zone, unsigned long range_start_pfn); extern void setup_per_zone_wmarks(void); extern int __meminit init_per_zone_wmark_min(void); extern void mem_init(void); -- cgit v1.2.3 From ab28cb6e1e5e59eb8bf3ad399133617414301d3a Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Wed, 24 Feb 2021 12:06:14 -0800 Subject: mm: rename memmap_init() and memmap_init_zone() The current memmap_init_zone() only handles memory region inside one zone, actually memmap_init() does the memmap init of one zone. So rename both of them accordingly. Link: https://lkml.kernel.org/r/20210122135956.5946-3-bhe@redhat.com Signed-off-by: Baoquan He Reviewed-by: Mike Rapoport Reviewed-by: David Hildenbrand Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/mm/init.c | 6 +++--- include/linux/mm.h | 4 ++-- mm/memory_hotplug.c | 2 +- mm/page_alloc.c | 8 ++++---- 4 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index b19f47a5a305..39b782f62d7d 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -536,18 +536,18 @@ virtual_memmap_init(u64 start, u64 end, void *arg) / sizeof(struct page)); if (map_start < map_end) - memmap_init_zone((unsigned long)(map_end - map_start), + memmap_init_range((unsigned long)(map_end - map_start), args->nid, args->zone, page_to_pfn(map_start), page_to_pfn(map_end), MEMINIT_EARLY, NULL, MIGRATE_MOVABLE); return 0; } void __meminit -memmap_init (unsigned long size, int nid, unsigned long zone, +memmap_init_zone(unsigned long size, int nid, unsigned long zone, unsigned long start_pfn) { if (!vmem_map) { - memmap_init_zone(size, nid, zone, start_pfn, start_pfn + size, + memmap_init_range(size, nid, zone, start_pfn, start_pfn + size, MEMINIT_EARLY, NULL, MIGRATE_MOVABLE); } else { struct page *start; diff --git a/include/linux/mm.h b/include/linux/mm.h index 1c1eabdf112c..56d0eeae0ce3 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2405,10 +2405,10 @@ extern int __meminit early_pfn_to_nid(unsigned long pfn); #endif extern void set_dma_reserve(unsigned long new_dma_reserve); -extern void memmap_init_zone(unsigned long, int, unsigned long, +extern void memmap_init_range(unsigned long, int, unsigned long, unsigned long, unsigned long, enum meminit_context, struct vmem_altmap *, int migratetype); -extern void memmap_init(unsigned long size, int nid, +extern void memmap_init_zone(unsigned long size, int nid, unsigned long zone, unsigned long range_start_pfn); extern void setup_per_zone_wmarks(void); extern int __meminit init_per_zone_wmark_min(void); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index f9d57b9be8c7..ddcb1cd24c60 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -713,7 +713,7 @@ void __ref move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn, * expects the zone spans the pfn range. All the pages in the range * are reserved so nobody should be touching them so we should be safe */ - memmap_init_zone(nr_pages, nid, zone_idx(zone), start_pfn, 0, + memmap_init_range(nr_pages, nid, zone_idx(zone), start_pfn, 0, MEMINIT_HOTPLUG, altmap, migratetype); set_zone_contiguous(zone); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 069561aadc7b..519cf52963eb 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6121,7 +6121,7 @@ overlap_memmap_init(unsigned long zone, unsigned long *pfn) * (usually MIGRATE_MOVABLE). Besides setting the migratetype, no related * zone stats (e.g., nr_isolate_pageblock) are touched. */ -void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, +void __meminit memmap_init_range(unsigned long size, int nid, unsigned long zone, unsigned long start_pfn, unsigned long zone_end_pfn, enum meminit_context context, struct vmem_altmap *altmap, int migratetype) @@ -6258,7 +6258,7 @@ static void __meminit zone_init_free_lists(struct zone *zone) } } -void __meminit __weak memmap_init(unsigned long size, int nid, +void __meminit __weak memmap_init_zone(unsigned long size, int nid, unsigned long zone, unsigned long range_start_pfn) { @@ -6272,7 +6272,7 @@ void __meminit __weak memmap_init(unsigned long size, int nid, if (end_pfn > start_pfn) { size = end_pfn - start_pfn; - memmap_init_zone(size, nid, zone, start_pfn, range_end_pfn, + memmap_init_range(size, nid, zone, start_pfn, range_end_pfn, MEMINIT_EARLY, NULL, MIGRATE_MOVABLE); } } @@ -6982,7 +6982,7 @@ static void __init free_area_init_core(struct pglist_data *pgdat) set_pageblock_order(); setup_usemap(pgdat, zone, zone_start_pfn, size); init_currently_empty_zone(zone, zone_start_pfn, size); - memmap_init(size, nid, j, zone_start_pfn); + memmap_init_zone(size, nid, j, zone_start_pfn); } } -- cgit v1.2.3 From 3256ff83c566235e812498ee1dc806c45a5d5af7 Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Wed, 24 Feb 2021 12:06:17 -0800 Subject: mm: simplify parater of function memmap_init_zone() As David suggested, simply passing 'struct zone *zone' is enough. We can get all needed information from 'struct zone*' easily. Link: https://lkml.kernel.org/r/20210122135956.5946-4-bhe@redhat.com Signed-off-by: Baoquan He Suggested-by: David Hildenbrand Reviewed-by: Mike Rapoport Reviewed-by: David Hildenbrand Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/mm/init.c | 12 +++++++----- include/linux/mm.h | 3 +-- mm/page_alloc.c | 24 +++++++++++------------- 3 files changed, 19 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index 39b782f62d7d..16d0d7d22657 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -542,12 +542,14 @@ virtual_memmap_init(u64 start, u64 end, void *arg) return 0; } -void __meminit -memmap_init_zone(unsigned long size, int nid, unsigned long zone, - unsigned long start_pfn) +void __meminit memmap_init_zone(struct zone *zone) { + int nid = zone_to_nid(zone), zone_id = zone_idx(zone); + unsigned long start_pfn = zone->zone_start_pfn; + unsigned long size = zone->spanned_pages; + if (!vmem_map) { - memmap_init_range(size, nid, zone, start_pfn, start_pfn + size, + memmap_init_range(size, nid, zone_id, start_pfn, start_pfn + size, MEMINIT_EARLY, NULL, MIGRATE_MOVABLE); } else { struct page *start; @@ -557,7 +559,7 @@ memmap_init_zone(unsigned long size, int nid, unsigned long zone, args.start = start; args.end = start + size; args.nid = nid; - args.zone = zone; + args.zone = zone_id; efi_memmap_walk(virtual_memmap_init, &args); } diff --git a/include/linux/mm.h b/include/linux/mm.h index 56d0eeae0ce3..2601a5cce0ef 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2408,8 +2408,7 @@ extern void set_dma_reserve(unsigned long new_dma_reserve); extern void memmap_init_range(unsigned long, int, unsigned long, unsigned long, unsigned long, enum meminit_context, struct vmem_altmap *, int migratetype); -extern void memmap_init_zone(unsigned long size, int nid, - unsigned long zone, unsigned long range_start_pfn); +extern void memmap_init_zone(struct zone *zone); extern void setup_per_zone_wmarks(void); extern int __meminit init_per_zone_wmark_min(void); extern void mem_init(void); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 519cf52963eb..aa04c54ad47c 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6258,23 +6258,21 @@ static void __meminit zone_init_free_lists(struct zone *zone) } } -void __meminit __weak memmap_init_zone(unsigned long size, int nid, - unsigned long zone, - unsigned long range_start_pfn) +void __meminit __weak memmap_init_zone(struct zone *zone) { + unsigned long zone_start_pfn = zone->zone_start_pfn; + unsigned long zone_end_pfn = zone_start_pfn + zone->spanned_pages; + int i, nid = zone_to_nid(zone), zone_id = zone_idx(zone); unsigned long start_pfn, end_pfn; - unsigned long range_end_pfn = range_start_pfn + size; - int i; for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) { - start_pfn = clamp(start_pfn, range_start_pfn, range_end_pfn); - end_pfn = clamp(end_pfn, range_start_pfn, range_end_pfn); + start_pfn = clamp(start_pfn, zone_start_pfn, zone_end_pfn); + end_pfn = clamp(end_pfn, zone_start_pfn, zone_end_pfn); - if (end_pfn > start_pfn) { - size = end_pfn - start_pfn; - memmap_init_range(size, nid, zone, start_pfn, range_end_pfn, - MEMINIT_EARLY, NULL, MIGRATE_MOVABLE); - } + if (end_pfn > start_pfn) + memmap_init_range(end_pfn - start_pfn, nid, + zone_id, start_pfn, zone_end_pfn, + MEMINIT_EARLY, NULL, MIGRATE_MOVABLE); } } @@ -6982,7 +6980,7 @@ static void __init free_area_init_core(struct pglist_data *pgdat) set_pageblock_order(); setup_usemap(pgdat, zone, zone_start_pfn, size); init_currently_empty_zone(zone, zone_start_pfn, size); - memmap_init_zone(size, nid, j, zone_start_pfn); + memmap_init_zone(zone); } } -- cgit v1.2.3 From a0cd7a7c4bc004587d1f4785a320f58e72d880eb Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Wed, 24 Feb 2021 12:06:32 -0800 Subject: mm: simplify free_highmem_page() and free_reserved_page() adjust_managed_page_count() as called by free_reserved_page() properly handles pages in a highmem zone, so we can reuse it for free_highmem_page(). We can now get rid of totalhigh_pages_inc() and simplify free_reserved_page(). Link: https://lkml.kernel.org/r/20210126182113.19892-3-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Oscar Salvador Reviewed-by: Anshuman Khandual Cc: Thomas Gleixner Cc: "Peter Zijlstra (Intel)" Cc: Mike Rapoport Cc: Michal Hocko Cc: Wei Yang Cc: "Gustavo A. R. Silva" Cc: Sam Ravnborg Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/highmem-internal.h | 5 ----- include/linux/mm.h | 16 ++-------------- mm/page_alloc.c | 11 ----------- 3 files changed, 2 insertions(+), 30 deletions(-) (limited to 'include') diff --git a/include/linux/highmem-internal.h b/include/linux/highmem-internal.h index 1bbe96dc8be6..7902c7d8b55f 100644 --- a/include/linux/highmem-internal.h +++ b/include/linux/highmem-internal.h @@ -127,11 +127,6 @@ static inline unsigned long totalhigh_pages(void) return (unsigned long)atomic_long_read(&_totalhigh_pages); } -static inline void totalhigh_pages_inc(void) -{ - atomic_long_inc(&_totalhigh_pages); -} - static inline void totalhigh_pages_add(long count) { atomic_long_add(count, &_totalhigh_pages); diff --git a/include/linux/mm.h b/include/linux/mm.h index 2601a5cce0ef..76cab132c295 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2310,32 +2310,20 @@ extern void free_initmem(void); extern unsigned long free_reserved_area(void *start, void *end, int poison, const char *s); -#ifdef CONFIG_HIGHMEM -/* - * Free a highmem page into the buddy system, adjusting totalhigh_pages - * and totalram_pages. - */ -extern void free_highmem_page(struct page *page); -#endif - extern void adjust_managed_page_count(struct page *page, long count); extern void mem_init_print_info(const char *str); extern void reserve_bootmem_region(phys_addr_t start, phys_addr_t end); /* Free the reserved page into the buddy system, so it gets managed. */ -static inline void __free_reserved_page(struct page *page) +static inline void free_reserved_page(struct page *page) { ClearPageReserved(page); init_page_count(page); __free_page(page); -} - -static inline void free_reserved_page(struct page *page) -{ - __free_reserved_page(page); adjust_managed_page_count(page, 1); } +#define free_highmem_page(page) free_reserved_page(page) static inline void mark_page_reserved(struct page *page) { diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 35e230cadb94..ddccc59f2f72 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -7691,17 +7691,6 @@ unsigned long free_reserved_area(void *start, void *end, int poison, const char return pages; } -#ifdef CONFIG_HIGHMEM -void free_highmem_page(struct page *page) -{ - __free_reserved_page(page); - totalram_pages_inc(); - atomic_long_inc(&page_zone(page)->managed_pages); - totalhigh_pages_inc(); -} -#endif - - void __init mem_init_print_info(const char *str) { unsigned long physpages, codesize, datasize, rosize, bss_size; -- cgit v1.2.3 From 3b2ebeaf98a028d5dd4ec63095855ef507920276 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 24 Feb 2021 12:06:35 -0800 Subject: mm/gfp: add kernel-doc for gfp_t The generated html will link to the definition of the gfp_t automatically once we define it. Move the one-paragraph overview of GFP flags from the documentation directory into gfp.h and pull gfp.h into the documentation. This generates warnings with clang (https://lkml.kernel.org/r/20210219195509.GA59987@24bbad8f3778), so use a #if 0 to hide it from the compiler for now. Link: https://lkml.kernel.org/r/20210215204909.3824509-1-willy@infradead.org Link: https://lkml.kernel.org/r/20210220003049.GZ2858050@casper.infradead.org Signed-off-by: Matthew Wilcox (Oracle) Acked-by: Mike Rapoport Cc: Nathan Chancellor Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/core-api/mm-api.rst | 7 ++----- include/linux/gfp.h | 14 ++++++++++++++ 2 files changed, 16 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/Documentation/core-api/mm-api.rst b/Documentation/core-api/mm-api.rst index 2adffb3f7914..201b5423303b 100644 --- a/Documentation/core-api/mm-api.rst +++ b/Documentation/core-api/mm-api.rst @@ -19,11 +19,8 @@ User Space Memory Access Memory Allocation Controls ========================== -Functions which need to allocate memory often use GFP flags to express -how that memory should be allocated. The GFP acronym stands for "get -free pages", the underlying memory allocation function. Not every GFP -flag is allowed to every function which may allocate memory. Most -users will want to use a plain ``GFP_KERNEL``. +.. kernel-doc:: include/linux/gfp.h + :internal: .. kernel-doc:: include/linux/gfp.h :doc: Page mobility and placement hints diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 80544d5c08e7..220cd553a9e7 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -8,6 +8,20 @@ #include #include +/* The typedef is in types.h but we want the documentation here */ +#if 0 +/** + * typedef gfp_t - Memory allocation flags. + * + * GFP flags are commonly used throughout Linux to indicate how memory + * should be allocated. The GFP acronym stands for get_free_pages(), + * the underlying memory allocation function. Not every GFP flag is + * supported by every function which may allocate memory. Most users + * will want to use a plain ``GFP_KERNEL``. + */ +typedef unsigned int __bitwise gfp_t; +#endif + struct vm_area_struct; /* -- cgit v1.2.3 From 0fa5bc4023c188082024833b3deffd5543b93bc9 Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Wed, 24 Feb 2021 12:07:12 -0800 Subject: mm/hugetlb: grab head page refcount once for group of subpages Patch series "mm/hugetlb: follow_hugetlb_page() improvements", v2. While looking at ZONE_DEVICE struct page reuse particularly the last patch[0], I found two possible improvements for follow_hugetlb_page() which is solely used for get_user_pages()/pin_user_pages(). The first patch batches page refcount updates while the second tidies up storing the subpages/vmas. Both together bring the cost of slow variant of gup() cost from ~87.6k usecs to ~5.8k usecs. libhugetlbfs tests seem to pass as well gup_test benchmarks with hugetlbfs vmas. This patch (of 2): follow_hugetlb_page() once it locks the pmd/pud, checks all its N subpages in a huge page and grabs a reference for each one. Similar to gup-fast, have follow_hugetlb_page() grab the head page refcount only after counting all its subpages that are part of the just faulted huge page. Consequently we reduce the number of atomics necessary to pin said huge page, which improves non-fast gup() considerably: - 16G with 1G huge page size gup_test -f /mnt/huge/file -m 16384 -r 10 -L -S -n 512 -w PIN_LONGTERM_BENCHMARK: ~87.6k us -> ~12.8k us Link: https://lkml.kernel.org/r/20210128182632.24562-1-joao.m.martins@oracle.com Link: https://lkml.kernel.org/r/20210128182632.24562-2-joao.m.martins@oracle.com Signed-off-by: Joao Martins Reviewed-by: Mike Kravetz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 3 +++ mm/gup.c | 5 ++--- mm/hugetlb.c | 43 ++++++++++++++++++++++++------------------- 3 files changed, 29 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 76cab132c295..77e64e3eac80 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1187,6 +1187,9 @@ static inline void get_page(struct page *page) } bool __must_check try_grab_page(struct page *page, unsigned int flags); +__maybe_unused struct page *try_grab_compound_head(struct page *page, int refs, + unsigned int flags); + static inline __must_check bool try_get_page(struct page *page) { diff --git a/mm/gup.c b/mm/gup.c index e4c224cd9661..e40579624f10 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -78,9 +78,8 @@ static inline struct page *try_get_compound_head(struct page *page, int refs) * considered failure, and furthermore, a likely bug in the caller, so a warning * is also emitted. */ -static __maybe_unused struct page *try_grab_compound_head(struct page *page, - int refs, - unsigned int flags) +__maybe_unused struct page *try_grab_compound_head(struct page *page, + int refs, unsigned int flags) { if (flags & FOLL_GET) return try_get_compound_head(page, refs); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 6920c71d7e0d..d4fc5db6bc32 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4796,7 +4796,7 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long vaddr = *position; unsigned long remainder = *nr_pages; struct hstate *h = hstate_vma(vma); - int err = -EFAULT; + int err = -EFAULT, refs; while (vaddr < vma->vm_end && remainder) { pte_t *pte; @@ -4916,26 +4916,11 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, continue; } + refs = 0; + same_page: - if (pages) { + if (pages) pages[i] = mem_map_offset(page, pfn_offset); - /* - * try_grab_page() should always succeed here, because: - * a) we hold the ptl lock, and b) we've just checked - * that the huge page is present in the page tables. If - * the huge page is present, then the tail pages must - * also be present. The ptl prevents the head page and - * tail pages from being rearranged in any way. So this - * page must be available at this point, unless the page - * refcount overflowed: - */ - if (WARN_ON_ONCE(!try_grab_page(pages[i], flags))) { - spin_unlock(ptl); - remainder = 0; - err = -ENOMEM; - break; - } - } if (vmas) vmas[i] = vma; @@ -4944,6 +4929,7 @@ same_page: ++pfn_offset; --remainder; ++i; + ++refs; if (vaddr < vma->vm_end && remainder && pfn_offset < pages_per_huge_page(h)) { /* @@ -4951,6 +4937,25 @@ same_page: * of this compound page. */ goto same_page; + } else if (pages) { + /* + * try_grab_compound_head() should always succeed here, + * because: a) we hold the ptl lock, and b) we've just + * checked that the huge page is present in the page + * tables. If the huge page is present, then the tail + * pages must also be present. The ptl prevents the + * head page and tail pages from being rearranged in + * any way. So this page must be available at this + * point, unless the page refcount overflowed: + */ + if (WARN_ON_ONCE(!try_grab_compound_head(pages[i-1], + refs, + flags))) { + spin_unlock(ptl); + remainder = 0; + err = -ENOMEM; + break; + } } spin_unlock(ptl); } -- cgit v1.2.3 From 6c26d3108393211ecfd44d89404cfb744027bafd Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Wed, 24 Feb 2021 12:07:19 -0800 Subject: mm/hugetlb: fix some comment typos Fix typos sasitfy to satisfy, reservtion to reservation, hugegpage to hugepage and uniprocesor to uniprocessor in comments. Link: https://lkml.kernel.org/r/20210128112028.64831-1-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Reviewed-by: Souptick Joarder Cc: Mike Kravetz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 2 +- mm/hugetlb.c | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index b5807f23caf8..ac3cb239a7ec 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -37,7 +37,7 @@ struct hugepage_subpool { struct hstate *hstate; long min_hpages; /* Minimum huge pages or -1 if no minimum. */ long rsv_hpages; /* Pages reserved against global pool to */ - /* sasitfy minimum size. */ + /* satisfy minimum size. */ }; struct resv_map { diff --git a/mm/hugetlb.c b/mm/hugetlb.c index cf6653879bb4..fc895e25920c 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1434,7 +1434,7 @@ static void __free_huge_page(struct page *page) * reservation. If the page was associated with a subpool, there * would have been a page reserved in the subpool before allocation * via hugepage_subpool_get_pages(). Since we are 'restoring' the - * reservtion, do not call hugepage_subpool_put_pages() as this will + * reservation, do not call hugepage_subpool_put_pages() as this will * remove the reserved page from the subpool. */ if (!restore_reserve) { @@ -3707,7 +3707,7 @@ static unsigned long hugetlb_vm_op_pagesize(struct vm_area_struct *vma) /* * We cannot handle pagefaults against hugetlb pages at all. They cause * handle_mm_fault() to try to instantiate regular-sized pages in the - * hugegpage VMA. do_page_fault() is supposed to trap this, so BUG is we get + * hugepage VMA. do_page_fault() is supposed to trap this, so BUG is we get * this far. */ static vm_fault_t hugetlb_vm_op_fault(struct vm_fault *vmf) @@ -4491,7 +4491,7 @@ u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx) } #else /* - * For uniprocesor systems we always use a single mutex, so just + * For uniprocessor systems we always use a single mutex, so just * return 0 and avoid the hashing overhead. */ u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx) -- cgit v1.2.3 From bae84953815793f68ddd8edeadd3f4e32676a2c8 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Wed, 24 Feb 2021 12:07:32 -0800 Subject: mm/pmem: avoid inserting hugepage PTE entry with fsdax if hugepage support is disabled Differentiate between hardware not supporting hugepages and user disabling THP via 'echo never > /sys/kernel/mm/transparent_hugepage/enabled' For the devdax namespace, the kernel handles the above via the supported_alignment attribute and failing to initialize the namespace if the namespace align value is not supported on the platform. For the fsdax namespace, the kernel will continue to initialize the namespace. This can result in the kernel creating a huge pte entry even though the hardware don't support the same. We do want hugepage support with pmem even if the end-user disabled THP via sysfs file (/sys/kernel/mm/transparent_hugepage/enabled). Hence differentiate between hardware/firmware lacking support vs user-controlled disable of THP and prevent a huge fault if the hardware lacks hugepage support. Link: https://lkml.kernel.org/r/20210205023956.417587-1-aneesh.kumar@linux.ibm.com Signed-off-by: Aneesh Kumar K.V Reviewed-by: Dan Williams Cc: "Kirill A . Shutemov" Cc: Jan Kara Cc: David Hildenbrand Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 15 +++++++++------ mm/huge_memory.c | 6 +++++- 2 files changed, 14 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 6a19f35f836b..ba973efcd369 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -78,6 +78,7 @@ static inline vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, } enum transparent_hugepage_flag { + TRANSPARENT_HUGEPAGE_NEVER_DAX, TRANSPARENT_HUGEPAGE_FLAG, TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, @@ -123,6 +124,13 @@ extern unsigned long transparent_hugepage_flags; */ static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) { + + /* + * If the hardware/firmware marked hugepage support disabled. + */ + if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_NEVER_DAX)) + return false; + if (vma->vm_flags & VM_NOHUGEPAGE) return false; @@ -134,12 +142,7 @@ static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_FLAG)) return true; - /* - * For dax vmas, try to always use hugepage mappings. If the kernel does - * not support hugepages, fsdax mappings will fallback to PAGE_SIZE - * mappings, and device-dax namespaces, that try to guarantee a given - * mapping size, will fail to enable - */ + if (vma_is_dax(vma)) return true; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 4cdcc4da36e8..d77605c30f2e 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -386,7 +386,11 @@ static int __init hugepage_init(void) struct kobject *hugepage_kobj; if (!has_transparent_hugepage()) { - transparent_hugepage_flags = 0; + /* + * Hardware doesn't support hugepages, hence disable + * DAX PMD support. + */ + transparent_hugepage_flags = 1 << TRANSPARENT_HUGEPAGE_NEVER_DAX; return -EINVAL; } -- cgit v1.2.3 From c2135f7c570bc274035834848d9bf46ea89ba763 Mon Sep 17 00:00:00 2001 From: Alex Shi Date: Wed, 24 Feb 2021 12:08:01 -0800 Subject: mm/vmscan: __isolate_lru_page_prepare() cleanup The function just returns 2 results, so using a 'switch' to deal with its result is unnecessary. Also simplify it to a bool func as Vlastimil suggested. Also remove 'goto' by reusing list_move(), and take Matthew Wilcox's suggestion to update comments in function. Link: https://lkml.kernel.org/r/728874d7-2d93-4049-68c1-dcc3b2d52ccd@linux.alibaba.com Signed-off-by: Alex Shi Reviewed-by: Andrew Morton Acked-by: Vlastimil Babka Cc: Matthew Wilcox Cc: Hugh Dickins Cc: Yu Zhao Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 2 +- mm/compaction.c | 2 +- mm/vmscan.c | 68 ++++++++++++++++++++++++---------------------------- 3 files changed, 33 insertions(+), 39 deletions(-) (limited to 'include') diff --git a/include/linux/swap.h b/include/linux/swap.h index 0d64a2bc7e00..32f665b1ee85 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -356,7 +356,7 @@ extern void lru_cache_add_inactive_or_unevictable(struct page *page, extern unsigned long zone_reclaimable_pages(struct zone *zone); extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask); -extern int __isolate_lru_page_prepare(struct page *page, isolate_mode_t mode); +extern bool __isolate_lru_page_prepare(struct page *page, isolate_mode_t mode); extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, diff --git a/mm/compaction.c b/mm/compaction.c index 190ccdaa6c19..8f52532675a9 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -988,7 +988,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, if (unlikely(!get_page_unless_zero(page))) goto isolate_fail; - if (__isolate_lru_page_prepare(page, isolate_mode) != 0) + if (!__isolate_lru_page_prepare(page, isolate_mode)) goto isolate_fail_put; /* Try isolate the page */ diff --git a/mm/vmscan.c b/mm/vmscan.c index b1b574ad199d..04509994aed4 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1539,19 +1539,17 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone, * page: page to consider * mode: one of the LRU isolation modes defined above * - * returns 0 on success, -ve errno on failure. + * returns true on success, false on failure. */ -int __isolate_lru_page_prepare(struct page *page, isolate_mode_t mode) +bool __isolate_lru_page_prepare(struct page *page, isolate_mode_t mode) { - int ret = -EBUSY; - /* Only take pages on the LRU. */ if (!PageLRU(page)) - return ret; + return false; /* Compaction should not handle unevictable pages but CMA can do so */ if (PageUnevictable(page) && !(mode & ISOLATE_UNEVICTABLE)) - return ret; + return false; /* * To minimise LRU disruption, the caller can indicate that it only @@ -1564,7 +1562,7 @@ int __isolate_lru_page_prepare(struct page *page, isolate_mode_t mode) if (mode & ISOLATE_ASYNC_MIGRATE) { /* All the caller can do on PageWriteback is block */ if (PageWriteback(page)) - return ret; + return false; if (PageDirty(page)) { struct address_space *mapping; @@ -1580,20 +1578,20 @@ int __isolate_lru_page_prepare(struct page *page, isolate_mode_t mode) * from the page cache. */ if (!trylock_page(page)) - return ret; + return false; mapping = page_mapping(page); migrate_dirty = !mapping || mapping->a_ops->migratepage; unlock_page(page); if (!migrate_dirty) - return ret; + return false; } } if ((mode & ISOLATE_UNMAPPED) && page_mapped(page)) - return ret; + return false; - return 0; + return true; } /* @@ -1677,35 +1675,31 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, * only when the page is being freed somewhere else. */ scan += nr_pages; - switch (__isolate_lru_page_prepare(page, mode)) { - case 0: - /* - * Be careful not to clear PageLRU until after we're - * sure the page is not being freed elsewhere -- the - * page release code relies on it. - */ - if (unlikely(!get_page_unless_zero(page))) - goto busy; - - if (!TestClearPageLRU(page)) { - /* - * This page may in other isolation path, - * but we still hold lru_lock. - */ - put_page(page); - goto busy; - } - - nr_taken += nr_pages; - nr_zone_taken[page_zonenum(page)] += nr_pages; - list_move(&page->lru, dst); - break; + if (!__isolate_lru_page_prepare(page, mode)) { + /* It is being freed elsewhere */ + list_move(&page->lru, src); + continue; + } + /* + * Be careful not to clear PageLRU until after we're + * sure the page is not being freed elsewhere -- the + * page release code relies on it. + */ + if (unlikely(!get_page_unless_zero(page))) { + list_move(&page->lru, src); + continue; + } - default: -busy: - /* else it is being freed elsewhere */ + if (!TestClearPageLRU(page)) { + /* Another thread is already isolating this page */ + put_page(page); list_move(&page->lru, src); + continue; } + + nr_taken += nr_pages; + nr_zone_taken[page_zonenum(page)] += nr_pages; + list_move(&page->lru, dst); } /* -- cgit v1.2.3 From f90d8191ac864df33b1898bc7edc54eaa24e22bc Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Wed, 24 Feb 2021 12:08:13 -0800 Subject: include/linux/mm_inline.h: shuffle lru list addition and deletion functions These functions will call page_lru() in the following patches. Move them below page_lru() to avoid the forward declaration. Link: https://lore.kernel.org/linux-mm/20201207220949.830352-3-yuzhao@google.com/ Link: https://lkml.kernel.org/r/20210122220600.906146-3-yuzhao@google.com Signed-off-by: Yu Zhao Acked-by: Vlastimil Babka Reviewed-by: Miaohe Lin Cc: Alex Shi Cc: Hugh Dickins Cc: Johannes Weiner Cc: Matthew Wilcox Cc: Michal Hocko Cc: Roman Gushchin Cc: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_inline.h | 42 +++++++++++++++++++++--------------------- 1 file changed, 21 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 8fc71e9d7bb0..2889741f450a 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -45,27 +45,6 @@ static __always_inline void update_lru_size(struct lruvec *lruvec, #endif } -static __always_inline void add_page_to_lru_list(struct page *page, - struct lruvec *lruvec, enum lru_list lru) -{ - update_lru_size(lruvec, lru, page_zonenum(page), thp_nr_pages(page)); - list_add(&page->lru, &lruvec->lists[lru]); -} - -static __always_inline void add_page_to_lru_list_tail(struct page *page, - struct lruvec *lruvec, enum lru_list lru) -{ - update_lru_size(lruvec, lru, page_zonenum(page), thp_nr_pages(page)); - list_add_tail(&page->lru, &lruvec->lists[lru]); -} - -static __always_inline void del_page_from_lru_list(struct page *page, - struct lruvec *lruvec, enum lru_list lru) -{ - list_del(&page->lru); - update_lru_size(lruvec, lru, page_zonenum(page), -thp_nr_pages(page)); -} - /** * page_lru_base_type - which LRU list type should a page be on? * @page: the page to test @@ -125,4 +104,25 @@ static __always_inline enum lru_list page_lru(struct page *page) } return lru; } + +static __always_inline void add_page_to_lru_list(struct page *page, + struct lruvec *lruvec, enum lru_list lru) +{ + update_lru_size(lruvec, lru, page_zonenum(page), thp_nr_pages(page)); + list_add(&page->lru, &lruvec->lists[lru]); +} + +static __always_inline void add_page_to_lru_list_tail(struct page *page, + struct lruvec *lruvec, enum lru_list lru) +{ + update_lru_size(lruvec, lru, page_zonenum(page), thp_nr_pages(page)); + list_add_tail(&page->lru, &lruvec->lists[lru]); +} + +static __always_inline void del_page_from_lru_list(struct page *page, + struct lruvec *lruvec, enum lru_list lru) +{ + list_del(&page->lru); + update_lru_size(lruvec, lru, page_zonenum(page), -thp_nr_pages(page)); +} #endif -- cgit v1.2.3 From 3a9c9788a3149d9745b7eb2eae811e57ef3b127c Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Wed, 24 Feb 2021 12:08:17 -0800 Subject: mm: don't pass "enum lru_list" to lru list addition functions The "enum lru_list" parameter to add_page_to_lru_list() and add_page_to_lru_list_tail() is redundant in the sense that it can be extracted from the "struct page" parameter by page_lru(). A caveat is that we need to make sure PageActive() or PageUnevictable() is correctly set or cleared before calling these two functions. And they are indeed. Link: https://lore.kernel.org/linux-mm/20201207220949.830352-4-yuzhao@google.com/ Link: https://lkml.kernel.org/r/20210122220600.906146-4-yuzhao@google.com Signed-off-by: Yu Zhao Cc: Alex Shi Cc: Hugh Dickins Cc: Johannes Weiner Cc: Matthew Wilcox Cc: Michal Hocko Cc: Roman Gushchin Cc: Vladimir Davydov Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_inline.h | 8 ++++++-- mm/swap.c | 15 +++++++-------- mm/vmscan.c | 6 ++---- 3 files changed, 15 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 2889741f450a..130ba3201d3f 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -106,15 +106,19 @@ static __always_inline enum lru_list page_lru(struct page *page) } static __always_inline void add_page_to_lru_list(struct page *page, - struct lruvec *lruvec, enum lru_list lru) + struct lruvec *lruvec) { + enum lru_list lru = page_lru(page); + update_lru_size(lruvec, lru, page_zonenum(page), thp_nr_pages(page)); list_add(&page->lru, &lruvec->lists[lru]); } static __always_inline void add_page_to_lru_list_tail(struct page *page, - struct lruvec *lruvec, enum lru_list lru) + struct lruvec *lruvec) { + enum lru_list lru = page_lru(page); + update_lru_size(lruvec, lru, page_zonenum(page), thp_nr_pages(page)); list_add_tail(&page->lru, &lruvec->lists[lru]); } diff --git a/mm/swap.c b/mm/swap.c index 2cca7141470c..22fad34b9c18 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -231,7 +231,7 @@ static void pagevec_move_tail_fn(struct page *page, struct lruvec *lruvec) if (!PageUnevictable(page)) { del_page_from_lru_list(page, lruvec, page_lru(page)); ClearPageActive(page); - add_page_to_lru_list_tail(page, lruvec, page_lru(page)); + add_page_to_lru_list_tail(page, lruvec); __count_vm_events(PGROTATED, thp_nr_pages(page)); } } @@ -313,8 +313,7 @@ static void __activate_page(struct page *page, struct lruvec *lruvec) del_page_from_lru_list(page, lruvec, lru); SetPageActive(page); - lru += LRU_ACTIVE; - add_page_to_lru_list(page, lruvec, lru); + add_page_to_lru_list(page, lruvec); trace_mm_lru_activate(page); __count_vm_events(PGACTIVATE, nr_pages); @@ -543,14 +542,14 @@ static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec) * It can make readahead confusing. But race window * is _really_ small and it's non-critical problem. */ - add_page_to_lru_list(page, lruvec, lru); + add_page_to_lru_list(page, lruvec); SetPageReclaim(page); } else { /* * The page's writeback ends up during pagevec * We moves tha page into tail of inactive. */ - add_page_to_lru_list_tail(page, lruvec, lru); + add_page_to_lru_list_tail(page, lruvec); __count_vm_events(PGROTATED, nr_pages); } @@ -570,7 +569,7 @@ static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec) del_page_from_lru_list(page, lruvec, lru + LRU_ACTIVE); ClearPageActive(page); ClearPageReferenced(page); - add_page_to_lru_list(page, lruvec, lru); + add_page_to_lru_list(page, lruvec); __count_vm_events(PGDEACTIVATE, nr_pages); __count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, @@ -595,7 +594,7 @@ static void lru_lazyfree_fn(struct page *page, struct lruvec *lruvec) * anonymous pages */ ClearPageSwapBacked(page); - add_page_to_lru_list(page, lruvec, LRU_INACTIVE_FILE); + add_page_to_lru_list(page, lruvec); __count_vm_events(PGLAZYFREE, nr_pages); __count_memcg_events(lruvec_memcg(lruvec), PGLAZYFREE, @@ -1005,7 +1004,7 @@ static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec) __count_vm_events(UNEVICTABLE_PGCULLED, nr_pages); } - add_page_to_lru_list(page, lruvec, lru); + add_page_to_lru_list(page, lruvec); trace_mm_lru_insertion(page, lru); } diff --git a/mm/vmscan.c b/mm/vmscan.c index 19875660e8f8..09e4f97488c9 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1867,7 +1867,7 @@ static unsigned noinline_for_stack move_pages_to_lru(struct lruvec *lruvec, * inhibits memcg migration). */ VM_BUG_ON_PAGE(!lruvec_holds_page_lru_lock(page, lruvec), page); - add_page_to_lru_list(page, lruvec, page_lru(page)); + add_page_to_lru_list(page, lruvec); nr_pages = thp_nr_pages(page); nr_moved += nr_pages; if (PageActive(page)) @@ -4282,12 +4282,10 @@ void check_move_unevictable_pages(struct pagevec *pvec) lruvec = relock_page_lruvec_irq(page, lruvec); if (page_evictable(page) && PageUnevictable(page)) { - enum lru_list lru = page_lru_base_type(page); - VM_BUG_ON_PAGE(PageActive(page), page); ClearPageUnevictable(page); del_page_from_lru_list(page, lruvec, LRU_UNEVICTABLE); - add_page_to_lru_list(page, lruvec, lru); + add_page_to_lru_list(page, lruvec); pgrescued += nr_pages; } SetPageLRU(page); -- cgit v1.2.3 From 861404536a3af3c39f1b10959a40def3d8efa2dd Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Wed, 24 Feb 2021 12:08:21 -0800 Subject: mm/swap.c: don't pass "enum lru_list" to trace_mm_lru_insertion() The parameter is redundant in the sense that it can be extracted from the "struct page" parameter by page_lru() correctly. Link: https://lore.kernel.org/linux-mm/20201207220949.830352-5-yuzhao@google.com/ Link: https://lkml.kernel.org/r/20210122220600.906146-5-yuzhao@google.com Signed-off-by: Yu Zhao Reviewed-by: Alex Shi Cc: Hugh Dickins Cc: Johannes Weiner Cc: Matthew Wilcox Cc: Michal Hocko Cc: Roman Gushchin Cc: Vladimir Davydov Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/pagemap.h | 11 ++++------- mm/swap.c | 5 +---- 2 files changed, 5 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/trace/events/pagemap.h b/include/trace/events/pagemap.h index 8fd1babae761..e1735fe7c76a 100644 --- a/include/trace/events/pagemap.h +++ b/include/trace/events/pagemap.h @@ -27,24 +27,21 @@ TRACE_EVENT(mm_lru_insertion, - TP_PROTO( - struct page *page, - int lru - ), + TP_PROTO(struct page *page), - TP_ARGS(page, lru), + TP_ARGS(page), TP_STRUCT__entry( __field(struct page *, page ) __field(unsigned long, pfn ) - __field(int, lru ) + __field(enum lru_list, lru ) __field(unsigned long, flags ) ), TP_fast_assign( __entry->page = page; __entry->pfn = page_to_pfn(page); - __entry->lru = lru; + __entry->lru = page_lru(page); __entry->flags = trace_pagemap_flags(page); ), diff --git a/mm/swap.c b/mm/swap.c index 22fad34b9c18..a26e3a4fe17b 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -957,7 +957,6 @@ EXPORT_SYMBOL(__pagevec_release); static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec) { - enum lru_list lru; int was_unevictable = TestClearPageUnevictable(page); int nr_pages = thp_nr_pages(page); @@ -993,11 +992,9 @@ static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec) smp_mb__after_atomic(); if (page_evictable(page)) { - lru = page_lru(page); if (was_unevictable) __count_vm_events(UNEVICTABLE_PGRESCUED, nr_pages); } else { - lru = LRU_UNEVICTABLE; ClearPageActive(page); SetPageUnevictable(page); if (!was_unevictable) @@ -1005,7 +1002,7 @@ static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec) } add_page_to_lru_list(page, lruvec); - trace_mm_lru_insertion(page, lru); + trace_mm_lru_insertion(page); } /* -- cgit v1.2.3 From 46ae6b2cc2a47904a368d238425531ea91f3a2a5 Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Wed, 24 Feb 2021 12:08:25 -0800 Subject: mm/swap.c: don't pass "enum lru_list" to del_page_from_lru_list() The parameter is redundant in the sense that it can be potentially extracted from the "struct page" parameter by page_lru(). We need to make sure that existing PageActive() or PageUnevictable() remains until the function returns. A few places don't conform, and simple reordering fixes them. This patch may have left page_off_lru() seemingly odd, and we'll take care of it in the next patch. Link: https://lore.kernel.org/linux-mm/20201207220949.830352-6-yuzhao@google.com/ Link: https://lkml.kernel.org/r/20210122220600.906146-6-yuzhao@google.com Signed-off-by: Yu Zhao Cc: Alex Shi Cc: Hugh Dickins Cc: Johannes Weiner Cc: Matthew Wilcox Cc: Michal Hocko Cc: Roman Gushchin Cc: Vladimir Davydov Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_inline.h | 5 +++-- mm/compaction.c | 2 +- mm/mlock.c | 3 +-- mm/swap.c | 26 ++++++++++---------------- mm/vmscan.c | 4 ++-- 5 files changed, 17 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 130ba3201d3f..ffacc6273678 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -124,9 +124,10 @@ static __always_inline void add_page_to_lru_list_tail(struct page *page, } static __always_inline void del_page_from_lru_list(struct page *page, - struct lruvec *lruvec, enum lru_list lru) + struct lruvec *lruvec) { list_del(&page->lru); - update_lru_size(lruvec, lru, page_zonenum(page), -thp_nr_pages(page)); + update_lru_size(lruvec, page_lru(page), page_zonenum(page), + -thp_nr_pages(page)); } #endif diff --git a/mm/compaction.c b/mm/compaction.c index 8f52532675a9..3aef10c61d0e 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1034,7 +1034,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, low_pfn += compound_nr(page) - 1; /* Successfully isolated */ - del_page_from_lru_list(page, lruvec, page_lru(page)); + del_page_from_lru_list(page, lruvec); mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON + page_is_file_lru(page), thp_nr_pages(page)); diff --git a/mm/mlock.c b/mm/mlock.c index 55b3b3672977..73960bb3464d 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -278,8 +278,7 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone) */ if (TestClearPageLRU(page)) { lruvec = relock_page_lruvec_irq(page, lruvec); - del_page_from_lru_list(page, lruvec, - page_lru(page)); + del_page_from_lru_list(page, lruvec); continue; } else __munlock_isolation_failed(page); diff --git a/mm/swap.c b/mm/swap.c index a26e3a4fe17b..ff910f636df2 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -85,7 +85,8 @@ static void __page_cache_release(struct page *page) lruvec = lock_page_lruvec_irqsave(page, &flags); VM_BUG_ON_PAGE(!PageLRU(page), page); __ClearPageLRU(page); - del_page_from_lru_list(page, lruvec, page_off_lru(page)); + del_page_from_lru_list(page, lruvec); + page_off_lru(page); unlock_page_lruvec_irqrestore(lruvec, flags); } __ClearPageWaiters(page); @@ -229,7 +230,7 @@ static void pagevec_lru_move_fn(struct pagevec *pvec, static void pagevec_move_tail_fn(struct page *page, struct lruvec *lruvec) { if (!PageUnevictable(page)) { - del_page_from_lru_list(page, lruvec, page_lru(page)); + del_page_from_lru_list(page, lruvec); ClearPageActive(page); add_page_to_lru_list_tail(page, lruvec); __count_vm_events(PGROTATED, thp_nr_pages(page)); @@ -308,10 +309,9 @@ void lru_note_cost_page(struct page *page) static void __activate_page(struct page *page, struct lruvec *lruvec) { if (!PageActive(page) && !PageUnevictable(page)) { - int lru = page_lru_base_type(page); int nr_pages = thp_nr_pages(page); - del_page_from_lru_list(page, lruvec, lru); + del_page_from_lru_list(page, lruvec); SetPageActive(page); add_page_to_lru_list(page, lruvec); trace_mm_lru_activate(page); @@ -518,8 +518,7 @@ void lru_cache_add_inactive_or_unevictable(struct page *page, */ static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec) { - int lru; - bool active; + bool active = PageActive(page); int nr_pages = thp_nr_pages(page); if (PageUnevictable(page)) @@ -529,10 +528,7 @@ static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec) if (page_mapped(page)) return; - active = PageActive(page); - lru = page_lru_base_type(page); - - del_page_from_lru_list(page, lruvec, lru + active); + del_page_from_lru_list(page, lruvec); ClearPageActive(page); ClearPageReferenced(page); @@ -563,10 +559,9 @@ static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec) static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec) { if (PageActive(page) && !PageUnevictable(page)) { - int lru = page_lru_base_type(page); int nr_pages = thp_nr_pages(page); - del_page_from_lru_list(page, lruvec, lru + LRU_ACTIVE); + del_page_from_lru_list(page, lruvec); ClearPageActive(page); ClearPageReferenced(page); add_page_to_lru_list(page, lruvec); @@ -581,11 +576,9 @@ static void lru_lazyfree_fn(struct page *page, struct lruvec *lruvec) { if (PageAnon(page) && PageSwapBacked(page) && !PageSwapCache(page) && !PageUnevictable(page)) { - bool active = PageActive(page); int nr_pages = thp_nr_pages(page); - del_page_from_lru_list(page, lruvec, - LRU_INACTIVE_ANON + active); + del_page_from_lru_list(page, lruvec); ClearPageActive(page); ClearPageReferenced(page); /* @@ -919,7 +912,8 @@ void release_pages(struct page **pages, int nr) VM_BUG_ON_PAGE(!PageLRU(page), page); __ClearPageLRU(page); - del_page_from_lru_list(page, lruvec, page_off_lru(page)); + del_page_from_lru_list(page, lruvec); + page_off_lru(page); } __ClearPageWaiters(page); diff --git a/mm/vmscan.c b/mm/vmscan.c index 09e4f97488c9..7c65d47e6612 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1766,7 +1766,7 @@ int isolate_lru_page(struct page *page) get_page(page); lruvec = lock_page_lruvec_irq(page); - del_page_from_lru_list(page, lruvec, page_lru(page)); + del_page_from_lru_list(page, lruvec); unlock_page_lruvec_irq(lruvec); ret = 0; } @@ -4283,8 +4283,8 @@ void check_move_unevictable_pages(struct pagevec *pvec) lruvec = relock_page_lruvec_irq(page, lruvec); if (page_evictable(page) && PageUnevictable(page)) { VM_BUG_ON_PAGE(PageActive(page), page); + del_page_from_lru_list(page, lruvec); ClearPageUnevictable(page); - del_page_from_lru_list(page, lruvec, LRU_UNEVICTABLE); add_page_to_lru_list(page, lruvec); pgrescued += nr_pages; } -- cgit v1.2.3 From 875601796267214f286d3581fe74f2805d060fe8 Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Wed, 24 Feb 2021 12:08:28 -0800 Subject: mm: add __clear_page_lru_flags() to replace page_off_lru() Similar to page_off_lru(), the new function does non-atomic clearing of PageLRU() in addition to PageActive() and PageUnevictable(), on a page that has no references left. If PageActive() and PageUnevictable() are both set, refuse to clear either and leave them to bad_page(). This is a behavior change that is meant to help debug. Link: https://lore.kernel.org/linux-mm/20201207220949.830352-7-yuzhao@google.com/ Link: https://lkml.kernel.org/r/20210122220600.906146-7-yuzhao@google.com Signed-off-by: Yu Zhao Cc: Alex Shi Cc: Hugh Dickins Cc: Johannes Weiner Cc: Matthew Wilcox Cc: Michal Hocko Cc: Roman Gushchin Cc: Vladimir Davydov Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_inline.h | 28 ++++++++++------------------ mm/swap.c | 6 ++---- mm/vmscan.c | 3 +-- 3 files changed, 13 insertions(+), 24 deletions(-) (limited to 'include') diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index ffacc6273678..ef3fd79222e5 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -61,27 +61,19 @@ static inline enum lru_list page_lru_base_type(struct page *page) } /** - * page_off_lru - which LRU list was page on? clearing its lru flags. - * @page: the page to test - * - * Returns the LRU list a page was on, as an index into the array of LRU - * lists; and clears its Unevictable or Active flags, ready for freeing. + * __clear_page_lru_flags - clear page lru flags before releasing a page + * @page: the page that was on lru and now has a zero reference */ -static __always_inline enum lru_list page_off_lru(struct page *page) +static __always_inline void __clear_page_lru_flags(struct page *page) { - enum lru_list lru; + __ClearPageLRU(page); - if (PageUnevictable(page)) { - __ClearPageUnevictable(page); - lru = LRU_UNEVICTABLE; - } else { - lru = page_lru_base_type(page); - if (PageActive(page)) { - __ClearPageActive(page); - lru += LRU_ACTIVE; - } - } - return lru; + /* this shouldn't happen, so leave the flags to bad_page() */ + if (PageActive(page) && PageUnevictable(page)) + return; + + __ClearPageActive(page); + __ClearPageUnevictable(page); } /** diff --git a/mm/swap.c b/mm/swap.c index ff910f636df2..1455fa56a0ee 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -84,9 +84,8 @@ static void __page_cache_release(struct page *page) lruvec = lock_page_lruvec_irqsave(page, &flags); VM_BUG_ON_PAGE(!PageLRU(page), page); - __ClearPageLRU(page); del_page_from_lru_list(page, lruvec); - page_off_lru(page); + __clear_page_lru_flags(page); unlock_page_lruvec_irqrestore(lruvec, flags); } __ClearPageWaiters(page); @@ -911,9 +910,8 @@ void release_pages(struct page **pages, int nr) lock_batch = 0; VM_BUG_ON_PAGE(!PageLRU(page), page); - __ClearPageLRU(page); del_page_from_lru_list(page, lruvec); - page_off_lru(page); + __clear_page_lru_flags(page); } __ClearPageWaiters(page); diff --git a/mm/vmscan.c b/mm/vmscan.c index 7c65d47e6612..452dd3818aa3 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1849,8 +1849,7 @@ static unsigned noinline_for_stack move_pages_to_lru(struct lruvec *lruvec, SetPageLRU(page); if (unlikely(put_page_testzero(page))) { - __ClearPageLRU(page); - __ClearPageActive(page); + __clear_page_lru_flags(page); if (unlikely(PageCompound(page))) { spin_unlock_irq(&lruvec->lru_lock); -- cgit v1.2.3 From bc7112719e1e80e4208eef3fc9bd8d2b6c263e7d Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Wed, 24 Feb 2021 12:08:32 -0800 Subject: mm: VM_BUG_ON lru page flags Move scattered VM_BUG_ONs to two essential places that cover all lru list additions and deletions. Link: https://lore.kernel.org/linux-mm/20201207220949.830352-8-yuzhao@google.com/ Link: https://lkml.kernel.org/r/20210122220600.906146-8-yuzhao@google.com Signed-off-by: Yu Zhao Cc: Alex Shi Cc: Hugh Dickins Cc: Johannes Weiner Cc: Matthew Wilcox Cc: Michal Hocko Cc: Roman Gushchin Cc: Vladimir Davydov Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_inline.h | 4 ++++ mm/swap.c | 2 -- mm/vmscan.c | 1 - 3 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index ef3fd79222e5..6d907a4dd6ad 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -66,6 +66,8 @@ static inline enum lru_list page_lru_base_type(struct page *page) */ static __always_inline void __clear_page_lru_flags(struct page *page) { + VM_BUG_ON_PAGE(!PageLRU(page), page); + __ClearPageLRU(page); /* this shouldn't happen, so leave the flags to bad_page() */ @@ -87,6 +89,8 @@ static __always_inline enum lru_list page_lru(struct page *page) { enum lru_list lru; + VM_BUG_ON_PAGE(PageActive(page) && PageUnevictable(page), page); + if (PageUnevictable(page)) lru = LRU_UNEVICTABLE; else { diff --git a/mm/swap.c b/mm/swap.c index 1455fa56a0ee..ab3258afcbeb 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -83,7 +83,6 @@ static void __page_cache_release(struct page *page) unsigned long flags; lruvec = lock_page_lruvec_irqsave(page, &flags); - VM_BUG_ON_PAGE(!PageLRU(page), page); del_page_from_lru_list(page, lruvec); __clear_page_lru_flags(page); unlock_page_lruvec_irqrestore(lruvec, flags); @@ -909,7 +908,6 @@ void release_pages(struct page **pages, int nr) if (prev_lruvec != lruvec) lock_batch = 0; - VM_BUG_ON_PAGE(!PageLRU(page), page); del_page_from_lru_list(page, lruvec); __clear_page_lru_flags(page); } diff --git a/mm/vmscan.c b/mm/vmscan.c index 452dd3818aa3..348a90096550 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -4281,7 +4281,6 @@ void check_move_unevictable_pages(struct pagevec *pvec) lruvec = relock_page_lruvec_irq(page, lruvec); if (page_evictable(page) && PageUnevictable(page)) { - VM_BUG_ON_PAGE(PageActive(page), page); del_page_from_lru_list(page, lruvec); ClearPageUnevictable(page); add_page_to_lru_list(page, lruvec); -- cgit v1.2.3 From c1770e34f3e7640887d8129fc05d13fe17101301 Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Wed, 24 Feb 2021 12:08:36 -0800 Subject: include/linux/mm_inline.h: fold page_lru_base_type() into its sole caller We've removed all other references to this function. Link: https://lore.kernel.org/linux-mm/20201207220949.830352-9-yuzhao@google.com/ Link: https://lkml.kernel.org/r/20210122220600.906146-9-yuzhao@google.com Signed-off-by: Yu Zhao Reviewed-by: Alex Shi Cc: Hugh Dickins Cc: Johannes Weiner Cc: Matthew Wilcox Cc: Michal Hocko Cc: Roman Gushchin Cc: Vladimir Davydov Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_inline.h | 27 ++++++--------------------- 1 file changed, 6 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 6d907a4dd6ad..7183c7a03f09 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -45,21 +45,6 @@ static __always_inline void update_lru_size(struct lruvec *lruvec, #endif } -/** - * page_lru_base_type - which LRU list type should a page be on? - * @page: the page to test - * - * Used for LRU list index arithmetic. - * - * Returns the base LRU type - file or anon - @page should be on. - */ -static inline enum lru_list page_lru_base_type(struct page *page) -{ - if (page_is_file_lru(page)) - return LRU_INACTIVE_FILE; - return LRU_INACTIVE_ANON; -} - /** * __clear_page_lru_flags - clear page lru flags before releasing a page * @page: the page that was on lru and now has a zero reference @@ -92,12 +77,12 @@ static __always_inline enum lru_list page_lru(struct page *page) VM_BUG_ON_PAGE(PageActive(page) && PageUnevictable(page), page); if (PageUnevictable(page)) - lru = LRU_UNEVICTABLE; - else { - lru = page_lru_base_type(page); - if (PageActive(page)) - lru += LRU_ACTIVE; - } + return LRU_UNEVICTABLE; + + lru = page_is_file_lru(page) ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON; + if (PageActive(page)) + lru += LRU_ACTIVE; + return lru; } -- cgit v1.2.3 From 289ccba18af436f2b65ec69b2be1b086ec9f24a4 Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Wed, 24 Feb 2021 12:08:40 -0800 Subject: include/linux/mm_inline.h: fold __update_lru_size() into its sole caller All other references to the function were removed after commit a892cb6b977f ("mm/vmscan.c: use update_lru_size() in update_lru_sizes()"). Link: https://lore.kernel.org/linux-mm/20201207220949.830352-10-yuzhao@google.com/ Link: https://lkml.kernel.org/r/20210122220600.906146-10-yuzhao@google.com Signed-off-by: Yu Zhao Reviewed-by: Alex Shi Cc: Hugh Dickins Cc: Johannes Weiner Cc: Matthew Wilcox Cc: Michal Hocko Cc: Roman Gushchin Cc: Vladimir Davydov Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_inline.h | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 7183c7a03f09..355ea1ee32bd 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -24,7 +24,7 @@ static inline int page_is_file_lru(struct page *page) return !PageSwapBacked(page); } -static __always_inline void __update_lru_size(struct lruvec *lruvec, +static __always_inline void update_lru_size(struct lruvec *lruvec, enum lru_list lru, enum zone_type zid, int nr_pages) { @@ -33,13 +33,6 @@ static __always_inline void __update_lru_size(struct lruvec *lruvec, __mod_lruvec_state(lruvec, NR_LRU_BASE + lru, nr_pages); __mod_zone_page_state(&pgdat->node_zones[zid], NR_ZONE_LRU_BASE + lru, nr_pages); -} - -static __always_inline void update_lru_size(struct lruvec *lruvec, - enum lru_list lru, enum zone_type zid, - int nr_pages) -{ - __update_lru_size(lruvec, lru, zid, nr_pages); #ifdef CONFIG_MEMCG mem_cgroup_update_lru_size(lruvec, lru, zid, nr_pages); #endif -- cgit v1.2.3 From 2091339d59e7808e9b39a79f48e3d17ef7389b97 Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Wed, 24 Feb 2021 12:08:44 -0800 Subject: mm/vmscan.c: make lruvec_lru_size() static All other references to the function were removed after commit b910718a948a ("mm: vmscan: detect file thrashing at the reclaim root"). Link: https://lore.kernel.org/linux-mm/20201207220949.830352-11-yuzhao@google.com/ Link: https://lkml.kernel.org/r/20210122220600.906146-11-yuzhao@google.com Signed-off-by: Yu Zhao Reviewed-by: Alex Shi Cc: Hugh Dickins Cc: Johannes Weiner Cc: Matthew Wilcox Cc: Michal Hocko Cc: Roman Gushchin Cc: Vladimir Davydov Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 2 -- mm/vmscan.c | 3 ++- 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index fc99e9241846..9198b7ade85f 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -892,8 +892,6 @@ static inline struct pglist_data *lruvec_pgdat(struct lruvec *lruvec) #endif } -extern unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx); - #ifdef CONFIG_HAVE_MEMORYLESS_NODES int local_memory_node(int node_id); #else diff --git a/mm/vmscan.c b/mm/vmscan.c index 348a90096550..fea6b43bc1f9 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -310,7 +310,8 @@ unsigned long zone_reclaimable_pages(struct zone *zone) * @lru: lru to use * @zone_idx: zones to consider (use MAX_NR_ZONES for the whole LRU list) */ -unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx) +static unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, + int zone_idx) { unsigned long size = 0; int zid; -- cgit v1.2.3 From d6995da311221a05c8aef3bda2629e5cb14c7302 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Wed, 24 Feb 2021 12:08:51 -0800 Subject: hugetlb: use page.private for hugetlb specific page flags Patch series "create hugetlb flags to consolidate state", v3. While discussing a series of hugetlb fixes in [1], it became evident that the hugetlb specific page state information is stored in a somewhat haphazard manner. Code dealing with state information would be easier to read, understand and maintain if this information was stored in a consistent manner. This series uses page.private of the hugetlb head page for storing a set of hugetlb specific page flags. Routines are priovided for test, set and clear of the flags. [1] https://lore.kernel.org/r/20210106084739.63318-1-songmuchun@bytedance.com This patch (of 4): As hugetlbfs evolved, state information about hugetlb pages was added. One 'convenient' way of doing this was to use available fields in tail pages. Over time, it has become difficult to know the meaning or contents of fields simply by looking at a small bit of code. Sometimes, the naming is just confusing. For example: The PagePrivate flag indicates a huge page reservation was consumed and needs to be restored if an error is encountered and the page is freed before it is instantiated. The page.private field contains the pointer to a subpool if the page is associated with one. In an effort to make the code more readable, use page.private to contain hugetlb specific page flags. These flags will have test, set and clear functions similar to those used for 'normal' page flags. More importantly, an enum of flag values will be created with names that actually reflect their purpose. In this patch, - Create infrastructure for hugetlb specific page flag functions - Move subpool pointer to page[1].private to make way for flags Create routines with meaningful names to modify subpool field - Use new HPageRestoreReserve flag instead of PagePrivate Conversion of other state information will happen in subsequent patches. Link: https://lkml.kernel.org/r/20210122195231.324857-1-mike.kravetz@oracle.com Link: https://lkml.kernel.org/r/20210122195231.324857-2-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Reviewed-by: Oscar Salvador Acked-by: Michal Hocko Cc: Naoya Horiguchi Cc: Muchun Song Cc: David Hildenbrand Cc: Matthew Wilcox Cc: Miaohe Lin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/hugetlbfs/inode.c | 12 +++------ include/linux/hugetlb.h | 68 +++++++++++++++++++++++++++++++++++++++++++++++++ mm/hugetlb.c | 48 +++++++++++++++++----------------- 3 files changed, 96 insertions(+), 32 deletions(-) (limited to 'include') diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index b7a72f577aab..907f6405e805 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -973,15 +973,9 @@ static int hugetlbfs_migrate_page(struct address_space *mapping, if (rc != MIGRATEPAGE_SUCCESS) return rc; - /* - * page_private is subpool pointer in hugetlb pages. Transfer to - * new page. PagePrivate is not associated with page_private for - * hugetlb pages and can not be set here as only page_huge_active - * pages can be migrated. - */ - if (page_private(page)) { - set_page_private(newpage, page_private(page)); - set_page_private(page, 0); + if (hugetlb_page_subpool(page)) { + hugetlb_set_page_subpool(newpage, hugetlb_page_subpool(page)); + hugetlb_set_page_subpool(page, NULL); } if (mode != MIGRATE_SYNC_NO_COPY) diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index ac3cb239a7ec..249c65e1d8ca 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -472,6 +472,60 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long flags); #endif /* HAVE_ARCH_HUGETLB_UNMAPPED_AREA */ +/* + * huegtlb page specific state flags. These flags are located in page.private + * of the hugetlb head page. Functions created via the below macros should be + * used to manipulate these flags. + * + * HPG_restore_reserve - Set when a hugetlb page consumes a reservation at + * allocation time. Cleared when page is fully instantiated. Free + * routine checks flag to restore a reservation on error paths. + */ +enum hugetlb_page_flags { + HPG_restore_reserve = 0, + __NR_HPAGEFLAGS, +}; + +/* + * Macros to create test, set and clear function definitions for + * hugetlb specific page flags. + */ +#ifdef CONFIG_HUGETLB_PAGE +#define TESTHPAGEFLAG(uname, flname) \ +static inline int HPage##uname(struct page *page) \ + { return test_bit(HPG_##flname, &(page->private)); } + +#define SETHPAGEFLAG(uname, flname) \ +static inline void SetHPage##uname(struct page *page) \ + { set_bit(HPG_##flname, &(page->private)); } + +#define CLEARHPAGEFLAG(uname, flname) \ +static inline void ClearHPage##uname(struct page *page) \ + { clear_bit(HPG_##flname, &(page->private)); } +#else +#define TESTHPAGEFLAG(uname, flname) \ +static inline int HPage##uname(struct page *page) \ + { return 0; } + +#define SETHPAGEFLAG(uname, flname) \ +static inline void SetHPage##uname(struct page *page) \ + { } + +#define CLEARHPAGEFLAG(uname, flname) \ +static inline void ClearHPage##uname(struct page *page) \ + { } +#endif + +#define HPAGEFLAG(uname, flname) \ + TESTHPAGEFLAG(uname, flname) \ + SETHPAGEFLAG(uname, flname) \ + CLEARHPAGEFLAG(uname, flname) \ + +/* + * Create functions associated with hugetlb page flags + */ +HPAGEFLAG(RestoreReserve, restore_reserve) + #ifdef CONFIG_HUGETLB_PAGE #define HSTATE_NAME_LEN 32 @@ -531,6 +585,20 @@ extern unsigned int default_hstate_idx; #define default_hstate (hstates[default_hstate_idx]) +/* + * hugetlb page subpool pointer located in hpage[1].private + */ +static inline struct hugepage_subpool *hugetlb_page_subpool(struct page *hpage) +{ + return (struct hugepage_subpool *)(hpage+1)->private; +} + +static inline void hugetlb_set_page_subpool(struct page *hpage, + struct hugepage_subpool *subpool) +{ + set_page_private(hpage+1, (unsigned long)subpool); +} + static inline struct hstate *hstate_file(struct file *f) { return hstate_inode(file_inode(f)); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 8a1d1f85e21e..f5e85dabb7a3 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1143,7 +1143,7 @@ static struct page *dequeue_huge_page_vma(struct hstate *h, nid = huge_node(vma, address, gfp_mask, &mpol, &nodemask); page = dequeue_huge_page_nodemask(h, gfp_mask, nid, nodemask); if (page && !avoid_reserve && vma_has_reserves(vma, chg)) { - SetPagePrivate(page); + SetHPageRestoreReserve(page); h->resv_huge_pages--; } @@ -1418,20 +1418,19 @@ static void __free_huge_page(struct page *page) */ struct hstate *h = page_hstate(page); int nid = page_to_nid(page); - struct hugepage_subpool *spool = - (struct hugepage_subpool *)page_private(page); + struct hugepage_subpool *spool = hugetlb_page_subpool(page); bool restore_reserve; VM_BUG_ON_PAGE(page_count(page), page); VM_BUG_ON_PAGE(page_mapcount(page), page); - set_page_private(page, 0); + hugetlb_set_page_subpool(page, NULL); page->mapping = NULL; - restore_reserve = PagePrivate(page); - ClearPagePrivate(page); + restore_reserve = HPageRestoreReserve(page); + ClearHPageRestoreReserve(page); /* - * If PagePrivate() was set on page, page allocation consumed a + * If HPageRestoreReserve was set on page, page allocation consumed a * reservation. If the page was associated with a subpool, there * would have been a page reserved in the subpool before allocation * via hugepage_subpool_get_pages(). Since we are 'restoring' the @@ -2263,24 +2262,24 @@ static long vma_add_reservation(struct hstate *h, * This routine is called to restore a reservation on error paths. In the * specific error paths, a huge page was allocated (via alloc_huge_page) * and is about to be freed. If a reservation for the page existed, - * alloc_huge_page would have consumed the reservation and set PagePrivate - * in the newly allocated page. When the page is freed via free_huge_page, - * the global reservation count will be incremented if PagePrivate is set. - * However, free_huge_page can not adjust the reserve map. Adjust the - * reserve map here to be consistent with global reserve count adjustments - * to be made by free_huge_page. + * alloc_huge_page would have consumed the reservation and set + * HPageRestoreReserve in the newly allocated page. When the page is freed + * via free_huge_page, the global reservation count will be incremented if + * HPageRestoreReserve is set. However, free_huge_page can not adjust the + * reserve map. Adjust the reserve map here to be consistent with global + * reserve count adjustments to be made by free_huge_page. */ static void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, unsigned long address, struct page *page) { - if (unlikely(PagePrivate(page))) { + if (unlikely(HPageRestoreReserve(page))) { long rc = vma_needs_reservation(h, vma, address); if (unlikely(rc < 0)) { /* * Rare out of memory condition in reserve map - * manipulation. Clear PagePrivate so that + * manipulation. Clear HPageRestoreReserve so that * global reserve count will not be incremented * by free_huge_page. This will make it appear * as though the reservation for this page was @@ -2289,7 +2288,7 @@ static void restore_reserve_on_error(struct hstate *h, * is better than inconsistent global huge page * accounting of reserve counts. */ - ClearPagePrivate(page); + ClearHPageRestoreReserve(page); } else if (rc) { rc = vma_add_reservation(h, vma, address); if (unlikely(rc < 0)) @@ -2297,7 +2296,7 @@ static void restore_reserve_on_error(struct hstate *h, * See above comment about rare out of * memory condition. */ - ClearPagePrivate(page); + ClearHPageRestoreReserve(page); } else vma_end_reservation(h, vma, address); } @@ -2378,7 +2377,7 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, if (!page) goto out_uncharge_cgroup; if (!avoid_reserve && vma_has_reserves(vma, gbl_chg)) { - SetPagePrivate(page); + SetHPageRestoreReserve(page); h->resv_huge_pages--; } spin_lock(&hugetlb_lock); @@ -2396,7 +2395,7 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, spin_unlock(&hugetlb_lock); - set_page_private(page, (unsigned long)spool); + hugetlb_set_page_subpool(page, spool); map_commit = vma_commit_reservation(h, vma, addr); if (unlikely(map_chg > map_commit)) { @@ -3170,6 +3169,9 @@ static int __init hugetlb_init(void) { int i; + BUILD_BUG_ON(sizeof_field(struct page, private) * BITS_PER_BYTE < + __NR_HPAGEFLAGS); + if (!hugepages_supported()) { if (hugetlb_max_hstate || default_hstate_max_huge_pages) pr_warn("HugeTLB: huge pages not supported, ignoring associated command-line parameters\n"); @@ -4207,7 +4209,7 @@ retry_avoidcopy: spin_lock(ptl); ptep = huge_pte_offset(mm, haddr, huge_page_size(h)); if (likely(ptep && pte_same(huge_ptep_get(ptep), pte))) { - ClearPagePrivate(new_page); + ClearHPageRestoreReserve(new_page); /* Break COW */ huge_ptep_clear_flush(vma, haddr, ptep); @@ -4274,7 +4276,7 @@ int huge_add_to_page_cache(struct page *page, struct address_space *mapping, if (err) return err; - ClearPagePrivate(page); + ClearHPageRestoreReserve(page); /* * set page dirty so that it will not be removed from cache/file @@ -4436,7 +4438,7 @@ retry: goto backout; if (anon_rmap) { - ClearPagePrivate(page); + ClearHPageRestoreReserve(page); hugepage_add_new_anon_rmap(page, vma, haddr); } else page_dup_rmap(page, true); @@ -4750,7 +4752,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, if (vm_shared) { page_dup_rmap(page, true); } else { - ClearPagePrivate(page); + ClearHPageRestoreReserve(page); hugepage_add_new_anon_rmap(page, dst_vma, dst_addr); } -- cgit v1.2.3 From 8f251a3d5ce3bdea73bd045ed35db64f32e0d0d9 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Wed, 24 Feb 2021 12:08:56 -0800 Subject: hugetlb: convert page_huge_active() HPageMigratable flag Use the new hugetlb page specific flag HPageMigratable to replace the page_huge_active interfaces. By it's name, page_huge_active implied that a huge page was on the active list. However, that is not really what code checking the flag wanted to know. It really wanted to determine if the huge page could be migrated. This happens when the page is actually added to the page cache and/or task page table. This is the reasoning behind the name change. The VM_BUG_ON_PAGE() calls in the *_huge_active() interfaces are not really necessary as we KNOW the page is a hugetlb page. Therefore, they are removed. The routine page_huge_active checked for PageHeadHuge before testing the active bit. This is unnecessary in the case where we hold a reference or lock and know it is a hugetlb head page. page_huge_active is also called without holding a reference or lock (scan_movable_pages), and can race with code freeing the page. The extra check in page_huge_active shortened the race window, but did not prevent the race. Offline code calling scan_movable_pages already deals with these races, so removing the check is acceptable. Add comment to racy code. [songmuchun@bytedance.com: remove set_page_huge_active() declaration from include/linux/hugetlb.h] Link: https://lkml.kernel.org/r/CAMZfGtUda+KoAZscU0718TN61cSFwp4zy=y2oZ=+6Z2TAZZwng@mail.gmail.com Link: https://lkml.kernel.org/r/20210122195231.324857-3-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Reviewed-by: Oscar Salvador Reviewed-by: Muchun Song Reviewed-by: Miaohe Lin Acked-by: Michal Hocko Cc: David Hildenbrand Cc: Matthew Wilcox Cc: Naoya Horiguchi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/hugetlbfs/inode.c | 2 +- include/linux/hugetlb.h | 7 +++++-- include/linux/page-flags.h | 6 ------ mm/hugetlb.c | 45 +++++++++++---------------------------------- mm/memory_hotplug.c | 9 ++++++++- 5 files changed, 25 insertions(+), 44 deletions(-) (limited to 'include') diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 907f6405e805..5a8ed6bd4f87 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -735,7 +735,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, mutex_unlock(&hugetlb_fault_mutex_table[hash]); - set_page_huge_active(page); + SetHPageMigratable(page); /* * unlock_page because locked by add_to_page_cache() * put_page() due to reference from alloc_huge_page() diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 249c65e1d8ca..77f2a032fe32 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -480,9 +480,13 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, * HPG_restore_reserve - Set when a hugetlb page consumes a reservation at * allocation time. Cleared when page is fully instantiated. Free * routine checks flag to restore a reservation on error paths. + * HPG_migratable - Set after a newly allocated page is added to the page + * cache and/or page tables. Indicates the page is a candidate for + * migration. */ enum hugetlb_page_flags { HPG_restore_reserve = 0, + HPG_migratable, __NR_HPAGEFLAGS, }; @@ -525,6 +529,7 @@ static inline void ClearHPage##uname(struct page *page) \ * Create functions associated with hugetlb page flags */ HPAGEFLAG(RestoreReserve, restore_reserve) +HPAGEFLAG(Migratable, migratable) #ifdef CONFIG_HUGETLB_PAGE @@ -838,8 +843,6 @@ static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, } #endif -void set_page_huge_active(struct page *page); - #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index ec5d0290e0ee..db914477057b 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -592,15 +592,9 @@ static inline void ClearPageCompound(struct page *page) #ifdef CONFIG_HUGETLB_PAGE int PageHuge(struct page *page); int PageHeadHuge(struct page *page); -bool page_huge_active(struct page *page); #else TESTPAGEFLAG_FALSE(Huge) TESTPAGEFLAG_FALSE(HeadHuge) - -static inline bool page_huge_active(struct page *page) -{ - return 0; -} #endif diff --git a/mm/hugetlb.c b/mm/hugetlb.c index f5e85dabb7a3..727c09713627 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1364,30 +1364,6 @@ struct hstate *size_to_hstate(unsigned long size) return NULL; } -/* - * Test to determine whether the hugepage is "active/in-use" (i.e. being linked - * to hstate->hugepage_activelist.) - * - * This function can be called for tail pages, but never returns true for them. - */ -bool page_huge_active(struct page *page) -{ - return PageHeadHuge(page) && PagePrivate(&page[1]); -} - -/* never called for tail page */ -void set_page_huge_active(struct page *page) -{ - VM_BUG_ON_PAGE(!PageHeadHuge(page), page); - SetPagePrivate(&page[1]); -} - -static void clear_page_huge_active(struct page *page) -{ - VM_BUG_ON_PAGE(!PageHeadHuge(page), page); - ClearPagePrivate(&page[1]); -} - /* * Internal hugetlb specific page flag. Do not use outside of the hugetlb * code @@ -1449,7 +1425,7 @@ static void __free_huge_page(struct page *page) } spin_lock(&hugetlb_lock); - clear_page_huge_active(page); + ClearHPageMigratable(page); hugetlb_cgroup_uncharge_page(hstate_index(h), pages_per_huge_page(h), page); hugetlb_cgroup_uncharge_page_rsvd(hstate_index(h), @@ -4218,7 +4194,7 @@ retry_avoidcopy: make_huge_pte(vma, new_page, 1)); page_remove_rmap(old_page, true); hugepage_add_new_anon_rmap(new_page, vma, haddr); - set_page_huge_active(new_page); + SetHPageMigratable(new_page); /* Make the old page be freed below */ new_page = old_page; } @@ -4455,12 +4431,12 @@ retry: spin_unlock(ptl); /* - * Only make newly allocated pages active. Existing pages found - * in the pagecache could be !page_huge_active() if they have been - * isolated for migration. + * Only set HPageMigratable in newly allocated pages. Existing pages + * found in the pagecache may not have HPageMigratableset if they have + * been isolated for migration. */ if (new_page) - set_page_huge_active(page); + SetHPageMigratable(page); unlock_page(page); out: @@ -4771,7 +4747,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, update_mmu_cache(dst_vma, dst_addr, dst_pte); spin_unlock(ptl); - set_page_huge_active(page); + SetHPageMigratable(page); if (vm_shared) unlock_page(page); ret = 0; @@ -5610,12 +5586,13 @@ bool isolate_huge_page(struct page *page, struct list_head *list) bool ret = true; spin_lock(&hugetlb_lock); - if (!PageHeadHuge(page) || !page_huge_active(page) || + if (!PageHeadHuge(page) || + !HPageMigratable(page) || !get_page_unless_zero(page)) { ret = false; goto unlock; } - clear_page_huge_active(page); + ClearHPageMigratable(page); list_move_tail(&page->lru, list); unlock: spin_unlock(&hugetlb_lock); @@ -5625,7 +5602,7 @@ unlock: void putback_active_hugepage(struct page *page) { spin_lock(&hugetlb_lock); - set_page_huge_active(page); + SetHPageMigratable(page); list_move_tail(&page->lru, &(page_hstate(page))->hugepage_activelist); spin_unlock(&hugetlb_lock); put_page(page); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index ddcb1cd24c60..abe43c1ae920 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1260,7 +1260,14 @@ static int scan_movable_pages(unsigned long start, unsigned long end, if (!PageHuge(page)) continue; head = compound_head(page); - if (page_huge_active(head)) + /* + * This test is racy as we hold no reference or lock. The + * hugetlb page could have been free'ed and head is no longer + * a hugetlb page before the following check. In such unlikely + * cases false positives and negatives are possible. Calling + * code must deal with these scenarios. + */ + if (HPageMigratable(head)) goto found; skip = compound_nr(head) - (page - head); pfn += skip - 1; -- cgit v1.2.3 From 9157c31186c358c5750dea50ac5705d61d7fc917 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Wed, 24 Feb 2021 12:09:00 -0800 Subject: hugetlb: convert PageHugeTemporary() to HPageTemporary flag Use new hugetlb specific HPageTemporary flag to replace the PageHugeTemporary() interfaces. PageHugeTemporary does contain a PageHuge() check. However, this interface is only used within hugetlb code where we know we are dealing with a hugetlb page. Therefore, the check can be eliminated. Link: https://lkml.kernel.org/r/20210122195231.324857-5-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Reviewed-by: Oscar Salvador Reviewed-by: Muchun Song Acked-by: Michal Hocko Cc: David Hildenbrand Cc: Matthew Wilcox Cc: Miaohe Lin Cc: Naoya Horiguchi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 6 ++++++ mm/hugetlb.c | 36 +++++++----------------------------- 2 files changed, 13 insertions(+), 29 deletions(-) (limited to 'include') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 77f2a032fe32..e97498a21010 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -483,10 +483,15 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, * HPG_migratable - Set after a newly allocated page is added to the page * cache and/or page tables. Indicates the page is a candidate for * migration. + * HPG_temporary - - Set on a page that is temporarily allocated from the buddy + * allocator. Typically used for migration target pages when no pages + * are available in the pool. The hugetlb free page path will + * immediately free pages with this flag set to the buddy allocator. */ enum hugetlb_page_flags { HPG_restore_reserve = 0, HPG_migratable, + HPG_temporary, __NR_HPAGEFLAGS, }; @@ -530,6 +535,7 @@ static inline void ClearHPage##uname(struct page *page) \ */ HPAGEFLAG(RestoreReserve, restore_reserve) HPAGEFLAG(Migratable, migratable) +HPAGEFLAG(Temporary, temporary) #ifdef CONFIG_HUGETLB_PAGE diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 727c09713627..4d7d4535a313 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1364,28 +1364,6 @@ struct hstate *size_to_hstate(unsigned long size) return NULL; } -/* - * Internal hugetlb specific page flag. Do not use outside of the hugetlb - * code - */ -static inline bool PageHugeTemporary(struct page *page) -{ - if (!PageHuge(page)) - return false; - - return (unsigned long)page[2].mapping == -1U; -} - -static inline void SetPageHugeTemporary(struct page *page) -{ - page[2].mapping = (void *)-1U; -} - -static inline void ClearPageHugeTemporary(struct page *page) -{ - page[2].mapping = NULL; -} - static void __free_huge_page(struct page *page) { /* @@ -1433,9 +1411,9 @@ static void __free_huge_page(struct page *page) if (restore_reserve) h->resv_huge_pages++; - if (PageHugeTemporary(page)) { + if (HPageTemporary(page)) { list_del(&page->lru); - ClearPageHugeTemporary(page); + ClearHPageTemporary(page); update_and_free_page(h, page); } else if (h->surplus_huge_pages_node[nid]) { /* remove the page from active list */ @@ -1869,7 +1847,7 @@ static struct page *alloc_surplus_huge_page(struct hstate *h, gfp_t gfp_mask, * codeflow */ if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages) { - SetPageHugeTemporary(page); + SetHPageTemporary(page); spin_unlock(&hugetlb_lock); put_page(page); return NULL; @@ -1900,7 +1878,7 @@ static struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask, * We do not account these pages as surplus because they are only * temporary and will be released properly on the last reference */ - SetPageHugeTemporary(page); + SetHPageTemporary(page); return page; } @@ -5625,12 +5603,12 @@ void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason) * here as well otherwise the global surplus count will not match * the per-node's. */ - if (PageHugeTemporary(newpage)) { + if (HPageTemporary(newpage)) { int old_nid = page_to_nid(oldpage); int new_nid = page_to_nid(newpage); - SetPageHugeTemporary(oldpage); - ClearPageHugeTemporary(newpage); + SetHPageTemporary(oldpage); + ClearHPageTemporary(newpage); spin_lock(&hugetlb_lock); if (h->surplus_huge_pages_node[old_nid]) { -- cgit v1.2.3 From 6c037149014027d50175da5be4ae4531374dcbe0 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Wed, 24 Feb 2021 12:09:04 -0800 Subject: hugetlb: convert PageHugeFreed to HPageFreed flag Use new hugetlb specific HPageFreed flag to replace the PageHugeFreed interfaces. Link: https://lkml.kernel.org/r/20210122195231.324857-6-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Reviewed-by: Oscar Salvador Reviewed-by: Muchun Song Acked-by: Michal Hocko Cc: David Hildenbrand Cc: Matthew Wilcox Cc: Miaohe Lin Cc: Michal Hocko Cc: Naoya Horiguchi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 3 +++ mm/hugetlb.c | 23 ++++------------------- 2 files changed, 7 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index e97498a21010..eb2682fd97b6 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -487,11 +487,13 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, * allocator. Typically used for migration target pages when no pages * are available in the pool. The hugetlb free page path will * immediately free pages with this flag set to the buddy allocator. + * HPG_freed - Set when page is on the free lists. */ enum hugetlb_page_flags { HPG_restore_reserve = 0, HPG_migratable, HPG_temporary, + HPG_freed, __NR_HPAGEFLAGS, }; @@ -536,6 +538,7 @@ static inline void ClearHPage##uname(struct page *page) \ HPAGEFLAG(RestoreReserve, restore_reserve) HPAGEFLAG(Migratable, migratable) HPAGEFLAG(Temporary, temporary) +HPAGEFLAG(Freed, freed) #ifdef CONFIG_HUGETLB_PAGE diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 4d7d4535a313..5377e1dad044 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -79,21 +79,6 @@ DEFINE_SPINLOCK(hugetlb_lock); static int num_fault_mutexes; struct mutex *hugetlb_fault_mutex_table ____cacheline_aligned_in_smp; -static inline bool PageHugeFreed(struct page *head) -{ - return page_private(head + 4) == -1UL; -} - -static inline void SetPageHugeFreed(struct page *head) -{ - set_page_private(head + 4, -1UL); -} - -static inline void ClearPageHugeFreed(struct page *head) -{ - set_page_private(head + 4, 0); -} - /* Forward declaration */ static int hugetlb_acct_memory(struct hstate *h, long delta); @@ -1053,7 +1038,7 @@ static void enqueue_huge_page(struct hstate *h, struct page *page) list_move(&page->lru, &h->hugepage_freelists[nid]); h->free_huge_pages++; h->free_huge_pages_node[nid]++; - SetPageHugeFreed(page); + SetHPageFreed(page); } static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid) @@ -1070,7 +1055,7 @@ static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid) list_move(&page->lru, &h->hugepage_activelist); set_page_refcounted(page); - ClearPageHugeFreed(page); + ClearHPageFreed(page); h->free_huge_pages--; h->free_huge_pages_node[nid]--; return page; @@ -1485,7 +1470,7 @@ static void prep_new_huge_page(struct hstate *h, struct page *page, int nid) spin_lock(&hugetlb_lock); h->nr_huge_pages++; h->nr_huge_pages_node[nid]++; - ClearPageHugeFreed(page); + ClearHPageFreed(page); spin_unlock(&hugetlb_lock); } @@ -1756,7 +1741,7 @@ retry: * We should make sure that the page is already on the free list * when it is dissolved. */ - if (unlikely(!PageHugeFreed(head))) { + if (unlikely(!HPageFreed(head))) { spin_unlock(&hugetlb_lock); cond_resched(); -- cgit v1.2.3 From d95c0337774b1dc74d271e7475a96fe8838332ea Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Wed, 24 Feb 2021 12:09:08 -0800 Subject: include/linux/hugetlb.h: add synchronization information for new hugetlb specific flags Add comments, no functional change. Link: https://lkml.kernel.org/r/62a80585-2a73-10cc-4a2d-5721540d4ad2@oracle.com Signed-off-by: Mike Kravetz Acked-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index eb2682fd97b6..3a541c6cf5c3 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -480,14 +480,24 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, * HPG_restore_reserve - Set when a hugetlb page consumes a reservation at * allocation time. Cleared when page is fully instantiated. Free * routine checks flag to restore a reservation on error paths. + * Synchronization: Examined or modified by code that knows it has + * the only reference to page. i.e. After allocation but before use + * or when the page is being freed. * HPG_migratable - Set after a newly allocated page is added to the page * cache and/or page tables. Indicates the page is a candidate for * migration. + * Synchronization: Initially set after new page allocation with no + * locking. When examined and modified during migration processing + * (isolate, migrate, putback) the hugetlb_lock is held. * HPG_temporary - - Set on a page that is temporarily allocated from the buddy * allocator. Typically used for migration target pages when no pages * are available in the pool. The hugetlb free page path will * immediately free pages with this flag set to the buddy allocator. + * Synchronization: Can be set after huge page allocation from buddy when + * code knows it has only reference. All other examinations and + * modifications require hugetlb_lock. * HPG_freed - Set when page is on the free lists. + * Synchronization: hugetlb_lock held for examination and modification. */ enum hugetlb_page_flags { HPG_restore_reserve = 0, -- cgit v1.2.3 From bda420b985054a3badafef23807c4b4fa38a3dff Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Wed, 24 Feb 2021 12:09:43 -0800 Subject: numa balancing: migrate on fault among multiple bound nodes Now, NUMA balancing can only optimize the page placement among the NUMA nodes if the default memory policy is used. Because the memory policy specified explicitly should take precedence. But this seems too strict in some situations. For example, on a system with 4 NUMA nodes, if the memory of an application is bound to the node 0 and 1, NUMA balancing can potentially migrate the pages between the node 0 and 1 to reduce cross-node accessing without breaking the explicit memory binding policy. So in this patch, we add MPOL_F_NUMA_BALANCING mode flag to set_mempolicy() when mode is MPOL_BIND. With the flag specified, NUMA balancing will be enabled within the thread to optimize the page placement within the constrains of the specified memory binding policy. With the newly added flag, the NUMA balancing control mechanism becomes, - sysctl knob numa_balancing can enable/disable the NUMA balancing globally. - even if sysctl numa_balancing is enabled, the NUMA balancing will be disabled for the memory areas or applications with the explicit memory policy by default. - MPOL_F_NUMA_BALANCING can be used to enable the NUMA balancing for the applications when specifying the explicit memory policy (MPOL_BIND). Various page placement optimization based on the NUMA balancing can be done with these flags. As the first step, in this patch, if the memory of the application is bound to multiple nodes (MPOL_BIND), and in the hint page fault handler the accessing node are in the policy nodemask, the page will be tried to be migrated to the accessing node to reduce the cross-node accessing. If the newly added MPOL_F_NUMA_BALANCING flag is specified by an application on an old kernel version without its support, set_mempolicy() will return -1 and errno will be set to EINVAL. The application can use this behavior to run on both old and new kernel versions. And if the MPOL_F_NUMA_BALANCING flag is specified for the mode other than MPOL_BIND, set_mempolicy() will return -1 and errno will be set to EINVAL as before. Because we don't support optimization based on the NUMA balancing for these modes. In the previous version of the patch, we tried to reuse MPOL_MF_LAZY for mbind(). But that flag is tied to MPOL_MF_MOVE.*, so it seems not a good API/ABI for the purpose of the patch. And because it's not clear whether it's necessary to enable NUMA balancing for a specific memory area inside an application, so we only add the flag at the thread level (set_mempolicy()) instead of the memory area level (mbind()). We can do that when it become necessary. To test the patch, we run a test case as follows on a 4-node machine with 192 GB memory (48 GB per node). 1. Change pmbench memory accessing benchmark to call set_mempolicy() to bind its memory to node 1 and 3 and enable NUMA balancing. Some related code snippets are as follows, #include #include struct bitmask *bmp; int ret; bmp = numa_parse_nodestring("1,3"); ret = set_mempolicy(MPOL_BIND | MPOL_F_NUMA_BALANCING, bmp->maskp, bmp->size + 1); /* If MPOL_F_NUMA_BALANCING isn't supported, fall back to MPOL_BIND */ if (ret < 0 && errno == EINVAL) ret = set_mempolicy(MPOL_BIND, bmp->maskp, bmp->size + 1); if (ret < 0) { perror("Failed to call set_mempolicy"); exit(-1); } 2. Run a memory eater on node 3 to use 40 GB memory before running pmbench. 3. Run pmbench with 64 processes, the working-set size of each process is 640 MB, so the total working-set size is 64 * 640 MB = 40 GB. The CPU and the memory (as in step 1.) of all pmbench processes is bound to node 1 and 3. So, after CPU usage is balanced, some pmbench processes run on the CPUs of the node 3 will access the memory of the node 1. 4. After the pmbench processes run for 100 seconds, kill the memory eater. Now it's possible for some pmbench processes to migrate their pages from node 1 to node 3 to reduce cross-node accessing. Test results show that, with the patch, the pages can be migrated from node 1 to node 3 after killing the memory eater, and the pmbench score can increase about 17.5%. Link: https://lkml.kernel.org/r/20210120061235.148637-2-ying.huang@intel.com Signed-off-by: "Huang, Ying" Acked-by: Mel Gorman Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Rik van Riel Cc: Johannes Weiner Cc: "Matthew Wilcox (Oracle)" Cc: Dave Hansen Cc: Andi Kleen Cc: Michal Hocko Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/uapi/linux/mempolicy.h | 4 +++- mm/mempolicy.c | 16 ++++++++++++++++ 2 files changed, 19 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/mempolicy.h b/include/uapi/linux/mempolicy.h index 3354774af61e..8948467b3992 100644 --- a/include/uapi/linux/mempolicy.h +++ b/include/uapi/linux/mempolicy.h @@ -28,12 +28,14 @@ enum { /* Flags for set_mempolicy */ #define MPOL_F_STATIC_NODES (1 << 15) #define MPOL_F_RELATIVE_NODES (1 << 14) +#define MPOL_F_NUMA_BALANCING (1 << 13) /* Optimize with NUMA balancing if possible */ /* * MPOL_MODE_FLAGS is the union of all possible optional mode flags passed to * either set_mempolicy() or mbind(). */ -#define MPOL_MODE_FLAGS (MPOL_F_STATIC_NODES | MPOL_F_RELATIVE_NODES) +#define MPOL_MODE_FLAGS \ + (MPOL_F_STATIC_NODES | MPOL_F_RELATIVE_NODES | MPOL_F_NUMA_BALANCING) /* Flags for get_mempolicy */ #define MPOL_F_NODE (1<<0) /* return next IL mode instead of node mask */ diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 2c3a86502053..6961238c7ef5 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -875,6 +875,16 @@ static long do_set_mempolicy(unsigned short mode, unsigned short flags, goto out; } + if (flags & MPOL_F_NUMA_BALANCING) { + if (new && new->mode == MPOL_BIND) { + new->flags |= (MPOL_F_MOF | MPOL_F_MORON); + } else { + ret = -EINVAL; + mpol_put(new); + goto out; + } + } + ret = mpol_set_nodemask(new, nodes, scratch); if (ret) { mpol_put(new); @@ -2486,6 +2496,12 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long break; case MPOL_BIND: + /* Optimize placement among multiple nodes via NUMA balancing */ + if (pol->flags & MPOL_F_MORON) { + if (node_isset(thisnid, pol->v.nodes)) + break; + goto out; + } /* * allows binding to multiple nodes. -- cgit v1.2.3 From 33b8f84a4ee78491a8f4f9e4c5520c9da4a10983 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Wed, 24 Feb 2021 12:09:54 -0800 Subject: mm/hugetlb: change hugetlb_reserve_pages() to type bool While reviewing a bug in hugetlb_reserve_pages, it was noticed that all callers ignore the return value. Any failure is considered an ENOMEM error by the callers. Change the function to be of type bool. The function will return true if the reservation was successful, false otherwise. Callers currently assume a zero return code indicates success. Change the callers to look for true to indicate success. No functional change, only code cleanup. Link: https://lkml.kernel.org/r/20201221192542.15732-1-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Reviewed-by: Matthew Wilcox (Oracle) Cc: David Hildenbrand Cc: Dan Carpenter Cc: Michal Hocko Cc: Davidlohr Bueso Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/hugetlbfs/inode.c | 4 ++-- include/linux/hugetlb.h | 2 +- mm/hugetlb.c | 37 ++++++++++++++----------------------- 3 files changed, 17 insertions(+), 26 deletions(-) (limited to 'include') diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 5a8ed6bd4f87..3eca85a4d940 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -171,7 +171,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) file_accessed(file); ret = -ENOMEM; - if (hugetlb_reserve_pages(inode, + if (!hugetlb_reserve_pages(inode, vma->vm_pgoff >> huge_page_order(h), len >> huge_page_shift(h), vma, vma->vm_flags)) @@ -1493,7 +1493,7 @@ struct file *hugetlb_file_setup(const char *name, size_t size, inode->i_size = size; clear_nlink(inode); - if (hugetlb_reserve_pages(inode, 0, + if (!hugetlb_reserve_pages(inode, 0, size >> huge_page_shift(hstate_inode(inode)), NULL, acctflag)) file = ERR_PTR(-ENOMEM); diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 3a541c6cf5c3..cccd1aab69dd 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -139,7 +139,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, pte_t *dst_pte, unsigned long dst_addr, unsigned long src_addr, struct page **pagep); -int hugetlb_reserve_pages(struct inode *inode, long from, long to, +bool hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, vm_flags_t vm_flags); long hugetlb_unreserve_pages(struct inode *inode, long start, long end, diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 8e5f494291c6..8fb42c6dd74b 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5016,12 +5016,13 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, return pages << h->order; } -int hugetlb_reserve_pages(struct inode *inode, +/* Return true if reservation was successful, false otherwise. */ +bool hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, vm_flags_t vm_flags) { - long ret, chg, add = -1; + long chg, add = -1; struct hstate *h = hstate_inode(inode); struct hugepage_subpool *spool = subpool_inode(inode); struct resv_map *resv_map; @@ -5031,7 +5032,7 @@ int hugetlb_reserve_pages(struct inode *inode, /* This should never happen */ if (from > to) { VM_WARN(1, "%s called with a negative range\n", __func__); - return -EINVAL; + return false; } /* @@ -5040,7 +5041,7 @@ int hugetlb_reserve_pages(struct inode *inode, * without using reserves */ if (vm_flags & VM_NORESERVE) - return 0; + return true; /* * Shared mappings base their reservation on the number of pages that @@ -5062,7 +5063,7 @@ int hugetlb_reserve_pages(struct inode *inode, /* Private mapping. */ resv_map = resv_map_alloc(); if (!resv_map) - return -ENOMEM; + return false; chg = to - from; @@ -5070,18 +5071,12 @@ int hugetlb_reserve_pages(struct inode *inode, set_vma_resv_flags(vma, HPAGE_RESV_OWNER); } - if (chg < 0) { - ret = chg; + if (chg < 0) goto out_err; - } - ret = hugetlb_cgroup_charge_cgroup_rsvd( - hstate_index(h), chg * pages_per_huge_page(h), &h_cg); - - if (ret < 0) { - ret = -ENOMEM; + if (hugetlb_cgroup_charge_cgroup_rsvd(hstate_index(h), + chg * pages_per_huge_page(h), &h_cg) < 0) goto out_err; - } if (vma && !(vma->vm_flags & VM_MAYSHARE) && h_cg) { /* For private mappings, the hugetlb_cgroup uncharge info hangs @@ -5096,19 +5091,15 @@ int hugetlb_reserve_pages(struct inode *inode, * reservations already in place (gbl_reserve). */ gbl_reserve = hugepage_subpool_get_pages(spool, chg); - if (gbl_reserve < 0) { - ret = -ENOSPC; + if (gbl_reserve < 0) goto out_uncharge_cgroup; - } /* * Check enough hugepages are available for the reservation. * Hand the pages back to the subpool if there are not */ - ret = hugetlb_acct_memory(h, gbl_reserve); - if (ret < 0) { + if (hugetlb_acct_memory(h, gbl_reserve) < 0) goto out_put_pages; - } /* * Account for the reservations made. Shared mappings record regions @@ -5126,7 +5117,6 @@ int hugetlb_reserve_pages(struct inode *inode, if (unlikely(add < 0)) { hugetlb_acct_memory(h, -gbl_reserve); - ret = add; goto out_put_pages; } else if (unlikely(chg > add)) { /* @@ -5147,7 +5137,8 @@ int hugetlb_reserve_pages(struct inode *inode, hugetlb_acct_memory(h, -rsv_adjust); } } - return 0; + return true; + out_put_pages: /* put back original number of pages, chg */ (void)hugepage_subpool_put_pages(spool, chg); @@ -5163,7 +5154,7 @@ out_err: region_abort(resv_map, from, to, regions_needed); if (vma && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) kref_put(&resv_map->refs, resv_map_release); - return ret; + return false; } long hugetlb_unreserve_pages(struct inode *inode, long start, long end, -- cgit v1.2.3 From a553e3cd2053501b658feec2be9a3b662eb1b22b Mon Sep 17 00:00:00 2001 From: Chengyang Fan Date: Wed, 24 Feb 2021 12:10:28 -0800 Subject: mm/migrate: remove unneeded semicolons Remove superfluous semicolons after function definitions. Link: https://lkml.kernel.org/r/20210115110131.2359683-1-cy.fan@huawei.com Signed-off-by: Chengyang Fan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 4594838a0f7c..3a389633b68f 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -89,7 +89,7 @@ extern int PageMovable(struct page *page); extern void __SetPageMovable(struct page *page, struct address_space *mapping); extern void __ClearPageMovable(struct page *page); #else -static inline int PageMovable(struct page *page) { return 0; }; +static inline int PageMovable(struct page *page) { return 0; } static inline void __SetPageMovable(struct page *page, struct address_space *mapping) { -- cgit v1.2.3 From 4e096a18867a5a989b510f6999d9c6b6622e8f7b Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Tue, 23 Feb 2021 08:01:26 +0100 Subject: net: introduce CAN specific pointer in the struct net_device Since 20dd3850bcf8 ("can: Speed up CAN frame receiption by using ml_priv") the CAN framework uses per device specific data in the AF_CAN protocol. For this purpose the struct net_device->ml_priv is used. Later the ml_priv usage in CAN was extended for other users, one of them being CAN_J1939. Later in the kernel ml_priv was converted to an union, used by other drivers. E.g. the tun driver started storing it's stats pointer. Since tun devices can claim to be a CAN device, CAN specific protocols will wrongly interpret this pointer, which will cause system crashes. Mostly this issue is visible in the CAN_J1939 stack. To fix this issue, we request a dedicated CAN pointer within the net_device struct. Reported-by: syzbot+5138c4dd15a0401bec7b@syzkaller.appspotmail.com Fixes: 20dd3850bcf8 ("can: Speed up CAN frame receiption by using ml_priv") Fixes: ffd956eef69b ("can: introduce CAN midlayer private and allocate it automatically") Fixes: 9d71dd0c7009 ("can: add support of SAE J1939 protocol") Fixes: 497a5757ce4e ("tun: switch to net core provided statistics counters") Signed-off-by: Oleksij Rempel Link: https://lore.kernel.org/r/20210223070127.4538-1-o.rempel@pengutronix.de Signed-off-by: Jakub Kicinski --- drivers/net/can/dev/dev.c | 4 +++- drivers/net/can/slcan.c | 4 +++- drivers/net/can/vcan.c | 2 +- drivers/net/can/vxcan.c | 6 +++++- include/linux/can/can-ml.h | 12 ++++++++++++ include/linux/netdevice.h | 34 +++++++++++++++++++++++++++++++++- net/can/af_can.c | 34 ++-------------------------------- net/can/j1939/main.c | 22 ++++++++-------------- net/can/j1939/socket.c | 13 ++++--------- net/can/proc.c | 19 +++++++++++++------ 10 files changed, 84 insertions(+), 66 deletions(-) (limited to 'include') diff --git a/drivers/net/can/dev/dev.c b/drivers/net/can/dev/dev.c index d9281ae853f8..311d8564d611 100644 --- a/drivers/net/can/dev/dev.c +++ b/drivers/net/can/dev/dev.c @@ -239,6 +239,7 @@ void can_setup(struct net_device *dev) struct net_device *alloc_candev_mqs(int sizeof_priv, unsigned int echo_skb_max, unsigned int txqs, unsigned int rxqs) { + struct can_ml_priv *can_ml; struct net_device *dev; struct can_priv *priv; int size; @@ -270,7 +271,8 @@ struct net_device *alloc_candev_mqs(int sizeof_priv, unsigned int echo_skb_max, priv = netdev_priv(dev); priv->dev = dev; - dev->ml_priv = (void *)priv + ALIGN(sizeof_priv, NETDEV_ALIGN); + can_ml = (void *)priv + ALIGN(sizeof_priv, NETDEV_ALIGN); + can_set_ml_priv(dev, can_ml); if (echo_skb_max) { priv->echo_skb_max = echo_skb_max; diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c index a1bd1be09548..30c8d53c9745 100644 --- a/drivers/net/can/slcan.c +++ b/drivers/net/can/slcan.c @@ -516,6 +516,7 @@ static struct slcan *slc_alloc(void) int i; char name[IFNAMSIZ]; struct net_device *dev = NULL; + struct can_ml_priv *can_ml; struct slcan *sl; int size; @@ -538,7 +539,8 @@ static struct slcan *slc_alloc(void) dev->base_addr = i; sl = netdev_priv(dev); - dev->ml_priv = (void *)sl + ALIGN(sizeof(*sl), NETDEV_ALIGN); + can_ml = (void *)sl + ALIGN(sizeof(*sl), NETDEV_ALIGN); + can_set_ml_priv(dev, can_ml); /* Initialize channel control data */ sl->magic = SLCAN_MAGIC; diff --git a/drivers/net/can/vcan.c b/drivers/net/can/vcan.c index 39ca14b0585d..067705e2850b 100644 --- a/drivers/net/can/vcan.c +++ b/drivers/net/can/vcan.c @@ -153,7 +153,7 @@ static void vcan_setup(struct net_device *dev) dev->addr_len = 0; dev->tx_queue_len = 0; dev->flags = IFF_NOARP; - dev->ml_priv = netdev_priv(dev); + can_set_ml_priv(dev, netdev_priv(dev)); /* set flags according to driver capabilities */ if (echo) diff --git a/drivers/net/can/vxcan.c b/drivers/net/can/vxcan.c index f9a524c5f6d6..8861a7d875e7 100644 --- a/drivers/net/can/vxcan.c +++ b/drivers/net/can/vxcan.c @@ -141,6 +141,8 @@ static const struct net_device_ops vxcan_netdev_ops = { static void vxcan_setup(struct net_device *dev) { + struct can_ml_priv *can_ml; + dev->type = ARPHRD_CAN; dev->mtu = CANFD_MTU; dev->hard_header_len = 0; @@ -149,7 +151,9 @@ static void vxcan_setup(struct net_device *dev) dev->flags = (IFF_NOARP|IFF_ECHO); dev->netdev_ops = &vxcan_netdev_ops; dev->needs_free_netdev = true; - dev->ml_priv = netdev_priv(dev) + ALIGN(sizeof(struct vxcan_priv), NETDEV_ALIGN); + + can_ml = netdev_priv(dev) + ALIGN(sizeof(struct vxcan_priv), NETDEV_ALIGN); + can_set_ml_priv(dev, can_ml); } /* forward declaration for rtnl_create_link() */ diff --git a/include/linux/can/can-ml.h b/include/linux/can/can-ml.h index 2f5d731ae251..8afa92d15a66 100644 --- a/include/linux/can/can-ml.h +++ b/include/linux/can/can-ml.h @@ -44,6 +44,7 @@ #include #include +#include #define CAN_SFF_RCV_ARRAY_SZ (1 << CAN_SFF_ID_BITS) #define CAN_EFF_RCV_HASH_BITS 10 @@ -65,4 +66,15 @@ struct can_ml_priv { #endif }; +static inline struct can_ml_priv *can_get_ml_priv(struct net_device *dev) +{ + return netdev_get_ml_priv(dev, ML_PRIV_CAN); +} + +static inline void can_set_ml_priv(struct net_device *dev, + struct can_ml_priv *ml_priv) +{ + netdev_set_ml_priv(dev, ml_priv, ML_PRIV_CAN); +} + #endif /* CAN_ML_H */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ddf4cfc12615..f06fbee8638e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1584,6 +1584,12 @@ enum netdev_priv_flags { #define IFF_L3MDEV_RX_HANDLER IFF_L3MDEV_RX_HANDLER #define IFF_LIVE_RENAME_OK IFF_LIVE_RENAME_OK +/* Specifies the type of the struct net_device::ml_priv pointer */ +enum netdev_ml_priv_type { + ML_PRIV_NONE, + ML_PRIV_CAN, +}; + /** * struct net_device - The DEVICE structure. * @@ -1779,6 +1785,7 @@ enum netdev_priv_flags { * @nd_net: Network namespace this network device is inside * * @ml_priv: Mid-layer private + * @ml_priv_type: Mid-layer private type * @lstats: Loopback statistics * @tstats: Tunnel statistics * @dstats: Dummy statistics @@ -2094,8 +2101,10 @@ struct net_device { possible_net_t nd_net; /* mid-layer private */ + void *ml_priv; + enum netdev_ml_priv_type ml_priv_type; + union { - void *ml_priv; struct pcpu_lstats __percpu *lstats; struct pcpu_sw_netstats __percpu *tstats; struct pcpu_dstats __percpu *dstats; @@ -2286,6 +2295,29 @@ static inline void netdev_reset_rx_headroom(struct net_device *dev) netdev_set_rx_headroom(dev, -1); } +static inline void *netdev_get_ml_priv(struct net_device *dev, + enum netdev_ml_priv_type type) +{ + if (dev->ml_priv_type != type) + return NULL; + + return dev->ml_priv; +} + +static inline void netdev_set_ml_priv(struct net_device *dev, + void *ml_priv, + enum netdev_ml_priv_type type) +{ + WARN(dev->ml_priv_type && dev->ml_priv_type != type, + "Overwriting already set ml_priv_type (%u) with different ml_priv_type (%u)!\n", + dev->ml_priv_type, type); + WARN(!dev->ml_priv_type && dev->ml_priv, + "Overwriting already set ml_priv and ml_priv_type is ML_PRIV_NONE!\n"); + + dev->ml_priv = ml_priv; + dev->ml_priv_type = type; +} + /* * Net namespace inlines */ diff --git a/net/can/af_can.c b/net/can/af_can.c index 837bb8af0ec3..cce2af10eb3e 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -304,8 +304,8 @@ static struct can_dev_rcv_lists *can_dev_rcv_lists_find(struct net *net, struct net_device *dev) { if (dev) { - struct can_ml_priv *ml_priv = dev->ml_priv; - return &ml_priv->dev_rcv_lists; + struct can_ml_priv *can_ml = can_get_ml_priv(dev); + return &can_ml->dev_rcv_lists; } else { return net->can.rx_alldev_list; } @@ -790,25 +790,6 @@ void can_proto_unregister(const struct can_proto *cp) } EXPORT_SYMBOL(can_proto_unregister); -/* af_can notifier to create/remove CAN netdevice specific structs */ -static int can_notifier(struct notifier_block *nb, unsigned long msg, - void *ptr) -{ - struct net_device *dev = netdev_notifier_info_to_dev(ptr); - - if (dev->type != ARPHRD_CAN) - return NOTIFY_DONE; - - switch (msg) { - case NETDEV_REGISTER: - WARN(!dev->ml_priv, - "No CAN mid layer private allocated, please fix your driver and use alloc_candev()!\n"); - break; - } - - return NOTIFY_DONE; -} - static int can_pernet_init(struct net *net) { spin_lock_init(&net->can.rcvlists_lock); @@ -876,11 +857,6 @@ static const struct net_proto_family can_family_ops = { .owner = THIS_MODULE, }; -/* notifier block for netdevice event */ -static struct notifier_block can_netdev_notifier __read_mostly = { - .notifier_call = can_notifier, -}; - static struct pernet_operations can_pernet_ops __read_mostly = { .init = can_pernet_init, .exit = can_pernet_exit, @@ -911,17 +887,12 @@ static __init int can_init(void) err = sock_register(&can_family_ops); if (err) goto out_sock; - err = register_netdevice_notifier(&can_netdev_notifier); - if (err) - goto out_notifier; dev_add_pack(&can_packet); dev_add_pack(&canfd_packet); return 0; -out_notifier: - sock_unregister(PF_CAN); out_sock: unregister_pernet_subsys(&can_pernet_ops); out_pernet: @@ -935,7 +906,6 @@ static __exit void can_exit(void) /* protocol unregister */ dev_remove_pack(&canfd_packet); dev_remove_pack(&can_packet); - unregister_netdevice_notifier(&can_netdev_notifier); sock_unregister(PF_CAN); unregister_pernet_subsys(&can_pernet_ops); diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c index bb914d8b4216..da3a7a7bcff2 100644 --- a/net/can/j1939/main.c +++ b/net/can/j1939/main.c @@ -140,9 +140,9 @@ static struct j1939_priv *j1939_priv_create(struct net_device *ndev) static inline void j1939_priv_set(struct net_device *ndev, struct j1939_priv *priv) { - struct can_ml_priv *can_ml_priv = ndev->ml_priv; + struct can_ml_priv *can_ml = can_get_ml_priv(ndev); - can_ml_priv->j1939_priv = priv; + can_ml->j1939_priv = priv; } static void __j1939_priv_release(struct kref *kref) @@ -211,12 +211,9 @@ static void __j1939_rx_release(struct kref *kref) /* get pointer to priv without increasing ref counter */ static inline struct j1939_priv *j1939_ndev_to_priv(struct net_device *ndev) { - struct can_ml_priv *can_ml_priv = ndev->ml_priv; + struct can_ml_priv *can_ml = can_get_ml_priv(ndev); - if (!can_ml_priv) - return NULL; - - return can_ml_priv->j1939_priv; + return can_ml->j1939_priv; } static struct j1939_priv *j1939_priv_get_by_ndev_locked(struct net_device *ndev) @@ -225,9 +222,6 @@ static struct j1939_priv *j1939_priv_get_by_ndev_locked(struct net_device *ndev) lockdep_assert_held(&j1939_netdev_lock); - if (ndev->type != ARPHRD_CAN) - return NULL; - priv = j1939_ndev_to_priv(ndev); if (priv) j1939_priv_get(priv); @@ -348,15 +342,16 @@ static int j1939_netdev_notify(struct notifier_block *nb, unsigned long msg, void *data) { struct net_device *ndev = netdev_notifier_info_to_dev(data); + struct can_ml_priv *can_ml = can_get_ml_priv(ndev); struct j1939_priv *priv; + if (!can_ml) + goto notify_done; + priv = j1939_priv_get_by_ndev(ndev); if (!priv) goto notify_done; - if (ndev->type != ARPHRD_CAN) - goto notify_put; - switch (msg) { case NETDEV_DOWN: j1939_cancel_active_session(priv, NULL); @@ -365,7 +360,6 @@ static int j1939_netdev_notify(struct notifier_block *nb, break; } -notify_put: j1939_priv_put(priv); notify_done: diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index f23966526a88..56aa66147d5a 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -12,6 +12,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include #include #include #include @@ -453,6 +454,7 @@ static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len) j1939_jsk_del(priv, jsk); j1939_local_ecu_put(priv, jsk->addr.src_name, jsk->addr.sa); } else { + struct can_ml_priv *can_ml; struct net_device *ndev; ndev = dev_get_by_index(net, addr->can_ifindex); @@ -461,15 +463,8 @@ static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len) goto out_release_sock; } - if (ndev->type != ARPHRD_CAN) { - dev_put(ndev); - ret = -ENODEV; - goto out_release_sock; - } - - if (!ndev->ml_priv) { - netdev_warn_once(ndev, - "No CAN mid layer private allocated, please fix your driver and use alloc_candev()!\n"); + can_ml = can_get_ml_priv(ndev); + if (!can_ml) { dev_put(ndev); ret = -ENODEV; goto out_release_sock; diff --git a/net/can/proc.c b/net/can/proc.c index 5ea8695f507e..b15760b5c1cc 100644 --- a/net/can/proc.c +++ b/net/can/proc.c @@ -322,8 +322,11 @@ static int can_rcvlist_proc_show(struct seq_file *m, void *v) /* receive list for registered CAN devices */ for_each_netdev_rcu(net, dev) { - if (dev->type == ARPHRD_CAN && dev->ml_priv) - can_rcvlist_proc_show_one(m, idx, dev, dev->ml_priv); + struct can_ml_priv *can_ml = can_get_ml_priv(dev); + + if (can_ml) + can_rcvlist_proc_show_one(m, idx, dev, + &can_ml->dev_rcv_lists); } rcu_read_unlock(); @@ -375,8 +378,10 @@ static int can_rcvlist_sff_proc_show(struct seq_file *m, void *v) /* sff receive list for registered CAN devices */ for_each_netdev_rcu(net, dev) { - if (dev->type == ARPHRD_CAN && dev->ml_priv) { - dev_rcv_lists = dev->ml_priv; + struct can_ml_priv *can_ml = can_get_ml_priv(dev); + + if (can_ml) { + dev_rcv_lists = &can_ml->dev_rcv_lists; can_rcvlist_proc_show_array(m, dev, dev_rcv_lists->rx_sff, ARRAY_SIZE(dev_rcv_lists->rx_sff)); } @@ -406,8 +411,10 @@ static int can_rcvlist_eff_proc_show(struct seq_file *m, void *v) /* eff receive list for registered CAN devices */ for_each_netdev_rcu(net, dev) { - if (dev->type == ARPHRD_CAN && dev->ml_priv) { - dev_rcv_lists = dev->ml_priv; + struct can_ml_priv *can_ml = can_get_ml_priv(dev); + + if (can_ml) { + dev_rcv_lists = &can_ml->dev_rcv_lists; can_rcvlist_proc_show_array(m, dev, dev_rcv_lists->rx_eff, ARRAY_SIZE(dev_rcv_lists->rx_eff)); } -- cgit v1.2.3 From d814567942ff6ac73869052bdb8ca911364e5eb0 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 25 Feb 2021 12:49:58 -0500 Subject: mm, tracing: Fix kmem_cache_free trace event to not print stale pointers The update to kmem_cache_free trace event added printing of the slab name in the trace event. But it only stores the pointer of the name which will be printed as a string when the event is read some time in the future. This is dangerous because the name could be freed in the mean time and when reading the trace event it would try to dereference the string name by the pointer to the name that has been freed. Instead, use the trace event helper macros __string(), __assign_str(), and __get_str() that are for this very case. Cc: Jacob Wen Fixes: 3544de8ee6e4 ("mm, tracing: record slab name for kmem_cache_free()") Signed-off-by: Steven Rostedt (VMware) --- include/trace/events/kmem.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h index 40845b0d5dad..3a60b6b6db32 100644 --- a/include/trace/events/kmem.h +++ b/include/trace/events/kmem.h @@ -144,17 +144,17 @@ TRACE_EVENT(kmem_cache_free, TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) - __field( const char *, name ) + __string( name, name ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; - __entry->name = name; + __assign_str(name, name); ), TP_printk("call_site=%pS ptr=%p name=%s", - (void *)__entry->call_site, __entry->ptr, __entry->name) + (void *)__entry->call_site, __entry->ptr, __get_str(name)) ); TRACE_EVENT(mm_page_free, -- cgit v1.2.3 From f5b6a74d9c08b19740ca056876bf6584acdba582 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Fri, 29 Jan 2021 17:46:51 -0700 Subject: vmlinux.lds.h: Define SANTIZER_DISCARDS with CONFIG_GCOV_KERNEL=y clang produces .eh_frame sections when CONFIG_GCOV_KERNEL is enabled, even when -fno-asynchronous-unwind-tables is in KBUILD_CFLAGS: $ make CC=clang vmlinux ... ld: warning: orphan section `.eh_frame' from `init/main.o' being placed in section `.eh_frame' ld: warning: orphan section `.eh_frame' from `init/version.o' being placed in section `.eh_frame' ld: warning: orphan section `.eh_frame' from `init/do_mounts.o' being placed in section `.eh_frame' ld: warning: orphan section `.eh_frame' from `init/do_mounts_initrd.o' being placed in section `.eh_frame' ld: warning: orphan section `.eh_frame' from `init/initramfs.o' being placed in section `.eh_frame' ld: warning: orphan section `.eh_frame' from `init/calibrate.o' being placed in section `.eh_frame' ld: warning: orphan section `.eh_frame' from `init/init_task.o' being placed in section `.eh_frame' ... $ rg "GCOV_KERNEL|GCOV_PROFILE_ALL" .config CONFIG_GCOV_KERNEL=y CONFIG_ARCH_HAS_GCOV_PROFILE_ALL=y CONFIG_GCOV_PROFILE_ALL=y This was already handled for a couple of other options in commit d812db78288d ("vmlinux.lds.h: Avoid KASAN and KCSAN's unwanted sections") and there is an open LLVM bug for this issue. Take advantage of that section for this config as well so that there are no more orphan warnings. Link: https://bugs.llvm.org/show_bug.cgi?id=46478 Link: https://github.com/ClangBuiltLinux/linux/issues/1069 Reported-by: kernel test robot Reviewed-by: Fangrui Song Reviewed-by: Nick Desaulniers Signed-off-by: Nathan Chancellor Fixes: d812db78288d ("vmlinux.lds.h: Avoid KASAN and KCSAN's unwanted sections") Cc: stable@vger.kernel.org Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20210130004650.2682422-1-nathan@kernel.org --- include/asm-generic/vmlinux.lds.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index b97c628ad91f..ec89e657ea2f 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -988,12 +988,13 @@ #endif /* - * Clang's -fsanitize=kernel-address and -fsanitize=thread produce - * unwanted sections (.eh_frame and .init_array.*), but - * CONFIG_CONSTRUCTORS wants to keep any .init_array.* sections. + * Clang's -fprofile-arcs, -fsanitize=kernel-address, and + * -fsanitize=thread produce unwanted sections (.eh_frame + * and .init_array.*), but CONFIG_CONSTRUCTORS wants to + * keep any .init_array.* sections. * https://bugs.llvm.org/show_bug.cgi?id=46478 */ -#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KCSAN) +#if defined(CONFIG_GCOV_KERNEL) || defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KCSAN) # ifdef CONFIG_CONSTRUCTORS # define SANITIZER_DISCARDS \ *(.eh_frame) -- cgit v1.2.3 From 44835d20b2a0c9b4c0c3fb96e90f4e2fd4a4e41d Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 25 Feb 2021 17:15:36 -0800 Subject: mm: add FGP_ENTRY The functionality of find_lock_entry() and find_get_entry() can be provided by pagecache_get_page(), which lets us delete find_lock_entry() and make find_get_entry() static. Link: https://lkml.kernel.org/r/20201112212641.27837-5-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Cc: Dave Chinner Cc: Hugh Dickins Cc: Jan Kara Cc: Johannes Weiner Cc: Kirill A. Shutemov Cc: William Kucharski Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 1 + mm/filemap.c | 44 ++++++++------------------------------------ mm/internal.h | 3 --- mm/shmem.c | 3 ++- mm/swap_state.c | 3 ++- 5 files changed, 13 insertions(+), 41 deletions(-) (limited to 'include') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index bd629d676a27..b379b2388202 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -315,6 +315,7 @@ pgoff_t page_cache_prev_miss(struct address_space *mapping, #define FGP_NOWAIT 0x00000020 #define FGP_FOR_MMAP 0x00000040 #define FGP_HEAD 0x00000080 +#define FGP_ENTRY 0x00000100 struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset, int fgp_flags, gfp_t cache_gfp_mask); diff --git a/mm/filemap.c b/mm/filemap.c index 57eae5163bce..84b7813badf1 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1658,7 +1658,7 @@ pgoff_t page_cache_prev_miss(struct address_space *mapping, } EXPORT_SYMBOL(page_cache_prev_miss); -/** +/* * find_get_entry - find and get a page cache entry * @mapping: the address_space to search * @index: The page cache index. @@ -1671,7 +1671,7 @@ EXPORT_SYMBOL(page_cache_prev_miss); * * Return: The head page or shadow entry, %NULL if nothing is found. */ -struct page *find_get_entry(struct address_space *mapping, pgoff_t index) +static struct page *find_get_entry(struct address_space *mapping, pgoff_t index) { XA_STATE(xas, &mapping->i_pages, index); struct page *page; @@ -1707,39 +1707,6 @@ out: return page; } -/** - * find_lock_entry - Locate and lock a page cache entry. - * @mapping: The address_space to search. - * @index: The page cache index. - * - * Looks up the page at @mapping & @index. If there is a page in the - * cache, the head page is returned locked and with an increased refcount. - * - * If the slot holds a shadow entry of a previously evicted page, or a - * swap entry from shmem/tmpfs, it is returned. - * - * Context: May sleep. - * Return: The head page or shadow entry, %NULL if nothing is found. - */ -struct page *find_lock_entry(struct address_space *mapping, pgoff_t index) -{ - struct page *page; - -repeat: - page = find_get_entry(mapping, index); - if (page && !xa_is_value(page)) { - lock_page(page); - /* Has the page been truncated? */ - if (unlikely(page->mapping != mapping)) { - unlock_page(page); - put_page(page); - goto repeat; - } - VM_BUG_ON_PAGE(!thp_contains(page, index), page); - } - return page; -} - /** * pagecache_get_page - Find and get a reference to a page. * @mapping: The address_space to search. @@ -1755,6 +1722,8 @@ repeat: * * %FGP_LOCK - The page is returned locked. * * %FGP_HEAD - If the page is present and a THP, return the head page * rather than the exact page specified by the index. + * * %FGP_ENTRY - If there is a shadow / swap / DAX entry, return it + * instead of allocating a new page to replace it. * * %FGP_CREAT - If no page is present then a new page is allocated using * @gfp_mask and added to the page cache and the VM's LRU list. * The page is returned locked and with an increased refcount. @@ -1779,8 +1748,11 @@ struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index, repeat: page = find_get_entry(mapping, index); - if (xa_is_value(page)) + if (xa_is_value(page)) { + if (fgp_flags & FGP_ENTRY) + return page; page = NULL; + } if (!page) goto no_page; diff --git a/mm/internal.h b/mm/internal.h index 25d2b2439f19..eed74f1e6147 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -60,9 +60,6 @@ static inline void force_page_cache_readahead(struct address_space *mapping, force_page_cache_ra(&ractl, &file->f_ra, nr_to_read); } -struct page *find_get_entry(struct address_space *mapping, pgoff_t index); -struct page *find_lock_entry(struct address_space *mapping, pgoff_t index); - /** * page_evictable - test whether a page is evictable * @page: the page to test diff --git a/mm/shmem.c b/mm/shmem.c index 5ea1fa53db3f..bd5bb78128af 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1812,7 +1812,8 @@ repeat: sbinfo = SHMEM_SB(inode->i_sb); charge_mm = vma ? vma->vm_mm : current->mm; - page = find_lock_entry(mapping, index); + page = pagecache_get_page(mapping, index, + FGP_ENTRY | FGP_HEAD | FGP_LOCK, 0); if (xa_is_value(page)) { error = shmem_swapin_page(inode, index, &page, sgp, gfp, vma, fault_type); diff --git a/mm/swap_state.c b/mm/swap_state.c index f270c30d4681..3cdee7b11da9 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -403,7 +403,8 @@ struct page *find_get_incore_page(struct address_space *mapping, pgoff_t index) { swp_entry_t swp; struct swap_info_struct *si; - struct page *page = find_get_entry(mapping, index); + struct page *page = pagecache_get_page(mapping, index, + FGP_ENTRY | FGP_HEAD, 0); if (!page) return page; -- cgit v1.2.3 From 41139aa4c3a31ee7e072fc63353c74035aade2ff Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 25 Feb 2021 17:15:48 -0800 Subject: mm/filemap: add mapping_seek_hole_data Rewrite shmem_seek_hole_data() and move it to filemap.c. [willy@infradead.org: don't put an xa_is_value() page] Link: https://lkml.kernel.org/r/20201124041507.28996-4-willy@infradead.org Link: https://lkml.kernel.org/r/20201112212641.27837-8-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: William Kucharski Reviewed-by: Christoph Hellwig Cc: Dave Chinner Cc: Hugh Dickins Cc: Jan Kara Cc: Johannes Weiner Cc: Kirill A. Shutemov Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 2 ++ mm/filemap.c | 76 +++++++++++++++++++++++++++++++++++++++++++++++++ mm/shmem.c | 74 +++-------------------------------------------- 3 files changed, 82 insertions(+), 70 deletions(-) (limited to 'include') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index b379b2388202..3608993428d9 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -760,6 +760,8 @@ extern void __delete_from_page_cache(struct page *page, void *shadow); void replace_page_cache_page(struct page *old, struct page *new); void delete_from_page_cache_batch(struct address_space *mapping, struct pagevec *pvec); +loff_t mapping_seek_hole_data(struct address_space *, loff_t start, loff_t end, + int whence); /* * Like add_to_page_cache_locked, but used to add newly allocated pages: diff --git a/mm/filemap.c b/mm/filemap.c index 21443850aeae..eff3006be12a 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2553,6 +2553,82 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) } EXPORT_SYMBOL(generic_file_read_iter); +static inline bool page_seek_match(struct page *page, bool seek_data) +{ + if (xa_is_value(page) || PageUptodate(page)) + return seek_data; + return !seek_data; +} + +static inline +unsigned int seek_page_size(struct xa_state *xas, struct page *page) +{ + if (xa_is_value(page)) + return PAGE_SIZE << xa_get_order(xas->xa, xas->xa_index); + return thp_size(page); +} + +/** + * mapping_seek_hole_data - Seek for SEEK_DATA / SEEK_HOLE in the page cache. + * @mapping: Address space to search. + * @start: First byte to consider. + * @end: Limit of search (exclusive). + * @whence: Either SEEK_HOLE or SEEK_DATA. + * + * If the page cache knows which blocks contain holes and which blocks + * contain data, your filesystem can use this function to implement + * SEEK_HOLE and SEEK_DATA. This is useful for filesystems which are + * entirely memory-based such as tmpfs, and filesystems which support + * unwritten extents. + * + * Return: The requested offset on successs, or -ENXIO if @whence specifies + * SEEK_DATA and there is no data after @start. There is an implicit hole + * after @end - 1, so SEEK_HOLE returns @end if all the bytes between @start + * and @end contain data. + */ +loff_t mapping_seek_hole_data(struct address_space *mapping, loff_t start, + loff_t end, int whence) +{ + XA_STATE(xas, &mapping->i_pages, start >> PAGE_SHIFT); + pgoff_t max = (end - 1) / PAGE_SIZE; + bool seek_data = (whence == SEEK_DATA); + struct page *page; + + if (end <= start) + return -ENXIO; + + rcu_read_lock(); + while ((page = find_get_entry(&xas, max, XA_PRESENT))) { + loff_t pos = xas.xa_index * PAGE_SIZE; + + if (start < pos) { + if (!seek_data) + goto unlock; + start = pos; + } + + if (page_seek_match(page, seek_data)) + goto unlock; + start = pos + seek_page_size(&xas, page); + if (!xa_is_value(page)) + put_page(page); + } + rcu_read_unlock(); + + if (seek_data) + return -ENXIO; + goto out; + +unlock: + rcu_read_unlock(); + if (!xa_is_value(page)) + put_page(page); +out: + if (start > end) + return end; + return start; +} + #ifdef CONFIG_MMU #define MMAP_LOTSAMISS (100) /* diff --git a/mm/shmem.c b/mm/shmem.c index bd5bb78128af..deb22e128435 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2668,86 +2668,20 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) return retval ? retval : error; } -/* - * llseek SEEK_DATA or SEEK_HOLE through the page cache. - */ -static pgoff_t shmem_seek_hole_data(struct address_space *mapping, - pgoff_t index, pgoff_t end, int whence) -{ - struct page *page; - struct pagevec pvec; - pgoff_t indices[PAGEVEC_SIZE]; - bool done = false; - int i; - - pagevec_init(&pvec); - pvec.nr = 1; /* start small: we may be there already */ - while (!done) { - pvec.nr = find_get_entries(mapping, index, - pvec.nr, pvec.pages, indices); - if (!pvec.nr) { - if (whence == SEEK_DATA) - index = end; - break; - } - for (i = 0; i < pvec.nr; i++, index++) { - if (index < indices[i]) { - if (whence == SEEK_HOLE) { - done = true; - break; - } - index = indices[i]; - } - page = pvec.pages[i]; - if (page && !xa_is_value(page)) { - if (!PageUptodate(page)) - page = NULL; - } - if (index >= end || - (page && whence == SEEK_DATA) || - (!page && whence == SEEK_HOLE)) { - done = true; - break; - } - } - pagevec_remove_exceptionals(&pvec); - pagevec_release(&pvec); - pvec.nr = PAGEVEC_SIZE; - cond_resched(); - } - return index; -} - static loff_t shmem_file_llseek(struct file *file, loff_t offset, int whence) { struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; - pgoff_t start, end; - loff_t new_offset; if (whence != SEEK_DATA && whence != SEEK_HOLE) return generic_file_llseek_size(file, offset, whence, MAX_LFS_FILESIZE, i_size_read(inode)); + if (offset < 0) + return -ENXIO; + inode_lock(inode); /* We're holding i_mutex so we can access i_size directly */ - - if (offset < 0 || offset >= inode->i_size) - offset = -ENXIO; - else { - start = offset >> PAGE_SHIFT; - end = (inode->i_size + PAGE_SIZE - 1) >> PAGE_SHIFT; - new_offset = shmem_seek_hole_data(mapping, start, end, whence); - new_offset <<= PAGE_SHIFT; - if (new_offset > offset) { - if (new_offset < inode->i_size) - offset = new_offset; - else if (whence == SEEK_DATA) - offset = -ENXIO; - else - offset = inode->i_size; - } - } - + offset = mapping_seek_hole_data(mapping, offset, inode->i_size, whence); if (offset >= 0) offset = vfs_setpos(file, offset, MAX_LFS_FILESIZE); inode_unlock(inode); -- cgit v1.2.3 From ca122fe40eb463c8c11c3bfc1914f0048ca5c268 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 25 Feb 2021 17:16:00 -0800 Subject: mm: add an 'end' parameter to find_get_entries This simplifies the callers and leads to a more efficient implementation since the XArray has this functionality already. Link: https://lkml.kernel.org/r/20201112212641.27837-11-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Jan Kara Reviewed-by: William Kucharski Reviewed-by: Christoph Hellwig Cc: Dave Chinner Cc: Hugh Dickins Cc: Johannes Weiner Cc: Kirill A. Shutemov Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 4 ++-- mm/filemap.c | 9 +++++---- mm/shmem.c | 10 ++-------- mm/swap.c | 2 +- 4 files changed, 10 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 3608993428d9..fdb2c4e44851 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -451,8 +451,8 @@ static inline struct page *find_subpage(struct page *head, pgoff_t index) } unsigned find_get_entries(struct address_space *mapping, pgoff_t start, - unsigned int nr_entries, struct page **entries, - pgoff_t *indices); + pgoff_t end, unsigned int nr_entries, struct page **entries, + pgoff_t *indices); unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start, pgoff_t end, unsigned int nr_pages, struct page **pages); diff --git a/mm/filemap.c b/mm/filemap.c index 61fdcdc75275..65cfdff17ac6 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1865,6 +1865,7 @@ reset: * find_get_entries - gang pagecache lookup * @mapping: The address_space to search * @start: The starting page cache index + * @end: The final page index (inclusive). * @nr_entries: The maximum number of entries * @entries: Where the resulting entries are placed * @indices: The cache indices corresponding to the entries in @entries @@ -1888,9 +1889,9 @@ reset: * * Return: the number of pages and shadow entries which were found. */ -unsigned find_get_entries(struct address_space *mapping, - pgoff_t start, unsigned int nr_entries, - struct page **entries, pgoff_t *indices) +unsigned find_get_entries(struct address_space *mapping, pgoff_t start, + pgoff_t end, unsigned int nr_entries, struct page **entries, + pgoff_t *indices) { XA_STATE(xas, &mapping->i_pages, start); struct page *page; @@ -1900,7 +1901,7 @@ unsigned find_get_entries(struct address_space *mapping, return 0; rcu_read_lock(); - while ((page = find_get_entry(&xas, ULONG_MAX, XA_PRESENT))) { + while ((page = find_get_entry(&xas, end, XA_PRESENT))) { /* * Terminate early on finding a THP, to allow the caller to * handle it all at once; but continue if this is hugetlbfs. diff --git a/mm/shmem.c b/mm/shmem.c index 86b1f5bc502c..4aac760aa2d4 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -913,8 +913,6 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, struct page *page = pvec.pages[i]; index = indices[i]; - if (index >= end) - break; if (xa_is_value(page)) { if (unfalloc) @@ -967,9 +965,8 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, while (index < end) { cond_resched(); - pvec.nr = find_get_entries(mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE), - pvec.pages, indices); + pvec.nr = find_get_entries(mapping, index, end - 1, + PAGEVEC_SIZE, pvec.pages, indices); if (!pvec.nr) { /* If all gone or hole-punch or unfalloc, we're done */ if (index == start || end != -1) @@ -982,9 +979,6 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, struct page *page = pvec.pages[i]; index = indices[i]; - if (index >= end) - break; - if (xa_is_value(page)) { if (unfalloc) continue; diff --git a/mm/swap.c b/mm/swap.c index ab3258afcbeb..c5773a84feab 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -1046,7 +1046,7 @@ unsigned pagevec_lookup_entries(struct pagevec *pvec, pgoff_t start, unsigned nr_entries, pgoff_t *indices) { - pvec->nr = find_get_entries(mapping, start, nr_entries, + pvec->nr = find_get_entries(mapping, start, ULONG_MAX, nr_entries, pvec->pages, indices); return pagevec_count(pvec); } -- cgit v1.2.3 From 31d270fd98d196578223e5b568a0bd3bc6028b09 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 25 Feb 2021 17:16:03 -0800 Subject: mm: add an 'end' parameter to pagevec_lookup_entries Simplifies the callers and uses the existing functionality in find_get_entries(). We can also drop the final argument of truncate_exceptional_pvec_entries() and simplify the logic in that function. Link: https://lkml.kernel.org/r/20201112212641.27837-12-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Jan Kara Reviewed-by: William Kucharski Reviewed-by: Christoph Hellwig Cc: Dave Chinner Cc: Hugh Dickins Cc: Johannes Weiner Cc: Kirill A. Shutemov Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagevec.h | 5 ++--- mm/swap.c | 8 ++++---- mm/truncate.c | 41 ++++++++++------------------------------- 3 files changed, 16 insertions(+), 38 deletions(-) (limited to 'include') diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h index ad4ddc17d403..f70a9dc81504 100644 --- a/include/linux/pagevec.h +++ b/include/linux/pagevec.h @@ -26,9 +26,8 @@ struct pagevec { void __pagevec_release(struct pagevec *pvec); void __pagevec_lru_add(struct pagevec *pvec); unsigned pagevec_lookup_entries(struct pagevec *pvec, - struct address_space *mapping, - pgoff_t start, unsigned nr_entries, - pgoff_t *indices); + struct address_space *mapping, pgoff_t start, pgoff_t end, + unsigned nr_entries, pgoff_t *indices); void pagevec_remove_exceptionals(struct pagevec *pvec); unsigned pagevec_lookup_range(struct pagevec *pvec, struct address_space *mapping, diff --git a/mm/swap.c b/mm/swap.c index c5773a84feab..db8c354264a5 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -1022,6 +1022,7 @@ void __pagevec_lru_add(struct pagevec *pvec) * @pvec: Where the resulting entries are placed * @mapping: The address_space to search * @start: The starting entry index + * @end: The highest index to return (inclusive). * @nr_entries: The maximum number of pages * @indices: The cache indices corresponding to the entries in @pvec * @@ -1042,11 +1043,10 @@ void __pagevec_lru_add(struct pagevec *pvec) * found. */ unsigned pagevec_lookup_entries(struct pagevec *pvec, - struct address_space *mapping, - pgoff_t start, unsigned nr_entries, - pgoff_t *indices) + struct address_space *mapping, pgoff_t start, pgoff_t end, + unsigned nr_entries, pgoff_t *indices) { - pvec->nr = find_get_entries(mapping, start, ULONG_MAX, nr_entries, + pvec->nr = find_get_entries(mapping, start, end, nr_entries, pvec->pages, indices); return pagevec_count(pvec); } diff --git a/mm/truncate.c b/mm/truncate.c index de7f4f47f780..60df23890c2d 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -57,11 +57,10 @@ static void clear_shadow_entry(struct address_space *mapping, pgoff_t index, * exceptional entries similar to what pagevec_remove_exceptionals does. */ static void truncate_exceptional_pvec_entries(struct address_space *mapping, - struct pagevec *pvec, pgoff_t *indices, - pgoff_t end) + struct pagevec *pvec, pgoff_t *indices) { int i, j; - bool dax, lock; + bool dax; /* Handled by shmem itself */ if (shmem_mapping(mapping)) @@ -75,8 +74,7 @@ static void truncate_exceptional_pvec_entries(struct address_space *mapping, return; dax = dax_mapping(mapping); - lock = !dax && indices[j] < end; - if (lock) + if (!dax) xa_lock_irq(&mapping->i_pages); for (i = j; i < pagevec_count(pvec); i++) { @@ -88,9 +86,6 @@ static void truncate_exceptional_pvec_entries(struct address_space *mapping, continue; } - if (index >= end) - continue; - if (unlikely(dax)) { dax_delete_mapping_entry(mapping, index); continue; @@ -99,7 +94,7 @@ static void truncate_exceptional_pvec_entries(struct address_space *mapping, __clear_shadow_entry(mapping, index, page); } - if (lock) + if (!dax) xa_unlock_irq(&mapping->i_pages); pvec->nr = j; } @@ -329,7 +324,7 @@ void truncate_inode_pages_range(struct address_space *mapping, while (index < end && find_lock_entries(mapping, index, end - 1, &pvec, indices)) { index = indices[pagevec_count(&pvec) - 1] + 1; - truncate_exceptional_pvec_entries(mapping, &pvec, indices, end); + truncate_exceptional_pvec_entries(mapping, &pvec, indices); for (i = 0; i < pagevec_count(&pvec); i++) truncate_cleanup_page(mapping, pvec.pages[i]); delete_from_page_cache_batch(mapping, &pvec); @@ -381,8 +376,8 @@ void truncate_inode_pages_range(struct address_space *mapping, index = start; for ( ; ; ) { cond_resched(); - if (!pagevec_lookup_entries(&pvec, mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE), indices)) { + if (!pagevec_lookup_entries(&pvec, mapping, index, end - 1, + PAGEVEC_SIZE, indices)) { /* If all gone from start onwards, we're done */ if (index == start) break; @@ -390,23 +385,12 @@ void truncate_inode_pages_range(struct address_space *mapping, index = start; continue; } - if (index == start && indices[0] >= end) { - /* All gone out of hole to be punched, we're done */ - pagevec_remove_exceptionals(&pvec); - pagevec_release(&pvec); - break; - } for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; /* We rely upon deletion not changing page->index */ index = indices[i]; - if (index >= end) { - /* Restart punch to make sure all gone */ - index = start - 1; - break; - } if (xa_is_value(page)) continue; @@ -417,7 +401,7 @@ void truncate_inode_pages_range(struct address_space *mapping, truncate_inode_page(mapping, page); unlock_page(page); } - truncate_exceptional_pvec_entries(mapping, &pvec, indices, end); + truncate_exceptional_pvec_entries(mapping, &pvec, indices); pagevec_release(&pvec); index++; } @@ -513,8 +497,6 @@ static unsigned long __invalidate_mapping_pages(struct address_space *mapping, /* We rely upon deletion not changing page->index */ index = indices[i]; - if (index > end) - break; if (xa_is_value(page)) { invalidate_exceptional_entry(mapping, index, @@ -656,16 +638,13 @@ int invalidate_inode_pages2_range(struct address_space *mapping, pagevec_init(&pvec); index = start; - while (index <= end && pagevec_lookup_entries(&pvec, mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1, - indices)) { + while (pagevec_lookup_entries(&pvec, mapping, index, end, + PAGEVEC_SIZE, indices)) { for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; /* We rely upon deletion not changing page->index */ index = indices[i]; - if (index > end) - break; if (xa_is_value(page)) { if (!invalidate_exceptional_entry2(mapping, -- cgit v1.2.3 From 38cefeb33749992ceaad6ea40e12f92aa8f8e28f Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 25 Feb 2021 17:16:07 -0800 Subject: mm: remove nr_entries parameter from pagevec_lookup_entries All callers want to fetch the full size of the pvec. Link: https://lkml.kernel.org/r/20201112212641.27837-13-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Jan Kara Reviewed-by: William Kucharski Reviewed-by: Christoph Hellwig Cc: Dave Chinner Cc: Hugh Dickins Cc: Johannes Weiner Cc: Kirill A. Shutemov Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagevec.h | 2 +- mm/swap.c | 4 ++-- mm/truncate.c | 5 ++--- 3 files changed, 5 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h index f70a9dc81504..72c5ea2e708d 100644 --- a/include/linux/pagevec.h +++ b/include/linux/pagevec.h @@ -27,7 +27,7 @@ void __pagevec_release(struct pagevec *pvec); void __pagevec_lru_add(struct pagevec *pvec); unsigned pagevec_lookup_entries(struct pagevec *pvec, struct address_space *mapping, pgoff_t start, pgoff_t end, - unsigned nr_entries, pgoff_t *indices); + pgoff_t *indices); void pagevec_remove_exceptionals(struct pagevec *pvec); unsigned pagevec_lookup_range(struct pagevec *pvec, struct address_space *mapping, diff --git a/mm/swap.c b/mm/swap.c index db8c354264a5..cd9e1ed7e78f 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -1044,9 +1044,9 @@ void __pagevec_lru_add(struct pagevec *pvec) */ unsigned pagevec_lookup_entries(struct pagevec *pvec, struct address_space *mapping, pgoff_t start, pgoff_t end, - unsigned nr_entries, pgoff_t *indices) + pgoff_t *indices) { - pvec->nr = find_get_entries(mapping, start, end, nr_entries, + pvec->nr = find_get_entries(mapping, start, end, PAGEVEC_SIZE, pvec->pages, indices); return pagevec_count(pvec); } diff --git a/mm/truncate.c b/mm/truncate.c index 60df23890c2d..41e7377ad58d 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -377,7 +377,7 @@ void truncate_inode_pages_range(struct address_space *mapping, for ( ; ; ) { cond_resched(); if (!pagevec_lookup_entries(&pvec, mapping, index, end - 1, - PAGEVEC_SIZE, indices)) { + indices)) { /* If all gone from start onwards, we're done */ if (index == start) break; @@ -638,8 +638,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping, pagevec_init(&pvec); index = start; - while (pagevec_lookup_entries(&pvec, mapping, index, end, - PAGEVEC_SIZE, indices)) { + while (pagevec_lookup_entries(&pvec, mapping, index, end, indices)) { for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; -- cgit v1.2.3 From cf2039af1a2eee58fdbfa68bc0c9123e77477645 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 25 Feb 2021 17:16:11 -0800 Subject: mm: pass pvec directly to find_get_entries All callers of find_get_entries() use a pvec, so pass it directly instead of manipulating it in the caller. Link: https://lkml.kernel.org/r/20201112212641.27837-14-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Jan Kara Reviewed-by: William Kucharski Cc: Christoph Hellwig Cc: Dave Chinner Cc: Hugh Dickins Cc: Johannes Weiner Cc: Kirill A. Shutemov Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 3 +-- mm/filemap.c | 21 +++++++++------------ mm/shmem.c | 5 ++--- mm/swap.c | 4 +--- 4 files changed, 13 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index fdb2c4e44851..20225b067583 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -451,8 +451,7 @@ static inline struct page *find_subpage(struct page *head, pgoff_t index) } unsigned find_get_entries(struct address_space *mapping, pgoff_t start, - pgoff_t end, unsigned int nr_entries, struct page **entries, - pgoff_t *indices); + pgoff_t end, struct pagevec *pvec, pgoff_t *indices); unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start, pgoff_t end, unsigned int nr_pages, struct page **pages); diff --git a/mm/filemap.c b/mm/filemap.c index 65cfdff17ac6..43700480d897 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1866,14 +1866,12 @@ reset: * @mapping: The address_space to search * @start: The starting page cache index * @end: The final page index (inclusive). - * @nr_entries: The maximum number of entries - * @entries: Where the resulting entries are placed + * @pvec: Where the resulting entries are placed. * @indices: The cache indices corresponding to the entries in @entries * - * find_get_entries() will search for and return a group of up to - * @nr_entries entries in the mapping. The entries are placed at - * @entries. find_get_entries() takes a reference against any actual - * pages it returns. + * find_get_entries() will search for and return a batch of entries in + * the mapping. The entries are placed in @pvec. find_get_entries() + * takes a reference on any actual pages it returns. * * The search returns a group of mapping-contiguous page cache entries * with ascending indexes. There may be holes in the indices due to @@ -1890,15 +1888,12 @@ reset: * Return: the number of pages and shadow entries which were found. */ unsigned find_get_entries(struct address_space *mapping, pgoff_t start, - pgoff_t end, unsigned int nr_entries, struct page **entries, - pgoff_t *indices) + pgoff_t end, struct pagevec *pvec, pgoff_t *indices) { XA_STATE(xas, &mapping->i_pages, start); struct page *page; unsigned int ret = 0; - - if (!nr_entries) - return 0; + unsigned nr_entries = PAGEVEC_SIZE; rcu_read_lock(); while ((page = find_get_entry(&xas, end, XA_PRESENT))) { @@ -1913,11 +1908,13 @@ unsigned find_get_entries(struct address_space *mapping, pgoff_t start, } indices[ret] = xas.xa_index; - entries[ret] = page; + pvec->pages[ret] = page; if (++ret == nr_entries) break; } rcu_read_unlock(); + + pvec->nr = ret; return ret; } diff --git a/mm/shmem.c b/mm/shmem.c index 4aac760aa2d4..ee8f21832f98 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -965,9 +965,8 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, while (index < end) { cond_resched(); - pvec.nr = find_get_entries(mapping, index, end - 1, - PAGEVEC_SIZE, pvec.pages, indices); - if (!pvec.nr) { + if (!find_get_entries(mapping, index, end - 1, &pvec, + indices)) { /* If all gone or hole-punch or unfalloc, we're done */ if (index == start || end != -1) break; diff --git a/mm/swap.c b/mm/swap.c index cd9e1ed7e78f..d20a746a831e 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -1046,9 +1046,7 @@ unsigned pagevec_lookup_entries(struct pagevec *pvec, struct address_space *mapping, pgoff_t start, pgoff_t end, pgoff_t *indices) { - pvec->nr = find_get_entries(mapping, start, end, PAGEVEC_SIZE, - pvec->pages, indices); - return pagevec_count(pvec); + return find_get_entries(mapping, start, end, pvec, indices); } /** -- cgit v1.2.3 From a656a20241f08be532539c7d5bd82df741c2d487 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 25 Feb 2021 17:16:14 -0800 Subject: mm: remove pagevec_lookup_entries pagevec_lookup_entries() is now just a wrapper around find_get_entries() so remove it and convert all its callers. Link: https://lkml.kernel.org/r/20201112212641.27837-15-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Jan Kara Reviewed-by: William Kucharski Reviewed-by: Christoph Hellwig Cc: Dave Chinner Cc: Hugh Dickins Cc: Johannes Weiner Cc: Kirill A. Shutemov Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagevec.h | 3 --- mm/swap.c | 36 ++---------------------------------- mm/truncate.c | 4 ++-- 3 files changed, 4 insertions(+), 39 deletions(-) (limited to 'include') diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h index 72c5ea2e708d..7f3f19065a9f 100644 --- a/include/linux/pagevec.h +++ b/include/linux/pagevec.h @@ -25,9 +25,6 @@ struct pagevec { void __pagevec_release(struct pagevec *pvec); void __pagevec_lru_add(struct pagevec *pvec); -unsigned pagevec_lookup_entries(struct pagevec *pvec, - struct address_space *mapping, pgoff_t start, pgoff_t end, - pgoff_t *indices); void pagevec_remove_exceptionals(struct pagevec *pvec); unsigned pagevec_lookup_range(struct pagevec *pvec, struct address_space *mapping, diff --git a/mm/swap.c b/mm/swap.c index d20a746a831e..31b844d4ed94 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -1017,44 +1017,12 @@ void __pagevec_lru_add(struct pagevec *pvec) pagevec_reinit(pvec); } -/** - * pagevec_lookup_entries - gang pagecache lookup - * @pvec: Where the resulting entries are placed - * @mapping: The address_space to search - * @start: The starting entry index - * @end: The highest index to return (inclusive). - * @nr_entries: The maximum number of pages - * @indices: The cache indices corresponding to the entries in @pvec - * - * pagevec_lookup_entries() will search for and return a group of up - * to @nr_pages pages and shadow entries in the mapping. All - * entries are placed in @pvec. pagevec_lookup_entries() takes a - * reference against actual pages in @pvec. - * - * The search returns a group of mapping-contiguous entries with - * ascending indexes. There may be holes in the indices due to - * not-present entries. - * - * Only one subpage of a Transparent Huge Page is returned in one call: - * allowing truncate_inode_pages_range() to evict the whole THP without - * cycling through a pagevec of extra references. - * - * pagevec_lookup_entries() returns the number of entries which were - * found. - */ -unsigned pagevec_lookup_entries(struct pagevec *pvec, - struct address_space *mapping, pgoff_t start, pgoff_t end, - pgoff_t *indices) -{ - return find_get_entries(mapping, start, end, pvec, indices); -} - /** * pagevec_remove_exceptionals - pagevec exceptionals pruning * @pvec: The pagevec to prune * - * pagevec_lookup_entries() fills both pages and exceptional radix - * tree entries into the pagevec. This function prunes all + * find_get_entries() fills both pages and XArray value entries (aka + * exceptional entries) into the pagevec. This function prunes all * exceptionals from @pvec without leaving holes, so that it can be * passed on to page-only pagevec operations. */ diff --git a/mm/truncate.c b/mm/truncate.c index 41e7377ad58d..455944264663 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -376,7 +376,7 @@ void truncate_inode_pages_range(struct address_space *mapping, index = start; for ( ; ; ) { cond_resched(); - if (!pagevec_lookup_entries(&pvec, mapping, index, end - 1, + if (!find_get_entries(mapping, index, end - 1, &pvec, indices)) { /* If all gone from start onwards, we're done */ if (index == start) @@ -638,7 +638,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping, pagevec_init(&pvec); index = start; - while (pagevec_lookup_entries(&pvec, mapping, index, end, indices)) { + while (find_get_entries(mapping, index, end, &pvec, indices)) { for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; -- cgit v1.2.3 From 164cc4fef4456727466f8e35bb654c3994748070 Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Thu, 25 Feb 2021 17:16:18 -0800 Subject: mm,thp,shmem: limit shmem THP alloc gfp_mask Patch series "mm,thp,shm: limit shmem THP alloc gfp_mask", v6. The allocation flags of anonymous transparent huge pages can be controlled through the files in /sys/kernel/mm/transparent_hugepage/defrag, which can help the system from getting bogged down in the page reclaim and compaction code when many THPs are getting allocated simultaneously. However, the gfp_mask for shmem THP allocations were not limited by those configuration settings, and some workloads ended up with all CPUs stuck on the LRU lock in the page reclaim code, trying to allocate dozens of THPs simultaneously. This patch applies the same configurated limitation of THPs to shmem hugepage allocations, to prevent that from happening. This way a THP defrag setting of "never" or "defer+madvise" will result in quick allocation failures without direct reclaim when no 2MB free pages are available. With this patch applied, THP allocations for tmpfs will be a little more aggressive than today for files mmapped with MADV_HUGEPAGE, and a little less aggressive for files that are not mmapped or mapped without that flag. This patch (of 4): The allocation flags of anonymous transparent huge pages can be controlled through the files in /sys/kernel/mm/transparent_hugepage/defrag, which can help the system from getting bogged down in the page reclaim and compaction code when many THPs are getting allocated simultaneously. However, the gfp_mask for shmem THP allocations were not limited by those configuration settings, and some workloads ended up with all CPUs stuck on the LRU lock in the page reclaim code, trying to allocate dozens of THPs simultaneously. This patch applies the same configurated limitation of THPs to shmem hugepage allocations, to prevent that from happening. Controlling the gfp_mask of THP allocations through the knobs in sysfs allows users to determine the balance between how aggressively the system tries to allocate THPs at fault time, and how much the application may end up stalling attempting those allocations. This way a THP defrag setting of "never" or "defer+madvise" will result in quick allocation failures without direct reclaim when no 2MB free pages are available. With this patch applied, THP allocations for tmpfs will be a little more aggressive than today for files mmapped with MADV_HUGEPAGE, and a little less aggressive for files that are not mmapped or mapped without that flag. Link: https://lkml.kernel.org/r/20201124194925.623931-1-riel@surriel.com Link: https://lkml.kernel.org/r/20201124194925.623931-2-riel@surriel.com Signed-off-by: Rik van Riel Acked-by: Michal Hocko Acked-by: Vlastimil Babka Cc: Xu Yu Cc: Mel Gorman Cc: Andrea Arcangeli Cc: Matthew Wilcox (Oracle) Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 2 ++ mm/huge_memory.c | 6 +++--- mm/shmem.c | 8 +++++--- 3 files changed, 10 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 220cd553a9e7..8572a1474e16 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -634,6 +634,8 @@ bool gfp_pfmemalloc_allowed(gfp_t gfp_mask); extern void pm_restrict_gfp_mask(void); extern void pm_restore_gfp_mask(void); +extern gfp_t vma_thp_gfp_mask(struct vm_area_struct *vma); + #ifdef CONFIG_PM_SLEEP extern bool pm_suspended_storage(void); #else diff --git a/mm/huge_memory.c b/mm/huge_memory.c index d77605c30f2e..395c75111d33 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -668,9 +668,9 @@ release: * available * never: never stall for any thp allocation */ -static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma) +gfp_t vma_thp_gfp_mask(struct vm_area_struct *vma) { - const bool vma_madvised = !!(vma->vm_flags & VM_HUGEPAGE); + const bool vma_madvised = vma && (vma->vm_flags & VM_HUGEPAGE); /* Always do synchronous compaction */ if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags)) @@ -762,7 +762,7 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf) } return ret; } - gfp = alloc_hugepage_direct_gfpmask(vma); + gfp = vma_thp_gfp_mask(vma); page = alloc_hugepage_vma(gfp, vma, haddr, HPAGE_PMD_ORDER); if (unlikely(!page)) { count_vm_event(THP_FAULT_FALLBACK); diff --git a/mm/shmem.c b/mm/shmem.c index ee8f21832f98..596009a44431 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1519,8 +1519,8 @@ static struct page *shmem_alloc_hugepage(gfp_t gfp, return NULL; shmem_pseudo_vma_init(&pvma, info, hindex); - page = alloc_pages_vma(gfp | __GFP_COMP | __GFP_NORETRY | __GFP_NOWARN, - HPAGE_PMD_ORDER, &pvma, 0, numa_node_id(), true); + page = alloc_pages_vma(gfp, HPAGE_PMD_ORDER, &pvma, 0, numa_node_id(), + true); shmem_pseudo_vma_destroy(&pvma); if (page) prep_transhuge_page(page); @@ -1776,6 +1776,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, struct page *page; enum sgp_type sgp_huge = sgp; pgoff_t hindex = index; + gfp_t huge_gfp; int error; int once = 0; int alloced = 0; @@ -1862,7 +1863,8 @@ repeat: } alloc_huge: - page = shmem_alloc_and_acct_page(gfp, inode, index, true); + huge_gfp = vma_thp_gfp_mask(vma); + page = shmem_alloc_and_acct_page(huge_gfp, inode, index, true); if (IS_ERR(page)) { alloc_nohuge: page = shmem_alloc_and_acct_page(gfp, inode, -- cgit v1.2.3 From cd89fb06509903f942a0ffe97ffa63034671ed0c Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Thu, 25 Feb 2021 17:16:25 -0800 Subject: mm,thp,shmem: make khugepaged obey tmpfs mount flags Currently if thp enabled=[madvise], mounting a tmpfs filesystem with huge=always and mmapping files from that tmpfs does not result in khugepaged collapsing those mappings, despite the mount flag indicating that it should. Fix that by breaking up the blocks of tests in hugepage_vma_check a little bit, and testing things in the correct order. Link: https://lkml.kernel.org/r/20201124194925.623931-4-riel@surriel.com Fixes: c2231020ea7b ("mm: thp: register mm for khugepaged when merging vma for shmem") Signed-off-by: Rik van Riel Cc: Andrea Arcangeli Cc: Hugh Dickins Cc: Matthew Wilcox (Oracle) Cc: Mel Gorman Cc: Michal Hocko Cc: Vlastimil Babka Cc: Xu Yu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/khugepaged.h | 2 ++ mm/khugepaged.c | 22 ++++++++++++++++------ 2 files changed, 18 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h index c941b7377321..2fcc01891b47 100644 --- a/include/linux/khugepaged.h +++ b/include/linux/khugepaged.h @@ -3,6 +3,7 @@ #define _LINUX_KHUGEPAGED_H #include /* MMF_VM_HUGEPAGE */ +#include #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -57,6 +58,7 @@ static inline int khugepaged_enter(struct vm_area_struct *vma, { if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags)) if ((khugepaged_always() || + (shmem_file(vma->vm_file) && shmem_huge_enabled(vma)) || (khugepaged_req_madv() && (vm_flags & VM_HUGEPAGE))) && !(vm_flags & VM_NOHUGEPAGE) && !test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 75e246f680f4..a7d6cb912b05 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -442,18 +442,28 @@ static inline int khugepaged_test_exit(struct mm_struct *mm) static bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags) { - if ((!(vm_flags & VM_HUGEPAGE) && !khugepaged_always()) || - (vm_flags & VM_NOHUGEPAGE) || + /* Explicitly disabled through madvise. */ + if ((vm_flags & VM_NOHUGEPAGE) || test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) return false; - if (shmem_file(vma->vm_file) || - (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && - vma->vm_file && - (vm_flags & VM_DENYWRITE))) { + /* Enabled via shmem mount options or sysfs settings. */ + if (shmem_file(vma->vm_file) && shmem_huge_enabled(vma)) { return IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff, HPAGE_PMD_NR); } + + /* THP settings require madvise. */ + if (!(vm_flags & VM_HUGEPAGE) && !khugepaged_always()) + return false; + + /* Read-only file mappings need to be aligned for THP to work. */ + if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && vma->vm_file && + (vm_flags & VM_DENYWRITE)) { + return IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff, + HPAGE_PMD_NR); + } + if (!vma->anon_vma || vma->vm_ops) return false; if (vma_is_temporary_stack(vma)) -- cgit v1.2.3 From 3c381db1fac80373f2cc0d8c1d0bcfbf8bd4fb57 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 25 Feb 2021 17:16:40 -0800 Subject: mm/page_alloc: count CMA pages per zone and print them in /proc/zoneinfo Let's count the number of CMA pages per zone and print them in /proc/zoneinfo. Having access to the total number of CMA pages per zone is helpful for debugging purposes to know where exactly the CMA pages ended up, and to figure out how many pages of a zone might behave differently, even after some of these pages might already have been allocated. As one example, CMA pages part of a kernel zone cannot be used for ordinary kernel allocations but instead behave more like ZONE_MOVABLE. For now, we are only able to get the global nr+free cma pages from /proc/meminfo and the free cma pages per zone from /proc/zoneinfo. Example after this patch when booting a 6 GiB QEMU VM with "hugetlb_cma=2G": # cat /proc/zoneinfo | grep cma cma 0 nr_free_cma 0 cma 0 nr_free_cma 0 cma 524288 nr_free_cma 493016 cma 0 cma 0 # cat /proc/meminfo | grep Cma CmaTotal: 2097152 kB CmaFree: 1972064 kB Note: We print even without CONFIG_CMA, just like "nr_free_cma"; this way, one can be sure when spotting "cma 0", that there are definetly no CMA pages located in a zone. [david@redhat.com: v2] Link: https://lkml.kernel.org/r/20210128164533.18566-1-david@redhat.com [david@redhat.com: v3] Link: https://lkml.kernel.org/r/20210129113451.22085-1-david@redhat.com Link: https://lkml.kernel.org/r/20210127101813.6370-3-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Oscar Salvador Acked-by: David Rientjes Cc: Thomas Gleixner Cc: "Peter Zijlstra (Intel)" Cc: Mike Rapoport Cc: Michal Hocko Cc: Wei Yang Cc: Zi Yan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 15 +++++++++++++++ mm/page_alloc.c | 1 + mm/vmstat.c | 6 ++++-- 3 files changed, 20 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 9198b7ade85f..5f9c4dad73ed 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -503,6 +503,9 @@ struct zone { * bootmem allocator): * managed_pages = present_pages - reserved_pages; * + * cma pages is present pages that are assigned for CMA use + * (MIGRATE_CMA). + * * So present_pages may be used by memory hotplug or memory power * management logic to figure out unmanaged pages by checking * (present_pages - managed_pages). And managed_pages should be used @@ -527,6 +530,9 @@ struct zone { atomic_long_t managed_pages; unsigned long spanned_pages; unsigned long present_pages; +#ifdef CONFIG_CMA + unsigned long cma_pages; +#endif const char *name; @@ -624,6 +630,15 @@ static inline unsigned long zone_managed_pages(struct zone *zone) return (unsigned long)atomic_long_read(&zone->managed_pages); } +static inline unsigned long zone_cma_pages(struct zone *zone) +{ +#ifdef CONFIG_CMA + return zone->cma_pages; +#else + return 0; +#endif +} + static inline unsigned long zone_end_pfn(const struct zone *zone) { return zone->zone_start_pfn + zone->spanned_pages; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index ddccc59f2f72..3e4b29ee2b1e 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2168,6 +2168,7 @@ void __init init_cma_reserved_pageblock(struct page *page) } adjust_managed_page_count(page, pageblock_nr_pages); + page_zone(page)->cma_pages += pageblock_nr_pages; } #endif diff --git a/mm/vmstat.c b/mm/vmstat.c index a0e949542204..6cdf789ced5e 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1637,14 +1637,16 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, "\n high %lu" "\n spanned %lu" "\n present %lu" - "\n managed %lu", + "\n managed %lu" + "\n cma %lu", zone_page_state(zone, NR_FREE_PAGES), min_wmark_pages(zone), low_wmark_pages(zone), high_wmark_pages(zone), zone->spanned_pages, zone->present_pages, - zone_managed_pages(zone)); + zone_managed_pages(zone), + zone_cma_pages(zone)); seq_printf(m, "\n protection: (%ld", -- cgit v1.2.3 From 629484ae73754243917e06d8d5e5f37c26e99399 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 25 Feb 2021 17:16:51 -0800 Subject: mm: vmstat: add some comments on internal storage of byte items Byte-accounted items are used for slab object accounting at the cgroup level, because the objects in a slab page can belong to different cgroups. At the global level these items always change in multiples of whole slab pages. The vmstat code exploits this and stores these items as pages internally, which allows for more compact per-cpu data. This optimization isn't self-evident from the asserts and the division in the stat update functions. Provide the reader with some context. Link: https://lkml.kernel.org/r/20210202184411.118614-1-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmstat.h | 6 ++++++ mm/vmstat.c | 12 ++++++++++++ 2 files changed, 18 insertions(+) (limited to 'include') diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 773135fc6e19..506d625163a1 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -313,6 +313,12 @@ static inline void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item, int delta) { if (vmstat_item_in_bytes(item)) { + /* + * Only cgroups use subpage accounting right now; at + * the global level, these items still change in + * multiples of whole pages. Store them as pages + * internally to keep the per-cpu counters compact. + */ VM_WARN_ON_ONCE(delta & (PAGE_SIZE - 1)); delta >>= PAGE_SHIFT; } diff --git a/mm/vmstat.c b/mm/vmstat.c index 0b0fc3b77789..e60b36f5f0a9 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -342,6 +342,12 @@ void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item, long t; if (vmstat_item_in_bytes(item)) { + /* + * Only cgroups use subpage accounting right now; at + * the global level, these items still change in + * multiples of whole pages. Store them as pages + * internally to keep the per-cpu counters compact. + */ VM_WARN_ON_ONCE(delta & (PAGE_SIZE - 1)); delta >>= PAGE_SHIFT; } @@ -551,6 +557,12 @@ static inline void mod_node_state(struct pglist_data *pgdat, long o, n, t, z; if (vmstat_item_in_bytes(item)) { + /* + * Only cgroups use subpage accounting right now; at + * the global level, these items still change in + * multiples of whole pages. Store them as pages + * internally to keep the per-cpu counters compact. + */ VM_WARN_ON_ONCE(delta & (PAGE_SIZE - 1)); delta >>= PAGE_SHIFT; } -- cgit v1.2.3 From 9f605f260594f99b950062fd62244251e85dbd2b Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 25 Feb 2021 17:16:57 -0800 Subject: mm: move pfn_to_online_page() out of line Patch series "mm: Fix pfn_to_online_page() with respect to ZONE_DEVICE", v4. A pfn-walker that uses pfn_to_online_page() may inadvertently translate a pfn as online and in the page allocator, when it is offline managed by a ZONE_DEVICE mapping (details in Patch 3: ("mm: Teach pfn_to_online_page() about ZONE_DEVICE section collisions")). The 2 proposals under consideration are teach pfn_to_online_page() to be precise in the presence of mixed-zone sections, or teach the memory-add code to drop the System RAM associated with ZONE_DEVICE collisions. In order to not regress memory capacity by a few 10s to 100s of MiB the approach taken in this set is to add precision to pfn_to_online_page(). In the course of validating pfn_to_online_page() a couple other fixes fell out: 1/ soft_offline_page() fails to drop the reference taken in the madvise(..., MADV_SOFT_OFFLINE) case. 2/ memory_failure() uses get_dev_pagemap() to lookup ZONE_DEVICE pages, however that mapping may contain data pages and metadata raw pfns. Introduce pgmap_pfn_valid() to delineate the 2 types and fail the handling of raw metadata pfns. This patch (of 4); pfn_to_online_page() is already too large to be a macro or an inline function. In anticipation of further logic changes / growth, move it out of line. No functional change, just code movement. Link: https://lkml.kernel.org/r/161058499000.1840162.702316708443239771.stgit@dwillia2-desk3.amr.corp.intel.com Link: https://lkml.kernel.org/r/161058499608.1840162.10165648147615238793.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams Reported-by: Michal Hocko Acked-by: Michal Hocko Reviewed-by: David Hildenbrand Reviewed-by: Oscar Salvador Cc: Naoya Horiguchi Cc: Qian Cai Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 17 +---------------- mm/memory_hotplug.c | 16 ++++++++++++++++ 2 files changed, 17 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 15acce5ab106..3d99de0db2dd 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -16,22 +16,7 @@ struct resource; struct vmem_altmap; #ifdef CONFIG_MEMORY_HOTPLUG -/* - * Return page for the valid pfn only if the page is online. All pfn - * walkers which rely on the fully initialized page->flags and others - * should use this rather than pfn_valid && pfn_to_page - */ -#define pfn_to_online_page(pfn) \ -({ \ - struct page *___page = NULL; \ - unsigned long ___pfn = pfn; \ - unsigned long ___nr = pfn_to_section_nr(___pfn); \ - \ - if (___nr < NR_MEM_SECTIONS && online_section_nr(___nr) && \ - pfn_valid_within(___pfn)) \ - ___page = pfn_to_page(___pfn); \ - ___page; \ -}) +struct page *pfn_to_online_page(unsigned long pfn); /* * Types for free bootmem stored in page->lru.next. These have to be in diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index abe43c1ae920..fc6cdd99941b 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -300,6 +300,22 @@ static int check_hotplug_memory_addressable(unsigned long pfn, return 0; } +/* + * Return page for the valid pfn only if the page is online. All pfn + * walkers which rely on the fully initialized page->flags and others + * should use this rather than pfn_valid && pfn_to_page + */ +struct page *pfn_to_online_page(unsigned long pfn) +{ + unsigned long nr = pfn_to_section_nr(pfn); + + if (nr < NR_MEM_SECTIONS && online_section_nr(nr) && + pfn_valid_within(pfn)) + return pfn_to_page(pfn); + return NULL; +} +EXPORT_SYMBOL_GPL(pfn_to_online_page); + /* * Reasonably generic function for adding memory. It is * expected that archs that support memory hotplug will -- cgit v1.2.3 From 1f90a3477df3ff1a91e064af554cdc887c8f9e5e Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 25 Feb 2021 17:17:05 -0800 Subject: mm: teach pfn_to_online_page() about ZONE_DEVICE section collisions While pfn_to_online_page() is able to determine pfn_valid() at subsection granularity it is not able to reliably determine if a given pfn is also online if the section is mixes ZONE_{NORMAL,MOVABLE} with ZONE_DEVICE. This means that pfn_to_online_page() may return invalid @page objects. For example with a memory map like: 100000000-1fbffffff : System RAM 142000000-143002e16 : Kernel code 143200000-143713fff : Kernel rodata 143800000-143b15b7f : Kernel data 144227000-144ffffff : Kernel bss 1fc000000-2fbffffff : Persistent Memory (legacy) 1fc000000-2fbffffff : namespace0.0 This command: echo 0x1fc000000 > /sys/devices/system/memory/soft_offline_page ...succeeds when it should fail. When it succeeds it touches an uninitialized page and may crash or cause other damage (see dissolve_free_huge_page()). While the memory map above is contrived via the memmap=ss!nn kernel command line option, the collision happens in practice on shipping platforms. The memory controller resources that decode spans of physical address space are a limited resource. One technique platform-firmware uses to conserve those resources is to share a decoder across 2 devices to keep the address range contiguous. Unfortunately the unit of operation of a decoder is 64MiB while the Linux section size is 128MiB. This results in situations where, without subsection hotplug memory mappings with different lifetimes collide into one object that can only express one lifetime. Update move_pfn_range_to_zone() to flag (SECTION_TAINT_ZONE_DEVICE) a section that mixes ZONE_DEVICE pfns with other online pfns. With SECTION_TAINT_ZONE_DEVICE to delineate, pfn_to_online_page() can fall back to a slow-path check for ZONE_DEVICE pfns in an online section. In the fast path online_section() for a full ZONE_DEVICE section returns false. Because the collision case is rare, and for simplicity, the SECTION_TAINT_ZONE_DEVICE flag is never cleared once set. [dan.j.williams@intel.com: fix CONFIG_ZONE_DEVICE=n build] Link: https://lkml.kernel.org/r/CAPcyv4iX+7LAgAeSqx7Zw-Zd=ZV9gBv8Bo7oTbwCOOqJoZ3+Yg@mail.gmail.com Link: https://lkml.kernel.org/r/161058500675.1840162.7887862152161279354.stgit@dwillia2-desk3.amr.corp.intel.com Fixes: ba72b4c8cf60 ("mm/sparsemem: support sub-section hotplug") Signed-off-by: Dan Williams Reported-by: Michal Hocko Acked-by: Michal Hocko Reported-by: David Hildenbrand Reviewed-by: David Hildenbrand Reviewed-by: Oscar Salvador Cc: Naoya Horiguchi Cc: Qian Cai Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 34 +++++++++++++++++++++++++++------- mm/memory_hotplug.c | 38 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 65 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 5f9c4dad73ed..47946cec7584 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -918,6 +918,18 @@ static inline int local_memory_node(int node_id) { return node_id; }; */ #define zone_idx(zone) ((zone) - (zone)->zone_pgdat->node_zones) +#ifdef CONFIG_ZONE_DEVICE +static inline bool zone_is_zone_device(struct zone *zone) +{ + return zone_idx(zone) == ZONE_DEVICE; +} +#else +static inline bool zone_is_zone_device(struct zone *zone) +{ + return false; +} +#endif + /* * Returns true if a zone has pages managed by the buddy allocator. * All the reclaim decisions have to use this function rather than @@ -1306,13 +1318,14 @@ extern size_t mem_section_usage_size(void); * which results in PFN_SECTION_SHIFT equal 6. * To sum it up, at least 6 bits are available. */ -#define SECTION_MARKED_PRESENT (1UL<<0) -#define SECTION_HAS_MEM_MAP (1UL<<1) -#define SECTION_IS_ONLINE (1UL<<2) -#define SECTION_IS_EARLY (1UL<<3) -#define SECTION_MAP_LAST_BIT (1UL<<4) -#define SECTION_MAP_MASK (~(SECTION_MAP_LAST_BIT-1)) -#define SECTION_NID_SHIFT 3 +#define SECTION_MARKED_PRESENT (1UL<<0) +#define SECTION_HAS_MEM_MAP (1UL<<1) +#define SECTION_IS_ONLINE (1UL<<2) +#define SECTION_IS_EARLY (1UL<<3) +#define SECTION_TAINT_ZONE_DEVICE (1UL<<4) +#define SECTION_MAP_LAST_BIT (1UL<<5) +#define SECTION_MAP_MASK (~(SECTION_MAP_LAST_BIT-1)) +#define SECTION_NID_SHIFT 3 static inline struct page *__section_mem_map_addr(struct mem_section *section) { @@ -1351,6 +1364,13 @@ static inline int online_section(struct mem_section *section) return (section && (section->section_mem_map & SECTION_IS_ONLINE)); } +static inline int online_device_section(struct mem_section *section) +{ + unsigned long flags = SECTION_IS_ONLINE | SECTION_TAINT_ZONE_DEVICE; + + return section && ((section->section_mem_map & flags) == flags); +} + static inline int online_section_nr(unsigned long nr) { return online_section(__nr_to_section(nr)); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 02378f11e2d6..3af4d3851d1a 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -308,6 +308,7 @@ static int check_hotplug_memory_addressable(unsigned long pfn, struct page *pfn_to_online_page(unsigned long pfn) { unsigned long nr = pfn_to_section_nr(pfn); + struct dev_pagemap *pgmap; struct mem_section *ms; if (nr >= NR_MEM_SECTIONS) @@ -327,6 +328,22 @@ struct page *pfn_to_online_page(unsigned long pfn) if (!pfn_section_valid(ms, pfn)) return NULL; + if (!online_device_section(ms)) + return pfn_to_page(pfn); + + /* + * Slowpath: when ZONE_DEVICE collides with + * ZONE_{NORMAL,MOVABLE} within the same section some pfns in + * the section may be 'offline' but 'valid'. Only + * get_dev_pagemap() can determine sub-section online status. + */ + pgmap = get_dev_pagemap(pfn, NULL); + put_dev_pagemap(pgmap); + + /* The presence of a pgmap indicates ZONE_DEVICE offline pfn */ + if (pgmap) + return NULL; + return pfn_to_page(pfn); } EXPORT_SYMBOL_GPL(pfn_to_online_page); @@ -709,6 +726,14 @@ static void __meminit resize_pgdat_range(struct pglist_data *pgdat, unsigned lon pgdat->node_spanned_pages = max(start_pfn + nr_pages, old_end_pfn) - pgdat->node_start_pfn; } + +static void section_taint_zone_device(unsigned long pfn) +{ + struct mem_section *ms = __pfn_to_section(pfn); + + ms->section_mem_map |= SECTION_TAINT_ZONE_DEVICE; +} + /* * Associate the pfn range with the given zone, initializing the memmaps * and resizing the pgdat/zone data to span the added pages. After this @@ -738,6 +763,19 @@ void __ref move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn, resize_pgdat_range(pgdat, start_pfn, nr_pages); pgdat_resize_unlock(pgdat, &flags); + /* + * Subsection population requires care in pfn_to_online_page(). + * Set the taint to enable the slow path detection of + * ZONE_DEVICE pages in an otherwise ZONE_{NORMAL,MOVABLE} + * section. + */ + if (zone_is_zone_device(zone)) { + if (!IS_ALIGNED(start_pfn, PAGES_PER_SECTION)) + section_taint_zone_device(start_pfn); + if (!IS_ALIGNED(start_pfn + nr_pages, PAGES_PER_SECTION)) + section_taint_zone_device(start_pfn + nr_pages); + } + /* * TODO now we have a visible range of pages which are not associated * with their zone properly. Not nice but set_pfnblock_flags_mask -- cgit v1.2.3 From 34dc45be4563f344d59ba0428416d0d265aa4f4d Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 25 Feb 2021 17:17:08 -0800 Subject: mm: fix memory_failure() handling of dax-namespace metadata Given 'struct dev_pagemap' spans both data pages and metadata pages be careful to consult the altmap if present to delineate metadata. In fact the pfn_first() helper already identifies the first valid data pfn, so export that helper for other code paths via pgmap_pfn_valid(). Other usage of get_dev_pagemap() are not a concern because those are operating on known data pfns having been looked up by get_user_pages(). I.e. metadata pfns are never user mapped. Link: https://lkml.kernel.org/r/161058501758.1840162.4239831989762604527.stgit@dwillia2-desk3.amr.corp.intel.com Fixes: 6100e34b2526 ("mm, memory_failure: Teach memory_failure() about dev_pagemap pages") Signed-off-by: Dan Williams Reported-by: David Hildenbrand Reviewed-by: David Hildenbrand Reviewed-by: Naoya Horiguchi Cc: Michal Hocko Cc: Oscar Salvador Cc: Qian Cai Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memremap.h | 6 ++++++ mm/memory-failure.c | 6 ++++++ mm/memremap.c | 15 +++++++++++++++ 3 files changed, 27 insertions(+) (limited to 'include') diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 79c49e7f5c30..f5b464daeeca 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -137,6 +137,7 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap); void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap); struct dev_pagemap *get_dev_pagemap(unsigned long pfn, struct dev_pagemap *pgmap); +bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn); unsigned long vmem_altmap_offset(struct vmem_altmap *altmap); void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns); @@ -165,6 +166,11 @@ static inline struct dev_pagemap *get_dev_pagemap(unsigned long pfn, return NULL; } +static inline bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn) +{ + return false; +} + static inline unsigned long vmem_altmap_offset(struct vmem_altmap *altmap) { return 0; diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 55c671904aac..24210c9bd843 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1312,6 +1312,12 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags, */ put_page(page); + /* device metadata space is not recoverable */ + if (!pgmap_pfn_valid(pgmap, pfn)) { + rc = -ENXIO; + goto out; + } + /* * Prevent the inode from being freed while we are interrogating * the address_space, typically this would be handled by diff --git a/mm/memremap.c b/mm/memremap.c index 16b2fb482da1..2455bac89506 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -80,6 +80,21 @@ static unsigned long pfn_first(struct dev_pagemap *pgmap, int range_id) return pfn + vmem_altmap_offset(pgmap_altmap(pgmap)); } +bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn) +{ + int i; + + for (i = 0; i < pgmap->nr_range; i++) { + struct range *range = &pgmap->ranges[i]; + + if (pfn >= PHYS_PFN(range->start) && + pfn <= PHYS_PFN(range->end)) + return pfn >= pfn_first(pgmap, i); + } + + return false; +} + static unsigned long pfn_end(struct dev_pagemap *pgmap, int range_id) { const struct range *range = &pgmap->ranges[range_id]; -- cgit v1.2.3 From 1adf8b468ff6bc64ba01ce3848da4bcf409215b4 Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Thu, 25 Feb 2021 17:17:13 -0800 Subject: mm/memory_hotplug: rename all existing 'memhp' into 'mhp' This renames all 'memhp' instances to 'mhp' except for memhp_default_state for being a kernel command line option. This is just a clean up and should not cause a functional change. Let's make it consistent rater than mixing the two prefixes. In preparation for more users of the 'mhp' terminology. Link: https://lkml.kernel.org/r/1611554093-27316-1-git-send-email-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual Suggested-by: David Hildenbrand Reviewed-by: David Hildenbrand Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/memory.c | 10 +++++----- include/linux/memory_hotplug.h | 4 ++-- mm/memory_hotplug.c | 12 ++++++------ 3 files changed, 13 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/drivers/base/memory.c b/drivers/base/memory.c index eef4ffb6122c..901e379676be 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -35,7 +35,7 @@ static const char *const online_type_to_str[] = { [MMOP_ONLINE_MOVABLE] = "online_movable", }; -int memhp_online_type_from_str(const char *str) +int mhp_online_type_from_str(const char *str) { int i; @@ -253,7 +253,7 @@ static int memory_subsys_offline(struct device *dev) static ssize_t state_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - const int online_type = memhp_online_type_from_str(buf); + const int online_type = mhp_online_type_from_str(buf); struct memory_block *mem = to_memory_block(dev); int ret; @@ -387,19 +387,19 @@ static ssize_t auto_online_blocks_show(struct device *dev, struct device_attribute *attr, char *buf) { return sysfs_emit(buf, "%s\n", - online_type_to_str[memhp_default_online_type]); + online_type_to_str[mhp_default_online_type]); } static ssize_t auto_online_blocks_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - const int online_type = memhp_online_type_from_str(buf); + const int online_type = mhp_online_type_from_str(buf); if (online_type < 0) return -EINVAL; - memhp_default_online_type = online_type; + mhp_default_online_type = online_type; return count; } diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 3d99de0db2dd..ca5e8d137726 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -116,10 +116,10 @@ extern int arch_add_memory(int nid, u64 start, u64 size, struct mhp_params *params); extern u64 max_mem_size; -extern int memhp_online_type_from_str(const char *str); +extern int mhp_online_type_from_str(const char *str); /* Default online_type (MMOP_*) when new memory blocks are added. */ -extern int memhp_default_online_type; +extern int mhp_default_online_type; /* If movable_node boot option specified */ extern bool movable_node_enabled; static inline bool movable_node_is_enabled(void) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 3af4d3851d1a..ac1c686a5989 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -67,17 +67,17 @@ void put_online_mems(void) bool movable_node_enabled = false; #ifndef CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE -int memhp_default_online_type = MMOP_OFFLINE; +int mhp_default_online_type = MMOP_OFFLINE; #else -int memhp_default_online_type = MMOP_ONLINE; +int mhp_default_online_type = MMOP_ONLINE; #endif static int __init setup_memhp_default_state(char *str) { - const int online_type = memhp_online_type_from_str(str); + const int online_type = mhp_online_type_from_str(str); if (online_type >= 0) - memhp_default_online_type = online_type; + mhp_default_online_type = online_type; return 1; } @@ -1076,7 +1076,7 @@ static int check_hotplug_memory_range(u64 start, u64 size) static int online_memory_block(struct memory_block *mem, void *arg) { - mem->online_type = memhp_default_online_type; + mem->online_type = mhp_default_online_type; return device_online(&mem->dev); } @@ -1157,7 +1157,7 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) merge_system_ram_resource(res); /* online pages if requested */ - if (memhp_default_online_type != MMOP_OFFLINE) + if (mhp_default_online_type != MMOP_OFFLINE) walk_memory_blocks(start, size, NULL, online_memory_block); return ret; -- cgit v1.2.3 From 26011267e1a7ddaab50b5f81b402ca3e7fc2887c Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 25 Feb 2021 17:17:17 -0800 Subject: mm/memory_hotplug: MEMHP_MERGE_RESOURCE -> MHP_MERGE_RESOURCE Let's make "MEMHP_MERGE_RESOURCE" consistent with "MHP_NONE", "mhp_t" and "mhp_flags". As discussed recently [1], "mhp" is our internal acronym for memory hotplug now. [1] https://lore.kernel.org/linux-mm/c37de2d0-28a1-4f7d-f944-cfd7d81c334d@redhat.com/ Link: https://lkml.kernel.org/r/20210126115829.10909-1-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Miaohe Lin Acked-by: Michael S. Tsirkin Reviewed-by: Oscar Salvador Acked-by: Wei Liu Reviewed-by: Pankaj Gupta Cc: "K. Y. Srinivasan" Cc: Haiyang Zhang Cc: Stephen Hemminger Cc: Jason Wang Cc: Boris Ostrovsky Cc: Juergen Gross Cc: Stefano Stabellini Cc: Michal Hocko Cc: Anshuman Khandual Cc: Wei Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/hv/hv_balloon.c | 2 +- drivers/virtio/virtio_mem.c | 2 +- drivers/xen/balloon.c | 2 +- include/linux/memory_hotplug.h | 2 +- mm/memory_hotplug.c | 2 +- 5 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c index 8c471823a5af..2f776d78e3c1 100644 --- a/drivers/hv/hv_balloon.c +++ b/drivers/hv/hv_balloon.c @@ -726,7 +726,7 @@ static void hv_mem_hot_add(unsigned long start, unsigned long size, nid = memory_add_physaddr_to_nid(PFN_PHYS(start_pfn)); ret = add_memory(nid, PFN_PHYS((start_pfn)), - (HA_CHUNK << PAGE_SHIFT), MEMHP_MERGE_RESOURCE); + (HA_CHUNK << PAGE_SHIFT), MHP_MERGE_RESOURCE); if (ret) { pr_err("hot_add memory failed error is %d\n", ret); diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c index 9fc9ec4a25f5..d44e43869f17 100644 --- a/drivers/virtio/virtio_mem.c +++ b/drivers/virtio/virtio_mem.c @@ -623,7 +623,7 @@ static int virtio_mem_add_memory(struct virtio_mem *vm, uint64_t addr, /* Memory might get onlined immediately. */ atomic64_add(size, &vm->offline_size); rc = add_memory_driver_managed(vm->nid, addr, size, vm->resource_name, - MEMHP_MERGE_RESOURCE); + MHP_MERGE_RESOURCE); if (rc) { atomic64_sub(size, &vm->offline_size); dev_warn(&vm->vdev->dev, "adding memory failed: %d\n", rc); diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index b57b2067ecbf..671c71245a7b 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -331,7 +331,7 @@ static enum bp_state reserve_additional_memory(void) mutex_unlock(&balloon_mutex); /* add_memory_resource() requires the device_hotplug lock */ lock_device_hotplug(); - rc = add_memory_resource(nid, resource, MEMHP_MERGE_RESOURCE); + rc = add_memory_resource(nid, resource, MHP_MERGE_RESOURCE); unlock_device_hotplug(); mutex_lock(&balloon_mutex); diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index ca5e8d137726..08eeef679ab7 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -53,7 +53,7 @@ typedef int __bitwise mhp_t; * with this flag set, the resource pointer must no longer be used as it * might be stale, or the resource might have changed. */ -#define MEMHP_MERGE_RESOURCE ((__force mhp_t)BIT(0)) +#define MHP_MERGE_RESOURCE ((__force mhp_t)BIT(0)) /* * Extended parameters for memory hotplug: diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index ac1c686a5989..6a02c3f42717 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1153,7 +1153,7 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) * In case we're allowed to merge the resource, flag it and trigger * merging now that adding succeeded. */ - if (mhp_flags & MEMHP_MERGE_RESOURCE) + if (mhp_flags & MHP_MERGE_RESOURCE) merge_system_ram_resource(res); /* online pages if requested */ -- cgit v1.2.3 From e9a2e48e8704c9d20a625c6f2357147d03ea7b97 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 25 Feb 2021 17:17:24 -0800 Subject: drivers/base/memory: don't store phys_device in memory blocks No need to store the value for each and every memory block, as we can easily query the value at runtime. Reshuffle the members to optimize the memory layout. Also, let's clarify what the interface once was used for and why it's legacy nowadays. "phys_device" was used on s390x in older versions of lsmem[2]/chmem[3], back when they were still part of s390x-tools. They were later replaced by the variants in linux-utils. For example, RHEL6 and RHEL7 contain lsmem/chmem from s390-utils. RHEL8 switched to versions from util-linux on s390x [4]. "phys_device" was added with sysfs support for memory hotplug in commit 3947be1969a9 ("[PATCH] memory hotplug: sysfs and add/remove functions") in 2005. It always returned 0. s390x started returning something != 0 on some setups (if sclp.rzm is set by HW) in 2010 via commit 57b552ba0b2f ("memory hotplug/s390: set phys_device"). For s390x, it allowed for identifying which memory block devices belong to the same storage increment (RZM). Only if all memory block devices comprising a single storage increment were offline, the memory could actually be removed in the hypervisor. Since commit e5d709bb5fb7 ("s390/memory hotplug: provide memory_block_size_bytes() function") in 2013 a memory block device spans at least one storage increment - which is why the interface isn't really helpful/used anymore (except by old lsmem/chmem tools). There were once RFC patches to make use of "phys_device" in ACPI context; however, the underlying problem could be solved using different interfaces [1]. [1] https://patchwork.kernel.org/patch/2163871/ [2] https://github.com/ibm-s390-tools/s390-tools/blob/v2.1.0/zconf/lsmem [3] https://github.com/ibm-s390-tools/s390-tools/blob/v2.1.0/zconf/chmem [4] https://bugzilla.redhat.com/show_bug.cgi?id=1504134 Link: https://lkml.kernel.org/r/20210201181347.13262-2-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Michal Hocko Reviewed-by: Oscar Salvador Cc: Dave Hansen Cc: Greg Kroah-Hartman Cc: Gerald Schaefer Cc: Jonathan Corbet Cc: "Rafael J. Wysocki" Cc: Mauro Carvalho Chehab Cc: Ilya Dryomov Cc: Vaibhav Jain Cc: Tom Rix Cc: Geert Uytterhoeven Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/ABI/testing/sysfs-devices-memory | 5 +++-- Documentation/admin-guide/mm/memory-hotplug.rst | 4 ++-- drivers/base/memory.c | 25 +++++++++---------------- include/linux/memory.h | 3 +-- 4 files changed, 15 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/Documentation/ABI/testing/sysfs-devices-memory b/Documentation/ABI/testing/sysfs-devices-memory index 246a45b96d22..58dbc592bc57 100644 --- a/Documentation/ABI/testing/sysfs-devices-memory +++ b/Documentation/ABI/testing/sysfs-devices-memory @@ -26,8 +26,9 @@ Date: September 2008 Contact: Badari Pulavarty Description: The file /sys/devices/system/memory/memoryX/phys_device - is read-only and is designed to show the name of physical - memory device. Implementation is currently incomplete. + is read-only; it is a legacy interface only ever used on s390x + to expose the covered storage increment. +Users: Legacy s390-tools lsmem/chmem What: /sys/devices/system/memory/memoryX/phys_index Date: September 2008 diff --git a/Documentation/admin-guide/mm/memory-hotplug.rst b/Documentation/admin-guide/mm/memory-hotplug.rst index 5c4432c96c4b..245739f55ac7 100644 --- a/Documentation/admin-guide/mm/memory-hotplug.rst +++ b/Documentation/admin-guide/mm/memory-hotplug.rst @@ -160,8 +160,8 @@ Under each memory block, you can see 5 files: "online_movable", "online", "offline" command which will be performed on all sections in the block. -``phys_device`` read-only: designed to show the name of physical memory - device. This is not well implemented now. +``phys_device`` read-only: legacy interface only ever used on s390x to + expose the covered storage increment. ``removable`` read-only: contains an integer value indicating whether the memory block is removable or not removable. A value of 1 indicates that the memory diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 901e379676be..f35298425575 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -290,20 +290,20 @@ static ssize_t state_store(struct device *dev, struct device_attribute *attr, } /* - * phys_device is a bad name for this. What I really want - * is a way to differentiate between memory ranges that - * are part of physical devices that constitute - * a complete removable unit or fru. - * i.e. do these ranges belong to the same physical device, - * s.t. if I offline all of these sections I can then - * remove the physical device? + * Legacy interface that we cannot remove: s390x exposes the storage increment + * covered by a memory block, allowing for identifying which memory blocks + * comprise a storage increment. Since a memory block spans complete + * storage increments nowadays, this interface is basically unused. Other + * archs never exposed != 0. */ static ssize_t phys_device_show(struct device *dev, struct device_attribute *attr, char *buf) { struct memory_block *mem = to_memory_block(dev); + unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr); - return sysfs_emit(buf, "%d\n", mem->phys_device); + return sysfs_emit(buf, "%d\n", + arch_get_memory_phys_device(start_pfn)); } #ifdef CONFIG_MEMORY_HOTREMOVE @@ -488,11 +488,7 @@ static DEVICE_ATTR_WO(soft_offline_page); static DEVICE_ATTR_WO(hard_offline_page); #endif -/* - * Note that phys_device is optional. It is here to allow for - * differentiation between which *physical* devices each - * section belongs to... - */ +/* See phys_device_show(). */ int __weak arch_get_memory_phys_device(unsigned long start_pfn) { return 0; @@ -574,7 +570,6 @@ int register_memory(struct memory_block *memory) static int init_memory_block(unsigned long block_id, unsigned long state) { struct memory_block *mem; - unsigned long start_pfn; int ret = 0; mem = find_memory_block_by_id(block_id); @@ -588,8 +583,6 @@ static int init_memory_block(unsigned long block_id, unsigned long state) mem->start_section_nr = block_id * sections_per_block; mem->state = state; - start_pfn = section_nr_to_pfn(mem->start_section_nr); - mem->phys_device = arch_get_memory_phys_device(start_pfn); mem->nid = NUMA_NO_NODE; ret = register_memory(mem); diff --git a/include/linux/memory.h b/include/linux/memory.h index 439a89e758d8..4da95e684e20 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -27,9 +27,8 @@ struct memory_block { unsigned long start_section_nr; unsigned long state; /* serialized by the dev->lock */ int online_type; /* for passing data to online routine */ - int phys_device; /* to which fru does this belong? */ - struct device dev; int nid; /* NID for this memory block */ + struct device dev; }; int arch_get_memory_phys_device(unsigned long start_pfn); -- cgit v1.2.3 From bca3feaa0764ab5a4cbe6817871601f1d00c059d Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Thu, 25 Feb 2021 17:17:33 -0800 Subject: mm/memory_hotplug: prevalidate the address range being added with platform Patch series "mm/memory_hotplug: Pre-validate the address range with platform", v5. This series adds a mechanism allowing platforms to weigh in and prevalidate incoming address range before proceeding further with the memory hotplug. This helps prevent potential platform errors for the given address range, down the hotplug call chain, which inevitably fails the hotplug itself. This mechanism was suggested by David Hildenbrand during another discussion with respect to a memory hotplug fix on arm64 platform. https://lore.kernel.org/linux-arm-kernel/1600332402-30123-1-git-send-email-anshuman.khandual@arm.com/ This mechanism focuses on the addressibility aspect and not [sub] section alignment aspect. Hence check_hotplug_memory_range() and check_pfn_span() have been left unchanged. This patch (of 4): This introduces mhp_range_allowed() which can be called in various memory hotplug paths to prevalidate the address range which is being added, with the platform. Then mhp_range_allowed() calls mhp_get_pluggable_range() which provides applicable address range depending on whether linear mapping is required or not. For ranges that require linear mapping, it calls a new arch callback arch_get_mappable_range() which the platform can override. So the new callback, in turn provides the platform an opportunity to configure acceptable memory hotplug address ranges in case there are constraints. This mechanism will help prevent platform specific errors deep down during hotplug calls. This drops now redundant check_hotplug_memory_addressable() check in __add_pages() but instead adds a VM_BUG_ON() check which would ensure that the range has been validated with mhp_range_allowed() earlier in the call chain. Besides mhp_get_pluggable_range() also can be used by potential memory hotplug callers to avail the allowed physical range which would go through on a given platform. This does not really add any new range check in generic memory hotplug but instead compensates for lost checks in arch_add_memory() where applicable and check_hotplug_memory_addressable(), with unified mhp_range_allowed(). [akpm@linux-foundation.org: make pagemap_range() return -EINVAL when mhp_range_allowed() fails] Link: https://lkml.kernel.org/r/1612149902-7867-1-git-send-email-anshuman.khandual@arm.com Link: https://lkml.kernel.org/r/1612149902-7867-2-git-send-email-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual Suggested-by: David Hildenbrand Reviewed-by: David Hildenbrand Reviewed-by: Oscar Salvador Cc: Heiko Carstens Cc: Catalin Marinas Cc: Vasily Gorbik # s390 Cc: Will Deacon Cc: Ard Biesheuvel Cc: Mark Rutland Cc: Jason Wang Cc: Jonathan Cameron Cc: "Michael S. Tsirkin" Cc: Michal Hocko Cc: Pankaj Gupta Cc: Pankaj Gupta Cc: teawater Cc: Wei Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 10 ++++++ mm/memory_hotplug.c | 78 ++++++++++++++++++++++++++++++++---------- mm/memremap.c | 8 ++++- 3 files changed, 76 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 08eeef679ab7..7288aa5ef73b 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -66,6 +66,9 @@ struct mhp_params { pgprot_t pgprot; }; +bool mhp_range_allowed(u64 start, u64 size, bool need_mapping); +struct range mhp_get_pluggable_range(bool need_mapping); + /* * Zone resizing functions * @@ -266,6 +269,13 @@ static inline bool movable_node_is_enabled(void) } #endif /* ! CONFIG_MEMORY_HOTPLUG */ +/* + * Keep this declaration outside CONFIG_MEMORY_HOTPLUG as some + * platforms might override and use arch_get_mappable_range() + * for internal non memory hotplug purposes. + */ +struct range arch_get_mappable_range(void); + #if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT) /* * pgdat resizing functions diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index a969463bdda4..5ba51a8bdaeb 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -107,6 +107,9 @@ static struct resource *register_memory_resource(u64 start, u64 size, if (strcmp(resource_name, "System RAM")) flags |= IORESOURCE_SYSRAM_DRIVER_MANAGED; + if (!mhp_range_allowed(start, size, true)) + return ERR_PTR(-E2BIG); + /* * Make sure value parsed from 'mem=' only restricts memory adding * while booting, so that memory hotplug won't be impacted. Please @@ -284,22 +287,6 @@ static int check_pfn_span(unsigned long pfn, unsigned long nr_pages, return 0; } -static int check_hotplug_memory_addressable(unsigned long pfn, - unsigned long nr_pages) -{ - const u64 max_addr = PFN_PHYS(pfn + nr_pages) - 1; - - if (max_addr >> MAX_PHYSMEM_BITS) { - const u64 max_allowed = (1ull << (MAX_PHYSMEM_BITS + 1)) - 1; - WARN(1, - "Hotplugged memory exceeds maximum addressable address, range=%#llx-%#llx, maximum=%#llx\n", - (u64)PFN_PHYS(pfn), max_addr, max_allowed); - return -E2BIG; - } - - return 0; -} - /* * Return page for the valid pfn only if the page is online. All pfn * walkers which rely on the fully initialized page->flags and others @@ -365,9 +352,7 @@ int __ref __add_pages(int nid, unsigned long pfn, unsigned long nr_pages, if (WARN_ON_ONCE(!params->pgprot.pgprot)) return -EINVAL; - err = check_hotplug_memory_addressable(pfn, nr_pages); - if (err) - return err; + VM_BUG_ON(!mhp_range_allowed(PFN_PHYS(pfn), nr_pages * PAGE_SIZE, false)); if (altmap) { /* @@ -1248,6 +1233,61 @@ out_unlock: } EXPORT_SYMBOL_GPL(add_memory_driver_managed); +/* + * Platforms should define arch_get_mappable_range() that provides + * maximum possible addressable physical memory range for which the + * linear mapping could be created. The platform returned address + * range must adhere to these following semantics. + * + * - range.start <= range.end + * - Range includes both end points [range.start..range.end] + * + * There is also a fallback definition provided here, allowing the + * entire possible physical address range in case any platform does + * not define arch_get_mappable_range(). + */ +struct range __weak arch_get_mappable_range(void) +{ + struct range mhp_range = { + .start = 0UL, + .end = -1ULL, + }; + return mhp_range; +} + +struct range mhp_get_pluggable_range(bool need_mapping) +{ + const u64 max_phys = (1ULL << MAX_PHYSMEM_BITS) - 1; + struct range mhp_range; + + if (need_mapping) { + mhp_range = arch_get_mappable_range(); + if (mhp_range.start > max_phys) { + mhp_range.start = 0; + mhp_range.end = 0; + } + mhp_range.end = min_t(u64, mhp_range.end, max_phys); + } else { + mhp_range.start = 0; + mhp_range.end = max_phys; + } + return mhp_range; +} +EXPORT_SYMBOL_GPL(mhp_get_pluggable_range); + +bool mhp_range_allowed(u64 start, u64 size, bool need_mapping) +{ + struct range mhp_range = mhp_get_pluggable_range(need_mapping); + u64 end = start + size; + + if (start < end && start >= mhp_range.start && (end - 1) <= mhp_range.end) + return true; + + pr_warn("Hotplug memory [%#llx-%#llx] exceeds maximum addressable range [%#llx-%#llx]\n", + start, end, mhp_range.start, mhp_range.end); + return false; +} + #ifdef CONFIG_MEMORY_HOTREMOVE /* * Confirm all pages in a range [start, end) belong to the same zone (skipping diff --git a/mm/memremap.c b/mm/memremap.c index 2455bac89506..7aa7d6e80ee5 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -200,6 +200,7 @@ static void dev_pagemap_percpu_release(struct percpu_ref *ref) static int pagemap_range(struct dev_pagemap *pgmap, struct mhp_params *params, int range_id, int nid) { + const bool is_private = pgmap->type == MEMORY_DEVICE_PRIVATE; struct range *range = &pgmap->ranges[range_id]; struct dev_pagemap *conflict_pgmap; int error, is_ram; @@ -245,6 +246,11 @@ static int pagemap_range(struct dev_pagemap *pgmap, struct mhp_params *params, if (error) goto err_pfn_remap; + if (!mhp_range_allowed(range->start, range_len(range), !is_private)) { + error = -EINVAL; + goto err_pfn_remap; + } + mem_hotplug_begin(); /* @@ -258,7 +264,7 @@ static int pagemap_range(struct dev_pagemap *pgmap, struct mhp_params *params, * the CPU, we do want the linear mapping and thus use * arch_add_memory(). */ - if (pgmap->type == MEMORY_DEVICE_PRIVATE) { + if (is_private) { error = add_pages(nid, PHYS_PFN(range->start), PHYS_PFN(range_len(range)), params); } else { -- cgit v1.2.3 From 5d5d19eda6b0ee790af89c45e3f678345be6f50f Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Thu, 25 Feb 2021 17:18:09 -0800 Subject: mm/rmap: fix potential pte_unmap on an not mapped pte For PMD-mapped page (usually THP), pvmw->pte is NULL. For PTE-mapped THP, pvmw->pte is mapped. But for HugeTLB pages, pvmw->pte is not mapped and set to the relevant page table entry. So in page_vma_mapped_walk_done(), we may do pte_unmap() for HugeTLB pte which is not mapped. Fix this by checking pvmw->page against PageHuge before trying to do pte_unmap(). Link: https://lkml.kernel.org/r/20210127093349.39081-1-linmiaohe@huawei.com Fixes: ace71a19cec5 ("mm: introduce page_vma_mapped_walk()") Signed-off-by: Hongxiang Lou Signed-off-by: Miaohe Lin Tested-by: Sedat Dilek Cc: Kees Cook Cc: Nathan Chancellor Cc: Mike Kravetz Cc: Shakeel Butt Cc: Johannes Weiner Cc: Vlastimil Babka Cc: Michel Lespinasse Cc: Nick Desaulniers Cc: "Kirill A. Shutemov" Cc: Wei Yang Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: Brian Geffon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rmap.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 70085ca1a3fc..def5c62c93b3 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -213,7 +213,8 @@ struct page_vma_mapped_walk { static inline void page_vma_mapped_walk_done(struct page_vma_mapped_walk *pvmw) { - if (pvmw->pte) + /* HugeTLB pte is set to the relevant page table entry without pte_mapped. */ + if (pvmw->pte && !PageHuge(pvmw->page)) pte_unmap(pvmw->pte); if (pvmw->ptl) spin_unlock(pvmw->ptl); -- cgit v1.2.3 From fc6697a89f56d9773b2fbff718d4cf2a6d63379d Mon Sep 17 00:00:00 2001 From: Tian Tao Date: Thu, 25 Feb 2021 17:18:17 -0800 Subject: mm/zswap: add the flag can_sleep_mapped Patch series "Fix the compatibility of zsmalloc and zswap". Patch #1 adds a flag to zpool, then zswap used to determine if zpool drivers such as zbud/z3fold/zsmalloc will enter an atomic context after mapping. The difference between zbud/z3fold and zsmalloc is that zsmalloc requires an atomic context that since its map function holds a preempt-disabled, but zbud/z3fold don't require an atomic context. So patch #2 sets flag sleep_mapped to true indicating that zbud/z3fold can sleep after mapping. zsmalloc didn't support sleep after mapping, so don't set that flag to true. This patch (of 2): Add a flag to zpool, named is "can_sleep_mapped", and have it set true for zbud/z3fold, not set this flag for zsmalloc, so its default value is false. Then zswap could go the current path if the flag is true; and if it's false, copy data from src to a temporary buffer, then unmap the handle, take the mutex, process the buffer instead of src to avoid sleeping function called from atomic context. [natechancellor@gmail.com: add return value in zswap_frontswap_load] Link: https://lkml.kernel.org/r/20210121214804.926843-1-natechancellor@gmail.com [tiantao6@hisilicon.com: fix potential memory leak] Link: https://lkml.kernel.org/r/1611538365-51811-1-git-send-email-tiantao6@hisilicon.com [colin.king@canonical.com: fix potential uninitialized pointer read on tmp] Link: https://lkml.kernel.org/r/20210128141728.639030-1-colin.king@canonical.com [tiantao6@hisilicon.com: fix variable 'entry' is uninitialized when used] Link: https://lkml.kernel.org/r/1611223030-58346-1-git-send-email-tiantao6@hisilicon.comLink: https://lkml.kernel.org/r/1611035683-12732-1-git-send-email-tiantao6@hisilicon.com Link: https://lkml.kernel.org/r/1611035683-12732-2-git-send-email-tiantao6@hisilicon.com Signed-off-by: Tian Tao Signed-off-by: Nathan Chancellor Signed-off-by: Colin Ian King Reviewed-by: Vitaly Wool Acked-by: Sebastian Andrzej Siewior Reported-by: Mike Galbraith Cc: Barry Song Cc: Dan Streetman Cc: Seth Jennings Cc: Dan Carpenter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/zpool.h | 3 +++ mm/zpool.c | 13 +++++++++++++ mm/zswap.c | 51 ++++++++++++++++++++++++++++++++++++++++++++++----- 3 files changed, 62 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/zpool.h b/include/linux/zpool.h index 51bf43076165..e8997010612a 100644 --- a/include/linux/zpool.h +++ b/include/linux/zpool.h @@ -73,6 +73,7 @@ u64 zpool_get_total_size(struct zpool *pool); * @malloc: allocate mem from a pool. * @free: free mem from a pool. * @shrink: shrink the pool. + * @sleep_mapped: whether zpool driver can sleep during map. * @map: map a handle. * @unmap: unmap a handle. * @total_size: get total size of a pool. @@ -100,6 +101,7 @@ struct zpool_driver { int (*shrink)(void *pool, unsigned int pages, unsigned int *reclaimed); + bool sleep_mapped; void *(*map)(void *pool, unsigned long handle, enum zpool_mapmode mm); void (*unmap)(void *pool, unsigned long handle); @@ -112,5 +114,6 @@ void zpool_register_driver(struct zpool_driver *driver); int zpool_unregister_driver(struct zpool_driver *driver); bool zpool_evictable(struct zpool *pool); +bool zpool_can_sleep_mapped(struct zpool *pool); #endif diff --git a/mm/zpool.c b/mm/zpool.c index 3744a2d1a624..5ed71207ced7 100644 --- a/mm/zpool.c +++ b/mm/zpool.c @@ -23,6 +23,7 @@ struct zpool { void *pool; const struct zpool_ops *ops; bool evictable; + bool can_sleep_mapped; struct list_head list; }; @@ -183,6 +184,7 @@ struct zpool *zpool_create_pool(const char *type, const char *name, gfp_t gfp, zpool->pool = driver->create(name, gfp, ops, zpool); zpool->ops = ops; zpool->evictable = driver->shrink && ops && ops->evict; + zpool->can_sleep_mapped = driver->sleep_mapped; if (!zpool->pool) { pr_err("couldn't create %s pool\n", type); @@ -393,6 +395,17 @@ bool zpool_evictable(struct zpool *zpool) return zpool->evictable; } +/** + * zpool_can_sleep_mapped - Test if zpool can sleep when do mapped. + * @zpool: The zpool to test + * + * Returns: true if zpool can sleep; false otherwise. + */ +bool zpool_can_sleep_mapped(struct zpool *zpool) +{ + return zpool->can_sleep_mapped; +} + MODULE_LICENSE("GPL"); MODULE_AUTHOR("Dan Streetman "); MODULE_DESCRIPTION("Common API for compressed memory storage"); diff --git a/mm/zswap.c b/mm/zswap.c index 1e41c2857068..578d9f256920 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -935,13 +935,19 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle) struct scatterlist input, output; struct crypto_acomp_ctx *acomp_ctx; - u8 *src; + u8 *src, *tmp = NULL; unsigned int dlen; int ret; struct writeback_control wbc = { .sync_mode = WB_SYNC_NONE, }; + if (!zpool_can_sleep_mapped(pool)) { + tmp = kmalloc(PAGE_SIZE, GFP_ATOMIC); + if (!tmp) + return -ENOMEM; + } + /* extract swpentry from data */ zhdr = zpool_map_handle(pool, handle, ZPOOL_MM_RO); swpentry = zhdr->swpentry; /* here */ @@ -955,6 +961,7 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle) /* entry was invalidated */ spin_unlock(&tree->lock); zpool_unmap_handle(pool, handle); + kfree(tmp); return 0; } spin_unlock(&tree->lock); @@ -979,6 +986,14 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle) dlen = PAGE_SIZE; src = (u8 *)zhdr + sizeof(struct zswap_header); + if (!zpool_can_sleep_mapped(pool)) { + + memcpy(tmp, src, entry->length); + src = tmp; + + zpool_unmap_handle(pool, handle); + } + mutex_lock(acomp_ctx->mutex); sg_init_one(&input, src, entry->length); sg_init_table(&output, 1); @@ -1033,7 +1048,11 @@ fail: spin_unlock(&tree->lock); end: - zpool_unmap_handle(pool, handle); + if (zpool_can_sleep_mapped(pool)) + zpool_unmap_handle(pool, handle); + else + kfree(tmp); + return ret; } @@ -1235,7 +1254,7 @@ static int zswap_frontswap_load(unsigned type, pgoff_t offset, struct zswap_entry *entry; struct scatterlist input, output; struct crypto_acomp_ctx *acomp_ctx; - u8 *src, *dst; + u8 *src, *dst, *tmp; unsigned int dlen; int ret; @@ -1253,15 +1272,33 @@ static int zswap_frontswap_load(unsigned type, pgoff_t offset, dst = kmap_atomic(page); zswap_fill_page(dst, entry->value); kunmap_atomic(dst); + ret = 0; goto freeentry; } + if (!zpool_can_sleep_mapped(entry->pool->zpool)) { + + tmp = kmalloc(entry->length, GFP_ATOMIC); + if (!tmp) { + ret = -ENOMEM; + goto freeentry; + } + } + /* decompress */ dlen = PAGE_SIZE; src = zpool_map_handle(entry->pool->zpool, entry->handle, ZPOOL_MM_RO); if (zpool_evictable(entry->pool->zpool)) src += sizeof(struct zswap_header); + if (!zpool_can_sleep_mapped(entry->pool->zpool)) { + + memcpy(tmp, src, entry->length); + src = tmp; + + zpool_unmap_handle(entry->pool->zpool, entry->handle); + } + acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx); mutex_lock(acomp_ctx->mutex); sg_init_one(&input, src, entry->length); @@ -1271,7 +1308,11 @@ static int zswap_frontswap_load(unsigned type, pgoff_t offset, ret = crypto_wait_req(crypto_acomp_decompress(acomp_ctx->req), &acomp_ctx->wait); mutex_unlock(acomp_ctx->mutex); - zpool_unmap_handle(entry->pool->zpool, entry->handle); + if (zpool_can_sleep_mapped(entry->pool->zpool)) + zpool_unmap_handle(entry->pool->zpool, entry->handle); + else + kfree(tmp); + BUG_ON(ret); freeentry: @@ -1279,7 +1320,7 @@ freeentry: zswap_entry_put(tree, entry); spin_unlock(&tree->lock); - return 0; + return ret; } /* frees an entry in zswap */ -- cgit v1.2.3 From 2395928158059b8f9858365fce7713ce7fef62e4 Mon Sep 17 00:00:00 2001 From: Rokudo Yan Date: Thu, 25 Feb 2021 17:18:31 -0800 Subject: zsmalloc: account the number of compacted pages correctly There exists multiple path may do zram compaction concurrently. 1. auto-compaction triggered during memory reclaim 2. userspace utils write zram/compaction node So, multiple threads may call zs_shrinker_scan/zs_compact concurrently. But pages_compacted is a per zsmalloc pool variable and modification of the variable is not serialized(through under class->lock). There are two issues here: 1. the pages_compacted may not equal to total number of pages freed(due to concurrently add). 2. zs_shrinker_scan may not return the correct number of pages freed(issued by current shrinker). The fix is simple: 1. account the number of pages freed in zs_compact locally. 2. use actomic variable pages_compacted to accumulate total number. Link: https://lkml.kernel.org/r/20210202122235.26885-1-wu-yan@tcl.com Fixes: 860c707dca155a56 ("zsmalloc: account the number of compacted pages") Signed-off-by: Rokudo Yan Cc: Minchan Kim Cc: Sergey Senozhatsky Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/block/zram/zram_drv.c | 2 +- include/linux/zsmalloc.h | 2 +- mm/zsmalloc.c | 17 +++++++++++------ 3 files changed, 13 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index d7018543842e..a711a2e2a794 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1081,7 +1081,7 @@ static ssize_t mm_stat_show(struct device *dev, zram->limit_pages << PAGE_SHIFT, max_used << PAGE_SHIFT, (u64)atomic64_read(&zram->stats.same_pages), - pool_stats.pages_compacted, + atomic_long_read(&pool_stats.pages_compacted), (u64)atomic64_read(&zram->stats.huge_pages), (u64)atomic64_read(&zram->stats.huge_pages_since)); up_read(&zram->init_lock); diff --git a/include/linux/zsmalloc.h b/include/linux/zsmalloc.h index 4807ca4d52e0..2a430e713ce5 100644 --- a/include/linux/zsmalloc.h +++ b/include/linux/zsmalloc.h @@ -35,7 +35,7 @@ enum zs_mapmode { struct zs_pool_stats { /* How many pages were migrated (freed) */ - unsigned long pages_compacted; + atomic_long_t pages_compacted; }; struct zs_pool; diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index cf0ed0e4e911..1518732f95c3 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -2212,11 +2212,13 @@ static unsigned long zs_can_compact(struct size_class *class) return obj_wasted * class->pages_per_zspage; } -static void __zs_compact(struct zs_pool *pool, struct size_class *class) +static unsigned long __zs_compact(struct zs_pool *pool, + struct size_class *class) { struct zs_compact_control cc; struct zspage *src_zspage; struct zspage *dst_zspage = NULL; + unsigned long pages_freed = 0; spin_lock(&class->lock); while ((src_zspage = isolate_zspage(class, true))) { @@ -2246,7 +2248,7 @@ static void __zs_compact(struct zs_pool *pool, struct size_class *class) putback_zspage(class, dst_zspage); if (putback_zspage(class, src_zspage) == ZS_EMPTY) { free_zspage(pool, class, src_zspage); - pool->stats.pages_compacted += class->pages_per_zspage; + pages_freed += class->pages_per_zspage; } spin_unlock(&class->lock); cond_resched(); @@ -2257,12 +2259,15 @@ static void __zs_compact(struct zs_pool *pool, struct size_class *class) putback_zspage(class, src_zspage); spin_unlock(&class->lock); + + return pages_freed; } unsigned long zs_compact(struct zs_pool *pool) { int i; struct size_class *class; + unsigned long pages_freed = 0; for (i = ZS_SIZE_CLASSES - 1; i >= 0; i--) { class = pool->size_class[i]; @@ -2270,10 +2275,11 @@ unsigned long zs_compact(struct zs_pool *pool) continue; if (class->index != i) continue; - __zs_compact(pool, class); + pages_freed += __zs_compact(pool, class); } + atomic_long_add(pages_freed, &pool->stats.pages_compacted); - return pool->stats.pages_compacted; + return pages_freed; } EXPORT_SYMBOL_GPL(zs_compact); @@ -2290,13 +2296,12 @@ static unsigned long zs_shrinker_scan(struct shrinker *shrinker, struct zs_pool *pool = container_of(shrinker, struct zs_pool, shrinker); - pages_freed = pool->stats.pages_compacted; /* * Compact classes and calculate compaction delta. * Can run concurrently with a manually triggered * (by user) compaction. */ - pages_freed = zs_compact(pool) - pages_freed; + pages_freed = zs_compact(pool); return pages_freed ? pages_freed : SHRINK_STOP; } -- cgit v1.2.3 From 4be408cec257d1156d35647db57726f5ef977630 Mon Sep 17 00:00:00 2001 From: Guo Ren Date: Thu, 25 Feb 2021 17:18:38 -0800 Subject: mm: page-flags.h: Typo fix (It -> If) The "If" was wrongly spelled as "It". Link: https://lkml.kernel.org/r/1608959036-91409-1-git-send-email-guoren@kernel.org Signed-off-by: Guo Ren Cc: Oscar Salvador Cc: Alexander Duyck Cc: David Hildenbrand Cc: Steven Price Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index db914477057b..04a34c08e0a6 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -810,7 +810,7 @@ static inline void ClearPageSlabPfmemalloc(struct page *page) /* * Flags checked when a page is freed. Pages being freed should not have - * these flags set. It they are, there is a problem. + * these flags set. If they are, there is a problem. */ #define PAGE_FLAGS_CHECK_AT_FREE \ (1UL << PG_lru | 1UL << PG_locked | \ @@ -821,7 +821,7 @@ static inline void ClearPageSlabPfmemalloc(struct page *page) /* * Flags checked when a page is prepped for return by the page allocator. - * Pages being prepped should not have these flags set. It they are set, + * Pages being prepped should not have these flags set. If they are set, * there has been a kernel bug or struct page corruption. * * __PG_HWPOISON is exceptional because it needs to be kept beyond page's -- cgit v1.2.3 From 0ce20dd840897b12ae70869c69f1ba34d6d16965 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Thu, 25 Feb 2021 17:18:53 -0800 Subject: mm: add Kernel Electric-Fence infrastructure Patch series "KFENCE: A low-overhead sampling-based memory safety error detector", v7. This adds the Kernel Electric-Fence (KFENCE) infrastructure. KFENCE is a low-overhead sampling-based memory safety error detector of heap use-after-free, invalid-free, and out-of-bounds access errors. This series enables KFENCE for the x86 and arm64 architectures, and adds KFENCE hooks to the SLAB and SLUB allocators. KFENCE is designed to be enabled in production kernels, and has near zero performance overhead. Compared to KASAN, KFENCE trades performance for precision. The main motivation behind KFENCE's design, is that with enough total uptime KFENCE will detect bugs in code paths not typically exercised by non-production test workloads. One way to quickly achieve a large enough total uptime is when the tool is deployed across a large fleet of machines. KFENCE objects each reside on a dedicated page, at either the left or right page boundaries. The pages to the left and right of the object page are "guard pages", whose attributes are changed to a protected state, and cause page faults on any attempted access to them. Such page faults are then intercepted by KFENCE, which handles the fault gracefully by reporting a memory access error. Guarded allocations are set up based on a sample interval (can be set via kfence.sample_interval). After expiration of the sample interval, the next allocation through the main allocator (SLAB or SLUB) returns a guarded allocation from the KFENCE object pool. At this point, the timer is reset, and the next allocation is set up after the expiration of the interval. To enable/disable a KFENCE allocation through the main allocator's fast-path without overhead, KFENCE relies on static branches via the static keys infrastructure. The static branch is toggled to redirect the allocation to KFENCE. The KFENCE memory pool is of fixed size, and if the pool is exhausted no further KFENCE allocations occur. The default config is conservative with only 255 objects, resulting in a pool size of 2 MiB (with 4 KiB pages). We have verified by running synthetic benchmarks (sysbench I/O, hackbench) and production server-workload benchmarks that a kernel with KFENCE (using sample intervals 100-500ms) is performance-neutral compared to a non-KFENCE baseline kernel. KFENCE is inspired by GWP-ASan [1], a userspace tool with similar properties. The name "KFENCE" is a homage to the Electric Fence Malloc Debugger [2]. For more details, see Documentation/dev-tools/kfence.rst added in the series -- also viewable here: https://raw.githubusercontent.com/google/kasan/kfence/Documentation/dev-tools/kfence.rst [1] http://llvm.org/docs/GwpAsan.html [2] https://linux.die.net/man/3/efence This patch (of 9): This adds the Kernel Electric-Fence (KFENCE) infrastructure. KFENCE is a low-overhead sampling-based memory safety error detector of heap use-after-free, invalid-free, and out-of-bounds access errors. KFENCE is designed to be enabled in production kernels, and has near zero performance overhead. Compared to KASAN, KFENCE trades performance for precision. The main motivation behind KFENCE's design, is that with enough total uptime KFENCE will detect bugs in code paths not typically exercised by non-production test workloads. One way to quickly achieve a large enough total uptime is when the tool is deployed across a large fleet of machines. KFENCE objects each reside on a dedicated page, at either the left or right page boundaries. The pages to the left and right of the object page are "guard pages", whose attributes are changed to a protected state, and cause page faults on any attempted access to them. Such page faults are then intercepted by KFENCE, which handles the fault gracefully by reporting a memory access error. To detect out-of-bounds writes to memory within the object's page itself, KFENCE also uses pattern-based redzones. The following figure illustrates the page layout: ---+-----------+-----------+-----------+-----------+-----------+--- | xxxxxxxxx | O : | xxxxxxxxx | : O | xxxxxxxxx | | xxxxxxxxx | B : | xxxxxxxxx | : B | xxxxxxxxx | | x GUARD x | J : RED- | x GUARD x | RED- : J | x GUARD x | | xxxxxxxxx | E : ZONE | xxxxxxxxx | ZONE : E | xxxxxxxxx | | xxxxxxxxx | C : | xxxxxxxxx | : C | xxxxxxxxx | | xxxxxxxxx | T : | xxxxxxxxx | : T | xxxxxxxxx | ---+-----------+-----------+-----------+-----------+-----------+--- Guarded allocations are set up based on a sample interval (can be set via kfence.sample_interval). After expiration of the sample interval, a guarded allocation from the KFENCE object pool is returned to the main allocator (SLAB or SLUB). At this point, the timer is reset, and the next allocation is set up after the expiration of the interval. To enable/disable a KFENCE allocation through the main allocator's fast-path without overhead, KFENCE relies on static branches via the static keys infrastructure. The static branch is toggled to redirect the allocation to KFENCE. To date, we have verified by running synthetic benchmarks (sysbench I/O, hackbench) that a kernel compiled with KFENCE is performance-neutral compared to the non-KFENCE baseline. For more details, see Documentation/dev-tools/kfence.rst (added later in the series). [elver@google.com: fix parameter description for kfence_object_start()] Link: https://lkml.kernel.org/r/20201106092149.GA2851373@elver.google.com [elver@google.com: avoid stalling work queue task without allocations] Link: https://lkml.kernel.org/r/CADYN=9J0DQhizAGB0-jz4HOBBh+05kMBXb4c0cXMS7Qi5NAJiw@mail.gmail.com Link: https://lkml.kernel.org/r/20201110135320.3309507-1-elver@google.com [elver@google.com: fix potential deadlock due to wake_up()] Link: https://lkml.kernel.org/r/000000000000c0645805b7f982e4@google.com Link: https://lkml.kernel.org/r/20210104130749.1768991-1-elver@google.com [elver@google.com: add option to use KFENCE without static keys] Link: https://lkml.kernel.org/r/20210111091544.3287013-1-elver@google.com [elver@google.com: add missing copyright and description headers] Link: https://lkml.kernel.org/r/20210118092159.145934-1-elver@google.com Link: https://lkml.kernel.org/r/20201103175841.3495947-2-elver@google.com Signed-off-by: Marco Elver Signed-off-by: Alexander Potapenko Reviewed-by: Dmitry Vyukov Reviewed-by: SeongJae Park Co-developed-by: Marco Elver Reviewed-by: Jann Horn Cc: "H. Peter Anvin" Cc: Paul E. McKenney Cc: Andrey Konovalov Cc: Andrey Ryabinin Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christopher Lameter Cc: Dave Hansen Cc: David Rientjes Cc: Eric Dumazet Cc: Greg Kroah-Hartman Cc: Hillf Danton Cc: Ingo Molnar Cc: Jonathan Corbet Cc: Joonsoo Kim Cc: Joern Engel Cc: Kees Cook Cc: Mark Rutland Cc: Pekka Enberg Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Vlastimil Babka Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kfence.h | 216 +++++++++++++ init/main.c | 3 + lib/Kconfig.debug | 1 + lib/Kconfig.kfence | 67 ++++ mm/Makefile | 1 + mm/kfence/Makefile | 3 + mm/kfence/core.c | 840 +++++++++++++++++++++++++++++++++++++++++++++++++ mm/kfence/kfence.h | 113 +++++++ mm/kfence/report.c | 240 ++++++++++++++ 9 files changed, 1484 insertions(+) create mode 100644 include/linux/kfence.h create mode 100644 lib/Kconfig.kfence create mode 100644 mm/kfence/Makefile create mode 100644 mm/kfence/core.c create mode 100644 mm/kfence/kfence.h create mode 100644 mm/kfence/report.c (limited to 'include') diff --git a/include/linux/kfence.h b/include/linux/kfence.h new file mode 100644 index 000000000000..81f3911cb298 --- /dev/null +++ b/include/linux/kfence.h @@ -0,0 +1,216 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Kernel Electric-Fence (KFENCE). Public interface for allocator and fault + * handler integration. For more info see Documentation/dev-tools/kfence.rst. + * + * Copyright (C) 2020, Google LLC. + */ + +#ifndef _LINUX_KFENCE_H +#define _LINUX_KFENCE_H + +#include +#include + +#ifdef CONFIG_KFENCE + +/* + * We allocate an even number of pages, as it simplifies calculations to map + * address to metadata indices; effectively, the very first page serves as an + * extended guard page, but otherwise has no special purpose. + */ +#define KFENCE_POOL_SIZE ((CONFIG_KFENCE_NUM_OBJECTS + 1) * 2 * PAGE_SIZE) +extern char *__kfence_pool; + +#ifdef CONFIG_KFENCE_STATIC_KEYS +#include +DECLARE_STATIC_KEY_FALSE(kfence_allocation_key); +#else +#include +extern atomic_t kfence_allocation_gate; +#endif + +/** + * is_kfence_address() - check if an address belongs to KFENCE pool + * @addr: address to check + * + * Return: true or false depending on whether the address is within the KFENCE + * object range. + * + * KFENCE objects live in a separate page range and are not to be intermixed + * with regular heap objects (e.g. KFENCE objects must never be added to the + * allocator freelists). Failing to do so may and will result in heap + * corruptions, therefore is_kfence_address() must be used to check whether + * an object requires specific handling. + * + * Note: This function may be used in fast-paths, and is performance critical. + * Future changes should take this into account; for instance, we want to avoid + * introducing another load and therefore need to keep KFENCE_POOL_SIZE a + * constant (until immediate patching support is added to the kernel). + */ +static __always_inline bool is_kfence_address(const void *addr) +{ + /* + * The non-NULL check is required in case the __kfence_pool pointer was + * never initialized; keep it in the slow-path after the range-check. + */ + return unlikely((unsigned long)((char *)addr - __kfence_pool) < KFENCE_POOL_SIZE && addr); +} + +/** + * kfence_alloc_pool() - allocate the KFENCE pool via memblock + */ +void __init kfence_alloc_pool(void); + +/** + * kfence_init() - perform KFENCE initialization at boot time + * + * Requires that kfence_alloc_pool() was called before. This sets up the + * allocation gate timer, and requires that workqueues are available. + */ +void __init kfence_init(void); + +/** + * kfence_shutdown_cache() - handle shutdown_cache() for KFENCE objects + * @s: cache being shut down + * + * Before shutting down a cache, one must ensure there are no remaining objects + * allocated from it. Because KFENCE objects are not referenced from the cache + * directly, we need to check them here. + * + * Note that shutdown_cache() is internal to SL*B, and kmem_cache_destroy() does + * not return if allocated objects still exist: it prints an error message and + * simply aborts destruction of a cache, leaking memory. + * + * If the only such objects are KFENCE objects, we will not leak the entire + * cache, but instead try to provide more useful debug info by making allocated + * objects "zombie allocations". Objects may then still be used or freed (which + * is handled gracefully), but usage will result in showing KFENCE error reports + * which include stack traces to the user of the object, the original allocation + * site, and caller to shutdown_cache(). + */ +void kfence_shutdown_cache(struct kmem_cache *s); + +/* + * Allocate a KFENCE object. Allocators must not call this function directly, + * use kfence_alloc() instead. + */ +void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags); + +/** + * kfence_alloc() - allocate a KFENCE object with a low probability + * @s: struct kmem_cache with object requirements + * @size: exact size of the object to allocate (can be less than @s->size + * e.g. for kmalloc caches) + * @flags: GFP flags + * + * Return: + * * NULL - must proceed with allocating as usual, + * * non-NULL - pointer to a KFENCE object. + * + * kfence_alloc() should be inserted into the heap allocation fast path, + * allowing it to transparently return KFENCE-allocated objects with a low + * probability using a static branch (the probability is controlled by the + * kfence.sample_interval boot parameter). + */ +static __always_inline void *kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) +{ +#ifdef CONFIG_KFENCE_STATIC_KEYS + if (static_branch_unlikely(&kfence_allocation_key)) +#else + if (unlikely(!atomic_read(&kfence_allocation_gate))) +#endif + return __kfence_alloc(s, size, flags); + return NULL; +} + +/** + * kfence_ksize() - get actual amount of memory allocated for a KFENCE object + * @addr: pointer to a heap object + * + * Return: + * * 0 - not a KFENCE object, must call __ksize() instead, + * * non-0 - this many bytes can be accessed without causing a memory error. + * + * kfence_ksize() returns the number of bytes requested for a KFENCE object at + * allocation time. This number may be less than the object size of the + * corresponding struct kmem_cache. + */ +size_t kfence_ksize(const void *addr); + +/** + * kfence_object_start() - find the beginning of a KFENCE object + * @addr: address within a KFENCE-allocated object + * + * Return: address of the beginning of the object. + * + * SL[AU]B-allocated objects are laid out within a page one by one, so it is + * easy to calculate the beginning of an object given a pointer inside it and + * the object size. The same is not true for KFENCE, which places a single + * object at either end of the page. This helper function is used to find the + * beginning of a KFENCE-allocated object. + */ +void *kfence_object_start(const void *addr); + +/** + * __kfence_free() - release a KFENCE heap object to KFENCE pool + * @addr: object to be freed + * + * Requires: is_kfence_address(addr) + * + * Release a KFENCE object and mark it as freed. + */ +void __kfence_free(void *addr); + +/** + * kfence_free() - try to release an arbitrary heap object to KFENCE pool + * @addr: object to be freed + * + * Return: + * * false - object doesn't belong to KFENCE pool and was ignored, + * * true - object was released to KFENCE pool. + * + * Release a KFENCE object and mark it as freed. May be called on any object, + * even non-KFENCE objects, to simplify integration of the hooks into the + * allocator's free codepath. The allocator must check the return value to + * determine if it was a KFENCE object or not. + */ +static __always_inline __must_check bool kfence_free(void *addr) +{ + if (!is_kfence_address(addr)) + return false; + __kfence_free(addr); + return true; +} + +/** + * kfence_handle_page_fault() - perform page fault handling for KFENCE pages + * @addr: faulting address + * + * Return: + * * false - address outside KFENCE pool, + * * true - page fault handled by KFENCE, no additional handling required. + * + * A page fault inside KFENCE pool indicates a memory error, such as an + * out-of-bounds access, a use-after-free or an invalid memory access. In these + * cases KFENCE prints an error message and marks the offending page as + * present, so that the kernel can proceed. + */ +bool __must_check kfence_handle_page_fault(unsigned long addr); + +#else /* CONFIG_KFENCE */ + +static inline bool is_kfence_address(const void *addr) { return false; } +static inline void kfence_alloc_pool(void) { } +static inline void kfence_init(void) { } +static inline void kfence_shutdown_cache(struct kmem_cache *s) { } +static inline void *kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) { return NULL; } +static inline size_t kfence_ksize(const void *addr) { return 0; } +static inline void *kfence_object_start(const void *addr) { return NULL; } +static inline void __kfence_free(void *addr) { } +static inline bool __must_check kfence_free(void *addr) { return false; } +static inline bool __must_check kfence_handle_page_fault(unsigned long addr) { return false; } + +#endif + +#endif /* _LINUX_KFENCE_H */ diff --git a/init/main.c b/init/main.c index e9933cbf60d4..261051070e3c 100644 --- a/init/main.c +++ b/init/main.c @@ -40,6 +40,7 @@ #include #include #include +#include #include #include #include @@ -824,6 +825,7 @@ static void __init mm_init(void) */ page_ext_init_flatmem(); init_mem_debugging_and_hardening(); + kfence_alloc_pool(); report_meminit(); mem_init(); /* page_owner must be initialized after buddy is ready */ @@ -955,6 +957,7 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void) hrtimers_init(); softirq_init(); timekeeping_init(); + kfence_init(); /* * For best initial stack canary entropy, prepare it after: diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index f9febffffc21..2779c29d9981 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -938,6 +938,7 @@ config DEBUG_STACKOVERFLOW If in doubt, say "N". source "lib/Kconfig.kasan" +source "lib/Kconfig.kfence" endmenu # "Memory Debugging" diff --git a/lib/Kconfig.kfence b/lib/Kconfig.kfence new file mode 100644 index 000000000000..b88ac9d6b2e6 --- /dev/null +++ b/lib/Kconfig.kfence @@ -0,0 +1,67 @@ +# SPDX-License-Identifier: GPL-2.0-only + +config HAVE_ARCH_KFENCE + bool + +menuconfig KFENCE + bool "KFENCE: low-overhead sampling-based memory safety error detector" + depends on HAVE_ARCH_KFENCE && !KASAN && (SLAB || SLUB) + select STACKTRACE + help + KFENCE is a low-overhead sampling-based detector of heap out-of-bounds + access, use-after-free, and invalid-free errors. KFENCE is designed + to have negligible cost to permit enabling it in production + environments. + + Note that, KFENCE is not a substitute for explicit testing with tools + such as KASAN. KFENCE can detect a subset of bugs that KASAN can + detect, albeit at very different performance profiles. If you can + afford to use KASAN, continue using KASAN, for example in test + environments. If your kernel targets production use, and cannot + enable KASAN due to its cost, consider using KFENCE. + +if KFENCE + +config KFENCE_STATIC_KEYS + bool "Use static keys to set up allocations" + default y + depends on JUMP_LABEL # To ensure performance, require jump labels + help + Use static keys (static branches) to set up KFENCE allocations. Using + static keys is normally recommended, because it avoids a dynamic + branch in the allocator's fast path. However, with very low sample + intervals, or on systems that do not support jump labels, a dynamic + branch may still be an acceptable performance trade-off. + +config KFENCE_SAMPLE_INTERVAL + int "Default sample interval in milliseconds" + default 100 + help + The KFENCE sample interval determines the frequency with which heap + allocations will be guarded by KFENCE. May be overridden via boot + parameter "kfence.sample_interval". + + Set this to 0 to disable KFENCE by default, in which case only + setting "kfence.sample_interval" to a non-zero value enables KFENCE. + +config KFENCE_NUM_OBJECTS + int "Number of guarded objects available" + range 1 65535 + default 255 + help + The number of guarded objects available. For each KFENCE object, 2 + pages are required; with one containing the object and two adjacent + ones used as guard pages. + +config KFENCE_STRESS_TEST_FAULTS + int "Stress testing of fault handling and error reporting" if EXPERT + default 0 + help + The inverse probability with which to randomly protect KFENCE object + pages, resulting in spurious use-after-frees. The main purpose of + this option is to stress test KFENCE with concurrent error reports + and allocations/frees. A value of 0 disables stress testing logic. + + Only for KFENCE testing; set to 0 if you are not a KFENCE developer. + +endif # KFENCE diff --git a/mm/Makefile b/mm/Makefile index 135bbb65511a..72227b24a616 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -81,6 +81,7 @@ obj-$(CONFIG_PAGE_POISONING) += page_poison.o obj-$(CONFIG_SLAB) += slab.o obj-$(CONFIG_SLUB) += slub.o obj-$(CONFIG_KASAN) += kasan/ +obj-$(CONFIG_KFENCE) += kfence/ obj-$(CONFIG_FAILSLAB) += failslab.o obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o obj-$(CONFIG_MEMTEST) += memtest.o diff --git a/mm/kfence/Makefile b/mm/kfence/Makefile new file mode 100644 index 000000000000..d991e9a349f0 --- /dev/null +++ b/mm/kfence/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-$(CONFIG_KFENCE) := core.o report.o diff --git a/mm/kfence/core.c b/mm/kfence/core.c new file mode 100644 index 000000000000..d6a32c13336b --- /dev/null +++ b/mm/kfence/core.c @@ -0,0 +1,840 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KFENCE guarded object allocator and fault handling. + * + * Copyright (C) 2020, Google LLC. + */ + +#define pr_fmt(fmt) "kfence: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "kfence.h" + +/* Disables KFENCE on the first warning assuming an irrecoverable error. */ +#define KFENCE_WARN_ON(cond) \ + ({ \ + const bool __cond = WARN_ON(cond); \ + if (unlikely(__cond)) \ + WRITE_ONCE(kfence_enabled, false); \ + __cond; \ + }) + +/* === Data ================================================================= */ + +static bool kfence_enabled __read_mostly; + +static unsigned long kfence_sample_interval __read_mostly = CONFIG_KFENCE_SAMPLE_INTERVAL; + +#ifdef MODULE_PARAM_PREFIX +#undef MODULE_PARAM_PREFIX +#endif +#define MODULE_PARAM_PREFIX "kfence." + +static int param_set_sample_interval(const char *val, const struct kernel_param *kp) +{ + unsigned long num; + int ret = kstrtoul(val, 0, &num); + + if (ret < 0) + return ret; + + if (!num) /* Using 0 to indicate KFENCE is disabled. */ + WRITE_ONCE(kfence_enabled, false); + else if (!READ_ONCE(kfence_enabled) && system_state != SYSTEM_BOOTING) + return -EINVAL; /* Cannot (re-)enable KFENCE on-the-fly. */ + + *((unsigned long *)kp->arg) = num; + return 0; +} + +static int param_get_sample_interval(char *buffer, const struct kernel_param *kp) +{ + if (!READ_ONCE(kfence_enabled)) + return sprintf(buffer, "0\n"); + + return param_get_ulong(buffer, kp); +} + +static const struct kernel_param_ops sample_interval_param_ops = { + .set = param_set_sample_interval, + .get = param_get_sample_interval, +}; +module_param_cb(sample_interval, &sample_interval_param_ops, &kfence_sample_interval, 0600); + +/* The pool of pages used for guard pages and objects. */ +char *__kfence_pool __ro_after_init; +EXPORT_SYMBOL(__kfence_pool); /* Export for test modules. */ + +/* + * Per-object metadata, with one-to-one mapping of object metadata to + * backing pages (in __kfence_pool). + */ +static_assert(CONFIG_KFENCE_NUM_OBJECTS > 0); +struct kfence_metadata kfence_metadata[CONFIG_KFENCE_NUM_OBJECTS]; + +/* Freelist with available objects. */ +static struct list_head kfence_freelist = LIST_HEAD_INIT(kfence_freelist); +static DEFINE_RAW_SPINLOCK(kfence_freelist_lock); /* Lock protecting freelist. */ + +#ifdef CONFIG_KFENCE_STATIC_KEYS +/* The static key to set up a KFENCE allocation. */ +DEFINE_STATIC_KEY_FALSE(kfence_allocation_key); +#endif + +/* Gates the allocation, ensuring only one succeeds in a given period. */ +atomic_t kfence_allocation_gate = ATOMIC_INIT(1); + +/* Statistics counters for debugfs. */ +enum kfence_counter_id { + KFENCE_COUNTER_ALLOCATED, + KFENCE_COUNTER_ALLOCS, + KFENCE_COUNTER_FREES, + KFENCE_COUNTER_ZOMBIES, + KFENCE_COUNTER_BUGS, + KFENCE_COUNTER_COUNT, +}; +static atomic_long_t counters[KFENCE_COUNTER_COUNT]; +static const char *const counter_names[] = { + [KFENCE_COUNTER_ALLOCATED] = "currently allocated", + [KFENCE_COUNTER_ALLOCS] = "total allocations", + [KFENCE_COUNTER_FREES] = "total frees", + [KFENCE_COUNTER_ZOMBIES] = "zombie allocations", + [KFENCE_COUNTER_BUGS] = "total bugs", +}; +static_assert(ARRAY_SIZE(counter_names) == KFENCE_COUNTER_COUNT); + +/* === Internals ============================================================ */ + +static bool kfence_protect(unsigned long addr) +{ + return !KFENCE_WARN_ON(!kfence_protect_page(ALIGN_DOWN(addr, PAGE_SIZE), true)); +} + +static bool kfence_unprotect(unsigned long addr) +{ + return !KFENCE_WARN_ON(!kfence_protect_page(ALIGN_DOWN(addr, PAGE_SIZE), false)); +} + +static inline struct kfence_metadata *addr_to_metadata(unsigned long addr) +{ + long index; + + /* The checks do not affect performance; only called from slow-paths. */ + + if (!is_kfence_address((void *)addr)) + return NULL; + + /* + * May be an invalid index if called with an address at the edge of + * __kfence_pool, in which case we would report an "invalid access" + * error. + */ + index = (addr - (unsigned long)__kfence_pool) / (PAGE_SIZE * 2) - 1; + if (index < 0 || index >= CONFIG_KFENCE_NUM_OBJECTS) + return NULL; + + return &kfence_metadata[index]; +} + +static inline unsigned long metadata_to_pageaddr(const struct kfence_metadata *meta) +{ + unsigned long offset = (meta - kfence_metadata + 1) * PAGE_SIZE * 2; + unsigned long pageaddr = (unsigned long)&__kfence_pool[offset]; + + /* The checks do not affect performance; only called from slow-paths. */ + + /* Only call with a pointer into kfence_metadata. */ + if (KFENCE_WARN_ON(meta < kfence_metadata || + meta >= kfence_metadata + CONFIG_KFENCE_NUM_OBJECTS)) + return 0; + + /* + * This metadata object only ever maps to 1 page; verify that the stored + * address is in the expected range. + */ + if (KFENCE_WARN_ON(ALIGN_DOWN(meta->addr, PAGE_SIZE) != pageaddr)) + return 0; + + return pageaddr; +} + +/* + * Update the object's metadata state, including updating the alloc/free stacks + * depending on the state transition. + */ +static noinline void metadata_update_state(struct kfence_metadata *meta, + enum kfence_object_state next) +{ + struct kfence_track *track = + next == KFENCE_OBJECT_FREED ? &meta->free_track : &meta->alloc_track; + + lockdep_assert_held(&meta->lock); + + /* + * Skip over 1 (this) functions; noinline ensures we do not accidentally + * skip over the caller by never inlining. + */ + track->num_stack_entries = stack_trace_save(track->stack_entries, KFENCE_STACK_DEPTH, 1); + track->pid = task_pid_nr(current); + + /* + * Pairs with READ_ONCE() in + * kfence_shutdown_cache(), + * kfence_handle_page_fault(). + */ + WRITE_ONCE(meta->state, next); +} + +/* Write canary byte to @addr. */ +static inline bool set_canary_byte(u8 *addr) +{ + *addr = KFENCE_CANARY_PATTERN(addr); + return true; +} + +/* Check canary byte at @addr. */ +static inline bool check_canary_byte(u8 *addr) +{ + if (likely(*addr == KFENCE_CANARY_PATTERN(addr))) + return true; + + atomic_long_inc(&counters[KFENCE_COUNTER_BUGS]); + kfence_report_error((unsigned long)addr, addr_to_metadata((unsigned long)addr), + KFENCE_ERROR_CORRUPTION); + return false; +} + +/* __always_inline this to ensure we won't do an indirect call to fn. */ +static __always_inline void for_each_canary(const struct kfence_metadata *meta, bool (*fn)(u8 *)) +{ + const unsigned long pageaddr = ALIGN_DOWN(meta->addr, PAGE_SIZE); + unsigned long addr; + + lockdep_assert_held(&meta->lock); + + /* + * We'll iterate over each canary byte per-side until fn() returns + * false. However, we'll still iterate over the canary bytes to the + * right of the object even if there was an error in the canary bytes to + * the left of the object. Specifically, if check_canary_byte() + * generates an error, showing both sides might give more clues as to + * what the error is about when displaying which bytes were corrupted. + */ + + /* Apply to left of object. */ + for (addr = pageaddr; addr < meta->addr; addr++) { + if (!fn((u8 *)addr)) + break; + } + + /* Apply to right of object. */ + for (addr = meta->addr + meta->size; addr < pageaddr + PAGE_SIZE; addr++) { + if (!fn((u8 *)addr)) + break; + } +} + +static void *kfence_guarded_alloc(struct kmem_cache *cache, size_t size, gfp_t gfp) +{ + struct kfence_metadata *meta = NULL; + unsigned long flags; + struct page *page; + void *addr; + + /* Try to obtain a free object. */ + raw_spin_lock_irqsave(&kfence_freelist_lock, flags); + if (!list_empty(&kfence_freelist)) { + meta = list_entry(kfence_freelist.next, struct kfence_metadata, list); + list_del_init(&meta->list); + } + raw_spin_unlock_irqrestore(&kfence_freelist_lock, flags); + if (!meta) + return NULL; + + if (unlikely(!raw_spin_trylock_irqsave(&meta->lock, flags))) { + /* + * This is extremely unlikely -- we are reporting on a + * use-after-free, which locked meta->lock, and the reporting + * code via printk calls kmalloc() which ends up in + * kfence_alloc() and tries to grab the same object that we're + * reporting on. While it has never been observed, lockdep does + * report that there is a possibility of deadlock. Fix it by + * using trylock and bailing out gracefully. + */ + raw_spin_lock_irqsave(&kfence_freelist_lock, flags); + /* Put the object back on the freelist. */ + list_add_tail(&meta->list, &kfence_freelist); + raw_spin_unlock_irqrestore(&kfence_freelist_lock, flags); + + return NULL; + } + + meta->addr = metadata_to_pageaddr(meta); + /* Unprotect if we're reusing this page. */ + if (meta->state == KFENCE_OBJECT_FREED) + kfence_unprotect(meta->addr); + + /* + * Note: for allocations made before RNG initialization, will always + * return zero. We still benefit from enabling KFENCE as early as + * possible, even when the RNG is not yet available, as this will allow + * KFENCE to detect bugs due to earlier allocations. The only downside + * is that the out-of-bounds accesses detected are deterministic for + * such allocations. + */ + if (prandom_u32_max(2)) { + /* Allocate on the "right" side, re-calculate address. */ + meta->addr += PAGE_SIZE - size; + meta->addr = ALIGN_DOWN(meta->addr, cache->align); + } + + addr = (void *)meta->addr; + + /* Update remaining metadata. */ + metadata_update_state(meta, KFENCE_OBJECT_ALLOCATED); + /* Pairs with READ_ONCE() in kfence_shutdown_cache(). */ + WRITE_ONCE(meta->cache, cache); + meta->size = size; + for_each_canary(meta, set_canary_byte); + + /* Set required struct page fields. */ + page = virt_to_page(meta->addr); + page->slab_cache = cache; + + raw_spin_unlock_irqrestore(&meta->lock, flags); + + /* Memory initialization. */ + + /* + * We check slab_want_init_on_alloc() ourselves, rather than letting + * SL*B do the initialization, as otherwise we might overwrite KFENCE's + * redzone. + */ + if (unlikely(slab_want_init_on_alloc(gfp, cache))) + memzero_explicit(addr, size); + if (cache->ctor) + cache->ctor(addr); + + if (CONFIG_KFENCE_STRESS_TEST_FAULTS && !prandom_u32_max(CONFIG_KFENCE_STRESS_TEST_FAULTS)) + kfence_protect(meta->addr); /* Random "faults" by protecting the object. */ + + atomic_long_inc(&counters[KFENCE_COUNTER_ALLOCATED]); + atomic_long_inc(&counters[KFENCE_COUNTER_ALLOCS]); + + return addr; +} + +static void kfence_guarded_free(void *addr, struct kfence_metadata *meta, bool zombie) +{ + struct kcsan_scoped_access assert_page_exclusive; + unsigned long flags; + + raw_spin_lock_irqsave(&meta->lock, flags); + + if (meta->state != KFENCE_OBJECT_ALLOCATED || meta->addr != (unsigned long)addr) { + /* Invalid or double-free, bail out. */ + atomic_long_inc(&counters[KFENCE_COUNTER_BUGS]); + kfence_report_error((unsigned long)addr, meta, KFENCE_ERROR_INVALID_FREE); + raw_spin_unlock_irqrestore(&meta->lock, flags); + return; + } + + /* Detect racy use-after-free, or incorrect reallocation of this page by KFENCE. */ + kcsan_begin_scoped_access((void *)ALIGN_DOWN((unsigned long)addr, PAGE_SIZE), PAGE_SIZE, + KCSAN_ACCESS_SCOPED | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ASSERT, + &assert_page_exclusive); + + if (CONFIG_KFENCE_STRESS_TEST_FAULTS) + kfence_unprotect((unsigned long)addr); /* To check canary bytes. */ + + /* Restore page protection if there was an OOB access. */ + if (meta->unprotected_page) { + kfence_protect(meta->unprotected_page); + meta->unprotected_page = 0; + } + + /* Check canary bytes for memory corruption. */ + for_each_canary(meta, check_canary_byte); + + /* + * Clear memory if init-on-free is set. While we protect the page, the + * data is still there, and after a use-after-free is detected, we + * unprotect the page, so the data is still accessible. + */ + if (!zombie && unlikely(slab_want_init_on_free(meta->cache))) + memzero_explicit(addr, meta->size); + + /* Mark the object as freed. */ + metadata_update_state(meta, KFENCE_OBJECT_FREED); + + raw_spin_unlock_irqrestore(&meta->lock, flags); + + /* Protect to detect use-after-frees. */ + kfence_protect((unsigned long)addr); + + kcsan_end_scoped_access(&assert_page_exclusive); + if (!zombie) { + /* Add it to the tail of the freelist for reuse. */ + raw_spin_lock_irqsave(&kfence_freelist_lock, flags); + KFENCE_WARN_ON(!list_empty(&meta->list)); + list_add_tail(&meta->list, &kfence_freelist); + raw_spin_unlock_irqrestore(&kfence_freelist_lock, flags); + + atomic_long_dec(&counters[KFENCE_COUNTER_ALLOCATED]); + atomic_long_inc(&counters[KFENCE_COUNTER_FREES]); + } else { + /* See kfence_shutdown_cache(). */ + atomic_long_inc(&counters[KFENCE_COUNTER_ZOMBIES]); + } +} + +static void rcu_guarded_free(struct rcu_head *h) +{ + struct kfence_metadata *meta = container_of(h, struct kfence_metadata, rcu_head); + + kfence_guarded_free((void *)meta->addr, meta, false); +} + +static bool __init kfence_init_pool(void) +{ + unsigned long addr = (unsigned long)__kfence_pool; + struct page *pages; + int i; + + if (!__kfence_pool) + return false; + + if (!arch_kfence_init_pool()) + goto err; + + pages = virt_to_page(addr); + + /* + * Set up object pages: they must have PG_slab set, to avoid freeing + * these as real pages. + * + * We also want to avoid inserting kfence_free() in the kfree() + * fast-path in SLUB, and therefore need to ensure kfree() correctly + * enters __slab_free() slow-path. + */ + for (i = 0; i < KFENCE_POOL_SIZE / PAGE_SIZE; i++) { + if (!i || (i % 2)) + continue; + + /* Verify we do not have a compound head page. */ + if (WARN_ON(compound_head(&pages[i]) != &pages[i])) + goto err; + + __SetPageSlab(&pages[i]); + } + + /* + * Protect the first 2 pages. The first page is mostly unnecessary, and + * merely serves as an extended guard page. However, adding one + * additional page in the beginning gives us an even number of pages, + * which simplifies the mapping of address to metadata index. + */ + for (i = 0; i < 2; i++) { + if (unlikely(!kfence_protect(addr))) + goto err; + + addr += PAGE_SIZE; + } + + for (i = 0; i < CONFIG_KFENCE_NUM_OBJECTS; i++) { + struct kfence_metadata *meta = &kfence_metadata[i]; + + /* Initialize metadata. */ + INIT_LIST_HEAD(&meta->list); + raw_spin_lock_init(&meta->lock); + meta->state = KFENCE_OBJECT_UNUSED; + meta->addr = addr; /* Initialize for validation in metadata_to_pageaddr(). */ + list_add_tail(&meta->list, &kfence_freelist); + + /* Protect the right redzone. */ + if (unlikely(!kfence_protect(addr + PAGE_SIZE))) + goto err; + + addr += 2 * PAGE_SIZE; + } + + return true; + +err: + /* + * Only release unprotected pages, and do not try to go back and change + * page attributes due to risk of failing to do so as well. If changing + * page attributes for some pages fails, it is very likely that it also + * fails for the first page, and therefore expect addr==__kfence_pool in + * most failure cases. + */ + memblock_free_late(__pa(addr), KFENCE_POOL_SIZE - (addr - (unsigned long)__kfence_pool)); + __kfence_pool = NULL; + return false; +} + +/* === DebugFS Interface ==================================================== */ + +static int stats_show(struct seq_file *seq, void *v) +{ + int i; + + seq_printf(seq, "enabled: %i\n", READ_ONCE(kfence_enabled)); + for (i = 0; i < KFENCE_COUNTER_COUNT; i++) + seq_printf(seq, "%s: %ld\n", counter_names[i], atomic_long_read(&counters[i])); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(stats); + +/* + * debugfs seq_file operations for /sys/kernel/debug/kfence/objects. + * start_object() and next_object() return the object index + 1, because NULL is used + * to stop iteration. + */ +static void *start_object(struct seq_file *seq, loff_t *pos) +{ + if (*pos < CONFIG_KFENCE_NUM_OBJECTS) + return (void *)((long)*pos + 1); + return NULL; +} + +static void stop_object(struct seq_file *seq, void *v) +{ +} + +static void *next_object(struct seq_file *seq, void *v, loff_t *pos) +{ + ++*pos; + if (*pos < CONFIG_KFENCE_NUM_OBJECTS) + return (void *)((long)*pos + 1); + return NULL; +} + +static int show_object(struct seq_file *seq, void *v) +{ + struct kfence_metadata *meta = &kfence_metadata[(long)v - 1]; + unsigned long flags; + + raw_spin_lock_irqsave(&meta->lock, flags); + kfence_print_object(seq, meta); + raw_spin_unlock_irqrestore(&meta->lock, flags); + seq_puts(seq, "---------------------------------\n"); + + return 0; +} + +static const struct seq_operations object_seqops = { + .start = start_object, + .next = next_object, + .stop = stop_object, + .show = show_object, +}; + +static int open_objects(struct inode *inode, struct file *file) +{ + return seq_open(file, &object_seqops); +} + +static const struct file_operations objects_fops = { + .open = open_objects, + .read = seq_read, + .llseek = seq_lseek, +}; + +static int __init kfence_debugfs_init(void) +{ + struct dentry *kfence_dir = debugfs_create_dir("kfence", NULL); + + debugfs_create_file("stats", 0444, kfence_dir, NULL, &stats_fops); + debugfs_create_file("objects", 0400, kfence_dir, NULL, &objects_fops); + return 0; +} + +late_initcall(kfence_debugfs_init); + +/* === Allocation Gate Timer ================================================ */ + +/* + * Set up delayed work, which will enable and disable the static key. We need to + * use a work queue (rather than a simple timer), since enabling and disabling a + * static key cannot be done from an interrupt. + * + * Note: Toggling a static branch currently causes IPIs, and here we'll end up + * with a total of 2 IPIs to all CPUs. If this ends up a problem in future (with + * more aggressive sampling intervals), we could get away with a variant that + * avoids IPIs, at the cost of not immediately capturing allocations if the + * instructions remain cached. + */ +static struct delayed_work kfence_timer; +static void toggle_allocation_gate(struct work_struct *work) +{ + if (!READ_ONCE(kfence_enabled)) + return; + + /* Enable static key, and await allocation to happen. */ + atomic_set(&kfence_allocation_gate, 0); +#ifdef CONFIG_KFENCE_STATIC_KEYS + static_branch_enable(&kfence_allocation_key); + /* + * Await an allocation. Timeout after 1 second, in case the kernel stops + * doing allocations, to avoid stalling this worker task for too long. + */ + { + unsigned long end_wait = jiffies + HZ; + + do { + set_current_state(TASK_UNINTERRUPTIBLE); + if (atomic_read(&kfence_allocation_gate) != 0) + break; + schedule_timeout(1); + } while (time_before(jiffies, end_wait)); + __set_current_state(TASK_RUNNING); + } + /* Disable static key and reset timer. */ + static_branch_disable(&kfence_allocation_key); +#endif + schedule_delayed_work(&kfence_timer, msecs_to_jiffies(kfence_sample_interval)); +} +static DECLARE_DELAYED_WORK(kfence_timer, toggle_allocation_gate); + +/* === Public interface ===================================================== */ + +void __init kfence_alloc_pool(void) +{ + if (!kfence_sample_interval) + return; + + __kfence_pool = memblock_alloc(KFENCE_POOL_SIZE, PAGE_SIZE); + + if (!__kfence_pool) + pr_err("failed to allocate pool\n"); +} + +void __init kfence_init(void) +{ + /* Setting kfence_sample_interval to 0 on boot disables KFENCE. */ + if (!kfence_sample_interval) + return; + + if (!kfence_init_pool()) { + pr_err("%s failed\n", __func__); + return; + } + + WRITE_ONCE(kfence_enabled, true); + schedule_delayed_work(&kfence_timer, 0); + pr_info("initialized - using %lu bytes for %d objects", KFENCE_POOL_SIZE, + CONFIG_KFENCE_NUM_OBJECTS); + if (IS_ENABLED(CONFIG_DEBUG_KERNEL)) + pr_cont(" at 0x%px-0x%px\n", (void *)__kfence_pool, + (void *)(__kfence_pool + KFENCE_POOL_SIZE)); + else + pr_cont("\n"); +} + +void kfence_shutdown_cache(struct kmem_cache *s) +{ + unsigned long flags; + struct kfence_metadata *meta; + int i; + + for (i = 0; i < CONFIG_KFENCE_NUM_OBJECTS; i++) { + bool in_use; + + meta = &kfence_metadata[i]; + + /* + * If we observe some inconsistent cache and state pair where we + * should have returned false here, cache destruction is racing + * with either kmem_cache_alloc() or kmem_cache_free(). Taking + * the lock will not help, as different critical section + * serialization will have the same outcome. + */ + if (READ_ONCE(meta->cache) != s || + READ_ONCE(meta->state) != KFENCE_OBJECT_ALLOCATED) + continue; + + raw_spin_lock_irqsave(&meta->lock, flags); + in_use = meta->cache == s && meta->state == KFENCE_OBJECT_ALLOCATED; + raw_spin_unlock_irqrestore(&meta->lock, flags); + + if (in_use) { + /* + * This cache still has allocations, and we should not + * release them back into the freelist so they can still + * safely be used and retain the kernel's default + * behaviour of keeping the allocations alive (leak the + * cache); however, they effectively become "zombie + * allocations" as the KFENCE objects are the only ones + * still in use and the owning cache is being destroyed. + * + * We mark them freed, so that any subsequent use shows + * more useful error messages that will include stack + * traces of the user of the object, the original + * allocation, and caller to shutdown_cache(). + */ + kfence_guarded_free((void *)meta->addr, meta, /*zombie=*/true); + } + } + + for (i = 0; i < CONFIG_KFENCE_NUM_OBJECTS; i++) { + meta = &kfence_metadata[i]; + + /* See above. */ + if (READ_ONCE(meta->cache) != s || READ_ONCE(meta->state) != KFENCE_OBJECT_FREED) + continue; + + raw_spin_lock_irqsave(&meta->lock, flags); + if (meta->cache == s && meta->state == KFENCE_OBJECT_FREED) + meta->cache = NULL; + raw_spin_unlock_irqrestore(&meta->lock, flags); + } +} + +void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) +{ + /* + * allocation_gate only needs to become non-zero, so it doesn't make + * sense to continue writing to it and pay the associated contention + * cost, in case we have a large number of concurrent allocations. + */ + if (atomic_read(&kfence_allocation_gate) || atomic_inc_return(&kfence_allocation_gate) > 1) + return NULL; + + if (!READ_ONCE(kfence_enabled)) + return NULL; + + if (size > PAGE_SIZE) + return NULL; + + return kfence_guarded_alloc(s, size, flags); +} + +size_t kfence_ksize(const void *addr) +{ + const struct kfence_metadata *meta = addr_to_metadata((unsigned long)addr); + + /* + * Read locklessly -- if there is a race with __kfence_alloc(), this is + * either a use-after-free or invalid access. + */ + return meta ? meta->size : 0; +} + +void *kfence_object_start(const void *addr) +{ + const struct kfence_metadata *meta = addr_to_metadata((unsigned long)addr); + + /* + * Read locklessly -- if there is a race with __kfence_alloc(), this is + * either a use-after-free or invalid access. + */ + return meta ? (void *)meta->addr : NULL; +} + +void __kfence_free(void *addr) +{ + struct kfence_metadata *meta = addr_to_metadata((unsigned long)addr); + + /* + * If the objects of the cache are SLAB_TYPESAFE_BY_RCU, defer freeing + * the object, as the object page may be recycled for other-typed + * objects once it has been freed. meta->cache may be NULL if the cache + * was destroyed. + */ + if (unlikely(meta->cache && (meta->cache->flags & SLAB_TYPESAFE_BY_RCU))) + call_rcu(&meta->rcu_head, rcu_guarded_free); + else + kfence_guarded_free(addr, meta, false); +} + +bool kfence_handle_page_fault(unsigned long addr) +{ + const int page_index = (addr - (unsigned long)__kfence_pool) / PAGE_SIZE; + struct kfence_metadata *to_report = NULL; + enum kfence_error_type error_type; + unsigned long flags; + + if (!is_kfence_address((void *)addr)) + return false; + + if (!READ_ONCE(kfence_enabled)) /* If disabled at runtime ... */ + return kfence_unprotect(addr); /* ... unprotect and proceed. */ + + atomic_long_inc(&counters[KFENCE_COUNTER_BUGS]); + + if (page_index % 2) { + /* This is a redzone, report a buffer overflow. */ + struct kfence_metadata *meta; + int distance = 0; + + meta = addr_to_metadata(addr - PAGE_SIZE); + if (meta && READ_ONCE(meta->state) == KFENCE_OBJECT_ALLOCATED) { + to_report = meta; + /* Data race ok; distance calculation approximate. */ + distance = addr - data_race(meta->addr + meta->size); + } + + meta = addr_to_metadata(addr + PAGE_SIZE); + if (meta && READ_ONCE(meta->state) == KFENCE_OBJECT_ALLOCATED) { + /* Data race ok; distance calculation approximate. */ + if (!to_report || distance > data_race(meta->addr) - addr) + to_report = meta; + } + + if (!to_report) + goto out; + + raw_spin_lock_irqsave(&to_report->lock, flags); + to_report->unprotected_page = addr; + error_type = KFENCE_ERROR_OOB; + + /* + * If the object was freed before we took the look we can still + * report this as an OOB -- the report will simply show the + * stacktrace of the free as well. + */ + } else { + to_report = addr_to_metadata(addr); + if (!to_report) + goto out; + + raw_spin_lock_irqsave(&to_report->lock, flags); + error_type = KFENCE_ERROR_UAF; + /* + * We may race with __kfence_alloc(), and it is possible that a + * freed object may be reallocated. We simply report this as a + * use-after-free, with the stack trace showing the place where + * the object was re-allocated. + */ + } + +out: + if (to_report) { + kfence_report_error(addr, to_report, error_type); + raw_spin_unlock_irqrestore(&to_report->lock, flags); + } else { + /* This may be a UAF or OOB access, but we can't be sure. */ + kfence_report_error(addr, NULL, KFENCE_ERROR_INVALID); + } + + return kfence_unprotect(addr); /* Unprotect and let access proceed. */ +} diff --git a/mm/kfence/kfence.h b/mm/kfence/kfence.h new file mode 100644 index 000000000000..1014060f9707 --- /dev/null +++ b/mm/kfence/kfence.h @@ -0,0 +1,113 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Kernel Electric-Fence (KFENCE). For more info please see + * Documentation/dev-tools/kfence.rst. + * + * Copyright (C) 2020, Google LLC. + */ + +#ifndef MM_KFENCE_KFENCE_H +#define MM_KFENCE_KFENCE_H + +#include +#include +#include +#include + +#include "../slab.h" /* for struct kmem_cache */ + +/* For non-debug builds, avoid leaking kernel pointers into dmesg. */ +#ifdef CONFIG_DEBUG_KERNEL +#define PTR_FMT "%px" +#else +#define PTR_FMT "%p" +#endif + +/* + * Get the canary byte pattern for @addr. Use a pattern that varies based on the + * lower 3 bits of the address, to detect memory corruptions with higher + * probability, where similar constants are used. + */ +#define KFENCE_CANARY_PATTERN(addr) ((u8)0xaa ^ (u8)((unsigned long)(addr) & 0x7)) + +/* Maximum stack depth for reports. */ +#define KFENCE_STACK_DEPTH 64 + +/* KFENCE object states. */ +enum kfence_object_state { + KFENCE_OBJECT_UNUSED, /* Object is unused. */ + KFENCE_OBJECT_ALLOCATED, /* Object is currently allocated. */ + KFENCE_OBJECT_FREED, /* Object was allocated, and then freed. */ +}; + +/* Alloc/free tracking information. */ +struct kfence_track { + pid_t pid; + int num_stack_entries; + unsigned long stack_entries[KFENCE_STACK_DEPTH]; +}; + +/* KFENCE metadata per guarded allocation. */ +struct kfence_metadata { + struct list_head list; /* Freelist node; access under kfence_freelist_lock. */ + struct rcu_head rcu_head; /* For delayed freeing. */ + + /* + * Lock protecting below data; to ensure consistency of the below data, + * since the following may execute concurrently: __kfence_alloc(), + * __kfence_free(), kfence_handle_page_fault(). However, note that we + * cannot grab the same metadata off the freelist twice, and multiple + * __kfence_alloc() cannot run concurrently on the same metadata. + */ + raw_spinlock_t lock; + + /* The current state of the object; see above. */ + enum kfence_object_state state; + + /* + * Allocated object address; cannot be calculated from size, because of + * alignment requirements. + * + * Invariant: ALIGN_DOWN(addr, PAGE_SIZE) is constant. + */ + unsigned long addr; + + /* + * The size of the original allocation. + */ + size_t size; + + /* + * The kmem_cache cache of the last allocation; NULL if never allocated + * or the cache has already been destroyed. + */ + struct kmem_cache *cache; + + /* + * In case of an invalid access, the page that was unprotected; we + * optimistically only store one address. + */ + unsigned long unprotected_page; + + /* Allocation and free stack information. */ + struct kfence_track alloc_track; + struct kfence_track free_track; +}; + +extern struct kfence_metadata kfence_metadata[CONFIG_KFENCE_NUM_OBJECTS]; + +/* KFENCE error types for report generation. */ +enum kfence_error_type { + KFENCE_ERROR_OOB, /* Detected a out-of-bounds access. */ + KFENCE_ERROR_UAF, /* Detected a use-after-free access. */ + KFENCE_ERROR_CORRUPTION, /* Detected a memory corruption on free. */ + KFENCE_ERROR_INVALID, /* Invalid access of unknown type. */ + KFENCE_ERROR_INVALID_FREE, /* Invalid free. */ +}; + +void kfence_report_error(unsigned long address, const struct kfence_metadata *meta, + enum kfence_error_type type); + +void kfence_print_object(struct seq_file *seq, const struct kfence_metadata *meta); + +#endif /* MM_KFENCE_KFENCE_H */ diff --git a/mm/kfence/report.c b/mm/kfence/report.c new file mode 100644 index 000000000000..64f27c8d46a3 --- /dev/null +++ b/mm/kfence/report.c @@ -0,0 +1,240 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KFENCE reporting. + * + * Copyright (C) 2020, Google LLC. + */ + +#include + +#include +#include +#include +#include +#include +#include + +#include + +#include "kfence.h" + +/* Helper function to either print to a seq_file or to console. */ +__printf(2, 3) +static void seq_con_printf(struct seq_file *seq, const char *fmt, ...) +{ + va_list args; + + va_start(args, fmt); + if (seq) + seq_vprintf(seq, fmt, args); + else + vprintk(fmt, args); + va_end(args); +} + +/* + * Get the number of stack entries to skip to get out of MM internals. @type is + * optional, and if set to NULL, assumes an allocation or free stack. + */ +static int get_stack_skipnr(const unsigned long stack_entries[], int num_entries, + const enum kfence_error_type *type) +{ + char buf[64]; + int skipnr, fallback = 0; + bool is_access_fault = false; + + if (type) { + /* Depending on error type, find different stack entries. */ + switch (*type) { + case KFENCE_ERROR_UAF: + case KFENCE_ERROR_OOB: + case KFENCE_ERROR_INVALID: + is_access_fault = true; + break; + case KFENCE_ERROR_CORRUPTION: + case KFENCE_ERROR_INVALID_FREE: + break; + } + } + + for (skipnr = 0; skipnr < num_entries; skipnr++) { + int len = scnprintf(buf, sizeof(buf), "%ps", (void *)stack_entries[skipnr]); + + if (is_access_fault) { + if (!strncmp(buf, KFENCE_SKIP_ARCH_FAULT_HANDLER, len)) + goto found; + } else { + if (str_has_prefix(buf, "kfence_") || str_has_prefix(buf, "__kfence_") || + !strncmp(buf, "__slab_free", len)) { + /* + * In case of tail calls from any of the below + * to any of the above. + */ + fallback = skipnr + 1; + } + + /* Also the *_bulk() variants by only checking prefixes. */ + if (str_has_prefix(buf, "kfree") || + str_has_prefix(buf, "kmem_cache_free") || + str_has_prefix(buf, "__kmalloc") || + str_has_prefix(buf, "kmem_cache_alloc")) + goto found; + } + } + if (fallback < num_entries) + return fallback; +found: + skipnr++; + return skipnr < num_entries ? skipnr : 0; +} + +static void kfence_print_stack(struct seq_file *seq, const struct kfence_metadata *meta, + bool show_alloc) +{ + const struct kfence_track *track = show_alloc ? &meta->alloc_track : &meta->free_track; + + if (track->num_stack_entries) { + /* Skip allocation/free internals stack. */ + int i = get_stack_skipnr(track->stack_entries, track->num_stack_entries, NULL); + + /* stack_trace_seq_print() does not exist; open code our own. */ + for (; i < track->num_stack_entries; i++) + seq_con_printf(seq, " %pS\n", (void *)track->stack_entries[i]); + } else { + seq_con_printf(seq, " no %s stack\n", show_alloc ? "allocation" : "deallocation"); + } +} + +void kfence_print_object(struct seq_file *seq, const struct kfence_metadata *meta) +{ + const int size = abs(meta->size); + const unsigned long start = meta->addr; + const struct kmem_cache *const cache = meta->cache; + + lockdep_assert_held(&meta->lock); + + if (meta->state == KFENCE_OBJECT_UNUSED) { + seq_con_printf(seq, "kfence-#%zd unused\n", meta - kfence_metadata); + return; + } + + seq_con_printf(seq, + "kfence-#%zd [0x" PTR_FMT "-0x" PTR_FMT + ", size=%d, cache=%s] allocated by task %d:\n", + meta - kfence_metadata, (void *)start, (void *)(start + size - 1), size, + (cache && cache->name) ? cache->name : "", meta->alloc_track.pid); + kfence_print_stack(seq, meta, true); + + if (meta->state == KFENCE_OBJECT_FREED) { + seq_con_printf(seq, "\nfreed by task %d:\n", meta->free_track.pid); + kfence_print_stack(seq, meta, false); + } +} + +/* + * Show bytes at @addr that are different from the expected canary values, up to + * @max_bytes. + */ +static void print_diff_canary(unsigned long address, size_t bytes_to_show, + const struct kfence_metadata *meta) +{ + const unsigned long show_until_addr = address + bytes_to_show; + const u8 *cur, *end; + + /* Do not show contents of object nor read into following guard page. */ + end = (const u8 *)(address < meta->addr ? min(show_until_addr, meta->addr) + : min(show_until_addr, PAGE_ALIGN(address))); + + pr_cont("["); + for (cur = (const u8 *)address; cur < end; cur++) { + if (*cur == KFENCE_CANARY_PATTERN(cur)) + pr_cont(" ."); + else if (IS_ENABLED(CONFIG_DEBUG_KERNEL)) + pr_cont(" 0x%02x", *cur); + else /* Do not leak kernel memory in non-debug builds. */ + pr_cont(" !"); + } + pr_cont(" ]"); +} + +void kfence_report_error(unsigned long address, const struct kfence_metadata *meta, + enum kfence_error_type type) +{ + unsigned long stack_entries[KFENCE_STACK_DEPTH] = { 0 }; + int num_stack_entries = stack_trace_save(stack_entries, KFENCE_STACK_DEPTH, 1); + int skipnr = get_stack_skipnr(stack_entries, num_stack_entries, &type); + const ptrdiff_t object_index = meta ? meta - kfence_metadata : -1; + + /* Require non-NULL meta, except if KFENCE_ERROR_INVALID. */ + if (WARN_ON(type != KFENCE_ERROR_INVALID && !meta)) + return; + + if (meta) + lockdep_assert_held(&meta->lock); + /* + * Because we may generate reports in printk-unfriendly parts of the + * kernel, such as scheduler code, the use of printk() could deadlock. + * Until such time that all printing code here is safe in all parts of + * the kernel, accept the risk, and just get our message out (given the + * system might already behave unpredictably due to the memory error). + * As such, also disable lockdep to hide warnings, and avoid disabling + * lockdep for the rest of the kernel. + */ + lockdep_off(); + + pr_err("==================================================================\n"); + /* Print report header. */ + switch (type) { + case KFENCE_ERROR_OOB: { + const bool left_of_object = address < meta->addr; + + pr_err("BUG: KFENCE: out-of-bounds in %pS\n\n", (void *)stack_entries[skipnr]); + pr_err("Out-of-bounds access at 0x" PTR_FMT " (%luB %s of kfence-#%zd):\n", + (void *)address, + left_of_object ? meta->addr - address : address - meta->addr, + left_of_object ? "left" : "right", object_index); + break; + } + case KFENCE_ERROR_UAF: + pr_err("BUG: KFENCE: use-after-free in %pS\n\n", (void *)stack_entries[skipnr]); + pr_err("Use-after-free access at 0x" PTR_FMT " (in kfence-#%zd):\n", + (void *)address, object_index); + break; + case KFENCE_ERROR_CORRUPTION: + pr_err("BUG: KFENCE: memory corruption in %pS\n\n", (void *)stack_entries[skipnr]); + pr_err("Corrupted memory at 0x" PTR_FMT " ", (void *)address); + print_diff_canary(address, 16, meta); + pr_cont(" (in kfence-#%zd):\n", object_index); + break; + case KFENCE_ERROR_INVALID: + pr_err("BUG: KFENCE: invalid access in %pS\n\n", (void *)stack_entries[skipnr]); + pr_err("Invalid access at 0x" PTR_FMT ":\n", (void *)address); + break; + case KFENCE_ERROR_INVALID_FREE: + pr_err("BUG: KFENCE: invalid free in %pS\n\n", (void *)stack_entries[skipnr]); + pr_err("Invalid free of 0x" PTR_FMT " (in kfence-#%zd):\n", (void *)address, + object_index); + break; + } + + /* Print stack trace and object info. */ + stack_trace_print(stack_entries + skipnr, num_stack_entries - skipnr, 0); + + if (meta) { + pr_err("\n"); + kfence_print_object(NULL, meta); + } + + /* Print report footer. */ + pr_err("\n"); + dump_stack_print_info(KERN_ERR); + pr_err("==================================================================\n"); + + lockdep_on(); + + if (panic_on_warn) + panic("panic_on_warn set ...\n"); + + /* We encountered a memory unsafety error, taint the kernel! */ + add_taint(TAINT_BAD_PAGE, LOCKDEP_STILL_OK); +} -- cgit v1.2.3 From d438fabce7860df3cb9337776be6f90b59ced8ed Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Thu, 25 Feb 2021 17:19:08 -0800 Subject: kfence: use pt_regs to generate stack trace on faults Instead of removing the fault handling portion of the stack trace based on the fault handler's name, just use struct pt_regs directly. Change kfence_handle_page_fault() to take a struct pt_regs, and plumb it through to kfence_report_error() for out-of-bounds, use-after-free, or invalid access errors, where pt_regs is used to generate the stack trace. If the kernel is a DEBUG_KERNEL, also show registers for more information. Link: https://lkml.kernel.org/r/20201105092133.2075331-1-elver@google.com Signed-off-by: Marco Elver Suggested-by: Mark Rutland Acked-by: Mark Rutland Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Jann Horn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm64/include/asm/kfence.h | 2 -- arch/arm64/mm/fault.c | 2 +- arch/x86/include/asm/kfence.h | 6 ---- arch/x86/mm/fault.c | 2 +- include/linux/kfence.h | 5 ++-- mm/kfence/core.c | 10 +++---- mm/kfence/kfence.h | 4 +-- mm/kfence/report.c | 63 +++++++++++++++++++++++------------------ 8 files changed, 48 insertions(+), 46 deletions(-) (limited to 'include') diff --git a/arch/arm64/include/asm/kfence.h b/arch/arm64/include/asm/kfence.h index 42a06f83850a..d061176d57ea 100644 --- a/arch/arm64/include/asm/kfence.h +++ b/arch/arm64/include/asm/kfence.h @@ -10,8 +10,6 @@ #include -#define KFENCE_SKIP_ARCH_FAULT_HANDLER "el1_sync" - static inline bool arch_kfence_init_pool(void) { return true; } static inline bool kfence_protect_page(unsigned long addr, bool protect) diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 42515900ab2e..56d9423ca59c 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -390,7 +390,7 @@ static void __do_kernel_fault(unsigned long addr, unsigned int esr, } else if (addr < PAGE_SIZE) { msg = "NULL pointer dereference"; } else { - if (kfence_handle_page_fault(addr)) + if (kfence_handle_page_fault(addr, regs)) return; msg = "paging request"; diff --git a/arch/x86/include/asm/kfence.h b/arch/x86/include/asm/kfence.h index a0659dbd93ea..97bbb4a9083a 100644 --- a/arch/x86/include/asm/kfence.h +++ b/arch/x86/include/asm/kfence.h @@ -16,12 +16,6 @@ #include #include -/* - * The page fault handler entry function, up to which the stack trace is - * truncated in reports. - */ -#define KFENCE_SKIP_ARCH_FAULT_HANDLER "asm_exc_page_fault" - /* Force 4K pages for __kfence_pool. */ static inline bool arch_kfence_init_pool(void) { diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 99fe6d3e690d..38868b4ce8b0 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -682,7 +682,7 @@ page_fault_oops(struct pt_regs *regs, unsigned long error_code, efi_crash_gracefully_on_page_fault(address); /* Only not-present faults should be handled by KFENCE. */ - if (!(error_code & X86_PF_PROT) && kfence_handle_page_fault(address)) + if (!(error_code & X86_PF_PROT) && kfence_handle_page_fault(address, regs)) return; oops: diff --git a/include/linux/kfence.h b/include/linux/kfence.h index 81f3911cb298..5a56bcf5606c 100644 --- a/include/linux/kfence.h +++ b/include/linux/kfence.h @@ -186,6 +186,7 @@ static __always_inline __must_check bool kfence_free(void *addr) /** * kfence_handle_page_fault() - perform page fault handling for KFENCE pages * @addr: faulting address + * @regs: current struct pt_regs (can be NULL, but shows full stack trace) * * Return: * * false - address outside KFENCE pool, @@ -196,7 +197,7 @@ static __always_inline __must_check bool kfence_free(void *addr) * cases KFENCE prints an error message and marks the offending page as * present, so that the kernel can proceed. */ -bool __must_check kfence_handle_page_fault(unsigned long addr); +bool __must_check kfence_handle_page_fault(unsigned long addr, struct pt_regs *regs); #else /* CONFIG_KFENCE */ @@ -209,7 +210,7 @@ static inline size_t kfence_ksize(const void *addr) { return 0; } static inline void *kfence_object_start(const void *addr) { return NULL; } static inline void __kfence_free(void *addr) { } static inline bool __must_check kfence_free(void *addr) { return false; } -static inline bool __must_check kfence_handle_page_fault(unsigned long addr) { return false; } +static inline bool __must_check kfence_handle_page_fault(unsigned long addr, struct pt_regs *regs) { return false; } #endif diff --git a/mm/kfence/core.c b/mm/kfence/core.c index d6a32c13336b..61c76670a7a9 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -216,7 +216,7 @@ static inline bool check_canary_byte(u8 *addr) return true; atomic_long_inc(&counters[KFENCE_COUNTER_BUGS]); - kfence_report_error((unsigned long)addr, addr_to_metadata((unsigned long)addr), + kfence_report_error((unsigned long)addr, NULL, addr_to_metadata((unsigned long)addr), KFENCE_ERROR_CORRUPTION); return false; } @@ -351,7 +351,7 @@ static void kfence_guarded_free(void *addr, struct kfence_metadata *meta, bool z if (meta->state != KFENCE_OBJECT_ALLOCATED || meta->addr != (unsigned long)addr) { /* Invalid or double-free, bail out. */ atomic_long_inc(&counters[KFENCE_COUNTER_BUGS]); - kfence_report_error((unsigned long)addr, meta, KFENCE_ERROR_INVALID_FREE); + kfence_report_error((unsigned long)addr, NULL, meta, KFENCE_ERROR_INVALID_FREE); raw_spin_unlock_irqrestore(&meta->lock, flags); return; } @@ -766,7 +766,7 @@ void __kfence_free(void *addr) kfence_guarded_free(addr, meta, false); } -bool kfence_handle_page_fault(unsigned long addr) +bool kfence_handle_page_fault(unsigned long addr, struct pt_regs *regs) { const int page_index = (addr - (unsigned long)__kfence_pool) / PAGE_SIZE; struct kfence_metadata *to_report = NULL; @@ -829,11 +829,11 @@ bool kfence_handle_page_fault(unsigned long addr) out: if (to_report) { - kfence_report_error(addr, to_report, error_type); + kfence_report_error(addr, regs, to_report, error_type); raw_spin_unlock_irqrestore(&to_report->lock, flags); } else { /* This may be a UAF or OOB access, but we can't be sure. */ - kfence_report_error(addr, NULL, KFENCE_ERROR_INVALID); + kfence_report_error(addr, regs, NULL, KFENCE_ERROR_INVALID); } return kfence_unprotect(addr); /* Unprotect and let access proceed. */ diff --git a/mm/kfence/kfence.h b/mm/kfence/kfence.h index 1014060f9707..0d83e628a97d 100644 --- a/mm/kfence/kfence.h +++ b/mm/kfence/kfence.h @@ -105,8 +105,8 @@ enum kfence_error_type { KFENCE_ERROR_INVALID_FREE, /* Invalid free. */ }; -void kfence_report_error(unsigned long address, const struct kfence_metadata *meta, - enum kfence_error_type type); +void kfence_report_error(unsigned long address, struct pt_regs *regs, + const struct kfence_metadata *meta, enum kfence_error_type type); void kfence_print_object(struct seq_file *seq, const struct kfence_metadata *meta); diff --git a/mm/kfence/report.c b/mm/kfence/report.c index 64f27c8d46a3..4dbfa9a382e4 100644 --- a/mm/kfence/report.c +++ b/mm/kfence/report.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -41,7 +42,6 @@ static int get_stack_skipnr(const unsigned long stack_entries[], int num_entries { char buf[64]; int skipnr, fallback = 0; - bool is_access_fault = false; if (type) { /* Depending on error type, find different stack entries. */ @@ -49,8 +49,12 @@ static int get_stack_skipnr(const unsigned long stack_entries[], int num_entries case KFENCE_ERROR_UAF: case KFENCE_ERROR_OOB: case KFENCE_ERROR_INVALID: - is_access_fault = true; - break; + /* + * kfence_handle_page_fault() may be called with pt_regs + * set to NULL; in that case we'll simply show the full + * stack trace. + */ + return 0; case KFENCE_ERROR_CORRUPTION: case KFENCE_ERROR_INVALID_FREE: break; @@ -60,26 +64,21 @@ static int get_stack_skipnr(const unsigned long stack_entries[], int num_entries for (skipnr = 0; skipnr < num_entries; skipnr++) { int len = scnprintf(buf, sizeof(buf), "%ps", (void *)stack_entries[skipnr]); - if (is_access_fault) { - if (!strncmp(buf, KFENCE_SKIP_ARCH_FAULT_HANDLER, len)) - goto found; - } else { - if (str_has_prefix(buf, "kfence_") || str_has_prefix(buf, "__kfence_") || - !strncmp(buf, "__slab_free", len)) { - /* - * In case of tail calls from any of the below - * to any of the above. - */ - fallback = skipnr + 1; - } - - /* Also the *_bulk() variants by only checking prefixes. */ - if (str_has_prefix(buf, "kfree") || - str_has_prefix(buf, "kmem_cache_free") || - str_has_prefix(buf, "__kmalloc") || - str_has_prefix(buf, "kmem_cache_alloc")) - goto found; + if (str_has_prefix(buf, "kfence_") || str_has_prefix(buf, "__kfence_") || + !strncmp(buf, "__slab_free", len)) { + /* + * In case of tail calls from any of the below + * to any of the above. + */ + fallback = skipnr + 1; } + + /* Also the *_bulk() variants by only checking prefixes. */ + if (str_has_prefix(buf, "kfree") || + str_has_prefix(buf, "kmem_cache_free") || + str_has_prefix(buf, "__kmalloc") || + str_has_prefix(buf, "kmem_cache_alloc")) + goto found; } if (fallback < num_entries) return fallback; @@ -157,13 +156,20 @@ static void print_diff_canary(unsigned long address, size_t bytes_to_show, pr_cont(" ]"); } -void kfence_report_error(unsigned long address, const struct kfence_metadata *meta, - enum kfence_error_type type) +void kfence_report_error(unsigned long address, struct pt_regs *regs, + const struct kfence_metadata *meta, enum kfence_error_type type) { unsigned long stack_entries[KFENCE_STACK_DEPTH] = { 0 }; - int num_stack_entries = stack_trace_save(stack_entries, KFENCE_STACK_DEPTH, 1); - int skipnr = get_stack_skipnr(stack_entries, num_stack_entries, &type); const ptrdiff_t object_index = meta ? meta - kfence_metadata : -1; + int num_stack_entries; + int skipnr = 0; + + if (regs) { + num_stack_entries = stack_trace_save_regs(regs, stack_entries, KFENCE_STACK_DEPTH, 0); + } else { + num_stack_entries = stack_trace_save(stack_entries, KFENCE_STACK_DEPTH, 1); + skipnr = get_stack_skipnr(stack_entries, num_stack_entries, &type); + } /* Require non-NULL meta, except if KFENCE_ERROR_INVALID. */ if (WARN_ON(type != KFENCE_ERROR_INVALID && !meta)) @@ -227,7 +233,10 @@ void kfence_report_error(unsigned long address, const struct kfence_metadata *me /* Print report footer. */ pr_err("\n"); - dump_stack_print_info(KERN_ERR); + if (IS_ENABLED(CONFIG_DEBUG_KERNEL) && regs) + show_regs(regs); + else + dump_stack_print_info(KERN_ERR); pr_err("==================================================================\n"); lockdep_on(); -- cgit v1.2.3 From d3fb45f370d927224af35d22d34ea465884afec8 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Thu, 25 Feb 2021 17:19:11 -0800 Subject: mm, kfence: insert KFENCE hooks for SLAB Inserts KFENCE hooks into the SLAB allocator. To pass the originally requested size to KFENCE, add an argument 'orig_size' to slab_alloc*(). The additional argument is required to preserve the requested original size for kmalloc() allocations, which uses size classes (e.g. an allocation of 272 bytes will return an object of size 512). Therefore, kmem_cache::size does not represent the kmalloc-caller's requested size, and we must introduce the argument 'orig_size' to propagate the originally requested size to KFENCE. Without the originally requested size, we would not be able to detect out-of-bounds accesses for objects placed at the end of a KFENCE object page if that object is not equal to the kmalloc-size class it was bucketed into. When KFENCE is disabled, there is no additional overhead, since slab_alloc*() functions are __always_inline. Link: https://lkml.kernel.org/r/20201103175841.3495947-5-elver@google.com Signed-off-by: Marco Elver Signed-off-by: Alexander Potapenko Reviewed-by: Dmitry Vyukov Co-developed-by: Marco Elver Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Andrey Konovalov Cc: Andrey Ryabinin Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Catalin Marinas Cc: Dave Hansen Cc: Eric Dumazet Cc: Greg Kroah-Hartman Cc: Hillf Danton Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Jann Horn Cc: Joern Engel Cc: Jonathan Corbet Cc: Kees Cook Cc: Mark Rutland Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: SeongJae Park Cc: Thomas Gleixner Cc: Vlastimil Babka Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab_def.h | 3 +++ mm/kfence/core.c | 2 ++ mm/slab.c | 38 +++++++++++++++++++++++++++++--------- mm/slab_common.c | 5 ++++- 4 files changed, 38 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index 9eb430c163c2..3aa5e1e73ab6 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -2,6 +2,7 @@ #ifndef _LINUX_SLAB_DEF_H #define _LINUX_SLAB_DEF_H +#include #include /* @@ -114,6 +115,8 @@ static inline unsigned int obj_to_index(const struct kmem_cache *cache, static inline int objs_per_slab_page(const struct kmem_cache *cache, const struct page *page) { + if (is_kfence_address(page_address(page))) + return 1; return cache->num; } diff --git a/mm/kfence/core.c b/mm/kfence/core.c index 61c76670a7a9..05c18aa11851 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -317,6 +317,8 @@ static void *kfence_guarded_alloc(struct kmem_cache *cache, size_t size, gfp_t g /* Set required struct page fields. */ page = virt_to_page(meta->addr); page->slab_cache = cache; + if (IS_ENABLED(CONFIG_SLAB)) + page->s_mem = addr; raw_spin_unlock_irqrestore(&meta->lock, flags); diff --git a/mm/slab.c b/mm/slab.c index 35c68d99d460..51fd424e0d6d 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -100,6 +100,7 @@ #include #include #include +#include #include #include #include @@ -3208,7 +3209,7 @@ must_grow: } static __always_inline void * -slab_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid, +slab_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid, size_t orig_size, unsigned long caller) { unsigned long save_flags; @@ -3221,6 +3222,10 @@ slab_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid, if (unlikely(!cachep)) return NULL; + ptr = kfence_alloc(cachep, orig_size, flags); + if (unlikely(ptr)) + goto out_hooks; + cache_alloc_debugcheck_before(cachep, flags); local_irq_save(save_flags); @@ -3253,6 +3258,7 @@ slab_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid, if (unlikely(slab_want_init_on_alloc(flags, cachep)) && ptr) memset(ptr, 0, cachep->object_size); +out_hooks: slab_post_alloc_hook(cachep, objcg, flags, 1, &ptr); return ptr; } @@ -3290,7 +3296,7 @@ __do_cache_alloc(struct kmem_cache *cachep, gfp_t flags) #endif /* CONFIG_NUMA */ static __always_inline void * -slab_alloc(struct kmem_cache *cachep, gfp_t flags, unsigned long caller) +slab_alloc(struct kmem_cache *cachep, gfp_t flags, size_t orig_size, unsigned long caller) { unsigned long save_flags; void *objp; @@ -3301,6 +3307,10 @@ slab_alloc(struct kmem_cache *cachep, gfp_t flags, unsigned long caller) if (unlikely(!cachep)) return NULL; + objp = kfence_alloc(cachep, orig_size, flags); + if (unlikely(objp)) + goto out; + cache_alloc_debugcheck_before(cachep, flags); local_irq_save(save_flags); objp = __do_cache_alloc(cachep, flags); @@ -3311,6 +3321,7 @@ slab_alloc(struct kmem_cache *cachep, gfp_t flags, unsigned long caller) if (unlikely(slab_want_init_on_alloc(flags, cachep)) && objp) memset(objp, 0, cachep->object_size); +out: slab_post_alloc_hook(cachep, objcg, flags, 1, &objp); return objp; } @@ -3416,6 +3427,12 @@ free_done: static __always_inline void __cache_free(struct kmem_cache *cachep, void *objp, unsigned long caller) { + if (is_kfence_address(objp)) { + kmemleak_free_recursive(objp, cachep->flags); + __kfence_free(objp); + return; + } + if (unlikely(slab_want_init_on_free(cachep))) memset(objp, 0, cachep->object_size); @@ -3482,7 +3499,7 @@ void ___cache_free(struct kmem_cache *cachep, void *objp, */ void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags) { - void *ret = slab_alloc(cachep, flags, _RET_IP_); + void *ret = slab_alloc(cachep, flags, cachep->object_size, _RET_IP_); trace_kmem_cache_alloc(_RET_IP_, ret, cachep->object_size, cachep->size, flags); @@ -3515,7 +3532,7 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, local_irq_disable(); for (i = 0; i < size; i++) { - void *objp = __do_cache_alloc(s, flags); + void *objp = kfence_alloc(s, s->object_size, flags) ?: __do_cache_alloc(s, flags); if (unlikely(!objp)) goto error; @@ -3548,7 +3565,7 @@ kmem_cache_alloc_trace(struct kmem_cache *cachep, gfp_t flags, size_t size) { void *ret; - ret = slab_alloc(cachep, flags, _RET_IP_); + ret = slab_alloc(cachep, flags, size, _RET_IP_); ret = kasan_kmalloc(cachep, ret, size, flags); trace_kmalloc(_RET_IP_, ret, @@ -3574,7 +3591,7 @@ EXPORT_SYMBOL(kmem_cache_alloc_trace); */ void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid) { - void *ret = slab_alloc_node(cachep, flags, nodeid, _RET_IP_); + void *ret = slab_alloc_node(cachep, flags, nodeid, cachep->object_size, _RET_IP_); trace_kmem_cache_alloc_node(_RET_IP_, ret, cachep->object_size, cachep->size, @@ -3592,7 +3609,7 @@ void *kmem_cache_alloc_node_trace(struct kmem_cache *cachep, { void *ret; - ret = slab_alloc_node(cachep, flags, nodeid, _RET_IP_); + ret = slab_alloc_node(cachep, flags, nodeid, size, _RET_IP_); ret = kasan_kmalloc(cachep, ret, size, flags); trace_kmalloc_node(_RET_IP_, ret, @@ -3673,7 +3690,7 @@ static __always_inline void *__do_kmalloc(size_t size, gfp_t flags, cachep = kmalloc_slab(size, flags); if (unlikely(ZERO_OR_NULL_PTR(cachep))) return cachep; - ret = slab_alloc(cachep, flags, caller); + ret = slab_alloc(cachep, flags, size, caller); ret = kasan_kmalloc(cachep, ret, size, flags); trace_kmalloc(caller, ret, @@ -4172,7 +4189,10 @@ void __check_heap_object(const void *ptr, unsigned long n, struct page *page, BUG_ON(objnr >= cachep->num); /* Find offset within object. */ - offset = ptr - index_to_obj(cachep, page, objnr) - obj_offset(cachep); + if (is_kfence_address(ptr)) + offset = ptr - kfence_object_start(ptr); + else + offset = ptr - index_to_obj(cachep, page, objnr) - obj_offset(cachep); /* Allow address range falling entirely within usercopy region. */ if (offset >= cachep->useroffset && diff --git a/mm/slab_common.c b/mm/slab_common.c index 7c8298c17145..284954ef1da5 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -430,6 +431,7 @@ static void slab_caches_to_rcu_destroy_workfn(struct work_struct *work) rcu_barrier(); list_for_each_entry_safe(s, s2, &to_destroy, list) { + kfence_shutdown_cache(s); #ifdef SLAB_SUPPORTS_SYSFS sysfs_slab_release(s); #else @@ -455,6 +457,7 @@ static int shutdown_cache(struct kmem_cache *s) list_add_tail(&s->list, &slab_caches_to_rcu_destroy); schedule_work(&slab_caches_to_rcu_destroy_work); } else { + kfence_shutdown_cache(s); #ifdef SLAB_SUPPORTS_SYSFS sysfs_slab_unlink(s); sysfs_slab_release(s); @@ -1235,7 +1238,7 @@ size_t ksize(const void *objp) if (unlikely(ZERO_OR_NULL_PTR(objp)) || !kasan_check_byte(objp)) return 0; - size = __ksize(objp); + size = kfence_ksize(objp) ?: __ksize(objp); /* * We assume that ksize callers could use whole allocated area, * so we need to unpoison this area. -- cgit v1.2.3 From b89fb5ef0ce611b5db8eb9d3a5a7fcaab2cbe9e4 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Thu, 25 Feb 2021 17:19:16 -0800 Subject: mm, kfence: insert KFENCE hooks for SLUB Inserts KFENCE hooks into the SLUB allocator. To pass the originally requested size to KFENCE, add an argument 'orig_size' to slab_alloc*(). The additional argument is required to preserve the requested original size for kmalloc() allocations, which uses size classes (e.g. an allocation of 272 bytes will return an object of size 512). Therefore, kmem_cache::size does not represent the kmalloc-caller's requested size, and we must introduce the argument 'orig_size' to propagate the originally requested size to KFENCE. Without the originally requested size, we would not be able to detect out-of-bounds accesses for objects placed at the end of a KFENCE object page if that object is not equal to the kmalloc-size class it was bucketed into. When KFENCE is disabled, there is no additional overhead, since slab_alloc*() functions are __always_inline. Link: https://lkml.kernel.org/r/20201103175841.3495947-6-elver@google.com Signed-off-by: Marco Elver Signed-off-by: Alexander Potapenko Reviewed-by: Dmitry Vyukov Reviewed-by: Jann Horn Co-developed-by: Marco Elver Cc: Andrey Konovalov Cc: Andrey Ryabinin Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christopher Lameter Cc: Dave Hansen Cc: David Rientjes Cc: Eric Dumazet Cc: Greg Kroah-Hartman Cc: Hillf Danton Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Joern Engel Cc: Jonathan Corbet Cc: Joonsoo Kim Cc: Kees Cook Cc: Mark Rutland Cc: Paul E. McKenney Cc: Pekka Enberg Cc: Peter Zijlstra Cc: SeongJae Park Cc: Thomas Gleixner Cc: Vlastimil Babka Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slub_def.h | 3 +++ mm/kfence/core.c | 2 ++ mm/slub.c | 60 +++++++++++++++++++++++++++++++++++++----------- 3 files changed, 51 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 1be0ed5befa1..dcde82a4434c 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -7,6 +7,7 @@ * * (C) 2007 SGI, Christoph Lameter */ +#include #include #include @@ -185,6 +186,8 @@ static inline unsigned int __obj_to_index(const struct kmem_cache *cache, static inline unsigned int obj_to_index(const struct kmem_cache *cache, const struct page *page, void *obj) { + if (is_kfence_address(obj)) + return 0; return __obj_to_index(cache, page_address(page), obj); } diff --git a/mm/kfence/core.c b/mm/kfence/core.c index 05c18aa11851..7692af715fdb 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -317,6 +317,8 @@ static void *kfence_guarded_alloc(struct kmem_cache *cache, size_t size, gfp_t g /* Set required struct page fields. */ page = virt_to_page(meta->addr); page->slab_cache = cache; + if (IS_ENABLED(CONFIG_SLUB)) + page->objects = 1; if (IS_ENABLED(CONFIG_SLAB)) page->s_mem = addr; diff --git a/mm/slub.c b/mm/slub.c index b2833ce85c92..383616af28c4 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include @@ -1570,6 +1571,11 @@ static inline bool slab_free_freelist_hook(struct kmem_cache *s, void *old_tail = *tail ? *tail : *head; int rsize; + if (is_kfence_address(next)) { + slab_free_hook(s, next); + return true; + } + /* Head and tail of the reconstructed freelist */ *head = NULL; *tail = NULL; @@ -2809,7 +2815,7 @@ static __always_inline void maybe_wipe_obj_freeptr(struct kmem_cache *s, * Otherwise we can simply pick the next object from the lockless free list. */ static __always_inline void *slab_alloc_node(struct kmem_cache *s, - gfp_t gfpflags, int node, unsigned long addr) + gfp_t gfpflags, int node, unsigned long addr, size_t orig_size) { void *object; struct kmem_cache_cpu *c; @@ -2820,6 +2826,11 @@ static __always_inline void *slab_alloc_node(struct kmem_cache *s, s = slab_pre_alloc_hook(s, &objcg, 1, gfpflags); if (!s) return NULL; + + object = kfence_alloc(s, orig_size, gfpflags); + if (unlikely(object)) + goto out; + redo: /* * Must read kmem_cache cpu data via this cpu ptr. Preemption is @@ -2892,20 +2903,21 @@ redo: if (unlikely(slab_want_init_on_alloc(gfpflags, s)) && object) memset(kasan_reset_tag(object), 0, s->object_size); +out: slab_post_alloc_hook(s, objcg, gfpflags, 1, &object); return object; } static __always_inline void *slab_alloc(struct kmem_cache *s, - gfp_t gfpflags, unsigned long addr) + gfp_t gfpflags, unsigned long addr, size_t orig_size) { - return slab_alloc_node(s, gfpflags, NUMA_NO_NODE, addr); + return slab_alloc_node(s, gfpflags, NUMA_NO_NODE, addr, orig_size); } void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags) { - void *ret = slab_alloc(s, gfpflags, _RET_IP_); + void *ret = slab_alloc(s, gfpflags, _RET_IP_, s->object_size); trace_kmem_cache_alloc(_RET_IP_, ret, s->object_size, s->size, gfpflags); @@ -2917,7 +2929,7 @@ EXPORT_SYMBOL(kmem_cache_alloc); #ifdef CONFIG_TRACING void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t gfpflags, size_t size) { - void *ret = slab_alloc(s, gfpflags, _RET_IP_); + void *ret = slab_alloc(s, gfpflags, _RET_IP_, size); trace_kmalloc(_RET_IP_, ret, size, s->size, gfpflags); ret = kasan_kmalloc(s, ret, size, gfpflags); return ret; @@ -2928,7 +2940,7 @@ EXPORT_SYMBOL(kmem_cache_alloc_trace); #ifdef CONFIG_NUMA void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t gfpflags, int node) { - void *ret = slab_alloc_node(s, gfpflags, node, _RET_IP_); + void *ret = slab_alloc_node(s, gfpflags, node, _RET_IP_, s->object_size); trace_kmem_cache_alloc_node(_RET_IP_, ret, s->object_size, s->size, gfpflags, node); @@ -2942,7 +2954,7 @@ void *kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, int node, size_t size) { - void *ret = slab_alloc_node(s, gfpflags, node, _RET_IP_); + void *ret = slab_alloc_node(s, gfpflags, node, _RET_IP_, size); trace_kmalloc_node(_RET_IP_, ret, size, s->size, gfpflags, node); @@ -2976,6 +2988,9 @@ static void __slab_free(struct kmem_cache *s, struct page *page, stat(s, FREE_SLOWPATH); + if (kfence_free(head)) + return; + if (kmem_cache_debug(s) && !free_debug_processing(s, page, head, tail, cnt, addr)) return; @@ -3220,6 +3235,13 @@ int build_detached_freelist(struct kmem_cache *s, size_t size, df->s = cache_from_obj(s, object); /* Support for memcg */ } + if (is_kfence_address(object)) { + slab_free_hook(df->s, object); + __kfence_free(object); + p[size] = NULL; /* mark object processed */ + return size; + } + /* Start new detached freelist */ df->page = page; set_freepointer(df->s, object, NULL); @@ -3295,8 +3317,14 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, c = this_cpu_ptr(s->cpu_slab); for (i = 0; i < size; i++) { - void *object = c->freelist; + void *object = kfence_alloc(s, s->object_size, flags); + if (unlikely(object)) { + p[i] = object; + continue; + } + + object = c->freelist; if (unlikely(!object)) { /* * We may have removed an object from c->freelist using @@ -4021,7 +4049,7 @@ void *__kmalloc(size_t size, gfp_t flags) if (unlikely(ZERO_OR_NULL_PTR(s))) return s; - ret = slab_alloc(s, flags, _RET_IP_); + ret = slab_alloc(s, flags, _RET_IP_, size); trace_kmalloc(_RET_IP_, ret, size, s->size, flags); @@ -4069,7 +4097,7 @@ void *__kmalloc_node(size_t size, gfp_t flags, int node) if (unlikely(ZERO_OR_NULL_PTR(s))) return s; - ret = slab_alloc_node(s, flags, node, _RET_IP_); + ret = slab_alloc_node(s, flags, node, _RET_IP_, size); trace_kmalloc_node(_RET_IP_, ret, size, s->size, flags, node); @@ -4095,6 +4123,7 @@ void __check_heap_object(const void *ptr, unsigned long n, struct page *page, struct kmem_cache *s; unsigned int offset; size_t object_size; + bool is_kfence = is_kfence_address(ptr); ptr = kasan_reset_tag(ptr); @@ -4107,10 +4136,13 @@ void __check_heap_object(const void *ptr, unsigned long n, struct page *page, to_user, 0, n); /* Find offset within object. */ - offset = (ptr - page_address(page)) % s->size; + if (is_kfence) + offset = ptr - kfence_object_start(ptr); + else + offset = (ptr - page_address(page)) % s->size; /* Adjust for redzone and reject if within the redzone. */ - if (kmem_cache_debug_flags(s, SLAB_RED_ZONE)) { + if (!is_kfence && kmem_cache_debug_flags(s, SLAB_RED_ZONE)) { if (offset < s->red_left_pad) usercopy_abort("SLUB object in left red zone", s->name, to_user, offset, n); @@ -4527,7 +4559,7 @@ void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, unsigned long caller) if (unlikely(ZERO_OR_NULL_PTR(s))) return s; - ret = slab_alloc(s, gfpflags, caller); + ret = slab_alloc(s, gfpflags, caller, size); /* Honor the call site pointer we received. */ trace_kmalloc(caller, ret, size, s->size, gfpflags); @@ -4558,7 +4590,7 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags, if (unlikely(ZERO_OR_NULL_PTR(s))) return s; - ret = slab_alloc_node(s, gfpflags, node, caller); + ret = slab_alloc_node(s, gfpflags, node, caller, size); /* Honor the call site pointer we received. */ trace_kmalloc_node(caller, ret, size, s->size, gfpflags, node); -- cgit v1.2.3 From bc8fbc5f305aecf63423da91e5faf4c0ce40bf38 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Thu, 25 Feb 2021 17:19:31 -0800 Subject: kfence: add test suite Add KFENCE test suite, testing various error detection scenarios. Makes use of KUnit for test organization. Since KFENCE's interface to obtain error reports is via the console, the test verifies that KFENCE outputs expected reports to the console. [elver@google.com: fix typo in test] Link: https://lkml.kernel.org/r/X9lHQExmHGvETxY4@elver.google.com [elver@google.com: show access type in report] Link: https://lkml.kernel.org/r/20210111091544.3287013-2-elver@google.com Link: https://lkml.kernel.org/r/20201103175841.3495947-9-elver@google.com Signed-off-by: Alexander Potapenko Signed-off-by: Marco Elver Reviewed-by: Dmitry Vyukov Co-developed-by: Alexander Potapenko Reviewed-by: Jann Horn Cc: Andrey Konovalov Cc: Andrey Ryabinin Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christopher Lameter Cc: Dave Hansen Cc: David Rientjes Cc: Eric Dumazet Cc: Greg Kroah-Hartman Cc: Hillf Danton Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Joern Engel Cc: Jonathan Corbet Cc: Joonsoo Kim Cc: Kees Cook Cc: Mark Rutland Cc: Paul E. McKenney Cc: Pekka Enberg Cc: Peter Zijlstra Cc: SeongJae Park Cc: Thomas Gleixner Cc: Vlastimil Babka Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/dev-tools/kfence.rst | 12 +- arch/arm64/mm/fault.c | 2 +- arch/x86/mm/fault.c | 3 +- include/linux/kfence.h | 9 +- lib/Kconfig.kfence | 13 + mm/kfence/Makefile | 3 + mm/kfence/core.c | 11 +- mm/kfence/kfence.h | 2 +- mm/kfence/kfence_test.c | 858 +++++++++++++++++++++++++++++++++++++ mm/kfence/report.c | 27 +- 10 files changed, 915 insertions(+), 25 deletions(-) create mode 100644 mm/kfence/kfence_test.c (limited to 'include') diff --git a/Documentation/dev-tools/kfence.rst b/Documentation/dev-tools/kfence.rst index 0e2fb6ef3016..58a0a5fa1ddc 100644 --- a/Documentation/dev-tools/kfence.rst +++ b/Documentation/dev-tools/kfence.rst @@ -65,9 +65,9 @@ Error reports A typical out-of-bounds access looks like this:: ================================================================== - BUG: KFENCE: out-of-bounds in test_out_of_bounds_read+0xa3/0x22b + BUG: KFENCE: out-of-bounds read in test_out_of_bounds_read+0xa3/0x22b - Out-of-bounds access at 0xffffffffb672efff (1B left of kfence-#17): + Out-of-bounds read at 0xffffffffb672efff (1B left of kfence-#17): test_out_of_bounds_read+0xa3/0x22b kunit_try_run_case+0x51/0x85 kunit_generic_run_threadfn_adapter+0x16/0x30 @@ -94,9 +94,9 @@ its origin. Note that, real kernel addresses are only shown for Use-after-free accesses are reported as:: ================================================================== - BUG: KFENCE: use-after-free in test_use_after_free_read+0xb3/0x143 + BUG: KFENCE: use-after-free read in test_use_after_free_read+0xb3/0x143 - Use-after-free access at 0xffffffffb673dfe0 (in kfence-#24): + Use-after-free read at 0xffffffffb673dfe0 (in kfence-#24): test_use_after_free_read+0xb3/0x143 kunit_try_run_case+0x51/0x85 kunit_generic_run_threadfn_adapter+0x16/0x30 @@ -193,9 +193,9 @@ where it was not possible to determine an associated object, e.g. if adjacent object pages had not yet been allocated:: ================================================================== - BUG: KFENCE: invalid access in test_invalid_access+0x26/0xe0 + BUG: KFENCE: invalid read in test_invalid_access+0x26/0xe0 - Invalid access at 0xffffffffb670b00a: + Invalid read at 0xffffffffb670b00a: test_invalid_access+0x26/0xe0 kunit_try_run_case+0x51/0x85 kunit_generic_run_threadfn_adapter+0x16/0x30 diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 56d9423ca59c..f37d4e3830b7 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -390,7 +390,7 @@ static void __do_kernel_fault(unsigned long addr, unsigned int esr, } else if (addr < PAGE_SIZE) { msg = "NULL pointer dereference"; } else { - if (kfence_handle_page_fault(addr, regs)) + if (kfence_handle_page_fault(addr, esr & ESR_ELx_WNR, regs)) return; msg = "paging request"; diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 38868b4ce8b0..a73347e2cdfc 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -682,7 +682,8 @@ page_fault_oops(struct pt_regs *regs, unsigned long error_code, efi_crash_gracefully_on_page_fault(address); /* Only not-present faults should be handled by KFENCE. */ - if (!(error_code & X86_PF_PROT) && kfence_handle_page_fault(address, regs)) + if (!(error_code & X86_PF_PROT) && + kfence_handle_page_fault(address, error_code & X86_PF_WRITE, regs)) return; oops: diff --git a/include/linux/kfence.h b/include/linux/kfence.h index 5a56bcf5606c..a70d1ea03532 100644 --- a/include/linux/kfence.h +++ b/include/linux/kfence.h @@ -186,6 +186,7 @@ static __always_inline __must_check bool kfence_free(void *addr) /** * kfence_handle_page_fault() - perform page fault handling for KFENCE pages * @addr: faulting address + * @is_write: is access a write * @regs: current struct pt_regs (can be NULL, but shows full stack trace) * * Return: @@ -197,7 +198,7 @@ static __always_inline __must_check bool kfence_free(void *addr) * cases KFENCE prints an error message and marks the offending page as * present, so that the kernel can proceed. */ -bool __must_check kfence_handle_page_fault(unsigned long addr, struct pt_regs *regs); +bool __must_check kfence_handle_page_fault(unsigned long addr, bool is_write, struct pt_regs *regs); #else /* CONFIG_KFENCE */ @@ -210,7 +211,11 @@ static inline size_t kfence_ksize(const void *addr) { return 0; } static inline void *kfence_object_start(const void *addr) { return NULL; } static inline void __kfence_free(void *addr) { } static inline bool __must_check kfence_free(void *addr) { return false; } -static inline bool __must_check kfence_handle_page_fault(unsigned long addr, struct pt_regs *regs) { return false; } +static inline bool __must_check kfence_handle_page_fault(unsigned long addr, bool is_write, + struct pt_regs *regs) +{ + return false; +} #endif diff --git a/lib/Kconfig.kfence b/lib/Kconfig.kfence index 605125ac2ae0..78f50ccb3b45 100644 --- a/lib/Kconfig.kfence +++ b/lib/Kconfig.kfence @@ -66,4 +66,17 @@ config KFENCE_STRESS_TEST_FAULTS Only for KFENCE testing; set to 0 if you are not a KFENCE developer. +config KFENCE_KUNIT_TEST + tristate "KFENCE integration test suite" if !KUNIT_ALL_TESTS + default KUNIT_ALL_TESTS + depends on TRACEPOINTS && KUNIT + help + Test suite for KFENCE, testing various error detection scenarios with + various allocation types, and checking that reports are correctly + output to console. + + Say Y here if you want the test to be built into the kernel and run + during boot; say M if you want the test to build as a module; say N + if you are unsure. + endif # KFENCE diff --git a/mm/kfence/Makefile b/mm/kfence/Makefile index d991e9a349f0..6872cd5e5390 100644 --- a/mm/kfence/Makefile +++ b/mm/kfence/Makefile @@ -1,3 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_KFENCE) := core.o report.o + +CFLAGS_kfence_test.o := -g -fno-omit-frame-pointer -fno-optimize-sibling-calls +obj-$(CONFIG_KFENCE_KUNIT_TEST) += kfence_test.o diff --git a/mm/kfence/core.c b/mm/kfence/core.c index 7692af715fdb..cfe3d32ac5b7 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -216,7 +216,7 @@ static inline bool check_canary_byte(u8 *addr) return true; atomic_long_inc(&counters[KFENCE_COUNTER_BUGS]); - kfence_report_error((unsigned long)addr, NULL, addr_to_metadata((unsigned long)addr), + kfence_report_error((unsigned long)addr, false, NULL, addr_to_metadata((unsigned long)addr), KFENCE_ERROR_CORRUPTION); return false; } @@ -355,7 +355,8 @@ static void kfence_guarded_free(void *addr, struct kfence_metadata *meta, bool z if (meta->state != KFENCE_OBJECT_ALLOCATED || meta->addr != (unsigned long)addr) { /* Invalid or double-free, bail out. */ atomic_long_inc(&counters[KFENCE_COUNTER_BUGS]); - kfence_report_error((unsigned long)addr, NULL, meta, KFENCE_ERROR_INVALID_FREE); + kfence_report_error((unsigned long)addr, false, NULL, meta, + KFENCE_ERROR_INVALID_FREE); raw_spin_unlock_irqrestore(&meta->lock, flags); return; } @@ -770,7 +771,7 @@ void __kfence_free(void *addr) kfence_guarded_free(addr, meta, false); } -bool kfence_handle_page_fault(unsigned long addr, struct pt_regs *regs) +bool kfence_handle_page_fault(unsigned long addr, bool is_write, struct pt_regs *regs) { const int page_index = (addr - (unsigned long)__kfence_pool) / PAGE_SIZE; struct kfence_metadata *to_report = NULL; @@ -833,11 +834,11 @@ bool kfence_handle_page_fault(unsigned long addr, struct pt_regs *regs) out: if (to_report) { - kfence_report_error(addr, regs, to_report, error_type); + kfence_report_error(addr, is_write, regs, to_report, error_type); raw_spin_unlock_irqrestore(&to_report->lock, flags); } else { /* This may be a UAF or OOB access, but we can't be sure. */ - kfence_report_error(addr, regs, NULL, KFENCE_ERROR_INVALID); + kfence_report_error(addr, is_write, regs, NULL, KFENCE_ERROR_INVALID); } return kfence_unprotect(addr); /* Unprotect and let access proceed. */ diff --git a/mm/kfence/kfence.h b/mm/kfence/kfence.h index 0d83e628a97d..1accc840dbbe 100644 --- a/mm/kfence/kfence.h +++ b/mm/kfence/kfence.h @@ -105,7 +105,7 @@ enum kfence_error_type { KFENCE_ERROR_INVALID_FREE, /* Invalid free. */ }; -void kfence_report_error(unsigned long address, struct pt_regs *regs, +void kfence_report_error(unsigned long address, bool is_write, struct pt_regs *regs, const struct kfence_metadata *meta, enum kfence_error_type type); void kfence_print_object(struct seq_file *seq, const struct kfence_metadata *meta); diff --git a/mm/kfence/kfence_test.c b/mm/kfence/kfence_test.c new file mode 100644 index 000000000000..db1bb596acaf --- /dev/null +++ b/mm/kfence/kfence_test.c @@ -0,0 +1,858 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Test cases for KFENCE memory safety error detector. Since the interface with + * which KFENCE's reports are obtained is via the console, this is the output we + * should verify. For each test case checks the presence (or absence) of + * generated reports. Relies on 'console' tracepoint to capture reports as they + * appear in the kernel log. + * + * Copyright (C) 2020, Google LLC. + * Author: Alexander Potapenko + * Marco Elver + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "kfence.h" + +/* Report as observed from console. */ +static struct { + spinlock_t lock; + int nlines; + char lines[2][256]; +} observed = { + .lock = __SPIN_LOCK_UNLOCKED(observed.lock), +}; + +/* Probe for console output: obtains observed lines of interest. */ +static void probe_console(void *ignore, const char *buf, size_t len) +{ + unsigned long flags; + int nlines; + + spin_lock_irqsave(&observed.lock, flags); + nlines = observed.nlines; + + if (strnstr(buf, "BUG: KFENCE: ", len) && strnstr(buf, "test_", len)) { + /* + * KFENCE report and related to the test. + * + * The provided @buf is not NUL-terminated; copy no more than + * @len bytes and let strscpy() add the missing NUL-terminator. + */ + strscpy(observed.lines[0], buf, min(len + 1, sizeof(observed.lines[0]))); + nlines = 1; + } else if (nlines == 1 && (strnstr(buf, "at 0x", len) || strnstr(buf, "of 0x", len))) { + strscpy(observed.lines[nlines++], buf, min(len + 1, sizeof(observed.lines[0]))); + } + + WRITE_ONCE(observed.nlines, nlines); /* Publish new nlines. */ + spin_unlock_irqrestore(&observed.lock, flags); +} + +/* Check if a report related to the test exists. */ +static bool report_available(void) +{ + return READ_ONCE(observed.nlines) == ARRAY_SIZE(observed.lines); +} + +/* Information we expect in a report. */ +struct expect_report { + enum kfence_error_type type; /* The type or error. */ + void *fn; /* Function pointer to expected function where access occurred. */ + char *addr; /* Address at which the bad access occurred. */ + bool is_write; /* Is access a write. */ +}; + +static const char *get_access_type(const struct expect_report *r) +{ + return r->is_write ? "write" : "read"; +} + +/* Check observed report matches information in @r. */ +static bool report_matches(const struct expect_report *r) +{ + bool ret = false; + unsigned long flags; + typeof(observed.lines) expect; + const char *end; + char *cur; + + /* Doubled-checked locking. */ + if (!report_available()) + return false; + + /* Generate expected report contents. */ + + /* Title */ + cur = expect[0]; + end = &expect[0][sizeof(expect[0]) - 1]; + switch (r->type) { + case KFENCE_ERROR_OOB: + cur += scnprintf(cur, end - cur, "BUG: KFENCE: out-of-bounds %s", + get_access_type(r)); + break; + case KFENCE_ERROR_UAF: + cur += scnprintf(cur, end - cur, "BUG: KFENCE: use-after-free %s", + get_access_type(r)); + break; + case KFENCE_ERROR_CORRUPTION: + cur += scnprintf(cur, end - cur, "BUG: KFENCE: memory corruption"); + break; + case KFENCE_ERROR_INVALID: + cur += scnprintf(cur, end - cur, "BUG: KFENCE: invalid %s", + get_access_type(r)); + break; + case KFENCE_ERROR_INVALID_FREE: + cur += scnprintf(cur, end - cur, "BUG: KFENCE: invalid free"); + break; + } + + scnprintf(cur, end - cur, " in %pS", r->fn); + /* The exact offset won't match, remove it; also strip module name. */ + cur = strchr(expect[0], '+'); + if (cur) + *cur = '\0'; + + /* Access information */ + cur = expect[1]; + end = &expect[1][sizeof(expect[1]) - 1]; + + switch (r->type) { + case KFENCE_ERROR_OOB: + cur += scnprintf(cur, end - cur, "Out-of-bounds %s at", get_access_type(r)); + break; + case KFENCE_ERROR_UAF: + cur += scnprintf(cur, end - cur, "Use-after-free %s at", get_access_type(r)); + break; + case KFENCE_ERROR_CORRUPTION: + cur += scnprintf(cur, end - cur, "Corrupted memory at"); + break; + case KFENCE_ERROR_INVALID: + cur += scnprintf(cur, end - cur, "Invalid %s at", get_access_type(r)); + break; + case KFENCE_ERROR_INVALID_FREE: + cur += scnprintf(cur, end - cur, "Invalid free of"); + break; + } + + cur += scnprintf(cur, end - cur, " 0x" PTR_FMT, (void *)r->addr); + + spin_lock_irqsave(&observed.lock, flags); + if (!report_available()) + goto out; /* A new report is being captured. */ + + /* Finally match expected output to what we actually observed. */ + ret = strstr(observed.lines[0], expect[0]) && strstr(observed.lines[1], expect[1]); +out: + spin_unlock_irqrestore(&observed.lock, flags); + return ret; +} + +/* ===== Test cases ===== */ + +#define TEST_PRIV_WANT_MEMCACHE ((void *)1) + +/* Cache used by tests; if NULL, allocate from kmalloc instead. */ +static struct kmem_cache *test_cache; + +static size_t setup_test_cache(struct kunit *test, size_t size, slab_flags_t flags, + void (*ctor)(void *)) +{ + if (test->priv != TEST_PRIV_WANT_MEMCACHE) + return size; + + kunit_info(test, "%s: size=%zu, ctor=%ps\n", __func__, size, ctor); + + /* + * Use SLAB_NOLEAKTRACE to prevent merging with existing caches. Any + * other flag in SLAB_NEVER_MERGE also works. Use SLAB_ACCOUNT to + * allocate via memcg, if enabled. + */ + flags |= SLAB_NOLEAKTRACE | SLAB_ACCOUNT; + test_cache = kmem_cache_create("test", size, 1, flags, ctor); + KUNIT_ASSERT_TRUE_MSG(test, test_cache, "could not create cache"); + + return size; +} + +static void test_cache_destroy(void) +{ + if (!test_cache) + return; + + kmem_cache_destroy(test_cache); + test_cache = NULL; +} + +static inline size_t kmalloc_cache_alignment(size_t size) +{ + return kmalloc_caches[kmalloc_type(GFP_KERNEL)][kmalloc_index(size)]->align; +} + +/* Must always inline to match stack trace against caller. */ +static __always_inline void test_free(void *ptr) +{ + if (test_cache) + kmem_cache_free(test_cache, ptr); + else + kfree(ptr); +} + +/* + * If this should be a KFENCE allocation, and on which side the allocation and + * the closest guard page should be. + */ +enum allocation_policy { + ALLOCATE_ANY, /* KFENCE, any side. */ + ALLOCATE_LEFT, /* KFENCE, left side of page. */ + ALLOCATE_RIGHT, /* KFENCE, right side of page. */ + ALLOCATE_NONE, /* No KFENCE allocation. */ +}; + +/* + * Try to get a guarded allocation from KFENCE. Uses either kmalloc() or the + * current test_cache if set up. + */ +static void *test_alloc(struct kunit *test, size_t size, gfp_t gfp, enum allocation_policy policy) +{ + void *alloc; + unsigned long timeout, resched_after; + const char *policy_name; + + switch (policy) { + case ALLOCATE_ANY: + policy_name = "any"; + break; + case ALLOCATE_LEFT: + policy_name = "left"; + break; + case ALLOCATE_RIGHT: + policy_name = "right"; + break; + case ALLOCATE_NONE: + policy_name = "none"; + break; + } + + kunit_info(test, "%s: size=%zu, gfp=%x, policy=%s, cache=%i\n", __func__, size, gfp, + policy_name, !!test_cache); + + /* + * 100x the sample interval should be more than enough to ensure we get + * a KFENCE allocation eventually. + */ + timeout = jiffies + msecs_to_jiffies(100 * CONFIG_KFENCE_SAMPLE_INTERVAL); + /* + * Especially for non-preemption kernels, ensure the allocation-gate + * timer can catch up: after @resched_after, every failed allocation + * attempt yields, to ensure the allocation-gate timer is scheduled. + */ + resched_after = jiffies + msecs_to_jiffies(CONFIG_KFENCE_SAMPLE_INTERVAL); + do { + if (test_cache) + alloc = kmem_cache_alloc(test_cache, gfp); + else + alloc = kmalloc(size, gfp); + + if (is_kfence_address(alloc)) { + struct page *page = virt_to_head_page(alloc); + struct kmem_cache *s = test_cache ?: kmalloc_caches[kmalloc_type(GFP_KERNEL)][kmalloc_index(size)]; + + /* + * Verify that various helpers return the right values + * even for KFENCE objects; these are required so that + * memcg accounting works correctly. + */ + KUNIT_EXPECT_EQ(test, obj_to_index(s, page, alloc), 0U); + KUNIT_EXPECT_EQ(test, objs_per_slab_page(s, page), 1); + + if (policy == ALLOCATE_ANY) + return alloc; + if (policy == ALLOCATE_LEFT && IS_ALIGNED((unsigned long)alloc, PAGE_SIZE)) + return alloc; + if (policy == ALLOCATE_RIGHT && + !IS_ALIGNED((unsigned long)alloc, PAGE_SIZE)) + return alloc; + } else if (policy == ALLOCATE_NONE) + return alloc; + + test_free(alloc); + + if (time_after(jiffies, resched_after)) + cond_resched(); + } while (time_before(jiffies, timeout)); + + KUNIT_ASSERT_TRUE_MSG(test, false, "failed to allocate from KFENCE"); + return NULL; /* Unreachable. */ +} + +static void test_out_of_bounds_read(struct kunit *test) +{ + size_t size = 32; + struct expect_report expect = { + .type = KFENCE_ERROR_OOB, + .fn = test_out_of_bounds_read, + .is_write = false, + }; + char *buf; + + setup_test_cache(test, size, 0, NULL); + + /* + * If we don't have our own cache, adjust based on alignment, so that we + * actually access guard pages on either side. + */ + if (!test_cache) + size = kmalloc_cache_alignment(size); + + /* Test both sides. */ + + buf = test_alloc(test, size, GFP_KERNEL, ALLOCATE_LEFT); + expect.addr = buf - 1; + READ_ONCE(*expect.addr); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); + test_free(buf); + + buf = test_alloc(test, size, GFP_KERNEL, ALLOCATE_RIGHT); + expect.addr = buf + size; + READ_ONCE(*expect.addr); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); + test_free(buf); +} + +static void test_out_of_bounds_write(struct kunit *test) +{ + size_t size = 32; + struct expect_report expect = { + .type = KFENCE_ERROR_OOB, + .fn = test_out_of_bounds_write, + .is_write = true, + }; + char *buf; + + setup_test_cache(test, size, 0, NULL); + buf = test_alloc(test, size, GFP_KERNEL, ALLOCATE_LEFT); + expect.addr = buf - 1; + WRITE_ONCE(*expect.addr, 42); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); + test_free(buf); +} + +static void test_use_after_free_read(struct kunit *test) +{ + const size_t size = 32; + struct expect_report expect = { + .type = KFENCE_ERROR_UAF, + .fn = test_use_after_free_read, + .is_write = false, + }; + + setup_test_cache(test, size, 0, NULL); + expect.addr = test_alloc(test, size, GFP_KERNEL, ALLOCATE_ANY); + test_free(expect.addr); + READ_ONCE(*expect.addr); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); +} + +static void test_double_free(struct kunit *test) +{ + const size_t size = 32; + struct expect_report expect = { + .type = KFENCE_ERROR_INVALID_FREE, + .fn = test_double_free, + }; + + setup_test_cache(test, size, 0, NULL); + expect.addr = test_alloc(test, size, GFP_KERNEL, ALLOCATE_ANY); + test_free(expect.addr); + test_free(expect.addr); /* Double-free. */ + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); +} + +static void test_invalid_addr_free(struct kunit *test) +{ + const size_t size = 32; + struct expect_report expect = { + .type = KFENCE_ERROR_INVALID_FREE, + .fn = test_invalid_addr_free, + }; + char *buf; + + setup_test_cache(test, size, 0, NULL); + buf = test_alloc(test, size, GFP_KERNEL, ALLOCATE_ANY); + expect.addr = buf + 1; /* Free on invalid address. */ + test_free(expect.addr); /* Invalid address free. */ + test_free(buf); /* No error. */ + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); +} + +static void test_corruption(struct kunit *test) +{ + size_t size = 32; + struct expect_report expect = { + .type = KFENCE_ERROR_CORRUPTION, + .fn = test_corruption, + }; + char *buf; + + setup_test_cache(test, size, 0, NULL); + + /* Test both sides. */ + + buf = test_alloc(test, size, GFP_KERNEL, ALLOCATE_LEFT); + expect.addr = buf + size; + WRITE_ONCE(*expect.addr, 42); + test_free(buf); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); + + buf = test_alloc(test, size, GFP_KERNEL, ALLOCATE_RIGHT); + expect.addr = buf - 1; + WRITE_ONCE(*expect.addr, 42); + test_free(buf); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); +} + +/* + * KFENCE is unable to detect an OOB if the allocation's alignment requirements + * leave a gap between the object and the guard page. Specifically, an + * allocation of e.g. 73 bytes is aligned on 8 and 128 bytes for SLUB or SLAB + * respectively. Therefore it is impossible for the allocated object to + * contiguously line up with the right guard page. + * + * However, we test that an access to memory beyond the gap results in KFENCE + * detecting an OOB access. + */ +static void test_kmalloc_aligned_oob_read(struct kunit *test) +{ + const size_t size = 73; + const size_t align = kmalloc_cache_alignment(size); + struct expect_report expect = { + .type = KFENCE_ERROR_OOB, + .fn = test_kmalloc_aligned_oob_read, + .is_write = false, + }; + char *buf; + + buf = test_alloc(test, size, GFP_KERNEL, ALLOCATE_RIGHT); + + /* + * The object is offset to the right, so there won't be an OOB to the + * left of it. + */ + READ_ONCE(*(buf - 1)); + KUNIT_EXPECT_FALSE(test, report_available()); + + /* + * @buf must be aligned on @align, therefore buf + size belongs to the + * same page -> no OOB. + */ + READ_ONCE(*(buf + size)); + KUNIT_EXPECT_FALSE(test, report_available()); + + /* Overflowing by @align bytes will result in an OOB. */ + expect.addr = buf + size + align; + READ_ONCE(*expect.addr); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); + + test_free(buf); +} + +static void test_kmalloc_aligned_oob_write(struct kunit *test) +{ + const size_t size = 73; + struct expect_report expect = { + .type = KFENCE_ERROR_CORRUPTION, + .fn = test_kmalloc_aligned_oob_write, + }; + char *buf; + + buf = test_alloc(test, size, GFP_KERNEL, ALLOCATE_RIGHT); + /* + * The object is offset to the right, so we won't get a page + * fault immediately after it. + */ + expect.addr = buf + size; + WRITE_ONCE(*expect.addr, READ_ONCE(*expect.addr) + 1); + KUNIT_EXPECT_FALSE(test, report_available()); + test_free(buf); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); +} + +/* Test cache shrinking and destroying with KFENCE. */ +static void test_shrink_memcache(struct kunit *test) +{ + const size_t size = 32; + void *buf; + + setup_test_cache(test, size, 0, NULL); + KUNIT_EXPECT_TRUE(test, test_cache); + buf = test_alloc(test, size, GFP_KERNEL, ALLOCATE_ANY); + kmem_cache_shrink(test_cache); + test_free(buf); + + KUNIT_EXPECT_FALSE(test, report_available()); +} + +static void ctor_set_x(void *obj) +{ + /* Every object has at least 8 bytes. */ + memset(obj, 'x', 8); +} + +/* Ensure that SL*B does not modify KFENCE objects on bulk free. */ +static void test_free_bulk(struct kunit *test) +{ + int iter; + + for (iter = 0; iter < 5; iter++) { + const size_t size = setup_test_cache(test, 8 + prandom_u32_max(300), 0, + (iter & 1) ? ctor_set_x : NULL); + void *objects[] = { + test_alloc(test, size, GFP_KERNEL, ALLOCATE_RIGHT), + test_alloc(test, size, GFP_KERNEL, ALLOCATE_NONE), + test_alloc(test, size, GFP_KERNEL, ALLOCATE_LEFT), + test_alloc(test, size, GFP_KERNEL, ALLOCATE_NONE), + test_alloc(test, size, GFP_KERNEL, ALLOCATE_NONE), + }; + + kmem_cache_free_bulk(test_cache, ARRAY_SIZE(objects), objects); + KUNIT_ASSERT_FALSE(test, report_available()); + test_cache_destroy(); + } +} + +/* Test init-on-free works. */ +static void test_init_on_free(struct kunit *test) +{ + const size_t size = 32; + struct expect_report expect = { + .type = KFENCE_ERROR_UAF, + .fn = test_init_on_free, + .is_write = false, + }; + int i; + + if (!IS_ENABLED(CONFIG_INIT_ON_FREE_DEFAULT_ON)) + return; + /* Assume it hasn't been disabled on command line. */ + + setup_test_cache(test, size, 0, NULL); + expect.addr = test_alloc(test, size, GFP_KERNEL, ALLOCATE_ANY); + for (i = 0; i < size; i++) + expect.addr[i] = i + 1; + test_free(expect.addr); + + for (i = 0; i < size; i++) { + /* + * This may fail if the page was recycled by KFENCE and then + * written to again -- this however, is near impossible with a + * default config. + */ + KUNIT_EXPECT_EQ(test, expect.addr[i], (char)0); + + if (!i) /* Only check first access to not fail test if page is ever re-protected. */ + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); + } +} + +/* Ensure that constructors work properly. */ +static void test_memcache_ctor(struct kunit *test) +{ + const size_t size = 32; + char *buf; + int i; + + setup_test_cache(test, size, 0, ctor_set_x); + buf = test_alloc(test, size, GFP_KERNEL, ALLOCATE_ANY); + + for (i = 0; i < 8; i++) + KUNIT_EXPECT_EQ(test, buf[i], (char)'x'); + + test_free(buf); + + KUNIT_EXPECT_FALSE(test, report_available()); +} + +/* Test that memory is zeroed if requested. */ +static void test_gfpzero(struct kunit *test) +{ + const size_t size = PAGE_SIZE; /* PAGE_SIZE so we can use ALLOCATE_ANY. */ + char *buf1, *buf2; + int i; + + if (CONFIG_KFENCE_SAMPLE_INTERVAL > 100) { + kunit_warn(test, "skipping ... would take too long\n"); + return; + } + + setup_test_cache(test, size, 0, NULL); + buf1 = test_alloc(test, size, GFP_KERNEL, ALLOCATE_ANY); + for (i = 0; i < size; i++) + buf1[i] = i + 1; + test_free(buf1); + + /* Try to get same address again -- this can take a while. */ + for (i = 0;; i++) { + buf2 = test_alloc(test, size, GFP_KERNEL | __GFP_ZERO, ALLOCATE_ANY); + if (buf1 == buf2) + break; + test_free(buf2); + + if (i == CONFIG_KFENCE_NUM_OBJECTS) { + kunit_warn(test, "giving up ... cannot get same object back\n"); + return; + } + } + + for (i = 0; i < size; i++) + KUNIT_EXPECT_EQ(test, buf2[i], (char)0); + + test_free(buf2); + + KUNIT_EXPECT_FALSE(test, report_available()); +} + +static void test_invalid_access(struct kunit *test) +{ + const struct expect_report expect = { + .type = KFENCE_ERROR_INVALID, + .fn = test_invalid_access, + .addr = &__kfence_pool[10], + .is_write = false, + }; + + READ_ONCE(__kfence_pool[10]); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); +} + +/* Test SLAB_TYPESAFE_BY_RCU works. */ +static void test_memcache_typesafe_by_rcu(struct kunit *test) +{ + const size_t size = 32; + struct expect_report expect = { + .type = KFENCE_ERROR_UAF, + .fn = test_memcache_typesafe_by_rcu, + .is_write = false, + }; + + setup_test_cache(test, size, SLAB_TYPESAFE_BY_RCU, NULL); + KUNIT_EXPECT_TRUE(test, test_cache); /* Want memcache. */ + + expect.addr = test_alloc(test, size, GFP_KERNEL, ALLOCATE_ANY); + *expect.addr = 42; + + rcu_read_lock(); + test_free(expect.addr); + KUNIT_EXPECT_EQ(test, *expect.addr, (char)42); + /* + * Up to this point, memory should not have been freed yet, and + * therefore there should be no KFENCE report from the above access. + */ + rcu_read_unlock(); + + /* Above access to @expect.addr should not have generated a report! */ + KUNIT_EXPECT_FALSE(test, report_available()); + + /* Only after rcu_barrier() is the memory guaranteed to be freed. */ + rcu_barrier(); + + /* Expect use-after-free. */ + KUNIT_EXPECT_EQ(test, *expect.addr, (char)42); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); +} + +/* Test krealloc(). */ +static void test_krealloc(struct kunit *test) +{ + const size_t size = 32; + const struct expect_report expect = { + .type = KFENCE_ERROR_UAF, + .fn = test_krealloc, + .addr = test_alloc(test, size, GFP_KERNEL, ALLOCATE_ANY), + .is_write = false, + }; + char *buf = expect.addr; + int i; + + KUNIT_EXPECT_FALSE(test, test_cache); + KUNIT_EXPECT_EQ(test, ksize(buf), size); /* Precise size match after KFENCE alloc. */ + for (i = 0; i < size; i++) + buf[i] = i + 1; + + /* Check that we successfully change the size. */ + buf = krealloc(buf, size * 3, GFP_KERNEL); /* Grow. */ + /* Note: Might no longer be a KFENCE alloc. */ + KUNIT_EXPECT_GE(test, ksize(buf), size * 3); + for (i = 0; i < size; i++) + KUNIT_EXPECT_EQ(test, buf[i], (char)(i + 1)); + for (; i < size * 3; i++) /* Fill to extra bytes. */ + buf[i] = i + 1; + + buf = krealloc(buf, size * 2, GFP_KERNEL); /* Shrink. */ + KUNIT_EXPECT_GE(test, ksize(buf), size * 2); + for (i = 0; i < size * 2; i++) + KUNIT_EXPECT_EQ(test, buf[i], (char)(i + 1)); + + buf = krealloc(buf, 0, GFP_KERNEL); /* Free. */ + KUNIT_EXPECT_EQ(test, (unsigned long)buf, (unsigned long)ZERO_SIZE_PTR); + KUNIT_ASSERT_FALSE(test, report_available()); /* No reports yet! */ + + READ_ONCE(*expect.addr); /* Ensure krealloc() actually freed earlier KFENCE object. */ + KUNIT_ASSERT_TRUE(test, report_matches(&expect)); +} + +/* Test that some objects from a bulk allocation belong to KFENCE pool. */ +static void test_memcache_alloc_bulk(struct kunit *test) +{ + const size_t size = 32; + bool pass = false; + unsigned long timeout; + + setup_test_cache(test, size, 0, NULL); + KUNIT_EXPECT_TRUE(test, test_cache); /* Want memcache. */ + /* + * 100x the sample interval should be more than enough to ensure we get + * a KFENCE allocation eventually. + */ + timeout = jiffies + msecs_to_jiffies(100 * CONFIG_KFENCE_SAMPLE_INTERVAL); + do { + void *objects[100]; + int i, num = kmem_cache_alloc_bulk(test_cache, GFP_ATOMIC, ARRAY_SIZE(objects), + objects); + if (!num) + continue; + for (i = 0; i < ARRAY_SIZE(objects); i++) { + if (is_kfence_address(objects[i])) { + pass = true; + break; + } + } + kmem_cache_free_bulk(test_cache, num, objects); + /* + * kmem_cache_alloc_bulk() disables interrupts, and calling it + * in a tight loop may not give KFENCE a chance to switch the + * static branch. Call cond_resched() to let KFENCE chime in. + */ + cond_resched(); + } while (!pass && time_before(jiffies, timeout)); + + KUNIT_EXPECT_TRUE(test, pass); + KUNIT_EXPECT_FALSE(test, report_available()); +} + +/* + * KUnit does not provide a way to provide arguments to tests, and we encode + * additional info in the name. Set up 2 tests per test case, one using the + * default allocator, and another using a custom memcache (suffix '-memcache'). + */ +#define KFENCE_KUNIT_CASE(test_name) \ + { .run_case = test_name, .name = #test_name }, \ + { .run_case = test_name, .name = #test_name "-memcache" } + +static struct kunit_case kfence_test_cases[] = { + KFENCE_KUNIT_CASE(test_out_of_bounds_read), + KFENCE_KUNIT_CASE(test_out_of_bounds_write), + KFENCE_KUNIT_CASE(test_use_after_free_read), + KFENCE_KUNIT_CASE(test_double_free), + KFENCE_KUNIT_CASE(test_invalid_addr_free), + KFENCE_KUNIT_CASE(test_corruption), + KFENCE_KUNIT_CASE(test_free_bulk), + KFENCE_KUNIT_CASE(test_init_on_free), + KUNIT_CASE(test_kmalloc_aligned_oob_read), + KUNIT_CASE(test_kmalloc_aligned_oob_write), + KUNIT_CASE(test_shrink_memcache), + KUNIT_CASE(test_memcache_ctor), + KUNIT_CASE(test_invalid_access), + KUNIT_CASE(test_gfpzero), + KUNIT_CASE(test_memcache_typesafe_by_rcu), + KUNIT_CASE(test_krealloc), + KUNIT_CASE(test_memcache_alloc_bulk), + {}, +}; + +/* ===== End test cases ===== */ + +static int test_init(struct kunit *test) +{ + unsigned long flags; + int i; + + spin_lock_irqsave(&observed.lock, flags); + for (i = 0; i < ARRAY_SIZE(observed.lines); i++) + observed.lines[i][0] = '\0'; + observed.nlines = 0; + spin_unlock_irqrestore(&observed.lock, flags); + + /* Any test with 'memcache' in its name will want a memcache. */ + if (strstr(test->name, "memcache")) + test->priv = TEST_PRIV_WANT_MEMCACHE; + else + test->priv = NULL; + + return 0; +} + +static void test_exit(struct kunit *test) +{ + test_cache_destroy(); +} + +static struct kunit_suite kfence_test_suite = { + .name = "kfence", + .test_cases = kfence_test_cases, + .init = test_init, + .exit = test_exit, +}; +static struct kunit_suite *kfence_test_suites[] = { &kfence_test_suite, NULL }; + +static void register_tracepoints(struct tracepoint *tp, void *ignore) +{ + check_trace_callback_type_console(probe_console); + if (!strcmp(tp->name, "console")) + WARN_ON(tracepoint_probe_register(tp, probe_console, NULL)); +} + +static void unregister_tracepoints(struct tracepoint *tp, void *ignore) +{ + if (!strcmp(tp->name, "console")) + tracepoint_probe_unregister(tp, probe_console, NULL); +} + +/* + * We only want to do tracepoints setup and teardown once, therefore we have to + * customize the init and exit functions and cannot rely on kunit_test_suite(). + */ +static int __init kfence_test_init(void) +{ + /* + * Because we want to be able to build the test as a module, we need to + * iterate through all known tracepoints, since the static registration + * won't work here. + */ + for_each_kernel_tracepoint(register_tracepoints, NULL); + return __kunit_test_suites_init(kfence_test_suites); +} + +static void kfence_test_exit(void) +{ + __kunit_test_suites_exit(kfence_test_suites); + for_each_kernel_tracepoint(unregister_tracepoints, NULL); + tracepoint_synchronize_unregister(); +} + +late_initcall(kfence_test_init); +module_exit(kfence_test_exit); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Alexander Potapenko , Marco Elver "); diff --git a/mm/kfence/report.c b/mm/kfence/report.c index 4dbfa9a382e4..901bd7ee83d8 100644 --- a/mm/kfence/report.c +++ b/mm/kfence/report.c @@ -156,7 +156,12 @@ static void print_diff_canary(unsigned long address, size_t bytes_to_show, pr_cont(" ]"); } -void kfence_report_error(unsigned long address, struct pt_regs *regs, +static const char *get_access_type(bool is_write) +{ + return is_write ? "write" : "read"; +} + +void kfence_report_error(unsigned long address, bool is_write, struct pt_regs *regs, const struct kfence_metadata *meta, enum kfence_error_type type) { unsigned long stack_entries[KFENCE_STACK_DEPTH] = { 0 }; @@ -194,17 +199,19 @@ void kfence_report_error(unsigned long address, struct pt_regs *regs, case KFENCE_ERROR_OOB: { const bool left_of_object = address < meta->addr; - pr_err("BUG: KFENCE: out-of-bounds in %pS\n\n", (void *)stack_entries[skipnr]); - pr_err("Out-of-bounds access at 0x" PTR_FMT " (%luB %s of kfence-#%zd):\n", - (void *)address, + pr_err("BUG: KFENCE: out-of-bounds %s in %pS\n\n", get_access_type(is_write), + (void *)stack_entries[skipnr]); + pr_err("Out-of-bounds %s at 0x" PTR_FMT " (%luB %s of kfence-#%zd):\n", + get_access_type(is_write), (void *)address, left_of_object ? meta->addr - address : address - meta->addr, left_of_object ? "left" : "right", object_index); break; } case KFENCE_ERROR_UAF: - pr_err("BUG: KFENCE: use-after-free in %pS\n\n", (void *)stack_entries[skipnr]); - pr_err("Use-after-free access at 0x" PTR_FMT " (in kfence-#%zd):\n", - (void *)address, object_index); + pr_err("BUG: KFENCE: use-after-free %s in %pS\n\n", get_access_type(is_write), + (void *)stack_entries[skipnr]); + pr_err("Use-after-free %s at 0x" PTR_FMT " (in kfence-#%zd):\n", + get_access_type(is_write), (void *)address, object_index); break; case KFENCE_ERROR_CORRUPTION: pr_err("BUG: KFENCE: memory corruption in %pS\n\n", (void *)stack_entries[skipnr]); @@ -213,8 +220,10 @@ void kfence_report_error(unsigned long address, struct pt_regs *regs, pr_cont(" (in kfence-#%zd):\n", object_index); break; case KFENCE_ERROR_INVALID: - pr_err("BUG: KFENCE: invalid access in %pS\n\n", (void *)stack_entries[skipnr]); - pr_err("Invalid access at 0x" PTR_FMT ":\n", (void *)address); + pr_err("BUG: KFENCE: invalid %s in %pS\n\n", get_access_type(is_write), + (void *)stack_entries[skipnr]); + pr_err("Invalid %s at 0x" PTR_FMT ":\n", get_access_type(is_write), + (void *)address); break; case KFENCE_ERROR_INVALID_FREE: pr_err("BUG: KFENCE: invalid free in %pS\n\n", (void *)stack_entries[skipnr]); -- cgit v1.2.3 From 9c0dee54eb91d48cca048bd7bd2c1f4a166e0252 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Thu, 25 Feb 2021 17:19:44 -0800 Subject: tracing: add error_report_end trace point Patch series "Add error_report_end tracepoint to KFENCE and KASAN", v3. This patchset adds a tracepoint, error_repor_end, that is to be used by KFENCE, KASAN, and potentially other bug detection tools, when they print an error report. One of the possible use cases is userspace collection of kernel error reports: interested parties can subscribe to the tracing event via tracefs, and get notified when an error report occurs. This patch (of 3): Introduce error_report_end tracepoint. It can be used in debugging tools like KASAN, KFENCE, etc. to provide extensions to the error reporting mechanisms (e.g. allow tests hook into error reporting, ease error report collection from production kernels). Another benefit would be making use of ftrace for debugging or benchmarking the tools themselves. Should we need it, the tracepoint name leaves us with the possibility to introduce a complementary error_report_start tracepoint in the future. Link: https://lkml.kernel.org/r/20210121131915.1331302-1-glider@google.com Link: https://lkml.kernel.org/r/20210121131915.1331302-2-glider@google.com Signed-off-by: Alexander Potapenko Suggested-by: Marco Elver Cc: Andrey Konovalov Cc: Dmitry Vyukov Cc: Ingo Molnar Cc: Petr Mladek Cc: Steven Rostedt Cc: Sergey Senozhatsky Cc: Greg Kroah-Hartman Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/error_report.h | 74 +++++++++++++++++++++++++++++++++++++ kernel/trace/Makefile | 1 + kernel/trace/error_report-traces.c | 11 ++++++ 3 files changed, 86 insertions(+) create mode 100644 include/trace/events/error_report.h create mode 100644 kernel/trace/error_report-traces.c (limited to 'include') diff --git a/include/trace/events/error_report.h b/include/trace/events/error_report.h new file mode 100644 index 000000000000..96f64bf218b2 --- /dev/null +++ b/include/trace/events/error_report.h @@ -0,0 +1,74 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Declarations for error reporting tracepoints. + * + * Copyright (C) 2021, Google LLC. + */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM error_report + +#if !defined(_TRACE_ERROR_REPORT_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_ERROR_REPORT_H + +#include + +#ifndef __ERROR_REPORT_DECLARE_TRACE_ENUMS_ONCE_ONLY +#define __ERROR_REPORT_DECLARE_TRACE_ENUMS_ONCE_ONLY + +enum error_detector { + ERROR_DETECTOR_KFENCE, + ERROR_DETECTOR_KASAN +}; + +#endif /* __ERROR_REPORT_DECLARE_TRACE_ENUMS_ONCE_ONLY */ + +#define error_detector_list \ + EM(ERROR_DETECTOR_KFENCE, "kfence") \ + EMe(ERROR_DETECTOR_KASAN, "kasan") +/* Always end the list with an EMe. */ + +#undef EM +#undef EMe + +#define EM(a, b) TRACE_DEFINE_ENUM(a); +#define EMe(a, b) TRACE_DEFINE_ENUM(a); + +error_detector_list + +#undef EM +#undef EMe + +#define EM(a, b) { a, b }, +#define EMe(a, b) { a, b } + +#define show_error_detector_list(val) \ + __print_symbolic(val, error_detector_list) + +DECLARE_EVENT_CLASS(error_report_template, + TP_PROTO(enum error_detector error_detector, unsigned long id), + TP_ARGS(error_detector, id), + TP_STRUCT__entry(__field(enum error_detector, error_detector) + __field(unsigned long, id)), + TP_fast_assign(__entry->error_detector = error_detector; + __entry->id = id;), + TP_printk("[%s] %lx", + show_error_detector_list(__entry->error_detector), + __entry->id)); + +/** + * error_report_end - called after printing the error report + * @error_detector: short string describing the error detection tool + * @id: pseudo-unique descriptor identifying the report + * (e.g. the memory access address) + * + * This event occurs right after a debugging tool finishes printing the error + * report. + */ +DEFINE_EVENT(error_report_template, error_report_end, + TP_PROTO(enum error_detector error_detector, unsigned long id), + TP_ARGS(error_detector, id)); + +#endif /* _TRACE_ERROR_REPORT_H */ + +/* This part must be outside protection */ +#include diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index 7e44cea89fdc..b28d3e5013cd 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -81,6 +81,7 @@ obj-$(CONFIG_SYNTH_EVENTS) += trace_events_synth.o obj-$(CONFIG_HIST_TRIGGERS) += trace_events_hist.o obj-$(CONFIG_BPF_EVENTS) += bpf_trace.o obj-$(CONFIG_KPROBE_EVENTS) += trace_kprobe.o +obj-$(CONFIG_TRACEPOINTS) += error_report-traces.o obj-$(CONFIG_TRACEPOINTS) += power-traces.o ifeq ($(CONFIG_PM),y) obj-$(CONFIG_TRACEPOINTS) += rpm-traces.o diff --git a/kernel/trace/error_report-traces.c b/kernel/trace/error_report-traces.c new file mode 100644 index 000000000000..f89792c25b11 --- /dev/null +++ b/kernel/trace/error_report-traces.c @@ -0,0 +1,11 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Error reporting trace points. + * + * Copyright (C) 2021, Google LLC. + */ + +#define CREATE_TRACE_POINTS +#include + +EXPORT_TRACEPOINT_SYMBOL_GPL(error_report_end); -- cgit v1.2.3 From 928501344fc645f80390afc12708c81b3595745d Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Thu, 25 Feb 2021 17:19:55 -0800 Subject: kasan, mm: don't save alloc stacks twice Patch series "kasan: optimizations and fixes for HW_TAGS", v4. This patchset makes the HW_TAGS mode more efficient, mostly by reworking poisoning approaches and simplifying/inlining some internal helpers. With this change, the overhead of HW_TAGS annotations excluding setting and checking memory tags is ~3%. The performance impact caused by tags will be unknown until we have hardware that supports MTE. As a side-effect, this patchset speeds up generic KASAN by ~15%. This patch (of 13): Currently KASAN saves allocation stacks in both kasan_slab_alloc() and kasan_kmalloc() annotations. This patch changes KASAN to save allocation stacks for slab objects from kmalloc caches in kasan_kmalloc() only, and stacks for other slab objects in kasan_slab_alloc() only. This change requires ____kasan_kmalloc() knowing whether the object belongs to a kmalloc cache. This is implemented by adding a flag field to the kasan_info structure. That flag is only set for kmalloc caches via a new kasan_cache_create_kmalloc() annotation. Link: https://lkml.kernel.org/r/cover.1612546384.git.andreyknvl@google.com Link: https://lkml.kernel.org/r/7c673ebca8d00f40a7ad6f04ab9a2bddeeae2097.1612546384.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Reviewed-by: Marco Elver Cc: Catalin Marinas Cc: Vincenzo Frascino Cc: Dmitry Vyukov Cc: Alexander Potapenko Cc: Will Deacon Cc: Andrey Ryabinin Cc: Peter Collingbourne Cc: Evgenii Stepanov Cc: Branislav Rankov Cc: Kevin Brodsky Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kasan.h | 9 +++++++++ mm/kasan/common.c | 18 ++++++++++++++---- mm/slab_common.c | 1 + 3 files changed, 24 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 7eaf2d9effb4..3fb31e8a353e 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -83,6 +83,7 @@ static inline void kasan_disable_current(void) {} struct kasan_cache { int alloc_meta_offset; int free_meta_offset; + bool is_kmalloc; }; #ifdef CONFIG_KASAN_HW_TAGS @@ -143,6 +144,13 @@ static __always_inline void kasan_cache_create(struct kmem_cache *cache, __kasan_cache_create(cache, size, flags); } +void __kasan_cache_create_kmalloc(struct kmem_cache *cache); +static __always_inline void kasan_cache_create_kmalloc(struct kmem_cache *cache) +{ + if (kasan_enabled()) + __kasan_cache_create_kmalloc(cache); +} + size_t __kasan_metadata_size(struct kmem_cache *cache); static __always_inline size_t kasan_metadata_size(struct kmem_cache *cache) { @@ -278,6 +286,7 @@ static inline void kasan_free_pages(struct page *page, unsigned int order) {} static inline void kasan_cache_create(struct kmem_cache *cache, unsigned int *size, slab_flags_t *flags) {} +static inline void kasan_cache_create_kmalloc(struct kmem_cache *cache) {} static inline size_t kasan_metadata_size(struct kmem_cache *cache) { return 0; } static inline void kasan_poison_slab(struct page *page) {} static inline void kasan_unpoison_object_data(struct kmem_cache *cache, diff --git a/mm/kasan/common.c b/mm/kasan/common.c index af1768c4fee5..d8d83ca56fe2 100644 --- a/mm/kasan/common.c +++ b/mm/kasan/common.c @@ -210,6 +210,11 @@ void __kasan_cache_create(struct kmem_cache *cache, unsigned int *size, *size = optimal_size; } +void __kasan_cache_create_kmalloc(struct kmem_cache *cache) +{ + cache->kasan_info.is_kmalloc = true; +} + size_t __kasan_metadata_size(struct kmem_cache *cache) { if (!kasan_stack_collection_enabled()) @@ -394,17 +399,22 @@ void __kasan_slab_free_mempool(void *ptr, unsigned long ip) } } -static void set_alloc_info(struct kmem_cache *cache, void *object, gfp_t flags) +static void set_alloc_info(struct kmem_cache *cache, void *object, + gfp_t flags, bool is_kmalloc) { struct kasan_alloc_meta *alloc_meta; + /* Don't save alloc info for kmalloc caches in kasan_slab_alloc(). */ + if (cache->kasan_info.is_kmalloc && !is_kmalloc) + return; + alloc_meta = kasan_get_alloc_meta(cache, object); if (alloc_meta) kasan_set_track(&alloc_meta->alloc_track, flags); } static void *____kasan_kmalloc(struct kmem_cache *cache, const void *object, - size_t size, gfp_t flags, bool keep_tag) + size_t size, gfp_t flags, bool is_kmalloc) { unsigned long redzone_start; unsigned long redzone_end; @@ -423,7 +433,7 @@ static void *____kasan_kmalloc(struct kmem_cache *cache, const void *object, KASAN_GRANULE_SIZE); redzone_end = round_up((unsigned long)object + cache->object_size, KASAN_GRANULE_SIZE); - tag = assign_tag(cache, object, false, keep_tag); + tag = assign_tag(cache, object, false, is_kmalloc); /* Tag is ignored in set_tag without CONFIG_KASAN_SW/HW_TAGS */ kasan_unpoison(set_tag(object, tag), size); @@ -431,7 +441,7 @@ static void *____kasan_kmalloc(struct kmem_cache *cache, const void *object, KASAN_KMALLOC_REDZONE); if (kasan_stack_collection_enabled()) - set_alloc_info(cache, (void *)object, flags); + set_alloc_info(cache, (void *)object, flags, is_kmalloc); return set_tag(object, tag); } diff --git a/mm/slab_common.c b/mm/slab_common.c index 284954ef1da5..897c3a446b04 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -643,6 +643,7 @@ struct kmem_cache *__init create_kmalloc_cache(const char *name, panic("Out of memory when creating slab %s\n", name); create_boot_cache(s, name, size, flags, useroffset, usersize); + kasan_cache_create_kmalloc(s); list_add(&s->list, &slab_caches); s->refcount = 1; return s; -- cgit v1.2.3 From 200072ce33b298cf14d3ed2a570f5eb27609677d Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Thu, 25 Feb 2021 17:20:11 -0800 Subject: kasan: unify large kfree checks Unify checks in kasan_kfree_large() and in kasan_slab_free_mempool() for large allocations as it's done for small kfree() allocations. With this change, kasan_slab_free_mempool() starts checking that the first byte of the memory that's being freed is accessible. Link: https://lkml.kernel.org/r/14ffc4cd867e0b1ed58f7527e3b748a1b4ad08aa.1612546384.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Reviewed-by: Marco Elver Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Branislav Rankov Cc: Catalin Marinas Cc: Dmitry Vyukov Cc: Evgenii Stepanov Cc: Kevin Brodsky Cc: Peter Collingbourne Cc: Vincenzo Frascino Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kasan.h | 16 ++++++++-------- mm/kasan/common.c | 36 ++++++++++++++++++++++++++---------- 2 files changed, 34 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 3fb31e8a353e..b91732bd05d7 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -200,6 +200,13 @@ static __always_inline bool kasan_slab_free(struct kmem_cache *s, void *object) return false; } +void __kasan_kfree_large(void *ptr, unsigned long ip); +static __always_inline void kasan_kfree_large(void *ptr) +{ + if (kasan_enabled()) + __kasan_kfree_large(ptr, _RET_IP_); +} + void __kasan_slab_free_mempool(void *ptr, unsigned long ip); static __always_inline void kasan_slab_free_mempool(void *ptr) { @@ -247,13 +254,6 @@ static __always_inline void * __must_check kasan_krealloc(const void *object, return (void *)object; } -void __kasan_kfree_large(void *ptr, unsigned long ip); -static __always_inline void kasan_kfree_large(void *ptr) -{ - if (kasan_enabled()) - __kasan_kfree_large(ptr, _RET_IP_); -} - /* * Unlike kasan_check_read/write(), kasan_check_byte() is performed even for * the hardware tag-based mode that doesn't rely on compiler instrumentation. @@ -302,6 +302,7 @@ static inline bool kasan_slab_free(struct kmem_cache *s, void *object) { return false; } +static inline void kasan_kfree_large(void *ptr) {} static inline void kasan_slab_free_mempool(void *ptr) {} static inline void *kasan_slab_alloc(struct kmem_cache *s, void *object, gfp_t flags) @@ -322,7 +323,6 @@ static inline void *kasan_krealloc(const void *object, size_t new_size, { return (void *)object; } -static inline void kasan_kfree_large(void *ptr) {} static inline bool kasan_check_byte(const void *address) { return true; diff --git a/mm/kasan/common.c b/mm/kasan/common.c index 48d51daeda95..8a3d66393dc5 100644 --- a/mm/kasan/common.c +++ b/mm/kasan/common.c @@ -364,6 +364,31 @@ bool __kasan_slab_free(struct kmem_cache *cache, void *object, unsigned long ip) return ____kasan_slab_free(cache, object, ip, true); } +static bool ____kasan_kfree_large(void *ptr, unsigned long ip) +{ + if (ptr != page_address(virt_to_head_page(ptr))) { + kasan_report_invalid_free(ptr, ip); + return true; + } + + if (!kasan_byte_accessible(ptr)) { + kasan_report_invalid_free(ptr, ip); + return true; + } + + /* + * The object will be poisoned by kasan_free_pages() or + * kasan_slab_free_mempool(). + */ + + return false; +} + +void __kasan_kfree_large(void *ptr, unsigned long ip) +{ + ____kasan_kfree_large(ptr, ip); +} + void __kasan_slab_free_mempool(void *ptr, unsigned long ip) { struct page *page; @@ -377,10 +402,8 @@ void __kasan_slab_free_mempool(void *ptr, unsigned long ip) * KMALLOC_MAX_SIZE, and kmalloc falls back onto page_alloc. */ if (unlikely(!PageSlab(page))) { - if (ptr != page_address(page)) { - kasan_report_invalid_free(ptr, ip); + if (____kasan_kfree_large(ptr, ip)) return; - } kasan_poison(ptr, page_size(page), KASAN_FREE_PAGE); } else { ____kasan_slab_free(page->slab_cache, ptr, ip, false); @@ -539,13 +562,6 @@ void * __must_check __kasan_krealloc(const void *object, size_t size, gfp_t flag return ____kasan_kmalloc(page->slab_cache, object, size, flags); } -void __kasan_kfree_large(void *ptr, unsigned long ip) -{ - if (ptr != page_address(virt_to_head_page(ptr))) - kasan_report_invalid_free(ptr, ip); - /* The object will be poisoned by kasan_free_pages(). */ -} - bool __kasan_check_byte(const void *address, unsigned long ip) { if (!kasan_byte_accessible(address)) { -- cgit v1.2.3 From df54714f579a77662054132161612ce3da876b0d Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 25 Feb 2021 17:20:56 -0800 Subject: include/linux: remove repeated words Drop the doubled word "for" in a comment. {firewire-cdev.h} Drop the doubled word "in" in a comment. {input.h} Drop the doubled word "a" in a comment. {mdev.h} Drop the doubled word "the" in a comment. {ptrace.h} Link: https://lkml.kernel.org/r/20210126232444.22861-1-rdunlap@infradead.org Signed-off-by: Randy Dunlap Cc: Stefan Richter Cc: Dmitry Torokhov Cc: Kirti Wankhede Cc: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mdev.h | 2 +- include/linux/ptrace.h | 2 +- include/uapi/linux/firewire-cdev.h | 2 +- include/uapi/linux/input.h | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/mdev.h b/include/linux/mdev.h index 9004375c462e..27eb383cb95d 100644 --- a/include/linux/mdev.h +++ b/include/linux/mdev.h @@ -42,7 +42,7 @@ struct device *mdev_get_iommu_device(struct device *dev); * @mdev: mdev_device structure on of mediated device * that is being created * Returns integer: success (0) or error (< 0) - * @remove: Called to free resources in parent device's driver for a + * @remove: Called to free resources in parent device's driver for * a mediated device. It is mandatory to provide 'remove' * ops. * @mdev: mdev_device device structure which is being diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 2a9df80ea887..b5ebf6c01292 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -171,7 +171,7 @@ static inline void ptrace_event(int event, unsigned long message) * * Check whether @event is enabled and, if so, report @event and @pid * to the ptrace parent. @pid is reported as the pid_t seen from the - * the ptrace parent's pid namespace. + * ptrace parent's pid namespace. * * Called without locks. */ diff --git a/include/uapi/linux/firewire-cdev.h b/include/uapi/linux/firewire-cdev.h index 7e5b5c10a49c..5effa9832802 100644 --- a/include/uapi/linux/firewire-cdev.h +++ b/include/uapi/linux/firewire-cdev.h @@ -844,7 +844,7 @@ struct fw_cdev_queue_iso { * struct fw_cdev_start_iso - Start an isochronous transmission or reception * @cycle: Cycle in which to start I/O. If @cycle is greater than or * equal to 0, the I/O will start on that cycle. - * @sync: Determines the value to wait for for receive packets that have + * @sync: Determines the value to wait for receive packets that have * the %FW_CDEV_ISO_SYNC bit set * @tags: Tag filter bit mask. Only valid for isochronous reception. * Determines the tag values for which packets will be accepted. diff --git a/include/uapi/linux/input.h b/include/uapi/linux/input.h index 9a61c28ed3ae..ee3127461ee0 100644 --- a/include/uapi/linux/input.h +++ b/include/uapi/linux/input.h @@ -84,7 +84,7 @@ struct input_id { * in units per radian. * When INPUT_PROP_ACCELEROMETER is set the resolution changes. * The main axes (ABS_X, ABS_Y, ABS_Z) are then reported in - * in units per g (units/g) and in units per degree per second + * units per g (units/g) and in units per degree per second * (units/deg/s) for rotational axes (ABS_RX, ABS_RY, ABS_RZ). */ struct input_absinfo { -- cgit v1.2.3 From c131bd0b5448bb577b7a9ed48c4e528807e8d5af Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Thu, 25 Feb 2021 17:21:00 -0800 Subject: treewide: Miguel has moved Update contact info. Link: https://lkml.kernel.org/r/20210206162524.GA11520@kernel.org Signed-off-by: Miguel Ojeda Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- .mailmap | 1 + CREDITS | 9 +++------ Documentation/admin-guide/auxdisplay/cfag12864b.rst | 2 +- Documentation/admin-guide/auxdisplay/ks0108.rst | 2 +- MAINTAINERS | 12 ++++++------ drivers/auxdisplay/cfag12864b.c | 4 ++-- drivers/auxdisplay/cfag12864bfb.c | 4 ++-- drivers/auxdisplay/ks0108.c | 4 ++-- include/linux/cfag12864b.h | 2 +- include/linux/ks0108.h | 2 +- samples/auxdisplay/cfag12864b-example.c | 2 +- 11 files changed, 21 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/.mailmap b/.mailmap index 87a8bbdbf749..85b93cdefc87 100644 --- a/.mailmap +++ b/.mailmap @@ -237,6 +237,7 @@ Maxime Ripard Mayuresh Janorkar Michael Buesch Michel Dänzer +Miguel Ojeda Mike Rapoport Mike Rapoport Mike Rapoport diff --git a/CREDITS b/CREDITS index be097156bd71..cef83b958cbe 100644 --- a/CREDITS +++ b/CREDITS @@ -2841,14 +2841,11 @@ S: Subiaco, 6008 S: Perth, Western Australia S: Australia -N: Miguel Ojeda Sandonis -E: miguel.ojeda.sandonis@gmail.com -W: http://miguelojeda.es -W: http://jair.lab.fi.uva.es/~migojed/ +N: Miguel Ojeda +E: ojeda@kernel.org +W: https://ojeda.dev D: Author of the ks0108, cfag12864b and cfag12864bfb auxiliary display drivers. D: Maintainer of the auxiliary display drivers tree (drivers/auxdisplay/*) -S: C/ Mieses 20, 9-B -S: Valladolid 47009 S: Spain N: Peter Oruba diff --git a/Documentation/admin-guide/auxdisplay/cfag12864b.rst b/Documentation/admin-guide/auxdisplay/cfag12864b.rst index 18c2865bd322..da385d851acc 100644 --- a/Documentation/admin-guide/auxdisplay/cfag12864b.rst +++ b/Documentation/admin-guide/auxdisplay/cfag12864b.rst @@ -3,7 +3,7 @@ cfag12864b LCD Driver Documentation =================================== :License: GPLv2 -:Author & Maintainer: Miguel Ojeda Sandonis +:Author & Maintainer: Miguel Ojeda :Date: 2006-10-27 diff --git a/Documentation/admin-guide/auxdisplay/ks0108.rst b/Documentation/admin-guide/auxdisplay/ks0108.rst index c0b7faf73136..a7d3fe509373 100644 --- a/Documentation/admin-guide/auxdisplay/ks0108.rst +++ b/Documentation/admin-guide/auxdisplay/ks0108.rst @@ -3,7 +3,7 @@ ks0108 LCD Controller Driver Documentation ========================================== :License: GPLv2 -:Author & Maintainer: Miguel Ojeda Sandonis +:Author & Maintainer: Miguel Ojeda :Date: 2006-10-27 diff --git a/MAINTAINERS b/MAINTAINERS index 40040db747fc..e42082eccf36 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2982,7 +2982,7 @@ F: include/uapi/linux/audit.h F: kernel/audit* AUXILIARY DISPLAY DRIVERS -M: Miguel Ojeda Sandonis +M: Miguel Ojeda S: Maintained F: drivers/auxdisplay/ F: include/linux/cfag12864b.h @@ -4128,13 +4128,13 @@ F: scripts/extract-cert.c F: scripts/sign-file.c CFAG12864B LCD DRIVER -M: Miguel Ojeda Sandonis +M: Miguel Ojeda S: Maintained F: drivers/auxdisplay/cfag12864b.c F: include/linux/cfag12864b.h CFAG12864BFB LCD FRAMEBUFFER DRIVER -M: Miguel Ojeda Sandonis +M: Miguel Ojeda S: Maintained F: drivers/auxdisplay/cfag12864bfb.c F: include/linux/cfag12864b.h @@ -4304,7 +4304,7 @@ S: Supported F: drivers/infiniband/hw/usnic/ CLANG-FORMAT FILE -M: Miguel Ojeda +M: Miguel Ojeda S: Maintained F: .clang-format @@ -4444,7 +4444,7 @@ S: Maintained F: drivers/platform/x86/compal-laptop.c COMPILER ATTRIBUTES -M: Miguel Ojeda +M: Miguel Ojeda S: Maintained F: include/linux/compiler_attributes.h @@ -9939,7 +9939,7 @@ F: include/linux/kprobes.h F: kernel/kprobes.c KS0108 LCD CONTROLLER DRIVER -M: Miguel Ojeda Sandonis +M: Miguel Ojeda S: Maintained F: Documentation/admin-guide/auxdisplay/ks0108.rst F: drivers/auxdisplay/ks0108.c diff --git a/drivers/auxdisplay/cfag12864b.c b/drivers/auxdisplay/cfag12864b.c index 7eebae7e322c..fd430e6866a1 100644 --- a/drivers/auxdisplay/cfag12864b.c +++ b/drivers/auxdisplay/cfag12864b.c @@ -5,7 +5,7 @@ * Description: cfag12864b LCD driver * Depends: ks0108 * - * Author: Copyright (C) Miguel Ojeda Sandonis + * Author: Copyright (C) Miguel Ojeda * Date: 2006-10-31 */ @@ -376,5 +376,5 @@ module_init(cfag12864b_init); module_exit(cfag12864b_exit); MODULE_LICENSE("GPL v2"); -MODULE_AUTHOR("Miguel Ojeda Sandonis "); +MODULE_AUTHOR("Miguel Ojeda "); MODULE_DESCRIPTION("cfag12864b LCD driver"); diff --git a/drivers/auxdisplay/cfag12864bfb.c b/drivers/auxdisplay/cfag12864bfb.c index 2002291ab338..d66821adf453 100644 --- a/drivers/auxdisplay/cfag12864bfb.c +++ b/drivers/auxdisplay/cfag12864bfb.c @@ -5,7 +5,7 @@ * Description: cfag12864b LCD framebuffer driver * Depends: cfag12864b * - * Author: Copyright (C) Miguel Ojeda Sandonis + * Author: Copyright (C) Miguel Ojeda * Date: 2006-10-31 */ @@ -171,5 +171,5 @@ module_init(cfag12864bfb_init); module_exit(cfag12864bfb_exit); MODULE_LICENSE("GPL v2"); -MODULE_AUTHOR("Miguel Ojeda Sandonis "); +MODULE_AUTHOR("Miguel Ojeda "); MODULE_DESCRIPTION("cfag12864b LCD framebuffer driver"); diff --git a/drivers/auxdisplay/ks0108.c b/drivers/auxdisplay/ks0108.c index abfe3fa9e6f4..03c95ad4216c 100644 --- a/drivers/auxdisplay/ks0108.c +++ b/drivers/auxdisplay/ks0108.c @@ -5,7 +5,7 @@ * Description: ks0108 LCD Controller driver * Depends: parport * - * Author: Copyright (C) Miguel Ojeda Sandonis + * Author: Copyright (C) Miguel Ojeda * Date: 2006-10-31 */ @@ -182,6 +182,6 @@ module_init(ks0108_init); module_exit(ks0108_exit); MODULE_LICENSE("GPL v2"); -MODULE_AUTHOR("Miguel Ojeda Sandonis "); +MODULE_AUTHOR("Miguel Ojeda "); MODULE_DESCRIPTION("ks0108 LCD Controller driver"); diff --git a/include/linux/cfag12864b.h b/include/linux/cfag12864b.h index 4060004968c8..6617d9c68d86 100644 --- a/include/linux/cfag12864b.h +++ b/include/linux/cfag12864b.h @@ -4,7 +4,7 @@ * Version: 0.1.0 * Description: cfag12864b LCD driver header * - * Author: Copyright (C) Miguel Ojeda Sandonis + * Author: Copyright (C) Miguel Ojeda * Date: 2006-10-12 */ diff --git a/include/linux/ks0108.h b/include/linux/ks0108.h index 0738389b42b6..1a37a664f915 100644 --- a/include/linux/ks0108.h +++ b/include/linux/ks0108.h @@ -4,7 +4,7 @@ * Version: 0.1.0 * Description: ks0108 LCD Controller driver header * - * Author: Copyright (C) Miguel Ojeda Sandonis + * Author: Copyright (C) Miguel Ojeda * Date: 2006-10-31 */ diff --git a/samples/auxdisplay/cfag12864b-example.c b/samples/auxdisplay/cfag12864b-example.c index bfeab44f81d0..2e3bb7375c99 100644 --- a/samples/auxdisplay/cfag12864b-example.c +++ b/samples/auxdisplay/cfag12864b-example.c @@ -4,7 +4,7 @@ * Version: 0.1.0 * Description: cfag12864b LCD userspace example program * - * Author: Copyright (C) Miguel Ojeda Sandonis + * Author: Copyright (C) Miguel Ojeda * Date: 2006-10-31 */ -- cgit v1.2.3 From c1f26493ed7f363c63e0e9d91e50d4db26df6603 Mon Sep 17 00:00:00 2001 From: Hubert Jasudowicz Date: Thu, 25 Feb 2021 17:21:03 -0800 Subject: groups: use flexible-array member in struct group_info Replace zero-size array with flexible array member, as recommended by the docs. Link: https://lkml.kernel.org/r/155995eed35c3c1bdcc56e69d8997c8e4c46740a.1611620846.git.hubert.jasudowicz@gmail.com Signed-off-by: Hubert Jasudowicz Cc: "Peter Zijlstra (Intel)" Cc: Micah Morton Cc: Gao Xiang Cc: Michael Kelley Cc: Thomas Cedeno Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cred.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/cred.h b/include/linux/cred.h index 18639c069263..4c6350503697 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -25,7 +25,7 @@ struct inode; struct group_info { atomic_t usage; int ngroups; - kgid_t gid[0]; + kgid_t gid[]; } __randomize_layout; /** -- cgit v1.2.3 From a28a6e860c6cf231cf3c5171c75c342adcd00406 Mon Sep 17 00:00:00 2001 From: Francis Laniel Date: Thu, 25 Feb 2021 17:21:20 -0800 Subject: string.h: move fortified functions definitions in a dedicated header. This patch adds fortify-string.h to contain fortified functions definitions. Thus, the code is more separated and compile time is approximately 1% faster for people who do not set CONFIG_FORTIFY_SOURCE. Link: https://lkml.kernel.org/r/20210111092141.22946-1-laniel_francis@privacyrequired.com Link: https://lkml.kernel.org/r/20210111092141.22946-2-laniel_francis@privacyrequired.com Signed-off-by: Francis Laniel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fortify-string.h | 302 +++++++++++++++++++++++++++++++++++++++++ include/linux/string.h | 282 +------------------------------------- 2 files changed, 303 insertions(+), 281 deletions(-) create mode 100644 include/linux/fortify-string.h (limited to 'include') diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h new file mode 100644 index 000000000000..c1be37437e77 --- /dev/null +++ b/include/linux/fortify-string.h @@ -0,0 +1,302 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_FORTIFY_STRING_H_ +#define _LINUX_FORTIFY_STRING_H_ + + +#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) +extern void *__underlying_memchr(const void *p, int c, __kernel_size_t size) __RENAME(memchr); +extern int __underlying_memcmp(const void *p, const void *q, __kernel_size_t size) __RENAME(memcmp); +extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(memcpy); +extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(memmove); +extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(memset); +extern char *__underlying_strcat(char *p, const char *q) __RENAME(strcat); +extern char *__underlying_strcpy(char *p, const char *q) __RENAME(strcpy); +extern __kernel_size_t __underlying_strlen(const char *p) __RENAME(strlen); +extern char *__underlying_strncat(char *p, const char *q, __kernel_size_t count) __RENAME(strncat); +extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) __RENAME(strncpy); +#else +#define __underlying_memchr __builtin_memchr +#define __underlying_memcmp __builtin_memcmp +#define __underlying_memcpy __builtin_memcpy +#define __underlying_memmove __builtin_memmove +#define __underlying_memset __builtin_memset +#define __underlying_strcat __builtin_strcat +#define __underlying_strcpy __builtin_strcpy +#define __underlying_strlen __builtin_strlen +#define __underlying_strncat __builtin_strncat +#define __underlying_strncpy __builtin_strncpy +#endif + +__FORTIFY_INLINE char *strncpy(char *p, const char *q, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 1); + + if (__builtin_constant_p(size) && p_size < size) + __write_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __underlying_strncpy(p, q, size); +} + +__FORTIFY_INLINE char *strcat(char *p, const char *q) +{ + size_t p_size = __builtin_object_size(p, 1); + + if (p_size == (size_t)-1) + return __underlying_strcat(p, q); + if (strlcat(p, q, p_size) >= p_size) + fortify_panic(__func__); + return p; +} + +__FORTIFY_INLINE __kernel_size_t strlen(const char *p) +{ + __kernel_size_t ret; + size_t p_size = __builtin_object_size(p, 1); + + /* Work around gcc excess stack consumption issue */ + if (p_size == (size_t)-1 || + (__builtin_constant_p(p[p_size - 1]) && p[p_size - 1] == '\0')) + return __underlying_strlen(p); + ret = strnlen(p, p_size); + if (p_size <= ret) + fortify_panic(__func__); + return ret; +} + +extern __kernel_size_t __real_strnlen(const char *, __kernel_size_t) __RENAME(strnlen); +__FORTIFY_INLINE __kernel_size_t strnlen(const char *p, __kernel_size_t maxlen) +{ + size_t p_size = __builtin_object_size(p, 1); + __kernel_size_t ret = __real_strnlen(p, maxlen < p_size ? maxlen : p_size); + + if (p_size <= ret && maxlen != ret) + fortify_panic(__func__); + return ret; +} + +/* defined after fortified strlen to reuse it */ +extern size_t __real_strlcpy(char *, const char *, size_t) __RENAME(strlcpy); +__FORTIFY_INLINE size_t strlcpy(char *p, const char *q, size_t size) +{ + size_t ret; + size_t p_size = __builtin_object_size(p, 1); + size_t q_size = __builtin_object_size(q, 1); + + if (p_size == (size_t)-1 && q_size == (size_t)-1) + return __real_strlcpy(p, q, size); + ret = strlen(q); + if (size) { + size_t len = (ret >= size) ? size - 1 : ret; + + if (__builtin_constant_p(len) && len >= p_size) + __write_overflow(); + if (len >= p_size) + fortify_panic(__func__); + __underlying_memcpy(p, q, len); + p[len] = '\0'; + } + return ret; +} + +/* defined after fortified strnlen to reuse it */ +extern ssize_t __real_strscpy(char *, const char *, size_t) __RENAME(strscpy); +__FORTIFY_INLINE ssize_t strscpy(char *p, const char *q, size_t size) +{ + size_t len; + /* Use string size rather than possible enclosing struct size. */ + size_t p_size = __builtin_object_size(p, 1); + size_t q_size = __builtin_object_size(q, 1); + + /* If we cannot get size of p and q default to call strscpy. */ + if (p_size == (size_t) -1 && q_size == (size_t) -1) + return __real_strscpy(p, q, size); + + /* + * If size can be known at compile time and is greater than + * p_size, generate a compile time write overflow error. + */ + if (__builtin_constant_p(size) && size > p_size) + __write_overflow(); + + /* + * This call protects from read overflow, because len will default to q + * length if it smaller than size. + */ + len = strnlen(q, size); + /* + * If len equals size, we will copy only size bytes which leads to + * -E2BIG being returned. + * Otherwise we will copy len + 1 because of the final '\O'. + */ + len = len == size ? size : len + 1; + + /* + * Generate a runtime write overflow error if len is greater than + * p_size. + */ + if (len > p_size) + fortify_panic(__func__); + + /* + * We can now safely call vanilla strscpy because we are protected from: + * 1. Read overflow thanks to call to strnlen(). + * 2. Write overflow thanks to above ifs. + */ + return __real_strscpy(p, q, len); +} + +/* defined after fortified strlen and strnlen to reuse them */ +__FORTIFY_INLINE char *strncat(char *p, const char *q, __kernel_size_t count) +{ + size_t p_len, copy_len; + size_t p_size = __builtin_object_size(p, 1); + size_t q_size = __builtin_object_size(q, 1); + + if (p_size == (size_t)-1 && q_size == (size_t)-1) + return __underlying_strncat(p, q, count); + p_len = strlen(p); + copy_len = strnlen(q, count); + if (p_size < p_len + copy_len + 1) + fortify_panic(__func__); + __underlying_memcpy(p + p_len, q, copy_len); + p[p_len + copy_len] = '\0'; + return p; +} + +__FORTIFY_INLINE void *memset(void *p, int c, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + + if (__builtin_constant_p(size) && p_size < size) + __write_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __underlying_memset(p, c, size); +} + +__FORTIFY_INLINE void *memcpy(void *p, const void *q, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + size_t q_size = __builtin_object_size(q, 0); + + if (__builtin_constant_p(size)) { + if (p_size < size) + __write_overflow(); + if (q_size < size) + __read_overflow2(); + } + if (p_size < size || q_size < size) + fortify_panic(__func__); + return __underlying_memcpy(p, q, size); +} + +__FORTIFY_INLINE void *memmove(void *p, const void *q, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + size_t q_size = __builtin_object_size(q, 0); + + if (__builtin_constant_p(size)) { + if (p_size < size) + __write_overflow(); + if (q_size < size) + __read_overflow2(); + } + if (p_size < size || q_size < size) + fortify_panic(__func__); + return __underlying_memmove(p, q, size); +} + +extern void *__real_memscan(void *, int, __kernel_size_t) __RENAME(memscan); +__FORTIFY_INLINE void *memscan(void *p, int c, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + + if (__builtin_constant_p(size) && p_size < size) + __read_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __real_memscan(p, c, size); +} + +__FORTIFY_INLINE int memcmp(const void *p, const void *q, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + size_t q_size = __builtin_object_size(q, 0); + + if (__builtin_constant_p(size)) { + if (p_size < size) + __read_overflow(); + if (q_size < size) + __read_overflow2(); + } + if (p_size < size || q_size < size) + fortify_panic(__func__); + return __underlying_memcmp(p, q, size); +} + +__FORTIFY_INLINE void *memchr(const void *p, int c, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + + if (__builtin_constant_p(size) && p_size < size) + __read_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __underlying_memchr(p, c, size); +} + +void *__real_memchr_inv(const void *s, int c, size_t n) __RENAME(memchr_inv); +__FORTIFY_INLINE void *memchr_inv(const void *p, int c, size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + + if (__builtin_constant_p(size) && p_size < size) + __read_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __real_memchr_inv(p, c, size); +} + +extern void *__real_kmemdup(const void *src, size_t len, gfp_t gfp) __RENAME(kmemdup); +__FORTIFY_INLINE void *kmemdup(const void *p, size_t size, gfp_t gfp) +{ + size_t p_size = __builtin_object_size(p, 0); + + if (__builtin_constant_p(size) && p_size < size) + __read_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __real_kmemdup(p, size, gfp); +} + +/* defined after fortified strlen and memcpy to reuse them */ +__FORTIFY_INLINE char *strcpy(char *p, const char *q) +{ + size_t p_size = __builtin_object_size(p, 1); + size_t q_size = __builtin_object_size(q, 1); + size_t size; + + if (p_size == (size_t)-1 && q_size == (size_t)-1) + return __underlying_strcpy(p, q); + size = strlen(q) + 1; + /* test here to use the more stringent object size */ + if (p_size < size) + fortify_panic(__func__); + memcpy(p, q, size); + return p; +} + +/* Don't use these outside the FORITFY_SOURCE implementation */ +#undef __underlying_memchr +#undef __underlying_memcmp +#undef __underlying_memcpy +#undef __underlying_memmove +#undef __underlying_memset +#undef __underlying_strcat +#undef __underlying_strcpy +#undef __underlying_strlen +#undef __underlying_strncat +#undef __underlying_strncpy + +#endif /* _LINUX_FORTIFY_STRING_H_ */ diff --git a/include/linux/string.h b/include/linux/string.h index 4fcfb56abcf5..9521d8cab18e 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -266,287 +266,7 @@ void __read_overflow3(void) __compiletime_error("detected read beyond size of ob void __write_overflow(void) __compiletime_error("detected write beyond size of object passed as 1st parameter"); #if !defined(__NO_FORTIFY) && defined(__OPTIMIZE__) && defined(CONFIG_FORTIFY_SOURCE) - -#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) -extern void *__underlying_memchr(const void *p, int c, __kernel_size_t size) __RENAME(memchr); -extern int __underlying_memcmp(const void *p, const void *q, __kernel_size_t size) __RENAME(memcmp); -extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(memcpy); -extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(memmove); -extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(memset); -extern char *__underlying_strcat(char *p, const char *q) __RENAME(strcat); -extern char *__underlying_strcpy(char *p, const char *q) __RENAME(strcpy); -extern __kernel_size_t __underlying_strlen(const char *p) __RENAME(strlen); -extern char *__underlying_strncat(char *p, const char *q, __kernel_size_t count) __RENAME(strncat); -extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) __RENAME(strncpy); -#else -#define __underlying_memchr __builtin_memchr -#define __underlying_memcmp __builtin_memcmp -#define __underlying_memcpy __builtin_memcpy -#define __underlying_memmove __builtin_memmove -#define __underlying_memset __builtin_memset -#define __underlying_strcat __builtin_strcat -#define __underlying_strcpy __builtin_strcpy -#define __underlying_strlen __builtin_strlen -#define __underlying_strncat __builtin_strncat -#define __underlying_strncpy __builtin_strncpy -#endif - -__FORTIFY_INLINE char *strncpy(char *p, const char *q, __kernel_size_t size) -{ - size_t p_size = __builtin_object_size(p, 1); - if (__builtin_constant_p(size) && p_size < size) - __write_overflow(); - if (p_size < size) - fortify_panic(__func__); - return __underlying_strncpy(p, q, size); -} - -__FORTIFY_INLINE char *strcat(char *p, const char *q) -{ - size_t p_size = __builtin_object_size(p, 1); - if (p_size == (size_t)-1) - return __underlying_strcat(p, q); - if (strlcat(p, q, p_size) >= p_size) - fortify_panic(__func__); - return p; -} - -__FORTIFY_INLINE __kernel_size_t strlen(const char *p) -{ - __kernel_size_t ret; - size_t p_size = __builtin_object_size(p, 1); - - /* Work around gcc excess stack consumption issue */ - if (p_size == (size_t)-1 || - (__builtin_constant_p(p[p_size - 1]) && p[p_size - 1] == '\0')) - return __underlying_strlen(p); - ret = strnlen(p, p_size); - if (p_size <= ret) - fortify_panic(__func__); - return ret; -} - -extern __kernel_size_t __real_strnlen(const char *, __kernel_size_t) __RENAME(strnlen); -__FORTIFY_INLINE __kernel_size_t strnlen(const char *p, __kernel_size_t maxlen) -{ - size_t p_size = __builtin_object_size(p, 1); - __kernel_size_t ret = __real_strnlen(p, maxlen < p_size ? maxlen : p_size); - if (p_size <= ret && maxlen != ret) - fortify_panic(__func__); - return ret; -} - -/* defined after fortified strlen to reuse it */ -extern size_t __real_strlcpy(char *, const char *, size_t) __RENAME(strlcpy); -__FORTIFY_INLINE size_t strlcpy(char *p, const char *q, size_t size) -{ - size_t ret; - size_t p_size = __builtin_object_size(p, 1); - size_t q_size = __builtin_object_size(q, 1); - if (p_size == (size_t)-1 && q_size == (size_t)-1) - return __real_strlcpy(p, q, size); - ret = strlen(q); - if (size) { - size_t len = (ret >= size) ? size - 1 : ret; - if (__builtin_constant_p(len) && len >= p_size) - __write_overflow(); - if (len >= p_size) - fortify_panic(__func__); - __underlying_memcpy(p, q, len); - p[len] = '\0'; - } - return ret; -} - -/* defined after fortified strnlen to reuse it */ -extern ssize_t __real_strscpy(char *, const char *, size_t) __RENAME(strscpy); -__FORTIFY_INLINE ssize_t strscpy(char *p, const char *q, size_t size) -{ - size_t len; - /* Use string size rather than possible enclosing struct size. */ - size_t p_size = __builtin_object_size(p, 1); - size_t q_size = __builtin_object_size(q, 1); - - /* If we cannot get size of p and q default to call strscpy. */ - if (p_size == (size_t) -1 && q_size == (size_t) -1) - return __real_strscpy(p, q, size); - - /* - * If size can be known at compile time and is greater than - * p_size, generate a compile time write overflow error. - */ - if (__builtin_constant_p(size) && size > p_size) - __write_overflow(); - - /* - * This call protects from read overflow, because len will default to q - * length if it smaller than size. - */ - len = strnlen(q, size); - /* - * If len equals size, we will copy only size bytes which leads to - * -E2BIG being returned. - * Otherwise we will copy len + 1 because of the final '\O'. - */ - len = len == size ? size : len + 1; - - /* - * Generate a runtime write overflow error if len is greater than - * p_size. - */ - if (len > p_size) - fortify_panic(__func__); - - /* - * We can now safely call vanilla strscpy because we are protected from: - * 1. Read overflow thanks to call to strnlen(). - * 2. Write overflow thanks to above ifs. - */ - return __real_strscpy(p, q, len); -} - -/* defined after fortified strlen and strnlen to reuse them */ -__FORTIFY_INLINE char *strncat(char *p, const char *q, __kernel_size_t count) -{ - size_t p_len, copy_len; - size_t p_size = __builtin_object_size(p, 1); - size_t q_size = __builtin_object_size(q, 1); - if (p_size == (size_t)-1 && q_size == (size_t)-1) - return __underlying_strncat(p, q, count); - p_len = strlen(p); - copy_len = strnlen(q, count); - if (p_size < p_len + copy_len + 1) - fortify_panic(__func__); - __underlying_memcpy(p + p_len, q, copy_len); - p[p_len + copy_len] = '\0'; - return p; -} - -__FORTIFY_INLINE void *memset(void *p, int c, __kernel_size_t size) -{ - size_t p_size = __builtin_object_size(p, 0); - if (__builtin_constant_p(size) && p_size < size) - __write_overflow(); - if (p_size < size) - fortify_panic(__func__); - return __underlying_memset(p, c, size); -} - -__FORTIFY_INLINE void *memcpy(void *p, const void *q, __kernel_size_t size) -{ - size_t p_size = __builtin_object_size(p, 0); - size_t q_size = __builtin_object_size(q, 0); - if (__builtin_constant_p(size)) { - if (p_size < size) - __write_overflow(); - if (q_size < size) - __read_overflow2(); - } - if (p_size < size || q_size < size) - fortify_panic(__func__); - return __underlying_memcpy(p, q, size); -} - -__FORTIFY_INLINE void *memmove(void *p, const void *q, __kernel_size_t size) -{ - size_t p_size = __builtin_object_size(p, 0); - size_t q_size = __builtin_object_size(q, 0); - if (__builtin_constant_p(size)) { - if (p_size < size) - __write_overflow(); - if (q_size < size) - __read_overflow2(); - } - if (p_size < size || q_size < size) - fortify_panic(__func__); - return __underlying_memmove(p, q, size); -} - -extern void *__real_memscan(void *, int, __kernel_size_t) __RENAME(memscan); -__FORTIFY_INLINE void *memscan(void *p, int c, __kernel_size_t size) -{ - size_t p_size = __builtin_object_size(p, 0); - if (__builtin_constant_p(size) && p_size < size) - __read_overflow(); - if (p_size < size) - fortify_panic(__func__); - return __real_memscan(p, c, size); -} - -__FORTIFY_INLINE int memcmp(const void *p, const void *q, __kernel_size_t size) -{ - size_t p_size = __builtin_object_size(p, 0); - size_t q_size = __builtin_object_size(q, 0); - if (__builtin_constant_p(size)) { - if (p_size < size) - __read_overflow(); - if (q_size < size) - __read_overflow2(); - } - if (p_size < size || q_size < size) - fortify_panic(__func__); - return __underlying_memcmp(p, q, size); -} - -__FORTIFY_INLINE void *memchr(const void *p, int c, __kernel_size_t size) -{ - size_t p_size = __builtin_object_size(p, 0); - if (__builtin_constant_p(size) && p_size < size) - __read_overflow(); - if (p_size < size) - fortify_panic(__func__); - return __underlying_memchr(p, c, size); -} - -void *__real_memchr_inv(const void *s, int c, size_t n) __RENAME(memchr_inv); -__FORTIFY_INLINE void *memchr_inv(const void *p, int c, size_t size) -{ - size_t p_size = __builtin_object_size(p, 0); - if (__builtin_constant_p(size) && p_size < size) - __read_overflow(); - if (p_size < size) - fortify_panic(__func__); - return __real_memchr_inv(p, c, size); -} - -extern void *__real_kmemdup(const void *src, size_t len, gfp_t gfp) __RENAME(kmemdup); -__FORTIFY_INLINE void *kmemdup(const void *p, size_t size, gfp_t gfp) -{ - size_t p_size = __builtin_object_size(p, 0); - if (__builtin_constant_p(size) && p_size < size) - __read_overflow(); - if (p_size < size) - fortify_panic(__func__); - return __real_kmemdup(p, size, gfp); -} - -/* defined after fortified strlen and memcpy to reuse them */ -__FORTIFY_INLINE char *strcpy(char *p, const char *q) -{ - size_t p_size = __builtin_object_size(p, 1); - size_t q_size = __builtin_object_size(q, 1); - size_t size; - if (p_size == (size_t)-1 && q_size == (size_t)-1) - return __underlying_strcpy(p, q); - size = strlen(q) + 1; - /* test here to use the more stringent object size */ - if (p_size < size) - fortify_panic(__func__); - memcpy(p, q, size); - return p; -} - -/* Don't use these outside the FORITFY_SOURCE implementation */ -#undef __underlying_memchr -#undef __underlying_memcmp -#undef __underlying_memcpy -#undef __underlying_memmove -#undef __underlying_memset -#undef __underlying_strcat -#undef __underlying_strcpy -#undef __underlying_strlen -#undef __underlying_strncat -#undef __underlying_strncpy +#include #endif /** -- cgit v1.2.3 From e1fdc403349c64fa58f4c163f4bf9b860b4db808 Mon Sep 17 00:00:00 2001 From: Vijayanand Jitta Date: Thu, 25 Feb 2021 17:21:27 -0800 Subject: lib: stackdepot: add support to disable stack depot Add a kernel parameter stack_depot_disable to disable stack depot. So that stack hash table doesn't consume any memory when stack depot is disabled. The use case is CONFIG_PAGE_OWNER without page_owner=on. Without this patch, stackdepot will consume the memory for the hashtable. By default, it's 8M which is never trivial. With this option, in CONFIG_PAGE_OWNER configured system, page_owner=off, stack_depot_disable in kernel command line, we could save the wasted memory for the hashtable. [akpm@linux-foundation.org: fix CONFIG_STACKDEPOT=n build] Link: https://lkml.kernel.org/r/1611749198-24316-2-git-send-email-vjitta@codeaurora.org Signed-off-by: Vinayak Menon Signed-off-by: Vijayanand Jitta Cc: Alexander Potapenko Cc: Minchan Kim Cc: Yogesh Lal Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/kernel-parameters.txt | 6 +++++ include/linux/stackdepot.h | 9 +++++++ init/main.c | 2 ++ lib/stackdepot.c | 32 +++++++++++++++++++++---- 4 files changed, 45 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index bab6a8b01202..04545725f187 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -5182,6 +5182,12 @@ growing up) the main stack are reserved for no other mapping. Default value is 256 pages. + stack_depot_disable= [KNL] + Setting this to true through kernel command line will + disable the stack depot thereby saving the static memory + consumed by the stack hash table. By default this is set + to false. + stacktrace [FTRACE] Enabled the stack tracer on boot up. diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index 24d49c732341..6bb4bc1a5f54 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -21,4 +21,13 @@ unsigned int stack_depot_fetch(depot_stack_handle_t handle, unsigned int filter_irq_stacks(unsigned long *entries, unsigned int nr_entries); +#ifdef CONFIG_STACKDEPOT +int stack_depot_init(void); +#else +static inline int stack_depot_init(void) +{ + return 0; +} +#endif /* CONFIG_STACKDEPOT */ + #endif diff --git a/init/main.c b/init/main.c index 261051070e3c..3648c9f94882 100644 --- a/init/main.c +++ b/init/main.c @@ -97,6 +97,7 @@ #include #include #include +#include #include #include @@ -827,6 +828,7 @@ static void __init mm_init(void) init_mem_debugging_and_hardening(); kfence_alloc_pool(); report_meminit(); + stack_depot_init(); mem_init(); /* page_owner must be initialized after buddy is ready */ page_ext_init_flatmem_late(); diff --git a/lib/stackdepot.c b/lib/stackdepot.c index 4b9715470e87..cc21116512a7 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -31,6 +31,7 @@ #include #include #include +#include #define DEPOT_STACK_BITS (sizeof(depot_stack_handle_t) * 8) @@ -145,9 +146,32 @@ static struct stack_record *depot_alloc_stack(unsigned long *entries, int size, #define STACK_HASH_MASK (STACK_HASH_SIZE - 1) #define STACK_HASH_SEED 0x9747b28c -static struct stack_record *stack_table[STACK_HASH_SIZE] = { - [0 ... STACK_HASH_SIZE - 1] = NULL -}; +static bool stack_depot_disable; +static struct stack_record **stack_table; + +static int __init is_stack_depot_disabled(char *str) +{ + kstrtobool(str, &stack_depot_disable); + if (stack_depot_disable) { + pr_info("Stack Depot is disabled\n"); + stack_table = NULL; + } + return 0; +} +early_param("stack_depot_disable", is_stack_depot_disabled); + +int __init stack_depot_init(void) +{ + if (!stack_depot_disable) { + size_t size = (STACK_HASH_SIZE * sizeof(struct stack_record *)); + int i; + + stack_table = memblock_alloc(size, size); + for (i = 0; i < STACK_HASH_SIZE; i++) + stack_table[i] = NULL; + } + return 0; +} /* Calculate hash for a stack */ static inline u32 hash_stack(unsigned long *entries, unsigned int size) @@ -241,7 +265,7 @@ depot_stack_handle_t stack_depot_save(unsigned long *entries, unsigned long flags; u32 hash; - if (unlikely(nr_entries == 0)) + if (unlikely(nr_entries == 0) || stack_depot_disable) goto fast_exit; hash = hash_stack(entries, nr_entries); -- cgit v1.2.3 From 4945cca232ce8bc699b8743f2436af664c471b96 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 25 Feb 2021 17:21:37 -0800 Subject: include/linux/bitops.h: spelling s/synomyn/synonym/ Fix a misspelling of "synonym". Link: https://lkml.kernel.org/r/20210108105305.2028120-1-geert+renesas@glider.be Signed-off-by: Geert Uytterhoeven Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitops.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bitops.h b/include/linux/bitops.h index a61f192c096b..a5a48303b0f1 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -214,7 +214,7 @@ static inline int get_count_order_long(unsigned long l) * __ffs64 - find first set bit in a 64 bit word * @word: The 64 bit word * - * On 64 bit arches this is a synomyn for __ffs + * On 64 bit arches this is a synonym for __ffs * The result is not defined if no bits are set, so check that @word * is non-zero before calling this. */ -- cgit v1.2.3 From a5a673f7312253a842f3da8c60c980461cc269ec Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 25 Feb 2021 17:22:15 -0800 Subject: init: clean up early_param_on_off() macro Use early_param() to define early_param_on_off(). Link: https://lkml.kernel.org/r/20210201041532.4025025-1-masahiroy@kernel.org Signed-off-by: Masahiro Yamada Reviewed-by: Johan Hovold Reviewed-by: Miguel Ojeda Cc: Masahiro Yamada Cc: Joe Perches Cc: Nick Desaulniers Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/init.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/init.h b/include/linux/init.h index a01f01c1a5c5..31f54de58429 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -338,14 +338,14 @@ struct obs_kernel_param { var = 1; \ return 0; \ } \ - __setup_param(str_on, parse_##var##_on, parse_##var##_on, 1); \ + early_param(str_on, parse_##var##_on); \ \ static int __init parse_##var##_off(char *arg) \ { \ var = 0; \ return 0; \ } \ - __setup_param(str_off, parse_##var##_off, parse_##var##_off, 1) + early_param(str_off, parse_##var##_off) /* Relies on boot_command_line being set */ void __init parse_early_param(void); -- cgit v1.2.3 From d54ce6158e354f5358a547b96299ecd7f3725393 Mon Sep 17 00:00:00 2001 From: Sumit Garg Date: Thu, 25 Feb 2021 17:22:38 -0800 Subject: kgdb: fix to kill breakpoints on initmem after boot Currently breakpoints in kernel .init.text section are not handled correctly while allowing to remove them even after corresponding pages have been freed. Fix it via killing .init.text section breakpoints just prior to initmem pages being freed. Doug: "HW breakpoints aren't handled by this patch but it's probably not such a big deal". Link: https://lkml.kernel.org/r/20210224081652.587785-1-sumit.garg@linaro.org Signed-off-by: Sumit Garg Suggested-by: Doug Anderson Acked-by: Doug Anderson Acked-by: Daniel Thompson Tested-by: Daniel Thompson Cc: Masami Hiramatsu Cc: Steven Rostedt (VMware) Cc: Jason Wessel Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kgdb.h | 2 ++ init/main.c | 1 + kernel/debug/debug_core.c | 11 +++++++++++ 3 files changed, 14 insertions(+) (limited to 'include') diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index 0444b44bd156..392a3670944c 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -359,9 +359,11 @@ extern atomic_t kgdb_active; extern bool dbg_is_early; extern void __init dbg_late_init(void); extern void kgdb_panic(const char *msg); +extern void kgdb_free_init_mem(void); #else /* ! CONFIG_KGDB */ #define in_dbg_master() (0) #define dbg_late_init() static inline void kgdb_panic(const char *msg) {} +static inline void kgdb_free_init_mem(void) { } #endif /* ! CONFIG_KGDB */ #endif /* _KGDB_H_ */ diff --git a/init/main.c b/init/main.c index 3648c9f94882..53b278845b88 100644 --- a/init/main.c +++ b/init/main.c @@ -1426,6 +1426,7 @@ static int __ref kernel_init(void *unused) async_synchronize_full(); kprobe_free_init_mem(); ftrace_free_init_mem(); + kgdb_free_init_mem(); free_initmem(); mark_readonly(); diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index b636d517c02c..4708aec492df 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -455,6 +455,17 @@ setundefined: return 0; } +void kgdb_free_init_mem(void) +{ + int i; + + /* Clear init memory breakpoints. */ + for (i = 0; i < KGDB_MAX_BREAKPOINTS; i++) { + if (init_section_contains((void *)kgdb_break[i].bpt_addr, 0)) + kgdb_break[i].state = BP_UNDEFINED; + } +} + #ifdef CONFIG_KGDB_KDB void kdb_dump_stack_on_cpu(int cpu) { -- cgit v1.2.3 From f685a533a7fab35c5d069dcd663f59c8e4171a75 Mon Sep 17 00:00:00 2001 From: Huang Pei Date: Thu, 25 Feb 2021 17:22:49 -0800 Subject: MIPS: make userspace mapping young by default MIPS page fault path(except huge page) takes 3 exceptions (1 TLB Miss + 2 TLB Invalid), butthe second TLB Invalid exception is just triggered by __update_tlb from do_page_fault writing tlb without _PAGE_VALID set. With this patch, user space mapping prot is made young by default (with both _PAGE_VALID and _PAGE_YOUNG set), and it only take 1 TLB Miss + 1 TLB Invalid exception Remove pte_sw_mkyoung without polluting MM code and make page fault delay of MIPS on par with other architecture Link: https://lkml.kernel.org/r/20210204013942.8398-1-huangpei@loongson.cn Signed-off-by: Huang Pei Reviewed-by: Nicholas Piggin Acked-by: Acked-by: Thomas Bogendoerfer Cc: Christophe Leroy Cc: Cc: Bibo Mao Cc: Jiaxun Yang Cc: Paul Burton Cc: Li Xuefeng Cc: Yang Tiezhu Cc: Gao Juxin Cc: Fuxin Zhang Cc: Huacai Chen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/mips/mm/cache.c | 30 ++++++++++++++++-------------- include/linux/pgtable.h | 8 -------- mm/memory.c | 4 ---- 3 files changed, 16 insertions(+), 26 deletions(-) (limited to 'include') diff --git a/arch/mips/mm/cache.c b/arch/mips/mm/cache.c index 1754498b0717..7719d632df8d 100644 --- a/arch/mips/mm/cache.c +++ b/arch/mips/mm/cache.c @@ -157,29 +157,31 @@ unsigned long _page_cachable_default; EXPORT_SYMBOL(_page_cachable_default); #define PM(p) __pgprot(_page_cachable_default | (p)) +#define PVA(p) PM(_PAGE_VALID | _PAGE_ACCESSED | (p)) static inline void setup_protection_map(void) { protection_map[0] = PM(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ); - protection_map[1] = PM(_PAGE_PRESENT | _PAGE_NO_EXEC); - protection_map[2] = PM(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ); - protection_map[3] = PM(_PAGE_PRESENT | _PAGE_NO_EXEC); - protection_map[4] = PM(_PAGE_PRESENT); - protection_map[5] = PM(_PAGE_PRESENT); - protection_map[6] = PM(_PAGE_PRESENT); - protection_map[7] = PM(_PAGE_PRESENT); + protection_map[1] = PVA(_PAGE_PRESENT | _PAGE_NO_EXEC); + protection_map[2] = PVA(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ); + protection_map[3] = PVA(_PAGE_PRESENT | _PAGE_NO_EXEC); + protection_map[4] = PVA(_PAGE_PRESENT); + protection_map[5] = PVA(_PAGE_PRESENT); + protection_map[6] = PVA(_PAGE_PRESENT); + protection_map[7] = PVA(_PAGE_PRESENT); protection_map[8] = PM(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ); - protection_map[9] = PM(_PAGE_PRESENT | _PAGE_NO_EXEC); - protection_map[10] = PM(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE | + protection_map[9] = PVA(_PAGE_PRESENT | _PAGE_NO_EXEC); + protection_map[10] = PVA(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE | _PAGE_NO_READ); - protection_map[11] = PM(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE); - protection_map[12] = PM(_PAGE_PRESENT); - protection_map[13] = PM(_PAGE_PRESENT); - protection_map[14] = PM(_PAGE_PRESENT | _PAGE_WRITE); - protection_map[15] = PM(_PAGE_PRESENT | _PAGE_WRITE); + protection_map[11] = PVA(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE); + protection_map[12] = PVA(_PAGE_PRESENT); + protection_map[13] = PVA(_PAGE_PRESENT); + protection_map[14] = PVA(_PAGE_PRESENT); + protection_map[15] = PVA(_PAGE_PRESENT); } +#undef _PVA #undef PM void cpu_cache_init(void) diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 36eb748f3c97..cdfc4e9f253e 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -432,14 +432,6 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addres * To be differentiate with macro pte_mkyoung, this macro is used on platforms * where software maintains page access bit. */ -#ifndef pte_sw_mkyoung -static inline pte_t pte_sw_mkyoung(pte_t pte) -{ - return pte; -} -#define pte_sw_mkyoung pte_sw_mkyoung -#endif - #ifndef pte_savedwrite #define pte_savedwrite pte_write #endif diff --git a/mm/memory.c b/mm/memory.c index 784249f3307b..c8e357627318 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2902,7 +2902,6 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) } flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte)); entry = mk_pte(new_page, vma->vm_page_prot); - entry = pte_sw_mkyoung(entry); entry = maybe_mkwrite(pte_mkdirty(entry), vma); /* @@ -3560,7 +3559,6 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) __SetPageUptodate(page); entry = mk_pte(page, vma->vm_page_prot); - entry = pte_sw_mkyoung(entry); if (vma->vm_flags & VM_WRITE) entry = pte_mkwrite(pte_mkdirty(entry)); @@ -3745,8 +3743,6 @@ void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr) if (prefault && arch_wants_old_prefaulted_pte()) entry = pte_mkold(entry); - else - entry = pte_sw_mkyoung(entry); if (write) entry = maybe_mkwrite(pte_mkdirty(entry), vma); -- cgit v1.2.3 From 5f7136db82996089cdfb2939c7664b29e9da141d Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 29 Jan 2021 04:38:57 +0000 Subject: block: Add bio_max_segs It's often inconvenient to use BIO_MAX_PAGES due to min() requiring the sign to be the same. Introduce bio_max_segs() and change BIO_MAX_PAGES to be unsigned to make it easier for the users. Reviewed-by: Chaitanya Kulkarni Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Jens Axboe --- block/blk-map.c | 4 +--- drivers/block/xen-blkback/blkback.c | 4 +--- drivers/md/dm-io.c | 4 ++-- drivers/md/dm-log-writes.c | 10 +++++----- drivers/nvme/target/io-cmd-bdev.c | 8 ++++---- drivers/nvme/target/passthru.c | 4 ++-- drivers/target/target_core_iblock.c | 9 +++------ drivers/target/target_core_pscsi.c | 2 +- fs/block_dev.c | 10 +++++----- fs/direct-io.c | 2 +- fs/erofs/data.c | 4 +--- fs/ext4/readpage.c | 3 +-- fs/f2fs/data.c | 3 +-- fs/f2fs/node.c | 2 +- fs/iomap/buffered-io.c | 4 ++-- fs/mpage.c | 4 +--- fs/nfs/blocklayout/blocklayout.c | 6 +++--- fs/xfs/xfs_bio_io.c | 2 +- fs/xfs/xfs_buf.c | 4 ++-- include/linux/bio.h | 7 ++++++- 20 files changed, 44 insertions(+), 52 deletions(-) (limited to 'include') diff --git a/block/blk-map.c b/block/blk-map.c index 21630dccac62..369e204d14d0 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -150,9 +150,7 @@ static int bio_copy_user_iov(struct request *rq, struct rq_map_data *map_data, bmd->is_our_pages = !map_data; bmd->is_null_mapped = (map_data && map_data->null_mapped); - nr_pages = DIV_ROUND_UP(offset + len, PAGE_SIZE); - if (nr_pages > BIO_MAX_PAGES) - nr_pages = BIO_MAX_PAGES; + nr_pages = bio_max_segs(DIV_ROUND_UP(offset + len, PAGE_SIZE)); ret = -ENOMEM; bio = bio_kmalloc(gfp_mask, nr_pages); diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c index da16121140ca..1cdf09ff67b6 100644 --- a/drivers/block/xen-blkback/blkback.c +++ b/drivers/block/xen-blkback/blkback.c @@ -1326,9 +1326,7 @@ static int dispatch_rw_block_io(struct xen_blkif_ring *ring, pages[i]->page, seg[i].nsec << 9, seg[i].offset) == 0)) { - - int nr_iovecs = min_t(int, (nseg-i), BIO_MAX_PAGES); - bio = bio_alloc(GFP_KERNEL, nr_iovecs); + bio = bio_alloc(GFP_KERNEL, bio_max_segs(nseg - i)); if (unlikely(bio == NULL)) goto fail_put_bio; diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c index 4312007d2d34..2d3cda0acacb 100644 --- a/drivers/md/dm-io.c +++ b/drivers/md/dm-io.c @@ -341,8 +341,8 @@ static void do_region(int op, int op_flags, unsigned region, num_bvecs = 1; break; default: - num_bvecs = min_t(int, BIO_MAX_PAGES, - dm_sector_div_up(remaining, (PAGE_SIZE >> SECTOR_SHIFT))); + num_bvecs = bio_max_segs(dm_sector_div_up(remaining, + (PAGE_SIZE >> SECTOR_SHIFT))); } bio = bio_alloc_bioset(GFP_NOIO, num_bvecs, &io->client->bios); diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c index e3d35c6c9f71..57882654ffee 100644 --- a/drivers/md/dm-log-writes.c +++ b/drivers/md/dm-log-writes.c @@ -264,15 +264,14 @@ static int write_inline_data(struct log_writes_c *lc, void *entry, size_t entrylen, void *data, size_t datalen, sector_t sector) { - int num_pages, bio_pages, pg_datalen, pg_sectorlen, i; + int bio_pages, pg_datalen, pg_sectorlen, i; struct page *page; struct bio *bio; size_t ret; void *ptr; while (datalen) { - num_pages = ALIGN(datalen, PAGE_SIZE) >> PAGE_SHIFT; - bio_pages = min(num_pages, BIO_MAX_PAGES); + bio_pages = bio_max_segs(DIV_ROUND_UP(datalen, PAGE_SIZE)); atomic_inc(&lc->io_blocks); @@ -364,7 +363,7 @@ static int log_one_block(struct log_writes_c *lc, goto out; atomic_inc(&lc->io_blocks); - bio = bio_alloc(GFP_KERNEL, min(block->vec_cnt, BIO_MAX_PAGES)); + bio = bio_alloc(GFP_KERNEL, bio_max_segs(block->vec_cnt)); if (!bio) { DMERR("Couldn't alloc log bio"); goto error; @@ -386,7 +385,8 @@ static int log_one_block(struct log_writes_c *lc, if (ret != block->vecs[i].bv_len) { atomic_inc(&lc->io_blocks); submit_bio(bio); - bio = bio_alloc(GFP_KERNEL, min(block->vec_cnt - i, BIO_MAX_PAGES)); + bio = bio_alloc(GFP_KERNEL, + bio_max_segs(block->vec_cnt - i)); if (!bio) { DMERR("Couldn't alloc log bio"); goto error; diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c index 3d9a5d3ed9cd..9a8b3726a37c 100644 --- a/drivers/nvme/target/io-cmd-bdev.c +++ b/drivers/nvme/target/io-cmd-bdev.c @@ -185,7 +185,7 @@ static int nvmet_bdev_alloc_bip(struct nvmet_req *req, struct bio *bio, } bip = bio_integrity_alloc(bio, GFP_NOIO, - min_t(unsigned int, req->metadata_sg_cnt, BIO_MAX_PAGES)); + bio_max_segs(req->metadata_sg_cnt)); if (IS_ERR(bip)) { pr_err("Unable to allocate bio_integrity_payload\n"); return PTR_ERR(bip); @@ -225,7 +225,7 @@ static int nvmet_bdev_alloc_bip(struct nvmet_req *req, struct bio *bio, static void nvmet_bdev_execute_rw(struct nvmet_req *req) { - int sg_cnt = req->sg_cnt; + unsigned int sg_cnt = req->sg_cnt; struct bio *bio; struct scatterlist *sg; struct blk_plug plug; @@ -262,7 +262,7 @@ static void nvmet_bdev_execute_rw(struct nvmet_req *req) bio = &req->b.inline_bio; bio_init(bio, req->inline_bvec, ARRAY_SIZE(req->inline_bvec)); } else { - bio = bio_alloc(GFP_KERNEL, min(sg_cnt, BIO_MAX_PAGES)); + bio = bio_alloc(GFP_KERNEL, bio_max_segs(sg_cnt)); } bio_set_dev(bio, req->ns->bdev); bio->bi_iter.bi_sector = sector; @@ -289,7 +289,7 @@ static void nvmet_bdev_execute_rw(struct nvmet_req *req) } } - bio = bio_alloc(GFP_KERNEL, min(sg_cnt, BIO_MAX_PAGES)); + bio = bio_alloc(GFP_KERNEL, bio_max_segs(sg_cnt)); bio_set_dev(bio, req->ns->bdev); bio->bi_iter.bi_sector = sector; bio->bi_opf = op; diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c index f50c7b2bf21c..26c587ccd152 100644 --- a/drivers/nvme/target/passthru.c +++ b/drivers/nvme/target/passthru.c @@ -26,7 +26,7 @@ static u16 nvmet_passthru_override_id_ctrl(struct nvmet_req *req) struct nvme_ctrl *pctrl = ctrl->subsys->passthru_ctrl; u16 status = NVME_SC_SUCCESS; struct nvme_id_ctrl *id; - int max_hw_sectors; + unsigned int max_hw_sectors; int page_shift; id = kzalloc(sizeof(*id), GFP_KERNEL); @@ -198,7 +198,7 @@ static int nvmet_passthru_map_sg(struct nvmet_req *req, struct request *rq) bio = &req->p.inline_bio; bio_init(bio, req->inline_bvec, ARRAY_SIZE(req->inline_bvec)); } else { - bio = bio_alloc(GFP_KERNEL, min(req->sg_cnt, BIO_MAX_PAGES)); + bio = bio_alloc(GFP_KERNEL, bio_max_segs(req->sg_cnt)); bio->bi_end_io = bio_put; } bio->bi_opf = req_op(rq); diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c index 8ed93fd205c7..ee3d52061281 100644 --- a/drivers/target/target_core_iblock.c +++ b/drivers/target/target_core_iblock.c @@ -315,10 +315,8 @@ iblock_get_bio(struct se_cmd *cmd, sector_t lba, u32 sg_num, int op, * Only allocate as many vector entries as the bio code allows us to, * we'll loop later on until we have handled the whole request. */ - if (sg_num > BIO_MAX_PAGES) - sg_num = BIO_MAX_PAGES; - - bio = bio_alloc_bioset(GFP_NOIO, sg_num, &ib_dev->ibd_bio_set); + bio = bio_alloc_bioset(GFP_NOIO, bio_max_segs(sg_num), + &ib_dev->ibd_bio_set); if (!bio) { pr_err("Unable to allocate memory for bio\n"); return NULL; @@ -638,8 +636,7 @@ iblock_alloc_bip(struct se_cmd *cmd, struct bio *bio, return -ENODEV; } - bip = bio_integrity_alloc(bio, GFP_NOIO, - min_t(unsigned int, cmd->t_prot_nents, BIO_MAX_PAGES)); + bip = bio_integrity_alloc(bio, GFP_NOIO, bio_max_segs(cmd->t_prot_nents)); if (IS_ERR(bip)) { pr_err("Unable to allocate bio_integrity_payload\n"); return PTR_ERR(bip); diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c index 33770e5808ce..3cbc074992bc 100644 --- a/drivers/target/target_core_pscsi.c +++ b/drivers/target/target_core_pscsi.c @@ -881,7 +881,7 @@ pscsi_map_sg(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents, if (!bio) { new_bio: - nr_vecs = min_t(int, BIO_MAX_PAGES, nr_pages); + nr_vecs = bio_max_segs(nr_pages); nr_pages -= nr_vecs; /* * Calls bio_kmalloc() and sets bio->bi_end_io() diff --git a/fs/block_dev.c b/fs/block_dev.c index ec26179c8062..0f95ff343d6b 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -221,7 +221,7 @@ static void blkdev_bio_end_io_simple(struct bio *bio) static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter, - int nr_pages) + unsigned int nr_pages) { struct file *file = iocb->ki_filp; struct block_device *bdev = I_BDEV(bdev_file_inode(file)); @@ -355,8 +355,8 @@ static void blkdev_bio_end_io(struct bio *bio) } } -static ssize_t -__blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) +static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, + unsigned int nr_pages) { struct file *file = iocb->ki_filp; struct inode *inode = bdev_file_inode(file); @@ -486,7 +486,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) static ssize_t blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { - int nr_pages; + unsigned int nr_pages; if (!iov_iter_count(iter)) return 0; @@ -495,7 +495,7 @@ blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter) if (is_sync_kiocb(iocb) && nr_pages <= BIO_MAX_PAGES) return __blkdev_direct_IO_simple(iocb, iter, nr_pages); - return __blkdev_direct_IO(iocb, iter, min(nr_pages, BIO_MAX_PAGES)); + return __blkdev_direct_IO(iocb, iter, bio_max_segs(nr_pages)); } static __init int blkdev_init(void) diff --git a/fs/direct-io.c b/fs/direct-io.c index aa1083ecd623..c9639b4166c2 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -695,7 +695,7 @@ static inline int dio_new_bio(struct dio *dio, struct dio_submit *sdio, if (ret) goto out; sector = start_sector << (sdio->blkbits - 9); - nr_pages = min(sdio->pages_in_io, BIO_MAX_PAGES); + nr_pages = bio_max_segs(sdio->pages_in_io); BUG_ON(nr_pages <= 0); dio_bio_alloc(dio, sdio, map_bh->b_bdev, sector, nr_pages); sdio->boundary = 0; diff --git a/fs/erofs/data.c b/fs/erofs/data.c index ea4f693bee22..f88851c5c250 100644 --- a/fs/erofs/data.c +++ b/fs/erofs/data.c @@ -215,10 +215,8 @@ submit_bio_retry: /* max # of continuous pages */ if (nblocks > DIV_ROUND_UP(map.m_plen, PAGE_SIZE)) nblocks = DIV_ROUND_UP(map.m_plen, PAGE_SIZE); - if (nblocks > BIO_MAX_PAGES) - nblocks = BIO_MAX_PAGES; - bio = bio_alloc(GFP_NOIO, nblocks); + bio = bio_alloc(GFP_NOIO, bio_max_segs(nblocks)); bio->bi_end_io = erofs_readendio; bio_set_dev(bio, sb->s_bdev); diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c index f014c5e473a9..3db923403505 100644 --- a/fs/ext4/readpage.c +++ b/fs/ext4/readpage.c @@ -371,8 +371,7 @@ int ext4_mpage_readpages(struct inode *inode, * bio_alloc will _always_ be able to allocate a bio if * __GFP_DIRECT_RECLAIM is set, see bio_alloc_bioset(). */ - bio = bio_alloc(GFP_KERNEL, - min_t(int, nr_pages, BIO_MAX_PAGES)); + bio = bio_alloc(GFP_KERNEL, bio_max_segs(nr_pages)); fscrypt_set_bio_crypt_ctx(bio, inode, next_block, GFP_KERNEL); ext4_set_bio_post_read_ctx(bio, inode, page->index); diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index b9721c8f116c..7c95818639a6 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -969,8 +969,7 @@ static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr, unsigned int post_read_steps = 0; bio = bio_alloc_bioset(for_write ? GFP_NOIO : GFP_KERNEL, - min_t(int, nr_pages, BIO_MAX_PAGES), - &f2fs_bioset); + bio_max_segs(nr_pages), &f2fs_bioset); if (!bio) return ERR_PTR(-ENOMEM); diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index a8a0fb890e8d..4b0e2e3c2c88 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -2747,7 +2747,7 @@ int f2fs_restore_node_summary(struct f2fs_sb_info *sbi, sum_entry = &sum->entries[0]; for (i = 0; i < last_offset; i += nrpages, addr += nrpages) { - nrpages = min(last_offset - i, BIO_MAX_PAGES); + nrpages = bio_max_segs(last_offset - i); /* readahead node pages */ f2fs_ra_meta_pages(sbi, addr, nrpages, META_POR, true); diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 16a1e82e3aeb..0d9d1a6a947e 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -278,14 +278,14 @@ iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data, if (!is_contig || bio_full(ctx->bio, plen)) { gfp_t gfp = mapping_gfp_constraint(page->mapping, GFP_KERNEL); gfp_t orig_gfp = gfp; - int nr_vecs = (length + PAGE_SIZE - 1) >> PAGE_SHIFT; + unsigned int nr_vecs = DIV_ROUND_UP(length, PAGE_SIZE); if (ctx->bio) submit_bio(ctx->bio); if (ctx->rac) /* same as readahead_gfp_mask */ gfp |= __GFP_NORETRY | __GFP_NOWARN; - ctx->bio = bio_alloc(gfp, min(BIO_MAX_PAGES, nr_vecs)); + ctx->bio = bio_alloc(gfp, bio_max_segs(nr_vecs)); /* * If the bio_alloc fails, try it again for a single page to * avoid having to deal with partial page reads. This emulates diff --git a/fs/mpage.c b/fs/mpage.c index 830e6cc2a9e7..961234d68779 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -304,9 +304,7 @@ alloc_new: goto out; } args->bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9), - min_t(int, args->nr_pages, - BIO_MAX_PAGES), - gfp); + bio_max_segs(args->nr_pages), gfp); if (args->bio == NULL) goto confused; } diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index 1a96ce28efb0..fe860c538747 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -115,13 +115,13 @@ bl_submit_bio(struct bio *bio) return NULL; } -static struct bio * -bl_alloc_init_bio(int npg, struct block_device *bdev, sector_t disk_sector, +static struct bio *bl_alloc_init_bio(unsigned int npg, + struct block_device *bdev, sector_t disk_sector, bio_end_io_t end_io, struct parallel_io *par) { struct bio *bio; - npg = min(npg, BIO_MAX_PAGES); + npg = bio_max_segs(npg); bio = bio_alloc(GFP_NOIO, npg); if (bio) { bio->bi_iter.bi_sector = disk_sector; diff --git a/fs/xfs/xfs_bio_io.c b/fs/xfs/xfs_bio_io.c index e2148f2d5d6b..17f36db2f792 100644 --- a/fs/xfs/xfs_bio_io.c +++ b/fs/xfs/xfs_bio_io.c @@ -6,7 +6,7 @@ static inline unsigned int bio_max_vecs(unsigned int count) { - return min_t(unsigned, howmany(count, PAGE_SIZE), BIO_MAX_PAGES); + return bio_max_segs(howmany(count, PAGE_SIZE)); } int diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index f6e5235df7c9..37a1d12762d8 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -1480,7 +1480,7 @@ xfs_buf_ioapply_map( int op) { int page_index; - int total_nr_pages = bp->b_page_count; + unsigned int total_nr_pages = bp->b_page_count; int nr_pages; struct bio *bio; sector_t sector = bp->b_maps[map].bm_bn; @@ -1505,7 +1505,7 @@ xfs_buf_ioapply_map( next_chunk: atomic_inc(&bp->b_io_remaining); - nr_pages = min(total_nr_pages, BIO_MAX_PAGES); + nr_pages = bio_max_segs(total_nr_pages); bio = bio_alloc(GFP_NOIO, nr_pages); bio_set_dev(bio, bp->b_target->bt_bdev); diff --git a/include/linux/bio.h b/include/linux/bio.h index 5b468f2242ff..983ed2fe7c85 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -20,7 +20,12 @@ #define BIO_BUG_ON #endif -#define BIO_MAX_PAGES 256 +#define BIO_MAX_PAGES 256U + +static inline unsigned int bio_max_segs(unsigned int nr_segs) +{ + return min(nr_segs, BIO_MAX_PAGES); +} #define bio_prio(bio) (bio)->bi_ioprio #define bio_set_prio(bio, prio) ((bio)->bi_ioprio = prio) -- cgit v1.2.3 From c7929b15b6e926c7150d9ec64844aceecf8a7a4a Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Mon, 1 Mar 2021 18:31:19 -0600 Subject: ASoC: soc-acpi: allow for partial match in parent name To change the module dependencies and simplify Kconfigs, we need to introduce new driver names (sof-audio-acpi-intel-byt and sof-audio-acpi-intel-bdw), and move from an exact string match to a partial one. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Kai Vehmanen Reviewed-by: Guennadi Liakhovetski Reviewed-by: Bard Liao Acked-by: Mark Brown Acked-by: Vinod Koul Link: https://lore.kernel.org/r/20210302003125.1178419-2-pierre-louis.bossart@linux.intel.com Signed-off-by: Takashi Iwai --- include/sound/soc-acpi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/sound/soc-acpi.h b/include/sound/soc-acpi.h index 9a43c44dcbbb..c45075024c30 100644 --- a/include/sound/soc-acpi.h +++ b/include/sound/soc-acpi.h @@ -174,7 +174,7 @@ struct snd_soc_acpi_codecs { static inline bool snd_soc_acpi_sof_parent(struct device *dev) { return dev->parent && dev->parent->driver && dev->parent->driver->name && - !strcmp(dev->parent->driver->name, "sof-audio-acpi"); + !strncmp(dev->parent->driver->name, "sof-audio-acpi", strlen("sof-audio-acpi")); } #endif -- cgit v1.2.3 From 08c2a4bc9f2acaefbd0158866db5cb3238a68674 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Mon, 1 Mar 2021 18:31:24 -0600 Subject: ALSA: hda: move Intel SoundWire ACPI scan to dedicated module The ACPI scan capabilities is called from the intel-dspconfig as well as the SOF/HDaudio drivers. This creates dependencies and randconfig issues when HDaudio and SOF/SoundWire are not all configured as modules. To simplify Kconfig dependencies between HDAudio, SoundWire, SOF and intel-dspconfig, move the ACPI scan helpers to a dedicated module. This follows the same idea as NHLT helpers which are already handled as a dedicated module. The only functional change is that the kernel parameter to filter links is now handled by a different module, but that was only provided for developers needing work-arounds for early BIOS releases. Reported-by: Arnd Bergmann Signed-off-by: Pierre-Louis Bossart Reviewed-by: Kai Vehmanen Reviewed-by: Guennadi Liakhovetski Reviewed-by: Bard Liao Acked-by: Mark Brown Acked-by: Vinod Koul Link: https://lore.kernel.org/r/20210302003125.1178419-7-pierre-louis.bossart@linux.intel.com Signed-off-by: Takashi Iwai --- drivers/soundwire/intel.h | 2 - drivers/soundwire/intel_init.c | 158 -------------------------------- include/linux/soundwire/sdw_intel.h | 2 + sound/hda/Kconfig | 4 + sound/hda/Makefile | 3 + sound/hda/intel-dsp-config.c | 2 +- sound/hda/intel-sdw-acpi.c | 174 ++++++++++++++++++++++++++++++++++++ sound/soc/sof/intel/Kconfig | 1 + sound/soc/sof/intel/hda.c | 1 + 9 files changed, 186 insertions(+), 161 deletions(-) create mode 100644 sound/hda/intel-sdw-acpi.c (limited to 'include') diff --git a/drivers/soundwire/intel.h b/drivers/soundwire/intel.h index 76820d0b9deb..06bac8ba14e9 100644 --- a/drivers/soundwire/intel.h +++ b/drivers/soundwire/intel.h @@ -48,8 +48,6 @@ struct sdw_intel { #endif }; -#define SDW_INTEL_QUIRK_MASK_BUS_DISABLE BIT(1) - int intel_master_startup(struct platform_device *pdev); int intel_master_process_wakeen_event(struct platform_device *pdev); diff --git a/drivers/soundwire/intel_init.c b/drivers/soundwire/intel_init.c index bc8520eb385e..05b726cdfebc 100644 --- a/drivers/soundwire/intel_init.c +++ b/drivers/soundwire/intel_init.c @@ -18,42 +18,12 @@ #include "cadence_master.h" #include "intel.h" -#define SDW_LINK_TYPE 4 /* from Intel ACPI documentation */ -#define SDW_MAX_LINKS 4 #define SDW_SHIM_LCAP 0x0 #define SDW_SHIM_BASE 0x2C000 #define SDW_ALH_BASE 0x2C800 #define SDW_LINK_BASE 0x30000 #define SDW_LINK_SIZE 0x10000 -static int ctrl_link_mask; -module_param_named(sdw_link_mask, ctrl_link_mask, int, 0444); -MODULE_PARM_DESC(sdw_link_mask, "Intel link mask (one bit per link)"); - -static bool is_link_enabled(struct fwnode_handle *fw_node, int i) -{ - struct fwnode_handle *link; - char name[32]; - u32 quirk_mask = 0; - - /* Find master handle */ - snprintf(name, sizeof(name), - "mipi-sdw-link-%d-subproperties", i); - - link = fwnode_get_named_child_node(fw_node, name); - if (!link) - return false; - - fwnode_property_read_u32(link, - "intel-quirk-mask", - &quirk_mask); - - if (quirk_mask & SDW_INTEL_QUIRK_MASK_BUS_DISABLE) - return false; - - return true; -} - static int sdw_intel_cleanup(struct sdw_intel_ctx *ctx) { struct sdw_intel_link_res *link = ctx->links; @@ -81,74 +51,6 @@ static int sdw_intel_cleanup(struct sdw_intel_ctx *ctx) return 0; } -static int -sdw_intel_scan_controller(struct sdw_intel_acpi_info *info) -{ - struct acpi_device *adev; - int ret, i; - u8 count; - - if (acpi_bus_get_device(info->handle, &adev)) - return -EINVAL; - - /* Found controller, find links supported */ - count = 0; - ret = fwnode_property_read_u8_array(acpi_fwnode_handle(adev), - "mipi-sdw-master-count", &count, 1); - - /* - * In theory we could check the number of links supported in - * hardware, but in that step we cannot assume SoundWire IP is - * powered. - * - * In addition, if the BIOS doesn't even provide this - * 'master-count' property then all the inits based on link - * masks will fail as well. - * - * We will check the hardware capabilities in the startup() step - */ - - if (ret) { - dev_err(&adev->dev, - "Failed to read mipi-sdw-master-count: %d\n", ret); - return -EINVAL; - } - - /* Check count is within bounds */ - if (count > SDW_MAX_LINKS) { - dev_err(&adev->dev, "Link count %d exceeds max %d\n", - count, SDW_MAX_LINKS); - return -EINVAL; - } - - if (!count) { - dev_warn(&adev->dev, "No SoundWire links detected\n"); - return -EINVAL; - } - dev_dbg(&adev->dev, "ACPI reports %d SDW Link devices\n", count); - - info->count = count; - info->link_mask = 0; - - for (i = 0; i < count; i++) { - if (ctrl_link_mask && !(ctrl_link_mask & BIT(i))) { - dev_dbg(&adev->dev, - "Link %d masked, will not be enabled\n", i); - continue; - } - - if (!is_link_enabled(acpi_fwnode_handle(adev), i)) { - dev_dbg(&adev->dev, - "Link %d not selected in firmware\n", i); - continue; - } - - info->link_mask |= BIT(i); - } - - return 0; -} - #define HDA_DSP_REG_ADSPIC2 (0x10) #define HDA_DSP_REG_ADSPIS2 (0x14) #define HDA_DSP_REG_ADSPIC2_SNDW BIT(5) @@ -357,66 +259,6 @@ sdw_intel_startup_controller(struct sdw_intel_ctx *ctx) return 0; } -static acpi_status sdw_intel_acpi_cb(acpi_handle handle, u32 level, - void *cdata, void **return_value) -{ - struct sdw_intel_acpi_info *info = cdata; - struct acpi_device *adev; - acpi_status status; - u64 adr; - - status = acpi_evaluate_integer(handle, METHOD_NAME__ADR, NULL, &adr); - if (ACPI_FAILURE(status)) - return AE_OK; /* keep going */ - - if (acpi_bus_get_device(handle, &adev)) { - pr_err("%s: Couldn't find ACPI handle\n", __func__); - return AE_NOT_FOUND; - } - - info->handle = handle; - - /* - * On some Intel platforms, multiple children of the HDAS - * device can be found, but only one of them is the SoundWire - * controller. The SNDW device is always exposed with - * Name(_ADR, 0x40000000), with bits 31..28 representing the - * SoundWire link so filter accordingly - */ - if (FIELD_GET(GENMASK(31, 28), adr) != SDW_LINK_TYPE) - return AE_OK; /* keep going */ - - /* device found, stop namespace walk */ - return AE_CTRL_TERMINATE; -} - -/** - * sdw_intel_acpi_scan() - SoundWire Intel init routine - * @parent_handle: ACPI parent handle - * @info: description of what firmware/DSDT tables expose - * - * This scans the namespace and queries firmware to figure out which - * links to enable. A follow-up use of sdw_intel_probe() and - * sdw_intel_startup() is required for creation of devices and bus - * startup - */ -int sdw_intel_acpi_scan(acpi_handle *parent_handle, - struct sdw_intel_acpi_info *info) -{ - acpi_status status; - - info->handle = NULL; - status = acpi_walk_namespace(ACPI_TYPE_DEVICE, - parent_handle, 1, - sdw_intel_acpi_cb, - NULL, info, NULL); - if (ACPI_FAILURE(status) || info->handle == NULL) - return -ENODEV; - - return sdw_intel_scan_controller(info); -} -EXPORT_SYMBOL_NS(sdw_intel_acpi_scan, SOUNDWIRE_INTEL_INIT); - /** * sdw_intel_probe() - SoundWire Intel probe routine * @res: resource data diff --git a/include/linux/soundwire/sdw_intel.h b/include/linux/soundwire/sdw_intel.h index 120ffddc03d2..3a5446ac014a 100644 --- a/include/linux/soundwire/sdw_intel.h +++ b/include/linux/soundwire/sdw_intel.h @@ -187,4 +187,6 @@ void sdw_intel_enable_irq(void __iomem *mmio_base, bool enable); irqreturn_t sdw_intel_thread(int irq, void *dev_id); +#define SDW_INTEL_QUIRK_MASK_BUS_DISABLE BIT(1) + #endif diff --git a/sound/hda/Kconfig b/sound/hda/Kconfig index 9ed5cfa3c18c..57595f1552c9 100644 --- a/sound/hda/Kconfig +++ b/sound/hda/Kconfig @@ -44,9 +44,13 @@ config SND_INTEL_NHLT config SND_INTEL_DSP_CONFIG tristate select SND_INTEL_NHLT if ACPI + select SND_INTEL_SOUNDWIRE_ACPI if ACPI # this config should be selected only for Intel DSP platforms. # A fallback is provided so that the code compiles in all cases. +config SND_INTEL_SOUNDWIRE_ACPI + tristate + config SND_INTEL_BYT_PREFER_SOF bool "Prefer SOF driver over SST on BY/CHT platforms" depends on SND_SST_ATOM_HIFI2_PLATFORM_ACPI && SND_SOC_SOF_BAYTRAIL diff --git a/sound/hda/Makefile b/sound/hda/Makefile index 601e617918b8..78f487a635f8 100644 --- a/sound/hda/Makefile +++ b/sound/hda/Makefile @@ -17,3 +17,6 @@ obj-$(CONFIG_SND_HDA_EXT_CORE) += ext/ snd-intel-dspcfg-objs := intel-dsp-config.o snd-intel-dspcfg-$(CONFIG_SND_INTEL_NHLT) += intel-nhlt.o obj-$(CONFIG_SND_INTEL_DSP_CONFIG) += snd-intel-dspcfg.o + +snd-intel-sdw-acpi-objs := intel-sdw-acpi.o +obj-$(CONFIG_SND_INTEL_SOUNDWIRE_ACPI) += snd-intel-sdw-acpi.o diff --git a/sound/hda/intel-dsp-config.c b/sound/hda/intel-dsp-config.c index d1eb9d34993a..ab5ff7867eb9 100644 --- a/sound/hda/intel-dsp-config.c +++ b/sound/hda/intel-dsp-config.c @@ -557,4 +557,4 @@ EXPORT_SYMBOL_GPL(snd_intel_acpi_dsp_driver_probe); MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("Intel DSP config driver"); -MODULE_IMPORT_NS(SOUNDWIRE_INTEL_INIT); +MODULE_IMPORT_NS(SND_INTEL_SOUNDWIRE_ACPI); diff --git a/sound/hda/intel-sdw-acpi.c b/sound/hda/intel-sdw-acpi.c new file mode 100644 index 000000000000..6359936a1503 --- /dev/null +++ b/sound/hda/intel-sdw-acpi.c @@ -0,0 +1,174 @@ +// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) +// Copyright(c) 2015-2021 Intel Corporation. + +/* + * SDW Intel ACPI scan helpers + */ + +#include +#include +#include +#include +#include + +#define SDW_LINK_TYPE 4 /* from Intel ACPI documentation */ +#define SDW_MAX_LINKS 4 + +static int ctrl_link_mask; +module_param_named(sdw_link_mask, ctrl_link_mask, int, 0444); +MODULE_PARM_DESC(sdw_link_mask, "Intel link mask (one bit per link)"); + +static bool is_link_enabled(struct fwnode_handle *fw_node, int i) +{ + struct fwnode_handle *link; + char name[32]; + u32 quirk_mask = 0; + + /* Find master handle */ + snprintf(name, sizeof(name), + "mipi-sdw-link-%d-subproperties", i); + + link = fwnode_get_named_child_node(fw_node, name); + if (!link) + return false; + + fwnode_property_read_u32(link, + "intel-quirk-mask", + &quirk_mask); + + if (quirk_mask & SDW_INTEL_QUIRK_MASK_BUS_DISABLE) + return false; + + return true; +} + +static int +sdw_intel_scan_controller(struct sdw_intel_acpi_info *info) +{ + struct acpi_device *adev; + int ret, i; + u8 count; + + if (acpi_bus_get_device(info->handle, &adev)) + return -EINVAL; + + /* Found controller, find links supported */ + count = 0; + ret = fwnode_property_read_u8_array(acpi_fwnode_handle(adev), + "mipi-sdw-master-count", &count, 1); + + /* + * In theory we could check the number of links supported in + * hardware, but in that step we cannot assume SoundWire IP is + * powered. + * + * In addition, if the BIOS doesn't even provide this + * 'master-count' property then all the inits based on link + * masks will fail as well. + * + * We will check the hardware capabilities in the startup() step + */ + + if (ret) { + dev_err(&adev->dev, + "Failed to read mipi-sdw-master-count: %d\n", ret); + return -EINVAL; + } + + /* Check count is within bounds */ + if (count > SDW_MAX_LINKS) { + dev_err(&adev->dev, "Link count %d exceeds max %d\n", + count, SDW_MAX_LINKS); + return -EINVAL; + } + + if (!count) { + dev_warn(&adev->dev, "No SoundWire links detected\n"); + return -EINVAL; + } + dev_dbg(&adev->dev, "ACPI reports %d SDW Link devices\n", count); + + info->count = count; + info->link_mask = 0; + + for (i = 0; i < count; i++) { + if (ctrl_link_mask && !(ctrl_link_mask & BIT(i))) { + dev_dbg(&adev->dev, + "Link %d masked, will not be enabled\n", i); + continue; + } + + if (!is_link_enabled(acpi_fwnode_handle(adev), i)) { + dev_dbg(&adev->dev, + "Link %d not selected in firmware\n", i); + continue; + } + + info->link_mask |= BIT(i); + } + + return 0; +} + +static acpi_status sdw_intel_acpi_cb(acpi_handle handle, u32 level, + void *cdata, void **return_value) +{ + struct sdw_intel_acpi_info *info = cdata; + struct acpi_device *adev; + acpi_status status; + u64 adr; + + status = acpi_evaluate_integer(handle, METHOD_NAME__ADR, NULL, &adr); + if (ACPI_FAILURE(status)) + return AE_OK; /* keep going */ + + if (acpi_bus_get_device(handle, &adev)) { + pr_err("%s: Couldn't find ACPI handle\n", __func__); + return AE_NOT_FOUND; + } + + info->handle = handle; + + /* + * On some Intel platforms, multiple children of the HDAS + * device can be found, but only one of them is the SoundWire + * controller. The SNDW device is always exposed with + * Name(_ADR, 0x40000000), with bits 31..28 representing the + * SoundWire link so filter accordingly + */ + if (FIELD_GET(GENMASK(31, 28), adr) != SDW_LINK_TYPE) + return AE_OK; /* keep going */ + + /* device found, stop namespace walk */ + return AE_CTRL_TERMINATE; +} + +/** + * sdw_intel_acpi_scan() - SoundWire Intel init routine + * @parent_handle: ACPI parent handle + * @info: description of what firmware/DSDT tables expose + * + * This scans the namespace and queries firmware to figure out which + * links to enable. A follow-up use of sdw_intel_probe() and + * sdw_intel_startup() is required for creation of devices and bus + * startup + */ +int sdw_intel_acpi_scan(acpi_handle *parent_handle, + struct sdw_intel_acpi_info *info) +{ + acpi_status status; + + info->handle = NULL; + status = acpi_walk_namespace(ACPI_TYPE_DEVICE, + parent_handle, 1, + sdw_intel_acpi_cb, + NULL, info, NULL); + if (ACPI_FAILURE(status) || info->handle == NULL) + return -ENODEV; + + return sdw_intel_scan_controller(info); +} +EXPORT_SYMBOL_NS(sdw_intel_acpi_scan, SND_INTEL_SOUNDWIRE_ACPI); + +MODULE_LICENSE("Dual BSD/GPL"); +MODULE_DESCRIPTION("Intel Soundwire ACPI helpers"); diff --git a/sound/soc/sof/intel/Kconfig b/sound/soc/sof/intel/Kconfig index 21e24a3c64fb..da1c396f529d 100644 --- a/sound/soc/sof/intel/Kconfig +++ b/sound/soc/sof/intel/Kconfig @@ -286,6 +286,7 @@ config SND_SOC_SOF_INTEL_SOUNDWIRE depends on ACPI && SOUNDWIRE depends on !(SOUNDWIRE=m && SND_SOC_SOF_INTEL_SOUNDWIRE_LINK_BASELINE=y) select SOUNDWIRE_INTEL + select SND_INTEL_SOUNDWIRE_ACPI help This adds support for SoundWire with Sound Open Firmware for Intel(R) platforms. diff --git a/sound/soc/sof/intel/hda.c b/sound/soc/sof/intel/hda.c index 995a8c427177..1d29b1fd6a94 100644 --- a/sound/soc/sof/intel/hda.c +++ b/sound/soc/sof/intel/hda.c @@ -1279,4 +1279,5 @@ MODULE_IMPORT_NS(SND_SOC_SOF_PCI_DEV); MODULE_IMPORT_NS(SND_SOC_SOF_HDA_AUDIO_CODEC); MODULE_IMPORT_NS(SND_SOC_SOF_HDA_AUDIO_CODEC_I915); MODULE_IMPORT_NS(SND_SOC_SOF_XTENSA); +MODULE_IMPORT_NS(SND_INTEL_SOUNDWIRE_ACPI); MODULE_IMPORT_NS(SOUNDWIRE_INTEL_INIT); -- cgit v1.2.3