diff options
Diffstat (limited to 'drivers/gpu')
634 files changed, 20949 insertions, 11515 deletions
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index f7ea8e895c0c..fda170730468 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -396,6 +396,8 @@ source "drivers/gpu/drm/sprd/Kconfig" source "drivers/gpu/drm/imagination/Kconfig" +source "drivers/gpu/drm/tyr/Kconfig" + config DRM_HYPERV tristate "DRM Support for Hyper-V synthetic video device" depends on DRM && PCI && HYPERV diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile index 4dafbdc8f86a..4b2f7d794275 100644 --- a/drivers/gpu/drm/Makefile +++ b/drivers/gpu/drm/Makefile @@ -220,6 +220,7 @@ obj-$(CONFIG_DRM_VBOXVIDEO) += vboxvideo/ obj-$(CONFIG_DRM_LIMA) += lima/ obj-$(CONFIG_DRM_PANFROST) += panfrost/ obj-$(CONFIG_DRM_PANTHOR) += panthor/ +obj-$(CONFIG_DRM_TYR) += tyr/ obj-$(CONFIG_DRM_ASPEED_GFX) += aspeed/ obj-$(CONFIG_DRM_MCDE) += mcde/ obj-$(CONFIG_DRM_TIDSS) += tidss/ diff --git a/drivers/gpu/drm/amd/amdgpu/Makefile b/drivers/gpu/drm/amd/amdgpu/Makefile index 930de203d533..64e7acff8f18 100644 --- a/drivers/gpu/drm/amd/amdgpu/Makefile +++ b/drivers/gpu/drm/amd/amdgpu/Makefile @@ -84,7 +84,8 @@ amdgpu-y += \ vega20_reg_init.o nbio_v7_4.o nbio_v2_3.o nv.o arct_reg_init.o mxgpu_nv.o \ nbio_v7_2.o hdp_v4_0.o hdp_v5_0.o aldebaran_reg_init.o aldebaran.o soc21.o soc24.o \ sienna_cichlid.o smu_v13_0_10.o nbio_v4_3.o hdp_v6_0.o nbio_v7_7.o hdp_v5_2.o lsdma_v6_0.o \ - nbio_v7_9.o aqua_vanjaram.o nbio_v7_11.o lsdma_v7_0.o hdp_v7_0.o nbif_v6_3_1.o + nbio_v7_9.o aqua_vanjaram.o nbio_v7_11.o lsdma_v7_0.o hdp_v7_0.o nbif_v6_3_1.o \ + cyan_skillfish_reg_init.o # add DF block amdgpu-y += \ @@ -137,7 +138,6 @@ amdgpu-y += \ # add DCE block amdgpu-y += \ dce_v10_0.o \ - dce_v11_0.o \ amdgpu_vkms.o # add GFX block diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 01f53700694b..2a0df4cabb99 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -63,6 +63,7 @@ #include "kgd_pp_interface.h" #include "amd_shared.h" +#include "amdgpu_utils.h" #include "amdgpu_mode.h" #include "amdgpu_ih.h" #include "amdgpu_irq.h" @@ -434,7 +435,6 @@ struct amdgpu_clock { uint32_t default_mclk; uint32_t default_sclk; uint32_t default_dispclk; - uint32_t current_dispclk; uint32_t dp_extclk; uint32_t max_pixel_clock; }; @@ -545,7 +545,7 @@ struct amdgpu_wb { * this value can be accessed directly by using the offset as an index. * For the GPU address, it is necessary to use gpu_addr and the offset. */ - volatile uint32_t *wb; + uint32_t *wb; /** * @gpu_addr: @@ -721,7 +721,7 @@ int amdgpu_cs_wait_fences_ioctl(struct drm_device *dev, void *data, /* VRAM scratch page for HDP bug, default vram page */ struct amdgpu_mem_scratch { struct amdgpu_bo *robj; - volatile uint32_t *ptr; + uint32_t *ptr; u64 gpu_addr; }; @@ -752,6 +752,7 @@ typedef void (*amdgpu_block_wreg_t)(struct amdgpu_device*, uint32_t, uint32_t, u struct amdgpu_mmio_remap { u32 reg_offset; resource_size_t bus_addr; + struct amdgpu_bo *bo; }; /* Define the HW IP blocks will be used in driver , add more if necessary */ @@ -1149,9 +1150,6 @@ struct amdgpu_device { /* for userq and VM fences */ struct amdgpu_seq64 seq64; - /* KFD */ - struct amdgpu_kfd_dev kfd; - /* UMC */ struct amdgpu_umc umc; @@ -1314,6 +1312,11 @@ struct amdgpu_device { struct mutex userq_mutex; bool userq_halt_for_enforce_isolation; struct amdgpu_uid *uid_info; + + /* KFD + * Must be last --ends in a flexible-array member. + */ + struct amdgpu_kfd_dev kfd; }; static inline uint32_t amdgpu_ip_version(const struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c index fbe7616555c8..a2879d2b7c8e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c @@ -250,16 +250,24 @@ void amdgpu_amdkfd_interrupt(struct amdgpu_device *adev, void amdgpu_amdkfd_suspend(struct amdgpu_device *adev, bool suspend_proc) { - if (adev->kfd.dev) - kgd2kfd_suspend(adev->kfd.dev, suspend_proc); + if (adev->kfd.dev) { + if (adev->in_s0ix) + kgd2kfd_stop_sched_all_nodes(adev->kfd.dev); + else + kgd2kfd_suspend(adev->kfd.dev, suspend_proc); + } } int amdgpu_amdkfd_resume(struct amdgpu_device *adev, bool resume_proc) { int r = 0; - if (adev->kfd.dev) - r = kgd2kfd_resume(adev->kfd.dev, resume_proc); + if (adev->kfd.dev) { + if (adev->in_s0ix) + r = kgd2kfd_start_sched_all_nodes(adev->kfd.dev); + else + r = kgd2kfd_resume(adev->kfd.dev, resume_proc); + } return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h index 33eb4826b58b..9e120c934cc1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h @@ -107,11 +107,13 @@ struct amdgpu_kfd_dev { bool init_complete; struct work_struct reset_work; - /* HMM page migration MEMORY_DEVICE_PRIVATE mapping */ - struct dev_pagemap pgmap; - /* Client for KFD BO GEM handle allocations */ struct drm_client_dev client; + + /* HMM page migration MEMORY_DEVICE_PRIVATE mapping + * Must be last --ends in a flexible-array member. + */ + struct dev_pagemap pgmap; }; enum kgd_engine_type { @@ -426,7 +428,9 @@ void kgd2kfd_smi_event_throttle(struct kfd_dev *kfd, uint64_t throttle_bitmask); int kgd2kfd_check_and_lock_kfd(struct kfd_dev *kfd); void kgd2kfd_unlock_kfd(struct kfd_dev *kfd); int kgd2kfd_start_sched(struct kfd_dev *kfd, uint32_t node_id); +int kgd2kfd_start_sched_all_nodes(struct kfd_dev *kfd); int kgd2kfd_stop_sched(struct kfd_dev *kfd, uint32_t node_id); +int kgd2kfd_stop_sched_all_nodes(struct kfd_dev *kfd); bool kgd2kfd_compute_active(struct kfd_dev *kfd, uint32_t node_id); bool kgd2kfd_vmfault_fast_path(struct amdgpu_device *adev, struct amdgpu_iv_entry *entry, bool retry_fault); @@ -516,11 +520,21 @@ static inline int kgd2kfd_start_sched(struct kfd_dev *kfd, uint32_t node_id) return 0; } +static inline int kgd2kfd_start_sched_all_nodes(struct kfd_dev *kfd) +{ + return 0; +} + static inline int kgd2kfd_stop_sched(struct kfd_dev *kfd, uint32_t node_id) { return 0; } +static inline int kgd2kfd_stop_sched_all_nodes(struct kfd_dev *kfd) +{ + return 0; +} + static inline bool kgd2kfd_compute_active(struct kfd_dev *kfd, uint32_t node_id) { return false; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index d478acb4568a..c3b34a410375 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -213,19 +213,35 @@ int amdgpu_amdkfd_reserve_mem_limit(struct amdgpu_device *adev, spin_lock(&kfd_mem_limit.mem_limit_lock); if (kfd_mem_limit.system_mem_used + system_mem_needed > - kfd_mem_limit.max_system_mem_limit) + kfd_mem_limit.max_system_mem_limit) { pr_debug("Set no_system_mem_limit=1 if using shared memory\n"); + if (!no_system_mem_limit) { + ret = -ENOMEM; + goto release; + } + } - if ((kfd_mem_limit.system_mem_used + system_mem_needed > - kfd_mem_limit.max_system_mem_limit && !no_system_mem_limit) || - (kfd_mem_limit.ttm_mem_used + ttm_mem_needed > - kfd_mem_limit.max_ttm_mem_limit) || - (adev && xcp_id >= 0 && adev->kfd.vram_used[xcp_id] + vram_needed > - vram_size - reserved_for_pt - reserved_for_ras - atomic64_read(&adev->vram_pin_size))) { + if (kfd_mem_limit.ttm_mem_used + ttm_mem_needed > + kfd_mem_limit.max_ttm_mem_limit) { ret = -ENOMEM; goto release; } + /*if is_app_apu is false and apu_prefer_gtt is true, it is an APU with + * carve out < gtt. In that case, VRAM allocation will go to gtt domain, skip + * VRAM check since ttm_mem_limit check already cover this allocation + */ + + if (adev && xcp_id >= 0 && (!adev->apu_prefer_gtt || adev->gmc.is_app_apu)) { + uint64_t vram_available = + vram_size - reserved_for_pt - reserved_for_ras - + atomic64_read(&adev->vram_pin_size); + if (adev->kfd.vram_used[xcp_id] + vram_needed > vram_available) { + ret = -ENOMEM; + goto release; + } + } + /* Update memory accounting by decreasing available system * memory, TTM memory and GPU memory as computed above */ @@ -1627,11 +1643,15 @@ size_t amdgpu_amdkfd_get_available_memory(struct amdgpu_device *adev, uint64_t vram_available, system_mem_available, ttm_mem_available; spin_lock(&kfd_mem_limit.mem_limit_lock); - vram_available = KFD_XCP_MEMORY_SIZE(adev, xcp_id) - - adev->kfd.vram_used_aligned[xcp_id] - - atomic64_read(&adev->vram_pin_size) - - reserved_for_pt - - reserved_for_ras; + if (adev->apu_prefer_gtt && !adev->gmc.is_app_apu) + vram_available = KFD_XCP_MEMORY_SIZE(adev, xcp_id) + - adev->kfd.vram_used_aligned[xcp_id]; + else + vram_available = KFD_XCP_MEMORY_SIZE(adev, xcp_id) + - adev->kfd.vram_used_aligned[xcp_id] + - atomic64_read(&adev->vram_pin_size) + - reserved_for_pt + - reserved_for_ras; if (adev->apu_prefer_gtt) { system_mem_available = no_system_mem_limit ? diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c index e476e45b996a..763f2b8dcf13 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c @@ -706,7 +706,6 @@ int amdgpu_atombios_get_clock_info(struct amdgpu_device *adev) } adev->clock.dp_extclk = le16_to_cpu(firmware_info->info_21.usUniphyDPModeExtClkFreq); - adev->clock.current_dispclk = adev->clock.default_dispclk; adev->clock.max_pixel_clock = le16_to_cpu(firmware_info->info.usMaxPixelClock); if (adev->clock.max_pixel_clock == 0) @@ -1816,16 +1815,43 @@ static ssize_t amdgpu_atombios_get_vbios_version(struct device *dev, return sysfs_emit(buf, "%s\n", ctx->vbios_pn); } +static ssize_t amdgpu_atombios_get_vbios_build(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct drm_device *ddev = dev_get_drvdata(dev); + struct amdgpu_device *adev = drm_to_adev(ddev); + struct atom_context *ctx = adev->mode_info.atom_context; + + return sysfs_emit(buf, "%s\n", ctx->build_num); +} + static DEVICE_ATTR(vbios_version, 0444, amdgpu_atombios_get_vbios_version, NULL); +static DEVICE_ATTR(vbios_build, 0444, amdgpu_atombios_get_vbios_build, NULL); static struct attribute *amdgpu_vbios_version_attrs[] = { - &dev_attr_vbios_version.attr, - NULL + &dev_attr_vbios_version.attr, &dev_attr_vbios_build.attr, NULL }; +static umode_t amdgpu_vbios_version_attrs_is_visible(struct kobject *kobj, + struct attribute *attr, + int index) +{ + struct device *dev = kobj_to_dev(kobj); + struct drm_device *ddev = dev_get_drvdata(dev); + struct amdgpu_device *adev = drm_to_adev(ddev); + struct atom_context *ctx = adev->mode_info.atom_context; + + if (attr == &dev_attr_vbios_build.attr && !strlen(ctx->build_num)) + return 0; + + return attr->mode; +} + const struct attribute_group amdgpu_vbios_version_attr_group = { - .attrs = amdgpu_vbios_version_attrs + .attrs = amdgpu_vbios_version_attrs, + .is_visible = amdgpu_vbios_version_attrs_is_visible, }; int amdgpu_atombios_sysfs_init(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c index 702f6610d024..66fb37b64388 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c @@ -184,43 +184,36 @@ void amdgpu_bo_list_put(struct amdgpu_bo_list *list) int amdgpu_bo_create_list_entry_array(struct drm_amdgpu_bo_list_in *in, struct drm_amdgpu_bo_list_entry **info_param) { - const void __user *uptr = u64_to_user_ptr(in->bo_info_ptr); const uint32_t info_size = sizeof(struct drm_amdgpu_bo_list_entry); + const void __user *uptr = u64_to_user_ptr(in->bo_info_ptr); + const uint32_t bo_info_size = in->bo_info_size; + const uint32_t bo_number = in->bo_number; struct drm_amdgpu_bo_list_entry *info; - int r; - - info = kvmalloc_array(in->bo_number, info_size, GFP_KERNEL); - if (!info) - return -ENOMEM; /* copy the handle array from userspace to a kernel buffer */ - r = -EFAULT; - if (likely(info_size == in->bo_info_size)) { - unsigned long bytes = in->bo_number * - in->bo_info_size; - - if (copy_from_user(info, uptr, bytes)) - goto error_free; - + if (likely(info_size == bo_info_size)) { + info = vmemdup_array_user(uptr, bo_number, info_size); + if (IS_ERR(info)) + return PTR_ERR(info); } else { - unsigned long bytes = min(in->bo_info_size, info_size); + const uint32_t bytes = min(bo_info_size, info_size); unsigned i; - memset(info, 0, in->bo_number * info_size); - for (i = 0; i < in->bo_number; ++i) { - if (copy_from_user(&info[i], uptr, bytes)) - goto error_free; + info = kvmalloc_array(bo_number, info_size, GFP_KERNEL); + if (!info) + return -ENOMEM; - uptr += in->bo_info_size; + memset(info, 0, bo_number * info_size); + for (i = 0; i < bo_number; ++i, uptr += bo_info_size) { + if (copy_from_user(&info[i], uptr, bytes)) { + kvfree(info); + return -EFAULT; + } } } *info_param = info; return 0; - -error_free: - kvfree(info); - return r; } int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c index a381de8648e5..bf38fc69c1cf 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c @@ -1196,7 +1196,10 @@ static void amdgpu_connector_dvi_force(struct drm_connector *connector) } /** - * Returns the maximum supported HDMI (TMDS) pixel clock in KHz. + * amdgpu_max_hdmi_pixel_clock - Return max supported HDMI (TMDS) pixel clock + * @adev: pointer to amdgpu_device + * + * Return: maximum supported HDMI (TMDS) pixel clock in KHz. */ static int amdgpu_max_hdmi_pixel_clock(const struct amdgpu_device *adev) { @@ -1209,8 +1212,14 @@ static int amdgpu_max_hdmi_pixel_clock(const struct amdgpu_device *adev) } /** - * Validates the given display mode on DVI and HDMI connectors, - * including analog signals on DVI-I. + * amdgpu_connector_dvi_mode_valid - Validate a mode on DVI/HDMI connectors + * @connector: DRM connector to validate the mode on + * @mode: display mode to validate + * + * Validate the given display mode on DVI and HDMI connectors, including + * analog signals on DVI-I. + * + * Return: drm_mode_status indicating whether the mode is valid. */ static enum drm_mode_status amdgpu_connector_dvi_mode_valid(struct drm_connector *connector, const struct drm_display_mode *mode) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cper.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cper.c index 6c266f18c598..ef996493115f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cper.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cper.c @@ -68,7 +68,6 @@ void amdgpu_cper_entry_fill_hdr(struct amdgpu_device *adev, hdr->error_severity = sev; hdr->valid_bits.platform_id = 1; - hdr->valid_bits.partition_id = 1; hdr->valid_bits.timestamp = 1; amdgpu_cper_get_timestamp(&hdr->timestamp); @@ -174,7 +173,7 @@ int amdgpu_cper_entry_fill_runtime_section(struct amdgpu_device *adev, struct cper_sec_nonstd_err *section; bool poison; - poison = (sev == CPER_SEV_NON_FATAL_CORRECTED) ? false : true; + poison = sev != CPER_SEV_NON_FATAL_CORRECTED; section_desc = (struct cper_sec_desc *)((uint8_t *)hdr + SEC_DESC_OFFSET(idx)); section = (struct cper_sec_nonstd_err *)((uint8_t *)hdr + NONSTD_SEC_OFFSET(hdr->sec_cnt, idx)); @@ -220,7 +219,10 @@ int amdgpu_cper_entry_fill_bad_page_threshold_section(struct amdgpu_device *adev section->hdr.valid_bits.err_context_cnt = 1; section->info.error_type = RUNTIME; + section->info.valid_bits.ms_chk = 1; section->info.ms_chk_bits.err_type_valid = 1; + section->info.ms_chk_bits.err_type = 1; + section->info.ms_chk_bits.pcc = 1; section->ctx.reg_ctx_type = CPER_CTX_TYPE_CRASH; section->ctx.reg_arr_size = sizeof(section->ctx.reg_dump); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 2ac9729e4c86..defb511acc5a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -178,25 +178,17 @@ static int amdgpu_cs_pass1(struct amdgpu_cs_parser *p, struct amdgpu_fpriv *fpriv = p->filp->driver_priv; unsigned int num_ibs[AMDGPU_CS_GANG_SIZE] = { }; struct amdgpu_vm *vm = &fpriv->vm; - uint64_t *chunk_array_user; uint64_t *chunk_array; uint32_t uf_offset = 0; size_t size; int ret; int i; - chunk_array = kvmalloc_array(cs->in.num_chunks, sizeof(uint64_t), - GFP_KERNEL); - if (!chunk_array) - return -ENOMEM; - - /* get chunks */ - chunk_array_user = u64_to_user_ptr(cs->in.chunks); - if (copy_from_user(chunk_array, chunk_array_user, - sizeof(uint64_t)*cs->in.num_chunks)) { - ret = -EFAULT; - goto free_chunk; - } + chunk_array = memdup_array_user(u64_to_user_ptr(cs->in.chunks), + cs->in.num_chunks, + sizeof(uint64_t)); + if (IS_ERR(chunk_array)) + return PTR_ERR(chunk_array); p->nchunks = cs->in.num_chunks; p->chunks = kvmalloc_array(p->nchunks, sizeof(struct amdgpu_cs_chunk), @@ -209,7 +201,6 @@ static int amdgpu_cs_pass1(struct amdgpu_cs_parser *p, for (i = 0; i < p->nchunks; i++) { struct drm_amdgpu_cs_chunk __user *chunk_ptr = NULL; struct drm_amdgpu_cs_chunk user_chunk; - uint32_t __user *cdata; chunk_ptr = u64_to_user_ptr(chunk_array[i]); if (copy_from_user(&user_chunk, chunk_ptr, @@ -222,20 +213,16 @@ static int amdgpu_cs_pass1(struct amdgpu_cs_parser *p, p->chunks[i].length_dw = user_chunk.length_dw; size = p->chunks[i].length_dw; - cdata = u64_to_user_ptr(user_chunk.chunk_data); - p->chunks[i].kdata = kvmalloc_array(size, sizeof(uint32_t), - GFP_KERNEL); - if (p->chunks[i].kdata == NULL) { - ret = -ENOMEM; + p->chunks[i].kdata = vmemdup_array_user(u64_to_user_ptr(user_chunk.chunk_data), + size, + sizeof(uint32_t)); + if (IS_ERR(p->chunks[i].kdata)) { + ret = PTR_ERR(p->chunks[i].kdata); i--; goto free_partial_kdata; } size *= sizeof(uint32_t); - if (copy_from_user(p->chunks[i].kdata, cdata, size)) { - ret = -EFAULT; - goto free_partial_kdata; - } /* Assume the worst on the following checks */ ret = -EINVAL; @@ -286,7 +273,7 @@ static int amdgpu_cs_pass1(struct amdgpu_cs_parser *p, } } - if (!p->gang_size) { + if (!p->gang_size || (amdgpu_sriov_vf(p->adev) && p->gang_size > 1)) { ret = -EINVAL; goto free_all_kdata; } @@ -1767,30 +1754,21 @@ int amdgpu_cs_wait_fences_ioctl(struct drm_device *dev, void *data, { struct amdgpu_device *adev = drm_to_adev(dev); union drm_amdgpu_wait_fences *wait = data; - uint32_t fence_count = wait->in.fence_count; - struct drm_amdgpu_fence *fences_user; struct drm_amdgpu_fence *fences; int r; /* Get the fences from userspace */ - fences = kmalloc_array(fence_count, sizeof(struct drm_amdgpu_fence), - GFP_KERNEL); - if (fences == NULL) - return -ENOMEM; - - fences_user = u64_to_user_ptr(wait->in.fences); - if (copy_from_user(fences, fences_user, - sizeof(struct drm_amdgpu_fence) * fence_count)) { - r = -EFAULT; - goto err_free_fences; - } + fences = memdup_array_user(u64_to_user_ptr(wait->in.fences), + wait->in.fence_count, + sizeof(struct drm_amdgpu_fence)); + if (IS_ERR(fences)) + return PTR_ERR(fences); if (wait->in.wait_all) r = amdgpu_cs_wait_all_fences(adev, filp, wait, fences); else r = amdgpu_cs_wait_any_fence(adev, filp, wait, fences); -err_free_fences: kfree(fences); return r; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c index dfb6cfd83760..02138aa55793 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c @@ -88,8 +88,8 @@ int amdgpu_map_static_csa(struct amdgpu_device *adev, struct amdgpu_vm *vm, } r = amdgpu_vm_bo_map(adev, *bo_va, csa_addr, 0, size, - AMDGPU_VM_PAGE_READABLE | AMDGPU_VM_PAGE_WRITEABLE | - AMDGPU_VM_PAGE_EXECUTABLE); + AMDGPU_PTE_READABLE | AMDGPU_PTE_WRITEABLE | + AMDGPU_PTE_EXECUTABLE); if (r) { DRM_ERROR("failed to do bo_map on static CSA, err=%d\n", r); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c index 0e6e2e2acf5b..a70651050acf 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c @@ -2136,12 +2136,14 @@ static int amdgpu_pt_info_read(struct seq_file *m, void *unused) struct drm_file *file; struct amdgpu_fpriv *fpriv; struct amdgpu_bo *root_bo; + struct amdgpu_device *adev; int r; file = m->private; if (!file) return -EINVAL; + adev = drm_to_adev(file->minor->dev); fpriv = file->driver_priv; if (!fpriv || !fpriv->vm.root.bo) return -ENODEV; @@ -2153,7 +2155,11 @@ static int amdgpu_pt_info_read(struct seq_file *m, void *unused) return -EINVAL; } - seq_printf(m, "gpu_address: 0x%llx\n", amdgpu_bo_gpu_offset(fpriv->vm.root.bo)); + seq_printf(m, "pd_address: 0x%llx\n", amdgpu_gmc_pd_addr(fpriv->vm.root.bo)); + seq_printf(m, "max_pfn: 0x%llx\n", adev->vm_manager.max_pfn); + seq_printf(m, "num_level: 0x%x\n", adev->vm_manager.num_level); + seq_printf(m, "block_size: 0x%x\n", adev->vm_manager.block_size); + seq_printf(m, "fragment_size: 0x%x\n", adev->vm_manager.fragment_size); amdgpu_bo_unreserve(root_bo); amdgpu_bo_unref(&root_bo); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index b9e2f0293d61..a77000c2e0bb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -95,6 +95,7 @@ MODULE_FIRMWARE("amdgpu/picasso_gpu_info.bin"); MODULE_FIRMWARE("amdgpu/raven2_gpu_info.bin"); MODULE_FIRMWARE("amdgpu/arcturus_gpu_info.bin"); MODULE_FIRMWARE("amdgpu/navi12_gpu_info.bin"); +MODULE_FIRMWARE("amdgpu/cyan_skillfish_gpu_info.bin"); #define AMDGPU_RESUME_MS 2000 #define AMDGPU_MAX_RETRY_LIMIT 2 @@ -2629,6 +2630,9 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev) return 0; chip_name = "navi12"; break; + case CHIP_CYAN_SKILLFISH: + chip_name = "cyan_skillfish"; + break; } err = amdgpu_ucode_request(adev, &adev->firmware.gpu_info_fw, @@ -5068,6 +5072,10 @@ static int amdgpu_device_evict_resources(struct amdgpu_device *adev) if (!adev->in_s4 && (adev->flags & AMD_IS_APU)) return 0; + /* No need to evict when going to S5 through S4 callbacks */ + if (system_state == SYSTEM_POWER_OFF) + return 0; + ret = amdgpu_ttm_evict_resources(adev, TTM_PL_VRAM); if (ret) { dev_warn(adev->dev, "evicting device resources failed\n"); @@ -5192,7 +5200,7 @@ int amdgpu_device_suspend(struct drm_device *dev, bool notify_clients) adev->in_suspend = true; if (amdgpu_sriov_vf(adev)) { - if (!adev->in_s0ix && !adev->in_runpm) + if (!adev->in_runpm) amdgpu_amdkfd_suspend_process(adev); amdgpu_virt_fini_data_exchange(adev); r = amdgpu_virt_request_full_gpu(adev, false); @@ -5212,10 +5220,8 @@ int amdgpu_device_suspend(struct drm_device *dev, bool notify_clients) amdgpu_device_ip_suspend_phase1(adev); - if (!adev->in_s0ix) { - amdgpu_amdkfd_suspend(adev, !amdgpu_sriov_vf(adev) && !adev->in_runpm); - amdgpu_userq_suspend(adev); - } + amdgpu_amdkfd_suspend(adev, !amdgpu_sriov_vf(adev) && !adev->in_runpm); + amdgpu_userq_suspend(adev); r = amdgpu_device_evict_resources(adev); if (r) @@ -5310,15 +5316,13 @@ int amdgpu_device_resume(struct drm_device *dev, bool notify_clients) goto exit; } - if (!adev->in_s0ix) { - r = amdgpu_amdkfd_resume(adev, !amdgpu_sriov_vf(adev) && !adev->in_runpm); - if (r) - goto exit; + r = amdgpu_amdkfd_resume(adev, !amdgpu_sriov_vf(adev) && !adev->in_runpm); + if (r) + goto exit; - r = amdgpu_userq_resume(adev); - if (r) - goto exit; - } + r = amdgpu_userq_resume(adev); + if (r) + goto exit; r = amdgpu_device_ip_late_init(adev); if (r) @@ -5331,7 +5335,7 @@ exit: amdgpu_virt_init_data_exchange(adev); amdgpu_virt_release_full_gpu(adev, true); - if (!adev->in_s0ix && !r && !adev->in_runpm) + if (!r && !adev->in_runpm) r = amdgpu_amdkfd_resume_process(adev); } @@ -6933,7 +6937,8 @@ pci_ers_result_t amdgpu_pci_error_detected(struct pci_dev *pdev, pci_channel_sta { struct drm_device *dev = pci_get_drvdata(pdev); struct amdgpu_device *adev = drm_to_adev(dev); - struct amdgpu_hive_info *hive = amdgpu_get_xgmi_hive(adev); + struct amdgpu_hive_info *hive __free(xgmi_put_hive) = + amdgpu_get_xgmi_hive(adev); struct amdgpu_reset_context reset_context; struct list_head device_list; @@ -6972,10 +6977,8 @@ pci_ers_result_t amdgpu_pci_error_detected(struct pci_dev *pdev, pci_channel_sta amdgpu_device_recovery_get_reset_lock(adev, &device_list); amdgpu_device_halt_activities(adev, NULL, &reset_context, &device_list, hive, false); - if (hive) { + if (hive) mutex_unlock(&hive->hive_lock); - amdgpu_put_xgmi_hive(hive); - } return PCI_ERS_RESULT_NEED_RESET; case pci_channel_io_perm_failure: /* Permanent error, prepare for device removal */ @@ -7157,7 +7160,7 @@ static void amdgpu_device_cache_switch_state(struct amdgpu_device *adev) struct pci_dev *parent = pci_upstream_bridge(adev->pdev); int r; - if (parent->vendor != PCI_VENDOR_ID_ATI) + if (!parent || parent->vendor != PCI_VENDOR_ID_ATI) return; /* If already saved, return */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c index efe0058b48ca..73401f0aeb34 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c @@ -2124,7 +2124,6 @@ static int amdgpu_discovery_set_smu_ip_blocks(struct amdgpu_device *adev) case IP_VERSION(11, 0, 5): case IP_VERSION(11, 0, 9): case IP_VERSION(11, 0, 7): - case IP_VERSION(11, 0, 8): case IP_VERSION(11, 0, 11): case IP_VERSION(11, 0, 12): case IP_VERSION(11, 0, 13): @@ -2132,6 +2131,10 @@ static int amdgpu_discovery_set_smu_ip_blocks(struct amdgpu_device *adev) case IP_VERSION(11, 5, 2): amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block); break; + case IP_VERSION(11, 0, 8): + if (adev->apu_flags & AMD_APU_IS_CYAN_SKILLFISH2) + amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block); + break; case IP_VERSION(12, 0, 0): case IP_VERSION(12, 0, 1): amdgpu_device_ip_block_add(adev, &smu_v12_0_ip_block); @@ -2746,6 +2749,36 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev) adev->ip_versions[UVD_HWIP][1] = IP_VERSION(2, 6, 0); adev->ip_versions[XGMI_HWIP][0] = IP_VERSION(6, 1, 0); break; + case CHIP_CYAN_SKILLFISH: + if (adev->apu_flags & AMD_APU_IS_CYAN_SKILLFISH2) { + r = amdgpu_discovery_reg_base_init(adev); + if (r) + return -EINVAL; + + amdgpu_discovery_harvest_ip(adev); + amdgpu_discovery_get_gfx_info(adev); + amdgpu_discovery_get_mall_info(adev); + amdgpu_discovery_get_vcn_info(adev); + } else { + cyan_skillfish_reg_base_init(adev); + adev->sdma.num_instances = 2; + adev->ip_versions[MMHUB_HWIP][0] = IP_VERSION(2, 0, 3); + adev->ip_versions[ATHUB_HWIP][0] = IP_VERSION(2, 0, 3); + adev->ip_versions[OSSSYS_HWIP][0] = IP_VERSION(5, 0, 1); + adev->ip_versions[HDP_HWIP][0] = IP_VERSION(5, 0, 1); + adev->ip_versions[SDMA0_HWIP][0] = IP_VERSION(5, 0, 1); + adev->ip_versions[SDMA1_HWIP][1] = IP_VERSION(5, 0, 1); + adev->ip_versions[DF_HWIP][0] = IP_VERSION(3, 5, 0); + adev->ip_versions[NBIO_HWIP][0] = IP_VERSION(2, 1, 1); + adev->ip_versions[UMC_HWIP][0] = IP_VERSION(8, 1, 1); + adev->ip_versions[MP0_HWIP][0] = IP_VERSION(11, 0, 8); + adev->ip_versions[MP1_HWIP][0] = IP_VERSION(11, 0, 8); + adev->ip_versions[THM_HWIP][0] = IP_VERSION(11, 0, 1); + adev->ip_versions[SMUIO_HWIP][0] = IP_VERSION(11, 0, 8); + adev->ip_versions[GC_HWIP][0] = IP_VERSION(10, 1, 3); + adev->ip_versions[UVD_HWIP][0] = IP_VERSION(2, 0, 3); + } + break; default: r = amdgpu_discovery_reg_base_init(adev); if (r) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index ff98c87b2e0b..8561ad7f6180 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -285,6 +285,36 @@ static int amdgpu_dma_buf_begin_cpu_access(struct dma_buf *dma_buf, return ret; } +static int amdgpu_dma_buf_vmap(struct dma_buf *dma_buf, struct iosys_map *map) +{ + struct drm_gem_object *obj = dma_buf->priv; + struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj); + int ret; + + /* + * Pin to keep buffer in place while it's vmap'ed. The actual + * domain is not that important as long as it's mapable. Using + * GTT and VRAM should be compatible with most use cases. + */ + ret = amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT | AMDGPU_GEM_DOMAIN_VRAM); + if (ret) + return ret; + ret = drm_gem_dmabuf_vmap(dma_buf, map); + if (ret) + amdgpu_bo_unpin(bo); + + return ret; +} + +static void amdgpu_dma_buf_vunmap(struct dma_buf *dma_buf, struct iosys_map *map) +{ + struct drm_gem_object *obj = dma_buf->priv; + struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj); + + drm_gem_dmabuf_vunmap(dma_buf, map); + amdgpu_bo_unpin(bo); +} + const struct dma_buf_ops amdgpu_dmabuf_ops = { .attach = amdgpu_dma_buf_attach, .pin = amdgpu_dma_buf_pin, @@ -294,8 +324,8 @@ const struct dma_buf_ops amdgpu_dmabuf_ops = { .release = drm_gem_dmabuf_release, .begin_cpu_access = amdgpu_dma_buf_begin_cpu_access, .mmap = drm_gem_dmabuf_mmap, - .vmap = drm_gem_dmabuf_vmap, - .vunmap = drm_gem_dmabuf_vunmap, + .vmap = amdgpu_dma_buf_vmap, + .vunmap = amdgpu_dma_buf_vunmap, }; /** @@ -313,11 +343,23 @@ struct dma_buf *amdgpu_gem_prime_export(struct drm_gem_object *gobj, { struct amdgpu_bo *bo = gem_to_amdgpu_bo(gobj); struct dma_buf *buf; + struct ttm_operation_ctx ctx = { + .interruptible = true, + .no_wait_gpu = true, + /* We opt to avoid OOM on system pages allocations */ + .gfp_retry_mayfail = true, + .allow_res_evict = false, + }; + int ret; if (amdgpu_ttm_tt_get_usermm(bo->tbo.ttm) || bo->flags & AMDGPU_GEM_CREATE_VM_ALWAYS_VALID) return ERR_PTR(-EPERM); + ret = ttm_bo_setup_export(&bo->tbo, &ctx); + if (ret) + return ERR_PTR(ret); + buf = drm_gem_prime_export(gobj, flags); if (!IS_ERR(buf)) buf->ops = &amdgpu_dmabuf_ops; @@ -514,7 +556,7 @@ bool amdgpu_dmabuf_is_xgmi_accessible(struct amdgpu_device *adev, return false; if (drm_gem_is_imported(obj)) { - struct dma_buf *dma_buf = obj->dma_buf; + struct dma_buf *dma_buf = obj->import_attach->dmabuf; if (dma_buf->ops != &amdgpu_dmabuf_ops) /* No XGMI with non AMD GPUs */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 17f754d1135d..ece251cbe8c3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -2172,6 +2172,11 @@ static const struct pci_device_id pciidlist[] = { {0x1002, 0x7410, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ALDEBARAN}, /* CYAN_SKILLFISH */ + {0x1002, 0x13DB, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYAN_SKILLFISH|AMD_IS_APU}, + {0x1002, 0x13F9, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYAN_SKILLFISH|AMD_IS_APU}, + {0x1002, 0x13FA, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYAN_SKILLFISH|AMD_IS_APU}, + {0x1002, 0x13FB, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYAN_SKILLFISH|AMD_IS_APU}, + {0x1002, 0x13FC, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYAN_SKILLFISH|AMD_IS_APU}, {0x1002, 0x13FE, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYAN_SKILLFISH|AMD_IS_APU}, {0x1002, 0x143F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYAN_SKILLFISH|AMD_IS_APU}, @@ -3051,6 +3056,7 @@ const struct drm_ioctl_desc amdgpu_ioctls_kms[] = { DRM_IOCTL_DEF_DRV(AMDGPU_USERQ, amdgpu_userq_ioctl, DRM_AUTH|DRM_RENDER_ALLOW), DRM_IOCTL_DEF_DRV(AMDGPU_USERQ_SIGNAL, amdgpu_userq_signal_ioctl, DRM_AUTH|DRM_RENDER_ALLOW), DRM_IOCTL_DEF_DRV(AMDGPU_USERQ_WAIT, amdgpu_userq_wait_ioctl, DRM_AUTH|DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(AMDGPU_GEM_LIST_HANDLES, amdgpu_gem_list_handles_ioctl, DRM_AUTH|DRM_RENDER_ALLOW), }; static const struct drm_driver amdgpu_kms_driver = { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fdinfo.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fdinfo.c index 91d638098889..b349bb3676d5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fdinfo.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fdinfo.c @@ -70,6 +70,7 @@ void amdgpu_show_fdinfo(struct drm_printer *p, struct drm_file *file) [AMDGPU_PL_GWS] = "gws", [AMDGPU_PL_OA] = "oa", [AMDGPU_PL_DOORBELL] = "doorbell", + [AMDGPU_PL_MMIO_REMAP] = "mmioremap", }; unsigned int hw_ip, i; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index d5e685c5e28b..1679c2c3d505 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -317,7 +317,8 @@ static int amdgpu_gem_object_open(struct drm_gem_object *obj, */ if (!vm->is_compute_context || !vm->process_info) return 0; - if (!drm_gem_is_imported(obj) || !dma_buf_is_dynamic(obj->dma_buf)) + if (!drm_gem_is_imported(obj) || + !dma_buf_is_dynamic(obj->import_attach->dmabuf)) return 0; mutex_lock_nested(&vm->process_info->lock, 1); if (!WARN_ON(!vm->process_info->eviction_fence)) { @@ -442,15 +443,7 @@ int amdgpu_gem_create_ioctl(struct drm_device *dev, void *data, int r; /* reject invalid gem flags */ - if (flags & ~(AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED | - AMDGPU_GEM_CREATE_NO_CPU_ACCESS | - AMDGPU_GEM_CREATE_CPU_GTT_USWC | - AMDGPU_GEM_CREATE_VRAM_CLEARED | - AMDGPU_GEM_CREATE_VM_ALWAYS_VALID | - AMDGPU_GEM_CREATE_EXPLICIT_SYNC | - AMDGPU_GEM_CREATE_ENCRYPTED | - AMDGPU_GEM_CREATE_GFX12_DCC | - AMDGPU_GEM_CREATE_DISCARDABLE)) + if (flags & ~AMDGPU_GEM_CREATE_SETTABLE_MASK) return -EINVAL; /* reject invalid gem domains */ @@ -465,6 +458,9 @@ int amdgpu_gem_create_ioctl(struct drm_device *dev, void *data, /* always clear VRAM */ flags |= AMDGPU_GEM_CREATE_VRAM_CLEARED; + if (args->in.domains & AMDGPU_GEM_DOMAIN_MMIO_REMAP) + return -EINVAL; + /* create a gem object to contain this object in */ if (args->in.domains & (AMDGPU_GEM_DOMAIN_GDS | AMDGPU_GEM_DOMAIN_GWS | AMDGPU_GEM_DOMAIN_OA)) { @@ -963,17 +959,34 @@ int amdgpu_gem_op_ioctl(struct drm_device *dev, void *data, struct drm_gem_object *gobj; struct amdgpu_vm_bo_base *base; struct amdgpu_bo *robj; + struct drm_exec exec; + struct amdgpu_fpriv *fpriv = filp->driver_priv; int r; + if (args->padding) + return -EINVAL; + gobj = drm_gem_object_lookup(filp, args->handle); if (!gobj) return -ENOENT; robj = gem_to_amdgpu_bo(gobj); - r = amdgpu_bo_reserve(robj, false); - if (unlikely(r)) - goto out; + drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT | + DRM_EXEC_IGNORE_DUPLICATES, 0); + drm_exec_until_all_locked(&exec) { + r = drm_exec_lock_obj(&exec, gobj); + drm_exec_retry_on_contention(&exec); + if (r) + goto out_exec; + + if (args->op == AMDGPU_GEM_OP_GET_MAPPING_INFO) { + r = amdgpu_vm_lock_pd(&fpriv->vm, &exec, 0); + drm_exec_retry_on_contention(&exec); + if (r) + goto out_exec; + } + } switch (args->op) { case AMDGPU_GEM_OP_GET_GEM_CREATE_INFO: { @@ -984,7 +997,7 @@ int amdgpu_gem_op_ioctl(struct drm_device *dev, void *data, info.alignment = robj->tbo.page_alignment << PAGE_SHIFT; info.domains = robj->preferred_domains; info.domain_flags = robj->flags; - amdgpu_bo_unreserve(robj); + drm_exec_fini(&exec); if (copy_to_user(out, &info, sizeof(info))) r = -EFAULT; break; @@ -993,20 +1006,17 @@ int amdgpu_gem_op_ioctl(struct drm_device *dev, void *data, if (drm_gem_is_imported(&robj->tbo.base) && args->value & AMDGPU_GEM_DOMAIN_VRAM) { r = -EINVAL; - amdgpu_bo_unreserve(robj); - break; + goto out_exec; } if (amdgpu_ttm_tt_get_usermm(robj->tbo.ttm)) { r = -EPERM; - amdgpu_bo_unreserve(robj); - break; + goto out_exec; } for (base = robj->vm_bo; base; base = base->next) if (amdgpu_xgmi_same_hive(amdgpu_ttm_adev(robj->tbo.bdev), amdgpu_ttm_adev(base->vm->root.bo->tbo.bdev))) { r = -EINVAL; - amdgpu_bo_unreserve(robj); - goto out; + goto out_exec; } @@ -1019,17 +1029,146 @@ int amdgpu_gem_op_ioctl(struct drm_device *dev, void *data, if (robj->flags & AMDGPU_GEM_CREATE_VM_ALWAYS_VALID) amdgpu_vm_bo_invalidate(robj, true); + drm_exec_fini(&exec); + break; + case AMDGPU_GEM_OP_GET_MAPPING_INFO: { + struct amdgpu_bo_va *bo_va = amdgpu_vm_bo_find(&fpriv->vm, robj); + struct drm_amdgpu_gem_vm_entry *vm_entries; + struct amdgpu_bo_va_mapping *mapping; + int num_mappings = 0; + /* + * num_entries is set as an input to the size of the user-allocated array of + * drm_amdgpu_gem_vm_entry stored at args->value. + * num_entries is sent back as output as the number of mappings the bo has. + * If that number is larger than the size of the array, the ioctl must + * be retried. + */ + vm_entries = kvcalloc(args->num_entries, sizeof(*vm_entries), GFP_KERNEL); + if (!vm_entries) + return -ENOMEM; + + amdgpu_vm_bo_va_for_each_valid_mapping(bo_va, mapping) { + if (num_mappings < args->num_entries) { + vm_entries[num_mappings].addr = mapping->start * AMDGPU_GPU_PAGE_SIZE; + vm_entries[num_mappings].size = (mapping->last - mapping->start + 1) * AMDGPU_GPU_PAGE_SIZE; + vm_entries[num_mappings].offset = mapping->offset; + vm_entries[num_mappings].flags = mapping->flags; + } + num_mappings += 1; + } + + amdgpu_vm_bo_va_for_each_invalid_mapping(bo_va, mapping) { + if (num_mappings < args->num_entries) { + vm_entries[num_mappings].addr = mapping->start * AMDGPU_GPU_PAGE_SIZE; + vm_entries[num_mappings].size = (mapping->last - mapping->start + 1) * AMDGPU_GPU_PAGE_SIZE; + vm_entries[num_mappings].offset = mapping->offset; + vm_entries[num_mappings].flags = mapping->flags; + } + num_mappings += 1; + } + + drm_exec_fini(&exec); + + if (num_mappings > 0 && num_mappings <= args->num_entries) + if (copy_to_user(u64_to_user_ptr(args->value), vm_entries, num_mappings * sizeof(*vm_entries))) + r = -EFAULT; + + args->num_entries = num_mappings; - amdgpu_bo_unreserve(robj); + kvfree(vm_entries); break; + } default: - amdgpu_bo_unreserve(robj); + drm_exec_fini(&exec); r = -EINVAL; } -out: drm_gem_object_put(gobj); return r; +out_exec: + drm_exec_fini(&exec); + drm_gem_object_put(gobj); + return r; +} + +/** + * amdgpu_gem_list_handles_ioctl - get information about a process' buffer objects + * + * @dev: drm device pointer + * @data: drm_amdgpu_gem_list_handles + * @filp: drm file pointer + * + * num_entries is set as an input to the size of the entries array. + * num_entries is sent back as output as the number of bos in the process. + * If that number is larger than the size of the array, the ioctl must + * be retried. + * + * Returns: + * 0 for success, -errno for errors. + */ +int amdgpu_gem_list_handles_ioctl(struct drm_device *dev, void *data, + struct drm_file *filp) +{ + struct drm_amdgpu_gem_list_handles *args = data; + struct drm_amdgpu_gem_list_handles_entry *bo_entries; + struct drm_gem_object *gobj; + int id, ret = 0; + int bo_index = 0; + int num_bos = 0; + + spin_lock(&filp->table_lock); + idr_for_each_entry(&filp->object_idr, gobj, id) + num_bos += 1; + spin_unlock(&filp->table_lock); + + if (args->num_entries < num_bos) { + args->num_entries = num_bos; + return 0; + } + + if (num_bos == 0) { + args->num_entries = 0; + return 0; + } + + bo_entries = kvcalloc(num_bos, sizeof(*bo_entries), GFP_KERNEL); + if (!bo_entries) + return -ENOMEM; + + spin_lock(&filp->table_lock); + idr_for_each_entry(&filp->object_idr, gobj, id) { + struct amdgpu_bo *bo = gem_to_amdgpu_bo(gobj); + struct drm_amdgpu_gem_list_handles_entry *bo_entry; + + if (bo_index >= num_bos) { + ret = -EAGAIN; + break; + } + + bo_entry = &bo_entries[bo_index]; + + bo_entry->size = amdgpu_bo_size(bo); + bo_entry->alloc_flags = bo->flags & AMDGPU_GEM_CREATE_SETTABLE_MASK; + bo_entry->preferred_domains = bo->preferred_domains; + bo_entry->gem_handle = id; + bo_entry->alignment = bo->tbo.page_alignment; + + if (bo->tbo.base.import_attach) + bo_entry->flags |= AMDGPU_GEM_LIST_HANDLES_FLAG_IS_IMPORT; + + bo_index += 1; + } + spin_unlock(&filp->table_lock); + + args->num_entries = bo_index; + + if (!ret) + if (copy_to_user(u64_to_user_ptr(args->entries), bo_entries, num_bos * sizeof(*bo_entries))) + ret = -EFAULT; + + kvfree(bo_entries); + + return ret; } static int amdgpu_gem_align_pitch(struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.h index b51e8f95ee86..b558336bc4c6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.h @@ -67,8 +67,24 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data, struct drm_file *filp); int amdgpu_gem_op_ioctl(struct drm_device *dev, void *data, struct drm_file *filp); +int amdgpu_gem_list_handles_ioctl(struct drm_device *dev, void *data, + struct drm_file *filp); int amdgpu_gem_metadata_ioctl(struct drm_device *dev, void *data, struct drm_file *filp); +#define AMDGPU_GEM_CREATE_SETTABLE_MASK (AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED | \ + AMDGPU_GEM_CREATE_NO_CPU_ACCESS | \ + AMDGPU_GEM_CREATE_CPU_GTT_USWC | \ + AMDGPU_GEM_CREATE_VRAM_CLEARED | \ + AMDGPU_GEM_CREATE_VM_ALWAYS_VALID | \ + AMDGPU_GEM_CREATE_EXPLICIT_SYNC | \ + AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE | \ + AMDGPU_GEM_CREATE_ENCRYPTED | \ + AMDGPU_GEM_CREATE_GFX12_DCC | \ + AMDGPU_GEM_CREATE_DISCARDABLE | \ + AMDGPU_GEM_CREATE_COHERENT | \ + AMDGPU_GEM_CREATE_UNCACHED | \ + AMDGPU_GEM_CREATE_EXT_COHERENT) + #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c index c80c8f543532..a09ccf7d8aa2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c @@ -1474,7 +1474,8 @@ static int amdgpu_gfx_run_cleaner_shader_job(struct amdgpu_ring *ring) owner = (void *)(unsigned long)atomic_inc_return(&counter); r = amdgpu_job_alloc_with_ib(ring->adev, &entity, owner, - 64, 0, &job); + 64, 0, &job, + AMDGPU_KERNEL_JOB_ID_CLEANER_SHADER); if (r) goto err; @@ -2279,7 +2280,7 @@ void amdgpu_gfx_profile_ring_end_use(struct amdgpu_ring *ring) * Return: * return the latest index. */ -u32 amdgpu_gfx_csb_preamble_start(volatile u32 *buffer) +u32 amdgpu_gfx_csb_preamble_start(u32 *buffer) { u32 count = 0; @@ -2303,7 +2304,7 @@ u32 amdgpu_gfx_csb_preamble_start(volatile u32 *buffer) * Return: * return the latest index. */ -u32 amdgpu_gfx_csb_data_parser(struct amdgpu_device *adev, volatile u32 *buffer, u32 count) +u32 amdgpu_gfx_csb_data_parser(struct amdgpu_device *adev, u32 *buffer, u32 count) { const struct cs_section_def *sect = NULL; const struct cs_extent_def *ext = NULL; @@ -2330,7 +2331,7 @@ u32 amdgpu_gfx_csb_data_parser(struct amdgpu_device *adev, volatile u32 *buffer, * @buffer: This is an output variable that gets the PACKET3 preamble end. * @count: Index to start set the preemble end. */ -void amdgpu_gfx_csb_preamble_end(volatile u32 *buffer, u32 count) +void amdgpu_gfx_csb_preamble_end(u32 *buffer, u32 count) { buffer[count++] = cpu_to_le32(PACKET3(PACKET3_PREAMBLE_CNTL, 0)); buffer[count++] = cpu_to_le32(PACKET3_PREAMBLE_END_CLEAR_STATE); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h index 08f268dab8f5..fb5f7a0ee029 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h @@ -642,9 +642,9 @@ void amdgpu_gfx_enforce_isolation_ring_end_use(struct amdgpu_ring *ring); void amdgpu_gfx_profile_idle_work_handler(struct work_struct *work); void amdgpu_gfx_profile_ring_begin_use(struct amdgpu_ring *ring); void amdgpu_gfx_profile_ring_end_use(struct amdgpu_ring *ring); -u32 amdgpu_gfx_csb_preamble_start(volatile u32 *buffer); -u32 amdgpu_gfx_csb_data_parser(struct amdgpu_device *adev, volatile u32 *buffer, u32 count); -void amdgpu_gfx_csb_preamble_end(volatile u32 *buffer, u32 count); +u32 amdgpu_gfx_csb_preamble_start(u32 *buffer); +u32 amdgpu_gfx_csb_data_parser(struct amdgpu_device *adev, u32 *buffer, u32 count); +void amdgpu_gfx_csb_preamble_end(u32 *buffer, u32 count); void amdgpu_debugfs_gfx_sched_mask_init(struct amdgpu_device *adev); void amdgpu_debugfs_compute_sched_mask_init(struct amdgpu_device *adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index 97b562a79ea8..9dcf51991b5b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -690,7 +690,7 @@ void amdgpu_gmc_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid, r = amdgpu_job_alloc_with_ib(ring->adev, &adev->mman.high_pr, AMDGPU_FENCE_OWNER_UNDEFINED, 16 * 4, AMDGPU_IB_POOL_IMMEDIATE, - &job); + &job, AMDGPU_KERNEL_JOB_ID_FLUSH_GPU_TLB); if (r) goto error_alloc; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c index 57101d24422f..9cb72f0c5277 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c @@ -184,7 +184,7 @@ struct amdgpu_i2c_chan *amdgpu_i2c_create(struct drm_device *dev, snprintf(i2c->adapter.name, sizeof(i2c->adapter.name), "AMDGPU i2c hw bus %s", name); i2c->adapter.algo = &amdgpu_atombios_i2c_algo; - ret = i2c_add_adapter(&i2c->adapter); + ret = devm_i2c_add_adapter(dev->dev, &i2c->adapter); if (ret) goto out_free; } else { @@ -215,15 +215,6 @@ out_free: } -void amdgpu_i2c_destroy(struct amdgpu_i2c_chan *i2c) -{ - if (!i2c) - return; - WARN_ON(i2c->has_aux); - i2c_del_adapter(&i2c->adapter); - kfree(i2c); -} - void amdgpu_i2c_init(struct amdgpu_device *adev) { if (!adev->is_atom_fw) { @@ -248,12 +239,9 @@ void amdgpu_i2c_fini(struct amdgpu_device *adev) { int i; - for (i = 0; i < AMDGPU_MAX_I2C_BUS; i++) { - if (adev->i2c_bus[i]) { - amdgpu_i2c_destroy(adev->i2c_bus[i]); + for (i = 0; i < AMDGPU_MAX_I2C_BUS; i++) + if (adev->i2c_bus[i]) adev->i2c_bus[i] = NULL; - } - } } /* looks up bus based on id */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h index 7f7ea046e209..f58b6be7fccc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h @@ -56,14 +56,14 @@ struct amdgpu_ih_ring { bool use_bus_addr; struct amdgpu_bo *ring_obj; - volatile uint32_t *ring; + uint32_t *ring; uint64_t gpu_addr; uint64_t wptr_addr; - volatile uint32_t *wptr_cpu; + uint32_t *wptr_cpu; uint64_t rptr_addr; - volatile uint32_t *rptr_cpu; + uint32_t *rptr_cpu; bool enabled; unsigned rptr; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index 9b1c55115921..d020a890a0ea 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -209,11 +209,12 @@ int amdgpu_job_alloc(struct amdgpu_device *adev, struct amdgpu_vm *vm, int amdgpu_job_alloc_with_ib(struct amdgpu_device *adev, struct drm_sched_entity *entity, void *owner, size_t size, enum amdgpu_ib_pool_type pool_type, - struct amdgpu_job **job) + struct amdgpu_job **job, u64 k_job_id) { int r; - r = amdgpu_job_alloc(adev, NULL, entity, owner, 1, job, 0); + r = amdgpu_job_alloc(adev, NULL, entity, owner, 1, job, + k_job_id); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h index 2f302266662b..4a6487eb6cb5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h @@ -44,6 +44,22 @@ struct amdgpu_fence; enum amdgpu_ib_pool_type; +/* Internal kernel job ids. (decreasing values, starting from U64_MAX). */ +#define AMDGPU_KERNEL_JOB_ID_VM_UPDATE (18446744073709551615ULL) +#define AMDGPU_KERNEL_JOB_ID_VM_UPDATE_PDES (18446744073709551614ULL) +#define AMDGPU_KERNEL_JOB_ID_VM_UPDATE_RANGE (18446744073709551613ULL) +#define AMDGPU_KERNEL_JOB_ID_VM_PT_CLEAR (18446744073709551612ULL) +#define AMDGPU_KERNEL_JOB_ID_TTM_MAP_BUFFER (18446744073709551611ULL) +#define AMDGPU_KERNEL_JOB_ID_TTM_ACCESS_MEMORY_SDMA (18446744073709551610ULL) +#define AMDGPU_KERNEL_JOB_ID_TTM_COPY_BUFFER (18446744073709551609ULL) +#define AMDGPU_KERNEL_JOB_ID_CLEAR_ON_RELEASE (18446744073709551608ULL) +#define AMDGPU_KERNEL_JOB_ID_MOVE_BLIT (18446744073709551607ULL) +#define AMDGPU_KERNEL_JOB_ID_TTM_CLEAR_BUFFER (18446744073709551606ULL) +#define AMDGPU_KERNEL_JOB_ID_CLEANER_SHADER (18446744073709551605ULL) +#define AMDGPU_KERNEL_JOB_ID_FLUSH_GPU_TLB (18446744073709551604ULL) +#define AMDGPU_KERNEL_JOB_ID_KFD_GART_MAP (18446744073709551603ULL) +#define AMDGPU_KERNEL_JOB_ID_VCN_RING_TEST (18446744073709551602ULL) + struct amdgpu_job { struct drm_sched_job base; struct amdgpu_vm *vm; @@ -96,7 +112,8 @@ int amdgpu_job_alloc(struct amdgpu_device *adev, struct amdgpu_vm *vm, int amdgpu_job_alloc_with_ib(struct amdgpu_device *adev, struct drm_sched_entity *entity, void *owner, size_t size, enum amdgpu_ib_pool_type pool_type, - struct amdgpu_job **job); + struct amdgpu_job **job, + u64 k_job_id); void amdgpu_job_set_resources(struct amdgpu_job *job, struct amdgpu_bo *gds, struct amdgpu_bo *gws, struct amdgpu_bo *oa); void amdgpu_job_free_resources(struct amdgpu_job *job); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c index f0d7e2487237..6b7d66b6d4cc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c @@ -196,7 +196,8 @@ static int amdgpu_jpeg_dec_set_reg(struct amdgpu_ring *ring, uint32_t handle, int i, r; r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL, ib_size_dw * 4, - AMDGPU_IB_POOL_DIRECT, &job); + AMDGPU_IB_POOL_DIRECT, &job, + AMDGPU_KERNEL_JOB_ID_VCN_RING_TEST); if (r) return r; @@ -539,3 +540,68 @@ void amdgpu_jpeg_print_ip_state(struct amdgpu_ip_block *ip_block, struct drm_pri drm_printf(p, "\nInactive Instance:JPEG%d\n", i); } } + +static inline bool amdgpu_jpeg_reg_valid(u32 reg) +{ + if (reg < JPEG_REG_RANGE_START || reg > JPEG_REG_RANGE_END || + (reg >= JPEG_ATOMIC_RANGE_START && reg <= JPEG_ATOMIC_RANGE_END)) + return false; + else + return true; +} + +/** + * amdgpu_jpeg_dec_parse_cs - command submission parser + * + * @parser: Command submission parser context + * @job: the job to parse + * @ib: the IB to parse + * + * Parse the command stream, return -EINVAL for invalid packet, + * 0 otherwise + */ + +int amdgpu_jpeg_dec_parse_cs(struct amdgpu_cs_parser *parser, + struct amdgpu_job *job, + struct amdgpu_ib *ib) +{ + u32 i, reg, res, cond, type; + struct amdgpu_device *adev = parser->adev; + + for (i = 0; i < ib->length_dw ; i += 2) { + reg = CP_PACKETJ_GET_REG(ib->ptr[i]); + res = CP_PACKETJ_GET_RES(ib->ptr[i]); + cond = CP_PACKETJ_GET_COND(ib->ptr[i]); + type = CP_PACKETJ_GET_TYPE(ib->ptr[i]); + + if (res) /* only support 0 at the moment */ + return -EINVAL; + + switch (type) { + case PACKETJ_TYPE0: + if (cond != PACKETJ_CONDITION_CHECK0 || + !amdgpu_jpeg_reg_valid(reg)) { + dev_err(adev->dev, "Invalid packet [0x%08x]!\n", ib->ptr[i]); + return -EINVAL; + } + break; + case PACKETJ_TYPE3: + if (cond != PACKETJ_CONDITION_CHECK3 || + !amdgpu_jpeg_reg_valid(reg)) { + dev_err(adev->dev, "Invalid packet [0x%08x]!\n", ib->ptr[i]); + return -EINVAL; + } + break; + case PACKETJ_TYPE6: + if (ib->ptr[i] == CP_PACKETJ_NOP) + continue; + dev_err(adev->dev, "Invalid packet [0x%08x]!\n", ib->ptr[i]); + return -EINVAL; + default: + dev_err(adev->dev, "Unknown packet type %d !\n", type); + return -EINVAL; + } + } + + return 0; +} diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.h index 4f0775e39b54..346ae0ab09d3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.h @@ -25,11 +25,18 @@ #define __AMDGPU_JPEG_H__ #include "amdgpu_ras.h" +#include "amdgpu_cs.h" #define AMDGPU_MAX_JPEG_INSTANCES 4 #define AMDGPU_MAX_JPEG_RINGS 10 #define AMDGPU_MAX_JPEG_RINGS_4_0_3 8 +#define JPEG_REG_RANGE_START 0x4000 +#define JPEG_REG_RANGE_END 0x41c2 +#define JPEG_ATOMIC_RANGE_START 0x4120 +#define JPEG_ATOMIC_RANGE_END 0x412A + + #define AMDGPU_JPEG_HARVEST_JPEG0 (1 << 0) #define AMDGPU_JPEG_HARVEST_JPEG1 (1 << 1) @@ -170,5 +177,8 @@ int amdgpu_jpeg_reg_dump_init(struct amdgpu_device *adev, const struct amdgpu_hwip_reg_entry *reg, u32 count); void amdgpu_jpeg_dump_ip_state(struct amdgpu_ip_block *ip_block); void amdgpu_jpeg_print_ip_state(struct amdgpu_ip_block *ip_block, struct drm_printer *p); +int amdgpu_jpeg_dec_parse_cs(struct amdgpu_cs_parser *parser, + struct amdgpu_job *job, + struct amdgpu_ib *ib); #endif /*__AMDGPU_JPEG_H__*/ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index 8a76960803c6..8676400834fc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -939,6 +939,10 @@ out: if (adev->gfx.config.ta_cntl2_truncate_coord_mode) dev_info->ids_flags |= AMDGPU_IDS_FLAGS_CONFORMANT_TRUNC_COORD; + /* Gang submit is not supported under SRIOV currently */ + if (!amdgpu_sriov_vf(adev)) + dev_info->ids_flags |= AMDGPU_IDS_FLAGS_GANG_SUBMIT; + if (amdgpu_passthrough(adev)) dev_info->ids_flags |= (AMDGPU_IDS_FLAGS_MODE_PT << AMDGPU_IDS_FLAGS_MODE_SHIFT) & diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c index 135598502c8d..5bf9be073cdd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c @@ -191,6 +191,20 @@ int amdgpu_mes_init(struct amdgpu_device *adev) if (r) goto error_doorbell; + if (adev->mes.hung_queue_db_array_size) { + r = amdgpu_bo_create_kernel(adev, + adev->mes.hung_queue_db_array_size * sizeof(u32), + PAGE_SIZE, + AMDGPU_GEM_DOMAIN_GTT, + &adev->mes.hung_queue_db_array_gpu_obj, + &adev->mes.hung_queue_db_array_gpu_addr, + &adev->mes.hung_queue_db_array_cpu_addr); + if (r) { + dev_warn(adev->dev, "failed to create MES hung db array buffer (%d)", r); + goto error_doorbell; + } + } + return 0; error_doorbell: @@ -216,6 +230,10 @@ void amdgpu_mes_fini(struct amdgpu_device *adev) { int i; + amdgpu_bo_free_kernel(&adev->mes.hung_queue_db_array_gpu_obj, + &adev->mes.hung_queue_db_array_gpu_addr, + &adev->mes.hung_queue_db_array_cpu_addr); + amdgpu_bo_free_kernel(&adev->mes.event_log_gpu_obj, &adev->mes.event_log_gpu_addr, &adev->mes.event_log_cpu_addr); @@ -366,6 +384,53 @@ int amdgpu_mes_reset_legacy_queue(struct amdgpu_device *adev, return r; } +int amdgpu_mes_get_hung_queue_db_array_size(struct amdgpu_device *adev) +{ + return adev->mes.hung_queue_db_array_size; +} + +int amdgpu_mes_detect_and_reset_hung_queues(struct amdgpu_device *adev, + int queue_type, + bool detect_only, + unsigned int *hung_db_num, + u32 *hung_db_array) + +{ + struct mes_detect_and_reset_queue_input input; + u32 *db_array = adev->mes.hung_queue_db_array_cpu_addr; + int r, i; + + if (!hung_db_num || !hung_db_array) + return -EINVAL; + + if ((queue_type != AMDGPU_RING_TYPE_GFX) && + (queue_type != AMDGPU_RING_TYPE_COMPUTE) && + (queue_type != AMDGPU_RING_TYPE_SDMA)) + return -EINVAL; + + /* Clear the doorbell array before detection */ + memset(adev->mes.hung_queue_db_array_cpu_addr, 0, + adev->mes.hung_queue_db_array_size * sizeof(u32)); + input.queue_type = queue_type; + input.detect_only = detect_only; + + r = adev->mes.funcs->detect_and_reset_hung_queues(&adev->mes, + &input); + if (r) { + dev_err(adev->dev, "failed to detect and reset\n"); + } else { + *hung_db_num = 0; + for (i = 0; i < adev->mes.hung_queue_db_array_size; i++) { + if (db_array[i] != AMDGPU_MES_INVALID_DB_OFFSET) { + hung_db_array[i] = db_array[i]; + *hung_db_num += 1; + } + } + } + + return r; +} + uint32_t amdgpu_mes_rreg(struct amdgpu_device *adev, uint32_t reg) { struct mes_misc_op_input op_input; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h index 489a4a0f0610..6b506fc72f58 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h @@ -41,6 +41,7 @@ #define AMDGPU_MES_API_VERSION_MASK 0x00fff000 #define AMDGPU_MES_FEAT_VERSION_MASK 0xff000000 #define AMDGPU_MES_MSCRATCH_SIZE 0x40000 +#define AMDGPU_MES_INVALID_DB_OFFSET 0xffffffff enum amdgpu_mes_priority_level { AMDGPU_MES_PRIORITY_LEVEL_LOW = 0, @@ -147,6 +148,10 @@ struct amdgpu_mes { uint64_t resource_1_gpu_addr[AMDGPU_MAX_MES_PIPES]; void *resource_1_addr[AMDGPU_MAX_MES_PIPES]; + int hung_queue_db_array_size; + struct amdgpu_bo *hung_queue_db_array_gpu_obj; + uint64_t hung_queue_db_array_gpu_addr; + void *hung_queue_db_array_cpu_addr; }; struct amdgpu_mes_gang { @@ -280,6 +285,11 @@ struct mes_reset_queue_input { bool is_kq; }; +struct mes_detect_and_reset_queue_input { + uint32_t queue_type; + bool detect_only; +}; + struct mes_inv_tlbs_pasid_input { uint32_t xcc_id; uint16_t pasid; @@ -375,6 +385,10 @@ struct amdgpu_mes_funcs { int (*reset_hw_queue)(struct amdgpu_mes *mes, struct mes_reset_queue_input *input); + int (*detect_and_reset_hung_queues)(struct amdgpu_mes *mes, + struct mes_detect_and_reset_queue_input *input); + + int (*invalidate_tlbs_pasid)(struct amdgpu_mes *mes, struct mes_inv_tlbs_pasid_input *input); }; @@ -400,6 +414,13 @@ int amdgpu_mes_reset_legacy_queue(struct amdgpu_device *adev, unsigned int vmid, bool use_mmio); +int amdgpu_mes_get_hung_queue_db_array_size(struct amdgpu_device *adev); +int amdgpu_mes_detect_and_reset_hung_queues(struct amdgpu_device *adev, + int queue_type, + bool detect_only, + unsigned int *hung_db_num, + u32 *hung_db_array); + uint32_t amdgpu_mes_rreg(struct amdgpu_device *adev, uint32_t reg); int amdgpu_mes_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t val); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h index 6da4f946cac0..20460cfd09bc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h @@ -496,8 +496,6 @@ struct amdgpu_crtc { struct drm_connector *connector; /* for dpm */ u32 line_time; - u32 wm_low; - u32 wm_high; u32 lb_vblank_lead_lines; struct drm_display_mode hw_mode; /* for virtual dce */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 122a88294883..e08f58de4b17 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -153,6 +153,14 @@ void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain) c++; } + if (domain & AMDGPU_GEM_DOMAIN_MMIO_REMAP) { + places[c].fpfn = 0; + places[c].lpfn = 0; + places[c].mem_type = AMDGPU_PL_MMIO_REMAP; + places[c].flags = 0; + c++; + } + if (domain & AMDGPU_GEM_DOMAIN_GTT) { places[c].fpfn = 0; places[c].lpfn = 0; @@ -1313,7 +1321,8 @@ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo) if (r) goto out; - r = amdgpu_fill_buffer(abo, 0, &bo->base._resv, &fence, true); + r = amdgpu_fill_buffer(abo, 0, &bo->base._resv, &fence, true, + AMDGPU_KERNEL_JOB_ID_CLEAR_ON_RELEASE); if (WARN_ON(r)) goto out; @@ -1545,6 +1554,8 @@ uint32_t amdgpu_bo_mem_stats_placement(struct amdgpu_bo *bo) return AMDGPU_PL_OA; case AMDGPU_GEM_DOMAIN_DOORBELL: return AMDGPU_PL_DOORBELL; + case AMDGPU_GEM_DOMAIN_MMIO_REMAP: + return AMDGPU_PL_MMIO_REMAP; default: return TTM_PL_SYSTEM; } @@ -1628,6 +1639,9 @@ u64 amdgpu_bo_print_info(int id, struct amdgpu_bo *bo, struct seq_file *m) case AMDGPU_PL_DOORBELL: placement = "DOORBELL"; break; + case AMDGPU_PL_MMIO_REMAP: + placement = "MMIO REMAP"; + break; case TTM_PL_SYSTEM: default: placement = "CPU"; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h index 87523fcd4386..656b8a931dae 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h @@ -167,6 +167,8 @@ static inline unsigned amdgpu_mem_type_to_domain(u32 mem_type) return AMDGPU_GEM_DOMAIN_OA; case AMDGPU_PL_DOORBELL: return AMDGPU_GEM_DOMAIN_DOORBELL; + case AMDGPU_PL_MMIO_REMAP: + return AMDGPU_GEM_DOMAIN_MMIO_REMAP; default: break; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 1d6e1d5de8fa..1578e4e2bf84 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -448,7 +448,7 @@ static int psp_sw_init(struct amdgpu_ip_block *ip_block) psp->cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL); if (!psp->cmd) { dev_err(adev->dev, "Failed to allocate memory to command buffer!\n"); - ret = -ENOMEM; + return -ENOMEM; } adev->psp.xgmi_context.supports_extended_data = @@ -506,7 +506,8 @@ static int psp_sw_init(struct amdgpu_ip_block *ip_block) } ret = amdgpu_bo_create_kernel(adev, PSP_1_MEG, PSP_1_MEG, - AMDGPU_GEM_DOMAIN_VRAM, + (amdgpu_sriov_vf(adev) || adev->debug_use_vram_fw_buf) ? + AMDGPU_GEM_DOMAIN_VRAM : AMDGPU_GEM_DOMAIN_GTT, &psp->fw_pri_bo, &psp->fw_pri_mc_addr, &psp->fw_pri_buf); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c index 38face981c3e..6e8aad91bcd3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c @@ -171,13 +171,9 @@ static ssize_t ta_if_load_debugfs_write(struct file *fp, const char *buf, size_t copy_pos += sizeof(uint32_t); - ta_bin = kzalloc(ta_bin_len, GFP_KERNEL); - if (!ta_bin) - return -ENOMEM; - if (copy_from_user((void *)ta_bin, &buf[copy_pos], ta_bin_len)) { - ret = -EFAULT; - goto err_free_bin; - } + ta_bin = memdup_user(&buf[copy_pos], ta_bin_len); + if (IS_ERR(ta_bin)) + return PTR_ERR(ta_bin); /* Set TA context and functions */ set_ta_context_funcs(psp, ta_type, &context); @@ -327,13 +323,9 @@ static ssize_t ta_if_invoke_debugfs_write(struct file *fp, const char *buf, size return -EFAULT; copy_pos += sizeof(uint32_t); - shared_buf = kzalloc(shared_buf_len, GFP_KERNEL); - if (!shared_buf) - return -ENOMEM; - if (copy_from_user((void *)shared_buf, &buf[copy_pos], shared_buf_len)) { - ret = -EFAULT; - goto err_free_shared_buf; - } + shared_buf = memdup_user(&buf[copy_pos], shared_buf_len); + if (IS_ERR(shared_buf)) + return PTR_ERR(shared_buf); set_ta_context_funcs(psp, ta_type, &context); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 7fe5b1940df8..e0ee21150860 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -219,10 +219,17 @@ static int amdgpu_check_address_validity(struct amdgpu_device *adev, struct amdgpu_vram_block_info blk_info; uint64_t page_pfns[32] = {0}; int i, ret, count; + bool hit = false; if (amdgpu_ip_version(adev, UMC_HWIP, 0) < IP_VERSION(12, 0, 0)) return 0; + if (amdgpu_sriov_vf(adev)) { + if (amdgpu_virt_check_vf_critical_region(adev, address, &hit)) + return -EPERM; + return hit ? -EACCES : 0; + } + if ((address >= adev->gmc.mc_vram_size) || (address >= RAS_UMC_INJECT_ADDR_LIMIT)) return -EFAULT; @@ -2702,6 +2709,7 @@ static void amdgpu_ras_do_recovery(struct work_struct *work) struct amdgpu_device *adev = ras->adev; struct list_head device_list, *device_list_handle = NULL; struct amdgpu_hive_info *hive = amdgpu_get_xgmi_hive(adev); + unsigned int error_query_mode; enum ras_event_type type; if (hive) { @@ -2730,6 +2738,13 @@ static void amdgpu_ras_do_recovery(struct work_struct *work) device_list_handle = &device_list; } + if (amdgpu_ras_get_error_query_mode(adev, &error_query_mode)) { + if (error_query_mode == AMDGPU_RAS_FIRMWARE_ERROR_QUERY) { + /* wait 500ms to ensure pmfw polling mca bank info done */ + msleep(500); + } + } + type = amdgpu_ras_get_fatal_error_event(adev); list_for_each_entry(remote_adev, device_list_handle, gmc.xgmi.head) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h index 50fcd86e1033..be2e56ce1355 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h @@ -91,6 +91,7 @@ static inline void amdgpu_res_first(struct ttm_resource *res, break; case TTM_PL_TT: case AMDGPU_PL_DOORBELL: + case AMDGPU_PL_MMIO_REMAP: node = to_ttm_range_mgr_node(res)->mm_nodes; while (start >= node->size << PAGE_SHIFT) start -= node++->size << PAGE_SHIFT; @@ -153,6 +154,7 @@ static inline void amdgpu_res_next(struct amdgpu_res_cursor *cur, uint64_t size) break; case TTM_PL_TT: case AMDGPU_PL_DOORBELL: + case AMDGPU_PL_MMIO_REMAP: node = cur->node; cur->node = ++node; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c index dabfbdf6f1ce..28c4ad62f50e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c @@ -340,6 +340,9 @@ void amdgpu_reset_get_desc(struct amdgpu_reset_context *rst_ctxt, char *buf, case AMDGPU_RESET_SRC_USER: strscpy(buf, "user trigger", len); break; + case AMDGPU_RESET_SRC_USERQ: + strscpy(buf, "user queue trigger", len); + break; default: strscpy(buf, "unknown", len); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h index 2f92b3be40f5..07b4d37f1db6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h @@ -43,6 +43,7 @@ enum AMDGPU_RESET_SRCS { AMDGPU_RESET_SRC_MES, AMDGPU_RESET_SRC_HWS, AMDGPU_RESET_SRC_USER, + AMDGPU_RESET_SRC_USERQ, }; struct amdgpu_reset_context { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c index 6379bb25bf5c..8f6ce948c684 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c @@ -364,7 +364,8 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring, /* Allocate ring buffer */ if (ring->ring_obj == NULL) { - r = amdgpu_bo_create_kernel(adev, ring->ring_size + ring->funcs->extra_dw, PAGE_SIZE, + r = amdgpu_bo_create_kernel(adev, ring->ring_size + ring->funcs->extra_bytes, + PAGE_SIZE, AMDGPU_GEM_DOMAIN_GTT, &ring->ring_obj, &ring->gpu_addr, @@ -421,8 +422,6 @@ void amdgpu_ring_fini(struct amdgpu_ring *ring) dma_fence_put(ring->vmid_wait); ring->vmid_wait = NULL; ring->me = 0; - - ring->adev->rings[ring->idx] = NULL; } /** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h index 7670f5d82b9e..b6b649179776 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h @@ -114,7 +114,7 @@ struct amdgpu_sched { */ struct amdgpu_fence_driver { uint64_t gpu_addr; - volatile uint32_t *cpu_addr; + uint32_t *cpu_addr; /* sync_seq is protected by ring emission lock */ uint32_t sync_seq; atomic_t last_seq; @@ -211,7 +211,18 @@ struct amdgpu_ring_funcs { bool support_64bit_ptrs; bool no_user_fence; bool secure_submission_supported; - unsigned extra_dw; + + /** + * @extra_bytes: + * + * Optional extra space in bytes that is added to the ring size + * when allocating the BO that holds the contents of the ring. + * This space isn't used for command submission to the ring, + * but is just there to satisfy some hardware requirements or + * implement workarounds. It's up to the implementation of each + * specific ring to initialize this space. + */ + unsigned extra_bytes; /* ring read/write ptr handling */ u64 (*get_rptr)(struct amdgpu_ring *ring); @@ -298,7 +309,7 @@ struct amdgpu_ring { unsigned int ring_backup_entries_to_copy; unsigned rptr_offs; u64 rptr_gpu_addr; - volatile u32 *rptr_cpu_addr; + u32 *rptr_cpu_addr; /** * @wptr: @@ -378,19 +389,19 @@ struct amdgpu_ring { * This is the CPU address pointer in the writeback slot. This is used * to commit changes to the GPU. */ - volatile u32 *wptr_cpu_addr; + u32 *wptr_cpu_addr; unsigned fence_offs; u64 fence_gpu_addr; - volatile u32 *fence_cpu_addr; + u32 *fence_cpu_addr; uint64_t current_ctx; char name[16]; u32 trail_seq; unsigned trail_fence_offs; u64 trail_fence_gpu_addr; - volatile u32 *trail_fence_cpu_addr; + u32 *trail_fence_cpu_addr; unsigned cond_exe_offs; u64 cond_exe_gpu_addr; - volatile u32 *cond_exe_cpu_addr; + u32 *cond_exe_cpu_addr; unsigned int set_q_mode_offs; u32 *set_q_mode_ptr; u64 set_q_mode_token; @@ -470,10 +481,7 @@ static inline void amdgpu_ring_set_preempt_cond_exec(struct amdgpu_ring *ring, static inline void amdgpu_ring_clear_ring(struct amdgpu_ring *ring) { - int i = 0; - while (i <= ring->buf_mask) - ring->ring[i++] = ring->funcs->nop; - + memset32(ring->ring, ring->funcs->nop, ring->buf_mask + 1); } static inline void amdgpu_ring_write(struct amdgpu_ring *ring, uint32_t v) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c index db5791e1a7ce..5aa830a02d80 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c @@ -89,7 +89,7 @@ void amdgpu_gfx_rlc_exit_safe_mode(struct amdgpu_device *adev, int xcc_id) int amdgpu_gfx_rlc_init_sr(struct amdgpu_device *adev, u32 dws) { const u32 *src_ptr; - volatile u32 *dst_ptr; + u32 *dst_ptr; u32 i; int r; @@ -189,7 +189,7 @@ int amdgpu_gfx_rlc_init_cpt(struct amdgpu_device *adev) void amdgpu_gfx_rlc_setup_cp_table(struct amdgpu_device *adev) { const __le32 *fw_data; - volatile u32 *dst_ptr; + u32 *dst_ptr; int me, i, max_me; u32 bo_offset = 0; u32 table_offset, table_size; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h index c210625be220..2ce310b31942 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h @@ -251,7 +251,7 @@ struct amdgpu_rlc_funcs { * and it also provides a pointer to it which is used by the firmware * to load the clear state in some cases. */ - void (*get_csb_buffer)(struct amdgpu_device *adev, volatile u32 *buffer); + void (*get_csb_buffer)(struct amdgpu_device *adev, u32 *buffer); int (*get_cp_table_num)(struct amdgpu_device *adev); int (*resume)(struct amdgpu_device *adev); void (*stop)(struct amdgpu_device *adev); @@ -275,19 +275,19 @@ struct amdgpu_rlc { /* for power gating */ struct amdgpu_bo *save_restore_obj; uint64_t save_restore_gpu_addr; - volatile uint32_t *sr_ptr; + uint32_t *sr_ptr; const u32 *reg_list; u32 reg_list_size; /* for clear state */ struct amdgpu_bo *clear_state_obj; uint64_t clear_state_gpu_addr; - volatile uint32_t *cs_ptr; + uint32_t *cs_ptr; const struct cs_section_def *cs_data; u32 clear_state_size; /* for cp tables */ struct amdgpu_bo *cp_table_obj; uint64_t cp_table_gpu_addr; - volatile uint32_t *cp_table_ptr; + uint32_t *cp_table_ptr; u32 cp_table_size; /* safe mode for updating CG/PG state */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 27ab4e754b2a..71b6691edab4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -123,6 +123,7 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo, case AMDGPU_PL_GWS: case AMDGPU_PL_OA: case AMDGPU_PL_DOORBELL: + case AMDGPU_PL_MMIO_REMAP: placement->num_placement = 0; return; @@ -226,7 +227,8 @@ static int amdgpu_ttm_map_buffer(struct ttm_buffer_object *bo, r = amdgpu_job_alloc_with_ib(adev, &adev->mman.high_pr, AMDGPU_FENCE_OWNER_UNDEFINED, num_dw * 4 + num_bytes, - AMDGPU_IB_POOL_DELAYED, &job); + AMDGPU_IB_POOL_DELAYED, &job, + AMDGPU_KERNEL_JOB_ID_TTM_MAP_BUFFER); if (r) return r; @@ -406,7 +408,7 @@ static int amdgpu_move_blit(struct ttm_buffer_object *bo, struct dma_fence *wipe_fence = NULL; r = amdgpu_fill_buffer(abo, 0, NULL, &wipe_fence, - false); + false, AMDGPU_KERNEL_JOB_ID_MOVE_BLIT); if (r) { goto error; } else if (wipe_fence) { @@ -447,7 +449,8 @@ bool amdgpu_res_cpu_visible(struct amdgpu_device *adev, return false; if (res->mem_type == TTM_PL_SYSTEM || res->mem_type == TTM_PL_TT || - res->mem_type == AMDGPU_PL_PREEMPT || res->mem_type == AMDGPU_PL_DOORBELL) + res->mem_type == AMDGPU_PL_PREEMPT || res->mem_type == AMDGPU_PL_DOORBELL || + res->mem_type == AMDGPU_PL_MMIO_REMAP) return true; if (res->mem_type != TTM_PL_VRAM) @@ -538,10 +541,12 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict, old_mem->mem_type == AMDGPU_PL_GWS || old_mem->mem_type == AMDGPU_PL_OA || old_mem->mem_type == AMDGPU_PL_DOORBELL || + old_mem->mem_type == AMDGPU_PL_MMIO_REMAP || new_mem->mem_type == AMDGPU_PL_GDS || new_mem->mem_type == AMDGPU_PL_GWS || new_mem->mem_type == AMDGPU_PL_OA || - new_mem->mem_type == AMDGPU_PL_DOORBELL) { + new_mem->mem_type == AMDGPU_PL_DOORBELL || + new_mem->mem_type == AMDGPU_PL_MMIO_REMAP) { /* Nothing to save here */ amdgpu_bo_move_notify(bo, evict, new_mem); ttm_bo_move_null(bo, new_mem); @@ -629,6 +634,12 @@ static int amdgpu_ttm_io_mem_reserve(struct ttm_device *bdev, mem->bus.is_iomem = true; mem->bus.caching = ttm_uncached; break; + case AMDGPU_PL_MMIO_REMAP: + mem->bus.offset = mem->start << PAGE_SHIFT; + mem->bus.offset += adev->rmmio_remap.bus_addr; + mem->bus.is_iomem = true; + mem->bus.caching = ttm_uncached; + break; default: return -EINVAL; } @@ -646,6 +657,8 @@ static unsigned long amdgpu_ttm_io_mem_pfn(struct ttm_buffer_object *bo, if (bo->resource->mem_type == AMDGPU_PL_DOORBELL) return ((uint64_t)(adev->doorbell.base + cursor.start)) >> PAGE_SHIFT; + else if (bo->resource->mem_type == AMDGPU_PL_MMIO_REMAP) + return ((uint64_t)(adev->rmmio_remap.bus_addr + cursor.start)) >> PAGE_SHIFT; return (adev->gmc.aper_base + cursor.start) >> PAGE_SHIFT; } @@ -1355,7 +1368,8 @@ uint64_t amdgpu_ttm_tt_pde_flags(struct ttm_tt *ttm, struct ttm_resource *mem) if (mem && (mem->mem_type == TTM_PL_TT || mem->mem_type == AMDGPU_PL_DOORBELL || - mem->mem_type == AMDGPU_PL_PREEMPT)) { + mem->mem_type == AMDGPU_PL_PREEMPT || + mem->mem_type == AMDGPU_PL_MMIO_REMAP)) { flags |= AMDGPU_PTE_SYSTEM; if (ttm->caching == ttm_cached) @@ -1510,7 +1524,8 @@ static int amdgpu_ttm_access_memory_sdma(struct ttm_buffer_object *bo, r = amdgpu_job_alloc_with_ib(adev, &adev->mman.high_pr, AMDGPU_FENCE_OWNER_UNDEFINED, num_dw * 4, AMDGPU_IB_POOL_DELAYED, - &job); + &job, + AMDGPU_KERNEL_JOB_ID_TTM_ACCESS_MEMORY_SDMA); if (r) goto out; @@ -1841,6 +1856,59 @@ static void amdgpu_ttm_pools_fini(struct amdgpu_device *adev) adev->mman.ttm_pools = NULL; } +/** + * amdgpu_ttm_mmio_remap_bo_init - Allocate the singleton 4K MMIO_REMAP BO + * @adev: amdgpu device + * + * Allocates a one-page (4K) GEM BO in AMDGPU_GEM_DOMAIN_MMIO_REMAP when the + * hardware exposes a remap base (adev->rmmio_remap.bus_addr) and the host + * PAGE_SIZE is <= AMDGPU_GPU_PAGE_SIZE (4K). The BO is created as a regular + * GEM object (amdgpu_bo_create). + * + * Return: + * * 0 on success or intentional skip (feature not present/unsupported) + * * negative errno on allocation failure + */ +static int amdgpu_ttm_mmio_remap_bo_init(struct amdgpu_device *adev) +{ + struct amdgpu_bo_param bp; + int r; + + /* Skip if HW doesn't expose remap, or if PAGE_SIZE > AMDGPU_GPU_PAGE_SIZE (4K). */ + if (!adev->rmmio_remap.bus_addr || PAGE_SIZE > AMDGPU_GPU_PAGE_SIZE) + return 0; + + memset(&bp, 0, sizeof(bp)); + + /* Create exactly one GEM BO in the MMIO_REMAP domain. */ + bp.type = ttm_bo_type_device; /* userspace-mappable GEM */ + bp.size = AMDGPU_GPU_PAGE_SIZE; /* 4K */ + bp.byte_align = AMDGPU_GPU_PAGE_SIZE; + bp.domain = AMDGPU_GEM_DOMAIN_MMIO_REMAP; + bp.flags = 0; + bp.resv = NULL; + bp.bo_ptr_size = sizeof(struct amdgpu_bo); + + r = amdgpu_bo_create(adev, &bp, &adev->rmmio_remap.bo); + if (r) + return r; + + return 0; +} + +/** + * amdgpu_ttm_mmio_remap_bo_fini - Free the singleton MMIO_REMAP BO + * @adev: amdgpu device + * + * Frees the kernel-owned MMIO_REMAP BO if it was allocated by + * amdgpu_ttm_mmio_remap_bo_init(). + */ +static void amdgpu_ttm_mmio_remap_bo_fini(struct amdgpu_device *adev) +{ + amdgpu_bo_unref(&adev->rmmio_remap.bo); + adev->rmmio_remap.bo = NULL; +} + /* * amdgpu_ttm_init - Init the memory management (ttm) as well as various * gtt/vram related fields. @@ -1877,11 +1945,13 @@ int amdgpu_ttm_init(struct amdgpu_device *adev) } adev->mman.initialized = true; - /* Initialize VRAM pool with all of VRAM divided into pages */ - r = amdgpu_vram_mgr_init(adev); - if (r) { - dev_err(adev->dev, "Failed initializing VRAM heap.\n"); - return r; + if (!adev->gmc.is_app_apu) { + /* Initialize VRAM pool with all of VRAM divided into pages */ + r = amdgpu_vram_mgr_init(adev); + if (r) { + dev_err(adev->dev, "Failed initializing VRAM heap.\n"); + return r; + } } /* Change the size here instead of the init above so only lpfn is affected */ @@ -2008,6 +2078,18 @@ int amdgpu_ttm_init(struct amdgpu_device *adev) return r; } + /* Initialize MMIO-remap pool (single page 4K) */ + r = amdgpu_ttm_init_on_chip(adev, AMDGPU_PL_MMIO_REMAP, 1); + if (r) { + dev_err(adev->dev, "Failed initializing MMIO-remap heap.\n"); + return r; + } + + /* Allocate the singleton MMIO_REMAP BO (4K) if supported */ + r = amdgpu_ttm_mmio_remap_bo_init(adev); + if (r) + return r; + /* Initialize preemptible memory pool */ r = amdgpu_preempt_mgr_init(adev); if (r) { @@ -2070,6 +2152,8 @@ void amdgpu_ttm_fini(struct amdgpu_device *adev) } amdgpu_bo_free_kernel(&adev->mman.sdma_access_bo, NULL, &adev->mman.sdma_access_ptr); + + amdgpu_ttm_mmio_remap_bo_fini(adev); amdgpu_ttm_fw_reserve_vram_fini(adev); amdgpu_ttm_drv_reserve_vram_fini(adev); @@ -2082,7 +2166,8 @@ void amdgpu_ttm_fini(struct amdgpu_device *adev) drm_dev_exit(idx); } - amdgpu_vram_mgr_fini(adev); + if (!adev->gmc.is_app_apu) + amdgpu_vram_mgr_fini(adev); amdgpu_gtt_mgr_fini(adev); amdgpu_preempt_mgr_fini(adev); amdgpu_doorbell_fini(adev); @@ -2091,6 +2176,7 @@ void amdgpu_ttm_fini(struct amdgpu_device *adev) ttm_range_man_fini(&adev->mman.bdev, AMDGPU_PL_GWS); ttm_range_man_fini(&adev->mman.bdev, AMDGPU_PL_OA); ttm_range_man_fini(&adev->mman.bdev, AMDGPU_PL_DOORBELL); + ttm_range_man_fini(&adev->mman.bdev, AMDGPU_PL_MMIO_REMAP); ttm_device_fini(&adev->mman.bdev); adev->mman.initialized = false; dev_info(adev->dev, "amdgpu: ttm finalized\n"); @@ -2167,7 +2253,7 @@ static int amdgpu_ttm_prepare_job(struct amdgpu_device *adev, struct dma_resv *resv, bool vm_needs_flush, struct amdgpu_job **job, - bool delayed) + bool delayed, u64 k_job_id) { enum amdgpu_ib_pool_type pool = direct_submit ? AMDGPU_IB_POOL_DIRECT : @@ -2177,7 +2263,7 @@ static int amdgpu_ttm_prepare_job(struct amdgpu_device *adev, &adev->mman.high_pr; r = amdgpu_job_alloc_with_ib(adev, entity, AMDGPU_FENCE_OWNER_UNDEFINED, - num_dw * 4, pool, job); + num_dw * 4, pool, job, k_job_id); if (r) return r; @@ -2217,7 +2303,8 @@ int amdgpu_copy_buffer(struct amdgpu_ring *ring, uint64_t src_offset, num_loops = DIV_ROUND_UP(byte_count, max_bytes); num_dw = ALIGN(num_loops * adev->mman.buffer_funcs->copy_num_dw, 8); r = amdgpu_ttm_prepare_job(adev, direct_submit, num_dw, - resv, vm_needs_flush, &job, false); + resv, vm_needs_flush, &job, false, + AMDGPU_KERNEL_JOB_ID_TTM_COPY_BUFFER); if (r) return r; @@ -2252,7 +2339,8 @@ static int amdgpu_ttm_fill_mem(struct amdgpu_ring *ring, uint32_t src_data, uint64_t dst_addr, uint32_t byte_count, struct dma_resv *resv, struct dma_fence **fence, - bool vm_needs_flush, bool delayed) + bool vm_needs_flush, bool delayed, + u64 k_job_id) { struct amdgpu_device *adev = ring->adev; unsigned int num_loops, num_dw; @@ -2265,7 +2353,7 @@ static int amdgpu_ttm_fill_mem(struct amdgpu_ring *ring, uint32_t src_data, num_loops = DIV_ROUND_UP_ULL(byte_count, max_bytes); num_dw = ALIGN(num_loops * adev->mman.buffer_funcs->fill_num_dw, 8); r = amdgpu_ttm_prepare_job(adev, false, num_dw, resv, vm_needs_flush, - &job, delayed); + &job, delayed, k_job_id); if (r) return r; @@ -2335,7 +2423,8 @@ int amdgpu_ttm_clear_buffer(struct amdgpu_bo *bo, goto err; r = amdgpu_ttm_fill_mem(ring, 0, addr, size, resv, - &next, true, true); + &next, true, true, + AMDGPU_KERNEL_JOB_ID_TTM_CLEAR_BUFFER); if (r) goto err; @@ -2354,7 +2443,8 @@ int amdgpu_fill_buffer(struct amdgpu_bo *bo, uint32_t src_data, struct dma_resv *resv, struct dma_fence **f, - bool delayed) + bool delayed, + u64 k_job_id) { struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); struct amdgpu_ring *ring = adev->mman.buffer_funcs_ring; @@ -2384,7 +2474,7 @@ int amdgpu_fill_buffer(struct amdgpu_bo *bo, goto error; r = amdgpu_ttm_fill_mem(ring, src_data, to, cur_size, resv, - &next, true, delayed); + &next, true, delayed, k_job_id); if (r) goto error; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h index 2309df3f68a9..1c5c7836ce4f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h @@ -34,7 +34,8 @@ #define AMDGPU_PL_OA (TTM_PL_PRIV + 2) #define AMDGPU_PL_PREEMPT (TTM_PL_PRIV + 3) #define AMDGPU_PL_DOORBELL (TTM_PL_PRIV + 4) -#define __AMDGPU_PL_NUM (TTM_PL_PRIV + 5) +#define AMDGPU_PL_MMIO_REMAP (TTM_PL_PRIV + 5) +#define __AMDGPU_PL_NUM (TTM_PL_PRIV + 6) #define AMDGPU_GTT_MAX_TRANSFER_SIZE 512 #define AMDGPU_GTT_NUM_TRANSFER_WINDOWS 2 @@ -182,7 +183,8 @@ int amdgpu_fill_buffer(struct amdgpu_bo *bo, uint32_t src_data, struct dma_resv *resv, struct dma_fence **fence, - bool delayed); + bool delayed, + u64 k_job_id); int amdgpu_ttm_alloc_gart(struct ttm_buffer_object *bo); void amdgpu_ttm_recover_gart(struct ttm_buffer_object *tbo); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c index f72de06a4ac8..a22e6025de61 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c @@ -44,8 +44,40 @@ u32 amdgpu_userq_get_supported_ip_mask(struct amdgpu_device *adev) return userq_ip_mask; } +int amdgpu_userq_input_va_validate(struct amdgpu_vm *vm, u64 addr, + u64 expected_size) +{ + struct amdgpu_bo_va_mapping *va_map; + u64 user_addr; + u64 size; + int r = 0; + + user_addr = (addr & AMDGPU_GMC_HOLE_MASK) >> AMDGPU_GPU_PAGE_SHIFT; + size = expected_size >> AMDGPU_GPU_PAGE_SHIFT; + + r = amdgpu_bo_reserve(vm->root.bo, false); + if (r) + return r; + + va_map = amdgpu_vm_bo_lookup_mapping(vm, user_addr); + if (!va_map) { + r = -EINVAL; + goto out_err; + } + /* Only validate the userq whether resident in the VM mapping range */ + if (user_addr >= va_map->start && + va_map->last - user_addr + 1 >= size) { + amdgpu_bo_unreserve(vm->root.bo); + return 0; + } + +out_err: + amdgpu_bo_unreserve(vm->root.bo); + return r; +} + static int -amdgpu_userq_unmap_helper(struct amdgpu_userq_mgr *uq_mgr, +amdgpu_userq_preempt_helper(struct amdgpu_userq_mgr *uq_mgr, struct amdgpu_usermode_queue *queue) { struct amdgpu_device *adev = uq_mgr->adev; @@ -54,6 +86,49 @@ amdgpu_userq_unmap_helper(struct amdgpu_userq_mgr *uq_mgr, int r = 0; if (queue->state == AMDGPU_USERQ_STATE_MAPPED) { + r = userq_funcs->preempt(uq_mgr, queue); + if (r) { + queue->state = AMDGPU_USERQ_STATE_HUNG; + } else { + queue->state = AMDGPU_USERQ_STATE_PREEMPTED; + } + } + + return r; +} + +static int +amdgpu_userq_restore_helper(struct amdgpu_userq_mgr *uq_mgr, + struct amdgpu_usermode_queue *queue) +{ + struct amdgpu_device *adev = uq_mgr->adev; + const struct amdgpu_userq_funcs *userq_funcs = + adev->userq_funcs[queue->queue_type]; + int r = 0; + + if (queue->state == AMDGPU_USERQ_STATE_PREEMPTED) { + r = userq_funcs->restore(uq_mgr, queue); + if (r) { + queue->state = AMDGPU_USERQ_STATE_HUNG; + } else { + queue->state = AMDGPU_USERQ_STATE_MAPPED; + } + } + + return r; +} + +static int +amdgpu_userq_unmap_helper(struct amdgpu_userq_mgr *uq_mgr, + struct amdgpu_usermode_queue *queue) +{ + struct amdgpu_device *adev = uq_mgr->adev; + const struct amdgpu_userq_funcs *userq_funcs = + adev->userq_funcs[queue->queue_type]; + int r = 0; + + if ((queue->state == AMDGPU_USERQ_STATE_MAPPED) || + (queue->state == AMDGPU_USERQ_STATE_PREEMPTED)) { r = userq_funcs->unmap(uq_mgr, queue); if (r) queue->state = AMDGPU_USERQ_STATE_HUNG; @@ -112,22 +187,6 @@ amdgpu_userq_cleanup(struct amdgpu_userq_mgr *uq_mgr, kfree(queue); } -int -amdgpu_userq_active(struct amdgpu_userq_mgr *uq_mgr) -{ - struct amdgpu_usermode_queue *queue; - int queue_id; - int ret = 0; - - mutex_lock(&uq_mgr->userq_mutex); - /* Resume all the queues for this process */ - idr_for_each_entry(&uq_mgr->userq_idr, queue, queue_id) - ret += queue->state == AMDGPU_USERQ_STATE_MAPPED; - - mutex_unlock(&uq_mgr->userq_mutex); - return ret; -} - static struct amdgpu_usermode_queue * amdgpu_userq_find(struct amdgpu_userq_mgr *uq_mgr, int qid) { @@ -323,6 +382,11 @@ amdgpu_userq_destroy(struct drm_file *filp, int queue_id) debugfs_remove_recursive(queue->debugfs_queue); #endif r = amdgpu_userq_unmap_helper(uq_mgr, queue); + /*TODO: It requires a reset for userq hw unmap error*/ + if (unlikely(r != AMDGPU_USERQ_STATE_UNMAPPED)) { + drm_warn(adev_to_drm(uq_mgr->adev), "trying to destroy a HW mapping userq\n"); + queue->state = AMDGPU_USERQ_STATE_HUNG; + } amdgpu_userq_cleanup(uq_mgr, queue, queue_id); mutex_unlock(&uq_mgr->userq_mutex); @@ -364,7 +428,7 @@ static int amdgpu_mqd_info_read(struct seq_file *m, void *unused) return -EINVAL; } - seq_printf(m, "queue_type %d\n", queue->queue_type); + seq_printf(m, "queue_type: %d\n", queue->queue_type); seq_printf(m, "mqd_gpu_address: 0x%llx\n", amdgpu_bo_gpu_offset(queue->mqd.obj)); amdgpu_bo_unreserve(bo); @@ -404,27 +468,10 @@ amdgpu_userq_create(struct drm_file *filp, union drm_amdgpu_userq *args) (args->in.flags & AMDGPU_USERQ_CREATE_FLAGS_QUEUE_PRIORITY_MASK) >> AMDGPU_USERQ_CREATE_FLAGS_QUEUE_PRIORITY_SHIFT; - /* Usermode queues are only supported for GFX IP as of now */ - if (args->in.ip_type != AMDGPU_HW_IP_GFX && - args->in.ip_type != AMDGPU_HW_IP_DMA && - args->in.ip_type != AMDGPU_HW_IP_COMPUTE) { - drm_file_err(uq_mgr->file, "Usermode queue doesn't support IP type %u\n", - args->in.ip_type); - return -EINVAL; - } - r = amdgpu_userq_priority_permit(filp, priority); if (r) return r; - if ((args->in.flags & AMDGPU_USERQ_CREATE_FLAGS_QUEUE_SECURE) && - (args->in.ip_type != AMDGPU_HW_IP_GFX) && - (args->in.ip_type != AMDGPU_HW_IP_COMPUTE) && - !amdgpu_is_tmz(adev)) { - drm_file_err(uq_mgr->file, "Secure only supported on GFX/Compute queues\n"); - return -EINVAL; - } - r = pm_runtime_get_sync(adev_to_drm(adev)->dev); if (r < 0) { drm_file_err(uq_mgr->file, "pm_runtime_get_sync() failed for userqueue create\n"); @@ -456,6 +503,14 @@ amdgpu_userq_create(struct drm_file *filp, union drm_amdgpu_userq *args) r = -ENOMEM; goto unlock; } + + /* Validate the userq virtual address.*/ + if (amdgpu_userq_input_va_validate(&fpriv->vm, args->in.queue_va, args->in.queue_size) || + amdgpu_userq_input_va_validate(&fpriv->vm, args->in.rptr_va, AMDGPU_GPU_PAGE_SIZE) || + amdgpu_userq_input_va_validate(&fpriv->vm, args->in.wptr_va, AMDGPU_GPU_PAGE_SIZE)) { + kfree(queue); + goto unlock; + } queue->doorbell_handle = args->in.doorbell_handle; queue->queue_type = args->in.ip_type; queue->vm = &fpriv->vm; @@ -543,22 +598,45 @@ unlock: return r; } -int amdgpu_userq_ioctl(struct drm_device *dev, void *data, - struct drm_file *filp) +static int amdgpu_userq_input_args_validate(struct drm_device *dev, + union drm_amdgpu_userq *args, + struct drm_file *filp) { - union drm_amdgpu_userq *args = data; - int r; + struct amdgpu_device *adev = drm_to_adev(dev); switch (args->in.op) { case AMDGPU_USERQ_OP_CREATE: if (args->in.flags & ~(AMDGPU_USERQ_CREATE_FLAGS_QUEUE_PRIORITY_MASK | AMDGPU_USERQ_CREATE_FLAGS_QUEUE_SECURE)) return -EINVAL; - r = amdgpu_userq_create(filp, args); - if (r) - drm_file_err(filp, "Failed to create usermode queue\n"); - break; + /* Usermode queues are only supported for GFX IP as of now */ + if (args->in.ip_type != AMDGPU_HW_IP_GFX && + args->in.ip_type != AMDGPU_HW_IP_DMA && + args->in.ip_type != AMDGPU_HW_IP_COMPUTE) { + drm_file_err(filp, "Usermode queue doesn't support IP type %u\n", + args->in.ip_type); + return -EINVAL; + } + + if ((args->in.flags & AMDGPU_USERQ_CREATE_FLAGS_QUEUE_SECURE) && + (args->in.ip_type != AMDGPU_HW_IP_GFX) && + (args->in.ip_type != AMDGPU_HW_IP_COMPUTE) && + !amdgpu_is_tmz(adev)) { + drm_file_err(filp, "Secure only supported on GFX/Compute queues\n"); + return -EINVAL; + } + if (args->in.queue_va == AMDGPU_BO_INVALID_OFFSET || + args->in.queue_va == 0 || + args->in.queue_size == 0) { + drm_file_err(filp, "invalidate userq queue va or size\n"); + return -EINVAL; + } + if (!args->in.wptr_va || !args->in.rptr_va) { + drm_file_err(filp, "invalidate userq queue rptr or wptr\n"); + return -EINVAL; + } + break; case AMDGPU_USERQ_OP_FREE: if (args->in.ip_type || args->in.doorbell_handle || @@ -571,6 +649,31 @@ int amdgpu_userq_ioctl(struct drm_device *dev, void *data, args->in.mqd || args->in.mqd_size) return -EINVAL; + break; + default: + return -EINVAL; + } + + return 0; +} + +int amdgpu_userq_ioctl(struct drm_device *dev, void *data, + struct drm_file *filp) +{ + union drm_amdgpu_userq *args = data; + int r; + + if (amdgpu_userq_input_args_validate(dev, args, filp) < 0) + return -EINVAL; + + switch (args->in.op) { + case AMDGPU_USERQ_OP_CREATE: + r = amdgpu_userq_create(filp, args); + if (r) + drm_file_err(filp, "Failed to create usermode queue\n"); + break; + + case AMDGPU_USERQ_OP_FREE: r = amdgpu_userq_destroy(filp, args->in.queue_id); if (r) drm_file_err(filp, "Failed to destroy usermode queue\n"); @@ -593,7 +696,7 @@ amdgpu_userq_restore_all(struct amdgpu_userq_mgr *uq_mgr) /* Resume all the queues for this process */ idr_for_each_entry(&uq_mgr->userq_idr, queue, queue_id) { - r = amdgpu_userq_map_helper(uq_mgr, queue); + r = amdgpu_userq_restore_helper(uq_mgr, queue); if (r) ret = r; } @@ -603,108 +706,106 @@ amdgpu_userq_restore_all(struct amdgpu_userq_mgr *uq_mgr) return ret; } +static int amdgpu_userq_validate_vm(void *param, struct amdgpu_bo *bo) +{ + struct ttm_operation_ctx ctx = { false, false }; + + amdgpu_bo_placement_from_domain(bo, bo->allowed_domains); + return ttm_bo_validate(&bo->tbo, &bo->placement, &ctx); +} + +/* Handle all BOs on the invalidated list, validate them and update the PTs */ static int -amdgpu_userq_validate_vm_bo(void *_unused, struct amdgpu_bo *bo) +amdgpu_userq_bo_validate(struct amdgpu_device *adev, struct drm_exec *exec, + struct amdgpu_vm *vm) { struct ttm_operation_ctx ctx = { false, false }; + struct amdgpu_bo_va *bo_va; + struct amdgpu_bo *bo; int ret; - amdgpu_bo_placement_from_domain(bo, bo->allowed_domains); + spin_lock(&vm->invalidated_lock); + while (!list_empty(&vm->invalidated)) { + bo_va = list_first_entry(&vm->invalidated, + struct amdgpu_bo_va, + base.vm_status); + spin_unlock(&vm->invalidated_lock); - ret = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx); - if (ret) - DRM_ERROR("Fail to validate\n"); + bo = bo_va->base.bo; + ret = drm_exec_prepare_obj(exec, &bo->tbo.base, 2); + if (unlikely(ret)) + return ret; - return ret; + amdgpu_bo_placement_from_domain(bo, bo->allowed_domains); + ret = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx); + if (ret) + return ret; + + /* This moves the bo_va to the done list */ + ret = amdgpu_vm_bo_update(adev, bo_va, false); + if (ret) + return ret; + + spin_lock(&vm->invalidated_lock); + } + spin_unlock(&vm->invalidated_lock); + + return 0; } +/* Make sure the whole VM is ready to be used */ static int -amdgpu_userq_validate_bos(struct amdgpu_userq_mgr *uq_mgr) +amdgpu_userq_vm_validate(struct amdgpu_userq_mgr *uq_mgr) { struct amdgpu_fpriv *fpriv = uq_mgr_to_fpriv(uq_mgr); - struct amdgpu_vm *vm = &fpriv->vm; struct amdgpu_device *adev = uq_mgr->adev; + struct amdgpu_vm *vm = &fpriv->vm; struct amdgpu_bo_va *bo_va; - struct ww_acquire_ctx *ticket; struct drm_exec exec; - struct amdgpu_bo *bo; - struct dma_resv *resv; - bool clear, unlock; - int ret = 0; + int ret; drm_exec_init(&exec, DRM_EXEC_IGNORE_DUPLICATES, 0); drm_exec_until_all_locked(&exec) { - ret = amdgpu_vm_lock_pd(vm, &exec, 2); + ret = amdgpu_vm_lock_pd(vm, &exec, 1); drm_exec_retry_on_contention(&exec); - if (unlikely(ret)) { - drm_file_err(uq_mgr->file, "Failed to lock PD\n"); + if (unlikely(ret)) goto unlock_all; - } - - /* Lock the done list */ - list_for_each_entry(bo_va, &vm->done, base.vm_status) { - bo = bo_va->base.bo; - if (!bo) - continue; - - ret = drm_exec_lock_obj(&exec, &bo->tbo.base); - drm_exec_retry_on_contention(&exec); - if (unlikely(ret)) - goto unlock_all; - } - } - spin_lock(&vm->status_lock); - while (!list_empty(&vm->moved)) { - bo_va = list_first_entry(&vm->moved, struct amdgpu_bo_va, - base.vm_status); - spin_unlock(&vm->status_lock); - - /* Per VM BOs never need to bo cleared in the page tables */ - ret = amdgpu_vm_bo_update(adev, bo_va, false); - if (ret) + ret = amdgpu_vm_lock_done_list(vm, &exec, 1); + drm_exec_retry_on_contention(&exec); + if (unlikely(ret)) goto unlock_all; - spin_lock(&vm->status_lock); - } - - ticket = &exec.ticket; - while (!list_empty(&vm->invalidated)) { - bo_va = list_first_entry(&vm->invalidated, struct amdgpu_bo_va, - base.vm_status); - resv = bo_va->base.bo->tbo.base.resv; - spin_unlock(&vm->status_lock); - bo = bo_va->base.bo; - ret = amdgpu_userq_validate_vm_bo(NULL, bo); - if (ret) { - drm_file_err(uq_mgr->file, "Failed to validate BO\n"); + /* This validates PDs, PTs and per VM BOs */ + ret = amdgpu_vm_validate(adev, vm, NULL, + amdgpu_userq_validate_vm, + NULL); + if (unlikely(ret)) goto unlock_all; - } - /* Try to reserve the BO to avoid clearing its ptes */ - if (!adev->debug_vm && dma_resv_trylock(resv)) { - clear = false; - unlock = true; - /* The caller is already holding the reservation lock */ - } else if (dma_resv_locking_ctx(resv) == ticket) { - clear = false; - unlock = false; - /* Somebody else is using the BO right now */ - } else { - clear = true; - unlock = false; - } + /* This locks and validates the remaining evicted BOs */ + ret = amdgpu_userq_bo_validate(adev, &exec, vm); + drm_exec_retry_on_contention(&exec); + if (unlikely(ret)) + goto unlock_all; + } - ret = amdgpu_vm_bo_update(adev, bo_va, clear); + ret = amdgpu_vm_handle_moved(adev, vm, NULL); + if (ret) + goto unlock_all; - if (unlock) - dma_resv_unlock(resv); - if (ret) - goto unlock_all; + ret = amdgpu_vm_update_pdes(adev, vm, false); + if (ret) + goto unlock_all; - spin_lock(&vm->status_lock); - } - spin_unlock(&vm->status_lock); + /* + * We need to wait for all VM updates to finish before restarting the + * queues. Using the done list like that is now ok since everything is + * locked in place. + */ + list_for_each_entry(bo_va, &vm->done, base.vm_status) + dma_fence_wait(bo_va->last_pt_update, false); + dma_fence_wait(vm->last_update, false); ret = amdgpu_eviction_fence_replace_fence(&fpriv->evf_mgr, &exec); if (ret) @@ -725,7 +826,7 @@ static void amdgpu_userq_restore_worker(struct work_struct *work) mutex_lock(&uq_mgr->userq_mutex); - ret = amdgpu_userq_validate_bos(uq_mgr); + ret = amdgpu_userq_vm_validate(uq_mgr); if (ret) { drm_file_err(uq_mgr->file, "Failed to validate BOs to restore\n"); goto unlock; @@ -750,7 +851,7 @@ amdgpu_userq_evict_all(struct amdgpu_userq_mgr *uq_mgr) /* Try to unmap all the queues in this process ctx */ idr_for_each_entry(&uq_mgr->userq_idr, queue, queue_id) { - r = amdgpu_userq_unmap_helper(uq_mgr, queue); + r = amdgpu_userq_preempt_helper(uq_mgr, queue); if (r) ret = r; } @@ -876,7 +977,10 @@ int amdgpu_userq_suspend(struct amdgpu_device *adev) cancel_delayed_work_sync(&uqm->resume_work); mutex_lock(&uqm->userq_mutex); idr_for_each_entry(&uqm->userq_idr, queue, queue_id) { - r = amdgpu_userq_unmap_helper(uqm, queue); + if (adev->in_s0ix) + r = amdgpu_userq_preempt_helper(uqm, queue); + else + r = amdgpu_userq_unmap_helper(uqm, queue); if (r) ret = r; } @@ -901,7 +1005,10 @@ int amdgpu_userq_resume(struct amdgpu_device *adev) list_for_each_entry_safe(uqm, tmp, &adev->userq_mgr_list, list) { mutex_lock(&uqm->userq_mutex); idr_for_each_entry(&uqm->userq_idr, queue, queue_id) { - r = amdgpu_userq_map_helper(uqm, queue); + if (adev->in_s0ix) + r = amdgpu_userq_restore_helper(uqm, queue); + else + r = amdgpu_userq_map_helper(uqm, queue); if (r) ret = r; } @@ -935,7 +1042,7 @@ int amdgpu_userq_stop_sched_for_enforce_isolation(struct amdgpu_device *adev, if (((queue->queue_type == AMDGPU_HW_IP_GFX) || (queue->queue_type == AMDGPU_HW_IP_COMPUTE)) && (queue->xcp_id == idx)) { - r = amdgpu_userq_unmap_helper(uqm, queue); + r = amdgpu_userq_preempt_helper(uqm, queue); if (r) ret = r; } @@ -969,7 +1076,7 @@ int amdgpu_userq_start_sched_for_enforce_isolation(struct amdgpu_device *adev, if (((queue->queue_type == AMDGPU_HW_IP_GFX) || (queue->queue_type == AMDGPU_HW_IP_COMPUTE)) && (queue->xcp_id == idx)) { - r = amdgpu_userq_map_helper(uqm, queue); + r = amdgpu_userq_restore_helper(uqm, queue); if (r) ret = r; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h index b1ca91b7cda4..c027dd916672 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h @@ -78,6 +78,12 @@ struct amdgpu_userq_funcs { struct amdgpu_usermode_queue *queue); int (*map)(struct amdgpu_userq_mgr *uq_mgr, struct amdgpu_usermode_queue *queue); + int (*preempt)(struct amdgpu_userq_mgr *uq_mgr, + struct amdgpu_usermode_queue *queue); + int (*restore)(struct amdgpu_userq_mgr *uq_mgr, + struct amdgpu_usermode_queue *queue); + int (*detect_and_reset)(struct amdgpu_device *adev, + int queue_type); }; /* Usermode queues for gfx */ @@ -114,8 +120,6 @@ void amdgpu_userq_destroy_object(struct amdgpu_userq_mgr *uq_mgr, void amdgpu_userq_evict(struct amdgpu_userq_mgr *uq_mgr, struct amdgpu_eviction_fence *ev_fence); -int amdgpu_userq_active(struct amdgpu_userq_mgr *uq_mgr); - void amdgpu_userq_ensure_ev_fence(struct amdgpu_userq_mgr *userq_mgr, struct amdgpu_eviction_fence_mgr *evf_mgr); @@ -133,4 +137,6 @@ int amdgpu_userq_stop_sched_for_enforce_isolation(struct amdgpu_device *adev, int amdgpu_userq_start_sched_for_enforce_isolation(struct amdgpu_device *adev, u32 idx); +int amdgpu_userq_input_va_validate(struct amdgpu_vm *vm, u64 addr, + u64 expected_size); #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c index c2a983ff23c9..95e91d1dc58a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c @@ -67,6 +67,14 @@ static u64 amdgpu_userq_fence_read(struct amdgpu_userq_fence_driver *fence_drv) return le64_to_cpu(*fence_drv->cpu_addr); } +static void +amdgpu_userq_fence_write(struct amdgpu_userq_fence_driver *fence_drv, + u64 seq) +{ + if (fence_drv->cpu_addr) + *fence_drv->cpu_addr = cpu_to_le64(seq); +} + int amdgpu_userq_fence_driver_alloc(struct amdgpu_device *adev, struct amdgpu_usermode_queue *userq) { @@ -408,6 +416,40 @@ static void amdgpu_userq_fence_cleanup(struct dma_fence *fence) dma_fence_put(fence); } +static void +amdgpu_userq_fence_driver_set_error(struct amdgpu_userq_fence *fence, + int error) +{ + struct amdgpu_userq_fence_driver *fence_drv = fence->fence_drv; + unsigned long flags; + struct dma_fence *f; + + spin_lock_irqsave(&fence_drv->fence_list_lock, flags); + + f = rcu_dereference_protected(&fence->base, + lockdep_is_held(&fence_drv->fence_list_lock)); + if (f && !dma_fence_is_signaled_locked(f)) + dma_fence_set_error(f, error); + spin_unlock_irqrestore(&fence_drv->fence_list_lock, flags); +} + +void +amdgpu_userq_fence_driver_force_completion(struct amdgpu_usermode_queue *userq) +{ + struct dma_fence *f = userq->last_fence; + + if (f) { + struct amdgpu_userq_fence *fence = to_amdgpu_userq_fence(f); + struct amdgpu_userq_fence_driver *fence_drv = fence->fence_drv; + u64 wptr = fence->base.seqno; + + amdgpu_userq_fence_driver_set_error(fence, -ECANCELED); + amdgpu_userq_fence_write(fence_drv, wptr); + amdgpu_userq_fence_driver_process(fence_drv); + + } +} + int amdgpu_userq_signal_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.h index 97a125ab8a78..d76add2afc77 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.h @@ -67,6 +67,7 @@ int amdgpu_userq_fence_driver_alloc(struct amdgpu_device *adev, struct amdgpu_usermode_queue *userq); void amdgpu_userq_fence_driver_free(struct amdgpu_usermode_queue *userq); void amdgpu_userq_fence_driver_process(struct amdgpu_userq_fence_driver *fence_drv); +void amdgpu_userq_fence_driver_force_completion(struct amdgpu_usermode_queue *userq); void amdgpu_userq_fence_driver_destroy(struct kref *ref); int amdgpu_userq_signal_ioctl(struct drm_device *dev, void *data, struct drm_file *filp); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_utils.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_utils.h new file mode 100644 index 000000000000..1e40ca3b1584 --- /dev/null +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_utils.h @@ -0,0 +1,91 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright 2025 Advanced Micro Devices, Inc. + * + * 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, sublicense, + * 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 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 NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) 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. + * + */ + +#ifndef AMDGPU_UTILS_H_ +#define AMDGPU_UTILS_H_ + +/* ---------- Generic 2‑bit capability attribute encoding ---------- + * 00 INVALID, 01 RO, 10 WO, 11 RW + */ +enum amdgpu_cap_attr { + AMDGPU_CAP_ATTR_INVALID = 0, + AMDGPU_CAP_ATTR_RO = 1 << 0, + AMDGPU_CAP_ATTR_WO = 1 << 1, + AMDGPU_CAP_ATTR_RW = (AMDGPU_CAP_ATTR_RO | AMDGPU_CAP_ATTR_WO), +}; + +#define AMDGPU_CAP_ATTR_BITS 2 +#define AMDGPU_CAP_ATTR_MAX ((1U << AMDGPU_CAP_ATTR_BITS) - 1) + +/* Internal helper to build helpers for a given enum NAME */ +#define DECLARE_ATTR_CAP_CLASS_HELPERS(NAME) \ +enum { NAME##_BITMAP_BITS = NAME##_COUNT * AMDGPU_CAP_ATTR_BITS }; \ +struct NAME##_caps { \ + DECLARE_BITMAP(bmap, NAME##_BITMAP_BITS); \ +}; \ +static inline unsigned int NAME##_ATTR_START(enum NAME##_cap_id cap) \ +{ return (unsigned int)cap * AMDGPU_CAP_ATTR_BITS; } \ +static inline void NAME##_attr_init(struct NAME##_caps *c) \ +{ if (c) bitmap_zero(c->bmap, NAME##_BITMAP_BITS); } \ +static inline int NAME##_attr_set(struct NAME##_caps *c, \ + enum NAME##_cap_id cap, enum amdgpu_cap_attr attr) \ +{ \ + if (!c) \ + return -EINVAL; \ + if (cap >= NAME##_COUNT) \ + return -EINVAL; \ + if ((unsigned int)attr > AMDGPU_CAP_ATTR_MAX) \ + return -EINVAL; \ + bitmap_write(c->bmap, (unsigned long)attr, \ + NAME##_ATTR_START(cap), AMDGPU_CAP_ATTR_BITS); \ + return 0; \ +} \ +static inline int NAME##_attr_get(const struct NAME##_caps *c, \ + enum NAME##_cap_id cap, enum amdgpu_cap_attr *out) \ +{ \ + unsigned long v; \ + if (!c || !out) \ + return -EINVAL; \ + if (cap >= NAME##_COUNT) \ + return -EINVAL; \ + v = bitmap_read(c->bmap, NAME##_ATTR_START(cap), AMDGPU_CAP_ATTR_BITS); \ + *out = (enum amdgpu_cap_attr)v; \ + return 0; \ +} \ +static inline bool NAME##_cap_is_ro(const struct NAME##_caps *c, enum NAME##_cap_id id) \ +{ enum amdgpu_cap_attr a; return !NAME##_attr_get(c, id, &a) && a == AMDGPU_CAP_ATTR_RO; } \ +static inline bool NAME##_cap_is_wo(const struct NAME##_caps *c, enum NAME##_cap_id id) \ +{ enum amdgpu_cap_attr a; return !NAME##_attr_get(c, id, &a) && a == AMDGPU_CAP_ATTR_WO; } \ +static inline bool NAME##_cap_is_rw(const struct NAME##_caps *c, enum NAME##_cap_id id) \ +{ enum amdgpu_cap_attr a; return !NAME##_attr_get(c, id, &a) && a == AMDGPU_CAP_ATTR_RW; } + +/* Element expander for enum creation */ +#define _CAP_ENUM_ELEM(x) x, + +/* Public macro: declare enum + helpers from an X‑macro list */ +#define DECLARE_ATTR_CAP_CLASS(NAME, LIST_MACRO) \ + enum NAME##_cap_id { LIST_MACRO(_CAP_ENUM_ELEM) NAME##_COUNT }; \ + DECLARE_ATTR_CAP_CLASS_HELPERS(NAME) + +#endif /* AMDGPU_UTILS_H_ */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c index 74758b5ffc6c..5c38f0d30c87 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c @@ -1136,7 +1136,8 @@ static int amdgpu_uvd_send_msg(struct amdgpu_ring *ring, struct amdgpu_bo *bo, r = amdgpu_job_alloc_with_ib(ring->adev, &adev->uvd.entity, AMDGPU_FENCE_OWNER_UNDEFINED, 64, direct ? AMDGPU_IB_POOL_DIRECT : - AMDGPU_IB_POOL_DELAYED, &job); + AMDGPU_IB_POOL_DELAYED, &job, + AMDGPU_KERNEL_JOB_ID_VCN_RING_TEST); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c index b9060bcd4806..ce318f5de047 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c @@ -449,7 +449,7 @@ static int amdgpu_vce_get_create_msg(struct amdgpu_ring *ring, uint32_t handle, r = amdgpu_job_alloc_with_ib(ring->adev, &ring->adev->vce.entity, AMDGPU_FENCE_OWNER_UNDEFINED, ib_size_dw * 4, AMDGPU_IB_POOL_DIRECT, - &job); + &job, AMDGPU_KERNEL_JOB_ID_VCN_RING_TEST); if (r) return r; @@ -540,7 +540,8 @@ static int amdgpu_vce_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle, AMDGPU_FENCE_OWNER_UNDEFINED, ib_size_dw * 4, direct ? AMDGPU_IB_POOL_DIRECT : - AMDGPU_IB_POOL_DELAYED, &job); + AMDGPU_IB_POOL_DELAYED, &job, + AMDGPU_KERNEL_JOB_ID_VCN_RING_TEST); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c index ad415203d245..5e0786ea911b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c @@ -257,12 +257,12 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev, int i) return 0; } -int amdgpu_vcn_sw_fini(struct amdgpu_device *adev, int i) +void amdgpu_vcn_sw_fini(struct amdgpu_device *adev, int i) { int j; if (adev->vcn.harvest_config & (1 << i)) - return 0; + return; amdgpu_bo_free_kernel( &adev->vcn.inst[i].dpg_sram_bo, @@ -292,8 +292,6 @@ int amdgpu_vcn_sw_fini(struct amdgpu_device *adev, int i) mutex_destroy(&adev->vcn.inst[i].vcn_pg_lock); mutex_destroy(&adev->vcn.inst[i].vcn1_jpeg1_workaround); - - return 0; } bool amdgpu_vcn_is_disabled_vcn(struct amdgpu_device *adev, enum vcn_ring_type type, uint32_t vcn_instance) @@ -628,7 +626,7 @@ static int amdgpu_vcn_dec_send_msg(struct amdgpu_ring *ring, r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL, 64, AMDGPU_IB_POOL_DIRECT, - &job); + &job, AMDGPU_KERNEL_JOB_ID_VCN_RING_TEST); if (r) goto err; @@ -808,7 +806,7 @@ static int amdgpu_vcn_dec_sw_send_msg(struct amdgpu_ring *ring, r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL, ib_size_dw * 4, AMDGPU_IB_POOL_DIRECT, - &job); + &job, AMDGPU_KERNEL_JOB_ID_VCN_RING_TEST); if (r) goto err; @@ -938,7 +936,7 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL, ib_size_dw * 4, AMDGPU_IB_POOL_DIRECT, - &job); + &job, AMDGPU_KERNEL_JOB_ID_VCN_RING_TEST); if (r) return r; @@ -1005,7 +1003,7 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL, ib_size_dw * 4, AMDGPU_IB_POOL_DIRECT, - &job); + &job, AMDGPU_KERNEL_JOB_ID_VCN_RING_TEST); if (r) return r; @@ -1159,7 +1157,7 @@ static ssize_t amdgpu_debugfs_vcn_fwlog_read(struct file *f, char __user *buf, { struct amdgpu_vcn_inst *vcn; void *log_buf; - volatile struct amdgpu_vcn_fwlog *plog; + struct amdgpu_vcn_fwlog *plog; unsigned int read_pos, write_pos, available, i, read_bytes = 0; unsigned int read_num[2] = {0}; @@ -1172,7 +1170,7 @@ static ssize_t amdgpu_debugfs_vcn_fwlog_read(struct file *f, char __user *buf, log_buf = vcn->fw_shared.cpu_addr + vcn->fw_shared.mem_size; - plog = (volatile struct amdgpu_vcn_fwlog *)log_buf; + plog = (struct amdgpu_vcn_fwlog *)log_buf; read_pos = plog->rptr; write_pos = plog->wptr; @@ -1239,11 +1237,11 @@ void amdgpu_debugfs_vcn_fwlog_init(struct amdgpu_device *adev, uint8_t i, void amdgpu_vcn_fwlog_init(struct amdgpu_vcn_inst *vcn) { #if defined(CONFIG_DEBUG_FS) - volatile uint32_t *flag = vcn->fw_shared.cpu_addr; + uint32_t *flag = vcn->fw_shared.cpu_addr; void *fw_log_cpu_addr = vcn->fw_shared.cpu_addr + vcn->fw_shared.mem_size; uint64_t fw_log_gpu_addr = vcn->fw_shared.gpu_addr + vcn->fw_shared.mem_size; - volatile struct amdgpu_vcn_fwlog *log_buf = fw_log_cpu_addr; - volatile struct amdgpu_fw_shared_fw_logging *fw_log = vcn->fw_shared.cpu_addr + struct amdgpu_vcn_fwlog *log_buf = fw_log_cpu_addr; + struct amdgpu_fw_shared_fw_logging *fw_log = vcn->fw_shared.cpu_addr + vcn->fw_shared.log_offset; *flag |= cpu_to_le32(AMDGPU_VCN_FW_LOGGING_FLAG); fw_log->is_enabled = 1; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h index 6d9acd36041d..bebfc2b34afe 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h @@ -516,7 +516,7 @@ enum vcn_ring_type { int amdgpu_vcn_early_init(struct amdgpu_device *adev, int i); int amdgpu_vcn_sw_init(struct amdgpu_device *adev, int i); -int amdgpu_vcn_sw_fini(struct amdgpu_device *adev, int i); +void amdgpu_vcn_sw_fini(struct amdgpu_device *adev, int i); int amdgpu_vcn_suspend(struct amdgpu_device *adev, int i); int amdgpu_vcn_resume(struct amdgpu_device *adev, int i); void amdgpu_vcn_ring_begin_use(struct amdgpu_ring *ring); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c index 13f0cdeb59c4..3328ab63376b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c @@ -828,11 +828,14 @@ static void amdgpu_virt_init_ras(struct amdgpu_device *adev) { ratelimit_state_init(&adev->virt.ras.ras_error_cnt_rs, 5 * HZ, 1); ratelimit_state_init(&adev->virt.ras.ras_cper_dump_rs, 5 * HZ, 1); + ratelimit_state_init(&adev->virt.ras.ras_chk_criti_rs, 5 * HZ, 1); ratelimit_set_flags(&adev->virt.ras.ras_error_cnt_rs, RATELIMIT_MSG_ON_RELEASE); ratelimit_set_flags(&adev->virt.ras.ras_cper_dump_rs, RATELIMIT_MSG_ON_RELEASE); + ratelimit_set_flags(&adev->virt.ras.ras_chk_criti_rs, + RATELIMIT_MSG_ON_RELEASE); mutex_init(&adev->virt.ras.ras_telemetry_mutex); @@ -1501,3 +1504,55 @@ void amdgpu_virt_request_bad_pages(struct amdgpu_device *adev) if (virt->ops && virt->ops->req_bad_pages) virt->ops->req_bad_pages(adev); } + +static int amdgpu_virt_cache_chk_criti_hit(struct amdgpu_device *adev, + struct amdsriov_ras_telemetry *host_telemetry, + bool *hit) +{ + struct amd_sriov_ras_chk_criti *tmp = NULL; + uint32_t checksum, used_size; + + checksum = host_telemetry->header.checksum; + used_size = host_telemetry->header.used_size; + + if (used_size > (AMD_SRIOV_RAS_TELEMETRY_SIZE_KB << 10)) + return 0; + + tmp = kmemdup(&host_telemetry->body.chk_criti, used_size, GFP_KERNEL); + if (!tmp) + return -ENOMEM; + + if (checksum != amd_sriov_msg_checksum(tmp, used_size, 0, 0)) + goto out; + + if (hit) + *hit = tmp->hit ? true : false; + +out: + kfree(tmp); + + return 0; +} + +int amdgpu_virt_check_vf_critical_region(struct amdgpu_device *adev, u64 addr, bool *hit) +{ + struct amdgpu_virt *virt = &adev->virt; + int r = -EPERM; + + if (!virt->ops || !virt->ops->req_ras_chk_criti) + return -EOPNOTSUPP; + + /* Host allows 15 ras telemetry requests per 60 seconds. Afterwhich, the Host + * will ignore incoming guest messages. Ratelimit the guest messages to + * prevent guest self DOS. + */ + if (__ratelimit(&virt->ras.ras_chk_criti_rs)) { + mutex_lock(&virt->ras.ras_telemetry_mutex); + if (!virt->ops->req_ras_chk_criti(adev, addr)) + r = amdgpu_virt_cache_chk_criti_hit( + adev, virt->fw_reserve.ras_telemetry, hit); + mutex_unlock(&virt->ras.ras_telemetry_mutex); + } + + return r; +} diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h index 58accf2259b3..d1172c8e58c4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h @@ -98,6 +98,7 @@ struct amdgpu_virt_ops { int (*req_ras_err_count)(struct amdgpu_device *adev); int (*req_ras_cper_dump)(struct amdgpu_device *adev, u64 vf_rptr); int (*req_bad_pages)(struct amdgpu_device *adev); + int (*req_ras_chk_criti)(struct amdgpu_device *adev, u64 addr); }; /* @@ -252,10 +253,15 @@ struct amdgpu_virt_ras_err_handler_data { struct amdgpu_virt_ras { struct ratelimit_state ras_error_cnt_rs; struct ratelimit_state ras_cper_dump_rs; + struct ratelimit_state ras_chk_criti_rs; struct mutex ras_telemetry_mutex; uint64_t cper_rptr; }; +#define AMDGPU_VIRT_CAPS_LIST(X) X(AMDGPU_VIRT_CAP_POWER_LIMIT) + +DECLARE_ATTR_CAP_CLASS(amdgpu_virt, AMDGPU_VIRT_CAPS_LIST); + /* GPU virtualization */ struct amdgpu_virt { uint32_t caps; @@ -274,6 +280,7 @@ struct amdgpu_virt { const struct amdgpu_virt_ops *ops; struct amdgpu_vf_error_buffer vf_errors; struct amdgpu_virt_fw_reserve fw_reserve; + struct amdgpu_virt_caps virt_caps; uint32_t gim_feature; uint32_t reg_access_mode; int req_init_data_ver; @@ -448,4 +455,5 @@ int amdgpu_virt_ras_telemetry_post_reset(struct amdgpu_device *adev); bool amdgpu_virt_ras_telemetry_block_en(struct amdgpu_device *adev, enum amdgpu_ras_block block); void amdgpu_virt_request_bad_pages(struct amdgpu_device *adev); +int amdgpu_virt_check_vf_critical_region(struct amdgpu_device *adev, u64 addr, bool *hit); #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c index 155bb9891a17..79bad9cbe2ab 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c @@ -14,7 +14,6 @@ #include "dce_v8_0.h" #endif #include "dce_v10_0.h" -#include "dce_v11_0.h" #include "ivsrcid/ivsrcid_vislands30.h" #include "amdgpu_vkms.h" #include "amdgpu_display.h" @@ -581,13 +580,6 @@ static int amdgpu_vkms_hw_init(struct amdgpu_ip_block *ip_block) case CHIP_TONGA: dce_v10_0_disable_dce(adev); break; - case CHIP_CARRIZO: - case CHIP_STONEY: - case CHIP_POLARIS10: - case CHIP_POLARIS11: - case CHIP_VEGAM: - dce_v11_0_disable_dce(adev); - break; case CHIP_TOPAZ: #ifdef CONFIG_DRM_AMDGPU_SI case CHIP_HAINAN: diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index bd12d8ff15a4..112ce584a5ad 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -128,6 +128,17 @@ struct amdgpu_vm_tlb_seq_struct { }; /** + * amdgpu_vm_assert_locked - check if VM is correctly locked + * @vm: the VM which schould be tested + * + * Asserts that the VM root PD is locked. + */ +static void amdgpu_vm_assert_locked(struct amdgpu_vm *vm) +{ + dma_resv_assert_held(vm->root.bo->tbo.base.resv); +} + +/** * amdgpu_vm_set_pasid - manage pasid and vm ptr mapping * * @adev: amdgpu_device pointer @@ -143,6 +154,8 @@ int amdgpu_vm_set_pasid(struct amdgpu_device *adev, struct amdgpu_vm *vm, { int r; + amdgpu_vm_assert_locked(vm); + if (vm->pasid == pasid) return 0; @@ -181,12 +194,11 @@ static void amdgpu_vm_bo_evicted(struct amdgpu_vm_bo_base *vm_bo) struct amdgpu_bo *bo = vm_bo->bo; vm_bo->moved = true; - spin_lock(&vm_bo->vm->status_lock); + amdgpu_vm_assert_locked(vm); if (bo->tbo.type == ttm_bo_type_kernel) list_move(&vm_bo->vm_status, &vm->evicted); else list_move_tail(&vm_bo->vm_status, &vm->evicted); - spin_unlock(&vm_bo->vm->status_lock); } /** * amdgpu_vm_bo_moved - vm_bo is moved @@ -198,9 +210,8 @@ static void amdgpu_vm_bo_evicted(struct amdgpu_vm_bo_base *vm_bo) */ static void amdgpu_vm_bo_moved(struct amdgpu_vm_bo_base *vm_bo) { - spin_lock(&vm_bo->vm->status_lock); + amdgpu_vm_assert_locked(vm_bo->vm); list_move(&vm_bo->vm_status, &vm_bo->vm->moved); - spin_unlock(&vm_bo->vm->status_lock); } /** @@ -213,9 +224,8 @@ static void amdgpu_vm_bo_moved(struct amdgpu_vm_bo_base *vm_bo) */ static void amdgpu_vm_bo_idle(struct amdgpu_vm_bo_base *vm_bo) { - spin_lock(&vm_bo->vm->status_lock); + amdgpu_vm_assert_locked(vm_bo->vm); list_move(&vm_bo->vm_status, &vm_bo->vm->idle); - spin_unlock(&vm_bo->vm->status_lock); vm_bo->moved = false; } @@ -229,9 +239,9 @@ static void amdgpu_vm_bo_idle(struct amdgpu_vm_bo_base *vm_bo) */ static void amdgpu_vm_bo_invalidated(struct amdgpu_vm_bo_base *vm_bo) { - spin_lock(&vm_bo->vm->status_lock); + spin_lock(&vm_bo->vm->invalidated_lock); list_move(&vm_bo->vm_status, &vm_bo->vm->invalidated); - spin_unlock(&vm_bo->vm->status_lock); + spin_unlock(&vm_bo->vm->invalidated_lock); } /** @@ -244,10 +254,9 @@ static void amdgpu_vm_bo_invalidated(struct amdgpu_vm_bo_base *vm_bo) */ static void amdgpu_vm_bo_evicted_user(struct amdgpu_vm_bo_base *vm_bo) { + amdgpu_vm_assert_locked(vm_bo->vm); vm_bo->moved = true; - spin_lock(&vm_bo->vm->status_lock); list_move(&vm_bo->vm_status, &vm_bo->vm->evicted_user); - spin_unlock(&vm_bo->vm->status_lock); } /** @@ -260,13 +269,11 @@ static void amdgpu_vm_bo_evicted_user(struct amdgpu_vm_bo_base *vm_bo) */ static void amdgpu_vm_bo_relocated(struct amdgpu_vm_bo_base *vm_bo) { - if (vm_bo->bo->parent) { - spin_lock(&vm_bo->vm->status_lock); + amdgpu_vm_assert_locked(vm_bo->vm); + if (vm_bo->bo->parent) list_move(&vm_bo->vm_status, &vm_bo->vm->relocated); - spin_unlock(&vm_bo->vm->status_lock); - } else { + else amdgpu_vm_bo_idle(vm_bo); - } } /** @@ -279,9 +286,8 @@ static void amdgpu_vm_bo_relocated(struct amdgpu_vm_bo_base *vm_bo) */ static void amdgpu_vm_bo_done(struct amdgpu_vm_bo_base *vm_bo) { - spin_lock(&vm_bo->vm->status_lock); + amdgpu_vm_assert_locked(vm_bo->vm); list_move(&vm_bo->vm_status, &vm_bo->vm->done); - spin_unlock(&vm_bo->vm->status_lock); } /** @@ -295,10 +301,13 @@ static void amdgpu_vm_bo_reset_state_machine(struct amdgpu_vm *vm) { struct amdgpu_vm_bo_base *vm_bo, *tmp; - spin_lock(&vm->status_lock); + spin_lock(&vm->invalidated_lock); list_splice_init(&vm->done, &vm->invalidated); list_for_each_entry(vm_bo, &vm->invalidated, vm_status) vm_bo->moved = true; + spin_unlock(&vm->invalidated_lock); + + amdgpu_vm_assert_locked(vm_bo->vm); list_for_each_entry_safe(vm_bo, tmp, &vm->idle, vm_status) { struct amdgpu_bo *bo = vm_bo->bo; @@ -308,14 +317,13 @@ static void amdgpu_vm_bo_reset_state_machine(struct amdgpu_vm *vm) else if (bo->parent) list_move(&vm_bo->vm_status, &vm_bo->vm->relocated); } - spin_unlock(&vm->status_lock); } /** * amdgpu_vm_update_shared - helper to update shared memory stat * @base: base structure for tracking BO usage in a VM * - * Takes the vm status_lock and updates the shared memory stat. If the basic + * Takes the vm stats_lock and updates the shared memory stat. If the basic * stat changed (e.g. buffer was moved) amdgpu_vm_update_stats need to be called * as well. */ @@ -327,7 +335,8 @@ static void amdgpu_vm_update_shared(struct amdgpu_vm_bo_base *base) uint32_t bo_memtype = amdgpu_bo_mem_stats_placement(bo); bool shared; - spin_lock(&vm->status_lock); + dma_resv_assert_held(bo->tbo.base.resv); + spin_lock(&vm->stats_lock); shared = drm_gem_object_is_shared_for_memory_stats(&bo->tbo.base); if (base->shared != shared) { base->shared = shared; @@ -339,7 +348,7 @@ static void amdgpu_vm_update_shared(struct amdgpu_vm_bo_base *base) vm->stats[bo_memtype].drm.private += size; } } - spin_unlock(&vm->status_lock); + spin_unlock(&vm->stats_lock); } /** @@ -364,11 +373,11 @@ void amdgpu_vm_bo_update_shared(struct amdgpu_bo *bo) * be bo->tbo.resource * @sign: if we should add (+1) or subtract (-1) from the stat * - * Caller need to have the vm status_lock held. Useful for when multiple update + * Caller need to have the vm stats_lock held. Useful for when multiple update * need to happen at the same time. */ static void amdgpu_vm_update_stats_locked(struct amdgpu_vm_bo_base *base, - struct ttm_resource *res, int sign) + struct ttm_resource *res, int sign) { struct amdgpu_vm *vm = base->vm; struct amdgpu_bo *bo = base->bo; @@ -392,7 +401,8 @@ static void amdgpu_vm_update_stats_locked(struct amdgpu_vm_bo_base *base, */ if (bo->flags & AMDGPU_GEM_CREATE_DISCARDABLE) vm->stats[res_memtype].drm.purgeable += size; - if (!(bo->preferred_domains & amdgpu_mem_type_to_domain(res_memtype))) + if (!(bo->preferred_domains & + amdgpu_mem_type_to_domain(res_memtype))) vm->stats[bo_memtype].evicted += size; } } @@ -411,9 +421,9 @@ void amdgpu_vm_update_stats(struct amdgpu_vm_bo_base *base, { struct amdgpu_vm *vm = base->vm; - spin_lock(&vm->status_lock); + spin_lock(&vm->stats_lock); amdgpu_vm_update_stats_locked(base, res, sign); - spin_unlock(&vm->status_lock); + spin_unlock(&vm->stats_lock); } /** @@ -439,10 +449,10 @@ void amdgpu_vm_bo_base_init(struct amdgpu_vm_bo_base *base, base->next = bo->vm_bo; bo->vm_bo = base; - spin_lock(&vm->status_lock); + spin_lock(&vm->stats_lock); base->shared = drm_gem_object_is_shared_for_memory_stats(&bo->tbo.base); amdgpu_vm_update_stats_locked(base, bo->tbo.resource, +1); - spin_unlock(&vm->status_lock); + spin_unlock(&vm->stats_lock); if (!amdgpu_vm_is_bo_always_valid(vm, bo)) return; @@ -485,6 +495,42 @@ int amdgpu_vm_lock_pd(struct amdgpu_vm *vm, struct drm_exec *exec, } /** + * amdgpu_vm_lock_done_list - lock all BOs on the done list + * @vm: vm providing the BOs + * @exec: drm execution context + * @num_fences: number of extra fences to reserve + * + * Lock the BOs on the done list in the DRM execution context. + */ +int amdgpu_vm_lock_done_list(struct amdgpu_vm *vm, struct drm_exec *exec, + unsigned int num_fences) +{ + struct list_head *prev = &vm->done; + struct amdgpu_bo_va *bo_va; + struct amdgpu_bo *bo; + int ret; + + /* We can only trust prev->next while holding the lock */ + spin_lock(&vm->invalidated_lock); + while (!list_is_head(prev->next, &vm->done)) { + bo_va = list_entry(prev->next, typeof(*bo_va), base.vm_status); + spin_unlock(&vm->invalidated_lock); + + bo = bo_va->base.bo; + if (bo) { + ret = drm_exec_prepare_obj(exec, &bo->tbo.base, 1); + if (unlikely(ret)) + return ret; + } + spin_lock(&vm->invalidated_lock); + prev = prev->next; + } + spin_unlock(&vm->invalidated_lock); + + return 0; +} + +/** * amdgpu_vm_move_to_lru_tail - move all BOs to the end of LRU * * @adev: amdgpu device pointer @@ -575,7 +621,7 @@ int amdgpu_vm_validate(struct amdgpu_device *adev, struct amdgpu_vm *vm, void *param) { uint64_t new_vm_generation = amdgpu_vm_generation(adev, vm); - struct amdgpu_vm_bo_base *bo_base; + struct amdgpu_vm_bo_base *bo_base, *tmp; struct amdgpu_bo *bo; int r; @@ -588,13 +634,7 @@ int amdgpu_vm_validate(struct amdgpu_device *adev, struct amdgpu_vm *vm, return r; } - spin_lock(&vm->status_lock); - while (!list_empty(&vm->evicted)) { - bo_base = list_first_entry(&vm->evicted, - struct amdgpu_vm_bo_base, - vm_status); - spin_unlock(&vm->status_lock); - + list_for_each_entry_safe(bo_base, tmp, &vm->evicted, vm_status) { bo = bo_base->bo; r = validate(param, bo); @@ -607,37 +647,21 @@ int amdgpu_vm_validate(struct amdgpu_device *adev, struct amdgpu_vm *vm, vm->update_funcs->map_table(to_amdgpu_bo_vm(bo)); amdgpu_vm_bo_relocated(bo_base); } - spin_lock(&vm->status_lock); } - while (ticket && !list_empty(&vm->evicted_user)) { - bo_base = list_first_entry(&vm->evicted_user, - struct amdgpu_vm_bo_base, - vm_status); - spin_unlock(&vm->status_lock); - - bo = bo_base->bo; - if (dma_resv_locking_ctx(bo->tbo.base.resv) != ticket) { - struct amdgpu_task_info *ti = amdgpu_vm_get_task_info_vm(vm); + if (ticket) { + list_for_each_entry_safe(bo_base, tmp, &vm->evicted_user, + vm_status) { + bo = bo_base->bo; + dma_resv_assert_held(bo->tbo.base.resv); - pr_warn_ratelimited("Evicted user BO is not reserved\n"); - if (ti) { - pr_warn_ratelimited("pid %d\n", ti->task.pid); - amdgpu_vm_put_task_info(ti); - } + r = validate(param, bo); + if (r) + return r; - return -EINVAL; + amdgpu_vm_bo_invalidated(bo_base); } - - r = validate(param, bo); - if (r) - return r; - - amdgpu_vm_bo_invalidated(bo_base); - - spin_lock(&vm->status_lock); } - spin_unlock(&vm->status_lock); amdgpu_vm_eviction_lock(vm); vm->evicting = false; @@ -660,13 +684,13 @@ bool amdgpu_vm_ready(struct amdgpu_vm *vm) { bool ret; + amdgpu_vm_assert_locked(vm); + amdgpu_vm_eviction_lock(vm); ret = !vm->evicting; amdgpu_vm_eviction_unlock(vm); - spin_lock(&vm->status_lock); ret &= list_empty(&vm->evicted); - spin_unlock(&vm->status_lock); spin_lock(&vm->immediate.lock); ret &= !vm->immediate.stopped; @@ -957,16 +981,13 @@ int amdgpu_vm_update_pdes(struct amdgpu_device *adev, struct amdgpu_vm *vm, bool immediate) { struct amdgpu_vm_update_params params; - struct amdgpu_vm_bo_base *entry; + struct amdgpu_vm_bo_base *entry, *tmp; bool flush_tlb_needed = false; - LIST_HEAD(relocated); int r, idx; - spin_lock(&vm->status_lock); - list_splice_init(&vm->relocated, &relocated); - spin_unlock(&vm->status_lock); + amdgpu_vm_assert_locked(vm); - if (list_empty(&relocated)) + if (list_empty(&vm->relocated)) return 0; if (!drm_dev_enter(adev_to_drm(adev), &idx)) @@ -977,11 +998,12 @@ int amdgpu_vm_update_pdes(struct amdgpu_device *adev, params.vm = vm; params.immediate = immediate; - r = vm->update_funcs->prepare(¶ms, NULL); + r = vm->update_funcs->prepare(¶ms, NULL, + AMDGPU_KERNEL_JOB_ID_VM_UPDATE_PDES); if (r) goto error; - list_for_each_entry(entry, &relocated, vm_status) { + list_for_each_entry(entry, &vm->relocated, vm_status) { /* vm_flush_needed after updating moved PDEs */ flush_tlb_needed |= entry->moved; @@ -997,9 +1019,7 @@ int amdgpu_vm_update_pdes(struct amdgpu_device *adev, if (flush_tlb_needed) atomic64_inc(&vm->tlb_seq); - while (!list_empty(&relocated)) { - entry = list_first_entry(&relocated, struct amdgpu_vm_bo_base, - vm_status); + list_for_each_entry_safe(entry, tmp, &vm->relocated, vm_status) { amdgpu_vm_bo_idle(entry); } @@ -1146,7 +1166,8 @@ int amdgpu_vm_update_range(struct amdgpu_device *adev, struct amdgpu_vm *vm, dma_fence_put(tmp); } - r = vm->update_funcs->prepare(¶ms, sync); + r = vm->update_funcs->prepare(¶ms, sync, + AMDGPU_KERNEL_JOB_ID_VM_UPDATE_RANGE); if (r) goto error_free; @@ -1225,9 +1246,9 @@ error_free: void amdgpu_vm_get_memory(struct amdgpu_vm *vm, struct amdgpu_mem_stats stats[__AMDGPU_PL_NUM]) { - spin_lock(&vm->status_lock); + spin_lock(&vm->stats_lock); memcpy(stats, vm->stats, sizeof(*stats) * __AMDGPU_PL_NUM); - spin_unlock(&vm->status_lock); + spin_unlock(&vm->stats_lock); } /** @@ -1283,7 +1304,7 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va, struct drm_gem_object *obj = &bo->tbo.base; if (drm_gem_is_imported(obj) && bo_va->is_xgmi) { - struct dma_buf *dma_buf = obj->dma_buf; + struct dma_buf *dma_buf = obj->import_attach->dmabuf; struct drm_gem_object *gobj = dma_buf->priv; struct amdgpu_bo *abo = gem_to_amdgpu_bo(gobj); @@ -1594,29 +1615,24 @@ int amdgpu_vm_handle_moved(struct amdgpu_device *adev, struct amdgpu_vm *vm, struct ww_acquire_ctx *ticket) { - struct amdgpu_bo_va *bo_va; + struct amdgpu_bo_va *bo_va, *tmp; struct dma_resv *resv; bool clear, unlock; int r; - spin_lock(&vm->status_lock); - while (!list_empty(&vm->moved)) { - bo_va = list_first_entry(&vm->moved, struct amdgpu_bo_va, - base.vm_status); - spin_unlock(&vm->status_lock); - + list_for_each_entry_safe(bo_va, tmp, &vm->moved, base.vm_status) { /* Per VM BOs never need to bo cleared in the page tables */ r = amdgpu_vm_bo_update(adev, bo_va, false); if (r) return r; - spin_lock(&vm->status_lock); } + spin_lock(&vm->invalidated_lock); while (!list_empty(&vm->invalidated)) { bo_va = list_first_entry(&vm->invalidated, struct amdgpu_bo_va, base.vm_status); resv = bo_va->base.bo->tbo.base.resv; - spin_unlock(&vm->status_lock); + spin_unlock(&vm->invalidated_lock); /* Try to reserve the BO to avoid clearing its ptes */ if (!adev->debug_vm && dma_resv_trylock(resv)) { @@ -1648,9 +1664,9 @@ int amdgpu_vm_handle_moved(struct amdgpu_device *adev, bo_va->base.bo->tbo.resource->mem_type == TTM_PL_SYSTEM)) amdgpu_vm_bo_evicted_user(&bo_va->base); - spin_lock(&vm->status_lock); + spin_lock(&vm->invalidated_lock); } - spin_unlock(&vm->status_lock); + spin_unlock(&vm->invalidated_lock); return 0; } @@ -2179,9 +2195,9 @@ void amdgpu_vm_bo_del(struct amdgpu_device *adev, } } - spin_lock(&vm->status_lock); + spin_lock(&vm->invalidated_lock); list_del(&bo_va->base.vm_status); - spin_unlock(&vm->status_lock); + spin_unlock(&vm->invalidated_lock); list_for_each_entry_safe(mapping, next, &bo_va->valids, list) { list_del(&mapping->list); @@ -2289,10 +2305,10 @@ void amdgpu_vm_bo_move(struct amdgpu_bo *bo, struct ttm_resource *new_mem, for (bo_base = bo->vm_bo; bo_base; bo_base = bo_base->next) { struct amdgpu_vm *vm = bo_base->vm; - spin_lock(&vm->status_lock); + spin_lock(&vm->stats_lock); amdgpu_vm_update_stats_locked(bo_base, bo->tbo.resource, -1); amdgpu_vm_update_stats_locked(bo_base, new_mem, +1); - spin_unlock(&vm->status_lock); + spin_unlock(&vm->stats_lock); } amdgpu_vm_bo_invalidate(bo, evicted); @@ -2559,11 +2575,12 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, INIT_LIST_HEAD(&vm->relocated); INIT_LIST_HEAD(&vm->moved); INIT_LIST_HEAD(&vm->idle); + spin_lock_init(&vm->invalidated_lock); INIT_LIST_HEAD(&vm->invalidated); - spin_lock_init(&vm->status_lock); INIT_LIST_HEAD(&vm->freed); INIT_LIST_HEAD(&vm->done); INIT_KFIFO(vm->faults); + spin_lock_init(&vm->stats_lock); r = amdgpu_vm_init_entities(adev, vm); if (r) @@ -3028,7 +3045,8 @@ void amdgpu_debugfs_vm_bo_info(struct amdgpu_vm *vm, struct seq_file *m) unsigned int total_done_objs = 0; unsigned int id = 0; - spin_lock(&vm->status_lock); + amdgpu_vm_assert_locked(vm); + seq_puts(m, "\tIdle BOs:\n"); list_for_each_entry_safe(bo_va, tmp, &vm->idle, base.vm_status) { if (!bo_va->base.bo) @@ -3066,11 +3084,13 @@ void amdgpu_debugfs_vm_bo_info(struct amdgpu_vm *vm, struct seq_file *m) id = 0; seq_puts(m, "\tInvalidated BOs:\n"); + spin_lock(&vm->invalidated_lock); list_for_each_entry_safe(bo_va, tmp, &vm->invalidated, base.vm_status) { if (!bo_va->base.bo) continue; total_invalidated += amdgpu_bo_print_info(id++, bo_va->base.bo, m); } + spin_unlock(&vm->invalidated_lock); total_invalidated_objs = id; id = 0; @@ -3080,7 +3100,6 @@ void amdgpu_debugfs_vm_bo_info(struct amdgpu_vm *vm, struct seq_file *m) continue; total_done += amdgpu_bo_print_info(id++, bo_va->base.bo, m); } - spin_unlock(&vm->status_lock); total_done_objs = id; seq_printf(m, "\tTotal idle size: %12lld\tobjs:\t%d\n", total_idle, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h index 3b4fa3246675..988e970d9e96 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h @@ -203,11 +203,11 @@ struct amdgpu_vm_bo_base { /* protected by bo being reserved */ struct amdgpu_vm_bo_base *next; - /* protected by vm status_lock */ + /* protected by vm reservation and invalidated_lock */ struct list_head vm_status; /* if the bo is counted as shared in mem stats - * protected by vm status_lock */ + * protected by vm BO being reserved */ bool shared; /* protected by the BO being reserved */ @@ -308,7 +308,7 @@ struct amdgpu_vm_update_params { struct amdgpu_vm_update_funcs { int (*map_table)(struct amdgpu_bo_vm *bo); int (*prepare)(struct amdgpu_vm_update_params *p, - struct amdgpu_sync *sync); + struct amdgpu_sync *sync, u64 k_job_id); int (*update)(struct amdgpu_vm_update_params *p, struct amdgpu_bo_vm *bo, uint64_t pe, uint64_t addr, unsigned count, uint32_t incr, uint64_t flags); @@ -343,18 +343,22 @@ struct amdgpu_vm { bool evicting; unsigned int saved_flags; - /* Lock to protect vm_bo add/del/move on all lists of vm */ - spinlock_t status_lock; - - /* Memory statistics for this vm, protected by status_lock */ + /* Memory statistics for this vm, protected by stats_lock */ + spinlock_t stats_lock; struct amdgpu_mem_stats stats[__AMDGPU_PL_NUM]; + /* + * The following lists contain amdgpu_vm_bo_base objects for either + * PDs, PTs or per VM BOs. The state transits are: + * + * evicted -> relocated (PDs, PTs) or moved (per VM BOs) -> idle + * + * Lists are protected by the root PD dma_resv lock. + */ + /* Per-VM and PT BOs who needs a validation */ struct list_head evicted; - /* BOs for user mode queues that need a validation */ - struct list_head evicted_user; - /* PT BOs which relocated and their parent need an update */ struct list_head relocated; @@ -364,15 +368,32 @@ struct amdgpu_vm { /* All BOs of this VM not currently in the state machine */ struct list_head idle; + /* + * The following lists contain amdgpu_vm_bo_base objects for BOs which + * have their own dma_resv object and not depend on the root PD. Their + * state transits are: + * + * evicted_user or invalidated -> done + * + * Lists are protected by the invalidated_lock. + */ + spinlock_t invalidated_lock; + + /* BOs for user mode queues that need a validation */ + struct list_head evicted_user; + /* regular invalidated BOs, but not yet updated in the PT */ struct list_head invalidated; - /* BO mappings freed, but not yet updated in the PT */ - struct list_head freed; - /* BOs which are invalidated, has been updated in the PTs */ struct list_head done; + /* + * This list contains amdgpu_bo_va_mapping objects which have been freed + * but not updated in the PTs + */ + struct list_head freed; + /* contains the page directory */ struct amdgpu_vm_bo_base root; struct dma_fence *last_update; @@ -491,6 +512,8 @@ int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm); void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm); int amdgpu_vm_lock_pd(struct amdgpu_vm *vm, struct drm_exec *exec, unsigned int num_fences); +int amdgpu_vm_lock_done_list(struct amdgpu_vm *vm, struct drm_exec *exec, + unsigned int num_fences); bool amdgpu_vm_ready(struct amdgpu_vm *vm); uint64_t amdgpu_vm_generation(struct amdgpu_device *adev, struct amdgpu_vm *vm); int amdgpu_vm_validate(struct amdgpu_device *adev, struct amdgpu_vm *vm, @@ -670,4 +693,9 @@ void amdgpu_vm_tlb_fence_create(struct amdgpu_device *adev, void amdgpu_vm_print_task_info(struct amdgpu_device *adev, struct amdgpu_task_info *task_info); +#define amdgpu_vm_bo_va_for_each_valid_mapping(bo_va, mapping) \ + list_for_each_entry(mapping, &(bo_va)->valids, list) +#define amdgpu_vm_bo_va_for_each_invalid_mapping(bo_va, mapping) \ + list_for_each_entry(mapping, &(bo_va)->invalids, list) + #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_cpu.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_cpu.c index 0c1ef5850a5e..22e2e5b47341 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_cpu.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_cpu.c @@ -40,12 +40,14 @@ static int amdgpu_vm_cpu_map_table(struct amdgpu_bo_vm *table) * * @p: see amdgpu_vm_update_params definition * @sync: sync obj with fences to wait on + * @k_job_id: the id for tracing/debug purposes * * Returns: * Negativ errno, 0 for success. */ static int amdgpu_vm_cpu_prepare(struct amdgpu_vm_update_params *p, - struct amdgpu_sync *sync) + struct amdgpu_sync *sync, + u64 k_job_id) { if (!sync) return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c index 30022123b0bf..7a4c12ff9b18 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c @@ -26,6 +26,7 @@ #include "amdgpu.h" #include "amdgpu_trace.h" #include "amdgpu_vm.h" +#include "amdgpu_job.h" /* * amdgpu_vm_pt_cursor - state for for_each_amdgpu_vm_pt @@ -395,7 +396,8 @@ int amdgpu_vm_pt_clear(struct amdgpu_device *adev, struct amdgpu_vm *vm, params.vm = vm; params.immediate = immediate; - r = vm->update_funcs->prepare(¶ms, NULL); + r = vm->update_funcs->prepare(¶ms, NULL, + AMDGPU_KERNEL_JOB_ID_VM_PT_CLEAR); if (r) goto exit; @@ -541,9 +543,7 @@ static void amdgpu_vm_pt_free(struct amdgpu_vm_bo_base *entry) entry->bo->vm_bo = NULL; ttm_bo_set_bulk_move(&entry->bo->tbo, NULL); - spin_lock(&entry->vm->status_lock); list_del(&entry->vm_status); - spin_unlock(&entry->vm->status_lock); amdgpu_bo_unref(&entry->bo); } @@ -587,7 +587,6 @@ static void amdgpu_vm_pt_add_list(struct amdgpu_vm_update_params *params, struct amdgpu_vm_pt_cursor seek; struct amdgpu_vm_bo_base *entry; - spin_lock(¶ms->vm->status_lock); for_each_amdgpu_vm_pt_dfs_safe(params->adev, params->vm, cursor, seek, entry) { if (entry && entry->bo) list_move(&entry->vm_status, ¶ms->tlb_flush_waitlist); @@ -595,7 +594,6 @@ static void amdgpu_vm_pt_add_list(struct amdgpu_vm_update_params *params, /* enter start node now */ list_move(&cursor->entry->vm_status, ¶ms->tlb_flush_waitlist); - spin_unlock(¶ms->vm->status_lock); } /** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c index 46d9fb433ab2..36805dcfa159 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c @@ -40,7 +40,7 @@ static int amdgpu_vm_sdma_map_table(struct amdgpu_bo_vm *table) /* Allocate a new job for @count PTE updates */ static int amdgpu_vm_sdma_alloc_job(struct amdgpu_vm_update_params *p, - unsigned int count) + unsigned int count, u64 k_job_id) { enum amdgpu_ib_pool_type pool = p->immediate ? AMDGPU_IB_POOL_IMMEDIATE : AMDGPU_IB_POOL_DELAYED; @@ -56,7 +56,7 @@ static int amdgpu_vm_sdma_alloc_job(struct amdgpu_vm_update_params *p, ndw = min(ndw, AMDGPU_VM_SDMA_MAX_NUM_DW); r = amdgpu_job_alloc_with_ib(p->adev, entity, AMDGPU_FENCE_OWNER_VM, - ndw * 4, pool, &p->job); + ndw * 4, pool, &p->job, k_job_id); if (r) return r; @@ -69,16 +69,17 @@ static int amdgpu_vm_sdma_alloc_job(struct amdgpu_vm_update_params *p, * * @p: see amdgpu_vm_update_params definition * @sync: amdgpu_sync object with fences to wait for + * @k_job_id: identifier of the job, for tracing purpose * * Returns: * Negativ errno, 0 for success. */ static int amdgpu_vm_sdma_prepare(struct amdgpu_vm_update_params *p, - struct amdgpu_sync *sync) + struct amdgpu_sync *sync, u64 k_job_id) { int r; - r = amdgpu_vm_sdma_alloc_job(p, 0); + r = amdgpu_vm_sdma_alloc_job(p, 0, k_job_id); if (r) return r; @@ -249,7 +250,8 @@ static int amdgpu_vm_sdma_update(struct amdgpu_vm_update_params *p, if (r) return r; - r = amdgpu_vm_sdma_alloc_job(p, count); + r = amdgpu_vm_sdma_alloc_job(p, count, + AMDGPU_KERNEL_JOB_ID_VM_UPDATE); if (r) return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c index e69db0a93378..a5adb2ed9b3c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c @@ -425,45 +425,6 @@ out: return ret; } -static void amdgpu_dummy_vram_mgr_debug(struct ttm_resource_manager *man, - struct drm_printer *printer) -{ - DRM_DEBUG_DRIVER("Dummy vram mgr debug\n"); -} - -static bool amdgpu_dummy_vram_mgr_compatible(struct ttm_resource_manager *man, - struct ttm_resource *res, - const struct ttm_place *place, - size_t size) -{ - DRM_DEBUG_DRIVER("Dummy vram mgr compatible\n"); - return false; -} - -static bool amdgpu_dummy_vram_mgr_intersects(struct ttm_resource_manager *man, - struct ttm_resource *res, - const struct ttm_place *place, - size_t size) -{ - DRM_DEBUG_DRIVER("Dummy vram mgr intersects\n"); - return true; -} - -static void amdgpu_dummy_vram_mgr_del(struct ttm_resource_manager *man, - struct ttm_resource *res) -{ - DRM_DEBUG_DRIVER("Dummy vram mgr deleted\n"); -} - -static int amdgpu_dummy_vram_mgr_new(struct ttm_resource_manager *man, - struct ttm_buffer_object *tbo, - const struct ttm_place *place, - struct ttm_resource **res) -{ - DRM_DEBUG_DRIVER("Dummy vram mgr new\n"); - return -ENOSPC; -} - /** * amdgpu_vram_mgr_new - allocate new ranges * @@ -932,14 +893,6 @@ static void amdgpu_vram_mgr_debug(struct ttm_resource_manager *man, mutex_unlock(&mgr->lock); } -static const struct ttm_resource_manager_func amdgpu_dummy_vram_mgr_func = { - .alloc = amdgpu_dummy_vram_mgr_new, - .free = amdgpu_dummy_vram_mgr_del, - .intersects = amdgpu_dummy_vram_mgr_intersects, - .compatible = amdgpu_dummy_vram_mgr_compatible, - .debug = amdgpu_dummy_vram_mgr_debug -}; - static const struct ttm_resource_manager_func amdgpu_vram_mgr_func = { .alloc = amdgpu_vram_mgr_new, .free = amdgpu_vram_mgr_del, @@ -973,16 +926,10 @@ int amdgpu_vram_mgr_init(struct amdgpu_device *adev) INIT_LIST_HEAD(&mgr->allocated_vres_list); mgr->default_page_size = PAGE_SIZE; - if (!adev->gmc.is_app_apu) { - man->func = &amdgpu_vram_mgr_func; - - err = drm_buddy_init(&mgr->mm, man->size, PAGE_SIZE); - if (err) - return err; - } else { - man->func = &amdgpu_dummy_vram_mgr_func; - DRM_INFO("Setup dummy vram mgr\n"); - } + man->func = &amdgpu_vram_mgr_func; + err = drm_buddy_init(&mgr->mm, man->size, PAGE_SIZE); + if (err) + return err; ttm_set_driver_manager(&adev->mman.bdev, TTM_PL_VRAM, &mgr->manager); ttm_resource_manager_set_used(man, true); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h index bba0b26fee8f..5f36aff17e79 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h @@ -126,4 +126,8 @@ uint32_t amdgpu_xgmi_get_max_bandwidth(struct amdgpu_device *adev); void amgpu_xgmi_set_max_speed_width(struct amdgpu_device *adev, uint16_t max_speed, uint8_t max_width); + +/* Cleanup macro for use with __free(xgmi_put_hive) */ +DEFINE_FREE(xgmi_put_hive, struct amdgpu_hive_info *, if (_T) amdgpu_put_xgmi_hive(_T)) + #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h b/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h index 33edad1f9dcd..3a79ed7d8031 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h @@ -405,12 +405,17 @@ struct amd_sriov_ras_cper_dump { uint32_t buf[]; }; +struct amd_sriov_ras_chk_criti { + uint32_t hit; +}; + struct amdsriov_ras_telemetry { struct amd_sriov_ras_telemetry_header header; union { struct amd_sriov_ras_telemetry_error_count error_count; struct amd_sriov_ras_cper_dump cper_dump; + struct amd_sriov_ras_chk_criti chk_criti; } body; }; diff --git a/drivers/gpu/drm/amd/amdgpu/atom.c b/drivers/gpu/drm/amd/amdgpu/atom.c index 427b073de2fc..be5d67c2c7a1 100644 --- a/drivers/gpu/drm/amd/amdgpu/atom.c +++ b/drivers/gpu/drm/amd/amdgpu/atom.c @@ -1246,6 +1246,10 @@ static int amdgpu_atom_execute_table_locked(struct atom_context *ctx, int index, ectx.last_jump_jiffies = 0; if (ws) { ectx.ws = kcalloc(4, ws, GFP_KERNEL); + if (!ectx.ws) { + ret = -ENOMEM; + goto free; + } ectx.ws_size = ws; } else { ectx.ws = NULL; @@ -1494,6 +1498,27 @@ static void atom_get_vbios_version(struct atom_context *ctx) } } +static void atom_get_vbios_build(struct atom_context *ctx) +{ + unsigned char *atom_rom_hdr; + unsigned char *str; + uint16_t base; + + base = CU16(ATOM_ROM_TABLE_PTR); + atom_rom_hdr = CSTR(base); + + str = CSTR(CU16(base + ATOM_ROM_CFG_PTR)); + /* Skip config string */ + while (str < atom_rom_hdr && *str++) + ; + /* Skip change list string */ + while (str < atom_rom_hdr && *str++) + ; + + if ((str + STRLEN_NORMAL) < atom_rom_hdr) + strscpy(ctx->build_num, str, STRLEN_NORMAL); +} + struct atom_context *amdgpu_atom_parse(struct card_info *card, void *bios) { int base; @@ -1554,6 +1579,7 @@ struct atom_context *amdgpu_atom_parse(struct card_info *card, void *bios) atom_get_vbios_pn(ctx); atom_get_vbios_date(ctx); atom_get_vbios_version(ctx); + atom_get_vbios_build(ctx); return ctx; } diff --git a/drivers/gpu/drm/amd/amdgpu/atom.h b/drivers/gpu/drm/amd/amdgpu/atom.h index b807f6639a4c..825ff28731f5 100644 --- a/drivers/gpu/drm/amd/amdgpu/atom.h +++ b/drivers/gpu/drm/amd/amdgpu/atom.h @@ -37,6 +37,7 @@ struct drm_device; #define ATOM_ROM_MAGIC "ATOM" #define ATOM_ROM_MAGIC_PTR 4 +#define ATOM_ROM_CFG_PTR 0xC #define ATOM_ROM_MSG_PTR 0x10 #define ATOM_ROM_CMD_PTR 0x1E #define ATOM_ROM_DATA_PTR 0x20 @@ -151,6 +152,7 @@ struct atom_context { uint32_t version; uint8_t vbios_ver_str[STRLEN_NORMAL]; uint8_t date[STRLEN_NORMAL]; + uint8_t build_num[STRLEN_NORMAL]; }; extern int amdgpu_atom_debug; diff --git a/drivers/gpu/drm/amd/amdgpu/cyan_skillfish_reg_init.c b/drivers/gpu/drm/amd/amdgpu/cyan_skillfish_reg_init.c new file mode 100644 index 000000000000..96616a865aac --- /dev/null +++ b/drivers/gpu/drm/amd/amdgpu/cyan_skillfish_reg_init.c @@ -0,0 +1,56 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright 2018 Advanced Micro Devices, Inc. + * + * 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, sublicense, + * 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 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 NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) 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. + * + */ +#include "amdgpu.h" +#include "nv.h" + +#include "soc15_common.h" +#include "soc15_hw_ip.h" +#include "cyan_skillfish_ip_offset.h" + +int cyan_skillfish_reg_base_init(struct amdgpu_device *adev) +{ + /* HW has more IP blocks, only initialized the blocke needed by driver */ + uint32_t i; + + adev->gfx.xcc_mask = 1; + for (i = 0 ; i < MAX_INSTANCE ; ++i) { + adev->reg_offset[GC_HWIP][i] = (uint32_t *)(&(GC_BASE.instance[i])); + adev->reg_offset[HDP_HWIP][i] = (uint32_t *)(&(HDP_BASE.instance[i])); + adev->reg_offset[MMHUB_HWIP][i] = (uint32_t *)(&(MMHUB_BASE.instance[i])); + adev->reg_offset[ATHUB_HWIP][i] = (uint32_t *)(&(ATHUB_BASE.instance[i])); + adev->reg_offset[NBIO_HWIP][i] = (uint32_t *)(&(NBIO_BASE.instance[i])); + adev->reg_offset[MP0_HWIP][i] = (uint32_t *)(&(MP0_BASE.instance[i])); + adev->reg_offset[MP1_HWIP][i] = (uint32_t *)(&(MP1_BASE.instance[i])); + adev->reg_offset[VCN_HWIP][i] = (uint32_t *)(&(UVD0_BASE.instance[i])); + adev->reg_offset[DF_HWIP][i] = (uint32_t *)(&(DF_BASE.instance[i])); + adev->reg_offset[DCE_HWIP][i] = (uint32_t *)(&(DMU_BASE.instance[i])); + adev->reg_offset[OSSSYS_HWIP][i] = (uint32_t *)(&(OSSSYS_BASE.instance[i])); + adev->reg_offset[SDMA0_HWIP][i] = (uint32_t *)(&(GC_BASE.instance[i])); + adev->reg_offset[SDMA1_HWIP][i] = (uint32_t *)(&(GC_BASE.instance[i])); + adev->reg_offset[SMUIO_HWIP][i] = (uint32_t *)(&(SMUIO_BASE.instance[i])); + adev->reg_offset[THM_HWIP][i] = (uint32_t *)(&(THM_BASE.instance[i])); + adev->reg_offset[CLK_HWIP][i] = (uint32_t *)(&(CLK_BASE.instance[i])); + } + return 0; +} diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c index ba73518f5cdf..72ca6538b2e4 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c @@ -1141,8 +1141,7 @@ static void dce_v10_0_program_watermarks(struct amdgpu_device *adev, /* save values for DPM */ amdgpu_crtc->line_time = line_time; - amdgpu_crtc->wm_high = latency_watermark_a; - amdgpu_crtc->wm_low = latency_watermark_b; + /* Save number of lines the linebuffer leads before the scanout */ amdgpu_crtc->lb_vblank_lead_lines = lb_vblank_lead_lines; } diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c deleted file mode 100644 index b01d88d078fa..000000000000 --- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c +++ /dev/null @@ -1,3818 +0,0 @@ -/* - * Copyright 2014 Advanced Micro Devices, Inc. - * - * 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, sublicense, - * 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 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 NONINFRINGEMENT. IN NO EVENT SHALL - * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) 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. - * - */ - -#include <drm/drm_edid.h> -#include <drm/drm_fourcc.h> -#include <drm/drm_modeset_helper.h> -#include <drm/drm_modeset_helper_vtables.h> -#include <drm/drm_vblank.h> - -#include "amdgpu.h" -#include "amdgpu_pm.h" -#include "amdgpu_i2c.h" -#include "vid.h" -#include "atom.h" -#include "amdgpu_atombios.h" -#include "atombios_crtc.h" -#include "atombios_encoders.h" -#include "amdgpu_pll.h" -#include "amdgpu_connectors.h" -#include "amdgpu_display.h" -#include "dce_v11_0.h" - -#include "dce/dce_11_0_d.h" -#include "dce/dce_11_0_sh_mask.h" -#include "dce/dce_11_0_enum.h" -#include "oss/oss_3_0_d.h" -#include "oss/oss_3_0_sh_mask.h" -#include "gmc/gmc_8_1_d.h" -#include "gmc/gmc_8_1_sh_mask.h" - -#include "ivsrcid/ivsrcid_vislands30.h" - -static void dce_v11_0_set_display_funcs(struct amdgpu_device *adev); -static void dce_v11_0_set_irq_funcs(struct amdgpu_device *adev); -static void dce_v11_0_hpd_int_ack(struct amdgpu_device *adev, int hpd); - -static const u32 crtc_offsets[] = -{ - CRTC0_REGISTER_OFFSET, - CRTC1_REGISTER_OFFSET, - CRTC2_REGISTER_OFFSET, - CRTC3_REGISTER_OFFSET, - CRTC4_REGISTER_OFFSET, - CRTC5_REGISTER_OFFSET, - CRTC6_REGISTER_OFFSET -}; - -static const u32 hpd_offsets[] = -{ - HPD0_REGISTER_OFFSET, - HPD1_REGISTER_OFFSET, - HPD2_REGISTER_OFFSET, - HPD3_REGISTER_OFFSET, - HPD4_REGISTER_OFFSET, - HPD5_REGISTER_OFFSET -}; - -static const uint32_t dig_offsets[] = { - DIG0_REGISTER_OFFSET, - DIG1_REGISTER_OFFSET, - DIG2_REGISTER_OFFSET, - DIG3_REGISTER_OFFSET, - DIG4_REGISTER_OFFSET, - DIG5_REGISTER_OFFSET, - DIG6_REGISTER_OFFSET, - DIG7_REGISTER_OFFSET, - DIG8_REGISTER_OFFSET -}; - -static const struct { - uint32_t reg; - uint32_t vblank; - uint32_t vline; - uint32_t hpd; - -} interrupt_status_offsets[] = { { - .reg = mmDISP_INTERRUPT_STATUS, - .vblank = DISP_INTERRUPT_STATUS__LB_D1_VBLANK_INTERRUPT_MASK, - .vline = DISP_INTERRUPT_STATUS__LB_D1_VLINE_INTERRUPT_MASK, - .hpd = DISP_INTERRUPT_STATUS__DC_HPD1_INTERRUPT_MASK -}, { - .reg = mmDISP_INTERRUPT_STATUS_CONTINUE, - .vblank = DISP_INTERRUPT_STATUS_CONTINUE__LB_D2_VBLANK_INTERRUPT_MASK, - .vline = DISP_INTERRUPT_STATUS_CONTINUE__LB_D2_VLINE_INTERRUPT_MASK, - .hpd = DISP_INTERRUPT_STATUS_CONTINUE__DC_HPD2_INTERRUPT_MASK -}, { - .reg = mmDISP_INTERRUPT_STATUS_CONTINUE2, - .vblank = DISP_INTERRUPT_STATUS_CONTINUE2__LB_D3_VBLANK_INTERRUPT_MASK, - .vline = DISP_INTERRUPT_STATUS_CONTINUE2__LB_D3_VLINE_INTERRUPT_MASK, - .hpd = DISP_INTERRUPT_STATUS_CONTINUE2__DC_HPD3_INTERRUPT_MASK -}, { - .reg = mmDISP_INTERRUPT_STATUS_CONTINUE3, - .vblank = DISP_INTERRUPT_STATUS_CONTINUE3__LB_D4_VBLANK_INTERRUPT_MASK, - .vline = DISP_INTERRUPT_STATUS_CONTINUE3__LB_D4_VLINE_INTERRUPT_MASK, - .hpd = DISP_INTERRUPT_STATUS_CONTINUE3__DC_HPD4_INTERRUPT_MASK -}, { - .reg = mmDISP_INTERRUPT_STATUS_CONTINUE4, - .vblank = DISP_INTERRUPT_STATUS_CONTINUE4__LB_D5_VBLANK_INTERRUPT_MASK, - .vline = DISP_INTERRUPT_STATUS_CONTINUE4__LB_D5_VLINE_INTERRUPT_MASK, - .hpd = DISP_INTERRUPT_STATUS_CONTINUE4__DC_HPD5_INTERRUPT_MASK -}, { - .reg = mmDISP_INTERRUPT_STATUS_CONTINUE5, - .vblank = DISP_INTERRUPT_STATUS_CONTINUE5__LB_D6_VBLANK_INTERRUPT_MASK, - .vline = DISP_INTERRUPT_STATUS_CONTINUE5__LB_D6_VLINE_INTERRUPT_MASK, - .hpd = DISP_INTERRUPT_STATUS_CONTINUE5__DC_HPD6_INTERRUPT_MASK -} }; - -static const u32 cz_golden_settings_a11[] = -{ - mmCRTC_DOUBLE_BUFFER_CONTROL, 0x00010101, 0x00010000, - mmFBC_MISC, 0x1f311fff, 0x14300000, -}; - -static const u32 cz_mgcg_cgcg_init[] = -{ - mmXDMA_CLOCK_GATING_CNTL, 0xffffffff, 0x00000100, - mmXDMA_MEM_POWER_CNTL, 0x00000101, 0x00000000, -}; - -static const u32 stoney_golden_settings_a11[] = -{ - mmCRTC_DOUBLE_BUFFER_CONTROL, 0x00010101, 0x00010000, - mmFBC_MISC, 0x1f311fff, 0x14302000, -}; - -static const u32 polaris11_golden_settings_a11[] = -{ - mmDCI_CLK_CNTL, 0x00000080, 0x00000000, - mmFBC_DEBUG_COMP, 0x000000f0, 0x00000070, - mmFBC_DEBUG1, 0xffffffff, 0x00000008, - mmFBC_MISC, 0x9f313fff, 0x14302008, - mmHDMI_CONTROL, 0x313f031f, 0x00000011, -}; - -static const u32 polaris10_golden_settings_a11[] = -{ - mmDCI_CLK_CNTL, 0x00000080, 0x00000000, - mmFBC_DEBUG_COMP, 0x000000f0, 0x00000070, - mmFBC_MISC, 0x9f313fff, 0x14302008, - mmHDMI_CONTROL, 0x313f031f, 0x00000011, -}; - -static void dce_v11_0_init_golden_registers(struct amdgpu_device *adev) -{ - switch (adev->asic_type) { - case CHIP_CARRIZO: - amdgpu_device_program_register_sequence(adev, - cz_mgcg_cgcg_init, - ARRAY_SIZE(cz_mgcg_cgcg_init)); - amdgpu_device_program_register_sequence(adev, - cz_golden_settings_a11, - ARRAY_SIZE(cz_golden_settings_a11)); - break; - case CHIP_STONEY: - amdgpu_device_program_register_sequence(adev, - stoney_golden_settings_a11, - ARRAY_SIZE(stoney_golden_settings_a11)); - break; - case CHIP_POLARIS11: - case CHIP_POLARIS12: - amdgpu_device_program_register_sequence(adev, - polaris11_golden_settings_a11, - ARRAY_SIZE(polaris11_golden_settings_a11)); - break; - case CHIP_POLARIS10: - case CHIP_VEGAM: - amdgpu_device_program_register_sequence(adev, - polaris10_golden_settings_a11, - ARRAY_SIZE(polaris10_golden_settings_a11)); - break; - default: - break; - } -} - -static u32 dce_v11_0_audio_endpt_rreg(struct amdgpu_device *adev, - u32 block_offset, u32 reg) -{ - unsigned long flags; - u32 r; - - spin_lock_irqsave(&adev->audio_endpt_idx_lock, flags); - WREG32(mmAZALIA_F0_CODEC_ENDPOINT_INDEX + block_offset, reg); - r = RREG32(mmAZALIA_F0_CODEC_ENDPOINT_DATA + block_offset); - spin_unlock_irqrestore(&adev->audio_endpt_idx_lock, flags); - - return r; -} - -static void dce_v11_0_audio_endpt_wreg(struct amdgpu_device *adev, - u32 block_offset, u32 reg, u32 v) -{ - unsigned long flags; - - spin_lock_irqsave(&adev->audio_endpt_idx_lock, flags); - WREG32(mmAZALIA_F0_CODEC_ENDPOINT_INDEX + block_offset, reg); - WREG32(mmAZALIA_F0_CODEC_ENDPOINT_DATA + block_offset, v); - spin_unlock_irqrestore(&adev->audio_endpt_idx_lock, flags); -} - -static u32 dce_v11_0_vblank_get_counter(struct amdgpu_device *adev, int crtc) -{ - if (crtc < 0 || crtc >= adev->mode_info.num_crtc) - return 0; - else - return RREG32(mmCRTC_STATUS_FRAME_COUNT + crtc_offsets[crtc]); -} - -static void dce_v11_0_pageflip_interrupt_init(struct amdgpu_device *adev) -{ - unsigned i; - - /* Enable pflip interrupts */ - for (i = 0; i < adev->mode_info.num_crtc; i++) - amdgpu_irq_get(adev, &adev->pageflip_irq, i); -} - -static void dce_v11_0_pageflip_interrupt_fini(struct amdgpu_device *adev) -{ - unsigned i; - - /* Disable pflip interrupts */ - for (i = 0; i < adev->mode_info.num_crtc; i++) - amdgpu_irq_put(adev, &adev->pageflip_irq, i); -} - -/** - * dce_v11_0_page_flip - pageflip callback. - * - * @adev: amdgpu_device pointer - * @crtc_id: crtc to cleanup pageflip on - * @crtc_base: new address of the crtc (GPU MC address) - * @async: asynchronous flip - * - * Triggers the actual pageflip by updating the primary - * surface base address. - */ -static void dce_v11_0_page_flip(struct amdgpu_device *adev, - int crtc_id, u64 crtc_base, bool async) -{ - struct amdgpu_crtc *amdgpu_crtc = adev->mode_info.crtcs[crtc_id]; - struct drm_framebuffer *fb = amdgpu_crtc->base.primary->fb; - u32 tmp; - - /* flip immediate for async, default is vsync */ - tmp = RREG32(mmGRPH_FLIP_CONTROL + amdgpu_crtc->crtc_offset); - tmp = REG_SET_FIELD(tmp, GRPH_FLIP_CONTROL, - GRPH_SURFACE_UPDATE_IMMEDIATE_EN, async ? 1 : 0); - WREG32(mmGRPH_FLIP_CONTROL + amdgpu_crtc->crtc_offset, tmp); - /* update pitch */ - WREG32(mmGRPH_PITCH + amdgpu_crtc->crtc_offset, - fb->pitches[0] / fb->format->cpp[0]); - /* update the scanout addresses */ - WREG32(mmGRPH_PRIMARY_SURFACE_ADDRESS_HIGH + amdgpu_crtc->crtc_offset, - upper_32_bits(crtc_base)); - /* writing to the low address triggers the update */ - WREG32(mmGRPH_PRIMARY_SURFACE_ADDRESS + amdgpu_crtc->crtc_offset, - lower_32_bits(crtc_base)); - /* post the write */ - RREG32(mmGRPH_PRIMARY_SURFACE_ADDRESS + amdgpu_crtc->crtc_offset); -} - -static int dce_v11_0_crtc_get_scanoutpos(struct amdgpu_device *adev, int crtc, - u32 *vbl, u32 *position) -{ - if ((crtc < 0) || (crtc >= adev->mode_info.num_crtc)) - return -EINVAL; - - *vbl = RREG32(mmCRTC_V_BLANK_START_END + crtc_offsets[crtc]); - *position = RREG32(mmCRTC_STATUS_POSITION + crtc_offsets[crtc]); - - return 0; -} - -/** - * dce_v11_0_hpd_sense - hpd sense callback. - * - * @adev: amdgpu_device pointer - * @hpd: hpd (hotplug detect) pin - * - * Checks if a digital monitor is connected (evergreen+). - * Returns true if connected, false if not connected. - */ -static bool dce_v11_0_hpd_sense(struct amdgpu_device *adev, - enum amdgpu_hpd_id hpd) -{ - bool connected = false; - - if (hpd >= adev->mode_info.num_hpd) - return connected; - - if (RREG32(mmDC_HPD_INT_STATUS + hpd_offsets[hpd]) & - DC_HPD_INT_STATUS__DC_HPD_SENSE_MASK) - connected = true; - - return connected; -} - -/** - * dce_v11_0_hpd_set_polarity - hpd set polarity callback. - * - * @adev: amdgpu_device pointer - * @hpd: hpd (hotplug detect) pin - * - * Set the polarity of the hpd pin (evergreen+). - */ -static void dce_v11_0_hpd_set_polarity(struct amdgpu_device *adev, - enum amdgpu_hpd_id hpd) -{ - u32 tmp; - bool connected = dce_v11_0_hpd_sense(adev, hpd); - - if (hpd >= adev->mode_info.num_hpd) - return; - - tmp = RREG32(mmDC_HPD_INT_CONTROL + hpd_offsets[hpd]); - if (connected) - tmp = REG_SET_FIELD(tmp, DC_HPD_INT_CONTROL, DC_HPD_INT_POLARITY, 0); - else - tmp = REG_SET_FIELD(tmp, DC_HPD_INT_CONTROL, DC_HPD_INT_POLARITY, 1); - WREG32(mmDC_HPD_INT_CONTROL + hpd_offsets[hpd], tmp); -} - -/** - * dce_v11_0_hpd_init - hpd setup callback. - * - * @adev: amdgpu_device pointer - * - * Setup the hpd pins used by the card (evergreen+). - * Enable the pin, set the polarity, and enable the hpd interrupts. - */ -static void dce_v11_0_hpd_init(struct amdgpu_device *adev) -{ - struct drm_device *dev = adev_to_drm(adev); - struct drm_connector *connector; - struct drm_connector_list_iter iter; - u32 tmp; - - drm_connector_list_iter_begin(dev, &iter); - drm_for_each_connector_iter(connector, &iter) { - struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector); - - if (amdgpu_connector->hpd.hpd >= adev->mode_info.num_hpd) - continue; - - if (connector->connector_type == DRM_MODE_CONNECTOR_eDP || - connector->connector_type == DRM_MODE_CONNECTOR_LVDS) { - /* don't try to enable hpd on eDP or LVDS avoid breaking the - * aux dp channel on imac and help (but not completely fix) - * https://bugzilla.redhat.com/show_bug.cgi?id=726143 - * also avoid interrupt storms during dpms. - */ - tmp = RREG32(mmDC_HPD_INT_CONTROL + hpd_offsets[amdgpu_connector->hpd.hpd]); - tmp = REG_SET_FIELD(tmp, DC_HPD_INT_CONTROL, DC_HPD_INT_EN, 0); - WREG32(mmDC_HPD_INT_CONTROL + hpd_offsets[amdgpu_connector->hpd.hpd], tmp); - continue; - } - - tmp = RREG32(mmDC_HPD_CONTROL + hpd_offsets[amdgpu_connector->hpd.hpd]); - tmp = REG_SET_FIELD(tmp, DC_HPD_CONTROL, DC_HPD_EN, 1); - WREG32(mmDC_HPD_CONTROL + hpd_offsets[amdgpu_connector->hpd.hpd], tmp); - - tmp = RREG32(mmDC_HPD_TOGGLE_FILT_CNTL + hpd_offsets[amdgpu_connector->hpd.hpd]); - tmp = REG_SET_FIELD(tmp, DC_HPD_TOGGLE_FILT_CNTL, - DC_HPD_CONNECT_INT_DELAY, - AMDGPU_HPD_CONNECT_INT_DELAY_IN_MS); - tmp = REG_SET_FIELD(tmp, DC_HPD_TOGGLE_FILT_CNTL, - DC_HPD_DISCONNECT_INT_DELAY, - AMDGPU_HPD_DISCONNECT_INT_DELAY_IN_MS); - WREG32(mmDC_HPD_TOGGLE_FILT_CNTL + hpd_offsets[amdgpu_connector->hpd.hpd], tmp); - - dce_v11_0_hpd_int_ack(adev, amdgpu_connector->hpd.hpd); - dce_v11_0_hpd_set_polarity(adev, amdgpu_connector->hpd.hpd); - amdgpu_irq_get(adev, &adev->hpd_irq, amdgpu_connector->hpd.hpd); - } - drm_connector_list_iter_end(&iter); -} - -/** - * dce_v11_0_hpd_fini - hpd tear down callback. - * - * @adev: amdgpu_device pointer - * - * Tear down the hpd pins used by the card (evergreen+). - * Disable the hpd interrupts. - */ -static void dce_v11_0_hpd_fini(struct amdgpu_device *adev) -{ - struct drm_device *dev = adev_to_drm(adev); - struct drm_connector *connector; - struct drm_connector_list_iter iter; - u32 tmp; - - drm_connector_list_iter_begin(dev, &iter); - drm_for_each_connector_iter(connector, &iter) { - struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector); - - if (amdgpu_connector->hpd.hpd >= adev->mode_info.num_hpd) - continue; - - tmp = RREG32(mmDC_HPD_CONTROL + hpd_offsets[amdgpu_connector->hpd.hpd]); - tmp = REG_SET_FIELD(tmp, DC_HPD_CONTROL, DC_HPD_EN, 0); - WREG32(mmDC_HPD_CONTROL + hpd_offsets[amdgpu_connector->hpd.hpd], tmp); - - amdgpu_irq_put(adev, &adev->hpd_irq, amdgpu_connector->hpd.hpd); - } - drm_connector_list_iter_end(&iter); -} - -static u32 dce_v11_0_hpd_get_gpio_reg(struct amdgpu_device *adev) -{ - return mmDC_GPIO_HPD_A; -} - -static bool dce_v11_0_is_display_hung(struct amdgpu_device *adev) -{ - u32 crtc_hung = 0; - u32 crtc_status[6]; - u32 i, j, tmp; - - for (i = 0; i < adev->mode_info.num_crtc; i++) { - tmp = RREG32(mmCRTC_CONTROL + crtc_offsets[i]); - if (REG_GET_FIELD(tmp, CRTC_CONTROL, CRTC_MASTER_EN)) { - crtc_status[i] = RREG32(mmCRTC_STATUS_HV_COUNT + crtc_offsets[i]); - crtc_hung |= (1 << i); - } - } - - for (j = 0; j < 10; j++) { - for (i = 0; i < adev->mode_info.num_crtc; i++) { - if (crtc_hung & (1 << i)) { - tmp = RREG32(mmCRTC_STATUS_HV_COUNT + crtc_offsets[i]); - if (tmp != crtc_status[i]) - crtc_hung &= ~(1 << i); - } - } - if (crtc_hung == 0) - return false; - udelay(100); - } - - return true; -} - -static void dce_v11_0_set_vga_render_state(struct amdgpu_device *adev, - bool render) -{ - u32 tmp; - - /* Lockout access through VGA aperture*/ - tmp = RREG32(mmVGA_HDP_CONTROL); - if (render) - tmp = REG_SET_FIELD(tmp, VGA_HDP_CONTROL, VGA_MEMORY_DISABLE, 0); - else - tmp = REG_SET_FIELD(tmp, VGA_HDP_CONTROL, VGA_MEMORY_DISABLE, 1); - WREG32(mmVGA_HDP_CONTROL, tmp); - - /* disable VGA render */ - tmp = RREG32(mmVGA_RENDER_CONTROL); - if (render) - tmp = REG_SET_FIELD(tmp, VGA_RENDER_CONTROL, VGA_VSTATUS_CNTL, 1); - else - tmp = REG_SET_FIELD(tmp, VGA_RENDER_CONTROL, VGA_VSTATUS_CNTL, 0); - WREG32(mmVGA_RENDER_CONTROL, tmp); -} - -static int dce_v11_0_get_num_crtc (struct amdgpu_device *adev) -{ - int num_crtc = 0; - - switch (adev->asic_type) { - case CHIP_CARRIZO: - num_crtc = 3; - break; - case CHIP_STONEY: - num_crtc = 2; - break; - case CHIP_POLARIS10: - case CHIP_VEGAM: - num_crtc = 6; - break; - case CHIP_POLARIS11: - case CHIP_POLARIS12: - num_crtc = 5; - break; - default: - num_crtc = 0; - } - return num_crtc; -} - -void dce_v11_0_disable_dce(struct amdgpu_device *adev) -{ - /*Disable VGA render and enabled crtc, if has DCE engine*/ - if (amdgpu_atombios_has_dce_engine_info(adev)) { - u32 tmp; - int crtc_enabled, i; - - dce_v11_0_set_vga_render_state(adev, false); - - /*Disable crtc*/ - for (i = 0; i < dce_v11_0_get_num_crtc(adev); i++) { - crtc_enabled = REG_GET_FIELD(RREG32(mmCRTC_CONTROL + crtc_offsets[i]), - CRTC_CONTROL, CRTC_MASTER_EN); - if (crtc_enabled) { - WREG32(mmCRTC_UPDATE_LOCK + crtc_offsets[i], 1); - tmp = RREG32(mmCRTC_CONTROL + crtc_offsets[i]); - tmp = REG_SET_FIELD(tmp, CRTC_CONTROL, CRTC_MASTER_EN, 0); - WREG32(mmCRTC_CONTROL + crtc_offsets[i], tmp); - WREG32(mmCRTC_UPDATE_LOCK + crtc_offsets[i], 0); - } - } - } -} - -static void dce_v11_0_program_fmt(struct drm_encoder *encoder) -{ - struct drm_device *dev = encoder->dev; - struct amdgpu_device *adev = drm_to_adev(dev); - struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder); - struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(encoder->crtc); - struct drm_connector *connector = amdgpu_get_connector_for_encoder(encoder); - int bpc = 0; - u32 tmp = 0; - enum amdgpu_connector_dither dither = AMDGPU_FMT_DITHER_DISABLE; - - if (connector) { - struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector); - bpc = amdgpu_connector_get_monitor_bpc(connector); - dither = amdgpu_connector->dither; - } - - /* LVDS/eDP FMT is set up by atom */ - if (amdgpu_encoder->devices & ATOM_DEVICE_LCD_SUPPORT) - return; - - /* not needed for analog */ - if ((amdgpu_encoder->encoder_id == ENCODER_OBJECT_ID_INTERNAL_KLDSCP_DAC1) || - (amdgpu_encoder->encoder_id == ENCODER_OBJECT_ID_INTERNAL_KLDSCP_DAC2)) - return; - - if (bpc == 0) - return; - - switch (bpc) { - case 6: - if (dither == AMDGPU_FMT_DITHER_ENABLE) { - /* XXX sort out optimal dither settings */ - tmp = REG_SET_FIELD(tmp, FMT_BIT_DEPTH_CONTROL, FMT_FRAME_RANDOM_ENABLE, 1); - tmp = REG_SET_FIELD(tmp, FMT_BIT_DEPTH_CONTROL, FMT_HIGHPASS_RANDOM_ENABLE, 1); - tmp = REG_SET_FIELD(tmp, FMT_BIT_DEPTH_CONTROL, FMT_SPATIAL_DITHER_EN, 1); - tmp = REG_SET_FIELD(tmp, FMT_BIT_DEPTH_CONTROL, FMT_SPATIAL_DITHER_DEPTH, 0); - } else { - tmp = REG_SET_FIELD(tmp, FMT_BIT_DEPTH_CONTROL, FMT_TRUNCATE_EN, 1); - tmp = REG_SET_FIELD(tmp, FMT_BIT_DEPTH_CONTROL, FMT_TRUNCATE_DEPTH, 0); - } - break; - case 8: - if (dither == AMDGPU_FMT_DITHER_ENABLE) { - /* XXX sort out optimal dither settings */ - tmp = REG_SET_FIELD(tmp, FMT_BIT_DEPTH_CONTROL, FMT_FRAME_RANDOM_ENABLE, 1); - tmp = REG_SET_FIELD(tmp, FMT_BIT_DEPTH_CONTROL, FMT_HIGHPASS_RANDOM_ENABLE, 1); - tmp = REG_SET_FIELD(tmp, FMT_BIT_DEPTH_CONTROL, FMT_RGB_RANDOM_ENABLE, 1); - tmp = REG_SET_FIELD(tmp, FMT_BIT_DEPTH_CONTROL, FMT_SPATIAL_DITHER_EN, 1); - tmp = REG_SET_FIELD(tmp, FMT_BIT_DEPTH_CONTROL, FMT_SPATIAL_DITHER_DEPTH, 1); - } else { - tmp = REG_SET_FIELD(tmp, FMT_BIT_DEPTH_CONTROL, FMT_TRUNCATE_EN, 1); - tmp = REG_SET_FIELD(tmp, FMT_BIT_DEPTH_CONTROL, FMT_TRUNCATE_DEPTH, 1); - } - break; - case 10: - if (dither == AMDGPU_FMT_DITHER_ENABLE) { - /* XXX sort out optimal dither settings */ - tmp = REG_SET_FIELD(tmp, FMT_BIT_DEPTH_CONTROL, FMT_FRAME_RANDOM_ENABLE, 1); - tmp = REG_SET_FIELD(tmp, FMT_BIT_DEPTH_CONTROL, FMT_HIGHPASS_RANDOM_ENABLE, 1); - tmp = REG_SET_FIELD(tmp, FMT_BIT_DEPTH_CONTROL, FMT_RGB_RANDOM_ENABLE, 1); - tmp = REG_SET_FIELD(tmp, FMT_BIT_DEPTH_CONTROL, FMT_SPATIAL_DITHER_EN, 1); - tmp = REG_SET_FIELD(tmp, FMT_BIT_DEPTH_CONTROL, FMT_SPATIAL_DITHER_DEPTH, 2); - } else { - tmp = REG_SET_FIELD(tmp, FMT_BIT_DEPTH_CONTROL, FMT_TRUNCATE_EN, 1); - tmp = REG_SET_FIELD(tmp, FMT_BIT_DEPTH_CONTROL, FMT_TRUNCATE_DEPTH, 2); - } - break; - default: - /* not needed */ - break; - } - - WREG32(mmFMT_BIT_DEPTH_CONTROL + amdgpu_crtc->crtc_offset, tmp); -} - - -/* display watermark setup */ -/** - * dce_v11_0_line_buffer_adjust - Set up the line buffer - * - * @adev: amdgpu_device pointer - * @amdgpu_crtc: the selected display controller - * @mode: the current display mode on the selected display - * controller - * - * Setup up the line buffer allocation for - * the selected display controller (CIK). - * Returns the line buffer size in pixels. - */ -static u32 dce_v11_0_line_buffer_adjust(struct amdgpu_device *adev, - struct amdgpu_crtc *amdgpu_crtc, - struct drm_display_mode *mode) -{ - u32 tmp, buffer_alloc, i, mem_cfg; - u32 pipe_offset = amdgpu_crtc->crtc_id; - /* - * Line Buffer Setup - * There are 6 line buffers, one for each display controllers. - * There are 3 partitions per LB. Select the number of partitions - * to enable based on the display width. For display widths larger - * than 4096, you need use to use 2 display controllers and combine - * them using the stereo blender. - */ - if (amdgpu_crtc->base.enabled && mode) { - if (mode->crtc_hdisplay < 1920) { - mem_cfg = 1; - buffer_alloc = 2; - } else if (mode->crtc_hdisplay < 2560) { - mem_cfg = 2; - buffer_alloc = 2; - } else if (mode->crtc_hdisplay < 4096) { - mem_cfg = 0; - buffer_alloc = (adev->flags & AMD_IS_APU) ? 2 : 4; - } else { - DRM_DEBUG_KMS("Mode too big for LB!\n"); - mem_cfg = 0; - buffer_alloc = (adev->flags & AMD_IS_APU) ? 2 : 4; - } - } else { - mem_cfg = 1; - buffer_alloc = 0; - } - - tmp = RREG32(mmLB_MEMORY_CTRL + amdgpu_crtc->crtc_offset); - tmp = REG_SET_FIELD(tmp, LB_MEMORY_CTRL, LB_MEMORY_CONFIG, mem_cfg); - WREG32(mmLB_MEMORY_CTRL + amdgpu_crtc->crtc_offset, tmp); - - tmp = RREG32(mmPIPE0_DMIF_BUFFER_CONTROL + pipe_offset); - tmp = REG_SET_FIELD(tmp, PIPE0_DMIF_BUFFER_CONTROL, DMIF_BUFFERS_ALLOCATED, buffer_alloc); - WREG32(mmPIPE0_DMIF_BUFFER_CONTROL + pipe_offset, tmp); - - for (i = 0; i < adev->usec_timeout; i++) { - tmp = RREG32(mmPIPE0_DMIF_BUFFER_CONTROL + pipe_offset); - if (REG_GET_FIELD(tmp, PIPE0_DMIF_BUFFER_CONTROL, DMIF_BUFFERS_ALLOCATION_COMPLETED)) - break; - udelay(1); - } - - if (amdgpu_crtc->base.enabled && mode) { - switch (mem_cfg) { - case 0: - default: - return 4096 * 2; - case 1: - return 1920 * 2; - case 2: - return 2560 * 2; - } - } - - /* controller not enabled, so no lb used */ - return 0; -} - -/** - * cik_get_number_of_dram_channels - get the number of dram channels - * - * @adev: amdgpu_device pointer - * - * Look up the number of video ram channels (CIK). - * Used for display watermark bandwidth calculations - * Returns the number of dram channels - */ -static u32 cik_get_number_of_dram_channels(struct amdgpu_device *adev) -{ - u32 tmp = RREG32(mmMC_SHARED_CHMAP); - - switch (REG_GET_FIELD(tmp, MC_SHARED_CHMAP, NOOFCHAN)) { - case 0: - default: - return 1; - case 1: - return 2; - case 2: - return 4; - case 3: - return 8; - case 4: - return 3; - case 5: - return 6; - case 6: - return 10; - case 7: - return 12; - case 8: - return 16; - } -} - -struct dce10_wm_params { - u32 dram_channels; /* number of dram channels */ - u32 yclk; /* bandwidth per dram data pin in kHz */ - u32 sclk; /* engine clock in kHz */ - u32 disp_clk; /* display clock in kHz */ - u32 src_width; /* viewport width */ - u32 active_time; /* active display time in ns */ - u32 blank_time; /* blank time in ns */ - bool interlaced; /* mode is interlaced */ - fixed20_12 vsc; /* vertical scale ratio */ - u32 num_heads; /* number of active crtcs */ - u32 bytes_per_pixel; /* bytes per pixel display + overlay */ - u32 lb_size; /* line buffer allocated to pipe */ - u32 vtaps; /* vertical scaler taps */ -}; - -/** - * dce_v11_0_dram_bandwidth - get the dram bandwidth - * - * @wm: watermark calculation data - * - * Calculate the raw dram bandwidth (CIK). - * Used for display watermark bandwidth calculations - * Returns the dram bandwidth in MBytes/s - */ -static u32 dce_v11_0_dram_bandwidth(struct dce10_wm_params *wm) -{ - /* Calculate raw DRAM Bandwidth */ - fixed20_12 dram_efficiency; /* 0.7 */ - fixed20_12 yclk, dram_channels, bandwidth; - fixed20_12 a; - - a.full = dfixed_const(1000); - yclk.full = dfixed_const(wm->yclk); - yclk.full = dfixed_div(yclk, a); - dram_channels.full = dfixed_const(wm->dram_channels * 4); - a.full = dfixed_const(10); - dram_efficiency.full = dfixed_const(7); - dram_efficiency.full = dfixed_div(dram_efficiency, a); - bandwidth.full = dfixed_mul(dram_channels, yclk); - bandwidth.full = dfixed_mul(bandwidth, dram_efficiency); - - return dfixed_trunc(bandwidth); -} - -/** - * dce_v11_0_dram_bandwidth_for_display - get the dram bandwidth for display - * - * @wm: watermark calculation data - * - * Calculate the dram bandwidth used for display (CIK). - * Used for display watermark bandwidth calculations - * Returns the dram bandwidth for display in MBytes/s - */ -static u32 dce_v11_0_dram_bandwidth_for_display(struct dce10_wm_params *wm) -{ - /* Calculate DRAM Bandwidth and the part allocated to display. */ - fixed20_12 disp_dram_allocation; /* 0.3 to 0.7 */ - fixed20_12 yclk, dram_channels, bandwidth; - fixed20_12 a; - - a.full = dfixed_const(1000); - yclk.full = dfixed_const(wm->yclk); - yclk.full = dfixed_div(yclk, a); - dram_channels.full = dfixed_const(wm->dram_channels * 4); - a.full = dfixed_const(10); - disp_dram_allocation.full = dfixed_const(3); /* XXX worse case value 0.3 */ - disp_dram_allocation.full = dfixed_div(disp_dram_allocation, a); - bandwidth.full = dfixed_mul(dram_channels, yclk); - bandwidth.full = dfixed_mul(bandwidth, disp_dram_allocation); - - return dfixed_trunc(bandwidth); -} - -/** - * dce_v11_0_data_return_bandwidth - get the data return bandwidth - * - * @wm: watermark calculation data - * - * Calculate the data return bandwidth used for display (CIK). - * Used for display watermark bandwidth calculations - * Returns the data return bandwidth in MBytes/s - */ -static u32 dce_v11_0_data_return_bandwidth(struct dce10_wm_params *wm) -{ - /* Calculate the display Data return Bandwidth */ - fixed20_12 return_efficiency; /* 0.8 */ - fixed20_12 sclk, bandwidth; - fixed20_12 a; - - a.full = dfixed_const(1000); - sclk.full = dfixed_const(wm->sclk); - sclk.full = dfixed_div(sclk, a); - a.full = dfixed_const(10); - return_efficiency.full = dfixed_const(8); - return_efficiency.full = dfixed_div(return_efficiency, a); - a.full = dfixed_const(32); - bandwidth.full = dfixed_mul(a, sclk); - bandwidth.full = dfixed_mul(bandwidth, return_efficiency); - - return dfixed_trunc(bandwidth); -} - -/** - * dce_v11_0_dmif_request_bandwidth - get the dmif bandwidth - * - * @wm: watermark calculation data - * - * Calculate the dmif bandwidth used for display (CIK). - * Used for display watermark bandwidth calculations - * Returns the dmif bandwidth in MBytes/s - */ -static u32 dce_v11_0_dmif_request_bandwidth(struct dce10_wm_params *wm) -{ - /* Calculate the DMIF Request Bandwidth */ - fixed20_12 disp_clk_request_efficiency; /* 0.8 */ - fixed20_12 disp_clk, bandwidth; - fixed20_12 a, b; - - a.full = dfixed_const(1000); - disp_clk.full = dfixed_const(wm->disp_clk); - disp_clk.full = dfixed_div(disp_clk, a); - a.full = dfixed_const(32); - b.full = dfixed_mul(a, disp_clk); - - a.full = dfixed_const(10); - disp_clk_request_efficiency.full = dfixed_const(8); - disp_clk_request_efficiency.full = dfixed_div(disp_clk_request_efficiency, a); - - bandwidth.full = dfixed_mul(b, disp_clk_request_efficiency); - - return dfixed_trunc(bandwidth); -} - -/** - * dce_v11_0_available_bandwidth - get the min available bandwidth - * - * @wm: watermark calculation data - * - * Calculate the min available bandwidth used for display (CIK). - * Used for display watermark bandwidth calculations - * Returns the min available bandwidth in MBytes/s - */ -static u32 dce_v11_0_available_bandwidth(struct dce10_wm_params *wm) -{ - /* Calculate the Available bandwidth. Display can use this temporarily but not in average. */ - u32 dram_bandwidth = dce_v11_0_dram_bandwidth(wm); - u32 data_return_bandwidth = dce_v11_0_data_return_bandwidth(wm); - u32 dmif_req_bandwidth = dce_v11_0_dmif_request_bandwidth(wm); - - return min(dram_bandwidth, min(data_return_bandwidth, dmif_req_bandwidth)); -} - -/** - * dce_v11_0_average_bandwidth - get the average available bandwidth - * - * @wm: watermark calculation data - * - * Calculate the average available bandwidth used for display (CIK). - * Used for display watermark bandwidth calculations - * Returns the average available bandwidth in MBytes/s - */ -static u32 dce_v11_0_average_bandwidth(struct dce10_wm_params *wm) -{ - /* Calculate the display mode Average Bandwidth - * DisplayMode should contain the source and destination dimensions, - * timing, etc. - */ - fixed20_12 bpp; - fixed20_12 line_time; - fixed20_12 src_width; - fixed20_12 bandwidth; - fixed20_12 a; - - a.full = dfixed_const(1000); - line_time.full = dfixed_const(wm->active_time + wm->blank_time); - line_time.full = dfixed_div(line_time, a); - bpp.full = dfixed_const(wm->bytes_per_pixel); - src_width.full = dfixed_const(wm->src_width); - bandwidth.full = dfixed_mul(src_width, bpp); - bandwidth.full = dfixed_mul(bandwidth, wm->vsc); - bandwidth.full = dfixed_div(bandwidth, line_time); - - return dfixed_trunc(bandwidth); -} - -/** - * dce_v11_0_latency_watermark - get the latency watermark - * - * @wm: watermark calculation data - * - * Calculate the latency watermark (CIK). - * Used for display watermark bandwidth calculations - * Returns the latency watermark in ns - */ -static u32 dce_v11_0_latency_watermark(struct dce10_wm_params *wm) -{ - /* First calculate the latency in ns */ - u32 mc_latency = 2000; /* 2000 ns. */ - u32 available_bandwidth = dce_v11_0_available_bandwidth(wm); - u32 worst_chunk_return_time = (512 * 8 * 1000) / available_bandwidth; - u32 cursor_line_pair_return_time = (128 * 4 * 1000) / available_bandwidth; - u32 dc_latency = 40000000 / wm->disp_clk; /* dc pipe latency */ - u32 other_heads_data_return_time = ((wm->num_heads + 1) * worst_chunk_return_time) + - (wm->num_heads * cursor_line_pair_return_time); - u32 latency = mc_latency + other_heads_data_return_time + dc_latency; - u32 max_src_lines_per_dst_line, lb_fill_bw, line_fill_time; - u32 tmp, dmif_size = 12288; - fixed20_12 a, b, c; - - if (wm->num_heads == 0) - return 0; - - a.full = dfixed_const(2); - b.full = dfixed_const(1); - if ((wm->vsc.full > a.full) || - ((wm->vsc.full > b.full) && (wm->vtaps >= 3)) || - (wm->vtaps >= 5) || - ((wm->vsc.full >= a.full) && wm->interlaced)) - max_src_lines_per_dst_line = 4; - else - max_src_lines_per_dst_line = 2; - - a.full = dfixed_const(available_bandwidth); - b.full = dfixed_const(wm->num_heads); - a.full = dfixed_div(a, b); - tmp = div_u64((u64) dmif_size * (u64) wm->disp_clk, mc_latency + 512); - tmp = min(dfixed_trunc(a), tmp); - - lb_fill_bw = min(tmp, wm->disp_clk * wm->bytes_per_pixel / 1000); - - a.full = dfixed_const(max_src_lines_per_dst_line * wm->src_width * wm->bytes_per_pixel); - b.full = dfixed_const(1000); - c.full = dfixed_const(lb_fill_bw); - b.full = dfixed_div(c, b); - a.full = dfixed_div(a, b); - line_fill_time = dfixed_trunc(a); - - if (line_fill_time < wm->active_time) - return latency; - else - return latency + (line_fill_time - wm->active_time); - -} - -/** - * dce_v11_0_average_bandwidth_vs_dram_bandwidth_for_display - check - * average and available dram bandwidth - * - * @wm: watermark calculation data - * - * Check if the display average bandwidth fits in the display - * dram bandwidth (CIK). - * Used for display watermark bandwidth calculations - * Returns true if the display fits, false if not. - */ -static bool dce_v11_0_average_bandwidth_vs_dram_bandwidth_for_display(struct dce10_wm_params *wm) -{ - if (dce_v11_0_average_bandwidth(wm) <= - (dce_v11_0_dram_bandwidth_for_display(wm) / wm->num_heads)) - return true; - else - return false; -} - -/** - * dce_v11_0_average_bandwidth_vs_available_bandwidth - check - * average and available bandwidth - * - * @wm: watermark calculation data - * - * Check if the display average bandwidth fits in the display - * available bandwidth (CIK). - * Used for display watermark bandwidth calculations - * Returns true if the display fits, false if not. - */ -static bool dce_v11_0_average_bandwidth_vs_available_bandwidth(struct dce10_wm_params *wm) -{ - if (dce_v11_0_average_bandwidth(wm) <= - (dce_v11_0_available_bandwidth(wm) / wm->num_heads)) - return true; - else - return false; -} - -/** - * dce_v11_0_check_latency_hiding - check latency hiding - * - * @wm: watermark calculation data - * - * Check latency hiding (CIK). - * Used for display watermark bandwidth calculations - * Returns true if the display fits, false if not. - */ -static bool dce_v11_0_check_latency_hiding(struct dce10_wm_params *wm) -{ - u32 lb_partitions = wm->lb_size / wm->src_width; - u32 line_time = wm->active_time + wm->blank_time; - u32 latency_tolerant_lines; - u32 latency_hiding; - fixed20_12 a; - - a.full = dfixed_const(1); - if (wm->vsc.full > a.full) - latency_tolerant_lines = 1; - else { - if (lb_partitions <= (wm->vtaps + 1)) - latency_tolerant_lines = 1; - else - latency_tolerant_lines = 2; - } - - latency_hiding = (latency_tolerant_lines * line_time + wm->blank_time); - - if (dce_v11_0_latency_watermark(wm) <= latency_hiding) - return true; - else - return false; -} - -/** - * dce_v11_0_program_watermarks - program display watermarks - * - * @adev: amdgpu_device pointer - * @amdgpu_crtc: the selected display controller - * @lb_size: line buffer size - * @num_heads: number of display controllers in use - * - * Calculate and program the display watermarks for the - * selected display controller (CIK). - */ -static void dce_v11_0_program_watermarks(struct amdgpu_device *adev, - struct amdgpu_crtc *amdgpu_crtc, - u32 lb_size, u32 num_heads) -{ - struct drm_display_mode *mode = &amdgpu_crtc->base.mode; - struct dce10_wm_params wm_low, wm_high; - u32 active_time; - u32 line_time = 0; - u32 latency_watermark_a = 0, latency_watermark_b = 0; - u32 tmp, wm_mask, lb_vblank_lead_lines = 0; - - if (amdgpu_crtc->base.enabled && num_heads && mode) { - active_time = (u32) div_u64((u64)mode->crtc_hdisplay * 1000000, - (u32)mode->clock); - line_time = (u32) div_u64((u64)mode->crtc_htotal * 1000000, - (u32)mode->clock); - line_time = min_t(u32, line_time, 65535); - - /* watermark for high clocks */ - if (adev->pm.dpm_enabled) { - wm_high.yclk = - amdgpu_dpm_get_mclk(adev, false) * 10; - wm_high.sclk = - amdgpu_dpm_get_sclk(adev, false) * 10; - } else { - wm_high.yclk = adev->pm.current_mclk * 10; - wm_high.sclk = adev->pm.current_sclk * 10; - } - - wm_high.disp_clk = mode->clock; - wm_high.src_width = mode->crtc_hdisplay; - wm_high.active_time = active_time; - wm_high.blank_time = line_time - wm_high.active_time; - wm_high.interlaced = false; - if (mode->flags & DRM_MODE_FLAG_INTERLACE) - wm_high.interlaced = true; - wm_high.vsc = amdgpu_crtc->vsc; - wm_high.vtaps = 1; - if (amdgpu_crtc->rmx_type != RMX_OFF) - wm_high.vtaps = 2; - wm_high.bytes_per_pixel = 4; /* XXX: get this from fb config */ - wm_high.lb_size = lb_size; - wm_high.dram_channels = cik_get_number_of_dram_channels(adev); - wm_high.num_heads = num_heads; - - /* set for high clocks */ - latency_watermark_a = min_t(u32, dce_v11_0_latency_watermark(&wm_high), 65535); - - /* possibly force display priority to high */ - /* should really do this at mode validation time... */ - if (!dce_v11_0_average_bandwidth_vs_dram_bandwidth_for_display(&wm_high) || - !dce_v11_0_average_bandwidth_vs_available_bandwidth(&wm_high) || - !dce_v11_0_check_latency_hiding(&wm_high) || - (adev->mode_info.disp_priority == 2)) { - DRM_DEBUG_KMS("force priority to high\n"); - } - - /* watermark for low clocks */ - if (adev->pm.dpm_enabled) { - wm_low.yclk = - amdgpu_dpm_get_mclk(adev, true) * 10; - wm_low.sclk = - amdgpu_dpm_get_sclk(adev, true) * 10; - } else { - wm_low.yclk = adev->pm.current_mclk * 10; - wm_low.sclk = adev->pm.current_sclk * 10; - } - - wm_low.disp_clk = mode->clock; - wm_low.src_width = mode->crtc_hdisplay; - wm_low.active_time = active_time; - wm_low.blank_time = line_time - wm_low.active_time; - wm_low.interlaced = false; - if (mode->flags & DRM_MODE_FLAG_INTERLACE) - wm_low.interlaced = true; - wm_low.vsc = amdgpu_crtc->vsc; - wm_low.vtaps = 1; - if (amdgpu_crtc->rmx_type != RMX_OFF) - wm_low.vtaps = 2; - wm_low.bytes_per_pixel = 4; /* XXX: get this from fb config */ - wm_low.lb_size = lb_size; - wm_low.dram_channels = cik_get_number_of_dram_channels(adev); - wm_low.num_heads = num_heads; - - /* set for low clocks */ - latency_watermark_b = min_t(u32, dce_v11_0_latency_watermark(&wm_low), 65535); - - /* possibly force display priority to high */ - /* should really do this at mode validation time... */ - if (!dce_v11_0_average_bandwidth_vs_dram_bandwidth_for_display(&wm_low) || - !dce_v11_0_average_bandwidth_vs_available_bandwidth(&wm_low) || - !dce_v11_0_check_latency_hiding(&wm_low) || - (adev->mode_info.disp_priority == 2)) { - DRM_DEBUG_KMS("force priority to high\n"); - } - lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode->crtc_hdisplay); - } - - /* select wm A */ - wm_mask = RREG32(mmDPG_WATERMARK_MASK_CONTROL + amdgpu_crtc->crtc_offset); - tmp = REG_SET_FIELD(wm_mask, DPG_WATERMARK_MASK_CONTROL, URGENCY_WATERMARK_MASK, 1); - WREG32(mmDPG_WATERMARK_MASK_CONTROL + amdgpu_crtc->crtc_offset, tmp); - tmp = RREG32(mmDPG_PIPE_URGENCY_CONTROL + amdgpu_crtc->crtc_offset); - tmp = REG_SET_FIELD(tmp, DPG_PIPE_URGENCY_CONTROL, URGENCY_LOW_WATERMARK, latency_watermark_a); - tmp = REG_SET_FIELD(tmp, DPG_PIPE_URGENCY_CONTROL, URGENCY_HIGH_WATERMARK, line_time); - WREG32(mmDPG_PIPE_URGENCY_CONTROL + amdgpu_crtc->crtc_offset, tmp); - /* select wm B */ - tmp = REG_SET_FIELD(wm_mask, DPG_WATERMARK_MASK_CONTROL, URGENCY_WATERMARK_MASK, 2); - WREG32(mmDPG_WATERMARK_MASK_CONTROL + amdgpu_crtc->crtc_offset, tmp); - tmp = RREG32(mmDPG_PIPE_URGENCY_CONTROL + amdgpu_crtc->crtc_offset); - tmp = REG_SET_FIELD(tmp, DPG_PIPE_URGENCY_CONTROL, URGENCY_LOW_WATERMARK, latency_watermark_b); - tmp = REG_SET_FIELD(tmp, DPG_PIPE_URGENCY_CONTROL, URGENCY_HIGH_WATERMARK, line_time); - WREG32(mmDPG_PIPE_URGENCY_CONTROL + amdgpu_crtc->crtc_offset, tmp); - /* restore original selection */ - WREG32(mmDPG_WATERMARK_MASK_CONTROL + amdgpu_crtc->crtc_offset, wm_mask); - - /* save values for DPM */ - amdgpu_crtc->line_time = line_time; - amdgpu_crtc->wm_high = latency_watermark_a; - amdgpu_crtc->wm_low = latency_watermark_b; - /* Save number of lines the linebuffer leads before the scanout */ - amdgpu_crtc->lb_vblank_lead_lines = lb_vblank_lead_lines; -} - -/** - * dce_v11_0_bandwidth_update - program display watermarks - * - * @adev: amdgpu_device pointer - * - * Calculate and program the display watermarks and line - * buffer allocation (CIK). - */ -static void dce_v11_0_bandwidth_update(struct amdgpu_device *adev) -{ - struct drm_display_mode *mode = NULL; - u32 num_heads = 0, lb_size; - int i; - - amdgpu_display_update_priority(adev); - - for (i = 0; i < adev->mode_info.num_crtc; i++) { - if (adev->mode_info.crtcs[i]->base.enabled) - num_heads++; - } - for (i = 0; i < adev->mode_info.num_crtc; i++) { - mode = &adev->mode_info.crtcs[i]->base.mode; - lb_size = dce_v11_0_line_buffer_adjust(adev, adev->mode_info.crtcs[i], mode); - dce_v11_0_program_watermarks(adev, adev->mode_info.crtcs[i], - lb_size, num_heads); - } -} - -static void dce_v11_0_audio_get_connected_pins(struct amdgpu_device *adev) -{ - int i; - u32 offset, tmp; - - for (i = 0; i < adev->mode_info.audio.num_pins; i++) { - offset = adev->mode_info.audio.pin[i].offset; - tmp = RREG32_AUDIO_ENDPT(offset, - ixAZALIA_F0_CODEC_PIN_CONTROL_RESPONSE_CONFIGURATION_DEFAULT); - if (((tmp & - AZALIA_F0_CODEC_PIN_CONTROL_RESPONSE_CONFIGURATION_DEFAULT__PORT_CONNECTIVITY_MASK) >> - AZALIA_F0_CODEC_PIN_CONTROL_RESPONSE_CONFIGURATION_DEFAULT__PORT_CONNECTIVITY__SHIFT) == 1) - adev->mode_info.audio.pin[i].connected = false; - else - adev->mode_info.audio.pin[i].connected = true; - } -} - -static struct amdgpu_audio_pin *dce_v11_0_audio_get_pin(struct amdgpu_device *adev) -{ - int i; - - dce_v11_0_audio_get_connected_pins(adev); - - for (i = 0; i < adev->mode_info.audio.num_pins; i++) { - if (adev->mode_info.audio.pin[i].connected) - return &adev->mode_info.audio.pin[i]; - } - DRM_ERROR("No connected audio pins found!\n"); - return NULL; -} - -static void dce_v11_0_afmt_audio_select_pin(struct drm_encoder *encoder) -{ - struct amdgpu_device *adev = drm_to_adev(encoder->dev); - struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder); - struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv; - u32 tmp; - - if (!dig || !dig->afmt || !dig->afmt->pin) - return; - - tmp = RREG32(mmAFMT_AUDIO_SRC_CONTROL + dig->afmt->offset); - tmp = REG_SET_FIELD(tmp, AFMT_AUDIO_SRC_CONTROL, AFMT_AUDIO_SRC_SELECT, dig->afmt->pin->id); - WREG32(mmAFMT_AUDIO_SRC_CONTROL + dig->afmt->offset, tmp); -} - -static void dce_v11_0_audio_write_latency_fields(struct drm_encoder *encoder, - struct drm_display_mode *mode) -{ - struct drm_device *dev = encoder->dev; - struct amdgpu_device *adev = drm_to_adev(dev); - struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder); - struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv; - struct drm_connector *connector; - struct drm_connector_list_iter iter; - struct amdgpu_connector *amdgpu_connector = NULL; - u32 tmp; - int interlace = 0; - - if (!dig || !dig->afmt || !dig->afmt->pin) - return; - - drm_connector_list_iter_begin(dev, &iter); - drm_for_each_connector_iter(connector, &iter) { - if (connector->encoder == encoder) { - amdgpu_connector = to_amdgpu_connector(connector); - break; - } - } - drm_connector_list_iter_end(&iter); - - if (!amdgpu_connector) { - DRM_ERROR("Couldn't find encoder's connector\n"); - return; - } - - if (mode->flags & DRM_MODE_FLAG_INTERLACE) - interlace = 1; - if (connector->latency_present[interlace]) { - tmp = REG_SET_FIELD(0, AZALIA_F0_CODEC_PIN_CONTROL_RESPONSE_LIPSYNC, - VIDEO_LIPSYNC, connector->video_latency[interlace]); - tmp = REG_SET_FIELD(0, AZALIA_F0_CODEC_PIN_CONTROL_RESPONSE_LIPSYNC, - AUDIO_LIPSYNC, connector->audio_latency[interlace]); - } else { - tmp = REG_SET_FIELD(0, AZALIA_F0_CODEC_PIN_CONTROL_RESPONSE_LIPSYNC, - VIDEO_LIPSYNC, 0); - tmp = REG_SET_FIELD(0, AZALIA_F0_CODEC_PIN_CONTROL_RESPONSE_LIPSYNC, - AUDIO_LIPSYNC, 0); - } - WREG32_AUDIO_ENDPT(dig->afmt->pin->offset, - ixAZALIA_F0_CODEC_PIN_CONTROL_RESPONSE_LIPSYNC, tmp); -} - -static void dce_v11_0_audio_write_speaker_allocation(struct drm_encoder *encoder) -{ - struct drm_device *dev = encoder->dev; - struct amdgpu_device *adev = drm_to_adev(dev); - struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder); - struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv; - struct drm_connector *connector; - struct drm_connector_list_iter iter; - struct amdgpu_connector *amdgpu_connector = NULL; - u32 tmp; - u8 *sadb = NULL; - int sad_count; - - if (!dig || !dig->afmt || !dig->afmt->pin) - return; - - drm_connector_list_iter_begin(dev, &iter); - drm_for_each_connector_iter(connector, &iter) { - if (connector->encoder == encoder) { - amdgpu_connector = to_amdgpu_connector(connector); - break; - } - } - drm_connector_list_iter_end(&iter); - - if (!amdgpu_connector) { - DRM_ERROR("Couldn't find encoder's connector\n"); - return; - } - - sad_count = drm_edid_to_speaker_allocation(amdgpu_connector->edid, &sadb); - if (sad_count < 0) { - DRM_ERROR("Couldn't read Speaker Allocation Data Block: %d\n", sad_count); - sad_count = 0; - } - - /* program the speaker allocation */ - tmp = RREG32_AUDIO_ENDPT(dig->afmt->pin->offset, - ixAZALIA_F0_CODEC_PIN_CONTROL_CHANNEL_SPEAKER); - tmp = REG_SET_FIELD(tmp, AZALIA_F0_CODEC_PIN_CONTROL_CHANNEL_SPEAKER, - DP_CONNECTION, 0); - /* set HDMI mode */ - tmp = REG_SET_FIELD(tmp, AZALIA_F0_CODEC_PIN_CONTROL_CHANNEL_SPEAKER, - HDMI_CONNECTION, 1); - if (sad_count) - tmp = REG_SET_FIELD(tmp, AZALIA_F0_CODEC_PIN_CONTROL_CHANNEL_SPEAKER, - SPEAKER_ALLOCATION, sadb[0]); - else - tmp = REG_SET_FIELD(tmp, AZALIA_F0_CODEC_PIN_CONTROL_CHANNEL_SPEAKER, - SPEAKER_ALLOCATION, 5); /* stereo */ - WREG32_AUDIO_ENDPT(dig->afmt->pin->offset, - ixAZALIA_F0_CODEC_PIN_CONTROL_CHANNEL_SPEAKER, tmp); - - kfree(sadb); -} - -static void dce_v11_0_audio_write_sad_regs(struct drm_encoder *encoder) -{ - struct drm_device *dev = encoder->dev; - struct amdgpu_device *adev = drm_to_adev(dev); - struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder); - struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv; - struct drm_connector *connector; - struct drm_connector_list_iter iter; - struct amdgpu_connector *amdgpu_connector = NULL; - struct cea_sad *sads; - int i, sad_count; - - static const u16 eld_reg_to_type[][2] = { - { ixAZALIA_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR0, HDMI_AUDIO_CODING_TYPE_PCM }, - { ixAZALIA_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR1, HDMI_AUDIO_CODING_TYPE_AC3 }, - { ixAZALIA_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR2, HDMI_AUDIO_CODING_TYPE_MPEG1 }, - { ixAZALIA_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR3, HDMI_AUDIO_CODING_TYPE_MP3 }, - { ixAZALIA_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR4, HDMI_AUDIO_CODING_TYPE_MPEG2 }, - { ixAZALIA_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR5, HDMI_AUDIO_CODING_TYPE_AAC_LC }, - { ixAZALIA_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR6, HDMI_AUDIO_CODING_TYPE_DTS }, - { ixAZALIA_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR7, HDMI_AUDIO_CODING_TYPE_ATRAC }, - { ixAZALIA_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR9, HDMI_AUDIO_CODING_TYPE_EAC3 }, - { ixAZALIA_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR10, HDMI_AUDIO_CODING_TYPE_DTS_HD }, - { ixAZALIA_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR11, HDMI_AUDIO_CODING_TYPE_MLP }, - { ixAZALIA_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR13, HDMI_AUDIO_CODING_TYPE_WMA_PRO }, - }; - - if (!dig || !dig->afmt || !dig->afmt->pin) - return; - - drm_connector_list_iter_begin(dev, &iter); - drm_for_each_connector_iter(connector, &iter) { - if (connector->encoder == encoder) { - amdgpu_connector = to_amdgpu_connector(connector); - break; - } - } - drm_connector_list_iter_end(&iter); - - if (!amdgpu_connector) { - DRM_ERROR("Couldn't find encoder's connector\n"); - return; - } - - sad_count = drm_edid_to_sad(amdgpu_connector->edid, &sads); - if (sad_count < 0) - DRM_ERROR("Couldn't read SADs: %d\n", sad_count); - if (sad_count <= 0) - return; - BUG_ON(!sads); - - for (i = 0; i < ARRAY_SIZE(eld_reg_to_type); i++) { - u32 tmp = 0; - u8 stereo_freqs = 0; - int max_channels = -1; - int j; - - for (j = 0; j < sad_count; j++) { - struct cea_sad *sad = &sads[j]; - - if (sad->format == eld_reg_to_type[i][1]) { - if (sad->channels > max_channels) { - tmp = REG_SET_FIELD(tmp, AZALIA_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR0, - MAX_CHANNELS, sad->channels); - tmp = REG_SET_FIELD(tmp, AZALIA_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR0, - DESCRIPTOR_BYTE_2, sad->byte2); - tmp = REG_SET_FIELD(tmp, AZALIA_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR0, - SUPPORTED_FREQUENCIES, sad->freq); - max_channels = sad->channels; - } - - if (sad->format == HDMI_AUDIO_CODING_TYPE_PCM) - stereo_freqs |= sad->freq; - else - break; - } - } - - tmp = REG_SET_FIELD(tmp, AZALIA_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR0, - SUPPORTED_FREQUENCIES_STEREO, stereo_freqs); - WREG32_AUDIO_ENDPT(dig->afmt->pin->offset, eld_reg_to_type[i][0], tmp); - } - - kfree(sads); -} - -static void dce_v11_0_audio_enable(struct amdgpu_device *adev, - struct amdgpu_audio_pin *pin, - bool enable) -{ - if (!pin) - return; - - WREG32_AUDIO_ENDPT(pin->offset, ixAZALIA_F0_CODEC_PIN_CONTROL_HOT_PLUG_CONTROL, - enable ? AZALIA_F0_CODEC_PIN_CONTROL_HOT_PLUG_CONTROL__AUDIO_ENABLED_MASK : 0); -} - -static const u32 pin_offsets[] = -{ - AUD0_REGISTER_OFFSET, - AUD1_REGISTER_OFFSET, - AUD2_REGISTER_OFFSET, - AUD3_REGISTER_OFFSET, - AUD4_REGISTER_OFFSET, - AUD5_REGISTER_OFFSET, - AUD6_REGISTER_OFFSET, - AUD7_REGISTER_OFFSET, -}; - -static int dce_v11_0_audio_init(struct amdgpu_device *adev) -{ - int i; - - if (!amdgpu_audio) - return 0; - - adev->mode_info.audio.enabled = true; - - switch (adev->asic_type) { - case CHIP_CARRIZO: - case CHIP_STONEY: - adev->mode_info.audio.num_pins = 7; - break; - case CHIP_POLARIS10: - case CHIP_VEGAM: - adev->mode_info.audio.num_pins = 8; - break; - case CHIP_POLARIS11: - case CHIP_POLARIS12: - adev->mode_info.audio.num_pins = 6; - break; - default: - return -EINVAL; - } - - for (i = 0; i < adev->mode_info.audio.num_pins; i++) { - adev->mode_info.audio.pin[i].channels = -1; - adev->mode_info.audio.pin[i].rate = -1; - adev->mode_info.audio.pin[i].bits_per_sample = -1; - adev->mode_info.audio.pin[i].status_bits = 0; - adev->mode_info.audio.pin[i].category_code = 0; - adev->mode_info.audio.pin[i].connected = false; - adev->mode_info.audio.pin[i].offset = pin_offsets[i]; - adev->mode_info.audio.pin[i].id = i; - /* disable audio. it will be set up later */ - /* XXX remove once we switch to ip funcs */ - dce_v11_0_audio_enable(adev, &adev->mode_info.audio.pin[i], false); - } - - return 0; -} - -static void dce_v11_0_audio_fini(struct amdgpu_device *adev) -{ - if (!amdgpu_audio) - return; - - if (!adev->mode_info.audio.enabled) - return; - - adev->mode_info.audio.enabled = false; -} - -/* - * update the N and CTS parameters for a given pixel clock rate - */ -static void dce_v11_0_afmt_update_ACR(struct drm_encoder *encoder, uint32_t clock) -{ - struct drm_device *dev = encoder->dev; - struct amdgpu_device *adev = drm_to_adev(dev); - struct amdgpu_afmt_acr acr = amdgpu_afmt_acr(clock); - struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder); - struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv; - u32 tmp; - - tmp = RREG32(mmHDMI_ACR_32_0 + dig->afmt->offset); - tmp = REG_SET_FIELD(tmp, HDMI_ACR_32_0, HDMI_ACR_CTS_32, acr.cts_32khz); - WREG32(mmHDMI_ACR_32_0 + dig->afmt->offset, tmp); - tmp = RREG32(mmHDMI_ACR_32_1 + dig->afmt->offset); - tmp = REG_SET_FIELD(tmp, HDMI_ACR_32_1, HDMI_ACR_N_32, acr.n_32khz); - WREG32(mmHDMI_ACR_32_1 + dig->afmt->offset, tmp); - - tmp = RREG32(mmHDMI_ACR_44_0 + dig->afmt->offset); - tmp = REG_SET_FIELD(tmp, HDMI_ACR_44_0, HDMI_ACR_CTS_44, acr.cts_44_1khz); - WREG32(mmHDMI_ACR_44_0 + dig->afmt->offset, tmp); - tmp = RREG32(mmHDMI_ACR_44_1 + dig->afmt->offset); - tmp = REG_SET_FIELD(tmp, HDMI_ACR_44_1, HDMI_ACR_N_44, acr.n_44_1khz); - WREG32(mmHDMI_ACR_44_1 + dig->afmt->offset, tmp); - - tmp = RREG32(mmHDMI_ACR_48_0 + dig->afmt->offset); - tmp = REG_SET_FIELD(tmp, HDMI_ACR_48_0, HDMI_ACR_CTS_48, acr.cts_48khz); - WREG32(mmHDMI_ACR_48_0 + dig->afmt->offset, tmp); - tmp = RREG32(mmHDMI_ACR_48_1 + dig->afmt->offset); - tmp = REG_SET_FIELD(tmp, HDMI_ACR_48_1, HDMI_ACR_N_48, acr.n_48khz); - WREG32(mmHDMI_ACR_48_1 + dig->afmt->offset, tmp); - -} - -/* - * build a HDMI Video Info Frame - */ -static void dce_v11_0_afmt_update_avi_infoframe(struct drm_encoder *encoder, - void *buffer, size_t size) -{ - struct drm_device *dev = encoder->dev; - struct amdgpu_device *adev = drm_to_adev(dev); - struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder); - struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv; - uint8_t *frame = buffer + 3; - uint8_t *header = buffer; - - WREG32(mmAFMT_AVI_INFO0 + dig->afmt->offset, - frame[0x0] | (frame[0x1] << 8) | (frame[0x2] << 16) | (frame[0x3] << 24)); - WREG32(mmAFMT_AVI_INFO1 + dig->afmt->offset, - frame[0x4] | (frame[0x5] << 8) | (frame[0x6] << 16) | (frame[0x7] << 24)); - WREG32(mmAFMT_AVI_INFO2 + dig->afmt->offset, - frame[0x8] | (frame[0x9] << 8) | (frame[0xA] << 16) | (frame[0xB] << 24)); - WREG32(mmAFMT_AVI_INFO3 + dig->afmt->offset, - frame[0xC] | (frame[0xD] << 8) | (header[1] << 24)); -} - -static void dce_v11_0_audio_set_dto(struct drm_encoder *encoder, u32 clock) -{ - struct drm_device *dev = encoder->dev; - struct amdgpu_device *adev = drm_to_adev(dev); - struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder); - struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv; - struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(encoder->crtc); - u32 dto_phase = 24 * 1000; - u32 dto_modulo = clock; - u32 tmp; - - if (!dig || !dig->afmt) - return; - - /* XXX two dtos; generally use dto0 for hdmi */ - /* Express [24MHz / target pixel clock] as an exact rational - * number (coefficient of two integer numbers. DCCG_AUDIO_DTOx_PHASE - * is the numerator, DCCG_AUDIO_DTOx_MODULE is the denominator - */ - tmp = RREG32(mmDCCG_AUDIO_DTO_SOURCE); - tmp = REG_SET_FIELD(tmp, DCCG_AUDIO_DTO_SOURCE, DCCG_AUDIO_DTO0_SOURCE_SEL, - amdgpu_crtc->crtc_id); - WREG32(mmDCCG_AUDIO_DTO_SOURCE, tmp); - WREG32(mmDCCG_AUDIO_DTO0_PHASE, dto_phase); - WREG32(mmDCCG_AUDIO_DTO0_MODULE, dto_modulo); -} - -/* - * update the info frames with the data from the current display mode - */ -static void dce_v11_0_afmt_setmode(struct drm_encoder *encoder, - struct drm_display_mode *mode) -{ - struct drm_device *dev = encoder->dev; - struct amdgpu_device *adev = drm_to_adev(dev); - struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder); - struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv; - struct drm_connector *connector = amdgpu_get_connector_for_encoder(encoder); - u8 buffer[HDMI_INFOFRAME_HEADER_SIZE + HDMI_AVI_INFOFRAME_SIZE]; - struct hdmi_avi_infoframe frame; - ssize_t err; - u32 tmp; - int bpc = 8; - - if (!dig || !dig->afmt) - return; - - /* Silent, r600_hdmi_enable will raise WARN for us */ - if (!dig->afmt->enabled) - return; - - /* hdmi deep color mode general control packets setup, if bpc > 8 */ - if (encoder->crtc) { - struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(encoder->crtc); - bpc = amdgpu_crtc->bpc; - } - - /* disable audio prior to setting up hw */ - dig->afmt->pin = dce_v11_0_audio_get_pin(adev); - dce_v11_0_audio_enable(adev, dig->afmt->pin, false); - - dce_v11_0_audio_set_dto(encoder, mode->clock); - - tmp = RREG32(mmHDMI_VBI_PACKET_CONTROL + dig->afmt->offset); - tmp = REG_SET_FIELD(tmp, HDMI_VBI_PACKET_CONTROL, HDMI_NULL_SEND, 1); - WREG32(mmHDMI_VBI_PACKET_CONTROL + dig->afmt->offset, tmp); /* send null packets when required */ - - WREG32(mmAFMT_AUDIO_CRC_CONTROL + dig->afmt->offset, 0x1000); - - tmp = RREG32(mmHDMI_CONTROL + dig->afmt->offset); - switch (bpc) { - case 0: - case 6: - case 8: - case 16: - default: - tmp = REG_SET_FIELD(tmp, HDMI_CONTROL, HDMI_DEEP_COLOR_ENABLE, 0); - tmp = REG_SET_FIELD(tmp, HDMI_CONTROL, HDMI_DEEP_COLOR_DEPTH, 0); - DRM_DEBUG("%s: Disabling hdmi deep color for %d bpc.\n", - connector->name, bpc); - break; - case 10: - tmp = REG_SET_FIELD(tmp, HDMI_CONTROL, HDMI_DEEP_COLOR_ENABLE, 1); - tmp = REG_SET_FIELD(tmp, HDMI_CONTROL, HDMI_DEEP_COLOR_DEPTH, 1); - DRM_DEBUG("%s: Enabling hdmi deep color 30 for 10 bpc.\n", - connector->name); - break; - case 12: - tmp = REG_SET_FIELD(tmp, HDMI_CONTROL, HDMI_DEEP_COLOR_ENABLE, 1); - tmp = REG_SET_FIELD(tmp, HDMI_CONTROL, HDMI_DEEP_COLOR_DEPTH, 2); - DRM_DEBUG("%s: Enabling hdmi deep color 36 for 12 bpc.\n", - connector->name); - break; - } - WREG32(mmHDMI_CONTROL + dig->afmt->offset, tmp); - - tmp = RREG32(mmHDMI_VBI_PACKET_CONTROL + dig->afmt->offset); - tmp = REG_SET_FIELD(tmp, HDMI_VBI_PACKET_CONTROL, HDMI_NULL_SEND, 1); /* send null packets when required */ - tmp = REG_SET_FIELD(tmp, HDMI_VBI_PACKET_CONTROL, HDMI_GC_SEND, 1); /* send general control packets */ - tmp = REG_SET_FIELD(tmp, HDMI_VBI_PACKET_CONTROL, HDMI_GC_CONT, 1); /* send general control packets every frame */ - WREG32(mmHDMI_VBI_PACKET_CONTROL + dig->afmt->offset, tmp); - - tmp = RREG32(mmHDMI_INFOFRAME_CONTROL0 + dig->afmt->offset); - /* enable audio info frames (frames won't be set until audio is enabled) */ - tmp = REG_SET_FIELD(tmp, HDMI_INFOFRAME_CONTROL0, HDMI_AUDIO_INFO_SEND, 1); - /* required for audio info values to be updated */ - tmp = REG_SET_FIELD(tmp, HDMI_INFOFRAME_CONTROL0, HDMI_AUDIO_INFO_CONT, 1); - WREG32(mmHDMI_INFOFRAME_CONTROL0 + dig->afmt->offset, tmp); - - tmp = RREG32(mmAFMT_INFOFRAME_CONTROL0 + dig->afmt->offset); - /* required for audio info values to be updated */ - tmp = REG_SET_FIELD(tmp, AFMT_INFOFRAME_CONTROL0, AFMT_AUDIO_INFO_UPDATE, 1); - WREG32(mmAFMT_INFOFRAME_CONTROL0 + dig->afmt->offset, tmp); - - tmp = RREG32(mmHDMI_INFOFRAME_CONTROL1 + dig->afmt->offset); - /* anything other than 0 */ - tmp = REG_SET_FIELD(tmp, HDMI_INFOFRAME_CONTROL1, HDMI_AUDIO_INFO_LINE, 2); - WREG32(mmHDMI_INFOFRAME_CONTROL1 + dig->afmt->offset, tmp); - - WREG32(mmHDMI_GC + dig->afmt->offset, 0); /* unset HDMI_GC_AVMUTE */ - - tmp = RREG32(mmHDMI_AUDIO_PACKET_CONTROL + dig->afmt->offset); - /* set the default audio delay */ - tmp = REG_SET_FIELD(tmp, HDMI_AUDIO_PACKET_CONTROL, HDMI_AUDIO_DELAY_EN, 1); - /* should be suffient for all audio modes and small enough for all hblanks */ - tmp = REG_SET_FIELD(tmp, HDMI_AUDIO_PACKET_CONTROL, HDMI_AUDIO_PACKETS_PER_LINE, 3); - WREG32(mmHDMI_AUDIO_PACKET_CONTROL + dig->afmt->offset, tmp); - - tmp = RREG32(mmAFMT_AUDIO_PACKET_CONTROL + dig->afmt->offset); - /* allow 60958 channel status fields to be updated */ - tmp = REG_SET_FIELD(tmp, AFMT_AUDIO_PACKET_CONTROL, AFMT_60958_CS_UPDATE, 1); - WREG32(mmAFMT_AUDIO_PACKET_CONTROL + dig->afmt->offset, tmp); - - tmp = RREG32(mmHDMI_ACR_PACKET_CONTROL + dig->afmt->offset); - if (bpc > 8) - /* clear SW CTS value */ - tmp = REG_SET_FIELD(tmp, HDMI_ACR_PACKET_CONTROL, HDMI_ACR_SOURCE, 0); - else - /* select SW CTS value */ - tmp = REG_SET_FIELD(tmp, HDMI_ACR_PACKET_CONTROL, HDMI_ACR_SOURCE, 1); - /* allow hw to sent ACR packets when required */ - tmp = REG_SET_FIELD(tmp, HDMI_ACR_PACKET_CONTROL, HDMI_ACR_AUTO_SEND, 1); - WREG32(mmHDMI_ACR_PACKET_CONTROL + dig->afmt->offset, tmp); - - dce_v11_0_afmt_update_ACR(encoder, mode->clock); - - tmp = RREG32(mmAFMT_60958_0 + dig->afmt->offset); - tmp = REG_SET_FIELD(tmp, AFMT_60958_0, AFMT_60958_CS_CHANNEL_NUMBER_L, 1); - WREG32(mmAFMT_60958_0 + dig->afmt->offset, tmp); - - tmp = RREG32(mmAFMT_60958_1 + dig->afmt->offset); - tmp = REG_SET_FIELD(tmp, AFMT_60958_1, AFMT_60958_CS_CHANNEL_NUMBER_R, 2); - WREG32(mmAFMT_60958_1 + dig->afmt->offset, tmp); - - tmp = RREG32(mmAFMT_60958_2 + dig->afmt->offset); - tmp = REG_SET_FIELD(tmp, AFMT_60958_2, AFMT_60958_CS_CHANNEL_NUMBER_2, 3); - tmp = REG_SET_FIELD(tmp, AFMT_60958_2, AFMT_60958_CS_CHANNEL_NUMBER_3, 4); - tmp = REG_SET_FIELD(tmp, AFMT_60958_2, AFMT_60958_CS_CHANNEL_NUMBER_4, 5); - tmp = REG_SET_FIELD(tmp, AFMT_60958_2, AFMT_60958_CS_CHANNEL_NUMBER_5, 6); - tmp = REG_SET_FIELD(tmp, AFMT_60958_2, AFMT_60958_CS_CHANNEL_NUMBER_6, 7); - tmp = REG_SET_FIELD(tmp, AFMT_60958_2, AFMT_60958_CS_CHANNEL_NUMBER_7, 8); - WREG32(mmAFMT_60958_2 + dig->afmt->offset, tmp); - - dce_v11_0_audio_write_speaker_allocation(encoder); - - WREG32(mmAFMT_AUDIO_PACKET_CONTROL2 + dig->afmt->offset, - (0xff << AFMT_AUDIO_PACKET_CONTROL2__AFMT_AUDIO_CHANNEL_ENABLE__SHIFT)); - - dce_v11_0_afmt_audio_select_pin(encoder); - dce_v11_0_audio_write_sad_regs(encoder); - dce_v11_0_audio_write_latency_fields(encoder, mode); - - err = drm_hdmi_avi_infoframe_from_display_mode(&frame, connector, mode); - if (err < 0) { - DRM_ERROR("failed to setup AVI infoframe: %zd\n", err); - return; - } - - err = hdmi_avi_infoframe_pack(&frame, buffer, sizeof(buffer)); - if (err < 0) { - DRM_ERROR("failed to pack AVI infoframe: %zd\n", err); - return; - } - - dce_v11_0_afmt_update_avi_infoframe(encoder, buffer, sizeof(buffer)); - - tmp = RREG32(mmHDMI_INFOFRAME_CONTROL0 + dig->afmt->offset); - /* enable AVI info frames */ - tmp = REG_SET_FIELD(tmp, HDMI_INFOFRAME_CONTROL0, HDMI_AVI_INFO_SEND, 1); - /* required for audio info values to be updated */ - tmp = REG_SET_FIELD(tmp, HDMI_INFOFRAME_CONTROL0, HDMI_AVI_INFO_CONT, 1); - WREG32(mmHDMI_INFOFRAME_CONTROL0 + dig->afmt->offset, tmp); - - tmp = RREG32(mmHDMI_INFOFRAME_CONTROL1 + dig->afmt->offset); - tmp = REG_SET_FIELD(tmp, HDMI_INFOFRAME_CONTROL1, HDMI_AVI_INFO_LINE, 2); - WREG32(mmHDMI_INFOFRAME_CONTROL1 + dig->afmt->offset, tmp); - - tmp = RREG32(mmAFMT_AUDIO_PACKET_CONTROL + dig->afmt->offset); - /* send audio packets */ - tmp = REG_SET_FIELD(tmp, AFMT_AUDIO_PACKET_CONTROL, AFMT_AUDIO_SAMPLE_SEND, 1); - WREG32(mmAFMT_AUDIO_PACKET_CONTROL + dig->afmt->offset, tmp); - - WREG32(mmAFMT_RAMP_CONTROL0 + dig->afmt->offset, 0x00FFFFFF); - WREG32(mmAFMT_RAMP_CONTROL1 + dig->afmt->offset, 0x007FFFFF); - WREG32(mmAFMT_RAMP_CONTROL2 + dig->afmt->offset, 0x00000001); - WREG32(mmAFMT_RAMP_CONTROL3 + dig->afmt->offset, 0x00000001); - - /* enable audio after to setting up hw */ - dce_v11_0_audio_enable(adev, dig->afmt->pin, true); -} - -static void dce_v11_0_afmt_enable(struct drm_encoder *encoder, bool enable) -{ - struct drm_device *dev = encoder->dev; - struct amdgpu_device *adev = drm_to_adev(dev); - struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder); - struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv; - - if (!dig || !dig->afmt) - return; - - /* Silent, r600_hdmi_enable will raise WARN for us */ - if (enable && dig->afmt->enabled) - return; - if (!enable && !dig->afmt->enabled) - return; - - if (!enable && dig->afmt->pin) { - dce_v11_0_audio_enable(adev, dig->afmt->pin, false); - dig->afmt->pin = NULL; - } - - dig->afmt->enabled = enable; - - DRM_DEBUG("%sabling AFMT interface @ 0x%04X for encoder 0x%x\n", - enable ? "En" : "Dis", dig->afmt->offset, amdgpu_encoder->encoder_id); -} - -static int dce_v11_0_afmt_init(struct amdgpu_device *adev) -{ - int i; - - for (i = 0; i < adev->mode_info.num_dig; i++) - adev->mode_info.afmt[i] = NULL; - - /* DCE11 has audio blocks tied to DIG encoders */ - for (i = 0; i < adev->mode_info.num_dig; i++) { - adev->mode_info.afmt[i] = kzalloc(sizeof(struct amdgpu_afmt), GFP_KERNEL); - if (adev->mode_info.afmt[i]) { - adev->mode_info.afmt[i]->offset = dig_offsets[i]; - adev->mode_info.afmt[i]->id = i; - } else { - int j; - for (j = 0; j < i; j++) { - kfree(adev->mode_info.afmt[j]); - adev->mode_info.afmt[j] = NULL; - } - return -ENOMEM; - } - } - return 0; -} - -static void dce_v11_0_afmt_fini(struct amdgpu_device *adev) -{ - int i; - - for (i = 0; i < adev->mode_info.num_dig; i++) { - kfree(adev->mode_info.afmt[i]); - adev->mode_info.afmt[i] = NULL; - } -} - -static const u32 vga_control_regs[6] = -{ - mmD1VGA_CONTROL, - mmD2VGA_CONTROL, - mmD3VGA_CONTROL, - mmD4VGA_CONTROL, - mmD5VGA_CONTROL, - mmD6VGA_CONTROL, -}; - -static void dce_v11_0_vga_enable(struct drm_crtc *crtc, bool enable) -{ - struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); - struct drm_device *dev = crtc->dev; - struct amdgpu_device *adev = drm_to_adev(dev); - u32 vga_control; - - vga_control = RREG32(vga_control_regs[amdgpu_crtc->crtc_id]) & ~1; - if (enable) - WREG32(vga_control_regs[amdgpu_crtc->crtc_id], vga_control | 1); - else - WREG32(vga_control_regs[amdgpu_crtc->crtc_id], vga_control); -} - -static void dce_v11_0_grph_enable(struct drm_crtc *crtc, bool enable) -{ - struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); - struct drm_device *dev = crtc->dev; - struct amdgpu_device *adev = drm_to_adev(dev); - - if (enable) - WREG32(mmGRPH_ENABLE + amdgpu_crtc->crtc_offset, 1); - else - WREG32(mmGRPH_ENABLE + amdgpu_crtc->crtc_offset, 0); -} - -static int dce_v11_0_crtc_do_set_base(struct drm_crtc *crtc, - struct drm_framebuffer *fb, - int x, int y, int atomic) -{ - struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); - struct drm_device *dev = crtc->dev; - struct amdgpu_device *adev = drm_to_adev(dev); - struct drm_framebuffer *target_fb; - struct drm_gem_object *obj; - struct amdgpu_bo *abo; - uint64_t fb_location, tiling_flags; - uint32_t fb_format, fb_pitch_pixels; - u32 fb_swap = REG_SET_FIELD(0, GRPH_SWAP_CNTL, GRPH_ENDIAN_SWAP, ENDIAN_NONE); - u32 pipe_config; - u32 tmp, viewport_w, viewport_h; - int r; - bool bypass_lut = false; - - /* no fb bound */ - if (!atomic && !crtc->primary->fb) { - DRM_DEBUG_KMS("No FB bound\n"); - return 0; - } - - if (atomic) - target_fb = fb; - else - target_fb = crtc->primary->fb; - - /* If atomic, assume fb object is pinned & idle & fenced and - * just update base pointers - */ - obj = target_fb->obj[0]; - abo = gem_to_amdgpu_bo(obj); - r = amdgpu_bo_reserve(abo, false); - if (unlikely(r != 0)) - return r; - - if (!atomic) { - abo->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; - r = amdgpu_bo_pin(abo, AMDGPU_GEM_DOMAIN_VRAM); - if (unlikely(r != 0)) { - amdgpu_bo_unreserve(abo); - return -EINVAL; - } - } - fb_location = amdgpu_bo_gpu_offset(abo); - - amdgpu_bo_get_tiling_flags(abo, &tiling_flags); - amdgpu_bo_unreserve(abo); - - pipe_config = AMDGPU_TILING_GET(tiling_flags, PIPE_CONFIG); - - switch (target_fb->format->format) { - case DRM_FORMAT_C8: - fb_format = REG_SET_FIELD(0, GRPH_CONTROL, GRPH_DEPTH, 0); - fb_format = REG_SET_FIELD(fb_format, GRPH_CONTROL, GRPH_FORMAT, 0); - break; - case DRM_FORMAT_XRGB4444: - case DRM_FORMAT_ARGB4444: - fb_format = REG_SET_FIELD(0, GRPH_CONTROL, GRPH_DEPTH, 1); - fb_format = REG_SET_FIELD(fb_format, GRPH_CONTROL, GRPH_FORMAT, 2); -#ifdef __BIG_ENDIAN - fb_swap = REG_SET_FIELD(fb_swap, GRPH_SWAP_CNTL, GRPH_ENDIAN_SWAP, - ENDIAN_8IN16); -#endif - break; - case DRM_FORMAT_XRGB1555: - case DRM_FORMAT_ARGB1555: - fb_format = REG_SET_FIELD(0, GRPH_CONTROL, GRPH_DEPTH, 1); - fb_format = REG_SET_FIELD(fb_format, GRPH_CONTROL, GRPH_FORMAT, 0); -#ifdef __BIG_ENDIAN - fb_swap = REG_SET_FIELD(fb_swap, GRPH_SWAP_CNTL, GRPH_ENDIAN_SWAP, - ENDIAN_8IN16); -#endif - break; - case DRM_FORMAT_BGRX5551: - case DRM_FORMAT_BGRA5551: - fb_format = REG_SET_FIELD(0, GRPH_CONTROL, GRPH_DEPTH, 1); - fb_format = REG_SET_FIELD(fb_format, GRPH_CONTROL, GRPH_FORMAT, 5); -#ifdef __BIG_ENDIAN - fb_swap = REG_SET_FIELD(fb_swap, GRPH_SWAP_CNTL, GRPH_ENDIAN_SWAP, - ENDIAN_8IN16); -#endif - break; - case DRM_FORMAT_RGB565: - fb_format = REG_SET_FIELD(0, GRPH_CONTROL, GRPH_DEPTH, 1); - fb_format = REG_SET_FIELD(fb_format, GRPH_CONTROL, GRPH_FORMAT, 1); -#ifdef __BIG_ENDIAN - fb_swap = REG_SET_FIELD(fb_swap, GRPH_SWAP_CNTL, GRPH_ENDIAN_SWAP, - ENDIAN_8IN16); -#endif - break; - case DRM_FORMAT_XRGB8888: - case DRM_FORMAT_ARGB8888: - fb_format = REG_SET_FIELD(0, GRPH_CONTROL, GRPH_DEPTH, 2); - fb_format = REG_SET_FIELD(fb_format, GRPH_CONTROL, GRPH_FORMAT, 0); -#ifdef __BIG_ENDIAN - fb_swap = REG_SET_FIELD(fb_swap, GRPH_SWAP_CNTL, GRPH_ENDIAN_SWAP, - ENDIAN_8IN32); -#endif - break; - case DRM_FORMAT_XRGB2101010: - case DRM_FORMAT_ARGB2101010: - fb_format = REG_SET_FIELD(0, GRPH_CONTROL, GRPH_DEPTH, 2); - fb_format = REG_SET_FIELD(fb_format, GRPH_CONTROL, GRPH_FORMAT, 1); -#ifdef __BIG_ENDIAN - fb_swap = REG_SET_FIELD(fb_swap, GRPH_SWAP_CNTL, GRPH_ENDIAN_SWAP, - ENDIAN_8IN32); -#endif - /* Greater 8 bpc fb needs to bypass hw-lut to retain precision */ - bypass_lut = true; - break; - case DRM_FORMAT_BGRX1010102: - case DRM_FORMAT_BGRA1010102: - fb_format = REG_SET_FIELD(0, GRPH_CONTROL, GRPH_DEPTH, 2); - fb_format = REG_SET_FIELD(fb_format, GRPH_CONTROL, GRPH_FORMAT, 4); -#ifdef __BIG_ENDIAN - fb_swap = REG_SET_FIELD(fb_swap, GRPH_SWAP_CNTL, GRPH_ENDIAN_SWAP, - ENDIAN_8IN32); -#endif - /* Greater 8 bpc fb needs to bypass hw-lut to retain precision */ - bypass_lut = true; - break; - case DRM_FORMAT_XBGR8888: - case DRM_FORMAT_ABGR8888: - fb_format = REG_SET_FIELD(0, GRPH_CONTROL, GRPH_DEPTH, 2); - fb_format = REG_SET_FIELD(fb_format, GRPH_CONTROL, GRPH_FORMAT, 0); - fb_swap = REG_SET_FIELD(fb_swap, GRPH_SWAP_CNTL, GRPH_RED_CROSSBAR, 2); - fb_swap = REG_SET_FIELD(fb_swap, GRPH_SWAP_CNTL, GRPH_BLUE_CROSSBAR, 2); -#ifdef __BIG_ENDIAN - fb_swap = REG_SET_FIELD(fb_swap, GRPH_SWAP_CNTL, GRPH_ENDIAN_SWAP, - ENDIAN_8IN32); -#endif - break; - default: - DRM_ERROR("Unsupported screen format %p4cc\n", - &target_fb->format->format); - return -EINVAL; - } - - if (AMDGPU_TILING_GET(tiling_flags, ARRAY_MODE) == ARRAY_2D_TILED_THIN1) { - unsigned bankw, bankh, mtaspect, tile_split, num_banks; - - bankw = AMDGPU_TILING_GET(tiling_flags, BANK_WIDTH); - bankh = AMDGPU_TILING_GET(tiling_flags, BANK_HEIGHT); - mtaspect = AMDGPU_TILING_GET(tiling_flags, MACRO_TILE_ASPECT); - tile_split = AMDGPU_TILING_GET(tiling_flags, TILE_SPLIT); - num_banks = AMDGPU_TILING_GET(tiling_flags, NUM_BANKS); - - fb_format = REG_SET_FIELD(fb_format, GRPH_CONTROL, GRPH_NUM_BANKS, num_banks); - fb_format = REG_SET_FIELD(fb_format, GRPH_CONTROL, GRPH_ARRAY_MODE, - ARRAY_2D_TILED_THIN1); - fb_format = REG_SET_FIELD(fb_format, GRPH_CONTROL, GRPH_TILE_SPLIT, - tile_split); - fb_format = REG_SET_FIELD(fb_format, GRPH_CONTROL, GRPH_BANK_WIDTH, bankw); - fb_format = REG_SET_FIELD(fb_format, GRPH_CONTROL, GRPH_BANK_HEIGHT, bankh); - fb_format = REG_SET_FIELD(fb_format, GRPH_CONTROL, GRPH_MACRO_TILE_ASPECT, - mtaspect); - fb_format = REG_SET_FIELD(fb_format, GRPH_CONTROL, GRPH_MICRO_TILE_MODE, - ADDR_SURF_MICRO_TILING_DISPLAY); - } else if (AMDGPU_TILING_GET(tiling_flags, ARRAY_MODE) == ARRAY_1D_TILED_THIN1) { - fb_format = REG_SET_FIELD(fb_format, GRPH_CONTROL, GRPH_ARRAY_MODE, - ARRAY_1D_TILED_THIN1); - } - - fb_format = REG_SET_FIELD(fb_format, GRPH_CONTROL, GRPH_PIPE_CONFIG, - pipe_config); - - dce_v11_0_vga_enable(crtc, false); - - /* Make sure surface address is updated at vertical blank rather than - * horizontal blank - */ - tmp = RREG32(mmGRPH_FLIP_CONTROL + amdgpu_crtc->crtc_offset); - tmp = REG_SET_FIELD(tmp, GRPH_FLIP_CONTROL, - GRPH_SURFACE_UPDATE_H_RETRACE_EN, 0); - WREG32(mmGRPH_FLIP_CONTROL + amdgpu_crtc->crtc_offset, tmp); - - WREG32(mmGRPH_PRIMARY_SURFACE_ADDRESS_HIGH + amdgpu_crtc->crtc_offset, - upper_32_bits(fb_location)); - WREG32(mmGRPH_SECONDARY_SURFACE_ADDRESS_HIGH + amdgpu_crtc->crtc_offset, - upper_32_bits(fb_location)); - WREG32(mmGRPH_PRIMARY_SURFACE_ADDRESS + amdgpu_crtc->crtc_offset, - (u32)fb_location & GRPH_PRIMARY_SURFACE_ADDRESS__GRPH_PRIMARY_SURFACE_ADDRESS_MASK); - WREG32(mmGRPH_SECONDARY_SURFACE_ADDRESS + amdgpu_crtc->crtc_offset, - (u32) fb_location & GRPH_SECONDARY_SURFACE_ADDRESS__GRPH_SECONDARY_SURFACE_ADDRESS_MASK); - WREG32(mmGRPH_CONTROL + amdgpu_crtc->crtc_offset, fb_format); - WREG32(mmGRPH_SWAP_CNTL + amdgpu_crtc->crtc_offset, fb_swap); - - /* - * The LUT only has 256 slots for indexing by a 8 bpc fb. Bypass the LUT - * for > 8 bpc scanout to avoid truncation of fb indices to 8 msb's, to - * retain the full precision throughout the pipeline. - */ - tmp = RREG32(mmGRPH_LUT_10BIT_BYPASS + amdgpu_crtc->crtc_offset); - if (bypass_lut) - tmp = REG_SET_FIELD(tmp, GRPH_LUT_10BIT_BYPASS, GRPH_LUT_10BIT_BYPASS_EN, 1); - else - tmp = REG_SET_FIELD(tmp, GRPH_LUT_10BIT_BYPASS, GRPH_LUT_10BIT_BYPASS_EN, 0); - WREG32(mmGRPH_LUT_10BIT_BYPASS + amdgpu_crtc->crtc_offset, tmp); - - if (bypass_lut) - DRM_DEBUG_KMS("Bypassing hardware LUT due to 10 bit fb scanout.\n"); - - WREG32(mmGRPH_SURFACE_OFFSET_X + amdgpu_crtc->crtc_offset, 0); - WREG32(mmGRPH_SURFACE_OFFSET_Y + amdgpu_crtc->crtc_offset, 0); - WREG32(mmGRPH_X_START + amdgpu_crtc->crtc_offset, 0); - WREG32(mmGRPH_Y_START + amdgpu_crtc->crtc_offset, 0); - WREG32(mmGRPH_X_END + amdgpu_crtc->crtc_offset, target_fb->width); - WREG32(mmGRPH_Y_END + amdgpu_crtc->crtc_offset, target_fb->height); - - fb_pitch_pixels = target_fb->pitches[0] / target_fb->format->cpp[0]; - WREG32(mmGRPH_PITCH + amdgpu_crtc->crtc_offset, fb_pitch_pixels); - - dce_v11_0_grph_enable(crtc, true); - - WREG32(mmLB_DESKTOP_HEIGHT + amdgpu_crtc->crtc_offset, - target_fb->height); - - x &= ~3; - y &= ~1; - WREG32(mmVIEWPORT_START + amdgpu_crtc->crtc_offset, - (x << 16) | y); - viewport_w = crtc->mode.hdisplay; - viewport_h = (crtc->mode.vdisplay + 1) & ~1; - WREG32(mmVIEWPORT_SIZE + amdgpu_crtc->crtc_offset, - (viewport_w << 16) | viewport_h); - - /* set pageflip to happen anywhere in vblank interval */ - WREG32(mmCRTC_MASTER_UPDATE_MODE + amdgpu_crtc->crtc_offset, 0); - - if (!atomic && fb && fb != crtc->primary->fb) { - abo = gem_to_amdgpu_bo(fb->obj[0]); - r = amdgpu_bo_reserve(abo, true); - if (unlikely(r != 0)) - return r; - amdgpu_bo_unpin(abo); - amdgpu_bo_unreserve(abo); - } - - /* Bytes per pixel may have changed */ - dce_v11_0_bandwidth_update(adev); - - return 0; -} - -static void dce_v11_0_set_interleave(struct drm_crtc *crtc, - struct drm_display_mode *mode) -{ - struct drm_device *dev = crtc->dev; - struct amdgpu_device *adev = drm_to_adev(dev); - struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); - u32 tmp; - - tmp = RREG32(mmLB_DATA_FORMAT + amdgpu_crtc->crtc_offset); - if (mode->flags & DRM_MODE_FLAG_INTERLACE) - tmp = REG_SET_FIELD(tmp, LB_DATA_FORMAT, INTERLEAVE_EN, 1); - else - tmp = REG_SET_FIELD(tmp, LB_DATA_FORMAT, INTERLEAVE_EN, 0); - WREG32(mmLB_DATA_FORMAT + amdgpu_crtc->crtc_offset, tmp); -} - -static void dce_v11_0_crtc_load_lut(struct drm_crtc *crtc) -{ - struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); - struct drm_device *dev = crtc->dev; - struct amdgpu_device *adev = drm_to_adev(dev); - u16 *r, *g, *b; - int i; - u32 tmp; - - DRM_DEBUG_KMS("%d\n", amdgpu_crtc->crtc_id); - - tmp = RREG32(mmINPUT_CSC_CONTROL + amdgpu_crtc->crtc_offset); - tmp = REG_SET_FIELD(tmp, INPUT_CSC_CONTROL, INPUT_CSC_GRPH_MODE, 0); - WREG32(mmINPUT_CSC_CONTROL + amdgpu_crtc->crtc_offset, tmp); - - tmp = RREG32(mmPRESCALE_GRPH_CONTROL + amdgpu_crtc->crtc_offset); - tmp = REG_SET_FIELD(tmp, PRESCALE_GRPH_CONTROL, GRPH_PRESCALE_BYPASS, 1); - WREG32(mmPRESCALE_GRPH_CONTROL + amdgpu_crtc->crtc_offset, tmp); - - tmp = RREG32(mmINPUT_GAMMA_CONTROL + amdgpu_crtc->crtc_offset); - tmp = REG_SET_FIELD(tmp, INPUT_GAMMA_CONTROL, GRPH_INPUT_GAMMA_MODE, 0); - WREG32(mmINPUT_GAMMA_CONTROL + amdgpu_crtc->crtc_offset, tmp); - - WREG32(mmDC_LUT_CONTROL + amdgpu_crtc->crtc_offset, 0); - - WREG32(mmDC_LUT_BLACK_OFFSET_BLUE + amdgpu_crtc->crtc_offset, 0); - WREG32(mmDC_LUT_BLACK_OFFSET_GREEN + amdgpu_crtc->crtc_offset, 0); - WREG32(mmDC_LUT_BLACK_OFFSET_RED + amdgpu_crtc->crtc_offset, 0); - - WREG32(mmDC_LUT_WHITE_OFFSET_BLUE + amdgpu_crtc->crtc_offset, 0xffff); - WREG32(mmDC_LUT_WHITE_OFFSET_GREEN + amdgpu_crtc->crtc_offset, 0xffff); - WREG32(mmDC_LUT_WHITE_OFFSET_RED + amdgpu_crtc->crtc_offset, 0xffff); - - WREG32(mmDC_LUT_RW_MODE + amdgpu_crtc->crtc_offset, 0); - WREG32(mmDC_LUT_WRITE_EN_MASK + amdgpu_crtc->crtc_offset, 0x00000007); - - WREG32(mmDC_LUT_RW_INDEX + amdgpu_crtc->crtc_offset, 0); - r = crtc->gamma_store; - g = r + crtc->gamma_size; - b = g + crtc->gamma_size; - for (i = 0; i < 256; i++) { - WREG32(mmDC_LUT_30_COLOR + amdgpu_crtc->crtc_offset, - ((*r++ & 0xffc0) << 14) | - ((*g++ & 0xffc0) << 4) | - (*b++ >> 6)); - } - - tmp = RREG32(mmDEGAMMA_CONTROL + amdgpu_crtc->crtc_offset); - tmp = REG_SET_FIELD(tmp, DEGAMMA_CONTROL, GRPH_DEGAMMA_MODE, 0); - tmp = REG_SET_FIELD(tmp, DEGAMMA_CONTROL, CURSOR_DEGAMMA_MODE, 0); - tmp = REG_SET_FIELD(tmp, DEGAMMA_CONTROL, CURSOR2_DEGAMMA_MODE, 0); - WREG32(mmDEGAMMA_CONTROL + amdgpu_crtc->crtc_offset, tmp); - - tmp = RREG32(mmGAMUT_REMAP_CONTROL + amdgpu_crtc->crtc_offset); - tmp = REG_SET_FIELD(tmp, GAMUT_REMAP_CONTROL, GRPH_GAMUT_REMAP_MODE, 0); - WREG32(mmGAMUT_REMAP_CONTROL + amdgpu_crtc->crtc_offset, tmp); - - tmp = RREG32(mmREGAMMA_CONTROL + amdgpu_crtc->crtc_offset); - tmp = REG_SET_FIELD(tmp, REGAMMA_CONTROL, GRPH_REGAMMA_MODE, 0); - WREG32(mmREGAMMA_CONTROL + amdgpu_crtc->crtc_offset, tmp); - - tmp = RREG32(mmOUTPUT_CSC_CONTROL + amdgpu_crtc->crtc_offset); - tmp = REG_SET_FIELD(tmp, OUTPUT_CSC_CONTROL, OUTPUT_CSC_GRPH_MODE, 0); - WREG32(mmOUTPUT_CSC_CONTROL + amdgpu_crtc->crtc_offset, tmp); - - /* XXX match this to the depth of the crtc fmt block, move to modeset? */ - WREG32(mmDENORM_CONTROL + amdgpu_crtc->crtc_offset, 0); - /* XXX this only needs to be programmed once per crtc at startup, - * not sure where the best place for it is - */ - tmp = RREG32(mmALPHA_CONTROL + amdgpu_crtc->crtc_offset); - tmp = REG_SET_FIELD(tmp, ALPHA_CONTROL, CURSOR_ALPHA_BLND_ENA, 1); - WREG32(mmALPHA_CONTROL + amdgpu_crtc->crtc_offset, tmp); -} - -static int dce_v11_0_pick_dig_encoder(struct drm_encoder *encoder) -{ - struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder); - struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv; - - switch (amdgpu_encoder->encoder_id) { - case ENCODER_OBJECT_ID_INTERNAL_UNIPHY: - if (dig->linkb) - return 1; - else - return 0; - case ENCODER_OBJECT_ID_INTERNAL_UNIPHY1: - if (dig->linkb) - return 3; - else - return 2; - case ENCODER_OBJECT_ID_INTERNAL_UNIPHY2: - if (dig->linkb) - return 5; - else - return 4; - case ENCODER_OBJECT_ID_INTERNAL_UNIPHY3: - return 6; - default: - DRM_ERROR("invalid encoder_id: 0x%x\n", amdgpu_encoder->encoder_id); - return 0; - } -} - -/** - * dce_v11_0_pick_pll - Allocate a PPLL for use by the crtc. - * - * @crtc: drm crtc - * - * Returns the PPLL (Pixel PLL) to be used by the crtc. For DP monitors - * a single PPLL can be used for all DP crtcs/encoders. For non-DP - * monitors a dedicated PPLL must be used. If a particular board has - * an external DP PLL, return ATOM_PPLL_INVALID to skip PLL programming - * as there is no need to program the PLL itself. If we are not able to - * allocate a PLL, return ATOM_PPLL_INVALID to skip PLL programming to - * avoid messing up an existing monitor. - * - * Asic specific PLL information - * - * DCE 10.x - * Tonga - * - PPLL1, PPLL2 are available for all UNIPHY (both DP and non-DP) - * CI - * - PPLL0, PPLL1, PPLL2 are available for all UNIPHY (both DP and non-DP) and DAC - * - */ -static u32 dce_v11_0_pick_pll(struct drm_crtc *crtc) -{ - struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); - struct drm_device *dev = crtc->dev; - struct amdgpu_device *adev = drm_to_adev(dev); - u32 pll_in_use; - int pll; - - if ((adev->asic_type == CHIP_POLARIS10) || - (adev->asic_type == CHIP_POLARIS11) || - (adev->asic_type == CHIP_POLARIS12) || - (adev->asic_type == CHIP_VEGAM)) { - struct amdgpu_encoder *amdgpu_encoder = - to_amdgpu_encoder(amdgpu_crtc->encoder); - struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv; - - if (ENCODER_MODE_IS_DP(amdgpu_atombios_encoder_get_encoder_mode(amdgpu_crtc->encoder))) - return ATOM_DP_DTO; - - switch (amdgpu_encoder->encoder_id) { - case ENCODER_OBJECT_ID_INTERNAL_UNIPHY: - if (dig->linkb) - return ATOM_COMBOPHY_PLL1; - else - return ATOM_COMBOPHY_PLL0; - case ENCODER_OBJECT_ID_INTERNAL_UNIPHY1: - if (dig->linkb) - return ATOM_COMBOPHY_PLL3; - else - return ATOM_COMBOPHY_PLL2; - case ENCODER_OBJECT_ID_INTERNAL_UNIPHY2: - if (dig->linkb) - return ATOM_COMBOPHY_PLL5; - else - return ATOM_COMBOPHY_PLL4; - default: - DRM_ERROR("invalid encoder_id: 0x%x\n", amdgpu_encoder->encoder_id); - return ATOM_PPLL_INVALID; - } - } - - if (ENCODER_MODE_IS_DP(amdgpu_atombios_encoder_get_encoder_mode(amdgpu_crtc->encoder))) { - if (adev->clock.dp_extclk) - /* skip PPLL programming if using ext clock */ - return ATOM_PPLL_INVALID; - else { - /* use the same PPLL for all DP monitors */ - pll = amdgpu_pll_get_shared_dp_ppll(crtc); - if (pll != ATOM_PPLL_INVALID) - return pll; - } - } else { - /* use the same PPLL for all monitors with the same clock */ - pll = amdgpu_pll_get_shared_nondp_ppll(crtc); - if (pll != ATOM_PPLL_INVALID) - return pll; - } - - /* XXX need to determine what plls are available on each DCE11 part */ - pll_in_use = amdgpu_pll_get_use_mask(crtc); - if (adev->flags & AMD_IS_APU) { - if (!(pll_in_use & (1 << ATOM_PPLL1))) - return ATOM_PPLL1; - if (!(pll_in_use & (1 << ATOM_PPLL0))) - return ATOM_PPLL0; - DRM_ERROR("unable to allocate a PPLL\n"); - return ATOM_PPLL_INVALID; - } else { - if (!(pll_in_use & (1 << ATOM_PPLL2))) - return ATOM_PPLL2; - if (!(pll_in_use & (1 << ATOM_PPLL1))) - return ATOM_PPLL1; - if (!(pll_in_use & (1 << ATOM_PPLL0))) - return ATOM_PPLL0; - DRM_ERROR("unable to allocate a PPLL\n"); - return ATOM_PPLL_INVALID; - } - return ATOM_PPLL_INVALID; -} - -static void dce_v11_0_lock_cursor(struct drm_crtc *crtc, bool lock) -{ - struct amdgpu_device *adev = drm_to_adev(crtc->dev); - struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); - uint32_t cur_lock; - - cur_lock = RREG32(mmCUR_UPDATE + amdgpu_crtc->crtc_offset); - if (lock) - cur_lock = REG_SET_FIELD(cur_lock, CUR_UPDATE, CURSOR_UPDATE_LOCK, 1); - else - cur_lock = REG_SET_FIELD(cur_lock, CUR_UPDATE, CURSOR_UPDATE_LOCK, 0); - WREG32(mmCUR_UPDATE + amdgpu_crtc->crtc_offset, cur_lock); -} - -static void dce_v11_0_hide_cursor(struct drm_crtc *crtc) -{ - struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); - struct amdgpu_device *adev = drm_to_adev(crtc->dev); - u32 tmp; - - tmp = RREG32(mmCUR_CONTROL + amdgpu_crtc->crtc_offset); - tmp = REG_SET_FIELD(tmp, CUR_CONTROL, CURSOR_EN, 0); - WREG32(mmCUR_CONTROL + amdgpu_crtc->crtc_offset, tmp); -} - -static void dce_v11_0_show_cursor(struct drm_crtc *crtc) -{ - struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); - struct amdgpu_device *adev = drm_to_adev(crtc->dev); - u32 tmp; - - WREG32(mmCUR_SURFACE_ADDRESS_HIGH + amdgpu_crtc->crtc_offset, - upper_32_bits(amdgpu_crtc->cursor_addr)); - WREG32(mmCUR_SURFACE_ADDRESS + amdgpu_crtc->crtc_offset, - lower_32_bits(amdgpu_crtc->cursor_addr)); - - tmp = RREG32(mmCUR_CONTROL + amdgpu_crtc->crtc_offset); - tmp = REG_SET_FIELD(tmp, CUR_CONTROL, CURSOR_EN, 1); - tmp = REG_SET_FIELD(tmp, CUR_CONTROL, CURSOR_MODE, 2); - WREG32(mmCUR_CONTROL + amdgpu_crtc->crtc_offset, tmp); -} - -static int dce_v11_0_cursor_move_locked(struct drm_crtc *crtc, - int x, int y) -{ - struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); - struct amdgpu_device *adev = drm_to_adev(crtc->dev); - int xorigin = 0, yorigin = 0; - - amdgpu_crtc->cursor_x = x; - amdgpu_crtc->cursor_y = y; - - /* avivo cursor are offset into the total surface */ - x += crtc->x; - y += crtc->y; - DRM_DEBUG("x %d y %d c->x %d c->y %d\n", x, y, crtc->x, crtc->y); - - if (x < 0) { - xorigin = min(-x, amdgpu_crtc->max_cursor_width - 1); - x = 0; - } - if (y < 0) { - yorigin = min(-y, amdgpu_crtc->max_cursor_height - 1); - y = 0; - } - - WREG32(mmCUR_POSITION + amdgpu_crtc->crtc_offset, (x << 16) | y); - WREG32(mmCUR_HOT_SPOT + amdgpu_crtc->crtc_offset, (xorigin << 16) | yorigin); - WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset, - ((amdgpu_crtc->cursor_width - 1) << 16) | (amdgpu_crtc->cursor_height - 1)); - - return 0; -} - -static int dce_v11_0_crtc_cursor_move(struct drm_crtc *crtc, - int x, int y) -{ - int ret; - - dce_v11_0_lock_cursor(crtc, true); - ret = dce_v11_0_cursor_move_locked(crtc, x, y); - dce_v11_0_lock_cursor(crtc, false); - - return ret; -} - -static int dce_v11_0_crtc_cursor_set2(struct drm_crtc *crtc, - struct drm_file *file_priv, - uint32_t handle, - uint32_t width, - uint32_t height, - int32_t hot_x, - int32_t hot_y) -{ - struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); - struct drm_gem_object *obj; - struct amdgpu_bo *aobj; - int ret; - - if (!handle) { - /* turn off cursor */ - dce_v11_0_hide_cursor(crtc); - obj = NULL; - goto unpin; - } - - if ((width > amdgpu_crtc->max_cursor_width) || - (height > amdgpu_crtc->max_cursor_height)) { - DRM_ERROR("bad cursor width or height %d x %d\n", width, height); - return -EINVAL; - } - - obj = drm_gem_object_lookup(file_priv, handle); - if (!obj) { - DRM_ERROR("Cannot find cursor object %x for crtc %d\n", handle, amdgpu_crtc->crtc_id); - return -ENOENT; - } - - aobj = gem_to_amdgpu_bo(obj); - ret = amdgpu_bo_reserve(aobj, false); - if (ret != 0) { - drm_gem_object_put(obj); - return ret; - } - - aobj->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; - ret = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM); - amdgpu_bo_unreserve(aobj); - if (ret) { - DRM_ERROR("Failed to pin new cursor BO (%d)\n", ret); - drm_gem_object_put(obj); - return ret; - } - amdgpu_crtc->cursor_addr = amdgpu_bo_gpu_offset(aobj); - - dce_v11_0_lock_cursor(crtc, true); - - if (width != amdgpu_crtc->cursor_width || - height != amdgpu_crtc->cursor_height || - hot_x != amdgpu_crtc->cursor_hot_x || - hot_y != amdgpu_crtc->cursor_hot_y) { - int x, y; - - x = amdgpu_crtc->cursor_x + amdgpu_crtc->cursor_hot_x - hot_x; - y = amdgpu_crtc->cursor_y + amdgpu_crtc->cursor_hot_y - hot_y; - - dce_v11_0_cursor_move_locked(crtc, x, y); - - amdgpu_crtc->cursor_width = width; - amdgpu_crtc->cursor_height = height; - amdgpu_crtc->cursor_hot_x = hot_x; - amdgpu_crtc->cursor_hot_y = hot_y; - } - - dce_v11_0_show_cursor(crtc); - dce_v11_0_lock_cursor(crtc, false); - -unpin: - if (amdgpu_crtc->cursor_bo) { - struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo); - ret = amdgpu_bo_reserve(aobj, true); - if (likely(ret == 0)) { - amdgpu_bo_unpin(aobj); - amdgpu_bo_unreserve(aobj); - } - drm_gem_object_put(amdgpu_crtc->cursor_bo); - } - - amdgpu_crtc->cursor_bo = obj; - return 0; -} - -static void dce_v11_0_cursor_reset(struct drm_crtc *crtc) -{ - struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); - - if (amdgpu_crtc->cursor_bo) { - dce_v11_0_lock_cursor(crtc, true); - - dce_v11_0_cursor_move_locked(crtc, amdgpu_crtc->cursor_x, - amdgpu_crtc->cursor_y); - - dce_v11_0_show_cursor(crtc); - - dce_v11_0_lock_cursor(crtc, false); - } -} - -static int dce_v11_0_crtc_gamma_set(struct drm_crtc *crtc, u16 *red, u16 *green, - u16 *blue, uint32_t size, - struct drm_modeset_acquire_ctx *ctx) -{ - dce_v11_0_crtc_load_lut(crtc); - - return 0; -} - -static void dce_v11_0_crtc_destroy(struct drm_crtc *crtc) -{ - struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); - - drm_crtc_cleanup(crtc); - kfree(amdgpu_crtc); -} - -static const struct drm_crtc_funcs dce_v11_0_crtc_funcs = { - .cursor_set2 = dce_v11_0_crtc_cursor_set2, - .cursor_move = dce_v11_0_crtc_cursor_move, - .gamma_set = dce_v11_0_crtc_gamma_set, - .set_config = amdgpu_display_crtc_set_config, - .destroy = dce_v11_0_crtc_destroy, - .page_flip_target = amdgpu_display_crtc_page_flip_target, - .get_vblank_counter = amdgpu_get_vblank_counter_kms, - .enable_vblank = amdgpu_enable_vblank_kms, - .disable_vblank = amdgpu_disable_vblank_kms, - .get_vblank_timestamp = drm_crtc_vblank_helper_get_vblank_timestamp, -}; - -static void dce_v11_0_crtc_dpms(struct drm_crtc *crtc, int mode) -{ - struct drm_device *dev = crtc->dev; - struct amdgpu_device *adev = drm_to_adev(dev); - struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); - unsigned type; - - switch (mode) { - case DRM_MODE_DPMS_ON: - amdgpu_crtc->enabled = true; - amdgpu_atombios_crtc_enable(crtc, ATOM_ENABLE); - dce_v11_0_vga_enable(crtc, true); - amdgpu_atombios_crtc_blank(crtc, ATOM_DISABLE); - dce_v11_0_vga_enable(crtc, false); - /* Make sure VBLANK and PFLIP interrupts are still enabled */ - type = amdgpu_display_crtc_idx_to_irq_type(adev, - amdgpu_crtc->crtc_id); - amdgpu_irq_update(adev, &adev->crtc_irq, type); - amdgpu_irq_update(adev, &adev->pageflip_irq, type); - drm_crtc_vblank_on(crtc); - dce_v11_0_crtc_load_lut(crtc); - break; - case DRM_MODE_DPMS_STANDBY: - case DRM_MODE_DPMS_SUSPEND: - case DRM_MODE_DPMS_OFF: - drm_crtc_vblank_off(crtc); - if (amdgpu_crtc->enabled) { - dce_v11_0_vga_enable(crtc, true); - amdgpu_atombios_crtc_blank(crtc, ATOM_ENABLE); - dce_v11_0_vga_enable(crtc, false); - } - amdgpu_atombios_crtc_enable(crtc, ATOM_DISABLE); - amdgpu_crtc->enabled = false; - break; - } - /* adjust pm to dpms */ - amdgpu_dpm_compute_clocks(adev); -} - -static void dce_v11_0_crtc_prepare(struct drm_crtc *crtc) -{ - /* disable crtc pair power gating before programming */ - amdgpu_atombios_crtc_powergate(crtc, ATOM_DISABLE); - amdgpu_atombios_crtc_lock(crtc, ATOM_ENABLE); - dce_v11_0_crtc_dpms(crtc, DRM_MODE_DPMS_OFF); -} - -static void dce_v11_0_crtc_commit(struct drm_crtc *crtc) -{ - dce_v11_0_crtc_dpms(crtc, DRM_MODE_DPMS_ON); - amdgpu_atombios_crtc_lock(crtc, ATOM_DISABLE); -} - -static void dce_v11_0_crtc_disable(struct drm_crtc *crtc) -{ - struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); - struct drm_device *dev = crtc->dev; - struct amdgpu_device *adev = drm_to_adev(dev); - struct amdgpu_atom_ss ss; - int i; - - dce_v11_0_crtc_dpms(crtc, DRM_MODE_DPMS_OFF); - if (crtc->primary->fb) { - int r; - struct amdgpu_bo *abo; - - abo = gem_to_amdgpu_bo(crtc->primary->fb->obj[0]); - r = amdgpu_bo_reserve(abo, true); - if (unlikely(r)) - DRM_ERROR("failed to reserve abo before unpin\n"); - else { - amdgpu_bo_unpin(abo); - amdgpu_bo_unreserve(abo); - } - } - /* disable the GRPH */ - dce_v11_0_grph_enable(crtc, false); - - amdgpu_atombios_crtc_powergate(crtc, ATOM_ENABLE); - - for (i = 0; i < adev->mode_info.num_crtc; i++) { - if (adev->mode_info.crtcs[i] && - adev->mode_info.crtcs[i]->enabled && - i != amdgpu_crtc->crtc_id && - amdgpu_crtc->pll_id == adev->mode_info.crtcs[i]->pll_id) { - /* one other crtc is using this pll don't turn - * off the pll - */ - goto done; - } - } - - switch (amdgpu_crtc->pll_id) { - case ATOM_PPLL0: - case ATOM_PPLL1: - case ATOM_PPLL2: - /* disable the ppll */ - amdgpu_atombios_crtc_program_pll(crtc, amdgpu_crtc->crtc_id, amdgpu_crtc->pll_id, - 0, 0, ATOM_DISABLE, 0, 0, 0, 0, 0, false, &ss); - break; - case ATOM_COMBOPHY_PLL0: - case ATOM_COMBOPHY_PLL1: - case ATOM_COMBOPHY_PLL2: - case ATOM_COMBOPHY_PLL3: - case ATOM_COMBOPHY_PLL4: - case ATOM_COMBOPHY_PLL5: - /* disable the ppll */ - amdgpu_atombios_crtc_program_pll(crtc, ATOM_CRTC_INVALID, amdgpu_crtc->pll_id, - 0, 0, ATOM_DISABLE, 0, 0, 0, 0, 0, false, &ss); - break; - default: - break; - } -done: - amdgpu_crtc->pll_id = ATOM_PPLL_INVALID; - amdgpu_crtc->adjusted_clock = 0; - amdgpu_crtc->encoder = NULL; - amdgpu_crtc->connector = NULL; -} - -static int dce_v11_0_crtc_mode_set(struct drm_crtc *crtc, - struct drm_display_mode *mode, - struct drm_display_mode *adjusted_mode, - int x, int y, struct drm_framebuffer *old_fb) -{ - struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); - struct drm_device *dev = crtc->dev; - struct amdgpu_device *adev = drm_to_adev(dev); - - if (!amdgpu_crtc->adjusted_clock) - return -EINVAL; - - if ((adev->asic_type == CHIP_POLARIS10) || - (adev->asic_type == CHIP_POLARIS11) || - (adev->asic_type == CHIP_POLARIS12) || - (adev->asic_type == CHIP_VEGAM)) { - struct amdgpu_encoder *amdgpu_encoder = - to_amdgpu_encoder(amdgpu_crtc->encoder); - int encoder_mode = - amdgpu_atombios_encoder_get_encoder_mode(amdgpu_crtc->encoder); - - /* SetPixelClock calculates the plls and ss values now */ - amdgpu_atombios_crtc_program_pll(crtc, amdgpu_crtc->crtc_id, - amdgpu_crtc->pll_id, - encoder_mode, amdgpu_encoder->encoder_id, - adjusted_mode->clock, 0, 0, 0, 0, - amdgpu_crtc->bpc, amdgpu_crtc->ss_enabled, &amdgpu_crtc->ss); - } else { - amdgpu_atombios_crtc_set_pll(crtc, adjusted_mode); - } - amdgpu_atombios_crtc_set_dtd_timing(crtc, adjusted_mode); - dce_v11_0_crtc_do_set_base(crtc, old_fb, x, y, 0); - amdgpu_atombios_crtc_overscan_setup(crtc, mode, adjusted_mode); - amdgpu_atombios_crtc_scaler_setup(crtc); - dce_v11_0_cursor_reset(crtc); - /* update the hw version fpr dpm */ - amdgpu_crtc->hw_mode = *adjusted_mode; - - return 0; -} - -static bool dce_v11_0_crtc_mode_fixup(struct drm_crtc *crtc, - const struct drm_display_mode *mode, - struct drm_display_mode *adjusted_mode) -{ - struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); - struct drm_device *dev = crtc->dev; - struct drm_encoder *encoder; - - /* assign the encoder to the amdgpu crtc to avoid repeated lookups later */ - list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) { - if (encoder->crtc == crtc) { - amdgpu_crtc->encoder = encoder; - amdgpu_crtc->connector = amdgpu_get_connector_for_encoder(encoder); - break; - } - } - if ((amdgpu_crtc->encoder == NULL) || (amdgpu_crtc->connector == NULL)) { - amdgpu_crtc->encoder = NULL; - amdgpu_crtc->connector = NULL; - return false; - } - if (!amdgpu_display_crtc_scaling_mode_fixup(crtc, mode, adjusted_mode)) - return false; - if (amdgpu_atombios_crtc_prepare_pll(crtc, adjusted_mode)) - return false; - /* pick pll */ - amdgpu_crtc->pll_id = dce_v11_0_pick_pll(crtc); - /* if we can't get a PPLL for a non-DP encoder, fail */ - if ((amdgpu_crtc->pll_id == ATOM_PPLL_INVALID) && - !ENCODER_MODE_IS_DP(amdgpu_atombios_encoder_get_encoder_mode(amdgpu_crtc->encoder))) - return false; - - return true; -} - -static int dce_v11_0_crtc_set_base(struct drm_crtc *crtc, int x, int y, - struct drm_framebuffer *old_fb) -{ - return dce_v11_0_crtc_do_set_base(crtc, old_fb, x, y, 0); -} - -static int dce_v11_0_crtc_set_base_atomic(struct drm_crtc *crtc, - struct drm_framebuffer *fb, - int x, int y, enum mode_set_atomic state) -{ - return dce_v11_0_crtc_do_set_base(crtc, fb, x, y, 1); -} - -static const struct drm_crtc_helper_funcs dce_v11_0_crtc_helper_funcs = { - .dpms = dce_v11_0_crtc_dpms, - .mode_fixup = dce_v11_0_crtc_mode_fixup, - .mode_set = dce_v11_0_crtc_mode_set, - .mode_set_base = dce_v11_0_crtc_set_base, - .mode_set_base_atomic = dce_v11_0_crtc_set_base_atomic, - .prepare = dce_v11_0_crtc_prepare, - .commit = dce_v11_0_crtc_commit, - .disable = dce_v11_0_crtc_disable, - .get_scanout_position = amdgpu_crtc_get_scanout_position, -}; - -static void dce_v11_0_panic_flush(struct drm_plane *plane) -{ - struct drm_framebuffer *fb; - struct amdgpu_crtc *amdgpu_crtc; - struct amdgpu_device *adev; - uint32_t fb_format; - - if (!plane->fb) - return; - - fb = plane->fb; - amdgpu_crtc = to_amdgpu_crtc(plane->crtc); - adev = drm_to_adev(fb->dev); - - /* Disable DC tiling */ - fb_format = RREG32(mmGRPH_CONTROL + amdgpu_crtc->crtc_offset); - fb_format &= ~GRPH_CONTROL__GRPH_ARRAY_MODE_MASK; - WREG32(mmGRPH_CONTROL + amdgpu_crtc->crtc_offset, fb_format); - -} - -static const struct drm_plane_helper_funcs dce_v11_0_drm_primary_plane_helper_funcs = { - .get_scanout_buffer = amdgpu_display_get_scanout_buffer, - .panic_flush = dce_v11_0_panic_flush, -}; - -static int dce_v11_0_crtc_init(struct amdgpu_device *adev, int index) -{ - struct amdgpu_crtc *amdgpu_crtc; - - amdgpu_crtc = kzalloc(sizeof(struct amdgpu_crtc) + - (AMDGPUFB_CONN_LIMIT * sizeof(struct drm_connector *)), GFP_KERNEL); - if (amdgpu_crtc == NULL) - return -ENOMEM; - - drm_crtc_init(adev_to_drm(adev), &amdgpu_crtc->base, &dce_v11_0_crtc_funcs); - - drm_mode_crtc_set_gamma_size(&amdgpu_crtc->base, 256); - amdgpu_crtc->crtc_id = index; - adev->mode_info.crtcs[index] = amdgpu_crtc; - - amdgpu_crtc->max_cursor_width = 128; - amdgpu_crtc->max_cursor_height = 128; - adev_to_drm(adev)->mode_config.cursor_width = amdgpu_crtc->max_cursor_width; - adev_to_drm(adev)->mode_config.cursor_height = amdgpu_crtc->max_cursor_height; - - switch (amdgpu_crtc->crtc_id) { - case 0: - default: - amdgpu_crtc->crtc_offset = CRTC0_REGISTER_OFFSET; - break; - case 1: - amdgpu_crtc->crtc_offset = CRTC1_REGISTER_OFFSET; - break; - case 2: - amdgpu_crtc->crtc_offset = CRTC2_REGISTER_OFFSET; - break; - case 3: - amdgpu_crtc->crtc_offset = CRTC3_REGISTER_OFFSET; - break; - case 4: - amdgpu_crtc->crtc_offset = CRTC4_REGISTER_OFFSET; - break; - case 5: - amdgpu_crtc->crtc_offset = CRTC5_REGISTER_OFFSET; - break; - } - - amdgpu_crtc->pll_id = ATOM_PPLL_INVALID; - amdgpu_crtc->adjusted_clock = 0; - amdgpu_crtc->encoder = NULL; - amdgpu_crtc->connector = NULL; - drm_crtc_helper_add(&amdgpu_crtc->base, &dce_v11_0_crtc_helper_funcs); - drm_plane_helper_add(amdgpu_crtc->base.primary, &dce_v11_0_drm_primary_plane_helper_funcs); - - return 0; -} - -static int dce_v11_0_early_init(struct amdgpu_ip_block *ip_block) -{ - struct amdgpu_device *adev = ip_block->adev; - - adev->audio_endpt_rreg = &dce_v11_0_audio_endpt_rreg; - adev->audio_endpt_wreg = &dce_v11_0_audio_endpt_wreg; - - dce_v11_0_set_display_funcs(adev); - - adev->mode_info.num_crtc = dce_v11_0_get_num_crtc(adev); - - switch (adev->asic_type) { - case CHIP_CARRIZO: - adev->mode_info.num_hpd = 6; - adev->mode_info.num_dig = 9; - break; - case CHIP_STONEY: - adev->mode_info.num_hpd = 6; - adev->mode_info.num_dig = 9; - break; - case CHIP_POLARIS10: - case CHIP_VEGAM: - adev->mode_info.num_hpd = 6; - adev->mode_info.num_dig = 6; - break; - case CHIP_POLARIS11: - case CHIP_POLARIS12: - adev->mode_info.num_hpd = 5; - adev->mode_info.num_dig = 5; - break; - default: - /* FIXME: not supported yet */ - return -EINVAL; - } - - dce_v11_0_set_irq_funcs(adev); - - return 0; -} - -static int dce_v11_0_sw_init(struct amdgpu_ip_block *ip_block) -{ - int r, i; - struct amdgpu_device *adev = ip_block->adev; - - for (i = 0; i < adev->mode_info.num_crtc; i++) { - r = amdgpu_irq_add_id(adev, AMDGPU_IRQ_CLIENTID_LEGACY, i + 1, &adev->crtc_irq); - if (r) - return r; - } - - for (i = VISLANDS30_IV_SRCID_D1_GRPH_PFLIP; i < 20; i += 2) { - r = amdgpu_irq_add_id(adev, AMDGPU_IRQ_CLIENTID_LEGACY, i, &adev->pageflip_irq); - if (r) - return r; - } - - /* HPD hotplug */ - r = amdgpu_irq_add_id(adev, AMDGPU_IRQ_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_HOTPLUG_DETECT_A, &adev->hpd_irq); - if (r) - return r; - - adev_to_drm(adev)->mode_config.funcs = &amdgpu_mode_funcs; - - adev_to_drm(adev)->mode_config.async_page_flip = true; - - adev_to_drm(adev)->mode_config.max_width = 16384; - adev_to_drm(adev)->mode_config.max_height = 16384; - - adev_to_drm(adev)->mode_config.preferred_depth = 24; - adev_to_drm(adev)->mode_config.prefer_shadow = 1; - - adev_to_drm(adev)->mode_config.fb_modifiers_not_supported = true; - - r = amdgpu_display_modeset_create_props(adev); - if (r) - return r; - - adev_to_drm(adev)->mode_config.max_width = 16384; - adev_to_drm(adev)->mode_config.max_height = 16384; - - - /* allocate crtcs */ - for (i = 0; i < adev->mode_info.num_crtc; i++) { - r = dce_v11_0_crtc_init(adev, i); - if (r) - return r; - } - - if (amdgpu_atombios_get_connector_info_from_object_table(adev)) - amdgpu_display_print_display_setup(adev_to_drm(adev)); - else - return -EINVAL; - - /* setup afmt */ - r = dce_v11_0_afmt_init(adev); - if (r) - return r; - - r = dce_v11_0_audio_init(adev); - if (r) - return r; - - /* Disable vblank IRQs aggressively for power-saving */ - /* XXX: can this be enabled for DC? */ - adev_to_drm(adev)->vblank_disable_immediate = true; - - r = drm_vblank_init(adev_to_drm(adev), adev->mode_info.num_crtc); - if (r) - return r; - - INIT_DELAYED_WORK(&adev->hotplug_work, - amdgpu_display_hotplug_work_func); - - drm_kms_helper_poll_init(adev_to_drm(adev)); - - adev->mode_info.mode_config_initialized = true; - return 0; -} - -static int dce_v11_0_sw_fini(struct amdgpu_ip_block *ip_block) -{ - struct amdgpu_device *adev = ip_block->adev; - - drm_edid_free(adev->mode_info.bios_hardcoded_edid); - - drm_kms_helper_poll_fini(adev_to_drm(adev)); - - dce_v11_0_audio_fini(adev); - - dce_v11_0_afmt_fini(adev); - - drm_mode_config_cleanup(adev_to_drm(adev)); - adev->mode_info.mode_config_initialized = false; - - return 0; -} - -static int dce_v11_0_hw_init(struct amdgpu_ip_block *ip_block) -{ - int i; - struct amdgpu_device *adev = ip_block->adev; - - dce_v11_0_init_golden_registers(adev); - - /* disable vga render */ - dce_v11_0_set_vga_render_state(adev, false); - /* init dig PHYs, disp eng pll */ - amdgpu_atombios_crtc_powergate_init(adev); - amdgpu_atombios_encoder_init_dig(adev); - if ((adev->asic_type == CHIP_POLARIS10) || - (adev->asic_type == CHIP_POLARIS11) || - (adev->asic_type == CHIP_POLARIS12) || - (adev->asic_type == CHIP_VEGAM)) { - amdgpu_atombios_crtc_set_dce_clock(adev, adev->clock.default_dispclk, - DCE_CLOCK_TYPE_DISPCLK, ATOM_GCK_DFS); - amdgpu_atombios_crtc_set_dce_clock(adev, 0, - DCE_CLOCK_TYPE_DPREFCLK, ATOM_GCK_DFS); - } else { - amdgpu_atombios_crtc_set_disp_eng_pll(adev, adev->clock.default_dispclk); - } - - /* initialize hpd */ - dce_v11_0_hpd_init(adev); - - for (i = 0; i < adev->mode_info.audio.num_pins; i++) { - dce_v11_0_audio_enable(adev, &adev->mode_info.audio.pin[i], false); - } - - dce_v11_0_pageflip_interrupt_init(adev); - - return 0; -} - -static int dce_v11_0_hw_fini(struct amdgpu_ip_block *ip_block) -{ - int i; - struct amdgpu_device *adev = ip_block->adev; - - dce_v11_0_hpd_fini(adev); - - for (i = 0; i < adev->mode_info.audio.num_pins; i++) { - dce_v11_0_audio_enable(adev, &adev->mode_info.audio.pin[i], false); - } - - dce_v11_0_pageflip_interrupt_fini(adev); - - flush_delayed_work(&adev->hotplug_work); - - return 0; -} - -static int dce_v11_0_suspend(struct amdgpu_ip_block *ip_block) -{ - struct amdgpu_device *adev = ip_block->adev; - int r; - - r = amdgpu_display_suspend_helper(adev); - if (r) - return r; - - adev->mode_info.bl_level = - amdgpu_atombios_encoder_get_backlight_level_from_reg(adev); - - return dce_v11_0_hw_fini(ip_block); -} - -static int dce_v11_0_resume(struct amdgpu_ip_block *ip_block) -{ - struct amdgpu_device *adev = ip_block->adev; - int ret; - - amdgpu_atombios_encoder_set_backlight_level_to_reg(adev, - adev->mode_info.bl_level); - - ret = dce_v11_0_hw_init(ip_block); - - /* turn on the BL */ - if (adev->mode_info.bl_encoder) { - u8 bl_level = amdgpu_display_backlight_get_level(adev, - adev->mode_info.bl_encoder); - amdgpu_display_backlight_set_level(adev, adev->mode_info.bl_encoder, - bl_level); - } - if (ret) - return ret; - - return amdgpu_display_resume_helper(adev); -} - -static bool dce_v11_0_is_idle(struct amdgpu_ip_block *ip_block) -{ - return true; -} - -static int dce_v11_0_soft_reset(struct amdgpu_ip_block *ip_block) -{ - u32 srbm_soft_reset = 0, tmp; - struct amdgpu_device *adev = ip_block->adev; - - if (dce_v11_0_is_display_hung(adev)) - srbm_soft_reset |= SRBM_SOFT_RESET__SOFT_RESET_DC_MASK; - - if (srbm_soft_reset) { - tmp = RREG32(mmSRBM_SOFT_RESET); - tmp |= srbm_soft_reset; - dev_info(adev->dev, "SRBM_SOFT_RESET=0x%08X\n", tmp); - WREG32(mmSRBM_SOFT_RESET, tmp); - tmp = RREG32(mmSRBM_SOFT_RESET); - - udelay(50); - - tmp &= ~srbm_soft_reset; - WREG32(mmSRBM_SOFT_RESET, tmp); - tmp = RREG32(mmSRBM_SOFT_RESET); - - /* Wait a little for things to settle down */ - udelay(50); - } - return 0; -} - -static void dce_v11_0_set_crtc_vblank_interrupt_state(struct amdgpu_device *adev, - int crtc, - enum amdgpu_interrupt_state state) -{ - u32 lb_interrupt_mask; - - if (crtc >= adev->mode_info.num_crtc) { - DRM_DEBUG("invalid crtc %d\n", crtc); - return; - } - - switch (state) { - case AMDGPU_IRQ_STATE_DISABLE: - lb_interrupt_mask = RREG32(mmLB_INTERRUPT_MASK + crtc_offsets[crtc]); - lb_interrupt_mask = REG_SET_FIELD(lb_interrupt_mask, LB_INTERRUPT_MASK, - VBLANK_INTERRUPT_MASK, 0); - WREG32(mmLB_INTERRUPT_MASK + crtc_offsets[crtc], lb_interrupt_mask); - break; - case AMDGPU_IRQ_STATE_ENABLE: - lb_interrupt_mask = RREG32(mmLB_INTERRUPT_MASK + crtc_offsets[crtc]); - lb_interrupt_mask = REG_SET_FIELD(lb_interrupt_mask, LB_INTERRUPT_MASK, - VBLANK_INTERRUPT_MASK, 1); - WREG32(mmLB_INTERRUPT_MASK + crtc_offsets[crtc], lb_interrupt_mask); - break; - default: - break; - } -} - -static void dce_v11_0_set_crtc_vline_interrupt_state(struct amdgpu_device *adev, - int crtc, - enum amdgpu_interrupt_state state) -{ - u32 lb_interrupt_mask; - - if (crtc >= adev->mode_info.num_crtc) { - DRM_DEBUG("invalid crtc %d\n", crtc); - return; - } - - switch (state) { - case AMDGPU_IRQ_STATE_DISABLE: - lb_interrupt_mask = RREG32(mmLB_INTERRUPT_MASK + crtc_offsets[crtc]); - lb_interrupt_mask = REG_SET_FIELD(lb_interrupt_mask, LB_INTERRUPT_MASK, - VLINE_INTERRUPT_MASK, 0); - WREG32(mmLB_INTERRUPT_MASK + crtc_offsets[crtc], lb_interrupt_mask); - break; - case AMDGPU_IRQ_STATE_ENABLE: - lb_interrupt_mask = RREG32(mmLB_INTERRUPT_MASK + crtc_offsets[crtc]); - lb_interrupt_mask = REG_SET_FIELD(lb_interrupt_mask, LB_INTERRUPT_MASK, - VLINE_INTERRUPT_MASK, 1); - WREG32(mmLB_INTERRUPT_MASK + crtc_offsets[crtc], lb_interrupt_mask); - break; - default: - break; - } -} - -static int dce_v11_0_set_hpd_irq_state(struct amdgpu_device *adev, - struct amdgpu_irq_src *source, - unsigned hpd, - enum amdgpu_interrupt_state state) -{ - u32 tmp; - - if (hpd >= adev->mode_info.num_hpd) { - DRM_DEBUG("invalid hpd %d\n", hpd); - return 0; - } - - switch (state) { - case AMDGPU_IRQ_STATE_DISABLE: - tmp = RREG32(mmDC_HPD_INT_CONTROL + hpd_offsets[hpd]); - tmp = REG_SET_FIELD(tmp, DC_HPD_INT_CONTROL, DC_HPD_INT_EN, 0); - WREG32(mmDC_HPD_INT_CONTROL + hpd_offsets[hpd], tmp); - break; - case AMDGPU_IRQ_STATE_ENABLE: - tmp = RREG32(mmDC_HPD_INT_CONTROL + hpd_offsets[hpd]); - tmp = REG_SET_FIELD(tmp, DC_HPD_INT_CONTROL, DC_HPD_INT_EN, 1); - WREG32(mmDC_HPD_INT_CONTROL + hpd_offsets[hpd], tmp); - break; - default: - break; - } - - return 0; -} - -static int dce_v11_0_set_crtc_irq_state(struct amdgpu_device *adev, - struct amdgpu_irq_src *source, - unsigned type, - enum amdgpu_interrupt_state state) -{ - switch (type) { - case AMDGPU_CRTC_IRQ_VBLANK1: - dce_v11_0_set_crtc_vblank_interrupt_state(adev, 0, state); - break; - case AMDGPU_CRTC_IRQ_VBLANK2: - dce_v11_0_set_crtc_vblank_interrupt_state(adev, 1, state); - break; - case AMDGPU_CRTC_IRQ_VBLANK3: - dce_v11_0_set_crtc_vblank_interrupt_state(adev, 2, state); - break; - case AMDGPU_CRTC_IRQ_VBLANK4: - dce_v11_0_set_crtc_vblank_interrupt_state(adev, 3, state); - break; - case AMDGPU_CRTC_IRQ_VBLANK5: - dce_v11_0_set_crtc_vblank_interrupt_state(adev, 4, state); - break; - case AMDGPU_CRTC_IRQ_VBLANK6: - dce_v11_0_set_crtc_vblank_interrupt_state(adev, 5, state); - break; - case AMDGPU_CRTC_IRQ_VLINE1: - dce_v11_0_set_crtc_vline_interrupt_state(adev, 0, state); - break; - case AMDGPU_CRTC_IRQ_VLINE2: - dce_v11_0_set_crtc_vline_interrupt_state(adev, 1, state); - break; - case AMDGPU_CRTC_IRQ_VLINE3: - dce_v11_0_set_crtc_vline_interrupt_state(adev, 2, state); - break; - case AMDGPU_CRTC_IRQ_VLINE4: - dce_v11_0_set_crtc_vline_interrupt_state(adev, 3, state); - break; - case AMDGPU_CRTC_IRQ_VLINE5: - dce_v11_0_set_crtc_vline_interrupt_state(adev, 4, state); - break; - case AMDGPU_CRTC_IRQ_VLINE6: - dce_v11_0_set_crtc_vline_interrupt_state(adev, 5, state); - break; - default: - break; - } - return 0; -} - -static int dce_v11_0_set_pageflip_irq_state(struct amdgpu_device *adev, - struct amdgpu_irq_src *src, - unsigned type, - enum amdgpu_interrupt_state state) -{ - u32 reg; - - if (type >= adev->mode_info.num_crtc) { - DRM_ERROR("invalid pageflip crtc %d\n", type); - return -EINVAL; - } - - reg = RREG32(mmGRPH_INTERRUPT_CONTROL + crtc_offsets[type]); - if (state == AMDGPU_IRQ_STATE_DISABLE) - WREG32(mmGRPH_INTERRUPT_CONTROL + crtc_offsets[type], - reg & ~GRPH_INTERRUPT_CONTROL__GRPH_PFLIP_INT_MASK_MASK); - else - WREG32(mmGRPH_INTERRUPT_CONTROL + crtc_offsets[type], - reg | GRPH_INTERRUPT_CONTROL__GRPH_PFLIP_INT_MASK_MASK); - - return 0; -} - -static int dce_v11_0_pageflip_irq(struct amdgpu_device *adev, - struct amdgpu_irq_src *source, - struct amdgpu_iv_entry *entry) -{ - unsigned long flags; - unsigned crtc_id; - struct amdgpu_crtc *amdgpu_crtc; - struct amdgpu_flip_work *works; - - crtc_id = (entry->src_id - 8) >> 1; - amdgpu_crtc = adev->mode_info.crtcs[crtc_id]; - - if (crtc_id >= adev->mode_info.num_crtc) { - DRM_ERROR("invalid pageflip crtc %d\n", crtc_id); - return -EINVAL; - } - - if (RREG32(mmGRPH_INTERRUPT_STATUS + crtc_offsets[crtc_id]) & - GRPH_INTERRUPT_STATUS__GRPH_PFLIP_INT_OCCURRED_MASK) - WREG32(mmGRPH_INTERRUPT_STATUS + crtc_offsets[crtc_id], - GRPH_INTERRUPT_STATUS__GRPH_PFLIP_INT_CLEAR_MASK); - - /* IRQ could occur when in initial stage */ - if(amdgpu_crtc == NULL) - return 0; - - spin_lock_irqsave(&adev_to_drm(adev)->event_lock, flags); - works = amdgpu_crtc->pflip_works; - if (amdgpu_crtc->pflip_status != AMDGPU_FLIP_SUBMITTED){ - DRM_DEBUG_DRIVER("amdgpu_crtc->pflip_status = %d != " - "AMDGPU_FLIP_SUBMITTED(%d)\n", - amdgpu_crtc->pflip_status, - AMDGPU_FLIP_SUBMITTED); - spin_unlock_irqrestore(&adev_to_drm(adev)->event_lock, flags); - return 0; - } - - /* page flip completed. clean up */ - amdgpu_crtc->pflip_status = AMDGPU_FLIP_NONE; - amdgpu_crtc->pflip_works = NULL; - - /* wakeup usersapce */ - if(works->event) - drm_crtc_send_vblank_event(&amdgpu_crtc->base, works->event); - - spin_unlock_irqrestore(&adev_to_drm(adev)->event_lock, flags); - - drm_crtc_vblank_put(&amdgpu_crtc->base); - schedule_work(&works->unpin_work); - - return 0; -} - -static void dce_v11_0_hpd_int_ack(struct amdgpu_device *adev, - int hpd) -{ - u32 tmp; - - if (hpd >= adev->mode_info.num_hpd) { - DRM_DEBUG("invalid hpd %d\n", hpd); - return; - } - - tmp = RREG32(mmDC_HPD_INT_CONTROL + hpd_offsets[hpd]); - tmp = REG_SET_FIELD(tmp, DC_HPD_INT_CONTROL, DC_HPD_INT_ACK, 1); - WREG32(mmDC_HPD_INT_CONTROL + hpd_offsets[hpd], tmp); -} - -static void dce_v11_0_crtc_vblank_int_ack(struct amdgpu_device *adev, - int crtc) -{ - u32 tmp; - - if (crtc < 0 || crtc >= adev->mode_info.num_crtc) { - DRM_DEBUG("invalid crtc %d\n", crtc); - return; - } - - tmp = RREG32(mmLB_VBLANK_STATUS + crtc_offsets[crtc]); - tmp = REG_SET_FIELD(tmp, LB_VBLANK_STATUS, VBLANK_ACK, 1); - WREG32(mmLB_VBLANK_STATUS + crtc_offsets[crtc], tmp); -} - -static void dce_v11_0_crtc_vline_int_ack(struct amdgpu_device *adev, - int crtc) -{ - u32 tmp; - - if (crtc < 0 || crtc >= adev->mode_info.num_crtc) { - DRM_DEBUG("invalid crtc %d\n", crtc); - return; - } - - tmp = RREG32(mmLB_VLINE_STATUS + crtc_offsets[crtc]); - tmp = REG_SET_FIELD(tmp, LB_VLINE_STATUS, VLINE_ACK, 1); - WREG32(mmLB_VLINE_STATUS + crtc_offsets[crtc], tmp); -} - -static int dce_v11_0_crtc_irq(struct amdgpu_device *adev, - struct amdgpu_irq_src *source, - struct amdgpu_iv_entry *entry) -{ - unsigned crtc = entry->src_id - 1; - uint32_t disp_int = RREG32(interrupt_status_offsets[crtc].reg); - unsigned int irq_type = amdgpu_display_crtc_idx_to_irq_type(adev, - crtc); - - switch (entry->src_data[0]) { - case 0: /* vblank */ - if (disp_int & interrupt_status_offsets[crtc].vblank) - dce_v11_0_crtc_vblank_int_ack(adev, crtc); - else - DRM_DEBUG("IH: IH event w/o asserted irq bit?\n"); - - if (amdgpu_irq_enabled(adev, source, irq_type)) { - drm_handle_vblank(adev_to_drm(adev), crtc); - } - DRM_DEBUG("IH: D%d vblank\n", crtc + 1); - - break; - case 1: /* vline */ - if (disp_int & interrupt_status_offsets[crtc].vline) - dce_v11_0_crtc_vline_int_ack(adev, crtc); - else - DRM_DEBUG("IH: IH event w/o asserted irq bit?\n"); - - DRM_DEBUG("IH: D%d vline\n", crtc + 1); - - break; - default: - DRM_DEBUG("Unhandled interrupt: %d %d\n", entry->src_id, entry->src_data[0]); - break; - } - - return 0; -} - -static int dce_v11_0_hpd_irq(struct amdgpu_device *adev, - struct amdgpu_irq_src *source, - struct amdgpu_iv_entry *entry) -{ - uint32_t disp_int, mask; - unsigned hpd; - - if (entry->src_data[0] >= adev->mode_info.num_hpd) { - DRM_DEBUG("Unhandled interrupt: %d %d\n", entry->src_id, entry->src_data[0]); - return 0; - } - - hpd = entry->src_data[0]; - disp_int = RREG32(interrupt_status_offsets[hpd].reg); - mask = interrupt_status_offsets[hpd].hpd; - - if (disp_int & mask) { - dce_v11_0_hpd_int_ack(adev, hpd); - schedule_delayed_work(&adev->hotplug_work, 0); - DRM_DEBUG("IH: HPD%d\n", hpd + 1); - } - - return 0; -} - -static int dce_v11_0_set_clockgating_state(struct amdgpu_ip_block *ip_block, - enum amd_clockgating_state state) -{ - return 0; -} - -static int dce_v11_0_set_powergating_state(struct amdgpu_ip_block *ip_block, - enum amd_powergating_state state) -{ - return 0; -} - -static const struct amd_ip_funcs dce_v11_0_ip_funcs = { - .name = "dce_v11_0", - .early_init = dce_v11_0_early_init, - .sw_init = dce_v11_0_sw_init, - .sw_fini = dce_v11_0_sw_fini, - .hw_init = dce_v11_0_hw_init, - .hw_fini = dce_v11_0_hw_fini, - .suspend = dce_v11_0_suspend, - .resume = dce_v11_0_resume, - .is_idle = dce_v11_0_is_idle, - .soft_reset = dce_v11_0_soft_reset, - .set_clockgating_state = dce_v11_0_set_clockgating_state, - .set_powergating_state = dce_v11_0_set_powergating_state, -}; - -static void dce_v11_0_encoder_mode_set(struct drm_encoder *encoder, - struct drm_display_mode *mode, - struct drm_display_mode *adjusted_mode) -{ - struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder); - - amdgpu_encoder->pixel_clock = adjusted_mode->clock; - - /* need to call this here rather than in prepare() since we need some crtc info */ - amdgpu_atombios_encoder_dpms(encoder, DRM_MODE_DPMS_OFF); - - /* set scaler clears this on some chips */ - dce_v11_0_set_interleave(encoder->crtc, mode); - - if (amdgpu_atombios_encoder_get_encoder_mode(encoder) == ATOM_ENCODER_MODE_HDMI) { - dce_v11_0_afmt_enable(encoder, true); - dce_v11_0_afmt_setmode(encoder, adjusted_mode); - } -} - -static void dce_v11_0_encoder_prepare(struct drm_encoder *encoder) -{ - struct amdgpu_device *adev = drm_to_adev(encoder->dev); - struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder); - struct drm_connector *connector = amdgpu_get_connector_for_encoder(encoder); - - if ((amdgpu_encoder->active_device & - (ATOM_DEVICE_DFP_SUPPORT | ATOM_DEVICE_LCD_SUPPORT)) || - (amdgpu_encoder_get_dp_bridge_encoder_id(encoder) != - ENCODER_OBJECT_ID_NONE)) { - struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv; - if (dig) { - dig->dig_encoder = dce_v11_0_pick_dig_encoder(encoder); - if (amdgpu_encoder->active_device & ATOM_DEVICE_DFP_SUPPORT) - dig->afmt = adev->mode_info.afmt[dig->dig_encoder]; - } - } - - amdgpu_atombios_scratch_regs_lock(adev, true); - - if (connector) { - struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector); - - /* select the clock/data port if it uses a router */ - if (amdgpu_connector->router.cd_valid) - amdgpu_i2c_router_select_cd_port(amdgpu_connector); - - /* turn eDP panel on for mode set */ - if (connector->connector_type == DRM_MODE_CONNECTOR_eDP) - amdgpu_atombios_encoder_set_edp_panel_power(connector, - ATOM_TRANSMITTER_ACTION_POWER_ON); - } - - /* this is needed for the pll/ss setup to work correctly in some cases */ - amdgpu_atombios_encoder_set_crtc_source(encoder); - /* set up the FMT blocks */ - dce_v11_0_program_fmt(encoder); -} - -static void dce_v11_0_encoder_commit(struct drm_encoder *encoder) -{ - struct drm_device *dev = encoder->dev; - struct amdgpu_device *adev = drm_to_adev(dev); - - /* need to call this here as we need the crtc set up */ - amdgpu_atombios_encoder_dpms(encoder, DRM_MODE_DPMS_ON); - amdgpu_atombios_scratch_regs_lock(adev, false); -} - -static void dce_v11_0_encoder_disable(struct drm_encoder *encoder) -{ - struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder); - struct amdgpu_encoder_atom_dig *dig; - - amdgpu_atombios_encoder_dpms(encoder, DRM_MODE_DPMS_OFF); - - if (amdgpu_atombios_encoder_is_digital(encoder)) { - if (amdgpu_atombios_encoder_get_encoder_mode(encoder) == ATOM_ENCODER_MODE_HDMI) - dce_v11_0_afmt_enable(encoder, false); - dig = amdgpu_encoder->enc_priv; - dig->dig_encoder = -1; - } - amdgpu_encoder->active_device = 0; -} - -/* these are handled by the primary encoders */ -static void dce_v11_0_ext_prepare(struct drm_encoder *encoder) -{ - -} - -static void dce_v11_0_ext_commit(struct drm_encoder *encoder) -{ - -} - -static void -dce_v11_0_ext_mode_set(struct drm_encoder *encoder, - struct drm_display_mode *mode, - struct drm_display_mode *adjusted_mode) -{ - -} - -static void dce_v11_0_ext_disable(struct drm_encoder *encoder) -{ - -} - -static void -dce_v11_0_ext_dpms(struct drm_encoder *encoder, int mode) -{ - -} - -static const struct drm_encoder_helper_funcs dce_v11_0_ext_helper_funcs = { - .dpms = dce_v11_0_ext_dpms, - .prepare = dce_v11_0_ext_prepare, - .mode_set = dce_v11_0_ext_mode_set, - .commit = dce_v11_0_ext_commit, - .disable = dce_v11_0_ext_disable, - /* no detect for TMDS/LVDS yet */ -}; - -static const struct drm_encoder_helper_funcs dce_v11_0_dig_helper_funcs = { - .dpms = amdgpu_atombios_encoder_dpms, - .mode_fixup = amdgpu_atombios_encoder_mode_fixup, - .prepare = dce_v11_0_encoder_prepare, - .mode_set = dce_v11_0_encoder_mode_set, - .commit = dce_v11_0_encoder_commit, - .disable = dce_v11_0_encoder_disable, - .detect = amdgpu_atombios_encoder_dig_detect, -}; - -static const struct drm_encoder_helper_funcs dce_v11_0_dac_helper_funcs = { - .dpms = amdgpu_atombios_encoder_dpms, - .mode_fixup = amdgpu_atombios_encoder_mode_fixup, - .prepare = dce_v11_0_encoder_prepare, - .mode_set = dce_v11_0_encoder_mode_set, - .commit = dce_v11_0_encoder_commit, - .detect = amdgpu_atombios_encoder_dac_detect, -}; - -static void dce_v11_0_encoder_destroy(struct drm_encoder *encoder) -{ - struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder); - if (amdgpu_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT)) - amdgpu_atombios_encoder_fini_backlight(amdgpu_encoder); - kfree(amdgpu_encoder->enc_priv); - drm_encoder_cleanup(encoder); - kfree(amdgpu_encoder); -} - -static const struct drm_encoder_funcs dce_v11_0_encoder_funcs = { - .destroy = dce_v11_0_encoder_destroy, -}; - -static void dce_v11_0_encoder_add(struct amdgpu_device *adev, - uint32_t encoder_enum, - uint32_t supported_device, - u16 caps) -{ - struct drm_device *dev = adev_to_drm(adev); - struct drm_encoder *encoder; - struct amdgpu_encoder *amdgpu_encoder; - - /* see if we already added it */ - list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) { - amdgpu_encoder = to_amdgpu_encoder(encoder); - if (amdgpu_encoder->encoder_enum == encoder_enum) { - amdgpu_encoder->devices |= supported_device; - return; - } - - } - - /* add a new one */ - amdgpu_encoder = kzalloc(sizeof(struct amdgpu_encoder), GFP_KERNEL); - if (!amdgpu_encoder) - return; - - encoder = &amdgpu_encoder->base; - switch (adev->mode_info.num_crtc) { - case 1: - encoder->possible_crtcs = 0x1; - break; - case 2: - default: - encoder->possible_crtcs = 0x3; - break; - case 3: - encoder->possible_crtcs = 0x7; - break; - case 4: - encoder->possible_crtcs = 0xf; - break; - case 5: - encoder->possible_crtcs = 0x1f; - break; - case 6: - encoder->possible_crtcs = 0x3f; - break; - } - - amdgpu_encoder->enc_priv = NULL; - - amdgpu_encoder->encoder_enum = encoder_enum; - amdgpu_encoder->encoder_id = (encoder_enum & OBJECT_ID_MASK) >> OBJECT_ID_SHIFT; - amdgpu_encoder->devices = supported_device; - amdgpu_encoder->rmx_type = RMX_OFF; - amdgpu_encoder->underscan_type = UNDERSCAN_OFF; - amdgpu_encoder->is_ext_encoder = false; - amdgpu_encoder->caps = caps; - - switch (amdgpu_encoder->encoder_id) { - case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_DAC1: - case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_DAC2: - drm_encoder_init(dev, encoder, &dce_v11_0_encoder_funcs, - DRM_MODE_ENCODER_DAC, NULL); - drm_encoder_helper_add(encoder, &dce_v11_0_dac_helper_funcs); - break; - case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_DVO1: - case ENCODER_OBJECT_ID_INTERNAL_UNIPHY: - case ENCODER_OBJECT_ID_INTERNAL_UNIPHY1: - case ENCODER_OBJECT_ID_INTERNAL_UNIPHY2: - case ENCODER_OBJECT_ID_INTERNAL_UNIPHY3: - if (amdgpu_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT)) { - amdgpu_encoder->rmx_type = RMX_FULL; - drm_encoder_init(dev, encoder, &dce_v11_0_encoder_funcs, - DRM_MODE_ENCODER_LVDS, NULL); - amdgpu_encoder->enc_priv = amdgpu_atombios_encoder_get_lcd_info(amdgpu_encoder); - } else if (amdgpu_encoder->devices & (ATOM_DEVICE_CRT_SUPPORT)) { - drm_encoder_init(dev, encoder, &dce_v11_0_encoder_funcs, - DRM_MODE_ENCODER_DAC, NULL); - amdgpu_encoder->enc_priv = amdgpu_atombios_encoder_get_dig_info(amdgpu_encoder); - } else { - drm_encoder_init(dev, encoder, &dce_v11_0_encoder_funcs, - DRM_MODE_ENCODER_TMDS, NULL); - amdgpu_encoder->enc_priv = amdgpu_atombios_encoder_get_dig_info(amdgpu_encoder); - } - drm_encoder_helper_add(encoder, &dce_v11_0_dig_helper_funcs); - break; - case ENCODER_OBJECT_ID_SI170B: - case ENCODER_OBJECT_ID_CH7303: - case ENCODER_OBJECT_ID_EXTERNAL_SDVOA: - case ENCODER_OBJECT_ID_EXTERNAL_SDVOB: - case ENCODER_OBJECT_ID_TITFP513: - case ENCODER_OBJECT_ID_VT1623: - case ENCODER_OBJECT_ID_HDMI_SI1930: - case ENCODER_OBJECT_ID_TRAVIS: - case ENCODER_OBJECT_ID_NUTMEG: - /* these are handled by the primary encoders */ - amdgpu_encoder->is_ext_encoder = true; - if (amdgpu_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT)) - drm_encoder_init(dev, encoder, &dce_v11_0_encoder_funcs, - DRM_MODE_ENCODER_LVDS, NULL); - else if (amdgpu_encoder->devices & (ATOM_DEVICE_CRT_SUPPORT)) - drm_encoder_init(dev, encoder, &dce_v11_0_encoder_funcs, - DRM_MODE_ENCODER_DAC, NULL); - else - drm_encoder_init(dev, encoder, &dce_v11_0_encoder_funcs, - DRM_MODE_ENCODER_TMDS, NULL); - drm_encoder_helper_add(encoder, &dce_v11_0_ext_helper_funcs); - break; - } -} - -static const struct amdgpu_display_funcs dce_v11_0_display_funcs = { - .bandwidth_update = &dce_v11_0_bandwidth_update, - .vblank_get_counter = &dce_v11_0_vblank_get_counter, - .backlight_set_level = &amdgpu_atombios_encoder_set_backlight_level, - .backlight_get_level = &amdgpu_atombios_encoder_get_backlight_level, - .hpd_sense = &dce_v11_0_hpd_sense, - .hpd_set_polarity = &dce_v11_0_hpd_set_polarity, - .hpd_get_gpio_reg = &dce_v11_0_hpd_get_gpio_reg, - .page_flip = &dce_v11_0_page_flip, - .page_flip_get_scanoutpos = &dce_v11_0_crtc_get_scanoutpos, - .add_encoder = &dce_v11_0_encoder_add, - .add_connector = &amdgpu_connector_add, -}; - -static void dce_v11_0_set_display_funcs(struct amdgpu_device *adev) -{ - adev->mode_info.funcs = &dce_v11_0_display_funcs; -} - -static const struct amdgpu_irq_src_funcs dce_v11_0_crtc_irq_funcs = { - .set = dce_v11_0_set_crtc_irq_state, - .process = dce_v11_0_crtc_irq, -}; - -static const struct amdgpu_irq_src_funcs dce_v11_0_pageflip_irq_funcs = { - .set = dce_v11_0_set_pageflip_irq_state, - .process = dce_v11_0_pageflip_irq, -}; - -static const struct amdgpu_irq_src_funcs dce_v11_0_hpd_irq_funcs = { - .set = dce_v11_0_set_hpd_irq_state, - .process = dce_v11_0_hpd_irq, -}; - -static void dce_v11_0_set_irq_funcs(struct amdgpu_device *adev) -{ - if (adev->mode_info.num_crtc > 0) - adev->crtc_irq.num_types = AMDGPU_CRTC_IRQ_VLINE1 + adev->mode_info.num_crtc; - else - adev->crtc_irq.num_types = 0; - adev->crtc_irq.funcs = &dce_v11_0_crtc_irq_funcs; - - adev->pageflip_irq.num_types = adev->mode_info.num_crtc; - adev->pageflip_irq.funcs = &dce_v11_0_pageflip_irq_funcs; - - adev->hpd_irq.num_types = adev->mode_info.num_hpd; - adev->hpd_irq.funcs = &dce_v11_0_hpd_irq_funcs; -} - -const struct amdgpu_ip_block_version dce_v11_0_ip_block = -{ - .type = AMD_IP_BLOCK_TYPE_DCE, - .major = 11, - .minor = 0, - .rev = 0, - .funcs = &dce_v11_0_ip_funcs, -}; - -const struct amdgpu_ip_block_version dce_v11_2_ip_block = -{ - .type = AMD_IP_BLOCK_TYPE_DCE, - .major = 11, - .minor = 2, - .rev = 0, - .funcs = &dce_v11_0_ip_funcs, -}; diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.h b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.h deleted file mode 100644 index 0d878ca3acba..000000000000 --- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.h +++ /dev/null @@ -1,32 +0,0 @@ -/* - * Copyright 2014 Advanced Micro Devices, Inc. - * - * 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, sublicense, - * 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 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 NONINFRINGEMENT. IN NO EVENT SHALL - * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) 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. - * - */ - -#ifndef __DCE_V11_0_H__ -#define __DCE_V11_0_H__ - -extern const struct amdgpu_ip_block_version dce_v11_0_ip_block; -extern const struct amdgpu_ip_block_version dce_v11_2_ip_block; - -void dce_v11_0_disable_dce(struct amdgpu_device *adev); - -#endif diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c index 81760a26f2ff..acc887a58518 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c @@ -1034,7 +1034,6 @@ static void dce_v6_0_program_watermarks(struct amdgpu_device *adev, /* save values for DPM */ amdgpu_crtc->line_time = line_time; - amdgpu_crtc->wm_high = latency_watermark_a; /* Save number of lines the linebuffer leads before the scanout */ amdgpu_crtc->lb_vblank_lead_lines = lb_vblank_lead_lines; diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c index 19a265bd4d19..2ccd6aad8dd6 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c @@ -1096,8 +1096,7 @@ static void dce_v8_0_program_watermarks(struct amdgpu_device *adev, /* save values for DPM */ amdgpu_crtc->line_time = line_time; - amdgpu_crtc->wm_high = latency_watermark_a; - amdgpu_crtc->wm_low = latency_watermark_b; + /* Save number of lines the linebuffer leads before the scanout */ amdgpu_crtc->lb_vblank_lead_lines = lb_vblank_lead_lines; } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 264183ab24ec..8841d7213de4 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -4075,7 +4075,7 @@ static int gfx_v10_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) struct dma_fence *f = NULL; unsigned int index; uint64_t gpu_addr; - volatile uint32_t *cpu_ptr; + uint32_t *cpu_ptr; long r; memset(&ib, 0, sizeof(ib)); @@ -4322,8 +4322,7 @@ static u32 gfx_v10_0_get_csb_size(struct amdgpu_device *adev) return count; } -static void gfx_v10_0_get_csb_buffer(struct amdgpu_device *adev, - volatile u32 *buffer) +static void gfx_v10_0_get_csb_buffer(struct amdgpu_device *adev, u32 *buffer) { u32 count = 0; int ctx_reg_offset; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index c85de8c8f6f5..66c47c466532 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -603,7 +603,7 @@ static int gfx_v11_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) struct dma_fence *f = NULL; unsigned index; uint64_t gpu_addr; - volatile uint32_t *cpu_ptr; + uint32_t *cpu_ptr; long r; /* MES KIQ fw hasn't indirect buffer support for now */ @@ -850,8 +850,7 @@ static u32 gfx_v11_0_get_csb_size(struct amdgpu_device *adev) return count; } -static void gfx_v11_0_get_csb_buffer(struct amdgpu_device *adev, - volatile u32 *buffer) +static void gfx_v11_0_get_csb_buffer(struct amdgpu_device *adev, u32 *buffer) { u32 count = 0; int ctx_reg_offset; @@ -1654,6 +1653,21 @@ static int gfx_v11_0_sw_init(struct amdgpu_ip_block *ip_block) } } break; + case IP_VERSION(11, 0, 1): + case IP_VERSION(11, 0, 4): + adev->gfx.cleaner_shader_ptr = gfx_11_0_3_cleaner_shader_hex; + adev->gfx.cleaner_shader_size = sizeof(gfx_11_0_3_cleaner_shader_hex); + if (adev->gfx.pfp_fw_version >= 102 && + adev->gfx.mec_fw_version >= 66 && + adev->mes.fw_version[0] >= 128) { + adev->gfx.enable_cleaner_shader = true; + r = amdgpu_gfx_cleaner_shader_sw_init(adev, adev->gfx.cleaner_shader_size); + if (r) { + adev->gfx.enable_cleaner_shader = false; + dev_err(adev->dev, "Failed to initialize cleaner shader\n"); + } + } + break; case IP_VERSION(11, 5, 0): case IP_VERSION(11, 5, 1): adev->gfx.cleaner_shader_ptr = gfx_11_0_3_cleaner_shader_hex; @@ -4643,8 +4657,7 @@ static int gfx_v11_0_gfxhub_enable(struct amdgpu_device *adev) amdgpu_device_flush_hdp(adev, NULL); - value = (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS) ? - false : true; + value = amdgpu_vm_fault_stop != AMDGPU_VM_FAULT_STOP_ALWAYS; adev->gfxhub.funcs->set_fault_enable_default(adev, value); /* TODO investigate why this and the hdp flush above is needed, diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c index fd44d5503e28..710ec9c34e43 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c @@ -497,7 +497,7 @@ static int gfx_v12_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) struct dma_fence *f = NULL; unsigned index; uint64_t gpu_addr; - volatile uint32_t *cpu_ptr; + uint32_t *cpu_ptr; long r; /* MES KIQ fw hasn't indirect buffer support for now */ @@ -685,8 +685,7 @@ static u32 gfx_v12_0_get_csb_size(struct amdgpu_device *adev) return count; } -static void gfx_v12_0_get_csb_buffer(struct amdgpu_device *adev, - volatile u32 *buffer) +static void gfx_v12_0_get_csb_buffer(struct amdgpu_device *adev, u32 *buffer) { u32 count = 0, clustercount = 0, i; const struct cs_section_def *sect = NULL; @@ -3524,8 +3523,7 @@ static int gfx_v12_0_gfxhub_enable(struct amdgpu_device *adev) amdgpu_device_flush_hdp(adev, NULL); - value = (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS) ? - false : true; + value = amdgpu_vm_fault_stop != AMDGPU_VM_FAULT_STOP_ALWAYS; adev->gfxhub.funcs->set_fault_enable_default(adev, value); /* TODO investigate why this and the hdp flush above is needed, diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c index 70d7a1f434c4..7693b7953426 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c @@ -86,7 +86,7 @@ MODULE_FIRMWARE("amdgpu/hainan_ce.bin"); MODULE_FIRMWARE("amdgpu/hainan_rlc.bin"); static u32 gfx_v6_0_get_csb_size(struct amdgpu_device *adev); -static void gfx_v6_0_get_csb_buffer(struct amdgpu_device *adev, volatile u32 *buffer); +static void gfx_v6_0_get_csb_buffer(struct amdgpu_device *adev, u32 *buffer); //static void gfx_v6_0_init_cp_pg_table(struct amdgpu_device *adev); static void gfx_v6_0_init_pg(struct amdgpu_device *adev); @@ -2354,7 +2354,7 @@ static void gfx_v6_0_ring_emit_wreg(struct amdgpu_ring *ring, static int gfx_v6_0_rlc_init(struct amdgpu_device *adev) { const u32 *src_ptr; - volatile u32 *dst_ptr; + u32 *dst_ptr; u32 dws; u64 reg_list_mc_addr; const struct cs_section_def *cs_data; @@ -2855,8 +2855,7 @@ static u32 gfx_v6_0_get_csb_size(struct amdgpu_device *adev) return count; } -static void gfx_v6_0_get_csb_buffer(struct amdgpu_device *adev, - volatile u32 *buffer) +static void gfx_v6_0_get_csb_buffer(struct amdgpu_device *adev, u32 *buffer) { u32 count = 0; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c index 2aa323dab34e..5976ed55d9db 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c @@ -883,7 +883,7 @@ static const u32 kalindi_rlc_save_restore_register_list[] = { }; static u32 gfx_v7_0_get_csb_size(struct amdgpu_device *adev); -static void gfx_v7_0_get_csb_buffer(struct amdgpu_device *adev, volatile u32 *buffer); +static void gfx_v7_0_get_csb_buffer(struct amdgpu_device *adev, u32 *buffer); static void gfx_v7_0_init_pg(struct amdgpu_device *adev); static void gfx_v7_0_get_cu_info(struct amdgpu_device *adev); @@ -3882,8 +3882,7 @@ static u32 gfx_v7_0_get_csb_size(struct amdgpu_device *adev) return count; } -static void gfx_v7_0_get_csb_buffer(struct amdgpu_device *adev, - volatile u32 *buffer) +static void gfx_v7_0_get_csb_buffer(struct amdgpu_device *adev, u32 *buffer) { u32 count = 0; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index 367449d8061b..0856ff65288c 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -1220,8 +1220,7 @@ out: return err; } -static void gfx_v8_0_get_csb_buffer(struct amdgpu_device *adev, - volatile u32 *buffer) +static void gfx_v8_0_get_csb_buffer(struct amdgpu_device *adev, u32 *buffer) { u32 count = 0; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index a6ff9a137a83..dd19a97436db 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -1648,8 +1648,7 @@ static u32 gfx_v9_0_get_csb_size(struct amdgpu_device *adev) return count; } -static void gfx_v9_0_get_csb_buffer(struct amdgpu_device *adev, - volatile u32 *buffer) +static void gfx_v9_0_get_csb_buffer(struct amdgpu_device *adev, u32 *buffer) { u32 count = 0; diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c index 7031dd8c3c5e..d7499be8c4bf 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c @@ -963,8 +963,7 @@ static int gmc_v10_0_gart_enable(struct amdgpu_device *adev) /* Flush HDP after it is initialized */ amdgpu_device_flush_hdp(adev, NULL); - value = (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS) ? - false : true; + value = amdgpu_vm_fault_stop != AMDGPU_VM_FAULT_STOP_ALWAYS; if (!adev->in_s0ix) adev->gfxhub.funcs->set_fault_enable_default(adev, value); diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c index 93d2b0bbe641..7bc389d9f5c4 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c @@ -905,8 +905,7 @@ static int gmc_v11_0_gart_enable(struct amdgpu_device *adev) /* Flush HDP after it is initialized */ amdgpu_device_flush_hdp(adev, NULL); - value = (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS) ? - false : true; + value = amdgpu_vm_fault_stop != AMDGPU_VM_FAULT_STOP_ALWAYS; adev->mmhub.funcs->set_fault_enable_default(adev, value); gmc_v11_0_flush_gpu_tlb(adev, 0, AMDGPU_MMHUB0(0), 0); diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c index 9ba055ddc00f..404cc8c2ff2c 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c @@ -337,7 +337,7 @@ static void gmc_v12_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev, int vmid, i; if (adev->enable_uni_mes && adev->mes.ring[AMDGPU_MES_SCHED_PIPE].sched.ready && - (adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) >= 0x81) { + (adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) >= 0x83) { struct mes_inv_tlbs_pasid_input input = {0}; input.pasid = pasid; input.flush_type = flush_type; @@ -521,6 +521,7 @@ static void gmc_v12_0_get_vm_pte(struct amdgpu_device *adev, *flags &= ~AMDGPU_PTE_NOALLOC; if (vm_flags & AMDGPU_VM_PAGE_PRT) { + *flags |= AMDGPU_PTE_PRT_GFX12; *flags |= AMDGPU_PTE_SNOOPED; *flags |= AMDGPU_PTE_SYSTEM; *flags |= AMDGPU_PTE_IS_PTE; @@ -893,8 +894,7 @@ static int gmc_v12_0_gart_enable(struct amdgpu_device *adev) /* Flush HDP after it is initialized */ amdgpu_device_flush_hdp(adev, NULL); - value = (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS) ? - false : true; + value = amdgpu_vm_fault_stop != AMDGPU_VM_FAULT_STOP_ALWAYS; adev->mmhub.funcs->set_fault_enable_default(adev, value); gmc_v12_0_flush_gpu_tlb(adev, 0, AMDGPU_MMHUB0(0), 0); diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index 8404695eb13f..0d1dd587db5f 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -1834,11 +1834,19 @@ static void gmc_v9_0_save_registers(struct amdgpu_device *adev) static void gmc_v9_4_3_init_vram_info(struct amdgpu_device *adev) { + static const u32 regBIF_BIOS_SCRATCH_4 = 0x50; + u32 vram_info; + adev->gmc.vram_type = AMDGPU_VRAM_TYPE_HBM; adev->gmc.vram_width = 128 * 64; if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 5, 0)) adev->gmc.vram_type = AMDGPU_VRAM_TYPE_HBM3E; + + if (!(adev->flags & AMD_IS_APU) && !amdgpu_sriov_vf(adev)) { + vram_info = RREG32(regBIF_BIOS_SCRATCH_4); + adev->gmc.vram_vendor = vram_info & 0xF; + } } static int gmc_v9_0_sw_init(struct amdgpu_ip_block *ip_block) diff --git a/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c b/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c index 5900b560b7de..333e9c30c091 100644 --- a/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c @@ -587,8 +587,7 @@ static int ih_v6_0_sw_init(struct amdgpu_ip_block *ip_block) /* use gpu virtual address for ih ring * until ih_checken is programmed to allow * use bus address for ih ring by psp bl */ - use_bus_addr = - (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) ? false : true; + use_bus_addr = adev->firmware.load_type != AMDGPU_FW_LOAD_PSP; r = amdgpu_ih_ring_init(adev, &adev->irq.ih, IH_RING_SIZE, use_bus_addr); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c b/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c index 068ed849dbad..95b3f4e55ec3 100644 --- a/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c +++ b/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c @@ -562,8 +562,7 @@ static int ih_v6_1_sw_init(struct amdgpu_ip_block *ip_block) /* use gpu virtual address for ih ring * until ih_checken is programmed to allow * use bus address for ih ring by psp bl */ - use_bus_addr = - (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) ? false : true; + use_bus_addr = adev->firmware.load_type != AMDGPU_FW_LOAD_PSP; r = amdgpu_ih_ring_init(adev, &adev->irq.ih, 256 * 1024, use_bus_addr); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/ih_v7_0.c b/drivers/gpu/drm/amd/amdgpu/ih_v7_0.c index 40a3530e0453..b32ea4129c61 100644 --- a/drivers/gpu/drm/amd/amdgpu/ih_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/ih_v7_0.c @@ -552,8 +552,7 @@ static int ih_v7_0_sw_init(struct amdgpu_ip_block *ip_block) /* use gpu virtual address for ih ring * until ih_checken is programmed to allow * use bus address for ih ring by psp bl */ - use_bus_addr = - (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) ? false : true; + use_bus_addr = adev->firmware.load_type != AMDGPU_FW_LOAD_PSP; r = amdgpu_ih_ring_init(adev, &adev->irq.ih, 256 * 1024, use_bus_addr); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c index a887df520414..4258d3e0b706 100644 --- a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c +++ b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c @@ -29,6 +29,8 @@ #include "amdgpu.h" #include "isp_v4_1_1.h" +MODULE_FIRMWARE("amdgpu/isp_4_1_1.bin"); + #define ISP_PERFORMANCE_STATE_LOW 0 #define ISP_PERFORMANCE_STATE_HIGH 1 diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c index 9e428e669ada..b5bb7f4d607c 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c @@ -557,7 +557,7 @@ static const struct amdgpu_ring_funcs jpeg_v1_0_decode_ring_vm_funcs = { .nop = PACKET0(0x81ff, 0), .support_64bit_ptrs = false, .no_user_fence = true, - .extra_dw = 64, + .extra_bytes = 256, .get_rptr = jpeg_v1_0_decode_ring_get_rptr, .get_wptr = jpeg_v1_0_decode_ring_get_wptr, .set_wptr = jpeg_v1_0_decode_ring_set_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c index 58239c405fda..27c76bd424cf 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c @@ -23,7 +23,6 @@ #include "amdgpu.h" #include "amdgpu_jpeg.h" -#include "amdgpu_cs.h" #include "amdgpu_pm.h" #include "soc15.h" #include "soc15d.h" @@ -806,7 +805,7 @@ static const struct amdgpu_ring_funcs jpeg_v2_0_dec_ring_vm_funcs = { .get_rptr = jpeg_v2_0_dec_ring_get_rptr, .get_wptr = jpeg_v2_0_dec_ring_get_wptr, .set_wptr = jpeg_v2_0_dec_ring_set_wptr, - .parse_cs = jpeg_v2_dec_ring_parse_cs, + .parse_cs = amdgpu_jpeg_dec_parse_cs, .emit_frame_size = SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 + @@ -854,58 +853,3 @@ const struct amdgpu_ip_block_version jpeg_v2_0_ip_block = { .rev = 0, .funcs = &jpeg_v2_0_ip_funcs, }; - -/** - * jpeg_v2_dec_ring_parse_cs - command submission parser - * - * @parser: Command submission parser context - * @job: the job to parse - * @ib: the IB to parse - * - * Parse the command stream, return -EINVAL for invalid packet, - * 0 otherwise - */ -int jpeg_v2_dec_ring_parse_cs(struct amdgpu_cs_parser *parser, - struct amdgpu_job *job, - struct amdgpu_ib *ib) -{ - u32 i, reg, res, cond, type; - struct amdgpu_device *adev = parser->adev; - - for (i = 0; i < ib->length_dw ; i += 2) { - reg = CP_PACKETJ_GET_REG(ib->ptr[i]); - res = CP_PACKETJ_GET_RES(ib->ptr[i]); - cond = CP_PACKETJ_GET_COND(ib->ptr[i]); - type = CP_PACKETJ_GET_TYPE(ib->ptr[i]); - - if (res) /* only support 0 at the moment */ - return -EINVAL; - - switch (type) { - case PACKETJ_TYPE0: - if (cond != PACKETJ_CONDITION_CHECK0 || reg < JPEG_REG_RANGE_START || - reg > JPEG_REG_RANGE_END) { - dev_err(adev->dev, "Invalid packet [0x%08x]!\n", ib->ptr[i]); - return -EINVAL; - } - break; - case PACKETJ_TYPE3: - if (cond != PACKETJ_CONDITION_CHECK3 || reg < JPEG_REG_RANGE_START || - reg > JPEG_REG_RANGE_END) { - dev_err(adev->dev, "Invalid packet [0x%08x]!\n", ib->ptr[i]); - return -EINVAL; - } - break; - case PACKETJ_TYPE6: - if (ib->ptr[i] == CP_PACKETJ_NOP) - continue; - dev_err(adev->dev, "Invalid packet [0x%08x]!\n", ib->ptr[i]); - return -EINVAL; - default: - dev_err(adev->dev, "Unknown packet type %d !\n", type); - return -EINVAL; - } - } - - return 0; -} diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.h b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.h index 63fadda7a673..654e43e83e2c 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.h +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.h @@ -45,9 +45,6 @@ #define JRBC_DEC_EXTERNAL_REG_WRITE_ADDR 0x18000 -#define JPEG_REG_RANGE_START 0x4000 -#define JPEG_REG_RANGE_END 0x41c2 - void jpeg_v2_0_dec_ring_insert_start(struct amdgpu_ring *ring); void jpeg_v2_0_dec_ring_insert_end(struct amdgpu_ring *ring); void jpeg_v2_0_dec_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq, @@ -60,9 +57,6 @@ void jpeg_v2_0_dec_ring_emit_vm_flush(struct amdgpu_ring *ring, unsigned vmid, uint64_t pd_addr); void jpeg_v2_0_dec_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg, uint32_t val); void jpeg_v2_0_dec_ring_nop(struct amdgpu_ring *ring, uint32_t count); -int jpeg_v2_dec_ring_parse_cs(struct amdgpu_cs_parser *parser, - struct amdgpu_job *job, - struct amdgpu_ib *ib); extern const struct amdgpu_ip_block_version jpeg_v2_0_ip_block; diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c index 3e2c389242db..20983f126b49 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c @@ -696,7 +696,7 @@ static const struct amdgpu_ring_funcs jpeg_v2_5_dec_ring_vm_funcs = { .get_rptr = jpeg_v2_5_dec_ring_get_rptr, .get_wptr = jpeg_v2_5_dec_ring_get_wptr, .set_wptr = jpeg_v2_5_dec_ring_set_wptr, - .parse_cs = jpeg_v2_dec_ring_parse_cs, + .parse_cs = amdgpu_jpeg_dec_parse_cs, .emit_frame_size = SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 + @@ -727,7 +727,7 @@ static const struct amdgpu_ring_funcs jpeg_v2_6_dec_ring_vm_funcs = { .get_rptr = jpeg_v2_5_dec_ring_get_rptr, .get_wptr = jpeg_v2_5_dec_ring_get_wptr, .set_wptr = jpeg_v2_5_dec_ring_set_wptr, - .parse_cs = jpeg_v2_dec_ring_parse_cs, + .parse_cs = amdgpu_jpeg_dec_parse_cs, .emit_frame_size = SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 + diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c index a44eb2667664..d1a011c40ba2 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c @@ -597,7 +597,7 @@ static const struct amdgpu_ring_funcs jpeg_v3_0_dec_ring_vm_funcs = { .get_rptr = jpeg_v3_0_dec_ring_get_rptr, .get_wptr = jpeg_v3_0_dec_ring_get_wptr, .set_wptr = jpeg_v3_0_dec_ring_set_wptr, - .parse_cs = jpeg_v2_dec_ring_parse_cs, + .parse_cs = amdgpu_jpeg_dec_parse_cs, .emit_frame_size = SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 + diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c index da3ee69f1a3b..33db2c1ae6cc 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c @@ -762,7 +762,7 @@ static const struct amdgpu_ring_funcs jpeg_v4_0_dec_ring_vm_funcs = { .get_rptr = jpeg_v4_0_dec_ring_get_rptr, .get_wptr = jpeg_v4_0_dec_ring_get_wptr, .set_wptr = jpeg_v4_0_dec_ring_set_wptr, - .parse_cs = jpeg_v2_dec_ring_parse_cs, + .parse_cs = amdgpu_jpeg_dec_parse_cs, .emit_frame_size = SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 + diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c index a78144773fab..aae7328973d1 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c @@ -1177,7 +1177,7 @@ static const struct amdgpu_ring_funcs jpeg_v4_0_3_dec_ring_vm_funcs = { .get_rptr = jpeg_v4_0_3_dec_ring_get_rptr, .get_wptr = jpeg_v4_0_3_dec_ring_get_wptr, .set_wptr = jpeg_v4_0_3_dec_ring_set_wptr, - .parse_cs = jpeg_v2_dec_ring_parse_cs, + .parse_cs = amdgpu_jpeg_dec_parse_cs, .emit_frame_size = SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 + diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c index 481d1a2dbe5a..54fd9c800c40 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c @@ -686,7 +686,7 @@ static int jpeg_v4_0_5_set_clockgating_state(struct amdgpu_ip_block *ip_block, enum amd_clockgating_state state) { struct amdgpu_device *adev = ip_block->adev; - bool enable = (state == AMD_CG_STATE_GATE) ? true : false; + bool enable = state == AMD_CG_STATE_GATE; int i; for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) { @@ -807,7 +807,7 @@ static const struct amdgpu_ring_funcs jpeg_v4_0_5_dec_ring_vm_funcs = { .get_rptr = jpeg_v4_0_5_dec_ring_get_rptr, .get_wptr = jpeg_v4_0_5_dec_ring_get_wptr, .set_wptr = jpeg_v4_0_5_dec_ring_set_wptr, - .parse_cs = jpeg_v2_dec_ring_parse_cs, + .parse_cs = amdgpu_jpeg_dec_parse_cs, .emit_frame_size = SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 + diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c index e0a71909252b..46bf15dce2bd 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c @@ -584,7 +584,7 @@ static int jpeg_v5_0_0_set_clockgating_state(struct amdgpu_ip_block *ip_block, enum amd_clockgating_state state) { struct amdgpu_device *adev = ip_block->adev; - bool enable = (state == AMD_CG_STATE_GATE) ? true : false; + bool enable = state == AMD_CG_STATE_GATE; if (enable) { if (!jpeg_v5_0_0_is_idle(ip_block)) @@ -683,7 +683,7 @@ static const struct amdgpu_ring_funcs jpeg_v5_0_0_dec_ring_vm_funcs = { .get_rptr = jpeg_v5_0_0_dec_ring_get_rptr, .get_wptr = jpeg_v5_0_0_dec_ring_get_wptr, .set_wptr = jpeg_v5_0_0_dec_ring_set_wptr, - .parse_cs = jpeg_v2_dec_ring_parse_cs, + .parse_cs = amdgpu_jpeg_dec_parse_cs, .emit_frame_size = SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 + diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c index 47bde62b3909..baf097d2e1ac 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c @@ -697,7 +697,7 @@ static int jpeg_v5_0_1_set_clockgating_state(struct amdgpu_ip_block *ip_block, enum amd_clockgating_state state) { struct amdgpu_device *adev = ip_block->adev; - bool enable = (state == AMD_CG_STATE_GATE) ? true : false; + bool enable = state == AMD_CG_STATE_GATE; int i; diff --git a/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c b/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c index d6f50b13e2ba..2db9b2c63693 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c @@ -21,6 +21,7 @@ * OTHER DEALINGS IN THE SOFTWARE. * */ +#include <drm/drm_drv.h> #include "amdgpu.h" #include "amdgpu_gfx.h" #include "mes_userqueue.h" @@ -198,6 +199,53 @@ static int mes_userq_create_ctx_space(struct amdgpu_userq_mgr *uq_mgr, return 0; } +static int mes_userq_detect_and_reset(struct amdgpu_device *adev, + int queue_type) +{ + int db_array_size = amdgpu_mes_get_hung_queue_db_array_size(adev); + struct mes_detect_and_reset_queue_input input; + struct amdgpu_usermode_queue *queue; + struct amdgpu_userq_mgr *uqm, *tmp; + unsigned int hung_db_num = 0; + int queue_id, r, i; + u32 db_array[4]; + + if (db_array_size > 4) { + dev_err(adev->dev, "DB array size (%d vs 4) too small\n", + db_array_size); + return -EINVAL; + } + + memset(&input, 0x0, sizeof(struct mes_detect_and_reset_queue_input)); + + input.queue_type = queue_type; + + amdgpu_mes_lock(&adev->mes); + r = amdgpu_mes_detect_and_reset_hung_queues(adev, queue_type, false, + &hung_db_num, db_array); + amdgpu_mes_unlock(&adev->mes); + if (r) { + dev_err(adev->dev, "Failed to detect and reset queues, err (%d)\n", r); + } else if (hung_db_num) { + list_for_each_entry_safe(uqm, tmp, &adev->userq_mgr_list, list) { + idr_for_each_entry(&uqm->userq_idr, queue, queue_id) { + if (queue->queue_type == queue_type) { + for (i = 0; i < hung_db_num; i++) { + if (queue->doorbell_index == db_array[i]) { + queue->state = AMDGPU_USERQ_STATE_HUNG; + atomic_inc(&adev->gpu_reset_counter); + amdgpu_userq_fence_driver_force_completion(queue); + drm_dev_wedged_event(adev_to_drm(adev), DRM_WEDGE_RECOVERY_NONE, NULL); + } + } + } + } + } + } + + return r; +} + static int mes_userq_mqd_create(struct amdgpu_userq_mgr *uq_mgr, struct drm_amdgpu_userq_in *args_in, struct amdgpu_usermode_queue *queue) @@ -206,6 +254,7 @@ static int mes_userq_mqd_create(struct amdgpu_userq_mgr *uq_mgr, struct amdgpu_mqd *mqd_hw_default = &adev->mqds[queue->queue_type]; struct drm_amdgpu_userq_in *mqd_user = args_in; struct amdgpu_mqd_prop *userq_props; + struct amdgpu_gfx_shadow_info shadow_info; int r; /* Structure to initialize MQD for userqueue using generic MQD init function */ @@ -215,13 +264,6 @@ static int mes_userq_mqd_create(struct amdgpu_userq_mgr *uq_mgr, return -ENOMEM; } - if (!mqd_user->wptr_va || !mqd_user->rptr_va || - !mqd_user->queue_va || mqd_user->queue_size == 0) { - DRM_ERROR("Invalid MQD parameters for userqueue\n"); - r = -EINVAL; - goto free_props; - } - r = amdgpu_userq_create_object(uq_mgr, &queue->mqd, mqd_hw_default->mqd_size); if (r) { DRM_ERROR("Failed to create MQD object for userqueue\n"); @@ -238,6 +280,8 @@ static int mes_userq_mqd_create(struct amdgpu_userq_mgr *uq_mgr, userq_props->doorbell_index = queue->doorbell_index; userq_props->fence_address = queue->fence_drv->gpu_addr; + if (adev->gfx.funcs->get_gfx_shadow_info) + adev->gfx.funcs->get_gfx_shadow_info(adev, &shadow_info, true); if (queue->queue_type == AMDGPU_HW_IP_COMPUTE) { struct drm_amdgpu_userq_mqd_compute_gfx11 *compute_mqd; @@ -254,6 +298,10 @@ static int mes_userq_mqd_create(struct amdgpu_userq_mgr *uq_mgr, goto free_mqd; } + if (amdgpu_userq_input_va_validate(queue->vm, compute_mqd->eop_va, + max_t(u32, PAGE_SIZE, AMDGPU_GPU_PAGE_SIZE))) + goto free_mqd; + userq_props->eop_gpu_addr = compute_mqd->eop_va; userq_props->hqd_pipe_priority = AMDGPU_GFX_PIPE_PRIO_NORMAL; userq_props->hqd_queue_priority = AMDGPU_GFX_QUEUE_PRIORITY_MINIMUM; @@ -281,6 +329,11 @@ static int mes_userq_mqd_create(struct amdgpu_userq_mgr *uq_mgr, userq_props->csa_addr = mqd_gfx_v11->csa_va; userq_props->tmz_queue = mqd_user->flags & AMDGPU_USERQ_CREATE_FLAGS_QUEUE_SECURE; + + if (amdgpu_userq_input_va_validate(queue->vm, mqd_gfx_v11->shadow_va, + shadow_info.shadow_size)) + goto free_mqd; + kfree(mqd_gfx_v11); } else if (queue->queue_type == AMDGPU_HW_IP_DMA) { struct drm_amdgpu_userq_mqd_sdma_gfx11 *mqd_sdma_v11; @@ -298,6 +351,10 @@ static int mes_userq_mqd_create(struct amdgpu_userq_mgr *uq_mgr, goto free_mqd; } + if (amdgpu_userq_input_va_validate(queue->vm, mqd_sdma_v11->csa_va, + shadow_info.csa_size)) + goto free_mqd; + userq_props->csa_addr = mqd_sdma_v11->csa_va; kfree(mqd_sdma_v11); } @@ -347,9 +404,82 @@ mes_userq_mqd_destroy(struct amdgpu_userq_mgr *uq_mgr, amdgpu_userq_destroy_object(uq_mgr, &queue->mqd); } +static int mes_userq_preempt(struct amdgpu_userq_mgr *uq_mgr, + struct amdgpu_usermode_queue *queue) +{ + struct amdgpu_device *adev = uq_mgr->adev; + struct mes_suspend_gang_input queue_input; + struct amdgpu_userq_obj *ctx = &queue->fw_obj; + signed long timeout = 2100000; /* 2100 ms */ + u64 fence_gpu_addr; + u32 fence_offset; + u64 *fence_ptr; + int i, r; + + if (queue->state != AMDGPU_USERQ_STATE_MAPPED) + return 0; + r = amdgpu_device_wb_get(adev, &fence_offset); + if (r) + return r; + + fence_gpu_addr = adev->wb.gpu_addr + (fence_offset * 4); + fence_ptr = (u64 *)&adev->wb.wb[fence_offset]; + *fence_ptr = 0; + + memset(&queue_input, 0x0, sizeof(struct mes_suspend_gang_input)); + queue_input.gang_context_addr = ctx->gpu_addr + AMDGPU_USERQ_PROC_CTX_SZ; + queue_input.suspend_fence_addr = fence_gpu_addr; + queue_input.suspend_fence_value = 1; + amdgpu_mes_lock(&adev->mes); + r = adev->mes.funcs->suspend_gang(&adev->mes, &queue_input); + amdgpu_mes_unlock(&adev->mes); + if (r) { + DRM_ERROR("Failed to suspend gang: %d\n", r); + goto out; + } + + for (i = 0; i < timeout; i++) { + if (*fence_ptr == 1) + goto out; + udelay(1); + } + r = -ETIMEDOUT; + +out: + amdgpu_device_wb_free(adev, fence_offset); + return r; +} + +static int mes_userq_restore(struct amdgpu_userq_mgr *uq_mgr, + struct amdgpu_usermode_queue *queue) +{ + struct amdgpu_device *adev = uq_mgr->adev; + struct mes_resume_gang_input queue_input; + struct amdgpu_userq_obj *ctx = &queue->fw_obj; + int r; + + if (queue->state == AMDGPU_USERQ_STATE_HUNG) + return -EINVAL; + if (queue->state != AMDGPU_USERQ_STATE_PREEMPTED) + return 0; + + memset(&queue_input, 0x0, sizeof(struct mes_resume_gang_input)); + queue_input.gang_context_addr = ctx->gpu_addr + AMDGPU_USERQ_PROC_CTX_SZ; + + amdgpu_mes_lock(&adev->mes); + r = adev->mes.funcs->resume_gang(&adev->mes, &queue_input); + amdgpu_mes_unlock(&adev->mes); + if (r) + dev_err(adev->dev, "Failed to resume queue, err (%d)\n", r); + return r; +} + const struct amdgpu_userq_funcs userq_mes_funcs = { .mqd_create = mes_userq_mqd_create, .mqd_destroy = mes_userq_mqd_destroy, .unmap = mes_userq_unmap, .map = mes_userq_map, + .detect_and_reset = mes_userq_detect_and_reset, + .preempt = mes_userq_preempt, + .restore = mes_userq_restore, }; diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c index 3f6a828cad8a..3b91ea601add 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c @@ -66,6 +66,8 @@ static int mes_v11_0_kiq_hw_fini(struct amdgpu_device *adev); #define GFX_MES_DRAM_SIZE 0x80000 #define MES11_HW_RESOURCE_1_SIZE (128 * AMDGPU_GPU_PAGE_SIZE) +#define MES11_HUNG_DB_OFFSET_ARRAY_SIZE 4 + static void mes_v11_0_ring_set_wptr(struct amdgpu_ring *ring) { struct amdgpu_device *adev = ring->adev; @@ -784,6 +786,32 @@ static int mes_v11_0_reset_hw_queue(struct amdgpu_mes *mes, offsetof(union MESAPI__RESET, api_status)); } +static int mes_v11_0_detect_and_reset_hung_queues(struct amdgpu_mes *mes, + struct mes_detect_and_reset_queue_input *input) +{ + union MESAPI__RESET mes_reset_queue_pkt; + + memset(&mes_reset_queue_pkt, 0, sizeof(mes_reset_queue_pkt)); + + mes_reset_queue_pkt.header.type = MES_API_TYPE_SCHEDULER; + mes_reset_queue_pkt.header.opcode = MES_SCH_API_RESET; + mes_reset_queue_pkt.header.dwsize = API_FRAME_SIZE_IN_DWORDS; + + mes_reset_queue_pkt.queue_type = + convert_to_mes_queue_type(input->queue_type); + mes_reset_queue_pkt.doorbell_offset_addr = + mes->hung_queue_db_array_gpu_addr; + + if (input->detect_only) + mes_reset_queue_pkt.hang_detect_only = 1; + else + mes_reset_queue_pkt.hang_detect_then_reset = 1; + + return mes_v11_0_submit_pkt_and_poll_completion(mes, + &mes_reset_queue_pkt, sizeof(mes_reset_queue_pkt), + offsetof(union MESAPI__RESET, api_status)); +} + static const struct amdgpu_mes_funcs mes_v11_0_funcs = { .add_hw_queue = mes_v11_0_add_hw_queue, .remove_hw_queue = mes_v11_0_remove_hw_queue, @@ -793,6 +821,7 @@ static const struct amdgpu_mes_funcs mes_v11_0_funcs = { .resume_gang = mes_v11_0_resume_gang, .misc_op = mes_v11_0_misc_op, .reset_hw_queue = mes_v11_0_reset_hw_queue, + .detect_and_reset_hung_queues = mes_v11_0_detect_and_reset_hung_queues, }; static int mes_v11_0_allocate_ucode_buffer(struct amdgpu_device *adev, @@ -1685,6 +1714,8 @@ static int mes_v11_0_early_init(struct amdgpu_ip_block *ip_block) struct amdgpu_device *adev = ip_block->adev; int pipe, r; + adev->mes.hung_queue_db_array_size = + MES11_HUNG_DB_OFFSET_ARRAY_SIZE; for (pipe = 0; pipe < AMDGPU_MAX_MES_PIPES; pipe++) { if (!adev->enable_mes_kiq && pipe == AMDGPU_MES_KIQ_PIPE) continue; diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c index cd5c966cee95..998893dff08e 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c @@ -47,6 +47,8 @@ static int mes_v12_0_kiq_hw_fini(struct amdgpu_device *adev); #define MES_EOP_SIZE 2048 +#define MES12_HUNG_DB_OFFSET_ARRAY_SIZE 4 + static void mes_v12_0_ring_set_wptr(struct amdgpu_ring *ring) { struct amdgpu_device *adev = ring->adev; @@ -568,13 +570,41 @@ static int mes_v12_0_unmap_legacy_queue(struct amdgpu_mes *mes, static int mes_v12_0_suspend_gang(struct amdgpu_mes *mes, struct mes_suspend_gang_input *input) { - return 0; + union MESAPI__SUSPEND mes_suspend_gang_pkt; + + memset(&mes_suspend_gang_pkt, 0, sizeof(mes_suspend_gang_pkt)); + + mes_suspend_gang_pkt.header.type = MES_API_TYPE_SCHEDULER; + mes_suspend_gang_pkt.header.opcode = MES_SCH_API_SUSPEND; + mes_suspend_gang_pkt.header.dwsize = API_FRAME_SIZE_IN_DWORDS; + + mes_suspend_gang_pkt.suspend_all_gangs = input->suspend_all_gangs; + mes_suspend_gang_pkt.gang_context_addr = input->gang_context_addr; + mes_suspend_gang_pkt.suspend_fence_addr = input->suspend_fence_addr; + mes_suspend_gang_pkt.suspend_fence_value = input->suspend_fence_value; + + return mes_v12_0_submit_pkt_and_poll_completion(mes, AMDGPU_MES_SCHED_PIPE, + &mes_suspend_gang_pkt, sizeof(mes_suspend_gang_pkt), + offsetof(union MESAPI__SUSPEND, api_status)); } static int mes_v12_0_resume_gang(struct amdgpu_mes *mes, struct mes_resume_gang_input *input) { - return 0; + union MESAPI__RESUME mes_resume_gang_pkt; + + memset(&mes_resume_gang_pkt, 0, sizeof(mes_resume_gang_pkt)); + + mes_resume_gang_pkt.header.type = MES_API_TYPE_SCHEDULER; + mes_resume_gang_pkt.header.opcode = MES_SCH_API_RESUME; + mes_resume_gang_pkt.header.dwsize = API_FRAME_SIZE_IN_DWORDS; + + mes_resume_gang_pkt.resume_all_gangs = input->resume_all_gangs; + mes_resume_gang_pkt.gang_context_addr = input->gang_context_addr; + + return mes_v12_0_submit_pkt_and_poll_completion(mes, AMDGPU_MES_SCHED_PIPE, + &mes_resume_gang_pkt, sizeof(mes_resume_gang_pkt), + offsetof(union MESAPI__RESUME, api_status)); } static int mes_v12_0_query_sched_status(struct amdgpu_mes *mes, int pipe) @@ -880,6 +910,32 @@ static int mes_v12_0_reset_hw_queue(struct amdgpu_mes *mes, offsetof(union MESAPI__RESET, api_status)); } +static int mes_v12_0_detect_and_reset_hung_queues(struct amdgpu_mes *mes, + struct mes_detect_and_reset_queue_input *input) +{ + union MESAPI__RESET mes_reset_queue_pkt; + + memset(&mes_reset_queue_pkt, 0, sizeof(mes_reset_queue_pkt)); + + mes_reset_queue_pkt.header.type = MES_API_TYPE_SCHEDULER; + mes_reset_queue_pkt.header.opcode = MES_SCH_API_RESET; + mes_reset_queue_pkt.header.dwsize = API_FRAME_SIZE_IN_DWORDS; + + mes_reset_queue_pkt.queue_type = + convert_to_mes_queue_type(input->queue_type); + mes_reset_queue_pkt.doorbell_offset_addr = + mes->hung_queue_db_array_gpu_addr; + + if (input->detect_only) + mes_reset_queue_pkt.hang_detect_only = 1; + else + mes_reset_queue_pkt.hang_detect_then_reset = 1; + + return mes_v12_0_submit_pkt_and_poll_completion(mes, AMDGPU_MES_SCHED_PIPE, + &mes_reset_queue_pkt, sizeof(mes_reset_queue_pkt), + offsetof(union MESAPI__RESET, api_status)); +} + static int mes_v12_inv_tlb_convert_hub_id(uint8_t id) { /* @@ -899,6 +955,7 @@ static int mes_v12_0_inv_tlbs_pasid(struct amdgpu_mes *mes, struct mes_inv_tlbs_pasid_input *input) { union MESAPI__INV_TLBS mes_inv_tlbs; + int ret; memset(&mes_inv_tlbs, 0, sizeof(mes_inv_tlbs)); @@ -911,9 +968,10 @@ static int mes_v12_0_inv_tlbs_pasid(struct amdgpu_mes *mes, mes_inv_tlbs.invalidate_tlbs.inv_sel_id = input->pasid; /*convert amdgpu_mes_hub_id to mes expected hub_id */ - mes_inv_tlbs.invalidate_tlbs.hub_id = mes_v12_inv_tlb_convert_hub_id(input->hub_id); - if (mes_inv_tlbs.invalidate_tlbs.hub_id < 0) + ret = mes_v12_inv_tlb_convert_hub_id(input->hub_id); + if (ret < 0) return -EINVAL; + mes_inv_tlbs.invalidate_tlbs.hub_id = ret; return mes_v12_0_submit_pkt_and_poll_completion(mes, AMDGPU_MES_KIQ_PIPE, &mes_inv_tlbs, sizeof(mes_inv_tlbs), offsetof(union MESAPI__INV_TLBS, api_status)); @@ -930,6 +988,7 @@ static const struct amdgpu_mes_funcs mes_v12_0_funcs = { .misc_op = mes_v12_0_misc_op, .reset_hw_queue = mes_v12_0_reset_hw_queue, .invalidate_tlbs_pasid = mes_v12_0_inv_tlbs_pasid, + .detect_and_reset_hung_queues = mes_v12_0_detect_and_reset_hung_queues, }; static int mes_v12_0_allocate_ucode_buffer(struct amdgpu_device *adev, @@ -1835,6 +1894,8 @@ static int mes_v12_0_early_init(struct amdgpu_ip_block *ip_block) struct amdgpu_device *adev = ip_block->adev; int pipe, r; + adev->mes.hung_queue_db_array_size = + MES12_HUNG_DB_OFFSET_ARRAY_SIZE; for (pipe = 0; pipe < AMDGPU_MAX_MES_PIPES; pipe++) { r = amdgpu_mes_init_microcode(adev, pipe); if (r) diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c index 457972aa5632..e5282a5d05d9 100644 --- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c +++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c @@ -202,6 +202,9 @@ send_request: case IDH_REQ_RAS_CPER_DUMP: event = IDH_RAS_CPER_DUMP_READY; break; + case IDH_REQ_RAS_CHK_CRITI: + event = IDH_REQ_RAS_CHK_CRITI_READY; + break; default: break; } @@ -556,6 +559,16 @@ static int xgpu_nv_req_ras_bad_pages(struct amdgpu_device *adev) return xgpu_nv_send_access_requests(adev, IDH_REQ_RAS_BAD_PAGES); } +static int xgpu_nv_check_vf_critical_region(struct amdgpu_device *adev, u64 addr) +{ + uint32_t addr_hi, addr_lo; + + addr_hi = (uint32_t)(addr >> 32); + addr_lo = (uint32_t)(addr & 0xFFFFFFFF); + return xgpu_nv_send_access_requests_with_param( + adev, IDH_REQ_RAS_CHK_CRITI, addr_hi, addr_lo, 0); +} + const struct amdgpu_virt_ops xgpu_nv_virt_ops = { .req_full_gpu = xgpu_nv_request_full_gpu_access, .rel_full_gpu = xgpu_nv_release_full_gpu_access, @@ -569,4 +582,5 @@ const struct amdgpu_virt_ops xgpu_nv_virt_ops = { .req_ras_err_count = xgpu_nv_req_ras_err_count, .req_ras_cper_dump = xgpu_nv_req_ras_cper_dump, .req_bad_pages = xgpu_nv_req_ras_bad_pages, + .req_ras_chk_criti = xgpu_nv_check_vf_critical_region }; diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.h b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.h index 5808689562cc..c1083e5e41e0 100644 --- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.h +++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.h @@ -43,6 +43,7 @@ enum idh_request { IDH_REQ_RAS_ERROR_COUNT = 203, IDH_REQ_RAS_CPER_DUMP = 204, IDH_REQ_RAS_BAD_PAGES = 205, + IDH_REQ_RAS_CHK_CRITI = 206 }; enum idh_event { @@ -62,6 +63,7 @@ enum idh_event { IDH_RAS_BAD_PAGES_READY = 15, IDH_RAS_BAD_PAGES_NOTIFICATION = 16, IDH_UNRECOV_ERR_NOTIFICATION = 17, + IDH_REQ_RAS_CHK_CRITI_READY = 18, IDH_TEXT_MESSAGE = 255, }; diff --git a/drivers/gpu/drm/amd/amdgpu/nv.h b/drivers/gpu/drm/amd/amdgpu/nv.h index 83e9782aef39..8f4817404f10 100644 --- a/drivers/gpu/drm/amd/amdgpu/nv.h +++ b/drivers/gpu/drm/amd/amdgpu/nv.h @@ -31,5 +31,6 @@ extern const struct amdgpu_ip_block_version nv_common_ip_block; void nv_grbm_select(struct amdgpu_device *adev, u32 me, u32 pipe, u32 queue, u32 vmid); void nv_set_virt_ops(struct amdgpu_device *adev); +int cyan_skillfish_reg_base_init(struct amdgpu_device *adev); #endif diff --git a/drivers/gpu/drm/amd/amdgpu/smu_v11_0_i2c.c b/drivers/gpu/drm/amd/amdgpu/smu_v11_0_i2c.c index dd2d66090d23..68aef47254a9 100644 --- a/drivers/gpu/drm/amd/amdgpu/smu_v11_0_i2c.c +++ b/drivers/gpu/drm/amd/amdgpu/smu_v11_0_i2c.c @@ -743,7 +743,7 @@ int smu_v11_0_i2c_control_init(struct amdgpu_device *adev) adev->pm.ras_eeprom_i2c_bus = &adev->pm.smu_i2c[0].adapter; adev->pm.fru_eeprom_i2c_bus = &adev->pm.smu_i2c[0].adapter; - res = i2c_add_adapter(control); + res = devm_i2c_add_adapter(adev->dev, control); if (res) DRM_ERROR("Failed to register hw i2c, err: %d\n", res); @@ -752,9 +752,6 @@ int smu_v11_0_i2c_control_init(struct amdgpu_device *adev) void smu_v11_0_i2c_control_fini(struct amdgpu_device *adev) { - struct i2c_adapter *control = adev->pm.ras_eeprom_i2c_bus; - - i2c_del_adapter(control); adev->pm.ras_eeprom_i2c_bus = NULL; adev->pm.fru_eeprom_i2c_bus = NULL; } diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c b/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c index 5dbaebb592b3..2e79a3afc774 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c @@ -623,7 +623,22 @@ static void uvd_v3_1_enable_mgcg(struct amdgpu_device *adev, * * @ip_block: Pointer to the amdgpu_ip_block for this hw instance. * - * Initialize the hardware, boot up the VCPU and do some testing + * Initialize the hardware, boot up the VCPU and do some testing. + * + * On SI, the UVD is meant to be used in a specific power state, + * or alternatively the driver can manually enable its clock. + * In amdgpu we use the dedicated UVD power state when DPM is enabled. + * Calling amdgpu_dpm_enable_uvd makes DPM select the UVD power state + * for the SMU and afterwards enables the UVD clock. + * This is automatically done by amdgpu_uvd_ring_begin_use when work + * is submitted to the UVD ring. Here, we have to call it manually + * in order to power up UVD before firmware validation. + * + * Note that we must not disable the UVD clock here, as that would + * cause the ring test to fail. However, UVD is powered off + * automatically after the ring test: amdgpu_uvd_ring_end_use calls + * the UVD idle work handler which will disable the UVD clock when + * all fences are signalled. */ static int uvd_v3_1_hw_init(struct amdgpu_ip_block *ip_block) { @@ -633,6 +648,15 @@ static int uvd_v3_1_hw_init(struct amdgpu_ip_block *ip_block) int r; uvd_v3_1_mc_resume(adev); + uvd_v3_1_enable_mgcg(adev, true); + + /* Make sure UVD is powered during FW validation. + * It's going to be automatically powered off after the ring test. + */ + if (adev->pm.dpm_enabled) + amdgpu_dpm_enable_uvd(adev, true); + else + amdgpu_asic_set_uvd_clocks(adev, 53300, 40000); r = uvd_v3_1_fw_validate(adev); if (r) { @@ -640,9 +664,6 @@ static int uvd_v3_1_hw_init(struct amdgpu_ip_block *ip_block) return r; } - uvd_v3_1_enable_mgcg(adev, true); - amdgpu_asic_set_uvd_clocks(adev, 53300, 40000); - uvd_v3_1_start(adev); r = amdgpu_ring_test_helper(ring); diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c index 1c07b701d0e4..ceb94bbb03a4 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c @@ -217,7 +217,8 @@ static int uvd_v6_0_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t handle int i, r; r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL, ib_size_dw * 4, - AMDGPU_IB_POOL_DIRECT, &job); + AMDGPU_IB_POOL_DIRECT, &job, + AMDGPU_KERNEL_JOB_ID_VCN_RING_TEST); if (r) return r; @@ -281,7 +282,8 @@ static int uvd_v6_0_enc_get_destroy_msg(struct amdgpu_ring *ring, int i, r; r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL, ib_size_dw * 4, - AMDGPU_IB_POOL_DIRECT, &job); + AMDGPU_IB_POOL_DIRECT, &job, + AMDGPU_KERNEL_JOB_ID_VCN_RING_TEST); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c index 9d237b5937fb..1f8866f3f63c 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c @@ -225,7 +225,8 @@ static int uvd_v7_0_enc_get_create_msg(struct amdgpu_ring *ring, u32 handle, int i, r; r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL, ib_size_dw * 4, - AMDGPU_IB_POOL_DIRECT, &job); + AMDGPU_IB_POOL_DIRECT, &job, + AMDGPU_KERNEL_JOB_ID_VCN_RING_TEST); if (r) return r; @@ -288,7 +289,8 @@ static int uvd_v7_0_enc_get_destroy_msg(struct amdgpu_ring *ring, u32 handle, int i, r; r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL, ib_size_dw * 4, - AMDGPU_IB_POOL_DIRECT, &job); + AMDGPU_IB_POOL_DIRECT, &job, + AMDGPU_KERNEL_JOB_ID_VCN_RING_TEST); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c index 1e89ba153d9d..a316797875a8 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c @@ -193,7 +193,7 @@ static int vcn_v1_0_sw_init(struct amdgpu_ip_block *ip_block) adev->vcn.inst[0].pause_dpg_mode = vcn_v1_0_pause_dpg_mode; if (amdgpu_vcnfw_log) { - volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst->fw_shared.cpu_addr; + struct amdgpu_fw_shared *fw_shared = adev->vcn.inst->fw_shared.cpu_addr; fw_shared->present_flag_0 = 0; amdgpu_vcn_fwlog_init(adev->vcn.inst); @@ -230,11 +230,11 @@ static int vcn_v1_0_sw_fini(struct amdgpu_ip_block *ip_block) jpeg_v1_0_sw_fini(ip_block); - r = amdgpu_vcn_sw_fini(adev, 0); + amdgpu_vcn_sw_fini(adev, 0); kfree(adev->vcn.ip_dump); - return r; + return 0; } /** diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c index b115137ab2d6..8897dcc9c1a0 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c @@ -137,7 +137,7 @@ static int vcn_v2_0_sw_init(struct amdgpu_ip_block *ip_block) struct amdgpu_ring *ring; int i, r; struct amdgpu_device *adev = ip_block->adev; - volatile struct amdgpu_fw_shared *fw_shared; + struct amdgpu_fw_shared *fw_shared; /* VCN DEC TRAP */ r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN, @@ -252,7 +252,7 @@ static int vcn_v2_0_sw_fini(struct amdgpu_ip_block *ip_block) { int r, idx; struct amdgpu_device *adev = ip_block->adev; - volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst->fw_shared.cpu_addr; + struct amdgpu_fw_shared *fw_shared = adev->vcn.inst->fw_shared.cpu_addr; if (drm_dev_enter(adev_to_drm(adev), &idx)) { fw_shared->present_flag_0 = 0; @@ -267,9 +267,9 @@ static int vcn_v2_0_sw_fini(struct amdgpu_ip_block *ip_block) amdgpu_vcn_sysfs_reset_mask_fini(adev); - r = amdgpu_vcn_sw_fini(adev, 0); + amdgpu_vcn_sw_fini(adev, 0); - return r; + return 0; } /** @@ -853,7 +853,7 @@ static void vcn_v2_0_enable_static_power_gating(struct amdgpu_vcn_inst *vinst) static int vcn_v2_0_start_dpg_mode(struct amdgpu_vcn_inst *vinst, bool indirect) { struct amdgpu_device *adev = vinst->adev; - volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst->fw_shared.cpu_addr; + struct amdgpu_fw_shared *fw_shared = adev->vcn.inst->fw_shared.cpu_addr; struct amdgpu_ring *ring = &adev->vcn.inst->ring_dec; uint32_t rb_bufsz, tmp; int ret; @@ -1001,7 +1001,7 @@ static int vcn_v2_0_start_dpg_mode(struct amdgpu_vcn_inst *vinst, bool indirect) static int vcn_v2_0_start(struct amdgpu_vcn_inst *vinst) { struct amdgpu_device *adev = vinst->adev; - volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst->fw_shared.cpu_addr; + struct amdgpu_fw_shared *fw_shared = adev->vcn.inst->fw_shared.cpu_addr; struct amdgpu_ring *ring = &adev->vcn.inst->ring_dec; uint32_t rb_bufsz, tmp; uint32_t lmi_swap_cntl; @@ -1308,7 +1308,7 @@ static int vcn_v2_0_pause_dpg_mode(struct amdgpu_vcn_inst *vinst, UVD_POWER_STATUS__UVD_POWER_STATUS_MASK); if (!ret_code) { - volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst->fw_shared.cpu_addr; + struct amdgpu_fw_shared *fw_shared = adev->vcn.inst->fw_shared.cpu_addr; /* pause DPG */ reg_data |= UVD_DPG_PAUSE__NJ_PAUSE_DPG_REQ_MASK; WREG32_SOC15(UVD, 0, mmUVD_DPG_PAUSE, reg_data); diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c index 904b94bc8693..cebee453871c 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c @@ -277,7 +277,7 @@ static int vcn_v2_5_sw_init(struct amdgpu_ip_block *ip_block) struct amdgpu_device *adev = ip_block->adev; for (j = 0; j < adev->vcn.num_vcn_inst; j++) { - volatile struct amdgpu_fw_shared *fw_shared; + struct amdgpu_fw_shared *fw_shared; if (adev->vcn.harvest_config & (1 << j)) continue; @@ -420,7 +420,7 @@ static int vcn_v2_5_sw_fini(struct amdgpu_ip_block *ip_block) { int i, r, idx; struct amdgpu_device *adev = ip_block->adev; - volatile struct amdgpu_fw_shared *fw_shared; + struct amdgpu_fw_shared *fw_shared; if (drm_dev_enter(adev_to_drm(adev), &idx)) { for (i = 0; i < adev->vcn.num_vcn_inst; i++) { @@ -442,9 +442,7 @@ static int vcn_v2_5_sw_fini(struct amdgpu_ip_block *ip_block) r = amdgpu_vcn_suspend(adev, i); if (r) return r; - r = amdgpu_vcn_sw_fini(adev, i); - if (r) - return r; + amdgpu_vcn_sw_fini(adev, i); } return 0; @@ -1000,7 +998,7 @@ static int vcn_v2_5_start_dpg_mode(struct amdgpu_vcn_inst *vinst, bool indirect) { struct amdgpu_device *adev = vinst->adev; int inst_idx = vinst->inst; - volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr; + struct amdgpu_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr; struct amdgpu_ring *ring; uint32_t rb_bufsz, tmp; int ret; @@ -1157,7 +1155,7 @@ static int vcn_v2_5_start(struct amdgpu_vcn_inst *vinst) { struct amdgpu_device *adev = vinst->adev; int i = vinst->inst; - volatile struct amdgpu_fw_shared *fw_shared = + struct amdgpu_fw_shared *fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; struct amdgpu_ring *ring; uint32_t rb_bufsz, tmp; @@ -1669,7 +1667,7 @@ static int vcn_v2_5_pause_dpg_mode(struct amdgpu_vcn_inst *vinst, UVD_POWER_STATUS__UVD_POWER_STATUS_MASK); if (!ret_code) { - volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr; + struct amdgpu_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr; /* pause DPG */ reg_data |= UVD_DPG_PAUSE__NJ_PAUSE_DPG_REQ_MASK; diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c index 95173156f956..d9cf8f0feeb3 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c @@ -191,7 +191,7 @@ static int vcn_v3_0_sw_init(struct amdgpu_ip_block *ip_block) } for (i = 0; i < adev->vcn.num_vcn_inst; i++) { - volatile struct amdgpu_fw_shared *fw_shared; + struct amdgpu_fw_shared *fw_shared; if (adev->vcn.harvest_config & (1 << i)) continue; @@ -327,7 +327,7 @@ static int vcn_v3_0_sw_fini(struct amdgpu_ip_block *ip_block) if (drm_dev_enter(adev_to_drm(adev), &idx)) { for (i = 0; i < adev->vcn.num_vcn_inst; i++) { - volatile struct amdgpu_fw_shared *fw_shared; + struct amdgpu_fw_shared *fw_shared; if (adev->vcn.harvest_config & (1 << i)) continue; @@ -349,9 +349,7 @@ static int vcn_v3_0_sw_fini(struct amdgpu_ip_block *ip_block) if (r) return r; - r = amdgpu_vcn_sw_fini(adev, i); - if (r) - return r; + amdgpu_vcn_sw_fini(adev, i); } return 0; @@ -1031,7 +1029,7 @@ static int vcn_v3_0_start_dpg_mode(struct amdgpu_vcn_inst *vinst, bool indirect) { struct amdgpu_device *adev = vinst->adev; int inst_idx = vinst->inst; - volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr; + struct amdgpu_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr; struct amdgpu_ring *ring; uint32_t rb_bufsz, tmp; int ret; @@ -1196,7 +1194,7 @@ static int vcn_v3_0_start(struct amdgpu_vcn_inst *vinst) { struct amdgpu_device *adev = vinst->adev; int i = vinst->inst; - volatile struct amdgpu_fw_shared *fw_shared; + struct amdgpu_fw_shared *fw_shared; struct amdgpu_ring *ring; uint32_t rb_bufsz, tmp; int j, k, r; @@ -1717,7 +1715,7 @@ static int vcn_v3_0_pause_dpg_mode(struct amdgpu_vcn_inst *vinst, { struct amdgpu_device *adev = vinst->adev; int inst_idx = vinst->inst; - volatile struct amdgpu_fw_shared *fw_shared; + struct amdgpu_fw_shared *fw_shared; struct amdgpu_ring *ring; uint32_t reg_data = 0; int ret_code; @@ -1836,7 +1834,7 @@ static uint64_t vcn_v3_0_dec_ring_get_wptr(struct amdgpu_ring *ring) static void vcn_v3_0_dec_ring_set_wptr(struct amdgpu_ring *ring) { struct amdgpu_device *adev = ring->adev; - volatile struct amdgpu_fw_shared *fw_shared; + struct amdgpu_fw_shared *fw_shared; if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { /*whenever update RBC_RB_WPTR, we save the wptr in shared rb.wptr and scratch2 */ @@ -1886,15 +1884,19 @@ static int vcn_v3_0_limit_sched(struct amdgpu_cs_parser *p, struct amdgpu_job *job) { struct drm_gpu_scheduler **scheds; - - /* The create msg must be in the first IB submitted */ - if (atomic_read(&job->base.entity->fence_seq)) - return -EINVAL; + struct dma_fence *fence; /* if VCN0 is harvested, we can't support AV1 */ if (p->adev->vcn.harvest_config & AMDGPU_VCN_HARVEST_VCN0) return -EINVAL; + /* wait for all jobs to finish before switching to instance 0 */ + fence = amdgpu_ctx_get_fence(p->ctx, job->base.entity, ~0ull); + if (fence) { + dma_fence_wait(fence, false); + dma_fence_put(fence); + } + scheds = p->adev->gpu_sched[AMDGPU_HW_IP_VCN_DEC] [AMDGPU_RING_PRIO_DEFAULT].sched; drm_sched_entity_modify_sched(job->base.entity, scheds, 1); diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c index d0d27790b73b..3ae666522d57 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c @@ -148,7 +148,7 @@ static int vcn_v4_0_early_init(struct amdgpu_ip_block *ip_block) static int vcn_v4_0_fw_shared_init(struct amdgpu_device *adev, int inst_idx) { - volatile struct amdgpu_vcn4_fw_shared *fw_shared; + struct amdgpu_vcn4_fw_shared *fw_shared; fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr; fw_shared->present_flag_0 = cpu_to_le32(AMDGPU_FW_SHARED_FLAG_0_UNIFIED_QUEUE); @@ -278,7 +278,7 @@ static int vcn_v4_0_sw_fini(struct amdgpu_ip_block *ip_block) if (drm_dev_enter(adev_to_drm(adev), &idx)) { for (i = 0; i < adev->vcn.num_vcn_inst; i++) { - volatile struct amdgpu_vcn4_fw_shared *fw_shared; + struct amdgpu_vcn4_fw_shared *fw_shared; if (adev->vcn.harvest_config & (1 << i)) continue; @@ -302,11 +302,8 @@ static int vcn_v4_0_sw_fini(struct amdgpu_ip_block *ip_block) amdgpu_vcn_sysfs_reset_mask_fini(adev); - for (i = 0; i < adev->vcn.num_vcn_inst; i++) { - r = amdgpu_vcn_sw_fini(adev, i); - if (r) - return r; - } + for (i = 0; i < adev->vcn.num_vcn_inst; i++) + amdgpu_vcn_sw_fini(adev, i); return 0; } @@ -1000,7 +997,7 @@ static int vcn_v4_0_start_dpg_mode(struct amdgpu_vcn_inst *vinst, bool indirect) { struct amdgpu_device *adev = vinst->adev; int inst_idx = vinst->inst; - volatile struct amdgpu_vcn4_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr; + struct amdgpu_vcn4_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr; struct amdgpu_ring *ring; uint32_t tmp; int ret; @@ -1140,7 +1137,7 @@ static int vcn_v4_0_start(struct amdgpu_vcn_inst *vinst) { struct amdgpu_device *adev = vinst->adev; int i = vinst->inst; - volatile struct amdgpu_vcn4_fw_shared *fw_shared; + struct amdgpu_vcn4_fw_shared *fw_shared; struct amdgpu_ring *ring; uint32_t tmp; int j, k, r; @@ -1357,8 +1354,8 @@ static int vcn_v4_0_start_sriov(struct amdgpu_device *adev) struct mmsch_v4_0_cmd_end end = { {0} }; struct mmsch_v4_0_init_header header; - volatile struct amdgpu_vcn4_fw_shared *fw_shared; - volatile struct amdgpu_fw_shared_rb_setup *rb_setup; + struct amdgpu_vcn4_fw_shared *fw_shared; + struct amdgpu_fw_shared_rb_setup *rb_setup; direct_wt.cmd_header.command_type = MMSCH_COMMAND__DIRECT_REG_WRITE; @@ -1609,7 +1606,7 @@ static int vcn_v4_0_stop(struct amdgpu_vcn_inst *vinst) { struct amdgpu_device *adev = vinst->adev; int i = vinst->inst; - volatile struct amdgpu_vcn4_fw_shared *fw_shared; + struct amdgpu_vcn4_fw_shared *fw_shared; uint32_t tmp; int r = 0; @@ -1804,15 +1801,19 @@ static int vcn_v4_0_limit_sched(struct amdgpu_cs_parser *p, struct amdgpu_job *job) { struct drm_gpu_scheduler **scheds; - - /* The create msg must be in the first IB submitted */ - if (atomic_read(&job->base.entity->fence_seq)) - return -EINVAL; + struct dma_fence *fence; /* if VCN0 is harvested, we can't support AV1 */ if (p->adev->vcn.harvest_config & AMDGPU_VCN_HARVEST_VCN0) return -EINVAL; + /* wait for all jobs to finish before switching to instance 0 */ + fence = amdgpu_ctx_get_fence(p->ctx, job->base.entity, ~0ull); + if (fence) { + dma_fence_wait(fence, false); + dma_fence_put(fence); + } + scheds = p->adev->gpu_sched[AMDGPU_HW_IP_VCN_ENC] [AMDGPU_RING_PRIO_0].sched; drm_sched_entity_modify_sched(job->base.entity, scheds, 1); @@ -1903,22 +1904,16 @@ out: #define RADEON_VCN_ENGINE_TYPE_ENCODE (0x00000002) #define RADEON_VCN_ENGINE_TYPE_DECODE (0x00000003) - #define RADEON_VCN_ENGINE_INFO (0x30000001) -#define RADEON_VCN_ENGINE_INFO_MAX_OFFSET 16 - #define RENCODE_ENCODE_STANDARD_AV1 2 #define RENCODE_IB_PARAM_SESSION_INIT 0x00000003 -#define RENCODE_IB_PARAM_SESSION_INIT_MAX_OFFSET 64 -/* return the offset in ib if id is found, -1 otherwise - * to speed up the searching we only search upto max_offset - */ -static int vcn_v4_0_enc_find_ib_param(struct amdgpu_ib *ib, uint32_t id, int max_offset) +/* return the offset in ib if id is found, -1 otherwise */ +static int vcn_v4_0_enc_find_ib_param(struct amdgpu_ib *ib, uint32_t id, int start) { int i; - for (i = 0; i < ib->length_dw && i < max_offset && ib->ptr[i] >= 8; i += ib->ptr[i]/4) { + for (i = start; i < ib->length_dw && ib->ptr[i] >= 8; i += ib->ptr[i] / 4) { if (ib->ptr[i + 1] == id) return i; } @@ -1933,33 +1928,29 @@ static int vcn_v4_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p, struct amdgpu_vcn_decode_buffer *decode_buffer; uint64_t addr; uint32_t val; - int idx; + int idx = 0, sidx; /* The first instance can decode anything */ if (!ring->me) return 0; - /* RADEON_VCN_ENGINE_INFO is at the top of ib block */ - idx = vcn_v4_0_enc_find_ib_param(ib, RADEON_VCN_ENGINE_INFO, - RADEON_VCN_ENGINE_INFO_MAX_OFFSET); - if (idx < 0) /* engine info is missing */ - return 0; - - val = amdgpu_ib_get_value(ib, idx + 2); /* RADEON_VCN_ENGINE_TYPE */ - if (val == RADEON_VCN_ENGINE_TYPE_DECODE) { - decode_buffer = (struct amdgpu_vcn_decode_buffer *)&ib->ptr[idx + 6]; - - if (!(decode_buffer->valid_buf_flag & 0x1)) - return 0; - - addr = ((u64)decode_buffer->msg_buffer_address_hi) << 32 | - decode_buffer->msg_buffer_address_lo; - return vcn_v4_0_dec_msg(p, job, addr); - } else if (val == RADEON_VCN_ENGINE_TYPE_ENCODE) { - idx = vcn_v4_0_enc_find_ib_param(ib, RENCODE_IB_PARAM_SESSION_INIT, - RENCODE_IB_PARAM_SESSION_INIT_MAX_OFFSET); - if (idx >= 0 && ib->ptr[idx + 2] == RENCODE_ENCODE_STANDARD_AV1) - return vcn_v4_0_limit_sched(p, job); + while ((idx = vcn_v4_0_enc_find_ib_param(ib, RADEON_VCN_ENGINE_INFO, idx)) >= 0) { + val = amdgpu_ib_get_value(ib, idx + 2); /* RADEON_VCN_ENGINE_TYPE */ + if (val == RADEON_VCN_ENGINE_TYPE_DECODE) { + decode_buffer = (struct amdgpu_vcn_decode_buffer *)&ib->ptr[idx + 6]; + + if (!(decode_buffer->valid_buf_flag & 0x1)) + return 0; + + addr = ((u64)decode_buffer->msg_buffer_address_hi) << 32 | + decode_buffer->msg_buffer_address_lo; + return vcn_v4_0_dec_msg(p, job, addr); + } else if (val == RADEON_VCN_ENGINE_TYPE_ENCODE) { + sidx = vcn_v4_0_enc_find_ib_param(ib, RENCODE_IB_PARAM_SESSION_INIT, idx); + if (sidx >= 0 && ib->ptr[sidx + 2] == RENCODE_ENCODE_STANDARD_AV1) + return vcn_v4_0_limit_sched(p, job); + } + idx += ib->ptr[idx] / 4; } return 0; } @@ -1986,7 +1977,7 @@ static struct amdgpu_ring_funcs vcn_v4_0_unified_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_ENC, .align_mask = 0x3f, .nop = VCN_ENC_CMD_NO_OP, - .extra_dw = sizeof(struct amdgpu_vcn_rb_metadata), + .extra_bytes = sizeof(struct amdgpu_vcn_rb_metadata), .get_rptr = vcn_v4_0_unified_ring_get_rptr, .get_wptr = vcn_v4_0_unified_ring_get_wptr, .set_wptr = vcn_v4_0_unified_ring_set_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c index 7b93a275ec4f..eacf4e93ba2f 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c @@ -212,7 +212,11 @@ static int vcn_v4_0_3_sw_init(struct amdgpu_ip_block *ip_block) ring->vm_hub = AMDGPU_MMHUB0(adev->vcn.inst[i].aid_id); sprintf(ring->name, "vcn_unified_%d", adev->vcn.inst[i].aid_id); - r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.inst->irq, 0, + + /* There are no per-instance irq source IDs on 4.0.3, the IH + * packets use a separate field to differentiate instances. + */ + r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.inst[0].irq, 0, AMDGPU_RING_PRIO_DEFAULT, &adev->vcn.inst[i].sched_score); if (r) @@ -259,7 +263,7 @@ static int vcn_v4_0_3_sw_fini(struct amdgpu_ip_block *ip_block) if (drm_dev_enter(&adev->ddev, &idx)) { for (i = 0; i < adev->vcn.num_vcn_inst; i++) { - volatile struct amdgpu_vcn4_fw_shared *fw_shared; + struct amdgpu_vcn4_fw_shared *fw_shared; fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; fw_shared->present_flag_0 = 0; @@ -279,11 +283,8 @@ static int vcn_v4_0_3_sw_fini(struct amdgpu_ip_block *ip_block) amdgpu_vcn_sysfs_reset_mask_fini(adev); - for (i = 0; i < adev->vcn.num_vcn_inst; i++) { - r = amdgpu_vcn_sw_fini(adev, i); - if (r) - return r; - } + for (i = 0; i < adev->vcn.num_vcn_inst; i++) + amdgpu_vcn_sw_fini(adev, i); return 0; } @@ -844,7 +845,7 @@ static int vcn_v4_0_3_start_dpg_mode(struct amdgpu_vcn_inst *vinst, { struct amdgpu_device *adev = vinst->adev; int inst_idx = vinst->inst; - volatile struct amdgpu_vcn4_fw_shared *fw_shared = + struct amdgpu_vcn4_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr; struct amdgpu_ring *ring; int vcn_inst, ret; @@ -1011,8 +1012,8 @@ static int vcn_v4_0_3_start_sriov(struct amdgpu_device *adev) struct mmsch_v4_0_cmd_end end = { {0} }; struct mmsch_v4_0_3_init_header header; - volatile struct amdgpu_vcn4_fw_shared *fw_shared; - volatile struct amdgpu_fw_shared_rb_setup *rb_setup; + struct amdgpu_vcn4_fw_shared *fw_shared; + struct amdgpu_fw_shared_rb_setup *rb_setup; direct_wt.cmd_header.command_type = MMSCH_COMMAND__DIRECT_REG_WRITE; @@ -1186,7 +1187,7 @@ static int vcn_v4_0_3_start(struct amdgpu_vcn_inst *vinst) { struct amdgpu_device *adev = vinst->adev; int i = vinst->inst; - volatile struct amdgpu_vcn4_fw_shared *fw_shared; + struct amdgpu_vcn4_fw_shared *fw_shared; struct amdgpu_ring *ring; int j, k, r, vcn_inst; uint32_t tmp; @@ -1396,7 +1397,7 @@ static int vcn_v4_0_3_stop(struct amdgpu_vcn_inst *vinst) { struct amdgpu_device *adev = vinst->adev; int i = vinst->inst; - volatile struct amdgpu_vcn4_fw_shared *fw_shared; + struct amdgpu_vcn4_fw_shared *fw_shared; int r = 0, vcn_inst; uint32_t tmp; diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c index 75c884a8f556..b107ee80e472 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c @@ -149,7 +149,7 @@ static int vcn_v4_0_5_sw_init(struct amdgpu_ip_block *ip_block) int i, r; for (i = 0; i < adev->vcn.num_vcn_inst; i++) { - volatile struct amdgpu_vcn4_fw_shared *fw_shared; + struct amdgpu_vcn4_fw_shared *fw_shared; if (adev->vcn.harvest_config & (1 << i)) continue; @@ -249,7 +249,7 @@ static int vcn_v4_0_5_sw_fini(struct amdgpu_ip_block *ip_block) if (drm_dev_enter(adev_to_drm(adev), &idx)) { for (i = 0; i < adev->vcn.num_vcn_inst; i++) { - volatile struct amdgpu_vcn4_fw_shared *fw_shared; + struct amdgpu_vcn4_fw_shared *fw_shared; if (adev->vcn.harvest_config & (1 << i)) continue; @@ -270,9 +270,7 @@ static int vcn_v4_0_5_sw_fini(struct amdgpu_ip_block *ip_block) if (r) return r; - r = amdgpu_vcn_sw_fini(adev, i); - if (r) - return r; + amdgpu_vcn_sw_fini(adev, i); } return 0; @@ -912,7 +910,7 @@ static int vcn_v4_0_5_start_dpg_mode(struct amdgpu_vcn_inst *vinst, { struct amdgpu_device *adev = vinst->adev; int inst_idx = vinst->inst; - volatile struct amdgpu_vcn4_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr; + struct amdgpu_vcn4_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr; struct amdgpu_ring *ring; uint32_t tmp; int ret; @@ -1049,7 +1047,7 @@ static int vcn_v4_0_5_start(struct amdgpu_vcn_inst *vinst) { struct amdgpu_device *adev = vinst->adev; int i = vinst->inst; - volatile struct amdgpu_vcn4_fw_shared *fw_shared; + struct amdgpu_vcn4_fw_shared *fw_shared; struct amdgpu_ring *ring; uint32_t tmp; int j, k, r; @@ -1268,7 +1266,7 @@ static int vcn_v4_0_5_stop(struct amdgpu_vcn_inst *vinst) { struct amdgpu_device *adev = vinst->adev; int i = vinst->inst; - volatile struct amdgpu_vcn4_fw_shared *fw_shared; + struct amdgpu_vcn4_fw_shared *fw_shared; uint32_t tmp; int r = 0; @@ -1591,7 +1589,7 @@ static int vcn_v4_0_5_set_clockgating_state(struct amdgpu_ip_block *ip_block, enum amd_clockgating_state state) { struct amdgpu_device *adev = ip_block->adev; - bool enable = (state == AMD_CG_STATE_GATE) ? true : false; + bool enable = state == AMD_CG_STATE_GATE; int i; for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c index 455f829b8bb9..0202df5db1e1 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c @@ -129,7 +129,7 @@ static int vcn_v5_0_0_sw_init(struct amdgpu_ip_block *ip_block) int i, r; for (i = 0; i < adev->vcn.num_vcn_inst; i++) { - volatile struct amdgpu_vcn5_fw_shared *fw_shared; + struct amdgpu_vcn5_fw_shared *fw_shared; if (adev->vcn.harvest_config & (1 << i)) continue; @@ -211,7 +211,7 @@ static int vcn_v5_0_0_sw_fini(struct amdgpu_ip_block *ip_block) if (drm_dev_enter(adev_to_drm(adev), &idx)) { for (i = 0; i < adev->vcn.num_vcn_inst; i++) { - volatile struct amdgpu_vcn5_fw_shared *fw_shared; + struct amdgpu_vcn5_fw_shared *fw_shared; if (adev->vcn.harvest_config & (1 << i)) continue; @@ -232,11 +232,8 @@ static int vcn_v5_0_0_sw_fini(struct amdgpu_ip_block *ip_block) amdgpu_vcn_sysfs_reset_mask_fini(adev); - for (i = 0; i < adev->vcn.num_vcn_inst; i++) { - r = amdgpu_vcn_sw_fini(adev, i); - if (r) - return r; - } + for (i = 0; i < adev->vcn.num_vcn_inst; i++) + amdgpu_vcn_sw_fini(adev, i); return 0; } @@ -695,7 +692,7 @@ static int vcn_v5_0_0_start_dpg_mode(struct amdgpu_vcn_inst *vinst, { struct amdgpu_device *adev = vinst->adev; int inst_idx = vinst->inst; - volatile struct amdgpu_vcn5_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr; + struct amdgpu_vcn5_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr; struct amdgpu_ring *ring; uint32_t tmp; int ret; @@ -805,7 +802,7 @@ static int vcn_v5_0_0_start(struct amdgpu_vcn_inst *vinst) { struct amdgpu_device *adev = vinst->adev; int i = vinst->inst; - volatile struct amdgpu_vcn5_fw_shared *fw_shared; + struct amdgpu_vcn5_fw_shared *fw_shared; struct amdgpu_ring *ring; uint32_t tmp; int j, k, r; @@ -998,7 +995,7 @@ static int vcn_v5_0_0_stop(struct amdgpu_vcn_inst *vinst) { struct amdgpu_device *adev = vinst->adev; int i = vinst->inst; - volatile struct amdgpu_vcn5_fw_shared *fw_shared; + struct amdgpu_vcn5_fw_shared *fw_shared; uint32_t tmp; int r = 0; @@ -1311,7 +1308,7 @@ static int vcn_v5_0_0_set_clockgating_state(struct amdgpu_ip_block *ip_block, enum amd_clockgating_state state) { struct amdgpu_device *adev = ip_block->adev; - bool enable = (state == AMD_CG_STATE_GATE) ? true : false; + bool enable = state == AMD_CG_STATE_GATE; int i; for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c index 4b01e35ad7ef..9c281ba6bced 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c @@ -226,7 +226,7 @@ static int vcn_v5_0_1_sw_fini(struct amdgpu_ip_block *ip_block) if (drm_dev_enter(adev_to_drm(adev), &idx)) { for (i = 0; i < adev->vcn.num_vcn_inst; i++) { - volatile struct amdgpu_vcn5_fw_shared *fw_shared; + struct amdgpu_vcn5_fw_shared *fw_shared; fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; fw_shared->present_flag_0 = 0; @@ -245,14 +245,11 @@ static int vcn_v5_0_1_sw_fini(struct amdgpu_ip_block *ip_block) return r; } - for (i = 0; i < adev->vcn.num_vcn_inst; i++) { - r = amdgpu_vcn_sw_fini(adev, i); - if (r) - return r; - } - amdgpu_vcn_sysfs_reset_mask_fini(adev); + for (i = 0; i < adev->vcn.num_vcn_inst; i++) + amdgpu_vcn_sw_fini(adev, i); + return 0; } @@ -643,7 +640,7 @@ static int vcn_v5_0_1_start_dpg_mode(struct amdgpu_vcn_inst *vinst, { struct amdgpu_device *adev = vinst->adev; int inst_idx = vinst->inst; - volatile struct amdgpu_vcn5_fw_shared *fw_shared = + struct amdgpu_vcn5_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr; struct amdgpu_ring *ring; struct dpg_pause_state state = {.fw_based = VCN_DPG_STATE__PAUSE}; @@ -779,8 +776,8 @@ static int vcn_v5_0_1_start_sriov(struct amdgpu_device *adev) struct mmsch_v5_0_cmd_end end = { {0} }; struct mmsch_v5_0_init_header header; - volatile struct amdgpu_vcn5_fw_shared *fw_shared; - volatile struct amdgpu_fw_shared_rb_setup *rb_setup; + struct amdgpu_vcn5_fw_shared *fw_shared; + struct amdgpu_fw_shared_rb_setup *rb_setup; direct_wt.cmd_header.command_type = MMSCH_COMMAND__DIRECT_REG_WRITE; @@ -954,7 +951,7 @@ static int vcn_v5_0_1_start(struct amdgpu_vcn_inst *vinst) { struct amdgpu_device *adev = vinst->adev; int i = vinst->inst; - volatile struct amdgpu_vcn5_fw_shared *fw_shared; + struct amdgpu_vcn5_fw_shared *fw_shared; struct amdgpu_ring *ring; uint32_t tmp; int j, k, r, vcn_inst; @@ -1146,7 +1143,7 @@ static int vcn_v5_0_1_stop(struct amdgpu_vcn_inst *vinst) { struct amdgpu_device *adev = vinst->adev; int i = vinst->inst; - volatile struct amdgpu_vcn5_fw_shared *fw_shared; + struct amdgpu_vcn5_fw_shared *fw_shared; uint32_t tmp; int r = 0, vcn_inst; diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c index 9b3510e53112..a611a7345125 100644 --- a/drivers/gpu/drm/amd/amdgpu/vi.c +++ b/drivers/gpu/drm/amd/amdgpu/vi.c @@ -67,7 +67,6 @@ #include "sdma_v2_4.h" #include "sdma_v3_0.h" #include "dce_v10_0.h" -#include "dce_v11_0.h" #include "iceland_ih.h" #include "tonga_ih.h" #include "cz_ih.h" @@ -2124,8 +2123,6 @@ int vi_set_ip_blocks(struct amdgpu_device *adev) else if (amdgpu_device_has_dc_support(adev)) amdgpu_device_ip_block_add(adev, &dm_ip_block); #endif - else - amdgpu_device_ip_block_add(adev, &dce_v11_2_ip_block); amdgpu_device_ip_block_add(adev, &uvd_v6_3_ip_block); amdgpu_device_ip_block_add(adev, &vce_v3_4_ip_block); break; @@ -2142,8 +2139,6 @@ int vi_set_ip_blocks(struct amdgpu_device *adev) else if (amdgpu_device_has_dc_support(adev)) amdgpu_device_ip_block_add(adev, &dm_ip_block); #endif - else - amdgpu_device_ip_block_add(adev, &dce_v11_0_ip_block); amdgpu_device_ip_block_add(adev, &uvd_v6_0_ip_block); amdgpu_device_ip_block_add(adev, &vce_v3_1_ip_block); #if defined(CONFIG_DRM_AMD_ACP) @@ -2163,8 +2158,6 @@ int vi_set_ip_blocks(struct amdgpu_device *adev) else if (amdgpu_device_has_dc_support(adev)) amdgpu_device_ip_block_add(adev, &dm_ip_block); #endif - else - amdgpu_device_ip_block_add(adev, &dce_v11_0_ip_block); amdgpu_device_ip_block_add(adev, &uvd_v6_2_ip_block); amdgpu_device_ip_block_add(adev, &vce_v3_4_ip_block); #if defined(CONFIG_DRM_AMD_ACP) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index 43115a374469..0f0719528bcc 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -521,15 +521,10 @@ static int kfd_ioctl_set_cu_mask(struct file *filp, struct kfd_process *p, cu_mask_size = sizeof(uint32_t) * (max_num_cus/32); } - minfo.cu_mask.ptr = kzalloc(cu_mask_size, GFP_KERNEL); - if (!minfo.cu_mask.ptr) - return -ENOMEM; - - retval = copy_from_user(minfo.cu_mask.ptr, cu_mask_ptr, cu_mask_size); - if (retval) { + minfo.cu_mask.ptr = memdup_user(cu_mask_ptr, cu_mask_size); + if (IS_ERR(minfo.cu_mask.ptr)) { pr_debug("Could not copy CU mask from userspace"); - retval = -EFAULT; - goto out; + return PTR_ERR(minfo.cu_mask.ptr); } mutex_lock(&p->mutex); @@ -538,7 +533,6 @@ static int kfd_ioctl_set_cu_mask(struct file *filp, struct kfd_process *p, mutex_unlock(&p->mutex); -out: kfree(minfo.cu_mask.ptr); return retval; } @@ -2571,8 +2565,8 @@ static int criu_restore(struct file *filep, pr_debug("CRIU restore (num_devices:%u num_bos:%u num_objects:%u priv_data_size:%llu)\n", args->num_devices, args->num_bos, args->num_objects, args->priv_data_size); - if (!args->bos || !args->devices || !args->priv_data || !args->priv_data_size || - !args->num_devices || !args->num_bos) + if ((args->num_bos > 0 && !args->bos) || !args->devices || !args->priv_data || + !args->priv_data_size || !args->num_devices) return -EINVAL; mutex_lock(&p->mutex); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index 7e749f9b6d69..349c351e242b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -1550,6 +1550,25 @@ int kgd2kfd_start_sched(struct kfd_dev *kfd, uint32_t node_id) return ret; } +int kgd2kfd_start_sched_all_nodes(struct kfd_dev *kfd) +{ + struct kfd_node *node; + int i, r; + + if (!kfd->init_complete) + return 0; + + for (i = 0; i < kfd->num_nodes; i++) { + node = kfd->nodes[i]; + r = node->dqm->ops.unhalt(node->dqm); + if (r) { + dev_err(kfd_device, "Error in starting scheduler\n"); + return r; + } + } + return 0; +} + int kgd2kfd_stop_sched(struct kfd_dev *kfd, uint32_t node_id) { struct kfd_node *node; @@ -1567,6 +1586,23 @@ int kgd2kfd_stop_sched(struct kfd_dev *kfd, uint32_t node_id) return node->dqm->ops.halt(node->dqm); } +int kgd2kfd_stop_sched_all_nodes(struct kfd_dev *kfd) +{ + struct kfd_node *node; + int i, r; + + if (!kfd->init_complete) + return 0; + + for (i = 0; i < kfd->num_nodes; i++) { + node = kfd->nodes[i]; + r = node->dqm->ops.halt(node->dqm); + if (r) + return r; + } + return 0; +} + bool kgd2kfd_compute_active(struct kfd_dev *kfd, uint32_t node_id) { struct kfd_node *node; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c index 5d7eb0234002..59a5a3fea65d 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c @@ -39,22 +39,22 @@ #endif #define dev_fmt(fmt) "kfd_migrate: " fmt -static uint64_t -svm_migrate_direct_mapping_addr(struct amdgpu_device *adev, uint64_t addr) +static u64 +svm_migrate_direct_mapping_addr(struct amdgpu_device *adev, u64 addr) { return addr + amdgpu_ttm_domain_start(adev, TTM_PL_VRAM); } static int -svm_migrate_gart_map(struct amdgpu_ring *ring, uint64_t npages, - dma_addr_t *addr, uint64_t *gart_addr, uint64_t flags) +svm_migrate_gart_map(struct amdgpu_ring *ring, u64 npages, + dma_addr_t *addr, u64 *gart_addr, u64 flags) { struct amdgpu_device *adev = ring->adev; struct amdgpu_job *job; unsigned int num_dw, num_bytes; struct dma_fence *fence; - uint64_t src_addr, dst_addr; - uint64_t pte_flags; + u64 src_addr, dst_addr; + u64 pte_flags; void *cpu_addr; int r; @@ -68,7 +68,8 @@ svm_migrate_gart_map(struct amdgpu_ring *ring, uint64_t npages, AMDGPU_FENCE_OWNER_UNDEFINED, num_dw * 4 + num_bytes, AMDGPU_IB_POOL_DELAYED, - &job); + &job, + AMDGPU_KERNEL_JOB_ID_KFD_GART_MAP); if (r) return r; @@ -122,15 +123,15 @@ svm_migrate_gart_map(struct amdgpu_ring *ring, uint64_t npages, static int svm_migrate_copy_memory_gart(struct amdgpu_device *adev, dma_addr_t *sys, - uint64_t *vram, uint64_t npages, + u64 *vram, u64 npages, enum MIGRATION_COPY_DIR direction, struct dma_fence **mfence) { - const uint64_t GTT_MAX_PAGES = AMDGPU_GTT_MAX_TRANSFER_SIZE; + const u64 GTT_MAX_PAGES = AMDGPU_GTT_MAX_TRANSFER_SIZE; struct amdgpu_ring *ring = adev->mman.buffer_funcs_ring; - uint64_t gart_s, gart_d; + u64 gart_s, gart_d; struct dma_fence *next; - uint64_t size; + u64 size; int r; mutex_lock(&adev->mman.gtt_window_lock); @@ -260,30 +261,42 @@ static void svm_migrate_put_sys_page(unsigned long addr) put_page(page); } -static long +static unsigned long svm_migrate_successful_pages(struct migrate_vma *migrate) +{ + unsigned long mpages = 0; + unsigned long i; + + for (i = 0; i < migrate->npages; i++) { + if (migrate->dst[i] & MIGRATE_PFN_VALID && + migrate->src[i] & MIGRATE_PFN_MIGRATE) + mpages++; + } + return mpages; +} + +static int svm_migrate_copy_to_vram(struct kfd_node *node, struct svm_range *prange, struct migrate_vma *migrate, struct dma_fence **mfence, - dma_addr_t *scratch, uint64_t ttm_res_offset) + dma_addr_t *scratch, u64 ttm_res_offset) { - uint64_t npages = migrate->npages; + u64 npages = migrate->npages; struct amdgpu_device *adev = node->adev; struct device *dev = adev->dev; struct amdgpu_res_cursor cursor; - long mpages; + u64 mpages = 0; dma_addr_t *src; - uint64_t *dst; - uint64_t i, j; + u64 *dst; + u64 i, j; int r; pr_debug("svms 0x%p [0x%lx 0x%lx 0x%llx]\n", prange->svms, prange->start, prange->last, ttm_res_offset); src = scratch; - dst = (uint64_t *)(scratch + npages); + dst = (u64 *)(scratch + npages); amdgpu_res_first(prange->ttm_res, ttm_res_offset, npages << PAGE_SHIFT, &cursor); - mpages = 0; for (i = j = 0; (i < npages) && (mpages < migrate->cpages); i++) { struct page *spage; @@ -344,14 +357,13 @@ svm_migrate_copy_to_vram(struct kfd_node *node, struct svm_range *prange, out_free_vram_pages: if (r) { pr_debug("failed %d to copy memory to vram\n", r); - while (i-- && mpages) { + for (i = 0; i < npages && mpages; i++) { if (!dst[i]) continue; svm_migrate_put_vram_page(adev, dst[i]); migrate->dst[i] = 0; mpages--; } - mpages = r; } #ifdef DEBUG_FORCE_MIXED_DOMAINS @@ -369,22 +381,22 @@ out_free_vram_pages: } #endif - return mpages; + return r; } static long svm_migrate_vma_to_vram(struct kfd_node *node, struct svm_range *prange, - struct vm_area_struct *vma, uint64_t start, - uint64_t end, uint32_t trigger, uint64_t ttm_res_offset) + struct vm_area_struct *vma, u64 start, + u64 end, uint32_t trigger, u64 ttm_res_offset) { struct kfd_process *p = container_of(prange->svms, struct kfd_process, svms); - uint64_t npages = (end - start) >> PAGE_SHIFT; + u64 npages = (end - start) >> PAGE_SHIFT; struct amdgpu_device *adev = node->adev; struct kfd_process_device *pdd; struct dma_fence *mfence = NULL; struct migrate_vma migrate = { 0 }; unsigned long cpages = 0; - long mpages = 0; + unsigned long mpages = 0; dma_addr_t *scratch; void *buf; int r = -ENOMEM; @@ -397,7 +409,7 @@ svm_migrate_vma_to_vram(struct kfd_node *node, struct svm_range *prange, migrate.pgmap_owner = SVM_ADEV_PGMAP_OWNER(adev); buf = kvcalloc(npages, - 2 * sizeof(*migrate.src) + sizeof(uint64_t) + sizeof(dma_addr_t), + 2 * sizeof(*migrate.src) + sizeof(u64) + sizeof(dma_addr_t), GFP_KERNEL); if (!buf) goto out; @@ -430,17 +442,15 @@ svm_migrate_vma_to_vram(struct kfd_node *node, struct svm_range *prange, else pr_debug("0x%lx pages collected\n", cpages); - mpages = svm_migrate_copy_to_vram(node, prange, &migrate, &mfence, scratch, ttm_res_offset); + r = svm_migrate_copy_to_vram(node, prange, &migrate, &mfence, scratch, ttm_res_offset); migrate_vma_pages(&migrate); svm_migrate_copy_done(adev, mfence); migrate_vma_finalize(&migrate); - if (mpages >= 0) - pr_debug("migrated/collected/requested 0x%lx/0x%lx/0x%lx\n", - mpages, cpages, migrate.npages); - else - r = mpages; + mpages = svm_migrate_successful_pages(&migrate); + pr_debug("migrated/collected/requested 0x%lx/0x%lx/0x%lx\n", + mpages, cpages, migrate.npages); svm_range_dma_unmap_dev(adev->dev, scratch, 0, npages); @@ -450,13 +460,14 @@ out_free: start >> PAGE_SHIFT, end >> PAGE_SHIFT, 0, node->id, trigger, r); out: - if (!r && mpages > 0) { + if (!r && mpages) { pdd = svm_range_get_pdd_by_node(prange, node); if (pdd) WRITE_ONCE(pdd->page_in, pdd->page_in + mpages); - } - return r ? r : mpages; + return mpages; + } + return r; } /** @@ -480,7 +491,7 @@ svm_migrate_ram_to_vram(struct svm_range *prange, uint32_t best_loc, { unsigned long addr, start, end; struct vm_area_struct *vma; - uint64_t ttm_res_offset; + u64 ttm_res_offset; struct kfd_node *node; unsigned long mpages = 0; long r = 0; @@ -567,18 +578,17 @@ static void svm_migrate_page_free(struct page *page) } } -static long +static int svm_migrate_copy_to_ram(struct amdgpu_device *adev, struct svm_range *prange, struct migrate_vma *migrate, struct dma_fence **mfence, - dma_addr_t *scratch, uint64_t npages) + dma_addr_t *scratch, u64 npages) { struct device *dev = adev->dev; - uint64_t *src; + u64 *src; dma_addr_t *dst; struct page *dpage; - long mpages; - uint64_t i = 0, j; - uint64_t addr; + u64 i = 0, j; + u64 addr; int r = 0; pr_debug("svms 0x%p [0x%lx 0x%lx]\n", prange->svms, prange->start, @@ -586,10 +596,9 @@ svm_migrate_copy_to_ram(struct amdgpu_device *adev, struct svm_range *prange, addr = migrate->start; - src = (uint64_t *)(scratch + npages); + src = (u64 *)(scratch + npages); dst = scratch; - mpages = 0; for (i = 0, j = 0; i < npages; i++, addr += PAGE_SIZE) { struct page *spage; @@ -638,7 +647,6 @@ svm_migrate_copy_to_ram(struct amdgpu_device *adev, struct svm_range *prange, dst[i] >> PAGE_SHIFT, page_to_pfn(dpage)); migrate->dst[i] = migrate_pfn(page_to_pfn(dpage)); - mpages++; j++; } @@ -648,17 +656,13 @@ svm_migrate_copy_to_ram(struct amdgpu_device *adev, struct svm_range *prange, out_oom: if (r) { pr_debug("failed %d copy to ram\n", r); - while (i-- && mpages) { - if (!migrate->dst[i]) - continue; + while (i--) { svm_migrate_put_sys_page(dst[i]); migrate->dst[i] = 0; - mpages--; } - mpages = r; } - return mpages; + return r; } /** @@ -680,13 +684,13 @@ out_oom: */ static long svm_migrate_vma_to_ram(struct kfd_node *node, struct svm_range *prange, - struct vm_area_struct *vma, uint64_t start, uint64_t end, + struct vm_area_struct *vma, u64 start, u64 end, uint32_t trigger, struct page *fault_page) { struct kfd_process *p = container_of(prange->svms, struct kfd_process, svms); - uint64_t npages = (end - start) >> PAGE_SHIFT; + u64 npages = (end - start) >> PAGE_SHIFT; unsigned long cpages = 0; - long mpages = 0; + unsigned long mpages = 0; struct amdgpu_device *adev = node->adev; struct kfd_process_device *pdd; struct dma_fence *mfence = NULL; @@ -706,7 +710,7 @@ svm_migrate_vma_to_ram(struct kfd_node *node, struct svm_range *prange, migrate.flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE; buf = kvcalloc(npages, - 2 * sizeof(*migrate.src) + sizeof(uint64_t) + sizeof(dma_addr_t), + 2 * sizeof(*migrate.src) + sizeof(u64) + sizeof(dma_addr_t), GFP_KERNEL); if (!buf) goto out; @@ -740,15 +744,13 @@ svm_migrate_vma_to_ram(struct kfd_node *node, struct svm_range *prange, else pr_debug("0x%lx pages collected\n", cpages); - mpages = svm_migrate_copy_to_ram(adev, prange, &migrate, &mfence, + r = svm_migrate_copy_to_ram(adev, prange, &migrate, &mfence, scratch, npages); migrate_vma_pages(&migrate); - if (mpages >= 0) - pr_debug("migrated/collected/requested 0x%lx/0x%lx/0x%lx\n", + mpages = svm_migrate_successful_pages(&migrate); + pr_debug("migrated/collected/requested 0x%lx/0x%lx/0x%lx\n", mpages, cpages, migrate.npages); - else - r = mpages; svm_migrate_copy_done(adev, mfence); migrate_vma_finalize(&migrate); @@ -761,7 +763,7 @@ out_free: start >> PAGE_SHIFT, end >> PAGE_SHIFT, node->id, 0, trigger, r); out: - if (!r && mpages > 0) { + if (!r && mpages) { pdd = svm_range_get_pdd_by_node(prange, node); if (pdd) WRITE_ONCE(pdd->page_out, pdd->page_out + mpages); @@ -845,8 +847,8 @@ int svm_migrate_vram_to_ram(struct svm_range *prange, struct mm_struct *mm, if (r >= 0) { WARN_ONCE(prange->vram_pages < mpages, - "Recorded vram pages(0x%llx) should not be less than migration pages(0x%lx).", - prange->vram_pages, mpages); + "Recorded vram pages(0x%llx) should not be less than migration pages(0x%lx).", + prange->vram_pages, mpages); prange->vram_pages -= mpages; /* prange does not have vram page set its actual_loc to system diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index 521c14c7a789..68ba239b2e5d 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -4261,7 +4261,7 @@ svm_ioctl(struct kfd_process *p, enum kfd_ioctl_svm_op op, uint64_t start, r = svm_range_get_attr(p, mm, start, size, nattrs, attrs); break; default: - r = EINVAL; + r = -EINVAL; break; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c index 82dbd68d8c99..5c98746eb72d 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c @@ -1589,7 +1589,8 @@ static int kfd_dev_create_p2p_links(void) break; if (!dev->gpu || !dev->gpu->adev || (dev->gpu->kfd->hive_id && - dev->gpu->kfd->hive_id == new_dev->gpu->kfd->hive_id)) + dev->gpu->kfd->hive_id == new_dev->gpu->kfd->hive_id && + amdgpu_xgmi_get_is_sharing_enabled(dev->gpu->adev, new_dev->gpu->adev))) goto next; /* check if node(s) is/are peer accessible in one direction or bi-direction */ 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 242f98564261..7012b2c692b3 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2081,6 +2081,8 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) dc_hardware_init(adev->dm.dc); + adev->dm.restore_backlight = true; + adev->dm.hpd_rx_offload_wq = hpd_rx_irq_create_workqueue(adev); if (!adev->dm.hpd_rx_offload_wq) { drm_err(adev_to_drm(adev), "failed to create hpd rx offload workqueue.\n"); @@ -2186,7 +2188,7 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) if (drm_vblank_init(adev_to_drm(adev), adev->dm.display_indexes_num)) { drm_err(adev_to_drm(adev), - "failed to initialize sw for display support.\n"); + "failed to initialize vblank for display support.\n"); goto error; } @@ -2945,7 +2947,7 @@ static int dm_oem_i2c_hw_init(struct amdgpu_device *adev) return -ENOMEM; } - r = i2c_add_adapter(&oem_i2c->base); + r = devm_i2c_add_adapter(adev->dev, &oem_i2c->base); if (r) { drm_info(adev_to_drm(adev), "Failed to register oem i2c\n"); kfree(oem_i2c); @@ -3007,8 +3009,6 @@ static int dm_hw_fini(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; - kfree(adev->dm.oem_i2c); - amdgpu_dm_hpd_fini(adev); amdgpu_dm_irq_fini(adev); @@ -3036,14 +3036,20 @@ static void dm_gpureset_toggle_interrupts(struct amdgpu_device *adev, drm_warn(adev_to_drm(adev), "Failed to %s pflip interrupts\n", enable ? "enable" : "disable"); - if (enable) { - if (amdgpu_dm_crtc_vrr_active(to_dm_crtc_state(acrtc->base.state))) - rc = amdgpu_dm_crtc_set_vupdate_irq(&acrtc->base, true); - } else - rc = amdgpu_dm_crtc_set_vupdate_irq(&acrtc->base, false); - - if (rc) - drm_warn(adev_to_drm(adev), "Failed to %sable vupdate interrupt\n", enable ? "en" : "dis"); + if (dc_supports_vrr(adev->dm.dc->ctx->dce_version)) { + if (enable) { + if (amdgpu_dm_crtc_vrr_active( + to_dm_crtc_state(acrtc->base.state))) + rc = amdgpu_dm_crtc_set_vupdate_irq( + &acrtc->base, true); + } else + rc = amdgpu_dm_crtc_set_vupdate_irq( + &acrtc->base, false); + + if (rc) + drm_warn(adev_to_drm(adev), "Failed to %sable vupdate interrupt\n", + enable ? "en" : "dis"); + } irq_source = IRQ_TYPE_VBLANK + acrtc->otg_inst; /* During gpu-reset we disable and then enable vblank irq, so @@ -3171,25 +3177,6 @@ static void dm_destroy_cached_state(struct amdgpu_device *adev) dm->cached_state = NULL; } -static void dm_complete(struct amdgpu_ip_block *ip_block) -{ - struct amdgpu_device *adev = ip_block->adev; - - dm_destroy_cached_state(adev); -} - -static int dm_prepare_suspend(struct amdgpu_ip_block *ip_block) -{ - struct amdgpu_device *adev = ip_block->adev; - - if (amdgpu_in_reset(adev)) - return 0; - - WARN_ON(adev->dm.cached_state); - - return dm_cache_state(adev); -} - static int dm_suspend(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; @@ -3451,6 +3438,7 @@ static int dm_resume(struct amdgpu_ip_block *ip_block) dc_set_power_state(dm->dc, DC_ACPI_CM_POWER_STATE_D0); dc_resume(dm->dc); + adev->dm.restore_backlight = true; amdgpu_dm_irq_resume_early(adev); @@ -3615,10 +3603,8 @@ static const struct amd_ip_funcs amdgpu_dm_funcs = { .early_fini = amdgpu_dm_early_fini, .hw_init = dm_hw_init, .hw_fini = dm_hw_fini, - .prepare_suspend = dm_prepare_suspend, .suspend = dm_suspend, .resume = dm_resume, - .complete = dm_complete, .is_idle = dm_is_idle, .wait_for_idle = dm_wait_for_idle, .check_soft_reset = dm_check_soft_reset, @@ -3656,18 +3642,20 @@ static struct drm_mode_config_helper_funcs amdgpu_dm_mode_config_helperfuncs = { static void update_connector_ext_caps(struct amdgpu_dm_connector *aconnector) { + const struct drm_panel_backlight_quirk *panel_backlight_quirk; struct amdgpu_dm_backlight_caps *caps; struct drm_connector *conn_base; struct amdgpu_device *adev; struct drm_luminance_range_info *luminance_range; - int min_input_signal_override; + struct drm_device *drm; if (aconnector->bl_idx == -1 || aconnector->dc_link->connector_signal != SIGNAL_TYPE_EDP) return; conn_base = &aconnector->base; - adev = drm_to_adev(conn_base->dev); + drm = conn_base->dev; + adev = drm_to_adev(drm); caps = &adev->dm.backlight_caps[aconnector->bl_idx]; caps->ext_caps = &aconnector->dc_link->dpcd_sink_ext_caps; @@ -3700,9 +3688,24 @@ static void update_connector_ext_caps(struct amdgpu_dm_connector *aconnector) else caps->aux_min_input_signal = 1; - min_input_signal_override = drm_get_panel_min_brightness_quirk(aconnector->drm_edid); - if (min_input_signal_override >= 0) - caps->min_input_signal = min_input_signal_override; + panel_backlight_quirk = + drm_get_panel_backlight_quirk(aconnector->drm_edid); + if (!IS_ERR_OR_NULL(panel_backlight_quirk)) { + if (panel_backlight_quirk->min_brightness) { + caps->min_input_signal = + panel_backlight_quirk->min_brightness - 1; + drm_info(drm, + "Applying panel backlight quirk, min_brightness: %d\n", + caps->min_input_signal); + } + if (panel_backlight_quirk->brightness_mask) { + drm_info(drm, + "Applying panel backlight quirk, brightness_mask: 0x%X\n", + panel_backlight_quirk->brightness_mask); + caps->brightness_mask = + panel_backlight_quirk->brightness_mask; + } + } } DEFINE_FREE(sink_release, struct dc_sink *, if (_T) dc_sink_release(_T)) @@ -4914,6 +4917,10 @@ static void amdgpu_dm_backlight_set_level(struct amdgpu_display_manager *dm, brightness = convert_brightness_from_user(caps, dm->brightness[bl_idx]); link = (struct dc_link *)dm->backlight_link[bl_idx]; + /* Apply brightness quirk */ + if (caps->brightness_mask) + brightness |= caps->brightness_mask; + /* Change brightness based on AUX property */ mutex_lock(&dm->dc_lock); if (dm->dc->caps.ips_support && dm->dc->ctx->dmub_srv->idle_allowed) { @@ -5049,8 +5056,11 @@ amdgpu_dm_register_backlight_device(struct amdgpu_dm_connector *aconnector) } else props.brightness = props.max_brightness = MAX_BACKLIGHT_LEVEL; - if (caps->data_points && !(amdgpu_dc_debug_mask & DC_DISABLE_CUSTOM_BRIGHTNESS_CURVE)) + if (caps->data_points && !(amdgpu_dc_debug_mask & DC_DISABLE_CUSTOM_BRIGHTNESS_CURVE)) { drm_info(drm, "Using custom brightness curve\n"); + props.scale = BACKLIGHT_SCALE_NON_LINEAR; + } else + props.scale = BACKLIGHT_SCALE_LINEAR; props.type = BACKLIGHT_RAW; snprintf(bl_name, sizeof(bl_name), "amdgpu_bl%d", @@ -6413,6 +6423,10 @@ static void fill_stream_properties_from_drm_display_mode( && aconnector && aconnector->force_yuv420_output) timing_out->pixel_encoding = PIXEL_ENCODING_YCBCR420; + else if ((connector->display_info.color_formats & DRM_COLOR_FORMAT_YCBCR422) + && aconnector + && aconnector->force_yuv422_output) + timing_out->pixel_encoding = PIXEL_ENCODING_YCBCR422; else if ((connector->display_info.color_formats & DRM_COLOR_FORMAT_YCBCR444) && stream->signal == SIGNAL_TYPE_HDMI_TYPE_A) timing_out->pixel_encoding = PIXEL_ENCODING_YCBCR444; @@ -7370,10 +7384,6 @@ static void amdgpu_dm_connector_destroy(struct drm_connector *connector) drm_dp_cec_unregister_connector(&aconnector->dm_dp_aux.aux); drm_connector_unregister(connector); drm_connector_cleanup(connector); - if (aconnector->i2c) { - i2c_del_adapter(&aconnector->i2c->base); - kfree(aconnector->i2c); - } kfree(aconnector->dm_dp_aux.aux.name); kfree(connector); @@ -7673,6 +7683,7 @@ create_validate_stream_for_sink(struct drm_connector *connector, bpc_limit = 8; do { + drm_dbg_kms(connector->dev, "Trying with %d bpc\n", requested_bpc); stream = create_stream_for_sink(connector, drm_mode, dm_state, old_stream, requested_bpc); @@ -7708,16 +7719,41 @@ create_validate_stream_for_sink(struct drm_connector *connector, } while (stream == NULL && requested_bpc >= bpc_limit); - if ((dc_result == DC_FAIL_ENC_VALIDATE || - dc_result == DC_EXCEED_DONGLE_CAP) && - !aconnector->force_yuv420_output) { - DRM_DEBUG_KMS("%s:%d Retry forcing yuv420 encoding\n", - __func__, __LINE__); - - aconnector->force_yuv420_output = true; + switch (dc_result) { + /* + * If we failed to validate DP bandwidth stream with the requested RGB color depth, + * we try to fallback and configure in order: + * YUV422 (8bpc, 6bpc) + * YUV420 (8bpc, 6bpc) + */ + case DC_FAIL_ENC_VALIDATE: + case DC_EXCEED_DONGLE_CAP: + case DC_NO_DP_LINK_BANDWIDTH: + /* recursively entered twice and already tried both YUV422 and YUV420 */ + if (aconnector->force_yuv422_output && aconnector->force_yuv420_output) + break; + /* first failure; try YUV422 */ + if (!aconnector->force_yuv422_output) { + drm_dbg_kms(connector->dev, "%s:%d Validation failed with %d, retrying w/ YUV422\n", + __func__, __LINE__, dc_result); + aconnector->force_yuv422_output = true; + /* recursively entered and YUV422 failed, try YUV420 */ + } else if (!aconnector->force_yuv420_output) { + drm_dbg_kms(connector->dev, "%s:%d Validation failed with %d, retrying w/ YUV420\n", + __func__, __LINE__, dc_result); + aconnector->force_yuv420_output = true; + } stream = create_validate_stream_for_sink(connector, drm_mode, - dm_state, old_stream); + dm_state, old_stream); + aconnector->force_yuv422_output = false; aconnector->force_yuv420_output = false; + break; + case DC_OK: + break; + default: + drm_dbg_kms(connector->dev, "%s:%d Unhandled validation failure %d\n", + __func__, __LINE__, dc_result); + break; } return stream; @@ -8001,7 +8037,7 @@ static int dm_encoder_helper_atomic_check(struct drm_encoder *encoder, if (IS_ERR(mst_state)) return PTR_ERR(mst_state); - mst_state->pbn_div.full = dfixed_const(dm_mst_get_pbn_divider(aconnector->mst_root->dc_link)); + mst_state->pbn_div.full = dm_mst_get_pbn_divider(aconnector->mst_root->dc_link); if (!state->duplicated) { int max_bpc = conn_state->max_requested_bpc; @@ -8705,7 +8741,7 @@ static int amdgpu_dm_connector_init(struct amdgpu_display_manager *dm, } aconnector->i2c = i2c; - res = i2c_add_adapter(&i2c->base); + res = devm_i2c_add_adapter(dm->adev->dev, &i2c->base); if (res) { drm_err(adev_to_drm(dm->adev), "Failed to register hw i2c %d\n", link->link_index); @@ -8803,7 +8839,16 @@ static int amdgpu_dm_encoder_init(struct drm_device *dev, static void manage_dm_interrupts(struct amdgpu_device *adev, struct amdgpu_crtc *acrtc, struct dm_crtc_state *acrtc_state) -{ +{ /* + * We cannot be sure that the frontend index maps to the same + * backend index - some even map to more than one. + * So we have to go through the CRTC to find the right IRQ. + */ + int irq_type = amdgpu_display_crtc_idx_to_irq_type( + adev, + acrtc->crtc_id); + struct drm_device *dev = adev_to_drm(adev); + struct drm_vblank_crtc_config config = {0}; struct dc_crtc_timing *timing; int offdelay; @@ -8856,7 +8901,35 @@ static void manage_dm_interrupts(struct amdgpu_device *adev, drm_crtc_vblank_on_config(&acrtc->base, &config); + /* Allow RX6xxx, RX7700, RX7800 GPUs to call amdgpu_irq_get.*/ + switch (amdgpu_ip_version(adev, DCE_HWIP, 0)) { + case IP_VERSION(3, 0, 0): + case IP_VERSION(3, 0, 2): + case IP_VERSION(3, 0, 3): + case IP_VERSION(3, 2, 0): + if (amdgpu_irq_get(adev, &adev->pageflip_irq, irq_type)) + drm_err(dev, "DM_IRQ: Cannot get pageflip irq!\n"); +#if defined(CONFIG_DRM_AMD_SECURE_DISPLAY) + if (amdgpu_irq_get(adev, &adev->vline0_irq, irq_type)) + drm_err(dev, "DM_IRQ: Cannot get vline0 irq!\n"); +#endif + } + } else { + /* Allow RX6xxx, RX7700, RX7800 GPUs to call amdgpu_irq_put.*/ + switch (amdgpu_ip_version(adev, DCE_HWIP, 0)) { + case IP_VERSION(3, 0, 0): + case IP_VERSION(3, 0, 2): + case IP_VERSION(3, 0, 3): + case IP_VERSION(3, 2, 0): +#if defined(CONFIG_DRM_AMD_SECURE_DISPLAY) + if (amdgpu_irq_put(adev, &adev->vline0_irq, irq_type)) + drm_err(dev, "DM_IRQ: Cannot put vline0 irq!\n"); +#endif + if (amdgpu_irq_put(adev, &adev->pageflip_irq, irq_type)) + drm_err(dev, "DM_IRQ: Cannot put pageflip irq!\n"); + } + drm_crtc_vblank_off(&acrtc->base); } } @@ -9878,7 +9951,6 @@ static void amdgpu_dm_commit_streams(struct drm_atomic_state *state, bool mode_set_reset_required = false; u32 i; struct dc_commit_streams_params params = {dc_state->streams, dc_state->stream_count}; - bool set_backlight_level = false; /* Disable writeback */ for_each_old_connector_in_state(state, connector, old_con_state, i) { @@ -9998,7 +10070,6 @@ static void amdgpu_dm_commit_streams(struct drm_atomic_state *state, acrtc->hw_mode = new_crtc_state->mode; crtc->hwmode = new_crtc_state->mode; mode_set_reset_required = true; - set_backlight_level = true; } else if (modereset_required(new_crtc_state)) { drm_dbg_atomic(dev, "Atomic commit: RESET. crtc id %d:[%p]\n", @@ -10055,13 +10126,16 @@ static void amdgpu_dm_commit_streams(struct drm_atomic_state *state, * to fix a flicker issue. * It will cause the dm->actual_brightness is not the current panel brightness * level. (the dm->brightness is the correct panel level) - * So we set the backlight level with dm->brightness value after set mode + * So we set the backlight level with dm->brightness value after initial + * set mode. Use restore_backlight flag to avoid setting backlight level + * for every subsequent mode set. */ - if (set_backlight_level) { + if (dm->restore_backlight) { for (i = 0; i < dm->num_of_edps; i++) { if (dm->backlight_dev[i]) amdgpu_dm_backlight_set_level(dm, i, dm->brightness[i]); } + dm->restore_backlight = false; } } @@ -10774,6 +10848,8 @@ static void get_freesync_config_for_crtc( } else { config.state = VRR_STATE_INACTIVE; } + } else { + config.state = VRR_STATE_UNSUPPORTED; } out: new_crtc_state->freesync_config = config; @@ -12675,7 +12751,7 @@ void amdgpu_dm_update_freesync_caps(struct drm_connector *connector, dm_con_state = to_dm_connector_state(connector->state); - if (!adev->dm.freesync_module) + if (!adev->dm.freesync_module || !dc_supports_vrr(sink->ctx->dce_version)) goto update; edid = drm_edid_raw(drm_edid); // FIXME: Get rid of drm_edid_raw() diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h index ce74125c713e..c41c0ee4687f 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h @@ -216,6 +216,11 @@ struct amdgpu_dm_backlight_caps { */ bool aux_support; /** + * @brightness_mask: After deriving brightness, OR it with this mask. + * Workaround for panels with issues with certain brightness values. + */ + u32 brightness_mask; + /** * @ac_level: the default brightness if booted on AC */ u8 ac_level; @@ -626,6 +631,13 @@ struct amdgpu_display_manager { u32 actual_brightness[AMDGPU_DM_MAX_NUM_EDP]; /** + * @restore_backlight: + * + * Flag to indicate whether to restore backlight after modeset. + */ + bool restore_backlight; + + /** * @aux_hpd_discon_quirk: * * quirk for hpd discon while aux is on-going. @@ -794,6 +806,7 @@ struct amdgpu_dm_connector { bool fake_enable; bool force_yuv420_output; + bool force_yuv422_output; struct dsc_preferred_settings dsc_settings; union dp_downstream_port_present mst_downstream_port_present; /* Cached display modes */ diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c index 45feb404b097..466dccb355d7 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c @@ -317,13 +317,17 @@ static inline int amdgpu_dm_crtc_set_vblank(struct drm_crtc *crtc, bool enable) dc->config.disable_ips != DMUB_IPS_DISABLE_ALL && sr_supported && vblank->config.disable_immediate) drm_crtc_vblank_restore(crtc); + } - /* vblank irq on -> Only need vupdate irq in vrr mode */ - if (amdgpu_dm_crtc_vrr_active(acrtc_state)) - rc = amdgpu_dm_crtc_set_vupdate_irq(crtc, true); - } else { - /* vblank irq off -> vupdate irq off */ - rc = amdgpu_dm_crtc_set_vupdate_irq(crtc, false); + if (dc_supports_vrr(dm->dc->ctx->dce_version)) { + if (enable) { + /* vblank irq on -> Only need vupdate irq in vrr mode */ + if (amdgpu_dm_crtc_vrr_active(acrtc_state)) + rc = amdgpu_dm_crtc_set_vupdate_irq(crtc, true); + } else { + /* vblank irq off -> vupdate irq off */ + rc = amdgpu_dm_crtc_set_vupdate_irq(crtc, false); + } } if (rc) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c index 437174d4fed5..58e084f52526 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c @@ -223,6 +223,7 @@ void hdcp_update_display(struct hdcp_workqueue *hdcp_work, display_adjust.disable = MOD_HDCP_DISPLAY_NOT_DISABLE; link_adjust.auth_delay = 2; + link_adjust.retry_limit = MAX_NUM_OF_ATTEMPTS; if (content_type == DRM_MODE_HDCP_CONTENT_TYPE0) { link_adjust.hdcp2.force_type = MOD_HDCP_FORCE_TYPE_0; @@ -572,6 +573,7 @@ static void update_config(void *handle, struct cp_psp_stream_config *config) link->dp.usb4_enabled = config->usb4_enabled; display->adjust.disable = MOD_HDCP_DISPLAY_DISABLE_AUTHENTICATION; link->adjust.auth_delay = 2; + link->adjust.retry_limit = MAX_NUM_OF_ATTEMPTS; link->adjust.hdcp1.disable = 0; hdcp_w->encryption_status[display->index] = MOD_HDCP_ENCRYPTION_STATUS_HDCP_OFF; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 6a817508c826..5e92eaa67aa3 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -841,6 +841,7 @@ void amdgpu_dm_initialize_dp_connector(struct amdgpu_display_manager *dm, drm_dp_aux_init(&aconnector->dm_dp_aux.aux); drm_dp_cec_register_connector(&aconnector->dm_dp_aux.aux, &aconnector->base); + drm_dp_dpcd_set_probe(&aconnector->dm_dp_aux.aux, false); if (aconnector->base.connector_type == DRM_MODE_CONNECTOR_eDP) return; @@ -853,13 +854,20 @@ void amdgpu_dm_initialize_dp_connector(struct amdgpu_display_manager *dm, drm_connector_attach_dp_subconnector_property(&aconnector->base); } -int dm_mst_get_pbn_divider(struct dc_link *link) +uint32_t dm_mst_get_pbn_divider(struct dc_link *link) { + uint32_t pbn_div_x100; + uint64_t dividend, divisor; + if (!link) return 0; - return dc_link_bandwidth_kbps(link, - dc_link_get_link_cap(link)) / (8 * 1000 * 54); + dividend = (uint64_t)dc_link_bandwidth_kbps(link, dc_link_get_link_cap(link)) * 100; + divisor = 8 * 1000 * 54; + + pbn_div_x100 = div64_u64(dividend, divisor); + + return dfixed_const(pbn_div_x100) / 100; } struct dsc_mst_fairness_params { diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h index 65f76a7d00db..6f7ea684b555 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h @@ -60,7 +60,7 @@ enum mst_msg_ready_type { struct amdgpu_display_manager; struct amdgpu_dm_connector; -int dm_mst_get_pbn_divider(struct dc_link *link); +uint32_t dm_mst_get_pbn_divider(struct dc_link *link); void amdgpu_dm_initialize_dp_connector(struct amdgpu_display_manager *dm, struct amdgpu_dm_connector *aconnector, diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c index eef51652ca35..08f629c64df3 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c @@ -146,7 +146,7 @@ static void amdgpu_dm_plane_add_modifier(uint64_t **mods, uint64_t *size, uint64 if (*cap - *size < 1) { uint64_t new_cap = *cap * 2; - uint64_t *new_mods = kmalloc(new_cap * sizeof(uint64_t), GFP_KERNEL); + uint64_t *new_mods = kmalloc_array(new_cap, sizeof(uint64_t), GFP_KERNEL); if (!new_mods) { kfree(*mods); @@ -732,7 +732,7 @@ static int amdgpu_dm_plane_get_plane_modifiers(struct amdgpu_device *adev, unsig if (adev->family < AMDGPU_FAMILY_AI) return 0; - *mods = kmalloc(capacity * sizeof(uint64_t), GFP_KERNEL); + *mods = kmalloc_array(capacity, sizeof(uint64_t), GFP_KERNEL); if (plane_type == DRM_PLANE_TYPE_CURSOR) { amdgpu_dm_plane_add_modifier(mods, &size, &capacity, DRM_FORMAT_MOD_LINEAR); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c index e5771f490f2e..11b2ea6edf95 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c @@ -98,6 +98,7 @@ bool dm_pp_apply_display_requirements( const struct dm_pp_single_disp_config *dc_cfg = &pp_display_cfg->disp_configs[i]; adev->pm.pm_display_cfg.displays[i].controller_id = dc_cfg->pipe_idx + 1; + adev->pm.pm_display_cfg.displays[i].pixel_clock = dc_cfg->pixel_clock; } amdgpu_dpm_display_configuration_change(adev, &adev->pm.pm_display_cfg); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_replay.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_replay.c index 82ea3fe5e764..80704d709e44 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_replay.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_replay.c @@ -31,7 +31,7 @@ #include "amdgpu_dm.h" #include "modules/power/power_helpers.h" #include "dmub/inc/dmub_cmd.h" -#include "dc/inc/link.h" +#include "dc/inc/link_service.h" /* * amdgpu_dm_link_supports_replay() - check if the link supports replay diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c index 4071851f9e86..15cf13ec5302 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c @@ -28,7 +28,7 @@ #include "dccg.h" #include "clk_mgr_internal.h" #include "dc_state_priv.h" -#include "link.h" +#include "link_service.h" #include "dce100/dce_clk_mgr.h" #include "dce110/dce110_clk_mgr.h" diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c index 13cf415e38e5..d50b9440210e 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c @@ -164,7 +164,7 @@ void dce110_fill_display_configs( stream->link->cur_link_settings.link_rate; cfg->link_settings.link_spread = stream->link->cur_link_settings.link_spread; - cfg->sym_clock = stream->phy_pix_clk; + cfg->pixel_clock = stream->phy_pix_clk; /* Round v_refresh*/ cfg->v_refresh = stream->timing.pix_clk_100hz * 100; cfg->v_refresh /= stream->timing.h_total; diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c index bc123f1884da..051052bd10c9 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c @@ -47,7 +47,7 @@ #include "dcn30/dcn30_clk_mgr.h" #include "dc_dmub_srv.h" -#include "link.h" +#include "link_service.h" #include "logger_types.h" diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c index 91d872d6d392..790bbd8235b1 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c @@ -48,7 +48,7 @@ #include "dcn31/dcn31_clk_mgr.h" #include "dc_dmub_srv.h" -#include "link.h" +#include "link_service.h" #include "dcn314_smu.h" diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c index e4d22f74f986..b315ed91e010 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c @@ -46,7 +46,7 @@ #define DC_LOGGER \ clk_mgr->base.base.ctx->logger -#include "link.h" +#include "link_service.h" #define TO_CLK_MGR_DCN315(clk_mgr)\ container_of(clk_mgr, struct clk_mgr_dcn315, base) diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c index 49efea0c8fcf..1769b1f26e75 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c @@ -39,7 +39,7 @@ #include "dcn316_smu.h" #include "dm_helpers.h" #include "dc_dmub_srv.h" -#include "link.h" +#include "link_service.h" // DCN316 this is CLK1 instance #define MAX_INSTANCE 7 diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c index 8376e2b0e73d..7da7b41bd092 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c @@ -33,7 +33,7 @@ #include "reg_helper.h" #include "core_types.h" #include "dm_helpers.h" -#include "link.h" +#include "link_service.h" #include "dc_state_priv.h" #include "atomfirmware.h" #include "dcn32_smu13_driver_if.h" diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c index bb1ac12a2b09..86edf11b8c5a 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c @@ -44,7 +44,7 @@ #include "dcn31/dcn31_clk_mgr.h" #include "dc_dmub_srv.h" -#include "link.h" +#include "link_service.h" #include "logger_types.h" #undef DC_LOGGER diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr.c index 47ff4c965d76..47461f249e83 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr.c @@ -13,7 +13,7 @@ #include "reg_helper.h" #include "core_types.h" #include "dm_helpers.h" -#include "link.h" +#include "link_service.h" #include "dc_state_priv.h" #include "atomfirmware.h" diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 261b7d43e91d..c4dd52ed377d 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -60,7 +60,7 @@ #include "link_encoder.h" #include "link_enc_cfg.h" -#include "link.h" +#include "link_service.h" #include "dm_helpers.h" #include "mem_input.h" @@ -4169,7 +4169,7 @@ static void commit_planes_for_stream(struct dc *dc, } if (dc->hwseq->funcs.wait_for_pipe_update_if_needed) - dc->hwseq->funcs.wait_for_pipe_update_if_needed(dc, top_pipe_to_program, update_type == UPDATE_TYPE_FAST); + dc->hwseq->funcs.wait_for_pipe_update_if_needed(dc, top_pipe_to_program, update_type < UPDATE_TYPE_FULL); if (should_lock_all_pipes && dc->hwss.interdependent_update_lock) { if (dc->hwss.subvp_pipe_control_lock) @@ -5622,8 +5622,8 @@ void dc_allow_idle_optimizations_internal(struct dc *dc, bool allow, char const subvp_pipe_type[i] = dc_state_get_pipe_subvp_type(context, pipe); } } - - DC_LOG_DC("%s: allow_idle=%d\n HardMinUClk_Khz=%d HardMinDramclk_Khz=%d\n Pipe_0=%d Pipe_1=%d Pipe_2=%d Pipe_3=%d Pipe_4=%d Pipe_5=%d (caller=%s)\n", + if (!dc->caps.is_apu) + DC_LOG_DC("%s: allow_idle=%d\n HardMinUClk_Khz=%d HardMinDramclk_Khz=%d\n Pipe_0=%d Pipe_1=%d Pipe_2=%d Pipe_3=%d Pipe_4=%d Pipe_5=%d (caller=%s)\n", __func__, allow, idle_fclk_khz, idle_dramclk_khz, subvp_pipe_type[0], subvp_pipe_type[1], subvp_pipe_type[2], subvp_pipe_type[3], subvp_pipe_type[4], subvp_pipe_type[5], caller_name); diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_enc_cfg.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_enc_cfg.c index 814f68d76257..a180f68f711c 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_enc_cfg.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_enc_cfg.c @@ -24,7 +24,7 @@ #include "link_enc_cfg.h" #include "resource.h" -#include "link.h" +#include "link_service.h" #define DC_LOGGER dc->ctx->logger diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_exports.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_exports.c index b7a5de4ecb61..9acd30019717 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_exports.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_exports.c @@ -33,8 +33,9 @@ * dc.h with detail interface documentation, then add function implementation * in this file which calls link functions. */ -#include "link.h" +#include "link_service.h" #include "dce/dce_i2c.h" + struct dc_link *dc_get_link_at_index(struct dc *dc, uint32_t link_index) { if (link_index >= MAX_LINKS) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index d712548b1927..cbca3c67f439 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -40,7 +40,7 @@ #include "virtual/virtual_stream_encoder.h" #include "dpcd_defs.h" #include "link_enc_cfg.h" -#include "link.h" +#include "link_service.h" #include "clk_mgr.h" #include "dc_state_priv.h" #include "dc_stream_priv.h" @@ -95,7 +95,6 @@ #define DC_LOGGER \ dc->ctx->logger #define DC_LOGGER_INIT(logger) - #include "dml2/dml2_wrapper.h" #define UNABLE_TO_SPLIT -1 @@ -2149,7 +2148,7 @@ int resource_get_odm_slice_dst_width(struct pipe_ctx *otg_master, h_active = timing->h_addressable + timing->h_border_left + timing->h_border_right + - otg_master->hblank_borrow; + otg_master->dsc_padding_params.dsc_hactive_padding; width = h_active / count; if (otg_master->stream_res.tg) @@ -4267,39 +4266,33 @@ fail: return res; } +#if defined(CONFIG_DRM_AMD_DC_FP) +#endif /* CONFIG_DRM_AMD_DC_FP */ + /** - * decide_hblank_borrow - Decides the horizontal blanking borrow value for a given pipe context. + * calculate_timing_params_for_dsc_with_padding - Calculates timing parameters for DSC with padding. * @pipe_ctx: Pointer to the pipe context structure. * - * This function calculates the horizontal blanking borrow value for a given pipe context based on the + * This function calculates the timing parameters for a given pipe context based on the * display stream compression (DSC) configuration. If the horizontal active pixels (hactive) are less - * than the total width of the DSC slices, it sets the hblank_borrow value to the difference. If the - * total horizontal timing minus the hblank_borrow value is less than 32, it resets the hblank_borrow + * than the total width of the DSC slices, it sets the dsc_hactive_padding value to the difference. If the + * total horizontal timing minus the dsc_hactive_padding value is less than 32, it resets the dsc_hactive_padding * value to 0. */ -static void decide_hblank_borrow(struct pipe_ctx *pipe_ctx) +static void calculate_timing_params_for_dsc_with_padding(struct pipe_ctx *pipe_ctx) { - uint32_t hactive; - uint32_t ceil_slice_width; struct dc_stream_state *stream = NULL; if (!pipe_ctx) return; stream = pipe_ctx->stream; + pipe_ctx->dsc_padding_params.dsc_hactive_padding = 0; + pipe_ctx->dsc_padding_params.dsc_htotal_padding = 0; - if (stream->timing.flags.DSC) { - hactive = stream->timing.h_addressable + stream->timing.h_border_left + stream->timing.h_border_right; + if (stream) + pipe_ctx->dsc_padding_params.dsc_pix_clk_100hz = stream->timing.pix_clk_100hz; - /* Assume if determined slices does not divide Hactive evenly, Hborrow is needed for padding*/ - if (hactive % stream->timing.dsc_cfg.num_slices_h != 0) { - ceil_slice_width = (hactive / stream->timing.dsc_cfg.num_slices_h) + 1; - pipe_ctx->hblank_borrow = ceil_slice_width * stream->timing.dsc_cfg.num_slices_h - hactive; - - if (stream->timing.h_total - hactive - pipe_ctx->hblank_borrow < 32) - pipe_ctx->hblank_borrow = 0; - } - } } /** @@ -4342,7 +4335,7 @@ enum dc_status dc_validate_global_state( /* Decide whether hblank borrow is needed and save it in pipe_ctx */ if (dc->debug.enable_hblank_borrow) - decide_hblank_borrow(pipe_ctx); + calculate_timing_params_for_dsc_with_padding(pipe_ctx); if (dc->res_pool->funcs->patch_unknown_plane_state && pipe_ctx->plane_state && diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_state.c b/drivers/gpu/drm/amd/display/dc/core/dc_state.c index 883054bb18e7..c61300a7cb1c 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_state.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_state.c @@ -211,7 +211,7 @@ struct dc_state *dc_state_create(struct dc *dc, struct dc_state_create_params *p return NULL; } - if (!dml2_create(dc, &dc->dml2_dc_power_options, &state->bw_ctx.dml2_dc_power_source)) { + if (dc->caps.dcmode_power_limits_present && !dml2_create(dc, &dc->dml2_dc_power_options, &state->bw_ctx.dml2_dc_power_source)) { dc_state_release(state); return NULL; } diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index b41e66c31e6a..9d15ba591772 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -55,7 +55,7 @@ struct aux_payload; struct set_config_cmd_payload; struct dmub_notification; -#define DC_VER "3.2.348" +#define DC_VER "3.2.350" /** * MAX_SURFACES - representative of the upper bound of surfaces that can be piped to a single CRTC @@ -1157,6 +1157,7 @@ struct dc_debug_options { bool enable_hblank_borrow; bool force_subvp_df_throttle; uint32_t acpi_transition_bitmasks[MAX_PIPES]; + bool enable_pg_cntl_debug_logs; unsigned int auxless_alpm_lfps_setup_ns; unsigned int auxless_alpm_lfps_period_ns; unsigned int auxless_alpm_lfps_silence_ns; diff --git a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h index 3a3ec38cdf8b..db669ccb1d58 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h @@ -1284,6 +1284,7 @@ struct dpcd_caps { union dp_receive_port0_cap receive_port0_cap; /* Indicates the number of SST links supported by MSO (Multi-Stream Output) */ uint8_t mso_cap_sst_links_supported; + uint8_t dp_edp_general_cap_2; }; union dpcd_sink_ext_caps { diff --git a/drivers/gpu/drm/amd/display/dc/dc_helper.c b/drivers/gpu/drm/amd/display/dc/dc_helper.c index 51e41aed7316..5a365bd19933 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_helper.c +++ b/drivers/gpu/drm/amd/display/dc/dc_helper.c @@ -755,3 +755,8 @@ char *dce_version_to_string(const int version) return "Unknown"; } } + +bool dc_supports_vrr(const enum dce_version v) +{ + return v >= DCE_VERSION_8_0; +} diff --git a/drivers/gpu/drm/amd/display/dc/dc_spl_translate.c b/drivers/gpu/drm/amd/display/dc/dc_spl_translate.c index 7f57661433eb..55704d4457ef 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_spl_translate.c +++ b/drivers/gpu/drm/amd/display/dc/dc_spl_translate.c @@ -128,7 +128,7 @@ void translate_SPL_in_params_from_pipe_ctx(struct pipe_ctx *pipe_ctx, struct spl spl_in->odm_slice_index = resource_get_odm_slice_index(pipe_ctx); // Make spl input basic out info output_size width point to stream h active spl_in->basic_out.output_size.width = - stream->timing.h_addressable + stream->timing.h_border_left + stream->timing.h_border_right + pipe_ctx->hblank_borrow; + stream->timing.h_addressable + stream->timing.h_border_left + stream->timing.h_border_right + pipe_ctx->dsc_padding_params.dsc_hactive_padding; // Make spl input basic out info output_size height point to v active spl_in->basic_out.output_size.height = stream->timing.v_addressable + stream->timing.v_border_bottom + stream->timing.v_border_top; diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn35/dcn35_dccg.c b/drivers/gpu/drm/amd/display/dc/dccg/dcn35/dcn35_dccg.c index 58c84f555c0f..0ce9489ac6b7 100644 --- a/drivers/gpu/drm/amd/display/dc/dccg/dcn35/dcn35_dccg.c +++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn35/dcn35_dccg.c @@ -133,30 +133,34 @@ enum dsc_clk_source { }; -static void dccg35_set_dsc_clk_rcg(struct dccg *dccg, int inst, bool enable) +static void dccg35_set_dsc_clk_rcg(struct dccg *dccg, int inst, bool allow_rcg) { struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); - if (!dccg->ctx->dc->debug.root_clock_optimization.bits.dsc && enable) + if (!dccg->ctx->dc->debug.root_clock_optimization.bits.dsc && allow_rcg) return; switch (inst) { case 0: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK0_ROOT_GATE_DISABLE, enable ? 0 : 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK0_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1); break; case 1: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK1_ROOT_GATE_DISABLE, enable ? 0 : 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK1_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1); break; case 2: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK2_ROOT_GATE_DISABLE, enable ? 0 : 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK2_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1); break; case 3: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK3_ROOT_GATE_DISABLE, enable ? 0 : 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK3_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1); break; default: BREAK_TO_DEBUGGER(); return; } + + /* Wait for clock to ramp */ + if (!allow_rcg) + udelay(10); } static void dccg35_set_symclk32_se_rcg( @@ -385,35 +389,34 @@ static void dccg35_set_dtbclk_p_rcg(struct dccg *dccg, int inst, bool enable) } } -static void dccg35_set_dppclk_rcg(struct dccg *dccg, - int inst, bool enable) +static void dccg35_set_dppclk_rcg(struct dccg *dccg, int inst, bool allow_rcg) { - struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); - - if (!dccg->ctx->dc->debug.root_clock_optimization.bits.dpp && enable) + if (!dccg->ctx->dc->debug.root_clock_optimization.bits.dpp && allow_rcg) return; switch (inst) { case 0: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK0_ROOT_GATE_DISABLE, enable ? 0 : 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK0_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1); break; case 1: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK1_ROOT_GATE_DISABLE, enable ? 0 : 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK1_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1); break; case 2: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK2_ROOT_GATE_DISABLE, enable ? 0 : 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK2_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1); break; case 3: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK3_ROOT_GATE_DISABLE, enable ? 0 : 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK3_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1); break; default: BREAK_TO_DEBUGGER(); break; } - //DC_LOG_DEBUG("%s: inst(%d) DPPCLK rcg_disable: %d\n", __func__, inst, enable ? 0 : 1); + /* Wait for clock to ramp */ + if (!allow_rcg) + udelay(10); } static void dccg35_set_dpstreamclk_rcg( @@ -1177,32 +1180,34 @@ static void dccg35_update_dpp_dto(struct dccg *dccg, int dpp_inst, } static void dccg35_set_dppclk_root_clock_gating(struct dccg *dccg, - uint32_t dpp_inst, uint32_t enable) + uint32_t dpp_inst, uint32_t disallow_rcg) { struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); - if (!dccg->ctx->dc->debug.root_clock_optimization.bits.dpp) + if (!dccg->ctx->dc->debug.root_clock_optimization.bits.dpp && !disallow_rcg) return; switch (dpp_inst) { case 0: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK0_ROOT_GATE_DISABLE, enable); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK0_ROOT_GATE_DISABLE, disallow_rcg); break; case 1: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK1_ROOT_GATE_DISABLE, enable); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK1_ROOT_GATE_DISABLE, disallow_rcg); break; case 2: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK2_ROOT_GATE_DISABLE, enable); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK2_ROOT_GATE_DISABLE, disallow_rcg); break; case 3: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK3_ROOT_GATE_DISABLE, enable); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK3_ROOT_GATE_DISABLE, disallow_rcg); break; default: break; } - //DC_LOG_DEBUG("%s: dpp_inst(%d) rcg: %d\n", __func__, dpp_inst, enable); + /* Wait for clock to ramp */ + if (disallow_rcg) + udelay(10); } static void dccg35_get_pixel_rate_div( @@ -1782,8 +1787,7 @@ static void dccg35_enable_dscclk(struct dccg *dccg, int inst) //Disable DTO switch (inst) { case 0: - if (dccg->ctx->dc->debug.root_clock_optimization.bits.dsc) - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK0_ROOT_GATE_DISABLE, 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK0_ROOT_GATE_DISABLE, 1); REG_UPDATE_2(DSCCLK0_DTO_PARAM, DSCCLK0_DTO_PHASE, 0, @@ -1791,8 +1795,7 @@ static void dccg35_enable_dscclk(struct dccg *dccg, int inst) REG_UPDATE(DSCCLK_DTO_CTRL, DSCCLK0_EN, 1); break; case 1: - if (dccg->ctx->dc->debug.root_clock_optimization.bits.dsc) - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK1_ROOT_GATE_DISABLE, 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK1_ROOT_GATE_DISABLE, 1); REG_UPDATE_2(DSCCLK1_DTO_PARAM, DSCCLK1_DTO_PHASE, 0, @@ -1800,8 +1803,7 @@ static void dccg35_enable_dscclk(struct dccg *dccg, int inst) REG_UPDATE(DSCCLK_DTO_CTRL, DSCCLK1_EN, 1); break; case 2: - if (dccg->ctx->dc->debug.root_clock_optimization.bits.dsc) - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK2_ROOT_GATE_DISABLE, 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK2_ROOT_GATE_DISABLE, 1); REG_UPDATE_2(DSCCLK2_DTO_PARAM, DSCCLK2_DTO_PHASE, 0, @@ -1809,8 +1811,7 @@ static void dccg35_enable_dscclk(struct dccg *dccg, int inst) REG_UPDATE(DSCCLK_DTO_CTRL, DSCCLK2_EN, 1); break; case 3: - if (dccg->ctx->dc->debug.root_clock_optimization.bits.dsc) - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK3_ROOT_GATE_DISABLE, 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK3_ROOT_GATE_DISABLE, 1); REG_UPDATE_2(DSCCLK3_DTO_PARAM, DSCCLK3_DTO_PHASE, 0, @@ -1821,6 +1822,9 @@ static void dccg35_enable_dscclk(struct dccg *dccg, int inst) BREAK_TO_DEBUGGER(); return; } + + /* Wait for clock to ramp */ + udelay(10); } static void dccg35_disable_dscclk(struct dccg *dccg, @@ -1864,6 +1868,9 @@ static void dccg35_disable_dscclk(struct dccg *dccg, default: return; } + + /* Wait for clock ramp */ + udelay(10); } static void dccg35_enable_symclk_se(struct dccg *dccg, uint32_t stream_enc_inst, uint32_t link_enc_inst) @@ -2349,10 +2356,7 @@ static void dccg35_disable_symclk_se_cb( void dccg35_root_gate_disable_control(struct dccg *dccg, uint32_t pipe_idx, uint32_t disable_clock_gating) { - - if (dccg->ctx->dc->debug.root_clock_optimization.bits.dpp) { - dccg35_set_dppclk_root_clock_gating(dccg, pipe_idx, disable_clock_gating); - } + dccg35_set_dppclk_root_clock_gating(dccg, pipe_idx, disable_clock_gating); } static const struct dccg_funcs dccg35_funcs_new = { diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c index bb4ac5042c80..673bb87d2c17 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c @@ -725,14 +725,18 @@ bool dce_aux_transfer_with_retries(struct ddc_service *ddc, for (i = 0; i < AUX_MAX_RETRIES; i++) { DC_TRACE_LEVEL_MESSAGE(DAL_TRACE_LEVEL_INFORMATION, LOG_FLAG_I2cAux_DceAux, - "dce_aux_transfer_with_retries: link_index=%u: START: retry %d of %d: address=0x%04x length=%u write=%d mot=%d", + "dce_aux_transfer_with_retries: link_index=%u: START: retry %d of %d: " + "address=0x%04x length=%u write=%d mot=%d is_i2c=%d is_dpia=%d ddc_hw_inst=%d", ddc && ddc->link ? ddc->link->link_index : UINT_MAX, i + 1, (int)AUX_MAX_RETRIES, payload->address, payload->length, (unsigned int) payload->write, - (unsigned int) payload->mot); + (unsigned int) payload->mot, + payload->i2c_over_aux, + (ddc->link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) ? true : false, + ddc->link->ddc_hw_inst); if (payload->write) dce_aux_log_payload(" write", payload->data, payload->length, 16); @@ -746,7 +750,9 @@ bool dce_aux_transfer_with_retries(struct ddc_service *ddc, DC_TRACE_LEVEL_MESSAGE(DAL_TRACE_LEVEL_INFORMATION, LOG_FLAG_I2cAux_DceAux, - "dce_aux_transfer_with_retries: link_index=%u: END: retry %d of %d: address=0x%04x length=%u write=%d mot=%d: ret=%d operation_result=%d payload->reply=%u", + "dce_aux_transfer_with_retries: link_index=%u: END: retry %d of %d: " + "address=0x%04x length=%u write=%d mot=%d: ret=%d operation_result=%d " + "payload->reply=%u is_i2c=%d is_dpia=%d ddc_hw_inst=%d", ddc && ddc->link ? ddc->link->link_index : UINT_MAX, i + 1, (int)AUX_MAX_RETRIES, @@ -756,7 +762,10 @@ bool dce_aux_transfer_with_retries(struct ddc_service *ddc, (unsigned int) payload->mot, ret, (int)operation_result, - (unsigned int) *payload->reply); + (unsigned int) *payload->reply, + payload->i2c_over_aux, + (ddc->link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) ? true : false, + ddc->link->ddc_hw_inst); if (!payload->write) dce_aux_log_payload(" read", payload->data, ret > 0 ? ret : 0, 16); diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c b/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c index 65b979617b0c..9e2a473a8852 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c @@ -3,7 +3,7 @@ // Copyright 2024 Advanced Micro Devices, Inc. #include "dc.h" -#include "link.h" +#include "link_service.h" #include "dc_dmub_srv.h" #include "dmub/dmub_srv.h" #include "core_types.h" diff --git a/drivers/gpu/drm/amd/display/dc/dio/dcn10/dcn10_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dio/dcn10/dcn10_link_encoder.c index e0558a78b11c..1c1228116487 100644 --- a/drivers/gpu/drm/amd/display/dc/dio/dcn10/dcn10_link_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dio/dcn10/dcn10_link_encoder.c @@ -812,7 +812,7 @@ bool dcn10_link_encoder_validate_output_with_stream( enc10, &stream->timing); break; case SIGNAL_TYPE_EDP: - is_valid = (stream->timing.pixel_encoding == PIXEL_ENCODING_RGB) ? true : false; + is_valid = stream->timing.pixel_encoding == PIXEL_ENCODING_RGB; break; case SIGNAL_TYPE_VIRTUAL: is_valid = true; diff --git a/drivers/gpu/drm/amd/display/dc/dio/dcn10/dcn10_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dio/dcn10/dcn10_stream_encoder.c index 22e66b375a7f..d928b4dcf6b8 100644 --- a/drivers/gpu/drm/amd/display/dc/dio/dcn10/dcn10_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dio/dcn10/dcn10_stream_encoder.c @@ -28,7 +28,7 @@ #include "dcn10_stream_encoder.h" #include "reg_helper.h" #include "hw_shared.h" -#include "link.h" +#include "link_service.h" #include "dpcd_defs.h" #include "dcn30/dcn30_afmt.h" diff --git a/drivers/gpu/drm/amd/display/dc/dio/dcn20/dcn20_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dio/dcn20/dcn20_stream_encoder.c index 0b47aeb60e79..bec0b4aaeb2b 100644 --- a/drivers/gpu/drm/amd/display/dc/dio/dcn20/dcn20_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dio/dcn20/dcn20_stream_encoder.c @@ -29,7 +29,7 @@ #include "dcn20_stream_encoder.h" #include "reg_helper.h" #include "hw_shared.h" -#include "link.h" +#include "link_service.h" #include "dpcd_defs.h" #define DC_LOGGER \ diff --git a/drivers/gpu/drm/amd/display/dc/dio/dcn31/dcn31_dio_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dio/dcn31/dcn31_dio_link_encoder.c index 9a92f73d5b7f..84cc2ddc52fe 100644 --- a/drivers/gpu/drm/amd/display/dc/dio/dcn31/dcn31_dio_link_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dio/dcn31/dcn31_dio_link_encoder.c @@ -37,7 +37,7 @@ #include "link_enc_cfg.h" #include "dc_dmub_srv.h" #include "dal_asic_id.h" -#include "link.h" +#include "link_service.h" #define CTX \ enc10->base.ctx diff --git a/drivers/gpu/drm/amd/display/dc/dio/dcn314/dcn314_dio_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dio/dcn314/dcn314_dio_stream_encoder.c index ae81451a3a72..3e85e9c3d2cb 100644 --- a/drivers/gpu/drm/amd/display/dc/dio/dcn314/dcn314_dio_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dio/dcn314/dcn314_dio_stream_encoder.c @@ -30,7 +30,7 @@ #include "dcn314_dio_stream_encoder.h" #include "reg_helper.h" #include "hw_shared.h" -#include "link.h" +#include "link_service.h" #include "dpcd_defs.h" #define DC_LOGGER \ diff --git a/drivers/gpu/drm/amd/display/dc/dio/dcn32/dcn32_dio_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dio/dcn32/dcn32_dio_stream_encoder.c index 1a9bb614c41e..3523d1cdc1a3 100644 --- a/drivers/gpu/drm/amd/display/dc/dio/dcn32/dcn32_dio_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dio/dcn32/dcn32_dio_stream_encoder.c @@ -29,7 +29,7 @@ #include "dcn32_dio_stream_encoder.h" #include "reg_helper.h" #include "hw_shared.h" -#include "link.h" +#include "link_service.h" #include "dpcd_defs.h" #define DC_LOGGER \ diff --git a/drivers/gpu/drm/amd/display/dc/dio/dcn35/dcn35_dio_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dio/dcn35/dcn35_dio_stream_encoder.c index 6ab2a218b769..fd5d1dbf9dc6 100644 --- a/drivers/gpu/drm/amd/display/dc/dio/dcn35/dcn35_dio_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dio/dcn35/dcn35_dio_stream_encoder.c @@ -29,7 +29,7 @@ #include "dcn35_dio_stream_encoder.h" #include "reg_helper.h" #include "hw_shared.h" -#include "link.h" +#include "link_service.h" #include "dpcd_defs.h" #define DC_LOGGER \ @@ -397,7 +397,7 @@ static bool enc35_is_fifo_enabled(struct stream_encoder *enc) uint32_t reset_val; REG_GET(DIG_FIFO_CTRL0, DIG_FIFO_ENABLE, &reset_val); - return (reset_val == 0) ? false : true; + return reset_val != 0; } void enc35_disable_fifo(struct stream_encoder *enc) { diff --git a/drivers/gpu/drm/amd/display/dc/dio/dcn401/dcn401_dio_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dio/dcn401/dcn401_dio_stream_encoder.c index d5fa551dd3c9..99aab70ef3e1 100644 --- a/drivers/gpu/drm/amd/display/dc/dio/dcn401/dcn401_dio_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dio/dcn401/dcn401_dio_stream_encoder.c @@ -32,7 +32,7 @@ #include "dcn401_dio_stream_encoder.h" #include "reg_helper.h" #include "hw_shared.h" -#include "link.h" +#include "link_service.h" #include "dpcd_defs.h" #define DC_LOGGER \ diff --git a/drivers/gpu/drm/amd/display/dc/dm_services.h b/drivers/gpu/drm/amd/display/dc/dm_services.h index 7b9c22c45453..7b398d4f4439 100644 --- a/drivers/gpu/drm/amd/display/dc/dm_services.h +++ b/drivers/gpu/drm/amd/display/dc/dm_services.h @@ -311,4 +311,6 @@ void dm_dtn_log_end(struct dc_context *ctx, char *dce_version_to_string(const int version); +bool dc_supports_vrr(const enum dce_version v); + #endif /* __DM_SERVICES_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/dm_services_types.h b/drivers/gpu/drm/amd/display/dc/dm_services_types.h index bf63da266a18..3b093b8699ab 100644 --- a/drivers/gpu/drm/amd/display/dc/dm_services_types.h +++ b/drivers/gpu/drm/amd/display/dc/dm_services_types.h @@ -127,7 +127,7 @@ struct dm_pp_single_disp_config { uint32_t src_height; uint32_t src_width; uint32_t v_refresh; - uint32_t sym_clock; /* HDMI only */ + uint32_t pixel_clock; /* Pixel clock in KHz (for HDMI only: normalized) */ struct dc_link_settings link_settings; /* DP only */ }; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c index 2a2eaf6adf26..7aaf13bbd4e4 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c @@ -30,8 +30,7 @@ #include "dcn20/dcn20_resource.h" #include "dcn21/dcn21_resource.h" #include "clk_mgr/dcn21/rn_clk_mgr.h" - -#include "link.h" +#include "link_service.h" #include "dcn20_fpu.h" #include "dc_state_priv.h" diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c index 18388fb00be8..8a0f128722b0 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c @@ -31,7 +31,7 @@ // We need this includes for WATERMARKS_* defines #include "clk_mgr/dcn32/dcn32_smu13_driver_if.h" #include "dcn30/dcn30_resource.h" -#include "link.h" +#include "link_service.h" #include "dc_state_priv.h" #define DC_LOGGER_INIT(logger) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c index 5d73efa2f0c9..c9dd920744c9 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c @@ -31,7 +31,7 @@ #include "dml/dcn31/dcn31_fpu.h" #include "dml/dml_inline_defs.h" -#include "link.h" +#include "link_service.h" #define DC_LOGGER_INIT(logger) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c index 6f516af82956..8cda18ce1a76 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c @@ -10,7 +10,7 @@ #include "dml/dcn35/dcn35_fpu.h" #include "dml/dml_inline_defs.h" -#include "link.h" +#include "link_service.h" #define DC_LOGGER_INIT(logger) diff --git a/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c b/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c index 715f9019a33e..4b9b2e84d381 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c @@ -6529,7 +6529,7 @@ static noinline_for_stack void dml_prefetch_check(struct display_mode_lib_st *mo mode_lib->ms.TotImmediateFlipBytes = 0; for (k = 0; k <= mode_lib->ms.num_active_planes - 1; k++) { if (!(mode_lib->ms.policy.ImmediateFlipRequirement[k] == dml_immediate_flip_not_required)) { - mode_lib->ms.TotImmediateFlipBytes = mode_lib->ms.TotImmediateFlipBytes + mode_lib->ms.NoOfDPP[j][k] * mode_lib->ms.PDEAndMetaPTEBytesPerFrame[j][k] + mode_lib->ms.MetaRowBytes[j][k]; + mode_lib->ms.TotImmediateFlipBytes = mode_lib->ms.TotImmediateFlipBytes + mode_lib->ms.NoOfDPP[j][k] * (mode_lib->ms.PDEAndMetaPTEBytesPerFrame[j][k] + mode_lib->ms.MetaRowBytes[j][k]); if (mode_lib->ms.use_one_row_for_frame_flip[j][k]) { mode_lib->ms.TotImmediateFlipBytes = mode_lib->ms.TotImmediateFlipBytes + mode_lib->ms.NoOfDPP[j][k] * (2 * mode_lib->ms.DPTEBytesPerRow[j][k]); } else { diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c index f6879e622271..bf5e7f4e0416 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c @@ -84,25 +84,29 @@ static unsigned int calc_max_hardware_v_total(const struct dc_stream_state *stre static void populate_dml21_timing_config_from_stream_state(struct dml2_timing_cfg *timing, struct dc_stream_state *stream, + struct pipe_ctx *pipe_ctx, struct dml2_context *dml_ctx) { unsigned int hblank_start, vblank_start, min_hardware_refresh_in_uhz; + uint32_t pix_clk_100hz; - timing->h_active = stream->timing.h_addressable + stream->timing.h_border_left + stream->timing.h_border_right; + timing->h_active = stream->timing.h_addressable + stream->timing.h_border_left + stream->timing.h_border_right + pipe_ctx->dsc_padding_params.dsc_hactive_padding; timing->v_active = stream->timing.v_addressable + stream->timing.v_border_bottom + stream->timing.v_border_top; timing->h_front_porch = stream->timing.h_front_porch; timing->v_front_porch = stream->timing.v_front_porch; timing->pixel_clock_khz = stream->timing.pix_clk_100hz / 10; + if (pipe_ctx->dsc_padding_params.dsc_hactive_padding != 0) + timing->pixel_clock_khz = pipe_ctx->dsc_padding_params.dsc_pix_clk_100hz / 10; if (stream->timing.timing_3d_format == TIMING_3D_FORMAT_HW_FRAME_PACKING) timing->pixel_clock_khz *= 2; - timing->h_total = stream->timing.h_total; + timing->h_total = stream->timing.h_total + pipe_ctx->dsc_padding_params.dsc_htotal_padding; timing->v_total = stream->timing.v_total; timing->h_sync_width = stream->timing.h_sync_width; timing->interlaced = stream->timing.flags.INTERLACE; hblank_start = stream->timing.h_total - stream->timing.h_front_porch; - timing->h_blank_end = hblank_start - stream->timing.h_addressable + timing->h_blank_end = hblank_start - stream->timing.h_addressable - pipe_ctx->dsc_padding_params.dsc_hactive_padding - stream->timing.h_border_left - stream->timing.h_border_right; if (hblank_start < stream->timing.h_addressable) @@ -121,8 +125,13 @@ static void populate_dml21_timing_config_from_stream_state(struct dml2_timing_cf /* limit min refresh rate to DC cap */ min_hardware_refresh_in_uhz = stream->timing.min_refresh_in_uhz; if (stream->ctx->dc->caps.max_v_total != 0) { - min_hardware_refresh_in_uhz = div64_u64((stream->timing.pix_clk_100hz * 100000000ULL), - (stream->timing.h_total * (long long)calc_max_hardware_v_total(stream))); + if (pipe_ctx->dsc_padding_params.dsc_hactive_padding != 0) { + pix_clk_100hz = pipe_ctx->dsc_padding_params.dsc_pix_clk_100hz; + } else { + pix_clk_100hz = stream->timing.pix_clk_100hz; + } + min_hardware_refresh_in_uhz = div64_u64((pix_clk_100hz * 100000000ULL), + (timing->h_total * (long long)calc_max_hardware_v_total(stream))); } timing->drr_config.min_refresh_uhz = max(stream->timing.min_refresh_in_uhz, min_hardware_refresh_in_uhz); @@ -173,21 +182,6 @@ static void populate_dml21_timing_config_from_stream_state(struct dml2_timing_cf timing->vblank_nom = timing->v_total - timing->v_active; } -/** - * adjust_dml21_hblank_timing_config_from_pipe_ctx - Adjusts the horizontal blanking timing configuration - * based on the pipe context. - * @timing: Pointer to the dml2_timing_cfg structure to be adjusted. - * @pipe: Pointer to the pipe_ctx structure containing the horizontal blanking borrow value. - * - * This function modifies the horizontal active and blank end timings by adding and subtracting - * the horizontal blanking borrow value from the pipe context, respectively. - */ -static void adjust_dml21_hblank_timing_config_from_pipe_ctx(struct dml2_timing_cfg *timing, struct pipe_ctx *pipe) -{ - timing->h_active += pipe->hblank_borrow; - timing->h_blank_end -= pipe->hblank_borrow; -} - static void populate_dml21_output_config_from_stream_state(struct dml2_link_output_cfg *output, struct dc_stream_state *stream, const struct pipe_ctx *pipe) { @@ -487,7 +481,9 @@ static const struct scaler_data *get_scaler_data_for_plane( temp_pipe->plane_state = pipe->plane_state; temp_pipe->plane_res.scl_data.taps = pipe->plane_res.scl_data.taps; temp_pipe->stream_res = pipe->stream_res; - temp_pipe->hblank_borrow = pipe->hblank_borrow; + temp_pipe->dsc_padding_params.dsc_hactive_padding = pipe->dsc_padding_params.dsc_hactive_padding; + temp_pipe->dsc_padding_params.dsc_htotal_padding = pipe->dsc_padding_params.dsc_htotal_padding; + temp_pipe->dsc_padding_params.dsc_pix_clk_100hz = pipe->dsc_padding_params.dsc_pix_clk_100hz; dml_ctx->config.callbacks.build_scaling_params(temp_pipe); break; } @@ -755,8 +751,7 @@ bool dml21_map_dc_state_into_dml_display_cfg(const struct dc *in_dc, struct dc_s disp_cfg_stream_location = dml_dispcfg->num_streams++; ASSERT(disp_cfg_stream_location >= 0 && disp_cfg_stream_location < __DML2_WRAPPER_MAX_STREAMS_PLANES__); - populate_dml21_timing_config_from_stream_state(&dml_dispcfg->stream_descriptors[disp_cfg_stream_location].timing, context->streams[stream_index], dml_ctx); - adjust_dml21_hblank_timing_config_from_pipe_ctx(&dml_dispcfg->stream_descriptors[disp_cfg_stream_location].timing, &context->res_ctx.pipe_ctx[stream_index]); + populate_dml21_timing_config_from_stream_state(&dml_dispcfg->stream_descriptors[disp_cfg_stream_location].timing, context->streams[stream_index], &context->res_ctx.pipe_ctx[stream_index], dml_ctx); populate_dml21_output_config_from_stream_state(&dml_dispcfg->stream_descriptors[disp_cfg_stream_location].output, context->streams[stream_index], &context->res_ctx.pipe_ctx[stream_index]); populate_dml21_stream_overrides_from_stream_state(&dml_dispcfg->stream_descriptors[disp_cfg_stream_location], context->streams[stream_index], &context->stream_status[stream_index]); diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_wrapper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_wrapper.c index 798abb2b2e67..08f7f03b1023 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_wrapper.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_wrapper.c @@ -224,7 +224,9 @@ static bool dml21_mode_check_and_programming(const struct dc *in_dc, struct dc_s dml_ctx->config.svp_pstate.callbacks.release_phantom_streams_and_planes(in_dc, context); /* Populate stream, plane mappings and other fields in display config. */ + DC_FP_START(); result = dml21_map_dc_state_into_dml_display_cfg(in_dc, context, dml_ctx); + DC_FP_END(); if (!result) return false; @@ -279,7 +281,9 @@ static bool dml21_check_mode_support(const struct dc *in_dc, struct dc_state *co dml_ctx->config.svp_pstate.callbacks.release_phantom_streams_and_planes(in_dc, context); mode_support->dml2_instance = dml_init->dml2_instance; + DC_FP_START(); dml21_map_dc_state_into_dml_display_cfg(in_dc, context, dml_ctx); + DC_FP_END(); dml_ctx->v21.mode_programming.dml2_instance->scratch.build_mode_programming_locals.mode_programming_params.programming = dml_ctx->v21.mode_programming.programming; DC_FP_START(); is_supported = dml2_check_mode_supported(mode_support); diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/inc/dml_top_types.h b/drivers/gpu/drm/amd/display/dc/dml2/dml21/inc/dml_top_types.h index 7de10a95cfdb..41adb1104d0f 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/inc/dml_top_types.h +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/inc/dml_top_types.h @@ -16,9 +16,9 @@ struct dml2_instance; enum dml2_project_id { dml2_project_invalid = 0, - dml2_project_dcn4x_stage1 = 1, - dml2_project_dcn4x_stage2 = 2, - dml2_project_dcn4x_stage2_auto_drr_svp = 3, + dml2_project_dcn4x_stage1, + dml2_project_dcn4x_stage2, + dml2_project_dcn4x_stage2_auto_drr_svp, }; enum dml2_pstate_change_support { diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c index 0318260370ed..9deb03a18ccc 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c @@ -535,7 +535,7 @@ static bool dml2_validate_only(struct dc_state *context, enum dc_validate_mode v if (result) result = does_configuration_meet_sw_policies(dml2, &dml2->v20.scratch.cur_display_config, &dml2->v20.scratch.mode_support_info); - return (result == 1) ? true : false; + return result == 1; } static void dml2_apply_debug_options(const struct dc *dc, struct dml2_context *dml2) diff --git a/drivers/gpu/drm/amd/display/dc/dsc/dcn20/dcn20_dsc.c b/drivers/gpu/drm/amd/display/dc/dsc/dcn20/dcn20_dsc.c index bd1b9aef6d5c..89f0d999bf35 100644 --- a/drivers/gpu/drm/amd/display/dc/dsc/dcn20/dcn20_dsc.c +++ b/drivers/gpu/drm/amd/display/dc/dsc/dcn20/dcn20_dsc.c @@ -406,9 +406,10 @@ bool dsc_prepare_config(const struct dsc_config *dsc_cfg, struct dsc_reg_values dsc_reg_vals->alternate_ich_encoding_en = dsc_reg_vals->pps.dsc_version_minor == 1 ? 0 : 1; dsc_reg_vals->ich_reset_at_eol = (dsc_cfg->is_odm || dsc_reg_vals->num_slices_h > 1) ? 0xF : 0; + // Need to find the ceiling value for the slice width + dsc_reg_vals->pps.slice_width = (dsc_cfg->pic_width + dsc_cfg->dc_dsc_cfg.num_slices_h - 1) / dsc_cfg->dc_dsc_cfg.num_slices_h; // TODO: in addition to validating slice height (pic height must be divisible by slice height), // see what happens when the same condition doesn't apply for slice_width/pic_width. - dsc_reg_vals->pps.slice_width = dsc_cfg->pic_width / dsc_cfg->dc_dsc_cfg.num_slices_h; dsc_reg_vals->pps.slice_height = dsc_cfg->pic_height / dsc_cfg->dc_dsc_cfg.num_slices_v; ASSERT(dsc_reg_vals->pps.slice_height * dsc_cfg->dc_dsc_cfg.num_slices_v == dsc_cfg->pic_height); diff --git a/drivers/gpu/drm/amd/display/dc/hdcp/hdcp_msg.c b/drivers/gpu/drm/amd/display/dc/hdcp/hdcp_msg.c index 1313a7c5d87b..73a1e6a03719 100644 --- a/drivers/gpu/drm/amd/display/dc/hdcp/hdcp_msg.c +++ b/drivers/gpu/drm/amd/display/dc/hdcp/hdcp_msg.c @@ -28,7 +28,7 @@ #include "include/hdcp_msg_types.h" #include "include/signal_types.h" #include "core_types.h" -#include "link.h" +#include "link_service.h" #include "link_hwss.h" #include "link/protocols/link_dpcd.h" diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c index 153d68375fa3..24184b4eb352 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c @@ -48,7 +48,7 @@ #include "link_encoder.h" #include "link_enc_cfg.h" #include "link_hwss.h" -#include "link.h" +#include "link_service.h" #include "dccg.h" #include "clock_source.h" #include "clk_mgr.h" @@ -1601,17 +1601,19 @@ enum dc_status dce110_apply_single_controller_ctx_to_hw( } if (pipe_ctx->stream_res.audio != NULL) { - build_audio_output(context, pipe_ctx, &pipe_ctx->stream_res.audio_output); + struct audio_output audio_output = {0}; - link_hwss->setup_audio_output(pipe_ctx, &pipe_ctx->stream_res.audio_output, + build_audio_output(context, pipe_ctx, &audio_output); + + link_hwss->setup_audio_output(pipe_ctx, &audio_output, pipe_ctx->stream_res.audio->inst); pipe_ctx->stream_res.audio->funcs->az_configure( pipe_ctx->stream_res.audio, pipe_ctx->stream->signal, - &pipe_ctx->stream_res.audio_output.crtc_info, + &audio_output.crtc_info, &pipe_ctx->stream->audio_info, - &pipe_ctx->stream_res.audio_output.dp_link_info); + &audio_output.dp_link_info); if (dc->config.disable_hbr_audio_dp2) if (pipe_ctx->stream_res.audio->funcs->az_disable_hbr_audio && @@ -1923,10 +1925,8 @@ void dce110_enable_accelerated_mode(struct dc *dc, struct dc_state *context) get_edp_streams(context, edp_streams, &edp_stream_num); - // Check fastboot support, disable on DCE8 because of blank screens - if (edp_num && edp_stream_num && dc->ctx->dce_version != DCE_VERSION_8_0 && - dc->ctx->dce_version != DCE_VERSION_8_1 && - dc->ctx->dce_version != DCE_VERSION_8_3) { + /* Check fastboot support, disable on DCE 6-8 because of blank screens */ + if (edp_num && edp_stream_num && dc->ctx->dce_version < DCE_VERSION_10_0) { for (i = 0; i < edp_num; i++) { edp_link = edp_links[i]; if (edp_link != edp_streams[0]->link) @@ -2385,7 +2385,9 @@ static void dce110_setup_audio_dto( if (pipe_ctx->stream->signal != SIGNAL_TYPE_HDMI_TYPE_A) continue; if (pipe_ctx->stream_res.audio != NULL) { - build_audio_output(context, pipe_ctx, &pipe_ctx->stream_res.audio_output); + struct audio_output audio_output; + + build_audio_output(context, pipe_ctx, &audio_output); if (dc->res_pool->dccg && dc->res_pool->dccg->funcs->set_audio_dtbclk_dto) { struct dtbclk_dto_params dto_params = {0}; @@ -2396,14 +2398,14 @@ static void dce110_setup_audio_dto( pipe_ctx->stream_res.audio->funcs->wall_dto_setup( pipe_ctx->stream_res.audio, pipe_ctx->stream->signal, - &pipe_ctx->stream_res.audio_output.crtc_info, - &pipe_ctx->stream_res.audio_output.pll_info); + &audio_output.crtc_info, + &audio_output.pll_info); } else pipe_ctx->stream_res.audio->funcs->wall_dto_setup( pipe_ctx->stream_res.audio, pipe_ctx->stream->signal, - &pipe_ctx->stream_res.audio_output.crtc_info, - &pipe_ctx->stream_res.audio_output.pll_info); + &audio_output.crtc_info, + &audio_output.pll_info); break; } } @@ -2423,15 +2425,15 @@ static void dce110_setup_audio_dto( continue; if (pipe_ctx->stream_res.audio != NULL) { - build_audio_output(context, - pipe_ctx, - &pipe_ctx->stream_res.audio_output); + struct audio_output audio_output = {0}; + + build_audio_output(context, pipe_ctx, &audio_output); pipe_ctx->stream_res.audio->funcs->wall_dto_setup( pipe_ctx->stream_res.audio, pipe_ctx->stream->signal, - &pipe_ctx->stream_res.audio_output.crtc_info, - &pipe_ctx->stream_res.audio_output.pll_info); + &audio_output.crtc_info, + &audio_output.pll_info); break; } } diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c index 506c3bbbf221..74f5e05f9cb4 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c @@ -55,7 +55,7 @@ #include "dce/dmub_hw_lock_mgr.h" #include "dc_trace.h" #include "dce/dmub_outbox.h" -#include "link.h" +#include "link_service.h" #include "dc_state_priv.h" #define DC_LOGGER \ diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c index 7d24fa1517bf..417f2679723e 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c @@ -54,7 +54,7 @@ #include "dpcd_defs.h" #include "inc/link_enc_cfg.h" #include "link_hwss.h" -#include "link.h" +#include "link_service.h" #include "dc_state_priv.h" #define DC_LOGGER \ @@ -955,7 +955,7 @@ enum dc_status dcn20_enable_stream_timing( return DC_ERROR_UNEXPECTED; } - fsleep(stream->timing.v_total * (stream->timing.h_total * 10000u / stream->timing.pix_clk_100hz)); + udelay(stream->timing.v_total * (stream->timing.h_total * 10000u / stream->timing.pix_clk_100hz)); params.vertical_total_min = stream->adjust.v_total_min; params.vertical_total_max = stream->adjust.v_total_max; diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c index 61efb15572ff..e2269211553c 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c @@ -35,7 +35,7 @@ #include "hw/clk_mgr.h" #include "dc_dmub_srv.h" #include "abm.h" -#include "link.h" +#include "link_service.h" #define DC_LOGGER_INIT(logger) diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c index 139a63101488..e47ed5571dfd 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c @@ -50,7 +50,7 @@ #include "dpcd_defs.h" #include "dcn20/dcn20_hwseq.h" #include "dcn30/dcn30_resource.h" -#include "link.h" +#include "link_service.h" #include "dc_state_priv.h" diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn31/dcn31_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn31/dcn31_hwseq.c index 8ba934b83957..b822f2dffff0 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn31/dcn31_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn31/dcn31_hwseq.c @@ -45,7 +45,7 @@ #include "link_hwss.h" #include "dpcd_defs.h" #include "dce/dmub_outbox.h" -#include "link.h" +#include "link_service.h" #include "dcn10/dcn10_hwseq.h" #include "dcn21/dcn21_hwseq.h" #include "inc/link_enc_cfg.h" diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c index 560984533950..f925f669f2a4 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c @@ -46,7 +46,7 @@ #include "link_hwss.h" #include "dpcd_defs.h" #include "dce/dmub_outbox.h" -#include "link.h" +#include "link_service.h" #include "dcn10/dcn10_hwseq.h" #include "inc/link_enc_cfg.h" #include "dcn30/dcn30_vpg.h" diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c index 416b1dca3dac..f39292952702 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c @@ -49,7 +49,7 @@ #include "dcn20/dcn20_optc.h" #include "dce/dmub_hw_lock_mgr.h" #include "dcn32/dcn32_resource.h" -#include "link.h" +#include "link_service.h" #include "../dcn20/dcn20_hwseq.h" #include "dc_state_priv.h" @@ -1052,7 +1052,7 @@ void dcn32_update_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable) } /* Enable DSC hw block */ - dsc_cfg.pic_width = (stream->timing.h_addressable + pipe_ctx->hblank_borrow + + dsc_cfg.pic_width = (stream->timing.h_addressable + pipe_ctx->dsc_padding_params.dsc_hactive_padding + stream->timing.h_border_left + stream->timing.h_border_right) / opp_cnt; dsc_cfg.pic_height = stream->timing.v_addressable + stream->timing.v_border_top + stream->timing.v_border_bottom; dsc_cfg.pixel_encoding = stream->timing.pixel_encoding; diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c index a267f574b619..05011061822c 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c @@ -46,7 +46,7 @@ #include "link_hwss.h" #include "dpcd_defs.h" #include "dce/dmub_outbox.h" -#include "link.h" +#include "link_service.h" #include "dcn10/dcn10_hwseq.h" #include "inc/link_enc_cfg.h" #include "dcn30/dcn30_vpg.h" @@ -113,6 +113,14 @@ static void enable_memory_low_power(struct dc *dc) } #endif +static void print_pg_status(struct dc *dc, const char *debug_func, const char *debug_log) +{ + if (dc->debug.enable_pg_cntl_debug_logs && dc->res_pool->pg_cntl) { + if (dc->res_pool->pg_cntl->funcs->print_pg_status) + dc->res_pool->pg_cntl->funcs->print_pg_status(dc->res_pool->pg_cntl, debug_func, debug_log); + } +} + void dcn35_set_dmu_fgcg(struct dce_hwseq *hws, bool enable) { REG_UPDATE_3(DMU_CLK_CNTL, @@ -137,6 +145,8 @@ void dcn35_init_hw(struct dc *dc) uint32_t user_level = MAX_BACKLIGHT_LEVEL; int i; + print_pg_status(dc, __func__, ": start"); + if (dc->clk_mgr && dc->clk_mgr->funcs->init_clocks) dc->clk_mgr->funcs->init_clocks(dc->clk_mgr); @@ -200,10 +210,7 @@ void dcn35_init_hw(struct dc *dc) /* we want to turn off all dp displays before doing detection */ dc->link_srv->blank_all_dp_displays(dc); -/* - if (hws->funcs.enable_power_gating_plane) - hws->funcs.enable_power_gating_plane(dc->hwseq, true); -*/ + if (res_pool->hubbub && res_pool->hubbub->funcs->dchubbub_init) res_pool->hubbub->funcs->dchubbub_init(dc->res_pool->hubbub); /* If taking control over from VBIOS, we may want to optimize our first @@ -236,6 +243,8 @@ void dcn35_init_hw(struct dc *dc) } hws->funcs.init_pipes(dc, dc->current_state); + print_pg_status(dc, __func__, ": after init_pipes"); + if (dc->res_pool->hubbub->funcs->allow_self_refresh_control && !dc->res_pool->hubbub->ctx->dc->debug.disable_stutter) dc->res_pool->hubbub->funcs->allow_self_refresh_control(dc->res_pool->hubbub, @@ -312,6 +321,7 @@ void dcn35_init_hw(struct dc *dc) if (dc->res_pool->pg_cntl->funcs->init_pg_status) dc->res_pool->pg_cntl->funcs->init_pg_status(dc->res_pool->pg_cntl); } + print_pg_status(dc, __func__, ": after init_pg_status"); } static void update_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable) @@ -500,97 +510,6 @@ void dcn35_physymclk_root_clock_control(struct dce_hwseq *hws, unsigned int phy_ } } -void dcn35_dsc_pg_control( - struct dce_hwseq *hws, - unsigned int dsc_inst, - bool power_on) -{ - uint32_t power_gate = power_on ? 0 : 1; - uint32_t pwr_status = power_on ? 0 : 2; - uint32_t org_ip_request_cntl = 0; - - if (hws->ctx->dc->debug.disable_dsc_power_gate) - return; - if (hws->ctx->dc->debug.ignore_pg) - return; - REG_GET(DC_IP_REQUEST_CNTL, IP_REQUEST_EN, &org_ip_request_cntl); - if (org_ip_request_cntl == 0) - REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 1); - - switch (dsc_inst) { - case 0: /* DSC0 */ - REG_UPDATE(DOMAIN16_PG_CONFIG, - DOMAIN_POWER_GATE, power_gate); - - REG_WAIT(DOMAIN16_PG_STATUS, - DOMAIN_PGFSM_PWR_STATUS, pwr_status, - 1, 1000); - break; - case 1: /* DSC1 */ - REG_UPDATE(DOMAIN17_PG_CONFIG, - DOMAIN_POWER_GATE, power_gate); - - REG_WAIT(DOMAIN17_PG_STATUS, - DOMAIN_PGFSM_PWR_STATUS, pwr_status, - 1, 1000); - break; - case 2: /* DSC2 */ - REG_UPDATE(DOMAIN18_PG_CONFIG, - DOMAIN_POWER_GATE, power_gate); - - REG_WAIT(DOMAIN18_PG_STATUS, - DOMAIN_PGFSM_PWR_STATUS, pwr_status, - 1, 1000); - break; - case 3: /* DSC3 */ - REG_UPDATE(DOMAIN19_PG_CONFIG, - DOMAIN_POWER_GATE, power_gate); - - REG_WAIT(DOMAIN19_PG_STATUS, - DOMAIN_PGFSM_PWR_STATUS, pwr_status, - 1, 1000); - break; - default: - BREAK_TO_DEBUGGER(); - break; - } - - if (org_ip_request_cntl == 0) - REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 0); -} - -void dcn35_enable_power_gating_plane(struct dce_hwseq *hws, bool enable) -{ - bool force_on = true; /* disable power gating */ - uint32_t org_ip_request_cntl = 0; - - if (hws->ctx->dc->debug.disable_hubp_power_gate) - return; - if (hws->ctx->dc->debug.ignore_pg) - return; - REG_GET(DC_IP_REQUEST_CNTL, IP_REQUEST_EN, &org_ip_request_cntl); - if (org_ip_request_cntl == 0) - REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 1); - /* DCHUBP0/1/2/3/4/5 */ - REG_UPDATE(DOMAIN0_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_UPDATE(DOMAIN2_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - /* DPP0/1/2/3/4/5 */ - REG_UPDATE(DOMAIN1_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_UPDATE(DOMAIN3_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - - force_on = true; /* disable power gating */ - if (enable && !hws->ctx->dc->debug.disable_dsc_power_gate) - force_on = false; - - /* DCS0/1/2/3/4 */ - REG_UPDATE(DOMAIN16_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_UPDATE(DOMAIN17_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_UPDATE(DOMAIN18_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_UPDATE(DOMAIN19_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - - -} - /* In headless boot cases, DIG may be turned * on which causes HW/SW discrepancies. * To avoid this, power down hardware on boot @@ -1453,6 +1372,8 @@ void dcn35_prepare_bandwidth( } dcn20_prepare_bandwidth(dc, context); + + print_pg_status(dc, __func__, ": after rcg and power up"); } void dcn35_optimize_bandwidth( @@ -1461,6 +1382,8 @@ void dcn35_optimize_bandwidth( { struct pg_block_update pg_update_state; + print_pg_status(dc, __func__, ": before rcg and power up"); + dcn20_optimize_bandwidth(dc, context); if (dc->hwss.calc_blocks_to_gate) { @@ -1472,6 +1395,8 @@ void dcn35_optimize_bandwidth( if (dc->hwss.root_clock_control) dc->hwss.root_clock_control(dc, &pg_update_state, false); } + + print_pg_status(dc, __func__, ": after rcg and power up"); } void dcn35_set_drr(struct pipe_ctx **pipe_ctx, diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c index 52cc488416ac..f2f16a0bdb4f 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c @@ -115,7 +115,6 @@ static const struct hw_sequencer_funcs dcn35_funcs = { .exit_optimized_pwr_state = dcn21_exit_optimized_pwr_state, .update_visual_confirm_color = dcn10_update_visual_confirm_color, .apply_idle_power_optimizations = dcn35_apply_idle_power_optimizations, - .update_dsc_pg = dcn32_update_dsc_pg, .calc_blocks_to_gate = dcn35_calc_blocks_to_gate, .calc_blocks_to_ungate = dcn35_calc_blocks_to_ungate, .hw_block_power_up = dcn35_hw_block_power_up, @@ -151,7 +150,6 @@ static const struct hwseq_private_funcs dcn35_private_funcs = { .plane_atomic_disable = dcn35_plane_atomic_disable, //.plane_atomic_disable = dcn20_plane_atomic_disable,/*todo*/ //.hubp_pg_control = dcn35_hubp_pg_control, - .enable_power_gating_plane = dcn35_enable_power_gating_plane, .dpp_root_clock_control = dcn35_dpp_root_clock_control, .dpstream_root_clock_control = dcn35_dpstream_root_clock_control, .physymclk_root_clock_control = dcn35_physymclk_root_clock_control, @@ -166,7 +164,6 @@ static const struct hwseq_private_funcs dcn35_private_funcs = { .calculate_dccg_k1_k2_values = dcn32_calculate_dccg_k1_k2_values, .resync_fifo_dccg_dio = dcn314_resync_fifo_dccg_dio, .is_dp_dig_pixel_rate_div_policy = dcn35_is_dp_dig_pixel_rate_div_policy, - .dsc_pg_control = dcn35_dsc_pg_control, .dsc_pg_status = dcn32_dsc_pg_status, .enable_plane = dcn35_enable_plane, .wait_for_pipe_update_if_needed = dcn10_wait_for_pipe_update_if_needed, diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c index e34efcb7bde5..09e60158f0b5 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c @@ -114,7 +114,6 @@ static const struct hw_sequencer_funcs dcn351_funcs = { .exit_optimized_pwr_state = dcn21_exit_optimized_pwr_state, .update_visual_confirm_color = dcn10_update_visual_confirm_color, .apply_idle_power_optimizations = dcn35_apply_idle_power_optimizations, - .update_dsc_pg = dcn32_update_dsc_pg, .calc_blocks_to_gate = dcn351_calc_blocks_to_gate, .calc_blocks_to_ungate = dcn351_calc_blocks_to_ungate, .hw_block_power_up = dcn351_hw_block_power_up, @@ -146,7 +145,6 @@ static const struct hwseq_private_funcs dcn351_private_funcs = { .plane_atomic_disable = dcn35_plane_atomic_disable, //.plane_atomic_disable = dcn20_plane_atomic_disable,/*todo*/ //.hubp_pg_control = dcn35_hubp_pg_control, - .enable_power_gating_plane = dcn35_enable_power_gating_plane, .dpp_root_clock_control = dcn35_dpp_root_clock_control, .dpstream_root_clock_control = dcn35_dpstream_root_clock_control, .physymclk_root_clock_control = dcn35_physymclk_root_clock_control, @@ -160,7 +158,6 @@ static const struct hwseq_private_funcs dcn351_private_funcs = { .setup_hpo_hw_control = dcn35_setup_hpo_hw_control, .calculate_dccg_k1_k2_values = dcn32_calculate_dccg_k1_k2_values, .is_dp_dig_pixel_rate_div_policy = dcn35_is_dp_dig_pixel_rate_div_policy, - .dsc_pg_control = dcn35_dsc_pg_control, .dsc_pg_status = dcn32_dsc_pg_status, .enable_plane = dcn35_enable_plane, .wait_for_pipe_update_if_needed = dcn10_wait_for_pipe_update_if_needed, diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c index d5b5e2ce6ff6..1b0b772fc5dd 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c @@ -25,7 +25,7 @@ #include "dpcd_defs.h" #include "clk_mgr.h" #include "dsc.h" -#include "link.h" +#include "link_service.h" #include "dce/dmub_hw_lock_mgr.h" #include "dcn10/dcn10_cm_common.h" @@ -810,9 +810,12 @@ enum dc_status dcn401_enable_stream_timing( if (dc->hwseq->funcs.PLAT_58856_wa && (!dc_is_dp_signal(stream->signal))) dc->hwseq->funcs.PLAT_58856_wa(context, pipe_ctx); - /* if we are borrowing from hblank, h_addressable needs to be adjusted */ - if (dc->debug.enable_hblank_borrow) - patched_crtc_timing.h_addressable = patched_crtc_timing.h_addressable + pipe_ctx->hblank_borrow; + /* if we are padding, h_addressable needs to be adjusted */ + if (dc->debug.enable_hblank_borrow) { + patched_crtc_timing.h_addressable = patched_crtc_timing.h_addressable + pipe_ctx->dsc_padding_params.dsc_hactive_padding; + patched_crtc_timing.h_total = patched_crtc_timing.h_total + pipe_ctx->dsc_padding_params.dsc_htotal_padding; + patched_crtc_timing.pix_clk_100hz = pipe_ctx->dsc_padding_params.dsc_pix_clk_100hz; + } pipe_ctx->stream_res.tg->funcs->program_timing( pipe_ctx->stream_res.tg, diff --git a/drivers/gpu/drm/amd/display/dc/inc/core_types.h b/drivers/gpu/drm/amd/display/dc/inc/core_types.h index d30f94c35f11..d11893f8c916 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/core_types.h +++ b/drivers/gpu/drm/amd/display/dc/inc/core_types.h @@ -228,7 +228,8 @@ struct resource_funcs { enum dc_status (*update_dc_state_for_encoder_switch)(struct dc_link *link, struct dc_link_settings *link_setting, uint8_t pipe_count, - struct pipe_ctx *pipes); + struct pipe_ctx *pipes, + struct audio_output *audio_output); }; struct audio_support{ @@ -360,8 +361,6 @@ struct stream_resource { uint8_t gsl_group; struct test_pattern_params test_pattern_params; - - struct audio_output audio_output; }; struct plane_resource { @@ -437,6 +436,13 @@ enum p_state_switch_method { P_STATE_V_BLANK_SUB_VP, }; +struct dsc_padding_params { + /* pixels borrowed from hblank to hactive */ + uint8_t dsc_hactive_padding; + uint32_t dsc_htotal_padding; + uint32_t dsc_pix_clk_100hz; +}; + struct pipe_ctx { struct dc_plane_state *plane_state; struct dc_stream_state *stream; @@ -494,8 +500,7 @@ struct pipe_ctx { /* subvp_index: only valid if the pipe is a SUBVP_MAIN*/ uint8_t subvp_index; struct pixel_rate_divider pixel_rate_divider; - /* pixels borrowed from hblank to hactive */ - uint8_t hblank_borrow; + struct dsc_padding_params dsc_padding_params; /* next vupdate */ uint32_t next_vupdate; uint32_t wait_frame_count; diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h index 9bee45b36629..843a18287c83 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h @@ -137,6 +137,19 @@ struct dcn_hubbub_state { uint32_t dram_state_cntl; }; +struct hubbub_system_latencies { + uint32_t max_latency_ns; + uint32_t avg_latency_ns; + uint32_t min_latency_ns; +}; + +struct hubbub_urgent_latency_params { + uint32_t refclk_mhz; + uint32_t t_win_ns; + uint32_t bandwidth_mbps; + uint32_t bw_factor_x1000; +}; + struct hubbub_funcs { void (*update_dchub)( struct hubbub *hubbub, @@ -231,6 +244,15 @@ struct hubbub_funcs { bool (*program_arbiter)(struct hubbub *hubbub, struct dml2_display_arb_regs *arb_regs, bool safe_to_lower); void (*get_det_sizes)(struct hubbub *hubbub, uint32_t *curr_det_sizes, uint32_t *target_det_sizes); uint32_t (*compbuf_config_error)(struct hubbub *hubbub); + struct hubbub_perfmon_funcs{ + void (*start_system_latency_measurement)(struct hubbub *hubbub); + void (*get_system_latency_result)(struct hubbub *hubbub, uint32_t refclk_mhz, struct hubbub_system_latencies *latencies); + void (*start_in_order_bandwidth_measurement)(struct hubbub *hubbub); + void (*get_in_order_bandwidth_result)(struct hubbub *hubbub, uint32_t refclk_mhz, uint32_t *bandwidth_mbps); + void (*start_urgent_ramp_latency_measurement)(struct hubbub *hubbub, const struct hubbub_urgent_latency_params *params); + void (*get_urgent_ramp_latency_result)(struct hubbub *hubbub, uint32_t refclk_mhz, uint32_t *latency_ns); + void (*reset)(struct hubbub *hubbub); + } perfmon; }; struct hubbub { diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/pg_cntl.h b/drivers/gpu/drm/amd/display/dc/inc/hw/pg_cntl.h index 44f86cc2d1d6..227e3f8d7e5f 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/pg_cntl.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/pg_cntl.h @@ -49,6 +49,7 @@ struct pg_cntl_funcs { void (*mem_pg_control)(struct pg_cntl *pg_cntl, bool power_on); void (*dio_pg_control)(struct pg_cntl *pg_cntl, bool power_on); void (*init_pg_status)(struct pg_cntl *pg_cntl); + void (*print_pg_status)(struct pg_cntl *pg_cntl, const char *debug_func, const char *debug_log); }; #endif //__DC_PG_CNTL_H__ diff --git a/drivers/gpu/drm/amd/display/dc/inc/link.h b/drivers/gpu/drm/amd/display/dc/inc/link_service.h index 0cce49d95e26..1e34e84160aa 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/link.h +++ b/drivers/gpu/drm/amd/display/dc/inc/link_service.h @@ -42,8 +42,8 @@ * dc_link_exports.c or other dc files implement dc.h * * DC to Link: - * dc_link_exports.c or other dc files include link.h - * link_factory.c implements link.h + * dc_link_exports.c or other dc files include link_service.h + * link_factory.c implements link_service.h * * Link sub-component to Link sub-component: * link_factory.c includes --> link_xxx.h @@ -73,7 +73,7 @@ * 2. Implement your function in the suitable link_xxx.c file. * 3. Assign the function to link_service in link_factory.c * 4. NEVER include link_xxx.h headers outside link component. - * 5. NEVER include link.h on DM side. + * 5. NEVER include link_service.h on DM side. */ #include "core_types.h" diff --git a/drivers/gpu/drm/amd/display/dc/inc/resource.h b/drivers/gpu/drm/amd/display/dc/inc/resource.h index a890f581f4e8..4e26a16a8743 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/resource.h +++ b/drivers/gpu/drm/amd/display/dc/inc/resource.h @@ -45,6 +45,7 @@ enum dce_version resource_parse_asic_id( struct resource_caps { int num_timing_generator; int num_opp; + int num_dpp; int num_video_plane; int num_audio; int num_stream_encoder; diff --git a/drivers/gpu/drm/amd/display/dc/link/accessories/link_dp_cts.c b/drivers/gpu/drm/amd/display/dc/link/accessories/link_dp_cts.c index 23f41c99fa38..9e33bf937a69 100644 --- a/drivers/gpu/drm/amd/display/dc/link/accessories/link_dp_cts.c +++ b/drivers/gpu/drm/amd/display/dc/link/accessories/link_dp_cts.c @@ -75,7 +75,7 @@ static void dp_retrain_link_dp_test(struct dc_link *link, bool is_hpo_acquired; uint8_t count; int i; - + struct audio_output audio_output[MAX_PIPES]; struct dc_stream_state *streams_on_link[MAX_PIPES]; int num_streams_on_link = 0; @@ -101,7 +101,7 @@ static void dp_retrain_link_dp_test(struct dc_link *link, if (needs_divider_update && link->dc->res_pool->funcs->update_dc_state_for_encoder_switch) { link->dc->res_pool->funcs->update_dc_state_for_encoder_switch(link, link_setting, count, - *pipes); + *pipes, &audio_output[0]); for (i = 0; i < count; i++) { pipes[i]->clock_source->funcs->program_pix_clk( pipes[i]->clock_source, @@ -113,16 +113,15 @@ static void dp_retrain_link_dp_test(struct dc_link *link, const struct link_hwss *link_hwss = get_link_hwss( link, &pipes[i]->link_res); - link_hwss->setup_audio_output(pipes[i], - &pipes[i]->stream_res.audio_output, - pipes[i]->stream_res.audio->inst); + link_hwss->setup_audio_output(pipes[i], &audio_output[i], + pipes[i]->stream_res.audio->inst); pipes[i]->stream_res.audio->funcs->az_configure( pipes[i]->stream_res.audio, pipes[i]->stream->signal, - &pipes[i]->stream_res.audio_output.crtc_info, + &audio_output[i].crtc_info, &pipes[i]->stream->audio_info, - &pipes[i]->stream_res.audio_output.dp_link_info); + &audio_output[i].dp_link_info); if (link->dc->config.disable_hbr_audio_dp2 && pipes[i]->stream_res.audio->funcs->az_disable_hbr_audio && diff --git a/drivers/gpu/drm/amd/display/dc/link/accessories/link_dp_cts.h b/drivers/gpu/drm/amd/display/dc/link/accessories/link_dp_cts.h index eae23ea7f6ec..033650cdb811 100644 --- a/drivers/gpu/drm/amd/display/dc/link/accessories/link_dp_cts.h +++ b/drivers/gpu/drm/amd/display/dc/link/accessories/link_dp_cts.h @@ -24,7 +24,7 @@ */ #ifndef __LINK_DP_CTS_H__ #define __LINK_DP_CTS_H__ -#include "link.h" +#include "link_service.h" void dp_handle_automated_test(struct dc_link *link); bool dp_set_test_pattern( struct dc_link *link, diff --git a/drivers/gpu/drm/amd/display/dc/link/accessories/link_dp_trace.h b/drivers/gpu/drm/amd/display/dc/link/accessories/link_dp_trace.h index ab437a0c9101..9ff4a6c46a2b 100644 --- a/drivers/gpu/drm/amd/display/dc/link/accessories/link_dp_trace.h +++ b/drivers/gpu/drm/amd/display/dc/link/accessories/link_dp_trace.h @@ -24,7 +24,7 @@ */ #ifndef __LINK_DP_TRACE_H__ #define __LINK_DP_TRACE_H__ -#include "link.h" +#include "link_service.h" void dp_trace_init(struct dc_link *link); void dp_trace_reset(struct dc_link *link); diff --git a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.c b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.c index b68bcc9fca0a..892907991f91 100644 --- a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.c +++ b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.c @@ -138,8 +138,7 @@ void setup_dio_stream_attribute(struct pipe_ctx *pipe_ctx) stream_encoder->funcs->dvi_set_stream_attribute( stream_encoder, &stream->timing, - (stream->signal == SIGNAL_TYPE_DVI_DUAL_LINK) ? - true : false); + stream->signal == SIGNAL_TYPE_DVI_DUAL_LINK); else if (dc_is_lvds_signal(stream->signal)) stream_encoder->funcs->lvds_set_stream_attribute( stream_encoder, diff --git a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.h b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.h index 45f0e091fcb0..4a25210a344f 100644 --- a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.h +++ b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.h @@ -27,7 +27,7 @@ #define __LINK_HWSS_DIO_H__ #include "link_hwss.h" -#include "link.h" +#include "link_service.h" const struct link_hwss *get_dio_link_hwss(void); bool can_use_dio_link_hwss(const struct dc_link *link, diff --git a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio_fixed_vs_pe_retimer.h b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio_fixed_vs_pe_retimer.h index 9ac08a332540..cf578a8662a4 100644 --- a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio_fixed_vs_pe_retimer.h +++ b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio_fixed_vs_pe_retimer.h @@ -25,7 +25,7 @@ #ifndef __LINK_HWSS_DIO_FIXED_VS_PE_RETIMER_H__ #define __LINK_HWSS_DIO_FIXED_VS_PE_RETIMER_H__ -#include "link.h" +#include "link_service.h" uint32_t dp_dio_fixed_vs_pe_retimer_get_lttpr_write_address(struct dc_link *link); uint8_t dp_dio_fixed_vs_pe_retimer_lane_cfg_to_hw_cfg(struct dc_link *link); diff --git a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_hpo_dp.h b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_hpo_dp.h index 1d3ed8ca83b5..7c9005bc2587 100644 --- a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_hpo_dp.h +++ b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_hpo_dp.h @@ -26,7 +26,7 @@ #define __LINK_HWSS_HPO_DP_H__ #include "link_hwss.h" -#include "link.h" +#include "link_service.h" void set_hpo_dp_throttled_vcp_size(struct pipe_ctx *pipe_ctx, struct fixed31_32 throttled_vcp_size); diff --git a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_hpo_fixed_vs_pe_retimer_dp.h b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_hpo_fixed_vs_pe_retimer_dp.h index 82301187bc7c..8bf36827ecfb 100644 --- a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_hpo_fixed_vs_pe_retimer_dp.h +++ b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_hpo_fixed_vs_pe_retimer_dp.h @@ -25,7 +25,7 @@ #ifndef __LINK_HWSS_HPO_FIXED_VS_PE_RETIMER_DP_H__ #define __LINK_HWSS_HPO_FIXED_VS_PE_RETIMER_DP_H__ -#include "link.h" +#include "link_service.h" bool requires_fixed_vs_pe_retimer_hpo_link_hwss(const struct dc_link *link); const struct link_hwss *get_hpo_fixed_vs_pe_retimer_dp_link_hwss(void); diff --git a/drivers/gpu/drm/amd/display/dc/link/link_detection.c b/drivers/gpu/drm/amd/display/dc/link/link_detection.c index 827b630daf49..85303167a553 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_detection.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_detection.c @@ -656,7 +656,7 @@ static bool wait_for_entering_dp_alt_mode(struct dc_link *link) return true; is_in_alt_mode = link->link_enc->funcs->is_in_alt_mode(link->link_enc); - DC_LOG_DC("DP Alt mode state on HPD: %d\n", is_in_alt_mode); + DC_LOG_DC("DP Alt mode state on HPD: %d Link=%d\n", is_in_alt_mode, link->link_index); if (is_in_alt_mode) return true; @@ -1140,6 +1140,10 @@ static bool detect_link_and_local_sink(struct dc_link *link, if (sink->sink_signal == SIGNAL_TYPE_HDMI_TYPE_A && !sink->edid_caps.edid_hdmi) sink->sink_signal = SIGNAL_TYPE_DVI_SINGLE_LINK; + else if (dc_is_dvi_signal(sink->sink_signal) && + aud_support->hdmi_audio_native && + sink->edid_caps.edid_hdmi) + sink->sink_signal = SIGNAL_TYPE_HDMI_TYPE_A; if (link->local_sink && dc_is_dp_signal(sink_caps.signal)) dp_trace_init(link); diff --git a/drivers/gpu/drm/amd/display/dc/link/link_detection.h b/drivers/gpu/drm/amd/display/dc/link/link_detection.h index 7da05078721e..1ab29476060b 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_detection.h +++ b/drivers/gpu/drm/amd/display/dc/link/link_detection.h @@ -25,7 +25,7 @@ #ifndef __DC_LINK_DETECTION_H__ #define __DC_LINK_DETECTION_H__ -#include "link.h" +#include "link_service.h" bool link_detect(struct dc_link *link, enum dc_detect_reason reason); bool link_detect_connection_type(struct dc_link *link, enum dc_connection_type *type); diff --git a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c index cb80b4599936..83419e1a9036 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c @@ -832,7 +832,7 @@ void link_set_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable) enum optc_dsc_mode optc_dsc_mode; /* Enable DSC hw block */ - dsc_cfg.pic_width = (stream->timing.h_addressable + pipe_ctx->hblank_borrow + + dsc_cfg.pic_width = (stream->timing.h_addressable + pipe_ctx->dsc_padding_params.dsc_hactive_padding + stream->timing.h_border_left + stream->timing.h_border_right) / opp_cnt; dsc_cfg.pic_height = stream->timing.v_addressable + stream->timing.v_border_top + stream->timing.v_border_bottom; dsc_cfg.pixel_encoding = stream->timing.pixel_encoding; @@ -2358,9 +2358,9 @@ void link_set_dpms_off(struct pipe_ctx *pipe_ctx) if (pipe_ctx->stream->sink) { if (pipe_ctx->stream->sink->sink_signal != SIGNAL_TYPE_VIRTUAL && pipe_ctx->stream->sink->sink_signal != SIGNAL_TYPE_NONE) { - DC_LOG_DC("%s pipe_ctx dispname=%s signal=%x\n", __func__, + DC_LOG_DC("%s pipe_ctx dispname=%s signal=%x link=%d\n", __func__, pipe_ctx->stream->sink->edid_caps.display_name, - pipe_ctx->stream->signal); + pipe_ctx->stream->signal, link->link_index); } } @@ -2473,9 +2473,10 @@ void link_set_dpms_on( if (pipe_ctx->stream->sink) { if (pipe_ctx->stream->sink->sink_signal != SIGNAL_TYPE_VIRTUAL && pipe_ctx->stream->sink->sink_signal != SIGNAL_TYPE_NONE) { - DC_LOG_DC("%s pipe_ctx dispname=%s signal=%x\n", __func__, + DC_LOG_DC("%s pipe_ctx dispname=%s signal=%x link=%d\n", __func__, pipe_ctx->stream->sink->edid_caps.display_name, - pipe_ctx->stream->signal); + pipe_ctx->stream->signal, + link->link_index); } } diff --git a/drivers/gpu/drm/amd/display/dc/link/link_dpms.h b/drivers/gpu/drm/amd/display/dc/link/link_dpms.h index 9398f9c1666a..bd6fc63064a3 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_dpms.h +++ b/drivers/gpu/drm/amd/display/dc/link/link_dpms.h @@ -26,7 +26,7 @@ #ifndef __DC_LINK_DPMS_H__ #define __DC_LINK_DPMS_H__ -#include "link.h" +#include "link_service.h" void link_set_dpms_on( struct dc_state *state, struct pipe_ctx *pipe_ctx); diff --git a/drivers/gpu/drm/amd/display/dc/link/link_factory.h b/drivers/gpu/drm/amd/display/dc/link/link_factory.h index e96220d48d03..aad36ca1a31c 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_factory.h +++ b/drivers/gpu/drm/amd/display/dc/link/link_factory.h @@ -24,7 +24,7 @@ */ #ifndef __LINK_FACTORY_H__ #define __LINK_FACTORY_H__ -#include "link.h" +#include "link_service.h" struct dc_link *link_create(const struct link_init_data *init_params); void link_destroy(struct dc_link **link); diff --git a/drivers/gpu/drm/amd/display/dc/link/link_resource.h b/drivers/gpu/drm/amd/display/dc/link/link_resource.h index 1907bda3cb6e..f7aa3bc3a93a 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_resource.h +++ b/drivers/gpu/drm/amd/display/dc/link/link_resource.h @@ -24,7 +24,7 @@ */ #ifndef __LINK_RESOURCE_H__ #define __LINK_RESOURCE_H__ -#include "link.h" +#include "link_service.h" void link_get_cur_res_map(const struct dc *dc, uint32_t *map); void link_restore_res_map(const struct dc *dc, uint32_t *map); void link_get_cur_link_res(const struct dc_link *link, diff --git a/drivers/gpu/drm/amd/display/dc/link/link_validation.h b/drivers/gpu/drm/amd/display/dc/link/link_validation.h index 9553c81053fe..595774e76453 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_validation.h +++ b/drivers/gpu/drm/amd/display/dc/link/link_validation.h @@ -24,7 +24,7 @@ */ #ifndef __LINK_VALIDATION_H__ #define __LINK_VALIDATION_H__ -#include "link.h" +#include "link_service.h" enum dc_status link_validate_mode_timing( const struct dc_stream_state *stream, diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_ddc.h b/drivers/gpu/drm/amd/display/dc/link/protocols/link_ddc.h index a3e25e55bed6..d3e6f01a6a90 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_ddc.h +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_ddc.h @@ -26,7 +26,7 @@ #ifndef __DAL_DDC_SERVICE_H__ #define __DAL_DDC_SERVICE_H__ -#include "link.h" +#include "link_service.h" #define AUX_POWER_UP_WA_DELAY 500 #define I2C_OVER_AUX_DEFER_WA_DELAY 70 diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c index caddb7dfb133..b12c11bd6a14 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c @@ -2195,6 +2195,12 @@ void detect_edp_sink_caps(struct dc_link *link) DP_EDP_MSO_LINK_CAPABILITIES, (uint8_t *)&link->dpcd_caps.mso_cap_sst_links_supported, sizeof(link->dpcd_caps.mso_cap_sst_links_supported)); + /* + * Read eDP general capability 2 + */ + core_link_read_dpcd(link, DP_EDP_GENERAL_CAP_2, + (uint8_t *)&link->dpcd_caps.dp_edp_general_cap_2, + sizeof(link->dpcd_caps.dp_edp_general_cap_2)); } bool dp_get_max_link_enc_cap(const struct dc_link *link, struct dc_link_settings *max_link_enc_cap) diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.h b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.h index 7170db5a1c13..6e17f72a752f 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.h +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.h @@ -26,7 +26,7 @@ #ifndef __DC_LINK_DP_CAPABILITY_H__ #define __DC_LINK_DP_CAPABILITY_H__ -#include "link.h" +#include "link_service.h" bool detect_dp_sink_caps(struct dc_link *link); diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia.h b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia.h index a61edfc9ca7a..7cd03fa4892b 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia.h +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia.h @@ -27,7 +27,7 @@ #ifndef __DC_LINK_DPIA_H__ #define __DC_LINK_DPIA_H__ -#include "link.h" +#include "link_service.h" /* Read tunneling device capability from DPCD and update link capability * accordingly. diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.h b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.h index 41efcb3e44e2..30cd8e2b9d35 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.h +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.h @@ -26,7 +26,7 @@ #ifndef DC_INC_LINK_DP_DPIA_BW_H_ #define DC_INC_LINK_DP_DPIA_BW_H_ -#include "link.h" +#include "link_service.h" /* diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_irq_handler.h b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_irq_handler.h index ac33730fedd4..87516fb3b45a 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_irq_handler.h +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_irq_handler.h @@ -26,7 +26,7 @@ #ifndef __DC_LINK_DP_IRQ_HANDLER_H__ #define __DC_LINK_DP_IRQ_HANDLER_H__ -#include "link.h" +#include "link_service.h" bool dp_parse_link_loss_status( struct dc_link *link, union hpd_irq_data *hpd_irq_dpcd_data); diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_phy.h b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_phy.h index ab1c1f8f1f8b..58e154494582 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_phy.h +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_phy.h @@ -26,7 +26,7 @@ #ifndef __DC_LINK_DP_PHY_H__ #define __DC_LINK_DP_PHY_H__ -#include "link.h" +#include "link_service.h" void dp_enable_link_phy( struct dc_link *link, const struct link_resource *link_res, diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c index 134093ce5a8e..08e2b572e0ff 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c @@ -1729,6 +1729,15 @@ bool perform_link_training_with_retries( break; } + if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA && + stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST && + !link->dc->config.enable_dpia_pre_training) { + if (j == (attempts - 1)) + do_fallback = true; + else + do_fallback = false; + } + if (j == (attempts - 1)) { DC_LOG_WARNING( "%s: Link(%d) training attempt %u of %d failed @ rate(%d) x lane(%d) @ spread = %x : fail reason:(%d)\n", diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.h b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.h index 574b083e0936..ce52de22ab7a 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.h +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.h @@ -26,7 +26,7 @@ #ifndef __DC_LINK_DP_TRAINING_H__ #define __DC_LINK_DP_TRAINING_H__ -#include "link.h" +#include "link_service.h" bool perform_link_training_with_retries( const struct dc_link_settings *link_setting, diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dpcd.h b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dpcd.h index 08d787a1e451..c2717c678c72 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dpcd.h +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dpcd.h @@ -25,7 +25,7 @@ #ifndef __LINK_DPCD_H__ #define __LINK_DPCD_H__ -#include "link.h" +#include "link_service.h" #include "dpcd_defs.h" enum dc_status core_link_read_dpcd( diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.h b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.h index 4a475d5b9dde..62a6344e613e 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.h +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.h @@ -25,7 +25,7 @@ #ifndef __DC_LINK_EDP_PANEL_CONTROL_H__ #define __DC_LINK_EDP_PANEL_CONTROL_H__ -#include "link.h" +#include "link_service.h" enum dp_panel_mode dp_get_panel_mode(struct dc_link *link); void dp_set_panel_mode(struct dc_link *link, enum dp_panel_mode panel_mode); diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_hpd.h b/drivers/gpu/drm/amd/display/dc/link/protocols/link_hpd.h index 4fb526b264f9..af529328ba17 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_hpd.h +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_hpd.h @@ -26,7 +26,7 @@ #ifndef __DC_LINK_HPD_H__ #define __DC_LINK_HPD_H__ -#include "link.h" +#include "link_service.h" enum hpd_source_id get_hpd_line(struct dc_link *link); /* diff --git a/drivers/gpu/drm/amd/display/dc/pg/dcn35/dcn35_pg_cntl.c b/drivers/gpu/drm/amd/display/dc/pg/dcn35/dcn35_pg_cntl.c index af21c0a27f86..72bd43f9bbe2 100644 --- a/drivers/gpu/drm/amd/display/dc/pg/dcn35/dcn35_pg_cntl.c +++ b/drivers/gpu/drm/amd/display/dc/pg/dcn35/dcn35_pg_cntl.c @@ -79,16 +79,12 @@ void pg_cntl35_dsc_pg_control(struct pg_cntl *pg_cntl, unsigned int dsc_inst, bo uint32_t power_gate = power_on ? 0 : 1; uint32_t pwr_status = power_on ? 0 : 2; uint32_t org_ip_request_cntl = 0; - bool block_enabled; - - /*need to enable dscclk regardless DSC_PG*/ - if (pg_cntl->ctx->dc->res_pool->dccg->funcs->enable_dsc && power_on) - pg_cntl->ctx->dc->res_pool->dccg->funcs->enable_dsc( - pg_cntl->ctx->dc->res_pool->dccg, dsc_inst); + bool block_enabled = false; + bool skip_pg = pg_cntl->ctx->dc->debug.ignore_pg || + pg_cntl->ctx->dc->debug.disable_dsc_power_gate || + pg_cntl->ctx->dc->idle_optimizations_allowed; - if (pg_cntl->ctx->dc->debug.ignore_pg || - pg_cntl->ctx->dc->debug.disable_dsc_power_gate || - pg_cntl->ctx->dc->idle_optimizations_allowed) + if (skip_pg && !power_on) return; block_enabled = pg_cntl35_dsc_pg_status(pg_cntl, dsc_inst); @@ -111,7 +107,7 @@ void pg_cntl35_dsc_pg_control(struct pg_cntl *pg_cntl, unsigned int dsc_inst, bo REG_WAIT(DOMAIN16_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, - 1, 1000); + 1, 10000); break; case 1: /* DSC1 */ REG_UPDATE(DOMAIN17_PG_CONFIG, @@ -119,7 +115,7 @@ void pg_cntl35_dsc_pg_control(struct pg_cntl *pg_cntl, unsigned int dsc_inst, bo REG_WAIT(DOMAIN17_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, - 1, 1000); + 1, 10000); break; case 2: /* DSC2 */ REG_UPDATE(DOMAIN18_PG_CONFIG, @@ -127,7 +123,7 @@ void pg_cntl35_dsc_pg_control(struct pg_cntl *pg_cntl, unsigned int dsc_inst, bo REG_WAIT(DOMAIN18_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, - 1, 1000); + 1, 10000); break; case 3: /* DSC3 */ REG_UPDATE(DOMAIN19_PG_CONFIG, @@ -135,7 +131,7 @@ void pg_cntl35_dsc_pg_control(struct pg_cntl *pg_cntl, unsigned int dsc_inst, bo REG_WAIT(DOMAIN19_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, - 1, 1000); + 1, 10000); break; default: BREAK_TO_DEBUGGER(); @@ -144,12 +140,6 @@ void pg_cntl35_dsc_pg_control(struct pg_cntl *pg_cntl, unsigned int dsc_inst, bo if (dsc_inst < MAX_PIPES) pg_cntl->pg_pipe_res_enable[PG_DSC][dsc_inst] = power_on; - - if (pg_cntl->ctx->dc->res_pool->dccg->funcs->disable_dsc && !power_on) { - /*this is to disable dscclk*/ - pg_cntl->ctx->dc->res_pool->dccg->funcs->disable_dsc( - pg_cntl->ctx->dc->res_pool->dccg, dsc_inst); - } } static bool pg_cntl35_hubp_dpp_pg_status(struct pg_cntl *pg_cntl, unsigned int hubp_dpp_inst) @@ -189,11 +179,12 @@ void pg_cntl35_hubp_dpp_pg_control(struct pg_cntl *pg_cntl, unsigned int hubp_dp uint32_t pwr_status = power_on ? 0 : 2; uint32_t org_ip_request_cntl; bool block_enabled; + bool skip_pg = pg_cntl->ctx->dc->debug.ignore_pg || + pg_cntl->ctx->dc->debug.disable_hubp_power_gate || + pg_cntl->ctx->dc->debug.disable_dpp_power_gate || + pg_cntl->ctx->dc->idle_optimizations_allowed; - if (pg_cntl->ctx->dc->debug.ignore_pg || - pg_cntl->ctx->dc->debug.disable_hubp_power_gate || - pg_cntl->ctx->dc->debug.disable_dpp_power_gate || - pg_cntl->ctx->dc->idle_optimizations_allowed) + if (skip_pg && !power_on) return; block_enabled = pg_cntl35_hubp_dpp_pg_status(pg_cntl, hubp_dpp_inst); @@ -213,22 +204,22 @@ void pg_cntl35_hubp_dpp_pg_control(struct pg_cntl *pg_cntl, unsigned int hubp_dp case 0: /* DPP0 & HUBP0 */ REG_UPDATE(DOMAIN0_PG_CONFIG, DOMAIN_POWER_GATE, power_gate); - REG_WAIT(DOMAIN0_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 1000); + REG_WAIT(DOMAIN0_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 10000); break; case 1: /* DPP1 & HUBP1 */ REG_UPDATE(DOMAIN1_PG_CONFIG, DOMAIN_POWER_GATE, power_gate); - REG_WAIT(DOMAIN1_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 1000); + REG_WAIT(DOMAIN1_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 10000); break; case 2: /* DPP2 & HUBP2 */ REG_UPDATE(DOMAIN2_PG_CONFIG, DOMAIN_POWER_GATE, power_gate); - REG_WAIT(DOMAIN2_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 1000); + REG_WAIT(DOMAIN2_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 10000); break; case 3: /* DPP3 & HUBP3 */ REG_UPDATE(DOMAIN3_PG_CONFIG, DOMAIN_POWER_GATE, power_gate); - REG_WAIT(DOMAIN3_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 1000); + REG_WAIT(DOMAIN3_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 10000); break; default: BREAK_TO_DEBUGGER(); @@ -501,6 +492,36 @@ void pg_cntl35_init_pg_status(struct pg_cntl *pg_cntl) pg_cntl->pg_res_enable[PG_DWB] = block_enabled; } +static void pg_cntl35_print_pg_status(struct pg_cntl *pg_cntl, const char *debug_func, const char *debug_log) +{ + int i = 0; + bool block_enabled = false; + + DC_LOG_DEBUG("%s: %s", debug_func, debug_log); + + DC_LOG_DEBUG("PG_CNTL status:\n"); + + block_enabled = pg_cntl35_io_clk_status(pg_cntl); + DC_LOG_DEBUG("ONO0=%d (DCCG, DIO, DCIO)\n", block_enabled ? 1 : 0); + + block_enabled = pg_cntl35_mem_status(pg_cntl); + DC_LOG_DEBUG("ONO1=%d (DCHUBBUB, DCHVM, DCHUBBUBMEM)\n", block_enabled ? 1 : 0); + + block_enabled = pg_cntl35_plane_otg_status(pg_cntl); + DC_LOG_DEBUG("ONO2=%d (MPC, OPP, OPTC, DWB)\n", block_enabled ? 1 : 0); + + block_enabled = pg_cntl35_hpo_pg_status(pg_cntl); + DC_LOG_DEBUG("ONO3=%d (HPO)\n", block_enabled ? 1 : 0); + + for (i = 0; i < pg_cntl->ctx->dc->res_pool->pipe_count; i++) { + block_enabled = pg_cntl35_hubp_dpp_pg_status(pg_cntl, i); + DC_LOG_DEBUG("ONO%d=%d (DCHUBP%d, DPP%d)\n", 4 + i * 2, block_enabled ? 1 : 0, i, i); + + block_enabled = pg_cntl35_dsc_pg_status(pg_cntl, i); + DC_LOG_DEBUG("ONO%d=%d (DSC%d)\n", 5 + i * 2, block_enabled ? 1 : 0, i); + } +} + static const struct pg_cntl_funcs pg_cntl35_funcs = { .init_pg_status = pg_cntl35_init_pg_status, .dsc_pg_control = pg_cntl35_dsc_pg_control, @@ -511,7 +532,8 @@ static const struct pg_cntl_funcs pg_cntl35_funcs = { .mpcc_pg_control = pg_cntl35_mpcc_pg_control, .opp_pg_control = pg_cntl35_opp_pg_control, .optc_pg_control = pg_cntl35_optc_pg_control, - .dwb_pg_control = pg_cntl35_dwb_pg_control + .dwb_pg_control = pg_cntl35_dwb_pg_control, + .print_pg_status = pg_cntl35_print_pg_status }; struct pg_cntl *pg_cntl35_create( diff --git a/drivers/gpu/drm/amd/display/dc/resource/dce120/dce120_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dce120/dce120_resource.c index 2f23cc6df571..540e04ec1e2d 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dce120/dce120_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dce120/dce120_resource.c @@ -67,7 +67,7 @@ #include "reg_helper.h" #include "dce100/dce100_resource.h" -#include "link.h" +#include "link_service.h" #ifndef mmDP0_DP_DPHY_INTERNAL_CTRL #define mmDP0_DP_DPHY_INTERNAL_CTRL 0x210f diff --git a/drivers/gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c index 53b60044653f..c164d2500c2a 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c @@ -881,7 +881,16 @@ static enum dc_status dce60_validate_bandwidth( context->bw_ctx.bw.dce.dispclk_khz = 681000; context->bw_ctx.bw.dce.yclk_khz = 250000 * MEMORY_TYPE_MULTIPLIER_CZ; } else { - context->bw_ctx.bw.dce.dispclk_khz = 0; + /* On DCE 6.0 and 6.4 the PLL0 is both the display engine clock and + * the DP clock, and shouldn't be turned off. Just select the display + * clock value from its low power mode. + */ + if (dc->ctx->dce_version == DCE_VERSION_6_0 || + dc->ctx->dce_version == DCE_VERSION_6_4) + context->bw_ctx.bw.dce.dispclk_khz = 352000; + else + context->bw_ctx.bw.dce.dispclk_khz = 0; + context->bw_ctx.bw.dce.yclk_khz = 0; } diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn20/dcn20_resource.c index f9cbdad3ef37..84b38d2d6967 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn20/dcn20_resource.c @@ -85,7 +85,7 @@ #include "vm_helper.h" #include "link_enc_cfg.h" -#include "link.h" +#include "link_service.h" #define DC_LOGGER_INIT(logger) diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn30/dcn30_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn30/dcn30_resource.c index 201ed863b69e..ff63f59ff928 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn30/dcn30_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn30/dcn30_resource.c @@ -60,7 +60,7 @@ #include "dml/display_mode_vba.h" #include "dcn30/dcn30_dccg.h" #include "dcn10/dcn10_resource.h" -#include "link.h" +#include "link_service.h" #include "dce/dce_panel_cntl.h" #include "dcn30/dcn30_dwb.h" diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn302/dcn302_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn302/dcn302_resource.c index 3345068a878c..61623cb518d9 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn302/dcn302_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn302/dcn302_resource.c @@ -47,7 +47,8 @@ #include "dcn10/dcn10_resource.h" -#include "link.h" +#include "link_service.h" + #include "dce/dce_abm.h" #include "dce/dce_audio.h" #include "dce/dce_aux.h" diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn303/dcn303_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn303/dcn303_resource.c index 3479e1eab4cd..02b9a84f2db3 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn303/dcn303_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn303/dcn303_resource.c @@ -47,7 +47,7 @@ #include "dcn10/dcn10_resource.h" -#include "link.h" +#include "link_service.h" #include "dce/dce_abm.h" #include "dce/dce_audio.h" diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c index ca17e5d8fdc2..3ed7f50554e2 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c @@ -2239,7 +2239,8 @@ struct resource_pool *dcn31_create_resource_pool( enum dc_status dcn31_update_dc_state_for_encoder_switch(struct dc_link *link, struct dc_link_settings *link_setting, uint8_t pipe_count, - struct pipe_ctx *pipes) + struct pipe_ctx *pipes, + struct audio_output *audio_output) { struct dc_state *state = link->dc->current_state; int i; @@ -2254,7 +2255,7 @@ enum dc_status dcn31_update_dc_state_for_encoder_switch(struct dc_link *link, // Setup audio if (pipes[i].stream_res.audio != NULL) - build_audio_output(state, &pipes[i], &pipes[i].stream_res.audio_output); + build_audio_output(state, &pipes[i], &audio_output[i]); } #else /* This DCN requires rate divider updates and audio reprogramming to allow DP1<-->DP2 link rate switching, diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.h b/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.h index 7e8fde65528f..c32c85ef0ba4 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.h +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.h @@ -69,7 +69,8 @@ unsigned int dcn31_get_det_buffer_size( enum dc_status dcn31_update_dc_state_for_encoder_switch(struct dc_link *link, struct dc_link_settings *link_setting, uint8_t pipe_count, - struct pipe_ctx *pipes); + struct pipe_ctx *pipes, + struct audio_output *audio_output); /*temp: B0 specific before switch to dcn313 headers*/ #ifndef regPHYPLLF_PIXCLK_RESYNC_CNTL diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c index 9917b366f00c..8f80ccb846d7 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c @@ -69,7 +69,7 @@ #include "dml/display_mode_vba.h" #include "dcn32/dcn32_dccg.h" #include "dcn10/dcn10_resource.h" -#include "link.h" +#include "link_service.h" #include "dcn31/dcn31_panel_cntl.h" #include "dcn30/dcn30_dwb.h" @@ -2852,7 +2852,7 @@ struct pipe_ctx *dcn32_acquire_free_pipe_as_secondary_opp_head( free_pipe->plane_res.xfm = pool->transforms[free_pipe_idx]; free_pipe->plane_res.dpp = pool->dpps[free_pipe_idx]; free_pipe->plane_res.mpcc_inst = pool->dpps[free_pipe_idx]->inst; - free_pipe->hblank_borrow = otg_master->hblank_borrow; + free_pipe->dsc_padding_params = otg_master->dsc_padding_params; if (free_pipe->stream->timing.flags.DSC == 1) { dcn20_acquire_dsc(free_pipe->stream->ctx->dc, &new_ctx->res_ctx, diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c index 061c0907d802..ad214986f7ac 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c @@ -72,7 +72,7 @@ #include "dml/display_mode_vba.h" #include "dcn32/dcn32_dccg.h" #include "dcn10/dcn10_resource.h" -#include "link.h" +#include "link_service.h" #include "dcn31/dcn31_panel_cntl.h" #include "dcn30/dcn30_dwb.h" diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c index 8475c6eec547..07552445e424 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c @@ -61,7 +61,7 @@ #include "dcn31/dcn31_hpo_dp_stream_encoder.h" #include "dcn31/dcn31_hpo_dp_link_encoder.h" #include "dcn32/dcn32_hpo_dp_link_encoder.h" -#include "link.h" +#include "link_service.h" #include "dcn31/dcn31_apg.h" #include "dcn32/dcn32_dio_link_encoder.h" #include "dcn31/dcn31_vpg.h" @@ -1900,9 +1900,6 @@ static bool dcn35_resource_construct( dc->caps.num_of_host_routers = 2; dc->caps.num_of_dpias_per_host_router = 2; - dc->caps.num_of_host_routers = 2; - dc->caps.num_of_dpias_per_host_router = 2; - /* max_disp_clock_khz_at_vmin is slightly lower than the STA value in order * to provide some margin. * It's expected for furture ASIC to have equal or higher value, in order to diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c index 0971c0f74186..cb0478a9a34d 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c @@ -40,7 +40,7 @@ #include "dcn31/dcn31_hpo_dp_stream_encoder.h" #include "dcn31/dcn31_hpo_dp_link_encoder.h" #include "dcn32/dcn32_hpo_dp_link_encoder.h" -#include "link.h" +#include "link_service.h" #include "dcn31/dcn31_apg.h" #include "dcn32/dcn32_dio_link_encoder.h" #include "dcn31/dcn31_vpg.h" @@ -1872,9 +1872,6 @@ static bool dcn351_resource_construct( dc->caps.num_of_host_routers = 2; dc->caps.num_of_dpias_per_host_router = 2; - dc->caps.num_of_host_routers = 2; - dc->caps.num_of_dpias_per_host_router = 2; - /* max_disp_clock_khz_at_vmin is slightly lower than the STA value in order * to provide some margin. * It's expected for furture ASIC to have equal or higher value, in order to diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn36/dcn36_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn36/dcn36_resource.c index 8bae7fcedc22..126090c9bb8a 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn36/dcn36_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn36/dcn36_resource.c @@ -40,7 +40,7 @@ #include "dcn31/dcn31_hpo_dp_stream_encoder.h" #include "dcn31/dcn31_hpo_dp_link_encoder.h" #include "dcn32/dcn32_hpo_dp_link_encoder.h" -#include "link.h" +#include "link_service.h" #include "dcn31/dcn31_apg.h" #include "dcn32/dcn32_dio_link_encoder.h" #include "dcn31/dcn31_vpg.h" @@ -1873,9 +1873,6 @@ static bool dcn36_resource_construct( dc->caps.num_of_host_routers = 2; dc->caps.num_of_dpias_per_host_router = 2; - dc->caps.num_of_host_routers = 2; - dc->caps.num_of_dpias_per_host_router = 2; - /* max_disp_clock_khz_at_vmin is slightly lower than the STA value in order * to provide some margin. * It's expected for furture ASIC to have equal or higher value, in order to diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn401/dcn401_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn401/dcn401_resource.c index 068c123ea8a8..1d18807e4749 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn401/dcn401_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn401/dcn401_resource.c @@ -50,7 +50,7 @@ #include "dml/display_mode_vba.h" #include "dcn401/dcn401_dccg.h" #include "dcn10/dcn10_resource.h" -#include "link.h" +#include "link_service.h" #include "link_enc_cfg.h" #include "dcn31/dcn31_panel_cntl.h" @@ -1699,6 +1699,9 @@ static void dcn401_build_pipe_pix_clk_params(struct pipe_ctx *pipe_ctx) pixel_clk_params->requested_pix_clk_100hz = stream->timing.pix_clk_100hz; + if (pipe_ctx->dsc_padding_params.dsc_hactive_padding != 0) + pixel_clk_params->requested_pix_clk_100hz = pipe_ctx->dsc_padding_params.dsc_pix_clk_100hz; + if (!pipe_ctx->stream->ctx->dc->config.unify_link_enc_assignment) link_enc = link_enc_cfg_get_link_enc(link); if (link_enc) diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h index 02a4a20e3560..e65747f7f12f 100644 --- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h +++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h @@ -4258,18 +4258,6 @@ struct dmub_rb_cmd_replay_enable_data { * This does not support HDMI/DP2 for now. */ uint8_t phy_rate; - /** - * @hpo_stream_enc_inst: HPO stream encoder instance - */ - uint8_t hpo_stream_enc_inst; - /** - * @hpo_link_enc_inst: HPO link encoder instance - */ - uint8_t hpo_link_enc_inst; - /** - * @pad: Align structure to 4 byte boundary. - */ - uint8_t pad[2]; }; /** diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn32.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn32.c index e7056205b050..ce041f6239dc 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn32.c +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn32.c @@ -89,44 +89,50 @@ static inline void dmub_dcn32_translate_addr(const union dmub_addr *addr_in, void dmub_dcn32_reset(struct dmub_srv *dmub) { union dmub_gpint_data_register cmd; - const uint32_t timeout = 30; - uint32_t in_reset, scratch, i; + const uint32_t timeout = 100000; + uint32_t in_reset, is_enabled, scratch, i, pwait_mode; REG_GET(DMCUB_CNTL2, DMCUB_SOFT_RESET, &in_reset); + REG_GET(DMCUB_CNTL, DMCUB_ENABLE, &is_enabled); - if (in_reset == 0) { + if (in_reset == 0 && is_enabled != 0) { cmd.bits.status = 1; cmd.bits.command_code = DMUB_GPINT__STOP_FW; cmd.bits.param = 0; dmub->hw_funcs.set_gpint(dmub, cmd); - /** - * Timeout covers both the ACK and the wait - * for remaining work to finish. - * - * This is mostly bound by the PHY disable sequence. - * Each register check will be greater than 1us, so - * don't bother using udelay. - */ - for (i = 0; i < timeout; ++i) { if (dmub->hw_funcs.is_gpint_acked(dmub, cmd)) break; + + udelay(1); } for (i = 0; i < timeout; ++i) { - scratch = dmub->hw_funcs.get_gpint_response(dmub); + scratch = REG_READ(DMCUB_SCRATCH7); if (scratch == DMUB_GPINT__STOP_FW_RESPONSE) break; + + udelay(1); } + for (i = 0; i < timeout; ++i) { + REG_GET(DMCUB_CNTL, DMCUB_PWAIT_MODE_STATUS, &pwait_mode); + if (pwait_mode & (1 << 0)) + break; + + udelay(1); + } /* Force reset in case we timed out, DMCUB is likely hung. */ } - REG_UPDATE(DMCUB_CNTL2, DMCUB_SOFT_RESET, 1); - REG_UPDATE(DMCUB_CNTL, DMCUB_ENABLE, 0); - REG_UPDATE(MMHUBBUB_SOFT_RESET, DMUIF_SOFT_RESET, 1); + if (is_enabled) { + REG_UPDATE(DMCUB_CNTL2, DMCUB_SOFT_RESET, 1); + udelay(1); + REG_UPDATE(DMCUB_CNTL, DMCUB_ENABLE, 0); + } + REG_WRITE(DMCUB_INBOX1_RPTR, 0); REG_WRITE(DMCUB_INBOX1_WPTR, 0); REG_WRITE(DMCUB_OUTBOX1_RPTR, 0); @@ -135,7 +141,7 @@ void dmub_dcn32_reset(struct dmub_srv *dmub) REG_WRITE(DMCUB_OUTBOX0_WPTR, 0); REG_WRITE(DMCUB_SCRATCH0, 0); - /* Clear the GPINT command manually so we don't reset again. */ + /* Clear the GPINT command manually so we don't send anything during boot. */ cmd.all = 0; dmub->hw_funcs.set_gpint(dmub, cmd); } @@ -419,8 +425,8 @@ uint32_t dmub_dcn32_get_current_time(struct dmub_srv *dmub) void dmub_dcn32_get_diagnostic_data(struct dmub_srv *dmub) { - uint32_t is_dmub_enabled, is_soft_reset, is_sec_reset; - uint32_t is_traceport_enabled, is_cw0_enabled, is_cw6_enabled; + uint32_t is_dmub_enabled, is_soft_reset, is_pwait; + uint32_t is_traceport_enabled, is_cw6_enabled; struct dmub_timeout_info timeout = {0}; if (!dmub) @@ -470,18 +476,15 @@ void dmub_dcn32_get_diagnostic_data(struct dmub_srv *dmub) REG_GET(DMCUB_CNTL, DMCUB_ENABLE, &is_dmub_enabled); dmub->debug.is_dmcub_enabled = is_dmub_enabled; + REG_GET(DMCUB_CNTL, DMCUB_PWAIT_MODE_STATUS, &is_pwait); + dmub->debug.is_pwait = is_pwait; + REG_GET(DMCUB_CNTL2, DMCUB_SOFT_RESET, &is_soft_reset); dmub->debug.is_dmcub_soft_reset = is_soft_reset; - REG_GET(DMCUB_SEC_CNTL, DMCUB_SEC_RESET_STATUS, &is_sec_reset); - dmub->debug.is_dmcub_secure_reset = is_sec_reset; - REG_GET(DMCUB_CNTL, DMCUB_TRACEPORT_EN, &is_traceport_enabled); dmub->debug.is_traceport_en = is_traceport_enabled; - REG_GET(DMCUB_REGION3_CW0_TOP_ADDRESS, DMCUB_REGION3_CW0_ENABLE, &is_cw0_enabled); - dmub->debug.is_cw0_enabled = is_cw0_enabled; - REG_GET(DMCUB_REGION3_CW6_TOP_ADDRESS, DMCUB_REGION3_CW6_ENABLE, &is_cw6_enabled); dmub->debug.is_cw6_enabled = is_cw6_enabled; diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn32.h b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn32.h index 1a229450c53d..daf81027d663 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn32.h +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn32.h @@ -89,6 +89,9 @@ struct dmub_srv; DMUB_SR(DMCUB_REGION5_OFFSET) \ DMUB_SR(DMCUB_REGION5_OFFSET_HIGH) \ DMUB_SR(DMCUB_REGION5_TOP_ADDRESS) \ + DMUB_SR(DMCUB_REGION6_OFFSET) \ + DMUB_SR(DMCUB_REGION6_OFFSET_HIGH) \ + DMUB_SR(DMCUB_REGION6_TOP_ADDRESS) \ DMUB_SR(DMCUB_SCRATCH0) \ DMUB_SR(DMCUB_SCRATCH1) \ DMUB_SR(DMCUB_SCRATCH2) \ @@ -155,6 +158,8 @@ struct dmub_srv; DMUB_SF(DMCUB_REGION4_TOP_ADDRESS, DMCUB_REGION4_ENABLE) \ DMUB_SF(DMCUB_REGION5_TOP_ADDRESS, DMCUB_REGION5_TOP_ADDRESS) \ DMUB_SF(DMCUB_REGION5_TOP_ADDRESS, DMCUB_REGION5_ENABLE) \ + DMUB_SF(DMCUB_REGION6_TOP_ADDRESS, DMCUB_REGION6_TOP_ADDRESS) \ + DMUB_SF(DMCUB_REGION6_TOP_ADDRESS, DMCUB_REGION6_ENABLE) \ DMUB_SF(CC_DC_PIPE_DIS, DC_DMCUB_ENABLE) \ DMUB_SF(MMHUBBUB_SOFT_RESET, DMUIF_SOFT_RESET) \ DMUB_SF(DCN_VM_FB_LOCATION_BASE, FB_BASE) \ @@ -162,7 +167,8 @@ struct dmub_srv; DMUB_SF(DMCUB_INBOX0_WPTR, DMCUB_INBOX0_WPTR) \ DMUB_SF(DMCUB_REGION3_TMR_AXI_SPACE, DMCUB_REGION3_TMR_AXI_SPACE) \ DMUB_SF(DMCUB_INTERRUPT_ENABLE, DMCUB_GPINT_IH_INT_EN) \ - DMUB_SF(DMCUB_INTERRUPT_ACK, DMCUB_GPINT_IH_INT_ACK) + DMUB_SF(DMCUB_INTERRUPT_ACK, DMCUB_GPINT_IH_INT_ACK) \ + DMUB_SF(DMCUB_CNTL, DMCUB_PWAIT_MODE_STATUS) struct dmub_srv_dcn32_reg_offset { #define DMUB_SR(reg) uint32_t reg; diff --git a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c index 71efd2770c99..ce421bcddcb0 100644 --- a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c +++ b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c @@ -226,8 +226,8 @@ static void update_v_total_for_static_ramp( unsigned int target_duration_in_us = calc_duration_in_us_from_refresh_in_uhz( in_out_vrr->fixed.target_refresh_in_uhz); - bool ramp_direction_is_up = (current_duration_in_us > - target_duration_in_us) ? true : false; + bool ramp_direction_is_up = current_duration_in_us > + target_duration_in_us; /* Calculate ratio between new and current frame duration with 3 digit */ unsigned int frame_duration_ratio = div64_u64(1000000, diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c index 5e01c6e24cbc..c760216a6240 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c @@ -29,6 +29,7 @@ static void push_error_status(struct mod_hdcp *hdcp, enum mod_hdcp_status status) { struct mod_hdcp_trace *trace = &hdcp->connection.trace; + const uint8_t retry_limit = hdcp->connection.link.adjust.retry_limit; if (trace->error_count < MAX_NUM_OF_ERROR_TRACE) { trace->errors[trace->error_count].status = status; @@ -39,11 +40,11 @@ static void push_error_status(struct mod_hdcp *hdcp, if (is_hdcp1(hdcp)) { hdcp->connection.hdcp1_retry_count++; - if (hdcp->connection.hdcp1_retry_count == MAX_NUM_OF_ATTEMPTS) + if (hdcp->connection.hdcp1_retry_count == retry_limit) hdcp->connection.link.adjust.hdcp1.disable = 1; } else if (is_hdcp2(hdcp)) { hdcp->connection.hdcp2_retry_count++; - if (hdcp->connection.hdcp2_retry_count == MAX_NUM_OF_ATTEMPTS) + if (hdcp->connection.hdcp2_retry_count == retry_limit) hdcp->connection.link.adjust.hdcp2.disable = 1; } } diff --git a/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h b/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h index c42468bb70ac..b51ddf2846df 100644 --- a/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h +++ b/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h @@ -220,6 +220,7 @@ struct mod_hdcp_link_adjustment_hdcp2 { struct mod_hdcp_link_adjustment { uint8_t auth_delay; + uint8_t retry_limit; struct mod_hdcp_link_adjustment_hdcp1 hdcp1; struct mod_hdcp_link_adjustment_hdcp2 hdcp2; }; diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h index bfb446736ca8..75efda2969cf 100644 --- a/drivers/gpu/drm/amd/include/amd_shared.h +++ b/drivers/gpu/drm/amd/include/amd_shared.h @@ -239,18 +239,51 @@ enum amd_harvest_ip_mask { AMD_HARVEST_IP_DMU_MASK = 0x4, }; +/** + * enum DC_FEATURE_MASK - Bits that control DC feature defaults + */ enum DC_FEATURE_MASK { //Default value can be found at "uint amdgpu_dc_feature_mask" - DC_FBC_MASK = (1 << 0), //0x1, disabled by default - DC_MULTI_MON_PP_MCLK_SWITCH_MASK = (1 << 1), //0x2, enabled by default - DC_DISABLE_FRACTIONAL_PWM_MASK = (1 << 2), //0x4, disabled by default - DC_PSR_MASK = (1 << 3), //0x8, disabled by default for dcn < 3.1 - DC_EDP_NO_POWER_SEQUENCING = (1 << 4), //0x10, disabled by default - DC_DISABLE_LTTPR_DP1_4A = (1 << 5), //0x20, disabled by default - DC_DISABLE_LTTPR_DP2_0 = (1 << 6), //0x40, disabled by default - DC_PSR_ALLOW_SMU_OPT = (1 << 7), //0x80, disabled by default - DC_PSR_ALLOW_MULTI_DISP_OPT = (1 << 8), //0x100, disabled by default - DC_REPLAY_MASK = (1 << 9), //0x200, disabled by default for dcn < 3.1.4 + /** + * @DC_FBC_MASK: (0x1) disabled by default + */ + DC_FBC_MASK = (1 << 0), + /** + * @DC_MULTI_MON_PP_MCLK_SWITCH_MASK: (0x2) enabled by default + */ + DC_MULTI_MON_PP_MCLK_SWITCH_MASK = (1 << 1), + /** + * @DC_DISABLE_FRACTIONAL_PWM_MASK: (0x4) disabled by default + */ + DC_DISABLE_FRACTIONAL_PWM_MASK = (1 << 2), + /** + * @DC_PSR_MASK: (0x8) disabled by default for DCN < 3.1 + */ + DC_PSR_MASK = (1 << 3), + /** + * @DC_EDP_NO_POWER_SEQUENCING: (0x10) disabled by default + */ + DC_EDP_NO_POWER_SEQUENCING = (1 << 4), + /** + * @DC_DISABLE_LTTPR_DP1_4A: (0x20) disabled by default + */ + DC_DISABLE_LTTPR_DP1_4A = (1 << 5), + /** + * @DC_DISABLE_LTTPR_DP2_0: (0x40) disabled by default + */ + DC_DISABLE_LTTPR_DP2_0 = (1 << 6), + /** + * @DC_PSR_ALLOW_SMU_OPT: (0x80) disabled by default + */ + DC_PSR_ALLOW_SMU_OPT = (1 << 7), + /** + * @DC_PSR_ALLOW_MULTI_DISP_OPT: (0x100) disabled by default + */ + DC_PSR_ALLOW_MULTI_DISP_OPT = (1 << 8), + /** + * @DC_REPLAY_MASK: (0x200) disabled by default for DCN < 3.1.4 + */ + DC_REPLAY_MASK = (1 << 9), }; /** @@ -258,64 +291,64 @@ enum DC_FEATURE_MASK { */ enum DC_DEBUG_MASK { /** - * @DC_DISABLE_PIPE_SPLIT: If set, disable pipe-splitting + * @DC_DISABLE_PIPE_SPLIT: (0x1) If set, disable pipe-splitting */ DC_DISABLE_PIPE_SPLIT = 0x1, /** - * @DC_DISABLE_STUTTER: If set, disable memory stutter mode + * @DC_DISABLE_STUTTER: (0x2) If set, disable memory stutter mode */ DC_DISABLE_STUTTER = 0x2, /** - * @DC_DISABLE_DSC: If set, disable display stream compression + * @DC_DISABLE_DSC: (0x4) If set, disable display stream compression */ DC_DISABLE_DSC = 0x4, /** - * @DC_DISABLE_CLOCK_GATING: If set, disable clock gating optimizations + * @DC_DISABLE_CLOCK_GATING: (0x8) If set, disable clock gating optimizations */ DC_DISABLE_CLOCK_GATING = 0x8, /** - * @DC_DISABLE_PSR: If set, disable Panel self refresh v1 and PSR-SU + * @DC_DISABLE_PSR: (0x10) If set, disable Panel self refresh v1 and PSR-SU */ DC_DISABLE_PSR = 0x10, /** - * @DC_FORCE_SUBVP_MCLK_SWITCH: If set, force mclk switch in subvp, even + * @DC_FORCE_SUBVP_MCLK_SWITCH: (0x20) If set, force mclk switch in subvp, even * if mclk switch in vblank is possible */ DC_FORCE_SUBVP_MCLK_SWITCH = 0x20, /** - * @DC_DISABLE_MPO: If set, disable multi-plane offloading + * @DC_DISABLE_MPO: (0x40) If set, disable multi-plane offloading */ DC_DISABLE_MPO = 0x40, /** - * @DC_ENABLE_DPIA_TRACE: If set, enable trace logging for DPIA + * @DC_ENABLE_DPIA_TRACE: (0x80) If set, enable trace logging for DPIA */ DC_ENABLE_DPIA_TRACE = 0x80, /** - * @DC_ENABLE_DML2: If set, force usage of DML2, even if the DCN version + * @DC_ENABLE_DML2: (0x100) If set, force usage of DML2, even if the DCN version * does not default to it. */ DC_ENABLE_DML2 = 0x100, /** - * @DC_DISABLE_PSR_SU: If set, disable PSR SU + * @DC_DISABLE_PSR_SU: (0x200) If set, disable PSR SU */ DC_DISABLE_PSR_SU = 0x200, /** - * @DC_DISABLE_REPLAY: If set, disable Panel Replay + * @DC_DISABLE_REPLAY: (0x400) If set, disable Panel Replay */ DC_DISABLE_REPLAY = 0x400, /** - * @DC_DISABLE_IPS: If set, disable all Idle Power States, all the time. + * @DC_DISABLE_IPS: (0x800) If set, disable all Idle Power States, all the time. * If more than one IPS debug bit is set, the lowest bit takes * precedence. For example, if DC_FORCE_IPS_ENABLE and * DC_DISABLE_IPS_DYNAMIC are set, then DC_DISABLE_IPS_DYNAMIC takes @@ -324,56 +357,57 @@ enum DC_DEBUG_MASK { DC_DISABLE_IPS = 0x800, /** - * @DC_DISABLE_IPS_DYNAMIC: If set, disable all IPS, all the time, + * @DC_DISABLE_IPS_DYNAMIC: (0x1000) If set, disable all IPS, all the time, * *except* when driver goes into suspend. */ DC_DISABLE_IPS_DYNAMIC = 0x1000, /** - * @DC_DISABLE_IPS2_DYNAMIC: If set, disable IPS2 (IPS1 allowed) if + * @DC_DISABLE_IPS2_DYNAMIC: (0x2000) If set, disable IPS2 (IPS1 allowed) if * there is an enabled display. Otherwise, enable all IPS. */ DC_DISABLE_IPS2_DYNAMIC = 0x2000, /** - * @DC_FORCE_IPS_ENABLE: If set, force enable all IPS, all the time. + * @DC_FORCE_IPS_ENABLE: (0x4000) If set, force enable all IPS, all the time. */ DC_FORCE_IPS_ENABLE = 0x4000, /** - * @DC_DISABLE_ACPI_EDID: If set, don't attempt to fetch EDID for + * @DC_DISABLE_ACPI_EDID: (0x8000) If set, don't attempt to fetch EDID for * eDP display from ACPI _DDC method. */ DC_DISABLE_ACPI_EDID = 0x8000, /** - * @DC_DISABLE_HDMI_CEC: If set, disable HDMI-CEC feature in amdgpu driver. + * @DC_DISABLE_HDMI_CEC: (0x10000) If set, disable HDMI-CEC feature in amdgpu driver. */ DC_DISABLE_HDMI_CEC = 0x10000, /** - * @DC_DISABLE_SUBVP_FAMS: If set, disable DCN Sub-Viewport & Firmware Assisted + * @DC_DISABLE_SUBVP_FAMS: (0x20000) If set, disable DCN Sub-Viewport & Firmware Assisted * Memory Clock Switching (FAMS) feature in amdgpu driver. */ DC_DISABLE_SUBVP_FAMS = 0x20000, /** - * @DC_DISABLE_CUSTOM_BRIGHTNESS_CURVE: If set, disable support for custom brightness curves + * @DC_DISABLE_CUSTOM_BRIGHTNESS_CURVE: (0x40000) If set, disable support for custom + * brightness curves */ DC_DISABLE_CUSTOM_BRIGHTNESS_CURVE = 0x40000, /** - * @DC_HDCP_LC_FORCE_FW_ENABLE: If set, use HDCP Locality Check FW + * @DC_HDCP_LC_FORCE_FW_ENABLE: (0x80000) If set, use HDCP Locality Check FW * path regardless of reported HW capabilities. */ DC_HDCP_LC_FORCE_FW_ENABLE = 0x80000, /** - * @DC_HDCP_LC_ENABLE_SW_FALLBACK: If set, upon HDCP Locality Check FW + * @DC_HDCP_LC_ENABLE_SW_FALLBACK: (0x100000) If set, upon HDCP Locality Check FW * path failure, retry using legacy SW path. */ DC_HDCP_LC_ENABLE_SW_FALLBACK = 0x100000, /** - * @DC_SKIP_DETECTION_LT: If set, skip detection link training + * @DC_SKIP_DETECTION_LT: (0x200000) If set, skip detection link training */ DC_SKIP_DETECTION_LT = 0x200000, }; diff --git a/drivers/gpu/drm/amd/include/dm_pp_interface.h b/drivers/gpu/drm/amd/include/dm_pp_interface.h index acd1cef61b7c..349544504c93 100644 --- a/drivers/gpu/drm/amd/include/dm_pp_interface.h +++ b/drivers/gpu/drm/amd/include/dm_pp_interface.h @@ -65,6 +65,7 @@ struct single_display_configuration { uint32_t view_resolution_cy; enum amd_pp_display_config_type displayconfigtype; uint32_t vertical_refresh; /* for active display */ + uint32_t pixel_clock; /* Pixel clock in KHz (for HDMI only: normalized) */ }; #define MAX_NUM_DISPLAY 32 diff --git a/drivers/gpu/drm/amd/include/kgd_pp_interface.h b/drivers/gpu/drm/amd/include/kgd_pp_interface.h index 2f7e4b5bebf3..2b0cdb2a2775 100644 --- a/drivers/gpu/drm/amd/include/kgd_pp_interface.h +++ b/drivers/gpu/drm/amd/include/kgd_pp_interface.h @@ -162,6 +162,10 @@ enum amd_pp_sensors { AMDGPU_PP_SENSOR_PEAK_PSTATE_SCLK, AMDGPU_PP_SENSOR_PEAK_PSTATE_MCLK, AMDGPU_PP_SENSOR_VCN_LOAD, + AMDGPU_PP_SENSOR_NODEPOWERLIMIT, + AMDGPU_PP_SENSOR_NODEPOWER, + AMDGPU_PP_SENSOR_GPPTRESIDENCY, + AMDGPU_PP_SENSOR_MAXNODEPOWERLIMIT, }; enum amd_pp_task { diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm_internal.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm_internal.c index 42efe838fa85..b5e9c3ecf703 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_dpm_internal.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm_internal.c @@ -27,69 +27,69 @@ #include "amdgpu_smu.h" #include "amdgpu_dpm_internal.h" -void amdgpu_dpm_get_active_displays(struct amdgpu_device *adev) +void amdgpu_dpm_get_display_cfg(struct amdgpu_device *adev) { struct drm_device *ddev = adev_to_drm(adev); + struct amd_pp_display_configuration *cfg = &adev->pm.pm_display_cfg; + struct single_display_configuration *display_cfg; struct drm_crtc *crtc; struct amdgpu_crtc *amdgpu_crtc; + struct amdgpu_connector *conn; + int num_crtcs = 0; + int vrefresh; + u32 vblank_in_pixels, vblank_time_us; + + cfg->min_vblank_time = 0xffffffff; /* if the displays are off, vblank time is max */ - adev->pm.dpm.new_active_crtcs = 0; - adev->pm.dpm.new_active_crtc_count = 0; if (adev->mode_info.num_crtc && adev->mode_info.mode_config_initialized) { - list_for_each_entry(crtc, - &ddev->mode_config.crtc_list, head) { + list_for_each_entry(crtc, &ddev->mode_config.crtc_list, head) { amdgpu_crtc = to_amdgpu_crtc(crtc); - if (amdgpu_crtc->enabled) { - adev->pm.dpm.new_active_crtcs |= (1 << amdgpu_crtc->crtc_id); - adev->pm.dpm.new_active_crtc_count++; - } - } - } -} -u32 amdgpu_dpm_get_vblank_time(struct amdgpu_device *adev) -{ - struct drm_device *dev = adev_to_drm(adev); - struct drm_crtc *crtc; - struct amdgpu_crtc *amdgpu_crtc; - u32 vblank_in_pixels; - u32 vblank_time_us = 0xffffffff; /* if the displays are off, vblank time is max */ + /* The array should only contain active displays. */ + if (!amdgpu_crtc->enabled) + continue; + + conn = to_amdgpu_connector(amdgpu_crtc->connector); + display_cfg = &adev->pm.pm_display_cfg.displays[num_crtcs++]; + + if (amdgpu_crtc->hw_mode.clock) { + vrefresh = drm_mode_vrefresh(&amdgpu_crtc->hw_mode); - if (adev->mode_info.num_crtc && adev->mode_info.mode_config_initialized) { - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { - amdgpu_crtc = to_amdgpu_crtc(crtc); - if (crtc->enabled && amdgpu_crtc->enabled && amdgpu_crtc->hw_mode.clock) { vblank_in_pixels = amdgpu_crtc->hw_mode.crtc_htotal * (amdgpu_crtc->hw_mode.crtc_vblank_end - amdgpu_crtc->hw_mode.crtc_vdisplay + (amdgpu_crtc->v_border * 2)); - vblank_time_us = vblank_in_pixels * 1000 / amdgpu_crtc->hw_mode.clock; - break; - } - } - } + vblank_time_us = + vblank_in_pixels * 1000 / amdgpu_crtc->hw_mode.clock; - return vblank_time_us; -} + /* The legacy (non-DC) code has issues with mclk switching + * with refresh rates over 120 Hz. Disable mclk switching. + */ + if (vrefresh > 120) + vblank_time_us = 0; -u32 amdgpu_dpm_get_vrefresh(struct amdgpu_device *adev) -{ - struct drm_device *dev = adev_to_drm(adev); - struct drm_crtc *crtc; - struct amdgpu_crtc *amdgpu_crtc; - u32 vrefresh = 0; + /* Find minimum vblank time. */ + if (vblank_time_us < cfg->min_vblank_time) + cfg->min_vblank_time = vblank_time_us; - if (adev->mode_info.num_crtc && adev->mode_info.mode_config_initialized) { - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { - amdgpu_crtc = to_amdgpu_crtc(crtc); - if (crtc->enabled && amdgpu_crtc->enabled && amdgpu_crtc->hw_mode.clock) { - vrefresh = drm_mode_vrefresh(&amdgpu_crtc->hw_mode); - break; + /* Find vertical refresh rate of first active display. */ + if (!cfg->vrefresh) + cfg->vrefresh = vrefresh; } + + if (amdgpu_crtc->crtc_id < cfg->crtc_index) { + /* Find first active CRTC and its line time. */ + cfg->crtc_index = amdgpu_crtc->crtc_id; + cfg->line_time_in_us = amdgpu_crtc->line_time; + } + + display_cfg->controller_id = amdgpu_crtc->crtc_id; + display_cfg->pixel_clock = conn->pixelclock_for_modeset; } } - return vrefresh; + cfg->display_clk = adev->clock.default_dispclk; + cfg->num_display = num_crtcs; } diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c index 5230276628a3..b5fbb0fd1dc0 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c @@ -110,9 +110,10 @@ static int amdgpu_pm_dev_state_check(struct amdgpu_device *adev, bool runpm) bool runpm_check = runpm ? adev->in_runpm : false; if (amdgpu_in_reset(adev)) - return -EPERM; + return -EBUSY; + if (adev->in_suspend && !runpm_check) - return -EPERM; + return -EBUSY; return 0; } @@ -1420,9 +1421,9 @@ static ssize_t amdgpu_set_pp_power_profile_mode(struct device *dev, return -EINVAL; } -static int amdgpu_hwmon_get_sensor_generic(struct amdgpu_device *adev, - enum amd_pp_sensors sensor, - void *query) +static int amdgpu_pm_get_sensor_generic(struct amdgpu_device *adev, + enum amd_pp_sensors sensor, + void *query) { int r, size = sizeof(uint32_t); @@ -1455,7 +1456,7 @@ static ssize_t amdgpu_get_gpu_busy_percent(struct device *dev, unsigned int value; int r; - r = amdgpu_hwmon_get_sensor_generic(adev, AMDGPU_PP_SENSOR_GPU_LOAD, &value); + r = amdgpu_pm_get_sensor_generic(adev, AMDGPU_PP_SENSOR_GPU_LOAD, &value); if (r) return r; @@ -1479,7 +1480,7 @@ static ssize_t amdgpu_get_mem_busy_percent(struct device *dev, unsigned int value; int r; - r = amdgpu_hwmon_get_sensor_generic(adev, AMDGPU_PP_SENSOR_MEM_LOAD, &value); + r = amdgpu_pm_get_sensor_generic(adev, AMDGPU_PP_SENSOR_MEM_LOAD, &value); if (r) return r; @@ -1503,7 +1504,7 @@ static ssize_t amdgpu_get_vcn_busy_percent(struct device *dev, unsigned int value; int r; - r = amdgpu_hwmon_get_sensor_generic(adev, AMDGPU_PP_SENSOR_VCN_LOAD, &value); + r = amdgpu_pm_get_sensor_generic(adev, AMDGPU_PP_SENSOR_VCN_LOAD, &value); if (r) return r; @@ -1782,7 +1783,7 @@ static int amdgpu_show_powershift_percent(struct device *dev, uint32_t ss_power; int r = 0, i; - r = amdgpu_hwmon_get_sensor_generic(adev, sensor, (void *)&ss_power); + r = amdgpu_pm_get_sensor_generic(adev, sensor, (void *)&ss_power); if (r == -EOPNOTSUPP) { /* sensor not available on dGPU, try to read from APU */ adev = NULL; @@ -1795,7 +1796,7 @@ static int amdgpu_show_powershift_percent(struct device *dev, } mutex_unlock(&mgpu_info.mutex); if (adev) - r = amdgpu_hwmon_get_sensor_generic(adev, sensor, (void *)&ss_power); + r = amdgpu_pm_get_sensor_generic(adev, sensor, (void *)&ss_power); } if (r) @@ -1905,11 +1906,11 @@ static int ss_bias_attr_update(struct amdgpu_device *adev, struct amdgpu_device_ if (!amdgpu_device_supports_smart_shift(adev)) *states = ATTR_STATE_UNSUPPORTED; - else if (amdgpu_hwmon_get_sensor_generic(adev, AMDGPU_PP_SENSOR_SS_APU_SHARE, - (void *)&ss_power)) + else if (amdgpu_pm_get_sensor_generic(adev, AMDGPU_PP_SENSOR_SS_APU_SHARE, + (void *)&ss_power)) *states = ATTR_STATE_UNSUPPORTED; - else if (amdgpu_hwmon_get_sensor_generic(adev, AMDGPU_PP_SENSOR_SS_DGPU_SHARE, - (void *)&ss_power)) + else if (amdgpu_pm_get_sensor_generic(adev, AMDGPU_PP_SENSOR_SS_DGPU_SHARE, + (void *)&ss_power)) *states = ATTR_STATE_UNSUPPORTED; return 0; @@ -2080,8 +2081,9 @@ static int pp_dpm_clk_default_attr_update(struct amdgpu_device *adev, struct amd * for user application to monitor various board reated attributes. * * The amdgpu driver provides a sysfs API for reporting board attributes. Presently, - * only two types of attributes are reported, baseboard temperature and - * gpu board temperature. Both of them are reported as binary files. + * seven types of attributes are reported. Baseboard temperature and + * gpu board temperature are reported as binary files. Npm status, current node power limit, + * max node power limit, node power and global ppt residency is reported as ASCII text file. * * * .. code-block:: console * @@ -2089,6 +2091,15 @@ static int pp_dpm_clk_default_attr_update(struct amdgpu_device *adev, struct amd * * hexdump /sys/bus/pci/devices/.../board/gpuboard_temp * + * hexdump /sys/bus/pci/devices/.../board/npm_status + * + * hexdump /sys/bus/pci/devices/.../board/cur_node_power_limit + * + * hexdump /sys/bus/pci/devices/.../board/max_node_power_limit + * + * hexdump /sys/bus/pci/devices/.../board/node_power + * + * hexdump /sys/bus/pci/devices/.../board/global_ppt_resid */ /** @@ -2167,8 +2178,129 @@ out: return size; } +/** + * DOC: cur_node_power_limit + * + * The amdgpu driver provides a sysfs API for retrieving current node power limit. + * The file cur_node_power_limit is used for this. + */ +static ssize_t amdgpu_show_cur_node_power_limit(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct drm_device *ddev = dev_get_drvdata(dev); + struct amdgpu_device *adev = drm_to_adev(ddev); + u32 nplimit; + int r; + + /* get the current node power limit */ + r = amdgpu_pm_get_sensor_generic(adev, AMDGPU_PP_SENSOR_NODEPOWERLIMIT, + (void *)&nplimit); + if (r) + return r; + + return sysfs_emit(buf, "%u\n", nplimit); +} + +/** + * DOC: node_power + * + * The amdgpu driver provides a sysfs API for retrieving current node power. + * The file node_power is used for this. + */ +static ssize_t amdgpu_show_node_power(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct drm_device *ddev = dev_get_drvdata(dev); + struct amdgpu_device *adev = drm_to_adev(ddev); + u32 npower; + int r; + + /* get the node power */ + r = amdgpu_pm_get_sensor_generic(adev, AMDGPU_PP_SENSOR_NODEPOWER, + (void *)&npower); + if (r) + return r; + + return sysfs_emit(buf, "%u\n", npower); +} + +/** + * DOC: npm_status + * + * The amdgpu driver provides a sysfs API for retrieving current node power management status. + * The file npm_status is used for this. It shows the status as enabled or disabled based on + * current node power value. If node power is zero, status is disabled else enabled. + */ +static ssize_t amdgpu_show_npm_status(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct drm_device *ddev = dev_get_drvdata(dev); + struct amdgpu_device *adev = drm_to_adev(ddev); + u32 npower; + int r; + + /* get the node power */ + r = amdgpu_pm_get_sensor_generic(adev, AMDGPU_PP_SENSOR_NODEPOWER, + (void *)&npower); + if (r) + return r; + + return sysfs_emit(buf, "%s\n", npower ? "enabled" : "disabled"); +} + +/** + * DOC: global_ppt_resid + * + * The amdgpu driver provides a sysfs API for retrieving global ppt residency. + * The file global_ppt_resid is used for this. + */ +static ssize_t amdgpu_show_global_ppt_resid(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct drm_device *ddev = dev_get_drvdata(dev); + struct amdgpu_device *adev = drm_to_adev(ddev); + u32 gpptresid; + int r; + + /* get the global ppt residency */ + r = amdgpu_pm_get_sensor_generic(adev, AMDGPU_PP_SENSOR_GPPTRESIDENCY, + (void *)&gpptresid); + if (r) + return r; + + return sysfs_emit(buf, "%u\n", gpptresid); +} + +/** + * DOC: max_node_power_limit + * + * The amdgpu driver provides a sysfs API for retrieving maximum node power limit. + * The file max_node_power_limit is used for this. + */ +static ssize_t amdgpu_show_max_node_power_limit(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct drm_device *ddev = dev_get_drvdata(dev); + struct amdgpu_device *adev = drm_to_adev(ddev); + u32 max_nplimit; + int r; + + /* get the max node power limit */ + r = amdgpu_pm_get_sensor_generic(adev, AMDGPU_PP_SENSOR_MAXNODEPOWERLIMIT, + (void *)&max_nplimit); + if (r) + return r; + + return sysfs_emit(buf, "%u\n", max_nplimit); +} + static DEVICE_ATTR(baseboard_temp, 0444, amdgpu_get_baseboard_temp_metrics, NULL); static DEVICE_ATTR(gpuboard_temp, 0444, amdgpu_get_gpuboard_temp_metrics, NULL); +static DEVICE_ATTR(cur_node_power_limit, 0444, amdgpu_show_cur_node_power_limit, NULL); +static DEVICE_ATTR(node_power, 0444, amdgpu_show_node_power, NULL); +static DEVICE_ATTR(global_ppt_resid, 0444, amdgpu_show_global_ppt_resid, NULL); +static DEVICE_ATTR(max_node_power_limit, 0444, amdgpu_show_max_node_power_limit, NULL); +static DEVICE_ATTR(npm_status, 0444, amdgpu_show_npm_status, NULL); static struct attribute *board_attrs[] = { &dev_attr_baseboard_temp.attr, @@ -2635,18 +2767,18 @@ static ssize_t amdgpu_hwmon_show_temp(struct device *dev, switch (channel) { case PP_TEMP_JUNCTION: /* get current junction temperature */ - r = amdgpu_hwmon_get_sensor_generic(adev, AMDGPU_PP_SENSOR_HOTSPOT_TEMP, - (void *)&temp); + r = amdgpu_pm_get_sensor_generic(adev, AMDGPU_PP_SENSOR_HOTSPOT_TEMP, + (void *)&temp); break; case PP_TEMP_EDGE: /* get current edge temperature */ - r = amdgpu_hwmon_get_sensor_generic(adev, AMDGPU_PP_SENSOR_EDGE_TEMP, - (void *)&temp); + r = amdgpu_pm_get_sensor_generic(adev, AMDGPU_PP_SENSOR_EDGE_TEMP, + (void *)&temp); break; case PP_TEMP_MEM: /* get current memory temperature */ - r = amdgpu_hwmon_get_sensor_generic(adev, AMDGPU_PP_SENSOR_MEM_TEMP, - (void *)&temp); + r = amdgpu_pm_get_sensor_generic(adev, AMDGPU_PP_SENSOR_MEM_TEMP, + (void *)&temp); break; default: r = -EINVAL; @@ -2908,8 +3040,8 @@ static ssize_t amdgpu_hwmon_get_fan1_min(struct device *dev, u32 min_rpm = 0; int r; - r = amdgpu_hwmon_get_sensor_generic(adev, AMDGPU_PP_SENSOR_MIN_FAN_RPM, - (void *)&min_rpm); + r = amdgpu_pm_get_sensor_generic(adev, AMDGPU_PP_SENSOR_MIN_FAN_RPM, + (void *)&min_rpm); if (r) return r; @@ -2925,8 +3057,8 @@ static ssize_t amdgpu_hwmon_get_fan1_max(struct device *dev, u32 max_rpm = 0; int r; - r = amdgpu_hwmon_get_sensor_generic(adev, AMDGPU_PP_SENSOR_MAX_FAN_RPM, - (void *)&max_rpm); + r = amdgpu_pm_get_sensor_generic(adev, AMDGPU_PP_SENSOR_MAX_FAN_RPM, + (void *)&max_rpm); if (r) return r; @@ -3059,8 +3191,8 @@ static ssize_t amdgpu_hwmon_show_vddgfx(struct device *dev, int r; /* get the voltage */ - r = amdgpu_hwmon_get_sensor_generic(adev, AMDGPU_PP_SENSOR_VDDGFX, - (void *)&vddgfx); + r = amdgpu_pm_get_sensor_generic(adev, AMDGPU_PP_SENSOR_VDDGFX, + (void *)&vddgfx); if (r) return r; @@ -3076,8 +3208,8 @@ static ssize_t amdgpu_hwmon_show_vddboard(struct device *dev, int r; /* get the voltage */ - r = amdgpu_hwmon_get_sensor_generic(adev, AMDGPU_PP_SENSOR_VDDBOARD, - (void *)&vddboard); + r = amdgpu_pm_get_sensor_generic(adev, AMDGPU_PP_SENSOR_VDDBOARD, + (void *)&vddboard); if (r) return r; @@ -3110,8 +3242,8 @@ static ssize_t amdgpu_hwmon_show_vddnb(struct device *dev, return -EINVAL; /* get the voltage */ - r = amdgpu_hwmon_get_sensor_generic(adev, AMDGPU_PP_SENSOR_VDDNB, - (void *)&vddnb); + r = amdgpu_pm_get_sensor_generic(adev, AMDGPU_PP_SENSOR_VDDNB, + (void *)&vddnb); if (r) return r; @@ -3133,7 +3265,7 @@ static int amdgpu_hwmon_get_power(struct device *dev, u32 query = 0; int r; - r = amdgpu_hwmon_get_sensor_generic(adev, sensor, (void *)&query); + r = amdgpu_pm_get_sensor_generic(adev, sensor, (void *)&query); if (r) return r; @@ -3253,9 +3385,6 @@ static ssize_t amdgpu_hwmon_set_power_cap(struct device *dev, int err; u32 value; - if (amdgpu_sriov_vf(adev)) - return -EINVAL; - err = kstrtou32(buf, 10, &value); if (err) return err; @@ -3286,8 +3415,8 @@ static ssize_t amdgpu_hwmon_show_sclk(struct device *dev, int r; /* get the sclk */ - r = amdgpu_hwmon_get_sensor_generic(adev, AMDGPU_PP_SENSOR_GFX_SCLK, - (void *)&sclk); + r = amdgpu_pm_get_sensor_generic(adev, AMDGPU_PP_SENSOR_GFX_SCLK, + (void *)&sclk); if (r) return r; @@ -3310,8 +3439,8 @@ static ssize_t amdgpu_hwmon_show_mclk(struct device *dev, int r; /* get the sclk */ - r = amdgpu_hwmon_get_sensor_generic(adev, AMDGPU_PP_SENSOR_GFX_MCLK, - (void *)&mclk); + r = amdgpu_pm_get_sensor_generic(adev, AMDGPU_PP_SENSOR_GFX_MCLK, + (void *)&mclk); if (r) return r; @@ -3597,6 +3726,10 @@ static umode_t hwmon_attributes_visible(struct kobject *kobj, return 0; } + if (attr == &sensor_dev_attr_power1_cap.dev_attr.attr && + amdgpu_virt_cap_is_rw(&adev->virt.virt_caps, AMDGPU_VIRT_CAP_POWER_LIMIT)) + effective_mode |= S_IWUSR; + /* not implemented yet for APUs having < GC 9.3.0 (Renoir) */ if (((adev->family == AMDGPU_FAMILY_SI) || ((adev->flags & AMD_IS_APU) && (gc_ver < IP_VERSION(9, 3, 0)))) && @@ -3605,10 +3738,12 @@ static umode_t hwmon_attributes_visible(struct kobject *kobj, /* not all products support both average and instantaneous */ if (attr == &sensor_dev_attr_power1_average.dev_attr.attr && - amdgpu_hwmon_get_sensor_generic(adev, AMDGPU_PP_SENSOR_GPU_AVG_POWER, (void *)&tmp) == -EOPNOTSUPP) + amdgpu_pm_get_sensor_generic(adev, AMDGPU_PP_SENSOR_GPU_AVG_POWER, + (void *)&tmp) == -EOPNOTSUPP) return 0; if (attr == &sensor_dev_attr_power1_input.dev_attr.attr && - amdgpu_hwmon_get_sensor_generic(adev, AMDGPU_PP_SENSOR_GPU_INPUT_POWER, (void *)&tmp) == -EOPNOTSUPP) + amdgpu_pm_get_sensor_generic(adev, AMDGPU_PP_SENSOR_GPU_INPUT_POWER, + (void *)&tmp) == -EOPNOTSUPP) return 0; /* hide max/min values if we can't both query and manage the fan */ @@ -3647,8 +3782,8 @@ static umode_t hwmon_attributes_visible(struct kobject *kobj, /* only few boards support vddboard */ if ((attr == &sensor_dev_attr_in2_input.dev_attr.attr || attr == &sensor_dev_attr_in2_label.dev_attr.attr) && - amdgpu_hwmon_get_sensor_generic(adev, AMDGPU_PP_SENSOR_VDDBOARD, - (void *)&tmp) == -EOPNOTSUPP) + amdgpu_pm_get_sensor_generic(adev, AMDGPU_PP_SENSOR_VDDBOARD, + (void *)&tmp) == -EOPNOTSUPP) return 0; /* no mclk on APUs other than gc 9,4,3*/ @@ -4530,6 +4665,7 @@ int amdgpu_pm_sysfs_init(struct amdgpu_device *adev) { enum amdgpu_sriov_vf_mode mode; uint32_t mask = 0; + uint32_t tmp; int ret; if (adev->pm.sysfs_initialized) @@ -4596,6 +4732,21 @@ int amdgpu_pm_sysfs_init(struct amdgpu_device *adev) &amdgpu_board_attr_group); if (ret) goto err_out0; + if (amdgpu_pm_get_sensor_generic(adev, AMDGPU_PP_SENSOR_MAXNODEPOWERLIMIT, + (void *)&tmp) != -EOPNOTSUPP) { + sysfs_add_file_to_group(&adev->dev->kobj, + &dev_attr_cur_node_power_limit.attr, + amdgpu_board_attr_group.name); + sysfs_add_file_to_group(&adev->dev->kobj, &dev_attr_node_power.attr, + amdgpu_board_attr_group.name); + sysfs_add_file_to_group(&adev->dev->kobj, &dev_attr_global_ppt_resid.attr, + amdgpu_board_attr_group.name); + sysfs_add_file_to_group(&adev->dev->kobj, + &dev_attr_max_node_power_limit.attr, + amdgpu_board_attr_group.name); + sysfs_add_file_to_group(&adev->dev->kobj, &dev_attr_npm_status.attr, + amdgpu_board_attr_group.name); + } } adev->pm.sysfs_initialized = true; diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h index 9748744133d9..65c1d98af26c 100644 --- a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h +++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h @@ -263,10 +263,6 @@ struct amdgpu_dpm { u32 voltage_response_time; u32 backbias_response_time; void *priv; - u32 new_active_crtcs; - int new_active_crtc_count; - u32 current_active_crtcs; - int current_active_crtc_count; struct amdgpu_dpm_dynamic_state dyn_state; struct amdgpu_dpm_fan fan; u32 tdp_limit; diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm_internal.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm_internal.h index 5c2a89f0d5d5..cc6d7ba040e9 100644 --- a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm_internal.h +++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm_internal.h @@ -23,10 +23,6 @@ #ifndef __AMDGPU_DPM_INTERNAL_H__ #define __AMDGPU_DPM_INTERNAL_H__ -void amdgpu_dpm_get_active_displays(struct amdgpu_device *adev); - -u32 amdgpu_dpm_get_vblank_time(struct amdgpu_device *adev); - -u32 amdgpu_dpm_get_vrefresh(struct amdgpu_device *adev); +void amdgpu_dpm_get_display_cfg(struct amdgpu_device *adev); #endif diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c index 307ebf7e3226..33eb85dd68e9 100644 --- a/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c +++ b/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c @@ -2299,7 +2299,7 @@ static void kv_apply_state_adjust_rules(struct amdgpu_device *adev, if (pi->sys_info.nb_dpm_enable) { force_high = (mclk >= pi->sys_info.nbp_memory_clock[3]) || - pi->video_start || (adev->pm.dpm.new_active_crtc_count >= 3) || + pi->video_start || (adev->pm.pm_display_cfg.num_display >= 3) || pi->disable_nb_ps3_in_battery; ps->dpm0_pg_nb_ps_lo = force_high ? 0x2 : 0x3; ps->dpm0_pg_nb_ps_hi = 0x2; @@ -2358,7 +2358,7 @@ static int kv_calculate_nbps_level_settings(struct amdgpu_device *adev) return 0; force_high = ((mclk >= pi->sys_info.nbp_memory_clock[3]) || - (adev->pm.dpm.new_active_crtc_count >= 3) || pi->video_start); + (adev->pm.pm_display_cfg.num_display >= 3) || pi->video_start); if (force_high) { for (i = pi->lowest_valid; i <= pi->highest_valid; i++) diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c index ea3ace882a10..c7ed0b457129 100644 --- a/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c +++ b/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c @@ -771,8 +771,7 @@ static struct amdgpu_ps *amdgpu_dpm_pick_power_state(struct amdgpu_device *adev, int i; struct amdgpu_ps *ps; u32 ui_class; - bool single_display = (adev->pm.dpm.new_active_crtc_count < 2) ? - true : false; + bool single_display = adev->pm.pm_display_cfg.num_display < 2; /* check if the vblank period is too short to adjust the mclk */ if (single_display && adev->powerplay.pp_funcs->vblank_too_short) { @@ -945,9 +944,6 @@ static int amdgpu_dpm_change_power_state_locked(struct amdgpu_device *adev) amdgpu_dpm_post_set_power_state(adev); - adev->pm.dpm.current_active_crtcs = adev->pm.dpm.new_active_crtcs; - adev->pm.dpm.current_active_crtc_count = adev->pm.dpm.new_active_crtc_count; - if (pp_funcs->force_performance_level) { if (adev->pm.dpm.thermal_active) { enum amd_dpm_forced_level level = adev->pm.dpm.forced_level; @@ -968,7 +964,8 @@ void amdgpu_legacy_dpm_compute_clocks(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; - amdgpu_dpm_get_active_displays(adev); + if (!adev->dc_enabled) + amdgpu_dpm_get_display_cfg(adev); amdgpu_dpm_change_power_state_locked(adev); } diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c index 52e732be59e3..cf9932e68055 100644 --- a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c +++ b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c @@ -3081,11 +3081,17 @@ static int si_get_vce_clock_voltage(struct amdgpu_device *adev, static bool si_dpm_vblank_too_short(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; - u32 vblank_time = amdgpu_dpm_get_vblank_time(adev); + u32 vblank_time = adev->pm.pm_display_cfg.min_vblank_time; /* we never hit the non-gddr5 limit so disable it */ u32 switch_limit = adev->gmc.vram_type == AMDGPU_VRAM_TYPE_GDDR5 ? 450 : 0; - if (vblank_time < switch_limit) + /* Consider zero vblank time too short and disable MCLK switching. + * Note that the vblank time is set to maximum when no displays are attached, + * so we'll still enable MCLK switching in that case. + */ + if (vblank_time == 0) + return true; + else if (vblank_time < switch_limit) return true; else return false; @@ -3441,6 +3447,8 @@ static void rv770_get_engine_memory_ss(struct amdgpu_device *adev) static void si_apply_state_adjust_rules(struct amdgpu_device *adev, struct amdgpu_ps *rps) { + const struct amd_pp_display_configuration *display_cfg = + &adev->pm.pm_display_cfg; struct si_ps *ps = si_get_ps(rps); struct amdgpu_clock_and_voltage_limits *max_limits; bool disable_mclk_switching = false; @@ -3449,6 +3457,7 @@ static void si_apply_state_adjust_rules(struct amdgpu_device *adev, u16 vddc, vddci, min_vce_voltage = 0; u32 max_sclk_vddc, max_mclk_vddci, max_mclk_vddc; u32 max_sclk = 0, max_mclk = 0; + u32 high_pixelclock_count = 0; int i; if (adev->asic_type == CHIP_HAINAN) { @@ -3476,6 +3485,30 @@ static void si_apply_state_adjust_rules(struct amdgpu_device *adev, } } + /* We define "high pixelclock" for SI as higher than necessary for 4K 30Hz. + * For example, 4K 60Hz and 1080p 144Hz fall into this category. + * Find number of such displays connected. + */ + for (i = 0; i < display_cfg->num_display; i++) { + /* The array only contains active displays. */ + if (display_cfg->displays[i].pixel_clock > 297000) + high_pixelclock_count++; + } + + /* These are some ad-hoc fixes to some issues observed with SI GPUs. + * They are necessary because we don't have something like dce_calcs + * for these GPUs to calculate bandwidth requirements. + */ + if (high_pixelclock_count) { + /* On Oland, we observe some flickering when two 4K 60Hz + * displays are connected, possibly because voltage is too low. + * Raise the voltage by requiring a higher SCLK. + * (Voltage cannot be adjusted independently without also SCLK.) + */ + if (high_pixelclock_count > 1 && adev->asic_type == CHIP_OLAND) + disable_sclk_switching = true; + } + if (rps->vce_active) { rps->evclk = adev->pm.dpm.vce_states[adev->pm.dpm.vce_level].evclk; rps->ecclk = adev->pm.dpm.vce_states[adev->pm.dpm.vce_level].ecclk; @@ -3486,7 +3519,7 @@ static void si_apply_state_adjust_rules(struct amdgpu_device *adev, rps->ecclk = 0; } - if ((adev->pm.dpm.new_active_crtc_count > 1) || + if ((adev->pm.pm_display_cfg.num_display > 1) || si_dpm_vblank_too_short(adev)) disable_mclk_switching = true; @@ -3634,7 +3667,7 @@ static void si_apply_state_adjust_rules(struct amdgpu_device *adev, ps->performance_levels[i].mclk, max_limits->vddc, &ps->performance_levels[i].vddc); btc_apply_voltage_dependency_rules(&adev->pm.dpm.dyn_state.vddc_dependency_on_dispclk, - adev->clock.current_dispclk, + display_cfg->display_clk, max_limits->vddc, &ps->performance_levels[i].vddc); } @@ -4159,16 +4192,16 @@ static void si_program_ds_registers(struct amdgpu_device *adev) static void si_program_display_gap(struct amdgpu_device *adev) { + const struct amd_pp_display_configuration *cfg = &adev->pm.pm_display_cfg; u32 tmp, pipe; - int i; tmp = RREG32(mmCG_DISPLAY_GAP_CNTL) & ~(CG_DISPLAY_GAP_CNTL__DISP1_GAP_MASK | CG_DISPLAY_GAP_CNTL__DISP2_GAP_MASK); - if (adev->pm.dpm.new_active_crtc_count > 0) + if (cfg->num_display > 0) tmp |= R600_PM_DISPLAY_GAP_VBLANK_OR_WM << CG_DISPLAY_GAP_CNTL__DISP1_GAP__SHIFT; else tmp |= R600_PM_DISPLAY_GAP_IGNORE << CG_DISPLAY_GAP_CNTL__DISP1_GAP__SHIFT; - if (adev->pm.dpm.new_active_crtc_count > 1) + if (cfg->num_display > 1) tmp |= R600_PM_DISPLAY_GAP_VBLANK_OR_WM << CG_DISPLAY_GAP_CNTL__DISP2_GAP__SHIFT; else tmp |= R600_PM_DISPLAY_GAP_IGNORE << CG_DISPLAY_GAP_CNTL__DISP2_GAP__SHIFT; @@ -4178,17 +4211,8 @@ static void si_program_display_gap(struct amdgpu_device *adev) tmp = RREG32(DCCG_DISP_SLOW_SELECT_REG); pipe = (tmp & DCCG_DISP1_SLOW_SELECT_MASK) >> DCCG_DISP1_SLOW_SELECT_SHIFT; - if ((adev->pm.dpm.new_active_crtc_count > 0) && - (!(adev->pm.dpm.new_active_crtcs & (1 << pipe)))) { - /* find the first active crtc */ - for (i = 0; i < adev->mode_info.num_crtc; i++) { - if (adev->pm.dpm.new_active_crtcs & (1 << i)) - break; - } - if (i == adev->mode_info.num_crtc) - pipe = 0; - else - pipe = i; + if (cfg->num_display > 0 && pipe != cfg->crtc_index) { + pipe = cfg->crtc_index; tmp &= ~DCCG_DISP1_SLOW_SELECT_MASK; tmp |= DCCG_DISP1_SLOW_SELECT(pipe); @@ -4199,7 +4223,7 @@ static void si_program_display_gap(struct amdgpu_device *adev) * This can be a problem on PowerXpress systems or if you want to use the card * for offscreen rendering or compute if there are no crtcs enabled. */ - si_notify_smc_display_change(adev, adev->pm.dpm.new_active_crtc_count > 0); + si_notify_smc_display_change(adev, cfg->num_display > 0); } static void si_enable_spread_spectrum(struct amdgpu_device *adev, bool enable) @@ -5508,7 +5532,7 @@ static int si_convert_power_level_to_smc(struct amdgpu_device *adev, (pl->mclk <= pi->mclk_stutter_mode_threshold) && !eg_pi->uvd_enabled && (RREG32(mmDPG_PIPE_STUTTER_CONTROL) & DPG_PIPE_STUTTER_CONTROL__STUTTER_ENABLE_MASK) && - (adev->pm.dpm.new_active_crtc_count <= 2)) { + (adev->pm.pm_display_cfg.num_display <= 2)) { level->mcFlags |= SISLANDS_SMC_MC_STUTTER_EN; } @@ -5637,14 +5661,10 @@ static int si_populate_smc_t(struct amdgpu_device *adev, static int si_disable_ulv(struct amdgpu_device *adev) { - struct si_power_info *si_pi = si_get_pi(adev); - struct si_ulv_param *ulv = &si_pi->ulv; - - if (ulv->supported) - return (amdgpu_si_send_msg_to_smc(adev, PPSMC_MSG_DisableULV) == PPSMC_Result_OK) ? - 0 : -EINVAL; + PPSMC_Result r; - return 0; + r = amdgpu_si_send_msg_to_smc(adev, PPSMC_MSG_DisableULV); + return (r == PPSMC_Result_OK) ? 0 : -EINVAL; } static bool si_is_state_ulv_compatible(struct amdgpu_device *adev, @@ -5661,7 +5681,7 @@ static bool si_is_state_ulv_compatible(struct amdgpu_device *adev, /* XXX validate against display requirements! */ for (i = 0; i < adev->pm.dpm.dyn_state.vddc_dependency_on_dispclk.count; i++) { - if (adev->clock.current_dispclk <= + if (adev->pm.pm_display_cfg.display_clk <= adev->pm.dpm.dyn_state.vddc_dependency_on_dispclk.entries[i].clk) { if (ulv->pl.vddc < adev->pm.dpm.dyn_state.vddc_dependency_on_dispclk.entries[i].v) @@ -5815,39 +5835,36 @@ static int si_upload_ulv_state(struct amdgpu_device *adev) static int si_upload_smc_data(struct amdgpu_device *adev) { - struct amdgpu_crtc *amdgpu_crtc = NULL; - int i; + const struct amd_pp_display_configuration *cfg = &adev->pm.pm_display_cfg; + u32 crtc_index = 0; + u32 mclk_change_block_cp_min = 0; + u32 mclk_change_block_cp_max = 0; - if (adev->pm.dpm.new_active_crtc_count == 0) - return 0; + /* When a display is plugged in, program these so that the SMC + * performs MCLK switching when it doesn't cause flickering. + * When no display is plugged in, there is no need to restrict + * MCLK switching, so program them to zero. + */ + if (cfg->num_display) { + crtc_index = cfg->crtc_index; - for (i = 0; i < adev->mode_info.num_crtc; i++) { - if (adev->pm.dpm.new_active_crtcs & (1 << i)) { - amdgpu_crtc = adev->mode_info.crtcs[i]; - break; + if (cfg->line_time_in_us) { + mclk_change_block_cp_min = 200 / cfg->line_time_in_us; + mclk_change_block_cp_max = 100 / cfg->line_time_in_us; } } - if (amdgpu_crtc == NULL) - return 0; - - if (amdgpu_crtc->line_time <= 0) - return 0; - - if (si_write_smc_soft_register(adev, - SI_SMC_SOFT_REGISTER_crtc_index, - amdgpu_crtc->crtc_id) != PPSMC_Result_OK) - return 0; + si_write_smc_soft_register(adev, + SI_SMC_SOFT_REGISTER_crtc_index, + crtc_index); - if (si_write_smc_soft_register(adev, - SI_SMC_SOFT_REGISTER_mclk_change_block_cp_min, - amdgpu_crtc->wm_high / amdgpu_crtc->line_time) != PPSMC_Result_OK) - return 0; + si_write_smc_soft_register(adev, + SI_SMC_SOFT_REGISTER_mclk_change_block_cp_min, + mclk_change_block_cp_min); - if (si_write_smc_soft_register(adev, - SI_SMC_SOFT_REGISTER_mclk_change_block_cp_max, - amdgpu_crtc->wm_low / amdgpu_crtc->line_time) != PPSMC_Result_OK) - return 0; + si_write_smc_soft_register(adev, + SI_SMC_SOFT_REGISTER_mclk_change_block_cp_max, + mclk_change_block_cp_max); return 0; } @@ -7954,6 +7971,7 @@ static void si_dpm_print_power_state(void *handle, amdgpu_dpm_dbg_print_class_info(adev, rps->class, rps->class2); amdgpu_dpm_dbg_print_cap_info(adev, rps->caps); drm_dbg(adev_to_drm(adev), "\tuvd vclk: %d dclk: %d\n", rps->vclk, rps->dclk); + drm_dbg(adev_to_drm(adev), "\tvce evclk: %d ecclk: %d\n", rps->evclk, rps->ecclk); for (i = 0; i < ps->performance_level_count; i++) { pl = &ps->performance_levels[i]; drm_dbg(adev_to_drm(adev), "\t\tpower level %d sclk: %u mclk: %u vddc: %u vddci: %u pcie gen: %u\n", diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/si_smc.c b/drivers/gpu/drm/amd/pm/legacy-dpm/si_smc.c index 4e65ab9e931c..281a5e377aee 100644 --- a/drivers/gpu/drm/amd/pm/legacy-dpm/si_smc.c +++ b/drivers/gpu/drm/amd/pm/legacy-dpm/si_smc.c @@ -172,20 +172,42 @@ PPSMC_Result amdgpu_si_send_msg_to_smc(struct amdgpu_device *adev, { u32 tmp; int i; + int usec_timeout; + + /* SMC seems to process some messages exceptionally slowly. */ + switch (msg) { + case PPSMC_MSG_NoForcedLevel: + case PPSMC_MSG_SetEnabledLevels: + case PPSMC_MSG_SetForcedLevels: + case PPSMC_MSG_DisableULV: + case PPSMC_MSG_SwitchToSwState: + usec_timeout = 1000000; /* 1 sec */ + break; + default: + usec_timeout = 200000; /* 200 ms */ + break; + } if (!amdgpu_si_is_smc_running(adev)) return PPSMC_Result_Failed; WREG32(mmSMC_MESSAGE_0, msg); - for (i = 0; i < adev->usec_timeout; i++) { + for (i = 0; i < usec_timeout; i++) { tmp = RREG32(mmSMC_RESP_0); if (tmp != 0) break; udelay(1); } - return (PPSMC_Result)RREG32(mmSMC_RESP_0); + tmp = RREG32(mmSMC_RESP_0); + if (tmp == 0) { + drm_warn(adev_to_drm(adev), + "%s timeout on message: %x (SMC_SCRATCH0: %x)\n", + __func__, msg, RREG32(mmSMC_SCRATCH0)); + } + + return (PPSMC_Result)tmp; } PPSMC_Result amdgpu_si_wait_for_smc_inactive(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c index b48a031cbba0..554492dfa3c0 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c +++ b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c @@ -1554,16 +1554,7 @@ static void pp_pm_compute_clocks(void *handle) struct amdgpu_device *adev = hwmgr->adev; if (!adev->dc_enabled) { - amdgpu_dpm_get_active_displays(adev); - adev->pm.pm_display_cfg.num_display = adev->pm.dpm.new_active_crtc_count; - adev->pm.pm_display_cfg.vrefresh = amdgpu_dpm_get_vrefresh(adev); - adev->pm.pm_display_cfg.min_vblank_time = amdgpu_dpm_get_vblank_time(adev); - /* we have issues with mclk switching with - * refresh rates over 120 hz on the non-DC code. - */ - if (adev->pm.pm_display_cfg.vrefresh > 120) - adev->pm.pm_display_cfg.min_vblank_time = 0; - + amdgpu_dpm_get_display_cfg(adev); pp_display_configuration_change(handle, &adev->pm.pm_display_cfg); } diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomctrl.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomctrl.c index 8d40ed0f0e83..ce166a7f8e42 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomctrl.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomctrl.c @@ -563,8 +563,8 @@ bool atomctrl_is_voltage_controlled_by_gpio_v3( PP_ASSERT_WITH_CODE((NULL != voltage_info), "Could not find Voltage Table in BIOS.", return false;); - ret = (NULL != atomctrl_lookup_voltage_type_v3 - (voltage_info, voltage_type, voltage_mode)) ? true : false; + ret = atomctrl_lookup_voltage_type_v3 + (voltage_info, voltage_type, voltage_mode) != NULL; return ret; } diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c index 9a821563bc8e..14ccd743ca1d 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c @@ -1032,7 +1032,7 @@ static int smu10_print_clock_levels(struct pp_hwmgr *hwmgr, data->clock_vol_info.vdd_dep_on_fclk; uint32_t i, now, size = 0; uint32_t min_freq, max_freq = 0; - uint32_t ret = 0; + int ret = 0; switch (type) { case PP_SCLK: diff --git a/drivers/gpu/drm/amd/pm/powerplay/smumgr/fiji_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/fiji_smumgr.c index 5e43ad2b2956..d2dbd90bb427 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/smumgr/fiji_smumgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/fiji_smumgr.c @@ -2540,9 +2540,8 @@ static int fiji_initialize_mc_reg_table(struct pp_hwmgr *hwmgr) static bool fiji_is_dpm_running(struct pp_hwmgr *hwmgr) { - return (1 == PHM_READ_INDIRECT_FIELD(hwmgr->device, - CGS_IND_REG__SMC, FEATURE_STATUS, VOLTAGE_CONTROLLER_ON)) - ? true : false; + return PHM_READ_INDIRECT_FIELD(hwmgr->device, + CGS_IND_REG__SMC, FEATURE_STATUS, VOLTAGE_CONTROLLER_ON) == 1; } static int fiji_update_dpm_settings(struct pp_hwmgr *hwmgr, diff --git a/drivers/gpu/drm/amd/pm/powerplay/smumgr/iceland_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/iceland_smumgr.c index 17d2f5bff4a7..1f50f1e74c48 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/smumgr/iceland_smumgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/iceland_smumgr.c @@ -2655,9 +2655,8 @@ static int iceland_initialize_mc_reg_table(struct pp_hwmgr *hwmgr) static bool iceland_is_dpm_running(struct pp_hwmgr *hwmgr) { - return (1 == PHM_READ_INDIRECT_FIELD(hwmgr->device, - CGS_IND_REG__SMC, FEATURE_STATUS, VOLTAGE_CONTROLLER_ON)) - ? true : false; + return PHM_READ_INDIRECT_FIELD(hwmgr->device, + CGS_IND_REG__SMC, FEATURE_STATUS, VOLTAGE_CONTROLLER_ON) == 1; } const struct pp_smumgr_func iceland_smu_funcs = { diff --git a/drivers/gpu/drm/amd/pm/powerplay/smumgr/polaris10_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/polaris10_smumgr.c index ff6b563ecbf5..bf6d09572cfc 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/smumgr/polaris10_smumgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/polaris10_smumgr.c @@ -2578,9 +2578,8 @@ static int polaris10_initialize_mc_reg_table(struct pp_hwmgr *hwmgr) static bool polaris10_is_dpm_running(struct pp_hwmgr *hwmgr) { - return (1 == PHM_READ_INDIRECT_FIELD(hwmgr->device, - CGS_IND_REG__SMC, FEATURE_STATUS, VOLTAGE_CONTROLLER_ON)) - ? true : false; + return PHM_READ_INDIRECT_FIELD(hwmgr->device, + CGS_IND_REG__SMC, FEATURE_STATUS, VOLTAGE_CONTROLLER_ON) == 1; } static int polaris10_update_dpm_settings(struct pp_hwmgr *hwmgr, diff --git a/drivers/gpu/drm/amd/pm/powerplay/smumgr/smu7_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/smu7_smumgr.c index baf51cd82a35..0d4cbe4113a0 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/smumgr/smu7_smumgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/smu7_smumgr.c @@ -401,7 +401,7 @@ failed: int smu7_check_fw_load_finish(struct pp_hwmgr *hwmgr, uint32_t fw_type) { struct smu7_smumgr *smu_data = (struct smu7_smumgr *)(hwmgr->smu_backend); - uint32_t ret; + int ret; ret = phm_wait_on_indirect_register(hwmgr, mmSMC_IND_INDEX_11, smu_data->soft_regs_start + smum_get_offsetof(hwmgr, diff --git a/drivers/gpu/drm/amd/pm/powerplay/smumgr/tonga_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/tonga_smumgr.c index 6fe6e6abb5d8..2e21f9d066cb 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/smumgr/tonga_smumgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/tonga_smumgr.c @@ -3139,9 +3139,8 @@ static int tonga_initialize_mc_reg_table(struct pp_hwmgr *hwmgr) static bool tonga_is_dpm_running(struct pp_hwmgr *hwmgr) { - return (1 == PHM_READ_INDIRECT_FIELD(hwmgr->device, - CGS_IND_REG__SMC, FEATURE_STATUS, VOLTAGE_CONTROLLER_ON)) - ? true : false; + return PHM_READ_INDIRECT_FIELD(hwmgr->device, + CGS_IND_REG__SMC, FEATURE_STATUS, VOLTAGE_CONTROLLER_ON) == 1; } static int tonga_update_dpm_settings(struct pp_hwmgr *hwmgr, diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index c5965924e7c6..fb8086859857 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -766,7 +766,6 @@ static int smu_set_funcs(struct amdgpu_device *adev) case IP_VERSION(13, 0, 14): case IP_VERSION(13, 0, 12): smu_v13_0_6_set_ppt_funcs(smu); - smu_v13_0_6_set_temp_funcs(smu); /* Enable pp_od_clk_voltage node */ smu->od_enabled = true; break; @@ -1316,6 +1315,33 @@ static void smu_init_power_profile(struct smu_context *smu) smu_power_profile_mode_get(smu, smu->power_profile_mode); } +void smu_feature_cap_set(struct smu_context *smu, enum smu_feature_cap_id fea_id) +{ + struct smu_feature_cap *fea_cap = &smu->fea_cap; + + if (fea_id >= SMU_FEATURE_CAP_ID__COUNT) + return; + + set_bit(fea_id, fea_cap->cap_map); +} + +bool smu_feature_cap_test(struct smu_context *smu, enum smu_feature_cap_id fea_id) +{ + struct smu_feature_cap *fea_cap = &smu->fea_cap; + + if (fea_id >= SMU_FEATURE_CAP_ID__COUNT) + return false; + + return test_bit(fea_id, fea_cap->cap_map); +} + +static void smu_feature_cap_init(struct smu_context *smu) +{ + struct smu_feature_cap *fea_cap = &smu->fea_cap; + + bitmap_zero(fea_cap->cap_map, SMU_FEATURE_CAP_ID__COUNT); +} + static int smu_sw_init(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; @@ -1348,6 +1374,8 @@ static int smu_sw_init(struct amdgpu_ip_block *ip_block) INIT_DELAYED_WORK(&smu->swctf_delayed_work, smu_swctf_delayed_work_handler); + smu_feature_cap_init(smu); + ret = smu_smc_table_sw_init(smu); if (ret) { dev_err(adev->dev, "Failed to sw init smc table!\n"); @@ -1897,7 +1925,6 @@ static int smu_hw_init(struct amdgpu_ip_block *ip_block) for (i = 0; i < adev->vcn.num_vcn_inst; i++) smu_dpm_set_vcn_enable(smu, true, i); smu_dpm_set_jpeg_enable(smu, true); - smu_dpm_set_vpe_enable(smu, true); smu_dpm_set_umsch_mm_enable(smu, true); smu_set_mall_enable(smu); smu_set_gfx_cgpg(smu, true); @@ -2105,7 +2132,6 @@ static int smu_hw_fini(struct amdgpu_ip_block *ip_block) } smu_dpm_set_jpeg_enable(smu, false); adev->jpeg.cur_state = AMD_PG_STATE_GATE; - smu_dpm_set_vpe_enable(smu, false); smu_dpm_set_umsch_mm_enable(smu, false); if (!smu->pm_enabled) @@ -2237,7 +2263,7 @@ static int smu_resume(struct amdgpu_ip_block *ip_block) return ret; } - if (smu_dpm_ctx->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL) { + if (smu_dpm_ctx->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL && smu->od_enabled) { ret = smu_od_edit_dpm_table(smu, PP_OD_COMMIT_DPM_TABLE, NULL, 0); if (ret) return ret; @@ -3508,15 +3534,10 @@ bool smu_mode1_reset_is_support(struct smu_context *smu) bool smu_link_reset_is_support(struct smu_context *smu) { - bool ret = false; - if (!smu->pm_enabled) return false; - if (smu->ppt_funcs && smu->ppt_funcs->link_reset_is_support) - ret = smu->ppt_funcs->link_reset_is_support(smu); - - return ret; + return smu_feature_cap_test(smu, SMU_FEATURE_CAP_ID__LINK_RESET); } int smu_mode1_reset(struct smu_context *smu) @@ -4106,12 +4127,7 @@ int smu_send_rma_reason(struct smu_context *smu) */ bool smu_reset_sdma_is_supported(struct smu_context *smu) { - bool ret = false; - - if (smu->ppt_funcs && smu->ppt_funcs->reset_sdma_is_supported) - ret = smu->ppt_funcs->reset_sdma_is_supported(smu); - - return ret; + return smu_feature_cap_test(smu, SMU_FEATURE_CAP_ID__SDMA_RESET); } int smu_reset_sdma(struct smu_context *smu, uint32_t inst_mask) @@ -4126,12 +4142,7 @@ int smu_reset_sdma(struct smu_context *smu, uint32_t inst_mask) bool smu_reset_vcn_is_supported(struct smu_context *smu) { - bool ret = false; - - if (smu->ppt_funcs && smu->ppt_funcs->reset_vcn_is_supported) - ret = smu->ppt_funcs->reset_vcn_is_supported(smu); - - return ret; + return smu_feature_cap_test(smu, SMU_FEATURE_CAP_ID__VCN_RESET); } int smu_reset_vcn(struct smu_context *smu, uint32_t inst_mask) diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h index 5dd49eca598d..582c186d8b62 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h @@ -333,6 +333,7 @@ enum smu_table_id { SMU_TABLE_WIFIBAND, SMU_TABLE_GPUBOARD_TEMP_METRICS, SMU_TABLE_BASEBOARD_TEMP_METRICS, + SMU_TABLE_PMFW_SYSTEM_METRICS, SMU_TABLE_COUNT, }; @@ -527,6 +528,17 @@ enum smu_fw_status { */ #define SMU_WBRF_EVENT_HANDLING_PACE 10 +enum smu_feature_cap_id { + SMU_FEATURE_CAP_ID__LINK_RESET = 0, + SMU_FEATURE_CAP_ID__SDMA_RESET, + SMU_FEATURE_CAP_ID__VCN_RESET, + SMU_FEATURE_CAP_ID__COUNT, +}; + +struct smu_feature_cap { + DECLARE_BITMAP(cap_map, SMU_FEATURE_CAP_ID__COUNT); +}; + struct smu_context { struct amdgpu_device *adev; struct amdgpu_irq_src irq_source; @@ -549,6 +561,7 @@ struct smu_context { struct amd_pp_display_configuration *display_config; struct smu_baco_context smu_baco; struct smu_temperature_range thermal_range; + struct smu_feature_cap fea_cap; void *od_settings; struct smu_umd_pstate_table pstate_table; @@ -1272,11 +1285,6 @@ struct pptable_funcs { bool (*mode1_reset_is_support)(struct smu_context *smu); /** - * @link_reset_is_support: Check if GPU supports link reset. - */ - bool (*link_reset_is_support)(struct smu_context *smu); - - /** * @mode1_reset: Perform mode1 reset. * * Complete GPU reset. @@ -1426,19 +1434,11 @@ struct pptable_funcs { * @reset_sdma: message SMU to soft reset sdma instance. */ int (*reset_sdma)(struct smu_context *smu, uint32_t inst_mask); - /** - * @reset_sdma_is_supported: Check if support resets the SDMA engine. - */ - bool (*reset_sdma_is_supported)(struct smu_context *smu); /** * @reset_vcn: message SMU to soft reset vcn instance. */ int (*dpm_reset_vcn)(struct smu_context *smu, uint32_t inst_mask); - /** - * @reset_vcn_is_supported: Check if support resets vcn. - */ - bool (*reset_vcn_is_supported)(struct smu_context *smu); /** * @get_ecc_table: message SMU to get ECC INFO table. @@ -1787,4 +1787,7 @@ ssize_t smu_get_pm_policy_info(struct smu_context *smu, enum pp_pm_policy p_type, char *sysbuf); #endif + +void smu_feature_cap_set(struct smu_context *smu, enum smu_feature_cap_id fea_id); +bool smu_feature_cap_test(struct smu_context *smu, enum smu_feature_cap_id fea_id); #endif diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_12_pmfw.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_12_pmfw.h index 1c407a8e96ee..bf6aa9620911 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_12_pmfw.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_12_pmfw.h @@ -191,7 +191,7 @@ typedef enum { #define SMU_METRICS_TABLE_VERSION 0x14 -#define SMU_SYSTEM_METRICS_TABLE_VERSION 0x0 +#define SMU_SYSTEM_METRICS_TABLE_VERSION 0x1 typedef struct __attribute__((packed, aligned(4))) { uint64_t AccumulationCounter; @@ -304,7 +304,12 @@ typedef struct { int16_t SystemTemperatures[SYSTEM_TEMP_MAX_ENTRIES]; // Signed integer temperature value in Celsius, unused fields are set to 0xFFFF int16_t NodeTemperatures[NODE_TEMP_MAX_TEMP_ENTRIES]; // Signed integer temperature value in Celsius, unused fields are set to 0xFFFF int16_t VrTemperatures[SVI_MAX_TEMP_ENTRIES]; // Signed integer temperature value in Celsius - int16_t spare[3]; + int16_t spare[7]; + + //NPM: NODE POWER MANAGEMENT + uint32_t NodePowerLimit; + uint32_t NodePower; + uint32_t GlobalPPTResidencyAcc; } SystemMetricsTable_t; #pragma pack(pop) @@ -359,6 +364,9 @@ typedef struct { // General info uint32_t pldmVersion[2]; + + //Node Power Limit + uint32_t MaxNodePowerLimit; } StaticMetricsTable_t; #pragma pack(pop) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c index 599eddb5a67d..4fff78da81ff 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c @@ -1745,10 +1745,10 @@ static int arcturus_i2c_control_init(struct smu_context *smu) snprintf(control->name, sizeof(control->name), "AMDGPU SMU %d", i); i2c_set_adapdata(control, smu_i2c); - res = i2c_add_adapter(control); + res = devm_i2c_add_adapter(adev->dev, control); if (res) { DRM_ERROR("Failed to register hw i2c, err: %d\n", res); - goto Out_err; + return res; } } @@ -1756,27 +1756,12 @@ static int arcturus_i2c_control_init(struct smu_context *smu) adev->pm.fru_eeprom_i2c_bus = &adev->pm.smu_i2c[1].adapter; return 0; -Out_err: - for ( ; i >= 0; i--) { - struct amdgpu_smu_i2c_bus *smu_i2c = &adev->pm.smu_i2c[i]; - struct i2c_adapter *control = &smu_i2c->adapter; - - i2c_del_adapter(control); - } - return res; } static void arcturus_i2c_control_fini(struct smu_context *smu) { struct amdgpu_device *adev = smu->adev; - int i; - for (i = 0; i < MAX_SMU_I2C_BUSES; i++) { - struct amdgpu_smu_i2c_bus *smu_i2c = &adev->pm.smu_i2c[i]; - struct i2c_adapter *control = &smu_i2c->adapter; - - i2c_del_adapter(control); - } adev->pm.ras_eeprom_i2c_bus = NULL; adev->pm.fru_eeprom_i2c_bus = NULL; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c index aac202d0c30e..0028f10ead42 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c @@ -3145,10 +3145,10 @@ static int navi10_i2c_control_init(struct smu_context *smu) control->quirks = &navi10_i2c_control_quirks; i2c_set_adapdata(control, smu_i2c); - res = i2c_add_adapter(control); + res = devm_i2c_add_adapter(adev->dev, control); if (res) { DRM_ERROR("Failed to register hw i2c, err: %d\n", res); - goto Out_err; + return res; } } @@ -3156,27 +3156,12 @@ static int navi10_i2c_control_init(struct smu_context *smu) adev->pm.fru_eeprom_i2c_bus = &adev->pm.smu_i2c[1].adapter; return 0; -Out_err: - for ( ; i >= 0; i--) { - struct amdgpu_smu_i2c_bus *smu_i2c = &adev->pm.smu_i2c[i]; - struct i2c_adapter *control = &smu_i2c->adapter; - - i2c_del_adapter(control); - } - return res; } static void navi10_i2c_control_fini(struct smu_context *smu) { struct amdgpu_device *adev = smu->adev; - int i; - for (i = 0; i < MAX_SMU_I2C_BUSES; i++) { - struct amdgpu_smu_i2c_bus *smu_i2c = &adev->pm.smu_i2c[i]; - struct i2c_adapter *control = &smu_i2c->adapter; - - i2c_del_adapter(control); - } adev->pm.ras_eeprom_i2c_bus = NULL; adev->pm.fru_eeprom_i2c_bus = NULL; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c index d57591509aed..31c2c0386b1f 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c @@ -2648,10 +2648,10 @@ static int sienna_cichlid_i2c_control_init(struct smu_context *smu) control->quirks = &sienna_cichlid_i2c_control_quirks; i2c_set_adapdata(control, smu_i2c); - res = i2c_add_adapter(control); + res = devm_i2c_add_adapter(adev->dev, control); if (res) { DRM_ERROR("Failed to register hw i2c, err: %d\n", res); - goto Out_err; + return res; } } /* assign the buses used for the FRU EEPROM and RAS EEPROM */ @@ -2660,27 +2660,12 @@ static int sienna_cichlid_i2c_control_init(struct smu_context *smu) adev->pm.fru_eeprom_i2c_bus = &adev->pm.smu_i2c[0].adapter; return 0; -Out_err: - for ( ; i >= 0; i--) { - struct amdgpu_smu_i2c_bus *smu_i2c = &adev->pm.smu_i2c[i]; - struct i2c_adapter *control = &smu_i2c->adapter; - - i2c_del_adapter(control); - } - return res; } static void sienna_cichlid_i2c_control_fini(struct smu_context *smu) { struct amdgpu_device *adev = smu->adev; - int i; - for (i = 0; i < MAX_SMU_I2C_BUSES; i++) { - struct amdgpu_smu_i2c_bus *smu_i2c = &adev->pm.smu_i2c[i]; - struct i2c_adapter *control = &smu_i2c->adapter; - - i2c_del_adapter(control); - } adev->pm.ras_eeprom_i2c_bus = NULL; adev->pm.fru_eeprom_i2c_bus = NULL; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c index e97b0cf19197..3baf20f4c373 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c @@ -470,7 +470,7 @@ static int renoir_od_edit_dpm_table(struct smu_context *smu, static int renoir_set_fine_grain_gfx_freq_parameters(struct smu_context *smu) { uint32_t min = 0, max = 0; - uint32_t ret = 0; + int ret = 0; ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_GetMinGfxclkFrequency, diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c index b067147b7c41..18d5d0704509 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c @@ -1641,33 +1641,22 @@ static int aldebaran_i2c_control_init(struct smu_context *smu) control->quirks = &aldebaran_i2c_control_quirks; i2c_set_adapdata(control, smu_i2c); - res = i2c_add_adapter(control); + res = devm_i2c_add_adapter(adev->dev, control); if (res) { DRM_ERROR("Failed to register hw i2c, err: %d\n", res); - goto Out_err; + return res; } adev->pm.ras_eeprom_i2c_bus = &adev->pm.smu_i2c[0].adapter; adev->pm.fru_eeprom_i2c_bus = &adev->pm.smu_i2c[0].adapter; return 0; -Out_err: - i2c_del_adapter(control); - - return res; } static void aldebaran_i2c_control_fini(struct smu_context *smu) { struct amdgpu_device *adev = smu->adev; - int i; - - for (i = 0; i < MAX_SMU_I2C_BUSES; i++) { - struct amdgpu_smu_i2c_bus *smu_i2c = &adev->pm.smu_i2c[i]; - struct i2c_adapter *control = &smu_i2c->adapter; - i2c_del_adapter(control); - } adev->pm.ras_eeprom_i2c_bus = NULL; adev->pm.fru_eeprom_i2c_bus = NULL; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index e084ed99ec0e..c1062e5f0393 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -2825,10 +2825,10 @@ static int smu_v13_0_0_i2c_control_init(struct smu_context *smu) control->quirks = &smu_v13_0_0_i2c_control_quirks; i2c_set_adapdata(control, smu_i2c); - res = i2c_add_adapter(control); + res = devm_i2c_add_adapter(adev->dev, control); if (res) { DRM_ERROR("Failed to register hw i2c, err: %d\n", res); - goto Out_err; + return res; } } @@ -2838,27 +2838,12 @@ static int smu_v13_0_0_i2c_control_init(struct smu_context *smu) adev->pm.fru_eeprom_i2c_bus = &adev->pm.smu_i2c[0].adapter; return 0; -Out_err: - for ( ; i >= 0; i--) { - struct amdgpu_smu_i2c_bus *smu_i2c = &adev->pm.smu_i2c[i]; - struct i2c_adapter *control = &smu_i2c->adapter; - - i2c_del_adapter(control); - } - return res; } static void smu_v13_0_0_i2c_control_fini(struct smu_context *smu) { struct amdgpu_device *adev = smu->adev; - int i; - for (i = 0; i < MAX_SMU_I2C_BUSES; i++) { - struct amdgpu_smu_i2c_bus *smu_i2c = &adev->pm.smu_i2c[i]; - struct i2c_adapter *control = &smu_i2c->adapter; - - i2c_del_adapter(control); - } adev->pm.ras_eeprom_i2c_bus = NULL; adev->pm.fru_eeprom_i2c_bus = NULL; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c index 32fd0be05cff..1842a33b2bce 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c @@ -137,7 +137,7 @@ const struct cmn2asic_msg_mapping smu_v13_0_12_message_map[SMU_MSG_MAX_COUNT] = MSG_MAP(SetThrottlingPolicy, PPSMC_MSG_SetThrottlingPolicy, 0), MSG_MAP(ResetSDMA, PPSMC_MSG_ResetSDMA, 0), MSG_MAP(GetStaticMetricsTable, PPSMC_MSG_GetStaticMetricsTable, 1), - MSG_MAP(GetSystemMetricsTable, PPSMC_MSG_GetSystemMetricsTable, 0), + MSG_MAP(GetSystemMetricsTable, PPSMC_MSG_GetSystemMetricsTable, 1), }; int smu_v13_0_12_tables_init(struct smu_context *smu) @@ -149,6 +149,12 @@ int smu_v13_0_12_tables_init(struct smu_context *smu) struct smu_table_cache *cache; int ret; + ret = smu_table_cache_init(smu, SMU_TABLE_PMFW_SYSTEM_METRICS, + smu_v13_0_12_get_system_metrics_size(), 5); + + if (ret) + return ret; + ret = smu_table_cache_init(smu, SMU_TABLE_BASEBOARD_TEMP_METRICS, sizeof(*baseboard_temp_metrics), 50); if (ret) @@ -162,6 +168,7 @@ int smu_v13_0_12_tables_init(struct smu_context *smu) ret = smu_table_cache_init(smu, SMU_TABLE_GPUBOARD_TEMP_METRICS, sizeof(*gpuboard_temp_metrics), 50); if (ret) { + smu_table_cache_fini(smu, SMU_TABLE_PMFW_SYSTEM_METRICS); smu_table_cache_fini(smu, SMU_TABLE_BASEBOARD_TEMP_METRICS); return ret; } @@ -176,6 +183,7 @@ void smu_v13_0_12_tables_fini(struct smu_context *smu) { smu_table_cache_fini(smu, SMU_TABLE_BASEBOARD_TEMP_METRICS); smu_table_cache_fini(smu, SMU_TABLE_GPUBOARD_TEMP_METRICS); + smu_table_cache_fini(smu, SMU_TABLE_PMFW_SYSTEM_METRICS); } static int smu_v13_0_12_get_enabled_mask(struct smu_context *smu, @@ -222,8 +230,12 @@ static int smu_v13_0_12_fru_get_product_info(struct smu_context *smu, int smu_v13_0_12_get_max_metrics_size(void) { - return max3(sizeof(StaticMetricsTable_t), sizeof(MetricsTable_t), - sizeof(SystemMetricsTable_t)); + return max(sizeof(StaticMetricsTable_t), sizeof(MetricsTable_t)); +} + +size_t smu_v13_0_12_get_system_metrics_size(void) +{ + return sizeof(SystemMetricsTable_t); } static void smu_v13_0_12_init_xgmi_data(struct smu_context *smu, @@ -329,6 +341,9 @@ int smu_v13_0_12_setup_driver_pptable(struct smu_context *smu) static_metrics->pldmVersion[0] != 0xFFFFFFFF) smu->adev->firmware.pldm_version = static_metrics->pldmVersion[0]; + if (smu_v13_0_6_cap_supported(smu, SMU_CAP(NPM_METRICS))) + pptable->MaxNodePowerLimit = + SMUQ10_ROUND(static_metrics->MaxNodePowerLimit); smu_v13_0_12_init_xgmi_data(smu, static_metrics); pptable->Init = true; } @@ -414,14 +429,18 @@ int smu_v13_0_12_get_smu_metrics_data(struct smu_context *smu, return 0; } -static int smu_v13_0_12_get_system_metrics_table(struct smu_context *smu, - void *metrics_table) +static int smu_v13_0_12_get_system_metrics_table(struct smu_context *smu) { struct smu_table_context *smu_table = &smu->smu_table; - uint32_t table_size = smu_table->tables[SMU_TABLE_SMU_METRICS].size; struct smu_table *table = &smu_table->driver_table; + struct smu_table *tables = smu_table->tables; + struct smu_table *sys_table; int ret; + sys_table = &tables[SMU_TABLE_PMFW_SYSTEM_METRICS]; + if (smu_table_cache_is_valid(sys_table)) + return 0; + ret = smu_cmn_send_smc_msg(smu, SMU_MSG_GetSystemMetricsTable, NULL); if (ret) { dev_info(smu->adev->dev, @@ -430,10 +449,9 @@ static int smu_v13_0_12_get_system_metrics_table(struct smu_context *smu, } amdgpu_asic_invalidate_hdp(smu->adev, NULL); - memcpy(smu_table->metrics_table, table->cpu_addr, table_size); - - if (metrics_table) - memcpy(metrics_table, smu_table->metrics_table, sizeof(SystemMetricsTable_t)); + smu_table_cache_update_time(sys_table, jiffies); + memcpy(sys_table->cache.buffer, table->cpu_addr, + smu_v13_0_12_get_system_metrics_size()); return 0; } @@ -565,16 +583,60 @@ static bool smu_v13_0_12_is_temp_metrics_supported(struct smu_context *smu, return false; } +int smu_v13_0_12_get_npm_data(struct smu_context *smu, + enum amd_pp_sensors sensor, + uint32_t *value) +{ + struct smu_table_context *smu_table = &smu->smu_table; + struct PPTable_t *pptable = + (struct PPTable_t *)smu_table->driver_pptable; + struct smu_table *tables = smu_table->tables; + SystemMetricsTable_t *metrics; + struct smu_table *sys_table; + int ret; + + if (!smu_v13_0_6_cap_supported(smu, SMU_CAP(NPM_METRICS))) + return -EOPNOTSUPP; + + if (sensor == AMDGPU_PP_SENSOR_MAXNODEPOWERLIMIT) { + *value = pptable->MaxNodePowerLimit; + return 0; + } + + ret = smu_v13_0_12_get_system_metrics_table(smu); + if (ret) + return ret; + + sys_table = &tables[SMU_TABLE_PMFW_SYSTEM_METRICS]; + metrics = (SystemMetricsTable_t *)sys_table->cache.buffer; + + switch (sensor) { + case AMDGPU_PP_SENSOR_NODEPOWERLIMIT: + *value = SMUQ10_ROUND(metrics->NodePowerLimit); + break; + case AMDGPU_PP_SENSOR_NODEPOWER: + *value = SMUQ10_ROUND(metrics->NodePower); + break; + case AMDGPU_PP_SENSOR_GPPTRESIDENCY: + *value = SMUQ10_ROUND(metrics->GlobalPPTResidencyAcc); + break; + default: + return -EINVAL; + } + + return ret; +} + static ssize_t smu_v13_0_12_get_temp_metrics(struct smu_context *smu, enum smu_temp_metric_type type, void *table) { struct amdgpu_baseboard_temp_metrics_v1_0 *baseboard_temp_metrics; struct amdgpu_gpuboard_temp_metrics_v1_0 *gpuboard_temp_metrics; struct smu_table_context *smu_table = &smu->smu_table; - SystemMetricsTable_t *metrics = - (SystemMetricsTable_t *)smu_table->metrics_table; - + struct smu_table *tables = smu_table->tables; + SystemMetricsTable_t *metrics; struct smu_table *data_table; + struct smu_table *sys_table; int ret, sensor_type; u32 idx, sensors; ssize_t size; @@ -596,10 +658,12 @@ static ssize_t smu_v13_0_12_get_temp_metrics(struct smu_context *smu, size = sizeof(*baseboard_temp_metrics); } - ret = smu_v13_0_12_get_system_metrics_table(smu, NULL); + ret = smu_v13_0_12_get_system_metrics_table(smu); if (ret) return ret; + sys_table = &tables[SMU_TABLE_PMFW_SYSTEM_METRICS]; + metrics = (SystemMetricsTable_t *)sys_table->cache.buffer; smu_table_cache_update_time(data_table, jiffies); if (type == SMU_TEMP_METRIC_GPUBOARD) { diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c index e37b7b5358ea..349b6b8be010 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c @@ -143,7 +143,7 @@ static const struct cmn2asic_msg_mapping smu_v13_0_6_message_map[SMU_MSG_MAX_COU MSG_MAP(GetMinDpmFreq, PPSMC_MSG_GetMinDpmFreq, 1), MSG_MAP(GetMaxDpmFreq, PPSMC_MSG_GetMaxDpmFreq, 1), MSG_MAP(GetDpmFreqByIndex, PPSMC_MSG_GetDpmFreqByIndex, 1), - MSG_MAP(SetPptLimit, PPSMC_MSG_SetPptLimit, 0), + MSG_MAP(SetPptLimit, PPSMC_MSG_SetPptLimit, 1), MSG_MAP(GetPptLimit, PPSMC_MSG_GetPptLimit, 1), MSG_MAP(GfxDeviceDriverReset, PPSMC_MSG_GfxDriverReset, SMU_MSG_RAS_PRI | SMU_MSG_NO_PRECHECK), MSG_MAP(DramLogSetDramAddrHigh, PPSMC_MSG_DramLogSetDramAddrHigh, 0), @@ -354,7 +354,11 @@ static void smu_v13_0_12_init_caps(struct smu_context *smu) } if (fw_ver >= 0x04560700) { - if (!amdgpu_sriov_vf(smu->adev)) + if (fw_ver >= 0x04560900) { + smu_v13_0_6_cap_set(smu, SMU_CAP(TEMP_METRICS)); + if (smu->adev->gmc.xgmi.physical_node_id == 0) + smu_v13_0_6_cap_set(smu, SMU_CAP(NPM_METRICS)); + } else if (!amdgpu_sriov_vf(smu->adev)) smu_v13_0_6_cap_set(smu, SMU_CAP(TEMP_METRICS)); } else { smu_v13_0_12_tables_fini(smu); @@ -413,6 +417,10 @@ static void smu_v13_0_6_init_caps(struct smu_context *smu) smu_v13_0_6_cap_set(smu, SMU_CAP(HST_LIMIT_METRICS)); if (amdgpu_sriov_vf(adev)) { + if (fw_ver >= 0x00558200) + amdgpu_virt_attr_set(&adev->virt.virt_caps, + AMDGPU_VIRT_CAP_POWER_LIMIT, + AMDGPU_CAP_ATTR_RW); if ((pgm == 0 && fw_ver >= 0x00558000) || (pgm == 7 && fw_ver >= 0x7551000)) { smu_v13_0_6_cap_set(smu, @@ -559,6 +567,10 @@ static int smu_v13_0_6_tables_init(struct smu_context *smu) PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM | AMDGPU_GEM_DOMAIN_GTT); + SMU_TABLE_INIT(tables, SMU_TABLE_PMFW_SYSTEM_METRICS, + smu_v13_0_12_get_system_metrics_size(), PAGE_SIZE, + AMDGPU_GEM_DOMAIN_VRAM | AMDGPU_GEM_DOMAIN_GTT); + metrics_table = kzalloc(METRICS_TABLE_SIZE, GFP_KERNEL); if (!metrics_table) return -ENOMEM; @@ -1791,6 +1803,15 @@ static int smu_v13_0_6_read_sensor(struct smu_context *smu, ret = -EOPNOTSUPP; break; } + case AMDGPU_PP_SENSOR_NODEPOWERLIMIT: + case AMDGPU_PP_SENSOR_NODEPOWER: + case AMDGPU_PP_SENSOR_GPPTRESIDENCY: + case AMDGPU_PP_SENSOR_MAXNODEPOWERLIMIT: + ret = smu_v13_0_12_get_npm_data(smu, sensor, (uint32_t *)data); + if (ret) + return ret; + *size = 4; + break; case AMDGPU_PP_SENSOR_GPU_AVG_POWER: default: ret = -EOPNOTSUPP; @@ -2486,10 +2507,10 @@ static int smu_v13_0_6_i2c_control_init(struct smu_context *smu) control->quirks = &smu_v13_0_6_i2c_control_quirks; i2c_set_adapdata(control, smu_i2c); - res = i2c_add_adapter(control); + res = devm_i2c_add_adapter(adev->dev, control); if (res) { DRM_ERROR("Failed to register hw i2c, err: %d\n", res); - goto Out_err; + return res; } } @@ -2497,27 +2518,12 @@ static int smu_v13_0_6_i2c_control_init(struct smu_context *smu) adev->pm.fru_eeprom_i2c_bus = &adev->pm.smu_i2c[0].adapter; return 0; -Out_err: - for ( ; i >= 0; i--) { - struct amdgpu_smu_i2c_bus *smu_i2c = &adev->pm.smu_i2c[i]; - struct i2c_adapter *control = &smu_i2c->adapter; - - i2c_del_adapter(control); - } - return res; } static void smu_v13_0_6_i2c_control_fini(struct smu_context *smu) { struct amdgpu_device *adev = smu->adev; - int i; - - for (i = 0; i < MAX_SMU_I2C_BUSES; i++) { - struct amdgpu_smu_i2c_bus *smu_i2c = &adev->pm.smu_i2c[i]; - struct i2c_adapter *control = &smu_i2c->adapter; - i2c_del_adapter(control); - } adev->pm.ras_eeprom_i2c_bus = NULL; adev->pm.fru_eeprom_i2c_bus = NULL; } @@ -3219,6 +3225,20 @@ static int smu_v13_0_6_reset_vcn(struct smu_context *smu, uint32_t inst_mask) } +static int smu_v13_0_6_post_init(struct smu_context *smu) +{ + if (smu_v13_0_6_is_link_reset_supported(smu)) + smu_feature_cap_set(smu, SMU_FEATURE_CAP_ID__LINK_RESET); + + if (smu_v13_0_6_reset_sdma_is_supported(smu)) + smu_feature_cap_set(smu, SMU_FEATURE_CAP_ID__SDMA_RESET); + + if (smu_v13_0_6_reset_vcn_is_supported(smu)) + smu_feature_cap_set(smu, SMU_FEATURE_CAP_ID__VCN_RESET); + + return 0; +} + static int mca_smu_set_debug_mode(struct amdgpu_device *adev, bool enable) { struct smu_context *smu = adev->powerplay.pp_handle; @@ -3835,6 +3855,12 @@ static const struct aca_smu_funcs smu_v13_0_6_aca_smu_funcs = { .parse_error_code = aca_smu_parse_error_code, }; +static void smu_v13_0_6_set_temp_funcs(struct smu_context *smu) +{ + smu->smu_temp.temp_funcs = (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) + == IP_VERSION(13, 0, 12)) ? &smu_v13_0_12_temp_funcs : NULL; +} + static const struct pptable_funcs smu_v13_0_6_ppt_funcs = { /* init dpm */ .get_allowed_feature_mask = smu_v13_0_6_get_allowed_feature_mask, @@ -3882,7 +3908,6 @@ static const struct pptable_funcs smu_v13_0_6_ppt_funcs = { .get_xcp_metrics = smu_v13_0_6_get_xcp_metrics, .get_thermal_temperature_range = smu_v13_0_6_get_thermal_temperature_range, .mode1_reset_is_support = smu_v13_0_6_is_mode1_reset_supported, - .link_reset_is_support = smu_v13_0_6_is_link_reset_supported, .mode1_reset = smu_v13_0_6_mode1_reset, .mode2_reset = smu_v13_0_6_mode2_reset, .link_reset = smu_v13_0_6_link_reset, @@ -3892,9 +3917,8 @@ static const struct pptable_funcs smu_v13_0_6_ppt_funcs = { .send_hbm_bad_pages_num = smu_v13_0_6_smu_send_hbm_bad_page_num, .send_rma_reason = smu_v13_0_6_send_rma_reason, .reset_sdma = smu_v13_0_6_reset_sdma, - .reset_sdma_is_supported = smu_v13_0_6_reset_sdma_is_supported, .dpm_reset_vcn = smu_v13_0_6_reset_vcn, - .reset_vcn_is_supported = smu_v13_0_6_reset_vcn_is_supported, + .post_init = smu_v13_0_6_post_init, }; void smu_v13_0_6_set_ppt_funcs(struct smu_context *smu) @@ -3909,12 +3933,8 @@ void smu_v13_0_6_set_ppt_funcs(struct smu_context *smu) smu->smc_driver_if_version = SMU13_0_6_DRIVER_IF_VERSION; smu->smc_fw_caps |= SMU_FW_CAP_RAS_PRI; smu_v13_0_set_smu_mailbox_registers(smu); + smu_v13_0_6_set_temp_funcs(smu); amdgpu_mca_smu_init_funcs(smu->adev, &smu_v13_0_6_mca_smu_funcs); amdgpu_aca_set_smu_funcs(smu->adev, &smu_v13_0_6_aca_smu_funcs); } -void smu_v13_0_6_set_temp_funcs(struct smu_context *smu) -{ - smu->smu_temp.temp_funcs = (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) - == IP_VERSION(13, 0, 12)) ? &smu_v13_0_12_temp_funcs : NULL; -} diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.h b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.h index bcb8246c0804..7ef5f3e66c27 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.h +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.h @@ -49,6 +49,7 @@ struct PPTable_t { uint32_t MaxLclkDpmRange; uint32_t MinLclkDpmRange; uint64_t PublicSerialNumber_AID; + uint32_t MaxNodePowerLimit; bool Init; }; @@ -70,11 +71,11 @@ enum smu_v13_0_6_caps { SMU_CAP(BOARD_VOLTAGE), SMU_CAP(PLDM_VERSION), SMU_CAP(TEMP_METRICS), + SMU_CAP(NPM_METRICS), SMU_CAP(ALL), }; extern void smu_v13_0_6_set_ppt_funcs(struct smu_context *smu); -extern void smu_v13_0_6_set_temp_funcs(struct smu_context *smu); bool smu_v13_0_6_cap_supported(struct smu_context *smu, enum smu_v13_0_6_caps cap); int smu_v13_0_6_get_static_metrics_table(struct smu_context *smu); int smu_v13_0_6_get_metrics_table(struct smu_context *smu, void *metrics_table, @@ -82,6 +83,7 @@ int smu_v13_0_6_get_metrics_table(struct smu_context *smu, void *metrics_table, bool smu_v13_0_12_is_dpm_running(struct smu_context *smu); int smu_v13_0_12_get_max_metrics_size(void); +size_t smu_v13_0_12_get_system_metrics_size(void); int smu_v13_0_12_setup_driver_pptable(struct smu_context *smu); int smu_v13_0_12_get_smu_metrics_data(struct smu_context *smu, MetricsMember_t member, uint32_t *value); @@ -91,6 +93,9 @@ ssize_t smu_v13_0_12_get_xcp_metrics(struct smu_context *smu, void *smu_metrics); int smu_v13_0_12_tables_init(struct smu_context *smu); void smu_v13_0_12_tables_fini(struct smu_context *smu); +int smu_v13_0_12_get_npm_data(struct smu_context *smu, + enum amd_pp_sensors sensor, + uint32_t *value); extern const struct cmn2asic_mapping smu_v13_0_12_feature_mask_map[]; extern const struct cmn2asic_msg_mapping smu_v13_0_12_message_map[]; extern const struct smu_temp_funcs smu_v13_0_12_temp_funcs; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c index f32474af90b3..086501cc5213 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c @@ -2087,10 +2087,10 @@ static int smu_v14_0_2_i2c_control_init(struct smu_context *smu) control->quirks = &smu_v14_0_2_i2c_control_quirks; i2c_set_adapdata(control, smu_i2c); - res = i2c_add_adapter(control); + res = devm_i2c_add_adapter(adev->dev, control); if (res) { DRM_ERROR("Failed to register hw i2c, err: %d\n", res); - goto Out_err; + return res; } } @@ -2100,27 +2100,12 @@ static int smu_v14_0_2_i2c_control_init(struct smu_context *smu) adev->pm.fru_eeprom_i2c_bus = &adev->pm.smu_i2c[0].adapter; return 0; -Out_err: - for ( ; i >= 0; i--) { - struct amdgpu_smu_i2c_bus *smu_i2c = &adev->pm.smu_i2c[i]; - struct i2c_adapter *control = &smu_i2c->adapter; - - i2c_del_adapter(control); - } - return res; } static void smu_v14_0_2_i2c_control_fini(struct smu_context *smu) { struct amdgpu_device *adev = smu->adev; - int i; - for (i = 0; i < MAX_SMU_I2C_BUSES; i++) { - struct amdgpu_smu_i2c_bus *smu_i2c = &adev->pm.smu_i2c[i]; - struct i2c_adapter *control = &smu_i2c->adapter; - - i2c_del_adapter(control); - } adev->pm.ras_eeprom_i2c_bus = NULL; adev->pm.fru_eeprom_i2c_bus = NULL; } diff --git a/drivers/gpu/drm/ast/ast_2100.c b/drivers/gpu/drm/ast/ast_2100.c index 477ee15eff5d..829e3b8b0d19 100644 --- a/drivers/gpu/drm/ast/ast_2100.c +++ b/drivers/gpu/drm/ast/ast_2100.c @@ -32,6 +32,39 @@ #include "ast_post.h" /* + * DRAM type + */ + +static enum ast_dram_layout ast_2100_get_dram_layout_p2a(struct ast_device *ast) +{ + u32 mcr_cfg; + enum ast_dram_layout dram_layout; + + ast_write32(ast, 0xf004, 0x1e6e0000); + ast_write32(ast, 0xf000, 0x1); + mcr_cfg = ast_read32(ast, 0x10004); + + switch (mcr_cfg & 0x0c) { + case 0: + case 4: + default: + dram_layout = AST_DRAM_512Mx16; + break; + case 8: + if (mcr_cfg & 0x40) + dram_layout = AST_DRAM_1Gx16; + else + dram_layout = AST_DRAM_512Mx32; + break; + case 0xc: + dram_layout = AST_DRAM_1Gx32; + break; + } + + return dram_layout; +} + +/* * POST */ @@ -266,6 +299,7 @@ static void ast_post_chip_2100(struct ast_device *ast) u8 j; u32 data, temp, i; const struct ast_dramstruct *dram_reg_info; + enum ast_dram_layout dram_layout = ast_2100_get_dram_layout_p2a(ast); j = ast_get_index_reg_mask(ast, AST_IO_VGACRI, 0xd0, 0xff); @@ -292,11 +326,17 @@ static void ast_post_chip_2100(struct ast_device *ast) for (i = 0; i < 15; i++) udelay(dram_reg_info->data); } else if (AST_DRAMSTRUCT_IS(dram_reg_info, DRAM_TYPE)) { - data = dram_reg_info->data; - if (ast->dram_type == AST_DRAM_1Gx16) + switch (dram_layout) { + case AST_DRAM_1Gx16: data = 0x00000d89; - else if (ast->dram_type == AST_DRAM_1Gx32) + break; + case AST_DRAM_1Gx32: data = 0x00000c8d; + break; + default: + data = dram_reg_info->data; + break; + } temp = ast_read32(ast, 0x12070); temp &= 0xc; diff --git a/drivers/gpu/drm/ast/ast_drv.h b/drivers/gpu/drm/ast/ast_drv.h index e37a55295ed7..c15aef014f69 100644 --- a/drivers/gpu/drm/ast/ast_drv.h +++ b/drivers/gpu/drm/ast/ast_drv.h @@ -98,13 +98,15 @@ enum ast_config_mode { ast_use_defaults }; -#define AST_DRAM_512Mx16 0 -#define AST_DRAM_1Gx16 1 -#define AST_DRAM_512Mx32 2 -#define AST_DRAM_1Gx32 3 -#define AST_DRAM_2Gx16 6 -#define AST_DRAM_4Gx16 7 -#define AST_DRAM_8Gx16 8 +enum ast_dram_layout { + AST_DRAM_512Mx16 = 0, + AST_DRAM_1Gx16 = 1, + AST_DRAM_512Mx32 = 2, + AST_DRAM_1Gx32 = 3, + AST_DRAM_2Gx16 = 6, + AST_DRAM_4Gx16 = 7, + AST_DRAM_8Gx16 = 8, +}; /* * Hardware cursor @@ -172,10 +174,6 @@ struct ast_device { enum ast_config_mode config_mode; enum ast_chip chip; - uint32_t dram_bus_width; - uint32_t dram_type; - uint32_t mclk; - void __iomem *vram; unsigned long vram_base; unsigned long vram_size; diff --git a/drivers/gpu/drm/ast/ast_main.c b/drivers/gpu/drm/ast/ast_main.c index 44b9b5f659fc..3eea6a6cdacd 100644 --- a/drivers/gpu/drm/ast/ast_main.c +++ b/drivers/gpu/drm/ast/ast_main.c @@ -210,126 +210,6 @@ static void ast_detect_tx_chip(struct ast_device *ast, bool need_post) drm_info(dev, "Using %s\n", info_str[ast->tx_chip]); } -static int ast_get_dram_info(struct ast_device *ast) -{ - struct drm_device *dev = &ast->base; - struct device_node *np = dev->dev->of_node; - uint32_t mcr_cfg, mcr_scu_mpll, mcr_scu_strap; - uint32_t denum, num, div, ref_pll, dsel; - - switch (ast->config_mode) { - case ast_use_dt: - /* - * If some properties are missing, use reasonable - * defaults for GEN5 - */ - if (of_property_read_u32(np, "aspeed,mcr-configuration", - &mcr_cfg)) - mcr_cfg = 0x00000577; - if (of_property_read_u32(np, "aspeed,mcr-scu-mpll", - &mcr_scu_mpll)) - mcr_scu_mpll = 0x000050C0; - if (of_property_read_u32(np, "aspeed,mcr-scu-strap", - &mcr_scu_strap)) - mcr_scu_strap = 0; - break; - case ast_use_p2a: - ast_write32(ast, 0xf004, 0x1e6e0000); - ast_write32(ast, 0xf000, 0x1); - mcr_cfg = ast_read32(ast, 0x10004); - mcr_scu_mpll = ast_read32(ast, 0x10120); - mcr_scu_strap = ast_read32(ast, 0x10170); - break; - case ast_use_defaults: - default: - ast->dram_bus_width = 16; - ast->dram_type = AST_DRAM_1Gx16; - if (IS_AST_GEN6(ast)) - ast->mclk = 800; - else - ast->mclk = 396; - return 0; - } - - if (mcr_cfg & 0x40) - ast->dram_bus_width = 16; - else - ast->dram_bus_width = 32; - - if (IS_AST_GEN6(ast)) { - switch (mcr_cfg & 0x03) { - case 0: - ast->dram_type = AST_DRAM_1Gx16; - break; - default: - case 1: - ast->dram_type = AST_DRAM_2Gx16; - break; - case 2: - ast->dram_type = AST_DRAM_4Gx16; - break; - case 3: - ast->dram_type = AST_DRAM_8Gx16; - break; - } - } else if (IS_AST_GEN4(ast) || IS_AST_GEN5(ast)) { - switch (mcr_cfg & 0x03) { - case 0: - ast->dram_type = AST_DRAM_512Mx16; - break; - default: - case 1: - ast->dram_type = AST_DRAM_1Gx16; - break; - case 2: - ast->dram_type = AST_DRAM_2Gx16; - break; - case 3: - ast->dram_type = AST_DRAM_4Gx16; - break; - } - } else { - switch (mcr_cfg & 0x0c) { - case 0: - case 4: - ast->dram_type = AST_DRAM_512Mx16; - break; - case 8: - if (mcr_cfg & 0x40) - ast->dram_type = AST_DRAM_1Gx16; - else - ast->dram_type = AST_DRAM_512Mx32; - break; - case 0xc: - ast->dram_type = AST_DRAM_1Gx32; - break; - } - } - - if (mcr_scu_strap & 0x2000) - ref_pll = 14318; - else - ref_pll = 12000; - - denum = mcr_scu_mpll & 0x1f; - num = (mcr_scu_mpll & 0x3fe0) >> 5; - dsel = (mcr_scu_mpll & 0xc000) >> 14; - switch (dsel) { - case 3: - div = 0x4; - break; - case 2: - case 1: - div = 0x2; - break; - default: - div = 0x1; - break; - } - ast->mclk = ref_pll * (num + 2) / ((denum + 2) * (div * 1000)); - return 0; -} - struct drm_device *ast_device_create(struct pci_dev *pdev, const struct drm_driver *drv, enum ast_chip chip, @@ -352,12 +232,6 @@ struct drm_device *ast_device_create(struct pci_dev *pdev, ast->regs = regs; ast->ioregs = ioregs; - ret = ast_get_dram_info(ast); - if (ret) - return ERR_PTR(ret); - drm_info(dev, "dram MCLK=%u Mhz type=%d bus_width=%d\n", - ast->mclk, ast->dram_type, ast->dram_bus_width); - ast_detect_tx_chip(ast, need_post); switch (ast->tx_chip) { case AST_TX_ASTDP: diff --git a/drivers/gpu/drm/bridge/Kconfig b/drivers/gpu/drm/bridge/Kconfig index 6945029b3592..a250afd8d662 100644 --- a/drivers/gpu/drm/bridge/Kconfig +++ b/drivers/gpu/drm/bridge/Kconfig @@ -120,8 +120,7 @@ config DRM_ITE_IT6505 select DRM_DISPLAY_DP_AUX_BUS select DRM_KMS_HELPER select EXTCON - select CRYPTO - select CRYPTO_HASH + select CRYPTO_LIB_SHA1 select REGMAP_I2C help ITE IT6505 DisplayPort bridge chip driver. diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511.h b/drivers/gpu/drm/bridge/adv7511/adv7511.h index 85ebead9809c..8be7266fd4f4 100644 --- a/drivers/gpu/drm/bridge/adv7511/adv7511.h +++ b/drivers/gpu/drm/bridge/adv7511/adv7511.h @@ -195,13 +195,14 @@ #define ADV7511_I2S_IEC958_DIRECT 3 #define ADV7511_PACKET(p, x) ((p) * 0x20 + (x)) -#define ADV7511_PACKET_SDP(x) ADV7511_PACKET(0, x) +#define ADV7511_PACKET_SPD(x) ADV7511_PACKET(0, x) #define ADV7511_PACKET_MPEG(x) ADV7511_PACKET(1, x) #define ADV7511_PACKET_ACP(x) ADV7511_PACKET(2, x) #define ADV7511_PACKET_ISRC1(x) ADV7511_PACKET(3, x) #define ADV7511_PACKET_ISRC2(x) ADV7511_PACKET(4, x) #define ADV7511_PACKET_GM(x) ADV7511_PACKET(5, x) -#define ADV7511_PACKET_SPARE(x) ADV7511_PACKET(6, x) +#define ADV7511_PACKET_SPARE1(x) ADV7511_PACKET(6, x) +#define ADV7511_PACKET_SPARE2(x) ADV7511_PACKET(7, x) #define ADV7511_REG_CEC_TX_FRAME_HDR 0x00 #define ADV7511_REG_CEC_TX_FRAME_DATA0 0x01 @@ -348,6 +349,7 @@ struct adv7511 { struct i2c_client *i2c_cec; struct regmap *regmap; + struct regmap *regmap_packet; struct regmap *regmap_cec; enum drm_connector_status status; bool powered; diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_audio.c b/drivers/gpu/drm/bridge/adv7511/adv7511_audio.c index 766b1c96bc88..87e7e820810a 100644 --- a/drivers/gpu/drm/bridge/adv7511/adv7511_audio.c +++ b/drivers/gpu/drm/bridge/adv7511/adv7511_audio.c @@ -12,6 +12,8 @@ #include <sound/soc.h> #include <linux/of_graph.h> +#include <drm/display/drm_hdmi_state_helper.h> + #include "adv7511.h" static void adv7511_calc_cts_n(unsigned int f_tmds, unsigned int fs, @@ -155,17 +157,8 @@ int adv7511_hdmi_audio_prepare(struct drm_bridge *bridge, regmap_update_bits(adv7511->regmap, ADV7511_REG_I2C_FREQ_ID_CFG, ADV7511_I2C_FREQ_ID_CFG_RATE_MASK, rate << 4); - /* send current Audio infoframe values while updating */ - regmap_update_bits(adv7511->regmap, ADV7511_REG_INFOFRAME_UPDATE, - BIT(5), BIT(5)); - - regmap_write(adv7511->regmap, ADV7511_REG_AUDIO_INFOFRAME(0), 0x1); - - /* use Audio infoframe updated info */ - regmap_update_bits(adv7511->regmap, ADV7511_REG_INFOFRAME_UPDATE, - BIT(5), 0); - - return 0; + return drm_atomic_helper_connector_hdmi_update_audio_infoframe(connector, + &hparms->cea); } int adv7511_hdmi_audio_startup(struct drm_bridge *bridge, @@ -188,15 +181,9 @@ int adv7511_hdmi_audio_startup(struct drm_bridge *bridge, /* not copyrighted */ regmap_update_bits(adv7511->regmap, ADV7511_REG_AUDIO_CFG1, BIT(5), BIT(5)); - /* enable audio infoframes */ - regmap_update_bits(adv7511->regmap, ADV7511_REG_PACKET_ENABLE1, - BIT(3), BIT(3)); /* AV mute disable */ regmap_update_bits(adv7511->regmap, ADV7511_REG_GC(0), BIT(7) | BIT(6), BIT(7)); - /* use Audio infoframe updated info */ - regmap_update_bits(adv7511->regmap, ADV7511_REG_INFOFRAME_UPDATE, - BIT(5), 0); /* enable SPDIF receiver */ if (adv7511->audio_source == ADV7511_AUDIO_SOURCE_SPDIF) @@ -214,4 +201,6 @@ void adv7511_hdmi_audio_shutdown(struct drm_bridge *bridge, if (adv7511->audio_source == ADV7511_AUDIO_SOURCE_SPDIF) regmap_update_bits(adv7511->regmap, ADV7511_REG_AUDIO_CONFIG, BIT(7), 0); + + drm_atomic_helper_connector_hdmi_clear_audio_infoframe(connector); } diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c index 00d6417c177b..b9be86541307 100644 --- a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c +++ b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c @@ -132,6 +132,13 @@ static const struct regmap_config adv7511_regmap_config = { .volatile_reg = adv7511_register_volatile, }; +static const struct regmap_config adv7511_packet_config = { + .reg_bits = 8, + .val_bits = 8, + + .max_register = 0xff, +}; + /* ----------------------------------------------------------------------------- * Hardware configuration */ @@ -886,9 +893,18 @@ static int adv7511_bridge_hdmi_clear_infoframe(struct drm_bridge *bridge, struct adv7511 *adv7511 = bridge_to_adv7511(bridge); switch (type) { + case HDMI_INFOFRAME_TYPE_AUDIO: + adv7511_packet_disable(adv7511, ADV7511_PACKET_ENABLE_AUDIO_INFOFRAME); + break; case HDMI_INFOFRAME_TYPE_AVI: adv7511_packet_disable(adv7511, ADV7511_PACKET_ENABLE_AVI_INFOFRAME); break; + case HDMI_INFOFRAME_TYPE_SPD: + adv7511_packet_disable(adv7511, ADV7511_PACKET_ENABLE_SPD); + break; + case HDMI_INFOFRAME_TYPE_VENDOR: + adv7511_packet_disable(adv7511, ADV7511_PACKET_ENABLE_SPARE1); + break; default: drm_dbg_driver(adv7511->bridge.dev, "Unsupported HDMI InfoFrame %x\n", type); break; @@ -903,16 +919,52 @@ static int adv7511_bridge_hdmi_write_infoframe(struct drm_bridge *bridge, { struct adv7511 *adv7511 = bridge_to_adv7511(bridge); - adv7511_bridge_hdmi_clear_infoframe(bridge, type); - switch (type) { + case HDMI_INFOFRAME_TYPE_AUDIO: + /* send current Audio infoframe values while updating */ + regmap_update_bits(adv7511->regmap, ADV7511_REG_INFOFRAME_UPDATE, + BIT(5), BIT(5)); + + /* The Audio infoframe id is not configurable */ + regmap_bulk_write(adv7511->regmap, ADV7511_REG_AUDIO_INFOFRAME_VERSION, + buffer + 1, len - 1); + + /* use Audio infoframe updated info */ + regmap_update_bits(adv7511->regmap, ADV7511_REG_INFOFRAME_UPDATE, + BIT(5), 0); + + adv7511_packet_enable(adv7511, ADV7511_PACKET_ENABLE_AUDIO_INFOFRAME); + break; case HDMI_INFOFRAME_TYPE_AVI: + /* send current AVI infoframe values while updating */ + regmap_update_bits(adv7511->regmap, ADV7511_REG_INFOFRAME_UPDATE, + BIT(6), BIT(6)); + /* The AVI infoframe id is not configurable */ regmap_bulk_write(adv7511->regmap, ADV7511_REG_AVI_INFOFRAME_VERSION, buffer + 1, len - 1); + regmap_write(adv7511->regmap, ADV7511_REG_AUDIO_INFOFRAME_LENGTH, 0x2); + regmap_write(adv7511->regmap, ADV7511_REG_AUDIO_INFOFRAME(1), 0x1); + + /* use AVI infoframe updated info */ + regmap_update_bits(adv7511->regmap, ADV7511_REG_INFOFRAME_UPDATE, + BIT(6), 0); + adv7511_packet_enable(adv7511, ADV7511_PACKET_ENABLE_AVI_INFOFRAME); break; + case HDMI_INFOFRAME_TYPE_SPD: + adv7511_packet_disable(adv7511, ADV7511_PACKET_ENABLE_SPD); + regmap_bulk_write(adv7511->regmap_packet, ADV7511_PACKET_SPD(0), + buffer, len); + adv7511_packet_enable(adv7511, ADV7511_PACKET_ENABLE_SPD); + break; + case HDMI_INFOFRAME_TYPE_VENDOR: + adv7511_packet_disable(adv7511, ADV7511_PACKET_ENABLE_SPARE1); + regmap_bulk_write(adv7511->regmap_packet, ADV7511_PACKET_SPARE1(0), + buffer, len); + adv7511_packet_enable(adv7511, ADV7511_PACKET_ENABLE_SPARE1); + break; default: drm_dbg_driver(adv7511->bridge.dev, "Unsupported HDMI InfoFrame %x\n", type); break; @@ -1242,6 +1294,13 @@ static int adv7511_probe(struct i2c_client *i2c) goto err_i2c_unregister_edid; } + adv7511->regmap_packet = devm_regmap_init_i2c(adv7511->i2c_packet, + &adv7511_packet_config); + if (IS_ERR(adv7511->regmap_packet)) { + ret = PTR_ERR(adv7511->regmap_packet); + goto err_i2c_unregister_packet; + } + regmap_write(adv7511->regmap, ADV7511_REG_PACKET_I2C_ADDR, adv7511->i2c_packet->addr << 1); diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c index ed35e567d117..efe534977d12 100644 --- a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c +++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c @@ -1474,8 +1474,8 @@ analogix_dp_probe(struct device *dev, struct analogix_dp_plat_data *plat_data) dp = devm_drm_bridge_alloc(dev, struct analogix_dp_device, bridge, &analogix_dp_bridge_funcs); - if (!dp) - return ERR_PTR(-ENOMEM); + if (IS_ERR(dp)) + return ERR_CAST(dp); dp->dev = &pdev->dev; dp->dpms_mode = DRM_MODE_DPMS_OFF; diff --git a/drivers/gpu/drm/bridge/cadence/Kconfig b/drivers/gpu/drm/bridge/cadence/Kconfig index cced81633ddc..f1d8a8a151d8 100644 --- a/drivers/gpu/drm/bridge/cadence/Kconfig +++ b/drivers/gpu/drm/bridge/cadence/Kconfig @@ -6,6 +6,7 @@ config DRM_CDNS_DSI select DRM_PANEL_BRIDGE select GENERIC_PHY select GENERIC_PHY_MIPI_DPHY + select VIDEOMODE_HELPERS depends on OF help Support Cadence DPI to DSI bridge. This is an internal diff --git a/drivers/gpu/drm/bridge/imx/imx93-mipi-dsi.c b/drivers/gpu/drm/bridge/imx/imx93-mipi-dsi.c index bea8346515b8..8f7a0d46601a 100644 --- a/drivers/gpu/drm/bridge/imx/imx93-mipi-dsi.c +++ b/drivers/gpu/drm/bridge/imx/imx93-mipi-dsi.c @@ -492,14 +492,12 @@ static int imx93_dsi_get_phy_configure_opts(struct imx93_dsi *dsi, static enum drm_mode_status imx93_dsi_validate_mode(struct imx93_dsi *dsi, const struct drm_display_mode *mode) { - struct drm_bridge *bridge = dw_mipi_dsi_get_bridge(dsi->dmd); + struct drm_bridge *dmd_bridge = dw_mipi_dsi_get_bridge(dsi->dmd); + struct drm_bridge *last_bridge __free(drm_bridge_put) = + drm_bridge_chain_get_last_bridge(dmd_bridge->encoder); - /* Get the last bridge */ - while (drm_bridge_get_next_bridge(bridge)) - bridge = drm_bridge_get_next_bridge(bridge); - - if ((bridge->ops & DRM_BRIDGE_OP_DETECT) && - (bridge->ops & DRM_BRIDGE_OP_EDID)) { + if ((last_bridge->ops & DRM_BRIDGE_OP_DETECT) && + (last_bridge->ops & DRM_BRIDGE_OP_EDID)) { unsigned long pixel_clock_rate = mode->clock * 1000; unsigned long rounded_rate; diff --git a/drivers/gpu/drm/bridge/ite-it6263.c b/drivers/gpu/drm/bridge/ite-it6263.c index cf813672b4ff..2eb8fba7016c 100644 --- a/drivers/gpu/drm/bridge/ite-it6263.c +++ b/drivers/gpu/drm/bridge/ite-it6263.c @@ -146,6 +146,7 @@ #define HDMI_COLOR_DEPTH_24 FIELD_PREP(HDMI_COLOR_DEPTH, 4) #define HDMI_REG_PKT_GENERAL_CTRL 0xc6 +#define HDMI_REG_PKT_NULL_CTRL 0xc9 #define HDMI_REG_AVI_INFOFRM_CTRL 0xcd #define ENABLE_PKT BIT(0) #define REPEAT_PKT BIT(1) @@ -154,6 +155,12 @@ * 3) HDMI register bank1: 0x130 ~ 0x1ff (HDMI packet registers) */ +/* NULL packet registers */ +/* Header Byte(HB): n = 0 ~ 2 */ +#define HDMI_REG_PKT_HB(n) (0x138 + (n)) +/* Packet Byte(PB): n = 0 ~ 27(HDMI_MAX_INFOFRAME_SIZE), n = 0 for checksum */ +#define HDMI_REG_PKT_PB(n) (0x13b + (n)) + /* AVI packet registers */ #define HDMI_REG_AVI_DB1 0x158 #define HDMI_REG_AVI_DB2 0x159 @@ -224,7 +231,9 @@ static bool it6263_hdmi_writeable_reg(struct device *dev, unsigned int reg) case HDMI_REG_HDMI_MODE: case HDMI_REG_GCP: case HDMI_REG_PKT_GENERAL_CTRL: + case HDMI_REG_PKT_NULL_CTRL: case HDMI_REG_AVI_INFOFRM_CTRL: + case HDMI_REG_PKT_HB(0) ... HDMI_REG_PKT_PB(HDMI_MAX_INFOFRAME_SIZE): case HDMI_REG_AVI_DB1: case HDMI_REG_AVI_DB2: case HDMI_REG_AVI_DB3: @@ -755,10 +764,16 @@ static int it6263_hdmi_clear_infoframe(struct drm_bridge *bridge, { struct it6263 *it = bridge_to_it6263(bridge); - if (type == HDMI_INFOFRAME_TYPE_AVI) + switch (type) { + case HDMI_INFOFRAME_TYPE_AVI: regmap_write(it->hdmi_regmap, HDMI_REG_AVI_INFOFRM_CTRL, 0); - else + break; + case HDMI_INFOFRAME_TYPE_VENDOR: + regmap_write(it->hdmi_regmap, HDMI_REG_PKT_NULL_CTRL, 0); + break; + default: dev_dbg(it->dev, "unsupported HDMI infoframe 0x%x\n", type); + } return 0; } @@ -770,27 +785,36 @@ static int it6263_hdmi_write_infoframe(struct drm_bridge *bridge, struct it6263 *it = bridge_to_it6263(bridge); struct regmap *regmap = it->hdmi_regmap; - if (type != HDMI_INFOFRAME_TYPE_AVI) { + switch (type) { + case HDMI_INFOFRAME_TYPE_AVI: + /* write the first AVI infoframe data byte chunk(DB1-DB5) */ + regmap_bulk_write(regmap, HDMI_REG_AVI_DB1, + &buffer[HDMI_INFOFRAME_HEADER_SIZE], + HDMI_AVI_DB_CHUNK1_SIZE); + + /* write the second AVI infoframe data byte chunk(DB6-DB13) */ + regmap_bulk_write(regmap, HDMI_REG_AVI_DB6, + &buffer[HDMI_INFOFRAME_HEADER_SIZE + + HDMI_AVI_DB_CHUNK1_SIZE], + HDMI_AVI_DB_CHUNK2_SIZE); + + /* write checksum */ + regmap_write(regmap, HDMI_REG_AVI_CSUM, buffer[3]); + + regmap_write(regmap, HDMI_REG_AVI_INFOFRM_CTRL, + ENABLE_PKT | REPEAT_PKT); + break; + case HDMI_INFOFRAME_TYPE_VENDOR: + /* write header and payload */ + regmap_bulk_write(regmap, HDMI_REG_PKT_HB(0), buffer, len); + + regmap_write(regmap, HDMI_REG_PKT_NULL_CTRL, + ENABLE_PKT | REPEAT_PKT); + break; + default: dev_dbg(it->dev, "unsupported HDMI infoframe 0x%x\n", type); - return 0; } - /* write the first AVI infoframe data byte chunk(DB1-DB5) */ - regmap_bulk_write(regmap, HDMI_REG_AVI_DB1, - &buffer[HDMI_INFOFRAME_HEADER_SIZE], - HDMI_AVI_DB_CHUNK1_SIZE); - - /* write the second AVI infoframe data byte chunk(DB6-DB13) */ - regmap_bulk_write(regmap, HDMI_REG_AVI_DB6, - &buffer[HDMI_INFOFRAME_HEADER_SIZE + - HDMI_AVI_DB_CHUNK1_SIZE], - HDMI_AVI_DB_CHUNK2_SIZE); - - /* write checksum */ - regmap_write(regmap, HDMI_REG_AVI_CSUM, buffer[3]); - - regmap_write(regmap, HDMI_REG_AVI_INFOFRM_CTRL, ENABLE_PKT | REPEAT_PKT); - return 0; } diff --git a/drivers/gpu/drm/bridge/ite-it6505.c b/drivers/gpu/drm/bridge/ite-it6505.c index 89649c17ffad..a094803ba7aa 100644 --- a/drivers/gpu/drm/bridge/ite-it6505.c +++ b/drivers/gpu/drm/bridge/ite-it6505.c @@ -21,7 +21,7 @@ #include <linux/wait.h> #include <linux/bitfield.h> -#include <crypto/hash.h> +#include <crypto/sha1.h> #include <drm/display/drm_dp_helper.h> #include <drm/display/drm_hdcp_helper.h> @@ -2107,35 +2107,6 @@ static void it6505_hdcp_part1_auth(struct it6505 *it6505) it6505->hdcp_status = HDCP_AUTH_GOING; } -static int it6505_sha1_digest(struct it6505 *it6505, u8 *sha1_input, - unsigned int size, u8 *output_av) -{ - struct shash_desc *desc; - struct crypto_shash *tfm; - int err; - struct device *dev = it6505->dev; - - tfm = crypto_alloc_shash("sha1", 0, 0); - if (IS_ERR(tfm)) { - dev_err(dev, "crypto_alloc_shash sha1 failed"); - return PTR_ERR(tfm); - } - desc = kzalloc(sizeof(*desc) + crypto_shash_descsize(tfm), GFP_KERNEL); - if (!desc) { - crypto_free_shash(tfm); - return -ENOMEM; - } - - desc->tfm = tfm; - err = crypto_shash_digest(desc, sha1_input, size, output_av); - if (err) - dev_err(dev, "crypto_shash_digest sha1 failed"); - - crypto_free_shash(tfm); - kfree(desc); - return err; -} - static int it6505_setup_sha1_input(struct it6505 *it6505, u8 *sha1_input) { struct device *dev = it6505->dev; @@ -2205,7 +2176,7 @@ static bool it6505_hdcp_part2_ksvlist_check(struct it6505 *it6505) return false; } - it6505_sha1_digest(it6505, it6505->sha1_input, i, (u8 *)av); + sha1(it6505->sha1_input, i, (u8 *)av); /*1B-05 V' must retry 3 times */ for (retry = 0; retry < 3; retry++) { err = it6505_get_dpcd(it6505, DP_AUX_HDCP_V_PRIME(0), (u8 *)bv, diff --git a/drivers/gpu/drm/bridge/samsung-dsim.c b/drivers/gpu/drm/bridge/samsung-dsim.c index b5dd71f6a990..eabc4c32f6ab 100644 --- a/drivers/gpu/drm/bridge/samsung-dsim.c +++ b/drivers/gpu/drm/bridge/samsung-dsim.c @@ -31,11 +31,10 @@ /* returns true iff both arguments logically differs */ #define NEQV(a, b) (!(a) ^ !(b)) -/* DSIM_STATUS */ +/* DSIM_STATUS or DSIM_DPHY_STATUS */ #define DSIM_STOP_STATE_DAT(x) (((x) & 0xf) << 0) #define DSIM_STOP_STATE_CLK BIT(8) #define DSIM_TX_READY_HS_CLK BIT(10) -#define DSIM_PLL_STABLE BIT(31) /* DSIM_SWRST */ #define DSIM_FUNCRST BIT(16) @@ -46,17 +45,13 @@ #define DSIM_BTA_TIMEOUT(x) ((x) << 16) /* DSIM_CLKCTRL */ -#define DSIM_ESC_PRESCALER(x) (((x) & 0xffff) << 0) -#define DSIM_ESC_PRESCALER_MASK (0xffff << 0) -#define DSIM_LANE_ESC_CLK_EN_CLK BIT(19) -#define DSIM_LANE_ESC_CLK_EN_DATA(x) (((x) & 0xf) << 20) -#define DSIM_LANE_ESC_CLK_EN_DATA_MASK (0xf << 20) -#define DSIM_BYTE_CLKEN BIT(24) -#define DSIM_BYTE_CLK_SRC(x) (((x) & 0x3) << 25) -#define DSIM_BYTE_CLK_SRC_MASK (0x3 << 25) -#define DSIM_PLL_BYPASS BIT(27) -#define DSIM_ESC_CLKEN BIT(28) -#define DSIM_TX_REQUEST_HSCLK BIT(31) +#define DSIM_ESC_PRESCALER(x) (((x) & 0xffff) << 0) +#define DSIM_ESC_PRESCALER_MASK (0xffff << 0) +#define DSIM_LANE_ESC_CLK_EN_DATA(x, offset) (((x) & 0xf) << offset) +#define DSIM_LANE_ESC_CLK_EN_DATA_MASK(offset) (0xf << offset) +#define DSIM_BYTE_CLK_SRC(x) (((x) & 0x3) << 25) +#define DSIM_BYTE_CLK_SRC_MASK (0x3 << 25) +#define DSIM_PLL_BYPASS BIT(27) /* DSIM_CONFIG */ #define DSIM_LANE_EN_CLK BIT(0) @@ -91,7 +86,6 @@ */ #define DSIM_HSE_DISABLE_MODE BIT(23) #define DSIM_AUTO_MODE BIT(24) -#define DSIM_VIDEO_MODE BIT(25) #define DSIM_BURST_MODE BIT(26) #define DSIM_SYNC_INFORM BIT(27) #define DSIM_EOT_DISABLE BIT(28) @@ -129,9 +123,9 @@ #define DSIM_MAIN_HBP_MASK ((0xffff) << 0) /* DSIM_MSYNC */ -#define DSIM_MAIN_VSA(x) ((x) << 22) +#define DSIM_MAIN_VSA(x, offset) ((x) << offset) #define DSIM_MAIN_HSA(x) ((x) << 0) -#define DSIM_MAIN_VSA_MASK ((0x3ff) << 22) +#define DSIM_MAIN_VSA_MASK(offset) ((0x3ff) << offset) #define DSIM_MAIN_HSA_MASK ((0xffff) << 0) /* DSIM_SDRESOL */ @@ -157,6 +151,11 @@ #define DSIM_INT_RX_ECC_ERR BIT(15) #define DSIM_INT_RX_CRC_ERR BIT(14) +/* DSIM_SFRCTRL */ +#define DSIM_SFR_CTRL_STAND_BY BIT(4) +#define DSIM_SFR_CTRL_SHADOW_UPDATE BIT(1) +#define DSIM_SFR_CTRL_SHADOW_EN BIT(0) + /* DSIM_FIFOCTRL */ #define DSIM_RX_DATA_FULL BIT(25) #define DSIM_RX_DATA_EMPTY BIT(24) @@ -191,9 +190,7 @@ #define DSIM_PLL_DPDNSWAP_DAT (1 << 24) #define DSIM_FREQ_BAND(x) ((x) << 24) #define DSIM_PLL_EN BIT(23) -#define DSIM_PLL_P(x, offset) ((x) << (offset)) -#define DSIM_PLL_M(x) ((x) << 4) -#define DSIM_PLL_S(x) ((x) << 1) +#define DSIM_PLL(x, offset) ((x) << (offset)) /* DSIM_PHYCTRL */ #define DSIM_PHYCTRL_ULPS_EXIT(x) (((x) & 0x1ff) << 0) @@ -222,25 +219,42 @@ #define DSI_XFER_TIMEOUT_MS 100 #define DSI_RX_FIFO_EMPTY 0x30800002 -#define OLD_SCLK_MIPI_CLK_NAME "pll_clk" - #define PS_TO_CYCLE(ps, hz) DIV64_U64_ROUND_CLOSEST(((ps) * (hz)), 1000000000000ULL) -static const char *const clk_names[5] = { - "bus_clk", - "sclk_mipi", - "phyclk_mipidphy0_bitclkdiv8", - "phyclk_mipidphy0_rxclkesc0", - "sclk_rgb_vclk_to_dsim0" -}; - enum samsung_dsim_transfer_type { EXYNOS_DSI_TX, EXYNOS_DSI_RX, }; +static struct clk_bulk_data exynos3_clk_bulk_data[] = { + { .id = "bus_clk" }, + { .id = "pll_clk" }, +}; + +static struct clk_bulk_data exynos4_clk_bulk_data[] = { + { .id = "bus_clk" }, + { .id = "sclk_mipi" }, +}; + +static struct clk_bulk_data exynos5433_clk_bulk_data[] = { + { .id = "bus_clk" }, + { .id = "sclk_mipi" }, + { .id = "phyclk_mipidphy0_bitclkdiv8" }, + { .id = "phyclk_mipidphy0_rxclkesc0" }, + { .id = "sclk_rgb_vclk_to_dsim0" }, +}; + +static struct clk_bulk_data exynos7870_clk_bulk_data[] = { + { .id = "bus" }, + { .id = "pll" }, + { .id = "byte" }, + { .id = "esc" }, +}; + enum reg_idx { - DSIM_STATUS_REG, /* Status register */ + DSIM_STATUS_REG, /* Status register (legacy) */ + DSIM_LINK_STATUS_REG, /* Link status register */ + DSIM_DPHY_STATUS_REG, /* D-PHY status register */ DSIM_SWRST_REG, /* Software reset register */ DSIM_CLKCTRL_REG, /* Clock control register */ DSIM_TIMEOUT_REG, /* Time out register */ @@ -255,6 +269,7 @@ enum reg_idx { DSIM_PKTHDR_REG, /* Packet Header FIFO register */ DSIM_PAYLOAD_REG, /* Payload FIFO register */ DSIM_RXFIFO_REG, /* Read FIFO register */ + DSIM_SFRCTRL_REG, /* SFR standby and shadow control register */ DSIM_FIFOCTRL_REG, /* FIFO status and control register */ DSIM_PLLCTRL_REG, /* PLL control register */ DSIM_PHYCTRL_REG, @@ -312,6 +327,32 @@ static const unsigned int exynos5433_reg_ofs[] = { [DSIM_PHYTIMING2_REG] = 0xBC, }; +static const unsigned int exynos7870_reg_ofs[] = { + [DSIM_LINK_STATUS_REG] = 0x04, + [DSIM_DPHY_STATUS_REG] = 0x08, + [DSIM_SWRST_REG] = 0x0C, + [DSIM_CLKCTRL_REG] = 0x10, + [DSIM_TIMEOUT_REG] = 0x14, + [DSIM_ESCMODE_REG] = 0x1C, + [DSIM_MDRESOL_REG] = 0x20, + [DSIM_MVPORCH_REG] = 0x24, + [DSIM_MHPORCH_REG] = 0x28, + [DSIM_MSYNC_REG] = 0x2C, + [DSIM_CONFIG_REG] = 0x30, + [DSIM_INTSRC_REG] = 0x34, + [DSIM_INTMSK_REG] = 0x38, + [DSIM_PKTHDR_REG] = 0x3C, + [DSIM_PAYLOAD_REG] = 0x40, + [DSIM_RXFIFO_REG] = 0x44, + [DSIM_SFRCTRL_REG] = 0x48, + [DSIM_FIFOCTRL_REG] = 0x4C, + [DSIM_PLLCTRL_REG] = 0x94, + [DSIM_PHYCTRL_REG] = 0xA4, + [DSIM_PHYTIMING_REG] = 0xB4, + [DSIM_PHYTIMING1_REG] = 0xB8, + [DSIM_PHYTIMING2_REG] = 0xBC, +}; + enum reg_value_idx { RESET_TYPE, PLL_TIMER, @@ -384,6 +425,24 @@ static const unsigned int exynos5433_reg_values[] = { [PHYTIMING_HS_TRAIL] = DSIM_PHYTIMING2_HS_TRAIL(0x0c), }; +static const unsigned int exynos7870_reg_values[] = { + [RESET_TYPE] = DSIM_SWRST, + [PLL_TIMER] = 80000, + [STOP_STATE_CNT] = 0xa, + [PHYCTRL_ULPS_EXIT] = DSIM_PHYCTRL_ULPS_EXIT(0x177), + [PHYCTRL_VREG_LP] = 0, + [PHYCTRL_SLEW_UP] = 0, + [PHYTIMING_LPX] = DSIM_PHYTIMING_LPX(0x07), + [PHYTIMING_HS_EXIT] = DSIM_PHYTIMING_HS_EXIT(0x0c), + [PHYTIMING_CLK_PREPARE] = DSIM_PHYTIMING1_CLK_PREPARE(0x08), + [PHYTIMING_CLK_ZERO] = DSIM_PHYTIMING1_CLK_ZERO(0x2b), + [PHYTIMING_CLK_POST] = DSIM_PHYTIMING1_CLK_POST(0x0d), + [PHYTIMING_CLK_TRAIL] = DSIM_PHYTIMING1_CLK_TRAIL(0x09), + [PHYTIMING_HS_PREPARE] = DSIM_PHYTIMING2_HS_PREPARE(0x09), + [PHYTIMING_HS_ZERO] = DSIM_PHYTIMING2_HS_ZERO(0x0f), + [PHYTIMING_HS_TRAIL] = DSIM_PHYTIMING2_HS_TRAIL(0x0c), +}; + static const unsigned int imx8mm_dsim_reg_values[] = { [RESET_TYPE] = DSIM_SWRST, [PLL_TIMER] = 500, @@ -405,13 +464,26 @@ static const unsigned int imx8mm_dsim_reg_values[] = { static const struct samsung_dsim_driver_data exynos3_dsi_driver_data = { .reg_ofs = exynos_reg_ofs, .plltmr_reg = 0x50, + .has_legacy_status_reg = 1, .has_freqband = 1, .has_clklane_stop = 1, - .num_clks = 2, + .clk_data = exynos3_clk_bulk_data, + .num_clks = ARRAY_SIZE(exynos3_clk_bulk_data), .max_freq = 1000, + .wait_for_hdr_fifo = 1, .wait_for_reset = 1, .num_bits_resol = 11, + .video_mode_bit = 25, + .pll_stable_bit = 31, + .esc_clken_bit = 28, + .byte_clken_bit = 24, + .tx_req_hsclk_bit = 31, + .lane_esc_clk_bit = 19, + .lane_esc_data_offset = 20, .pll_p_offset = 13, + .pll_m_offset = 4, + .pll_s_offset = 1, + .main_vsa_offset = 22, .reg_values = reg_values, .pll_fin_min = 6, .pll_fin_max = 12, @@ -424,13 +496,26 @@ static const struct samsung_dsim_driver_data exynos3_dsi_driver_data = { static const struct samsung_dsim_driver_data exynos4_dsi_driver_data = { .reg_ofs = exynos_reg_ofs, .plltmr_reg = 0x50, + .has_legacy_status_reg = 1, .has_freqband = 1, .has_clklane_stop = 1, - .num_clks = 2, + .clk_data = exynos4_clk_bulk_data, + .num_clks = ARRAY_SIZE(exynos4_clk_bulk_data), .max_freq = 1000, + .wait_for_hdr_fifo = 1, .wait_for_reset = 1, .num_bits_resol = 11, + .video_mode_bit = 25, + .pll_stable_bit = 31, + .esc_clken_bit = 28, + .byte_clken_bit = 24, + .tx_req_hsclk_bit = 31, + .lane_esc_clk_bit = 19, + .lane_esc_data_offset = 20, .pll_p_offset = 13, + .pll_m_offset = 4, + .pll_s_offset = 1, + .main_vsa_offset = 22, .reg_values = reg_values, .pll_fin_min = 6, .pll_fin_max = 12, @@ -443,11 +528,24 @@ static const struct samsung_dsim_driver_data exynos4_dsi_driver_data = { static const struct samsung_dsim_driver_data exynos5_dsi_driver_data = { .reg_ofs = exynos_reg_ofs, .plltmr_reg = 0x58, - .num_clks = 2, + .has_legacy_status_reg = 1, + .clk_data = exynos3_clk_bulk_data, + .num_clks = ARRAY_SIZE(exynos3_clk_bulk_data), .max_freq = 1000, + .wait_for_hdr_fifo = 1, .wait_for_reset = 1, .num_bits_resol = 11, + .video_mode_bit = 25, + .pll_stable_bit = 31, + .esc_clken_bit = 28, + .byte_clken_bit = 24, + .tx_req_hsclk_bit = 31, + .lane_esc_clk_bit = 19, + .lane_esc_data_offset = 20, .pll_p_offset = 13, + .pll_m_offset = 4, + .pll_s_offset = 1, + .main_vsa_offset = 22, .reg_values = reg_values, .pll_fin_min = 6, .pll_fin_max = 12, @@ -459,12 +557,25 @@ static const struct samsung_dsim_driver_data exynos5_dsi_driver_data = { static const struct samsung_dsim_driver_data exynos5433_dsi_driver_data = { .reg_ofs = exynos5433_reg_ofs, .plltmr_reg = 0xa0, + .has_legacy_status_reg = 1, .has_clklane_stop = 1, - .num_clks = 5, + .clk_data = exynos5433_clk_bulk_data, + .num_clks = ARRAY_SIZE(exynos5433_clk_bulk_data), .max_freq = 1500, + .wait_for_hdr_fifo = 1, .wait_for_reset = 0, .num_bits_resol = 12, + .video_mode_bit = 25, + .pll_stable_bit = 31, + .esc_clken_bit = 28, + .byte_clken_bit = 24, + .tx_req_hsclk_bit = 31, + .lane_esc_clk_bit = 19, + .lane_esc_data_offset = 20, .pll_p_offset = 13, + .pll_m_offset = 4, + .pll_s_offset = 1, + .main_vsa_offset = 22, .reg_values = exynos5433_reg_values, .pll_fin_min = 6, .pll_fin_max = 12, @@ -476,12 +587,25 @@ static const struct samsung_dsim_driver_data exynos5433_dsi_driver_data = { static const struct samsung_dsim_driver_data exynos5422_dsi_driver_data = { .reg_ofs = exynos5433_reg_ofs, .plltmr_reg = 0xa0, + .has_legacy_status_reg = 1, .has_clklane_stop = 1, - .num_clks = 2, + .clk_data = exynos3_clk_bulk_data, + .num_clks = ARRAY_SIZE(exynos3_clk_bulk_data), .max_freq = 1500, + .wait_for_hdr_fifo = 1, .wait_for_reset = 1, .num_bits_resol = 12, + .video_mode_bit = 25, + .pll_stable_bit = 31, + .esc_clken_bit = 28, + .byte_clken_bit = 24, + .tx_req_hsclk_bit = 31, + .lane_esc_clk_bit = 19, + .lane_esc_data_offset = 20, .pll_p_offset = 13, + .pll_m_offset = 4, + .pll_s_offset = 1, + .main_vsa_offset = 22, .reg_values = exynos5422_reg_values, .pll_fin_min = 6, .pll_fin_max = 12, @@ -490,19 +614,62 @@ static const struct samsung_dsim_driver_data exynos5422_dsi_driver_data = { .min_freq = 500, }; +static const struct samsung_dsim_driver_data exynos7870_dsi_driver_data = { + .reg_ofs = exynos7870_reg_ofs, + .plltmr_reg = 0xa0, + .has_clklane_stop = 1, + .has_sfrctrl = 1, + .clk_data = exynos7870_clk_bulk_data, + .num_clks = ARRAY_SIZE(exynos7870_clk_bulk_data), + .max_freq = 1500, + .wait_for_hdr_fifo = 0, + .wait_for_reset = 1, + .num_bits_resol = 12, + .video_mode_bit = 18, + .pll_stable_bit = 24, + .esc_clken_bit = 16, + .byte_clken_bit = 17, + .tx_req_hsclk_bit = 20, + .lane_esc_clk_bit = 8, + .lane_esc_data_offset = 9, + .pll_p_offset = 13, + .pll_m_offset = 3, + .pll_s_offset = 0, + .main_vsa_offset = 16, + .reg_values = exynos7870_reg_values, + .pll_fin_min = 6, + .pll_fin_max = 12, + .m_min = 41, + .m_max = 125, + .min_freq = 500, +}; + static const struct samsung_dsim_driver_data imx8mm_dsi_driver_data = { .reg_ofs = exynos5433_reg_ofs, .plltmr_reg = 0xa0, + .has_legacy_status_reg = 1, .has_clklane_stop = 1, - .num_clks = 2, + .clk_data = exynos4_clk_bulk_data, + .num_clks = ARRAY_SIZE(exynos4_clk_bulk_data), .max_freq = 2100, + .wait_for_hdr_fifo = 1, .wait_for_reset = 0, .num_bits_resol = 12, + .video_mode_bit = 25, + .pll_stable_bit = 31, + .esc_clken_bit = 28, + .byte_clken_bit = 24, + .tx_req_hsclk_bit = 31, + .lane_esc_clk_bit = 19, + .lane_esc_data_offset = 20, /* * Unlike Exynos, PLL_P(PMS_P) offset 14 is used in i.MX8M Mini/Nano/Plus * downstream driver - drivers/gpu/drm/bridge/sec-dsim.c */ .pll_p_offset = 14, + .pll_m_offset = 4, + .pll_s_offset = 1, + .main_vsa_offset = 22, .reg_values = imx8mm_dsim_reg_values, .pll_fin_min = 2, .pll_fin_max = 30, @@ -518,6 +685,7 @@ samsung_dsim_types[DSIM_TYPE_COUNT] = { [DSIM_TYPE_EXYNOS5410] = &exynos5_dsi_driver_data, [DSIM_TYPE_EXYNOS5422] = &exynos5422_dsi_driver_data, [DSIM_TYPE_EXYNOS5433] = &exynos5433_dsi_driver_data, + [DSIM_TYPE_EXYNOS7870] = &exynos7870_dsi_driver_data, [DSIM_TYPE_IMX8MM] = &imx8mm_dsi_driver_data, [DSIM_TYPE_IMX8MP] = &imx8mm_dsi_driver_data, }; @@ -653,8 +821,9 @@ static unsigned long samsung_dsim_set_pll(struct samsung_dsim *dsi, writel(driver_data->reg_values[PLL_TIMER], dsi->reg_base + driver_data->plltmr_reg); - reg = DSIM_PLL_EN | DSIM_PLL_P(p, driver_data->pll_p_offset) | - DSIM_PLL_M(m) | DSIM_PLL_S(s); + reg = DSIM_PLL_EN | DSIM_PLL(p, driver_data->pll_p_offset) + | DSIM_PLL(m, driver_data->pll_m_offset) + | DSIM_PLL(s, driver_data->pll_s_offset); if (driver_data->has_freqband) { static const unsigned long freq_bands[] = { @@ -682,14 +851,17 @@ static unsigned long samsung_dsim_set_pll(struct samsung_dsim *dsi, samsung_dsim_write(dsi, DSIM_PLLCTRL_REG, reg); - timeout = 1000; + timeout = 3000; do { if (timeout-- == 0) { dev_err(dsi->dev, "PLL failed to stabilize\n"); return 0; } - reg = samsung_dsim_read(dsi, DSIM_STATUS_REG); - } while ((reg & DSIM_PLL_STABLE) == 0); + if (driver_data->has_legacy_status_reg) + reg = samsung_dsim_read(dsi, DSIM_STATUS_REG); + else + reg = samsung_dsim_read(dsi, DSIM_LINK_STATUS_REG); + } while ((reg & BIT(driver_data->pll_stable_bit)) == 0); dsi->hs_clock = fout; @@ -698,6 +870,7 @@ static unsigned long samsung_dsim_set_pll(struct samsung_dsim *dsi, static int samsung_dsim_enable_clock(struct samsung_dsim *dsi) { + const struct samsung_dsim_driver_data *driver_data = dsi->driver_data; unsigned long hs_clk, byte_clk, esc_clk, pix_clk; unsigned long esc_div; u32 reg; @@ -731,15 +904,17 @@ static int samsung_dsim_enable_clock(struct samsung_dsim *dsi) hs_clk, byte_clk, esc_clk); reg = samsung_dsim_read(dsi, DSIM_CLKCTRL_REG); - reg &= ~(DSIM_ESC_PRESCALER_MASK | DSIM_LANE_ESC_CLK_EN_CLK - | DSIM_LANE_ESC_CLK_EN_DATA_MASK | DSIM_PLL_BYPASS - | DSIM_BYTE_CLK_SRC_MASK); - reg |= DSIM_ESC_CLKEN | DSIM_BYTE_CLKEN - | DSIM_ESC_PRESCALER(esc_div) - | DSIM_LANE_ESC_CLK_EN_CLK - | DSIM_LANE_ESC_CLK_EN_DATA(BIT(dsi->lanes) - 1) - | DSIM_BYTE_CLK_SRC(0) - | DSIM_TX_REQUEST_HSCLK; + reg &= ~(DSIM_ESC_PRESCALER_MASK | BIT(driver_data->lane_esc_clk_bit) + | DSIM_LANE_ESC_CLK_EN_DATA_MASK(driver_data->lane_esc_data_offset) + | DSIM_PLL_BYPASS + | DSIM_BYTE_CLK_SRC_MASK); + reg |= BIT(driver_data->esc_clken_bit) | BIT(driver_data->byte_clken_bit) + | DSIM_ESC_PRESCALER(esc_div) + | BIT(driver_data->lane_esc_clk_bit) + | DSIM_LANE_ESC_CLK_EN_DATA(BIT(dsi->lanes) - 1, + driver_data->lane_esc_data_offset) + | DSIM_BYTE_CLK_SRC(0) + | BIT(driver_data->tx_req_hsclk_bit); samsung_dsim_write(dsi, DSIM_CLKCTRL_REG, reg); return 0; @@ -843,11 +1018,14 @@ static void samsung_dsim_set_phy_ctrl(struct samsung_dsim *dsi) static void samsung_dsim_disable_clock(struct samsung_dsim *dsi) { + const struct samsung_dsim_driver_data *driver_data = dsi->driver_data; u32 reg; reg = samsung_dsim_read(dsi, DSIM_CLKCTRL_REG); - reg &= ~(DSIM_LANE_ESC_CLK_EN_CLK | DSIM_LANE_ESC_CLK_EN_DATA_MASK - | DSIM_ESC_CLKEN | DSIM_BYTE_CLKEN); + reg &= ~(BIT(driver_data->lane_esc_clk_bit) + | DSIM_LANE_ESC_CLK_EN_DATA_MASK(driver_data->lane_esc_data_offset) + | BIT(driver_data->esc_clken_bit) + | BIT(driver_data->byte_clken_bit)); samsung_dsim_write(dsi, DSIM_CLKCTRL_REG, reg); reg = samsung_dsim_read(dsi, DSIM_PLLCTRL_REG); @@ -891,7 +1069,7 @@ static int samsung_dsim_init_link(struct samsung_dsim *dsi) * mode, otherwise it will support command mode. */ if (dsi->mode_flags & MIPI_DSI_MODE_VIDEO) { - reg |= DSIM_VIDEO_MODE; + reg |= BIT(driver_data->video_mode_bit); /* * The user manual describes that following bits are ignored in @@ -962,7 +1140,10 @@ static int samsung_dsim_init_link(struct samsung_dsim *dsi) return -EFAULT; } - reg = samsung_dsim_read(dsi, DSIM_STATUS_REG); + if (driver_data->has_legacy_status_reg) + reg = samsung_dsim_read(dsi, DSIM_STATUS_REG); + else + reg = samsung_dsim_read(dsi, DSIM_DPHY_STATUS_REG); if ((reg & DSIM_STOP_STATE_DAT(lanes_mask)) != DSIM_STOP_STATE_DAT(lanes_mask)) continue; @@ -983,6 +1164,7 @@ static void samsung_dsim_set_display_mode(struct samsung_dsim *dsi) { struct drm_display_mode *m = &dsi->mode; unsigned int num_bits_resol = dsi->driver_data->num_bits_resol; + unsigned int main_vsa_offset = dsi->driver_data->main_vsa_offset; u32 reg; if (dsi->mode_flags & MIPI_DSI_MODE_VIDEO) { @@ -1009,7 +1191,7 @@ static void samsung_dsim_set_display_mode(struct samsung_dsim *dsi) reg = DSIM_MAIN_HFP(hfp) | DSIM_MAIN_HBP(hbp); samsung_dsim_write(dsi, DSIM_MHPORCH_REG, reg); - reg = DSIM_MAIN_VSA(m->vsync_end - m->vsync_start) + reg = DSIM_MAIN_VSA(m->vsync_end - m->vsync_start, main_vsa_offset) | DSIM_MAIN_HSA(hsa); samsung_dsim_write(dsi, DSIM_MSYNC_REG, reg); } @@ -1023,6 +1205,7 @@ static void samsung_dsim_set_display_mode(struct samsung_dsim *dsi) static void samsung_dsim_set_display_enable(struct samsung_dsim *dsi, bool enable) { + const struct samsung_dsim_driver_data *driver_data = dsi->driver_data; u32 reg; reg = samsung_dsim_read(dsi, DSIM_MDRESOL_REG); @@ -1031,6 +1214,15 @@ static void samsung_dsim_set_display_enable(struct samsung_dsim *dsi, bool enabl else reg &= ~DSIM_MAIN_STAND_BY; samsung_dsim_write(dsi, DSIM_MDRESOL_REG, reg); + + if (driver_data->has_sfrctrl) { + reg = samsung_dsim_read(dsi, DSIM_SFRCTRL_REG); + if (enable) + reg |= DSIM_SFR_CTRL_STAND_BY; + else + reg &= ~DSIM_SFR_CTRL_STAND_BY; + samsung_dsim_write(dsi, DSIM_SFRCTRL_REG, reg); + } } static int samsung_dsim_wait_for_hdr_fifo(struct samsung_dsim *dsi) @@ -1087,6 +1279,7 @@ static void samsung_dsim_send_to_fifo(struct samsung_dsim *dsi, { struct device *dev = dsi->dev; struct mipi_dsi_packet *pkt = &xfer->packet; + const struct samsung_dsim_driver_data *driver_data = dsi->driver_data; const u8 *payload = pkt->payload + xfer->tx_done; u16 length = pkt->payload_length - xfer->tx_done; bool first = !xfer->tx_done; @@ -1127,9 +1320,11 @@ static void samsung_dsim_send_to_fifo(struct samsung_dsim *dsi, return; reg = get_unaligned_le32(pkt->header); - if (samsung_dsim_wait_for_hdr_fifo(dsi)) { - dev_err(dev, "waiting for header FIFO timed out\n"); - return; + if (driver_data->wait_for_hdr_fifo) { + if (samsung_dsim_wait_for_hdr_fifo(dsi)) { + dev_err(dev, "waiting for header FIFO timed out\n"); + return; + } } if (NEQV(xfer->flags & MIPI_DSI_MSG_USE_LPM, @@ -1922,7 +2117,7 @@ int samsung_dsim_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct samsung_dsim *dsi; - int ret, i; + int ret; dsi = devm_drm_bridge_alloc(dev, struct samsung_dsim, bridge, &samsung_dsim_bridge_funcs); if (IS_ERR(dsi)) @@ -1946,23 +2141,11 @@ int samsung_dsim_probe(struct platform_device *pdev) if (ret) return dev_err_probe(dev, ret, "failed to get regulators\n"); - dsi->clks = devm_kcalloc(dev, dsi->driver_data->num_clks, - sizeof(*dsi->clks), GFP_KERNEL); - if (!dsi->clks) - return -ENOMEM; - - for (i = 0; i < dsi->driver_data->num_clks; i++) { - dsi->clks[i] = devm_clk_get(dev, clk_names[i]); - if (IS_ERR(dsi->clks[i])) { - if (strcmp(clk_names[i], "sclk_mipi") == 0) { - dsi->clks[i] = devm_clk_get(dev, OLD_SCLK_MIPI_CLK_NAME); - if (!IS_ERR(dsi->clks[i])) - continue; - } - - dev_info(dev, "failed to get the clock: %s\n", clk_names[i]); - return PTR_ERR(dsi->clks[i]); - } + ret = devm_clk_bulk_get(dev, dsi->driver_data->num_clks, + dsi->driver_data->clk_data); + if (ret) { + dev_err(dev, "failed to get clocks in bulk (%d)\n", ret); + return ret; } dsi->reg_base = devm_platform_ioremap_resource(pdev, 0); @@ -2035,7 +2218,7 @@ static int samsung_dsim_suspend(struct device *dev) { struct samsung_dsim *dsi = dev_get_drvdata(dev); const struct samsung_dsim_driver_data *driver_data = dsi->driver_data; - int ret, i; + int ret; usleep_range(10000, 20000); @@ -2051,8 +2234,7 @@ static int samsung_dsim_suspend(struct device *dev) phy_power_off(dsi->phy); - for (i = driver_data->num_clks - 1; i > -1; i--) - clk_disable_unprepare(dsi->clks[i]); + clk_bulk_disable_unprepare(driver_data->num_clks, driver_data->clk_data); ret = regulator_bulk_disable(ARRAY_SIZE(dsi->supplies), dsi->supplies); if (ret < 0) @@ -2065,7 +2247,7 @@ static int samsung_dsim_resume(struct device *dev) { struct samsung_dsim *dsi = dev_get_drvdata(dev); const struct samsung_dsim_driver_data *driver_data = dsi->driver_data; - int ret, i; + int ret; ret = regulator_bulk_enable(ARRAY_SIZE(dsi->supplies), dsi->supplies); if (ret < 0) { @@ -2073,11 +2255,9 @@ static int samsung_dsim_resume(struct device *dev) return ret; } - for (i = 0; i < driver_data->num_clks; i++) { - ret = clk_prepare_enable(dsi->clks[i]); - if (ret < 0) - goto err_clk; - } + ret = clk_bulk_prepare_enable(driver_data->num_clks, driver_data->clk_data); + if (ret < 0) + goto err_clk; ret = phy_power_on(dsi->phy); if (ret < 0) { @@ -2088,8 +2268,7 @@ static int samsung_dsim_resume(struct device *dev) return 0; err_clk: - while (--i > -1) - clk_disable_unprepare(dsi->clks[i]); + clk_bulk_disable_unprepare(driver_data->num_clks, driver_data->clk_data); regulator_bulk_disable(ARRAY_SIZE(dsi->supplies), dsi->supplies); return ret; diff --git a/drivers/gpu/drm/bridge/simple-bridge.c b/drivers/gpu/drm/bridge/simple-bridge.c index 1f16d568bcc4..e4d0bc2200f8 100644 --- a/drivers/gpu/drm/bridge/simple-bridge.c +++ b/drivers/gpu/drm/bridge/simple-bridge.c @@ -267,6 +267,11 @@ static const struct of_device_id simple_bridge_match[] = { .connector_type = DRM_MODE_CONNECTOR_HDMIA, }, }, { + .compatible = "realtek,rtd2171", + .data = &(const struct simple_bridge_info) { + .connector_type = DRM_MODE_CONNECTOR_HDMIA, + }, + }, { .compatible = "ti,opa362", .data = &(const struct simple_bridge_info) { .connector_type = DRM_MODE_CONNECTOR_Composite, diff --git a/drivers/gpu/drm/bridge/synopsys/Kconfig b/drivers/gpu/drm/bridge/synopsys/Kconfig index f3ab2f985f8c..2c5e532410de 100644 --- a/drivers/gpu/drm/bridge/synopsys/Kconfig +++ b/drivers/gpu/drm/bridge/synopsys/Kconfig @@ -1,4 +1,11 @@ # SPDX-License-Identifier: GPL-2.0-only +config DRM_DW_DP + tristate + select DRM_DISPLAY_HELPER + select DRM_DISPLAY_DP_HELPER + select DRM_KMS_HELPER + select REGMAP_MMIO + config DRM_DW_HDMI tristate select DRM_DISPLAY_HDMI_HELPER diff --git a/drivers/gpu/drm/bridge/synopsys/Makefile b/drivers/gpu/drm/bridge/synopsys/Makefile index 9dc376d220ad..4dada44029ac 100644 --- a/drivers/gpu/drm/bridge/synopsys/Makefile +++ b/drivers/gpu/drm/bridge/synopsys/Makefile @@ -1,4 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only +obj-$(CONFIG_DRM_DW_DP) += dw-dp.o obj-$(CONFIG_DRM_DW_HDMI) += dw-hdmi.o obj-$(CONFIG_DRM_DW_HDMI_AHB_AUDIO) += dw-hdmi-ahb-audio.o obj-$(CONFIG_DRM_DW_HDMI_GP_AUDIO) += dw-hdmi-gp-audio.o diff --git a/drivers/gpu/drm/bridge/synopsys/dw-dp.c b/drivers/gpu/drm/bridge/synopsys/dw-dp.c new file mode 100644 index 000000000000..9bbfe8da3de0 --- /dev/null +++ b/drivers/gpu/drm/bridge/synopsys/dw-dp.c @@ -0,0 +1,2095 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Synopsys DesignWare Cores DisplayPort Transmitter Controller + * + * Copyright (c) 2025 Rockchip Electronics Co., Ltd. + * + * Author: Andy Yan <andy.yan@rock-chips.com> + */ +#include <linux/bitfield.h> +#include <linux/clk.h> +#include <linux/iopoll.h> +#include <linux/irq.h> +#include <linux/media-bus-format.h> +#include <linux/of_device.h> +#include <linux/platform_device.h> +#include <linux/regmap.h> +#include <linux/reset.h> +#include <linux/phy/phy.h> +#include <linux/unaligned.h> + +#include <drm/bridge/dw_dp.h> +#include <drm/drm_atomic_helper.h> +#include <drm/drm_bridge.h> +#include <drm/drm_bridge_connector.h> +#include <drm/display/drm_dp_helper.h> +#include <drm/drm_edid.h> +#include <drm/drm_of.h> +#include <drm/drm_print.h> +#include <drm/drm_probe_helper.h> +#include <drm/drm_simple_kms_helper.h> + +#define DW_DP_VERSION_NUMBER 0x0000 +#define DW_DP_VERSION_TYPE 0x0004 +#define DW_DP_ID 0x0008 + +#define DW_DP_CONFIG_REG1 0x0100 +#define DW_DP_CONFIG_REG2 0x0104 +#define DW_DP_CONFIG_REG3 0x0108 + +#define DW_DP_CCTL 0x0200 +#define FORCE_HPD BIT(4) +#define DEFAULT_FAST_LINK_TRAIN_EN BIT(2) +#define ENHANCE_FRAMING_EN BIT(1) +#define SCRAMBLE_DIS BIT(0) +#define DW_DP_SOFT_RESET_CTRL 0x0204 +#define VIDEO_RESET BIT(5) +#define AUX_RESET BIT(4) +#define AUDIO_SAMPLER_RESET BIT(3) +#define HDCP_MODULE_RESET BIT(2) +#define PHY_SOFT_RESET BIT(1) +#define CONTROLLER_RESET BIT(0) + +#define DW_DP_VSAMPLE_CTRL 0x0300 +#define PIXEL_MODE_SELECT GENMASK(22, 21) +#define VIDEO_MAPPING GENMASK(20, 16) +#define VIDEO_STREAM_ENABLE BIT(5) + +#define DW_DP_VSAMPLE_STUFF_CTRL1 0x0304 + +#define DW_DP_VSAMPLE_STUFF_CTRL2 0x0308 + +#define DW_DP_VINPUT_POLARITY_CTRL 0x030c +#define DE_IN_POLARITY BIT(2) +#define HSYNC_IN_POLARITY BIT(1) +#define VSYNC_IN_POLARITY BIT(0) + +#define DW_DP_VIDEO_CONFIG1 0x0310 +#define HACTIVE GENMASK(31, 16) +#define HBLANK GENMASK(15, 2) +#define I_P BIT(1) +#define R_V_BLANK_IN_OSC BIT(0) + +#define DW_DP_VIDEO_CONFIG2 0x0314 +#define VBLANK GENMASK(31, 16) +#define VACTIVE GENMASK(15, 0) + +#define DW_DP_VIDEO_CONFIG3 0x0318 +#define H_SYNC_WIDTH GENMASK(31, 16) +#define H_FRONT_PORCH GENMASK(15, 0) + +#define DW_DP_VIDEO_CONFIG4 0x031c +#define V_SYNC_WIDTH GENMASK(31, 16) +#define V_FRONT_PORCH GENMASK(15, 0) + +#define DW_DP_VIDEO_CONFIG5 0x0320 +#define INIT_THRESHOLD_HI GENMASK(22, 21) +#define AVERAGE_BYTES_PER_TU_FRAC GENMASK(19, 16) +#define INIT_THRESHOLD GENMASK(13, 7) +#define AVERAGE_BYTES_PER_TU GENMASK(6, 0) + +#define DW_DP_VIDEO_MSA1 0x0324 +#define VSTART GENMASK(31, 16) +#define HSTART GENMASK(15, 0) + +#define DW_DP_VIDEO_MSA2 0x0328 +#define MISC0 GENMASK(31, 24) + +#define DW_DP_VIDEO_MSA3 0x032c +#define MISC1 GENMASK(31, 24) + +#define DW_DP_VIDEO_HBLANK_INTERVAL 0x0330 +#define HBLANK_INTERVAL_EN BIT(16) +#define HBLANK_INTERVAL GENMASK(15, 0) + +#define DW_DP_AUD_CONFIG1 0x0400 +#define AUDIO_TIMESTAMP_VERSION_NUM GENMASK(29, 24) +#define AUDIO_PACKET_ID GENMASK(23, 16) +#define AUDIO_MUTE BIT(15) +#define NUM_CHANNELS GENMASK(14, 12) +#define HBR_MODE_ENABLE BIT(10) +#define AUDIO_DATA_WIDTH GENMASK(9, 5) +#define AUDIO_DATA_IN_EN GENMASK(4, 1) +#define AUDIO_INF_SELECT BIT(0) + +#define DW_DP_SDP_VERTICAL_CTRL 0x0500 +#define EN_VERTICAL_SDP BIT(2) +#define EN_AUDIO_STREAM_SDP BIT(1) +#define EN_AUDIO_TIMESTAMP_SDP BIT(0) +#define DW_DP_SDP_HORIZONTAL_CTRL 0x0504 +#define EN_HORIZONTAL_SDP BIT(2) +#define DW_DP_SDP_STATUS_REGISTER 0x0508 +#define DW_DP_SDP_MANUAL_CTRL 0x050c +#define DW_DP_SDP_STATUS_EN 0x0510 + +#define DW_DP_SDP_REGISTER_BANK 0x0600 +#define SDP_REGS GENMASK(31, 0) + +#define DW_DP_PHYIF_CTRL 0x0a00 +#define PHY_WIDTH BIT(25) +#define PHY_POWERDOWN GENMASK(20, 17) +#define PHY_BUSY GENMASK(15, 12) +#define SSC_DIS BIT(16) +#define XMIT_ENABLE GENMASK(11, 8) +#define PHY_LANES GENMASK(7, 6) +#define PHY_RATE GENMASK(5, 4) +#define TPS_SEL GENMASK(3, 0) + +#define DW_DP_PHY_TX_EQ 0x0a04 +#define DW_DP_CUSTOMPAT0 0x0a08 +#define DW_DP_CUSTOMPAT1 0x0a0c +#define DW_DP_CUSTOMPAT2 0x0a10 +#define DW_DP_HBR2_COMPLIANCE_SCRAMBLER_RESET 0x0a14 +#define DW_DP_PHYIF_PWRDOWN_CTRL 0x0a18 + +#define DW_DP_AUX_CMD 0x0b00 +#define AUX_CMD_TYPE GENMASK(31, 28) +#define AUX_ADDR GENMASK(27, 8) +#define I2C_ADDR_ONLY BIT(4) +#define AUX_LEN_REQ GENMASK(3, 0) + +#define DW_DP_AUX_STATUS 0x0b04 +#define AUX_TIMEOUT BIT(17) +#define AUX_BYTES_READ GENMASK(23, 19) +#define AUX_STATUS GENMASK(7, 4) + +#define DW_DP_AUX_DATA0 0x0b08 +#define DW_DP_AUX_DATA1 0x0b0c +#define DW_DP_AUX_DATA2 0x0b10 +#define DW_DP_AUX_DATA3 0x0b14 + +#define DW_DP_GENERAL_INTERRUPT 0x0d00 +#define VIDEO_FIFO_OVERFLOW_STREAM0 BIT(6) +#define AUDIO_FIFO_OVERFLOW_STREAM0 BIT(5) +#define SDP_EVENT_STREAM0 BIT(4) +#define AUX_CMD_INVALID BIT(3) +#define HDCP_EVENT BIT(2) +#define AUX_REPLY_EVENT BIT(1) +#define HPD_EVENT BIT(0) + +#define DW_DP_GENERAL_INTERRUPT_ENABLE 0x0d04 +#define HDCP_EVENT_EN BIT(2) +#define AUX_REPLY_EVENT_EN BIT(1) +#define HPD_EVENT_EN BIT(0) + +#define DW_DP_HPD_STATUS 0x0d08 +#define HPD_STATE GENMASK(11, 9) +#define HPD_STATUS BIT(8) +#define HPD_HOT_UNPLUG BIT(2) +#define HPD_HOT_PLUG BIT(1) +#define HPD_IRQ BIT(0) + +#define DW_DP_HPD_INTERRUPT_ENABLE 0x0d0c +#define HPD_UNPLUG_ERR_EN BIT(3) +#define HPD_UNPLUG_EN BIT(2) +#define HPD_PLUG_EN BIT(1) +#define HPD_IRQ_EN BIT(0) + +#define DW_DP_HDCP_CFG 0x0e00 +#define DPCD12PLUS BIT(7) +#define CP_IRQ BIT(6) +#define BYPENCRYPTION BIT(5) +#define HDCP_LOCK BIT(4) +#define ENCRYPTIONDISABLE BIT(3) +#define ENABLE_HDCP_13 BIT(2) +#define ENABLE_HDCP BIT(1) + +#define DW_DP_HDCP_OBS 0x0e04 +#define HDCP22_RE_AUTHENTICATION_REQ BIT(31) +#define HDCP22_AUTHENTICATION_FAILED BIT(30) +#define HDCP22_AUTHENTICATION_SUCCESS BIT(29) +#define HDCP22_CAPABLE_SINK BIT(28) +#define HDCP22_SINK_CAP_CHECK_COMPLETE BIT(27) +#define HDCP22_STATE GENMASK(26, 24) +#define HDCP22_BOOTED BIT(23) +#define HDCP13_BSTATUS GENMASK(22, 19) +#define REPEATER BIT(18) +#define HDCP_CAPABLE BIT(17) +#define STATEE GENMASK(16, 14) +#define STATEOEG GENMASK(13, 11) +#define STATER GENMASK(10, 8) +#define STATEA GENMASK(7, 4) +#define SUBSTATEA GENMASK(3, 1) +#define HDCPENGAGED BIT(0) + +#define DW_DP_HDCP_APIINTCLR 0x0e08 +#define DW_DP_HDCP_APIINTSTAT 0x0e0c +#define DW_DP_HDCP_APIINTMSK 0x0e10 +#define HDCP22_GPIOINT BIT(8) +#define HDCP_ENGAGED BIT(7) +#define HDCP_FAILED BIT(6) +#define KSVSHA1CALCDONEINT BIT(5) +#define AUXRESPNACK7TIMES BIT(4) +#define AUXRESPTIMEOUT BIT(3) +#define AUXRESPDEFER7TIMES BIT(2) +#define KSVACCESSINT BIT(0) + +#define DW_DP_HDCP_KSVMEMCTRL 0x0e18 +#define KSVSHA1STATUS BIT(4) +#define KSVMEMACCESS BIT(1) +#define KSVMEMREQUEST BIT(0) + +#define DW_DP_HDCP_REG_BKSV0 0x3600 +#define DW_DP_HDCP_REG_BKSV1 0x3604 +#define DW_DP_HDCP_REG_ANCONF 0x3608 +#define AN_BYPASS BIT(0) + +#define DW_DP_HDCP_REG_AN0 0x360c +#define DW_DP_HDCP_REG_AN1 0x3610 +#define DW_DP_HDCP_REG_RMLCTL 0x3614 +#define ODPK_DECRYPT_ENABLE BIT(0) + +#define DW_DP_HDCP_REG_RMLSTS 0x3618 +#define IDPK_WR_OK_STS BIT(6) +#define IDPK_DATA_INDEX GENMASK(5, 0) +#define DW_DP_HDCP_REG_SEED 0x361c +#define DW_DP_HDCP_REG_DPK0 0x3620 +#define DW_DP_HDCP_REG_DPK1 0x3624 +#define DW_DP_HDCP22_GPIOSTS 0x3628 +#define DW_DP_HDCP22_GPIOCHNGSTS 0x362c +#define DW_DP_HDCP_REG_DPK_CRC 0x3630 + +#define DW_DP_MAX_REGISTER DW_DP_HDCP_REG_DPK_CRC + +#define SDP_REG_BANK_SIZE 16 + +struct dw_dp_link_caps { + bool enhanced_framing; + bool tps3_supported; + bool tps4_supported; + bool fast_training; + bool channel_coding; + bool ssc; +}; + +struct dw_dp_link_train_set { + unsigned int voltage_swing[4]; + unsigned int pre_emphasis[4]; + bool voltage_max_reached[4]; + bool pre_max_reached[4]; +}; + +struct dw_dp_link_train { + struct dw_dp_link_train_set adjust; + bool clock_recovered; + bool channel_equalized; +}; + +struct dw_dp_link { + u8 dpcd[DP_RECEIVER_CAP_SIZE]; + unsigned char revision; + unsigned int rate; + unsigned int lanes; + u8 sink_count; + u8 vsc_sdp_supported; + struct dw_dp_link_caps caps; + struct dw_dp_link_train train; + struct drm_dp_desc desc; +}; + +struct dw_dp_bridge_state { + struct drm_bridge_state base; + struct drm_display_mode mode; + u8 video_mapping; + u8 color_format; + u8 bpc; + u8 bpp; +}; + +struct dw_dp_sdp { + struct dp_sdp base; + unsigned long flags; +}; + +struct dw_dp_hotplug { + bool long_hpd; +}; + +struct dw_dp { + struct drm_bridge bridge; + struct device *dev; + struct regmap *regmap; + struct phy *phy; + struct clk *apb_clk; + struct clk *aux_clk; + struct clk *i2s_clk; + struct clk *spdif_clk; + struct clk *hdcp_clk; + struct reset_control *rstc; + struct completion complete; + int irq; + struct work_struct hpd_work; + struct dw_dp_hotplug hotplug; + /* Serialize hpd status access */ + struct mutex irq_lock; + + struct drm_dp_aux aux; + + struct dw_dp_link link; + struct dw_dp_plat_data plat_data; + u8 pixel_mode; + + DECLARE_BITMAP(sdp_reg_bank, SDP_REG_BANK_SIZE); +}; + +enum { + DW_DP_RGB_6BIT, + DW_DP_RGB_8BIT, + DW_DP_RGB_10BIT, + DW_DP_RGB_12BIT, + DW_DP_RGB_16BIT, + DW_DP_YCBCR444_8BIT, + DW_DP_YCBCR444_10BIT, + DW_DP_YCBCR444_12BIT, + DW_DP_YCBCR444_16BIT, + DW_DP_YCBCR422_8BIT, + DW_DP_YCBCR422_10BIT, + DW_DP_YCBCR422_12BIT, + DW_DP_YCBCR422_16BIT, + DW_DP_YCBCR420_8BIT, + DW_DP_YCBCR420_10BIT, + DW_DP_YCBCR420_12BIT, + DW_DP_YCBCR420_16BIT, +}; + +enum { + DW_DP_MP_SINGLE_PIXEL, + DW_DP_MP_DUAL_PIXEL, + DW_DP_MP_QUAD_PIXEL, +}; + +enum { + DW_DP_SDP_VERTICAL_INTERVAL = BIT(0), + DW_DP_SDP_HORIZONTAL_INTERVAL = BIT(1), +}; + +enum { + DW_DP_HPD_STATE_IDLE, + DW_DP_HPD_STATE_UNPLUG, + DP_DP_HPD_STATE_TIMEOUT = 4, + DW_DP_HPD_STATE_PLUG = 7 +}; + +enum { + DW_DP_PHY_PATTERN_NONE, + DW_DP_PHY_PATTERN_TPS_1, + DW_DP_PHY_PATTERN_TPS_2, + DW_DP_PHY_PATTERN_TPS_3, + DW_DP_PHY_PATTERN_TPS_4, + DW_DP_PHY_PATTERN_SERM, + DW_DP_PHY_PATTERN_PBRS7, + DW_DP_PHY_PATTERN_CUSTOM_80BIT, + DW_DP_PHY_PATTERN_CP2520_1, + DW_DP_PHY_PATTERN_CP2520_2, +}; + +struct dw_dp_output_format { + u32 bus_format; + u32 color_format; + u8 video_mapping; + u8 bpc; + u8 bpp; +}; + +#define to_dw_dp_bridge_state(s) container_of(s, struct dw_dp_bridge_state, base) + +static const struct dw_dp_output_format dw_dp_output_formats[] = { + { MEDIA_BUS_FMT_RGB101010_1X30, DRM_COLOR_FORMAT_RGB444, DW_DP_RGB_10BIT, 10, 30 }, + { MEDIA_BUS_FMT_RGB888_1X24, DRM_COLOR_FORMAT_RGB444, DW_DP_RGB_8BIT, 8, 24 }, + { MEDIA_BUS_FMT_YUV10_1X30, DRM_COLOR_FORMAT_YCBCR444, DW_DP_YCBCR444_10BIT, 10, 30 }, + { MEDIA_BUS_FMT_YUV8_1X24, DRM_COLOR_FORMAT_YCBCR444, DW_DP_YCBCR444_8BIT, 8, 24}, + { MEDIA_BUS_FMT_YUYV10_1X20, DRM_COLOR_FORMAT_YCBCR422, DW_DP_YCBCR422_10BIT, 10, 20 }, + { MEDIA_BUS_FMT_YUYV8_1X16, DRM_COLOR_FORMAT_YCBCR422, DW_DP_YCBCR422_8BIT, 8, 16 }, + { MEDIA_BUS_FMT_UYYVYY10_0_5X30, DRM_COLOR_FORMAT_YCBCR420, DW_DP_YCBCR420_10BIT, 10, 15 }, + { MEDIA_BUS_FMT_UYYVYY8_0_5X24, DRM_COLOR_FORMAT_YCBCR420, DW_DP_YCBCR420_8BIT, 8, 12 }, + { MEDIA_BUS_FMT_RGB666_1X24_CPADHI, DRM_COLOR_FORMAT_RGB444, DW_DP_RGB_6BIT, 6, 18 }, +}; + +static const struct dw_dp_output_format *dw_dp_get_output_format(u32 bus_format) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(dw_dp_output_formats); i++) + if (dw_dp_output_formats[i].bus_format == bus_format) + return &dw_dp_output_formats[i]; + + return NULL; +} + +static inline struct dw_dp *bridge_to_dp(struct drm_bridge *b) +{ + return container_of(b, struct dw_dp, bridge); +} + +static struct dw_dp_bridge_state *dw_dp_get_bridge_state(struct dw_dp *dp) +{ + struct dw_dp_bridge_state *dw_bridge_state; + struct drm_bridge_state *state; + + state = drm_priv_to_bridge_state(dp->bridge.base.state); + if (!state) + return NULL; + + dw_bridge_state = to_dw_dp_bridge_state(state); + if (!dw_bridge_state) + return NULL; + + return dw_bridge_state; +} + +static inline void dw_dp_phy_set_pattern(struct dw_dp *dp, u32 pattern) +{ + regmap_update_bits(dp->regmap, DW_DP_PHYIF_CTRL, TPS_SEL, + FIELD_PREP(TPS_SEL, pattern)); +} + +static void dw_dp_phy_xmit_enable(struct dw_dp *dp, u32 lanes) +{ + u32 xmit_enable; + + switch (lanes) { + case 4: + case 2: + case 1: + xmit_enable = GENMASK(lanes - 1, 0); + break; + case 0: + default: + xmit_enable = 0; + break; + } + + regmap_update_bits(dp->regmap, DW_DP_PHYIF_CTRL, XMIT_ENABLE, + FIELD_PREP(XMIT_ENABLE, xmit_enable)); +} + +static bool dw_dp_bandwidth_ok(struct dw_dp *dp, + const struct drm_display_mode *mode, u32 bpp, + unsigned int lanes, unsigned int rate) +{ + u32 max_bw, req_bw; + + req_bw = mode->clock * bpp / 8; + max_bw = lanes * rate; + if (req_bw > max_bw) + return false; + + return true; +} + +static bool dw_dp_hpd_detect(struct dw_dp *dp) +{ + u32 value; + + regmap_read(dp->regmap, DW_DP_HPD_STATUS, &value); + + return FIELD_GET(HPD_STATE, value) == DW_DP_HPD_STATE_PLUG; +} + +static void dw_dp_link_caps_reset(struct dw_dp_link_caps *caps) +{ + caps->enhanced_framing = false; + caps->tps3_supported = false; + caps->tps4_supported = false; + caps->fast_training = false; + caps->channel_coding = false; +} + +static void dw_dp_link_reset(struct dw_dp_link *link) +{ + link->vsc_sdp_supported = 0; + link->sink_count = 0; + link->revision = 0; + link->rate = 0; + link->lanes = 0; + + dw_dp_link_caps_reset(&link->caps); + memset(link->dpcd, 0, sizeof(link->dpcd)); +} + +static int dw_dp_link_parse(struct dw_dp *dp, struct drm_connector *connector) +{ + struct dw_dp_link *link = &dp->link; + int ret; + + dw_dp_link_reset(link); + + ret = drm_dp_read_dpcd_caps(&dp->aux, link->dpcd); + if (ret < 0) + return ret; + + drm_dp_read_desc(&dp->aux, &link->desc, drm_dp_is_branch(link->dpcd)); + + if (drm_dp_read_sink_count_cap(connector, link->dpcd, &link->desc)) { + ret = drm_dp_read_sink_count(&dp->aux); + if (ret < 0) + return ret; + + link->sink_count = ret; + + /* Dongle connected, but no display */ + if (!link->sink_count) + return -ENODEV; + } + + link->vsc_sdp_supported = drm_dp_vsc_sdp_supported(&dp->aux, link->dpcd); + + link->revision = link->dpcd[DP_DPCD_REV]; + link->rate = min_t(u32, min(dp->plat_data.max_link_rate, + dp->phy->attrs.max_link_rate * 100), + drm_dp_max_link_rate(link->dpcd)); + link->lanes = min_t(u8, phy_get_bus_width(dp->phy), + drm_dp_max_lane_count(link->dpcd)); + + link->caps.enhanced_framing = drm_dp_enhanced_frame_cap(link->dpcd); + link->caps.tps3_supported = drm_dp_tps3_supported(link->dpcd); + link->caps.tps4_supported = drm_dp_tps4_supported(link->dpcd); + link->caps.fast_training = drm_dp_fast_training_cap(link->dpcd); + link->caps.channel_coding = drm_dp_channel_coding_supported(link->dpcd); + link->caps.ssc = !!(link->dpcd[DP_MAX_DOWNSPREAD] & DP_MAX_DOWNSPREAD_0_5); + + return 0; +} + +static int dw_dp_link_train_update_vs_emph(struct dw_dp *dp) +{ + struct dw_dp_link *link = &dp->link; + struct dw_dp_link_train_set *train_set = &link->train.adjust; + unsigned int lanes = dp->link.lanes; + union phy_configure_opts phy_cfg; + unsigned int *vs, *pe; + int i, ret; + u8 buf[4]; + + vs = train_set->voltage_swing; + pe = train_set->pre_emphasis; + + for (i = 0; i < lanes; i++) { + phy_cfg.dp.voltage[i] = vs[i]; + phy_cfg.dp.pre[i] = pe[i]; + } + + phy_cfg.dp.set_lanes = false; + phy_cfg.dp.set_rate = false; + phy_cfg.dp.set_voltages = true; + + ret = phy_configure(dp->phy, &phy_cfg); + if (ret) + return ret; + + for (i = 0; i < lanes; i++) { + buf[i] = (vs[i] << DP_TRAIN_VOLTAGE_SWING_SHIFT) | + (pe[i] << DP_TRAIN_PRE_EMPHASIS_SHIFT); + if (train_set->voltage_max_reached[i]) + buf[i] |= DP_TRAIN_MAX_SWING_REACHED; + if (train_set->pre_max_reached[i]) + buf[i] |= DP_TRAIN_MAX_PRE_EMPHASIS_REACHED; + } + + ret = drm_dp_dpcd_write(&dp->aux, DP_TRAINING_LANE0_SET, buf, lanes); + if (ret < 0) + return ret; + + return 0; +} + +static int dw_dp_phy_configure(struct dw_dp *dp, unsigned int rate, + unsigned int lanes, bool ssc) +{ + union phy_configure_opts phy_cfg; + int ret; + + /* Move PHY to P3 */ + regmap_update_bits(dp->regmap, DW_DP_PHYIF_CTRL, PHY_POWERDOWN, + FIELD_PREP(PHY_POWERDOWN, 0x3)); + + phy_cfg.dp.lanes = lanes; + phy_cfg.dp.link_rate = rate / 100; + phy_cfg.dp.ssc = ssc; + phy_cfg.dp.set_lanes = true; + phy_cfg.dp.set_rate = true; + phy_cfg.dp.set_voltages = false; + ret = phy_configure(dp->phy, &phy_cfg); + if (ret) + return ret; + + regmap_update_bits(dp->regmap, DW_DP_PHYIF_CTRL, PHY_LANES, + FIELD_PREP(PHY_LANES, lanes / 2)); + + /* Move PHY to P0 */ + regmap_update_bits(dp->regmap, DW_DP_PHYIF_CTRL, PHY_POWERDOWN, + FIELD_PREP(PHY_POWERDOWN, 0x0)); + + dw_dp_phy_xmit_enable(dp, lanes); + + return 0; +} + +static int dw_dp_link_configure(struct dw_dp *dp) +{ + struct dw_dp_link *link = &dp->link; + u8 buf[2]; + int ret; + + ret = dw_dp_phy_configure(dp, link->rate, link->lanes, link->caps.ssc); + if (ret) + return ret; + + buf[0] = drm_dp_link_rate_to_bw_code(link->rate); + buf[1] = link->lanes; + + if (link->caps.enhanced_framing) { + buf[1] |= DP_LANE_COUNT_ENHANCED_FRAME_EN; + regmap_update_bits(dp->regmap, DW_DP_CCTL, ENHANCE_FRAMING_EN, + FIELD_PREP(ENHANCE_FRAMING_EN, 1)); + } else { + regmap_update_bits(dp->regmap, DW_DP_CCTL, ENHANCE_FRAMING_EN, + FIELD_PREP(ENHANCE_FRAMING_EN, 0)); + } + + ret = drm_dp_dpcd_write(&dp->aux, DP_LINK_BW_SET, buf, sizeof(buf)); + if (ret < 0) + return ret; + + buf[0] = link->caps.ssc ? DP_SPREAD_AMP_0_5 : 0; + buf[1] = link->caps.channel_coding ? DP_SET_ANSI_8B10B : 0; + + ret = drm_dp_dpcd_write(&dp->aux, DP_DOWNSPREAD_CTRL, buf, sizeof(buf)); + if (ret < 0) + return ret; + + return 0; +} + +static void dw_dp_link_train_init(struct dw_dp_link_train *train) +{ + struct dw_dp_link_train_set *adj = &train->adjust; + unsigned int i; + + for (i = 0; i < 4; i++) { + adj->voltage_swing[i] = 0; + adj->pre_emphasis[i] = 0; + adj->voltage_max_reached[i] = false; + adj->pre_max_reached[i] = false; + } + + train->clock_recovered = false; + train->channel_equalized = false; +} + +static bool dw_dp_link_train_valid(const struct dw_dp_link_train *train) +{ + return train->clock_recovered && train->channel_equalized; +} + +static int dw_dp_link_train_set_pattern(struct dw_dp *dp, u32 pattern) +{ + u8 buf = 0; + int ret; + + if (pattern && pattern != DP_TRAINING_PATTERN_4) { + buf |= DP_LINK_SCRAMBLING_DISABLE; + + regmap_update_bits(dp->regmap, DW_DP_CCTL, SCRAMBLE_DIS, + FIELD_PREP(SCRAMBLE_DIS, 1)); + } else { + regmap_update_bits(dp->regmap, DW_DP_CCTL, SCRAMBLE_DIS, + FIELD_PREP(SCRAMBLE_DIS, 0)); + } + + switch (pattern) { + case DP_TRAINING_PATTERN_DISABLE: + dw_dp_phy_set_pattern(dp, DW_DP_PHY_PATTERN_NONE); + break; + case DP_TRAINING_PATTERN_1: + dw_dp_phy_set_pattern(dp, DW_DP_PHY_PATTERN_TPS_1); + break; + case DP_TRAINING_PATTERN_2: + dw_dp_phy_set_pattern(dp, DW_DP_PHY_PATTERN_TPS_2); + break; + case DP_TRAINING_PATTERN_3: + dw_dp_phy_set_pattern(dp, DW_DP_PHY_PATTERN_TPS_3); + break; + case DP_TRAINING_PATTERN_4: + dw_dp_phy_set_pattern(dp, DW_DP_PHY_PATTERN_TPS_4); + break; + default: + return -EINVAL; + } + + ret = drm_dp_dpcd_writeb(&dp->aux, DP_TRAINING_PATTERN_SET, + buf | pattern); + if (ret < 0) + return ret; + + return 0; +} + +static u8 dw_dp_voltage_max(u8 preemph) +{ + switch (preemph & DP_TRAIN_PRE_EMPHASIS_MASK) { + case DP_TRAIN_PRE_EMPH_LEVEL_0: + return DP_TRAIN_VOLTAGE_SWING_LEVEL_3; + case DP_TRAIN_PRE_EMPH_LEVEL_1: + return DP_TRAIN_VOLTAGE_SWING_LEVEL_2; + case DP_TRAIN_PRE_EMPH_LEVEL_2: + return DP_TRAIN_VOLTAGE_SWING_LEVEL_1; + case DP_TRAIN_PRE_EMPH_LEVEL_3: + default: + return DP_TRAIN_VOLTAGE_SWING_LEVEL_0; + } +} + +static bool dw_dp_link_get_adjustments(struct dw_dp_link *link, + u8 status[DP_LINK_STATUS_SIZE]) +{ + struct dw_dp_link_train_set *adj = &link->train.adjust; + unsigned int i; + bool changed = false; + u8 v = 0; + u8 p = 0; + + for (i = 0; i < link->lanes; i++) { + v = drm_dp_get_adjust_request_voltage(status, i); + v >>= DP_TRAIN_VOLTAGE_SWING_SHIFT; + p = drm_dp_get_adjust_request_pre_emphasis(status, i); + p >>= DP_TRAIN_PRE_EMPHASIS_SHIFT; + + if (v != adj->voltage_swing[i] || p != adj->pre_emphasis[i]) + changed = true; + + if (p >= (DP_TRAIN_PRE_EMPH_LEVEL_3 >> DP_TRAIN_PRE_EMPHASIS_SHIFT)) { + adj->pre_emphasis[i] = DP_TRAIN_PRE_EMPH_LEVEL_3 >> + DP_TRAIN_PRE_EMPHASIS_SHIFT; + adj->pre_max_reached[i] = true; + } else { + adj->pre_emphasis[i] = p; + adj->pre_max_reached[i] = false; + } + + v = min(v, dw_dp_voltage_max(p)); + if (v >= (DP_TRAIN_VOLTAGE_SWING_LEVEL_3 >> DP_TRAIN_VOLTAGE_SWING_SHIFT)) { + adj->voltage_swing[i] = DP_TRAIN_VOLTAGE_SWING_LEVEL_3 >> + DP_TRAIN_VOLTAGE_SWING_SHIFT; + adj->voltage_max_reached[i] = true; + } else { + adj->voltage_swing[i] = v; + adj->voltage_max_reached[i] = false; + } + } + + return changed; +} + +static int dw_dp_link_clock_recovery(struct dw_dp *dp) +{ + struct dw_dp_link *link = &dp->link; + u8 status[DP_LINK_STATUS_SIZE]; + unsigned int tries = 0; + int ret; + bool adj_changed; + + ret = dw_dp_link_train_set_pattern(dp, DP_TRAINING_PATTERN_1); + if (ret) + return ret; + + for (;;) { + ret = dw_dp_link_train_update_vs_emph(dp); + if (ret) + return ret; + + drm_dp_link_train_clock_recovery_delay(&dp->aux, link->dpcd); + + ret = drm_dp_dpcd_read_link_status(&dp->aux, status); + if (ret < 0) { + dev_err(dp->dev, "failed to read link status: %d\n", ret); + return ret; + } + + if (drm_dp_clock_recovery_ok(status, link->lanes)) { + link->train.clock_recovered = true; + break; + } + + /* + * According to DP spec 1.4, if current ADJ is the same + * with previous REQ, we need to retry 5 times. + */ + adj_changed = dw_dp_link_get_adjustments(link, status); + if (!adj_changed) + tries++; + else + tries = 0; + + if (tries == 5) + break; + } + + return 0; +} + +static int dw_dp_link_channel_equalization(struct dw_dp *dp) +{ + struct dw_dp_link *link = &dp->link; + u8 status[DP_LINK_STATUS_SIZE], pattern; + unsigned int tries; + int ret; + + if (link->caps.tps4_supported) + pattern = DP_TRAINING_PATTERN_4; + else if (link->caps.tps3_supported) + pattern = DP_TRAINING_PATTERN_3; + else + pattern = DP_TRAINING_PATTERN_2; + ret = dw_dp_link_train_set_pattern(dp, pattern); + if (ret) + return ret; + + for (tries = 1; tries < 5; tries++) { + ret = dw_dp_link_train_update_vs_emph(dp); + if (ret) + return ret; + + drm_dp_link_train_channel_eq_delay(&dp->aux, link->dpcd); + + ret = drm_dp_dpcd_read_link_status(&dp->aux, status); + if (ret < 0) + return ret; + + if (!drm_dp_clock_recovery_ok(status, link->lanes)) { + dev_err(dp->dev, "clock recovery lost while equalizing channel\n"); + link->train.clock_recovered = false; + break; + } + + if (drm_dp_channel_eq_ok(status, link->lanes)) { + link->train.channel_equalized = true; + break; + } + + dw_dp_link_get_adjustments(link, status); + } + + return 0; +} + +static int dw_dp_link_downgrade(struct dw_dp *dp) +{ + struct dw_dp_link *link = &dp->link; + struct dw_dp_bridge_state *state; + + state = dw_dp_get_bridge_state(dp); + + switch (link->rate) { + case 162000: + return -EINVAL; + case 270000: + link->rate = 162000; + break; + case 540000: + link->rate = 270000; + break; + case 810000: + link->rate = 540000; + break; + } + + if (!dw_dp_bandwidth_ok(dp, &state->mode, state->bpp, link->lanes, + link->rate)) + return -E2BIG; + + return 0; +} + +static int dw_dp_link_train_full(struct dw_dp *dp) +{ + struct dw_dp_link *link = &dp->link; + int ret; + +retry: + dw_dp_link_train_init(&link->train); + + dev_dbg(dp->dev, "full-training link: %u lane%s at %u MHz\n", + link->lanes, (link->lanes > 1) ? "s" : "", link->rate / 100); + + ret = dw_dp_link_configure(dp); + if (ret < 0) { + dev_err(dp->dev, "failed to configure DP link: %d\n", ret); + return ret; + } + + ret = dw_dp_link_clock_recovery(dp); + if (ret < 0) { + dev_err(dp->dev, "clock recovery failed: %d\n", ret); + goto out; + } + + if (!link->train.clock_recovered) { + dev_err(dp->dev, "clock recovery failed, downgrading link\n"); + + ret = dw_dp_link_downgrade(dp); + if (ret < 0) + goto out; + else + goto retry; + } + + dev_dbg(dp->dev, "clock recovery succeeded\n"); + + ret = dw_dp_link_channel_equalization(dp); + if (ret < 0) { + dev_err(dp->dev, "channel equalization failed: %d\n", ret); + goto out; + } + + if (!link->train.channel_equalized) { + dev_err(dp->dev, "channel equalization failed, downgrading link\n"); + + ret = dw_dp_link_downgrade(dp); + if (ret < 0) + goto out; + else + goto retry; + } + + dev_dbg(dp->dev, "channel equalization succeeded\n"); + +out: + dw_dp_link_train_set_pattern(dp, DP_TRAINING_PATTERN_DISABLE); + return ret; +} + +static int dw_dp_link_train_fast(struct dw_dp *dp) +{ + struct dw_dp_link *link = &dp->link; + int ret; + u8 status[DP_LINK_STATUS_SIZE]; + u8 pattern; + + dw_dp_link_train_init(&link->train); + + dev_dbg(dp->dev, "fast-training link: %u lane%s at %u MHz\n", + link->lanes, (link->lanes > 1) ? "s" : "", link->rate / 100); + + ret = dw_dp_link_configure(dp); + if (ret < 0) { + dev_err(dp->dev, "failed to configure DP link: %d\n", ret); + return ret; + } + + ret = dw_dp_link_train_set_pattern(dp, DP_TRAINING_PATTERN_1); + if (ret) + goto out; + + usleep_range(500, 1000); + + if (link->caps.tps4_supported) + pattern = DP_TRAINING_PATTERN_4; + else if (link->caps.tps3_supported) + pattern = DP_TRAINING_PATTERN_3; + else + pattern = DP_TRAINING_PATTERN_2; + ret = dw_dp_link_train_set_pattern(dp, pattern); + if (ret) + goto out; + + usleep_range(500, 1000); + + ret = drm_dp_dpcd_read_link_status(&dp->aux, status); + if (ret < 0) { + dev_err(dp->dev, "failed to read link status: %d\n", ret); + goto out; + } + + if (!drm_dp_clock_recovery_ok(status, link->lanes)) { + dev_err(dp->dev, "clock recovery failed\n"); + ret = -EIO; + goto out; + } + + if (!drm_dp_channel_eq_ok(status, link->lanes)) { + dev_err(dp->dev, "channel equalization failed\n"); + ret = -EIO; + goto out; + } + +out: + dw_dp_link_train_set_pattern(dp, DP_TRAINING_PATTERN_DISABLE); + return ret; +} + +static int dw_dp_link_train(struct dw_dp *dp) +{ + struct dw_dp_link *link = &dp->link; + int ret; + + if (link->caps.fast_training) { + if (dw_dp_link_train_valid(&link->train)) { + ret = dw_dp_link_train_fast(dp); + if (ret < 0) + dev_err(dp->dev, "fast link training failed: %d\n", ret); + else + return 0; + } + } + + ret = dw_dp_link_train_full(dp); + if (ret < 0) { + dev_err(dp->dev, "full link training failed: %d\n", ret); + return ret; + } + + return 0; +} + +static int dw_dp_send_sdp(struct dw_dp *dp, struct dw_dp_sdp *sdp) +{ + const u8 *payload = sdp->base.db; + u32 reg; + int i, nr; + + nr = find_first_zero_bit(dp->sdp_reg_bank, SDP_REG_BANK_SIZE); + if (nr < SDP_REG_BANK_SIZE) + set_bit(nr, dp->sdp_reg_bank); + else + return -EBUSY; + + reg = DW_DP_SDP_REGISTER_BANK + nr * 9 * 4; + + /* SDP header */ + regmap_write(dp->regmap, reg, get_unaligned_le32(&sdp->base.sdp_header)); + + /* SDP data payload */ + for (i = 1; i < 9; i++, payload += 4) + regmap_write(dp->regmap, reg + i * 4, + FIELD_PREP(SDP_REGS, get_unaligned_le32(payload))); + + if (sdp->flags & DW_DP_SDP_VERTICAL_INTERVAL) + regmap_update_bits(dp->regmap, DW_DP_SDP_VERTICAL_CTRL, + EN_VERTICAL_SDP << nr, + EN_VERTICAL_SDP << nr); + + if (sdp->flags & DW_DP_SDP_HORIZONTAL_INTERVAL) + regmap_update_bits(dp->regmap, DW_DP_SDP_HORIZONTAL_CTRL, + EN_HORIZONTAL_SDP << nr, + EN_HORIZONTAL_SDP << nr); + + return 0; +} + +static int dw_dp_send_vsc_sdp(struct dw_dp *dp) +{ + struct dw_dp_bridge_state *state; + struct dw_dp_sdp sdp = {}; + struct drm_dp_vsc_sdp vsc = {}; + + state = dw_dp_get_bridge_state(dp); + if (!state) + return -EINVAL; + + vsc.bpc = state->bpc; + + vsc.sdp_type = DP_SDP_VSC; + vsc.revision = 0x5; + vsc.length = 0x13; + vsc.content_type = DP_CONTENT_TYPE_NOT_DEFINED; + + sdp.flags = DW_DP_SDP_VERTICAL_INTERVAL; + + switch (state->color_format) { + case DRM_COLOR_FORMAT_YCBCR444: + vsc.pixelformat = DP_PIXELFORMAT_YUV444; + break; + case DRM_COLOR_FORMAT_YCBCR420: + vsc.pixelformat = DP_PIXELFORMAT_YUV420; + break; + case DRM_COLOR_FORMAT_YCBCR422: + vsc.pixelformat = DP_PIXELFORMAT_YUV422; + break; + case DRM_COLOR_FORMAT_RGB444: + default: + vsc.pixelformat = DP_PIXELFORMAT_RGB; + break; + } + + if (state->color_format == DRM_COLOR_FORMAT_RGB444) { + vsc.colorimetry = DP_COLORIMETRY_DEFAULT; + vsc.dynamic_range = DP_DYNAMIC_RANGE_VESA; + } else { + vsc.colorimetry = DP_COLORIMETRY_BT709_YCC; + vsc.dynamic_range = DP_DYNAMIC_RANGE_CTA; + } + + drm_dp_vsc_sdp_pack(&vsc, &sdp.base); + + return dw_dp_send_sdp(dp, &sdp); +} + +static int dw_dp_video_set_pixel_mode(struct dw_dp *dp) +{ + switch (dp->pixel_mode) { + case DW_DP_MP_SINGLE_PIXEL: + case DW_DP_MP_DUAL_PIXEL: + case DW_DP_MP_QUAD_PIXEL: + break; + default: + return -EINVAL; + } + + regmap_update_bits(dp->regmap, DW_DP_VSAMPLE_CTRL, PIXEL_MODE_SELECT, + FIELD_PREP(PIXEL_MODE_SELECT, dp->pixel_mode)); + + return 0; +} + +static bool dw_dp_video_need_vsc_sdp(struct dw_dp *dp) +{ + struct dw_dp_link *link = &dp->link; + struct dw_dp_bridge_state *state; + + state = dw_dp_get_bridge_state(dp); + if (!state) + return -EINVAL; + + if (!link->vsc_sdp_supported) + return false; + + if (state->color_format == DRM_COLOR_FORMAT_YCBCR420) + return true; + + return false; +} + +static int dw_dp_video_set_msa(struct dw_dp *dp, u8 color_format, u8 bpc, + u16 vstart, u16 hstart) +{ + u16 misc = 0; + + if (dw_dp_video_need_vsc_sdp(dp)) + misc |= DP_MSA_MISC_COLOR_VSC_SDP; + + switch (color_format) { + case DRM_COLOR_FORMAT_RGB444: + misc |= DP_MSA_MISC_COLOR_RGB; + break; + case DRM_COLOR_FORMAT_YCBCR444: + misc |= DP_MSA_MISC_COLOR_YCBCR_444_BT709; + break; + case DRM_COLOR_FORMAT_YCBCR422: + misc |= DP_MSA_MISC_COLOR_YCBCR_422_BT709; + break; + case DRM_COLOR_FORMAT_YCBCR420: + break; + default: + return -EINVAL; + } + + switch (bpc) { + case 6: + misc |= DP_MSA_MISC_6_BPC; + break; + case 8: + misc |= DP_MSA_MISC_8_BPC; + break; + case 10: + misc |= DP_MSA_MISC_10_BPC; + break; + case 12: + misc |= DP_MSA_MISC_12_BPC; + break; + case 16: + misc |= DP_MSA_MISC_16_BPC; + break; + default: + return -EINVAL; + } + + regmap_write(dp->regmap, DW_DP_VIDEO_MSA1, + FIELD_PREP(VSTART, vstart) | FIELD_PREP(HSTART, hstart)); + regmap_write(dp->regmap, DW_DP_VIDEO_MSA2, FIELD_PREP(MISC0, misc)); + regmap_write(dp->regmap, DW_DP_VIDEO_MSA3, FIELD_PREP(MISC1, misc >> 8)); + + return 0; +} + +static void dw_dp_video_disable(struct dw_dp *dp) +{ + regmap_update_bits(dp->regmap, DW_DP_VSAMPLE_CTRL, VIDEO_STREAM_ENABLE, + FIELD_PREP(VIDEO_STREAM_ENABLE, 0)); +} + +static int dw_dp_video_enable(struct dw_dp *dp) +{ + struct dw_dp_link *link = &dp->link; + struct dw_dp_bridge_state *state; + struct drm_display_mode *mode; + u8 color_format, bpc, bpp; + u8 init_threshold, vic; + u32 hstart, hactive, hblank, h_sync_width, h_front_porch; + u32 vstart, vactive, vblank, v_sync_width, v_front_porch; + u32 peak_stream_bandwidth, link_bandwidth; + u32 average_bytes_per_tu, average_bytes_per_tu_frac; + u32 ts, hblank_interval; + u32 value; + int ret; + + state = dw_dp_get_bridge_state(dp); + if (!state) + return -EINVAL; + + bpc = state->bpc; + bpp = state->bpp; + color_format = state->color_format; + mode = &state->mode; + + vstart = mode->vtotal - mode->vsync_start; + hstart = mode->htotal - mode->hsync_start; + + ret = dw_dp_video_set_pixel_mode(dp); + if (ret) + return ret; + + ret = dw_dp_video_set_msa(dp, color_format, bpc, vstart, hstart); + if (ret) + return ret; + + regmap_update_bits(dp->regmap, DW_DP_VSAMPLE_CTRL, VIDEO_MAPPING, + FIELD_PREP(VIDEO_MAPPING, state->video_mapping)); + + /* Configure DW_DP_VINPUT_POLARITY_CTRL register */ + value = 0; + if (mode->flags & DRM_MODE_FLAG_PHSYNC) + value |= FIELD_PREP(HSYNC_IN_POLARITY, 1); + if (mode->flags & DRM_MODE_FLAG_PVSYNC) + value |= FIELD_PREP(VSYNC_IN_POLARITY, 1); + regmap_write(dp->regmap, DW_DP_VINPUT_POLARITY_CTRL, value); + + /* Configure DW_DP_VIDEO_CONFIG1 register */ + hactive = mode->hdisplay; + hblank = mode->htotal - mode->hdisplay; + value = FIELD_PREP(HACTIVE, hactive) | FIELD_PREP(HBLANK, hblank); + if (mode->flags & DRM_MODE_FLAG_INTERLACE) + value |= FIELD_PREP(I_P, 1); + vic = drm_match_cea_mode(mode); + if (vic == 5 || vic == 6 || vic == 7 || + vic == 10 || vic == 11 || vic == 20 || + vic == 21 || vic == 22 || vic == 39 || + vic == 25 || vic == 26 || vic == 40 || + vic == 44 || vic == 45 || vic == 46 || + vic == 50 || vic == 51 || vic == 54 || + vic == 55 || vic == 58 || vic == 59) + value |= R_V_BLANK_IN_OSC; + regmap_write(dp->regmap, DW_DP_VIDEO_CONFIG1, value); + + /* Configure DW_DP_VIDEO_CONFIG2 register */ + vblank = mode->vtotal - mode->vdisplay; + vactive = mode->vdisplay; + regmap_write(dp->regmap, DW_DP_VIDEO_CONFIG2, + FIELD_PREP(VBLANK, vblank) | FIELD_PREP(VACTIVE, vactive)); + + /* Configure DW_DP_VIDEO_CONFIG3 register */ + h_sync_width = mode->hsync_end - mode->hsync_start; + h_front_porch = mode->hsync_start - mode->hdisplay; + regmap_write(dp->regmap, DW_DP_VIDEO_CONFIG3, + FIELD_PREP(H_SYNC_WIDTH, h_sync_width) | + FIELD_PREP(H_FRONT_PORCH, h_front_porch)); + + /* Configure DW_DP_VIDEO_CONFIG4 register */ + v_sync_width = mode->vsync_end - mode->vsync_start; + v_front_porch = mode->vsync_start - mode->vdisplay; + regmap_write(dp->regmap, DW_DP_VIDEO_CONFIG4, + FIELD_PREP(V_SYNC_WIDTH, v_sync_width) | + FIELD_PREP(V_FRONT_PORCH, v_front_porch)); + + /* Configure DW_DP_VIDEO_CONFIG5 register */ + peak_stream_bandwidth = mode->clock * bpp / 8; + link_bandwidth = (link->rate / 1000) * link->lanes; + ts = peak_stream_bandwidth * 64 / link_bandwidth; + average_bytes_per_tu = ts / 1000; + average_bytes_per_tu_frac = ts / 100 - average_bytes_per_tu * 10; + if (dp->pixel_mode == DW_DP_MP_SINGLE_PIXEL) { + if (average_bytes_per_tu < 6) + init_threshold = 32; + else if (hblank <= 80 && color_format != DRM_COLOR_FORMAT_YCBCR420) + init_threshold = 12; + else if (hblank <= 40 && color_format == DRM_COLOR_FORMAT_YCBCR420) + init_threshold = 3; + else + init_threshold = 16; + } else { + u32 t1 = 0, t2 = 0, t3 = 0; + + switch (bpc) { + case 6: + t1 = (4 * 1000 / 9) * link->lanes; + break; + case 8: + if (color_format == DRM_COLOR_FORMAT_YCBCR422) { + t1 = (1000 / 2) * link->lanes; + } else { + if (dp->pixel_mode == DW_DP_MP_DUAL_PIXEL) + t1 = (1000 / 3) * link->lanes; + else + t1 = (3000 / 16) * link->lanes; + } + break; + case 10: + if (color_format == DRM_COLOR_FORMAT_YCBCR422) + t1 = (2000 / 5) * link->lanes; + else + t1 = (4000 / 15) * link->lanes; + break; + case 12: + if (color_format == DRM_COLOR_FORMAT_YCBCR422) { + if (dp->pixel_mode == DW_DP_MP_DUAL_PIXEL) + t1 = (1000 / 6) * link->lanes; + else + t1 = (1000 / 3) * link->lanes; + } else { + t1 = (2000 / 9) * link->lanes; + } + break; + case 16: + if (color_format != DRM_COLOR_FORMAT_YCBCR422 && + dp->pixel_mode == DW_DP_MP_DUAL_PIXEL) + t1 = (1000 / 6) * link->lanes; + else + t1 = (1000 / 4) * link->lanes; + break; + default: + return -EINVAL; + } + + if (color_format == DRM_COLOR_FORMAT_YCBCR420) + t2 = (link->rate / 4) * 1000 / (mode->clock / 2); + else + t2 = (link->rate / 4) * 1000 / mode->clock; + + if (average_bytes_per_tu_frac) + t3 = average_bytes_per_tu + 1; + else + t3 = average_bytes_per_tu; + init_threshold = t1 * t2 * t3 / (1000 * 1000); + if (init_threshold <= 16 || average_bytes_per_tu < 10) + init_threshold = 40; + } + + regmap_write(dp->regmap, DW_DP_VIDEO_CONFIG5, + FIELD_PREP(INIT_THRESHOLD_HI, init_threshold >> 6) | + FIELD_PREP(AVERAGE_BYTES_PER_TU_FRAC, average_bytes_per_tu_frac) | + FIELD_PREP(INIT_THRESHOLD, init_threshold) | + FIELD_PREP(AVERAGE_BYTES_PER_TU, average_bytes_per_tu)); + + /* Configure DW_DP_VIDEO_HBLANK_INTERVAL register */ + hblank_interval = hblank * (link->rate / 4) / mode->clock; + regmap_write(dp->regmap, DW_DP_VIDEO_HBLANK_INTERVAL, + FIELD_PREP(HBLANK_INTERVAL_EN, 1) | + FIELD_PREP(HBLANK_INTERVAL, hblank_interval)); + + /* Video stream enable */ + regmap_update_bits(dp->regmap, DW_DP_VSAMPLE_CTRL, VIDEO_STREAM_ENABLE, + FIELD_PREP(VIDEO_STREAM_ENABLE, 1)); + + if (dw_dp_video_need_vsc_sdp(dp)) + dw_dp_send_vsc_sdp(dp); + + return 0; +} + +static void dw_dp_hpd_init(struct dw_dp *dp) +{ + /* Enable all HPD interrupts */ + regmap_update_bits(dp->regmap, DW_DP_HPD_INTERRUPT_ENABLE, + HPD_UNPLUG_EN | HPD_PLUG_EN | HPD_IRQ_EN, + FIELD_PREP(HPD_UNPLUG_EN, 1) | + FIELD_PREP(HPD_PLUG_EN, 1) | + FIELD_PREP(HPD_IRQ_EN, 1)); + + /* Enable all top-level interrupts */ + regmap_update_bits(dp->regmap, DW_DP_GENERAL_INTERRUPT_ENABLE, + HPD_EVENT_EN, FIELD_PREP(HPD_EVENT_EN, 1)); +} + +static void dw_dp_aux_init(struct dw_dp *dp) +{ + regmap_update_bits(dp->regmap, DW_DP_GENERAL_INTERRUPT_ENABLE, + AUX_REPLY_EVENT_EN, FIELD_PREP(AUX_REPLY_EVENT_EN, 1)); +} + +static void dw_dp_init_hw(struct dw_dp *dp) +{ + regmap_update_bits(dp->regmap, DW_DP_CCTL, DEFAULT_FAST_LINK_TRAIN_EN, + FIELD_PREP(DEFAULT_FAST_LINK_TRAIN_EN, 0)); + + dw_dp_hpd_init(dp); + dw_dp_aux_init(dp); +} + +static int dw_dp_aux_write_data(struct dw_dp *dp, const u8 *buffer, size_t size) +{ + size_t i, j; + + for (i = 0; i < DIV_ROUND_UP(size, 4); i++) { + size_t num = min_t(size_t, size - i * 4, 4); + u32 value = 0; + + for (j = 0; j < num; j++) + value |= buffer[i * 4 + j] << (j * 8); + + regmap_write(dp->regmap, DW_DP_AUX_DATA0 + i * 4, value); + } + + return size; +} + +static int dw_dp_aux_read_data(struct dw_dp *dp, u8 *buffer, size_t size) +{ + size_t i, j; + + for (i = 0; i < DIV_ROUND_UP(size, 4); i++) { + size_t num = min_t(size_t, size - i * 4, 4); + u32 value; + + regmap_read(dp->regmap, DW_DP_AUX_DATA0 + i * 4, &value); + + for (j = 0; j < num; j++) + buffer[i * 4 + j] = value >> (j * 8); + } + + return size; +} + +static ssize_t dw_dp_aux_transfer(struct drm_dp_aux *aux, + struct drm_dp_aux_msg *msg) +{ + struct dw_dp *dp = container_of(aux, struct dw_dp, aux); + unsigned long timeout = msecs_to_jiffies(10); + u32 status, value; + ssize_t ret = 0; + + if (WARN_ON(msg->size > 16)) + return -E2BIG; + + switch (msg->request & ~DP_AUX_I2C_MOT) { + case DP_AUX_NATIVE_WRITE: + case DP_AUX_I2C_WRITE: + case DP_AUX_I2C_WRITE_STATUS_UPDATE: + ret = dw_dp_aux_write_data(dp, msg->buffer, msg->size); + if (ret < 0) + return ret; + break; + case DP_AUX_NATIVE_READ: + case DP_AUX_I2C_READ: + break; + default: + return -EINVAL; + } + + if (msg->size > 0) + value = FIELD_PREP(AUX_LEN_REQ, msg->size - 1); + else + value = FIELD_PREP(I2C_ADDR_ONLY, 1); + value |= FIELD_PREP(AUX_CMD_TYPE, msg->request); + value |= FIELD_PREP(AUX_ADDR, msg->address); + regmap_write(dp->regmap, DW_DP_AUX_CMD, value); + + status = wait_for_completion_timeout(&dp->complete, timeout); + if (!status) { + dev_err(dp->dev, "timeout waiting for AUX reply\n"); + return -ETIMEDOUT; + } + + regmap_read(dp->regmap, DW_DP_AUX_STATUS, &value); + if (value & AUX_TIMEOUT) + return -ETIMEDOUT; + + msg->reply = FIELD_GET(AUX_STATUS, value); + + if (msg->size > 0 && msg->reply == DP_AUX_NATIVE_REPLY_ACK) { + if (msg->request & DP_AUX_I2C_READ) { + size_t count = FIELD_GET(AUX_BYTES_READ, value) - 1; + + if (count != msg->size) + return -EBUSY; + + ret = dw_dp_aux_read_data(dp, msg->buffer, count); + if (ret < 0) + return ret; + } + } + + return ret; +} + +/* + * Limits for the video timing for DP: + * 1. the hfp should be 2 pixels aligned; + * 2. the minimum hsync should be 9 pixel; + * 3. the minimum hbp should be 16 pixel; + */ +static int dw_dp_bridge_atomic_check(struct drm_bridge *bridge, + struct drm_bridge_state *bridge_state, + struct drm_crtc_state *crtc_state, + struct drm_connector_state *conn_state) +{ + struct drm_display_mode *adjusted_mode = &crtc_state->adjusted_mode; + struct dw_dp *dp = bridge_to_dp(bridge); + struct dw_dp_bridge_state *state; + const struct dw_dp_output_format *fmt; + struct drm_display_mode *mode; + int min_hbp = 16; + int min_hsync = 9; + + state = to_dw_dp_bridge_state(bridge_state); + mode = &state->mode; + + fmt = dw_dp_get_output_format(bridge_state->output_bus_cfg.format); + if (!fmt) + return -EINVAL; + + state->video_mapping = fmt->video_mapping; + state->color_format = fmt->color_format; + state->bpc = fmt->bpc; + state->bpp = fmt->bpp; + + if ((adjusted_mode->hsync_start - adjusted_mode->hdisplay) & 0x1) { + adjusted_mode->hsync_start += 1; + dev_warn(dp->dev, "hfp is not 2 pixeel aligned, fixup to aligned hfp\n"); + } + + if (adjusted_mode->hsync_end - adjusted_mode->hsync_start < min_hsync) { + adjusted_mode->hsync_end = adjusted_mode->hsync_start + min_hsync; + dev_warn(dp->dev, "hsync is too narrow, fixup to min hsync:%d\n", min_hsync); + } + + if (adjusted_mode->htotal - adjusted_mode->hsync_end < min_hbp) { + adjusted_mode->htotal = adjusted_mode->hsync_end + min_hbp; + dev_warn(dp->dev, "hbp is too narrow, fixup to min hbp:%d\n", min_hbp); + } + + drm_mode_copy(mode, adjusted_mode); + + return 0; +} + +static enum drm_mode_status dw_dp_bridge_mode_valid(struct drm_bridge *bridge, + const struct drm_display_info *info, + const struct drm_display_mode *mode) +{ + struct dw_dp *dp = bridge_to_dp(bridge); + struct dw_dp_link *link = &dp->link; + u32 min_bpp; + + if (info->color_formats & DRM_COLOR_FORMAT_YCBCR420 && + link->vsc_sdp_supported && + (drm_mode_is_420_only(info, mode) || drm_mode_is_420_also(info, mode))) + min_bpp = 12; + else if (info->color_formats & DRM_COLOR_FORMAT_YCBCR422) + min_bpp = 16; + else if (info->color_formats & DRM_COLOR_FORMAT_RGB444) + min_bpp = 18; + else + min_bpp = 24; + + if (!link->vsc_sdp_supported && + drm_mode_is_420_only(info, mode)) + return MODE_NO_420; + + if (!dw_dp_bandwidth_ok(dp, mode, min_bpp, link->lanes, link->rate)) + return MODE_CLOCK_HIGH; + + return MODE_OK; +} + +static bool dw_dp_needs_link_retrain(struct dw_dp *dp) +{ + struct dw_dp_link *link = &dp->link; + u8 link_status[DP_LINK_STATUS_SIZE]; + + if (!dw_dp_link_train_valid(&link->train)) + return false; + + if (drm_dp_dpcd_read_link_status(&dp->aux, link_status) < 0) + return false; + + /* Retrain if Channel EQ or CR not ok */ + return !drm_dp_channel_eq_ok(link_status, dp->link.lanes); +} + +static void dw_dp_link_disable(struct dw_dp *dp) +{ + struct dw_dp_link *link = &dp->link; + + if (dw_dp_hpd_detect(dp)) + drm_dp_link_power_down(&dp->aux, dp->link.revision); + + dw_dp_phy_xmit_enable(dp, 0); + + phy_power_off(dp->phy); + + link->train.clock_recovered = false; + link->train.channel_equalized = false; +} + +static int dw_dp_link_enable(struct dw_dp *dp) +{ + int ret; + + ret = phy_power_on(dp->phy); + if (ret) + return ret; + + ret = drm_dp_link_power_up(&dp->aux, dp->link.revision); + if (ret < 0) + return ret; + + ret = dw_dp_link_train(dp); + + return ret; +} + +static void dw_dp_bridge_atomic_enable(struct drm_bridge *bridge, + struct drm_atomic_state *state) +{ + struct dw_dp *dp = bridge_to_dp(bridge); + struct drm_connector *connector; + struct drm_connector_state *conn_state; + int ret; + + connector = drm_atomic_get_new_connector_for_encoder(state, bridge->encoder); + if (!connector) { + dev_err(dp->dev, "failed to get connector\n"); + return; + } + + conn_state = drm_atomic_get_new_connector_state(state, connector); + if (!conn_state) { + dev_err(dp->dev, "failed to get connector state\n"); + return; + } + + set_bit(0, dp->sdp_reg_bank); + + ret = dw_dp_link_enable(dp); + if (ret < 0) { + dev_err(dp->dev, "failed to enable link: %d\n", ret); + return; + } + + ret = dw_dp_video_enable(dp); + if (ret < 0) { + dev_err(dp->dev, "failed to enable video: %d\n", ret); + return; + } +} + +static void dw_dp_reset(struct dw_dp *dp) +{ + int val; + + disable_irq(dp->irq); + regmap_update_bits(dp->regmap, DW_DP_SOFT_RESET_CTRL, CONTROLLER_RESET, + FIELD_PREP(CONTROLLER_RESET, 1)); + usleep_range(10, 20); + regmap_update_bits(dp->regmap, DW_DP_SOFT_RESET_CTRL, CONTROLLER_RESET, + FIELD_PREP(CONTROLLER_RESET, 0)); + + dw_dp_init_hw(dp); + regmap_read_poll_timeout(dp->regmap, DW_DP_HPD_STATUS, val, + FIELD_GET(HPD_HOT_PLUG, val), 200, 200000); + regmap_write(dp->regmap, DW_DP_HPD_STATUS, HPD_HOT_PLUG); + enable_irq(dp->irq); +} + +static void dw_dp_bridge_atomic_disable(struct drm_bridge *bridge, + struct drm_atomic_state *state) +{ + struct dw_dp *dp = bridge_to_dp(bridge); + + dw_dp_video_disable(dp); + dw_dp_link_disable(dp); + bitmap_zero(dp->sdp_reg_bank, SDP_REG_BANK_SIZE); + dw_dp_reset(dp); +} + +static bool dw_dp_hpd_detect_link(struct dw_dp *dp, struct drm_connector *connector) +{ + int ret; + + ret = phy_power_on(dp->phy); + if (ret < 0) + return false; + ret = dw_dp_link_parse(dp, connector); + phy_power_off(dp->phy); + + return !ret; +} + +static enum drm_connector_status dw_dp_bridge_detect(struct drm_bridge *bridge, + struct drm_connector *connector) +{ + struct dw_dp *dp = bridge_to_dp(bridge); + + if (!dw_dp_hpd_detect(dp)) + return connector_status_disconnected; + + if (!dw_dp_hpd_detect_link(dp, connector)) + return connector_status_disconnected; + + return connector_status_connected; +} + +static const struct drm_edid *dw_dp_bridge_edid_read(struct drm_bridge *bridge, + struct drm_connector *connector) +{ + struct dw_dp *dp = bridge_to_dp(bridge); + const struct drm_edid *edid; + int ret; + + ret = phy_power_on(dp->phy); + if (ret) + return NULL; + + edid = drm_edid_read_ddc(connector, &dp->aux.ddc); + + phy_power_off(dp->phy); + + return edid; +} + +static u32 *dw_dp_bridge_atomic_get_output_bus_fmts(struct drm_bridge *bridge, + struct drm_bridge_state *bridge_state, + struct drm_crtc_state *crtc_state, + struct drm_connector_state *conn_state, + unsigned int *num_output_fmts) +{ + struct dw_dp *dp = bridge_to_dp(bridge); + struct dw_dp_link *link = &dp->link; + struct drm_display_info *di = &conn_state->connector->display_info; + struct drm_display_mode mode = crtc_state->mode; + const struct dw_dp_output_format *fmt; + u32 i, j = 0; + u32 *output_fmts; + + *num_output_fmts = 0; + + output_fmts = kcalloc(ARRAY_SIZE(dw_dp_output_formats), sizeof(*output_fmts), GFP_KERNEL); + if (!output_fmts) + return NULL; + + for (i = 0; i < ARRAY_SIZE(dw_dp_output_formats); i++) { + fmt = &dw_dp_output_formats[i]; + + if (fmt->bpc > conn_state->max_bpc) + continue; + + if (!(fmt->color_format & di->color_formats)) + continue; + + if (fmt->color_format == DRM_COLOR_FORMAT_YCBCR420 && + !link->vsc_sdp_supported) + continue; + + if (fmt->color_format != DRM_COLOR_FORMAT_YCBCR420 && + drm_mode_is_420_only(di, &mode)) + continue; + + if (!dw_dp_bandwidth_ok(dp, &mode, fmt->bpp, link->lanes, link->rate)) + continue; + + output_fmts[j++] = fmt->bus_format; + } + + *num_output_fmts = j; + + return output_fmts; +} + +static struct drm_bridge_state *dw_dp_bridge_atomic_duplicate_state(struct drm_bridge *bridge) +{ + struct dw_dp_bridge_state *state; + + state = kzalloc(sizeof(*state), GFP_KERNEL); + if (!state) + return NULL; + + __drm_atomic_helper_bridge_duplicate_state(bridge, &state->base); + + return &state->base; +} + +static const struct drm_bridge_funcs dw_dp_bridge_funcs = { + .atomic_duplicate_state = dw_dp_bridge_atomic_duplicate_state, + .atomic_destroy_state = drm_atomic_helper_bridge_destroy_state, + .atomic_reset = drm_atomic_helper_bridge_reset, + .atomic_get_input_bus_fmts = drm_atomic_helper_bridge_propagate_bus_fmt, + .atomic_get_output_bus_fmts = dw_dp_bridge_atomic_get_output_bus_fmts, + .atomic_check = dw_dp_bridge_atomic_check, + .mode_valid = dw_dp_bridge_mode_valid, + .atomic_enable = dw_dp_bridge_atomic_enable, + .atomic_disable = dw_dp_bridge_atomic_disable, + .detect = dw_dp_bridge_detect, + .edid_read = dw_dp_bridge_edid_read, +}; + +static int dw_dp_link_retrain(struct dw_dp *dp) +{ + struct drm_device *dev = dp->bridge.dev; + struct drm_modeset_acquire_ctx ctx; + int ret; + + if (!dw_dp_needs_link_retrain(dp)) + return 0; + + dev_dbg(dp->dev, "Retraining link\n"); + + drm_modeset_acquire_init(&ctx, 0); + for (;;) { + ret = drm_modeset_lock(&dev->mode_config.connection_mutex, &ctx); + if (ret != -EDEADLK) + break; + + drm_modeset_backoff(&ctx); + } + + if (!ret) + ret = dw_dp_link_train(dp); + + drm_modeset_drop_locks(&ctx); + drm_modeset_acquire_fini(&ctx); + + return ret; +} + +static void dw_dp_hpd_work(struct work_struct *work) +{ + struct dw_dp *dp = container_of(work, struct dw_dp, hpd_work); + bool long_hpd; + int ret; + + mutex_lock(&dp->irq_lock); + long_hpd = dp->hotplug.long_hpd; + mutex_unlock(&dp->irq_lock); + + dev_dbg(dp->dev, "[drm] Get hpd irq - %s\n", long_hpd ? "long" : "short"); + + if (!long_hpd) { + if (dw_dp_needs_link_retrain(dp)) { + ret = dw_dp_link_retrain(dp); + if (ret) + dev_warn(dp->dev, "Retrain link failed\n"); + } + } else { + drm_helper_hpd_irq_event(dp->bridge.dev); + } +} + +static void dw_dp_handle_hpd_event(struct dw_dp *dp) +{ + u32 value; + + mutex_lock(&dp->irq_lock); + regmap_read(dp->regmap, DW_DP_HPD_STATUS, &value); + + if (value & HPD_IRQ) { + dev_dbg(dp->dev, "IRQ from the HPD\n"); + dp->hotplug.long_hpd = false; + regmap_write(dp->regmap, DW_DP_HPD_STATUS, HPD_IRQ); + } + + if (value & HPD_HOT_PLUG) { + dev_dbg(dp->dev, "Hot plug detected\n"); + dp->hotplug.long_hpd = true; + regmap_write(dp->regmap, DW_DP_HPD_STATUS, HPD_HOT_PLUG); + } + + if (value & HPD_HOT_UNPLUG) { + dev_dbg(dp->dev, "Unplug detected\n"); + dp->hotplug.long_hpd = true; + regmap_write(dp->regmap, DW_DP_HPD_STATUS, HPD_HOT_UNPLUG); + } + mutex_unlock(&dp->irq_lock); + + schedule_work(&dp->hpd_work); +} + +static irqreturn_t dw_dp_irq(int irq, void *data) +{ + struct dw_dp *dp = data; + u32 value; + + regmap_read(dp->regmap, DW_DP_GENERAL_INTERRUPT, &value); + if (!value) + return IRQ_NONE; + + if (value & HPD_EVENT) + dw_dp_handle_hpd_event(dp); + + if (value & AUX_REPLY_EVENT) { + regmap_write(dp->regmap, DW_DP_GENERAL_INTERRUPT, AUX_REPLY_EVENT); + complete(&dp->complete); + } + + return IRQ_HANDLED; +} + +static const struct regmap_range dw_dp_readable_ranges[] = { + regmap_reg_range(DW_DP_VERSION_NUMBER, DW_DP_ID), + regmap_reg_range(DW_DP_CONFIG_REG1, DW_DP_CONFIG_REG3), + regmap_reg_range(DW_DP_CCTL, DW_DP_SOFT_RESET_CTRL), + regmap_reg_range(DW_DP_VSAMPLE_CTRL, DW_DP_VIDEO_HBLANK_INTERVAL), + regmap_reg_range(DW_DP_AUD_CONFIG1, DW_DP_AUD_CONFIG1), + regmap_reg_range(DW_DP_SDP_VERTICAL_CTRL, DW_DP_SDP_STATUS_EN), + regmap_reg_range(DW_DP_PHYIF_CTRL, DW_DP_PHYIF_PWRDOWN_CTRL), + regmap_reg_range(DW_DP_AUX_CMD, DW_DP_AUX_DATA3), + regmap_reg_range(DW_DP_GENERAL_INTERRUPT, DW_DP_HPD_INTERRUPT_ENABLE), +}; + +static const struct regmap_access_table dw_dp_readable_table = { + .yes_ranges = dw_dp_readable_ranges, + .n_yes_ranges = ARRAY_SIZE(dw_dp_readable_ranges), +}; + +static const struct regmap_config dw_dp_regmap_config = { + .reg_bits = 32, + .reg_stride = 4, + .val_bits = 32, + .fast_io = true, + .max_register = DW_DP_MAX_REGISTER, + .rd_table = &dw_dp_readable_table, +}; + +static void dw_dp_phy_exit(void *data) +{ + struct dw_dp *dp = data; + + phy_exit(dp->phy); +} + +struct dw_dp *dw_dp_bind(struct device *dev, struct drm_encoder *encoder, + const struct dw_dp_plat_data *plat_data) +{ + struct platform_device *pdev = to_platform_device(dev); + struct dw_dp *dp; + struct drm_bridge *bridge; + void __iomem *res; + int ret; + + dp = devm_kzalloc(dev, sizeof(*dp), GFP_KERNEL); + if (!dp) + return ERR_PTR(-ENOMEM); + + dp = devm_drm_bridge_alloc(dev, struct dw_dp, bridge, &dw_dp_bridge_funcs); + if (IS_ERR(dp)) + return ERR_CAST(dp); + + dp->dev = dev; + dp->pixel_mode = DW_DP_MP_QUAD_PIXEL; + + dp->plat_data.max_link_rate = plat_data->max_link_rate; + bridge = &dp->bridge; + mutex_init(&dp->irq_lock); + INIT_WORK(&dp->hpd_work, dw_dp_hpd_work); + init_completion(&dp->complete); + + res = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(res)) + return ERR_CAST(res); + + dp->regmap = devm_regmap_init_mmio(dev, res, &dw_dp_regmap_config); + if (IS_ERR(dp->regmap)) { + dev_err_probe(dev, PTR_ERR(dp->regmap), "failed to create regmap\n"); + return ERR_CAST(dp->regmap); + } + + dp->phy = devm_of_phy_get(dev, dev->of_node, NULL); + if (IS_ERR(dp->phy)) { + dev_err_probe(dev, PTR_ERR(dp->phy), "failed to get phy\n"); + return ERR_CAST(dp->phy); + } + + dp->apb_clk = devm_clk_get_enabled(dev, "apb"); + if (IS_ERR(dp->apb_clk)) { + dev_err_probe(dev, PTR_ERR(dp->apb_clk), "failed to get apb clock\n"); + return ERR_CAST(dp->apb_clk); + } + + dp->aux_clk = devm_clk_get_enabled(dev, "aux"); + if (IS_ERR(dp->aux_clk)) { + dev_err_probe(dev, PTR_ERR(dp->aux_clk), "failed to get aux clock\n"); + return ERR_CAST(dp->aux_clk); + } + + dp->i2s_clk = devm_clk_get(dev, "i2s"); + if (IS_ERR(dp->i2s_clk)) { + dev_err_probe(dev, PTR_ERR(dp->i2s_clk), "failed to get i2s clock\n"); + return ERR_CAST(dp->i2s_clk); + } + + dp->spdif_clk = devm_clk_get(dev, "spdif"); + if (IS_ERR(dp->spdif_clk)) { + dev_err_probe(dev, PTR_ERR(dp->spdif_clk), "failed to get spdif clock\n"); + return ERR_CAST(dp->spdif_clk); + } + + dp->hdcp_clk = devm_clk_get(dev, "hdcp"); + if (IS_ERR(dp->hdcp_clk)) { + dev_err_probe(dev, PTR_ERR(dp->hdcp_clk), "failed to get hdcp clock\n"); + return ERR_CAST(dp->hdcp_clk); + } + + dp->rstc = devm_reset_control_get(dev, NULL); + if (IS_ERR(dp->rstc)) { + dev_err_probe(dev, PTR_ERR(dp->rstc), "failed to get reset control\n"); + return ERR_CAST(dp->rstc); + } + + bridge->of_node = dev->of_node; + bridge->ops = DRM_BRIDGE_OP_DETECT | DRM_BRIDGE_OP_EDID | DRM_BRIDGE_OP_HPD; + bridge->type = DRM_MODE_CONNECTOR_DisplayPort; + bridge->ycbcr_420_allowed = true; + + dp->aux.dev = dev; + dp->aux.drm_dev = encoder->dev; + dp->aux.name = dev_name(dev); + dp->aux.transfer = dw_dp_aux_transfer; + ret = drm_dp_aux_register(&dp->aux); + if (ret) { + dev_err_probe(dev, ret, "Aux register failed\n"); + return ERR_PTR(ret); + } + + ret = drm_bridge_attach(encoder, bridge, NULL, DRM_BRIDGE_ATTACH_NO_CONNECTOR); + if (ret) + dev_err_probe(dev, ret, "Failed to attach bridge\n"); + + dw_dp_init_hw(dp); + + ret = phy_init(dp->phy); + if (ret) { + dev_err_probe(dev, ret, "phy init failed\n"); + return ERR_PTR(ret); + } + + ret = devm_add_action_or_reset(dev, dw_dp_phy_exit, dp); + if (ret) + return ERR_PTR(ret); + + dp->irq = platform_get_irq(pdev, 0); + if (dp->irq < 0) + return ERR_PTR(ret); + + ret = devm_request_threaded_irq(dev, dp->irq, NULL, dw_dp_irq, + IRQF_ONESHOT, dev_name(dev), dp); + if (ret) { + dev_err_probe(dev, ret, "failed to request irq\n"); + return ERR_PTR(ret); + } + + return dp; +} +EXPORT_SYMBOL_GPL(dw_dp_bind); + +MODULE_AUTHOR("Andy Yan <andyshrk@163.com>"); +MODULE_DESCRIPTION("DW DP Core Library"); +MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c index 464390372b34..ae0d08e5e960 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c @@ -393,6 +393,17 @@ static int __maybe_unused ti_sn65dsi86_resume(struct device *dev) gpiod_set_value_cansleep(pdata->enable_gpio, 1); /* + * After EN is deasserted and an external clock is detected, the bridge + * will sample GPIO3:1 to determine its frequency. The driver will + * overwrite this setting in ti_sn_bridge_set_refclk_freq(). But this is + * racy. Thus we have to wait a couple of us. According to the datasheet + * the GPIO lines has to be stable at least 5 us (td5) but it seems that + * is not enough and the refclk frequency value is still lost or + * overwritten by the bridge itself. Waiting for 20us seems to work. + */ + usleep_range(20, 30); + + /* * If we have a reference clock we can enable communication w/ the * panel (including the aux channel) w/out any need for an input clock * so we can do it in resume which lets us read the EDID before diff --git a/drivers/gpu/drm/bridge/waveshare-dsi.c b/drivers/gpu/drm/bridge/waveshare-dsi.c index 01c70e7d3d3b..43f4e7412d72 100644 --- a/drivers/gpu/drm/bridge/waveshare-dsi.c +++ b/drivers/gpu/drm/bridge/waveshare-dsi.c @@ -147,8 +147,8 @@ static int ws_bridge_probe(struct i2c_client *i2c) int ret; ws = devm_drm_bridge_alloc(dev, struct ws_bridge, bridge, &ws_bridge_bridge_funcs); - if (!ws) - return -ENOMEM; + if (IS_ERR(ws)) + return PTR_ERR(ws); ws->dev = dev; diff --git a/drivers/gpu/drm/display/drm_bridge_connector.c b/drivers/gpu/drm/display/drm_bridge_connector.c index 091c5335355a..baacd21e7341 100644 --- a/drivers/gpu/drm/display/drm_bridge_connector.c +++ b/drivers/gpu/drm/display/drm_bridge_connector.c @@ -751,12 +751,11 @@ struct drm_connector *drm_bridge_connector_init(struct drm_device *drm, return ERR_PTR(-EINVAL); } - if (!drm_bridge_get_next_bridge(bridge)) + if (drm_bridge_is_last(bridge)) connector_type = bridge->type; #ifdef CONFIG_OF - if (!drm_bridge_get_next_bridge(bridge) && - bridge->of_node) + if (drm_bridge_is_last(bridge) && bridge->of_node) connector->fwnode = fwnode_handle_get(of_fwnode_handle(bridge->of_node)); #endif @@ -777,8 +776,6 @@ struct drm_connector *drm_bridge_connector_init(struct drm_device *drm, if (!connector->ycbcr_420_allowed) supported_formats &= ~BIT(HDMI_COLORSPACE_YUV420); - bridge = bridge_connector->bridge_hdmi; - ret = drmm_connector_hdmi_init(drm, connector, bridge_connector->bridge_hdmi->vendor, bridge_connector->bridge_hdmi->product, diff --git a/drivers/gpu/drm/drm_bridge.c b/drivers/gpu/drm/drm_bridge.c index dd439d55177a..d031447eebc9 100644 --- a/drivers/gpu/drm/drm_bridge.c +++ b/drivers/gpu/drm/drm_bridge.c @@ -1435,6 +1435,9 @@ static void drm_bridge_debugfs_show_bridge(struct drm_printer *p, unsigned int idx) { drm_printf(p, "bridge[%u]: %ps\n", idx, bridge->funcs); + + drm_printf(p, "\trefcount: %u\n", kref_read(&bridge->refcount)); + drm_printf(p, "\ttype: [%d] %s\n", bridge->type, drm_get_connector_type_name(bridge->type)); diff --git a/drivers/gpu/drm/drm_format_helper.c b/drivers/gpu/drm/drm_format_helper.c index 37d5e0a7eb46..006836554cc2 100644 --- a/drivers/gpu/drm/drm_format_helper.c +++ b/drivers/gpu/drm/drm_format_helper.c @@ -1256,6 +1256,25 @@ int drm_fb_blit(struct iosys_map *dst, const unsigned int *dst_pitch, uint32_t d } EXPORT_SYMBOL(drm_fb_blit); +static void drm_fb_gray8_to_gray2_line(void *dbuf, const void *sbuf, unsigned int pixels) +{ + u8 *dbuf8 = dbuf; + const u8 *sbuf8 = sbuf; + u8 px; + + while (pixels) { + unsigned int i, bits = min(pixels, 4U); + u8 byte = 0; + + for (i = 0; i < bits; i++, pixels--) { + byte >>= 2; + px = (*sbuf8++ * 3 + 127) / 255; + byte |= (px &= 0x03) << 6; + } + *dbuf8++ = byte; + } +} + static void drm_fb_gray8_to_mono_line(void *dbuf, const void *sbuf, unsigned int pixels) { u8 *dbuf8 = dbuf; @@ -1362,3 +1381,92 @@ void drm_fb_xrgb8888_to_mono(struct iosys_map *dst, const unsigned int *dst_pitc } } EXPORT_SYMBOL(drm_fb_xrgb8888_to_mono); + +/** + * drm_fb_xrgb8888_to_gray2 - Convert XRGB8888 to gray2 + * @dst: Array of gray2 destination buffer + * @dst_pitch: Array of numbers of bytes between the start of two consecutive scanlines + * within @dst; can be NULL if scanlines are stored next to each other. + * @src: Array of XRGB8888 source buffers + * @fb: DRM framebuffer + * @clip: Clip rectangle area to copy + * @state: Transform and conversion state + * + * This function copies parts of a framebuffer to display memory and converts the + * color format during the process. Destination and framebuffer formats must match. The + * parameters @dst, @dst_pitch and @src refer to arrays. Each array must have at + * least as many entries as there are planes in @fb's format. Each entry stores the + * value for the format's respective color plane at the same index. + * + * This function does not apply clipping on @dst (i.e. the destination is at the + * top-left corner). The first pixel (upper left corner of the clip rectangle) will + * be converted and copied to the two first bits (LSB) in the first byte of the gray2 + * destination buffer. If the caller requires that the first pixel in a byte must + * be located at an x-coordinate that is a multiple of 8, then the caller must take + * care itself of supplying a suitable clip rectangle. + * + * DRM doesn't have native gray2 support. Drivers can use this function for + * gray2 devices that don't support XRGB8888 natively. Such drivers can + * announce the commonly supported XR24 format to userspace and use this function + * to convert to the native format. + * + */ +void drm_fb_xrgb8888_to_gray2(struct iosys_map *dst, const unsigned int *dst_pitch, + const struct iosys_map *src, const struct drm_framebuffer *fb, + const struct drm_rect *clip, struct drm_format_conv_state *state) +{ + static const unsigned int default_dst_pitch[DRM_FORMAT_MAX_PLANES] = { + 0, 0, 0, 0 + }; + unsigned int linepixels = drm_rect_width(clip); + unsigned int lines = drm_rect_height(clip); + unsigned int cpp = fb->format->cpp[0]; + unsigned int len_src32 = linepixels * cpp; + struct drm_device *dev = fb->dev; + void *vaddr = src[0].vaddr; + unsigned int dst_pitch_0; + unsigned int y; + u8 *gray2 = dst[0].vaddr, *gray8; + u32 *src32; + + if (drm_WARN_ON(dev, fb->format->format != DRM_FORMAT_XRGB8888)) + return; + + if (!dst_pitch) + dst_pitch = default_dst_pitch; + dst_pitch_0 = dst_pitch[0]; + + /* + * The gray2 destination buffer contains 2 bit per pixel + */ + if (!dst_pitch_0) + dst_pitch_0 = DIV_ROUND_UP(linepixels, 4); + + /* + * The dma memory is write-combined so reads are uncached. + * Speed up by fetching one line at a time. + * + * Also, format conversion from XR24 to gray2 are done + * line-by-line but are converted to 8-bit grayscale as an + * intermediate step. + * + * Allocate a buffer to be used for both copying from the cma + * memory and to store the intermediate grayscale line pixels. + */ + src32 = drm_format_conv_state_reserve(state, len_src32 + linepixels, GFP_KERNEL); + if (!src32) + return; + + gray8 = (u8 *)src32 + len_src32; + + vaddr += clip_offset(clip, fb->pitches[0], cpp); + for (y = 0; y < lines; y++) { + src32 = memcpy(src32, vaddr, len_src32); + drm_fb_xrgb8888_to_gray8_line(gray8, src32, linepixels); + drm_fb_gray8_to_gray2_line(gray2, gray8, linepixels); + vaddr += fb->pitches[0]; + gray2 += dst_pitch_0; + } +} +EXPORT_SYMBOL(drm_fb_xrgb8888_to_gray2); + diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index 4a89b6acb6af..8d25cc65707d 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -187,6 +187,7 @@ void drm_gem_private_object_init(struct drm_device *dev, kref_init(&obj->refcount); obj->handle_count = 0; obj->size = size; + mutex_init(&obj->gpuva.lock); dma_resv_init(&obj->_resv); if (!obj->resv) obj->resv = &obj->_resv; @@ -210,6 +211,7 @@ void drm_gem_private_object_fini(struct drm_gem_object *obj) WARN_ON(obj->dma_buf); dma_resv_fini(&obj->_resv); + mutex_destroy(&obj->gpuva.lock); } EXPORT_SYMBOL(drm_gem_private_object_fini); diff --git a/drivers/gpu/drm/drm_gpusvm.c b/drivers/gpu/drm/drm_gpusvm.c index e2a9a6ae1d54..eeeeb99cfdf6 100644 --- a/drivers/gpu/drm/drm_gpusvm.c +++ b/drivers/gpu/drm/drm_gpusvm.c @@ -373,6 +373,12 @@ static const struct mmu_interval_notifier_ops drm_gpusvm_notifier_ops = { * * This function initializes the GPU SVM. * + * Note: If only using the simple drm_gpusvm_pages API (get/unmap/free), + * then only @gpusvm, @name, and @drm are expected. However, the same base + * @gpusvm can also be used with both modes together in which case the full + * setup is needed, where the core drm_gpusvm_pages API will simply never use + * the other fields. + * * Return: 0 on success, a negative error code on failure. */ int drm_gpusvm_init(struct drm_gpusvm *gpusvm, @@ -383,8 +389,16 @@ int drm_gpusvm_init(struct drm_gpusvm *gpusvm, const struct drm_gpusvm_ops *ops, const unsigned long *chunk_sizes, int num_chunks) { - if (!ops->invalidate || !num_chunks) - return -EINVAL; + if (mm) { + if (!ops->invalidate || !num_chunks) + return -EINVAL; + mmgrab(mm); + } else { + /* No full SVM mode, only core drm_gpusvm_pages API. */ + if (ops || num_chunks || mm_range || notifier_size || + device_private_page_owner) + return -EINVAL; + } gpusvm->name = name; gpusvm->drm = drm; @@ -397,7 +411,6 @@ int drm_gpusvm_init(struct drm_gpusvm *gpusvm, gpusvm->chunk_sizes = chunk_sizes; gpusvm->num_chunks = num_chunks; - mmgrab(mm); gpusvm->root = RB_ROOT_CACHED; INIT_LIST_HEAD(&gpusvm->notifier_list); @@ -489,7 +502,8 @@ void drm_gpusvm_fini(struct drm_gpusvm *gpusvm) drm_gpusvm_range_remove(gpusvm, range); } - mmdrop(gpusvm->mm); + if (gpusvm->mm) + mmdrop(gpusvm->mm); WARN_ON(!RB_EMPTY_ROOT(&gpusvm->root.rb_root)); } EXPORT_SYMBOL_GPL(drm_gpusvm_fini); @@ -629,13 +643,42 @@ drm_gpusvm_range_alloc(struct drm_gpusvm *gpusvm, range->itree.start = ALIGN_DOWN(fault_addr, chunk_size); range->itree.last = ALIGN(fault_addr + 1, chunk_size) - 1; INIT_LIST_HEAD(&range->entry); - range->notifier_seq = LONG_MAX; - range->flags.migrate_devmem = migrate_devmem ? 1 : 0; + range->pages.notifier_seq = LONG_MAX; + range->pages.flags.migrate_devmem = migrate_devmem ? 1 : 0; return range; } /** + * drm_gpusvm_hmm_pfn_to_order() - Get the largest CPU mapping order. + * @hmm_pfn: The current hmm_pfn. + * @hmm_pfn_index: Index of the @hmm_pfn within the pfn array. + * @npages: Number of pages within the pfn array i.e the hmm range size. + * + * To allow skipping PFNs with the same flags (like when they belong to + * the same huge PTE) when looping over the pfn array, take a given a hmm_pfn, + * and return the largest order that will fit inside the CPU PTE, but also + * crucially accounting for the original hmm range boundaries. + * + * Return: The largest order that will safely fit within the size of the hmm_pfn + * CPU PTE. + */ +static unsigned int drm_gpusvm_hmm_pfn_to_order(unsigned long hmm_pfn, + unsigned long hmm_pfn_index, + unsigned long npages) +{ + unsigned long size; + + size = 1UL << hmm_pfn_to_map_order(hmm_pfn); + size -= (hmm_pfn & ~HMM_PFN_FLAGS) & (size - 1); + hmm_pfn_index += size; + if (hmm_pfn_index > npages) + size -= (hmm_pfn_index - npages); + + return ilog2(size); +} + +/** * drm_gpusvm_check_pages() - Check pages * @gpusvm: Pointer to the GPU SVM structure * @notifier: Pointer to the GPU SVM notifier structure @@ -693,7 +736,7 @@ static bool drm_gpusvm_check_pages(struct drm_gpusvm *gpusvm, err = -EFAULT; goto err_free; } - i += 0x1 << hmm_pfn_to_map_order(pfns[i]); + i += 0x1 << drm_gpusvm_hmm_pfn_to_order(pfns[i], i, npages); } err_free: @@ -951,31 +994,31 @@ err_mmunlock: EXPORT_SYMBOL_GPL(drm_gpusvm_range_find_or_insert); /** - * __drm_gpusvm_range_unmap_pages() - Unmap pages associated with a GPU SVM range (internal) + * __drm_gpusvm_unmap_pages() - Unmap pages associated with GPU SVM pages (internal) * @gpusvm: Pointer to the GPU SVM structure - * @range: Pointer to the GPU SVM range structure + * @svm_pages: Pointer to the GPU SVM pages structure * @npages: Number of pages to unmap * - * This function unmap pages associated with a GPU SVM range. Assumes and + * This function unmap pages associated with a GPU SVM pages struct. Assumes and * asserts correct locking is in place when called. */ -static void __drm_gpusvm_range_unmap_pages(struct drm_gpusvm *gpusvm, - struct drm_gpusvm_range *range, - unsigned long npages) +static void __drm_gpusvm_unmap_pages(struct drm_gpusvm *gpusvm, + struct drm_gpusvm_pages *svm_pages, + unsigned long npages) { - unsigned long i, j; - struct drm_pagemap *dpagemap = range->dpagemap; + struct drm_pagemap *dpagemap = svm_pages->dpagemap; struct device *dev = gpusvm->drm->dev; + unsigned long i, j; lockdep_assert_held(&gpusvm->notifier_lock); - if (range->flags.has_dma_mapping) { - struct drm_gpusvm_range_flags flags = { - .__flags = range->flags.__flags, + if (svm_pages->flags.has_dma_mapping) { + struct drm_gpusvm_pages_flags flags = { + .__flags = svm_pages->flags.__flags, }; for (i = 0, j = 0; i < npages; j++) { - struct drm_pagemap_addr *addr = &range->dma_addr[j]; + struct drm_pagemap_addr *addr = &svm_pages->dma_addr[j]; if (addr->proto == DRM_INTERCONNECT_SYSTEM) dma_unmap_page(dev, @@ -991,31 +1034,52 @@ static void __drm_gpusvm_range_unmap_pages(struct drm_gpusvm *gpusvm, /* WRITE_ONCE pairs with READ_ONCE for opportunistic checks */ flags.has_devmem_pages = false; flags.has_dma_mapping = false; - WRITE_ONCE(range->flags.__flags, flags.__flags); + WRITE_ONCE(svm_pages->flags.__flags, flags.__flags); - range->dpagemap = NULL; + svm_pages->dpagemap = NULL; } } /** - * drm_gpusvm_range_free_pages() - Free pages associated with a GPU SVM range + * __drm_gpusvm_free_pages() - Free dma array associated with GPU SVM pages * @gpusvm: Pointer to the GPU SVM structure - * @range: Pointer to the GPU SVM range structure + * @svm_pages: Pointer to the GPU SVM pages structure * * This function frees the dma address array associated with a GPU SVM range. */ -static void drm_gpusvm_range_free_pages(struct drm_gpusvm *gpusvm, - struct drm_gpusvm_range *range) +static void __drm_gpusvm_free_pages(struct drm_gpusvm *gpusvm, + struct drm_gpusvm_pages *svm_pages) { lockdep_assert_held(&gpusvm->notifier_lock); - if (range->dma_addr) { - kvfree(range->dma_addr); - range->dma_addr = NULL; + if (svm_pages->dma_addr) { + kvfree(svm_pages->dma_addr); + svm_pages->dma_addr = NULL; } } /** + * drm_gpusvm_free_pages() - Free dma-mapping associated with GPU SVM pages + * struct + * @gpusvm: Pointer to the GPU SVM structure + * @svm_pages: Pointer to the GPU SVM pages structure + * @npages: Number of mapped pages + * + * This function unmaps and frees the dma address array associated with a GPU + * SVM pages struct. + */ +void drm_gpusvm_free_pages(struct drm_gpusvm *gpusvm, + struct drm_gpusvm_pages *svm_pages, + unsigned long npages) +{ + drm_gpusvm_notifier_lock(gpusvm); + __drm_gpusvm_unmap_pages(gpusvm, svm_pages, npages); + __drm_gpusvm_free_pages(gpusvm, svm_pages); + drm_gpusvm_notifier_unlock(gpusvm); +} +EXPORT_SYMBOL_GPL(drm_gpusvm_free_pages); + +/** * drm_gpusvm_range_remove() - Remove GPU SVM range * @gpusvm: Pointer to the GPU SVM structure * @range: Pointer to the GPU SVM range to be removed @@ -1040,8 +1104,8 @@ void drm_gpusvm_range_remove(struct drm_gpusvm *gpusvm, return; drm_gpusvm_notifier_lock(gpusvm); - __drm_gpusvm_range_unmap_pages(gpusvm, range, npages); - drm_gpusvm_range_free_pages(gpusvm, range); + __drm_gpusvm_unmap_pages(gpusvm, &range->pages, npages); + __drm_gpusvm_free_pages(gpusvm, &range->pages); __drm_gpusvm_range_remove(notifier, range); drm_gpusvm_notifier_unlock(gpusvm); @@ -1107,6 +1171,28 @@ void drm_gpusvm_range_put(struct drm_gpusvm_range *range) EXPORT_SYMBOL_GPL(drm_gpusvm_range_put); /** + * drm_gpusvm_pages_valid() - GPU SVM range pages valid + * @gpusvm: Pointer to the GPU SVM structure + * @svm_pages: Pointer to the GPU SVM pages structure + * + * This function determines if a GPU SVM range pages are valid. Expected be + * called holding gpusvm->notifier_lock and as the last step before committing a + * GPU binding. This is akin to a notifier seqno check in the HMM documentation + * but due to wider notifiers (i.e., notifiers which span multiple ranges) this + * function is required for finer grained checking (i.e., per range) if pages + * are valid. + * + * Return: True if GPU SVM range has valid pages, False otherwise + */ +static bool drm_gpusvm_pages_valid(struct drm_gpusvm *gpusvm, + struct drm_gpusvm_pages *svm_pages) +{ + lockdep_assert_held(&gpusvm->notifier_lock); + + return svm_pages->flags.has_devmem_pages || svm_pages->flags.has_dma_mapping; +} + +/** * drm_gpusvm_range_pages_valid() - GPU SVM range pages valid * @gpusvm: Pointer to the GPU SVM structure * @range: Pointer to the GPU SVM range structure @@ -1123,9 +1209,7 @@ EXPORT_SYMBOL_GPL(drm_gpusvm_range_put); bool drm_gpusvm_range_pages_valid(struct drm_gpusvm *gpusvm, struct drm_gpusvm_range *range) { - lockdep_assert_held(&gpusvm->notifier_lock); - - return range->flags.has_devmem_pages || range->flags.has_dma_mapping; + return drm_gpusvm_pages_valid(gpusvm, &range->pages); } EXPORT_SYMBOL_GPL(drm_gpusvm_range_pages_valid); @@ -1139,66 +1223,71 @@ EXPORT_SYMBOL_GPL(drm_gpusvm_range_pages_valid); * * Return: True if GPU SVM range has valid pages, False otherwise */ -static bool -drm_gpusvm_range_pages_valid_unlocked(struct drm_gpusvm *gpusvm, - struct drm_gpusvm_range *range) +static bool drm_gpusvm_pages_valid_unlocked(struct drm_gpusvm *gpusvm, + struct drm_gpusvm_pages *svm_pages) { bool pages_valid; - if (!range->dma_addr) + if (!svm_pages->dma_addr) return false; drm_gpusvm_notifier_lock(gpusvm); - pages_valid = drm_gpusvm_range_pages_valid(gpusvm, range); + pages_valid = drm_gpusvm_pages_valid(gpusvm, svm_pages); if (!pages_valid) - drm_gpusvm_range_free_pages(gpusvm, range); + __drm_gpusvm_free_pages(gpusvm, svm_pages); drm_gpusvm_notifier_unlock(gpusvm); return pages_valid; } /** - * drm_gpusvm_range_get_pages() - Get pages for a GPU SVM range + * drm_gpusvm_get_pages() - Get pages and populate GPU SVM pages struct * @gpusvm: Pointer to the GPU SVM structure - * @range: Pointer to the GPU SVM range structure + * @svm_pages: The SVM pages to populate. This will contain the dma-addresses + * @mm: The mm corresponding to the CPU range + * @notifier: The corresponding notifier for the given CPU range + * @pages_start: Start CPU address for the pages + * @pages_end: End CPU address for the pages (exclusive) * @ctx: GPU SVM context * - * This function gets pages for a GPU SVM range and ensures they are mapped for - * DMA access. + * This function gets and maps pages for CPU range and ensures they are + * mapped for DMA access. * * Return: 0 on success, negative error code on failure. */ -int drm_gpusvm_range_get_pages(struct drm_gpusvm *gpusvm, - struct drm_gpusvm_range *range, - const struct drm_gpusvm_ctx *ctx) +int drm_gpusvm_get_pages(struct drm_gpusvm *gpusvm, + struct drm_gpusvm_pages *svm_pages, + struct mm_struct *mm, + struct mmu_interval_notifier *notifier, + unsigned long pages_start, unsigned long pages_end, + const struct drm_gpusvm_ctx *ctx) { - struct mmu_interval_notifier *notifier = &range->notifier->notifier; struct hmm_range hmm_range = { .default_flags = HMM_PFN_REQ_FAULT | (ctx->read_only ? 0 : HMM_PFN_REQ_WRITE), .notifier = notifier, - .start = drm_gpusvm_range_start(range), - .end = drm_gpusvm_range_end(range), + .start = pages_start, + .end = pages_end, .dev_private_owner = gpusvm->device_private_page_owner, }; - struct mm_struct *mm = gpusvm->mm; void *zdd; unsigned long timeout = jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT); unsigned long i, j; - unsigned long npages = npages_in_range(drm_gpusvm_range_start(range), - drm_gpusvm_range_end(range)); + unsigned long npages = npages_in_range(pages_start, pages_end); unsigned long num_dma_mapped; unsigned int order = 0; unsigned long *pfns; int err = 0; struct dev_pagemap *pagemap; struct drm_pagemap *dpagemap; - struct drm_gpusvm_range_flags flags; + struct drm_gpusvm_pages_flags flags; + enum dma_data_direction dma_dir = ctx->read_only ? DMA_TO_DEVICE : + DMA_BIDIRECTIONAL; retry: hmm_range.notifier_seq = mmu_interval_read_begin(notifier); - if (drm_gpusvm_range_pages_valid_unlocked(gpusvm, range)) + if (drm_gpusvm_pages_valid_unlocked(gpusvm, svm_pages)) goto set_seqno; pfns = kvmalloc_array(npages, sizeof(*pfns), GFP_KERNEL); @@ -1238,7 +1327,7 @@ map_pages: */ drm_gpusvm_notifier_lock(gpusvm); - flags.__flags = range->flags.__flags; + flags.__flags = svm_pages->flags.__flags; if (flags.unmapped) { drm_gpusvm_notifier_unlock(gpusvm); err = -EFAULT; @@ -1251,13 +1340,12 @@ map_pages: goto retry; } - if (!range->dma_addr) { + if (!svm_pages->dma_addr) { /* Unlock and restart mapping to allocate memory. */ drm_gpusvm_notifier_unlock(gpusvm); - range->dma_addr = kvmalloc_array(npages, - sizeof(*range->dma_addr), - GFP_KERNEL); - if (!range->dma_addr) { + svm_pages->dma_addr = + kvmalloc_array(npages, sizeof(*svm_pages->dma_addr), GFP_KERNEL); + if (!svm_pages->dma_addr) { err = -ENOMEM; goto err_free; } @@ -1270,7 +1358,7 @@ map_pages: for (i = 0, j = 0; i < npages; ++j) { struct page *page = hmm_pfn_to_page(pfns[i]); - order = hmm_pfn_to_map_order(pfns[i]); + order = drm_gpusvm_hmm_pfn_to_order(pfns[i], i, npages); if (is_device_private_page(page) || is_device_coherent_page(page)) { if (zdd != page->zone_device_data && i > 0) { @@ -1296,13 +1384,13 @@ map_pages: goto err_unmap; } } - range->dma_addr[j] = + svm_pages->dma_addr[j] = dpagemap->ops->device_map(dpagemap, gpusvm->drm->dev, page, order, - DMA_BIDIRECTIONAL); + dma_dir); if (dma_mapping_error(gpusvm->drm->dev, - range->dma_addr[j].addr)) { + svm_pages->dma_addr[j].addr)) { err = -EFAULT; goto err_unmap; } @@ -1322,15 +1410,15 @@ map_pages: addr = dma_map_page(gpusvm->drm->dev, page, 0, PAGE_SIZE << order, - DMA_BIDIRECTIONAL); + dma_dir); if (dma_mapping_error(gpusvm->drm->dev, addr)) { err = -EFAULT; goto err_unmap; } - range->dma_addr[j] = drm_pagemap_addr_encode + svm_pages->dma_addr[j] = drm_pagemap_addr_encode (addr, DRM_INTERCONNECT_SYSTEM, order, - DMA_BIDIRECTIONAL); + dma_dir); } i += 1 << order; num_dma_mapped = i; @@ -1339,21 +1427,21 @@ map_pages: if (pagemap) { flags.has_devmem_pages = true; - range->dpagemap = dpagemap; + svm_pages->dpagemap = dpagemap; } /* WRITE_ONCE pairs with READ_ONCE for opportunistic checks */ - WRITE_ONCE(range->flags.__flags, flags.__flags); + WRITE_ONCE(svm_pages->flags.__flags, flags.__flags); drm_gpusvm_notifier_unlock(gpusvm); kvfree(pfns); set_seqno: - range->notifier_seq = hmm_range.notifier_seq; + svm_pages->notifier_seq = hmm_range.notifier_seq; return 0; err_unmap: - __drm_gpusvm_range_unmap_pages(gpusvm, range, num_dma_mapped); + __drm_gpusvm_unmap_pages(gpusvm, svm_pages, num_dma_mapped); drm_gpusvm_notifier_unlock(gpusvm); err_free: kvfree(pfns); @@ -1361,11 +1449,62 @@ err_free: goto retry; return err; } +EXPORT_SYMBOL_GPL(drm_gpusvm_get_pages); + +/** + * drm_gpusvm_range_get_pages() - Get pages for a GPU SVM range + * @gpusvm: Pointer to the GPU SVM structure + * @range: Pointer to the GPU SVM range structure + * @ctx: GPU SVM context + * + * This function gets pages for a GPU SVM range and ensures they are mapped for + * DMA access. + * + * Return: 0 on success, negative error code on failure. + */ +int drm_gpusvm_range_get_pages(struct drm_gpusvm *gpusvm, + struct drm_gpusvm_range *range, + const struct drm_gpusvm_ctx *ctx) +{ + return drm_gpusvm_get_pages(gpusvm, &range->pages, gpusvm->mm, + &range->notifier->notifier, + drm_gpusvm_range_start(range), + drm_gpusvm_range_end(range), ctx); +} EXPORT_SYMBOL_GPL(drm_gpusvm_range_get_pages); /** + * drm_gpusvm_unmap_pages() - Unmap GPU svm pages + * @gpusvm: Pointer to the GPU SVM structure + * @svm_pages: Pointer to the GPU SVM pages structure + * @npages: Number of pages in @svm_pages. + * @ctx: GPU SVM context + * + * This function unmaps pages associated with a GPU SVM pages struct. If + * @in_notifier is set, it is assumed that gpusvm->notifier_lock is held in + * write mode; if it is clear, it acquires gpusvm->notifier_lock in read mode. + * Must be called in the invalidate() callback of the corresponding notifier for + * IOMMU security model. + */ +void drm_gpusvm_unmap_pages(struct drm_gpusvm *gpusvm, + struct drm_gpusvm_pages *svm_pages, + unsigned long npages, + const struct drm_gpusvm_ctx *ctx) +{ + if (ctx->in_notifier) + lockdep_assert_held_write(&gpusvm->notifier_lock); + else + drm_gpusvm_notifier_lock(gpusvm); + + __drm_gpusvm_unmap_pages(gpusvm, svm_pages, npages); + + if (!ctx->in_notifier) + drm_gpusvm_notifier_unlock(gpusvm); +} +EXPORT_SYMBOL_GPL(drm_gpusvm_unmap_pages); + +/** * drm_gpusvm_range_unmap_pages() - Unmap pages associated with a GPU SVM range - * drm_gpusvm_range_evict() - Evict GPU SVM range * @gpusvm: Pointer to the GPU SVM structure * @range: Pointer to the GPU SVM range structure * @ctx: GPU SVM context @@ -1383,15 +1522,7 @@ void drm_gpusvm_range_unmap_pages(struct drm_gpusvm *gpusvm, unsigned long npages = npages_in_range(drm_gpusvm_range_start(range), drm_gpusvm_range_end(range)); - if (ctx->in_notifier) - lockdep_assert_held_write(&gpusvm->notifier_lock); - else - drm_gpusvm_notifier_lock(gpusvm); - - __drm_gpusvm_range_unmap_pages(gpusvm, range, npages); - - if (!ctx->in_notifier) - drm_gpusvm_notifier_unlock(gpusvm); + return drm_gpusvm_unmap_pages(gpusvm, &range->pages, npages, ctx); } EXPORT_SYMBOL_GPL(drm_gpusvm_range_unmap_pages); @@ -1489,10 +1620,10 @@ void drm_gpusvm_range_set_unmapped(struct drm_gpusvm_range *range, { lockdep_assert_held_write(&range->gpusvm->notifier_lock); - range->flags.unmapped = true; + range->pages.flags.unmapped = true; if (drm_gpusvm_range_start(range) < mmu_range->start || drm_gpusvm_range_end(range) > mmu_range->end) - range->flags.partial_unmap = true; + range->pages.flags.partial_unmap = true; } EXPORT_SYMBOL_GPL(drm_gpusvm_range_set_unmapped); diff --git a/drivers/gpu/drm/drm_gpuvm.c b/drivers/gpu/drm/drm_gpuvm.c index d6bea8a4fffd..a52e95555549 100644 --- a/drivers/gpu/drm/drm_gpuvm.c +++ b/drivers/gpu/drm/drm_gpuvm.c @@ -40,7 +40,7 @@ * mapping's backing &drm_gem_object buffers. * * &drm_gem_object buffers maintain a list of &drm_gpuva objects representing - * all existent GPU VA mappings using this &drm_gem_object as backing buffer. + * all existing GPU VA mappings using this &drm_gem_object as backing buffer. * * GPU VAs can be flagged as sparse, such that drivers may use GPU VAs to also * keep track of sparse PTEs in order to support Vulkan 'Sparse Resources'. @@ -72,7 +72,7 @@ * but it can also be a 'dummy' object, which can be allocated with * drm_gpuvm_resv_object_alloc(). * - * In order to connect a struct drm_gpuva its backing &drm_gem_object each + * In order to connect a struct drm_gpuva to its backing &drm_gem_object each * &drm_gem_object maintains a list of &drm_gpuvm_bo structures, and each * &drm_gpuvm_bo contains a list of &drm_gpuva structures. * @@ -81,7 +81,7 @@ * This is ensured by the API through drm_gpuvm_bo_obtain() and * drm_gpuvm_bo_obtain_prealloc() which first look into the corresponding * &drm_gem_object list of &drm_gpuvm_bos for an existing instance of this - * particular combination. If not existent a new instance is created and linked + * particular combination. If not present, a new instance is created and linked * to the &drm_gem_object. * * &drm_gpuvm_bo structures, since unique for a given &drm_gpuvm, are also used @@ -108,7 +108,7 @@ * sequence of operations to satisfy a given map or unmap request. * * Therefore the DRM GPU VA manager provides an algorithm implementing splitting - * and merging of existent GPU VA mappings with the ones that are requested to + * and merging of existing GPU VA mappings with the ones that are requested to * be mapped or unmapped. This feature is required by the Vulkan API to * implement Vulkan 'Sparse Memory Bindings' - drivers UAPIs often refer to this * as VM BIND. @@ -119,7 +119,7 @@ * execute in order to integrate the new mapping cleanly into the current state * of the GPU VA space. * - * Depending on how the new GPU VA mapping intersects with the existent mappings + * Depending on how the new GPU VA mapping intersects with the existing mappings * of the GPU VA space the &drm_gpuvm_ops callbacks contain an arbitrary amount * of unmap operations, a maximum of two remap operations and a single map * operation. The caller might receive no callback at all if no operation is @@ -139,16 +139,16 @@ * one unmap operation and one or two map operations, such that drivers can * derive the page table update delta accordingly. * - * Note that there can't be more than two existent mappings to split up, one at + * Note that there can't be more than two existing mappings to split up, one at * the beginning and one at the end of the new mapping, hence there is a * maximum of two remap operations. * * Analogous to drm_gpuvm_sm_map() drm_gpuvm_sm_unmap() uses &drm_gpuvm_ops to * call back into the driver in order to unmap a range of GPU VA space. The - * logic behind this function is way simpler though: For all existent mappings + * logic behind this function is way simpler though: For all existing mappings * enclosed by the given range unmap operations are created. For mappings which - * are only partically located within the given range, remap operations are - * created such that those mappings are split up and re-mapped partically. + * are only partially located within the given range, remap operations are + * created such that those mappings are split up and re-mapped partially. * * As an alternative to drm_gpuvm_sm_map() and drm_gpuvm_sm_unmap(), * drm_gpuvm_sm_map_ops_create() and drm_gpuvm_sm_unmap_ops_create() can be used @@ -168,7 +168,7 @@ * provided helper functions drm_gpuva_map(), drm_gpuva_remap() and * drm_gpuva_unmap() instead. * - * The following diagram depicts the basic relationships of existent GPU VA + * The following diagram depicts the basic relationships of existing GPU VA * mappings, a newly requested mapping and the resulting mappings as implemented * by drm_gpuvm_sm_map() - it doesn't cover any arbitrary combinations of these. * @@ -218,7 +218,7 @@ * * * 4) Existent mapping is a left aligned subset of the requested one, hence - * replace the existent one. + * replace the existing one. * * :: * @@ -236,9 +236,9 @@ * and/or non-contiguous BO offset. * * - * 5) Requested mapping's range is a left aligned subset of the existent one, + * 5) Requested mapping's range is a left aligned subset of the existing one, * but backed by a different BO. Hence, map the requested mapping and split - * the existent one adjusting its BO offset. + * the existing one adjusting its BO offset. * * :: * @@ -271,9 +271,9 @@ * new: |-----|-----| (a.bo_offset=n, a'.bo_offset=n+1) * * - * 7) Requested mapping's range is a right aligned subset of the existent one, + * 7) Requested mapping's range is a right aligned subset of the existing one, * but backed by a different BO. Hence, map the requested mapping and split - * the existent one, without adjusting the BO offset. + * the existing one, without adjusting the BO offset. * * :: * @@ -304,7 +304,7 @@ * * 9) Existent mapping is overlapped at the end by the requested mapping backed * by a different BO. Hence, map the requested mapping and split up the - * existent one, without adjusting the BO offset. + * existing one, without adjusting the BO offset. * * :: * @@ -334,9 +334,9 @@ * new: |-----|-----------| (a'.bo_offset=n, a.bo_offset=n+1) * * - * 11) Requested mapping's range is a centered subset of the existent one + * 11) Requested mapping's range is a centered subset of the existing one * having a different backing BO. Hence, map the requested mapping and split - * up the existent one in two mappings, adjusting the BO offset of the right + * up the existing one in two mappings, adjusting the BO offset of the right * one accordingly. * * :: @@ -351,7 +351,7 @@ * new: |-----|-----|-----| (a.bo_offset=n,b.bo_offset=m,a'.bo_offset=n+2) * * - * 12) Requested mapping is a contiguous subset of the existent one. Split it + * 12) Requested mapping is a contiguous subset of the existing one. Split it * up, but indicate that the backing PTEs could be kept. * * :: @@ -367,7 +367,7 @@ * * * 13) Existent mapping is a right aligned subset of the requested one, hence - * replace the existent one. + * replace the existing one. * * :: * @@ -386,7 +386,7 @@ * * * 14) Existent mapping is a centered subset of the requested one, hence - * replace the existent one. + * replace the existing one. * * :: * @@ -406,7 +406,7 @@ * * 15) Existent mappings is overlapped at the beginning by the requested mapping * backed by a different BO. Hence, map the requested mapping and split up - * the existent one, adjusting its BO offset accordingly. + * the existing one, adjusting its BO offset accordingly. * * :: * @@ -497,8 +497,7 @@ * DRM GPUVM also does not take care of the locking of the backing * &drm_gem_object buffers GPU VA lists and &drm_gpuvm_bo abstractions by * itself; drivers are responsible to enforce mutual exclusion using either the - * GEMs dma_resv lock or alternatively a driver specific external lock. For the - * latter see also drm_gem_gpuva_set_lock(). + * GEMs dma_resv lock or the GEMs gpuva.lock mutex. * * However, DRM GPUVM contains lockdep checks to ensure callers of its API hold * the corresponding lock whenever the &drm_gem_objects GPU VA list is accessed @@ -534,8 +533,8 @@ * make use of them. * * The below code is strictly limited to illustrate the generic usage pattern. - * To maintain simplicitly, it doesn't make use of any abstractions for common - * code, different (asyncronous) stages with fence signalling critical paths, + * To maintain simplicity, it doesn't make use of any abstractions for common + * code, different (asynchronous) stages with fence signalling critical paths, * any other helpers or error handling in terms of freeing memory and dropping * previously taken locks. * @@ -544,7 +543,7 @@ * // Allocates a new &drm_gpuva. * struct drm_gpuva * driver_gpuva_alloc(void); * - * // Typically drivers would embedd the &drm_gpuvm and &drm_gpuva + * // Typically drivers would embed the &drm_gpuvm and &drm_gpuva * // structure in individual driver structures and lock the dma-resv with * // drm_exec or similar helpers. * int driver_mapping_create(struct drm_gpuvm *gpuvm, @@ -652,7 +651,7 @@ * .sm_step_unmap = driver_gpuva_unmap, * }; * - * // Typically drivers would embedd the &drm_gpuvm and &drm_gpuva + * // Typically drivers would embed the &drm_gpuvm and &drm_gpuva * // structure in individual driver structures and lock the dma-resv with * // drm_exec or similar helpers. * int driver_mapping_create(struct drm_gpuvm *gpuvm, @@ -750,7 +749,7 @@ * * This helper is here to provide lockless list iteration. Lockless as in, the * iterator releases the lock immediately after picking the first element from - * the list, so list insertion deletion can happen concurrently. + * the list, so list insertion and deletion can happen concurrently. * * Elements popped from the original list are kept in a local list, so removal * and is_empty checks can still happen while we're iterating the list. @@ -1230,7 +1229,7 @@ drm_gpuvm_prepare_objects_locked(struct drm_gpuvm *gpuvm, } /** - * drm_gpuvm_prepare_objects() - prepare all assoiciated BOs + * drm_gpuvm_prepare_objects() - prepare all associated BOs * @gpuvm: the &drm_gpuvm * @exec: the &drm_exec locking context * @num_fences: the amount of &dma_fences to reserve @@ -1300,13 +1299,13 @@ drm_gpuvm_prepare_range(struct drm_gpuvm *gpuvm, struct drm_exec *exec, EXPORT_SYMBOL_GPL(drm_gpuvm_prepare_range); /** - * drm_gpuvm_exec_lock() - lock all dma-resv of all assoiciated BOs + * drm_gpuvm_exec_lock() - lock all dma-resv of all associated BOs * @vm_exec: the &drm_gpuvm_exec wrapper * * Acquires all dma-resv locks of all &drm_gem_objects the given * &drm_gpuvm contains mappings of. * - * Addionally, when calling this function with struct drm_gpuvm_exec::extra + * Additionally, when calling this function with struct drm_gpuvm_exec::extra * being set the driver receives the given @fn callback to lock additional * dma-resv in the context of the &drm_gpuvm_exec instance. Typically, drivers * would call drm_exec_prepare_obj() from within this callback. @@ -1363,7 +1362,7 @@ fn_lock_array(struct drm_gpuvm_exec *vm_exec) } /** - * drm_gpuvm_exec_lock_array() - lock all dma-resv of all assoiciated BOs + * drm_gpuvm_exec_lock_array() - lock all dma-resv of all associated BOs * @vm_exec: the &drm_gpuvm_exec wrapper * @objs: additional &drm_gem_objects to lock * @num_objs: the number of additional &drm_gem_objects to lock @@ -1582,7 +1581,7 @@ drm_gpuvm_bo_destroy(struct kref *kref) drm_gpuvm_bo_list_del(vm_bo, extobj, lock); drm_gpuvm_bo_list_del(vm_bo, evict, lock); - drm_gem_gpuva_assert_lock_held(obj); + drm_gem_gpuva_assert_lock_held(gpuvm, obj); list_del(&vm_bo->list.entry.gem); if (ops && ops->vm_bo_free) @@ -1603,7 +1602,8 @@ drm_gpuvm_bo_destroy(struct kref *kref) * If the reference count drops to zero, the &gpuvm_bo is destroyed, which * includes removing it from the GEMs gpuva list. Hence, if a call to this * function can potentially let the reference count drop to zero the caller must - * hold the dma-resv or driver specific GEM gpuva lock. + * hold the lock that the GEM uses for its gpuva list (either the GEM's + * dma-resv or gpuva.lock mutex). * * This function may only be called from non-atomic context. * @@ -1627,7 +1627,7 @@ __drm_gpuvm_bo_find(struct drm_gpuvm *gpuvm, { struct drm_gpuvm_bo *vm_bo; - drm_gem_gpuva_assert_lock_held(obj); + drm_gem_gpuva_assert_lock_held(gpuvm, obj); drm_gem_for_each_gpuvm_bo(vm_bo, obj) if (vm_bo->vm == gpuvm) return vm_bo; @@ -1658,7 +1658,7 @@ drm_gpuvm_bo_find(struct drm_gpuvm *gpuvm, EXPORT_SYMBOL_GPL(drm_gpuvm_bo_find); /** - * drm_gpuvm_bo_obtain() - obtains and instance of the &drm_gpuvm_bo for the + * drm_gpuvm_bo_obtain() - obtains an instance of the &drm_gpuvm_bo for the * given &drm_gpuvm and &drm_gem_object * @gpuvm: The &drm_gpuvm the @obj is mapped in. * @obj: The &drm_gem_object being mapped in the @gpuvm. @@ -1686,7 +1686,7 @@ drm_gpuvm_bo_obtain(struct drm_gpuvm *gpuvm, if (!vm_bo) return ERR_PTR(-ENOMEM); - drm_gem_gpuva_assert_lock_held(obj); + drm_gem_gpuva_assert_lock_held(gpuvm, obj); list_add_tail(&vm_bo->list.entry.gem, &obj->gpuva.list); return vm_bo; @@ -1694,7 +1694,7 @@ drm_gpuvm_bo_obtain(struct drm_gpuvm *gpuvm, EXPORT_SYMBOL_GPL(drm_gpuvm_bo_obtain); /** - * drm_gpuvm_bo_obtain_prealloc() - obtains and instance of the &drm_gpuvm_bo + * drm_gpuvm_bo_obtain_prealloc() - obtains an instance of the &drm_gpuvm_bo * for the given &drm_gpuvm and &drm_gem_object * @__vm_bo: A pre-allocated struct drm_gpuvm_bo. * @@ -1722,7 +1722,7 @@ drm_gpuvm_bo_obtain_prealloc(struct drm_gpuvm_bo *__vm_bo) return vm_bo; } - drm_gem_gpuva_assert_lock_held(obj); + drm_gem_gpuva_assert_lock_held(gpuvm, obj); list_add_tail(&__vm_bo->list.entry.gem, &obj->gpuva.list); return __vm_bo; @@ -1758,7 +1758,7 @@ EXPORT_SYMBOL_GPL(drm_gpuvm_bo_extobj_add); * @vm_bo: the &drm_gpuvm_bo to add or remove * @evict: indicates whether the object is evicted * - * Adds a &drm_gpuvm_bo to or removes it from the &drm_gpuvms evicted list. + * Adds a &drm_gpuvm_bo to or removes it from the &drm_gpuvm's evicted list. */ void drm_gpuvm_bo_evict(struct drm_gpuvm_bo *vm_bo, bool evict) @@ -1860,7 +1860,7 @@ __drm_gpuva_remove(struct drm_gpuva *va) * drm_gpuva_remove() - remove a &drm_gpuva * @va: the &drm_gpuva to remove * - * This removes the given &va from the underlaying tree. + * This removes the given &va from the underlying tree. * * It is safe to use this function using the safe versions of iterating the GPU * VA space, such as drm_gpuvm_for_each_va_safe() and @@ -1894,8 +1894,7 @@ EXPORT_SYMBOL_GPL(drm_gpuva_remove); * reference of the latter is taken. * * This function expects the caller to protect the GEM's GPUVA list against - * concurrent access using either the GEMs dma_resv lock or a driver specific - * lock set through drm_gem_gpuva_set_lock(). + * concurrent access using either the GEM's dma-resv or gpuva.lock mutex. */ void drm_gpuva_link(struct drm_gpuva *va, struct drm_gpuvm_bo *vm_bo) @@ -1910,7 +1909,7 @@ drm_gpuva_link(struct drm_gpuva *va, struct drm_gpuvm_bo *vm_bo) va->vm_bo = drm_gpuvm_bo_get(vm_bo); - drm_gem_gpuva_assert_lock_held(obj); + drm_gem_gpuva_assert_lock_held(gpuvm, obj); list_add_tail(&va->gem.entry, &vm_bo->list.gpuva); } EXPORT_SYMBOL_GPL(drm_gpuva_link); @@ -1930,8 +1929,7 @@ EXPORT_SYMBOL_GPL(drm_gpuva_link); * the latter is dropped. * * This function expects the caller to protect the GEM's GPUVA list against - * concurrent access using either the GEMs dma_resv lock or a driver specific - * lock set through drm_gem_gpuva_set_lock(). + * concurrent access using either the GEM's dma-resv or gpuva.lock mutex. */ void drm_gpuva_unlink(struct drm_gpuva *va) @@ -1942,7 +1940,7 @@ drm_gpuva_unlink(struct drm_gpuva *va) if (unlikely(!obj)) return; - drm_gem_gpuva_assert_lock_held(obj); + drm_gem_gpuva_assert_lock_held(va->vm, obj); list_del_init(&va->gem.entry); va->vm_bo = NULL; @@ -2464,7 +2462,7 @@ EXPORT_SYMBOL_GPL(drm_gpuvm_sm_map); * * This function iterates the given range of the GPU VA space. It utilizes the * &drm_gpuvm_ops to call back into the driver providing the operations to - * unmap and, if required, split existent mappings. + * unmap and, if required, split existing mappings. * * Drivers may use these callbacks to update the GPU VA space right away within * the callback. In case the driver decides to copy and store the operations for @@ -2533,7 +2531,9 @@ static const struct drm_gpuvm_ops lock_ops = { * remapped, and locks+prepares (drm_exec_prepare_object()) objects that * will be newly mapped. * - * The expected usage is: + * The expected usage is:: + * + * .. code-block:: c * * vm_bind { * struct drm_exec exec; @@ -2574,7 +2574,7 @@ static const struct drm_gpuvm_ops lock_ops = { * required without the earlier DRIVER_OP_MAP. This is safe because we've * already locked the GEM object in the earlier DRIVER_OP_MAP step. * - * Returns: 0 on success or a negative error codec + * Returns: 0 on success or a negative error code */ int drm_gpuvm_sm_map_exec_lock(struct drm_gpuvm *gpuvm, @@ -2746,12 +2746,12 @@ err_free_ops: * @req: map request arguments * * This function creates a list of operations to perform splitting and merging - * of existent mapping(s) with the newly requested one. + * of existing mapping(s) with the newly requested one. * * The list can be iterated with &drm_gpuva_for_each_op and must be processed * in the given order. It can contain map, unmap and remap operations, but it * also can be empty if no operation is required, e.g. if the requested mapping - * already exists is the exact same way. + * already exists in the exact same way. * * There can be an arbitrary amount of unmap operations, a maximum of two remap * operations and a single map operation. The latter one represents the original @@ -2943,8 +2943,8 @@ EXPORT_SYMBOL_GPL(drm_gpuvm_prefetch_ops_create); * After the caller finished processing the returned &drm_gpuva_ops, they must * be freed with &drm_gpuva_ops_free. * - * It is the callers responsibility to protect the GEMs GPUVA list against - * concurrent access using the GEMs dma_resv lock. + * This function expects the caller to protect the GEM's GPUVA list against + * concurrent access using either the GEM's dma-resv or gpuva.lock mutex. * * Returns: a pointer to the &drm_gpuva_ops on success, an ERR_PTR on failure */ @@ -2956,7 +2956,7 @@ drm_gpuvm_bo_unmap_ops_create(struct drm_gpuvm_bo *vm_bo) struct drm_gpuva *va; int ret; - drm_gem_gpuva_assert_lock_held(vm_bo->obj); + drm_gem_gpuva_assert_lock_held(vm_bo->vm, vm_bo->obj); ops = kzalloc(sizeof(*ops), GFP_KERNEL); if (!ops) diff --git a/drivers/gpu/drm/drm_panel_backlight_quirks.c b/drivers/gpu/drm/drm_panel_backlight_quirks.c index 598f812b7cb3..537dc6dd0534 100644 --- a/drivers/gpu/drm/drm_panel_backlight_quirks.c +++ b/drivers/gpu/drm/drm_panel_backlight_quirks.c @@ -8,23 +8,26 @@ #include <drm/drm_edid.h> #include <drm/drm_utils.h> -struct drm_panel_min_backlight_quirk { - struct { - enum dmi_field field; - const char * const value; - } dmi_match; +struct drm_panel_match { + enum dmi_field field; + const char * const value; +}; + +struct drm_get_panel_backlight_quirk { + struct drm_panel_match dmi_match; + struct drm_panel_match dmi_match_other; struct drm_edid_ident ident; - u8 min_brightness; + struct drm_panel_backlight_quirk quirk; }; -static const struct drm_panel_min_backlight_quirk drm_panel_min_backlight_quirks[] = { +static const struct drm_get_panel_backlight_quirk drm_panel_min_backlight_quirks[] = { /* 13 inch matte panel */ { .dmi_match.field = DMI_BOARD_VENDOR, .dmi_match.value = "Framework", .ident.panel_id = drm_edid_encode_panel_id('B', 'O', 'E', 0x0bca), .ident.name = "NE135FBM-N41", - .min_brightness = 0, + .quirk = { .min_brightness = 1, }, }, /* 13 inch glossy panel */ { @@ -32,7 +35,7 @@ static const struct drm_panel_min_backlight_quirk drm_panel_min_backlight_quirks .dmi_match.value = "Framework", .ident.panel_id = drm_edid_encode_panel_id('B', 'O', 'E', 0x095f), .ident.name = "NE135FBM-N41", - .min_brightness = 0, + .quirk = { .min_brightness = 1, }, }, /* 13 inch 2.8k panel */ { @@ -40,56 +43,114 @@ static const struct drm_panel_min_backlight_quirk drm_panel_min_backlight_quirks .dmi_match.value = "Framework", .ident.panel_id = drm_edid_encode_panel_id('B', 'O', 'E', 0x0cb4), .ident.name = "NE135A1M-NY1", - .min_brightness = 0, + .quirk = { .min_brightness = 1, }, + }, + /* Steam Deck models */ + { + .dmi_match.field = DMI_SYS_VENDOR, + .dmi_match.value = "Valve", + .dmi_match_other.field = DMI_PRODUCT_NAME, + .dmi_match_other.value = "Jupiter", + .quirk = { .min_brightness = 1, }, + }, + { + .dmi_match.field = DMI_SYS_VENDOR, + .dmi_match.value = "Valve", + .dmi_match_other.field = DMI_PRODUCT_NAME, + .dmi_match_other.value = "Galileo", + .quirk = { .min_brightness = 1, }, + }, + /* Have OLED Panels with brightness issue when last byte is 0/1 */ + { + .dmi_match.field = DMI_SYS_VENDOR, + .dmi_match.value = "AYANEO", + .dmi_match_other.field = DMI_PRODUCT_NAME, + .dmi_match_other.value = "AYANEO 3", + .quirk = { .brightness_mask = 3, }, + }, + { + .dmi_match.field = DMI_SYS_VENDOR, + .dmi_match.value = "ZOTAC", + .dmi_match_other.field = DMI_BOARD_NAME, + .dmi_match_other.value = "G0A1W", + .quirk = { .brightness_mask = 3, }, + }, + { + .dmi_match.field = DMI_SYS_VENDOR, + .dmi_match.value = "ZOTAC", + .dmi_match_other.field = DMI_BOARD_NAME, + .dmi_match_other.value = "G1A1W", + .quirk = { .brightness_mask = 3, }, + }, + { + .dmi_match.field = DMI_SYS_VENDOR, + .dmi_match.value = "ONE-NETBOOK", + .dmi_match_other.field = DMI_PRODUCT_NAME, + .dmi_match_other.value = "ONEXPLAYER F1Pro", + .quirk = { .brightness_mask = 3, }, + }, + { + .dmi_match.field = DMI_SYS_VENDOR, + .dmi_match.value = "ONE-NETBOOK", + .dmi_match_other.field = DMI_PRODUCT_NAME, + .dmi_match_other.value = "ONEXPLAYER F1 EVA-02", + .quirk = { .brightness_mask = 3, }, }, }; -static bool drm_panel_min_backlight_quirk_matches(const struct drm_panel_min_backlight_quirk *quirk, - const struct drm_edid *edid) +static bool drm_panel_min_backlight_quirk_matches( + const struct drm_get_panel_backlight_quirk *quirk, + const struct drm_edid *edid) { - if (!dmi_match(quirk->dmi_match.field, quirk->dmi_match.value)) + if (quirk->dmi_match.field && + !dmi_match(quirk->dmi_match.field, quirk->dmi_match.value)) + return false; + + if (quirk->dmi_match_other.field && + !dmi_match(quirk->dmi_match_other.field, + quirk->dmi_match_other.value)) return false; - if (!drm_edid_match(edid, &quirk->ident)) + if (quirk->ident.panel_id && !drm_edid_match(edid, &quirk->ident)) return false; return true; } /** - * drm_get_panel_min_brightness_quirk - Get minimum supported brightness level for a panel. + * drm_get_panel_backlight_quirk - Get backlight quirks for a panel * @edid: EDID of the panel to check * * This function checks for platform specific (e.g. DMI based) quirks * providing info on the minimum backlight brightness for systems where this - * cannot be probed correctly from the hard-/firm-ware. + * cannot be probed correctly from the hard-/firm-ware and other sources. * * Returns: - * A negative error value or - * an override value in the range [0, 255] representing 0-100% to be scaled to - * the drivers target range. + * a drm_panel_backlight_quirk struct if a quirk was found, otherwise an + * error pointer. */ -int drm_get_panel_min_brightness_quirk(const struct drm_edid *edid) +const struct drm_panel_backlight_quirk * +drm_get_panel_backlight_quirk(const struct drm_edid *edid) { - const struct drm_panel_min_backlight_quirk *quirk; + const struct drm_get_panel_backlight_quirk *quirk; size_t i; if (!IS_ENABLED(CONFIG_DMI)) - return -ENODATA; + return ERR_PTR(-ENODATA); if (!edid) - return -EINVAL; + return ERR_PTR(-EINVAL); for (i = 0; i < ARRAY_SIZE(drm_panel_min_backlight_quirks); i++) { quirk = &drm_panel_min_backlight_quirks[i]; if (drm_panel_min_backlight_quirk_matches(quirk, edid)) - return quirk->min_brightness; + return &quirk->quirk; } - return -ENODATA; + return ERR_PTR(-ENODATA); } -EXPORT_SYMBOL(drm_get_panel_min_brightness_quirk); +EXPORT_SYMBOL(drm_get_panel_backlight_quirk); MODULE_DESCRIPTION("Quirks for panel backlight overrides"); MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/drm_panic_qr.rs b/drivers/gpu/drm/drm_panic_qr.rs index 09a9b452e8b7..50c286c5cee8 100644 --- a/drivers/gpu/drm/drm_panic_qr.rs +++ b/drivers/gpu/drm/drm_panic_qr.rs @@ -381,6 +381,26 @@ struct DecFifo { len: usize, } +// On arm32 architecture, dividing an `u64` by a constant will generate a call +// to `__aeabi_uldivmod` which is not present in the kernel. +// So use the multiply by inverse method for this architecture. +fn div10(val: u64) -> u64 { + if cfg!(target_arch = "arm") { + let val_h = val >> 32; + let val_l = val & 0xFFFFFFFF; + let b_h: u64 = 0x66666666; + let b_l: u64 = 0x66666667; + + let tmp1 = val_h * b_l + ((val_l * b_l) >> 32); + let tmp2 = val_l * b_h + (tmp1 & 0xffffffff); + let tmp3 = val_h * b_h + (tmp1 >> 32) + (tmp2 >> 32); + + tmp3 >> 2 + } else { + val / 10 + } +} + impl DecFifo { fn push(&mut self, data: u64, len: usize) { let mut chunk = data; @@ -389,7 +409,7 @@ impl DecFifo { } for i in 0..len { self.decimals[i] = (chunk % 10) as u8; - chunk /= 10; + chunk = div10(chunk); } self.len += len; } diff --git a/drivers/gpu/drm/drm_sysfs.c b/drivers/gpu/drm/drm_sysfs.c index a455c56dbbeb..b01ffa4d6509 100644 --- a/drivers/gpu/drm/drm_sysfs.c +++ b/drivers/gpu/drm/drm_sysfs.c @@ -18,6 +18,7 @@ #include <linux/gfp.h> #include <linux/i2c.h> #include <linux/kdev_t.h> +#include <linux/pci.h> #include <linux/property.h> #include <linux/slab.h> @@ -30,6 +31,8 @@ #include <drm/drm_property.h> #include <drm/drm_sysfs.h> +#include <asm/video.h> + #include "drm_internal.h" #include "drm_crtc_internal.h" @@ -508,6 +511,43 @@ void drm_sysfs_connector_property_event(struct drm_connector *connector, } EXPORT_SYMBOL(drm_sysfs_connector_property_event); +static ssize_t boot_display_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + return sysfs_emit(buf, "1\n"); +} +static DEVICE_ATTR_RO(boot_display); + +static struct attribute *display_attrs[] = { + &dev_attr_boot_display.attr, + NULL +}; + +static umode_t boot_display_visible(struct kobject *kobj, + struct attribute *a, int n) +{ + struct device *dev = kobj_to_dev(kobj)->parent; + + if (dev_is_pci(dev)) { + struct pci_dev *pdev = to_pci_dev(dev); + + if (video_is_primary_device(&pdev->dev)) + return a->mode; + } + + return 0; +} + +static const struct attribute_group display_attr_group = { + .attrs = display_attrs, + .is_visible = boot_display_visible, +}; + +static const struct attribute_group *card_dev_groups[] = { + &display_attr_group, + NULL +}; + struct device *drm_sysfs_minor_alloc(struct drm_minor *minor) { const char *minor_str; @@ -531,6 +571,7 @@ struct device *drm_sysfs_minor_alloc(struct drm_minor *minor) kdev->devt = MKDEV(DRM_MAJOR, minor->index); kdev->class = drm_class; + kdev->groups = card_dev_groups; kdev->type = &drm_sysfs_device_minor; } diff --git a/drivers/gpu/drm/exynos/exynos7_drm_decon.c b/drivers/gpu/drm/exynos/exynos7_drm_decon.c index 805aa28c1723..b8d9b7251319 100644 --- a/drivers/gpu/drm/exynos/exynos7_drm_decon.c +++ b/drivers/gpu/drm/exynos/exynos7_drm_decon.c @@ -69,7 +69,6 @@ struct decon_context { void __iomem *regs; unsigned long irq_flags; bool i80_if; - bool suspended; wait_queue_head_t wait_vsync_queue; atomic_t wait_vsync_event; @@ -132,9 +131,6 @@ static void decon_shadow_protect_win(struct decon_context *ctx, static void decon_wait_for_vblank(struct decon_context *ctx) { - if (ctx->suspended) - return; - atomic_set(&ctx->wait_vsync_event, 1); /* @@ -210,9 +206,6 @@ static void decon_commit(struct exynos_drm_crtc *crtc) struct drm_display_mode *mode = &crtc->base.state->adjusted_mode; u32 val, clkdiv; - if (ctx->suspended) - return; - /* nothing to do if we haven't set the mode yet */ if (mode->htotal == 0 || mode->vtotal == 0) return; @@ -274,9 +267,6 @@ static int decon_enable_vblank(struct exynos_drm_crtc *crtc) struct decon_context *ctx = crtc->ctx; u32 val; - if (ctx->suspended) - return -EPERM; - if (!test_and_set_bit(0, &ctx->irq_flags)) { val = readl(ctx->regs + VIDINTCON0); @@ -299,9 +289,6 @@ static void decon_disable_vblank(struct exynos_drm_crtc *crtc) struct decon_context *ctx = crtc->ctx; u32 val; - if (ctx->suspended) - return; - if (test_and_clear_bit(0, &ctx->irq_flags)) { val = readl(ctx->regs + VIDINTCON0); @@ -404,9 +391,6 @@ static void decon_atomic_begin(struct exynos_drm_crtc *crtc) struct decon_context *ctx = crtc->ctx; int i; - if (ctx->suspended) - return; - for (i = 0; i < WINDOWS_NR; i++) decon_shadow_protect_win(ctx, i, true); } @@ -427,9 +411,6 @@ static void decon_update_plane(struct exynos_drm_crtc *crtc, unsigned int pitch = fb->pitches[0]; unsigned int vidw_addr0_base = ctx->data->vidw_buf_start_base; - if (ctx->suspended) - return; - /* * SHADOWCON/PRTCON register is used for enabling timing. * @@ -517,9 +498,6 @@ static void decon_disable_plane(struct exynos_drm_crtc *crtc, unsigned int win = plane->index; u32 val; - if (ctx->suspended) - return; - /* protect windows */ decon_shadow_protect_win(ctx, win, true); @@ -538,9 +516,6 @@ static void decon_atomic_flush(struct exynos_drm_crtc *crtc) struct decon_context *ctx = crtc->ctx; int i; - if (ctx->suspended) - return; - for (i = 0; i < WINDOWS_NR; i++) decon_shadow_protect_win(ctx, i, false); exynos_crtc_handle_event(crtc); @@ -568,9 +543,6 @@ static void decon_atomic_enable(struct exynos_drm_crtc *crtc) struct decon_context *ctx = crtc->ctx; int ret; - if (!ctx->suspended) - return; - ret = pm_runtime_resume_and_get(ctx->dev); if (ret < 0) { DRM_DEV_ERROR(ctx->dev, "failed to enable DECON device.\n"); @@ -584,8 +556,6 @@ static void decon_atomic_enable(struct exynos_drm_crtc *crtc) decon_enable_vblank(ctx->crtc); decon_commit(ctx->crtc); - - ctx->suspended = false; } static void decon_atomic_disable(struct exynos_drm_crtc *crtc) @@ -593,9 +563,6 @@ static void decon_atomic_disable(struct exynos_drm_crtc *crtc) struct decon_context *ctx = crtc->ctx; int i; - if (ctx->suspended) - return; - /* * We need to make sure that all windows are disabled before we * suspend that connector. Otherwise we might try to scan from @@ -605,8 +572,6 @@ static void decon_atomic_disable(struct exynos_drm_crtc *crtc) decon_disable_plane(crtc, &ctx->planes[i]); pm_runtime_put_sync(ctx->dev); - - ctx->suspended = true; } static const struct exynos_drm_crtc_ops decon_crtc_ops = { @@ -727,7 +692,6 @@ static int decon_probe(struct platform_device *pdev) return -ENOMEM; ctx->dev = dev; - ctx->suspended = true; ctx->data = of_device_get_match_data(dev); i80_if_timings = of_get_child_by_name(dev->of_node, "i80-if-timings"); diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c index 896a03639e2d..c4d098ab7863 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c +++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c @@ -154,6 +154,11 @@ static const struct samsung_dsim_plat_data exynos5433_dsi_pdata = { .host_ops = &exynos_dsi_exynos_host_ops, }; +static const struct samsung_dsim_plat_data exynos7870_dsi_pdata = { + .hw_type = DSIM_TYPE_EXYNOS7870, + .host_ops = &exynos_dsi_exynos_host_ops, +}; + static const struct of_device_id exynos_dsi_of_match[] = { { .compatible = "samsung,exynos3250-mipi-dsi", @@ -175,6 +180,10 @@ static const struct of_device_id exynos_dsi_of_match[] = { .compatible = "samsung,exynos5433-mipi-dsi", .data = &exynos5433_dsi_pdata, }, + { + .compatible = "samsung,exynos7870-mipi-dsi", + .data = &exynos7870_dsi_pdata, + }, { /* sentinel. */ } }; MODULE_DEVICE_TABLE(of, exynos_dsi_of_match); diff --git a/drivers/gpu/drm/gma500/fbdev.c b/drivers/gpu/drm/gma500/fbdev.c index 4a37136f90f4..32d31e5f5f1a 100644 --- a/drivers/gpu/drm/gma500/fbdev.c +++ b/drivers/gpu/drm/gma500/fbdev.c @@ -120,7 +120,6 @@ static void psb_fbdev_fb_destroy(struct fb_info *info) drm_fb_helper_fini(fb_helper); drm_framebuffer_unregister_private(fb); - fb->obj[0] = NULL; drm_framebuffer_cleanup(fb); kfree(fb); @@ -245,7 +244,6 @@ int psb_fbdev_driver_fbdev_probe(struct drm_fb_helper *fb_helper, err_drm_framebuffer_unregister_private: drm_framebuffer_unregister_private(fb); - fb->obj[0] = NULL; drm_framebuffer_cleanup(fb); kfree(fb); err_drm_gem_object_put: diff --git a/drivers/gpu/drm/gud/gud_connector.c b/drivers/gpu/drm/gud/gud_connector.c index 0f07d77c5d52..4a15695fa933 100644 --- a/drivers/gpu/drm/gud/gud_connector.c +++ b/drivers/gpu/drm/gud/gud_connector.c @@ -16,7 +16,6 @@ #include <drm/drm_modeset_helper_vtables.h> #include <drm/drm_print.h> #include <drm/drm_probe_helper.h> -#include <drm/drm_simple_kms_helper.h> #include <drm/gud.h> #include "gud_internal.h" @@ -607,13 +606,16 @@ int gud_connector_fill_properties(struct drm_connector_state *connector_state, return gconn->num_properties; } +static const struct drm_encoder_funcs gud_drm_simple_encoder_funcs_cleanup = { + .destroy = drm_encoder_cleanup, +}; + static int gud_connector_create(struct gud_device *gdrm, unsigned int index, struct gud_connector_descriptor_req *desc) { struct drm_device *drm = &gdrm->drm; struct gud_connector *gconn; struct drm_connector *connector; - struct drm_encoder *encoder; int ret, connector_type; u32 flags; @@ -681,20 +683,13 @@ static int gud_connector_create(struct gud_device *gdrm, unsigned int index, return ret; } - /* The first connector is attached to the existing simple pipe encoder */ - if (!connector->index) { - encoder = &gdrm->pipe.encoder; - } else { - encoder = &gconn->encoder; - - ret = drm_simple_encoder_init(drm, encoder, DRM_MODE_ENCODER_NONE); - if (ret) - return ret; - - encoder->possible_crtcs = 1; - } + gconn->encoder.possible_crtcs = drm_crtc_mask(&gdrm->crtc); + ret = drm_encoder_init(drm, &gconn->encoder, &gud_drm_simple_encoder_funcs_cleanup, + DRM_MODE_ENCODER_NONE, NULL); + if (ret) + return ret; - return drm_connector_attach_encoder(connector, encoder); + return drm_connector_attach_encoder(connector, &gconn->encoder); } int gud_get_connectors(struct gud_device *gdrm) diff --git a/drivers/gpu/drm/gud/gud_drv.c b/drivers/gpu/drm/gud/gud_drv.c index b52a12cbba3e..b7345c8d823d 100644 --- a/drivers/gpu/drm/gud/gud_drv.c +++ b/drivers/gpu/drm/gud/gud_drv.c @@ -16,6 +16,7 @@ #include <drm/clients/drm_client_setup.h> #include <drm/drm_atomic_helper.h> #include <drm/drm_blend.h> +#include <drm/drm_crtc_helper.h> #include <drm/drm_damage_helper.h> #include <drm/drm_debugfs.h> #include <drm/drm_drv.h> @@ -27,7 +28,6 @@ #include <drm/drm_managed.h> #include <drm/drm_print.h> #include <drm/drm_probe_helper.h> -#include <drm/drm_simple_kms_helper.h> #include <drm/gud.h> #include "gud_internal.h" @@ -289,7 +289,7 @@ static int gud_get_properties(struct gud_device *gdrm) * but mask out any additions on future devices. */ val &= GUD_ROTATION_MASK; - ret = drm_plane_create_rotation_property(&gdrm->pipe.plane, + ret = drm_plane_create_rotation_property(&gdrm->plane, DRM_MODE_ROTATE_0, val); break; default: @@ -338,10 +338,30 @@ static int gud_stats_debugfs(struct seq_file *m, void *data) return 0; } -static const struct drm_simple_display_pipe_funcs gud_pipe_funcs = { - .check = gud_pipe_check, - .update = gud_pipe_update, - DRM_GEM_SIMPLE_DISPLAY_PIPE_SHADOW_PLANE_FUNCS +static const struct drm_crtc_helper_funcs gud_crtc_helper_funcs = { + .atomic_check = drm_crtc_helper_atomic_check +}; + +static const struct drm_crtc_funcs gud_crtc_funcs = { + .reset = drm_atomic_helper_crtc_reset, + .destroy = drm_crtc_cleanup, + .set_config = drm_atomic_helper_set_config, + .page_flip = drm_atomic_helper_page_flip, + .atomic_duplicate_state = drm_atomic_helper_crtc_duplicate_state, + .atomic_destroy_state = drm_atomic_helper_crtc_destroy_state, +}; + +static const struct drm_plane_helper_funcs gud_plane_helper_funcs = { + DRM_GEM_SHADOW_PLANE_HELPER_FUNCS, + .atomic_check = gud_plane_atomic_check, + .atomic_update = gud_plane_atomic_update, +}; + +static const struct drm_plane_funcs gud_plane_funcs = { + .update_plane = drm_atomic_helper_update_plane, + .disable_plane = drm_atomic_helper_disable_plane, + .destroy = drm_plane_cleanup, + DRM_GEM_SHADOW_PLANE_FUNCS, }; static const struct drm_mode_config_funcs gud_mode_config_funcs = { @@ -350,7 +370,7 @@ static const struct drm_mode_config_funcs gud_mode_config_funcs = { .atomic_commit = drm_atomic_helper_commit, }; -static const u64 gud_pipe_modifiers[] = { +static const u64 gud_plane_modifiers[] = { DRM_FORMAT_MOD_LINEAR, DRM_FORMAT_MOD_INVALID }; @@ -567,12 +587,17 @@ static int gud_probe(struct usb_interface *intf, const struct usb_device_id *id) return -ENOMEM; } - ret = drm_simple_display_pipe_init(drm, &gdrm->pipe, &gud_pipe_funcs, - formats, num_formats, - gud_pipe_modifiers, NULL); + ret = drm_universal_plane_init(drm, &gdrm->plane, 0, + &gud_plane_funcs, + formats, num_formats, + gud_plane_modifiers, + DRM_PLANE_TYPE_PRIMARY, NULL); if (ret) return ret; + drm_plane_helper_add(&gdrm->plane, &gud_plane_helper_funcs); + drm_plane_enable_fb_damage_clips(&gdrm->plane); + devm_kfree(dev, formats); devm_kfree(dev, formats_dev); @@ -582,7 +607,12 @@ static int gud_probe(struct usb_interface *intf, const struct usb_device_id *id) return ret; } - drm_plane_enable_fb_damage_clips(&gdrm->pipe.plane); + ret = drm_crtc_init_with_planes(drm, &gdrm->crtc, &gdrm->plane, NULL, + &gud_crtc_funcs, NULL); + if (ret) + return ret; + + drm_crtc_helper_add(&gdrm->crtc, &gud_crtc_helper_funcs); ret = gud_get_connectors(gdrm); if (ret) { diff --git a/drivers/gpu/drm/gud/gud_internal.h b/drivers/gpu/drm/gud/gud_internal.h index d6fb25388722..d27c31648341 100644 --- a/drivers/gpu/drm/gud/gud_internal.h +++ b/drivers/gpu/drm/gud/gud_internal.h @@ -11,11 +11,11 @@ #include <uapi/drm/drm_fourcc.h> #include <drm/drm_modes.h> -#include <drm/drm_simple_kms_helper.h> struct gud_device { struct drm_device drm; - struct drm_simple_display_pipe pipe; + struct drm_plane plane; + struct drm_crtc crtc; struct work_struct work; u32 flags; const struct drm_format_info *xrgb8888_emulation_format; @@ -62,11 +62,10 @@ int gud_usb_set_u8(struct gud_device *gdrm, u8 request, u8 val); void gud_clear_damage(struct gud_device *gdrm); void gud_flush_work(struct work_struct *work); -int gud_pipe_check(struct drm_simple_display_pipe *pipe, - struct drm_plane_state *new_plane_state, - struct drm_crtc_state *new_crtc_state); -void gud_pipe_update(struct drm_simple_display_pipe *pipe, - struct drm_plane_state *old_state); +int gud_plane_atomic_check(struct drm_plane *plane, + struct drm_atomic_state *state); +void gud_plane_atomic_update(struct drm_plane *plane, + struct drm_atomic_state *atomic_state); int gud_connector_fill_properties(struct drm_connector_state *connector_state, struct gud_property_req *properties); int gud_get_connectors(struct gud_device *gdrm); diff --git a/drivers/gpu/drm/gud/gud_pipe.c b/drivers/gpu/drm/gud/gud_pipe.c index 8d548d08f127..54d9aa9998e5 100644 --- a/drivers/gpu/drm/gud/gud_pipe.c +++ b/drivers/gpu/drm/gud/gud_pipe.c @@ -20,7 +20,6 @@ #include <drm/drm_gem_framebuffer_helper.h> #include <drm/drm_print.h> #include <drm/drm_rect.h> -#include <drm/drm_simple_kms_helper.h> #include <drm/gud.h> #include "gud_internal.h" @@ -451,14 +450,15 @@ static void gud_fb_handle_damage(struct gud_device *gdrm, struct drm_framebuffer gud_flush_damage(gdrm, fb, src, !fb->obj[0]->import_attach, damage); } -int gud_pipe_check(struct drm_simple_display_pipe *pipe, - struct drm_plane_state *new_plane_state, - struct drm_crtc_state *new_crtc_state) +int gud_plane_atomic_check(struct drm_plane *plane, + struct drm_atomic_state *state) { - struct gud_device *gdrm = to_gud_device(pipe->crtc.dev); - struct drm_plane_state *old_plane_state = pipe->plane.state; - const struct drm_display_mode *mode = &new_crtc_state->mode; - struct drm_atomic_state *state = new_plane_state->state; + struct gud_device *gdrm = to_gud_device(plane->dev); + struct drm_plane_state *old_plane_state = drm_atomic_get_old_plane_state(state, plane); + struct drm_plane_state *new_plane_state = drm_atomic_get_new_plane_state(state, plane); + struct drm_crtc *crtc = new_plane_state->crtc; + struct drm_crtc_state *crtc_state; + const struct drm_display_mode *mode; struct drm_framebuffer *old_fb = old_plane_state->fb; struct drm_connector_state *connector_state = NULL; struct drm_framebuffer *fb = new_plane_state->fb; @@ -469,20 +469,37 @@ int gud_pipe_check(struct drm_simple_display_pipe *pipe, int idx, ret; size_t len; - if (WARN_ON_ONCE(!fb)) + if (drm_WARN_ON_ONCE(plane->dev, !fb)) return -EINVAL; + if (drm_WARN_ON_ONCE(plane->dev, !crtc)) + return -EINVAL; + + crtc_state = drm_atomic_get_new_crtc_state(state, crtc); + + mode = &crtc_state->mode; + + ret = drm_atomic_helper_check_plane_state(new_plane_state, crtc_state, + DRM_PLANE_NO_SCALING, + DRM_PLANE_NO_SCALING, + false, false); + if (ret) + return ret; + + if (!new_plane_state->visible) + return 0; + if (old_plane_state->rotation != new_plane_state->rotation) - new_crtc_state->mode_changed = true; + crtc_state->mode_changed = true; if (old_fb && old_fb->format != format) - new_crtc_state->mode_changed = true; + crtc_state->mode_changed = true; - if (!new_crtc_state->mode_changed && !new_crtc_state->connectors_changed) + if (!crtc_state->mode_changed && !crtc_state->connectors_changed) return 0; /* Only one connector is supported */ - if (hweight32(new_crtc_state->connector_mask) != 1) + if (hweight32(crtc_state->connector_mask) != 1) return -EINVAL; if (format->format == DRM_FORMAT_XRGB8888 && gdrm->xrgb8888_emulation_format) @@ -500,7 +517,7 @@ int gud_pipe_check(struct drm_simple_display_pipe *pipe, if (!connector_state) { struct drm_connector_list_iter conn_iter; - drm_connector_list_iter_begin(pipe->crtc.dev, &conn_iter); + drm_connector_list_iter_begin(plane->dev, &conn_iter); drm_for_each_connector_iter(connector, &conn_iter) { if (connector->state->crtc) { connector_state = connector->state; @@ -567,16 +584,18 @@ out: return ret; } -void gud_pipe_update(struct drm_simple_display_pipe *pipe, - struct drm_plane_state *old_state) +void gud_plane_atomic_update(struct drm_plane *plane, + struct drm_atomic_state *atomic_state) { - struct drm_device *drm = pipe->crtc.dev; + struct drm_device *drm = plane->dev; struct gud_device *gdrm = to_gud_device(drm); - struct drm_plane_state *state = pipe->plane.state; - struct drm_shadow_plane_state *shadow_plane_state = to_drm_shadow_plane_state(state); - struct drm_framebuffer *fb = state->fb; - struct drm_crtc *crtc = &pipe->crtc; + struct drm_plane_state *old_state = drm_atomic_get_old_plane_state(atomic_state, plane); + struct drm_plane_state *new_state = drm_atomic_get_new_plane_state(atomic_state, plane); + struct drm_shadow_plane_state *shadow_plane_state = to_drm_shadow_plane_state(new_state); + struct drm_framebuffer *fb = new_state->fb; + struct drm_crtc *crtc = new_state->crtc; struct drm_rect damage; + struct drm_atomic_helper_damage_iter iter; int ret, idx; if (crtc->state->mode_changed || !crtc->state->enable) { @@ -611,7 +630,8 @@ void gud_pipe_update(struct drm_simple_display_pipe *pipe, if (ret) goto ctrl_disable; - if (drm_atomic_helper_damage_merged(old_state, state, &damage)) + drm_atomic_helper_damage_iter_init(&iter, old_state, new_state); + drm_atomic_for_each_plane_damage(&iter, &damage) gud_fb_handle_damage(gdrm, fb, &shadow_plane_state->data[0], &damage); drm_gem_fb_end_cpu_access(fb, DMA_FROM_DEVICE); diff --git a/drivers/gpu/drm/hisilicon/hibmc/dp/dp_link.c b/drivers/gpu/drm/hisilicon/hibmc/dp/dp_link.c index 74f7832ea53e..0726cb5b736e 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/dp/dp_link.c +++ b/drivers/gpu/drm/hisilicon/hibmc/dp/dp_link.c @@ -325,6 +325,17 @@ static int hibmc_dp_link_downgrade_training_eq(struct hibmc_dp_dev *dp) return hibmc_dp_link_reduce_rate(dp); } +static void hibmc_dp_update_caps(struct hibmc_dp_dev *dp) +{ + dp->link.cap.link_rate = dp->dpcd[DP_MAX_LINK_RATE]; + if (dp->link.cap.link_rate > DP_LINK_BW_8_1 || !dp->link.cap.link_rate) + dp->link.cap.link_rate = DP_LINK_BW_8_1; + + dp->link.cap.lanes = dp->dpcd[DP_MAX_LANE_COUNT] & DP_MAX_LANE_COUNT_MASK; + if (dp->link.cap.lanes > HIBMC_DP_LANE_NUM_MAX) + dp->link.cap.lanes = HIBMC_DP_LANE_NUM_MAX; +} + int hibmc_dp_link_training(struct hibmc_dp_dev *dp) { struct hibmc_dp_link *link = &dp->link; @@ -334,8 +345,7 @@ int hibmc_dp_link_training(struct hibmc_dp_dev *dp) if (ret) drm_err(dp->dev, "dp aux read dpcd failed, ret: %d\n", ret); - dp->link.cap.link_rate = dp->dpcd[DP_MAX_LINK_RATE]; - dp->link.cap.lanes = 0x2; + hibmc_dp_update_caps(dp); ret = hibmc_dp_get_serdes_rate_cfg(dp); if (ret < 0) diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c index 768b97f9e74a..289304500ab0 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c @@ -32,7 +32,7 @@ DEFINE_DRM_GEM_FOPS(hibmc_fops); -static const char *g_irqs_names_map[HIBMC_MAX_VECTORS] = { "vblank", "hpd" }; +static const char *g_irqs_names_map[HIBMC_MAX_VECTORS] = { "hibmc-vblank", "hibmc-hpd" }; static irqreturn_t hibmc_interrupt(int irq, void *arg) { @@ -115,6 +115,8 @@ static const struct drm_mode_config_funcs hibmc_mode_funcs = { static int hibmc_kms_init(struct hibmc_drm_private *priv) { struct drm_device *dev = &priv->dev; + struct drm_encoder *encoder; + u32 clone_mask = 0; int ret; ret = drmm_mode_config_init(dev); @@ -154,6 +156,12 @@ static int hibmc_kms_init(struct hibmc_drm_private *priv) return ret; } + drm_for_each_encoder(encoder, dev) + clone_mask |= drm_encoder_mask(encoder); + + drm_for_each_encoder(encoder, dev) + encoder->possible_clones = clone_mask; + return 0; } @@ -277,7 +285,6 @@ static void hibmc_unload(struct drm_device *dev) static int hibmc_msi_init(struct drm_device *dev) { struct pci_dev *pdev = to_pci_dev(dev->dev); - char name[32] = {0}; int valid_irq_num; int irq; int ret; @@ -292,9 +299,6 @@ static int hibmc_msi_init(struct drm_device *dev) valid_irq_num = ret; for (int i = 0; i < valid_irq_num; i++) { - snprintf(name, ARRAY_SIZE(name) - 1, "%s-%s-%s", - dev->driver->name, pci_name(pdev), g_irqs_names_map[i]); - irq = pci_irq_vector(pdev, i); if (i) @@ -302,10 +306,10 @@ static int hibmc_msi_init(struct drm_device *dev) ret = devm_request_threaded_irq(&pdev->dev, irq, hibmc_dp_interrupt, hibmc_dp_hpd_isr, - IRQF_SHARED, name, dev); + IRQF_SHARED, g_irqs_names_map[i], dev); else ret = devm_request_irq(&pdev->dev, irq, hibmc_interrupt, - IRQF_SHARED, name, dev); + IRQF_SHARED, g_irqs_names_map[i], dev); if (ret) { drm_err(dev, "install irq failed: %d\n", ret); return ret; @@ -323,13 +327,13 @@ static int hibmc_load(struct drm_device *dev) ret = hibmc_hw_init(priv); if (ret) - goto err; + return ret; ret = drmm_vram_helper_init(dev, pci_resource_start(pdev, 0), pci_resource_len(pdev, 0)); if (ret) { drm_err(dev, "Error initializing VRAM MM; %d\n", ret); - goto err; + return ret; } ret = hibmc_kms_init(priv); diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h index 274feabe7df0..ca8502e2760c 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h @@ -69,6 +69,7 @@ int hibmc_de_init(struct hibmc_drm_private *priv); int hibmc_vdac_init(struct hibmc_drm_private *priv); int hibmc_ddc_create(struct drm_device *drm_dev, struct hibmc_vdac *connector); +void hibmc_ddc_del(struct hibmc_vdac *vdac); int hibmc_dp_init(struct hibmc_drm_private *priv); diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c index 99b3b77b5445..44860011855e 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c @@ -95,3 +95,8 @@ int hibmc_ddc_create(struct drm_device *drm_dev, struct hibmc_vdac *vdac) return i2c_bit_add_bus(&vdac->adapter); } + +void hibmc_ddc_del(struct hibmc_vdac *vdac) +{ + i2c_del_adapter(&vdac->adapter); +} diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c index e8a527ede854..841e81f47b68 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c @@ -53,7 +53,7 @@ static void hibmc_connector_destroy(struct drm_connector *connector) { struct hibmc_vdac *vdac = to_hibmc_vdac(connector); - i2c_del_adapter(&vdac->adapter); + hibmc_ddc_del(vdac); drm_connector_cleanup(connector); } @@ -110,7 +110,7 @@ int hibmc_vdac_init(struct hibmc_drm_private *priv) ret = drmm_encoder_init(dev, encoder, NULL, DRM_MODE_ENCODER_DAC, NULL); if (ret) { drm_err(dev, "failed to init encoder: %d\n", ret); - return ret; + goto err; } drm_encoder_helper_add(encoder, &hibmc_encoder_helper_funcs); @@ -121,7 +121,7 @@ int hibmc_vdac_init(struct hibmc_drm_private *priv) &vdac->adapter); if (ret) { drm_err(dev, "failed to init connector: %d\n", ret); - return ret; + goto err; } drm_connector_helper_add(connector, &hibmc_connector_helper_funcs); @@ -131,4 +131,9 @@ int hibmc_vdac_init(struct hibmc_drm_private *priv) connector->polled = DRM_CONNECTOR_POLL_CONNECT | DRM_CONNECTOR_POLL_DISCONNECT; return 0; + +err: + hibmc_ddc_del(vdac); + + return ret; } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c index 15835952352e..ed6599694835 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c @@ -2158,18 +2158,12 @@ static int set_context_image(struct i915_gem_context *ctx, goto out_ce; } - state = kmalloc(ce->engine->context_size, GFP_KERNEL); - if (!state) { - ret = -ENOMEM; + state = memdup_user(u64_to_user_ptr(user.image), ce->engine->context_size); + if (IS_ERR(state)) { + ret = PTR_ERR(state); goto out_ce; } - if (copy_from_user(state, u64_to_user_ptr(user.image), - ce->engine->context_size)) { - ret = -EFAULT; - goto out_state; - } - shmem_state = shmem_create_from_data(ce->engine->name, state, ce->engine->context_size); if (IS_ERR(shmem_state)) { diff --git a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c index 619c70c54ef9..4f252f704975 100644 --- a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c +++ b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c @@ -904,9 +904,7 @@ static void active_engine(struct kthread_work *work) arg->result = PTR_ERR(ce[count]); pr_err("[%s] Create context #%ld failed: %d!\n", engine->name, count, arg->result); - if (!count) - return; - while (--count) + while (count--) intel_context_put(ce[count]); return; } diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c index 1bb1491f90fc..b1bda1b84f0a 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c @@ -48,6 +48,14 @@ static void guc_prepare_xfer(struct intel_gt *gt) /* allows for 5us (in 10ns units) before GT can go to RC6 */ intel_uncore_write(uncore, GUC_ARAT_C6DIS, 0x1FF); } + + /* + * Starting from IP 12.50 we need to enable the mirroring of GuC + * internal state to debug registers. This is always enabled on previous + * IPs. + */ + if (GRAPHICS_VER_FULL(uncore->i915) >= IP_VER(12, 50)) + intel_uncore_rmw(uncore, GUC_SHIM_CONTROL2, 0, GUC_ENABLE_DEBUG_REG); } static int guc_xfer_rsa_mmio(struct intel_uc_fw *guc_fw, diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_reg.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_reg.h index 3fd798837502..f73dab527547 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_reg.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_reg.h @@ -96,6 +96,7 @@ #define GUC_GEN10_SHIM_WC_ENABLE (1<<21) #define GUC_SHIM_CONTROL2 _MMIO(0xc068) +#define GUC_ENABLE_DEBUG_REG (1<<11) #define GUC_IS_PRIVILEGED (1<<29) #define GSC_LOADS_HUC (1<<30) diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 89f7c04a3330..7582ef34bf3f 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -685,6 +685,74 @@ static void err_print_guc_ctb(struct drm_i915_error_state_buf *m, ctb->head, ctb->tail, ctb->desc_offset, ctb->cmds_offset, ctb->size); } +/* This list includes registers that are useful in debugging GuC hangs. */ +const struct { + u32 start; + u32 count; +} guc_hw_reg_state[] = { + { 0xc0b0, 2 }, + { 0xc000, 65 }, + { 0xc140, 1 }, + { 0xc180, 16 }, + { 0xc1dc, 10 }, + { 0xc300, 79 }, + { 0xc4b4, 47 }, + { 0xc574, 1 }, + { 0xc57c, 1 }, + { 0xc584, 11 }, + { 0xc5c0, 8 }, + { 0xc5e4, 1 }, + { 0xc5ec, 103 }, + { 0xc7c0, 1 }, + { 0xc0b0, 2 } +}; + +static u32 print_range_line(struct drm_i915_error_state_buf *m, u32 start, u32 *dump, u32 count) +{ + if (count >= 8) { + err_printf(m, "[0x%04x] 0x%08x 0x%08x 0x%08x 0x%08x 0x%08x 0x%08x 0x%08x 0x%08x\n", + start, dump[0], dump[1], dump[2], dump[3], + dump[4], dump[5], dump[6], dump[7]); + return 8; + } else if (count >= 4) { + err_printf(m, "[0x%04x] 0x%08x 0x%08x 0x%08x 0x%08x\n", + start, dump[0], dump[1], dump[2], dump[3]); + return 4; + } else if (count >= 2) { + err_printf(m, "[0x%04x] 0x%08x 0x%08x\n", start, dump[0], dump[1]); + return 2; + } + + err_printf(m, "[0x%04x] 0x%08x\n", start, dump[0]); + return 1; +} + +static void err_print_guc_hw_state(struct drm_i915_error_state_buf *m, u32 *hw_state) +{ + u32 total = 0; + int i; + + if (!hw_state) + return; + + err_printf(m, "GuC Register State:\n"); + + for (i = 0; i < ARRAY_SIZE(guc_hw_reg_state); i++) { + u32 entry = 0; + + while (entry < guc_hw_reg_state[i].count) { + u32 start = guc_hw_reg_state[i].start + entry * sizeof(u32); + u32 count = guc_hw_reg_state[i].count - entry; + u32 *values = hw_state + total + entry; + + entry += print_range_line(m, start, values, count); + } + + GEM_BUG_ON(entry != guc_hw_reg_state[i].count); + total += entry; + } +} + static void err_print_uc(struct drm_i915_error_state_buf *m, const struct intel_uc_coredump *error_uc) { @@ -693,6 +761,7 @@ static void err_print_uc(struct drm_i915_error_state_buf *m, intel_uc_fw_dump(&error_uc->guc_fw, &p); intel_uc_fw_dump(&error_uc->huc_fw, &p); err_printf(m, "GuC timestamp: 0x%08x\n", error_uc->guc.timestamp); + err_print_guc_hw_state(m, error_uc->guc.hw_state); intel_gpu_error_print_vma(m, NULL, error_uc->guc.vma_log); err_printf(m, "GuC CTB fence: %d\n", error_uc->guc.last_fence); err_print_guc_ctb(m, "Send", error_uc->guc.ctb + 0); @@ -1025,6 +1094,7 @@ static void cleanup_uc(struct intel_uc_coredump *uc) kfree(uc->huc_fw.file_wanted.path); i915_vma_coredump_free(uc->guc.vma_log); i915_vma_coredump_free(uc->guc.vma_ctb); + kfree(uc->guc.hw_state); kfree(uc); } @@ -1721,6 +1791,37 @@ static void gt_record_guc_ctb(struct intel_ctb_coredump *saved, saved->cmds_offset = ((void *)ctb->cmds) - blob_ptr; } +static u32 read_guc_state_reg(struct intel_uncore *uncore, int range, int count) +{ + GEM_BUG_ON(range >= ARRAY_SIZE(guc_hw_reg_state)); + GEM_BUG_ON(count >= guc_hw_reg_state[range].count); + + return intel_uncore_read(uncore, + _MMIO(guc_hw_reg_state[range].start + count * sizeof(u32))); +} + +static void gt_record_guc_hw_state(struct intel_uncore *uncore, + struct intel_uc_coredump *error_uc) +{ + u32 *hw_state; + u32 count = 0; + int i, j; + + for (i = 0; i < ARRAY_SIZE(guc_hw_reg_state); i++) + count += guc_hw_reg_state[i].count; + + hw_state = kcalloc(count, sizeof(u32), ALLOW_FAIL); + if (!hw_state) + return; + + count = 0; + for (i = 0; i < ARRAY_SIZE(guc_hw_reg_state); i++) + for (j = 0; j < guc_hw_reg_state[i].count; j++) + hw_state[count++] = read_guc_state_reg(uncore, i, j); + + error_uc->guc.hw_state = hw_state; +} + static struct intel_uc_coredump * gt_record_uc(struct intel_gt_coredump *gt, struct i915_vma_compress *compress) @@ -1755,6 +1856,7 @@ gt_record_uc(struct intel_gt_coredump *gt, uc->guc.ct.ctbs.send.desc, (struct intel_guc *)&uc->guc); gt_record_guc_ctb(error_uc->guc.ctb + 1, &uc->guc.ct.ctbs.recv, uc->guc.ct.ctbs.send.desc, (struct intel_guc *)&uc->guc); + gt_record_guc_hw_state(gt->_gt->uncore, error_uc); return error_uc; } diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h b/drivers/gpu/drm/i915/i915_gpu_error.h index 182324979278..91b3df621a49 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.h +++ b/drivers/gpu/drm/i915/i915_gpu_error.h @@ -177,6 +177,7 @@ struct intel_gt_coredump { struct intel_ctb_coredump ctb[2]; struct i915_vma_coredump *vma_ctb; struct i915_vma_coredump *vma_log; + u32 *hw_state; u32 timestamp; u16 last_fence; bool is_guc_capture; diff --git a/drivers/gpu/drm/imagination/Kconfig b/drivers/gpu/drm/imagination/Kconfig index 3bfa2ac212dc..682dd2633d0c 100644 --- a/drivers/gpu/drm/imagination/Kconfig +++ b/drivers/gpu/drm/imagination/Kconfig @@ -3,8 +3,9 @@ config DRM_POWERVR tristate "Imagination Technologies PowerVR (Series 6 and later) & IMG Graphics" - depends on ARM64 + depends on (ARM64 || RISCV && 64BIT) depends on DRM + depends on MMU depends on PM select DRM_EXEC select DRM_GEM_SHMEM_HELPER diff --git a/drivers/gpu/drm/imagination/pvr_device.c b/drivers/gpu/drm/imagination/pvr_device.c index 8b9ba4983c4c..294b6019b415 100644 --- a/drivers/gpu/drm/imagination/pvr_device.c +++ b/drivers/gpu/drm/imagination/pvr_device.c @@ -23,6 +23,7 @@ #include <linux/firmware.h> #include <linux/gfp.h> #include <linux/interrupt.h> +#include <linux/of.h> #include <linux/platform_device.h> #include <linux/pm_runtime.h> #include <linux/reset.h> @@ -121,21 +122,6 @@ static int pvr_device_clk_init(struct pvr_device *pvr_dev) return 0; } -static int pvr_device_reset_init(struct pvr_device *pvr_dev) -{ - struct drm_device *drm_dev = from_pvr_device(pvr_dev); - struct reset_control *reset; - - reset = devm_reset_control_get_optional_exclusive(drm_dev->dev, NULL); - if (IS_ERR(reset)) - return dev_err_probe(drm_dev->dev, PTR_ERR(reset), - "failed to get gpu reset line\n"); - - pvr_dev->reset = reset; - - return 0; -} - /** * pvr_device_process_active_queues() - Process all queue related events. * @pvr_dev: PowerVR device to check @@ -618,6 +604,9 @@ pvr_device_init(struct pvr_device *pvr_dev) struct device *dev = drm_dev->dev; int err; + /* Get the platform-specific data based on the compatible string. */ + pvr_dev->device_data = of_device_get_match_data(dev); + /* * Setup device parameters. We do this first in case other steps * depend on them. @@ -631,8 +620,7 @@ pvr_device_init(struct pvr_device *pvr_dev) if (err) return err; - /* Get the reset line for the GPU */ - err = pvr_device_reset_init(pvr_dev); + err = pvr_dev->device_data->pwr_ops->init(pvr_dev); if (err) return err; diff --git a/drivers/gpu/drm/imagination/pvr_device.h b/drivers/gpu/drm/imagination/pvr_device.h index 7cb01c38d2a9..ab8f56ae15df 100644 --- a/drivers/gpu/drm/imagination/pvr_device.h +++ b/drivers/gpu/drm/imagination/pvr_device.h @@ -37,6 +37,9 @@ struct clk; /* Forward declaration from <linux/firmware.h>. */ struct firmware; +/* Forward declaration from <linux/pwrseq/consumer.h> */ +struct pwrseq_desc; + /** * struct pvr_gpu_id - Hardware GPU ID information for a PowerVR device * @b: Branch ID. @@ -58,6 +61,14 @@ struct pvr_fw_version { }; /** + * struct pvr_device_data - Platform specific data associated with a compatible string. + * @pwr_ops: Pointer to a structure with platform-specific power functions. + */ +struct pvr_device_data { + const struct pvr_power_sequence_ops *pwr_ops; +}; + +/** * struct pvr_device - powervr-specific wrapper for &struct drm_device */ struct pvr_device { @@ -98,6 +109,9 @@ struct pvr_device { /** @fw_version: Firmware version detected at runtime. */ struct pvr_fw_version fw_version; + /** @device_data: Pointer to platform-specific data. */ + const struct pvr_device_data *device_data; + /** @regs_resource: Resource representing device control registers. */ struct resource *regs_resource; @@ -148,6 +162,9 @@ struct pvr_device { */ struct reset_control *reset; + /** @pwrseq: Pointer to a power sequencer, if one is used. */ + struct pwrseq_desc *pwrseq; + /** @irq: IRQ number. */ int irq; diff --git a/drivers/gpu/drm/imagination/pvr_drv.c b/drivers/gpu/drm/imagination/pvr_drv.c index b058ec183bb3..916b40ced7eb 100644 --- a/drivers/gpu/drm/imagination/pvr_drv.c +++ b/drivers/gpu/drm/imagination/pvr_drv.c @@ -1480,15 +1480,33 @@ static void pvr_remove(struct platform_device *plat_dev) pvr_power_domains_fini(pvr_dev); } +static const struct pvr_device_data pvr_device_data_manual = { + .pwr_ops = &pvr_power_sequence_ops_manual, +}; + +static const struct pvr_device_data pvr_device_data_pwrseq = { + .pwr_ops = &pvr_power_sequence_ops_pwrseq, +}; + static const struct of_device_id dt_match[] = { - { .compatible = "img,img-rogue", .data = NULL }, + { + .compatible = "thead,th1520-gpu", + .data = &pvr_device_data_pwrseq, + }, + { + .compatible = "img,img-rogue", + .data = &pvr_device_data_manual, + }, /* * This legacy compatible string was introduced early on before the more generic * "img,img-rogue" was added. Keep it around here for compatibility, but never use * "img,img-axe" in new devicetrees. */ - { .compatible = "img,img-axe", .data = NULL }, + { + .compatible = "img,img-axe", + .data = &pvr_device_data_manual, + }, {} }; MODULE_DEVICE_TABLE(of, dt_match); @@ -1513,4 +1531,5 @@ MODULE_DESCRIPTION(PVR_DRIVER_DESC); MODULE_LICENSE("Dual MIT/GPL"); MODULE_IMPORT_NS("DMA_BUF"); MODULE_FIRMWARE("powervr/rogue_33.15.11.3_v1.fw"); +MODULE_FIRMWARE("powervr/rogue_36.52.104.182_v1.fw"); MODULE_FIRMWARE("powervr/rogue_36.53.104.796_v1.fw"); diff --git a/drivers/gpu/drm/imagination/pvr_power.c b/drivers/gpu/drm/imagination/pvr_power.c index 187a07e0bd9a..c6e7ff9e935d 100644 --- a/drivers/gpu/drm/imagination/pvr_power.c +++ b/drivers/gpu/drm/imagination/pvr_power.c @@ -18,6 +18,7 @@ #include <linux/platform_device.h> #include <linux/pm_domain.h> #include <linux/pm_runtime.h> +#include <linux/pwrseq/consumer.h> #include <linux/reset.h> #include <linux/timer.h> #include <linux/types.h> @@ -234,6 +235,118 @@ pvr_watchdog_init(struct pvr_device *pvr_dev) return 0; } +static int pvr_power_init_manual(struct pvr_device *pvr_dev) +{ + struct drm_device *drm_dev = from_pvr_device(pvr_dev); + struct reset_control *reset; + + reset = devm_reset_control_get_optional_exclusive(drm_dev->dev, NULL); + if (IS_ERR(reset)) + return dev_err_probe(drm_dev->dev, PTR_ERR(reset), + "failed to get gpu reset line\n"); + + pvr_dev->reset = reset; + + return 0; +} + +static int pvr_power_on_sequence_manual(struct pvr_device *pvr_dev) +{ + int err; + + err = clk_prepare_enable(pvr_dev->core_clk); + if (err) + return err; + + err = clk_prepare_enable(pvr_dev->sys_clk); + if (err) + goto err_core_clk_disable; + + err = clk_prepare_enable(pvr_dev->mem_clk); + if (err) + goto err_sys_clk_disable; + + /* + * According to the hardware manual, a delay of at least 32 clock + * cycles is required between de-asserting the clkgen reset and + * de-asserting the GPU reset. Assuming a worst-case scenario with + * a very high GPU clock frequency, a delay of 1 microsecond is + * sufficient to ensure this requirement is met across all + * feasible GPU clock speeds. + */ + udelay(1); + + err = reset_control_deassert(pvr_dev->reset); + if (err) + goto err_mem_clk_disable; + + return 0; + +err_mem_clk_disable: + clk_disable_unprepare(pvr_dev->mem_clk); + +err_sys_clk_disable: + clk_disable_unprepare(pvr_dev->sys_clk); + +err_core_clk_disable: + clk_disable_unprepare(pvr_dev->core_clk); + + return err; +} + +static int pvr_power_off_sequence_manual(struct pvr_device *pvr_dev) +{ + int err; + + err = reset_control_assert(pvr_dev->reset); + + clk_disable_unprepare(pvr_dev->mem_clk); + clk_disable_unprepare(pvr_dev->sys_clk); + clk_disable_unprepare(pvr_dev->core_clk); + + return err; +} + +const struct pvr_power_sequence_ops pvr_power_sequence_ops_manual = { + .init = pvr_power_init_manual, + .power_on = pvr_power_on_sequence_manual, + .power_off = pvr_power_off_sequence_manual, +}; + +static int pvr_power_init_pwrseq(struct pvr_device *pvr_dev) +{ + struct device *dev = from_pvr_device(pvr_dev)->dev; + + pvr_dev->pwrseq = devm_pwrseq_get(dev, "gpu-power"); + if (IS_ERR(pvr_dev->pwrseq)) { + /* + * This platform requires a sequencer. If we can't get it, we + * must return the error (including -EPROBE_DEFER to wait for + * the provider to appear) + */ + return dev_err_probe(dev, PTR_ERR(pvr_dev->pwrseq), + "Failed to get required power sequencer\n"); + } + + return 0; +} + +static int pvr_power_on_sequence_pwrseq(struct pvr_device *pvr_dev) +{ + return pwrseq_power_on(pvr_dev->pwrseq); +} + +static int pvr_power_off_sequence_pwrseq(struct pvr_device *pvr_dev) +{ + return pwrseq_power_off(pvr_dev->pwrseq); +} + +const struct pvr_power_sequence_ops pvr_power_sequence_ops_pwrseq = { + .init = pvr_power_init_pwrseq, + .power_on = pvr_power_on_sequence_pwrseq, + .power_off = pvr_power_off_sequence_pwrseq, +}; + int pvr_power_device_suspend(struct device *dev) { @@ -252,11 +365,7 @@ pvr_power_device_suspend(struct device *dev) goto err_drm_dev_exit; } - clk_disable_unprepare(pvr_dev->mem_clk); - clk_disable_unprepare(pvr_dev->sys_clk); - clk_disable_unprepare(pvr_dev->core_clk); - - err = reset_control_assert(pvr_dev->reset); + err = pvr_dev->device_data->pwr_ops->power_off(pvr_dev); err_drm_dev_exit: drm_dev_exit(idx); @@ -276,53 +385,22 @@ pvr_power_device_resume(struct device *dev) if (!drm_dev_enter(drm_dev, &idx)) return -EIO; - err = clk_prepare_enable(pvr_dev->core_clk); + err = pvr_dev->device_data->pwr_ops->power_on(pvr_dev); if (err) goto err_drm_dev_exit; - err = clk_prepare_enable(pvr_dev->sys_clk); - if (err) - goto err_core_clk_disable; - - err = clk_prepare_enable(pvr_dev->mem_clk); - if (err) - goto err_sys_clk_disable; - - /* - * According to the hardware manual, a delay of at least 32 clock - * cycles is required between de-asserting the clkgen reset and - * de-asserting the GPU reset. Assuming a worst-case scenario with - * a very high GPU clock frequency, a delay of 1 microsecond is - * sufficient to ensure this requirement is met across all - * feasible GPU clock speeds. - */ - udelay(1); - - err = reset_control_deassert(pvr_dev->reset); - if (err) - goto err_mem_clk_disable; - if (pvr_dev->fw_dev.booted) { err = pvr_power_fw_enable(pvr_dev); if (err) - goto err_reset_assert; + goto err_power_off; } drm_dev_exit(idx); return 0; -err_reset_assert: - reset_control_assert(pvr_dev->reset); - -err_mem_clk_disable: - clk_disable_unprepare(pvr_dev->mem_clk); - -err_sys_clk_disable: - clk_disable_unprepare(pvr_dev->sys_clk); - -err_core_clk_disable: - clk_disable_unprepare(pvr_dev->core_clk); +err_power_off: + pvr_dev->device_data->pwr_ops->power_off(pvr_dev); err_drm_dev_exit: drm_dev_exit(idx); diff --git a/drivers/gpu/drm/imagination/pvr_power.h b/drivers/gpu/drm/imagination/pvr_power.h index ada85674a7ca..b853d092242c 100644 --- a/drivers/gpu/drm/imagination/pvr_power.h +++ b/drivers/gpu/drm/imagination/pvr_power.h @@ -41,4 +41,19 @@ pvr_power_put(struct pvr_device *pvr_dev) int pvr_power_domains_init(struct pvr_device *pvr_dev); void pvr_power_domains_fini(struct pvr_device *pvr_dev); +/** + * struct pvr_power_sequence_ops - Platform specific power sequence operations. + * @init: Pointer to the platform-specific initialization function. + * @power_on: Pointer to the platform-specific power on function. + * @power_off: Pointer to the platform-specific power off function. + */ +struct pvr_power_sequence_ops { + int (*init)(struct pvr_device *pvr_dev); + int (*power_on)(struct pvr_device *pvr_dev); + int (*power_off)(struct pvr_device *pvr_dev); +}; + +extern const struct pvr_power_sequence_ops pvr_power_sequence_ops_manual; +extern const struct pvr_power_sequence_ops pvr_power_sequence_ops_pwrseq; + #endif /* PVR_POWER_H */ diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c index d5e6bab36414..eb5537f0ac90 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c @@ -394,10 +394,12 @@ static bool mtk_drm_get_all_drm_priv(struct device *dev) continue; drm_dev = device_find_child(&pdev->dev, NULL, mtk_drm_match); + put_device(&pdev->dev); if (!drm_dev) continue; temp_drm_priv = dev_get_drvdata(drm_dev); + put_device(drm_dev); if (!temp_drm_priv) continue; diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c index d7726091819c..0e2bcd5f67b7 100644 --- a/drivers/gpu/drm/mediatek/mtk_dsi.c +++ b/drivers/gpu/drm/mediatek/mtk_dsi.c @@ -1002,6 +1002,12 @@ static int mtk_dsi_host_attach(struct mipi_dsi_host *host, return PTR_ERR(dsi->next_bridge); } + /* + * set flag to request the DSI host bridge be pre-enabled before device bridge + * in the chain, so the DSI host is ready when the device bridge is pre-enabled + */ + dsi->next_bridge->pre_enable_prev_first = true; + drm_bridge_add(&dsi->bridge); ret = component_add(host->dev, &mtk_dsi_component_ops); diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c index 845fd8aa43c3..b766dd5e6c8d 100644 --- a/drivers/gpu/drm/mediatek/mtk_hdmi.c +++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c @@ -182,8 +182,8 @@ static inline struct mtk_hdmi *hdmi_ctx_from_bridge(struct drm_bridge *b) static void mtk_hdmi_hw_vid_black(struct mtk_hdmi *hdmi, bool black) { - regmap_update_bits(hdmi->regs, VIDEO_SOURCE_SEL, - VIDEO_CFG_4, black ? GEN_RGB : NORMAL_PATH); + regmap_update_bits(hdmi->regs, VIDEO_CFG_4, + VIDEO_SOURCE_SEL, black ? GEN_RGB : NORMAL_PATH); } static void mtk_hdmi_hw_make_reg_writable(struct mtk_hdmi *hdmi, bool enable) @@ -310,8 +310,8 @@ static void mtk_hdmi_hw_send_info_frame(struct mtk_hdmi *hdmi, u8 *buffer, static void mtk_hdmi_hw_send_aud_packet(struct mtk_hdmi *hdmi, bool enable) { - regmap_update_bits(hdmi->regs, AUDIO_PACKET_OFF, - GRL_SHIFT_R2, enable ? 0 : AUDIO_PACKET_OFF); + regmap_update_bits(hdmi->regs, GRL_SHIFT_R2, + AUDIO_PACKET_OFF, enable ? 0 : AUDIO_PACKET_OFF); } static void mtk_hdmi_hw_config_sys(struct mtk_hdmi *hdmi) diff --git a/drivers/gpu/drm/mediatek/mtk_plane.c b/drivers/gpu/drm/mediatek/mtk_plane.c index cbc4f37da8ba..02349bd44001 100644 --- a/drivers/gpu/drm/mediatek/mtk_plane.c +++ b/drivers/gpu/drm/mediatek/mtk_plane.c @@ -292,7 +292,8 @@ static void mtk_plane_atomic_disable(struct drm_plane *plane, wmb(); /* Make sure the above parameter is set before update */ mtk_plane_state->pending.dirty = true; - mtk_crtc_plane_disable(old_state->crtc, plane); + if (old_state && old_state->crtc) + mtk_crtc_plane_disable(old_state->crtc, plane); } static void mtk_plane_atomic_update(struct drm_plane *plane, diff --git a/drivers/gpu/drm/msm/adreno/a6xx_catalog.c b/drivers/gpu/drm/msm/adreno/a6xx_catalog.c index 00e1afd46b81..44df6410bce1 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_catalog.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_catalog.c @@ -913,6 +913,11 @@ static const struct adreno_info a6xx_gpus[] = { { /* sentinel */ }, }, }, + .speedbins = ADRENO_SPEEDBINS( + { 0, 0 }, + { 185, 0 }, + { 127, 1 }, + ), }, { .chip_ids = ADRENO_CHIP_IDS( 0x06030001, @@ -1024,6 +1029,11 @@ static const struct adreno_info a6xx_gpus[] = { .gmu_cgc_mode = 0x00020200, .prim_fifo_threshold = 0x00300200, }, + .speedbins = ADRENO_SPEEDBINS( + { 0, 0 }, + { 169, 0 }, + { 113, 1 }, + ), }, { .chip_ids = ADRENO_CHIP_IDS(0x06030500), .family = ADRENO_6XX_GEN4, @@ -1343,6 +1353,69 @@ static const uint32_t a7xx_pwrup_reglist_regs[] = { DECLARE_ADRENO_REGLIST_LIST(a7xx_pwrup_reglist); +/* Applicable for X185, A750 */ +static const u32 a750_ifpc_reglist_regs[] = { + REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE(0), + REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE(1), + REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE(2), + REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE(3), + REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE(4), + REG_A6XX_TPL1_NC_MODE_CNTL, + REG_A6XX_SP_NC_MODE_CNTL, + REG_A6XX_CP_DBG_ECO_CNTL, + REG_A6XX_CP_PROTECT_CNTL, + REG_A6XX_CP_PROTECT(0), + REG_A6XX_CP_PROTECT(1), + REG_A6XX_CP_PROTECT(2), + REG_A6XX_CP_PROTECT(3), + REG_A6XX_CP_PROTECT(4), + REG_A6XX_CP_PROTECT(5), + REG_A6XX_CP_PROTECT(6), + REG_A6XX_CP_PROTECT(7), + REG_A6XX_CP_PROTECT(8), + REG_A6XX_CP_PROTECT(9), + REG_A6XX_CP_PROTECT(10), + REG_A6XX_CP_PROTECT(11), + REG_A6XX_CP_PROTECT(12), + REG_A6XX_CP_PROTECT(13), + REG_A6XX_CP_PROTECT(14), + REG_A6XX_CP_PROTECT(15), + REG_A6XX_CP_PROTECT(16), + REG_A6XX_CP_PROTECT(17), + REG_A6XX_CP_PROTECT(18), + REG_A6XX_CP_PROTECT(19), + REG_A6XX_CP_PROTECT(20), + REG_A6XX_CP_PROTECT(21), + REG_A6XX_CP_PROTECT(22), + REG_A6XX_CP_PROTECT(23), + REG_A6XX_CP_PROTECT(24), + REG_A6XX_CP_PROTECT(25), + REG_A6XX_CP_PROTECT(26), + REG_A6XX_CP_PROTECT(27), + REG_A6XX_CP_PROTECT(28), + REG_A6XX_CP_PROTECT(29), + REG_A6XX_CP_PROTECT(30), + REG_A6XX_CP_PROTECT(31), + REG_A6XX_CP_PROTECT(32), + REG_A6XX_CP_PROTECT(33), + REG_A6XX_CP_PROTECT(34), + REG_A6XX_CP_PROTECT(35), + REG_A6XX_CP_PROTECT(36), + REG_A6XX_CP_PROTECT(37), + REG_A6XX_CP_PROTECT(38), + REG_A6XX_CP_PROTECT(39), + REG_A6XX_CP_PROTECT(40), + REG_A6XX_CP_PROTECT(41), + REG_A6XX_CP_PROTECT(42), + REG_A6XX_CP_PROTECT(43), + REG_A6XX_CP_PROTECT(44), + REG_A6XX_CP_PROTECT(45), + REG_A6XX_CP_PROTECT(46), + REG_A6XX_CP_PROTECT(47), +}; + +DECLARE_ADRENO_REGLIST_LIST(a750_ifpc_reglist); + static const struct adreno_info a7xx_gpus[] = { { .chip_ids = ADRENO_CHIP_IDS(0x07000200), @@ -1432,14 +1505,27 @@ static const struct adreno_info a7xx_gpus[] = { .inactive_period = DRM_MSM_INACTIVE_PERIOD, .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | ADRENO_QUIRK_HAS_HW_APRIV | - ADRENO_QUIRK_PREEMPTION, + ADRENO_QUIRK_PREEMPTION | + ADRENO_QUIRK_IFPC, .init = a6xx_gpu_init, .a6xx = &(const struct a6xx_info) { .hwcg = a740_hwcg, .protect = &a730_protect, .pwrup_reglist = &a7xx_pwrup_reglist, + .ifpc_reglist = &a750_ifpc_reglist, .gmu_chipid = 0x7050001, .gmu_cgc_mode = 0x00020202, + .bcms = (const struct a6xx_bcm[]) { + { .name = "SH0", .buswidth = 16 }, + { .name = "MC0", .buswidth = 4 }, + { + .name = "ACV", + .fixed = true, + .perfmode = BIT(3), + .perfmode_bw = 16500000, + }, + { /* sentinel */ }, + }, }, .preempt_record_size = 4192 * SZ_1K, .speedbins = ADRENO_SPEEDBINS( @@ -1460,12 +1546,14 @@ static const struct adreno_info a7xx_gpus[] = { .inactive_period = DRM_MSM_INACTIVE_PERIOD, .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | ADRENO_QUIRK_HAS_HW_APRIV | - ADRENO_QUIRK_PREEMPTION, + ADRENO_QUIRK_PREEMPTION | + ADRENO_QUIRK_IFPC, .init = a6xx_gpu_init, .zapfw = "gen70900_zap.mbn", .a6xx = &(const struct a6xx_info) { .protect = &a730_protect, .pwrup_reglist = &a7xx_pwrup_reglist, + .ifpc_reglist = &a750_ifpc_reglist, .gmu_chipid = 0x7090100, .gmu_cgc_mode = 0x00020202, .bcms = (const struct a6xx_bcm[]) { diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c index 28e6705c6da6..fc62fef2fed8 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c @@ -93,14 +93,25 @@ bool a6xx_gmu_sptprac_is_on(struct a6xx_gmu *gmu) /* Check to see if the GX rail is still powered */ bool a6xx_gmu_gx_is_on(struct a6xx_gmu *gmu) { + struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu); + struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; u32 val; /* This can be called from gpu state code so make sure GMU is valid */ if (!gmu->initialized) return false; + /* If GMU is absent, then GX power domain is ON as long as GPU is in active state */ + if (adreno_has_gmu_wrapper(adreno_gpu)) + return true; + val = gmu_read(gmu, REG_A6XX_GMU_SPTPRAC_PWR_CLK_STATUS); + if (adreno_is_a7xx(adreno_gpu)) + return !(val & + (A7XX_GMU_SPTPRAC_PWR_CLK_STATUS_GX_HM_GDSC_POWER_OFF | + A7XX_GMU_SPTPRAC_PWR_CLK_STATUS_GX_HM_CLK_OFF)); + return !(val & (A6XX_GMU_SPTPRAC_PWR_CLK_STATUS_GX_HM_GDSC_POWER_OFF | A6XX_GMU_SPTPRAC_PWR_CLK_STATUS_GX_HM_CLK_OFF)); @@ -272,6 +283,8 @@ static int a6xx_gmu_start(struct a6xx_gmu *gmu) if (ret) DRM_DEV_ERROR(gmu->dev, "GMU firmware initialization timed out\n"); + set_bit(GMU_STATUS_FW_START, &gmu->status); + return ret; } @@ -403,7 +416,10 @@ int a6xx_sptprac_enable(struct a6xx_gmu *gmu) int ret; u32 val; - if (!gmu->legacy) + WARN_ON(!gmu->legacy); + + /* Nothing to do if GMU does the power management */ + if (gmu->idle_level > GMU_IDLE_STATE_ACTIVE) return 0; gmu_write(gmu, REG_A6XX_GMU_GX_SPTPRAC_POWER_CONTROL, 0x778000); @@ -518,6 +534,9 @@ static int a6xx_rpmh_start(struct a6xx_gmu *gmu) int ret; u32 val; + if (!test_and_clear_bit(GMU_STATUS_PDC_SLEEP, &gmu->status)) + return 0; + gmu_write(gmu, REG_A6XX_GMU_RSCC_CONTROL_REQ, BIT(1)); ret = gmu_poll_timeout(gmu, REG_A6XX_GMU_RSCC_CONTROL_ACK, val, @@ -545,6 +564,9 @@ static void a6xx_rpmh_stop(struct a6xx_gmu *gmu) int ret; u32 val; + if (test_and_clear_bit(GMU_STATUS_FW_START, &gmu->status)) + return; + gmu_write(gmu, REG_A6XX_GMU_RSCC_CONTROL_REQ, 1); ret = gmu_poll_timeout_rscc(gmu, REG_A6XX_GPU_RSCC_RSC_STATUS0_DRV0, @@ -553,6 +575,8 @@ static void a6xx_rpmh_stop(struct a6xx_gmu *gmu) DRM_DEV_ERROR(gmu->dev, "Unable to power off the GPU RSC\n"); gmu_write(gmu, REG_A6XX_GMU_RSCC_CONTROL_REQ, 0); + + set_bit(GMU_STATUS_PDC_SLEEP, &gmu->status); } static inline void pdc_write(void __iomem *ptr, u32 offset, u32 value) @@ -681,8 +705,6 @@ setup_pdc: /* ensure no writes happen before the uCode is fully written */ wmb(); - a6xx_rpmh_stop(gmu); - err: if (!IS_ERR_OR_NULL(pdcptr)) iounmap(pdcptr); @@ -842,19 +864,15 @@ static int a6xx_gmu_fw_start(struct a6xx_gmu *gmu, unsigned int state) else gmu_write(gmu, REG_A6XX_GMU_GENERAL_7, 1); - if (state == GMU_WARM_BOOT) { - ret = a6xx_rpmh_start(gmu); - if (ret) - return ret; - } else { + ret = a6xx_rpmh_start(gmu); + if (ret) + return ret; + + if (state == GMU_COLD_BOOT) { if (WARN(!adreno_gpu->fw[ADRENO_FW_GMU], "GMU firmware is not loaded\n")) return -ENOENT; - ret = a6xx_rpmh_start(gmu); - if (ret) - return ret; - ret = a6xx_gmu_fw_load(gmu); if (ret) return ret; @@ -925,10 +943,7 @@ static int a6xx_gmu_fw_start(struct a6xx_gmu *gmu, unsigned int state) ret = a6xx_gmu_gfx_rail_on(gmu); if (ret) return ret; - } - /* Enable SPTP_PC if the CPU is responsible for it */ - if (gmu->idle_level < GMU_IDLE_STATE_SPTP) { ret = a6xx_sptprac_enable(gmu); if (ret) return ret; @@ -980,6 +995,22 @@ static void a6xx_gmu_rpmh_off(struct a6xx_gmu *gmu) val, (val & 1), 100, 10000); gmu_poll_timeout_rscc(gmu, REG_A6XX_RSCC_TCS3_DRV0_STATUS + seqmem_off, val, (val & 1), 100, 1000); + + if (!adreno_is_a740_family(adreno_gpu)) + return; + + gmu_poll_timeout_rscc(gmu, REG_A7XX_RSCC_TCS4_DRV0_STATUS + seqmem_off, + val, (val & 1), 100, 10000); + gmu_poll_timeout_rscc(gmu, REG_A7XX_RSCC_TCS5_DRV0_STATUS + seqmem_off, + val, (val & 1), 100, 10000); + gmu_poll_timeout_rscc(gmu, REG_A7XX_RSCC_TCS6_DRV0_STATUS + seqmem_off, + val, (val & 1), 100, 10000); + gmu_poll_timeout_rscc(gmu, REG_A7XX_RSCC_TCS7_DRV0_STATUS + seqmem_off, + val, (val & 1), 100, 1000); + gmu_poll_timeout_rscc(gmu, REG_A7XX_RSCC_TCS8_DRV0_STATUS + seqmem_off, + val, (val & 1), 100, 10000); + gmu_poll_timeout_rscc(gmu, REG_A7XX_RSCC_TCS9_DRV0_STATUS + seqmem_off, + val, (val & 1), 100, 1000); } /* Force the GMU off in case it isn't responsive */ @@ -1023,6 +1054,8 @@ static void a6xx_gmu_force_off(struct a6xx_gmu *gmu) /* Reset GPU core blocks */ a6xx_gpu_sw_reset(gpu, true); + + a6xx_rpmh_stop(gmu); } static void a6xx_gmu_set_initial_freq(struct msm_gpu *gpu, struct a6xx_gmu *gmu) @@ -1128,6 +1161,11 @@ int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu) /* Set the GPU to the current freq */ a6xx_gmu_set_initial_freq(gpu, gmu); + if (refcount_read(&gpu->sysprof_active) > 1) { + ret = a6xx_gmu_set_oob(gmu, GMU_OOB_PERFCOUNTER_SET); + if (!ret) + set_bit(GMU_STATUS_OOB_PERF_SET, &gmu->status); + } out: /* On failure, shut down the GMU to leave it in a good state */ if (ret) { @@ -1175,6 +1213,9 @@ static void a6xx_gmu_shutdown(struct a6xx_gmu *gmu) a6xx_gmu_clear_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET); } + if (test_and_clear_bit(GMU_STATUS_OOB_PERF_SET, &gmu->status)) + a6xx_gmu_clear_oob(gmu, GMU_OOB_PERFCOUNTER_SET); + ret = a6xx_gmu_wait_for_idle(gmu); /* If the GMU isn't responding assume it is hung */ @@ -1318,8 +1359,6 @@ static int a6xx_gmu_memory_probe(struct drm_device *drm, struct a6xx_gmu *gmu) struct msm_mmu *mmu; mmu = msm_iommu_new(gmu->dev, 0); - if (!mmu) - return -ENODEV; if (IS_ERR(mmu)) return PTR_ERR(mmu); @@ -1692,6 +1731,7 @@ static int a6xx_gmu_acd_probe(struct a6xx_gmu *gmu) u32 val; freq = gmu->gpu_freqs[i]; + /* This is unlikely to fail because we are passing back a known freq */ opp = dev_pm_opp_find_freq_exact(&gpu->pdev->dev, freq, true); np = dev_pm_opp_get_of_node(opp); @@ -1790,6 +1830,35 @@ static int a6xx_gmu_get_irq(struct a6xx_gmu *gmu, struct platform_device *pdev, return irq; } +void a6xx_gmu_sysprof_setup(struct msm_gpu *gpu) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + struct a6xx_gmu *gmu = &a6xx_gpu->gmu; + unsigned int sysprof_active; + + /* Nothing to do if GPU is suspended. We will handle this during GMU resume */ + if (!pm_runtime_get_if_active(&gpu->pdev->dev)) + return; + + mutex_lock(&gmu->lock); + + sysprof_active = refcount_read(&gpu->sysprof_active); + + /* + * 'Perfcounter select' register values are lost during IFPC collapse. To avoid that, + * use the currently unused perfcounter oob vote to block IFPC when sysprof is active + */ + if ((sysprof_active > 1) && !test_and_set_bit(GMU_STATUS_OOB_PERF_SET, &gmu->status)) + a6xx_gmu_set_oob(gmu, GMU_OOB_PERFCOUNTER_SET); + else if ((sysprof_active == 1) && test_and_clear_bit(GMU_STATUS_OOB_PERF_SET, &gmu->status)) + a6xx_gmu_clear_oob(gmu, GMU_OOB_PERFCOUNTER_SET); + + mutex_unlock(&gmu->lock); + + pm_runtime_put(&gpu->pdev->dev); +} + void a6xx_gmu_remove(struct a6xx_gpu *a6xx_gpu) { struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; @@ -1932,8 +2001,9 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node) if (ret) return ret; - /* Fow now, don't do anything fancy until we get our feet under us */ - gmu->idle_level = GMU_IDLE_STATE_ACTIVE; + /* Set GMU idle level */ + gmu->idle_level = (adreno_gpu->info->quirks & ADRENO_QUIRK_IFPC) ? + GMU_IDLE_STATE_IFPC : GMU_IDLE_STATE_ACTIVE; pm_runtime_enable(gmu->dev); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h index d1ce11131ba6..06cfc294016f 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h @@ -50,6 +50,9 @@ struct a6xx_bcm { /* The GMU does not do any idle state management */ #define GMU_IDLE_STATE_ACTIVE 0 +/* Unknown power state. Not exposed by the firmware. For documentation purpose only */ +#define GMU_IDLE_STATE_RESERVED 1 + /* The GMU manages SPTP power collapse */ #define GMU_IDLE_STATE_SPTP 2 @@ -117,6 +120,14 @@ struct a6xx_gmu { struct qmp *qmp; struct a6xx_hfi_msg_bw_table *bw_table; + +/* To check if we can trigger sleep seq at PDC. Cleared in a6xx_rpmh_stop() */ +#define GMU_STATUS_FW_START 0 +/* To track if PDC sleep seq was done */ +#define GMU_STATUS_PDC_SLEEP 1 +/* To track Perfcounter OOB set status */ +#define GMU_STATUS_OOB_PERF_SET 2 + unsigned long status; }; static inline u32 gmu_read(struct a6xx_gmu *gmu, u32 offset) @@ -158,6 +169,9 @@ static inline u64 gmu_read64(struct a6xx_gmu *gmu, u32 lo, u32 hi) #define gmu_poll_timeout(gmu, addr, val, cond, interval, timeout) \ readl_poll_timeout((gmu)->mmio + ((addr) << 2), val, cond, \ interval, timeout) +#define gmu_poll_timeout_atomic(gmu, addr, val, cond, interval, timeout) \ + readl_poll_timeout_atomic((gmu)->mmio + ((addr) << 2), val, cond, \ + interval, timeout) static inline u32 gmu_read_rscc(struct a6xx_gmu *gmu, u32 offset) { diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index 45dd5fd1c2bf..b8f8ae940b55 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -16,6 +16,97 @@ #define GPU_PAS_ID 13 +static u64 read_gmu_ao_counter(struct a6xx_gpu *a6xx_gpu) +{ + u64 count_hi, count_lo, temp; + + do { + count_hi = gmu_read(&a6xx_gpu->gmu, REG_A6XX_GMU_ALWAYS_ON_COUNTER_H); + count_lo = gmu_read(&a6xx_gpu->gmu, REG_A6XX_GMU_ALWAYS_ON_COUNTER_L); + temp = gmu_read(&a6xx_gpu->gmu, REG_A6XX_GMU_ALWAYS_ON_COUNTER_H); + } while (unlikely(count_hi != temp)); + + return (count_hi << 32) | count_lo; +} + +static bool fence_status_check(struct msm_gpu *gpu, u32 offset, u32 value, u32 status, u32 mask) +{ + /* Success if !writedropped0/1 */ + if (!(status & mask)) + return true; + + udelay(10); + + /* Try to update fenced register again */ + gpu_write(gpu, offset, value); + + /* We can't do a posted write here because the power domain could be + * in collapse state. So use the heaviest barrier instead + */ + mb(); + return false; +} + +static int fenced_write(struct a6xx_gpu *a6xx_gpu, u32 offset, u32 value, u32 mask) +{ + struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; + struct msm_gpu *gpu = &adreno_gpu->base; + struct a6xx_gmu *gmu = &a6xx_gpu->gmu; + u32 status; + + gpu_write(gpu, offset, value); + + /* Nothing else to be done in the case of no-GMU */ + if (adreno_has_gmu_wrapper(adreno_gpu)) + return 0; + + /* We can't do a posted write here because the power domain could be + * in collapse state. So use the heaviest barrier instead + */ + mb(); + + if (!gmu_poll_timeout(gmu, REG_A6XX_GMU_AHB_FENCE_STATUS, status, + fence_status_check(gpu, offset, value, status, mask), 0, 1000)) + return 0; + + /* Try again for another 1ms before failing */ + gpu_write(gpu, offset, value); + mb(); + + if (!gmu_poll_timeout(gmu, REG_A6XX_GMU_AHB_FENCE_STATUS, status, + fence_status_check(gpu, offset, value, status, mask), 0, 1000)) { + /* + * The 'delay' warning is here because the pause to print this + * warning will allow gpu to move to power collapse which + * defeats the purpose of continuous polling for 2 ms + */ + dev_err_ratelimited(gmu->dev, "delay in fenced register write (0x%x)\n", + offset); + return 0; + } + + dev_err_ratelimited(gmu->dev, "fenced register write (0x%x) fail\n", + offset); + + return -ETIMEDOUT; +} + +int a6xx_fenced_write(struct a6xx_gpu *a6xx_gpu, u32 offset, u64 value, u32 mask, bool is_64b) +{ + int ret; + + ret = fenced_write(a6xx_gpu, offset, lower_32_bits(value), mask); + if (ret) + return ret; + + if (!is_64b) + return 0; + + ret = fenced_write(a6xx_gpu, offset + 1, upper_32_bits(value), mask); + + return ret; +} + static inline bool _a6xx_check_idle(struct msm_gpu *gpu) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); @@ -86,7 +177,7 @@ static void a6xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring) /* Update HW if this is the current ring and we are not in preempt*/ if (!a6xx_in_preempt(a6xx_gpu)) { if (a6xx_gpu->cur_ring == ring) - gpu_write(gpu, REG_A6XX_CP_RB_WPTR, wptr); + a6xx_fenced_write(a6xx_gpu, REG_A6XX_CP_RB_WPTR, wptr, BIT(0), false); else ring->restore_wptr = true; } else { @@ -173,8 +264,8 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu, * Needed for preemption */ OUT_PKT7(ring, CP_MEM_WRITE, 5); - OUT_RING(ring, CP_MEM_WRITE_0_ADDR_LO(lower_32_bits(memptr))); - OUT_RING(ring, CP_MEM_WRITE_1_ADDR_HI(upper_32_bits(memptr))); + OUT_RING(ring, A5XX_CP_MEM_WRITE_ADDR_LO(lower_32_bits(memptr))); + OUT_RING(ring, A5XX_CP_MEM_WRITE_ADDR_HI(upper_32_bits(memptr))); OUT_RING(ring, lower_32_bits(ttbr)); OUT_RING(ring, upper_32_bits(ttbr)); OUT_RING(ring, ctx->seqno); @@ -204,9 +295,9 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu, */ OUT_PKT7(ring, CP_WAIT_REG_MEM, 6); OUT_RING(ring, CP_WAIT_REG_MEM_0_FUNCTION(WRITE_EQ)); - OUT_RING(ring, CP_WAIT_REG_MEM_1_POLL_ADDR_LO( + OUT_RING(ring, CP_WAIT_REG_MEM_POLL_ADDR_LO( REG_A6XX_RBBM_PERFCTR_SRAM_INIT_STATUS)); - OUT_RING(ring, CP_WAIT_REG_MEM_2_POLL_ADDR_HI(0)); + OUT_RING(ring, CP_WAIT_REG_MEM_POLL_ADDR_HI(0)); OUT_RING(ring, CP_WAIT_REG_MEM_3_REF(0x1)); OUT_RING(ring, CP_WAIT_REG_MEM_4_MASK(0x1)); OUT_RING(ring, CP_WAIT_REG_MEM_5_DELAY_LOOP_CYCLES(0)); @@ -298,8 +389,7 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) OUT_RING(ring, upper_32_bits(rbmemptr(ring, fence))); OUT_RING(ring, submit->seqno); - trace_msm_gpu_submit_flush(submit, - gpu_read64(gpu, REG_A6XX_CP_ALWAYS_ON_COUNTER)); + trace_msm_gpu_submit_flush(submit, read_gmu_ao_counter(a6xx_gpu)); a6xx_flush(gpu, ring); } @@ -499,8 +589,7 @@ static void a7xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) } - trace_msm_gpu_submit_flush(submit, - gpu_read64(gpu, REG_A6XX_CP_ALWAYS_ON_COUNTER)); + trace_msm_gpu_submit_flush(submit, read_gmu_ao_counter(a6xx_gpu)); a6xx_flush(gpu, ring); @@ -739,11 +828,10 @@ static void a7xx_patch_pwrup_reglist(struct msm_gpu *gpu) u32 *dest = (u32 *)&lock->regs[0]; int i; - reglist = adreno_gpu->info->a6xx->pwrup_reglist; - lock->gpu_req = lock->cpu_req = lock->turn = 0; - lock->ifpc_list_len = 0; - lock->preemption_list_len = reglist->count; + + reglist = adreno_gpu->info->a6xx->ifpc_reglist; + lock->ifpc_list_len = reglist->count; /* * For each entry in each of the lists, write the offset and the current @@ -754,6 +842,14 @@ static void a7xx_patch_pwrup_reglist(struct msm_gpu *gpu) *dest++ = gpu_read(gpu, reglist->regs[i]); } + reglist = adreno_gpu->info->a6xx->pwrup_reglist; + lock->preemption_list_len = reglist->count; + + for (i = 0; i < reglist->count; i++) { + *dest++ = reglist->regs[i]; + *dest++ = gpu_read(gpu, reglist->regs[i]); + } + /* * The overall register list is composed of * 1. Static IFPC-only registers @@ -1241,14 +1337,14 @@ static int hw_init(struct msm_gpu *gpu) /* Set weights for bicubic filtering */ if (adreno_is_a650_family(adreno_gpu) || adreno_is_x185(adreno_gpu)) { - gpu_write(gpu, REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE_0, 0); - gpu_write(gpu, REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE_1, + gpu_write(gpu, REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE(0), 0); + gpu_write(gpu, REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE(1), 0x3fe05ff4); - gpu_write(gpu, REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE_2, + gpu_write(gpu, REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE(2), 0x3fa0ebee); - gpu_write(gpu, REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE_3, + gpu_write(gpu, REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE(3), 0x3f5193ed); - gpu_write(gpu, REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE_4, + gpu_write(gpu, REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE(4), 0x3f0243f0); } @@ -1448,21 +1544,25 @@ static void a6xx_recover(struct msm_gpu *gpu) adreno_dump_info(gpu); - for (i = 0; i < 8; i++) - DRM_DEV_INFO(&gpu->pdev->dev, "CP_SCRATCH_REG%d: %u\n", i, - gpu_read(gpu, REG_A6XX_CP_SCRATCH_REG(i))); + if (a6xx_gmu_gx_is_on(&a6xx_gpu->gmu)) { + /* Sometimes crashstate capture is skipped, so SQE should be halted here again */ + gpu_write(gpu, REG_A6XX_CP_SQE_CNTL, 3); + + for (i = 0; i < 8; i++) + DRM_DEV_INFO(&gpu->pdev->dev, "CP_SCRATCH_REG%d: %u\n", i, + gpu_read(gpu, REG_A6XX_CP_SCRATCH_REG(i))); - if (hang_debug) - a6xx_dump(gpu); + if (hang_debug) + a6xx_dump(gpu); + + } /* * To handle recovery specific sequences during the rpm suspend we are * about to trigger */ - a6xx_gpu->hung = true; - /* Halt SQE first */ - gpu_write(gpu, REG_A6XX_CP_SQE_CNTL, 3); + a6xx_gpu->hung = true; pm_runtime_dont_use_autosuspend(&gpu->pdev->dev); @@ -1693,8 +1793,6 @@ static void a6xx_cp_hw_err_irq(struct msm_gpu *gpu) static void a6xx_fault_detect_irq(struct msm_gpu *gpu) { - struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); - struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); struct msm_ringbuffer *ring = gpu->funcs->active_ring(gpu); /* @@ -1706,13 +1804,6 @@ static void a6xx_fault_detect_irq(struct msm_gpu *gpu) if (gpu_read(gpu, REG_A6XX_RBBM_STATUS3) & A6XX_RBBM_STATUS3_SMMU_STALLED_ON_FAULT) return; - /* - * Force the GPU to stay on until after we finish - * collecting information - */ - if (!adreno_has_gmu_wrapper(adreno_gpu)) - gmu_write(&a6xx_gpu->gmu, REG_A6XX_GMU_GMU_PWR_COL_KEEPALIVE, 1); - DRM_DEV_ERROR(&gpu->pdev->dev, "gpu fault ring %d fence %x status %8.8X rb %4.4x/%4.4x ib1 %16.16llX/%4.4x ib2 %16.16llX/%4.4x\n", ring ? ring->id : -1, ring ? ring->fctx->last_fence : 0, @@ -1727,6 +1818,9 @@ static void a6xx_fault_detect_irq(struct msm_gpu *gpu) /* Turn off the hangcheck timer to keep it from bothering us */ timer_delete(&gpu->hangcheck_timer); + /* Turn off interrupts to avoid triggering recovery again */ + gpu_write(gpu, REG_A6XX_RBBM_INT_0_MASK, 0); + kthread_queue_work(gpu->worker, &gpu->recover_work); } @@ -1751,9 +1845,49 @@ static void a7xx_sw_fuse_violation_irq(struct msm_gpu *gpu) } } +static void a6xx_gpu_keepalive_vote(struct msm_gpu *gpu, bool on) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + + if (adreno_has_gmu_wrapper(adreno_gpu)) + return; + + gmu_write(&a6xx_gpu->gmu, REG_A6XX_GMU_GMU_PWR_COL_KEEPALIVE, on); +} + +static int irq_poll_fence(struct msm_gpu *gpu) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + struct a6xx_gmu *gmu = &a6xx_gpu->gmu; + u32 status; + + if (adreno_has_gmu_wrapper(adreno_gpu)) + return 0; + + if (gmu_poll_timeout_atomic(gmu, REG_A6XX_GMU_AO_AHB_FENCE_CTRL, status, !status, 1, 100)) { + u32 rbbm_unmasked = gmu_read(gmu, REG_A6XX_GMU_RBBM_INT_UNMASKED_STATUS); + + dev_err_ratelimited(&gpu->pdev->dev, + "irq fence poll timeout, fence_ctrl=0x%x, unmasked_status=0x%x\n", + status, rbbm_unmasked); + return -ETIMEDOUT; + } + + return 0; +} + static irqreturn_t a6xx_irq(struct msm_gpu *gpu) { struct msm_drm_private *priv = gpu->dev->dev_private; + + /* Set keepalive vote to avoid power collapse after RBBM_INT_0_STATUS is read */ + a6xx_gpu_keepalive_vote(gpu, true); + + if (irq_poll_fence(gpu)) + goto done; + u32 status = gpu_read(gpu, REG_A6XX_RBBM_INT_0_STATUS); gpu_write(gpu, REG_A6XX_RBBM_INT_CLEAR_CMD, status); @@ -1790,6 +1924,9 @@ static irqreturn_t a6xx_irq(struct msm_gpu *gpu) if (status & A6XX_RBBM_INT_0_MASK_CP_SW) a6xx_preempt_irq(gpu); +done: + a6xx_gpu_keepalive_vote(gpu, false); + return IRQ_HANDLED; } @@ -2179,16 +2316,7 @@ static int a6xx_gmu_get_timestamp(struct msm_gpu *gpu, uint64_t *value) struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); - mutex_lock(&a6xx_gpu->gmu.lock); - - /* Force the GPU power on so we can read this register */ - a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_PERFCOUNTER_SET); - - *value = gpu_read64(gpu, REG_A6XX_CP_ALWAYS_ON_COUNTER); - - a6xx_gmu_clear_oob(&a6xx_gpu->gmu, GMU_OOB_PERFCOUNTER_SET); - - mutex_unlock(&a6xx_gpu->gmu.lock); + *value = read_gmu_ao_counter(a6xx_gpu); return 0; } @@ -2298,18 +2426,36 @@ static uint32_t a6xx_get_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring) if (adreno_gpu->base.hw_apriv || a6xx_gpu->has_whereami) return a6xx_gpu->shadow[ring->id]; + /* + * This is true only on an A6XX_GEN1 with GMU, has IFPC enabled and a super old SQE firmware + * without 'whereami' support + */ + WARN_ONCE((to_adreno_gpu(gpu)->info->quirks & ADRENO_QUIRK_IFPC), + "Can't read CP_RB_RPTR register reliably\n"); + return ring->memptrs->rptr = gpu_read(gpu, REG_A6XX_CP_RB_RPTR); } static bool a6xx_progress(struct msm_gpu *gpu, struct msm_ringbuffer *ring) { - struct msm_cp_state cp_state = { + struct msm_cp_state cp_state; + bool progress; + + /* + * With IFPC, KMD doesn't know whether GX power domain is collapsed + * or not. So, we can't blindly read the below registers in GX domain. + * Lets trust the hang detection in HW and lie to the caller that + * there was progress. + */ + if (to_adreno_gpu(gpu)->info->quirks & ADRENO_QUIRK_IFPC) + return true; + + cp_state = (struct msm_cp_state) { .ib1_base = gpu_read64(gpu, REG_A6XX_CP_IB1_BASE), .ib2_base = gpu_read64(gpu, REG_A6XX_CP_IB2_BASE), .ib1_rem = gpu_read(gpu, REG_A6XX_CP_IB1_REM_SIZE), .ib2_rem = gpu_read(gpu, REG_A6XX_CP_IB2_REM_SIZE), }; - bool progress; /* * Adjust the remaining data to account for what has already been @@ -2408,6 +2554,7 @@ static const struct adreno_gpu_funcs funcs = { .create_private_vm = a6xx_create_private_vm, .get_rptr = a6xx_get_rptr, .progress = a6xx_progress, + .sysprof_setup = a6xx_gmu_sysprof_setup, }, .get_timestamp = a6xx_gmu_get_timestamp, }; @@ -2468,6 +2615,7 @@ static const struct adreno_gpu_funcs funcs_a7xx = { .create_private_vm = a6xx_create_private_vm, .get_rptr = a6xx_get_rptr, .progress = a6xx_progress, + .sysprof_setup = a6xx_gmu_sysprof_setup, }, .get_timestamp = a6xx_gmu_get_timestamp, }; diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h index 6e71f617fc3d..0b17d36c36a9 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h @@ -45,6 +45,7 @@ struct a6xx_info { const struct adreno_reglist *hwcg; const struct adreno_protect *protect; const struct adreno_reglist_list *pwrup_reglist; + const struct adreno_reglist_list *ifpc_reglist; u32 gmu_chipid; u32 gmu_cgc_mode; u32 prim_fifo_threshold; @@ -254,6 +255,7 @@ void a6xx_gmu_clear_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state); int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node); int a6xx_gmu_wrapper_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node); void a6xx_gmu_remove(struct a6xx_gpu *a6xx_gpu); +void a6xx_gmu_sysprof_setup(struct msm_gpu *gpu); void a6xx_preempt_init(struct msm_gpu *gpu); void a6xx_preempt_hw_init(struct msm_gpu *gpu); @@ -295,5 +297,6 @@ int a6xx_gpu_state_put(struct msm_gpu_state *state); void a6xx_bus_clear_pending_transactions(struct adreno_gpu *adreno_gpu, bool gx_off); void a6xx_gpu_sw_reset(struct msm_gpu *gpu, bool assert); +int a6xx_fenced_write(struct a6xx_gpu *gpu, u32 offset, u64 value, u32 mask, bool is_64b); #endif /* __A6XX_GPU_H__ */ diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c index faca2a0243ab..4c7f3c642f6a 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c @@ -11,7 +11,7 @@ static const unsigned int *gen7_0_0_external_core_regs[] __always_unused; static const unsigned int *gen7_2_0_external_core_regs[] __always_unused; static const unsigned int *gen7_9_0_external_core_regs[] __always_unused; -static struct gen7_sptp_cluster_registers gen7_9_0_sptp_clusters[] __always_unused; +static const struct gen7_sptp_cluster_registers gen7_9_0_sptp_clusters[] __always_unused; static const u32 gen7_9_0_cx_debugbus_blocks[] __always_unused; #include "adreno_gen7_0_0_snapshot.h" @@ -174,8 +174,15 @@ static int a6xx_crashdumper_run(struct msm_gpu *gpu, static int debugbus_read(struct msm_gpu *gpu, u32 block, u32 offset, u32 *data) { - u32 reg = A6XX_DBGC_CFG_DBGBUS_SEL_D_PING_INDEX(offset) | - A6XX_DBGC_CFG_DBGBUS_SEL_D_PING_BLK_SEL(block); + u32 reg; + + if (to_adreno_gpu(gpu)->info->family >= ADRENO_7XX_GEN1) { + reg = A7XX_DBGC_CFG_DBGBUS_SEL_D_PING_INDEX(offset) | + A7XX_DBGC_CFG_DBGBUS_SEL_D_PING_BLK_SEL(block); + } else { + reg = A6XX_DBGC_CFG_DBGBUS_SEL_D_PING_INDEX(offset) | + A6XX_DBGC_CFG_DBGBUS_SEL_D_PING_BLK_SEL(block); + } gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_SEL_A, reg); gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_SEL_B, reg); @@ -198,11 +205,18 @@ static int debugbus_read(struct msm_gpu *gpu, u32 block, u32 offset, readl((ptr) + ((offset) << 2)) /* read a value from the CX debug bus */ -static int cx_debugbus_read(void __iomem *cxdbg, u32 block, u32 offset, +static int cx_debugbus_read(struct msm_gpu *gpu, void __iomem *cxdbg, u32 block, u32 offset, u32 *data) { - u32 reg = A6XX_CX_DBGC_CFG_DBGBUS_SEL_A_PING_INDEX(offset) | - A6XX_CX_DBGC_CFG_DBGBUS_SEL_A_PING_BLK_SEL(block); + u32 reg; + + if (to_adreno_gpu(gpu)->info->family >= ADRENO_7XX_GEN1) { + reg = A7XX_CX_DBGC_CFG_DBGBUS_SEL_A_PING_INDEX(offset) | + A7XX_CX_DBGC_CFG_DBGBUS_SEL_A_PING_BLK_SEL(block); + } else { + reg = A6XX_CX_DBGC_CFG_DBGBUS_SEL_A_PING_INDEX(offset) | + A6XX_CX_DBGC_CFG_DBGBUS_SEL_A_PING_BLK_SEL(block); + } cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_SEL_A, reg); cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_SEL_B, reg); @@ -315,7 +329,8 @@ static void a6xx_get_debugbus_block(struct msm_gpu *gpu, ptr += debugbus_read(gpu, block->id, i, ptr); } -static void a6xx_get_cx_debugbus_block(void __iomem *cxdbg, +static void a6xx_get_cx_debugbus_block(struct msm_gpu *gpu, + void __iomem *cxdbg, struct a6xx_gpu_state *a6xx_state, const struct a6xx_debugbus_block *block, struct a6xx_gpu_state_obj *obj) @@ -330,7 +345,7 @@ static void a6xx_get_cx_debugbus_block(void __iomem *cxdbg, obj->handle = block; for (ptr = obj->data, i = 0; i < block->count; i++) - ptr += cx_debugbus_read(cxdbg, block->id, i, ptr); + ptr += cx_debugbus_read(gpu, cxdbg, block->id, i, ptr); } static void a6xx_get_debugbus_blocks(struct msm_gpu *gpu, @@ -423,8 +438,9 @@ static void a7xx_get_debugbus_blocks(struct msm_gpu *gpu, a6xx_state, &a7xx_debugbus_blocks[gbif_debugbus_blocks[i]], &a6xx_state->debugbus[i + debugbus_blocks_count]); } - } + a6xx_state->nr_debugbus = total_debugbus_blocks; + } } static void a6xx_get_debugbus(struct msm_gpu *gpu, @@ -526,7 +542,8 @@ static void a6xx_get_debugbus(struct msm_gpu *gpu, int i; for (i = 0; i < nr_cx_debugbus_blocks; i++) - a6xx_get_cx_debugbus_block(cxdbg, + a6xx_get_cx_debugbus_block(gpu, + cxdbg, a6xx_state, &cx_debugbus_blocks[i], &a6xx_state->cx_debugbus[i]); @@ -759,15 +776,15 @@ static void a7xx_get_cluster(struct msm_gpu *gpu, size_t datasize; int i, regcount = 0; - /* Some clusters need a selector register to be programmed too */ - if (cluster->sel) - in += CRASHDUMP_WRITE(in, cluster->sel->cd_reg, cluster->sel->val); - in += CRASHDUMP_WRITE(in, REG_A7XX_CP_APERTURE_CNTL_CD, A7XX_CP_APERTURE_CNTL_CD_PIPE(cluster->pipe_id) | A7XX_CP_APERTURE_CNTL_CD_CLUSTER(cluster->cluster_id) | A7XX_CP_APERTURE_CNTL_CD_CONTEXT(cluster->context_id)); + /* Some clusters need a selector register to be programmed too */ + if (cluster->sel) + in += CRASHDUMP_WRITE(in, cluster->sel->cd_reg, cluster->sel->val); + for (i = 0; cluster->regs[i] != UINT_MAX; i += 2) { int count = RANGE(cluster->regs, i); @@ -1569,8 +1586,7 @@ struct msm_gpu_state *a6xx_gpu_state_get(struct msm_gpu *gpu) struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); struct a6xx_gpu_state *a6xx_state = kzalloc(sizeof(*a6xx_state), GFP_KERNEL); - bool stalled = !!(gpu_read(gpu, REG_A6XX_RBBM_STATUS3) & - A6XX_RBBM_STATUS3_SMMU_STALLED_ON_FAULT); + bool stalled; if (!a6xx_state) return ERR_PTR(-ENOMEM); @@ -1591,15 +1607,20 @@ struct msm_gpu_state *a6xx_gpu_state_get(struct msm_gpu *gpu) } /* If GX isn't on the rest of the data isn't going to be accessible */ - if (!adreno_has_gmu_wrapper(adreno_gpu) && !a6xx_gmu_gx_is_on(&a6xx_gpu->gmu)) + if (!a6xx_gmu_gx_is_on(&a6xx_gpu->gmu)) return &a6xx_state->base; + /* Halt SQE first */ + gpu_write(gpu, REG_A6XX_CP_SQE_CNTL, 3); + /* Get the banks of indexed registers */ if (adreno_is_a7xx(adreno_gpu)) a7xx_get_indexed_registers(gpu, a6xx_state); else a6xx_get_indexed_registers(gpu, a6xx_state); + stalled = !!(gpu_read(gpu, REG_A6XX_RBBM_STATUS3) & + A6XX_RBBM_STATUS3_SMMU_STALLED_ON_FAULT); /* * Try to initialize the crashdumper, if we are not dumping state * with the SMMU stalled. The crashdumper needs memory access to @@ -1796,6 +1817,7 @@ static void a7xx_show_shader(struct a6xx_gpu_state_obj *obj, print_name(p, " - type: ", a7xx_statetype_names[block->statetype]); print_name(p, " - pipe: ", a7xx_pipe_names[block->pipeid]); + drm_printf(p, " - location: %d\n", block->location); for (i = 0; i < block->num_sps; i++) { drm_printf(p, " - sp: %d\n", i); @@ -1873,6 +1895,7 @@ static void a7xx_show_dbgahb_cluster(struct a6xx_gpu_state_obj *obj, print_name(p, " - pipe: ", a7xx_pipe_names[dbgahb->pipe_id]); print_name(p, " - cluster-name: ", a7xx_cluster_names[dbgahb->cluster_id]); drm_printf(p, " - context: %d\n", dbgahb->context_id); + drm_printf(p, " - location: %d\n", dbgahb->location_id); a7xx_show_registers_indented(dbgahb->regs, obj->data, p, 4); } } diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h index 95d93ac6812a..1c18499b60bb 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h @@ -419,47 +419,47 @@ static const struct a6xx_indexed_registers a6xx_indexed_reglist[] = { REG_A6XX_CP_SQE_STAT_DATA, 0x33, NULL }, { "CP_DRAW_STATE", REG_A6XX_CP_DRAW_STATE_ADDR, REG_A6XX_CP_DRAW_STATE_DATA, 0x100, NULL }, - { "CP_UCODE_DBG_DATA", REG_A6XX_CP_SQE_UCODE_DBG_ADDR, + { "CP_SQE_UCODE_DBG", REG_A6XX_CP_SQE_UCODE_DBG_ADDR, REG_A6XX_CP_SQE_UCODE_DBG_DATA, 0x8000, NULL }, - { "CP_ROQ", REG_A6XX_CP_ROQ_DBG_ADDR, + { "CP_ROQ_DBG", REG_A6XX_CP_ROQ_DBG_ADDR, REG_A6XX_CP_ROQ_DBG_DATA, 0, a6xx_get_cp_roq_size}, }; static const struct a6xx_indexed_registers a7xx_indexed_reglist[] = { { "CP_SQE_STAT", REG_A6XX_CP_SQE_STAT_ADDR, - REG_A6XX_CP_SQE_STAT_DATA, 0x33, NULL }, + REG_A6XX_CP_SQE_STAT_DATA, 0x40, NULL }, { "CP_DRAW_STATE", REG_A6XX_CP_DRAW_STATE_ADDR, REG_A6XX_CP_DRAW_STATE_DATA, 0x100, NULL }, - { "CP_UCODE_DBG_DATA", REG_A6XX_CP_SQE_UCODE_DBG_ADDR, + { "CP_SQE_UCODE_DBG", REG_A6XX_CP_SQE_UCODE_DBG_ADDR, REG_A6XX_CP_SQE_UCODE_DBG_DATA, 0x8000, NULL }, - { "CP_BV_SQE_STAT_ADDR", REG_A7XX_CP_BV_SQE_STAT_ADDR, - REG_A7XX_CP_BV_SQE_STAT_DATA, 0x33, NULL }, - { "CP_BV_DRAW_STATE_ADDR", REG_A7XX_CP_BV_DRAW_STATE_ADDR, + { "CP_BV_SQE_STAT", REG_A7XX_CP_BV_SQE_STAT_ADDR, + REG_A7XX_CP_BV_SQE_STAT_DATA, 0x40, NULL }, + { "CP_BV_DRAW_STATE", REG_A7XX_CP_BV_DRAW_STATE_ADDR, REG_A7XX_CP_BV_DRAW_STATE_DATA, 0x100, NULL }, - { "CP_BV_SQE_UCODE_DBG_ADDR", REG_A7XX_CP_BV_SQE_UCODE_DBG_ADDR, + { "CP_BV_SQE_UCODE_DBG", REG_A7XX_CP_BV_SQE_UCODE_DBG_ADDR, REG_A7XX_CP_BV_SQE_UCODE_DBG_DATA, 0x8000, NULL }, - { "CP_SQE_AC_STAT_ADDR", REG_A7XX_CP_SQE_AC_STAT_ADDR, - REG_A7XX_CP_SQE_AC_STAT_DATA, 0x33, NULL }, - { "CP_LPAC_DRAW_STATE_ADDR", REG_A7XX_CP_LPAC_DRAW_STATE_ADDR, + { "CP_SQE_AC_STAT", REG_A7XX_CP_SQE_AC_STAT_ADDR, + REG_A7XX_CP_SQE_AC_STAT_DATA, 0x40, NULL }, + { "CP_LPAC_DRAW_STATE", REG_A7XX_CP_LPAC_DRAW_STATE_ADDR, REG_A7XX_CP_LPAC_DRAW_STATE_DATA, 0x100, NULL }, - { "CP_SQE_AC_UCODE_DBG_ADDR", REG_A7XX_CP_SQE_AC_UCODE_DBG_ADDR, + { "CP_SQE_AC_UCODE_DBG", REG_A7XX_CP_SQE_AC_UCODE_DBG_ADDR, REG_A7XX_CP_SQE_AC_UCODE_DBG_DATA, 0x8000, NULL }, - { "CP_LPAC_FIFO_DBG_ADDR", REG_A7XX_CP_LPAC_FIFO_DBG_ADDR, + { "CP_LPAC_FIFO_DBG", REG_A7XX_CP_LPAC_FIFO_DBG_ADDR, REG_A7XX_CP_LPAC_FIFO_DBG_DATA, 0x40, NULL }, - { "CP_ROQ", REG_A6XX_CP_ROQ_DBG_ADDR, + { "CP_ROQ_DBG", REG_A6XX_CP_ROQ_DBG_ADDR, REG_A6XX_CP_ROQ_DBG_DATA, 0, a7xx_get_cp_roq_size }, }; static const struct a6xx_indexed_registers a6xx_cp_mempool_indexed = { - "CP_MEMPOOL", REG_A6XX_CP_MEM_POOL_DBG_ADDR, + "CP_MEM_POOL_DBG", REG_A6XX_CP_MEM_POOL_DBG_ADDR, REG_A6XX_CP_MEM_POOL_DBG_DATA, 0x2060, NULL, }; static const struct a6xx_indexed_registers a7xx_cp_bv_mempool_indexed[] = { - { "CP_MEMPOOL", REG_A6XX_CP_MEM_POOL_DBG_ADDR, - REG_A6XX_CP_MEM_POOL_DBG_DATA, 0x2100, NULL }, - { "CP_BV_MEMPOOL", REG_A7XX_CP_BV_MEM_POOL_DBG_ADDR, - REG_A7XX_CP_BV_MEM_POOL_DBG_DATA, 0x2100, NULL }, + { "CP_MEM_POOL_DBG", REG_A6XX_CP_MEM_POOL_DBG_ADDR, + REG_A6XX_CP_MEM_POOL_DBG_DATA, 0x2200, NULL }, + { "CP_BV_MEM_POOL_DBG", REG_A7XX_CP_BV_MEM_POOL_DBG_ADDR, + REG_A7XX_CP_BV_MEM_POOL_DBG_DATA, 0x2200, NULL }, }; #define DEBUGBUS(_id, _count) { .id = _id, .name = #_id, .count = _count } diff --git a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c index 8e69b1e84657..550de6ad68ef 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c @@ -21,6 +21,7 @@ static const char * const a6xx_hfi_msg_id[] = { HFI_MSG_ID(HFI_H2F_MSG_PERF_TABLE), HFI_MSG_ID(HFI_H2F_MSG_TEST), HFI_MSG_ID(HFI_H2F_MSG_START), + HFI_MSG_ID(HFI_H2F_FEATURE_CTRL), HFI_MSG_ID(HFI_H2F_MSG_CORE_FW_START), HFI_MSG_ID(HFI_H2F_MSG_GX_BW_PERF_VOTE), HFI_MSG_ID(HFI_H2F_MSG_PREPARE_SLUMBER), @@ -765,23 +766,40 @@ send: NULL, 0); } +static int a6xx_hfi_feature_ctrl_msg(struct a6xx_gmu *gmu, u32 feature, u32 enable, u32 data) +{ + struct a6xx_hfi_msg_feature_ctrl msg = { + .feature = feature, + .enable = enable, + .data = data, + }; + + return a6xx_hfi_send_msg(gmu, HFI_H2F_FEATURE_CTRL, &msg, sizeof(msg), NULL, 0); +} + +#define HFI_FEATURE_IFPC 9 +#define IFPC_LONG_HYST 0x1680 + +static int a6xx_hfi_enable_ifpc(struct a6xx_gmu *gmu) +{ + if (gmu->idle_level != GMU_IDLE_STATE_IFPC) + return 0; + + return a6xx_hfi_feature_ctrl_msg(gmu, HFI_FEATURE_IFPC, 1, IFPC_LONG_HYST); +} + #define HFI_FEATURE_ACD 12 static int a6xx_hfi_enable_acd(struct a6xx_gmu *gmu) { struct a6xx_hfi_acd_table *acd_table = &gmu->acd_table; - struct a6xx_hfi_msg_feature_ctrl msg = { - .feature = HFI_FEATURE_ACD, - .enable = 1, - .data = 0, - }; int ret; if (!acd_table->enable_by_level) return 0; /* Enable ACD feature at GMU */ - ret = a6xx_hfi_send_msg(gmu, HFI_H2F_FEATURE_CTRL, &msg, sizeof(msg), NULL, 0); + ret = a6xx_hfi_feature_ctrl_msg(gmu, HFI_FEATURE_ACD, 1, 0); if (ret) { DRM_DEV_ERROR(gmu->dev, "Unable to enable ACD (%d)\n", ret); return ret; @@ -898,6 +916,10 @@ int a6xx_hfi_start(struct a6xx_gmu *gmu, int boot_state) if (ret) return ret; + ret = a6xx_hfi_enable_ifpc(gmu); + if (ret) + return ret; + ret = a6xx_hfi_send_core_fw_start(gmu); if (ret) return ret; diff --git a/drivers/gpu/drm/msm/adreno/a6xx_preempt.c b/drivers/gpu/drm/msm/adreno/a6xx_preempt.c index 6a12a35dabff..afc5f4aa3b17 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_preempt.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_preempt.c @@ -41,7 +41,7 @@ static inline void set_preempt_state(struct a6xx_gpu *gpu, } /* Write the most recent wptr for the given ring into the hardware */ -static inline void update_wptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring) +static inline void update_wptr(struct a6xx_gpu *a6xx_gpu, struct msm_ringbuffer *ring) { unsigned long flags; uint32_t wptr; @@ -51,7 +51,7 @@ static inline void update_wptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring) if (ring->restore_wptr) { wptr = get_wptr(ring); - gpu_write(gpu, REG_A6XX_CP_RB_WPTR, wptr); + a6xx_fenced_write(a6xx_gpu, REG_A6XX_CP_RB_WPTR, wptr, BIT(0), false); ring->restore_wptr = false; } @@ -111,9 +111,9 @@ static void preempt_prepare_postamble(struct a6xx_gpu *a6xx_gpu) postamble[count++] = PKT7(CP_WAIT_REG_MEM, 6); postamble[count++] = CP_WAIT_REG_MEM_0_FUNCTION(WRITE_EQ); - postamble[count++] = CP_WAIT_REG_MEM_1_POLL_ADDR_LO( + postamble[count++] = CP_WAIT_REG_MEM_POLL_ADDR_LO( REG_A6XX_RBBM_PERFCTR_SRAM_INIT_STATUS); - postamble[count++] = CP_WAIT_REG_MEM_2_POLL_ADDR_HI(0); + postamble[count++] = CP_WAIT_REG_MEM_POLL_ADDR_HI(0); postamble[count++] = CP_WAIT_REG_MEM_3_REF(0x1); postamble[count++] = CP_WAIT_REG_MEM_4_MASK(0x1); postamble[count++] = CP_WAIT_REG_MEM_5_DELAY_LOOP_CYCLES(0); @@ -136,6 +136,21 @@ static void preempt_disable_postamble(struct a6xx_gpu *a6xx_gpu) a6xx_gpu->postamble_enabled = false; } +/* + * Set preemption keepalive vote. Please note that this vote is different from the one used in + * a6xx_irq() + */ +static void a6xx_preempt_keepalive_vote(struct msm_gpu *gpu, bool on) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + + if (adreno_has_gmu_wrapper(adreno_gpu)) + return; + + gmu_write(&a6xx_gpu->gmu, REG_A6XX_GMU_PWR_COL_PREEMPT_KEEPALIVE, on); +} + void a6xx_preempt_irq(struct msm_gpu *gpu) { uint32_t status; @@ -172,10 +187,12 @@ void a6xx_preempt_irq(struct msm_gpu *gpu) set_preempt_state(a6xx_gpu, PREEMPT_FINISH); - update_wptr(gpu, a6xx_gpu->cur_ring); + update_wptr(a6xx_gpu, a6xx_gpu->cur_ring); set_preempt_state(a6xx_gpu, PREEMPT_NONE); + a6xx_preempt_keepalive_vote(gpu, false); + trace_msm_gpu_preemption_irq(a6xx_gpu->cur_ring->id); /* @@ -268,7 +285,7 @@ void a6xx_preempt_trigger(struct msm_gpu *gpu) */ if (!ring || (a6xx_gpu->cur_ring == ring)) { set_preempt_state(a6xx_gpu, PREEMPT_FINISH); - update_wptr(gpu, a6xx_gpu->cur_ring); + update_wptr(a6xx_gpu, a6xx_gpu->cur_ring); set_preempt_state(a6xx_gpu, PREEMPT_NONE); spin_unlock_irqrestore(&a6xx_gpu->eval_lock, flags); return; @@ -302,13 +319,16 @@ void a6xx_preempt_trigger(struct msm_gpu *gpu) spin_unlock_irqrestore(&ring->preempt_lock, flags); - gpu_write64(gpu, - REG_A6XX_CP_CONTEXT_SWITCH_SMMU_INFO, - a6xx_gpu->preempt_smmu_iova[ring->id]); + /* Set the keepalive bit to keep the GPU ON until preemption is complete */ + a6xx_preempt_keepalive_vote(gpu, true); + + a6xx_fenced_write(a6xx_gpu, + REG_A6XX_CP_CONTEXT_SWITCH_SMMU_INFO, a6xx_gpu->preempt_smmu_iova[ring->id], + BIT(1), true); - gpu_write64(gpu, + a6xx_fenced_write(a6xx_gpu, REG_A6XX_CP_CONTEXT_SWITCH_PRIV_NON_SECURE_RESTORE_ADDR, - a6xx_gpu->preempt_iova[ring->id]); + a6xx_gpu->preempt_iova[ring->id], BIT(1), true); a6xx_gpu->next_ring = ring; @@ -328,7 +348,7 @@ void a6xx_preempt_trigger(struct msm_gpu *gpu) set_preempt_state(a6xx_gpu, PREEMPT_TRIGGERED); /* Trigger the preemption */ - gpu_write(gpu, REG_A6XX_CP_CONTEXT_SWITCH_CNTL, cntl); + a6xx_fenced_write(a6xx_gpu, REG_A6XX_CP_CONTEXT_SWITCH_CNTL, cntl, BIT(1), false); } static int preempt_init_ring(struct a6xx_gpu *a6xx_gpu, diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c index 50945bfe9b49..28f744f3caf7 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_device.c +++ b/drivers/gpu/drm/msm/adreno/adreno_device.c @@ -24,6 +24,10 @@ bool disable_acd; MODULE_PARM_DESC(disable_acd, "Forcefully disable GPU ACD"); module_param_unsafe(disable_acd, bool, 0400); +static bool skip_gpu; +MODULE_PARM_DESC(no_gpu, "Disable GPU driver register (0=enable GPU driver register (default), 1=skip GPU driver register"); +module_param(skip_gpu, bool, 0400); + extern const struct adreno_gpulist a2xx_gpulist; extern const struct adreno_gpulist a3xx_gpulist; extern const struct adreno_gpulist a4xx_gpulist; @@ -184,6 +188,9 @@ bool adreno_has_gpu(struct device_node *node) uint32_t chip_id; int ret; + if (skip_gpu) + return false; + ret = find_chipid(node, &chip_id); if (ret) return false; @@ -404,10 +411,16 @@ static struct platform_driver adreno_driver = { void __init adreno_register(void) { + if (skip_gpu) + return; + platform_driver_register(&adreno_driver); } void __exit adreno_unregister(void) { + if (skip_gpu) + return; + platform_driver_unregister(&adreno_driver); } diff --git a/drivers/gpu/drm/msm/adreno/adreno_gen7_0_0_snapshot.h b/drivers/gpu/drm/msm/adreno/adreno_gen7_0_0_snapshot.h index cb66ece6606b..04b49d385f9d 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gen7_0_0_snapshot.h +++ b/drivers/gpu/drm/msm/adreno/adreno_gen7_0_0_snapshot.h @@ -81,7 +81,7 @@ static const u32 gen7_0_0_debugbus_blocks[] = { A7XX_DBGBUS_USPTP_7, }; -static struct gen7_shader_block gen7_0_0_shader_blocks[] = { +static const struct gen7_shader_block gen7_0_0_shader_blocks[] = { {A7XX_TP0_TMO_DATA, 0x200, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, {A7XX_TP0_SMO_DATA, 0x80, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, {A7XX_TP0_MIPMAP_BASE_DATA, 0x3c0, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, @@ -668,12 +668,19 @@ static const u32 gen7_0_0_sp_noncontext_pipe_lpac_usptp_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_noncontext_pipe_lpac_usptp_registers), 8)); -/* Block: TPl1 Cluster: noncontext Pipeline: A7XX_PIPE_BR */ -static const u32 gen7_0_0_tpl1_noncontext_pipe_br_registers[] = { +/* Block: TPl1 Cluster: noncontext Pipeline: A7XX_PIPE_NONE */ +static const u32 gen7_0_0_tpl1_noncontext_pipe_none_registers[] = { 0x0b600, 0x0b600, 0x0b602, 0x0b602, 0x0b604, 0x0b604, 0x0b608, 0x0b60c, 0x0b60f, 0x0b621, 0x0b630, 0x0b633, UINT_MAX, UINT_MAX, }; +static_assert(IS_ALIGNED(sizeof(gen7_0_0_tpl1_noncontext_pipe_none_registers), 8)); + +/* Block: TPl1 Cluster: noncontext Pipeline: A7XX_PIPE_BR */ +static const u32 gen7_0_0_tpl1_noncontext_pipe_br_registers[] = { + 0x0b600, 0x0b600, + UINT_MAX, UINT_MAX, +}; static_assert(IS_ALIGNED(sizeof(gen7_0_0_tpl1_noncontext_pipe_br_registers), 8)); /* Block: TPl1 Cluster: noncontext Pipeline: A7XX_PIPE_LPAC */ @@ -695,7 +702,7 @@ static const struct gen7_sel_reg gen7_0_0_rb_rbp_sel = { .val = 0x9, }; -static struct gen7_cluster_registers gen7_0_0_clusters[] = { +static const struct gen7_cluster_registers gen7_0_0_clusters[] = { { A7XX_CLUSTER_NONE, A7XX_PIPE_BR, STATE_NON_CONTEXT, gen7_0_0_noncontext_pipe_br_registers, }, { A7XX_CLUSTER_NONE, A7XX_PIPE_BV, STATE_NON_CONTEXT, @@ -764,7 +771,7 @@ static struct gen7_cluster_registers gen7_0_0_clusters[] = { gen7_0_0_vpc_cluster_vpc_ps_pipe_bv_registers, }, }; -static struct gen7_sptp_cluster_registers gen7_0_0_sptp_clusters[] = { +static const struct gen7_sptp_cluster_registers gen7_0_0_sptp_clusters[] = { { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_STATE, gen7_0_0_sp_noncontext_pipe_br_hlsq_state_registers, 0xae00 }, { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_SP_TOP, @@ -914,7 +921,7 @@ static const u32 gen7_0_0_dpm_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_dpm_registers), 8)); -static struct gen7_reg_list gen7_0_0_reg_list[] = { +static const struct gen7_reg_list gen7_0_0_reg_list[] = { { gen7_0_0_gpu_registers, NULL }, { gen7_0_0_cx_misc_registers, NULL }, { gen7_0_0_dpm_registers, NULL }, diff --git a/drivers/gpu/drm/msm/adreno/adreno_gen7_2_0_snapshot.h b/drivers/gpu/drm/msm/adreno/adreno_gen7_2_0_snapshot.h index 6f8ad50f32ce..772652eb61f3 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gen7_2_0_snapshot.h +++ b/drivers/gpu/drm/msm/adreno/adreno_gen7_2_0_snapshot.h @@ -95,7 +95,7 @@ static const u32 gen7_2_0_debugbus_blocks[] = { A7XX_DBGBUS_CCHE_2, }; -static struct gen7_shader_block gen7_2_0_shader_blocks[] = { +static const struct gen7_shader_block gen7_2_0_shader_blocks[] = { {A7XX_TP0_TMO_DATA, 0x200, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, {A7XX_TP0_SMO_DATA, 0x80, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, {A7XX_TP0_MIPMAP_BASE_DATA, 0x3c0, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, @@ -489,7 +489,7 @@ static const struct gen7_sel_reg gen7_2_0_rb_rbp_sel = { .val = 0x9, }; -static struct gen7_cluster_registers gen7_2_0_clusters[] = { +static const struct gen7_cluster_registers gen7_2_0_clusters[] = { { A7XX_CLUSTER_NONE, A7XX_PIPE_BR, STATE_NON_CONTEXT, gen7_2_0_noncontext_pipe_br_registers, }, { A7XX_CLUSTER_NONE, A7XX_PIPE_BV, STATE_NON_CONTEXT, @@ -558,7 +558,7 @@ static struct gen7_cluster_registers gen7_2_0_clusters[] = { gen7_0_0_vpc_cluster_vpc_ps_pipe_bv_registers, }, }; -static struct gen7_sptp_cluster_registers gen7_2_0_sptp_clusters[] = { +static const struct gen7_sptp_cluster_registers gen7_2_0_sptp_clusters[] = { { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_STATE, gen7_0_0_sp_noncontext_pipe_br_hlsq_state_registers, 0xae00 }, { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_SP_TOP, @@ -573,6 +573,8 @@ static struct gen7_sptp_cluster_registers gen7_2_0_sptp_clusters[] = { gen7_0_0_sp_noncontext_pipe_lpac_usptp_registers, 0xaf80 }, { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_USPTP, gen7_0_0_tpl1_noncontext_pipe_br_registers, 0xb600 }, + { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, A7XX_PIPE_NONE, 0, A7XX_USPTP, + gen7_0_0_tpl1_noncontext_pipe_none_registers, 0xb600 }, { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, A7XX_PIPE_LPAC, 0, A7XX_USPTP, gen7_0_0_tpl1_noncontext_pipe_lpac_registers, 0xb780 }, { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_STATE, @@ -737,7 +739,7 @@ static const u32 gen7_2_0_dpm_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_2_0_dpm_registers), 8)); -static struct gen7_reg_list gen7_2_0_reg_list[] = { +static const struct gen7_reg_list gen7_2_0_reg_list[] = { { gen7_2_0_gpu_registers, NULL }, { gen7_2_0_cx_misc_registers, NULL }, { gen7_2_0_dpm_registers, NULL }, diff --git a/drivers/gpu/drm/msm/adreno/adreno_gen7_9_0_snapshot.h b/drivers/gpu/drm/msm/adreno/adreno_gen7_9_0_snapshot.h index e02cabb39f19..0956dfca1f05 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gen7_9_0_snapshot.h +++ b/drivers/gpu/drm/msm/adreno/adreno_gen7_9_0_snapshot.h @@ -117,7 +117,7 @@ static const u32 gen7_9_0_cx_debugbus_blocks[] = { A7XX_DBGBUS_GBIF_CX, }; -static struct gen7_shader_block gen7_9_0_shader_blocks[] = { +static const struct gen7_shader_block gen7_9_0_shader_blocks[] = { { A7XX_TP0_TMO_DATA, 0x0200, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, { A7XX_TP0_SMO_DATA, 0x0080, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, { A7XX_TP0_MIPMAP_BASE_DATA, 0x03C0, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, @@ -1116,7 +1116,7 @@ static const struct gen7_sel_reg gen7_9_0_rb_rbp_sel = { .val = 0x9, }; -static struct gen7_cluster_registers gen7_9_0_clusters[] = { +static const struct gen7_cluster_registers gen7_9_0_clusters[] = { { A7XX_CLUSTER_NONE, A7XX_PIPE_BR, STATE_NON_CONTEXT, gen7_9_0_non_context_pipe_br_registers, }, { A7XX_CLUSTER_NONE, A7XX_PIPE_BV, STATE_NON_CONTEXT, @@ -1185,7 +1185,7 @@ static struct gen7_cluster_registers gen7_9_0_clusters[] = { gen7_9_0_vpc_pipe_bv_cluster_vpc_ps_registers, }, }; -static struct gen7_sptp_cluster_registers gen7_9_0_sptp_clusters[] = { +static const struct gen7_sptp_cluster_registers gen7_9_0_sptp_clusters[] = { { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_STATE, gen7_9_0_non_context_sp_pipe_br_hlsq_state_registers, 0xae00}, { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_SP_TOP, @@ -1294,34 +1294,34 @@ static struct gen7_sptp_cluster_registers gen7_9_0_sptp_clusters[] = { gen7_9_0_tpl1_pipe_br_cluster_sp_ps_usptp_registers, 0xb000}, }; -static struct a6xx_indexed_registers gen7_9_0_cp_indexed_reg_list[] = { +static const struct a6xx_indexed_registers gen7_9_0_cp_indexed_reg_list[] = { { "CP_SQE_STAT", REG_A6XX_CP_SQE_STAT_ADDR, REG_A6XX_CP_SQE_STAT_DATA, 0x00040}, { "CP_DRAW_STATE", REG_A6XX_CP_DRAW_STATE_ADDR, REG_A6XX_CP_DRAW_STATE_DATA, 0x00200}, - { "CP_ROQ", REG_A6XX_CP_ROQ_DBG_ADDR, + { "CP_ROQ_DBG", REG_A6XX_CP_ROQ_DBG_ADDR, REG_A6XX_CP_ROQ_DBG_DATA, 0x00800}, - { "CP_UCODE_DBG_DATA", REG_A6XX_CP_SQE_UCODE_DBG_ADDR, + { "CP_SQE_UCODE_DBG", REG_A6XX_CP_SQE_UCODE_DBG_ADDR, REG_A6XX_CP_SQE_UCODE_DBG_DATA, 0x08000}, - { "CP_BV_DRAW_STATE_ADDR", REG_A7XX_CP_BV_DRAW_STATE_ADDR, + { "CP_BV_DRAW_STATE", REG_A7XX_CP_BV_DRAW_STATE_ADDR, REG_A7XX_CP_BV_DRAW_STATE_DATA, 0x00200}, - { "CP_BV_ROQ_DBG_ADDR", REG_A7XX_CP_BV_ROQ_DBG_ADDR, + { "CP_BV_ROQ_DBG", REG_A7XX_CP_BV_ROQ_DBG_ADDR, REG_A7XX_CP_BV_ROQ_DBG_DATA, 0x00800}, - { "CP_BV_SQE_UCODE_DBG_ADDR", REG_A7XX_CP_BV_SQE_UCODE_DBG_ADDR, + { "CP_BV_SQE_UCODE_DBG", REG_A7XX_CP_BV_SQE_UCODE_DBG_ADDR, REG_A7XX_CP_BV_SQE_UCODE_DBG_DATA, 0x08000}, - { "CP_BV_SQE_STAT_ADDR", REG_A7XX_CP_BV_SQE_STAT_ADDR, + { "CP_BV_SQE_STAT", REG_A7XX_CP_BV_SQE_STAT_ADDR, REG_A7XX_CP_BV_SQE_STAT_DATA, 0x00040}, - { "CP_RESOURCE_TBL", REG_A7XX_CP_RESOURCE_TABLE_DBG_ADDR, + { "CP_RESOURCE_TABLE_DBG", REG_A7XX_CP_RESOURCE_TABLE_DBG_ADDR, REG_A7XX_CP_RESOURCE_TABLE_DBG_DATA, 0x04100}, - { "CP_LPAC_DRAW_STATE_ADDR", REG_A7XX_CP_LPAC_DRAW_STATE_ADDR, + { "CP_LPAC_DRAW_STATE", REG_A7XX_CP_LPAC_DRAW_STATE_ADDR, REG_A7XX_CP_LPAC_DRAW_STATE_DATA, 0x00200}, - { "CP_LPAC_ROQ", REG_A7XX_CP_LPAC_ROQ_DBG_ADDR, + { "CP_LPAC_ROQ_DBG", REG_A7XX_CP_LPAC_ROQ_DBG_ADDR, REG_A7XX_CP_LPAC_ROQ_DBG_DATA, 0x00200}, - { "CP_SQE_AC_UCODE_DBG_ADDR", REG_A7XX_CP_SQE_AC_UCODE_DBG_ADDR, + { "CP_SQE_AC_UCODE_DBG", REG_A7XX_CP_SQE_AC_UCODE_DBG_ADDR, REG_A7XX_CP_SQE_AC_UCODE_DBG_DATA, 0x08000}, - { "CP_SQE_AC_STAT_ADDR", REG_A7XX_CP_SQE_AC_STAT_ADDR, + { "CP_SQE_AC_STAT", REG_A7XX_CP_SQE_AC_STAT_ADDR, REG_A7XX_CP_SQE_AC_STAT_DATA, 0x00040}, - { "CP_LPAC_FIFO_DBG_ADDR", REG_A7XX_CP_LPAC_FIFO_DBG_ADDR, + { "CP_LPAC_FIFO_DBG", REG_A7XX_CP_LPAC_FIFO_DBG_ADDR, REG_A7XX_CP_LPAC_FIFO_DBG_DATA, 0x00040}, { "CP_AQE_ROQ_0", REG_A7XX_CP_AQE_ROQ_DBG_ADDR_0, REG_A7XX_CP_AQE_ROQ_DBG_DATA_0, 0x00100}, @@ -1337,7 +1337,7 @@ static struct a6xx_indexed_registers gen7_9_0_cp_indexed_reg_list[] = { REG_A7XX_CP_AQE_STAT_DATA_1, 0x00040}, }; -static struct gen7_reg_list gen7_9_0_reg_list[] = { +static const struct gen7_reg_list gen7_9_0_reg_list[] = { { gen7_9_0_gpu_registers, NULL}, { gen7_9_0_cx_misc_registers, NULL}, { gen7_9_0_cx_dbgc_registers, NULL}, diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index f1230465bf0d..afaa3cfefd35 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -10,7 +10,7 @@ #include <linux/interconnect.h> #include <linux/firmware/qcom/qcom_scm.h> #include <linux/kernel.h> -#include <linux/of_address.h> +#include <linux/of_reserved_mem.h> #include <linux/pm_opp.h> #include <linux/slab.h> #include <linux/soc/qcom/mdt_loader.h> @@ -33,7 +33,7 @@ static int zap_shader_load_mdt(struct msm_gpu *gpu, const char *fwname, struct device *dev = &gpu->pdev->dev; const struct firmware *fw; const char *signed_fwname = NULL; - struct device_node *np, *mem_np; + struct device_node *np; struct resource r; phys_addr_t mem_phys; ssize_t mem_size; @@ -51,18 +51,11 @@ static int zap_shader_load_mdt(struct msm_gpu *gpu, const char *fwname, return -ENODEV; } - mem_np = of_parse_phandle(np, "memory-region", 0); - of_node_put(np); - if (!mem_np) { + ret = of_reserved_mem_region_to_resource(np, 0, &r); + if (ret) { zap_available = false; - return -EINVAL; - } - - ret = of_address_to_resource(mem_np, 0, &r); - of_node_put(mem_np); - if (ret) return ret; - + } mem_phys = r.start; /* @@ -209,9 +202,7 @@ adreno_iommu_create_vm(struct msm_gpu *gpu, u64 start, size; mmu = msm_iommu_gpu_new(&pdev->dev, gpu, quirks); - if (!mmu) - return ERR_PTR(-ENODEV); - else if (IS_ERR_OR_NULL(mmu)) + if (IS_ERR(mmu)) return ERR_CAST(mmu); geometry = msm_iommu_get_geometry(mmu); diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h index 9dc93c247196..390fa6720d9b 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h @@ -59,6 +59,7 @@ enum adreno_family { #define ADRENO_QUIRK_HAS_CACHED_COHERENT BIT(4) #define ADRENO_QUIRK_PREEMPTION BIT(5) #define ADRENO_QUIRK_4GB_VA BIT(6) +#define ADRENO_QUIRK_IFPC BIT(7) /* Helper for formating the chip_id in the way that userspace tools like * crashdec expect. diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c index 0fb5789c60d0..13cc658065c5 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c @@ -32,6 +32,26 @@ enum dpu_perf_mode { }; /** + * dpu_core_perf_adjusted_mode_clk - Adjust given mode clock rate according to + * the perf clock factor. + * @crtc_clk_rate - Unadjusted mode clock rate + * @perf_cfg: performance configuration + */ +u64 dpu_core_perf_adjusted_mode_clk(u64 mode_clk_rate, + const struct dpu_perf_cfg *perf_cfg) +{ + u32 clk_factor; + + clk_factor = perf_cfg->clk_inefficiency_factor; + if (clk_factor) { + mode_clk_rate *= clk_factor; + do_div(mode_clk_rate, 100); + } + + return mode_clk_rate; +} + +/** * _dpu_core_perf_calc_bw() - to calculate BW per crtc * @perf_cfg: performance configuration * @crtc: pointer to a crtc @@ -75,28 +95,21 @@ static u64 _dpu_core_perf_calc_clk(const struct dpu_perf_cfg *perf_cfg, struct drm_plane *plane; struct dpu_plane_state *pstate; struct drm_display_mode *mode; - u64 crtc_clk; - u32 clk_factor; + u64 mode_clk; mode = &state->adjusted_mode; - crtc_clk = (u64)mode->vtotal * mode->hdisplay * drm_mode_vrefresh(mode); + mode_clk = (u64)mode->vtotal * mode->hdisplay * drm_mode_vrefresh(mode); drm_atomic_crtc_for_each_plane(plane, crtc) { pstate = to_dpu_plane_state(plane->state); if (!pstate) continue; - crtc_clk = max(pstate->plane_clk, crtc_clk); - } - - clk_factor = perf_cfg->clk_inefficiency_factor; - if (clk_factor) { - crtc_clk *= clk_factor; - do_div(crtc_clk, 100); + mode_clk = max(pstate->plane_clk, mode_clk); } - return crtc_clk; + return dpu_core_perf_adjusted_mode_clk(mode_clk, perf_cfg); } static struct dpu_kms *_dpu_crtc_get_kms(struct drm_crtc *crtc) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h index d2f21d34e501..3740bc97422c 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h @@ -54,6 +54,9 @@ struct dpu_core_perf { u32 fix_core_ab_vote; }; +u64 dpu_core_perf_adjusted_mode_clk(u64 clk_rate, + const struct dpu_perf_cfg *perf_cfg); + int dpu_core_perf_crtc_check(struct drm_crtc *crtc, struct drm_crtc_state *state); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c index d4b545448d74..4b970a59deaf 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c @@ -377,11 +377,10 @@ static void _dpu_crtc_setup_blend_cfg(struct dpu_crtc_mixer *mixer, static void _dpu_crtc_program_lm_output_roi(struct drm_crtc *crtc) { struct dpu_crtc_state *crtc_state; - int lm_idx, lm_horiz_position; + int lm_idx; crtc_state = to_dpu_crtc_state(crtc->state); - lm_horiz_position = 0; for (lm_idx = 0; lm_idx < crtc_state->num_mixers; lm_idx++) { const struct drm_rect *lm_roi = &crtc_state->lm_bounds[lm_idx]; struct dpu_hw_mixer *hw_lm = crtc_state->mixers[lm_idx].hw_lm; @@ -392,7 +391,7 @@ static void _dpu_crtc_program_lm_output_roi(struct drm_crtc *crtc) cfg.out_width = drm_rect_width(lm_roi); cfg.out_height = drm_rect_height(lm_roi); - cfg.right_mixer = lm_horiz_position++; + cfg.right_mixer = lm_idx & 0x1; cfg.flags = 0; hw_lm->ops.setup_mixer_out(hw_lm, &cfg); } @@ -596,7 +595,7 @@ static void _dpu_crtc_complete_flip(struct drm_crtc *crtc) spin_lock_irqsave(&dev->event_lock, flags); if (dpu_crtc->event) { - DRM_DEBUG_VBL("%s: send event: %pK\n", dpu_crtc->name, + DRM_DEBUG_VBL("%s: send event: %p\n", dpu_crtc->name, dpu_crtc->event); trace_dpu_crtc_complete_flip(DRMID(crtc)); drm_crtc_send_vblank_event(crtc, dpu_crtc->event); @@ -1534,6 +1533,7 @@ static enum drm_mode_status dpu_crtc_mode_valid(struct drm_crtc *crtc, const struct drm_display_mode *mode) { struct dpu_kms *dpu_kms = _dpu_crtc_get_kms(crtc); + u64 adjusted_mode_clk; /* if there is no 3d_mux block we cannot merge LMs so we cannot * split the large layer into 2 LMs, filter out such modes @@ -1541,6 +1541,17 @@ static enum drm_mode_status dpu_crtc_mode_valid(struct drm_crtc *crtc, if (!dpu_kms->catalog->caps->has_3d_merge && mode->hdisplay > dpu_kms->catalog->caps->max_mixer_width) return MODE_BAD_HVALUE; + + adjusted_mode_clk = dpu_core_perf_adjusted_mode_clk(mode->clock, + dpu_kms->perf.perf_cfg); + + /* + * The given mode, adjusted for the perf clock factor, should not exceed + * the max core clock rate + */ + if (dpu_kms->perf.max_core_clk_rate < adjusted_mode_clk * 1000) + return MODE_CLOCK_HIGH; + /* * max crtc width is equal to the max mixer width * 2 and max height is 4K */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c index 05e5f3463e30..258edaa18fc0 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c @@ -730,6 +730,8 @@ bool dpu_encoder_needs_modeset(struct drm_encoder *drm_enc, struct drm_atomic_st return false; conn_state = drm_atomic_get_new_connector_state(state, connector); + if (!conn_state) + return false; /** * These checks are duplicated from dpu_encoder_update_topology() since diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c index 56a5b596554d..46f348972a97 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c @@ -446,7 +446,7 @@ static void _dpu_encoder_phys_wb_handle_wbdone_timeout( static int dpu_encoder_phys_wb_wait_for_commit_done( struct dpu_encoder_phys *phys_enc) { - unsigned long ret; + int ret; struct dpu_encoder_wait_info wait_info; struct dpu_encoder_phys_wb *wb_enc = to_dpu_encoder_phys_wb(phys_enc); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c index e824cd64fd3f..6641455c4ec6 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c @@ -338,7 +338,6 @@ static const struct dpu_sspp_sub_blks dpu_dma_sblk = _DMA_SBLK(); *************************************************************/ static const struct dpu_lm_sub_blks msm8998_lm_sblk = { - .maxwidth = DEFAULT_DPU_OUTPUT_LINE_WIDTH, .maxblendstages = 7, /* excluding base layer */ .blendstage_base = { /* offsets relative to mixer base */ 0x20, 0x50, 0x80, 0xb0, 0x230, @@ -347,7 +346,6 @@ static const struct dpu_lm_sub_blks msm8998_lm_sblk = { }; static const struct dpu_lm_sub_blks sdm845_lm_sblk = { - .maxwidth = DEFAULT_DPU_OUTPUT_LINE_WIDTH, .maxblendstages = 11, /* excluding base layer */ .blendstage_base = { /* offsets relative to mixer base */ 0x20, 0x38, 0x50, 0x68, 0x80, 0x98, @@ -356,7 +354,6 @@ static const struct dpu_lm_sub_blks sdm845_lm_sblk = { }; static const struct dpu_lm_sub_blks sc7180_lm_sblk = { - .maxwidth = DEFAULT_DPU_OUTPUT_LINE_WIDTH, .maxblendstages = 7, /* excluding base layer */ .blendstage_base = { /* offsets relative to mixer base */ 0x20, 0x38, 0x50, 0x68, 0x80, 0x98, 0xb0 @@ -364,7 +361,6 @@ static const struct dpu_lm_sub_blks sc7180_lm_sblk = { }; static const struct dpu_lm_sub_blks sm8750_lm_sblk = { - .maxwidth = DEFAULT_DPU_OUTPUT_LINE_WIDTH, .maxblendstages = 11, /* excluding base layer */ .blendstage_base = { /* offsets relative to mixer base */ /* 0x40 + n*0x30 */ @@ -374,7 +370,6 @@ static const struct dpu_lm_sub_blks sm8750_lm_sblk = { }; static const struct dpu_lm_sub_blks qcm2290_lm_sblk = { - .maxwidth = DEFAULT_DPU_LINE_WIDTH, .maxblendstages = 4, /* excluding base layer */ .blendstage_base = { /* offsets relative to mixer base */ 0x20, 0x38, 0x50, 0x68 diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h index a78bb2c334e3..f0768f54e9b3 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h @@ -307,7 +307,6 @@ struct dpu_sspp_sub_blks { * @blendstage_base: Blend-stage register base offset */ struct dpu_lm_sub_blks { - u32 maxwidth; u32 maxblendstages; u32 blendstage_base[MAX_BLOCKS]; }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c index 11fb1bc54fa9..54b20faa0b69 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c @@ -31,14 +31,14 @@ static void dpu_setup_dspp_pcc(struct dpu_hw_dspp *ctx, u32 base; if (!ctx) { - DRM_ERROR("invalid ctx %pK\n", ctx); + DRM_ERROR("invalid ctx %p\n", ctx); return; } base = ctx->cap->sblk->pcc.base; if (!base) { - DRM_ERROR("invalid ctx %pK pcc base 0x%x\n", ctx, base); + DRM_ERROR("invalid ctx %p pcc base 0x%x\n", ctx, base); return; } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c index 12dcb32b4724..4e5a8ecd31f7 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c @@ -1110,7 +1110,7 @@ static int _dpu_kms_mmu_init(struct dpu_kms *dpu_kms) { struct drm_gpuvm *vm; - vm = msm_kms_init_vm(dpu_kms->dev); + vm = msm_kms_init_vm(dpu_kms->dev, dpu_kms->dev->dev->parent); if (IS_ERR(vm)) return PTR_ERR(vm); @@ -1345,7 +1345,7 @@ static int dpu_kms_mmap_mdp5(struct dpu_kms *dpu_kms) dpu_kms->mmio = NULL; return ret; } - DRM_DEBUG("mapped dpu address space @%pK\n", dpu_kms->mmio); + DRM_DEBUG("mapped dpu address space @%p\n", dpu_kms->mmio); dpu_kms->vbif[VBIF_RT] = msm_ioremap_mdss(mdss_dev, dpu_kms->pdev, @@ -1380,7 +1380,7 @@ static int dpu_kms_mmap_dpu(struct dpu_kms *dpu_kms) dpu_kms->mmio = NULL; return ret; } - DRM_DEBUG("mapped dpu address space @%pK\n", dpu_kms->mmio); + DRM_DEBUG("mapped dpu address space @%p\n", dpu_kms->mmio); dpu_kms->vbif[VBIF_RT] = msm_ioremap(pdev, "vbif"); if (IS_ERR(dpu_kms->vbif[VBIF_RT])) { diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c index 01171c535a27..f54cf0faa1c7 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c @@ -922,6 +922,9 @@ static int dpu_plane_is_multirect_capable(struct dpu_hw_sspp *sspp, if (MSM_FORMAT_IS_YUV(fmt)) return false; + if (!sspp) + return true; + if (!test_bit(DPU_SSPP_SMART_DMA_V1, &sspp->cap->features) && !test_bit(DPU_SSPP_SMART_DMA_V2, &sspp->cap->features)) return false; @@ -1028,6 +1031,7 @@ static int dpu_plane_try_multirect_shared(struct dpu_plane_state *pstate, prev_pipe->multirect_mode != DPU_SSPP_MULTIRECT_NONE) return false; + /* Do not validate SSPP of current plane when it is not ready */ if (!dpu_plane_is_multirect_capable(pipe->sspp, pipe_cfg, fmt) || !dpu_plane_is_multirect_capable(prev_pipe->sspp, prev_pipe_cfg, prev_fmt)) return false; @@ -1129,7 +1133,7 @@ static int dpu_plane_virtual_atomic_check(struct drm_plane *plane, struct drm_plane_state *old_plane_state = drm_atomic_get_old_plane_state(state, plane); struct dpu_plane_state *pstate = to_dpu_plane_state(plane_state); - struct drm_crtc_state *crtc_state; + struct drm_crtc_state *crtc_state = NULL; int ret; if (IS_ERR(plane_state)) @@ -1162,7 +1166,7 @@ static int dpu_plane_virtual_atomic_check(struct drm_plane *plane, if (!old_plane_state || !old_plane_state->fb || old_plane_state->src_w != plane_state->src_w || old_plane_state->src_h != plane_state->src_h || - old_plane_state->src_w != plane_state->src_w || + old_plane_state->crtc_w != plane_state->crtc_w || old_plane_state->crtc_h != plane_state->crtc_h || msm_framebuffer_format(old_plane_state->fb) != msm_framebuffer_format(plane_state->fb)) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c index 25382120cb1a..2c77c74fac0f 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c @@ -865,6 +865,21 @@ void dpu_rm_release_all_sspp(struct dpu_global_state *global_state, ARRAY_SIZE(global_state->sspp_to_crtc_id), crtc_id); } +static char *dpu_hw_blk_type_name[] = { + [DPU_HW_BLK_TOP] = "TOP", + [DPU_HW_BLK_SSPP] = "SSPP", + [DPU_HW_BLK_LM] = "LM", + [DPU_HW_BLK_CTL] = "CTL", + [DPU_HW_BLK_PINGPONG] = "pingpong", + [DPU_HW_BLK_INTF] = "INTF", + [DPU_HW_BLK_WB] = "WB", + [DPU_HW_BLK_DSPP] = "DSPP", + [DPU_HW_BLK_MERGE_3D] = "merge_3d", + [DPU_HW_BLK_DSC] = "DSC", + [DPU_HW_BLK_CDM] = "CDM", + [DPU_HW_BLK_MAX] = "unknown", +}; + /** * dpu_rm_get_assigned_resources - Get hw resources of the given type that are * assigned to this encoder @@ -946,13 +961,13 @@ int dpu_rm_get_assigned_resources(struct dpu_rm *rm, } if (num_blks == blks_size) { - DPU_ERROR("More than %d resources assigned to crtc %d\n", - blks_size, crtc_id); + DPU_ERROR("More than %d %s assigned to crtc %d\n", + blks_size, dpu_hw_blk_type_name[type], crtc_id); break; } if (!hw_blks[i]) { - DPU_ERROR("Allocated resource %d unavailable to assign to crtc %d\n", - type, crtc_id); + DPU_ERROR("%s unavailable to assign to crtc %d\n", + dpu_hw_blk_type_name[type], crtc_id); break; } blks[num_blks++] = hw_blks[i]; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c index 8ff496082902..cd73468e369a 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c @@ -80,7 +80,6 @@ static int dpu_wb_conn_atomic_check(struct drm_connector *connector, static const struct drm_connector_funcs dpu_wb_conn_funcs = { .reset = drm_atomic_helper_connector_reset, .fill_modes = drm_helper_probe_single_connector_modes, - .destroy = drm_connector_cleanup, .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, }; @@ -131,12 +130,9 @@ int dpu_writeback_init(struct drm_device *dev, struct drm_encoder *enc, drm_connector_helper_add(&dpu_wb_conn->base.base, &dpu_wb_conn_helper_funcs); - /* DPU initializes the encoder and sets it up completely for writeback - * cases and hence should use the new API drm_writeback_connector_init_with_encoder - * to initialize the writeback connector - */ - rc = drm_writeback_connector_init_with_encoder(dev, &dpu_wb_conn->base, enc, - &dpu_wb_conn_funcs, format_list, num_formats); + rc = drmm_writeback_connector_init(dev, &dpu_wb_conn->base, + &dpu_wb_conn_funcs, enc, + format_list, num_formats); if (!rc) dpu_wb_conn->wb_enc = enc; diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c index 0952c7f18abd..809ca191e9de 100644 --- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c +++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c @@ -391,11 +391,9 @@ static void read_mdp_hw_revision(struct mdp4_kms *mdp4_kms, static int mdp4_kms_init(struct drm_device *dev) { - struct platform_device *pdev = to_platform_device(dev->dev); struct msm_drm_private *priv = dev->dev_private; struct mdp4_kms *mdp4_kms = to_mdp4_kms(to_mdp_kms(priv->kms)); struct msm_kms *kms = NULL; - struct msm_mmu *mmu; struct drm_gpuvm *vm; int ret; u32 major, minor; @@ -458,29 +456,14 @@ static int mdp4_kms_init(struct drm_device *dev) mdp4_disable(mdp4_kms); mdelay(16); - mmu = msm_iommu_new(&pdev->dev, 0); - if (IS_ERR(mmu)) { - ret = PTR_ERR(mmu); + vm = msm_kms_init_vm(mdp4_kms->dev, NULL); + if (IS_ERR(vm)) { + ret = PTR_ERR(vm); goto fail; - } else if (!mmu) { - DRM_DEV_INFO(dev->dev, "no iommu, fallback to phys " - "contig buffers for scanout\n"); - vm = NULL; - } else { - vm = msm_gem_vm_create(dev, mmu, "mdp4", - 0x1000, 0x100000000 - 0x1000, - true); - - if (IS_ERR(vm)) { - if (!IS_ERR(mmu)) - mmu->funcs->destroy(mmu); - ret = PTR_ERR(vm); - goto fail; - } - - kms->vm = vm; } + kms->vm = vm; + ret = modeset_init(mdp4_kms); if (ret) { DRM_DEV_ERROR(dev->dev, "modeset_init failed: %d\n", ret); @@ -529,7 +512,7 @@ static int mdp4_probe(struct platform_device *pdev) mdp4_kms = devm_kzalloc(dev, sizeof(*mdp4_kms), GFP_KERNEL); if (!mdp4_kms) - return dev_err_probe(dev, -ENOMEM, "failed to allocate kms\n"); + return -ENOMEM; mdp4_kms->mmio = msm_ioremap(pdev, NULL); if (IS_ERR(mdp4_kms->mmio)) diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.h b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.h index fb348583dc84..06458d4ee48c 100644 --- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.h +++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.h @@ -202,6 +202,6 @@ static inline struct drm_encoder *mdp4_dsi_encoder_init(struct drm_device *dev) } #endif -struct clk *mpd4_get_lcdc_clock(struct drm_device *dev); +struct clk *mdp4_get_lcdc_clock(struct drm_device *dev); #endif /* __MDP4_KMS_H__ */ diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c index 06a307c1272d..1051873057f6 100644 --- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c +++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c @@ -375,7 +375,7 @@ struct drm_encoder *mdp4_lcdc_encoder_init(struct drm_device *dev) drm_encoder_helper_add(encoder, &mdp4_lcdc_encoder_helper_funcs); - mdp4_lcdc_encoder->lcdc_clk = mpd4_get_lcdc_clock(dev); + mdp4_lcdc_encoder->lcdc_clk = mdp4_get_lcdc_clock(dev); if (IS_ERR(mdp4_lcdc_encoder->lcdc_clk)) { DRM_DEV_ERROR(dev->dev, "failed to get lvds_clk\n"); return ERR_CAST(mdp4_lcdc_encoder->lcdc_clk); diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_pll.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_pll.c index fa2c29470510..04c49bf3d854 100644 --- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_pll.c +++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_pll.c @@ -54,7 +54,7 @@ static const struct pll_rate *find_rate(unsigned long rate) return &freqtbl[i-1]; } -static int mpd4_lvds_pll_enable(struct clk_hw *hw) +static int mdp4_lvds_pll_enable(struct clk_hw *hw) { struct mdp4_lvds_pll *lvds_pll = to_mdp4_lvds_pll(hw); struct mdp4_kms *mdp4_kms = get_kms(lvds_pll); @@ -80,7 +80,7 @@ static int mpd4_lvds_pll_enable(struct clk_hw *hw) return 0; } -static void mpd4_lvds_pll_disable(struct clk_hw *hw) +static void mdp4_lvds_pll_disable(struct clk_hw *hw) { struct mdp4_lvds_pll *lvds_pll = to_mdp4_lvds_pll(hw); struct mdp4_kms *mdp4_kms = get_kms(lvds_pll); @@ -91,21 +91,24 @@ static void mpd4_lvds_pll_disable(struct clk_hw *hw) mdp4_write(mdp4_kms, REG_MDP4_LVDS_PHY_PLL_CTRL_0, 0x0); } -static unsigned long mpd4_lvds_pll_recalc_rate(struct clk_hw *hw, +static unsigned long mdp4_lvds_pll_recalc_rate(struct clk_hw *hw, unsigned long parent_rate) { struct mdp4_lvds_pll *lvds_pll = to_mdp4_lvds_pll(hw); return lvds_pll->pixclk; } -static long mpd4_lvds_pll_round_rate(struct clk_hw *hw, unsigned long rate, - unsigned long *parent_rate) +static int mdp4_lvds_pll_determine_rate(struct clk_hw *hw, + struct clk_rate_request *req) { - const struct pll_rate *pll_rate = find_rate(rate); - return pll_rate->rate; + const struct pll_rate *pll_rate = find_rate(req->rate); + + req->rate = pll_rate->rate; + + return 0; } -static int mpd4_lvds_pll_set_rate(struct clk_hw *hw, unsigned long rate, +static int mdp4_lvds_pll_set_rate(struct clk_hw *hw, unsigned long rate, unsigned long parent_rate) { struct mdp4_lvds_pll *lvds_pll = to_mdp4_lvds_pll(hw); @@ -114,26 +117,26 @@ static int mpd4_lvds_pll_set_rate(struct clk_hw *hw, unsigned long rate, } -static const struct clk_ops mpd4_lvds_pll_ops = { - .enable = mpd4_lvds_pll_enable, - .disable = mpd4_lvds_pll_disable, - .recalc_rate = mpd4_lvds_pll_recalc_rate, - .round_rate = mpd4_lvds_pll_round_rate, - .set_rate = mpd4_lvds_pll_set_rate, +static const struct clk_ops mdp4_lvds_pll_ops = { + .enable = mdp4_lvds_pll_enable, + .disable = mdp4_lvds_pll_disable, + .recalc_rate = mdp4_lvds_pll_recalc_rate, + .determine_rate = mdp4_lvds_pll_determine_rate, + .set_rate = mdp4_lvds_pll_set_rate, }; -static const struct clk_parent_data mpd4_lvds_pll_parents[] = { +static const struct clk_parent_data mdp4_lvds_pll_parents[] = { { .fw_name = "pxo", .name = "pxo", }, }; static struct clk_init_data pll_init = { - .name = "mpd4_lvds_pll", - .ops = &mpd4_lvds_pll_ops, - .parent_data = mpd4_lvds_pll_parents, - .num_parents = ARRAY_SIZE(mpd4_lvds_pll_parents), + .name = "mdp4_lvds_pll", + .ops = &mdp4_lvds_pll_ops, + .parent_data = mdp4_lvds_pll_parents, + .num_parents = ARRAY_SIZE(mdp4_lvds_pll_parents), }; -static struct clk_hw *mpd4_lvds_pll_init(struct drm_device *dev) +static struct clk_hw *mdp4_lvds_pll_init(struct drm_device *dev) { struct mdp4_lvds_pll *lvds_pll; int ret; @@ -156,14 +159,14 @@ static struct clk_hw *mpd4_lvds_pll_init(struct drm_device *dev) return &lvds_pll->pll_hw; } -struct clk *mpd4_get_lcdc_clock(struct drm_device *dev) +struct clk *mdp4_get_lcdc_clock(struct drm_device *dev) { struct clk_hw *hw; struct clk *clk; /* TODO: do we need different pll in other cases? */ - hw = mpd4_lvds_pll_init(dev); + hw = mdp4_lvds_pll_init(dev); if (IS_ERR(hw)) { DRM_DEV_ERROR(dev->dev, "failed to register LVDS PLL\n"); return ERR_CAST(hw); diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c index 5b6ca8dd929e..61edf6864092 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c @@ -534,7 +534,7 @@ static int mdp5_kms_init(struct drm_device *dev) } mdelay(16); - vm = msm_kms_init_vm(mdp5_kms->dev); + vm = msm_kms_init_vm(mdp5_kms->dev, pdev->dev.parent); if (IS_ERR(vm)) { ret = PTR_ERR(vm); goto fail; diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c index 221f12db5f8b..4ea681130dba 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c @@ -5,6 +5,8 @@ #include <linux/clk-provider.h> #include <linux/platform_device.h> +#include <linux/pm_clock.h> +#include <linux/pm_runtime.h> #include <dt-bindings/phy/phy.h> #include "dsi_phy.h" @@ -511,30 +513,6 @@ int msm_dsi_cphy_timing_calc_v4(struct msm_dsi_dphy_timing *timing, return 0; } -static int dsi_phy_enable_resource(struct msm_dsi_phy *phy) -{ - struct device *dev = &phy->pdev->dev; - int ret; - - ret = pm_runtime_resume_and_get(dev); - if (ret) - return ret; - - ret = clk_prepare_enable(phy->ahb_clk); - if (ret) { - DRM_DEV_ERROR(dev, "%s: can't enable ahb clk, %d\n", __func__, ret); - pm_runtime_put_sync(dev); - } - - return ret; -} - -static void dsi_phy_disable_resource(struct msm_dsi_phy *phy) -{ - clk_disable_unprepare(phy->ahb_clk); - pm_runtime_put(&phy->pdev->dev); -} - static const struct of_device_id dsi_phy_dt_match[] = { #ifdef CONFIG_DRM_MSM_DSI_28NM_PHY { .compatible = "qcom,dsi-phy-28nm-hpm", @@ -698,22 +676,20 @@ static int dsi_phy_driver_probe(struct platform_device *pdev) if (ret) return ret; - phy->ahb_clk = msm_clk_get(pdev, "iface"); - if (IS_ERR(phy->ahb_clk)) - return dev_err_probe(dev, PTR_ERR(phy->ahb_clk), - "Unable to get ahb clk\n"); + platform_set_drvdata(pdev, phy); - ret = devm_pm_runtime_enable(&pdev->dev); + ret = devm_pm_runtime_enable(dev); if (ret) return ret; - /* PLL init will call into clk_register which requires - * register access, so we need to enable power and ahb clock. - */ - ret = dsi_phy_enable_resource(phy); + ret = devm_pm_clk_create(dev); if (ret) return ret; + ret = pm_clk_add(dev, "iface"); + if (ret < 0) + return dev_err_probe(dev, ret, "Unable to get iface clk\n"); + if (phy->cfg->ops.pll_init) { ret = phy->cfg->ops.pll_init(phy); if (ret) @@ -727,18 +703,19 @@ static int dsi_phy_driver_probe(struct platform_device *pdev) return dev_err_probe(dev, ret, "Failed to register clk provider\n"); - dsi_phy_disable_resource(phy); - - platform_set_drvdata(pdev, phy); - return 0; } +static const struct dev_pm_ops dsi_phy_pm_ops = { + SET_RUNTIME_PM_OPS(pm_clk_suspend, pm_clk_resume, NULL) +}; + static struct platform_driver dsi_phy_platform_driver = { .probe = dsi_phy_driver_probe, .driver = { .name = "msm_dsi_phy", .of_match_table = dsi_phy_dt_match, + .pm = &dsi_phy_pm_ops, }, }; @@ -764,9 +741,9 @@ int msm_dsi_phy_enable(struct msm_dsi_phy *phy, dev = &phy->pdev->dev; - ret = dsi_phy_enable_resource(phy); + ret = pm_runtime_resume_and_get(dev); if (ret) { - DRM_DEV_ERROR(dev, "%s: resource enable failed, %d\n", + DRM_DEV_ERROR(dev, "%s: resume failed, %d\n", __func__, ret); goto res_en_fail; } @@ -810,7 +787,7 @@ pll_restor_fail: phy_en_fail: regulator_bulk_disable(phy->cfg->num_regulators, phy->supplies); reg_en_fail: - dsi_phy_disable_resource(phy); + pm_runtime_put(dev); res_en_fail: return ret; } @@ -823,7 +800,7 @@ void msm_dsi_phy_disable(struct msm_dsi_phy *phy) phy->cfg->ops.disable(phy); regulator_bulk_disable(phy->cfg->num_regulators, phy->supplies); - dsi_phy_disable_resource(phy); + pm_runtime_put(&phy->pdev->dev); } void msm_dsi_phy_set_usecase(struct msm_dsi_phy *phy, diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h index c558f8df1684..e391505fdaf0 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h @@ -104,12 +104,12 @@ struct msm_dsi_phy { phys_addr_t lane_size; int id; - struct clk *ahb_clk; struct regulator_bulk_data *supplies; struct msm_dsi_dphy_timing timing; const struct msm_dsi_phy_cfg *cfg; void *tuning_cfg; + void *pll_data; enum msm_dsi_phy_usecase usecase; bool regulator_ldo_mode; diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c index af2e30f3f842..ec486ff02c9b 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c @@ -444,21 +444,19 @@ static unsigned long dsi_pll_10nm_vco_recalc_rate(struct clk_hw *hw, return (unsigned long)vco_rate; } -static long dsi_pll_10nm_clk_round_rate(struct clk_hw *hw, - unsigned long rate, unsigned long *parent_rate) +static int dsi_pll_10nm_clk_determine_rate(struct clk_hw *hw, + struct clk_rate_request *req) { struct dsi_pll_10nm *pll_10nm = to_pll_10nm(hw); - if (rate < pll_10nm->phy->cfg->min_pll_rate) - return pll_10nm->phy->cfg->min_pll_rate; - else if (rate > pll_10nm->phy->cfg->max_pll_rate) - return pll_10nm->phy->cfg->max_pll_rate; - else - return rate; + req->rate = clamp_t(unsigned long, req->rate, + pll_10nm->phy->cfg->min_pll_rate, pll_10nm->phy->cfg->max_pll_rate); + + return 0; } static const struct clk_ops clk_ops_dsi_pll_10nm_vco = { - .round_rate = dsi_pll_10nm_clk_round_rate, + .determine_rate = dsi_pll_10nm_clk_determine_rate, .set_rate = dsi_pll_10nm_vco_set_rate, .recalc_rate = dsi_pll_10nm_vco_recalc_rate, .prepare = dsi_pll_10nm_vco_prepare, diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c index 3a1c8ece6657..fdefcbd9c284 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c @@ -578,21 +578,19 @@ static void dsi_pll_14nm_vco_unprepare(struct clk_hw *hw) pll_14nm->phy->pll_on = false; } -static long dsi_pll_14nm_clk_round_rate(struct clk_hw *hw, - unsigned long rate, unsigned long *parent_rate) +static int dsi_pll_14nm_clk_determine_rate(struct clk_hw *hw, + struct clk_rate_request *req) { struct dsi_pll_14nm *pll_14nm = to_pll_14nm(hw); - if (rate < pll_14nm->phy->cfg->min_pll_rate) - return pll_14nm->phy->cfg->min_pll_rate; - else if (rate > pll_14nm->phy->cfg->max_pll_rate) - return pll_14nm->phy->cfg->max_pll_rate; - else - return rate; + req->rate = clamp_t(unsigned long, req->rate, + pll_14nm->phy->cfg->min_pll_rate, pll_14nm->phy->cfg->max_pll_rate); + + return 0; } static const struct clk_ops clk_ops_dsi_pll_14nm_vco = { - .round_rate = dsi_pll_14nm_clk_round_rate, + .determine_rate = dsi_pll_14nm_clk_determine_rate, .set_rate = dsi_pll_14nm_vco_set_rate, .recalc_rate = dsi_pll_14nm_vco_recalc_rate, .prepare = dsi_pll_14nm_vco_prepare, @@ -622,18 +620,20 @@ static unsigned long dsi_pll_14nm_postdiv_recalc_rate(struct clk_hw *hw, postdiv->flags, width); } -static long dsi_pll_14nm_postdiv_round_rate(struct clk_hw *hw, - unsigned long rate, - unsigned long *prate) +static int dsi_pll_14nm_postdiv_determine_rate(struct clk_hw *hw, + struct clk_rate_request *req) { struct dsi_pll_14nm_postdiv *postdiv = to_pll_14nm_postdiv(hw); struct dsi_pll_14nm *pll_14nm = postdiv->pll; - DBG("DSI%d PLL parent rate=%lu", pll_14nm->phy->id, rate); + DBG("DSI%d PLL parent rate=%lu", pll_14nm->phy->id, req->rate); - return divider_round_rate(hw, rate, prate, NULL, - postdiv->width, - postdiv->flags); + req->rate = divider_round_rate(hw, req->rate, &req->best_parent_rate, + NULL, + postdiv->width, + postdiv->flags); + + return 0; } static int dsi_pll_14nm_postdiv_set_rate(struct clk_hw *hw, unsigned long rate, @@ -680,7 +680,7 @@ static int dsi_pll_14nm_postdiv_set_rate(struct clk_hw *hw, unsigned long rate, static const struct clk_ops clk_ops_dsi_pll_14nm_postdiv = { .recalc_rate = dsi_pll_14nm_postdiv_recalc_rate, - .round_rate = dsi_pll_14nm_postdiv_round_rate, + .determine_rate = dsi_pll_14nm_postdiv_determine_rate, .set_rate = dsi_pll_14nm_postdiv_set_rate, }; diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c index 90348a2af3e9..d00e415b9a99 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c @@ -533,21 +533,20 @@ static void dsi_pll_28nm_vco_unprepare(struct clk_hw *hw) pll_28nm->phy->pll_on = false; } -static long dsi_pll_28nm_clk_round_rate(struct clk_hw *hw, - unsigned long rate, unsigned long *parent_rate) +static int dsi_pll_28nm_clk_determine_rate(struct clk_hw *hw, + struct clk_rate_request *req) { struct dsi_pll_28nm *pll_28nm = to_pll_28nm(hw); - if (rate < pll_28nm->phy->cfg->min_pll_rate) - return pll_28nm->phy->cfg->min_pll_rate; - else if (rate > pll_28nm->phy->cfg->max_pll_rate) - return pll_28nm->phy->cfg->max_pll_rate; - else - return rate; + req->rate = clamp_t(unsigned long, req->rate, + pll_28nm->phy->cfg->min_pll_rate, + pll_28nm->phy->cfg->max_pll_rate); + + return 0; } static const struct clk_ops clk_ops_dsi_pll_28nm_vco_hpm = { - .round_rate = dsi_pll_28nm_clk_round_rate, + .determine_rate = dsi_pll_28nm_clk_determine_rate, .set_rate = dsi_pll_28nm_clk_set_rate, .recalc_rate = dsi_pll_28nm_clk_recalc_rate, .prepare = dsi_pll_28nm_vco_prepare_hpm, @@ -556,7 +555,7 @@ static const struct clk_ops clk_ops_dsi_pll_28nm_vco_hpm = { }; static const struct clk_ops clk_ops_dsi_pll_28nm_vco_lp = { - .round_rate = dsi_pll_28nm_clk_round_rate, + .determine_rate = dsi_pll_28nm_clk_determine_rate, .set_rate = dsi_pll_28nm_clk_set_rate, .recalc_rate = dsi_pll_28nm_clk_recalc_rate, .prepare = dsi_pll_28nm_vco_prepare_lp, @@ -565,7 +564,7 @@ static const struct clk_ops clk_ops_dsi_pll_28nm_vco_lp = { }; static const struct clk_ops clk_ops_dsi_pll_28nm_vco_8226 = { - .round_rate = dsi_pll_28nm_clk_round_rate, + .determine_rate = dsi_pll_28nm_clk_determine_rate, .set_rate = dsi_pll_28nm_clk_set_rate, .recalc_rate = dsi_pll_28nm_clk_recalc_rate, .prepare = dsi_pll_28nm_vco_prepare_8226, diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c index f3643320ff2f..8dcce9581dc3 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c @@ -231,21 +231,19 @@ static void dsi_pll_28nm_vco_unprepare(struct clk_hw *hw) pll_28nm->phy->pll_on = false; } -static long dsi_pll_28nm_clk_round_rate(struct clk_hw *hw, - unsigned long rate, unsigned long *parent_rate) +static int dsi_pll_28nm_clk_determine_rate(struct clk_hw *hw, + struct clk_rate_request *req) { struct dsi_pll_28nm *pll_28nm = to_pll_28nm(hw); - if (rate < pll_28nm->phy->cfg->min_pll_rate) - return pll_28nm->phy->cfg->min_pll_rate; - else if (rate > pll_28nm->phy->cfg->max_pll_rate) - return pll_28nm->phy->cfg->max_pll_rate; - else - return rate; + req->rate = clamp_t(unsigned long, req->rate, + pll_28nm->phy->cfg->min_pll_rate, pll_28nm->phy->cfg->max_pll_rate); + + return 0; } static const struct clk_ops clk_ops_dsi_pll_28nm_vco = { - .round_rate = dsi_pll_28nm_clk_round_rate, + .determine_rate = dsi_pll_28nm_clk_determine_rate, .set_rate = dsi_pll_28nm_clk_set_rate, .recalc_rate = dsi_pll_28nm_clk_recalc_rate, .prepare = dsi_pll_28nm_vco_prepare, @@ -296,18 +294,20 @@ static unsigned int get_vco_mul_factor(unsigned long byte_clk_rate) return 8; } -static long clk_bytediv_round_rate(struct clk_hw *hw, unsigned long rate, - unsigned long *prate) +static int clk_bytediv_determine_rate(struct clk_hw *hw, + struct clk_rate_request *req) { unsigned long best_parent; unsigned int factor; - factor = get_vco_mul_factor(rate); + factor = get_vco_mul_factor(req->rate); + + best_parent = req->rate * factor; + req->best_parent_rate = clk_hw_round_rate(clk_hw_get_parent(hw), best_parent); - best_parent = rate * factor; - *prate = clk_hw_round_rate(clk_hw_get_parent(hw), best_parent); + req->rate = req->best_parent_rate / factor; - return *prate / factor; + return 0; } static int clk_bytediv_set_rate(struct clk_hw *hw, unsigned long rate, @@ -328,7 +328,7 @@ static int clk_bytediv_set_rate(struct clk_hw *hw, unsigned long rate, /* Our special byte clock divider ops */ static const struct clk_ops clk_bytediv_ops = { - .round_rate = clk_bytediv_round_rate, + .determine_rate = clk_bytediv_determine_rate, .set_rate = clk_bytediv_set_rate, .recalc_rate = clk_bytediv_recalc_rate, }; diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c index 8c98f91a5930..32f06edd21a9 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c @@ -90,6 +90,13 @@ struct dsi_pll_7nm { /* protects REG_DSI_7nm_PHY_CMN_CLK_CFG1 register */ spinlock_t pclk_mux_lock; + /* + * protects REG_DSI_7nm_PHY_CMN_CTRL_0 register and pll_enable_cnt + * member + */ + spinlock_t pll_enable_lock; + int pll_enable_cnt; + struct pll_7nm_cached_state cached_state; struct dsi_pll_7nm *slave; @@ -103,6 +110,9 @@ struct dsi_pll_7nm { */ static struct dsi_pll_7nm *pll_7nm_list[DSI_MAX]; +static void dsi_pll_enable_pll_bias(struct dsi_pll_7nm *pll); +static void dsi_pll_disable_pll_bias(struct dsi_pll_7nm *pll); + static void dsi_pll_setup_config(struct dsi_pll_config *config) { config->ssc_freq = 31500; @@ -340,6 +350,7 @@ static int dsi_pll_7nm_vco_set_rate(struct clk_hw *hw, unsigned long rate, struct dsi_pll_7nm *pll_7nm = to_pll_7nm(hw); struct dsi_pll_config config; + dsi_pll_enable_pll_bias(pll_7nm); DBG("DSI PLL%d rate=%lu, parent's=%lu", pll_7nm->phy->id, rate, parent_rate); @@ -357,6 +368,7 @@ static int dsi_pll_7nm_vco_set_rate(struct clk_hw *hw, unsigned long rate, dsi_pll_ssc_commit(pll_7nm, &config); + dsi_pll_disable_pll_bias(pll_7nm); /* flush, ensure all register writes are done*/ wmb(); @@ -385,19 +397,47 @@ static int dsi_pll_7nm_lock_status(struct dsi_pll_7nm *pll) static void dsi_pll_disable_pll_bias(struct dsi_pll_7nm *pll) { - u32 data = readl(pll->phy->base + REG_DSI_7nm_PHY_CMN_CTRL_0); + unsigned long flags; + u32 data; + spin_lock_irqsave(&pll->pll_enable_lock, flags); + --pll->pll_enable_cnt; + if (pll->pll_enable_cnt < 0) { + spin_unlock_irqrestore(&pll->pll_enable_lock, flags); + DRM_DEV_ERROR_RATELIMITED(&pll->phy->pdev->dev, + "bug: imbalance in disabling PLL bias\n"); + return; + } else if (pll->pll_enable_cnt > 0) { + spin_unlock_irqrestore(&pll->pll_enable_lock, flags); + return; + } /* else: == 0 */ + + data = readl(pll->phy->base + REG_DSI_7nm_PHY_CMN_CTRL_0); + data &= ~DSI_7nm_PHY_CMN_CTRL_0_PLL_SHUTDOWNB; writel(0, pll->phy->pll_base + REG_DSI_7nm_PHY_PLL_SYSTEM_MUXES); - writel(data & ~BIT(5), pll->phy->base + REG_DSI_7nm_PHY_CMN_CTRL_0); + writel(data, pll->phy->base + REG_DSI_7nm_PHY_CMN_CTRL_0); + spin_unlock_irqrestore(&pll->pll_enable_lock, flags); ndelay(250); } static void dsi_pll_enable_pll_bias(struct dsi_pll_7nm *pll) { - u32 data = readl(pll->phy->base + REG_DSI_7nm_PHY_CMN_CTRL_0); + unsigned long flags; + u32 data; + + spin_lock_irqsave(&pll->pll_enable_lock, flags); + if (pll->pll_enable_cnt++) { + spin_unlock_irqrestore(&pll->pll_enable_lock, flags); + WARN_ON(pll->pll_enable_cnt == INT_MAX); + return; + } + + data = readl(pll->phy->base + REG_DSI_7nm_PHY_CMN_CTRL_0); + data |= DSI_7nm_PHY_CMN_CTRL_0_PLL_SHUTDOWNB; + writel(data, pll->phy->base + REG_DSI_7nm_PHY_CMN_CTRL_0); - writel(data | BIT(5), pll->phy->base + REG_DSI_7nm_PHY_CMN_CTRL_0); writel(0xc0, pll->phy->pll_base + REG_DSI_7nm_PHY_PLL_SYSTEM_MUXES); + spin_unlock_irqrestore(&pll->pll_enable_lock, flags); ndelay(250); } @@ -491,6 +531,10 @@ static int dsi_pll_7nm_vco_prepare(struct clk_hw *hw) if (pll_7nm->slave) dsi_pll_enable_global_clk(pll_7nm->slave); + writel(0x1, pll_7nm->phy->base + REG_DSI_7nm_PHY_CMN_RBUF_CTRL); + if (pll_7nm->slave) + writel(0x1, pll_7nm->slave->phy->base + REG_DSI_7nm_PHY_CMN_RBUF_CTRL); + error: return rc; } @@ -534,6 +578,7 @@ static unsigned long dsi_pll_7nm_vco_recalc_rate(struct clk_hw *hw, u32 dec; u64 pll_freq, tmp64; + dsi_pll_enable_pll_bias(pll_7nm); dec = readl(base + REG_DSI_7nm_PHY_PLL_DECIMAL_DIV_START_1); dec &= 0xff; @@ -558,24 +603,24 @@ static unsigned long dsi_pll_7nm_vco_recalc_rate(struct clk_hw *hw, DBG("DSI PLL%d returning vco rate = %lu, dec = %x, frac = %x", pll_7nm->phy->id, (unsigned long)vco_rate, dec, frac); + dsi_pll_disable_pll_bias(pll_7nm); + return (unsigned long)vco_rate; } -static long dsi_pll_7nm_clk_round_rate(struct clk_hw *hw, - unsigned long rate, unsigned long *parent_rate) +static int dsi_pll_7nm_clk_determine_rate(struct clk_hw *hw, + struct clk_rate_request *req) { struct dsi_pll_7nm *pll_7nm = to_pll_7nm(hw); - if (rate < pll_7nm->phy->cfg->min_pll_rate) - return pll_7nm->phy->cfg->min_pll_rate; - else if (rate > pll_7nm->phy->cfg->max_pll_rate) - return pll_7nm->phy->cfg->max_pll_rate; - else - return rate; + req->rate = clamp_t(unsigned long, req->rate, + pll_7nm->phy->cfg->min_pll_rate, pll_7nm->phy->cfg->max_pll_rate); + + return 0; } static const struct clk_ops clk_ops_dsi_pll_7nm_vco = { - .round_rate = dsi_pll_7nm_clk_round_rate, + .determine_rate = dsi_pll_7nm_clk_determine_rate, .set_rate = dsi_pll_7nm_vco_set_rate, .recalc_rate = dsi_pll_7nm_vco_recalc_rate, .prepare = dsi_pll_7nm_vco_prepare, @@ -593,6 +638,7 @@ static void dsi_7nm_pll_save_state(struct msm_dsi_phy *phy) void __iomem *phy_base = pll_7nm->phy->base; u32 cmn_clk_cfg0, cmn_clk_cfg1; + dsi_pll_enable_pll_bias(pll_7nm); cached->pll_out_div = readl(pll_7nm->phy->pll_base + REG_DSI_7nm_PHY_PLL_PLL_OUTDIV_RATE); cached->pll_out_div &= 0x3; @@ -604,6 +650,7 @@ static void dsi_7nm_pll_save_state(struct msm_dsi_phy *phy) cmn_clk_cfg1 = readl(phy_base + REG_DSI_7nm_PHY_CMN_CLK_CFG1); cached->pll_mux = FIELD_GET(DSI_7nm_PHY_CMN_CLK_CFG1_DSICLK_SEL__MASK, cmn_clk_cfg1); + dsi_pll_disable_pll_bias(pll_7nm); DBG("DSI PLL%d outdiv %x bit_clk_div %x pix_clk_div %x pll_mux %x", pll_7nm->phy->id, cached->pll_out_div, cached->bit_clk_div, cached->pix_clk_div, cached->pll_mux); @@ -826,8 +873,10 @@ static int dsi_pll_7nm_init(struct msm_dsi_phy *phy) spin_lock_init(&pll_7nm->postdiv_lock); spin_lock_init(&pll_7nm->pclk_mux_lock); + spin_lock_init(&pll_7nm->pll_enable_lock); pll_7nm->phy = phy; + phy->pll_data = pll_7nm; ret = pll_7nm_register(pll_7nm, phy->provided_clocks->hws); if (ret) { @@ -839,6 +888,12 @@ static int dsi_pll_7nm_init(struct msm_dsi_phy *phy) /* TODO: Remove this when we have proper display handover support */ msm_dsi_phy_pll_save_state(phy); + /* + * Store also proper vco_current_rate, because its value will be used in + * dsi_7nm_pll_restore_state(). + */ + if (!dsi_pll_7nm_vco_recalc_rate(&pll_7nm->clk_hw, VCO_REF_CLK_RATE)) + pll_7nm->vco_current_rate = pll_7nm->phy->cfg->min_pll_rate; return 0; } @@ -910,8 +965,10 @@ static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy, u32 const delay_us = 5; u32 const timeout_us = 1000; struct msm_dsi_dphy_timing *timing = &phy->timing; + struct dsi_pll_7nm *pll = phy->pll_data; void __iomem *base = phy->base; bool less_than_1500_mhz; + unsigned long flags; u32 vreg_ctrl_0, vreg_ctrl_1, lane_ctrl0; u32 glbl_pemph_ctrl_0; u32 glbl_str_swi_cal_sel_ctrl, glbl_hstx_str_ctrl_0; @@ -1033,9 +1090,13 @@ static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy, glbl_rescode_bot_ctrl = 0x3c; } + spin_lock_irqsave(&pll->pll_enable_lock, flags); + pll->pll_enable_cnt = 1; /* de-assert digital and pll power down */ - data = BIT(6) | BIT(5); + data = DSI_7nm_PHY_CMN_CTRL_0_DIGTOP_PWRDN_B | + DSI_7nm_PHY_CMN_CTRL_0_PLL_SHUTDOWNB; writel(data, base + REG_DSI_7nm_PHY_CMN_CTRL_0); + spin_unlock_irqrestore(&pll->pll_enable_lock, flags); /* Assert PLL core reset */ writel(0x00, base + REG_DSI_7nm_PHY_CMN_PLL_CNTRL); @@ -1148,7 +1209,9 @@ static bool dsi_7nm_set_continuous_clock(struct msm_dsi_phy *phy, bool enable) static void dsi_7nm_phy_disable(struct msm_dsi_phy *phy) { + struct dsi_pll_7nm *pll = phy->pll_data; void __iomem *base = phy->base; + unsigned long flags; u32 data; DBG(""); @@ -1175,8 +1238,12 @@ static void dsi_7nm_phy_disable(struct msm_dsi_phy *phy) writel(data, base + REG_DSI_7nm_PHY_CMN_CTRL_0); writel(0, base + REG_DSI_7nm_PHY_CMN_LANE_CTRL0); + spin_lock_irqsave(&pll->pll_enable_lock, flags); + pll->pll_enable_cnt = 0; /* Turn off all PHY blocks */ writel(0x00, base + REG_DSI_7nm_PHY_CMN_CTRL_0); + spin_unlock_irqrestore(&pll->pll_enable_lock, flags); + /* make sure phy is turned off */ wmb(); diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_phy_8996.c b/drivers/gpu/drm/msm/hdmi/hdmi_phy_8996.c index 8c8d80b59573..36e928b0fd5a 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi_phy_8996.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi_phy_8996.c @@ -629,16 +629,12 @@ static int hdmi_8996_pll_prepare(struct clk_hw *hw) return 0; } -static long hdmi_8996_pll_round_rate(struct clk_hw *hw, - unsigned long rate, - unsigned long *parent_rate) +static int hdmi_8996_pll_determine_rate(struct clk_hw *hw, + struct clk_rate_request *req) { - if (rate < HDMI_PCLK_MIN_FREQ) - return HDMI_PCLK_MIN_FREQ; - else if (rate > HDMI_PCLK_MAX_FREQ) - return HDMI_PCLK_MAX_FREQ; - else - return rate; + req->rate = clamp_t(unsigned long, req->rate, HDMI_PCLK_MIN_FREQ, HDMI_PCLK_MAX_FREQ); + + return 0; } static unsigned long hdmi_8996_pll_recalc_rate(struct clk_hw *hw, @@ -684,7 +680,7 @@ static int hdmi_8996_pll_is_enabled(struct clk_hw *hw) static const struct clk_ops hdmi_8996_pll_ops = { .set_rate = hdmi_8996_pll_set_clk_rate, - .round_rate = hdmi_8996_pll_round_rate, + .determine_rate = hdmi_8996_pll_determine_rate, .recalc_rate = hdmi_8996_pll_recalc_rate, .prepare = hdmi_8996_pll_prepare, .unprepare = hdmi_8996_pll_unprepare, diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_phy_8998.c b/drivers/gpu/drm/msm/hdmi/hdmi_phy_8998.c index 33bb48ae58a2..a86ff3706369 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi_phy_8998.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi_phy_8998.c @@ -646,16 +646,12 @@ static int hdmi_8998_pll_prepare(struct clk_hw *hw) return 0; } -static long hdmi_8998_pll_round_rate(struct clk_hw *hw, - unsigned long rate, - unsigned long *parent_rate) +static int hdmi_8998_pll_determine_rate(struct clk_hw *hw, + struct clk_rate_request *req) { - if (rate < HDMI_PCLK_MIN_FREQ) - return HDMI_PCLK_MIN_FREQ; - else if (rate > HDMI_PCLK_MAX_FREQ) - return HDMI_PCLK_MAX_FREQ; - else - return rate; + req->rate = clamp_t(unsigned long, req->rate, HDMI_PCLK_MIN_FREQ, HDMI_PCLK_MAX_FREQ); + + return 0; } static unsigned long hdmi_8998_pll_recalc_rate(struct clk_hw *hw, @@ -688,7 +684,7 @@ static int hdmi_8998_pll_is_enabled(struct clk_hw *hw) static const struct clk_ops hdmi_8998_pll_ops = { .set_rate = hdmi_8998_pll_set_clk_rate, - .round_rate = hdmi_8998_pll_round_rate, + .determine_rate = hdmi_8998_pll_determine_rate, .recalc_rate = hdmi_8998_pll_recalc_rate, .prepare = hdmi_8998_pll_prepare, .unprepare = hdmi_8998_pll_unprepare, diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_pll_8960.c b/drivers/gpu/drm/msm/hdmi/hdmi_pll_8960.c index 83c8781fcc3f..6ba6bbdb7e05 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi_pll_8960.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi_pll_8960.c @@ -373,12 +373,14 @@ static unsigned long hdmi_pll_recalc_rate(struct clk_hw *hw, return pll->pixclk; } -static long hdmi_pll_round_rate(struct clk_hw *hw, unsigned long rate, - unsigned long *parent_rate) +static int hdmi_pll_determine_rate(struct clk_hw *hw, + struct clk_rate_request *req) { - const struct pll_rate *pll_rate = find_rate(rate); + const struct pll_rate *pll_rate = find_rate(req->rate); + + req->rate = pll_rate->rate; - return pll_rate->rate; + return 0; } static int hdmi_pll_set_rate(struct clk_hw *hw, unsigned long rate, @@ -402,7 +404,7 @@ static const struct clk_ops hdmi_pll_ops = { .enable = hdmi_pll_enable, .disable = hdmi_pll_disable, .recalc_rate = hdmi_pll_recalc_rate, - .round_rate = hdmi_pll_round_rate, + .determine_rate = hdmi_pll_determine_rate, .set_rate = hdmi_pll_set_rate, }; diff --git a/drivers/gpu/drm/msm/msm_debugfs.c b/drivers/gpu/drm/msm/msm_debugfs.c index bbda865addae..97dc70876442 100644 --- a/drivers/gpu/drm/msm/msm_debugfs.c +++ b/drivers/gpu/drm/msm/msm_debugfs.c @@ -325,25 +325,28 @@ static struct drm_info_list msm_debugfs_list[] = { static int late_init_minor(struct drm_minor *minor) { - struct drm_device *dev = minor->dev; - struct msm_drm_private *priv = dev->dev_private; + struct drm_device *dev; + struct msm_drm_private *priv; int ret; if (!minor) return 0; + dev = minor->dev; + priv = dev->dev_private; + if (!priv->gpu_pdev) return 0; ret = msm_rd_debugfs_init(minor); if (ret) { - DRM_DEV_ERROR(minor->dev->dev, "could not install rd debugfs\n"); + DRM_DEV_ERROR(dev->dev, "could not install rd debugfs\n"); return ret; } ret = msm_perf_debugfs_init(minor); if (ret) { - DRM_DEV_ERROR(minor->dev->dev, "could not install perf debugfs\n"); + DRM_DEV_ERROR(dev->dev, "could not install perf debugfs\n"); return ret; } diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index 9dcc7a596a11..7e977fec4100 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -826,6 +826,7 @@ static const struct file_operations fops = { #define DRIVER_FEATURES_KMS ( \ DRIVER_GEM | \ + DRIVER_GEM_GPUVA | \ DRIVER_ATOMIC | \ DRIVER_MODESET | \ 0 ) diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h index 985db9febd98..6d847d593f1a 100644 --- a/drivers/gpu/drm/msm/msm_drv.h +++ b/drivers/gpu/drm/msm/msm_drv.h @@ -229,7 +229,7 @@ void msm_crtc_disable_vblank(struct drm_crtc *crtc); int msm_register_mmu(struct drm_device *dev, struct msm_mmu *mmu); void msm_unregister_mmu(struct drm_device *dev, struct msm_mmu *mmu); -struct drm_gpuvm *msm_kms_init_vm(struct drm_device *dev); +struct drm_gpuvm *msm_kms_init_vm(struct drm_device *dev, struct device *mdss_dev); bool msm_use_mmu(struct drm_device *dev); int msm_ioctl_gem_submit(struct drm_device *dev, void *data, diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index 7ff994d4f91a..07d8cdd6bb2e 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -95,7 +95,6 @@ void msm_gem_vma_get(struct drm_gem_object *obj) void msm_gem_vma_put(struct drm_gem_object *obj) { struct msm_drm_private *priv = obj->dev->dev_private; - struct drm_exec exec; if (atomic_dec_return(&to_msm_bo(obj)->vma_ref)) return; @@ -103,9 +102,13 @@ void msm_gem_vma_put(struct drm_gem_object *obj) if (!priv->kms) return; +#ifdef CONFIG_DRM_MSM_KMS + struct drm_exec exec; + msm_gem_lock_vm_and_obj(&exec, obj, priv->kms->vm); put_iova_spaces(obj, priv->kms->vm, true, "vma_put"); drm_exec_fini(&exec); /* drop locks */ +#endif } /* @@ -188,7 +191,7 @@ static struct page **get_pages(struct drm_gem_object *obj) if (!msm_obj->pages) { struct drm_device *dev = obj->dev; struct page **p; - int npages = obj->size >> PAGE_SHIFT; + size_t npages = obj->size >> PAGE_SHIFT; p = drm_gem_get_pages(obj); @@ -663,9 +666,13 @@ int msm_gem_set_iova(struct drm_gem_object *obj, static bool is_kms_vm(struct drm_gpuvm *vm) { +#ifdef CONFIG_DRM_MSM_KMS struct msm_drm_private *priv = vm->drm->dev_private; return priv->kms && (priv->kms->vm == vm); +#else + return false; +#endif } /* @@ -1113,10 +1120,12 @@ static void msm_gem_free_object(struct drm_gem_object *obj) put_pages(obj); } - if (msm_obj->flags & MSM_BO_NO_SHARE) { + if (obj->resv != &obj->_resv) { struct drm_gem_object *r_obj = container_of(obj->resv, struct drm_gem_object, _resv); + WARN_ON(!(msm_obj->flags & MSM_BO_NO_SHARE)); + /* Drop reference we hold to shared resv obj: */ drm_gem_object_put(r_obj); } @@ -1139,7 +1148,7 @@ static int msm_gem_object_mmap(struct drm_gem_object *obj, struct vm_area_struct /* convenience method to construct a GEM buffer object, and userspace handle */ int msm_gem_new_handle(struct drm_device *dev, struct drm_file *file, - uint32_t size, uint32_t flags, uint32_t *handle, + size_t size, uint32_t flags, uint32_t *handle, char *name) { struct drm_gem_object *obj; @@ -1205,9 +1214,8 @@ static const struct drm_gem_object_funcs msm_gem_object_funcs = { .vm_ops = &vm_ops, }; -static int msm_gem_new_impl(struct drm_device *dev, - uint32_t size, uint32_t flags, - struct drm_gem_object **obj) +static int msm_gem_new_impl(struct drm_device *dev, uint32_t flags, + struct drm_gem_object **obj) { struct msm_drm_private *priv = dev->dev_private; struct msm_gem_object *msm_obj; @@ -1241,7 +1249,7 @@ static int msm_gem_new_impl(struct drm_device *dev, return 0; } -struct drm_gem_object *msm_gem_new(struct drm_device *dev, uint32_t size, uint32_t flags) +struct drm_gem_object *msm_gem_new(struct drm_device *dev, size_t size, uint32_t flags) { struct msm_drm_private *priv = dev->dev_private; struct msm_gem_object *msm_obj; @@ -1256,7 +1264,7 @@ struct drm_gem_object *msm_gem_new(struct drm_device *dev, uint32_t size, uint32 if (size == 0) return ERR_PTR(-EINVAL); - ret = msm_gem_new_impl(dev, size, flags, &obj); + ret = msm_gem_new_impl(dev, flags, &obj); if (ret) return ERR_PTR(ret); @@ -1296,12 +1304,12 @@ struct drm_gem_object *msm_gem_import(struct drm_device *dev, struct msm_drm_private *priv = dev->dev_private; struct msm_gem_object *msm_obj; struct drm_gem_object *obj; - uint32_t size; - int ret, npages; + size_t size, npages; + int ret; size = PAGE_ALIGN(dmabuf->size); - ret = msm_gem_new_impl(dev, size, MSM_BO_WC, &obj); + ret = msm_gem_new_impl(dev, MSM_BO_WC, &obj); if (ret) return ERR_PTR(ret); @@ -1344,7 +1352,7 @@ fail: return ERR_PTR(ret); } -void *msm_gem_kernel_new(struct drm_device *dev, uint32_t size, uint32_t flags, +void *msm_gem_kernel_new(struct drm_device *dev, size_t size, uint32_t flags, struct drm_gpuvm *vm, struct drm_gem_object **bo, uint64_t *iova) { diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h index 88239da1cd72..a4cf31853c50 100644 --- a/drivers/gpu/drm/msm/msm_gem.h +++ b/drivers/gpu/drm/msm/msm_gem.h @@ -100,7 +100,7 @@ struct msm_gem_vm { * * Only used for kernel managed VMs, unused for user managed VMs. * - * Protected by @mm_lock. + * Protected by vm lock. See msm_gem_lock_vm_and_obj(), for ex. */ struct drm_mm mm; @@ -297,10 +297,10 @@ bool msm_gem_active(struct drm_gem_object *obj); int msm_gem_cpu_prep(struct drm_gem_object *obj, uint32_t op, ktime_t *timeout); int msm_gem_cpu_fini(struct drm_gem_object *obj); int msm_gem_new_handle(struct drm_device *dev, struct drm_file *file, - uint32_t size, uint32_t flags, uint32_t *handle, char *name); + size_t size, uint32_t flags, uint32_t *handle, char *name); struct drm_gem_object *msm_gem_new(struct drm_device *dev, - uint32_t size, uint32_t flags); -void *msm_gem_kernel_new(struct drm_device *dev, uint32_t size, uint32_t flags, + size_t size, uint32_t flags); +void *msm_gem_kernel_new(struct drm_device *dev, size_t size, uint32_t flags, struct drm_gpuvm *vm, struct drm_gem_object **bo, uint64_t *iova); void msm_gem_kernel_put(struct drm_gem_object *bo, struct drm_gpuvm *vm); diff --git a/drivers/gpu/drm/msm/msm_gem_prime.c b/drivers/gpu/drm/msm/msm_gem_prime.c index c0a33ac839cb..036d34c674d9 100644 --- a/drivers/gpu/drm/msm/msm_gem_prime.c +++ b/drivers/gpu/drm/msm/msm_gem_prime.c @@ -15,7 +15,7 @@ struct sg_table *msm_gem_prime_get_sg_table(struct drm_gem_object *obj) { struct msm_gem_object *msm_obj = to_msm_bo(obj); - int npages = obj->size >> PAGE_SHIFT; + size_t npages = obj->size >> PAGE_SHIFT; if (msm_obj->flags & MSM_BO_NO_SHARE) return ERR_PTR(-EINVAL); diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index 5f8e939a5906..3ab3b27134f9 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -271,32 +271,37 @@ out: return ret; } -/* This is where we make sure all the bo's are reserved and pin'd: */ -static int submit_lock_objects(struct msm_gem_submit *submit) +static int submit_lock_objects_vmbind(struct msm_gem_submit *submit) { - unsigned flags = DRM_EXEC_INTERRUPTIBLE_WAIT; + unsigned flags = DRM_EXEC_INTERRUPTIBLE_WAIT | DRM_EXEC_IGNORE_DUPLICATES; struct drm_exec *exec = &submit->exec; - int ret; + int ret = 0; - if (msm_context_is_vmbind(submit->queue->ctx)) { - flags |= DRM_EXEC_IGNORE_DUPLICATES; + drm_exec_init(&submit->exec, flags, submit->nr_bos); - drm_exec_init(&submit->exec, flags, submit->nr_bos); + drm_exec_until_all_locked (&submit->exec) { + ret = drm_gpuvm_prepare_vm(submit->vm, exec, 1); + drm_exec_retry_on_contention(exec); + if (ret) + break; - drm_exec_until_all_locked (&submit->exec) { - ret = drm_gpuvm_prepare_vm(submit->vm, exec, 1); - drm_exec_retry_on_contention(exec); - if (ret) - return ret; + ret = drm_gpuvm_prepare_objects(submit->vm, exec, 1); + drm_exec_retry_on_contention(exec); + if (ret) + break; + } - ret = drm_gpuvm_prepare_objects(submit->vm, exec, 1); - drm_exec_retry_on_contention(exec); - if (ret) - return ret; - } + return ret; +} - return 0; - } +/* This is where we make sure all the bo's are reserved and pin'd: */ +static int submit_lock_objects(struct msm_gem_submit *submit) +{ + unsigned flags = DRM_EXEC_INTERRUPTIBLE_WAIT; + int ret = 0; + + if (msm_context_is_vmbind(submit->queue->ctx)) + return submit_lock_objects_vmbind(submit); drm_exec_init(&submit->exec, flags, submit->nr_bos); @@ -305,17 +310,17 @@ static int submit_lock_objects(struct msm_gem_submit *submit) drm_gpuvm_resv_obj(submit->vm)); drm_exec_retry_on_contention(&submit->exec); if (ret) - return ret; + break; for (unsigned i = 0; i < submit->nr_bos; i++) { struct drm_gem_object *obj = submit->bos[i].obj; ret = drm_exec_prepare_obj(&submit->exec, obj, 1); drm_exec_retry_on_contention(&submit->exec); if (ret) - return ret; + break; } } - return 0; + return ret; } static int submit_fence_sync(struct msm_gem_submit *submit) @@ -514,14 +519,15 @@ out: */ static void submit_cleanup(struct msm_gem_submit *submit, bool error) { + if (error) + submit_unpin_objects(submit); + if (submit->exec.objects) drm_exec_fini(&submit->exec); - if (error) { - submit_unpin_objects(submit); - /* job wasn't enqueued to scheduler, so early retirement: */ + /* if job wasn't enqueued to scheduler, early retirement: */ + if (error) msm_submit_retire(submit); - } } void msm_submit_retire(struct msm_gem_submit *submit) @@ -769,12 +775,8 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, if (ret == 0 && args->flags & MSM_SUBMIT_FENCE_FD_OUT) { sync_file = sync_file_create(submit->user_fence); - if (!sync_file) { + if (!sync_file) ret = -ENOMEM; - } else { - fd_install(out_fence_fd, sync_file->file); - args->fence_fd = out_fence_fd; - } } if (ret) @@ -812,10 +814,14 @@ out: out_unlock: mutex_unlock(&queue->lock); out_post_unlock: - if (ret && (out_fence_fd >= 0)) { - put_unused_fd(out_fence_fd); + if (ret) { + if (out_fence_fd >= 0) + put_unused_fd(out_fence_fd); if (sync_file) fput(sync_file->file); + } else if (sync_file) { + fd_install(out_fence_fd, sync_file->file); + args->fence_fd = out_fence_fd; } if (!IS_ERR_OR_NULL(submit)) { diff --git a/drivers/gpu/drm/msm/msm_gem_vma.c b/drivers/gpu/drm/msm/msm_gem_vma.c index c632db9005e2..8316af1723c2 100644 --- a/drivers/gpu/drm/msm/msm_gem_vma.c +++ b/drivers/gpu/drm/msm/msm_gem_vma.c @@ -319,13 +319,10 @@ msm_gem_vma_map(struct drm_gpuva *vma, int prot, struct sg_table *sgt) mutex_lock(&vm->mmu_lock); /* - * NOTE: iommu/io-pgtable can allocate pages, so we cannot hold + * NOTE: if not using pgtable preallocation, we cannot hold * a lock across map/unmap which is also used in the job_run() * path, as this can cause deadlock in job_run() vs shrinker/ * reclaim. - * - * Revisit this if we can come up with a scheme to pre-alloc pages - * for the pgtable in map/unmap ops. */ ret = vm_map_op(vm, &(struct msm_vm_map_op){ .iova = vma->va.addr, @@ -461,6 +458,8 @@ msm_gem_vm_bo_validate(struct drm_gpuvm_bo *vm_bo, struct drm_exec *exec) struct op_arg { unsigned flags; struct msm_vm_bind_job *job; + const struct msm_vm_bind_op *op; + bool kept; }; static void @@ -482,14 +481,18 @@ vma_from_op(struct op_arg *arg, struct drm_gpuva_op_map *op) } static int -msm_gem_vm_sm_step_map(struct drm_gpuva_op *op, void *arg) +msm_gem_vm_sm_step_map(struct drm_gpuva_op *op, void *_arg) { - struct msm_vm_bind_job *job = ((struct op_arg *)arg)->job; + struct op_arg *arg = _arg; + struct msm_vm_bind_job *job = arg->job; struct drm_gem_object *obj = op->map.gem.obj; struct drm_gpuva *vma; struct sg_table *sgt; unsigned prot; + if (arg->kept) + return 0; + vma = vma_from_op(arg, &op->map); if (WARN_ON(IS_ERR(vma))) return PTR_ERR(vma); @@ -609,15 +612,41 @@ msm_gem_vm_sm_step_remap(struct drm_gpuva_op *op, void *arg) } static int -msm_gem_vm_sm_step_unmap(struct drm_gpuva_op *op, void *arg) +msm_gem_vm_sm_step_unmap(struct drm_gpuva_op *op, void *_arg) { - struct msm_vm_bind_job *job = ((struct op_arg *)arg)->job; + struct op_arg *arg = _arg; + struct msm_vm_bind_job *job = arg->job; struct drm_gpuva *vma = op->unmap.va; struct msm_gem_vma *msm_vma = to_msm_vma(vma); vm_dbg("%p:%p:%p: %016llx %016llx", vma->vm, vma, vma->gem.obj, vma->va.addr, vma->va.range); + /* + * Detect in-place remap. Turnip does this to change the vma flags, + * in particular MSM_VMA_DUMP. In this case we want to avoid actually + * touching the page tables, as that would require synchronization + * against SUBMIT jobs running on the GPU. + */ + if (op->unmap.keep && + (arg->op->op == MSM_VM_BIND_OP_MAP) && + (vma->gem.obj == arg->op->obj) && + (vma->gem.offset == arg->op->obj_offset) && + (vma->va.addr == arg->op->iova) && + (vma->va.range == arg->op->range)) { + /* We are only expecting a single in-place unmap+map cb pair: */ + WARN_ON(arg->kept); + + /* Leave the existing VMA in place, but signal that to the map cb: */ + arg->kept = true; + + /* Only flags are changing, so update that in-place: */ + unsigned orig_flags = vma->flags & (DRM_GPUVA_USERBITS - 1); + vma->flags = orig_flags | arg->flags; + + return 0; + } + if (!msm_vma->mapped) goto out_close; @@ -1001,6 +1030,7 @@ vm_bind_job_lookup_ops(struct msm_vm_bind_job *job, struct drm_msm_vm_bind *args struct drm_device *dev = job->vm->drm; int ret = 0; int cnt = 0; + int i = -1; if (args->nr_ops == 1) { /* Single op case, the op is inlined: */ @@ -1034,11 +1064,12 @@ vm_bind_job_lookup_ops(struct msm_vm_bind_job *job, struct drm_msm_vm_bind *args spin_lock(&file->table_lock); - for (unsigned i = 0; i < args->nr_ops; i++) { + for (i = 0; i < args->nr_ops; i++) { + struct msm_vm_bind_op *op = &job->ops[i]; struct drm_gem_object *obj; - if (!job->ops[i].handle) { - job->ops[i].obj = NULL; + if (!op->handle) { + op->obj = NULL; continue; } @@ -1046,16 +1077,22 @@ vm_bind_job_lookup_ops(struct msm_vm_bind_job *job, struct drm_msm_vm_bind *args * normally use drm_gem_object_lookup(), but for bulk lookup * all under single table_lock just hit object_idr directly: */ - obj = idr_find(&file->object_idr, job->ops[i].handle); + obj = idr_find(&file->object_idr, op->handle); if (!obj) { - ret = UERR(EINVAL, dev, "invalid handle %u at index %u\n", job->ops[i].handle, i); + ret = UERR(EINVAL, dev, "invalid handle %u at index %u\n", op->handle, i); goto out_unlock; } drm_gem_object_get(obj); - job->ops[i].obj = obj; + op->obj = obj; cnt++; + + if ((op->range + op->obj_offset) > obj->size) { + ret = UERR(EINVAL, dev, "invalid range: %016llx + %016llx > %016zx\n", + op->range, op->obj_offset, obj->size); + goto out_unlock; + } } *nr_bos = cnt; @@ -1063,6 +1100,17 @@ vm_bind_job_lookup_ops(struct msm_vm_bind_job *job, struct drm_msm_vm_bind *args out_unlock: spin_unlock(&file->table_lock); + if (ret) { + for (; i >= 0; i--) { + struct msm_vm_bind_op *op = &job->ops[i]; + + if (!op->obj) + continue; + + drm_gem_object_put(op->obj); + op->obj = NULL; + } + } out: return ret; } @@ -1284,6 +1332,7 @@ vm_bind_job_prepare(struct msm_vm_bind_job *job) const struct msm_vm_bind_op *op = &job->ops[i]; struct op_arg arg = { .job = job, + .op = op, }; switch (op->op) { @@ -1480,12 +1529,8 @@ msm_ioctl_vm_bind(struct drm_device *dev, void *data, struct drm_file *file) if (args->flags & MSM_VM_BIND_FENCE_FD_OUT) { sync_file = sync_file_create(job->fence); - if (!sync_file) { + if (!sync_file) ret = -ENOMEM; - } else { - fd_install(out_fence_fd, sync_file->file); - args->fence_fd = out_fence_fd; - } } if (ret) @@ -1514,10 +1559,14 @@ out: out_unlock: mutex_unlock(&queue->lock); out_post_unlock: - if (ret && (out_fence_fd >= 0)) { - put_unused_fd(out_fence_fd); + if (ret) { + if (out_fence_fd >= 0) + put_unused_fd(out_fence_fd); if (sync_file) fput(sync_file->file); + } else if (sync_file) { + fd_install(out_fence_fd, sync_file->file); + args->fence_fd = out_fence_fd; } if (!IS_ERR_OR_NULL(job)) { diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c index c317b25a8162..17759abc46d7 100644 --- a/drivers/gpu/drm/msm/msm_gpu.c +++ b/drivers/gpu/drm/msm/msm_gpu.c @@ -304,7 +304,7 @@ static void crashstate_get_bos(struct msm_gpu_state *state, struct msm_gem_submi sizeof(struct msm_gpu_state_bo), GFP_KERNEL); for (int i = 0; state->bos && i < submit->nr_bos; i++) { - struct drm_gem_object *obj = submit->bos[i].obj;; + struct drm_gem_object *obj = submit->bos[i].obj; bool dump = rd_full || (submit->bos[i].flags & MSM_SUBMIT_BO_DUMP); msm_gem_lock(obj); @@ -465,6 +465,7 @@ static void recover_worker(struct kthread_work *work) struct msm_gem_submit *submit; struct msm_ringbuffer *cur_ring = gpu->funcs->active_ring(gpu); char *comm = NULL, *cmd = NULL; + struct task_struct *task; int i; mutex_lock(&gpu->lock); @@ -482,16 +483,20 @@ static void recover_worker(struct kthread_work *work) /* Increment the fault counts */ submit->queue->faults++; - if (submit->vm) { + + task = get_pid_task(submit->pid, PIDTYPE_PID); + if (!task) + gpu->global_faults++; + else { struct msm_gem_vm *vm = to_msm_vm(submit->vm); vm->faults++; /* * If userspace has opted-in to VM_BIND (and therefore userspace - * management of the VM), faults mark the VM as unusuable. This + * management of the VM), faults mark the VM as unusable. This * matches vulkan expectations (vulkan is the main target for - * VM_BIND) + * VM_BIND). */ if (!vm->managed) msm_gem_vm_unusable(submit->vm); @@ -553,8 +558,15 @@ static void recover_worker(struct kthread_work *work) unsigned long flags; spin_lock_irqsave(&ring->submit_lock, flags); - list_for_each_entry(submit, &ring->submits, node) + list_for_each_entry(submit, &ring->submits, node) { + /* + * If the submit uses an unusable vm make sure + * we don't actually run it + */ + if (to_msm_vm(submit->vm)->unusable) + submit->nr_cmds = 0; gpu->funcs->submit(gpu, submit); + } spin_unlock_irqrestore(&ring->submit_lock, flags); } } diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h index b2a96544f92a..a597f2bee30b 100644 --- a/drivers/gpu/drm/msm/msm_gpu.h +++ b/drivers/gpu/drm/msm/msm_gpu.h @@ -16,6 +16,7 @@ #include "msm_drv.h" #include "msm_fence.h" +#include "msm_gpu_trace.h" #include "msm_ringbuffer.h" #include "msm_gem.h" @@ -91,6 +92,7 @@ struct msm_gpu_funcs { * for cmdstream that is buffered in this FIFO upstream of the CP fw. */ bool (*progress)(struct msm_gpu *gpu, struct msm_ringbuffer *ring); + void (*sysprof_setup)(struct msm_gpu *gpu); }; /* Additional state for iommu faults: */ @@ -613,16 +615,19 @@ struct msm_gpu_state { static inline void gpu_write(struct msm_gpu *gpu, u32 reg, u32 data) { + trace_msm_gpu_regaccess(reg); writel(data, gpu->mmio + (reg << 2)); } static inline u32 gpu_read(struct msm_gpu *gpu, u32 reg) { + trace_msm_gpu_regaccess(reg); return readl(gpu->mmio + (reg << 2)); } static inline void gpu_rmw(struct msm_gpu *gpu, u32 reg, u32 mask, u32 or) { + trace_msm_gpu_regaccess(reg); msm_rmw(gpu->mmio + (reg << 2), mask, or); } @@ -644,7 +649,9 @@ static inline u64 gpu_read64(struct msm_gpu *gpu, u32 reg) * when the lo is read, so make sure to read the lo first to trigger * that */ + trace_msm_gpu_regaccess(reg); val = (u64) readl(gpu->mmio + (reg << 2)); + trace_msm_gpu_regaccess(reg+1); val |= ((u64) readl(gpu->mmio + ((reg + 1) << 2)) << 32); return val; @@ -652,8 +659,10 @@ static inline u64 gpu_read64(struct msm_gpu *gpu, u32 reg) static inline void gpu_write64(struct msm_gpu *gpu, u32 reg, u64 val) { + trace_msm_gpu_regaccess(reg); /* Why not a writeq here? Read the screed above */ writel(lower_32_bits(val), gpu->mmio + (reg << 2)); + trace_msm_gpu_regaccess(reg+1); writel(upper_32_bits(val), gpu->mmio + ((reg + 1) << 2)); } diff --git a/drivers/gpu/drm/msm/msm_gpu_trace.h b/drivers/gpu/drm/msm/msm_gpu_trace.h index 781bbe5540bd..5417f8d389a3 100644 --- a/drivers/gpu/drm/msm/msm_gpu_trace.h +++ b/drivers/gpu/drm/msm/msm_gpu_trace.h @@ -219,6 +219,18 @@ TRACE_EVENT(msm_mmu_prealloc_cleanup, TP_printk("count=%u, remaining=%u", __entry->count, __entry->remaining) ); +TRACE_EVENT(msm_gpu_regaccess, + TP_PROTO(u32 offset), + TP_ARGS(offset), + TP_STRUCT__entry( + __field(u32, offset) + ), + TP_fast_assign( + __entry->offset = offset; + ), + TP_printk("offset=0x%x", __entry->offset) +); + #endif #undef TRACE_INCLUDE_PATH diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c index 55c29f49b788..0e18619f96cb 100644 --- a/drivers/gpu/drm/msm/msm_iommu.c +++ b/drivers/gpu/drm/msm/msm_iommu.c @@ -14,7 +14,9 @@ struct msm_iommu { struct msm_mmu base; struct iommu_domain *domain; - atomic_t pagetables; + + struct mutex init_lock; /* protects pagetables counter and prr_page */ + int pagetables; struct page *prr_page; struct kmem_cache *pt_cache; @@ -227,7 +229,8 @@ static void msm_iommu_pagetable_destroy(struct msm_mmu *mmu) * If this is the last attached pagetable for the parent, * disable TTBR0 in the arm-smmu driver */ - if (atomic_dec_return(&iommu->pagetables) == 0) { + mutex_lock(&iommu->init_lock); + if (--iommu->pagetables == 0) { adreno_smmu->set_ttbr0_cfg(adreno_smmu->cookie, NULL); if (adreno_smmu->set_prr_bit) { @@ -236,6 +239,7 @@ static void msm_iommu_pagetable_destroy(struct msm_mmu *mmu) iommu->prr_page = NULL; } } + mutex_unlock(&iommu->init_lock); free_io_pgtable_ops(pagetable->pgtbl_ops); kfree(pagetable); @@ -568,9 +572,12 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent, bool kernel_m * If this is the first pagetable that we've allocated, send it back to * the arm-smmu driver as a trigger to set up TTBR0 */ - if (atomic_inc_return(&iommu->pagetables) == 1) { + mutex_lock(&iommu->init_lock); + if (iommu->pagetables++ == 0) { ret = adreno_smmu->set_ttbr0_cfg(adreno_smmu->cookie, &ttbr0_cfg); if (ret) { + iommu->pagetables--; + mutex_unlock(&iommu->init_lock); free_io_pgtable_ops(pagetable->pgtbl_ops); kfree(pagetable); return ERR_PTR(ret); @@ -595,6 +602,7 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent, bool kernel_m adreno_smmu->set_prr_bit(adreno_smmu->cookie, true); } } + mutex_unlock(&iommu->init_lock); /* Needed later for TLB flush */ pagetable->parent = parent; @@ -713,7 +721,7 @@ struct msm_mmu *msm_iommu_new(struct device *dev, unsigned long quirks) int ret; if (!device_iommu_mapped(dev)) - return NULL; + return ERR_PTR(-ENODEV); domain = iommu_paging_domain_alloc(dev); if (IS_ERR(domain)) @@ -730,7 +738,7 @@ struct msm_mmu *msm_iommu_new(struct device *dev, unsigned long quirks) iommu->domain = domain; msm_mmu_init(&iommu->base, dev, &funcs, MSM_MMU_IOMMU); - atomic_set(&iommu->pagetables, 0); + mutex_init(&iommu->init_lock); ret = iommu_attach_device(iommu->domain, dev); if (ret) { @@ -748,7 +756,7 @@ struct msm_mmu *msm_iommu_disp_new(struct device *dev, unsigned long quirks) struct msm_mmu *mmu; mmu = msm_iommu_new(dev, quirks); - if (IS_ERR_OR_NULL(mmu)) + if (IS_ERR(mmu)) return mmu; iommu = to_msm_iommu(mmu); @@ -764,11 +772,11 @@ struct msm_mmu *msm_iommu_gpu_new(struct device *dev, struct msm_gpu *gpu, unsig struct msm_mmu *mmu; mmu = msm_iommu_new(dev, quirks); - if (IS_ERR_OR_NULL(mmu)) + if (IS_ERR(mmu)) return mmu; iommu = to_msm_iommu(mmu); - if (adreno_smmu && adreno_smmu->cookie) { + if (adreno_smmu->cookie) { const struct io_pgtable_cfg *cfg = adreno_smmu->get_ttbr1_cfg(adreno_smmu->cookie); size_t tblsz = get_tblsz(cfg); diff --git a/drivers/gpu/drm/msm/msm_kms.c b/drivers/gpu/drm/msm/msm_kms.c index 6889f1c1e721..6e5e94f5c9a7 100644 --- a/drivers/gpu/drm/msm/msm_kms.c +++ b/drivers/gpu/drm/msm/msm_kms.c @@ -177,12 +177,11 @@ static int msm_kms_fault_handler(void *arg, unsigned long iova, int flags, void return -ENOSYS; } -struct drm_gpuvm *msm_kms_init_vm(struct drm_device *dev) +struct drm_gpuvm *msm_kms_init_vm(struct drm_device *dev, struct device *mdss_dev) { struct drm_gpuvm *vm; struct msm_mmu *mmu; struct device *mdp_dev = dev->dev; - struct device *mdss_dev = mdp_dev->parent; struct msm_drm_private *priv = dev->dev_private; struct msm_kms *kms = priv->kms; struct device *iommu_dev; @@ -193,18 +192,17 @@ struct drm_gpuvm *msm_kms_init_vm(struct drm_device *dev) */ if (device_iommu_mapped(mdp_dev)) iommu_dev = mdp_dev; - else + else if (mdss_dev && device_iommu_mapped(mdss_dev)) iommu_dev = mdss_dev; + else { + drm_info(dev, "no IOMMU, bailing out\n"); + return ERR_PTR(-ENODEV); + } mmu = msm_iommu_disp_new(iommu_dev, 0); if (IS_ERR(mmu)) return ERR_CAST(mmu); - if (!mmu) { - drm_info(dev, "no IOMMU, fallback to phys contig buffers for scanout\n"); - return NULL; - } - vm = msm_gem_vm_create(dev, mmu, "mdp_kms", 0x1000, 0x100000000 - 0x1000, true); if (IS_ERR(vm)) { @@ -275,6 +273,12 @@ int msm_drm_kms_init(struct device *dev, const struct drm_driver *drv) if (ret) return ret; + ret = msm_disp_snapshot_init(ddev); + if (ret) { + DRM_DEV_ERROR(dev, "msm_disp_snapshot_init failed ret = %d\n", ret); + return ret; + } + ret = priv->kms_init(ddev); if (ret) { DRM_DEV_ERROR(dev, "failed to load kms\n"); @@ -327,10 +331,6 @@ int msm_drm_kms_init(struct device *dev, const struct drm_driver *drv) goto err_msm_uninit; } - ret = msm_disp_snapshot_init(ddev); - if (ret) - DRM_DEV_ERROR(dev, "msm_disp_snapshot_init failed ret = %d\n", ret); - drm_mode_config_reset(ddev); return 0; diff --git a/drivers/gpu/drm/msm/msm_mdss.c b/drivers/gpu/drm/msm/msm_mdss.c index 1f5fe7811e01..2d0e3e784c04 100644 --- a/drivers/gpu/drm/msm/msm_mdss.c +++ b/drivers/gpu/drm/msm/msm_mdss.c @@ -154,8 +154,7 @@ static int _msm_mdss_irq_domain_add(struct msm_mdss *msm_mdss) dev = msm_mdss->dev; - domain = irq_domain_create_linear(of_fwnode_handle(dev->of_node), 32, - &msm_mdss_irqdomain_ops, msm_mdss); + domain = irq_domain_create_linear(dev_fwnode(dev), 32, &msm_mdss_irqdomain_ops, msm_mdss); if (!domain) { dev_err(dev, "failed to add irq_domain\n"); return -EINVAL; @@ -423,7 +422,7 @@ static struct msm_mdss *msm_mdss_init(struct platform_device *pdev, bool is_mdp5 if (IS_ERR(msm_mdss->mmio)) return ERR_CAST(msm_mdss->mmio); - dev_dbg(&pdev->dev, "mapped mdss address space @%pK\n", msm_mdss->mmio); + dev_dbg(&pdev->dev, "mapped mdss address space @%p\n", msm_mdss->mmio); ret = msm_mdss_parse_data_bus_icc_path(&pdev->dev, msm_mdss); if (ret) diff --git a/drivers/gpu/drm/msm/msm_submitqueue.c b/drivers/gpu/drm/msm/msm_submitqueue.c index 8617a82cd6b3..d53dfad16bde 100644 --- a/drivers/gpu/drm/msm/msm_submitqueue.c +++ b/drivers/gpu/drm/msm/msm_submitqueue.c @@ -40,6 +40,10 @@ int msm_context_set_sysprof(struct msm_context *ctx, struct msm_gpu *gpu, int sy break; } + /* Some gpu families require additional setup for sysprof */ + if (gpu->funcs->sysprof_setup) + gpu->funcs->sysprof_setup(gpu); + ctx->sysprof = sysprof; return 0; diff --git a/drivers/gpu/drm/msm/registers/adreno/a6xx.xml b/drivers/gpu/drm/msm/registers/adreno/a6xx.xml index d860fd94feae..9459b6038217 100644 --- a/drivers/gpu/drm/msm/registers/adreno/a6xx.xml +++ b/drivers/gpu/drm/msm/registers/adreno/a6xx.xml @@ -594,10 +594,14 @@ by a particular renderpass/blit. <reg32 offset="0x0600" name="DBGC_CFG_DBGBUS_SEL_A"/> <reg32 offset="0x0601" name="DBGC_CFG_DBGBUS_SEL_B"/> <reg32 offset="0x0602" name="DBGC_CFG_DBGBUS_SEL_C"/> - <reg32 offset="0x0603" name="DBGC_CFG_DBGBUS_SEL_D"> + <reg32 offset="0x0603" name="DBGC_CFG_DBGBUS_SEL_D" variants="A6XX"> <bitfield high="7" low="0" name="PING_INDEX"/> <bitfield high="15" low="8" name="PING_BLK_SEL"/> </reg32> + <reg32 offset="0x0603" name="DBGC_CFG_DBGBUS_SEL_D" variants="A7XX-"> + <bitfield high="7" low="0" name="PING_INDEX"/> + <bitfield high="24" low="16" name="PING_BLK_SEL"/> + </reg32> <reg32 offset="0x0604" name="DBGC_CFG_DBGBUS_CNTLT"> <bitfield high="5" low="0" name="TRACEEN"/> <bitfield high="14" low="12" name="GRANU"/> @@ -810,7 +814,7 @@ by a particular renderpass/blit. <bitfield name="Y" low="16" high="29" type="uint"/> </bitset> - <reg32 offset="0x8000" name="GRAS_CL_CNTL" usage="rp_blit"> + <bitset name="a6xx_gras_cl_cntl" inline="yes"> <bitfield name="CLIP_DISABLE" pos="0" type="boolean"/> <bitfield name="ZNEAR_CLIP_DISABLE" pos="1" type="boolean"/> <bitfield name="ZFAR_CLIP_DISABLE" pos="2" type="boolean"/> @@ -822,18 +826,20 @@ by a particular renderpass/blit. <bitfield name="VP_CLIP_CODE_IGNORE" pos="7" type="boolean"/> <bitfield name="VP_XFORM_DISABLE" pos="8" type="boolean"/> <bitfield name="PERSP_DIVISION_DISABLE" pos="9" type="boolean"/> - </reg32> + </bitset> + + <reg32 offset="0x8000" name="GRAS_CL_CNTL" type="a6xx_gras_cl_cntl" variants="A6XX-A7XX" usage="rp_blit"/> <bitset name="a6xx_gras_xs_clip_cull_distance" inline="yes"> <bitfield name="CLIP_MASK" low="0" high="7"/> <bitfield name="CULL_MASK" low="8" high="15"/> </bitset> - <reg32 offset="0x8001" name="GRAS_CL_VS_CLIP_CULL_DISTANCE" type="a6xx_gras_xs_clip_cull_distance" usage="rp_blit"/> - <reg32 offset="0x8002" name="GRAS_CL_DS_CLIP_CULL_DISTANCE" type="a6xx_gras_xs_clip_cull_distance" usage="rp_blit"/> - <reg32 offset="0x8003" name="GRAS_CL_GS_CLIP_CULL_DISTANCE" type="a6xx_gras_xs_clip_cull_distance" usage="rp_blit"/> - <reg32 offset="0x8004" name="GRAS_CL_ARRAY_SIZE" low="0" high="10" type="uint" usage="rp_blit"/> + <reg32 offset="0x8001" name="GRAS_CL_VS_CLIP_CULL_DISTANCE" type="a6xx_gras_xs_clip_cull_distance" usage="rp_blit" variants="A6XX-A7XX" /> + <reg32 offset="0x8002" name="GRAS_CL_DS_CLIP_CULL_DISTANCE" type="a6xx_gras_xs_clip_cull_distance" usage="rp_blit" variants="A6XX-A7XX" /> + <reg32 offset="0x8003" name="GRAS_CL_GS_CLIP_CULL_DISTANCE" type="a6xx_gras_xs_clip_cull_distance" usage="rp_blit" variants="A6XX-A7XX" /> + <reg32 offset="0x8004" name="GRAS_CL_ARRAY_SIZE" low="0" high="10" type="uint" usage="rp_blit" variants="A6XX-A7XX" /> - <reg32 offset="0x8005" name="GRAS_CL_INTERP_CNTL" usage="rp_blit"> + <bitset name="a6xx_gras_cl_interp_cntl" inline="yes"> <!-- see also RB_INTERP_CNTL --> <bitfield name="IJ_PERSP_PIXEL" pos="0" type="boolean"/> <bitfield name="IJ_PERSP_CENTROID" pos="1" type="boolean"/> @@ -844,26 +850,69 @@ by a particular renderpass/blit. <bitfield name="COORD_MASK" low="6" high="9" type="hex"/> <bitfield name="UNK10" pos="10" type="boolean" variants="A7XX-"/> <bitfield name="UNK11" pos="11" type="boolean" variants="A7XX-"/> - </reg32> - <reg32 offset="0x8006" name="GRAS_CL_GUARDBAND_CLIP_ADJ" usage="rp_blit"> + </bitset> + + <reg32 offset="0x8005" name="GRAS_CL_INTERP_CNTL" type="a6xx_gras_cl_interp_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + + <bitset name="a6xx_gras_cl_guardband_clip_adj" inline="true"> <bitfield name="HORZ" low="0" high="8" type="uint"/> <bitfield name="VERT" low="10" high="18" type="uint"/> - </reg32> + </bitset> + + <reg32 offset="0x8006" name="GRAS_CL_GUARDBAND_CLIP_ADJ" type="a6xx_gras_cl_guardband_clip_adj" variants="A6XX-A7XX" usage="rp_blit"/> <!-- Something connected to depth-stencil attachment size --> <reg32 offset="0x8007" name="GRAS_UNKNOWN_8007" variants="A7XX-" usage="rp_blit"/> - <reg32 offset="0x8008" name="GRAS_UNKNOWN_8008" variants="A7XX-" usage="cmd"/> + <!-- the scale/offset is per view, with up to 6 views --> + <bitset name="a6xx_gras_bin_foveat" inline="yes"> + <bitfield name="BINSCALEEN" pos="6" type="boolean"/> + <enum name="a7xx_bin_scale"> + <value value="0" name="NOSCALE"/> + <value value="1" name="SCALE2X"/> + <value value="2" name="SCALE4X"/> + </enum> + <bitfield name="XSCALE_0" low="8" high="9" type="a7xx_bin_scale"/> + <bitfield name="YSCALE_0" low="10" high="11" type="a7xx_bin_scale"/> + <bitfield name="XSCALE_1" low="12" high="13" type="a7xx_bin_scale"/> + <bitfield name="YSCALE_1" low="14" high="15" type="a7xx_bin_scale"/> + <bitfield name="XSCALE_2" low="16" high="17" type="a7xx_bin_scale"/> + <bitfield name="YSCALE_2" low="18" high="19" type="a7xx_bin_scale"/> + <bitfield name="XSCALE_3" low="20" high="21" type="a7xx_bin_scale"/> + <bitfield name="YSCALE_3" low="22" high="23" type="a7xx_bin_scale"/> + <bitfield name="XSCALE_4" low="24" high="25" type="a7xx_bin_scale"/> + <bitfield name="YSCALE_4" low="26" high="27" type="a7xx_bin_scale"/> + <bitfield name="XSCALE_5" low="28" high="29" type="a7xx_bin_scale"/> + <bitfield name="YSCALE_5" low="30" high="31" type="a7xx_bin_scale"/> + </bitset> - <reg32 offset="0x8009" name="GRAS_UNKNOWN_8009" variants="A7XX-" usage="cmd"/> - <reg32 offset="0x800a" name="GRAS_UNKNOWN_800A" variants="A7XX-" usage="cmd"/> - <reg32 offset="0x800b" name="GRAS_UNKNOWN_800B" variants="A7XX-" usage="cmd"/> - <reg32 offset="0x800c" name="GRAS_UNKNOWN_800C" variants="A7XX-" usage="cmd"/> + <reg32 offset="0x8008" name="GRAS_BIN_FOVEAT" type="a6xx_gras_bin_foveat" variants="A7XX" usage="cmd"/> + + <reg32 offset="0x8009" name="GRAS_BIN_FOVEAT_OFFSET_0" variants="A7XX-" usage="cmd"> + <bitfield name="XOFFSET_0" low="0" high="9" shr="2" type="uint"/> + <bitfield name="XOFFSET_1" low="10" high="19" shr="2" type="uint"/> + <bitfield name="XOFFSET_2" low="20" high="29" shr="2" type="uint"/> + </reg32> + <reg32 offset="0x800a" name="GRAS_BIN_FOVEAT_OFFSET_1" variants="A7XX-" usage="cmd"> + <bitfield name="XOFFSET_3" low="0" high="9" shr="2" type="uint"/> + <bitfield name="XOFFSET_4" low="10" high="19" shr="2" type="uint"/> + <bitfield name="XOFFSET_5" low="20" high="29" shr="2" type="uint"/> + </reg32> + <reg32 offset="0x800b" name="GRAS_BIN_FOVEAT_OFFSET_2" variants="A7XX-" usage="cmd"> + <bitfield name="YOFFSET_0" low="0" high="9" shr="2" type="uint"/> + <bitfield name="YOFFSET_1" low="10" high="19" shr="2" type="uint"/> + <bitfield name="YOFFSET_2" low="20" high="29" shr="2" type="uint"/> + </reg32> + <reg32 offset="0x800c" name="GRAS_BIN_FOVEAT_OFFSET_3" variants="A7XX-" usage="cmd"> + <bitfield name="YOFFSET_3" low="0" high="9" shr="2" type="uint"/> + <bitfield name="YOFFSET_4" low="10" high="19" shr="2" type="uint"/> + <bitfield name="YOFFSET_5" low="20" high="29" shr="2" type="uint"/> + </reg32> <!-- <reg32 offset="0x80f0" name="GRAS_UNKNOWN_80F0" type="a6xx_reg_xy"/> --> <!-- 0x8006-0x800f invalid --> - <array offset="0x8010" name="GRAS_CL_VIEWPORT" stride="6" length="16" usage="rp_blit"> + <array offset="0x8010" name="GRAS_CL_VIEWPORT" stride="6" length="16" variants="A6XX-A7XX" usage="rp_blit"> <reg32 offset="0" name="XOFFSET" type="float"/> <reg32 offset="1" name="XSCALE" type="float"/> <reg32 offset="2" name="YOFFSET" type="float"/> @@ -871,12 +920,13 @@ by a particular renderpass/blit. <reg32 offset="4" name="ZOFFSET" type="float"/> <reg32 offset="5" name="ZSCALE" type="float"/> </array> - <array offset="0x8070" name="GRAS_CL_VIEWPORT_ZCLAMP" stride="2" length="16" usage="rp_blit"> + + <array offset="0x8070" name="GRAS_CL_VIEWPORT_ZCLAMP" stride="2" length="16" variants="A6XX-A7XX" usage="rp_blit"> <reg32 offset="0" name="MIN" type="float"/> <reg32 offset="1" name="MAX" type="float"/> </array> - <reg32 offset="0x8090" name="GRAS_SU_CNTL" usage="rp_blit"> + <bitset name="a6xx_gras_su_cntl" varset="chip"> <bitfield name="CULL_FRONT" pos="0" type="boolean"/> <bitfield name="CULL_BACK" pos="1" type="boolean"/> <bitfield name="FRONT_CW" pos="2" type="boolean"/> @@ -886,39 +936,66 @@ by a particular renderpass/blit. <bitfield name="LINE_MODE" pos="13" type="a5xx_line_mode"/> <bitfield name="UNK15" low="15" high="16"/> <!-- - On gen1 only MULTIVIEW_ENABLE exists. On gen3 we have - the ability to add the view index to either the RT array - index or the viewport index, and it seems that - MULTIVIEW_ENABLE doesn't do anything, instead we need to - set at least one of RENDERTARGETINDEXINCR or - VIEWPORTINDEXINCR to enable multiview. The blob still - sets MULTIVIEW_ENABLE regardless. - TODO: what about gen2 (a640)? + On gen1 only MULTIVIEW_ENABLE exists. On gen3 we have + the ability to add the view index to either the RT array + index or the viewport index, and it seems that + MULTIVIEW_ENABLE doesn't do anything, instead we need to + set at least one of RENDERTARGETINDEXINCR or + VIEWPORTINDEXINCR to enable multiview. The blob still + sets MULTIVIEW_ENABLE regardless. + TODO: what about gen2 (a640)? --> <bitfield name="MULTIVIEW_ENABLE" pos="17" type="boolean"/> - <bitfield name="RENDERTARGETINDEXINCR" pos="18" type="boolean"/> - <bitfield name="VIEWPORTINDEXINCR" pos="19" type="boolean"/> - <bitfield name="UNK20" low="20" high="22"/> - </reg32> - <reg32 offset="0x8091" name="GRAS_SU_POINT_MINMAX" usage="rp_blit"> + <bitfield name="RENDERTARGETINDEXINCR" pos="18" type="boolean" variants="A6XX-A7XX"/> + <bitfield name="VIEWPORTINDEXINCR" pos="19" type="boolean" variants="A6XX-A7XX"/> + <bitfield name="UNK20" low="20" high="22" variants="A6XX-A7XX"/> + </bitset> + <reg32 offset="0x8090" name="GRAS_SU_CNTL" type="a6xx_gras_su_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + + <bitset name="a6xx_gras_su_point_minmax" inline="yes"> <bitfield name="MIN" low="0" high="15" type="ufixed" radix="4"/> <bitfield name="MAX" low="16" high="31" type="ufixed" radix="4"/> - </reg32> - <reg32 offset="0x8092" name="GRAS_SU_POINT_SIZE" low="0" high="15" type="fixed" radix="4" usage="rp_blit"/> + </bitset> + + <reg32 offset="0x8091" name="GRAS_SU_POINT_MINMAX" type="a6xx_gras_su_point_minmax" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x8092" name="GRAS_SU_POINT_SIZE" low="0" high="15" type="fixed" radix="4" variants="A6XX-A7XX" usage="rp_blit"/> + + <bitset name="a6xx_gras_su_depth_cntl" inline="yes"> + <bitfield name="Z_TEST_ENABLE" pos="0" type="boolean"/> + </bitset> + + <reg32 offset="0x8114" name="GRAS_SU_DEPTH_CNTL" variants="A6XX-A7XX" type="a6xx_gras_su_depth_cntl" usage="rp_blit"/> + + <bitset name="a6xx_gras_su_stencil_cntl" inline="yes"> + <bitfield name="STENCIL_ENABLE" pos="0" type="boolean"/> + </bitset> + + <reg32 offset="0x8115" name="GRAS_SU_STENCIL_CNTL" type="a6xx_gras_su_stencil_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + + <bitset name="a6xx_gras_su_render_cntl" inline="yes"> + <bitfield name="FS_DISABLE" pos="7" type="boolean"/> + </bitset> + + <reg32 offset="0x8116" name="GRAS_SU_RENDER_CNTL" type="a6xx_gras_su_render_cntl" variants="A7XX" usage="rp_blit"/> + <!-- 0x8093 invalid --> - <reg32 offset="0x8094" name="GRAS_SU_DEPTH_PLANE_CNTL" usage="rp_blit"> + <bitset name="a6xx_depth_plane_cntl" inline="yes"> <bitfield name="Z_MODE" low="0" high="1" type="a6xx_ztest_mode"/> - </reg32> - <reg32 offset="0x8095" name="GRAS_SU_POLY_OFFSET_SCALE" type="float" usage="rp_blit"/> - <reg32 offset="0x8096" name="GRAS_SU_POLY_OFFSET_OFFSET" type="float" usage="rp_blit"/> - <reg32 offset="0x8097" name="GRAS_SU_POLY_OFFSET_OFFSET_CLAMP" type="float" usage="rp_blit"/> - <!-- duplicates RB_DEPTH_BUFFER_INFO: --> - <reg32 offset="0x8098" name="GRAS_SU_DEPTH_BUFFER_INFO" usage="rp_blit"> + </bitset> + + <reg32 offset="0x8094" name="GRAS_SU_DEPTH_PLANE_CNTL" type="a6xx_depth_plane_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x8095" name="GRAS_SU_POLY_OFFSET_SCALE" type="float" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x8096" name="GRAS_SU_POLY_OFFSET_OFFSET" type="float" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x8097" name="GRAS_SU_POLY_OFFSET_OFFSET_CLAMP" type="float" variants="A6XX-A7XX" usage="rp_blit"/> + <bitset name="a6xx_depth_buffer_info" inline="yes"> <bitfield name="DEPTH_FORMAT" low="0" high="2" type="a6xx_depth_format"/> <bitfield name="UNK3" pos="3"/> - </reg32> + </bitset> + + <!-- duplicates RB_DEPTH_BUFFER_INFO: --> + <reg32 offset="0x8098" name="GRAS_SU_DEPTH_BUFFER_INFO" type="a6xx_depth_buffer_info" variants="A6XX-A7XX" usage="rp_blit"/> - <reg32 offset="0x8099" name="GRAS_SU_CONSERVATIVE_RAS_CNTL" usage="cmd"> + <bitset name="a6xx_gras_su_conservative_ras_cntl" inline="yes"> <bitfield name="CONSERVATIVERASEN" pos="0" type="boolean"/> <enum name="a6xx_shift_amount"> <value value="0" name="NO_SHIFT"/> @@ -928,7 +1005,10 @@ by a particular renderpass/blit. <bitfield name="SHIFTAMOUNT" low="1" high="2" type="a6xx_shift_amount"/> <bitfield name="INNERCONSERVATIVERASEN" pos="3" type="boolean"/> <bitfield name="UNK4" low="4" high="5"/> - </reg32> + </bitset> + + <reg32 offset="0x8099" name="GRAS_SU_CONSERVATIVE_RAS_CNTL" type="a6xx_gras_su_conservative_ras_cntl" variants="A6XX-A7XX" usage="cmd"/> + <reg32 offset="0x809a" name="GRAS_SU_PATH_RENDERING_CNTL"> <bitfield name="UNK0" pos="0" type="boolean"/> <bitfield name="LINELENGTHEN" pos="1" type="boolean"/> @@ -938,10 +1018,13 @@ by a particular renderpass/blit. <bitfield name="WRITES_LAYER" pos="0" type="boolean"/> <bitfield name="WRITES_VIEW" pos="1" type="boolean"/> </bitset> - <reg32 offset="0x809b" name="GRAS_SU_VS_SIV_CNTL" type="a6xx_gras_us_xs_siv_cntl" usage="rp_blit"/> - <reg32 offset="0x809c" name="GRAS_SU_GS_SIV_CNTL" type="a6xx_gras_us_xs_siv_cntl" usage="rp_blit"/> - <reg32 offset="0x809d" name="GRAS_SU_DS_SIV_CNTL" type="a6xx_gras_us_xs_siv_cntl" usage="rp_blit"/> - <!-- 0x809e/0x809f invalid --> + <reg32 offset="0x809b" name="GRAS_SU_VS_SIV_CNTL" type="a6xx_gras_us_xs_siv_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x809c" name="GRAS_SU_GS_SIV_CNTL" type="a6xx_gras_us_xs_siv_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x809d" name="GRAS_SU_DS_SIV_CNTL" type="a6xx_gras_us_xs_siv_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + + <bitset name="a6xx_rast_cntl" inline="yes"> + <bitfield name="MODE" low="0" high="1" type="a6xx_polygon_mode"/> + </bitset> <enum name="a6xx_sequenced_thread_dist"> <value value="0x0" name="DIST_SCREEN_COORD"/> @@ -989,7 +1072,7 @@ by a particular renderpass/blit. <value value="0x3" name="RB_BT"/> </enum> - <reg32 offset="0x80a0" name="GRAS_SC_CNTL" usage="rp_blit"> + <bitset name="a6xx_gras_sc_cntl" inline="yes"> <bitfield name="CCUSINGLECACHELINESIZE" low="0" high="2"/> <bitfield name="SINGLE_PRIM_MODE" low="3" high="4" type="a6xx_single_prim_mode"/> <bitfield name="RASTER_MODE" pos="5" type="a6xx_raster_mode"/> @@ -999,7 +1082,9 @@ by a particular renderpass/blit. <bitfield name="UNK9" pos="9" type="boolean"/> <bitfield name="ROTATION" low="10" high="11" type="uint"/> <bitfield name="EARLYVIZOUTEN" pos="12" type="boolean"/> - </reg32> + </bitset> + + <reg32 offset="0x80a0" name="GRAS_SC_CNTL" type="a6xx_gras_sc_cntl" variants="A6XX-A7XX" usage="rp_blit"/> <enum name="a6xx_render_mode"> <value value="0x0" name="RENDERING_PASS"/> @@ -1020,7 +1105,7 @@ by a particular renderpass/blit. <value value="0x4" name="LRZ_FEEDBACK_LATE_Z"/> </enum> - <reg32 offset="0x80a1" name="GRAS_SC_BIN_CNTL" usage="rp_blit"> + <bitset name="a6xx_bin_cntl" inline="yes"> <bitfield name="BINW" low="0" high="5" shr="5" type="uint"/> <bitfield name="BINH" low="8" high="14" shr="4" type="uint"/> <bitfield name="RENDER_MODE" low="18" high="20" type="a6xx_render_mode"/> @@ -1033,18 +1118,25 @@ by a particular renderpass/blit. In sysmem mode GRAS_LRZ_CNTL.LRZ_WRITE is not considered. </doc> <bitfield name="LRZ_FEEDBACK_ZMODE_MASK" low="24" high="26" type="a6xx_lrz_feedback_mask"/> - <bitfield name="UNK27" pos="27"/> - </reg32> + <bitfield name="FORCE_LRZ_DIS" pos="27" type="boolean"/> + </bitset> + + <reg32 offset="0x80a1" name="GRAS_SC_BIN_CNTL" type="a6xx_bin_cntl" variants="A6XX-A7XX" usage="rp_blit"/> - <reg32 offset="0x80a2" name="GRAS_SC_RAS_MSAA_CNTL" usage="rp_blit"> + <bitset name="a6xx_gras_sc_ras_msaa_cntl" inline="yes"> <bitfield name="SAMPLES" low="0" high="1" type="a3xx_msaa_samples"/> <bitfield name="UNK2" pos="2"/> <bitfield name="UNK3" pos="3"/> - </reg32> - <reg32 offset="0x80a3" name="GRAS_SC_DEST_MSAA_CNTL" usage="rp_blit"> + </bitset> + + <reg32 offset="0x80a2" name="GRAS_SC_RAS_MSAA_CNTL" type="a6xx_gras_sc_ras_msaa_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + + <bitset name="a6xx_gras_sc_dest_msaa_cntl" inline="yes"> <bitfield name="SAMPLES" low="0" high="1" type="a3xx_msaa_samples"/> <bitfield name="MSAA_DISABLE" pos="2" type="boolean"/> - </reg32> + </bitset> + + <reg32 offset="0x80a3" name="GRAS_SC_DEST_MSAA_CNTL" type="a6xx_gras_sc_dest_msaa_cntl" variants="A6XX-A7XX" usage="rp_blit"/> <bitset name="a6xx_msaa_sample_pos_cntl" inline="yes"> <bitfield name="UNK0" pos="0"/> @@ -1062,30 +1154,35 @@ by a particular renderpass/blit. <bitfield name="SAMPLE_3_Y" low="28" high="31" radix="4" type="fixed"/> </bitset> - <reg32 offset="0x80a4" name="GRAS_SC_MSAA_SAMPLE_POS_CNTL" type="a6xx_msaa_sample_pos_cntl" usage="rp_blit"/> - <reg32 offset="0x80a5" name="GRAS_SC_PROGRAMMABLE_MSAA_POS_0" type="a6xx_programmable_msaa_pos" usage="rp_blit"/> - <reg32 offset="0x80a6" name="GRAS_SC_PROGRAMMABLE_MSAA_POS_1" type="a6xx_programmable_msaa_pos" usage="rp_blit"/> + <reg32 offset="0x80a4" name="GRAS_SC_MSAA_SAMPLE_POS_CNTL" type="a6xx_msaa_sample_pos_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x80a5" name="GRAS_SC_PROGRAMMABLE_MSAA_POS_0" type="a6xx_programmable_msaa_pos" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x80a6" name="GRAS_SC_PROGRAMMABLE_MSAA_POS_1" type="a6xx_programmable_msaa_pos" variants="A6XX-A7XX" usage="rp_blit"/> - <reg32 offset="0x80a7" name="GRAS_UNKNOWN_80A7" variants="A7XX-" usage="cmd"/> + <reg32 offset="0x80a7" name="GRAS_ROTATION_CNTL" variants="A7XX" usage="cmd"/> - <!-- 0x80a7-0x80ae invalid --> - <reg32 offset="0x80af" name="GRAS_UNKNOWN_80AF" pos="0" usage="cmd"/> + <bitset name="a6xx_screen_scissor_cntl" inline="yes"> + <bitfield name="SCISSOR_DISABLE" pos="0" type="boolean"/> + </bitset> + + <reg32 offset="0x80af" name="GRAS_SC_SCREEN_SCISSOR_CNTL" type="a6xx_screen_scissor_cntl" variants="A6XX-A7XX" pos="0" usage="cmd"/> <bitset name="a6xx_scissor_xy" inline="yes"> <bitfield name="X" low="0" high="15" type="uint"/> <bitfield name="Y" low="16" high="31" type="uint"/> </bitset> - <array offset="0x80b0" name="GRAS_SC_SCREEN_SCISSOR" stride="2" length="16" usage="rp_blit"> + + <array offset="0x80b0" name="GRAS_SC_SCREEN_SCISSOR" stride="2" length="16" variants="A6XX-A7XX" usage="rp_blit"> <reg32 offset="0" name="TL" type="a6xx_scissor_xy"/> <reg32 offset="1" name="BR" type="a6xx_scissor_xy"/> </array> - <array offset="0x80d0" name="GRAS_SC_VIEWPORT_SCISSOR" stride="2" length="16" usage="rp_blit"> + + <array offset="0x80d0" name="GRAS_SC_VIEWPORT_SCISSOR" stride="2" length="16" variants="A6XX-A7XX" usage="rp_blit"> <reg32 offset="0" name="TL" type="a6xx_scissor_xy"/> <reg32 offset="1" name="BR" type="a6xx_scissor_xy"/> </array> - <reg32 offset="0x80f0" name="GRAS_SC_WINDOW_SCISSOR_TL" type="a6xx_reg_xy" usage="rp_blit"/> - <reg32 offset="0x80f1" name="GRAS_SC_WINDOW_SCISSOR_BR" type="a6xx_reg_xy" usage="rp_blit"/> + <reg32 offset="0x80f0" name="GRAS_SC_WINDOW_SCISSOR_TL" type="a6xx_reg_xy" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x80f1" name="GRAS_SC_WINDOW_SCISSOR_BR" type="a6xx_reg_xy" variants="A6XX-A7XX" usage="rp_blit"/> <enum name="a6xx_fsr_combiner"> <value value="0" name="FSR_COMBINER_OP_KEEP"/> @@ -1095,7 +1192,7 @@ by a particular renderpass/blit. <value value="4" name="FSR_COMBINER_OP_MUL"/> </enum> - <reg32 offset="0x80f4" name="GRAS_VRS_CONFIG" variants="A7XX-" usage="rp_blit"> + <bitset name="a6xx_gras_vrs_config"> <bitfield name="PIPELINE_FSR_ENABLE" pos="0" type="boolean"/> <bitfield name="FRAG_SIZE_X" low="1" high="2" type="uint"/> <bitfield name="FRAG_SIZE_Y" low="3" high="4" type="uint"/> @@ -1103,20 +1200,32 @@ by a particular renderpass/blit. <bitfield name="COMBINER_OP_2" low="8" high="10" type="a6xx_fsr_combiner"/> <bitfield name="ATTACHMENT_FSR_ENABLE" pos="13" type="boolean"/> <bitfield name="PRIMITIVE_FSR_ENABLE" pos="20" type="boolean"/> - </reg32> - <reg32 offset="0x80f5" name="GRAS_QUALITY_BUFFER_INFO" variants="A7XX-" usage="rp_blit"> + </bitset> + + <reg32 offset="0x80f4" name="GRAS_VRS_CONFIG" type="a6xx_gras_vrs_config" variants="A7XX" usage="rp_blit"/> + + <bitset name="a6xx_gras_quality_buffer_info" inline="yes"> <bitfield name="LAYERED" pos="0" type="boolean"/> <bitfield name="TILE_MODE" low="1" high="2" type="a6xx_tile_mode"/> - </reg32> - <reg32 offset="0x80f6" name="GRAS_QUALITY_BUFFER_DIMENSION" variants="A7XX-" usage="rp_blit"> + </bitset> + + <reg32 offset="0x80f5" name="GRAS_QUALITY_BUFFER_INFO" type="a6xx_gras_quality_buffer_info" variants="A7XX" usage="rp_blit"/> + + <bitset name="a6xx_gras_quality_buffer_dimension" inline="yes"> <bitfield name="WIDTH" low="0" high="15" type="uint"/> <bitfield name="HEIGHT" low="16" high="31" type="uint"/> - </reg32> - <reg64 offset="0x80f8" name="GRAS_QUALITY_BUFFER_BASE" variants="A7XX-" type="waddress" usage="rp_blit"/> - <reg32 offset="0x80fa" name="GRAS_QUALITY_BUFFER_PITCH" variants="A7XX-" usage="rp_blit"> + </bitset> + + <reg32 offset="0x80f6" name="GRAS_QUALITY_BUFFER_DIMENSION" type="a6xx_gras_quality_buffer_dimension" variants="A7XX" usage="rp_blit"/> + + <reg64 offset="0x80f8" name="GRAS_QUALITY_BUFFER_BASE" variants="A7XX" type="waddress" usage="rp_blit"/> + + <bitset name="a6xx_gras_quality_buffer_pitch" inline="yes"> <bitfield name="PITCH" shr="6" low="0" high="7" type="uint"/> <bitfield name="ARRAY_PITCH" shr="6" low="10" high="28" type="uint"/> - </reg32> + </bitset> + + <reg32 offset="0x80fa" name="GRAS_QUALITY_BUFFER_PITCH" type="a6xx_gras_quality_buffer_pitch" variants="A7XX" usage="rp_blit"/> <enum name="a6xx_lrz_dir_status"> <value value="0x1" name="LRZ_DIR_LE"/> @@ -1124,7 +1233,7 @@ by a particular renderpass/blit. <value value="0x3" name="LRZ_DIR_INVALID"/> </enum> - <reg32 offset="0x8100" name="GRAS_LRZ_CNTL" usage="rp_blit"> + <bitset name="a6xx_gras_lrz_cntl" inline="yes"> <bitfield name="ENABLE" pos="0" type="boolean"/> <doc>LRZ write also disabled for blend/etc.</doc> <bitfield name="LRZ_WRITE" pos="1" type="boolean"/> @@ -1151,26 +1260,36 @@ by a particular renderpass/blit. </doc> <bitfield name="DISABLE_ON_WRONG_DIR" pos="9" type="boolean" variants="A6XX"/> <bitfield name="Z_FUNC" low="11" high="13" type="adreno_compare_func" variants="A7XX-"/> - </reg32> + </bitset> + + <reg32 offset="0x8100" name="GRAS_LRZ_CNTL" type="a6xx_gras_lrz_cntl" usage="rp_blit" variants="A6XX-A7XX"/> <enum name="a6xx_fragcoord_sample_mode"> <value value="0" name="FRAGCOORD_CENTER"/> <value value="3" name="FRAGCOORD_SAMPLE"/> </enum> - <reg32 offset="0x8101" name="GRAS_LRZ_PS_INPUT_CNTL" low="0" high="2" usage="rp_blit"> + <bitset name="a6xx_gras_lrz_ps_input_cntl" inline="yes"> <bitfield name="SAMPLEID" pos="0" type="boolean"/> <bitfield name="FRAGCOORDSAMPLEMODE" low="1" high="2" type="a6xx_fragcoord_sample_mode"/> - </reg32> + </bitset> + + <reg32 offset="0x8101" name="GRAS_LRZ_PS_INPUT_CNTL" type="a6xx_gras_lrz_ps_input_cntl" usage="rp_blit" variants="A6XX-A7XX"/> - <reg32 offset="0x8102" name="GRAS_LRZ_MRT_BUFFER_INFO_0" usage="rp_blit"> + <bitset name="a6xx_gras_lrz_mrt_buffer_info_0" inline="yes"> <bitfield name="COLOR_FORMAT" low="0" high="7" type="a6xx_format"/> - </reg32> - <reg64 offset="0x8103" name="GRAS_LRZ_BUFFER_BASE" align="256" type="waddress" usage="rp_blit"/> - <reg32 offset="0x8105" name="GRAS_LRZ_BUFFER_PITCH" usage="rp_blit"> + </bitset> + + <reg32 offset="0x8102" name="GRAS_LRZ_MRT_BUFFER_INFO_0" type="a6xx_gras_lrz_mrt_buffer_info_0" usage="rp_blit" variants="A6XX-A7XX"/> + + <reg64 offset="0x8103" name="GRAS_LRZ_BUFFER_BASE" align="256" type="waddress" usage="rp_blit" variants="A6XX-A7XX"/> + + <bitset name="a6xx_gras_lrz_buffer_pitch" inline="yes"> <bitfield name="PITCH" low="0" high="7" shr="5" type="uint"/> <bitfield name="ARRAY_PITCH" low="10" high="28" shr="8" type="uint"/> - </reg32> + </bitset> + + <reg32 offset="0x8105" name="GRAS_LRZ_BUFFER_PITCH" type="a6xx_gras_lrz_buffer_pitch" usage="rp_blit" variants="A6XX-A7XX"/> <!-- The LRZ "fast clear" buffer is initialized to zero's by blob, and @@ -1203,7 +1322,6 @@ by a particular renderpass/blit. not. --> <reg64 offset="0x8106" name="GRAS_LRZ_FAST_CLEAR_BUFFER_BASE" align="64" type="waddress" usage="rp_blit"/> - <!-- 0x8108 invalid --> <reg32 offset="0x8109" name="GRAS_LRZ_PS_SAMPLEFREQ_CNTL" usage="rp_blit"> <bitfield name="PER_SAMP_MODE" pos="0" type="boolean"/> </reg32> @@ -1228,19 +1346,20 @@ by a particular renderpass/blit. <!-- 0x810c-0x810f invalid --> - <reg32 offset="0x8110" name="GRAS_UNKNOWN_8110" low="0" high="1" usage="cmd"/> + <reg32 offset="0x8110" name="GRAS_MODE_CNTL" low="0" high="1" variants="A6XX-A7XX" usage="cmd"/> <!-- A bit tentative but it's a color and it is followed by LRZ_CLEAR --> - <reg32 offset="0x8111" name="GRAS_LRZ_DEPTH_CLEAR" type="float" variants="A7XX-"/> + <reg32 offset="0x8111" name="GRAS_LRZ_DEPTH_CLEAR" type="float" variants="A7XX"/> - <reg32 offset="0x8113" name="GRAS_LRZ_DEPTH_BUFFER_INFO" variants="A7XX-" usage="rp_blit"> + <bitset name="a6xx_gras_lrz_depth_buffer_info" inline="yes"> <bitfield name="DEPTH_FORMAT" low="0" high="2" type="a6xx_depth_format"/> <bitfield name="UNK3" pos="3"/> - </reg32> + </bitset> + + <reg32 offset="0x8113" name="GRAS_LRZ_DEPTH_BUFFER_INFO" type="a6xx_gras_lrz_depth_buffer_info" variants="A7XX" usage="rp_blit"/> - <!-- Always written together and always equal 09510840 00000a62 --> - <reg32 offset="0x8120" name="GRAS_UNKNOWN_8120" variants="A7XX-" usage="cmd"/> - <reg32 offset="0x8121" name="GRAS_UNKNOWN_8121" variants="A7XX-" usage="cmd"/> + <doc>LUT used to convert quality buffer values to HW shading rate values. An array of 4-bit values.</doc> + <array offset="0x8120" name="GRAS_LRZ_QUALITY_LOOKUP_TABLE" variants="A7XX-" stride="1" length="2"/> <!-- 0x8112-0x83ff invalid --> @@ -1265,28 +1384,29 @@ by a particular renderpass/blit. <bitfield name="D24S8" pos="19" type="boolean"/> <!-- some sort of channel mask, disabled channels are set to zero ? --> <bitfield name="MASK" low="20" high="23"/> - <bitfield name="IFMT" low="24" high="28" type="a6xx_2d_ifmt"/> + <bitfield name="IFMT" low="24" high="26" type="a6xx_2d_ifmt"/> + <bitfield name="UNK27" pos="27" type="boolean"/> + <bitfield name="UNK28" pos="28" type="boolean"/> <bitfield name="RASTER_MODE" pos="29" type="a6xx_raster_mode"/> - <bitfield name="UNK30" pos="30" type="boolean" variants="A7XX-"/> + <bitfield name="COPY" pos="30" type="boolean" variants="A7XX-"/> </bitset> - <reg32 offset="0x8400" name="GRAS_A2D_BLT_CNTL" type="a6xx_a2d_bit_cntl" usage="rp_blit"/> + <reg32 offset="0x8400" name="GRAS_A2D_BLT_CNTL" type="a6xx_a2d_bit_cntl" variants="A6XX-A7XX" usage="rp_blit"/> <!-- note: the low 8 bits for src coords are valid, probably fixed point it would be a bit weird though, since we subtract 1 from BR coords apparently signed, gallium driver uses negative coords and it works? --> - <reg32 offset="0x8401" name="GRAS_A2D_SRC_XMIN" low="8" high="24" type="int" usage="rp_blit"/> - <reg32 offset="0x8402" name="GRAS_A2D_SRC_XMAX" low="8" high="24" type="int" usage="rp_blit"/> - <reg32 offset="0x8403" name="GRAS_A2D_SRC_YMIN" low="8" high="24" type="int" usage="rp_blit"/> - <reg32 offset="0x8404" name="GRAS_A2D_SRC_YMAX" low="8" high="24" type="int" usage="rp_blit"/> - <reg32 offset="0x8405" name="GRAS_A2D_DEST_TL" type="a6xx_reg_xy" usage="rp_blit"/> - <reg32 offset="0x8406" name="GRAS_A2D_DEST_BR" type="a6xx_reg_xy" usage="rp_blit"/> + <reg32 offset="0x8401" name="GRAS_A2D_SRC_XMIN" low="8" high="24" type="int" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x8402" name="GRAS_A2D_SRC_XMAX" low="8" high="24" type="int" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x8403" name="GRAS_A2D_SRC_YMIN" low="8" high="24" type="int" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x8404" name="GRAS_A2D_SRC_YMAX" low="8" high="24" type="int" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x8405" name="GRAS_A2D_DEST_TL" type="a6xx_reg_xy" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x8406" name="GRAS_A2D_DEST_BR" type="a6xx_reg_xy" variants="A6XX-A7XX" usage="rp_blit"/> <reg32 offset="0x8407" name="GRAS_2D_UNKNOWN_8407" low="0" high="31"/> <reg32 offset="0x8408" name="GRAS_2D_UNKNOWN_8408" low="0" high="31"/> <reg32 offset="0x8409" name="GRAS_2D_UNKNOWN_8409" low="0" high="31"/> - <reg32 offset="0x840a" name="GRAS_A2D_SCISSOR_TL" type="a6xx_reg_xy" usage="rp_blit"/> - <reg32 offset="0x840b" name="GRAS_A2D_SCISSOR_BR" type="a6xx_reg_xy" usage="rp_blit"/> - <!-- 0x840c-0x85ff invalid --> + <reg32 offset="0x840a" name="GRAS_A2D_SCISSOR_TL" type="a6xx_reg_xy" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x840b" name="GRAS_A2D_SCISSOR_BR" type="a6xx_reg_xy" variants="A6XX-A7XX" usage="rp_blit"/> <!-- always 0x880 ? (and 0 in a640/a650 traces?) --> <reg32 offset="0x8600" name="GRAS_DBG_ECO_CNTL" usage="cmd"> @@ -1304,22 +1424,7 @@ by a particular renderpass/blit. --> <!-- same as GRAS_BIN_CONTROL, but without bit 27: --> - <reg32 offset="0x8800" name="RB_CNTL" variants="A6XX" usage="rp_blit"> - <bitfield name="BINW" low="0" high="5" shr="5" type="uint"/> - <bitfield name="BINH" low="8" high="14" shr="4" type="uint"/> - <bitfield name="RENDER_MODE" low="18" high="20" type="a6xx_render_mode"/> - <bitfield name="FORCE_LRZ_WRITE_DIS" pos="21" type="boolean"/> - <bitfield name="BUFFERS_LOCATION" low="22" high="23" type="a6xx_buffers_location"/> - <bitfield name="LRZ_FEEDBACK_ZMODE_MASK" low="24" high="26" type="a6xx_lrz_feedback_mask"/> - </reg32> - - <reg32 offset="0x8800" name="RB_CNTL" variants="A7XX-" usage="rp_blit"> - <bitfield name="BINW" low="0" high="5" shr="5" type="uint"/> - <bitfield name="BINH" low="8" high="14" shr="4" type="uint"/> - <bitfield name="RENDER_MODE" low="18" high="20" type="a6xx_render_mode"/> - <bitfield name="FORCE_LRZ_WRITE_DIS" pos="21" type="boolean"/> - <bitfield name="LRZ_FEEDBACK_ZMODE_MASK" low="24" high="26" type="a6xx_lrz_feedback_mask"/> - </reg32> + <reg32 offset="0x8800" name="RB_CNTL" variants="A6XX-A7XX" type="a6xx_bin_cntl" usage="rp_blit"/> <reg32 offset="0x8801" name="RB_RENDER_CNTL" variants="A6XX" usage="rp_blit"> <bitfield name="CCUSINGLECACHELINESIZE" low="3" high="5"/> @@ -1343,9 +1448,6 @@ by a particular renderpass/blit. <bitfield name="CONSERVATIVERASEN" pos="11" type="boolean"/> <bitfield name="INNERCONSERVATIVERASEN" pos="12" type="boolean"/> </reg32> - <reg32 offset="0x8116" name="GRAS_SU_RENDER_CNTL" variants="A7XX-" usage="rp_blit"> - <bitfield name="FS_DISABLE" pos="7" type="boolean"/> - </reg32> <reg32 offset="0x8802" name="RB_RAS_MSAA_CNTL" usage="rp_blit"> <bitfield name="SAMPLES" low="0" high="1" type="a3xx_msaa_samples"/> @@ -1512,9 +1614,7 @@ by a particular renderpass/blit. <bitfield name="SAMPLE_MASK" low="16" high="31"/> </reg32> <!-- 0x8866-0x886f invalid --> - <reg32 offset="0x8870" name="RB_DEPTH_PLANE_CNTL" usage="rp_blit"> - <bitfield name="Z_MODE" low="0" high="1" type="a6xx_ztest_mode"/> - </reg32> + <reg32 offset="0x8870" name="RB_DEPTH_PLANE_CNTL" type="a6xx_depth_plane_cntl" usage="rp_blit"/> <reg32 offset="0x8871" name="RB_DEPTH_CNTL" usage="rp_blit"> <bitfield name="Z_TEST_ENABLE" pos="0" type="boolean"/> @@ -1528,14 +1628,9 @@ by a particular renderpass/blit. <bitfield name="Z_READ_ENABLE" pos="6" type="boolean"/> <bitfield name="Z_BOUNDS_ENABLE" pos="7" type="boolean"/> </reg32> - <reg32 offset="0x8114" name="GRAS_SU_DEPTH_CNTL" usage="rp_blit"> - <bitfield name="Z_TEST_ENABLE" pos="0" type="boolean"/> - </reg32> + <!-- duplicates GRAS_SU_DEPTH_BUFFER_INFO: --> - <reg32 offset="0x8872" name="RB_DEPTH_BUFFER_INFO" variants="A6XX" usage="rp_blit"> - <bitfield name="DEPTH_FORMAT" low="0" high="2" type="a6xx_depth_format"/> - <bitfield name="UNK3" low="3" high="4"/> - </reg32> + <reg32 offset="0x8872" name="RB_DEPTH_BUFFER_INFO" variants="A6XX" type="a6xx_depth_buffer_info" usage="rp_blit"/> <!-- first 4 bits duplicates GRAS_SU_DEPTH_BUFFER_INFO --> <reg32 offset="0x8872" name="RB_DEPTH_BUFFER_INFO" variants="A7XX-" usage="rp_blit"> <bitfield name="DEPTH_FORMAT" low="0" high="2" type="a6xx_depth_format"/> @@ -1571,9 +1666,7 @@ by a particular renderpass/blit. <bitfield name="ZPASS_BF" low="26" high="28" type="adreno_stencil_op"/> <bitfield name="ZFAIL_BF" low="29" high="31" type="adreno_stencil_op"/> </reg32> - <reg32 offset="0x8115" name="GRAS_SU_STENCIL_CNTL" usage="rp_blit"> - <bitfield name="STENCIL_ENABLE" pos="0" type="boolean"/> - </reg32> + <reg32 offset="0x8881" name="RB_STENCIL_BUFFER_INFO" variants="A6XX" usage="rp_blit"> <bitfield name="SEPARATE_STENCIL" pos="0" type="boolean"/> <bitfield name="UNK1" pos="1" type="boolean"/> @@ -1612,8 +1705,9 @@ by a particular renderpass/blit. <reg32 offset="0x8899" name="RB_UNKNOWN_8899" variants="A7XX-" usage="cmd"/> <!-- 0x8899-0x88bf invalid --> <!-- clamps depth value for depth test/write --> - <reg32 offset="0x88c0" name="RB_VIEWPORT_ZCLAMP_MIN" type="float" usage="rp_blit"/> - <reg32 offset="0x88c1" name="RB_VIEWPORT_ZCLAMP_MAX" type="float" usage="rp_blit"/> + <reg32 offset="0x88c0" name="RB_VIEWPORT_ZCLAMP_MIN" type="float" usage="rp_blit" variants="A6XX-A7XX"/> + <reg32 offset="0x88c1" name="RB_VIEWPORT_ZCLAMP_MAX" type="float" usage="rp_blit" variants="A6XX-A7XX"/> + <!-- 0x88c2-0x88cf invalid--> <reg32 offset="0x88d0" name="RB_RESOLVE_CNTL_0" usage="rp_blit"> <bitfield name="UNK0" low="0" high="12"/> @@ -1622,7 +1716,7 @@ by a particular renderpass/blit. <reg32 offset="0x88d1" name="RB_RESOLVE_CNTL_1" type="a6xx_reg_xy" usage="rp_blit"/> <reg32 offset="0x88d2" name="RB_RESOLVE_CNTL_2" type="a6xx_reg_xy" usage="rp_blit"/> <!-- weird to duplicate other regs from same block?? --> - <reg32 offset="0x88d3" name="RB_RESOLVE_CNTL_3" usage="rp_blit"> + <reg32 offset="0x88d3" name="RB_RESOLVE_CNTL_3" variants="A6XX-A7XX" usage="rp_blit"> <bitfield name="BINW" low="0" high="5" shr="5" type="uint"/> <bitfield name="BINH" low="8" high="14" shr="4" type="uint"/> </reg32> @@ -1646,10 +1740,13 @@ by a particular renderpass/blit. <!-- array-pitch is size of layer --> <reg32 offset="0x88db" name="RB_RESOLVE_SYSTEM_BUFFER_ARRAY_PITCH" low="0" high="28" shr="6" type="uint" usage="rp_blit"/> <reg64 offset="0x88dc" name="RB_RESOLVE_SYSTEM_FLAG_BUFFER_BASE" type="waddress" align="64" usage="rp_blit"/> - <reg32 offset="0x88de" name="RB_RESOLVE_SYSTEM_FLAG_BUFFER_PITCH" usage="rp_blit"> + + <bitset name="a6xx_flag_buffer_pitch" inline="yes"> <bitfield name="PITCH" low="0" high="10" shr="6" type="uint"/> - <bitfield name="ARRAY_PITCH" low="11" high="27" shr="7" type="uint"/> - </reg32> + <bitfield name="ARRAY_PITCH" low="11" high="28" shr="7" type="uint"/> + </bitset> + + <reg32 offset="0x88de" name="RB_RESOLVE_SYSTEM_FLAG_BUFFER_PITCH" type="a6xx_flag_buffer_pitch" usage="rp_blit"/> <reg32 offset="0x88df" name="RB_RESOLVE_CLEAR_COLOR_DW0" usage="rp_blit"/> <reg32 offset="0x88e0" name="RB_RESOLVE_CLEAR_COLOR_DW1" usage="rp_blit"/> @@ -1722,10 +1819,7 @@ by a particular renderpass/blit. <reg32 offset="0x88f0" name="RB_UNKNOWN_88F0" low="0" high="11" usage="cmd"/> <!-- could be for separate stencil? (or may not be a flag buffer at all) --> <reg64 offset="0x88f1" name="RB_UNK_FLAG_BUFFER_BASE" type="waddress" align="64"/> - <reg32 offset="0x88f3" name="RB_UNK_FLAG_BUFFER_PITCH"> - <bitfield name="PITCH" low="0" high="10" shr="6" type="uint"/> - <bitfield name="ARRAY_PITCH" low="11" high="23" shr="7" type="uint"/> - </reg32> + <reg32 offset="0x88f3" name="RB_UNK_FLAG_BUFFER_PITCH" type="a6xx_flag_buffer_pitch"/> <reg32 offset="0x88f4" name="RB_VRS_CONFIG" usage="rp_blit"> <bitfield name="UNK2" pos="2" type="boolean"/> @@ -1733,8 +1827,9 @@ by a particular renderpass/blit. <bitfield name="ATTACHMENT_FSR_ENABLE" pos="5" type="boolean"/> <bitfield name="PRIMITIVE_FSR_ENABLE" pos="18" type="boolean"/> </reg32> - <!-- Connected to VK_EXT_fragment_density_map? --> - <reg32 offset="0x88f5" name="RB_UNKNOWN_88F5" variants="A7XX-"/> + <reg32 offset="0x88f5" name="RB_BIN_FOVEAT" variants="A7XX-" usage="cmd"> + <bitfield name="BINSCALEEN" pos="6" type="boolean"/> + </reg32> <!-- 0x88f6-0x88ff invalid --> <reg64 offset="0x8900" name="RB_DEPTH_FLAG_BUFFER_BASE" type="waddress" align="64" usage="rp_blit"/> <reg32 offset="0x8902" name="RB_DEPTH_FLAG_BUFFER_PITCH" usage="rp_blit"> @@ -1743,12 +1838,10 @@ by a particular renderpass/blit. <bitfield name="UNK8" low="8" high="10"/> <bitfield name="ARRAY_PITCH" low="11" high="27" shr="7" type="uint"/> </reg32> + <array offset="0x8903" name="RB_COLOR_FLAG_BUFFER" stride="3" length="8" usage="rp_blit"> <reg64 offset="0" name="ADDR" type="waddress" align="64"/> - <reg32 offset="2" name="PITCH"> - <bitfield name="PITCH" low="0" high="10" shr="6" type="uint"/> - <bitfield name="ARRAY_PITCH" low="11" high="28" shr="7" type="uint"/> - </reg32> + <reg32 offset="2" name="PITCH" type="a6xx_flag_buffer_pitch"/> </array> <!-- 0x891b-0x8926 invalid --> <doc> @@ -1811,7 +1904,7 @@ by a particular renderpass/blit. <reg64 offset="0x8c1e" name="RB_A2D_DEST_BUFFER_BASE_2" type="waddress" align="64" usage="rp_blit"/> <reg64 offset="0x8c20" name="RB_A2D_DEST_FLAG_BUFFER_BASE" type="waddress" align="64" usage="rp_blit"/> - <reg32 offset="0x8c22" name="RB_A2D_DEST_FLAG_BUFFER_PITCH" low="0" high="7" shr="6" type="uint" usage="rp_blit"/> + <reg32 offset="0x8c22" name="RB_A2D_DEST_FLAG_BUFFER_PITCH" type="a6xx_flag_buffer_pitch" usage="rp_blit"/> <!-- this is a guess but seems likely (for NV12 with UBWC): --> <reg64 offset="0x8c23" name="RB_A2D_DEST_FLAG_BUFFER_BASE_1" type="waddress" align="64" usage="rp_blit"/> <reg32 offset="0x8c25" name="RB_A2D_DEST_FLAG_BUFFER_PITCH_1" low="0" high="7" shr="6" type="uint" usage="rp_blit"/> @@ -1917,13 +2010,13 @@ by a particular renderpass/blit. <bitfield name="CLIP_DIST_03_LOC" low="8" high="15" type="uint"/> <bitfield name="CLIP_DIST_47_LOC" low="16" high="23" type="uint"/> </bitset> - <reg32 offset="0x9101" name="VPC_VS_CLIP_CULL_CNTL" type="a6xx_vpc_xs_clip_cntl" usage="rp_blit"/> - <reg32 offset="0x9102" name="VPC_GS_CLIP_CULL_CNTL" type="a6xx_vpc_xs_clip_cntl" usage="rp_blit"/> - <reg32 offset="0x9103" name="VPC_DS_CLIP_CULL_CNTL" type="a6xx_vpc_xs_clip_cntl" usage="rp_blit"/> + <reg32 offset="0x9101" name="VPC_VS_CLIP_CULL_CNTL" type="a6xx_vpc_xs_clip_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x9102" name="VPC_GS_CLIP_CULL_CNTL" type="a6xx_vpc_xs_clip_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x9103" name="VPC_DS_CLIP_CULL_CNTL" type="a6xx_vpc_xs_clip_cntl" variants="A6XX-A7XX" usage="rp_blit"/> - <reg32 offset="0x9311" name="VPC_VS_CLIP_CULL_CNTL_V2" type="a6xx_vpc_xs_clip_cntl" usage="rp_blit"/> - <reg32 offset="0x9312" name="VPC_GS_CLIP_CULL_CNTL_V2" type="a6xx_vpc_xs_clip_cntl" usage="rp_blit"/> - <reg32 offset="0x9313" name="VPC_DS_CLIP_CULL_CNTL_V2" type="a6xx_vpc_xs_clip_cntl" usage="rp_blit"/> + <reg32 offset="0x9311" name="VPC_VS_CLIP_CULL_CNTL_V2" type="a6xx_vpc_xs_clip_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x9312" name="VPC_GS_CLIP_CULL_CNTL_V2" type="a6xx_vpc_xs_clip_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x9313" name="VPC_DS_CLIP_CULL_CNTL_V2" type="a6xx_vpc_xs_clip_cntl" variants="A6XX-A7XX" usage="rp_blit"/> <bitset name="a6xx_vpc_xs_siv_cntl" inline="yes"> <bitfield name="LAYERLOC" low="0" high="7" type="uint"/> @@ -1931,23 +2024,33 @@ by a particular renderpass/blit. <bitfield name="SHADINGRATELOC" low="16" high="23" type="uint" variants="A7XX-"/> </bitset> - <reg32 offset="0x9104" name="VPC_VS_SIV_CNTL" type="a6xx_vpc_xs_siv_cntl" usage="rp_blit"/> - <reg32 offset="0x9105" name="VPC_GS_SIV_CNTL" type="a6xx_vpc_xs_siv_cntl" usage="rp_blit"/> - <reg32 offset="0x9106" name="VPC_DS_SIV_CNTL" type="a6xx_vpc_xs_siv_cntl" usage="rp_blit"/> + <reg32 offset="0x9104" name="VPC_VS_SIV_CNTL" type="a6xx_vpc_xs_siv_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x9105" name="VPC_GS_SIV_CNTL" type="a6xx_vpc_xs_siv_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x9106" name="VPC_DS_SIV_CNTL" type="a6xx_vpc_xs_siv_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + + + <reg32 offset="0x9314" name="VPC_VS_SIV_CNTL_V2" type="a6xx_vpc_xs_siv_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x9315" name="VPC_GS_SIV_CNTL_V2" type="a6xx_vpc_xs_siv_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x9316" name="VPC_DS_SIV_CNTL_V2" type="a6xx_vpc_xs_siv_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + + <bitset name="a6xx_vpc_rast_stream_cntl" inline="yes"> + <!-- which stream to send to GRAS --> + <bitfield name="STREAM" low="0" high="1" type="uint"/> + <!-- discard primitives before rasterization --> + <bitfield name="DISCARD" pos="2" type="boolean"/> + </bitset> - <reg32 offset="0x9314" name="VPC_VS_SIV_CNTL_V2" type="a6xx_vpc_xs_siv_cntl" usage="rp_blit"/> - <reg32 offset="0x9315" name="VPC_GS_SIV_CNTL_V2" type="a6xx_vpc_xs_siv_cntl" usage="rp_blit"/> - <reg32 offset="0x9316" name="VPC_DS_SIV_CNTL_V2" type="a6xx_vpc_xs_siv_cntl" usage="rp_blit"/> + <reg32 offset="0x9980" name="VPC_RAST_STREAM_CNTL" type="a6xx_vpc_rast_stream_cntl" variants="A6XX" usage="rp_blit"/> + <reg32 offset="0x9107" name="VPC_RAST_STREAM_CNTL" type="a6xx_vpc_rast_stream_cntl" variants="A7XX" usage="rp_blit"/> + <reg32 offset="0x9317" name="VPC_RAST_STREAM_CNTL_V2" type="a6xx_vpc_rast_stream_cntl" variants="A7XX" usage="rp_blit"/> <reg32 offset="0x9107" name="VPC_UNKNOWN_9107" variants="A6XX" usage="rp_blit"> <!-- this mirrors VPC_RAST_STREAM_CNTL::DISCARD, although it seems it's unused --> <bitfield name="RASTER_DISCARD" pos="0" type="boolean"/> <bitfield name="UNK2" pos="2" type="boolean"/> </reg32> - <reg32 offset="0x9108" name="VPC_RAST_CNTL" usage="rp_blit"> - <bitfield name="MODE" low="0" high="1" type="a6xx_polygon_mode"/> - </reg32> + <reg32 offset="0x9108" name="VPC_RAST_CNTL" type="a6xx_rast_cntl" variants="A6XX-A7XX" usage="rp_blit"/> <bitset name="a6xx_pc_cntl" inline="yes"> <bitfield name="PRIMITIVE_RESTART" pos="0" type="boolean"/> <bitfield name="PROVOKING_VTX_LAST" pos="1" type="boolean"/> @@ -1987,10 +2090,10 @@ by a particular renderpass/blit. <bitfield name="VIEWS" low="2" high="6" type="uint"/> </bitset> - <reg32 offset="0x9109" name="VPC_PC_CNTL" type="a6xx_pc_cntl" variants="A7XX-" usage="rp_blit"/> - <reg32 offset="0x910a" name="VPC_GS_PARAM_0" type="a6xx_gs_param_0" variants="A7XX-" usage="rp_blit"/> - <reg32 offset="0x910b" name="VPC_STEREO_RENDERING_VIEWMASK" type="hex" low="0" high="15" variants="A7XX-" usage="rp_blit"/> - <reg32 offset="0x910c" name="VPC_STEREO_RENDERING_CNTL" type="a6xx_stereo_rendering_cntl" variants="A7XX-" usage="rp_blit"/> + <reg32 offset="0x9109" name="VPC_PC_CNTL" type="a6xx_pc_cntl" variants="A7XX" usage="rp_blit"/> + <reg32 offset="0x910a" name="VPC_GS_PARAM_0" type="a6xx_gs_param_0" variants="A7XX" usage="rp_blit"/> + <reg32 offset="0x910b" name="VPC_STEREO_RENDERING_VIEWMASK" type="hex" low="0" high="15" variants="A7XX" usage="rp_blit"/> + <reg32 offset="0x910c" name="VPC_STEREO_RENDERING_CNTL" type="a6xx_stereo_rendering_cntl" variants="A7XX" usage="rp_blit"/> <enum name="a6xx_varying_interp_mode"> <value value="0" name="INTERP_SMOOTH"/> @@ -2007,11 +2110,11 @@ by a particular renderpass/blit. </enum> <!-- 0x9109-0x91ff invalid --> - <array offset="0x9200" name="VPC_VARYING_INTERP_MODE" stride="1" length="8" usage="rp_blit"> + <array offset="0x9200" name="VPC_VARYING_INTERP_MODE" stride="1" length="8" variants="A6XX-A7XX" usage="rp_blit"> <doc>Packed array of a6xx_varying_interp_mode</doc> <reg32 offset="0x0" name="MODE"/> </array> - <array offset="0x9208" name="VPC_VARYING_REPLACE_MODE_0" stride="1" length="8" usage="rp_blit"> + <array offset="0x9208" name="VPC_VARYING_REPLACE_MODE" stride="1" length="8" variants="A6XX-A7XX" usage="rp_blit"> <doc>Packed array of a6xx_varying_ps_repl_mode</doc> <reg32 offset="0x0" name="MODE"/> </array> @@ -2020,12 +2123,12 @@ by a particular renderpass/blit. <reg32 offset="0x9210" name="VPC_UNKNOWN_9210" low="0" high="31" variants="A6XX" usage="cmd"/> <reg32 offset="0x9211" name="VPC_UNKNOWN_9211" low="0" high="31" variants="A6XX" usage="cmd"/> - <array offset="0x9212" name="VPC_VARYING_LM_TRANSFER_CNTL_0" stride="1" length="4" usage="rp_blit"> + <array offset="0x9212" name="VPC_VARYING_LM_TRANSFER_CNTL" stride="1" length="4" variants="A6XX-A7XX" usage="rp_blit"> <!-- one bit per varying component: --> <reg32 offset="0" name="DISABLE"/> </array> - <reg32 offset="0x9216" name="VPC_SO_MAPPING_WPTR" usage="rp_blit"> + <bitset name="a6xx_vpc_so_mapping_wptr" inline="yes"> <!-- Choose which DWORD to write to. There is an array of (4 * 64) DWORD's, dumped in the devcoredump at @@ -2052,20 +2155,25 @@ by a particular renderpass/blit. <bitfield name="ADDR" low="0" high="7" type="hex"/> <!-- clear all A_EN and B_EN bits for all DWORD's --> <bitfield name="RESET" pos="16" type="boolean"/> - </reg32> - <!-- special register, write multiple times to load SO program (not readable) --> - <reg32 offset="0x9217" name="VPC_SO_MAPPING_PORT" usage="rp_blit"> + </bitset> + + <reg32 offset="0x9216" name="VPC_SO_MAPPING_WPTR" type="a6xx_vpc_so_mapping_wptr" variants="A6XX-A7XX" usage="rp_blit"/> + + <bitset name="a6xx_vpc_so_mapping_port" inline="yes"> <bitfield name="A_BUF" low="0" high="1" type="uint"/> <bitfield name="A_OFF" low="2" high="10" shr="2" type="uint"/> <bitfield name="A_EN" pos="11" type="boolean"/> <bitfield name="B_BUF" low="12" high="13" type="uint"/> <bitfield name="B_OFF" low="14" high="22" shr="2" type="uint"/> <bitfield name="B_EN" pos="23" type="boolean"/> - </reg32> + </bitset> + + <!-- special register, write multiple times to load SO program (not readable) --> + <reg32 offset="0x9217" name="VPC_SO_MAPPING_PORT" type="a6xx_vpc_so_mapping_port" variants="A6XX-A7XX" usage="rp_blit"/> - <reg64 offset="0x9218" name="VPC_SO_QUERY_BASE" type="waddress" align="32" usage="cmd"/> + <reg64 offset="0x9218" name="VPC_SO_QUERY_BASE" type="waddress" align="32" variants="A6XX-A7XX" usage="cmd"/> - <array offset="0x921a" name="VPC_SO" stride="7" length="4" usage="cmd"> + <array offset="0x921a" name="VPC_SO" stride="7" length="4" variants="A6XX-A7XX" usage="cmd"> <reg64 offset="0" name="BUFFER_BASE" type="waddress" align="32"/> <reg32 offset="2" name="BUFFER_SIZE" low="2" high="31" shr="2"/> <reg32 offset="3" name="BUFFER_STRIDE" low="0" high="9" shr="2"/> @@ -2073,12 +2181,13 @@ by a particular renderpass/blit. <reg64 offset="5" name="FLUSH_BASE" type="waddress" align="32"/> </array> - <reg32 offset="0x9236" name="VPC_REPLACE_MODE_CNTL" usage="cmd"> + <bitset name="a6xx_vpc_replace_mode_cntl" inline="yes"> <bitfield name="INVERT" pos="0" type="boolean"/> - </reg32> - <!-- 0x9237-0x92ff invalid --> - <!-- always 0x0 ? --> - <reg32 offset="0x9300" name="VPC_UNKNOWN_9300" low="0" high="2" usage="cmd"/> + </bitset> + + <reg32 offset="0x9236" name="VPC_REPLACE_MODE_CNTL" type="a6xx_vpc_replace_mode_cntl" variants="A6XX-A7XX" usage="cmd"/> + + <reg32 offset="0x9300" name="VPC_ROTATION_CNTL" low="0" high="2" variants="A6XX-A7XX" usage="cmd"/> <bitset name="a6xx_vpc_xs_cntl" inline="yes"> <doc> @@ -2097,11 +2206,12 @@ by a particular renderpass/blit. </doc> </bitfield> </bitset> - <reg32 offset="0x9301" name="VPC_VS_CNTL" type="a6xx_vpc_xs_cntl" usage="rp_blit"/> - <reg32 offset="0x9302" name="VPC_GS_CNTL" type="a6xx_vpc_xs_cntl" usage="rp_blit"/> - <reg32 offset="0x9303" name="VPC_DS_CNTL" type="a6xx_vpc_xs_cntl" usage="rp_blit"/> - <reg32 offset="0x9304" name="VPC_PS_CNTL" usage="rp_blit"> + <reg32 offset="0x9301" name="VPC_VS_CNTL" type="a6xx_vpc_xs_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x9302" name="VPC_GS_CNTL" type="a6xx_vpc_xs_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x9303" name="VPC_DS_CNTL" type="a6xx_vpc_xs_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + + <bitset name="a6xx_vpc_ps_cntl" inline="yes"> <bitfield name="NUMNONPOSVAR" low="0" high="7" type="uint"/> <!-- for fixed-function (i.e. no GS) gl_PrimitiveID in FS --> <bitfield name="PRIMIDLOC" low="8" high="15" type="uint"/> @@ -2118,9 +2228,11 @@ by a particular renderpass/blit. ViewID through the VS. </doc> </bitfield> - </reg32> + </bitset> + + <reg32 offset="0x9304" name="VPC_PS_CNTL" type="a6xx_vpc_ps_cntl" variants="A6XX-A7XX" usage="rp_blit"/> - <reg32 offset="0x9305" name="VPC_SO_CNTL" usage="rp_blit"> + <bitset name="a6xx_vpc_so_cntl" inline="yes"> <!-- It's offset by 1, and 0 means "disabled" --> @@ -2129,22 +2241,28 @@ by a particular renderpass/blit. <bitfield name="BUF2_STREAM" low="6" high="8" type="uint"/> <bitfield name="BUF3_STREAM" low="9" high="11" type="uint"/> <bitfield name="STREAM_ENABLE" low="15" high="18" type="hex"/> - </reg32> - <reg32 offset="0x9306" name="VPC_SO_OVERRIDE" usage="rp_blit"> + </bitset> + + <reg32 offset="0x9305" name="VPC_SO_CNTL" type="a6xx_vpc_so_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + + <bitset name="a6xx_so_override" inline="yes"> <bitfield name="DISABLE" pos="0" type="boolean"/> - </reg32> - <reg32 offset="0x9307" name="VPC_PS_RAST_CNTL" variants="A6XX-" usage="rp_blit"> <!-- A702 + A7xx --> - <bitfield name="MODE" low="0" high="1" type="a6xx_polygon_mode"/> - </reg32> - <reg32 offset="0x9308" name="VPC_ATTR_BUF_GMEM_SIZE" variants="A7XX-" usage="rp_blit"> - <bitfield name="SIZE_GMEM" low="0" high="31"/> - </reg32> - <reg32 offset="0x9309" name="VPC_ATTR_BUF_GMEM_BASE" variants="A7XX-" usage="rp_blit"> - <bitfield name="BASE_GMEM" low="0" high="31"/> - </reg32> - <reg32 offset="0x9b09" name="PC_ATTR_BUF_GMEM_SIZE" variants="A7XX-" usage="rp_blit"> - <bitfield name="SIZE_GMEM" low="0" high="31"/> - </reg32> + </bitset> + + <reg32 offset="0x9306" name="VPC_SO_OVERRIDE" type="a6xx_so_override" variants="A6XX-A7XX" usage="rp_blit"/> + + <reg32 offset="0x9807" name="PC_DGEN_SO_OVERRIDE" type="a6xx_so_override" variants="A7XX" usage="rp_blit"/> + + <reg32 offset="0x9307" name="VPC_PS_RAST_CNTL" type="a6xx_rast_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + + <reg32 offset="0x9308" name="VPC_ATTR_BUF_GMEM_SIZE" variants="A7XX" type="uint" usage="rp_blit"/> + <reg32 offset="0x9309" name="VPC_ATTR_BUF_GMEM_BASE" variants="A7XX" type="uint" usage="rp_blit"/> + + <reg32 offset="0x9b09" name="PC_ATTR_BUF_GMEM_SIZE" variants="A7XX" type="uint" usage="rp_blit"/> + + <reg32 offset="0x930a" name="VPC_UNKNOWN_930A" variants="A7XX"/> + + <reg32 offset="0x960a" name="VPC_FLATSHADE_MODE_CNTL" variants="A7XX"/> <!-- 0x9307-0x95ff invalid --> @@ -2159,52 +2277,62 @@ by a particular renderpass/blit. <!-- TODO: regs from 0x9624-0x963a --> <!-- 0x963b-0x97ff invalid --> - <reg32 offset="0x9800" name="PC_HS_PARAM_0" low="0" high="5" type="uint" usage="rp_blit"/> + <reg32 offset="0x9800" name="PC_HS_PARAM_0" low="0" high="5" type="uint" variants="A6XX-A7XX" usage="rp_blit"/> - <!-- always 0x0 ? --> - <reg32 offset="0x9801" name="PC_HS_PARAM_1" usage="rp_blit"> + <bitset name="a6xx_pc_hs_param_1" inline="yes"> <bitfield name="SIZE" low="0" high="10" type="uint"/> <bitfield name="UNK13" pos="13"/> - </reg32> + </bitset> - <reg32 offset="0x9802" name="PC_DS_PARAM" usage="rp_blit"> + <reg32 offset="0x9801" name="PC_HS_PARAM_1" type="a6xx_pc_hs_param_1" variants="A6XX-A7XX" usage="rp_blit"/> + + <bitset name="a6xx_pc_ds_param" inline="yes"> <bitfield name="SPACING" low="0" high="1" type="a6xx_tess_spacing"/> <bitfield name="OUTPUT" low="2" high="3" type="a6xx_tess_output"/> - </reg32> + </bitset> + + <reg32 offset="0x9802" name="PC_DS_PARAM" type="a6xx_pc_ds_param" variants="A6XX-A7XX" usage="rp_blit"/> - <reg32 offset="0x9803" name="PC_RESTART_INDEX" low="0" high="31" type="uint" usage="rp_blit"/> - <reg32 offset="0x9804" name="PC_MODE_CNTL" low="0" high="7" usage="rp_blit"/> + <reg32 offset="0x9803" name="PC_RESTART_INDEX" low="0" high="31" type="uint" variants="A6XX-A7XX" usage="rp_blit"/> + + <reg32 offset="0x9804" name="PC_MODE_CNTL" low="0" high="7" variants="A6XX-A7XX" usage="rp_blit"/> <reg32 offset="0x9805" name="PC_POWER_CNTL" low="0" high="2" usage="rp_blit"/> - <reg32 offset="0x9806" name="PC_PS_CNTL" usage="rp_blit"> + <bitset name="a6xx_pc_ps_cntl" inline="yes"> <bitfield name="PRIMITIVEIDEN" pos="0" type="boolean"/> - </reg32> + </bitset> - <!-- New in a6xx gen3+ --> - <reg32 offset="0x9808" name="PC_DGEN_SO_CNTL" usage="rp_blit"> + <reg32 offset="0x9806" name="PC_PS_CNTL" type="a6xx_pc_ps_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + + <bitset name="a6xx_pc_dgen_so_cntl" inline="yes"> <bitfield name="STREAM_ENABLE" low="15" high="18" type="hex"/> - </reg32> + </bitset> - <reg32 offset="0x980a" name="PC_DGEN_SU_CONSERVATIVE_RAS_CNTL"> + <!-- New in a6xx gen3+ --> + <reg32 offset="0x9808" name="PC_DGEN_SO_CNTL" type="a6xx_pc_dgen_so_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + + <bitset name="a6xx_pc_dgen_su_conservative_ras_cntl" inline="yes"> <bitfield name="CONSERVATIVERASEN" pos="0" type="boolean"/> - </reg32> - <!-- 0x980b-0x983f invalid --> + </bitset> + + <reg32 offset="0x980a" name="PC_DGEN_SU_CONSERVATIVE_RAS_CNTL" type="a6xx_pc_dgen_su_conservative_ras_cntl" variants="A6XX-A7XX"/> <!-- 0x9840 - 0x9842 are not readable --> - <reg32 offset="0x9840" name="PC_DRAW_INITIATOR"> + <bitset name="a6xx_draw_initiator" inline="yes"> <bitfield name="STATE_ID" low="0" high="7"/> - </reg32> + </bitset> - <reg32 offset="0x9841" name="PC_KERNEL_INITIATOR"> - <bitfield name="STATE_ID" low="0" high="7"/> - </reg32> + <reg32 offset="0x9840" name="PC_DRAW_INITIATOR" type="a6xx_draw_initiator" variants="A6XX-A7XX"/> + <reg32 offset="0x9841" name="PC_KERNEL_INITIATOR" type="a6xx_draw_initiator" variants="A6XX-A7XX"/> - <reg32 offset="0x9842" name="PC_EVENT_INITIATOR"> + <bitset name="a6xx_event_initiator" inline="yes"> <!-- I think only the low bit is actually used? --> <bitfield name="STATE_ID" low="16" high="23"/> <bitfield name="EVENT" low="0" high="6" type="vgt_event_type"/> - </reg32> + </bitset> + + <reg32 offset="0x9842" name="PC_EVENT_INITIATOR" type="a6xx_event_initiator" variants="A6XX-A7XX"/> <!-- 0x9880 written in a lot of places by SQE, same value gets written @@ -2215,45 +2343,21 @@ by a particular renderpass/blit. <!-- 0x9843-0x997f invalid --> - <reg32 offset="0x9981" name="PC_DGEN_RAST_CNTL" variants="A6XX" usage="rp_blit"> - <bitfield name="MODE" low="0" high="1" type="a6xx_polygon_mode"/> - </reg32> - <reg32 offset="0x9809" name="PC_DGEN_RAST_CNTL" variants="A7XX-" usage="rp_blit"> - <bitfield name="MODE" low="0" high="1" type="a6xx_polygon_mode"/> - </reg32> - - <reg32 offset="0x9980" name="VPC_RAST_STREAM_CNTL" variants="A6XX" usage="rp_blit"> - <!-- which stream to send to GRAS --> - <bitfield name="STREAM" low="0" high="1" type="uint"/> - <!-- discard primitives before rasterization --> - <bitfield name="DISCARD" pos="2" type="boolean"/> - </reg32> - <!-- VPC_RAST_STREAM_CNTL --> - <reg32 offset="0x9107" name="VPC_RAST_STREAM_CNTL" variants="A7XX-" usage="rp_blit"> - <!-- which stream to send to GRAS --> - <bitfield name="STREAM" low="0" high="1" type="uint"/> - <!-- discard primitives before rasterization --> - <bitfield name="DISCARD" pos="2" type="boolean"/> - </reg32> - <reg32 offset="0x9317" name="VPC_RAST_STREAM_CNTL_V2" variants="A7XX-" usage="rp_blit"> - <!-- which stream to send to GRAS --> - <bitfield name="STREAM" low="0" high="1" type="uint"/> - <!-- discard primitives before rasterization --> - <bitfield name="DISCARD" pos="2" type="boolean"/> - </reg32> + <reg32 offset="0x9981" name="PC_DGEN_RAST_CNTL" type="a6xx_rast_cntl" variants="A6XX" usage="rp_blit"/> + <reg32 offset="0x9809" name="PC_DGEN_RAST_CNTL" type="a6xx_rast_cntl" variants="A7XX" usage="rp_blit"/> <!-- Both are a750+. Probably needed to correctly overlap execution of several draws. --> - <reg32 offset="0x9885" name="PC_HS_BUFFER_SIZE" variants="A7XX-" usage="cmd"/> + <reg32 offset="0x9885" name="PC_HS_BUFFER_SIZE" variants="A7XX" usage="cmd"/> <!-- Blob adds a bit more space {0x10, 0x20, 0x30, 0x40} bytes, but the meaning of this additional space is not known. --> - <reg32 offset="0x9886" name="PC_TF_BUFFER_SIZE" variants="A7XX-" usage="cmd"/> + <reg32 offset="0x9886" name="PC_TF_BUFFER_SIZE" variants="A7XX" usage="cmd"/> <!-- 0x9982-0x9aff invalid --> - <reg32 offset="0x9b00" name="PC_CNTL" type="a6xx_pc_cntl" usage="rp_blit"/> + <reg32 offset="0x9b00" name="PC_CNTL" type="a6xx_pc_cntl" variants="A6XX-A7XX" usage="rp_blit"/> <bitset name="a6xx_pc_xs_cntl" inline="yes"> <doc> @@ -2266,18 +2370,18 @@ by a particular renderpass/blit. <bitfield name="LAYER" pos="9" type="boolean"/> <bitfield name="VIEW" pos="10" type="boolean"/> <!-- note: PC_VS_CNTL doesn't have the PRIMITIVE_ID bit --> + <!-- since HS can't output anything, only PRIMITIVE_ID is valid --> <bitfield name="PRIMITIVE_ID" pos="11" type="boolean"/> <bitfield name="CLIP_MASK" low="16" high="23" type="uint"/> <bitfield name="SHADINGRATE" pos="24" type="boolean" variants="A7XX-"/> </bitset> - <reg32 offset="0x9b01" name="PC_VS_CNTL" type="a6xx_pc_xs_cntl" usage="rp_blit"/> - <reg32 offset="0x9b02" name="PC_GS_CNTL" type="a6xx_pc_xs_cntl" usage="rp_blit"/> - <!-- since HS can't output anything, only PRIMITIVE_ID is valid --> - <reg32 offset="0x9b03" name="PC_HS_CNTL" type="a6xx_pc_xs_cntl" usage="rp_blit"/> - <reg32 offset="0x9b04" name="PC_DS_CNTL" type="a6xx_pc_xs_cntl" usage="rp_blit"/> + <reg32 offset="0x9b01" name="PC_VS_CNTL" type="a6xx_pc_xs_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x9b02" name="PC_GS_CNTL" type="a6xx_pc_xs_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x9b03" name="PC_HS_CNTL" type="a6xx_pc_xs_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x9b04" name="PC_DS_CNTL" type="a6xx_pc_xs_cntl" variants="A6XX-A7XX" usage="rp_blit"/> - <reg32 offset="0x9b05" name="PC_GS_PARAM_0" type="a6xx_gs_param_0" usage="rp_blit"/> + <reg32 offset="0x9b05" name="PC_GS_PARAM_0" type="a6xx_gs_param_0" variants="A6XX-A7XX" usage="rp_blit"/> <reg32 offset="0x9b06" name="PC_PRIMITIVE_CNTL_6" variants="A6XX" usage="rp_blit"> <doc> @@ -2286,9 +2390,9 @@ by a particular renderpass/blit. <bitfield name="STRIDE_IN_VPC" low="0" high="10" type="uint"/> </reg32> - <reg32 offset="0x9b07" name="PC_STEREO_RENDERING_CNTL" type="a6xx_stereo_rendering_cntl" usage="rp_blit"/> + <reg32 offset="0x9b07" name="PC_STEREO_RENDERING_CNTL" type="a6xx_stereo_rendering_cntl" variants="A6XX-A7XX" usage="rp_blit"/> <!-- mask of enabled views, doesn't exist on A630 --> - <reg32 offset="0x9b08" name="PC_STEREO_RENDERING_VIEWMASK" type="hex" low="0" high="15" usage="rp_blit"/> + <reg32 offset="0x9b08" name="PC_STEREO_RENDERING_VIEWMASK" type="hex" low="0" high="15" variants="A6XX-A7XX" usage="rp_blit"/> <!-- 0x9b09-0x9bff invalid --> <reg32 offset="0x9c00" name="PC_2D_EVENT_CMD"> <!-- special register (but note first 8 bits can be written/read) --> @@ -2299,34 +2403,39 @@ by a particular renderpass/blit. <!-- TODO: 0x9e00-0xa000 range incomplete --> <reg32 offset="0x9e00" name="PC_DBG_ECO_CNTL"/> <reg32 offset="0x9e01" name="PC_ADDR_MODE_CNTL" type="a5xx_address_mode"/> - <reg64 offset="0x9e04" name="PC_DMA_BASE"/> - <reg32 offset="0x9e06" name="PC_DMA_OFFSET" type="uint"/> - <reg32 offset="0x9e07" name="PC_DMA_SIZE" type="uint"/> + <reg64 offset="0x9e04" name="PC_DMA_BASE" type="address" variants="A6XX-A7XX"/> + <reg32 offset="0x9e06" name="PC_DMA_OFFSET" type="uint" variants="A6XX-A7XX"/> + <reg32 offset="0x9e07" name="PC_DMA_SIZE" type="uint" variants="A6XX-A7XX"/> + <reg64 offset="0x9e08" name="PC_TESS_BASE" variants="A6XX" type="waddress" align="32" usage="cmd"/> - <reg64 offset="0x9810" name="PC_TESS_BASE" variants="A7XX-" type="waddress" align="32" usage="cmd"/> + <reg64 offset="0x9810" name="PC_TESS_BASE" variants="A7XX" type="waddress" align="32" usage="cmd"/> - <reg32 offset="0x9e0b" name="PC_DRAWCALL_CNTL" type="vgt_draw_initiator_a4xx"> + <reg32 offset="0x9e0b" name="PC_DRAWCALL_CNTL" type="vgt_draw_initiator_a4xx" variants="A6XX-A7XX"> <doc> Possibly not really "initiating" the draw but the layout is similar to VGT_DRAW_INITIATOR on older gens </doc> </reg32> - <reg32 offset="0x9e0c" name="PC_DRAWCALL_INSTANCE_NUM" type="uint"/> - <reg32 offset="0x9e0d" name="PC_DRAWCALL_SIZE" type="uint"/> + <reg32 offset="0x9e0c" name="PC_DRAWCALL_INSTANCE_NUM" type="uint" variants="A6XX-A7XX"/> + <reg32 offset="0x9e0d" name="PC_DRAWCALL_SIZE" type="uint" variants="A6XX-A7XX"/> <!-- These match the contents of CP_SET_BIN_DATA (not written directly) --> - <reg32 offset="0x9e11" name="PC_VIS_STREAM_CNTL"> + <bitset name="a6xx_pc_vis_stream_cntl" inline="yes"> <bitfield name="UNK0" low="0" high="15"/> <bitfield name="VSC_SIZE" low="16" high="21" type="uint"/> <bitfield name="VSC_N" low="22" high="26" type="uint"/> - </reg32> - <reg64 offset="0x9e12" name="PC_PVIS_STREAM_BIN_BASE" type="waddress" align="32"/> - <reg64 offset="0x9e14" name="PC_DVIS_STREAM_BIN_BASE" type="waddress" align="32"/> + </bitset> + + <reg32 offset="0x9e11" name="PC_VIS_STREAM_CNTL" type="a6xx_pc_vis_stream_cntl" variants="A6XX-A7XX"/> + <reg64 offset="0x9e12" name="PC_PVIS_STREAM_BIN_BASE" type="waddress" align="32" variants="A6XX-A7XX"/> + <reg64 offset="0x9e14" name="PC_DVIS_STREAM_BIN_BASE" type="waddress" align="32" variants="A6XX-A7XX"/> - <reg32 offset="0x9e1c" name="PC_DRAWCALL_CNTL_OVERRIDE"> + <bitset name="a6xx_pc_drawcall_cntl_override" inline="yes"> <doc>Written by CP_SET_VISIBILITY_OVERRIDE handler</doc> <bitfield name="OVERRIDE" pos="0" type="boolean"/> - </reg32> + </bitset> + + <reg32 offset="0x9e1c" name="PC_DRAWCALL_CNTL_OVERRIDE" type="a6xx_pc_drawcall_cntl_override" variants="A6XX-A7XX"/> <reg32 offset="0x9e24" name="PC_UNKNOWN_9E24" variants="A7XX-" usage="cmd"/> @@ -2932,7 +3041,7 @@ by a particular renderpass/blit. <reg32 offset="0xa9b3" name="SP_CS_PROGRAM_COUNTER_OFFSET" type="uint" usage="cmd"/> <reg64 offset="0xa9b4" name="SP_CS_BASE" type="address" align="32" usage="cmd"/> <reg32 offset="0xa9b6" name="SP_CS_PVT_MEM_PARAM" type="a6xx_sp_xs_pvt_mem_param" usage="cmd"/> - <reg64 offset="0xa9b7" name="SP_CS_PVT_MEM_BASE" align="32" usage="cmd"/> + <reg64 offset="0xa9b7" name="SP_CS_PVT_MEM_BASE" type="waddress" align="32" usage="cmd"/> <reg32 offset="0xa9b9" name="SP_CS_PVT_MEM_SIZE" type="a6xx_sp_xs_pvt_mem_size" usage="cmd"/> <reg32 offset="0xa9ba" name="SP_CS_TSIZE" low="0" high="7" type="uint" usage="cmd"/> <reg32 offset="0xa9bb" name="SP_CS_CONFIG" type="a6xx_sp_xs_config" usage="cmd"/> @@ -3017,7 +3126,7 @@ by a particular renderpass/blit. UAV state for compute shader: --> <reg64 offset="0xa9f2" name="SP_CS_UAV_BASE" type="address" align="16" variants="A6XX"/> - <reg64 offset="0xa9f8" name="SP_CS_UAV_BASE" type="address" align="16" variants="A7XX"/> + <reg64 offset="0xa9f8" name="SP_CS_UAV_BASE" type="address" align="16" variants="A7XX-"/> <reg32 offset="0xaa00" name="SP_CS_USIZE" low="0" high="6" type="uint"/> <!-- Correlated with avgs/uvgs usage in FS --> @@ -3100,14 +3209,19 @@ by a particular renderpass/blit. instructions VS/HS/DS/GS/FS. See SP_CS_UAV_BASE_* for compute shaders. --> <reg64 offset="0xab1a" name="SP_GFX_UAV_BASE" type="address" align="16" usage="cmd"/> - <reg32 offset="0xab20" name="SP_GFX_USIZE" low="0" high="6" type="uint" usage="cmd"/> + <reg32 offset="0xab20" name="SP_GFX_USIZE" low="0" high="6" type="uint" variants="A6XX-A7XX" usage="cmd"/> - <reg32 offset="0xab22" name="SP_UNKNOWN_AB22" variants="A7XX-" usage="cmd"/> + <reg32 offset="0xab22" name="SP_UNKNOWN_AB22" variants="A7XX" usage="cmd"/> + + <enum name="a6xx_sp_a2d_output_ifmt_type"> + <value name="OUTPUT_IFMT_2D_FLOAT" value="0"/> + <value name="OUTPUT_IFMT_2D_SINT" value="1"/> + <value name="OUTPUT_IFMT_2D_UINT" value="2"/> + </enum> <bitset name="a6xx_sp_a2d_output_info" inline="yes"> - <bitfield name="NORM" pos="0" type="boolean"/> - <bitfield name="SINT" pos="1" type="boolean"/> - <bitfield name="UINT" pos="2" type="boolean"/> + <bitfield name="HALF_PRECISION" pos="0" type="boolean"/> + <bitfield name="IFMT_TYPE" low="1" high="2" type="a6xx_sp_a2d_output_ifmt_type"/> <!-- looks like HW only cares about the base type of this format, which matches the ifmt? --> <bitfield name="COLOR_FORMAT" low="3" high="10" type="a6xx_format"/> @@ -3152,7 +3266,7 @@ by a particular renderpass/blit. <reg32 offset="0xae6b" name="SP_UNKNOWN_AE6B" variants="A7XX-" usage="cmd"/> <reg32 offset="0xae6c" name="SP_HLSQ_DBG_ECO_CNTL" variants="A7XX-" usage="cmd"/> <reg32 offset="0xae6d" name="SP_READ_SEL" variants="A7XX-"> - <bitfield name="LOCATION" low="18" high="19" type="a7xx_state_location"/> + <bitfield name="LOCATION" low="18" high="20" type="a7xx_state_location"/> <bitfield name="PIPE" low="16" high="17" type="a7xx_pipe"/> <bitfield name="STATETYPE" low="8" high="15" type="a7xx_statetype_id"/> <bitfield name="USPTP" low="4" high="7"/> @@ -3188,7 +3302,7 @@ by a particular renderpass/blit. <!-- looks to work in the same way as a5xx: --> <reg64 offset="0xb302" name="TPL1_GFX_BORDER_COLOR_BASE" type="address" align="128" usage="cmd"/> - <reg32 offset="0xb304" name="TPL1_MSAA_SAMPLE_POS_CNTL" type="a6xx_msaa_sample_pos_cntl" usage="rp_blit"/> + <reg32 offset="0xb304" name="TPL1_MSAA_SAMPLE_POS_CNTL" type="a6xx_msaa_sample_pos_cntl" variants="A6XX-A7XX" usage="rp_blit"/> <reg32 offset="0xb305" name="TPL1_PROGRAMMABLE_MSAA_POS_0" type="a6xx_programmable_msaa_pos" usage="rp_blit"/> <reg32 offset="0xb306" name="TPL1_PROGRAMMABLE_MSAA_POS_1" type="a6xx_programmable_msaa_pos" usage="rp_blit"/> <reg32 offset="0xb307" name="TPL1_WINDOW_OFFSET" type="a6xx_reg_xy" usage="rp_blit"/> @@ -3228,12 +3342,12 @@ by a particular renderpass/blit. </reg32> <reg32 offset="0xb2c0" name="TPL1_A2D_SRC_TEXTURE_INFO" type="a6xx_a2d_src_texture_info" variants="A7XX-" usage="rp_blit"/> - <reg32 offset="0xb2c1" name="TPL1_A2D_SRC_TEXTURE_SIZE" variants="A7XX"> + <reg32 offset="0xb2c1" name="TPL1_A2D_SRC_TEXTURE_SIZE" variants="A7XX-"> <bitfield name="WIDTH" low="0" high="14" type="uint"/> <bitfield name="HEIGHT" low="15" high="29" type="uint"/> </reg32> <reg64 offset="0xb2c2" name="TPL1_A2D_SRC_TEXTURE_BASE" type="address" align="16" variants="A7XX-" usage="rp_blit"/> - <reg32 offset="0xb2c4" name="TPL1_A2D_SRC_TEXTURE_PITCH" variants="A7XX"> + <reg32 offset="0xb2c4" name="TPL1_A2D_SRC_TEXTURE_PITCH" variants="A7XX-"> <!-- Bits from 3..9 must be zero unless 'TPL1_A2D_BLT_CNTL::TYPE' is A6XX_TEX_IMG_BUFFER, which allows for lower alignment. @@ -3266,13 +3380,13 @@ by a particular renderpass/blit. <reg32 offset="0xb2ce" name="SP_PS_UNKNOWN_B4CE" low="0" high="31" variants="A7XX"/> <reg32 offset="0xb2cf" name="SP_PS_UNKNOWN_B4CF" low="0" high="30" variants="A7XX"/> <reg32 offset="0xb2d0" name="SP_PS_UNKNOWN_B4D0" low="0" high="29" variants="A7XX"/> - <reg32 offset="0xb2d1" name="TPL1_A2D_WINDOW_OFFSET" type="a6xx_reg_xy" variants="A7XX"/> + <reg32 offset="0xb2d1" name="TPL1_A2D_WINDOW_OFFSET" type="a6xx_reg_xy" variants="A7XX-"/> <reg32 offset="0xb2d2" name="TPL1_A2D_BLT_CNTL" variants="A7XX-" usage="rp_blit"> <bitfield name="RAW_COPY" pos="0" type="boolean"/> <bitfield name="START_OFFSET_TEXELS" low="16" high="21"/> <bitfield name="TYPE" low="29" high="31" type="a6xx_tex_type"/> </reg32> - <reg32 offset="0xab21" name="SP_WINDOW_OFFSET" type="a6xx_reg_xy" variants="A7XX-" usage="rp_blit"/> + <reg32 offset="0xab21" name="SP_WINDOW_OFFSET" type="a6xx_reg_xy" variants="A7XX" usage="rp_blit"/> <!-- always 0x100000 or 0x1000000? --> <reg32 offset="0xb600" name="TPL1_DBG_ECO_CNTL" low="0" high="25" usage="cmd"/> @@ -3292,17 +3406,13 @@ by a particular renderpass/blit. </reg32> <reg32 offset="0xb605" name="TPL1_UNKNOWN_B605" low="0" high="7" type="uint" variants="A6XX" usage="cmd"/> <!-- always 0x0 or 0x44 ? --> - <reg32 offset="0xb608" name="TPL1_BICUBIC_WEIGHTS_TABLE_0" low="0" high="29" variants="A6XX"/> - <reg32 offset="0xb609" name="TPL1_BICUBIC_WEIGHTS_TABLE_1" low="0" high="29" variants="A6XX"/> - <reg32 offset="0xb60a" name="TPL1_BICUBIC_WEIGHTS_TABLE_2" low="0" high="29" variants="A6XX"/> - <reg32 offset="0xb60b" name="TPL1_BICUBIC_WEIGHTS_TABLE_3" low="0" high="29" variants="A6XX"/> - <reg32 offset="0xb60c" name="TPL1_BICUBIC_WEIGHTS_TABLE_4" low="0" high="29" variants="A6XX"/> + <array offset="0xb608" name="TPL1_BICUBIC_WEIGHTS_TABLE" stride="1" length="5" variants="A6XX"> + <reg32 offset="0" name="REG" low="0" high="29"/> + </array> - <reg32 offset="0xb608" name="TPL1_BICUBIC_WEIGHTS_TABLE_0" low="0" high="29" variants="A7XX" usage="cmd"/> - <reg32 offset="0xb609" name="TPL1_BICUBIC_WEIGHTS_TABLE_1" low="0" high="29" variants="A7XX" usage="cmd"/> - <reg32 offset="0xb60a" name="TPL1_BICUBIC_WEIGHTS_TABLE_2" low="0" high="29" variants="A7XX" usage="cmd"/> - <reg32 offset="0xb60b" name="TPL1_BICUBIC_WEIGHTS_TABLE_3" low="0" high="29" variants="A7XX" usage="cmd"/> - <reg32 offset="0xb60c" name="TPL1_BICUBIC_WEIGHTS_TABLE_4" low="0" high="29" variants="A7XX" usage="cmd"/> + <array offset="0xb608" name="TPL1_BICUBIC_WEIGHTS_TABLE" stride="1" length="5" variants="A7XX"> + <reg32 offset="0" name="REG" low="0" high="29" usage="cmd"/> + </array> <array offset="0xb610" name="TPL1_PERFCTR_TP_SEL" stride="1" length="12" variants="A6XX"/> <array offset="0xb610" name="TPL1_PERFCTR_TP_SEL" stride="1" length="18" variants="A7XX"/> @@ -3634,7 +3744,7 @@ by a particular renderpass/blit. <reg32 offset="0xbb10" name="SP_PS_CONST_CONFIG" type="a6xx_xs_const_config" variants="A6XX" usage="rp_blit"/> <reg32 offset="0xab03" name="SP_PS_CONST_CONFIG" type="a6xx_xs_const_config" variants="A7XX-" usage="rp_blit"/> - <array offset="0xab40" name="SP_SHARED_CONSTANT_GFX_0" stride="1" length="64" variants="A7XX-"/> + <array offset="0xab40" name="SP_SHARED_CONSTANT_GFX" stride="1" length="64" variants="A7XX"/> <reg32 offset="0xbb11" name="HLSQ_SHARED_CONSTS" variants="A6XX" usage="cmd"> <doc> @@ -3796,6 +3906,14 @@ by a particular renderpass/blit. <reg32 offset="0x0030" name="CFG_DBGBUS_TRACE_BUF2"/> </domain> +<domain name="A7XX_CX_DBGC" width="32" varset="chip"> + <!-- Bitfields shifted, but otherwise the same: --> + <reg32 offset="0x0000" name="CFG_DBGBUS_SEL_A" variants="A7XX-"> + <bitfield high="7" low="0" name="PING_INDEX"/> + <bitfield high="24" low="16" name="PING_BLK_SEL"/> + </reg32> +</domain> + <domain name="A6XX_CX_MISC" width="32" prefix="variant" varset="chip"> <reg32 offset="0x0001" name="SYSTEM_CACHE_CNTL_0"/> <reg32 offset="0x0002" name="SYSTEM_CACHE_CNTL_1"/> diff --git a/drivers/gpu/drm/msm/registers/adreno/a6xx_descriptors.xml b/drivers/gpu/drm/msm/registers/adreno/a6xx_descriptors.xml index 307d43dda8a2..56cfaff614a4 100644 --- a/drivers/gpu/drm/msm/registers/adreno/a6xx_descriptors.xml +++ b/drivers/gpu/drm/msm/registers/adreno/a6xx_descriptors.xml @@ -9,38 +9,6 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <domain name="A6XX_TEX_SAMP" width="32"> <doc>Texture sampler dwords</doc> - <enum name="a6xx_tex_filter"> <!-- same as a4xx? --> - <value name="A6XX_TEX_NEAREST" value="0"/> - <value name="A6XX_TEX_LINEAR" value="1"/> - <value name="A6XX_TEX_ANISO" value="2"/> - <value name="A6XX_TEX_CUBIC" value="3"/> <!-- a650 only --> - </enum> - <enum name="a6xx_tex_clamp"> <!-- same as a4xx? --> - <value name="A6XX_TEX_REPEAT" value="0"/> - <value name="A6XX_TEX_CLAMP_TO_EDGE" value="1"/> - <value name="A6XX_TEX_MIRROR_REPEAT" value="2"/> - <value name="A6XX_TEX_CLAMP_TO_BORDER" value="3"/> - <value name="A6XX_TEX_MIRROR_CLAMP" value="4"/> - </enum> - <enum name="a6xx_tex_aniso"> <!-- same as a4xx? --> - <value name="A6XX_TEX_ANISO_1" value="0"/> - <value name="A6XX_TEX_ANISO_2" value="1"/> - <value name="A6XX_TEX_ANISO_4" value="2"/> - <value name="A6XX_TEX_ANISO_8" value="3"/> - <value name="A6XX_TEX_ANISO_16" value="4"/> - </enum> - <enum name="a6xx_reduction_mode"> - <value name="A6XX_REDUCTION_MODE_AVERAGE" value="0"/> - <value name="A6XX_REDUCTION_MODE_MIN" value="1"/> - <value name="A6XX_REDUCTION_MODE_MAX" value="2"/> - </enum> - <enum name="a6xx_fast_border_color"> - <!-- R B G A --> - <value name="A6XX_BORDER_COLOR_0_0_0_0" value="0"/> - <value name="A6XX_BORDER_COLOR_0_0_0_1" value="1"/> - <value name="A6XX_BORDER_COLOR_1_1_1_0" value="2"/> - <value name="A6XX_BORDER_COLOR_1_1_1_1" value="3"/> - </enum> <reg32 offset="0" name="0"> <bitfield name="MIPFILTER_LINEAR_NEAR" pos="0" type="boolean"/> @@ -79,14 +47,6 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <domain name="A6XX_TEX_CONST" width="32" varset="chip"> <doc>Texture constant dwords</doc> - <enum name="a6xx_tex_swiz"> <!-- same as a4xx? --> - <value name="A6XX_TEX_X" value="0"/> - <value name="A6XX_TEX_Y" value="1"/> - <value name="A6XX_TEX_Z" value="2"/> - <value name="A6XX_TEX_W" value="3"/> - <value name="A6XX_TEX_ZERO" value="4"/> - <value name="A6XX_TEX_ONE" value="5"/> - </enum> <reg32 offset="0" name="0"> <bitfield name="TILE_MODE" low="0" high="1" type="a6xx_tile_mode"/> <bitfield name="SRGB" pos="2" type="boolean"/> diff --git a/drivers/gpu/drm/msm/registers/adreno/a6xx_enums.xml b/drivers/gpu/drm/msm/registers/adreno/a6xx_enums.xml index 665539b098c6..4e42f055b85f 100644 --- a/drivers/gpu/drm/msm/registers/adreno/a6xx_enums.xml +++ b/drivers/gpu/drm/msm/registers/adreno/a6xx_enums.xml @@ -320,14 +320,14 @@ to upconvert to 32b float internally? 16b float: 3 --> <enum name="a6xx_2d_ifmt"> - <value value="0x10" name="R2D_UNORM8"/> <value value="0x7" name="R2D_INT32"/> <value value="0x6" name="R2D_INT16"/> <value value="0x5" name="R2D_INT8"/> <value value="0x4" name="R2D_FLOAT32"/> <value value="0x3" name="R2D_FLOAT16"/> + <value value="0x2" name="R2D_SNORM8"/> <value value="0x1" name="R2D_UNORM8_SRGB"/> - <value value="0x0" name="R2D_RAW"/> + <value value="0x0" name="R2D_UNORM8"/> </enum> <enum name="a6xx_tex_type"> @@ -380,4 +380,50 @@ to upconvert to 32b float internally? <value value="0x3" name="TESS_CCW_TRIS"/> </enum> +<enum name="a6xx_tex_filter"> <!-- same as a4xx? --> + <value name="A6XX_TEX_NEAREST" value="0"/> + <value name="A6XX_TEX_LINEAR" value="1"/> + <value name="A6XX_TEX_ANISO" value="2"/> + <value name="A6XX_TEX_CUBIC" value="3"/> <!-- a650 only --> +</enum> + +<enum name="a6xx_tex_clamp"> <!-- same as a4xx? --> + <value name="A6XX_TEX_REPEAT" value="0"/> + <value name="A6XX_TEX_CLAMP_TO_EDGE" value="1"/> + <value name="A6XX_TEX_MIRROR_REPEAT" value="2"/> + <value name="A6XX_TEX_CLAMP_TO_BORDER" value="3"/> + <value name="A6XX_TEX_MIRROR_CLAMP" value="4"/> +</enum> + +<enum name="a6xx_tex_aniso"> <!-- same as a4xx? --> + <value name="A6XX_TEX_ANISO_1" value="0"/> + <value name="A6XX_TEX_ANISO_2" value="1"/> + <value name="A6XX_TEX_ANISO_4" value="2"/> + <value name="A6XX_TEX_ANISO_8" value="3"/> + <value name="A6XX_TEX_ANISO_16" value="4"/> +</enum> + +<enum name="a6xx_reduction_mode"> + <value name="A6XX_REDUCTION_MODE_AVERAGE" value="0"/> + <value name="A6XX_REDUCTION_MODE_MIN" value="1"/> + <value name="A6XX_REDUCTION_MODE_MAX" value="2"/> +</enum> + +<enum name="a6xx_fast_border_color"> + <!-- R B G A --> + <value name="A6XX_BORDER_COLOR_0_0_0_0" value="0"/> + <value name="A6XX_BORDER_COLOR_0_0_0_1" value="1"/> + <value name="A6XX_BORDER_COLOR_1_1_1_0" value="2"/> + <value name="A6XX_BORDER_COLOR_1_1_1_1" value="3"/> +</enum> + +<enum name="a6xx_tex_swiz"> <!-- same as a4xx? --> + <value name="A6XX_TEX_X" value="0"/> + <value name="A6XX_TEX_Y" value="1"/> + <value name="A6XX_TEX_Z" value="2"/> + <value name="A6XX_TEX_W" value="3"/> + <value name="A6XX_TEX_ZERO" value="4"/> + <value name="A6XX_TEX_ONE" value="5"/> +</enum> + </database> diff --git a/drivers/gpu/drm/msm/registers/adreno/a6xx_gmu.xml b/drivers/gpu/drm/msm/registers/adreno/a6xx_gmu.xml index 3d2cc339b8f1..b15a242d974d 100644 --- a/drivers/gpu/drm/msm/registers/adreno/a6xx_gmu.xml +++ b/drivers/gpu/drm/msm/registers/adreno/a6xx_gmu.xml @@ -99,6 +99,10 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <bitfield name="GX_HM_GDSC_POWER_OFF" pos="6" type="boolean"/> <bitfield name="GX_HM_CLK_OFF" pos="7" type="boolean"/> </reg32> + <reg32 offset="0x50d0" name="GMU_SPTPRAC_PWR_CLK_STATUS" variants="A7XX"> + <bitfield name="GX_HM_GDSC_POWER_OFF" pos="0" type="boolean"/> + <bitfield name="GX_HM_CLK_OFF" pos="1" type="boolean"/> + </reg32> <reg32 offset="0x50e4" name="GMU_GPU_NAP_CTRL"> <bitfield name="HW_NAP_ENABLE" pos="0"/> <bitfield name="SID" low="4" high="8"/> @@ -127,6 +131,7 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <reg32 offset="0x5088" name="GMU_ALWAYS_ON_COUNTER_L"/> <reg32 offset="0x5089" name="GMU_ALWAYS_ON_COUNTER_H"/> <reg32 offset="0x50c3" name="GMU_GMU_PWR_COL_KEEPALIVE"/> + <reg32 offset="0x50c4" name="GMU_PWR_COL_PREEMPT_KEEPALIVE"/> <reg32 offset="0x5180" name="GMU_HFI_CTRL_STATUS"/> <reg32 offset="0x5181" name="GMU_HFI_VERSION_INFO"/> <reg32 offset="0x5182" name="GMU_HFI_SFR_ADDR"/> @@ -228,6 +233,12 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <reg32 offset="0x03ee" name="RSCC_TCS1_DRV0_STATUS"/> <reg32 offset="0x0496" name="RSCC_TCS2_DRV0_STATUS"/> <reg32 offset="0x053e" name="RSCC_TCS3_DRV0_STATUS"/> + <reg32 offset="0x05e6" name="RSCC_TCS4_DRV0_STATUS" variants="A7XX"/> + <reg32 offset="0x068e" name="RSCC_TCS5_DRV0_STATUS" variants="A7XX"/> + <reg32 offset="0x0736" name="RSCC_TCS6_DRV0_STATUS" variants="A7XX"/> + <reg32 offset="0x07de" name="RSCC_TCS7_DRV0_STATUS" variants="A7XX"/> + <reg32 offset="0x0886" name="RSCC_TCS8_DRV0_STATUS" variants="A7XX"/> + <reg32 offset="0x092e" name="RSCC_TCS9_DRV0_STATUS" variants="A7XX"/> </domain> </database> diff --git a/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml b/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml index 7abc08635495..0e10e1c6d263 100644 --- a/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml +++ b/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml @@ -120,12 +120,12 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <value name="LRZ_FLUSH" value="38" variants="A5XX-"/> <value name="BLIT_OP_FILL_2D" value="39" variants="A5XX-"/> <value name="BLIT_OP_COPY_2D" value="40" variants="A5XX-A6XX"/> - <value name="UNK_40" value="40" variants="A7XX"/> + <value name="LRZ_CACHE_INVALIDATE" value="40" variants="A7XX"/> <value name="LRZ_Q_CACHE_INVALIDATE" value="41" variants="A7XX"/> <value name="BLIT_OP_SCALE_2D" value="42" variants="A5XX-"/> <value name="CONTEXT_DONE_2D" value="43" variants="A5XX-"/> - <value name="UNK_2C" value="44" variants="A5XX-"/> - <value name="UNK_2D" value="45" variants="A5XX-"/> + <value name="VSC_BINNING_START" value="44" variants="A5XX-"/> + <value name="VSC_BINNING_END" value="45" variants="A5XX-"/> <!-- a6xx events --> <doc> @@ -523,7 +523,7 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <!-- Seems to set the mode flags which control which CP_SET_DRAW_STATE packets are executed, based on their ENABLE_MASK values - + CP_SET_MODE w/ payload of 0x1 seems to cause CP_SET_DRAW_STATE packets w/ ENABLE_MASK & 0x6 to execute immediately --> @@ -640,8 +640,7 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <value name="CP_BV_BR_COUNT_OPS" value="0x1b" variants="A7XX-"/> <doc> Clears, adds to local, or adds to global timestamp </doc> <value name="CP_MODIFY_TIMESTAMP" value="0x1c" variants="A7XX-"/> - <!-- similar to CP_CONTEXT_REG_BUNCH, but discards first two dwords?? --> - <value name="CP_CONTEXT_REG_BUNCH2" value="0x5d" variants="A7XX-"/> + <value name="CP_NON_CONTEXT_REG_BUNCH" value="0x5d" variants="A7XX-"/> <doc> Write to a scratch memory that is read by CP_REG_TEST with SOURCE_SCRATCH_MEM set. It's not the same scratch as scratch registers. @@ -918,12 +917,6 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) </reg32> <stripe varset="chip" variants="A5XX-"> - <reg32 offset="4" name="4"> - <bitfield name="INDX_BASE_LO" low="0" high="31"/> - </reg32> - <reg32 offset="5" name="5"> - <bitfield name="INDX_BASE_HI" low="0" high="31"/> - </reg32> <reg64 offset="4" name="INDX_BASE" type="address"/> <reg32 offset="6" name="6"> <!-- max # of elements in index buffer --> @@ -1099,8 +1092,10 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) <bitfield name="BINNING" pos="20" varset="chip" variants="A6XX-" type="boolean"/> <bitfield name="GMEM" pos="21" varset="chip" variants="A6XX-" type="boolean"/> <bitfield name="SYSMEM" pos="22" varset="chip" variants="A6XX-" type="boolean"/> - <bitfield name="GROUP_ID" low="24" high="28" type="uint"/> + <!-- high bit is 28 until a750: --> + <bitfield name="GROUP_ID" low="24" high="29" type="uint"/> </reg32> + <reg64 offset="1" name="ADDR" type="address"/> <reg32 offset="1" name="1"> <bitfield name="ADDR_LO" low="0" high="31" type="hex"/> </reg32> @@ -1166,26 +1161,11 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) </reg32> <stripe varset="a7xx_abs_mask_mode" variants="NO_ABS_MASK"> <!-- BIN_DATA_ADDR -> VSC_PIPE[p].DATA_ADDRESS --> - <reg32 offset="1" name="1"> - <bitfield name="BIN_DATA_ADDR_LO" low="0" high="31" type="hex"/> - </reg32> - <reg32 offset="2" name="2"> - <bitfield name="BIN_DATA_ADDR_HI" low="0" high="31" type="hex"/> - </reg32> + <reg64 offset="1" name="BIN_DATA_ADDR" type="address"/> <!-- BIN_SIZE_ADDRESS -> VSC_SIZE_ADDRESS + (p * 4)--> - <reg32 offset="3" name="3"> - <bitfield name="BIN_SIZE_ADDRESS_LO" low="0" high="31"/> - </reg32> - <reg32 offset="4" name="4"> - <bitfield name="BIN_SIZE_ADDRESS_HI" low="0" high="31"/> - </reg32> + <reg64 offset="3" name="BIN_SIZE_ADDR" type="address"/> <!-- new on a6xx, where BIN_DATA_ADDR is the DRAW_STRM: --> - <reg32 offset="5" name="5"> - <bitfield name="BIN_PRIM_STRM_LO" low="0" high="31"/> - </reg32> - <reg32 offset="6" name="6"> - <bitfield name="BIN_PRIM_STRM_HI" low="0" high="31"/> - </reg32> + <reg64 offset="5" name="BIN_PRIM_STRM" type="address"/> <!-- a7xx adds a few more addresses to the end of the pkt --> @@ -1195,26 +1175,11 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) <stripe varset="a7xx_abs_mask_mode" variants="ABS_MASK"> <reg32 offset="1" name="ABS_MASK"/> <!-- BIN_DATA_ADDR -> VSC_PIPE[p].DATA_ADDRESS --> - <reg32 offset="2" name="2"> - <bitfield name="BIN_DATA_ADDR_LO" low="0" high="31" type="hex"/> - </reg32> - <reg32 offset="3" name="3"> - <bitfield name="BIN_DATA_ADDR_HI" low="0" high="31" type="hex"/> - </reg32> + <reg64 offset="2" name="BIN_DATA_ADDR" type="address"/> <!-- BIN_SIZE_ADDRESS -> VSC_SIZE_ADDRESS + (p * 4)--> - <reg32 offset="4" name="4"> - <bitfield name="BIN_SIZE_ADDRESS_LO" low="0" high="31"/> - </reg32> - <reg32 offset="5" name="5"> - <bitfield name="BIN_SIZE_ADDRESS_HI" low="0" high="31"/> - </reg32> + <reg64 offset="4" name="BIN_SIZE_ADDR" type="address"/> <!-- new on a6xx, where BIN_DATA_ADDR is the DRAW_STRM: --> - <reg32 offset="6" name="6"> - <bitfield name="BIN_PRIM_STRM_LO" low="0" high="31"/> - </reg32> - <reg32 offset="7" name="7"> - <bitfield name="BIN_PRIM_STRM_HI" low="0" high="31"/> - </reg32> + <reg64 offset="6" name="BIN_PRIM_STRM" type="address"/> <!-- a7xx adds a few more addresses to the end of the pkt --> @@ -1300,7 +1265,7 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) </reg32> </domain> -<domain name="CP_REG_TO_MEM" width="32"> +<domain name="CP_REG_TO_MEM" width="32" prefix="chip"> <reg32 offset="0" name="0"> <bitfield name="REG" low="0" high="17" type="hex"/> <!-- number of registers/dwords copied is max(CNT, 1). --> @@ -1308,12 +1273,12 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) <bitfield name="64B" pos="30" type="boolean"/> <bitfield name="ACCUMULATE" pos="31" type="boolean"/> </reg32> - <reg32 offset="1" name="1"> - <bitfield name="DEST" low="0" high="31"/> - </reg32> - <reg32 offset="2" name="2" varset="chip" variants="A5XX-"> - <bitfield name="DEST_HI" low="0" high="31"/> - </reg32> + <stripe varset="chip" variants="A2XX-A4XX"> + <reg32 offset="1" name="DEST" type="address"/> + </stripe> + <stripe varset="chip" variants="A5XX-"> + <reg64 offset="1" name="DEST" type="address"/> + </stripe> </domain> <domain name="CP_REG_TO_MEM_OFFSET_REG" width="32"> @@ -1329,12 +1294,7 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) <bitfield name="64B" pos="30" type="boolean"/> <bitfield name="ACCUMULATE" pos="31" type="boolean"/> </reg32> - <reg32 offset="1" name="1"> - <bitfield name="DEST" low="0" high="31"/> - </reg32> - <reg32 offset="2" name="2" varset="chip" variants="A5XX-"> - <bitfield name="DEST_HI" low="0" high="31"/> - </reg32> + <reg64 offset="1" name="DEST" type="waddress"/> <reg32 offset="3" name="3"> <bitfield name="OFFSET0" low="0" high="17" type="hex"/> <bitfield name="OFFSET0_SCRATCH" pos="19" type="boolean"/> @@ -1354,18 +1314,8 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) <bitfield name="64B" pos="30" type="boolean"/> <bitfield name="ACCUMULATE" pos="31" type="boolean"/> </reg32> - <reg32 offset="1" name="1"> - <bitfield name="DEST" low="0" high="31"/> - </reg32> - <reg32 offset="2" name="2" varset="chip" variants="A5XX-"> - <bitfield name="DEST_HI" low="0" high="31"/> - </reg32> - <reg32 offset="3" name="3"> - <bitfield name="OFFSET_LO" low="0" high="31" type="hex"/> - </reg32> - <reg32 offset="4" name="4"> - <bitfield name="OFFSET_HI" low="0" high="31" type="hex"/> - </reg32> + <reg64 offset="1" name="DEST" type="waddress"/> + <reg64 offset="3" name="OFFSET" type="waddress"/> </domain> <domain name="CP_MEM_TO_REG" width="32"> @@ -1378,12 +1328,12 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) <!-- does the same thing as CP_MEM_TO_MEM::UNK31 --> <bitfield name="UNK31" pos="31" type="boolean"/> </reg32> - <reg32 offset="1" name="1"> - <bitfield name="SRC" low="0" high="31"/> - </reg32> - <reg32 offset="2" name="2" varset="chip" variants="A5XX-"> - <bitfield name="SRC_HI" low="0" high="31"/> - </reg32> + <stripe varset="chip" variants="A2XX-A4XX"> + <reg32 offset="1" name="SRC" type="address"/> + </stripe> + <stripe varset="chip" variants="A5XX-"> + <reg64 offset="1" name="SRC" type="address"/> + </stripe> </domain> <domain name="CP_MEM_TO_MEM" width="32"> @@ -1403,6 +1353,10 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) <!-- some other kind of wait --> <bitfield name="UNK31" pos="31" type="boolean"/> </reg32> + <reg64 offset="1" name="DST" type="waddress"/> + <reg64 offset="3" name="SRC_A" type="address"/> + <reg64 offset="5" name="SRC_B" type="address"/> + <reg64 offset="7" name="SRC_C" type="address"/> <!-- followed by sequence of addresses.. the first is the destination and the rest are N src addresses which are @@ -1461,12 +1415,12 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) </domain> <domain name="CP_MEM_WRITE" width="32"> - <reg32 offset="0" name="0"> - <bitfield name="ADDR_LO" low="0" high="31"/> - </reg32> - <reg32 offset="1" name="1"> - <bitfield name="ADDR_HI" low="0" high="31"/> - </reg32> + <stripe varset="chip" variants="A2XX-A4XX"> + <reg32 offset="0" name="ADDR" type="address"/> + </stripe> + <stripe varset="chip" variants="A5XX-"> + <reg64 offset="0" name="ADDR" type="address"/> + </stripe> <!-- followed by the DWORDs to write --> </domain> @@ -1518,24 +1472,14 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) <bitfield name="POLL" low="4" high="5" type="poll_memory_type"/> <bitfield name="WRITE_MEMORY" pos="8" type="boolean"/> </reg32> - <reg32 offset="1" name="1"> - <bitfield name="POLL_ADDR_LO" low="0" high="31" type="hex"/> - </reg32> - <reg32 offset="2" name="2"> - <bitfield name="POLL_ADDR_HI" low="0" high="31" type="hex"/> - </reg32> + <reg64 offset="1" name="POLL_ADDR" type="address"/> <reg32 offset="3" name="3"> <bitfield name="REF" low="0" high="31"/> </reg32> <reg32 offset="4" name="4"> <bitfield name="MASK" low="0" high="31"/> </reg32> - <reg32 offset="5" name="5"> - <bitfield name="WRITE_ADDR_LO" low="0" high="31" type="hex"/> - </reg32> - <reg32 offset="6" name="6"> - <bitfield name="WRITE_ADDR_HI" low="0" high="31" type="hex"/> - </reg32> + <reg64 offset="5" name="WRITE_ADDR" type="waddress"/> <reg32 offset="7" name="7"> <bitfield name="WRITE_DATA" low="0" high="31"/> </reg32> @@ -1550,12 +1494,7 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) <!-- Reserved for flags, presumably? Unused in FW --> <bitfield name="RESERVED" low="0" high="31" type="hex"/> </reg32> - <reg32 offset="1" name="1"> - <bitfield name="POLL_ADDR_LO" low="0" high="31" type="hex"/> - </reg32> - <reg32 offset="2" name="2"> - <bitfield name="POLL_ADDR_HI" low="0" high="31" type="hex"/> - </reg32> + <reg64 offset="1" name="POLL_ADDR" type="address"/> <reg32 offset="3" name="3"> <bitfield name="REF" low="0" high="31"/> </reg32> @@ -1573,12 +1512,7 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) <bitfield name="POLL" low="4" high="5" type="poll_memory_type"/> <bitfield name="WRITE_MEMORY" pos="8" type="boolean"/> </reg32> - <reg32 offset="1" name="1"> - <bitfield name="POLL_ADDR_LO" low="0" high="31" type="hex"/> - </reg32> - <reg32 offset="2" name="2"> - <bitfield name="POLL_ADDR_HI" low="0" high="31" type="hex"/> - </reg32> + <reg64 offset="1" name="POLL_ADDR" type="address"/> <reg32 offset="3" name="3"> <bitfield name="REF" low="0" high="31"/> </reg32> @@ -1712,12 +1646,7 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) TODO what is gpuaddr for, seems to be all 0's.. maybe needed for context switch? --> - <reg32 offset="1" name="1"> - <bitfield name="ADDR_0_LO" low="0" high="31"/> - </reg32> - <reg32 offset="2" name="2"> - <bitfield name="ADDR_0_HI" low="0" high="31"/> - </reg32> + <reg64 offset="1" name="ADDR" type="waddress"/> <reg32 offset="3" name="3"> <!-- ??? --> </reg32> @@ -1832,9 +1761,7 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) <reg32 offset="0" name="0"> </reg32> <stripe varset="chip" variants="A4XX"> - <reg32 offset="1" name="1"> - <bitfield name="ADDR" low="0" high="31"/> - </reg32> + <reg32 offset="1" name="ADDR" type="address"/> <reg32 offset="2" name="2"> <!-- localsize is value minus one: --> <bitfield name="LOCALSIZEX" low="2" high="11" type="uint"/> @@ -1843,12 +1770,7 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) </reg32> </stripe> <stripe varset="chip" variants="A5XX-"> - <reg32 offset="1" name="1"> - <bitfield name="ADDR_LO" low="0" high="31"/> - </reg32> - <reg32 offset="2" name="2"> - <bitfield name="ADDR_HI" low="0" high="31"/> - </reg32> + <reg64 offset="1" name="ADDR" type="address"/> <reg32 offset="3" name="3"> <!-- localsize is value minus one: --> <bitfield name="LOCALSIZEX" low="2" high="11" type="uint"/> @@ -2161,12 +2083,7 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) </doc> </value> </enum> - <reg32 offset="0" name="0"> - <bitfield name="ADDR_LO" low="0" high="31"/> - </reg32> - <reg32 offset="1" name="1"> - <bitfield name="ADDR_HI" low="0" high="31"/> - </reg32> + <reg64 offset="0" name="ADDR" type="address"/> <reg32 offset="2" name="2"> <bitfield name="DWORDS" low="0" high="19" type="uint"/> <bitfield name="TYPE" low="20" high="21" type="amble_type"/> diff --git a/drivers/gpu/drm/msm/registers/display/dsi.xml b/drivers/gpu/drm/msm/registers/display/dsi.xml index 501ffc585a9f..c7a7b633d747 100644 --- a/drivers/gpu/drm/msm/registers/display/dsi.xml +++ b/drivers/gpu/drm/msm/registers/display/dsi.xml @@ -159,28 +159,28 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <bitfield name="RGB_SWAP" low="12" high="14" type="dsi_rgb_swap"/> </reg32> <reg32 offset="0x00020" name="ACTIVE_H"> - <bitfield name="START" low="0" high="11" type="uint"/> - <bitfield name="END" low="16" high="27" type="uint"/> + <bitfield name="START" low="0" high="15" type="uint"/> + <bitfield name="END" low="16" high="31" type="uint"/> </reg32> <reg32 offset="0x00024" name="ACTIVE_V"> - <bitfield name="START" low="0" high="11" type="uint"/> - <bitfield name="END" low="16" high="27" type="uint"/> + <bitfield name="START" low="0" high="15" type="uint"/> + <bitfield name="END" low="16" high="31" type="uint"/> </reg32> <reg32 offset="0x00028" name="TOTAL"> - <bitfield name="H_TOTAL" low="0" high="11" type="uint"/> - <bitfield name="V_TOTAL" low="16" high="27" type="uint"/> + <bitfield name="H_TOTAL" low="0" high="15" type="uint"/> + <bitfield name="V_TOTAL" low="16" high="31" type="uint"/> </reg32> <reg32 offset="0x0002c" name="ACTIVE_HSYNC"> - <bitfield name="START" low="0" high="11" type="uint"/> - <bitfield name="END" low="16" high="27" type="uint"/> + <bitfield name="START" low="0" high="15" type="uint"/> + <bitfield name="END" low="16" high="31" type="uint"/> </reg32> <reg32 offset="0x00030" name="ACTIVE_VSYNC_HPOS"> - <bitfield name="START" low="0" high="11" type="uint"/> - <bitfield name="END" low="16" high="27" type="uint"/> + <bitfield name="START" low="0" high="15" type="uint"/> + <bitfield name="END" low="16" high="31" type="uint"/> </reg32> <reg32 offset="0x00034" name="ACTIVE_VSYNC_VPOS"> - <bitfield name="START" low="0" high="11" type="uint"/> - <bitfield name="END" low="16" high="27" type="uint"/> + <bitfield name="START" low="0" high="15" type="uint"/> + <bitfield name="END" low="16" high="31" type="uint"/> </reg32> <reg32 offset="0x00038" name="CMD_DMA_CTRL"> @@ -209,8 +209,8 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <bitfield name="WORD_COUNT" low="16" high="31" type="uint"/> </reg32> <reg32 offset="0x00058" name="CMD_MDP_STREAM0_TOTAL"> - <bitfield name="H_TOTAL" low="0" high="11" type="uint"/> - <bitfield name="V_TOTAL" low="16" high="27" type="uint"/> + <bitfield name="H_TOTAL" low="0" high="15" type="uint"/> + <bitfield name="V_TOTAL" low="16" high="31" type="uint"/> </reg32> <reg32 offset="0x0005c" name="CMD_MDP_STREAM1_CTRL"> <bitfield name="DATA_TYPE" low="0" high="5" type="uint"/> diff --git a/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml b/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml index 4e5ac0f25dea..f41516dd0567 100644 --- a/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml +++ b/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml @@ -22,7 +22,16 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <reg32 offset="0x00018" name="GLBL_CTRL"/> <reg32 offset="0x0001c" name="RBUF_CTRL"/> <reg32 offset="0x00020" name="VREG_CTRL_0"/> - <reg32 offset="0x00024" name="CTRL_0"/> + <reg32 offset="0x00024" name="CTRL_0"> + <bitfield name="CLKSL_SHUTDOWNB" pos="7" type="boolean"/> + <bitfield name="DIGTOP_PWRDN_B" pos="6" type="boolean"/> + <bitfield name="PLL_SHUTDOWNB" pos="5" type="boolean"/> + <bitfield name="DLN3_SHUTDOWNB" pos="4" type="boolean"/> + <bitfield name="DLN2_SHUTDOWNB" pos="3" type="boolean"/> + <bitfield name="CLK_SHUTDOWNB" pos="2" type="boolean"/> + <bitfield name="DLN1_SHUTDOWNB" pos="1" type="boolean"/> + <bitfield name="DLN0_SHUTDOWNB" pos="0" type="boolean"/> + </reg32> <reg32 offset="0x00028" name="CTRL_1"/> <reg32 offset="0x0002c" name="CTRL_2"/> <reg32 offset="0x00030" name="CTRL_3"/> diff --git a/drivers/gpu/drm/msm/registers/gen_header.py b/drivers/gpu/drm/msm/registers/gen_header.py index a409404627c7..1d603dadfabd 100644 --- a/drivers/gpu/drm/msm/registers/gen_header.py +++ b/drivers/gpu/drm/msm/registers/gen_header.py @@ -11,7 +11,6 @@ import collections import argparse import time import datetime -import re class Error(Exception): def __init__(self, message): @@ -31,7 +30,7 @@ class Enum(object): def names(self): return [n for (n, value) in self.values] - def dump(self): + def dump(self, is_deprecated): use_hex = False for (name, value) in self.values: if value > 0x1000: @@ -45,7 +44,7 @@ class Enum(object): print("\t%s = %d," % (name, value)) print("};\n") - def dump_pack_struct(self): + def dump_pack_struct(self, is_deprecated): pass class Field(object): @@ -70,11 +69,11 @@ class Field(object): raise parser.error("booleans should be 1 bit fields") elif self.type == "float" and not (high - low == 31 or high - low == 15): raise parser.error("floats should be 16 or 32 bit fields") - elif not self.type in builtin_types and not self.type in parser.enums: + elif self.type not in builtin_types and self.type not in parser.enums: raise parser.error("unknown type '%s'" % self.type) def ctype(self, var_name): - if self.type == None: + if self.type is None: type = "uint32_t" val = var_name elif self.type == "boolean": @@ -124,7 +123,7 @@ def field_name(reg, f): name = f.name.lower() else: # We hit this path when a reg is defined with no bitset fields, ie. - # <reg32 offset="0x88db" name="RB_BLIT_DST_ARRAY_PITCH" low="0" high="28" shr="6" type="uint"/> + # <reg32 offset="0x88db" name="RB_RESOLVE_SYSTEM_BUFFER_ARRAY_PITCH" low="0" high="28" shr="6" type="uint"/> name = reg.name.lower() if (name in [ "double", "float", "int" ]) or not (name[0].isalpha()): @@ -146,10 +145,23 @@ def indices_strides(indices): "%s(i%d)" % (offset, idx) for (idx, (ctype, stride, offset)) in enumerate(indices)]) +def is_number(str): + try: + int(str) + return True + except ValueError: + return False + +def sanitize_variant(variant): + if variant and "-" in variant: + return variant[:variant.index("-")] + return variant + class Bitset(object): def __init__(self, name, template): self.name = name self.inline = False + self.reg = None if template: self.fields = template.fields[:] else: @@ -175,11 +187,7 @@ class Bitset(object): print("#endif\n") print(" return (struct fd_reg_pair) {") - if reg.array: - print(" .reg = REG_%s(__i)," % reg.full_name) - else: - print(" .reg = REG_%s," % reg.full_name) - + print(" .reg = (uint32_t)%s," % reg.reg_offset()) print(" .value =") for f in self.fields: if f.type in [ "address", "waddress" ]: @@ -204,7 +212,7 @@ class Bitset(object): print(" };") - def dump_pack_struct(self, reg=None): + def dump_pack_struct(self, is_deprecated, reg=None): if not reg: return @@ -229,12 +237,15 @@ class Bitset(object): tab_to(" uint32_t", "dword;") print("};\n") + depcrstr = "" + if is_deprecated: + depcrstr = " FD_DEPRECATED" if reg.array: - print("static inline struct fd_reg_pair\npack_%s(uint32_t __i, struct %s fields)\n{" % - (prefix, prefix)) + print("static inline%s struct fd_reg_pair\npack_%s(uint32_t __i, struct %s fields)\n{" % + (depcrstr, prefix, prefix)) else: - print("static inline struct fd_reg_pair\npack_%s(struct %s fields)\n{" % - (prefix, prefix)) + print("static inline%s struct fd_reg_pair\npack_%s(struct %s fields)\n{" % + (depcrstr, prefix, prefix)) self.dump_regpair_builder(reg) @@ -253,18 +264,23 @@ class Bitset(object): (prefix, prefix, prefix, skip)) - def dump(self, prefix=None): - if prefix == None: + def dump(self, is_deprecated, prefix=None): + if prefix is None: prefix = self.name + if self.reg and self.reg.bit_size == 64: + print("static inline uint32_t %s_LO(uint32_t val)\n{" % prefix) + print("\treturn val;\n}") + print("static inline uint32_t %s_HI(uint32_t val)\n{" % prefix) + print("\treturn val;\n}") for f in self.fields: if f.name: name = prefix + "_" + f.name else: name = prefix - if not f.name and f.low == 0 and f.shr == 0 and not f.type in ["float", "fixed", "ufixed"]: + if not f.name and f.low == 0 and f.shr == 0 and f.type not in ["float", "fixed", "ufixed"]: pass - elif f.type == "boolean" or (f.type == None and f.low == f.high): + elif f.type == "boolean" or (f.type is None and f.low == f.high): tab_to("#define %s" % name, "0x%08x" % (1 << f.low)) else: tab_to("#define %s__MASK" % name, "0x%08x" % mask(f.low, f.high)) @@ -286,6 +302,7 @@ class Array(object): self.domain = domain self.variant = variant self.parent = parent + self.children = [] if self.parent: self.name = self.parent.name + "_" + self.local_name else: @@ -337,12 +354,15 @@ class Array(object): offset += self.parent.total_offset() return offset - def dump(self): + def dump(self, is_deprecated): + depcrstr = "" + if is_deprecated: + depcrstr = " FD_DEPRECATED" proto = indices_varlist(self.indices()) strides = indices_strides(self.indices()) array_offset = self.total_offset() if self.fixed_offsets: - print("static inline uint32_t __offset_%s(%s idx)" % (self.local_name, self.index_ctype())) + print("static inline%s uint32_t __offset_%s(%s idx)" % (depcrstr, self.local_name, self.index_ctype())) print("{\n\tswitch (idx) {") if self.index_type: for val, offset in zip(self.index_type.names(), self.offsets): @@ -357,7 +377,7 @@ class Array(object): else: tab_to("#define REG_%s_%s(%s)" % (self.domain, self.name, proto), "(0x%08x + %s )\n" % (array_offset, strides)) - def dump_pack_struct(self): + def dump_pack_struct(self, is_deprecated): pass def dump_regpair_builder(self): @@ -373,6 +393,7 @@ class Reg(object): self.bit_size = bit_size if array: self.name = array.name + "_" + self.name + array.children.append(self) self.full_name = self.domain + "_" + self.name if "stride" in attrs: self.stride = int(attrs["stride"], 0) @@ -397,25 +418,34 @@ class Reg(object): else: return self.offset - def dump(self): + def reg_offset(self): + if self.array: + offset = self.array.offset + self.offset + return "(0x%08x + 0x%x*__i)" % (offset, self.array.stride) + return "0x%08x" % self.offset + + def dump(self, is_deprecated): + depcrstr = "" + if is_deprecated: + depcrstr = " FD_DEPRECATED " proto = indices_prototype(self.indices()) strides = indices_strides(self.indices()) offset = self.total_offset() if proto == '': tab_to("#define REG_%s" % self.full_name, "0x%08x" % offset) else: - print("static inline uint32_t REG_%s(%s) { return 0x%08x + %s; }" % (self.full_name, proto, offset, strides)) + print("static inline%s uint32_t REG_%s(%s) { return 0x%08x + %s; }" % (depcrstr, self.full_name, proto, offset, strides)) if self.bitset.inline: - self.bitset.dump(self.full_name) + self.bitset.dump(is_deprecated, self.full_name) + print("") - def dump_pack_struct(self): + def dump_pack_struct(self, is_deprecated): if self.bitset.inline: - self.bitset.dump_pack_struct(self) + self.bitset.dump_pack_struct(is_deprecated, self) def dump_regpair_builder(self): - if self.bitset.inline: - self.bitset.dump_regpair_builder(self) + self.bitset.dump_regpair_builder(self) def dump_py(self): print("\tREG_%s = 0x%08x" % (self.full_name, self.offset)) @@ -444,9 +474,6 @@ class Parser(object): self.variants = set() self.file = [] self.xml_files = [] - self.copyright_year = None - self.authors = [] - self.license = None def error(self, message): parser, filename = self.stack[-1] @@ -454,7 +481,7 @@ class Parser(object): def prefix(self, variant=None): if self.current_prefix_type == "variant" and variant: - return variant + return sanitize_variant(variant) elif self.current_stripe: return self.current_stripe + "_" + self.current_domain elif self.current_prefix: @@ -500,15 +527,22 @@ class Parser(object): return varset def parse_variants(self, attrs): - if not "variants" in attrs: + if "variants" not in attrs: return None - variant = attrs["variants"].split(",")[0] - if "-" in variant: - variant = variant[:variant.index("-")] + variant = attrs["variants"].split(",")[0] varset = self.parse_varset(attrs) - assert varset.has_name(variant) + if "-" in variant: + # if we have a range, validate that both the start and end + # of the range are valid enums: + start = variant[:variant.index("-")] + end = variant[variant.index("-") + 1:] + assert varset.has_name(start) + if end != "": + assert varset.has_name(end) + else: + assert varset.has_name(variant) return variant @@ -572,9 +606,6 @@ class Parser(object): error_str = str(xmlschema.error_log.filter_from_errors()[0]) raise self.error("Schema validation failed for: " + filename + "\n" + error_str) except ImportError as e: - if self.validate: - raise e - print("lxml not found, skipping validation", file=sys.stderr) def do_parse(self, filename): @@ -620,6 +651,7 @@ class Parser(object): self.current_reg = Reg(attrs, self.prefix(variant), self.current_array, bit_size) self.current_reg.bitset = self.current_bitset + self.current_bitset.reg = self.current_reg if len(self.stack) == 1: self.file.append(self.current_reg) @@ -643,7 +675,7 @@ class Parser(object): elif name == "domain": self.current_domain = attrs["name"] if "prefix" in attrs: - self.current_prefix = self.parse_variants(attrs) + self.current_prefix = sanitize_variant(self.parse_variants(attrs)) self.current_prefix_type = attrs["prefix"] else: self.current_prefix = None @@ -651,7 +683,7 @@ class Parser(object): if "varset" in attrs: self.current_varset = self.enums[attrs["varset"]] elif name == "stripe": - self.current_stripe = self.parse_variants(attrs) + self.current_stripe = sanitize_variant(self.parse_variants(attrs)) elif name == "enum": self.current_enum_value = 0 self.current_enum = Enum(attrs["name"]) @@ -686,10 +718,6 @@ class Parser(object): self.parse_field(attrs["name"], attrs) elif name == "database": self.do_validate(attrs["xsi:schemaLocation"]) - elif name == "copyright": - self.copyright_year = attrs["year"] - elif name == "author": - self.authors.append(attrs["name"] + " <" + attrs["email"] + "> " + attrs["name"]) def end_element(self, name): if name == "domain": @@ -703,11 +731,16 @@ class Parser(object): elif name == "reg32": self.current_reg = None elif name == "array": + # if the array has no Reg children, push an implicit reg32: + if len(self.current_array.children) == 0: + attrs = { + "name": "REG", + "offset": "0", + } + self.parse_reg(attrs, 32) self.current_array = self.current_array.parent elif name == "enum": self.current_enum = None - elif name == "license": - self.license = self.cdata def character_data(self, data): self.cdata += data @@ -720,10 +753,10 @@ class Parser(object): if variants: for variant, vreg in variants.items(): if reg == vreg: - d[(usage, variant)].append(reg) + d[(usage, sanitize_variant(variant))].append(reg) else: for variant in self.variants: - d[(usage, variant)].append(reg) + d[(usage, sanitize_variant(variant))].append(reg) print("#ifdef __cplusplus") @@ -753,6 +786,9 @@ class Parser(object): print("#endif") + def has_variants(self, reg): + return reg.name in self.variant_regs and not is_number(reg.name) and not is_number(reg.name[1:]) + def dump(self): enums = [] bitsets = [] @@ -766,7 +802,7 @@ class Parser(object): regs.append(e) for e in enums + bitsets + regs: - e.dump() + e.dump(self.has_variants(e)) self.dump_reg_usages() @@ -782,8 +818,7 @@ class Parser(object): def dump_reg_variants(self, regname, variants): - # Don't bother for things that only have a single variant: - if len(variants) == 1: + if is_number(regname) or is_number(regname[1:]): return print("#ifdef __cplusplus") print("struct __%s {" % regname) @@ -834,11 +869,20 @@ class Parser(object): xtravar = "__i, " print("__%s(%sstruct __%s fields) {" % (regname, xtra, regname)) for variant in variants.keys(): - print(" if (%s == %s) {" % (varenum.upper(), variant)) + if "-" in variant: + start = variant[:variant.index("-")] + end = variant[variant.index("-") + 1:] + if end != "": + print(" if ((%s >= %s) && (%s <= %s)) {" % (varenum.upper(), start, varenum.upper(), end)) + else: + print(" if (%s >= %s) {" % (varenum.upper(), start)) + else: + print(" if (%s == %s) {" % (varenum.upper(), variant)) reg = variants[variant] reg.dump_regpair_builder() print(" } else") print(" assert(!\"invalid variant\");") + print(" return (struct fd_reg_pair){};") print("}") if bit_size == 64: @@ -851,7 +895,7 @@ class Parser(object): def dump_structs(self): for e in self.file: - e.dump_pack_struct() + e.dump_pack_struct(self.has_variants(e)) for regname in self.variant_regs: self.dump_reg_variants(regname, self.variant_regs[regname]) @@ -868,33 +912,7 @@ def dump_c(args, guard, func): print("#ifndef %s\n#define %s\n" % (guard, guard)) - print("""/* Autogenerated file, DO NOT EDIT manually! - -This file was generated by the rules-ng-ng gen_header.py tool in this git repository: -http://gitlab.freedesktop.org/mesa/mesa/ -git clone https://gitlab.freedesktop.org/mesa/mesa.git - -The rules-ng-ng source files this header was generated from are: -""") - maxlen = 0 - for filepath in p.xml_files: - new_filepath = re.sub("^.+drivers","drivers",filepath) - maxlen = max(maxlen, len(new_filepath)) - for filepath in p.xml_files: - pad = " " * (maxlen - len(new_filepath)) - filesize = str(os.path.getsize(filepath)) - filesize = " " * (7 - len(filesize)) + filesize - filetime = time.ctime(os.path.getmtime(filepath)) - print("- " + new_filepath + pad + " (" + filesize + " bytes, from <stripped>)") - if p.copyright_year: - current_year = str(datetime.date.today().year) - print() - print("Copyright (C) %s-%s by the following authors:" % (p.copyright_year, current_year)) - for author in p.authors: - print("- " + author) - if p.license: - print(p.license) - print("*/") + print("/* Autogenerated file, DO NOT EDIT manually! */") print() print("#ifdef __KERNEL__") @@ -912,9 +930,20 @@ The rules-ng-ng source files this header was generated from are: print("#endif") print() + print("#ifndef FD_NO_DEPRECATED_PACK") + print("#define FD_DEPRECATED __attribute__((deprecated))") + print("#else") + print("#define FD_DEPRECATED") + print("#endif") + print() + func(p) - print("\n#endif /* %s */" % guard) + print() + print("#undef FD_DEPRECATED") + print() + + print("#endif /* %s */" % guard) def dump_c_defines(args): @@ -931,7 +960,7 @@ def dump_py_defines(args): p = Parser() try: - p.parse(args.rnn, args.xml) + p.parse(args.rnn, args.xml, args.validate) except Error as e: print(e, file=sys.stderr) exit(1) diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c index 11d5b923d6e7..e2c55f4b9c5a 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/wndw.c +++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c @@ -795,6 +795,10 @@ static bool nv50_plane_format_mod_supported(struct drm_plane *plane, struct nouveau_drm *drm = nouveau_drm(plane->dev); uint8_t i; + /* All chipsets can display all formats in linear layout */ + if (modifier == DRM_FORMAT_MOD_LINEAR) + return true; + if (drm->client.device.info.chipset < 0xc0) { const struct drm_format_info *info = drm_format_info(format); const uint8_t kind = (modifier >> 12) & 0xff; diff --git a/drivers/gpu/drm/nouveau/gv100_fence.c b/drivers/gpu/drm/nouveau/gv100_fence.c index cccdeca72002..317e516c4ec7 100644 --- a/drivers/gpu/drm/nouveau/gv100_fence.c +++ b/drivers/gpu/drm/nouveau/gv100_fence.c @@ -18,7 +18,7 @@ gv100_fence_emit32(struct nouveau_channel *chan, u64 virtual, u32 sequence) struct nvif_push *push = &chan->chan.push; int ret; - ret = PUSH_WAIT(push, 8); + ret = PUSH_WAIT(push, 13); if (ret) return ret; @@ -32,6 +32,11 @@ gv100_fence_emit32(struct nouveau_channel *chan, u64 virtual, u32 sequence) NVDEF(NVC36F, SEM_EXECUTE, PAYLOAD_SIZE, 32BIT) | NVDEF(NVC36F, SEM_EXECUTE, RELEASE_TIMESTAMP, DIS)); + PUSH_MTHD(push, NVC36F, MEM_OP_A, 0, + MEM_OP_B, 0, + MEM_OP_C, NVDEF(NVC36F, MEM_OP_C, MEMBAR_TYPE, SYS_MEMBAR), + MEM_OP_D, NVDEF(NVC36F, MEM_OP_D, OPERATION, MEMBAR)); + PUSH_MTHD(push, NVC36F, NON_STALL_INTERRUPT, 0); PUSH_KICK(push); diff --git a/drivers/gpu/drm/nouveau/include/nvhw/class/clc36f.h b/drivers/gpu/drm/nouveau/include/nvhw/class/clc36f.h index 8735dda4c8a7..338f74b9f501 100644 --- a/drivers/gpu/drm/nouveau/include/nvhw/class/clc36f.h +++ b/drivers/gpu/drm/nouveau/include/nvhw/class/clc36f.h @@ -7,6 +7,91 @@ #define NVC36F_NON_STALL_INTERRUPT (0x00000020) #define NVC36F_NON_STALL_INTERRUPT_HANDLE 31:0 +// NOTE - MEM_OP_A and MEM_OP_B have been replaced in gp100 with methods for +// specifying the page address for a targeted TLB invalidate and the uTLB for +// a targeted REPLAY_CANCEL for UVM. +// The previous MEM_OP_A/B functionality is in MEM_OP_C/D, with slightly +// rearranged fields. +#define NVC36F_MEM_OP_A (0x00000028) +#define NVC36F_MEM_OP_A_TLB_INVALIDATE_CANCEL_TARGET_CLIENT_UNIT_ID 5:0 // only relevant for REPLAY_CANCEL_TARGETED +#define NVC36F_MEM_OP_A_TLB_INVALIDATE_INVALIDATION_SIZE 5:0 // Used to specify size of invalidate, used for invalidates which are not of the REPLAY_CANCEL_TARGETED type +#define NVC36F_MEM_OP_A_TLB_INVALIDATE_CANCEL_TARGET_GPC_ID 10:6 // only relevant for REPLAY_CANCEL_TARGETED +#define NVC36F_MEM_OP_A_TLB_INVALIDATE_CANCEL_MMU_ENGINE_ID 6:0 // only relevant for REPLAY_CANCEL_VA_GLOBAL +#define NVC36F_MEM_OP_A_TLB_INVALIDATE_SYSMEMBAR 11:11 +#define NVC36F_MEM_OP_A_TLB_INVALIDATE_SYSMEMBAR_EN 0x00000001 +#define NVC36F_MEM_OP_A_TLB_INVALIDATE_SYSMEMBAR_DIS 0x00000000 +#define NVC36F_MEM_OP_A_TLB_INVALIDATE_TARGET_ADDR_LO 31:12 +#define NVC36F_MEM_OP_B (0x0000002c) +#define NVC36F_MEM_OP_B_TLB_INVALIDATE_TARGET_ADDR_HI 31:0 +#define NVC36F_MEM_OP_C (0x00000030) +#define NVC36F_MEM_OP_C_MEMBAR_TYPE 2:0 +#define NVC36F_MEM_OP_C_MEMBAR_TYPE_SYS_MEMBAR 0x00000000 +#define NVC36F_MEM_OP_C_MEMBAR_TYPE_MEMBAR 0x00000001 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB 0:0 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB_ONE 0x00000000 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB_ALL 0x00000001 // Probably nonsensical for MMU_TLB_INVALIDATE_TARGETED +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_GPC 1:1 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_GPC_ENABLE 0x00000000 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_GPC_DISABLE 0x00000001 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_REPLAY 4:2 // only relevant if GPC ENABLE +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_REPLAY_NONE 0x00000000 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_REPLAY_START 0x00000001 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_REPLAY_START_ACK_ALL 0x00000002 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_REPLAY_CANCEL_TARGETED 0x00000003 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_REPLAY_CANCEL_GLOBAL 0x00000004 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_REPLAY_CANCEL_VA_GLOBAL 0x00000005 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACK_TYPE 6:5 // only relevant if GPC ENABLE +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACK_TYPE_NONE 0x00000000 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACK_TYPE_GLOBALLY 0x00000001 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACK_TYPE_INTRANODE 0x00000002 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE 9:7 //only relevant for REPLAY_CANCEL_VA_GLOBAL +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_READ 0 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_WRITE 1 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_ATOMIC_STRONG 2 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_RSVRVD 3 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_ATOMIC_WEAK 4 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_ATOMIC_ALL 5 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_WRITE_AND_ATOMIC 6 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_ALL 7 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL 9:7 // Invalidate affects this level and all below +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_ALL 0x00000000 // Invalidate tlb caches at all levels of the page table +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_PTE_ONLY 0x00000001 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_UP_TO_PDE0 0x00000002 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_UP_TO_PDE1 0x00000003 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_UP_TO_PDE2 0x00000004 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_UP_TO_PDE3 0x00000005 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_UP_TO_PDE4 0x00000006 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_UP_TO_PDE5 0x00000007 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB_APERTURE 11:10 // only relevant if PDB_ONE +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB_APERTURE_VID_MEM 0x00000000 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB_APERTURE_SYS_MEM_COHERENT 0x00000002 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB_APERTURE_SYS_MEM_NONCOHERENT 0x00000003 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB_ADDR_LO 31:12 // only relevant if PDB_ONE +#define NVC36F_MEM_OP_C_ACCESS_COUNTER_CLR_TARGETED_NOTIFY_TAG 19:0 +// MEM_OP_D MUST be preceded by MEM_OPs A-C. +#define NVC36F_MEM_OP_D (0x00000034) +#define NVC36F_MEM_OP_D_TLB_INVALIDATE_PDB_ADDR_HI 26:0 // only relevant if PDB_ONE +#define NVC36F_MEM_OP_D_OPERATION 31:27 +#define NVC36F_MEM_OP_D_OPERATION_MEMBAR 0x00000005 +#define NVC36F_MEM_OP_D_OPERATION_MMU_TLB_INVALIDATE 0x00000009 +#define NVC36F_MEM_OP_D_OPERATION_MMU_TLB_INVALIDATE_TARGETED 0x0000000a +#define NVC36F_MEM_OP_D_OPERATION_L2_PEERMEM_INVALIDATE 0x0000000d +#define NVC36F_MEM_OP_D_OPERATION_L2_SYSMEM_INVALIDATE 0x0000000e +// CLEAN_LINES is an alias for Tegra/GPU IP usage +#define NVC36F_MEM_OP_B_OPERATION_L2_INVALIDATE_CLEAN_LINES 0x0000000e +#define NVC36F_MEM_OP_D_OPERATION_L2_CLEAN_COMPTAGS 0x0000000f +#define NVC36F_MEM_OP_D_OPERATION_L2_FLUSH_DIRTY 0x00000010 +#define NVC36F_MEM_OP_D_OPERATION_L2_WAIT_FOR_SYS_PENDING_READS 0x00000015 +#define NVC36F_MEM_OP_D_OPERATION_ACCESS_COUNTER_CLR 0x00000016 +#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TYPE 1:0 +#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TYPE_MIMC 0x00000000 +#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TYPE_MOMC 0x00000001 +#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TYPE_ALL 0x00000002 +#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TYPE_TARGETED 0x00000003 +#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TARGETED_TYPE 2:2 +#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TARGETED_TYPE_MIMC 0x00000000 +#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TARGETED_TYPE_MOMC 0x00000001 +#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TARGETED_BANK 6:3 #define NVC36F_SEM_ADDR_LO (0x0000005c) #define NVC36F_SEM_ADDR_LO_OFFSET 31:2 #define NVC36F_SEM_ADDR_HI (0x00000060) diff --git a/drivers/gpu/drm/nouveau/nouveau_exec.c b/drivers/gpu/drm/nouveau/nouveau_exec.c index edbbda78bac9..c4949e815eb3 100644 --- a/drivers/gpu/drm/nouveau/nouveau_exec.c +++ b/drivers/gpu/drm/nouveau/nouveau_exec.c @@ -60,14 +60,14 @@ * virtual address in the GPU's VA space there is no guarantee that the actual * mappings are created in the GPU's MMU. If the given memory is swapped out * at the time the bind operation is executed the kernel will stash the mapping - * details into it's internal alloctor and create the actual MMU mappings once + * details into it's internal allocator and create the actual MMU mappings once * the memory is swapped back in. While this is transparent for userspace, it is * guaranteed that all the backing memory is swapped back in and all the memory * mappings, as requested by userspace previously, are actually mapped once the * DRM_NOUVEAU_EXEC ioctl is called to submit an exec job. * * A VM_BIND job can be executed either synchronously or asynchronously. If - * exectued asynchronously, userspace may provide a list of syncobjs this job + * executed asynchronously, userspace may provide a list of syncobjs this job * will wait for and/or a list of syncobj the kernel will signal once the * VM_BIND job finished execution. If executed synchronously the ioctl will * block until the bind job is finished. For synchronous jobs the kernel will @@ -82,7 +82,7 @@ * Since VM_BIND jobs update the GPU's VA space on job submit, EXEC jobs do have * an up to date view of the VA space. However, the actual mappings might still * be pending. Hence, EXEC jobs require to have the particular fences - of - * the corresponding VM_BIND jobs they depent on - attached to them. + * the corresponding VM_BIND jobs they depend on - attached to them. */ static int diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c index 9f345a008717..869d4335c0f4 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.c +++ b/drivers/gpu/drm/nouveau/nouveau_fence.c @@ -240,21 +240,6 @@ nouveau_fence_emit(struct nouveau_fence *fence) return ret; } -void -nouveau_fence_cancel(struct nouveau_fence *fence) -{ - struct nouveau_fence_chan *fctx = nouveau_fctx(fence); - unsigned long flags; - - spin_lock_irqsave(&fctx->lock, flags); - if (!dma_fence_is_signaled_locked(&fence->base)) { - dma_fence_set_error(&fence->base, -ECANCELED); - if (nouveau_fence_signal(fence)) - nvif_event_block(&fctx->event); - } - spin_unlock_irqrestore(&fctx->lock, flags); -} - bool nouveau_fence_done(struct nouveau_fence *fence) { diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.h b/drivers/gpu/drm/nouveau/nouveau_fence.h index 9957a919bd38..183dd43ecfff 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.h +++ b/drivers/gpu/drm/nouveau/nouveau_fence.h @@ -29,7 +29,6 @@ void nouveau_fence_unref(struct nouveau_fence **); int nouveau_fence_emit(struct nouveau_fence *); bool nouveau_fence_done(struct nouveau_fence *); -void nouveau_fence_cancel(struct nouveau_fence *fence); int nouveau_fence_wait(struct nouveau_fence *, bool lazy, bool intr); int nouveau_fence_sync(struct nouveau_bo *, struct nouveau_channel *, bool exclusive, bool intr); diff --git a/drivers/gpu/drm/nouveau/nouveau_platform.c b/drivers/gpu/drm/nouveau/nouveau_platform.c index a5ce8eb4a3be..8d5853deeee4 100644 --- a/drivers/gpu/drm/nouveau/nouveau_platform.c +++ b/drivers/gpu/drm/nouveau/nouveau_platform.c @@ -30,10 +30,7 @@ static int nouveau_platform_probe(struct platform_device *pdev) func = of_device_get_match_data(&pdev->dev); drm = nouveau_platform_device_create(func, pdev, &device); - if (IS_ERR(drm)) - return PTR_ERR(drm); - - return 0; + return PTR_ERR_OR_ZERO(drm); } static void nouveau_platform_remove(struct platform_device *pdev) diff --git a/drivers/gpu/drm/nouveau/nouveau_prime.c b/drivers/gpu/drm/nouveau/nouveau_prime.c index cd95446d6851..caab60fc62f6 100644 --- a/drivers/gpu/drm/nouveau/nouveau_prime.c +++ b/drivers/gpu/drm/nouveau/nouveau_prime.c @@ -108,9 +108,21 @@ struct dma_buf *nouveau_gem_prime_export(struct drm_gem_object *gobj, int flags) { struct nouveau_bo *nvbo = nouveau_gem_object(gobj); + struct ttm_operation_ctx ctx = { + .interruptible = true, + .no_wait_gpu = true, + /* We opt to avoid OOM on system pages allocations */ + .gfp_retry_mayfail = true, + .allow_res_evict = false, + }; + int ret; if (nvbo->no_share) return ERR_PTR(-EPERM); + ret = ttm_bo_setup_export(&nvbo->bo, &ctx); + if (ret) + return ERR_PTR(ret); + return drm_gem_prime_export(gobj, flags); } diff --git a/drivers/gpu/drm/nouveau/nouveau_sched.c b/drivers/gpu/drm/nouveau/nouveau_sched.c index 0cc0bc9f9952..e60f7892f5ce 100644 --- a/drivers/gpu/drm/nouveau/nouveau_sched.c +++ b/drivers/gpu/drm/nouveau/nouveau_sched.c @@ -11,7 +11,6 @@ #include "nouveau_exec.h" #include "nouveau_abi16.h" #include "nouveau_sched.h" -#include "nouveau_chan.h" #define NOUVEAU_SCHED_JOB_TIMEOUT_MS 10000 @@ -122,9 +121,11 @@ nouveau_job_done(struct nouveau_job *job) { struct nouveau_sched *sched = job->sched; - spin_lock(&sched->job_list.lock); + spin_lock(&sched->job.list.lock); list_del(&job->entry); - spin_unlock(&sched->job_list.lock); + spin_unlock(&sched->job.list.lock); + + wake_up(&sched->job.wq); } void @@ -305,9 +306,9 @@ nouveau_job_submit(struct nouveau_job *job) } /* Submit was successful; add the job to the schedulers job list. */ - spin_lock(&sched->job_list.lock); - list_add(&job->entry, &sched->job_list.head); - spin_unlock(&sched->job_list.lock); + spin_lock(&sched->job.list.lock); + list_add(&job->entry, &sched->job.list.head); + spin_unlock(&sched->job.list.lock); drm_sched_job_arm(&job->base); job->done_fence = dma_fence_get(&job->base.s_fence->finished); @@ -392,23 +393,10 @@ nouveau_sched_free_job(struct drm_sched_job *sched_job) nouveau_job_fini(job); } -static void -nouveau_sched_cancel_job(struct drm_sched_job *sched_job) -{ - struct nouveau_fence *fence; - struct nouveau_job *job; - - job = to_nouveau_job(sched_job); - fence = to_nouveau_fence(job->done_fence); - - nouveau_fence_cancel(fence); -} - static const struct drm_sched_backend_ops nouveau_sched_ops = { .run_job = nouveau_sched_run_job, .timedout_job = nouveau_sched_timedout_job, .free_job = nouveau_sched_free_job, - .cancel_job = nouveau_sched_cancel_job, }; static int @@ -458,8 +446,9 @@ nouveau_sched_init(struct nouveau_sched *sched, struct nouveau_drm *drm, goto fail_sched; mutex_init(&sched->mutex); - spin_lock_init(&sched->job_list.lock); - INIT_LIST_HEAD(&sched->job_list.head); + spin_lock_init(&sched->job.list.lock); + INIT_LIST_HEAD(&sched->job.list.head); + init_waitqueue_head(&sched->job.wq); return 0; @@ -493,12 +482,16 @@ nouveau_sched_create(struct nouveau_sched **psched, struct nouveau_drm *drm, return 0; } + static void nouveau_sched_fini(struct nouveau_sched *sched) { struct drm_gpu_scheduler *drm_sched = &sched->base; struct drm_sched_entity *entity = &sched->entity; + rmb(); /* for list_empty to work without lock */ + wait_event(sched->job.wq, list_empty(&sched->job.list.head)); + drm_sched_entity_fini(entity); drm_sched_fini(drm_sched); diff --git a/drivers/gpu/drm/nouveau/nouveau_sched.h b/drivers/gpu/drm/nouveau/nouveau_sched.h index b98c3f0bef30..20cd1da8db73 100644 --- a/drivers/gpu/drm/nouveau/nouveau_sched.h +++ b/drivers/gpu/drm/nouveau/nouveau_sched.h @@ -103,9 +103,12 @@ struct nouveau_sched { struct mutex mutex; struct { - struct list_head head; - spinlock_t lock; - } job_list; + struct { + struct list_head head; + spinlock_t lock; + } list; + struct wait_queue_head wq; + } job; }; int nouveau_sched_create(struct nouveau_sched **psched, struct nouveau_drm *drm, diff --git a/drivers/gpu/drm/nouveau/nouveau_uvmm.c b/drivers/gpu/drm/nouveau/nouveau_uvmm.c index d94a85509176..79eefdfd08a2 100644 --- a/drivers/gpu/drm/nouveau/nouveau_uvmm.c +++ b/drivers/gpu/drm/nouveau/nouveau_uvmm.c @@ -1019,8 +1019,8 @@ bind_validate_map_sparse(struct nouveau_job *job, u64 addr, u64 range) u64 end = addr + range; again: - spin_lock(&sched->job_list.lock); - list_for_each_entry(__job, &sched->job_list.head, entry) { + spin_lock(&sched->job.list.lock); + list_for_each_entry(__job, &sched->job.list.head, entry) { struct nouveau_uvmm_bind_job *bind_job = to_uvmm_bind_job(__job); list_for_each_op(op, &bind_job->ops) { @@ -1030,7 +1030,7 @@ again: if (!(end <= op_addr || addr >= op_end)) { nouveau_uvmm_bind_job_get(bind_job); - spin_unlock(&sched->job_list.lock); + spin_unlock(&sched->job.list.lock); wait_for_completion(&bind_job->complete); nouveau_uvmm_bind_job_put(bind_job); goto again; @@ -1038,7 +1038,7 @@ again: } } } - spin_unlock(&sched->job_list.lock); + spin_unlock(&sched->job.list.lock); } static int diff --git a/drivers/gpu/drm/nouveau/nvif/vmm.c b/drivers/gpu/drm/nouveau/nvif/vmm.c index 99296f03371a..07c1ebc2a941 100644 --- a/drivers/gpu/drm/nouveau/nvif/vmm.c +++ b/drivers/gpu/drm/nouveau/nvif/vmm.c @@ -219,7 +219,8 @@ nvif_vmm_ctor(struct nvif_mmu *mmu, const char *name, s32 oclass, case RAW: args->type = NVIF_VMM_V0_TYPE_RAW; break; default: WARN_ON(1); - return -EINVAL; + ret = -EINVAL; + goto done; } memcpy(args->data, argv, argc); diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/base.c index fdffa0391b31..6fd4e60634fb 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/base.c @@ -350,6 +350,8 @@ nvkm_fifo_dtor(struct nvkm_engine *engine) nvkm_chid_unref(&fifo->chid); nvkm_event_fini(&fifo->nonstall.event); + if (fifo->func->nonstall_dtor) + fifo->func->nonstall_dtor(fifo); mutex_destroy(&fifo->mutex); if (fifo->func->dtor) diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga100.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga100.c index e74493a4569e..6848a56f20c0 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga100.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga100.c @@ -517,19 +517,11 @@ ga100_fifo_nonstall_intr(struct nvkm_inth *inth) static void ga100_fifo_nonstall_block(struct nvkm_event *event, int type, int index) { - struct nvkm_fifo *fifo = container_of(event, typeof(*fifo), nonstall.event); - struct nvkm_runl *runl = nvkm_runl_get(fifo, index, 0); - - nvkm_inth_block(&runl->nonstall.inth); } static void ga100_fifo_nonstall_allow(struct nvkm_event *event, int type, int index) { - struct nvkm_fifo *fifo = container_of(event, typeof(*fifo), nonstall.event); - struct nvkm_runl *runl = nvkm_runl_get(fifo, index, 0); - - nvkm_inth_allow(&runl->nonstall.inth); } const struct nvkm_event_func @@ -564,12 +556,26 @@ ga100_fifo_nonstall_ctor(struct nvkm_fifo *fifo) if (ret) return ret; + nvkm_inth_allow(&runl->nonstall.inth); + nr = max(nr, runl->id + 1); } return nr; } +void +ga100_fifo_nonstall_dtor(struct nvkm_fifo *fifo) +{ + struct nvkm_runl *runl; + + nvkm_runl_foreach(runl, fifo) { + if (runl->nonstall.vector < 0) + continue; + nvkm_inth_block(&runl->nonstall.inth); + } +} + int ga100_fifo_runl_ctor(struct nvkm_fifo *fifo) { @@ -599,6 +605,7 @@ ga100_fifo = { .runl_ctor = ga100_fifo_runl_ctor, .mmu_fault = &tu102_fifo_mmu_fault, .nonstall_ctor = ga100_fifo_nonstall_ctor, + .nonstall_dtor = ga100_fifo_nonstall_dtor, .nonstall = &ga100_fifo_nonstall, .runl = &ga100_runl, .runq = &ga100_runq, diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga102.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga102.c index 755235f55b3a..18a0b1f4eab7 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga102.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga102.c @@ -30,6 +30,7 @@ ga102_fifo = { .runl_ctor = ga100_fifo_runl_ctor, .mmu_fault = &tu102_fifo_mmu_fault, .nonstall_ctor = ga100_fifo_nonstall_ctor, + .nonstall_dtor = ga100_fifo_nonstall_dtor, .nonstall = &ga100_fifo_nonstall, .runl = &ga100_runl, .runq = &ga100_runq, diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/priv.h b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/priv.h index 5e81ae195329..fff1428ef267 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/priv.h +++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/priv.h @@ -41,6 +41,7 @@ struct nvkm_fifo_func { void (*start)(struct nvkm_fifo *, unsigned long *); int (*nonstall_ctor)(struct nvkm_fifo *); + void (*nonstall_dtor)(struct nvkm_fifo *); const struct nvkm_event_func *nonstall; const struct nvkm_runl_func *runl; @@ -200,6 +201,7 @@ u32 tu102_chan_doorbell_handle(struct nvkm_chan *); int ga100_fifo_runl_ctor(struct nvkm_fifo *); int ga100_fifo_nonstall_ctor(struct nvkm_fifo *); +void ga100_fifo_nonstall_dtor(struct nvkm_fifo *); extern const struct nvkm_event_func ga100_fifo_nonstall; extern const struct nvkm_runl_func ga100_runl; extern const struct nvkm_runq_func ga100_runq; diff --git a/drivers/gpu/drm/nouveau/nvkm/falcon/gm200.c b/drivers/gpu/drm/nouveau/nvkm/falcon/gm200.c index b7da3ab44c27..7c43397c19e6 100644 --- a/drivers/gpu/drm/nouveau/nvkm/falcon/gm200.c +++ b/drivers/gpu/drm/nouveau/nvkm/falcon/gm200.c @@ -103,7 +103,7 @@ gm200_flcn_pio_imem_wr_init(struct nvkm_falcon *falcon, u8 port, bool sec, u32 i static void gm200_flcn_pio_imem_wr(struct nvkm_falcon *falcon, u8 port, const u8 *img, int len, u16 tag) { - nvkm_falcon_wr32(falcon, 0x188 + (port * 0x10), tag++); + nvkm_falcon_wr32(falcon, 0x188 + (port * 0x10), tag); while (len >= 4) { nvkm_falcon_wr32(falcon, 0x184 + (port * 0x10), *(u32 *)img); img += 4; @@ -249,9 +249,11 @@ int gm200_flcn_fw_load(struct nvkm_falcon_fw *fw) { struct nvkm_falcon *falcon = fw->falcon; - int target, ret; + int ret; if (fw->inst) { + int target; + nvkm_falcon_mask(falcon, 0x048, 0x00000001, 0x00000001); switch (nvkm_memory_target(fw->inst)) { @@ -285,15 +287,6 @@ gm200_flcn_fw_load(struct nvkm_falcon_fw *fw) } if (fw->boot) { - switch (nvkm_memory_target(&fw->fw.mem.memory)) { - case NVKM_MEM_TARGET_VRAM: target = 4; break; - case NVKM_MEM_TARGET_HOST: target = 5; break; - case NVKM_MEM_TARGET_NCOH: target = 6; break; - default: - WARN_ON(1); - return -EINVAL; - } - ret = nvkm_falcon_pio_wr(falcon, fw->boot, 0, 0, IMEM, falcon->code.limit - fw->boot_size, fw->boot_size, fw->boot_addr >> 8, false); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/fwsec.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/fwsec.c index 52412965fac1..5b721bd9d799 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/fwsec.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/fwsec.c @@ -209,11 +209,12 @@ nvkm_gsp_fwsec_v2(struct nvkm_gsp *gsp, const char *name, fw->boot_addr = bld->start_tag << 8; fw->boot_size = bld->code_size; fw->boot = kmemdup(bl->data + hdr->data_offset + bld->code_off, fw->boot_size, GFP_KERNEL); - if (!fw->boot) - ret = -ENOMEM; nvkm_firmware_put(bl); + if (!fw->boot) + return -ENOMEM; + /* Patch in interface data. */ return nvkm_gsp_fwsec_patch(gsp, fw, desc->InterfaceOffset, init_cmd); } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/fifo.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/fifo.c index 1ac5628c5140..4ed54b386a60 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/fifo.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/fifo.c @@ -601,6 +601,7 @@ r535_fifo_new(const struct nvkm_fifo_func *hw, struct nvkm_device *device, rm->chan.func = &r535_chan; rm->nonstall = &ga100_fifo_nonstall; rm->nonstall_ctor = ga100_fifo_nonstall_ctor; + rm->nonstall_dtor = ga100_fifo_nonstall_dtor; return nvkm_fifo_new_(rm, device, type, inst, pfifo); } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/rpc.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/rpc.c index 9d06ff722fea..0dc4782df8c0 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/rpc.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/rpc.c @@ -325,7 +325,7 @@ r535_gsp_msgq_recv(struct nvkm_gsp *gsp, u32 gsp_rpc_len, int *retries) rpc = r535_gsp_msgq_peek(gsp, sizeof(*rpc), info.retries); if (IS_ERR_OR_NULL(rpc)) { - kfree(buf); + kvfree(buf); return rpc; } @@ -334,7 +334,7 @@ r535_gsp_msgq_recv(struct nvkm_gsp *gsp, u32 gsp_rpc_len, int *retries) rpc = r535_gsp_msgq_recv_one_elem(gsp, &info); if (IS_ERR_OR_NULL(rpc)) { - kfree(buf); + kvfree(buf); return rpc; } diff --git a/drivers/gpu/drm/nova/driver.rs b/drivers/gpu/drm/nova/driver.rs index b28b2e05cc15..91b7380f83ab 100644 --- a/drivers/gpu/drm/nova/driver.rs +++ b/drivers/gpu/drm/nova/driver.rs @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 -use kernel::{auxiliary, c_str, device::Core, drm, drm::gem, drm::ioctl, prelude::*, types::ARef}; +use kernel::{ + auxiliary, c_str, device::Core, drm, drm::gem, drm::ioctl, prelude::*, sync::aref::ARef, +}; use crate::file::File; use crate::gem::NovaObject; diff --git a/drivers/gpu/drm/nova/file.rs b/drivers/gpu/drm/nova/file.rs index 7e7d4e2de2fb..90b9d2d0ec4a 100644 --- a/drivers/gpu/drm/nova/file.rs +++ b/drivers/gpu/drm/nova/file.rs @@ -36,7 +36,7 @@ impl File { _ => return Err(EINVAL), }; - getparam.value = value; + getparam.value = Into::<u64>::into(value); Ok(0) } diff --git a/drivers/gpu/drm/nova/gem.rs b/drivers/gpu/drm/nova/gem.rs index 33b62d21400c..2760ba4f3450 100644 --- a/drivers/gpu/drm/nova/gem.rs +++ b/drivers/gpu/drm/nova/gem.rs @@ -4,7 +4,7 @@ use kernel::{ drm, drm::{gem, gem::BaseObject}, prelude::*, - types::ARef, + sync::aref::ARef, }; use crate::{ @@ -16,16 +16,14 @@ use crate::{ #[pin_data] pub(crate) struct NovaObject {} -impl gem::BaseDriverObject<gem::Object<NovaObject>> for NovaObject { +impl gem::DriverObject for NovaObject { + type Driver = NovaDriver; + fn new(_dev: &NovaDevice, _size: usize) -> impl PinInit<Self, Error> { try_pin_init!(NovaObject {}) } } -impl gem::DriverObject for NovaObject { - type Driver = NovaDriver; -} - impl NovaObject { /// Create a new DRM GEM object. pub(crate) fn new(dev: &NovaDevice, size: usize) -> Result<ARef<gem::Object<Self>>> { diff --git a/drivers/gpu/drm/omapdrm/omap_drv.c b/drivers/gpu/drm/omapdrm/omap_drv.c index 054b71dba6a7..794267f0f007 100644 --- a/drivers/gpu/drm/omapdrm/omap_drv.c +++ b/drivers/gpu/drm/omapdrm/omap_drv.c @@ -378,10 +378,8 @@ static int omap_display_id(struct omap_dss_device *output) struct device_node *node = NULL; if (output->bridge) { - struct drm_bridge *bridge = output->bridge; - - while (drm_bridge_get_next_bridge(bridge)) - bridge = drm_bridge_get_next_bridge(bridge); + struct drm_bridge *bridge __free(drm_bridge_put) = + drm_bridge_chain_get_last_bridge(output->bridge->encoder); node = bridge->of_node; } diff --git a/drivers/gpu/drm/panel/panel-edp.c b/drivers/gpu/drm/panel/panel-edp.c index feba520a0f45..62435e3cd9f4 100644 --- a/drivers/gpu/drm/panel/panel-edp.c +++ b/drivers/gpu/drm/panel/panel-edp.c @@ -1843,6 +1843,13 @@ static const struct panel_delay delay_200_500_e50_d100 = { .disable = 100, }; +static const struct panel_delay delay_80_500_e50_d50 = { + .hpd_absent = 80, + .unprepare = 500, + .enable = 50, + .disable = 50, +}; + #define EDP_PANEL_ENTRY(vend_chr_0, vend_chr_1, vend_chr_2, product_id, _delay, _name) \ { \ .ident = { \ @@ -1955,6 +1962,7 @@ static const struct edp_panel_entry edp_panels[] = { EDP_PANEL_ENTRY('B', 'O', 'E', 0x0a36, &delay_200_500_e200, "Unknown"), EDP_PANEL_ENTRY('B', 'O', 'E', 0x0a3e, &delay_200_500_e80_d50, "NV116WHM-N49"), EDP_PANEL_ENTRY('B', 'O', 'E', 0x0a5d, &delay_200_500_e50, "NV116WHM-N45"), + EDP_PANEL_ENTRY('B', 'O', 'E', 0x0a6a, &delay_200_500_e80, "NV140WUM-N44"), EDP_PANEL_ENTRY('B', 'O', 'E', 0x0ac5, &delay_200_500_e50, "NV116WHM-N4C"), EDP_PANEL_ENTRY('B', 'O', 'E', 0x0ae8, &delay_200_500_e50_p2e80, "NV140WUM-N41"), EDP_PANEL_ENTRY('B', 'O', 'E', 0x0b09, &delay_200_500_e50_po2e200, "NV140FHM-NZ"), @@ -1996,6 +2004,7 @@ static const struct edp_panel_entry edp_panels[] = { EDP_PANEL_ENTRY('C', 'M', 'N', 0x124c, &delay_200_500_e80_d50, "N122JCA-ENK"), EDP_PANEL_ENTRY('C', 'M', 'N', 0x142b, &delay_200_500_e80_d50, "N140HCA-EAC"), EDP_PANEL_ENTRY('C', 'M', 'N', 0x142e, &delay_200_500_e80_d50, "N140BGA-EA4"), + EDP_PANEL_ENTRY('C', 'M', 'N', 0x1441, &delay_200_500_e80_d50, "N140JCA-ELK"), EDP_PANEL_ENTRY('C', 'M', 'N', 0x144f, &delay_200_500_e80_d50, "N140HGA-EA1"), EDP_PANEL_ENTRY('C', 'M', 'N', 0x1468, &delay_200_500_e80, "N140HGA-EA1"), EDP_PANEL_ENTRY('C', 'M', 'N', 0x14a8, &delay_200_500_e80, "N140JCA-ELP"), @@ -2011,10 +2020,12 @@ static const struct edp_panel_entry edp_panels[] = { EDP_PANEL_ENTRY('C', 'S', 'W', 0x1100, &delay_200_500_e80_d50, "MNB601LS1-1"), EDP_PANEL_ENTRY('C', 'S', 'W', 0x1103, &delay_200_500_e80_d50, "MNB601LS1-3"), EDP_PANEL_ENTRY('C', 'S', 'W', 0x1104, &delay_200_500_e50_d100, "MNB601LS1-4"), + EDP_PANEL_ENTRY('C', 'S', 'W', 0x143f, &delay_200_500_e50, "MNE007QS3-6"), EDP_PANEL_ENTRY('C', 'S', 'W', 0x1448, &delay_200_500_e50, "MNE007QS3-7"), EDP_PANEL_ENTRY('C', 'S', 'W', 0x1457, &delay_80_500_e80_p2e200, "MNE007QS3-8"), EDP_PANEL_ENTRY('C', 'S', 'W', 0x1462, &delay_200_500_e50, "MNE007QS5-2"), EDP_PANEL_ENTRY('C', 'S', 'W', 0x1468, &delay_200_500_e50, "MNE007QB2-2"), + EDP_PANEL_ENTRY('C', 'S', 'W', 0x146e, &delay_80_500_e50_d50, "MNE007QB3-1"), EDP_PANEL_ENTRY('E', 'T', 'C', 0x0000, &delay_50_500_e200_d200_po2e335, "LP079QX1-SP0V"), diff --git a/drivers/gpu/drm/panel/panel-lvds.c b/drivers/gpu/drm/panel/panel-lvds.c index 23fd535d8f47..46b07f38559f 100644 --- a/drivers/gpu/drm/panel/panel-lvds.c +++ b/drivers/gpu/drm/panel/panel-lvds.c @@ -28,8 +28,6 @@ struct panel_lvds { struct device *dev; const char *label; - unsigned int width; - unsigned int height; struct drm_display_mode dmode; u32 bus_flags; unsigned int bus_format; diff --git a/drivers/gpu/drm/panthor/panthor_drv.c b/drivers/gpu/drm/panthor/panthor_drv.c index 9256806eb662..4c202fc5ce05 100644 --- a/drivers/gpu/drm/panthor/panthor_drv.c +++ b/drivers/gpu/drm/panthor/panthor_drv.c @@ -1094,7 +1094,7 @@ static int panthor_ioctl_group_create(struct drm_device *ddev, void *data, struct drm_panthor_queue_create *queue_args; int ret; - if (!args->queues.count) + if (!args->queues.count || args->queues.count > MAX_CS_PER_CSG) return -EINVAL; ret = PANTHOR_UOBJ_GET_ARRAY(queue_args, &args->queues); diff --git a/drivers/gpu/drm/panthor/panthor_gem.c b/drivers/gpu/drm/panthor/panthor_gem.c index a123bc740ba1..156c7a0b62a2 100644 --- a/drivers/gpu/drm/panthor/panthor_gem.c +++ b/drivers/gpu/drm/panthor/panthor_gem.c @@ -74,7 +74,6 @@ static void panthor_gem_free_object(struct drm_gem_object *obj) mutex_destroy(&bo->label.lock); drm_gem_free_mmap_offset(&bo->base.base); - mutex_destroy(&bo->gpuva_list_lock); drm_gem_shmem_free(&bo->base); drm_gem_object_put(vm_root_gem); } @@ -246,8 +245,6 @@ struct drm_gem_object *panthor_gem_create_object(struct drm_device *ddev, size_t obj->base.base.funcs = &panthor_gem_funcs; obj->base.map_wc = !ptdev->coherent; - mutex_init(&obj->gpuva_list_lock); - drm_gem_gpuva_set_lock(&obj->base.base, &obj->gpuva_list_lock); mutex_init(&obj->label.lock); panthor_gem_debugfs_bo_init(obj); diff --git a/drivers/gpu/drm/panthor/panthor_gem.h b/drivers/gpu/drm/panthor/panthor_gem.h index 8fc7215e9b90..80c6e24112d0 100644 --- a/drivers/gpu/drm/panthor/panthor_gem.h +++ b/drivers/gpu/drm/panthor/panthor_gem.h @@ -79,18 +79,6 @@ struct panthor_gem_object { */ struct drm_gem_object *exclusive_vm_root_gem; - /** - * @gpuva_list_lock: Custom GPUVA lock. - * - * Used to protect insertion of drm_gpuva elements to the - * drm_gem_object.gpuva.list list. - * - * We can't use the GEM resv for that, because drm_gpuva_link() is - * called in a dma-signaling path, where we're not allowed to take - * resv locks. - */ - struct mutex gpuva_list_lock; - /** @flags: Combination of drm_panthor_bo_flags flags. */ u32 flags; diff --git a/drivers/gpu/drm/panthor/panthor_mmu.c b/drivers/gpu/drm/panthor/panthor_mmu.c index 2003b91a8409..6dec4354e378 100644 --- a/drivers/gpu/drm/panthor/panthor_mmu.c +++ b/drivers/gpu/drm/panthor/panthor_mmu.c @@ -569,15 +569,37 @@ static void lock_region(struct panthor_device *ptdev, u32 as_nr, write_cmd(ptdev, as_nr, AS_COMMAND_LOCK); } -static int mmu_hw_do_flush_on_gpu_ctrl(struct panthor_device *ptdev, int as_nr, - u32 op) +static int mmu_hw_do_operation_locked(struct panthor_device *ptdev, int as_nr, + u64 iova, u64 size, u32 op) { const u32 l2_flush_op = CACHE_CLEAN | CACHE_INV; - u32 lsc_flush_op = 0; + u32 lsc_flush_op; int ret; - if (op == AS_COMMAND_FLUSH_MEM) + lockdep_assert_held(&ptdev->mmu->as.slots_lock); + + switch (op) { + case AS_COMMAND_FLUSH_MEM: lsc_flush_op = CACHE_CLEAN | CACHE_INV; + break; + case AS_COMMAND_FLUSH_PT: + lsc_flush_op = 0; + break; + default: + drm_WARN(&ptdev->base, 1, "Unexpected AS_COMMAND: %d", op); + return -EINVAL; + } + + if (as_nr < 0) + return 0; + + /* + * If the AS number is greater than zero, then we can be sure + * the device is up and running, so we don't need to explicitly + * power it up + */ + + lock_region(ptdev, as_nr, iova, size); ret = wait_ready(ptdev, as_nr); if (ret) @@ -598,33 +620,6 @@ static int mmu_hw_do_flush_on_gpu_ctrl(struct panthor_device *ptdev, int as_nr, return wait_ready(ptdev, as_nr); } -static int mmu_hw_do_operation_locked(struct panthor_device *ptdev, int as_nr, - u64 iova, u64 size, u32 op) -{ - lockdep_assert_held(&ptdev->mmu->as.slots_lock); - - if (as_nr < 0) - return 0; - - /* - * If the AS number is greater than zero, then we can be sure - * the device is up and running, so we don't need to explicitly - * power it up - */ - - if (op != AS_COMMAND_UNLOCK) - lock_region(ptdev, as_nr, iova, size); - - if (op == AS_COMMAND_FLUSH_MEM || op == AS_COMMAND_FLUSH_PT) - return mmu_hw_do_flush_on_gpu_ctrl(ptdev, as_nr, op); - - /* Run the MMU operation */ - write_cmd(ptdev, as_nr, op); - - /* Wait for the flush to complete */ - return wait_ready(ptdev, as_nr); -} - static int mmu_hw_do_operation(struct panthor_vm *vm, u64 iova, u64 size, u32 op) { @@ -1107,9 +1102,9 @@ static void panthor_vm_bo_put(struct drm_gpuvm_bo *vm_bo) * GEM vm_bo list. */ dma_resv_lock(drm_gpuvm_resv(vm), NULL); - mutex_lock(&bo->gpuva_list_lock); + mutex_lock(&bo->base.base.gpuva.lock); unpin = drm_gpuvm_bo_put(vm_bo); - mutex_unlock(&bo->gpuva_list_lock); + mutex_unlock(&bo->base.base.gpuva.lock); dma_resv_unlock(drm_gpuvm_resv(vm)); /* If the vm_bo object was destroyed, release the pin reference that @@ -1227,7 +1222,7 @@ static int panthor_vm_prepare_map_op_ctx(struct panthor_vm_op_ctx *op_ctx, (flags & DRM_PANTHOR_VM_BIND_OP_TYPE_MASK) != DRM_PANTHOR_VM_BIND_OP_TYPE_MAP) return -EINVAL; - /* Make sure the VA and size are aligned and in-bounds. */ + /* Make sure the VA and size are in-bounds. */ if (size > bo->base.base.size || offset > bo->base.base.size - size) return -EINVAL; @@ -1282,9 +1277,9 @@ static int panthor_vm_prepare_map_op_ctx(struct panthor_vm_op_ctx *op_ctx, * calling this function. */ dma_resv_lock(panthor_vm_resv(vm), NULL); - mutex_lock(&bo->gpuva_list_lock); + mutex_lock(&bo->base.base.gpuva.lock); op_ctx->map.vm_bo = drm_gpuvm_bo_obtain_prealloc(preallocated_vm_bo); - mutex_unlock(&bo->gpuva_list_lock); + mutex_unlock(&bo->base.base.gpuva.lock); dma_resv_unlock(panthor_vm_resv(vm)); /* If the a vm_bo for this <VM,BO> combination exists, it already @@ -2036,10 +2031,10 @@ static void panthor_vma_link(struct panthor_vm *vm, { struct panthor_gem_object *bo = to_panthor_bo(vma->base.gem.obj); - mutex_lock(&bo->gpuva_list_lock); + mutex_lock(&bo->base.base.gpuva.lock); drm_gpuva_link(&vma->base, vm_bo); drm_WARN_ON(&vm->ptdev->base, drm_gpuvm_bo_put(vm_bo)); - mutex_unlock(&bo->gpuva_list_lock); + mutex_unlock(&bo->base.base.gpuva.lock); } static void panthor_vma_unlink(struct panthor_vm *vm, @@ -2048,9 +2043,9 @@ static void panthor_vma_unlink(struct panthor_vm *vm, struct panthor_gem_object *bo = to_panthor_bo(vma->base.gem.obj); struct drm_gpuvm_bo *vm_bo = drm_gpuvm_bo_get(vma->base.vm_bo); - mutex_lock(&bo->gpuva_list_lock); + mutex_lock(&bo->base.base.gpuva.lock); drm_gpuva_unlink(&vma->base); - mutex_unlock(&bo->gpuva_list_lock); + mutex_unlock(&bo->base.base.gpuva.lock); /* drm_gpuva_unlink() release the vm_bo, but we manually retained it * when entering this function, so we can implement deferred VMA @@ -2420,8 +2415,9 @@ panthor_vm_create(struct panthor_device *ptdev, bool for_mcu, * to be handled the same way user VMAs are. */ drm_gpuvm_init(&vm->base, for_mcu ? "panthor-MCU-VM" : "panthor-GPU-VM", - DRM_GPUVM_RESV_PROTECTED, &ptdev->base, dummy_gem, - min_va, va_range, 0, 0, &panthor_gpuvm_ops); + DRM_GPUVM_RESV_PROTECTED | DRM_GPUVM_IMMEDIATE_MODE, + &ptdev->base, dummy_gem, min_va, va_range, 0, 0, + &panthor_gpuvm_ops); drm_gem_object_put(dummy_gem); return vm; @@ -2451,7 +2447,7 @@ panthor_vm_bind_prepare_op_ctx(struct drm_file *file, int ret; /* Aligned on page size. */ - if (!IS_ALIGNED(op->va | op->size, vm_pgsz)) + if (!IS_ALIGNED(op->va | op->size | op->bo_offset, vm_pgsz)) return -EINVAL; switch (op->flags & DRM_PANTHOR_VM_BIND_OP_TYPE_MASK) { diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c index d1c5e471bdca..3d9f47bc807a 100644 --- a/drivers/gpu/drm/radeon/atombios_encoders.c +++ b/drivers/gpu/drm/radeon/atombios_encoders.c @@ -1832,7 +1832,7 @@ radeon_atom_encoder_dpms(struct drm_encoder *encoder, int mode) return; } - radeon_atombios_encoder_dpms_scratch_regs(encoder, (mode == DRM_MODE_DPMS_ON) ? true : false); + radeon_atombios_encoder_dpms_scratch_regs(encoder, mode == DRM_MODE_DPMS_ON); } diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c index 7c3a960f486a..ba8db1d07c07 100644 --- a/drivers/gpu/drm/radeon/ci_dpm.c +++ b/drivers/gpu/drm/radeon/ci_dpm.c @@ -2457,7 +2457,7 @@ static void ci_register_patching_mc_arb(struct radeon_device *rdev, u32 tmp, tmp2; tmp = RREG32(MC_SEQ_MISC0); - patch = ((tmp & 0x0000f00) == 0x300) ? true : false; + patch = (tmp & 0x0000f00) == 0x300; if (patch && ((rdev->pdev->device == 0x67B0) || @@ -3238,7 +3238,8 @@ static int ci_populate_all_graphic_levels(struct radeon_device *rdev) u32 level_array_size = sizeof(SMU7_Discrete_GraphicsLevel) * SMU7_MAX_LEVELS_GRAPHICS; SMU7_Discrete_GraphicsLevel *levels = pi->smc_state_table.GraphicsLevel; - u32 i, ret; + int ret; + u32 i; memset(levels, 0, level_array_size); @@ -3285,7 +3286,8 @@ static int ci_populate_all_memory_levels(struct radeon_device *rdev) u32 level_array_size = sizeof(SMU7_Discrete_MemoryLevel) * SMU7_MAX_LEVELS_MEMORY; SMU7_Discrete_MemoryLevel *levels = pi->smc_state_table.MemoryLevel; - u32 i, ret; + int ret; + u32 i; memset(levels, 0, level_array_size); @@ -3436,7 +3438,7 @@ static int ci_setup_default_dpm_tables(struct radeon_device *rdev) pi->dpm_table.sclk_table.dpm_levels[pi->dpm_table.sclk_table.count].value = allowed_sclk_vddc_table->entries[i].clk; pi->dpm_table.sclk_table.dpm_levels[pi->dpm_table.sclk_table.count].enabled = - (i == 0) ? true : false; + i == 0; pi->dpm_table.sclk_table.count++; } } @@ -3449,7 +3451,7 @@ static int ci_setup_default_dpm_tables(struct radeon_device *rdev) pi->dpm_table.mclk_table.dpm_levels[pi->dpm_table.mclk_table.count].value = allowed_mclk_table->entries[i].clk; pi->dpm_table.mclk_table.dpm_levels[pi->dpm_table.mclk_table.count].enabled = - (i == 0) ? true : false; + i == 0; pi->dpm_table.mclk_table.count++; } } @@ -4487,7 +4489,7 @@ static int ci_register_patching_mc_seq(struct radeon_device *rdev, bool patch; tmp = RREG32(MC_SEQ_MISC0); - patch = ((tmp & 0x0000f00) == 0x300) ? true : false; + patch = (tmp & 0x0000f00) == 0x300; if (patch && ((rdev->pdev->device == 0x67B0) || diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c index 266c57733136..1162cb5d75ed 100644 --- a/drivers/gpu/drm/radeon/evergreen_cs.c +++ b/drivers/gpu/drm/radeon/evergreen_cs.c @@ -951,13 +951,13 @@ static int evergreen_cs_track_check(struct radeon_cs_parser *p) u64 offset = (u64)track->vgt_strmout_bo_offset[i] + (u64)track->vgt_strmout_size[i]; if (offset > radeon_bo_size(track->vgt_strmout_bo[i])) { - DRM_ERROR("streamout %d bo too small: 0x%llx, 0x%lx\n", - i, offset, - radeon_bo_size(track->vgt_strmout_bo[i])); + dev_warn_once(p->dev, "streamout %d bo too small: 0x%llx, 0x%lx\n", + i, offset, + radeon_bo_size(track->vgt_strmout_bo[i])); return -EINVAL; } } else { - dev_warn(p->dev, "No buffer for streamout %d\n", i); + dev_warn_once(p->dev, "No buffer for streamout %d\n", i); return -EINVAL; } } @@ -979,8 +979,8 @@ static int evergreen_cs_track_check(struct radeon_cs_parser *p) (tmp >> (i * 4)) & 0xF) { /* at least one component is enabled */ if (track->cb_color_bo[i] == NULL) { - dev_warn(p->dev, "%s:%d mask 0x%08X | 0x%08X no cb for %d\n", - __func__, __LINE__, track->cb_target_mask, track->cb_shader_mask, i); + dev_warn_once(p->dev, "%s:%d mask 0x%08X | 0x%08X no cb for %d\n", + __func__, __LINE__, track->cb_target_mask, track->cb_shader_mask, i); return -EINVAL; } /* check cb */ @@ -1056,8 +1056,8 @@ static int evergreen_packet0_check(struct radeon_cs_parser *p, case EVERGREEN_VLINE_START_END: r = evergreen_cs_packet_parse_vline(p); if (r) { - DRM_ERROR("No reloc for ib[%d]=0x%04X\n", - idx, reg); + dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n", + idx, reg); return r; } break; @@ -1143,8 +1143,8 @@ static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) case SQ_VSTMP_RING_BASE: r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - dev_warn(p->dev, "bad SET_CONTEXT_REG " - "0x%04X\n", reg); + dev_warn_once(p->dev, "bad SET_CONTEXT_REG " + "0x%04X\n", reg); return -EINVAL; } ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff); @@ -1155,15 +1155,15 @@ static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) break; case CAYMAN_DB_EQAA: if (p->rdev->family < CHIP_CAYMAN) { - dev_warn(p->dev, "bad SET_CONTEXT_REG " - "0x%04X\n", reg); + dev_warn_once(p->dev, "bad SET_CONTEXT_REG " + "0x%04X\n", reg); return -EINVAL; } break; case CAYMAN_DB_DEPTH_INFO: if (p->rdev->family < CHIP_CAYMAN) { - dev_warn(p->dev, "bad SET_CONTEXT_REG " - "0x%04X\n", reg); + dev_warn_once(p->dev, "bad SET_CONTEXT_REG " + "0x%04X\n", reg); return -EINVAL; } break; @@ -1172,8 +1172,8 @@ static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) { r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - dev_warn(p->dev, "bad SET_CONTEXT_REG " - "0x%04X\n", reg); + dev_warn_once(p->dev, "bad SET_CONTEXT_REG " + "0x%04X\n", reg); return -EINVAL; } ib[idx] &= ~Z_ARRAY_MODE(0xf); @@ -1214,8 +1214,8 @@ static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) case DB_Z_READ_BASE: r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - dev_warn(p->dev, "bad SET_CONTEXT_REG " - "0x%04X\n", reg); + dev_warn_once(p->dev, "bad SET_CONTEXT_REG " + "0x%04X\n", reg); return -EINVAL; } track->db_z_read_offset = radeon_get_ib_value(p, idx); @@ -1226,8 +1226,8 @@ static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) case DB_Z_WRITE_BASE: r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - dev_warn(p->dev, "bad SET_CONTEXT_REG " - "0x%04X\n", reg); + dev_warn_once(p->dev, "bad SET_CONTEXT_REG " + "0x%04X\n", reg); return -EINVAL; } track->db_z_write_offset = radeon_get_ib_value(p, idx); @@ -1238,8 +1238,8 @@ static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) case DB_STENCIL_READ_BASE: r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - dev_warn(p->dev, "bad SET_CONTEXT_REG " - "0x%04X\n", reg); + dev_warn_once(p->dev, "bad SET_CONTEXT_REG " + "0x%04X\n", reg); return -EINVAL; } track->db_s_read_offset = radeon_get_ib_value(p, idx); @@ -1250,8 +1250,8 @@ static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) case DB_STENCIL_WRITE_BASE: r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - dev_warn(p->dev, "bad SET_CONTEXT_REG " - "0x%04X\n", reg); + dev_warn_once(p->dev, "bad SET_CONTEXT_REG " + "0x%04X\n", reg); return -EINVAL; } track->db_s_write_offset = radeon_get_ib_value(p, idx); @@ -1273,8 +1273,8 @@ static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) case VGT_STRMOUT_BUFFER_BASE_3: r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - dev_warn(p->dev, "bad SET_CONTEXT_REG " - "0x%04X\n", reg); + dev_warn_once(p->dev, "bad SET_CONTEXT_REG " + "0x%04X\n", reg); return -EINVAL; } tmp = (reg - VGT_STRMOUT_BUFFER_BASE_0) / 16; @@ -1295,8 +1295,8 @@ static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) case CP_COHER_BASE: r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - dev_warn(p->dev, "missing reloc for CP_COHER_BASE " - "0x%04X\n", reg); + dev_warn_once(p->dev, "missing reloc for CP_COHER_BASE " + "0x%04X\n", reg); return -EINVAL; } ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff); @@ -1311,8 +1311,8 @@ static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) break; case PA_SC_AA_CONFIG: if (p->rdev->family >= CHIP_CAYMAN) { - dev_warn(p->dev, "bad SET_CONTEXT_REG " - "0x%04X\n", reg); + dev_warn_once(p->dev, "bad SET_CONTEXT_REG " + "0x%04X\n", reg); return -EINVAL; } tmp = radeon_get_ib_value(p, idx) & MSAA_NUM_SAMPLES_MASK; @@ -1320,8 +1320,8 @@ static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) break; case CAYMAN_PA_SC_AA_CONFIG: if (p->rdev->family < CHIP_CAYMAN) { - dev_warn(p->dev, "bad SET_CONTEXT_REG " - "0x%04X\n", reg); + dev_warn_once(p->dev, "bad SET_CONTEXT_REG " + "0x%04X\n", reg); return -EINVAL; } tmp = radeon_get_ib_value(p, idx) & CAYMAN_MSAA_NUM_SAMPLES_MASK; @@ -1360,8 +1360,8 @@ static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) { r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - dev_warn(p->dev, "bad SET_CONTEXT_REG " - "0x%04X\n", reg); + dev_warn_once(p->dev, "bad SET_CONTEXT_REG " + "0x%04X\n", reg); return -EINVAL; } ib[idx] |= CB_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->tiling_flags)); @@ -1378,8 +1378,8 @@ static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) { r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - dev_warn(p->dev, "bad SET_CONTEXT_REG " - "0x%04X\n", reg); + dev_warn_once(p->dev, "bad SET_CONTEXT_REG " + "0x%04X\n", reg); return -EINVAL; } ib[idx] |= CB_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->tiling_flags)); @@ -1439,8 +1439,8 @@ static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) case CB_COLOR7_ATTRIB: r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - dev_warn(p->dev, "bad SET_CONTEXT_REG " - "0x%04X\n", reg); + dev_warn_once(p->dev, "bad SET_CONTEXT_REG " + "0x%04X\n", reg); return -EINVAL; } if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) { @@ -1467,8 +1467,8 @@ static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) case CB_COLOR11_ATTRIB: r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - dev_warn(p->dev, "bad SET_CONTEXT_REG " - "0x%04X\n", reg); + dev_warn_once(p->dev, "bad SET_CONTEXT_REG " + "0x%04X\n", reg); return -EINVAL; } if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) { @@ -1555,8 +1555,8 @@ static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) case CB_COLOR7_BASE: r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - dev_warn(p->dev, "bad SET_CONTEXT_REG " - "0x%04X\n", reg); + dev_warn_once(p->dev, "bad SET_CONTEXT_REG " + "0x%04X\n", reg); return -EINVAL; } tmp = (reg - CB_COLOR0_BASE) / 0x3c; @@ -1571,8 +1571,8 @@ static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) case CB_COLOR11_BASE: r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - dev_warn(p->dev, "bad SET_CONTEXT_REG " - "0x%04X\n", reg); + dev_warn_once(p->dev, "bad SET_CONTEXT_REG " + "0x%04X\n", reg); return -EINVAL; } tmp = ((reg - CB_COLOR8_BASE) / 0x1c) + 8; @@ -1584,8 +1584,8 @@ static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) case DB_HTILE_DATA_BASE: r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - dev_warn(p->dev, "bad SET_CONTEXT_REG " - "0x%04X\n", reg); + dev_warn_once(p->dev, "bad SET_CONTEXT_REG " + "0x%04X\n", reg); return -EINVAL; } track->htile_offset = radeon_get_ib_value(p, idx); @@ -1702,36 +1702,36 @@ static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) case SQ_ALU_CONST_CACHE_LS_15: r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - dev_warn(p->dev, "bad SET_CONTEXT_REG " - "0x%04X\n", reg); + dev_warn_once(p->dev, "bad SET_CONTEXT_REG " + "0x%04X\n", reg); return -EINVAL; } ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff); break; case SX_MEMORY_EXPORT_BASE: if (p->rdev->family >= CHIP_CAYMAN) { - dev_warn(p->dev, "bad SET_CONFIG_REG " - "0x%04X\n", reg); + dev_warn_once(p->dev, "bad SET_CONFIG_REG " + "0x%04X\n", reg); return -EINVAL; } r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - dev_warn(p->dev, "bad SET_CONFIG_REG " - "0x%04X\n", reg); + dev_warn_once(p->dev, "bad SET_CONFIG_REG " + "0x%04X\n", reg); return -EINVAL; } ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff); break; case CAYMAN_SX_SCATTER_EXPORT_BASE: if (p->rdev->family < CHIP_CAYMAN) { - dev_warn(p->dev, "bad SET_CONTEXT_REG " - "0x%04X\n", reg); + dev_warn_once(p->dev, "bad SET_CONTEXT_REG " + "0x%04X\n", reg); return -EINVAL; } r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - dev_warn(p->dev, "bad SET_CONTEXT_REG " - "0x%04X\n", reg); + dev_warn_once(p->dev, "bad SET_CONTEXT_REG " + "0x%04X\n", reg); return -EINVAL; } ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff); @@ -1740,7 +1740,7 @@ static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) track->sx_misc_kill_all_prims = (radeon_get_ib_value(p, idx) & 0x1) != 0; break; default: - dev_warn(p->dev, "forbidden register 0x%08x at %d\n", reg, idx); + dev_warn_once(p->dev, "forbidden register 0x%08x at %d\n", reg, idx); return -EINVAL; } return 0; @@ -1795,7 +1795,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, uint64_t offset; if (pkt->count != 1) { - DRM_ERROR("bad SET PREDICATION\n"); + dev_warn_once(p->dev, "bad SET PREDICATION\n"); return -EINVAL; } @@ -1807,13 +1807,13 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, return 0; if (pred_op > 2) { - DRM_ERROR("bad SET PREDICATION operation %d\n", pred_op); + dev_warn_once(p->dev, "bad SET PREDICATION operation %d\n", pred_op); return -EINVAL; } r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("bad SET PREDICATION\n"); + dev_warn_once(p->dev, "bad SET PREDICATION\n"); return -EINVAL; } @@ -1827,7 +1827,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, break; case PACKET3_CONTEXT_CONTROL: if (pkt->count != 1) { - DRM_ERROR("bad CONTEXT_CONTROL\n"); + dev_warn_once(p->dev, "bad CONTEXT_CONTROL\n"); return -EINVAL; } break; @@ -1835,17 +1835,17 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, case PACKET3_NUM_INSTANCES: case PACKET3_CLEAR_STATE: if (pkt->count) { - DRM_ERROR("bad INDEX_TYPE/NUM_INSTANCES/CLEAR_STATE\n"); + dev_warn_once(p->dev, "bad INDEX_TYPE/NUM_INSTANCES/CLEAR_STATE\n"); return -EINVAL; } break; case CAYMAN_PACKET3_DEALLOC_STATE: if (p->rdev->family < CHIP_CAYMAN) { - DRM_ERROR("bad PACKET3_DEALLOC_STATE\n"); + dev_warn_once(p->dev, "bad PACKET3_DEALLOC_STATE\n"); return -EINVAL; } if (pkt->count) { - DRM_ERROR("bad INDEX_TYPE/NUM_INSTANCES/CLEAR_STATE\n"); + dev_warn_once(p->dev, "bad INDEX_TYPE/NUM_INSTANCES/CLEAR_STATE\n"); return -EINVAL; } break; @@ -1854,12 +1854,12 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, uint64_t offset; if (pkt->count != 1) { - DRM_ERROR("bad INDEX_BASE\n"); + dev_warn_once(p->dev, "bad INDEX_BASE\n"); return -EINVAL; } r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("bad INDEX_BASE\n"); + dev_warn_once(p->dev, "bad INDEX_BASE\n"); return -EINVAL; } @@ -1872,7 +1872,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, r = evergreen_cs_track_check(p); if (r) { - dev_warn(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__); + dev_warn_once(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__); return r; } break; @@ -1880,7 +1880,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, case PACKET3_INDEX_BUFFER_SIZE: { if (pkt->count != 0) { - DRM_ERROR("bad INDEX_BUFFER_SIZE\n"); + dev_warn_once(p->dev, "bad INDEX_BUFFER_SIZE\n"); return -EINVAL; } break; @@ -1889,12 +1889,12 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, { uint64_t offset; if (pkt->count != 3) { - DRM_ERROR("bad DRAW_INDEX\n"); + dev_warn_once(p->dev, "bad DRAW_INDEX\n"); return -EINVAL; } r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("bad DRAW_INDEX\n"); + dev_warn_once(p->dev, "bad DRAW_INDEX\n"); return -EINVAL; } @@ -1907,7 +1907,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, r = evergreen_cs_track_check(p); if (r) { - dev_warn(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__); + dev_warn_once(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__); return r; } break; @@ -1917,12 +1917,12 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, uint64_t offset; if (pkt->count != 4) { - DRM_ERROR("bad DRAW_INDEX_2\n"); + dev_warn_once(p->dev, "bad DRAW_INDEX_2\n"); return -EINVAL; } r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("bad DRAW_INDEX_2\n"); + dev_warn_once(p->dev, "bad DRAW_INDEX_2\n"); return -EINVAL; } @@ -1935,63 +1935,63 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, r = evergreen_cs_track_check(p); if (r) { - dev_warn(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__); + dev_warn_once(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__); return r; } break; } case PACKET3_DRAW_INDEX_AUTO: if (pkt->count != 1) { - DRM_ERROR("bad DRAW_INDEX_AUTO\n"); + dev_warn_once(p->dev, "bad DRAW_INDEX_AUTO\n"); return -EINVAL; } r = evergreen_cs_track_check(p); if (r) { - dev_warn(p->dev, "%s:%d invalid cmd stream %d\n", __func__, __LINE__, idx); + dev_warn_once(p->dev, "%s:%d invalid cmd stream %d\n", __func__, __LINE__, idx); return r; } break; case PACKET3_DRAW_INDEX_MULTI_AUTO: if (pkt->count != 2) { - DRM_ERROR("bad DRAW_INDEX_MULTI_AUTO\n"); + dev_warn_once(p->dev, "bad DRAW_INDEX_MULTI_AUTO\n"); return -EINVAL; } r = evergreen_cs_track_check(p); if (r) { - dev_warn(p->dev, "%s:%d invalid cmd stream %d\n", __func__, __LINE__, idx); + dev_warn_once(p->dev, "%s:%d invalid cmd stream %d\n", __func__, __LINE__, idx); return r; } break; case PACKET3_DRAW_INDEX_IMMD: if (pkt->count < 2) { - DRM_ERROR("bad DRAW_INDEX_IMMD\n"); + dev_warn_once(p->dev, "bad DRAW_INDEX_IMMD\n"); return -EINVAL; } r = evergreen_cs_track_check(p); if (r) { - dev_warn(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__); + dev_warn_once(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__); return r; } break; case PACKET3_DRAW_INDEX_OFFSET: if (pkt->count != 2) { - DRM_ERROR("bad DRAW_INDEX_OFFSET\n"); + dev_warn_once(p->dev, "bad DRAW_INDEX_OFFSET\n"); return -EINVAL; } r = evergreen_cs_track_check(p); if (r) { - dev_warn(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__); + dev_warn_once(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__); return r; } break; case PACKET3_DRAW_INDEX_OFFSET_2: if (pkt->count != 3) { - DRM_ERROR("bad DRAW_INDEX_OFFSET_2\n"); + dev_warn_once(p->dev, "bad DRAW_INDEX_OFFSET_2\n"); return -EINVAL; } r = evergreen_cs_track_check(p); if (r) { - dev_warn(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__); + dev_warn_once(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__); return r; } break; @@ -2005,19 +2005,19 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, 4 ADDRESS_HI Bits [31:8] - Reserved. Bits [7:0] - Upper bits of Address [47:32] */ if (pkt->count != 2) { - DRM_ERROR("bad SET_BASE\n"); + dev_warn_once(p->dev, "bad SET_BASE\n"); return -EINVAL; } /* currently only supporting setting indirect draw buffer base address */ if (idx_value != 1) { - DRM_ERROR("bad SET_BASE\n"); + dev_warn_once(p->dev, "bad SET_BASE\n"); return -EINVAL; } r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("bad SET_BASE\n"); + dev_warn_once(p->dev, "bad SET_BASE\n"); return -EINVAL; } @@ -2039,54 +2039,54 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, 3 DRAW_INITIATOR Draw Initiator Register. Written to the VGT_DRAW_INITIATOR register for the assigned context */ if (pkt->count != 1) { - DRM_ERROR("bad DRAW_INDIRECT\n"); + dev_warn_once(p->dev, "bad DRAW_INDIRECT\n"); return -EINVAL; } if (idx_value + size > track->indirect_draw_buffer_size) { - dev_warn(p->dev, "DRAW_INDIRECT buffer too small %u + %llu > %lu\n", - idx_value, size, track->indirect_draw_buffer_size); + dev_warn_once(p->dev, "DRAW_INDIRECT buffer too small %u + %llu > %lu\n", + idx_value, size, track->indirect_draw_buffer_size); return -EINVAL; } r = evergreen_cs_track_check(p); if (r) { - dev_warn(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__); + dev_warn_once(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__); return r; } break; } case PACKET3_DISPATCH_DIRECT: if (pkt->count != 3) { - DRM_ERROR("bad DISPATCH_DIRECT\n"); + dev_warn_once(p->dev, "bad DISPATCH_DIRECT\n"); return -EINVAL; } r = evergreen_cs_track_check(p); if (r) { - dev_warn(p->dev, "%s:%d invalid cmd stream %d\n", __func__, __LINE__, idx); + dev_warn_once(p->dev, "%s:%d invalid cmd stream %d\n", __func__, __LINE__, idx); return r; } break; case PACKET3_DISPATCH_INDIRECT: if (pkt->count != 1) { - DRM_ERROR("bad DISPATCH_INDIRECT\n"); + dev_warn_once(p->dev, "bad DISPATCH_INDIRECT\n"); return -EINVAL; } r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("bad DISPATCH_INDIRECT\n"); + dev_warn_once(p->dev, "bad DISPATCH_INDIRECT\n"); return -EINVAL; } ib[idx+0] = idx_value + (u32)(reloc->gpu_offset & 0xffffffff); r = evergreen_cs_track_check(p); if (r) { - dev_warn(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__); + dev_warn_once(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__); return r; } break; case PACKET3_WAIT_REG_MEM: if (pkt->count != 5) { - DRM_ERROR("bad WAIT_REG_MEM\n"); + dev_warn_once(p->dev, "bad WAIT_REG_MEM\n"); return -EINVAL; } /* bit 4 is reg (0) or mem (1) */ @@ -2095,7 +2095,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("bad WAIT_REG_MEM\n"); + dev_warn_once(p->dev, "bad WAIT_REG_MEM\n"); return -EINVAL; } @@ -2106,7 +2106,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, ib[idx+1] = (ib[idx+1] & 0x3) | (offset & 0xfffffffc); ib[idx+2] = upper_32_bits(offset) & 0xff; } else if (idx_value & 0x100) { - DRM_ERROR("cannot use PFP on REG wait\n"); + dev_warn_once(p->dev, "cannot use PFP on REG wait\n"); return -EINVAL; } break; @@ -2115,7 +2115,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, u32 command, size, info; u64 offset, tmp; if (pkt->count != 4) { - DRM_ERROR("bad CP DMA\n"); + dev_warn_once(p->dev, "bad CP DMA\n"); return -EINVAL; } command = radeon_get_ib_value(p, idx+4); @@ -2129,7 +2129,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, (command & PACKET3_CP_DMA_CMD_SAS))) { /* src = register */ /* non mem to mem copies requires dw aligned count */ if (size % 4) { - DRM_ERROR("CP DMA command requires dw count alignment\n"); + dev_warn_once(p->dev, "CP DMA command requires dw count alignment\n"); return -EINVAL; } } @@ -2137,19 +2137,19 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, /* src address space is register */ /* GDS is ok */ if (((info & 0x60000000) >> 29) != 1) { - DRM_ERROR("CP DMA SAS not supported\n"); + dev_warn_once(p->dev, "CP DMA SAS not supported\n"); return -EINVAL; } } else { if (command & PACKET3_CP_DMA_CMD_SAIC) { - DRM_ERROR("CP DMA SAIC only supported for registers\n"); + dev_warn_once(p->dev, "CP DMA SAIC only supported for registers\n"); return -EINVAL; } /* src address space is memory */ if (((info & 0x60000000) >> 29) == 0) { r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("bad CP DMA SRC\n"); + dev_warn_once(p->dev, "bad CP DMA SRC\n"); return -EINVAL; } @@ -2159,15 +2159,15 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, offset = reloc->gpu_offset + tmp; if ((tmp + size) > radeon_bo_size(reloc->robj)) { - dev_warn(p->dev, "CP DMA src buffer too small (%llu %lu)\n", - tmp + size, radeon_bo_size(reloc->robj)); + dev_warn_once(p->dev, "CP DMA src buffer too small (%llu %lu)\n", + tmp + size, radeon_bo_size(reloc->robj)); return -EINVAL; } ib[idx] = offset; ib[idx+1] = (ib[idx+1] & 0xffffff00) | (upper_32_bits(offset) & 0xff); } else if (((info & 0x60000000) >> 29) != 2) { - DRM_ERROR("bad CP DMA SRC_SEL\n"); + dev_warn_once(p->dev, "bad CP DMA SRC_SEL\n"); return -EINVAL; } } @@ -2175,19 +2175,19 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, /* dst address space is register */ /* GDS is ok */ if (((info & 0x00300000) >> 20) != 1) { - DRM_ERROR("CP DMA DAS not supported\n"); + dev_warn_once(p->dev, "CP DMA DAS not supported\n"); return -EINVAL; } } else { /* dst address space is memory */ if (command & PACKET3_CP_DMA_CMD_DAIC) { - DRM_ERROR("CP DMA DAIC only supported for registers\n"); + dev_warn_once(p->dev, "CP DMA DAIC only supported for registers\n"); return -EINVAL; } if (((info & 0x00300000) >> 20) == 0) { r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("bad CP DMA DST\n"); + dev_warn_once(p->dev, "bad CP DMA DST\n"); return -EINVAL; } @@ -2197,15 +2197,15 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, offset = reloc->gpu_offset + tmp; if ((tmp + size) > radeon_bo_size(reloc->robj)) { - dev_warn(p->dev, "CP DMA dst buffer too small (%llu %lu)\n", - tmp + size, radeon_bo_size(reloc->robj)); + dev_warn_once(p->dev, "CP DMA dst buffer too small (%llu %lu)\n", + tmp + size, radeon_bo_size(reloc->robj)); return -EINVAL; } ib[idx+2] = offset; ib[idx+3] = upper_32_bits(offset) & 0xff; } else { - DRM_ERROR("bad CP DMA DST_SEL\n"); + dev_warn_once(p->dev, "bad CP DMA DST_SEL\n"); return -EINVAL; } } @@ -2213,13 +2213,13 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, } case PACKET3_PFP_SYNC_ME: if (pkt->count) { - DRM_ERROR("bad PFP_SYNC_ME\n"); + dev_warn_once(p->dev, "bad PFP_SYNC_ME\n"); return -EINVAL; } break; case PACKET3_SURFACE_SYNC: if (pkt->count != 3) { - DRM_ERROR("bad SURFACE_SYNC\n"); + dev_warn_once(p->dev, "bad SURFACE_SYNC\n"); return -EINVAL; } /* 0xffffffff/0x0 is flush all cache flag */ @@ -2227,7 +2227,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, radeon_get_ib_value(p, idx + 2) != 0) { r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("bad SURFACE_SYNC\n"); + dev_warn_once(p->dev, "bad SURFACE_SYNC\n"); return -EINVAL; } ib[idx+2] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff); @@ -2235,7 +2235,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, break; case PACKET3_EVENT_WRITE: if (pkt->count != 2 && pkt->count != 0) { - DRM_ERROR("bad EVENT_WRITE\n"); + dev_warn_once(p->dev, "bad EVENT_WRITE\n"); return -EINVAL; } if (pkt->count) { @@ -2243,7 +2243,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("bad EVENT_WRITE\n"); + dev_warn_once(p->dev, "bad EVENT_WRITE\n"); return -EINVAL; } offset = reloc->gpu_offset + @@ -2259,12 +2259,12 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, uint64_t offset; if (pkt->count != 4) { - DRM_ERROR("bad EVENT_WRITE_EOP\n"); + dev_warn_once(p->dev, "bad EVENT_WRITE_EOP\n"); return -EINVAL; } r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("bad EVENT_WRITE_EOP\n"); + dev_warn_once(p->dev, "bad EVENT_WRITE_EOP\n"); return -EINVAL; } @@ -2281,12 +2281,12 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, uint64_t offset; if (pkt->count != 3) { - DRM_ERROR("bad EVENT_WRITE_EOS\n"); + dev_warn_once(p->dev, "bad EVENT_WRITE_EOS\n"); return -EINVAL; } r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("bad EVENT_WRITE_EOS\n"); + dev_warn_once(p->dev, "bad EVENT_WRITE_EOS\n"); return -EINVAL; } @@ -2304,7 +2304,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, if ((start_reg < PACKET3_SET_CONFIG_REG_START) || (start_reg >= PACKET3_SET_CONFIG_REG_END) || (end_reg >= PACKET3_SET_CONFIG_REG_END)) { - DRM_ERROR("bad PACKET3_SET_CONFIG_REG\n"); + dev_warn_once(p->dev, "bad PACKET3_SET_CONFIG_REG\n"); return -EINVAL; } for (reg = start_reg, idx++; reg <= end_reg; reg += 4, idx++) { @@ -2321,7 +2321,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, if ((start_reg < PACKET3_SET_CONTEXT_REG_START) || (start_reg >= PACKET3_SET_CONTEXT_REG_END) || (end_reg >= PACKET3_SET_CONTEXT_REG_END)) { - DRM_ERROR("bad PACKET3_SET_CONTEXT_REG\n"); + dev_warn_once(p->dev, "bad PACKET3_SET_CONTEXT_REG\n"); return -EINVAL; } for (reg = start_reg, idx++; reg <= end_reg; reg += 4, idx++) { @@ -2334,7 +2334,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, break; case PACKET3_SET_RESOURCE: if (pkt->count % 8) { - DRM_ERROR("bad SET_RESOURCE\n"); + dev_warn_once(p->dev, "bad SET_RESOURCE\n"); return -EINVAL; } start_reg = (idx_value << 2) + PACKET3_SET_RESOURCE_START; @@ -2342,7 +2342,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, if ((start_reg < PACKET3_SET_RESOURCE_START) || (start_reg >= PACKET3_SET_RESOURCE_END) || (end_reg >= PACKET3_SET_RESOURCE_END)) { - DRM_ERROR("bad SET_RESOURCE\n"); + dev_warn_once(p->dev, "bad SET_RESOURCE\n"); return -EINVAL; } for (i = 0; i < (pkt->count / 8); i++) { @@ -2355,7 +2355,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, /* tex base */ r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("bad SET_RESOURCE (tex)\n"); + dev_warn_once(p->dev, "bad SET_RESOURCE (tex)\n"); return -EINVAL; } if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) { @@ -2392,7 +2392,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, } else { r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("bad SET_RESOURCE (tex)\n"); + dev_warn_once(p->dev, "bad SET_RESOURCE (tex)\n"); return -EINVAL; } moffset = (u32)((reloc->gpu_offset >> 8) & 0xffffffff); @@ -2411,14 +2411,15 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, /* vtx base */ r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("bad SET_RESOURCE (vtx)\n"); + dev_warn_once(p->dev, "bad SET_RESOURCE (vtx)\n"); return -EINVAL; } offset = radeon_get_ib_value(p, idx+1+(i*8)+0); size = radeon_get_ib_value(p, idx+1+(i*8)+1); if (p->rdev && (size + offset) > radeon_bo_size(reloc->robj)) { /* force size to size of the buffer */ - dev_warn_ratelimited(p->dev, "vbo resource seems too big for the bo\n"); + dev_warn_once(p->dev, "vbo resource seems too big (%d) for the bo (%ld)\n", + size + offset, radeon_bo_size(reloc->robj)); ib[idx+1+(i*8)+1] = radeon_bo_size(reloc->robj) - offset; } @@ -2431,7 +2432,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, case SQ_TEX_VTX_INVALID_TEXTURE: case SQ_TEX_VTX_INVALID_BUFFER: default: - DRM_ERROR("bad SET_RESOURCE\n"); + dev_warn_once(p->dev, "bad SET_RESOURCE\n"); return -EINVAL; } } @@ -2445,7 +2446,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, if ((start_reg < PACKET3_SET_BOOL_CONST_START) || (start_reg >= PACKET3_SET_BOOL_CONST_END) || (end_reg >= PACKET3_SET_BOOL_CONST_END)) { - DRM_ERROR("bad SET_BOOL_CONST\n"); + dev_warn_once(p->dev, "bad SET_BOOL_CONST\n"); return -EINVAL; } break; @@ -2455,7 +2456,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, if ((start_reg < PACKET3_SET_LOOP_CONST_START) || (start_reg >= PACKET3_SET_LOOP_CONST_END) || (end_reg >= PACKET3_SET_LOOP_CONST_END)) { - DRM_ERROR("bad SET_LOOP_CONST\n"); + dev_warn_once(p->dev, "bad SET_LOOP_CONST\n"); return -EINVAL; } break; @@ -2465,13 +2466,13 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, if ((start_reg < PACKET3_SET_CTL_CONST_START) || (start_reg >= PACKET3_SET_CTL_CONST_END) || (end_reg >= PACKET3_SET_CTL_CONST_END)) { - DRM_ERROR("bad SET_CTL_CONST\n"); + dev_warn_once(p->dev, "bad SET_CTL_CONST\n"); return -EINVAL; } break; case PACKET3_SET_SAMPLER: if (pkt->count % 3) { - DRM_ERROR("bad SET_SAMPLER\n"); + dev_warn_once(p->dev, "bad SET_SAMPLER\n"); return -EINVAL; } start_reg = (idx_value << 2) + PACKET3_SET_SAMPLER_START; @@ -2479,13 +2480,13 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, if ((start_reg < PACKET3_SET_SAMPLER_START) || (start_reg >= PACKET3_SET_SAMPLER_END) || (end_reg >= PACKET3_SET_SAMPLER_END)) { - DRM_ERROR("bad SET_SAMPLER\n"); + dev_warn_once(p->dev, "bad SET_SAMPLER\n"); return -EINVAL; } break; case PACKET3_STRMOUT_BUFFER_UPDATE: if (pkt->count != 4) { - DRM_ERROR("bad STRMOUT_BUFFER_UPDATE (invalid count)\n"); + dev_warn_once(p->dev, "bad STRMOUT_BUFFER_UPDATE (invalid count)\n"); return -EINVAL; } /* Updating memory at DST_ADDRESS. */ @@ -2493,14 +2494,14 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, u64 offset; r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("bad STRMOUT_BUFFER_UPDATE (missing dst reloc)\n"); + dev_warn_once(p->dev, "bad STRMOUT_BUFFER_UPDATE (missing dst reloc)\n"); return -EINVAL; } offset = radeon_get_ib_value(p, idx+1); offset += ((u64)(radeon_get_ib_value(p, idx+2) & 0xff)) << 32; if ((offset + 4) > radeon_bo_size(reloc->robj)) { - DRM_ERROR("bad STRMOUT_BUFFER_UPDATE dst bo too small: 0x%llx, 0x%lx\n", - offset + 4, radeon_bo_size(reloc->robj)); + dev_warn_once(p->dev, "bad STRMOUT_BUFFER_UPDATE dst bo too small: 0x%llx, 0x%lx\n", + offset + 4, radeon_bo_size(reloc->robj)); return -EINVAL; } offset += reloc->gpu_offset; @@ -2512,14 +2513,14 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, u64 offset; r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("bad STRMOUT_BUFFER_UPDATE (missing src reloc)\n"); + dev_warn_once(p->dev, "bad STRMOUT_BUFFER_UPDATE (missing src reloc)\n"); return -EINVAL; } offset = radeon_get_ib_value(p, idx+3); offset += ((u64)(radeon_get_ib_value(p, idx+4) & 0xff)) << 32; if ((offset + 4) > radeon_bo_size(reloc->robj)) { - DRM_ERROR("bad STRMOUT_BUFFER_UPDATE src bo too small: 0x%llx, 0x%lx\n", - offset + 4, radeon_bo_size(reloc->robj)); + dev_warn_once(p->dev, "bad STRMOUT_BUFFER_UPDATE src bo too small: 0x%llx, 0x%lx\n", + offset + 4, radeon_bo_size(reloc->robj)); return -EINVAL; } offset += reloc->gpu_offset; @@ -2532,23 +2533,23 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, u64 offset; if (pkt->count != 3) { - DRM_ERROR("bad MEM_WRITE (invalid count)\n"); + dev_warn_once(p->dev, "bad MEM_WRITE (invalid count)\n"); return -EINVAL; } r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("bad MEM_WRITE (missing reloc)\n"); + dev_warn_once(p->dev, "bad MEM_WRITE (missing reloc)\n"); return -EINVAL; } offset = radeon_get_ib_value(p, idx+0); offset += ((u64)(radeon_get_ib_value(p, idx+1) & 0xff)) << 32UL; if (offset & 0x7) { - DRM_ERROR("bad MEM_WRITE (address not qwords aligned)\n"); + dev_warn_once(p->dev, "bad MEM_WRITE (address not qwords aligned)\n"); return -EINVAL; } if ((offset + 8) > radeon_bo_size(reloc->robj)) { - DRM_ERROR("bad MEM_WRITE bo too small: 0x%llx, 0x%lx\n", - offset + 8, radeon_bo_size(reloc->robj)); + dev_warn_once(p->dev, "bad MEM_WRITE bo too small: 0x%llx, 0x%lx\n", + offset + 8, radeon_bo_size(reloc->robj)); return -EINVAL; } offset += reloc->gpu_offset; @@ -2558,7 +2559,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, } case PACKET3_COPY_DW: if (pkt->count != 4) { - DRM_ERROR("bad COPY_DW (invalid count)\n"); + dev_warn_once(p->dev, "bad COPY_DW (invalid count)\n"); return -EINVAL; } if (idx_value & 0x1) { @@ -2566,14 +2567,14 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, /* SRC is memory. */ r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("bad COPY_DW (missing src reloc)\n"); + dev_warn_once(p->dev, "bad COPY_DW (missing src reloc)\n"); return -EINVAL; } offset = radeon_get_ib_value(p, idx+1); offset += ((u64)(radeon_get_ib_value(p, idx+2) & 0xff)) << 32; if ((offset + 4) > radeon_bo_size(reloc->robj)) { - DRM_ERROR("bad COPY_DW src bo too small: 0x%llx, 0x%lx\n", - offset + 4, radeon_bo_size(reloc->robj)); + dev_warn_once(p->dev, "bad COPY_DW src bo too small: 0x%llx, 0x%lx\n", + offset + 4, radeon_bo_size(reloc->robj)); return -EINVAL; } offset += reloc->gpu_offset; @@ -2583,8 +2584,8 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, /* SRC is a reg. */ reg = radeon_get_ib_value(p, idx+1) << 2; if (!evergreen_is_safe_reg(p, reg)) { - dev_warn(p->dev, "forbidden register 0x%08x at %d\n", - reg, idx + 1); + dev_warn_once(p->dev, "forbidden register 0x%08x at %d\n", + reg, idx + 1); return -EINVAL; } } @@ -2593,14 +2594,14 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, /* DST is memory. */ r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("bad COPY_DW (missing dst reloc)\n"); + dev_warn_once(p->dev, "bad COPY_DW (missing dst reloc)\n"); return -EINVAL; } offset = radeon_get_ib_value(p, idx+3); offset += ((u64)(radeon_get_ib_value(p, idx+4) & 0xff)) << 32; if ((offset + 4) > radeon_bo_size(reloc->robj)) { - DRM_ERROR("bad COPY_DW dst bo too small: 0x%llx, 0x%lx\n", - offset + 4, radeon_bo_size(reloc->robj)); + dev_warn_once(p->dev, "bad COPY_DW dst bo too small: 0x%llx, 0x%lx\n", + offset + 4, radeon_bo_size(reloc->robj)); return -EINVAL; } offset += reloc->gpu_offset; @@ -2610,8 +2611,8 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, /* DST is a reg. */ reg = radeon_get_ib_value(p, idx+3) << 2; if (!evergreen_is_safe_reg(p, reg)) { - dev_warn(p->dev, "forbidden register 0x%08x at %d\n", - reg, idx + 3); + dev_warn_once(p->dev, "forbidden register 0x%08x at %d\n", + reg, idx + 3); return -EINVAL; } } @@ -2622,7 +2623,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, uint32_t allowed_reg_base; uint32_t source_sel; if (pkt->count != 2) { - DRM_ERROR("bad SET_APPEND_CNT (invalid count)\n"); + dev_warn_once(p->dev, "bad SET_APPEND_CNT (invalid count)\n"); return -EINVAL; } @@ -2632,8 +2633,8 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, areg = idx_value >> 16; if (areg < allowed_reg_base || areg > (allowed_reg_base + 11)) { - dev_warn(p->dev, "forbidden register for append cnt 0x%08x at %d\n", - areg, idx); + dev_warn_once(p->dev, "forbidden register for append cnt 0x%08x at %d\n", + areg, idx); return -EINVAL; } @@ -2643,7 +2644,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, uint32_t swap; r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("bad SET_APPEND_CNT (missing reloc)\n"); + dev_warn_once(p->dev, "bad SET_APPEND_CNT (missing reloc)\n"); return -EINVAL; } offset = radeon_get_ib_value(p, idx + 1); @@ -2656,7 +2657,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, ib[idx+1] = (offset & 0xfffffffc) | swap; ib[idx+2] = upper_32_bits(offset) & 0xff; } else { - DRM_ERROR("bad SET_APPEND_CNT (unsupported operation)\n"); + dev_warn_once(p->dev, "bad SET_APPEND_CNT (unsupported operation)\n"); return -EINVAL; } break; @@ -2666,23 +2667,23 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, u64 offset; if (pkt->count != 2) { - DRM_ERROR("bad COND_EXEC (invalid count)\n"); + dev_warn_once(p->dev, "bad COND_EXEC (invalid count)\n"); return -EINVAL; } r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("bad COND_EXEC (missing reloc)\n"); + dev_warn_once(p->dev, "bad COND_EXEC (missing reloc)\n"); return -EINVAL; } offset = radeon_get_ib_value(p, idx + 0); offset += ((u64)(radeon_get_ib_value(p, idx + 1) & 0xff)) << 32UL; if (offset & 0x7) { - DRM_ERROR("bad COND_EXEC (address not qwords aligned)\n"); + dev_warn_once(p->dev, "bad COND_EXEC (address not qwords aligned)\n"); return -EINVAL; } if ((offset + 8) > radeon_bo_size(reloc->robj)) { - DRM_ERROR("bad COND_EXEC bo too small: 0x%llx, 0x%lx\n", - offset + 8, radeon_bo_size(reloc->robj)); + dev_warn_once(p->dev, "bad COND_EXEC bo too small: 0x%llx, 0x%lx\n", + offset + 8, radeon_bo_size(reloc->robj)); return -EINVAL; } offset += reloc->gpu_offset; @@ -2692,7 +2693,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, } case PACKET3_COND_WRITE: if (pkt->count != 7) { - DRM_ERROR("bad COND_WRITE (invalid count)\n"); + dev_warn_once(p->dev, "bad COND_WRITE (invalid count)\n"); return -EINVAL; } if (idx_value & 0x10) { @@ -2700,14 +2701,14 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, /* POLL is memory. */ r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("bad COND_WRITE (missing src reloc)\n"); + dev_warn_once(p->dev, "bad COND_WRITE (missing src reloc)\n"); return -EINVAL; } offset = radeon_get_ib_value(p, idx + 1); offset += ((u64)(radeon_get_ib_value(p, idx + 2) & 0xff)) << 32; if ((offset + 8) > radeon_bo_size(reloc->robj)) { - DRM_ERROR("bad COND_WRITE src bo too small: 0x%llx, 0x%lx\n", - offset + 8, radeon_bo_size(reloc->robj)); + dev_warn_once(p->dev, "bad COND_WRITE src bo too small: 0x%llx, 0x%lx\n", + offset + 8, radeon_bo_size(reloc->robj)); return -EINVAL; } offset += reloc->gpu_offset; @@ -2717,8 +2718,8 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, /* POLL is a reg. */ reg = radeon_get_ib_value(p, idx + 1) << 2; if (!evergreen_is_safe_reg(p, reg)) { - dev_warn(p->dev, "forbidden register 0x%08x at %d\n", - reg, idx + 1); + dev_warn_once(p->dev, "forbidden register 0x%08x at %d\n", + reg, idx + 1); return -EINVAL; } } @@ -2727,14 +2728,14 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, /* WRITE is memory. */ r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("bad COND_WRITE (missing dst reloc)\n"); + dev_warn_once(p->dev, "bad COND_WRITE (missing dst reloc)\n"); return -EINVAL; } offset = radeon_get_ib_value(p, idx + 5); offset += ((u64)(radeon_get_ib_value(p, idx + 6) & 0xff)) << 32; if ((offset + 8) > radeon_bo_size(reloc->robj)) { - DRM_ERROR("bad COND_WRITE dst bo too small: 0x%llx, 0x%lx\n", - offset + 8, radeon_bo_size(reloc->robj)); + dev_warn_once(p->dev, "bad COND_WRITE dst bo too small: 0x%llx, 0x%lx\n", + offset + 8, radeon_bo_size(reloc->robj)); return -EINVAL; } offset += reloc->gpu_offset; @@ -2744,8 +2745,8 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, /* WRITE is a reg. */ reg = radeon_get_ib_value(p, idx + 5) << 2; if (!evergreen_is_safe_reg(p, reg)) { - dev_warn(p->dev, "forbidden register 0x%08x at %d\n", - reg, idx + 5); + dev_warn_once(p->dev, "forbidden register 0x%08x at %d\n", + reg, idx + 5); return -EINVAL; } } @@ -2753,7 +2754,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, case PACKET3_NOP: break; default: - DRM_ERROR("Packet3 opcode %x not supported\n", pkt->opcode); + dev_warn_once(p->dev, "Packet3 opcode %x not supported\n", pkt->opcode); return -EINVAL; } return 0; @@ -2853,7 +2854,7 @@ int evergreen_cs_parse(struct radeon_cs_parser *p) r = evergreen_packet3_check(p, &pkt); break; default: - DRM_ERROR("Unknown packet type %d !\n", pkt.type); + dev_warn_once(p->dev, "Unknown packet type %d !\n", pkt.type); kfree(p->track); p->track = NULL; return -EINVAL; @@ -2896,8 +2897,8 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p) do { if (p->idx >= ib_chunk->length_dw) { - DRM_ERROR("Can not parse packet at %d after CS end %d !\n", - p->idx, ib_chunk->length_dw); + dev_warn_once(p->dev, "Can not parse packet at %d after CS end %d !\n", + p->idx, ib_chunk->length_dw); return -EINVAL; } idx = p->idx; @@ -2910,7 +2911,7 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p) case DMA_PACKET_WRITE: r = r600_dma_cs_next_reloc(p, &dst_reloc); if (r) { - DRM_ERROR("bad DMA_PACKET_WRITE\n"); + dev_warn_once(p->dev, "bad DMA_PACKET_WRITE\n"); return -EINVAL; } switch (sub_cmd) { @@ -2932,24 +2933,24 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p) p->idx += count + 3; break; default: - DRM_ERROR("bad DMA_PACKET_WRITE [%6d] 0x%08x sub cmd is not 0 or 8\n", idx, header); + dev_warn_once(p->dev, "bad DMA_PACKET_WRITE [%6d] 0x%08x sub cmd is not 0 or 8\n", idx, header); return -EINVAL; } if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) { - dev_warn(p->dev, "DMA write buffer too small (%llu %lu)\n", - dst_offset, radeon_bo_size(dst_reloc->robj)); + dev_warn_once(p->dev, "DMA write buffer too small (%llu %lu)\n", + dst_offset, radeon_bo_size(dst_reloc->robj)); return -EINVAL; } break; case DMA_PACKET_COPY: r = r600_dma_cs_next_reloc(p, &src_reloc); if (r) { - DRM_ERROR("bad DMA_PACKET_COPY\n"); + dev_warn_once(p->dev, "bad DMA_PACKET_COPY\n"); return -EINVAL; } r = r600_dma_cs_next_reloc(p, &dst_reloc); if (r) { - DRM_ERROR("bad DMA_PACKET_COPY\n"); + dev_warn_once(p->dev, "bad DMA_PACKET_COPY\n"); return -EINVAL; } switch (sub_cmd) { @@ -2961,13 +2962,13 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p) dst_offset = radeon_get_ib_value(p, idx+1); dst_offset |= ((u64)(radeon_get_ib_value(p, idx+3) & 0xff)) << 32; if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) { - dev_warn(p->dev, "DMA L2L, dw src buffer too small (%llu %lu)\n", - src_offset + (count * 4), radeon_bo_size(src_reloc->robj)); + dev_warn_once(p->dev, "DMA L2L, dw src buffer too small (%llu %lu)\n", + src_offset + (count * 4), radeon_bo_size(src_reloc->robj)); return -EINVAL; } if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) { - dev_warn(p->dev, "DMA L2L, dw dst buffer too small (%llu %lu)\n", - dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj)); + dev_warn_once(p->dev, "DMA L2L, dw dst buffer too small (%llu %lu)\n", + dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj)); return -EINVAL; } ib[idx+1] += (u32)(dst_reloc->gpu_offset & 0xfffffffc); @@ -3001,13 +3002,13 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p) ib[idx+1] += (u32)(dst_reloc->gpu_offset >> 8); } if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) { - dev_warn(p->dev, "DMA L2T, src buffer too small (%llu %lu)\n", - src_offset + (count * 4), radeon_bo_size(src_reloc->robj)); + dev_warn_once(p->dev, "DMA L2T, src buffer too small (%llu %lu)\n", + src_offset + (count * 4), radeon_bo_size(src_reloc->robj)); return -EINVAL; } if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) { - dev_warn(p->dev, "DMA L2T, dst buffer too small (%llu %lu)\n", - dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj)); + dev_warn_once(p->dev, "DMA L2T, dst buffer too small (%llu %lu)\n", + dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj)); return -EINVAL; } p->idx += 9; @@ -3020,13 +3021,13 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p) dst_offset = radeon_get_ib_value(p, idx+1); dst_offset |= ((u64)(radeon_get_ib_value(p, idx+3) & 0xff)) << 32; if ((src_offset + count) > radeon_bo_size(src_reloc->robj)) { - dev_warn(p->dev, "DMA L2L, byte src buffer too small (%llu %lu)\n", - src_offset + count, radeon_bo_size(src_reloc->robj)); + dev_warn_once(p->dev, "DMA L2L, byte src buffer too small (%llu %lu)\n", + src_offset + count, radeon_bo_size(src_reloc->robj)); return -EINVAL; } if ((dst_offset + count) > radeon_bo_size(dst_reloc->robj)) { - dev_warn(p->dev, "DMA L2L, byte dst buffer too small (%llu %lu)\n", - dst_offset + count, radeon_bo_size(dst_reloc->robj)); + dev_warn_once(p->dev, "DMA L2L, byte dst buffer too small (%llu %lu)\n", + dst_offset + count, radeon_bo_size(dst_reloc->robj)); return -EINVAL; } ib[idx+1] += (u32)(dst_reloc->gpu_offset & 0xffffffff); @@ -3039,7 +3040,7 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p) case 0x41: /* L2L, partial */ if (p->family < CHIP_CAYMAN) { - DRM_ERROR("L2L Partial is cayman only !\n"); + dev_warn_once(p->dev, "L2L Partial is cayman only !\n"); return -EINVAL; } ib[idx+1] += (u32)(src_reloc->gpu_offset & 0xffffffff); @@ -3054,7 +3055,7 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p) /* L2L, dw, broadcast */ r = r600_dma_cs_next_reloc(p, &dst2_reloc); if (r) { - DRM_ERROR("bad L2L, dw, broadcast DMA_PACKET_COPY\n"); + dev_warn_once(p->dev, "bad L2L, dw, broadcast DMA_PACKET_COPY\n"); return -EINVAL; } dst_offset = radeon_get_ib_value(p, idx+1); @@ -3064,18 +3065,18 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p) src_offset = radeon_get_ib_value(p, idx+3); src_offset |= ((u64)(radeon_get_ib_value(p, idx+6) & 0xff)) << 32; if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) { - dev_warn(p->dev, "DMA L2L, dw, broadcast src buffer too small (%llu %lu)\n", - src_offset + (count * 4), radeon_bo_size(src_reloc->robj)); + dev_warn_once(p->dev, "DMA L2L, dw, broadcast src buffer too small (%llu %lu)\n", + src_offset + (count * 4), radeon_bo_size(src_reloc->robj)); return -EINVAL; } if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) { - dev_warn(p->dev, "DMA L2L, dw, broadcast dst buffer too small (%llu %lu)\n", - dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj)); + dev_warn_once(p->dev, "DMA L2L, dw, broadcast dst buffer too small (%llu %lu)\n", + dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj)); return -EINVAL; } if ((dst2_offset + (count * 4)) > radeon_bo_size(dst2_reloc->robj)) { - dev_warn(p->dev, "DMA L2L, dw, broadcast dst2 buffer too small (%llu %lu)\n", - dst2_offset + (count * 4), radeon_bo_size(dst2_reloc->robj)); + dev_warn_once(p->dev, "DMA L2L, dw, broadcast dst2 buffer too small (%llu %lu)\n", + dst2_offset + (count * 4), radeon_bo_size(dst2_reloc->robj)); return -EINVAL; } ib[idx+1] += (u32)(dst_reloc->gpu_offset & 0xfffffffc); @@ -3089,12 +3090,12 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p) /* Copy L2T Frame to Field */ case 0x48: if (radeon_get_ib_value(p, idx + 2) & (1 << 31)) { - DRM_ERROR("bad L2T, frame to fields DMA_PACKET_COPY\n"); + dev_warn_once(p->dev, "bad L2T, frame to fields DMA_PACKET_COPY\n"); return -EINVAL; } r = r600_dma_cs_next_reloc(p, &dst2_reloc); if (r) { - DRM_ERROR("bad L2T, frame to fields DMA_PACKET_COPY\n"); + dev_warn_once(p->dev, "bad L2T, frame to fields DMA_PACKET_COPY\n"); return -EINVAL; } dst_offset = radeon_get_ib_value(p, idx+1); @@ -3104,18 +3105,18 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p) src_offset = radeon_get_ib_value(p, idx+8); src_offset |= ((u64)(radeon_get_ib_value(p, idx+9) & 0xff)) << 32; if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) { - dev_warn(p->dev, "DMA L2T, frame to fields src buffer too small (%llu %lu)\n", - src_offset + (count * 4), radeon_bo_size(src_reloc->robj)); + dev_warn_once(p->dev, "DMA L2T, frame to fields src buffer too small (%llu %lu)\n", + src_offset + (count * 4), radeon_bo_size(src_reloc->robj)); return -EINVAL; } if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) { - dev_warn(p->dev, "DMA L2T, frame to fields buffer too small (%llu %lu)\n", - dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj)); + dev_warn_once(p->dev, "DMA L2T, frame to fields buffer too small (%llu %lu)\n", + dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj)); return -EINVAL; } if ((dst2_offset + (count * 4)) > radeon_bo_size(dst2_reloc->robj)) { - dev_warn(p->dev, "DMA L2T, frame to fields buffer too small (%llu %lu)\n", - dst2_offset + (count * 4), radeon_bo_size(dst2_reloc->robj)); + dev_warn_once(p->dev, "DMA L2T, frame to fields buffer too small (%llu %lu)\n", + dst2_offset + (count * 4), radeon_bo_size(dst2_reloc->robj)); return -EINVAL; } ib[idx+1] += (u32)(dst_reloc->gpu_offset >> 8); @@ -3128,7 +3129,7 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p) case 0x49: /* L2T, T2L partial */ if (p->family < CHIP_CAYMAN) { - DRM_ERROR("L2T, T2L Partial is cayman only !\n"); + dev_warn_once(p->dev, "L2T, T2L Partial is cayman only !\n"); return -EINVAL; } /* detile bit */ @@ -3151,12 +3152,12 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p) case 0x4b: /* L2T, broadcast */ if (radeon_get_ib_value(p, idx + 2) & (1 << 31)) { - DRM_ERROR("bad L2T, broadcast DMA_PACKET_COPY\n"); + dev_warn_once(p->dev, "bad L2T, broadcast DMA_PACKET_COPY\n"); return -EINVAL; } r = r600_dma_cs_next_reloc(p, &dst2_reloc); if (r) { - DRM_ERROR("bad L2T, broadcast DMA_PACKET_COPY\n"); + dev_warn_once(p->dev, "bad L2T, broadcast DMA_PACKET_COPY\n"); return -EINVAL; } dst_offset = radeon_get_ib_value(p, idx+1); @@ -3166,18 +3167,18 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p) src_offset = radeon_get_ib_value(p, idx+8); src_offset |= ((u64)(radeon_get_ib_value(p, idx+9) & 0xff)) << 32; if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) { - dev_warn(p->dev, "DMA L2T, broadcast src buffer too small (%llu %lu)\n", - src_offset + (count * 4), radeon_bo_size(src_reloc->robj)); + dev_warn_once(p->dev, "DMA L2T, broadcast src buffer too small (%llu %lu)\n", + src_offset + (count * 4), radeon_bo_size(src_reloc->robj)); return -EINVAL; } if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) { - dev_warn(p->dev, "DMA L2T, broadcast dst buffer too small (%llu %lu)\n", - dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj)); + dev_warn_once(p->dev, "DMA L2T, broadcast dst buffer too small (%llu %lu)\n", + dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj)); return -EINVAL; } if ((dst2_offset + (count * 4)) > radeon_bo_size(dst2_reloc->robj)) { - dev_warn(p->dev, "DMA L2T, broadcast dst2 buffer too small (%llu %lu)\n", - dst2_offset + (count * 4), radeon_bo_size(dst2_reloc->robj)); + dev_warn_once(p->dev, "DMA L2T, broadcast dst2 buffer too small (%llu %lu)\n", + dst2_offset + (count * 4), radeon_bo_size(dst2_reloc->robj)); return -EINVAL; } ib[idx+1] += (u32)(dst_reloc->gpu_offset >> 8); @@ -3212,13 +3213,13 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p) ib[idx+1] += (u32)(dst_reloc->gpu_offset >> 8); } if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) { - dev_warn(p->dev, "DMA L2T, T2L src buffer too small (%llu %lu)\n", - src_offset + (count * 4), radeon_bo_size(src_reloc->robj)); + dev_warn_once(p->dev, "DMA L2T, T2L src buffer too small (%llu %lu)\n", + src_offset + (count * 4), radeon_bo_size(src_reloc->robj)); return -EINVAL; } if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) { - dev_warn(p->dev, "DMA L2T, T2L dst buffer too small (%llu %lu)\n", - dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj)); + dev_warn_once(p->dev, "DMA L2T, T2L dst buffer too small (%llu %lu)\n", + dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj)); return -EINVAL; } p->idx += 9; @@ -3227,7 +3228,7 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p) case 0x4d: /* T2T partial */ if (p->family < CHIP_CAYMAN) { - DRM_ERROR("L2T, T2L Partial is cayman only !\n"); + dev_warn_once(p->dev, "L2T, T2L Partial is cayman only !\n"); return -EINVAL; } ib[idx+1] += (u32)(src_reloc->gpu_offset >> 8); @@ -3238,12 +3239,12 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p) case 0x4f: /* L2T, broadcast */ if (radeon_get_ib_value(p, idx + 2) & (1 << 31)) { - DRM_ERROR("bad L2T, broadcast DMA_PACKET_COPY\n"); + dev_warn_once(p->dev, "bad L2T, broadcast DMA_PACKET_COPY\n"); return -EINVAL; } r = r600_dma_cs_next_reloc(p, &dst2_reloc); if (r) { - DRM_ERROR("bad L2T, broadcast DMA_PACKET_COPY\n"); + dev_warn_once(p->dev, "bad L2T, broadcast DMA_PACKET_COPY\n"); return -EINVAL; } dst_offset = radeon_get_ib_value(p, idx+1); @@ -3253,18 +3254,18 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p) src_offset = radeon_get_ib_value(p, idx+8); src_offset |= ((u64)(radeon_get_ib_value(p, idx+9) & 0xff)) << 32; if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) { - dev_warn(p->dev, "DMA L2T, broadcast src buffer too small (%llu %lu)\n", - src_offset + (count * 4), radeon_bo_size(src_reloc->robj)); + dev_warn_once(p->dev, "DMA L2T, broadcast src buffer too small (%llu %lu)\n", + src_offset + (count * 4), radeon_bo_size(src_reloc->robj)); return -EINVAL; } if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) { - dev_warn(p->dev, "DMA L2T, broadcast dst buffer too small (%llu %lu)\n", - dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj)); + dev_warn_once(p->dev, "DMA L2T, broadcast dst buffer too small (%llu %lu)\n", + dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj)); return -EINVAL; } if ((dst2_offset + (count * 4)) > radeon_bo_size(dst2_reloc->robj)) { - dev_warn(p->dev, "DMA L2T, broadcast dst2 buffer too small (%llu %lu)\n", - dst2_offset + (count * 4), radeon_bo_size(dst2_reloc->robj)); + dev_warn_once(p->dev, "DMA L2T, broadcast dst2 buffer too small (%llu %lu)\n", + dst2_offset + (count * 4), radeon_bo_size(dst2_reloc->robj)); return -EINVAL; } ib[idx+1] += (u32)(dst_reloc->gpu_offset >> 8); @@ -3274,21 +3275,21 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p) p->idx += 10; break; default: - DRM_ERROR("bad DMA_PACKET_COPY [%6d] 0x%08x invalid sub cmd\n", idx, header); + dev_warn_once(p->dev, "bad DMA_PACKET_COPY [%6d] 0x%08x invalid sub cmd\n", idx, header); return -EINVAL; } break; case DMA_PACKET_CONSTANT_FILL: r = r600_dma_cs_next_reloc(p, &dst_reloc); if (r) { - DRM_ERROR("bad DMA_PACKET_CONSTANT_FILL\n"); + dev_warn_once(p->dev, "bad DMA_PACKET_CONSTANT_FILL\n"); return -EINVAL; } dst_offset = radeon_get_ib_value(p, idx+1); dst_offset |= ((u64)(radeon_get_ib_value(p, idx+3) & 0x00ff0000)) << 16; if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) { - dev_warn(p->dev, "DMA constant fill buffer too small (%llu %lu)\n", - dst_offset, radeon_bo_size(dst_reloc->robj)); + dev_warn_once(p->dev, "DMA constant fill buffer too small (%llu %lu)\n", + dst_offset, radeon_bo_size(dst_reloc->robj)); return -EINVAL; } ib[idx+1] += (u32)(dst_reloc->gpu_offset & 0xfffffffc); @@ -3299,7 +3300,7 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p) p->idx += 1; break; default: - DRM_ERROR("Unknown packet type %d at %d !\n", cmd, idx); + dev_warn_once(p->dev, "Unknown packet type %d at %d !\n", cmd, idx); return -EINVAL; } } while (p->idx < p->chunk_ib->length_dw); @@ -3430,7 +3431,7 @@ static bool evergreen_vm_reg_valid(u32 reg) case CAYMAN_SQ_EX_ALLOC_TABLE_SLOTS: return true; default: - DRM_ERROR("Invalid register 0x%x in CS\n", reg); + DRM_DEBUG("Invalid register 0x%x in CS\n", reg); return false; } } @@ -3448,7 +3449,7 @@ static int evergreen_vm_packet3_check(struct radeon_device *rdev, break; case PACKET3_SET_BASE: if (idx_value != 1) { - DRM_ERROR("bad SET_BASE"); + dev_warn_once(rdev->dev, "bad SET_BASE"); return -EINVAL; } break; @@ -3519,7 +3520,7 @@ static int evergreen_vm_packet3_check(struct radeon_device *rdev, if ((start_reg < PACKET3_SET_CONFIG_REG_START) || (start_reg >= PACKET3_SET_CONFIG_REG_END) || (end_reg >= PACKET3_SET_CONFIG_REG_END)) { - DRM_ERROR("bad PACKET3_SET_CONFIG_REG\n"); + dev_warn_once(rdev->dev, "bad PACKET3_SET_CONFIG_REG\n"); return -EINVAL; } for (i = 0; i < pkt->count; i++) { @@ -3539,7 +3540,7 @@ static int evergreen_vm_packet3_check(struct radeon_device *rdev, (command & PACKET3_CP_DMA_CMD_SAS))) { /* src = register */ /* non mem to mem copies requires dw aligned count */ if ((command & 0x1fffff) % 4) { - DRM_ERROR("CP DMA command requires dw count alignment\n"); + dev_warn_once(rdev->dev, "CP DMA command requires dw count alignment\n"); return -EINVAL; } } @@ -3550,14 +3551,14 @@ static int evergreen_vm_packet3_check(struct radeon_device *rdev, if (command & PACKET3_CP_DMA_CMD_SAIC) { reg = start_reg; if (!evergreen_vm_reg_valid(reg)) { - DRM_ERROR("CP DMA Bad SRC register\n"); + dev_warn_once(rdev->dev, "CP DMA Bad SRC register\n"); return -EINVAL; } } else { for (i = 0; i < (command & 0x1fffff); i++) { reg = start_reg + (4 * i); if (!evergreen_vm_reg_valid(reg)) { - DRM_ERROR("CP DMA Bad SRC register\n"); + dev_warn_once(rdev->dev, "CP DMA Bad SRC register\n"); return -EINVAL; } } @@ -3571,14 +3572,14 @@ static int evergreen_vm_packet3_check(struct radeon_device *rdev, if (command & PACKET3_CP_DMA_CMD_DAIC) { reg = start_reg; if (!evergreen_vm_reg_valid(reg)) { - DRM_ERROR("CP DMA Bad DST register\n"); + dev_warn_once(rdev->dev, "CP DMA Bad DST register\n"); return -EINVAL; } } else { for (i = 0; i < (command & 0x1fffff); i++) { reg = start_reg + (4 * i); if (!evergreen_vm_reg_valid(reg)) { - DRM_ERROR("CP DMA Bad DST register\n"); + dev_warn_once(rdev->dev, "CP DMA Bad DST register\n"); return -EINVAL; } } @@ -3591,7 +3592,7 @@ static int evergreen_vm_packet3_check(struct radeon_device *rdev, uint32_t allowed_reg_base; if (pkt->count != 2) { - DRM_ERROR("bad SET_APPEND_CNT (invalid count)\n"); + dev_warn_once(rdev->dev, "bad SET_APPEND_CNT (invalid count)\n"); return -EINVAL; } @@ -3601,8 +3602,8 @@ static int evergreen_vm_packet3_check(struct radeon_device *rdev, areg = idx_value >> 16; if (areg < allowed_reg_base || areg > (allowed_reg_base + 11)) { - DRM_ERROR("forbidden register for append cnt 0x%08x at %d\n", - areg, idx); + dev_warn_once(rdev->dev, "forbidden register for append cnt 0x%08x at %d\n", + areg, idx); return -EINVAL; } break; @@ -3681,7 +3682,9 @@ int evergreen_dma_ib_parse(struct radeon_device *rdev, struct radeon_ib *ib) idx += count + 3; break; default: - DRM_ERROR("bad DMA_PACKET_WRITE [%6d] 0x%08x sub cmd is not 0 or 8\n", idx, ib->ptr[idx]); + dev_warn_once(rdev->dev, + "bad DMA_PACKET_WRITE [%6d] 0x%08x sub cmd is not 0 or 8\n", + idx, ib->ptr[idx]); return -EINVAL; } break; @@ -3732,7 +3735,9 @@ int evergreen_dma_ib_parse(struct radeon_device *rdev, struct radeon_ib *ib) idx += 10; break; default: - DRM_ERROR("bad DMA_PACKET_COPY [%6d] 0x%08x invalid sub cmd\n", idx, ib->ptr[idx]); + dev_warn_once(rdev->dev, + "bad DMA_PACKET_COPY [%6d] 0x%08x invalid sub cmd\n", + idx, ib->ptr[idx]); return -EINVAL; } break; @@ -3743,7 +3748,7 @@ int evergreen_dma_ib_parse(struct radeon_device *rdev, struct radeon_ib *ib) idx += 1; break; default: - DRM_ERROR("Unknown packet type %d at %d !\n", cmd, idx); + dev_warn_once(rdev->dev, "Unknown packet type %d at %d !\n", cmd, idx); return -EINVAL; } } while (idx < ib->length_dw); diff --git a/drivers/gpu/drm/radeon/ni_dpm.c b/drivers/gpu/drm/radeon/ni_dpm.c index e08559c44a5c..82edbfb259bf 100644 --- a/drivers/gpu/drm/radeon/ni_dpm.c +++ b/drivers/gpu/drm/radeon/ni_dpm.c @@ -3397,7 +3397,7 @@ static int ni_enable_smc_cac(struct radeon_device *rdev, if (PPSMC_Result_OK != smc_result) ret = -EINVAL; - ni_pi->cac_enabled = (PPSMC_Result_OK == smc_result) ? true : false; + ni_pi->cac_enabled = PPSMC_Result_OK == smc_result; } } else if (ni_pi->cac_enabled) { smc_result = rv770_send_msg_to_smc(rdev, PPSMC_MSG_DisableCac); diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c index 80703417d8a1..07a9c523a17a 100644 --- a/drivers/gpu/drm/radeon/r100.c +++ b/drivers/gpu/drm/radeon/r100.c @@ -1298,8 +1298,8 @@ int r100_reloc_pitch_offset(struct radeon_cs_parser *p, r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("No reloc for ib[%d]=0x%04X\n", - idx, reg); + dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n", + idx, reg); radeon_cs_dump_packet(p, pkt); return r; } @@ -1313,7 +1313,7 @@ int r100_reloc_pitch_offset(struct radeon_cs_parser *p, tile_flags |= RADEON_DST_TILE_MACRO; if (reloc->tiling_flags & RADEON_TILING_MICRO) { if (reg == RADEON_SRC_PITCH_OFFSET) { - DRM_ERROR("Cannot src blit from microtiled surface\n"); + dev_warn_once(p->dev, "Cannot src blit from microtiled surface\n"); radeon_cs_dump_packet(p, pkt); return -EINVAL; } @@ -1342,8 +1342,8 @@ int r100_packet3_load_vbpntr(struct radeon_cs_parser *p, track = (struct r100_cs_track *)p->track; c = radeon_get_ib_value(p, idx++) & 0x1F; if (c > 16) { - DRM_ERROR("Only 16 vertex buffers are allowed %d\n", - pkt->opcode); + dev_warn_once(p->dev, "Only 16 vertex buffers are allowed %d\n", + pkt->opcode); radeon_cs_dump_packet(p, pkt); return -EINVAL; } @@ -1351,8 +1351,8 @@ int r100_packet3_load_vbpntr(struct radeon_cs_parser *p, for (i = 0; i < (c - 1); i += 2, idx += 3) { r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("No reloc for packet3 %d\n", - pkt->opcode); + dev_warn_once(p->dev, "No reloc for packet3 %d\n", + pkt->opcode); radeon_cs_dump_packet(p, pkt); return r; } @@ -1364,8 +1364,8 @@ int r100_packet3_load_vbpntr(struct radeon_cs_parser *p, track->arrays[i + 0].esize &= 0x7F; r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("No reloc for packet3 %d\n", - pkt->opcode); + dev_warn_once(p->dev, "No reloc for packet3 %d\n", + pkt->opcode); radeon_cs_dump_packet(p, pkt); return r; } @@ -1377,8 +1377,8 @@ int r100_packet3_load_vbpntr(struct radeon_cs_parser *p, if (c & 1) { r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("No reloc for packet3 %d\n", - pkt->opcode); + dev_warn_once(p->dev, "No reloc for packet3 %d\n", + pkt->opcode); radeon_cs_dump_packet(p, pkt); return r; } @@ -1470,12 +1470,12 @@ int r100_cs_packet_parse_vline(struct radeon_cs_parser *p) /* check its a wait until and only 1 count */ if (waitreloc.reg != RADEON_WAIT_UNTIL || waitreloc.count != 0) { - DRM_ERROR("vline wait had illegal wait until segment\n"); + dev_warn_once(p->dev, "vline wait had illegal wait until segment\n"); return -EINVAL; } if (radeon_get_ib_value(p, waitreloc.idx + 1) != RADEON_WAIT_CRTC_VLINE) { - DRM_ERROR("vline wait had illegal wait until\n"); + dev_warn_once(p->dev, "vline wait had illegal wait until\n"); return -EINVAL; } @@ -1493,7 +1493,7 @@ int r100_cs_packet_parse_vline(struct radeon_cs_parser *p) reg = R100_CP_PACKET0_GET_REG(header); crtc = drm_crtc_find(rdev_to_drm(p->rdev), p->filp, crtc_id); if (!crtc) { - DRM_ERROR("cannot find crtc %d\n", crtc_id); + dev_warn_once(p->dev, "cannot find crtc %d\n", crtc_id); return -ENOENT; } radeon_crtc = to_radeon_crtc(crtc); @@ -1514,7 +1514,7 @@ int r100_cs_packet_parse_vline(struct radeon_cs_parser *p) header |= RADEON_CRTC2_GUI_TRIG_VLINE >> 2; break; default: - DRM_ERROR("unknown crtc reloc\n"); + dev_warn_once(p->dev, "unknown crtc reloc\n"); return -EINVAL; } ib[h_idx] = header; @@ -1599,7 +1599,7 @@ static int r100_packet0_check(struct radeon_cs_parser *p, case RADEON_CRTC_GUI_TRIG_VLINE: r = r100_cs_packet_parse_vline(p); if (r) { - DRM_ERROR("No reloc for ib[%d]=0x%04X\n", + dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n", idx, reg); radeon_cs_dump_packet(p, pkt); return r; @@ -1616,8 +1616,8 @@ static int r100_packet0_check(struct radeon_cs_parser *p, case RADEON_RB3D_DEPTHOFFSET: r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("No reloc for ib[%d]=0x%04X\n", - idx, reg); + dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n", + idx, reg); radeon_cs_dump_packet(p, pkt); return r; } @@ -1629,8 +1629,8 @@ static int r100_packet0_check(struct radeon_cs_parser *p, case RADEON_RB3D_COLOROFFSET: r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("No reloc for ib[%d]=0x%04X\n", - idx, reg); + dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n", + idx, reg); radeon_cs_dump_packet(p, pkt); return r; } @@ -1645,8 +1645,8 @@ static int r100_packet0_check(struct radeon_cs_parser *p, i = (reg - RADEON_PP_TXOFFSET_0) / 24; r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("No reloc for ib[%d]=0x%04X\n", - idx, reg); + dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n", + idx, reg); radeon_cs_dump_packet(p, pkt); return r; } @@ -1672,8 +1672,8 @@ static int r100_packet0_check(struct radeon_cs_parser *p, i = (reg - RADEON_PP_CUBIC_OFFSET_T0_0) / 4; r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("No reloc for ib[%d]=0x%04X\n", - idx, reg); + dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n", + idx, reg); radeon_cs_dump_packet(p, pkt); return r; } @@ -1690,8 +1690,8 @@ static int r100_packet0_check(struct radeon_cs_parser *p, i = (reg - RADEON_PP_CUBIC_OFFSET_T1_0) / 4; r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("No reloc for ib[%d]=0x%04X\n", - idx, reg); + dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n", + idx, reg); radeon_cs_dump_packet(p, pkt); return r; } @@ -1708,8 +1708,8 @@ static int r100_packet0_check(struct radeon_cs_parser *p, i = (reg - RADEON_PP_CUBIC_OFFSET_T2_0) / 4; r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("No reloc for ib[%d]=0x%04X\n", - idx, reg); + dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n", + idx, reg); radeon_cs_dump_packet(p, pkt); return r; } @@ -1726,8 +1726,8 @@ static int r100_packet0_check(struct radeon_cs_parser *p, case RADEON_RB3D_COLORPITCH: r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("No reloc for ib[%d]=0x%04X\n", - idx, reg); + dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n", + idx, reg); radeon_cs_dump_packet(p, pkt); return r; } @@ -1768,8 +1768,8 @@ static int r100_packet0_check(struct radeon_cs_parser *p, track->cb[0].cpp = 4; break; default: - DRM_ERROR("Invalid color buffer format (%d) !\n", - ((idx_value >> RADEON_RB3D_COLOR_FORMAT_SHIFT) & 0x1f)); + dev_warn_once(p->dev, "Invalid color buffer format (%d) !\n", + ((idx_value >> RADEON_RB3D_COLOR_FORMAT_SHIFT) & 0x1f)); return -EINVAL; } track->z_enabled = !!(idx_value & RADEON_Z_ENABLE); @@ -1797,8 +1797,8 @@ static int r100_packet0_check(struct radeon_cs_parser *p, case RADEON_RB3D_ZPASS_ADDR: r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("No reloc for ib[%d]=0x%04X\n", - idx, reg); + dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n", + idx, reg); radeon_cs_dump_packet(p, pkt); return r; } @@ -1927,10 +1927,10 @@ int r100_cs_track_check_pkt3_indx_buffer(struct radeon_cs_parser *p, idx = pkt->idx + 1; value = radeon_get_ib_value(p, idx + 2); if ((value + 1) > radeon_bo_size(robj)) { - DRM_ERROR("[drm] Buffer too small for PACKET3 INDX_BUFFER " - "(need %u have %lu) !\n", - value + 1, - radeon_bo_size(robj)); + dev_warn_once(p->dev, "[drm] Buffer too small for PACKET3 INDX_BUFFER " + "(need %u have %lu) !\n", + value + 1, + radeon_bo_size(robj)); return -EINVAL; } return 0; @@ -1957,7 +1957,7 @@ static int r100_packet3_check(struct radeon_cs_parser *p, case PACKET3_INDX_BUFFER: r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("No reloc for packet3 %d\n", pkt->opcode); + dev_warn_once(p->dev, "No reloc for packet3 %d\n", pkt->opcode); radeon_cs_dump_packet(p, pkt); return r; } @@ -1971,7 +1971,7 @@ static int r100_packet3_check(struct radeon_cs_parser *p, /* 3D_RNDR_GEN_INDX_PRIM on r100/r200 */ r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("No reloc for packet3 %d\n", pkt->opcode); + dev_warn_once(p->dev, "No reloc for packet3 %d\n", pkt->opcode); radeon_cs_dump_packet(p, pkt); return r; } @@ -1992,7 +1992,7 @@ static int r100_packet3_check(struct radeon_cs_parser *p, break; case PACKET3_3D_DRAW_IMMD: if (((radeon_get_ib_value(p, idx + 1) >> 4) & 0x3) != 3) { - DRM_ERROR("PRIM_WALK must be 3 for IMMD draw\n"); + dev_warn_once(p->dev, "PRIM_WALK must be 3 for IMMD draw\n"); return -EINVAL; } track->vtx_size = r100_get_vtx_size(radeon_get_ib_value(p, idx + 0)); @@ -2005,7 +2005,7 @@ static int r100_packet3_check(struct radeon_cs_parser *p, /* triggers drawing using in-packet vertex data */ case PACKET3_3D_DRAW_IMMD_2: if (((radeon_get_ib_value(p, idx) >> 4) & 0x3) != 3) { - DRM_ERROR("PRIM_WALK must be 3 for IMMD draw\n"); + dev_warn_once(p->dev, "PRIM_WALK must be 3 for IMMD draw\n"); return -EINVAL; } track->vap_vf_cntl = radeon_get_ib_value(p, idx); @@ -2051,7 +2051,7 @@ static int r100_packet3_check(struct radeon_cs_parser *p, case PACKET3_NOP: break; default: - DRM_ERROR("Packet3 opcode %x not supported\n", pkt->opcode); + dev_warn_once(p->dev, "Packet3 opcode %x not supported\n", pkt->opcode); return -EINVAL; } return 0; @@ -2093,8 +2093,8 @@ int r100_cs_parse(struct radeon_cs_parser *p) r = r100_packet3_check(p, &pkt); break; default: - DRM_ERROR("Unknown packet type %d !\n", - pkt.type); + dev_warn_once(p->dev, "Unknown packet type %d !\n", + pkt.type); return -EINVAL; } if (r) @@ -2105,19 +2105,19 @@ int r100_cs_parse(struct radeon_cs_parser *p) static void r100_cs_track_texture_print(struct r100_cs_track_texture *t) { - DRM_ERROR("pitch %d\n", t->pitch); - DRM_ERROR("use_pitch %d\n", t->use_pitch); - DRM_ERROR("width %d\n", t->width); - DRM_ERROR("width_11 %d\n", t->width_11); - DRM_ERROR("height %d\n", t->height); - DRM_ERROR("height_11 %d\n", t->height_11); - DRM_ERROR("num levels %d\n", t->num_levels); - DRM_ERROR("depth %d\n", t->txdepth); - DRM_ERROR("bpp %d\n", t->cpp); - DRM_ERROR("coordinate type %d\n", t->tex_coord_type); - DRM_ERROR("width round to power of 2 %d\n", t->roundup_w); - DRM_ERROR("height round to power of 2 %d\n", t->roundup_h); - DRM_ERROR("compress format %d\n", t->compress_format); + DRM_DEBUG("pitch %d\n", t->pitch); + DRM_DEBUG("use_pitch %d\n", t->use_pitch); + DRM_DEBUG("width %d\n", t->width); + DRM_DEBUG("width_11 %d\n", t->width_11); + DRM_DEBUG("height %d\n", t->height); + DRM_DEBUG("height_11 %d\n", t->height_11); + DRM_DEBUG("num levels %d\n", t->num_levels); + DRM_DEBUG("depth %d\n", t->txdepth); + DRM_DEBUG("bpp %d\n", t->cpp); + DRM_DEBUG("coordinate type %d\n", t->tex_coord_type); + DRM_DEBUG("width round to power of 2 %d\n", t->roundup_w); + DRM_DEBUG("height round to power of 2 %d\n", t->roundup_h); + DRM_DEBUG("compress format %d\n", t->compress_format); } static int r100_track_compress_size(int compress_format, int w, int h) @@ -2172,8 +2172,9 @@ static int r100_cs_track_cube(struct radeon_device *rdev, size += track->textures[idx].cube_info[face].offset; if (size > radeon_bo_size(cube_robj)) { - DRM_ERROR("Cube texture offset greater than object size %lu %lu\n", - size, radeon_bo_size(cube_robj)); + dev_warn_once(rdev->dev, + "Cube texture offset greater than object size %lu %lu\n", + size, radeon_bo_size(cube_robj)); r100_cs_track_texture_print(&track->textures[idx]); return -1; } @@ -2196,7 +2197,7 @@ static int r100_cs_track_texture_check(struct radeon_device *rdev, continue; robj = track->textures[u].robj; if (robj == NULL) { - DRM_ERROR("No texture bound to unit %u\n", u); + dev_warn_once(rdev->dev, "No texture bound to unit %u\n", u); return -EINVAL; } size = 0; @@ -2249,13 +2250,13 @@ static int r100_cs_track_texture_check(struct radeon_device *rdev, size *= 6; break; default: - DRM_ERROR("Invalid texture coordinate type %u for unit " - "%u\n", track->textures[u].tex_coord_type, u); + dev_warn_once(rdev->dev, "Invalid texture coordinate type %u for unit " + "%u\n", track->textures[u].tex_coord_type, u); return -EINVAL; } if (size > radeon_bo_size(robj)) { - DRM_ERROR("Texture of unit %u needs %lu bytes but is " - "%lu\n", u, size, radeon_bo_size(robj)); + dev_warn_once(rdev->dev, "Texture of unit %u needs %lu bytes but is " + "%lu\n", u, size, radeon_bo_size(robj)); r100_cs_track_texture_print(&track->textures[u]); return -EINVAL; } @@ -2277,18 +2278,18 @@ int r100_cs_track_check(struct radeon_device *rdev, struct r100_cs_track *track) for (i = 0; i < num_cb; i++) { if (track->cb[i].robj == NULL) { - DRM_ERROR("[drm] No buffer for color buffer %d !\n", i); + dev_warn_once(rdev->dev, "[drm] No buffer for color buffer %d !\n", i); return -EINVAL; } size = track->cb[i].pitch * track->cb[i].cpp * track->maxy; size += track->cb[i].offset; if (size > radeon_bo_size(track->cb[i].robj)) { - DRM_ERROR("[drm] Buffer too small for color buffer %d " - "(need %lu have %lu) !\n", i, size, - radeon_bo_size(track->cb[i].robj)); - DRM_ERROR("[drm] color buffer %d (%u %u %u %u)\n", - i, track->cb[i].pitch, track->cb[i].cpp, - track->cb[i].offset, track->maxy); + dev_warn_once(rdev->dev, "[drm] Buffer too small for color buffer %d " + "(need %lu have %lu) !\n", i, size, + radeon_bo_size(track->cb[i].robj)); + dev_warn_once(rdev->dev, "[drm] color buffer %d (%u %u %u %u)\n", + i, track->cb[i].pitch, track->cb[i].cpp, + track->cb[i].offset, track->maxy); return -EINVAL; } } @@ -2296,18 +2297,18 @@ int r100_cs_track_check(struct radeon_device *rdev, struct r100_cs_track *track) if (track->zb_dirty && track->z_enabled) { if (track->zb.robj == NULL) { - DRM_ERROR("[drm] No buffer for z buffer !\n"); + dev_warn_once(rdev->dev, "[drm] No buffer for z buffer !\n"); return -EINVAL; } size = track->zb.pitch * track->zb.cpp * track->maxy; size += track->zb.offset; if (size > radeon_bo_size(track->zb.robj)) { - DRM_ERROR("[drm] Buffer too small for z buffer " - "(need %lu have %lu) !\n", size, - radeon_bo_size(track->zb.robj)); - DRM_ERROR("[drm] zbuffer (%u %u %u %u)\n", - track->zb.pitch, track->zb.cpp, - track->zb.offset, track->maxy); + dev_warn_once(rdev->dev, "[drm] Buffer too small for z buffer " + "(need %lu have %lu) !\n", size, + radeon_bo_size(track->zb.robj)); + dev_warn_once(rdev->dev, "[drm] zbuffer (%u %u %u %u)\n", + track->zb.pitch, track->zb.cpp, + track->zb.offset, track->maxy); return -EINVAL; } } @@ -2315,19 +2316,19 @@ int r100_cs_track_check(struct radeon_device *rdev, struct r100_cs_track *track) if (track->aa_dirty && track->aaresolve) { if (track->aa.robj == NULL) { - DRM_ERROR("[drm] No buffer for AA resolve buffer %d !\n", i); + dev_warn_once(rdev->dev, "[drm] No buffer for AA resolve buffer %d !\n", i); return -EINVAL; } /* I believe the format comes from colorbuffer0. */ size = track->aa.pitch * track->cb[0].cpp * track->maxy; size += track->aa.offset; if (size > radeon_bo_size(track->aa.robj)) { - DRM_ERROR("[drm] Buffer too small for AA resolve buffer %d " - "(need %lu have %lu) !\n", i, size, - radeon_bo_size(track->aa.robj)); - DRM_ERROR("[drm] AA resolve buffer %d (%u %u %u %u)\n", - i, track->aa.pitch, track->cb[0].cpp, - track->aa.offset, track->maxy); + dev_warn_once(rdev->dev, "[drm] Buffer too small for AA resolve buffer %d " + "(need %lu have %lu) !\n", i, size, + radeon_bo_size(track->aa.robj)); + dev_warn_once(rdev->dev, "[drm] AA resolve buffer %d (%u %u %u %u)\n", + i, track->aa.pitch, track->cb[0].cpp, + track->aa.offset, track->maxy); return -EINVAL; } } @@ -2344,17 +2345,17 @@ int r100_cs_track_check(struct radeon_device *rdev, struct r100_cs_track *track) for (i = 0; i < track->num_arrays; i++) { size = track->arrays[i].esize * track->max_indx * 4UL; if (track->arrays[i].robj == NULL) { - DRM_ERROR("(PW %u) Vertex array %u no buffer " - "bound\n", prim_walk, i); + dev_warn_once(rdev->dev, "(PW %u) Vertex array %u no buffer " + "bound\n", prim_walk, i); return -EINVAL; } if (size > radeon_bo_size(track->arrays[i].robj)) { - dev_err(rdev->dev, "(PW %u) Vertex array %u " - "need %lu dwords have %lu dwords\n", - prim_walk, i, size >> 2, - radeon_bo_size(track->arrays[i].robj) - >> 2); - DRM_ERROR("Max indices %u\n", track->max_indx); + dev_warn_once(rdev->dev, "(PW %u) Vertex array %u " + "need %lu dwords have %lu dwords\n", + prim_walk, i, size >> 2, + radeon_bo_size(track->arrays[i].robj) + >> 2); + dev_warn_once(rdev->dev, "Max indices %u\n", track->max_indx); return -EINVAL; } } @@ -2363,16 +2364,16 @@ int r100_cs_track_check(struct radeon_device *rdev, struct r100_cs_track *track) for (i = 0; i < track->num_arrays; i++) { size = track->arrays[i].esize * (nverts - 1) * 4UL; if (track->arrays[i].robj == NULL) { - DRM_ERROR("(PW %u) Vertex array %u no buffer " - "bound\n", prim_walk, i); + dev_warn_once(rdev->dev, "(PW %u) Vertex array %u no buffer " + "bound\n", prim_walk, i); return -EINVAL; } if (size > radeon_bo_size(track->arrays[i].robj)) { - dev_err(rdev->dev, "(PW %u) Vertex array %u " - "need %lu dwords have %lu dwords\n", - prim_walk, i, size >> 2, - radeon_bo_size(track->arrays[i].robj) - >> 2); + dev_warn_once(rdev->dev, "(PW %u) Vertex array %u " + "need %lu dwords have %lu dwords\n", + prim_walk, i, size >> 2, + radeon_bo_size(track->arrays[i].robj) + >> 2); return -EINVAL; } } @@ -2380,16 +2381,16 @@ int r100_cs_track_check(struct radeon_device *rdev, struct r100_cs_track *track) case 3: size = track->vtx_size * nverts; if (size != track->immd_dwords) { - DRM_ERROR("IMMD draw %u dwors but needs %lu dwords\n", - track->immd_dwords, size); - DRM_ERROR("VAP_VF_CNTL.NUM_VERTICES %u, VTX_SIZE %u\n", - nverts, track->vtx_size); + dev_warn_once(rdev->dev, "IMMD draw %u dwors but needs %lu dwords\n", + track->immd_dwords, size); + dev_warn_once(rdev->dev, "VAP_VF_CNTL.NUM_VERTICES %u, VTX_SIZE %u\n", + nverts, track->vtx_size); return -EINVAL; } break; default: - DRM_ERROR("[drm] Invalid primitive walk %d for VAP_VF_CNTL\n", - prim_walk); + dev_warn_once(rdev->dev, "[drm] Invalid primitive walk %d for VAP_VF_CNTL\n", + prim_walk); return -EINVAL; } diff --git a/drivers/gpu/drm/radeon/r200.c b/drivers/gpu/drm/radeon/r200.c index f5f2ffea5ab2..10a65a71de31 100644 --- a/drivers/gpu/drm/radeon/r200.c +++ b/drivers/gpu/drm/radeon/r200.c @@ -163,8 +163,8 @@ int r200_packet0_check(struct radeon_cs_parser *p, case RADEON_CRTC_GUI_TRIG_VLINE: r = r100_cs_packet_parse_vline(p); if (r) { - DRM_ERROR("No reloc for ib[%d]=0x%04X\n", - idx, reg); + dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n", + idx, reg); radeon_cs_dump_packet(p, pkt); return r; } @@ -180,8 +180,8 @@ int r200_packet0_check(struct radeon_cs_parser *p, case RADEON_RB3D_DEPTHOFFSET: r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("No reloc for ib[%d]=0x%04X\n", - idx, reg); + dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n", + idx, reg); radeon_cs_dump_packet(p, pkt); return r; } @@ -193,8 +193,8 @@ int r200_packet0_check(struct radeon_cs_parser *p, case RADEON_RB3D_COLOROFFSET: r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("No reloc for ib[%d]=0x%04X\n", - idx, reg); + dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n", + idx, reg); radeon_cs_dump_packet(p, pkt); return r; } @@ -212,8 +212,8 @@ int r200_packet0_check(struct radeon_cs_parser *p, i = (reg - R200_PP_TXOFFSET_0) / 24; r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("No reloc for ib[%d]=0x%04X\n", - idx, reg); + dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n", + idx, reg); radeon_cs_dump_packet(p, pkt); return r; } @@ -265,8 +265,8 @@ int r200_packet0_check(struct radeon_cs_parser *p, face = (reg - ((i * 24) + R200_PP_TXOFFSET_0)) / 4; r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("No reloc for ib[%d]=0x%04X\n", - idx, reg); + dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n", + idx, reg); radeon_cs_dump_packet(p, pkt); return r; } @@ -283,8 +283,8 @@ int r200_packet0_check(struct radeon_cs_parser *p, case RADEON_RB3D_COLORPITCH: r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("No reloc for ib[%d]=0x%04X\n", - idx, reg); + dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n", + idx, reg); radeon_cs_dump_packet(p, pkt); return r; } @@ -326,12 +326,12 @@ int r200_packet0_check(struct radeon_cs_parser *p, track->cb[0].cpp = 4; break; default: - DRM_ERROR("Invalid color buffer format (%d) !\n", - ((idx_value >> RADEON_RB3D_COLOR_FORMAT_SHIFT) & 0x1f)); + dev_warn_once(p->dev, "Invalid color buffer format (%d) !\n", + ((idx_value >> RADEON_RB3D_COLOR_FORMAT_SHIFT) & 0x1f)); return -EINVAL; } if (idx_value & RADEON_DEPTHXY_OFFSET_ENABLE) { - DRM_ERROR("No support for depth xy offset in kms\n"); + dev_warn_once(p->dev, "No support for depth xy offset in kms\n"); return -EINVAL; } @@ -360,8 +360,8 @@ int r200_packet0_check(struct radeon_cs_parser *p, case RADEON_RB3D_ZPASS_ADDR: r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("No reloc for ib[%d]=0x%04X\n", - idx, reg); + dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n", + idx, reg); radeon_cs_dump_packet(p, pkt); return r; } diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c index d22889fbfa9c..d2ee6deec039 100644 --- a/drivers/gpu/drm/radeon/r300.c +++ b/drivers/gpu/drm/radeon/r300.c @@ -645,8 +645,8 @@ static int r300_packet0_check(struct radeon_cs_parser *p, case RADEON_CRTC_GUI_TRIG_VLINE: r = r100_cs_packet_parse_vline(p); if (r) { - DRM_ERROR("No reloc for ib[%d]=0x%04X\n", - idx, reg); + dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n", + idx, reg); radeon_cs_dump_packet(p, pkt); return r; } @@ -664,8 +664,8 @@ static int r300_packet0_check(struct radeon_cs_parser *p, i = (reg - R300_RB3D_COLOROFFSET0) >> 2; r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("No reloc for ib[%d]=0x%04X\n", - idx, reg); + dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n", + idx, reg); radeon_cs_dump_packet(p, pkt); return r; } @@ -677,8 +677,8 @@ static int r300_packet0_check(struct radeon_cs_parser *p, case R300_ZB_DEPTHOFFSET: r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("No reloc for ib[%d]=0x%04X\n", - idx, reg); + dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n", + idx, reg); radeon_cs_dump_packet(p, pkt); return r; } @@ -706,8 +706,8 @@ static int r300_packet0_check(struct radeon_cs_parser *p, i = (reg - R300_TX_OFFSET_0) >> 2; r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("No reloc for ib[%d]=0x%04X\n", - idx, reg); + dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n", + idx, reg); radeon_cs_dump_packet(p, pkt); return r; } @@ -762,7 +762,7 @@ static int r300_packet0_check(struct radeon_cs_parser *p, /* RB3D_CCTL */ if ((idx_value & (1 << 10)) && /* CMASK_ENABLE */ p->rdev->cmask_filp != p->filp) { - DRM_ERROR("Invalid RB3D_CCTL: Cannot enable CMASK.\n"); + dev_warn_once(p->dev, "Invalid RB3D_CCTL: Cannot enable CMASK.\n"); return -EINVAL; } track->num_cb = ((idx_value >> 5) & 0x3) + 1; @@ -779,8 +779,8 @@ static int r300_packet0_check(struct radeon_cs_parser *p, if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) { r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("No reloc for ib[%d]=0x%04X\n", - idx, reg); + dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n", + idx, reg); radeon_cs_dump_packet(p, pkt); return r; } @@ -812,8 +812,8 @@ static int r300_packet0_check(struct radeon_cs_parser *p, break; case 5: if (p->rdev->family < CHIP_RV515) { - DRM_ERROR("Invalid color buffer format (%d)!\n", - ((idx_value >> 21) & 0xF)); + dev_warn_once(p->dev, "Invalid color buffer format (%d)!\n", + ((idx_value >> 21) & 0xF)); return -EINVAL; } fallthrough; @@ -827,8 +827,8 @@ static int r300_packet0_check(struct radeon_cs_parser *p, track->cb[i].cpp = 16; break; default: - DRM_ERROR("Invalid color buffer format (%d) !\n", - ((idx_value >> 21) & 0xF)); + dev_warn_once(p->dev, "Invalid color buffer format (%d) !\n", + ((idx_value >> 21) & 0xF)); return -EINVAL; } track->cb_dirty = true; @@ -853,8 +853,8 @@ static int r300_packet0_check(struct radeon_cs_parser *p, track->zb.cpp = 4; break; default: - DRM_ERROR("Invalid z buffer format (%d) !\n", - (idx_value & 0xF)); + dev_warn_once(p->dev, "Invalid z buffer format (%d) !\n", + (idx_value & 0xF)); return -EINVAL; } track->zb_dirty = true; @@ -864,8 +864,8 @@ static int r300_packet0_check(struct radeon_cs_parser *p, if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) { r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("No reloc for ib[%d]=0x%04X\n", - idx, reg); + dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n", + idx, reg); radeon_cs_dump_packet(p, pkt); return r; } @@ -962,8 +962,8 @@ static int r300_packet0_check(struct radeon_cs_parser *p, break; case R300_TX_FORMAT_ATI2N: if (p->rdev->family < CHIP_R420) { - DRM_ERROR("Invalid texture format %u\n", - (idx_value & 0x1F)); + dev_warn_once(p->dev, "Invalid texture format %u\n", + (idx_value & 0x1F)); return -EINVAL; } /* The same rules apply as for DXT3/5. */ @@ -974,8 +974,8 @@ static int r300_packet0_check(struct radeon_cs_parser *p, track->textures[i].compress_format = R100_TRACK_COMP_DXT35; break; default: - DRM_ERROR("Invalid texture format %u\n", - (idx_value & 0x1F)); + dev_warn_once(p->dev, "Invalid texture format %u\n", + (idx_value & 0x1F)); return -EINVAL; } track->tex_dirty = true; @@ -1041,7 +1041,7 @@ static int r300_packet0_check(struct radeon_cs_parser *p, R100_TRACK_COMP_DXT1; } } else if (idx_value & (1 << 14)) { - DRM_ERROR("Forbidden bit TXFORMAT_MSB\n"); + dev_warn_once(p->dev, "Forbidden bit TXFORMAT_MSB\n"); return -EINVAL; } track->tex_dirty = true; @@ -1079,8 +1079,8 @@ static int r300_packet0_check(struct radeon_cs_parser *p, case R300_ZB_ZPASS_ADDR: r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("No reloc for ib[%d]=0x%04X\n", - idx, reg); + dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n", + idx, reg); radeon_cs_dump_packet(p, pkt); return r; } @@ -1121,8 +1121,8 @@ static int r300_packet0_check(struct radeon_cs_parser *p, case R300_RB3D_AARESOLVE_OFFSET: r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("No reloc for ib[%d]=0x%04X\n", - idx, reg); + dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n", + idx, reg); radeon_cs_dump_packet(p, pkt); return r; } @@ -1191,7 +1191,7 @@ static int r300_packet3_check(struct radeon_cs_parser *p, case PACKET3_INDX_BUFFER: r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - DRM_ERROR("No reloc for packet3 %d\n", pkt->opcode); + dev_warn_once(p->dev, "No reloc for packet3 %d\n", pkt->opcode); radeon_cs_dump_packet(p, pkt); return r; } @@ -1207,7 +1207,7 @@ static int r300_packet3_check(struct radeon_cs_parser *p, * PRIM_WALK must be equal to 3 vertex data in embedded * in cmd stream */ if (((radeon_get_ib_value(p, idx + 1) >> 4) & 0x3) != 3) { - DRM_ERROR("PRIM_WALK must be 3 for IMMD draw\n"); + dev_warn_once(p->dev, "PRIM_WALK must be 3 for IMMD draw\n"); return -EINVAL; } track->vap_vf_cntl = radeon_get_ib_value(p, idx + 1); @@ -1222,7 +1222,7 @@ static int r300_packet3_check(struct radeon_cs_parser *p, * PRIM_WALK must be equal to 3 vertex data in embedded * in cmd stream */ if (((radeon_get_ib_value(p, idx) >> 4) & 0x3) != 3) { - DRM_ERROR("PRIM_WALK must be 3 for IMMD draw\n"); + dev_warn_once(p->dev, "PRIM_WALK must be 3 for IMMD draw\n"); return -EINVAL; } track->vap_vf_cntl = radeon_get_ib_value(p, idx); @@ -1272,7 +1272,7 @@ static int r300_packet3_check(struct radeon_cs_parser *p, case PACKET3_NOP: break; default: - DRM_ERROR("Packet3 opcode %x not supported\n", pkt->opcode); + dev_warn_once(p->dev, "Packet3 opcode %x not supported\n", pkt->opcode); return -EINVAL; } return 0; @@ -1308,7 +1308,7 @@ int r300_cs_parse(struct radeon_cs_parser *p) r = r300_packet3_check(p, &pkt); break; default: - DRM_ERROR("Unknown packet type %d !\n", pkt.type); + dev_warn_once(p->dev, "Unknown packet type %d !\n", pkt.type); return -EINVAL; } if (r) { diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c index 811265648a58..8eeceeeca362 100644 --- a/drivers/gpu/drm/radeon/r600_cs.c +++ b/drivers/gpu/drm/radeon/r600_cs.c @@ -361,9 +361,9 @@ static int r600_cs_track_validate_cb(struct radeon_cs_parser *p, int i) format = G_0280A0_FORMAT(track->cb_color_info[i]); if (!r600_fmt_is_valid_color(format)) { - dev_warn(p->dev, "%s:%d cb invalid format %d for %d (0x%08X)\n", - __func__, __LINE__, format, - i, track->cb_color_info[i]); + dev_warn_once(p->dev, "%s:%d cb invalid format %d for %d (0x%08X)\n", + __func__, __LINE__, format, + i, track->cb_color_info[i]); return -EINVAL; } /* pitch in pixels */ @@ -384,9 +384,9 @@ static int r600_cs_track_validate_cb(struct radeon_cs_parser *p, int i) array_check.blocksize = r600_fmt_get_blocksize(format); if (r600_get_array_mode_alignment(&array_check, &pitch_align, &height_align, &depth_align, &base_align)) { - dev_warn(p->dev, "%s invalid tiling %d for %d (0x%08X)\n", __func__, - G_0280A0_ARRAY_MODE(track->cb_color_info[i]), i, - track->cb_color_info[i]); + dev_warn_once(p->dev, "%s invalid tiling %d for %d (0x%08X)\n", __func__, + G_0280A0_ARRAY_MODE(track->cb_color_info[i]), i, + track->cb_color_info[i]); return -EINVAL; } switch (array_mode) { @@ -402,25 +402,26 @@ static int r600_cs_track_validate_cb(struct radeon_cs_parser *p, int i) case V_0280A0_ARRAY_2D_TILED_THIN1: break; default: - dev_warn(p->dev, "%s invalid tiling %d for %d (0x%08X)\n", __func__, - G_0280A0_ARRAY_MODE(track->cb_color_info[i]), i, - track->cb_color_info[i]); + dev_warn_once(p->dev, "%s invalid tiling %d for %d (0x%08X)\n", __func__, + G_0280A0_ARRAY_MODE(track->cb_color_info[i]), i, + track->cb_color_info[i]); return -EINVAL; } if (!IS_ALIGNED(pitch, pitch_align)) { - dev_warn(p->dev, "%s:%d cb pitch (%d, 0x%x, %d) invalid\n", - __func__, __LINE__, pitch, pitch_align, array_mode); + dev_warn_once(p->dev, "%s:%d cb pitch (%d, 0x%x, %d) invalid\n", + __func__, __LINE__, pitch, pitch_align, array_mode); return -EINVAL; } if (!IS_ALIGNED(height, height_align)) { - dev_warn(p->dev, "%s:%d cb height (%d, 0x%x, %d) invalid\n", - __func__, __LINE__, height, height_align, array_mode); + dev_warn_once(p->dev, "%s:%d cb height (%d, 0x%x, %d) invalid\n", + __func__, __LINE__, height, height_align, array_mode); return -EINVAL; } if (!IS_ALIGNED(base_offset, base_align)) { - dev_warn(p->dev, "%s offset[%d] 0x%llx 0x%llx, %d not aligned\n", __func__, i, - base_offset, base_align, array_mode); + dev_warn_once(p->dev, + "%s offset[%d] 0x%llx 0x%llx, %d not aligned\n", __func__, i, + base_offset, base_align, array_mode); return -EINVAL; } @@ -447,13 +448,14 @@ static int r600_cs_track_validate_cb(struct radeon_cs_parser *p, int i) * broken userspace. */ } else { - dev_warn(p->dev, "%s offset[%d] %d %llu %d %lu too big (%d %d) (%d %d %d)\n", - __func__, i, array_mode, - track->cb_color_bo_offset[i], tmp, - radeon_bo_size(track->cb_color_bo[i]), - pitch, height, r600_fmt_get_nblocksx(format, pitch), - r600_fmt_get_nblocksy(format, height), - r600_fmt_get_blocksize(format)); + dev_warn_once(p->dev, + "%s offset[%d] %d %llu %d %lu too big (%d %d) (%d %d %d)\n", + __func__, i, array_mode, + track->cb_color_bo_offset[i], tmp, + radeon_bo_size(track->cb_color_bo[i]), + pitch, height, r600_fmt_get_nblocksx(format, pitch), + r600_fmt_get_nblocksy(format, height), + r600_fmt_get_blocksize(format)); return -EINVAL; } } @@ -478,11 +480,11 @@ static int r600_cs_track_validate_cb(struct radeon_cs_parser *p, int i) if (bytes + track->cb_color_frag_offset[i] > radeon_bo_size(track->cb_color_frag_bo[i])) { - dev_warn(p->dev, "%s FMASK_TILE_MAX too large " - "(tile_max=%u, bytes=%u, offset=%llu, bo_size=%lu)\n", - __func__, tile_max, bytes, - track->cb_color_frag_offset[i], - radeon_bo_size(track->cb_color_frag_bo[i])); + dev_warn_once(p->dev, "%s FMASK_TILE_MAX too large " + "(tile_max=%u, bytes=%u, offset=%llu, bo_size=%lu)\n", + __func__, tile_max, bytes, + track->cb_color_frag_offset[i], + radeon_bo_size(track->cb_color_frag_bo[i])); return -EINVAL; } } @@ -496,17 +498,17 @@ static int r600_cs_track_validate_cb(struct radeon_cs_parser *p, int i) if (bytes + track->cb_color_tile_offset[i] > radeon_bo_size(track->cb_color_tile_bo[i])) { - dev_warn(p->dev, "%s CMASK_BLOCK_MAX too large " - "(block_max=%u, bytes=%u, offset=%llu, bo_size=%lu)\n", - __func__, block_max, bytes, - track->cb_color_tile_offset[i], - radeon_bo_size(track->cb_color_tile_bo[i])); + dev_warn_once(p->dev, "%s CMASK_BLOCK_MAX too large " + "(block_max=%u, bytes=%u, offset=%llu, bo_size=%lu)\n", + __func__, block_max, bytes, + track->cb_color_tile_offset[i], + radeon_bo_size(track->cb_color_tile_bo[i])); return -EINVAL; } break; } default: - dev_warn(p->dev, "%s invalid tile mode\n", __func__); + dev_warn_once(p->dev, "%s invalid tile mode\n", __func__); return -EINVAL; } return 0; @@ -526,7 +528,7 @@ static int r600_cs_track_validate_db(struct radeon_cs_parser *p) if (track->db_bo == NULL) { - dev_warn(p->dev, "z/stencil with no depth buffer\n"); + dev_warn_once(p->dev, "z/stencil with no depth buffer\n"); return -EINVAL; } switch (G_028010_FORMAT(track->db_depth_info)) { @@ -544,20 +546,22 @@ static int r600_cs_track_validate_db(struct radeon_cs_parser *p) bpe = 8; break; default: - dev_warn(p->dev, "z/stencil with invalid format %d\n", G_028010_FORMAT(track->db_depth_info)); + dev_warn_once(p->dev, + "z/stencil with invalid format %d\n", + G_028010_FORMAT(track->db_depth_info)); return -EINVAL; } if ((track->db_depth_size & 0xFFFFFC00) == 0xFFFFFC00) { if (!track->db_depth_size_idx) { - dev_warn(p->dev, "z/stencil buffer size not set\n"); + dev_warn_once(p->dev, "z/stencil buffer size not set\n"); return -EINVAL; } tmp = radeon_bo_size(track->db_bo) - track->db_offset; tmp = (tmp / bpe) >> 6; if (!tmp) { - dev_warn(p->dev, "z/stencil buffer too small (0x%08X %d %d %ld)\n", - track->db_depth_size, bpe, track->db_offset, - radeon_bo_size(track->db_bo)); + dev_warn_once(p->dev, "z/stencil buffer too small (0x%08X %d %d %ld)\n", + track->db_depth_size, bpe, track->db_offset, + radeon_bo_size(track->db_bo)); return -EINVAL; } ib[track->db_depth_size_idx] = S_028000_SLICE_TILE_MAX(tmp - 1) | (track->db_depth_size & 0x3FF); @@ -579,9 +583,9 @@ static int r600_cs_track_validate_db(struct radeon_cs_parser *p) array_check.blocksize = bpe; if (r600_get_array_mode_alignment(&array_check, &pitch_align, &height_align, &depth_align, &base_align)) { - dev_warn(p->dev, "%s invalid tiling %d (0x%08X)\n", __func__, - G_028010_ARRAY_MODE(track->db_depth_info), - track->db_depth_info); + dev_warn_once(p->dev, "%s invalid tiling %d (0x%08X)\n", __func__, + G_028010_ARRAY_MODE(track->db_depth_info), + track->db_depth_info); return -EINVAL; } switch (array_mode) { @@ -592,24 +596,24 @@ static int r600_cs_track_validate_db(struct radeon_cs_parser *p) case V_028010_ARRAY_2D_TILED_THIN1: break; default: - dev_warn(p->dev, "%s invalid tiling %d (0x%08X)\n", __func__, - G_028010_ARRAY_MODE(track->db_depth_info), - track->db_depth_info); + dev_warn_once(p->dev, "%s invalid tiling %d (0x%08X)\n", __func__, + G_028010_ARRAY_MODE(track->db_depth_info), + track->db_depth_info); return -EINVAL; } if (!IS_ALIGNED(pitch, pitch_align)) { - dev_warn(p->dev, "%s:%d db pitch (%d, 0x%x, %d) invalid\n", + dev_warn_once(p->dev, "%s:%d db pitch (%d, 0x%x, %d) invalid\n", __func__, __LINE__, pitch, pitch_align, array_mode); return -EINVAL; } if (!IS_ALIGNED(height, height_align)) { - dev_warn(p->dev, "%s:%d db height (%d, 0x%x, %d) invalid\n", + dev_warn_once(p->dev, "%s:%d db height (%d, 0x%x, %d) invalid\n", __func__, __LINE__, height, height_align, array_mode); return -EINVAL; } if (!IS_ALIGNED(base_offset, base_align)) { - dev_warn(p->dev, "%s offset 0x%llx, 0x%llx, %d not aligned\n", __func__, + dev_warn_once(p->dev, "%s offset 0x%llx, 0x%llx, %d not aligned\n", __func__, base_offset, base_align, array_mode); return -EINVAL; } @@ -618,10 +622,11 @@ static int r600_cs_track_validate_db(struct radeon_cs_parser *p) nviews = G_028004_SLICE_MAX(track->db_depth_view) + 1; tmp = ntiles * bpe * 64 * nviews * track->nsamples; if ((tmp + track->db_offset) > radeon_bo_size(track->db_bo)) { - dev_warn(p->dev, "z/stencil buffer (%d) too small (0x%08X %d %d %d -> %u have %lu)\n", - array_mode, - track->db_depth_size, ntiles, nviews, bpe, tmp + track->db_offset, - radeon_bo_size(track->db_bo)); + dev_warn_once(p->dev, + "z/stencil buffer (%d) too small (0x%08X %d %d %d -> %u have %lu)\n", + array_mode, + track->db_depth_size, ntiles, nviews, bpe, tmp + track->db_offset, + radeon_bo_size(track->db_bo)); return -EINVAL; } } @@ -632,13 +637,13 @@ static int r600_cs_track_validate_db(struct radeon_cs_parser *p) unsigned nbx, nby; if (track->htile_bo == NULL) { - dev_warn(p->dev, "%s:%d htile enabled without htile surface 0x%08x\n", - __func__, __LINE__, track->db_depth_info); + dev_warn_once(p->dev, "%s:%d htile enabled without htile surface 0x%08x\n", + __func__, __LINE__, track->db_depth_info); return -EINVAL; } if ((track->db_depth_size & 0xFFFFFC00) == 0xFFFFFC00) { - dev_warn(p->dev, "%s:%d htile can't be enabled with bogus db_depth_size 0x%08x\n", - __func__, __LINE__, track->db_depth_size); + dev_warn_once(p->dev, "%s:%d htile can't be enabled with bogus db_depth_size 0x%08x\n", + __func__, __LINE__, track->db_depth_size); return -EINVAL; } @@ -676,8 +681,8 @@ static int r600_cs_track_validate_db(struct radeon_cs_parser *p) nby = round_up(nby, 16 * 8); break; default: - dev_warn(p->dev, "%s:%d invalid num pipes %d\n", - __func__, __LINE__, track->npipes); + dev_warn_once(p->dev, "%s:%d invalid num pipes %d\n", + __func__, __LINE__, track->npipes); return -EINVAL; } } @@ -689,9 +694,9 @@ static int r600_cs_track_validate_db(struct radeon_cs_parser *p) size += track->htile_offset; if (size > radeon_bo_size(track->htile_bo)) { - dev_warn(p->dev, "%s:%d htile surface too small %ld for %ld (%d %d)\n", - __func__, __LINE__, radeon_bo_size(track->htile_bo), - size, nbx, nby); + dev_warn_once(p->dev, "%s:%d htile surface too small %ld for %ld (%d %d)\n", + __func__, __LINE__, radeon_bo_size(track->htile_bo), + size, nbx, nby); return -EINVAL; } } @@ -718,13 +723,13 @@ static int r600_cs_track_check(struct radeon_cs_parser *p) u64 offset = (u64)track->vgt_strmout_bo_offset[i] + (u64)track->vgt_strmout_size[i]; if (offset > radeon_bo_size(track->vgt_strmout_bo[i])) { - DRM_ERROR("streamout %d bo too small: 0x%llx, 0x%lx\n", - i, offset, - radeon_bo_size(track->vgt_strmout_bo[i])); + dev_warn_once(p->dev, "streamout %d bo too small: 0x%llx, 0x%lx\n", + i, offset, + radeon_bo_size(track->vgt_strmout_bo[i])); return -EINVAL; } } else { - dev_warn(p->dev, "No buffer for streamout %d\n", i); + dev_warn_once(p->dev, "No buffer for streamout %d\n", i); return -EINVAL; } } @@ -753,8 +758,8 @@ static int r600_cs_track_check(struct radeon_cs_parser *p) (tmp >> (i * 4)) & 0xF) { /* at least one component is enabled */ if (track->cb_color_bo[i] == NULL) { - dev_warn(p->dev, "%s:%d mask 0x%08X | 0x%08X no cb for %d\n", - __func__, __LINE__, track->cb_target_mask, track->cb_shader_mask, i); + dev_warn_once(p->dev, "%s:%d mask 0x%08X | 0x%08X no cb for %d\n", + __func__, __LINE__, track->cb_target_mask, track->cb_shader_mask, i); return -EINVAL; } /* perform rewrite of CB_COLOR[0-7]_SIZE */ @@ -841,33 +846,33 @@ int r600_cs_common_vline_parse(struct radeon_cs_parser *p, /* check its a WAIT_REG_MEM */ if (wait_reg_mem.type != RADEON_PACKET_TYPE3 || wait_reg_mem.opcode != PACKET3_WAIT_REG_MEM) { - DRM_ERROR("vline wait missing WAIT_REG_MEM segment\n"); + dev_warn_once(p->dev, "vline wait missing WAIT_REG_MEM segment\n"); return -EINVAL; } wait_reg_mem_info = radeon_get_ib_value(p, wait_reg_mem.idx + 1); /* bit 4 is reg (0) or mem (1) */ if (wait_reg_mem_info & 0x10) { - DRM_ERROR("vline WAIT_REG_MEM waiting on MEM instead of REG\n"); + dev_warn_once(p->dev, "vline WAIT_REG_MEM waiting on MEM instead of REG\n"); return -EINVAL; } /* bit 8 is me (0) or pfp (1) */ if (wait_reg_mem_info & 0x100) { - DRM_ERROR("vline WAIT_REG_MEM waiting on PFP instead of ME\n"); + dev_warn_once(p->dev, "vline WAIT_REG_MEM waiting on PFP instead of ME\n"); return -EINVAL; } /* waiting for value to be equal */ if ((wait_reg_mem_info & 0x7) != 0x3) { - DRM_ERROR("vline WAIT_REG_MEM function not equal\n"); + dev_warn_once(p->dev, "vline WAIT_REG_MEM function not equal\n"); return -EINVAL; } if ((radeon_get_ib_value(p, wait_reg_mem.idx + 2) << 2) != vline_status[0]) { - DRM_ERROR("vline WAIT_REG_MEM bad reg\n"); + dev_warn_once(p->dev, "vline WAIT_REG_MEM bad reg\n"); return -EINVAL; } if (radeon_get_ib_value(p, wait_reg_mem.idx + 5) != RADEON_VLINE_STAT) { - DRM_ERROR("vline WAIT_REG_MEM bad bit mask\n"); + dev_warn_once(p->dev, "vline WAIT_REG_MEM bad bit mask\n"); return -EINVAL; } @@ -886,7 +891,7 @@ int r600_cs_common_vline_parse(struct radeon_cs_parser *p, crtc = drm_crtc_find(rdev_to_drm(p->rdev), p->filp, crtc_id); if (!crtc) { - DRM_ERROR("cannot find crtc %d\n", crtc_id); + dev_warn_once(p->dev, "cannot find crtc %d\n", crtc_id); return -ENOENT; } radeon_crtc = to_radeon_crtc(crtc); @@ -907,7 +912,7 @@ int r600_cs_common_vline_parse(struct radeon_cs_parser *p, ib[h_idx] = header; ib[h_idx + 4] = vline_status[crtc_id] >> 2; } else { - DRM_ERROR("unknown crtc reloc\n"); + dev_warn_once(p->dev, "unknown crtc reloc\n"); return -EINVAL; } return 0; @@ -923,8 +928,8 @@ static int r600_packet0_check(struct radeon_cs_parser *p, case AVIVO_D1MODE_VLINE_START_END: r = r600_cs_packet_parse_vline(p); if (r) { - DRM_ERROR("No reloc for ib[%d]=0x%04X\n", - idx, reg); + dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n", + idx, reg); return r; } break; @@ -972,7 +977,7 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) i = (reg >> 7); if (i >= ARRAY_SIZE(r600_reg_safe_bm)) { - dev_warn(p->dev, "forbidden register 0x%08x at %d\n", reg, idx); + dev_warn_once(p->dev, "forbidden register 0x%08x at %d\n", reg, idx); return -EINVAL; } m = 1 << ((reg >> 2) & 31); @@ -1013,8 +1018,8 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) case SQ_VSTMP_RING_BASE: r = radeon_cs_packet_next_reloc(p, &reloc, 0); if (r) { - dev_warn(p->dev, "bad SET_CONTEXT_REG " - "0x%04X\n", reg); + dev_warn_once(p->dev, "bad SET_CONTEXT_REG " + "0x%04X\n", reg); return -EINVAL; } ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff); @@ -1031,8 +1036,8 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) radeon_cs_packet_next_is_pkt3_nop(p)) { r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm); if (r) { - dev_warn(p->dev, "bad SET_CONTEXT_REG " - "0x%04X\n", reg); + dev_warn_once(p->dev, "bad SET_CONTEXT_REG " + "0x%04X\n", reg); return -EINVAL; } track->db_depth_info = radeon_get_ib_value(p, idx); @@ -1073,8 +1078,8 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) case VGT_STRMOUT_BUFFER_BASE_3: r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm); if (r) { - dev_warn(p->dev, "bad SET_CONTEXT_REG " - "0x%04X\n", reg); + dev_warn_once(p->dev, "bad SET_CONTEXT_REG " + "0x%04X\n", reg); return -EINVAL; } tmp = (reg - VGT_STRMOUT_BUFFER_BASE_0) / 16; @@ -1096,8 +1101,8 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) case CP_COHER_BASE: r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm); if (r) { - dev_warn(p->dev, "missing reloc for CP_COHER_BASE " - "0x%04X\n", reg); + dev_warn_once(p->dev, "missing reloc for CP_COHER_BASE " + "0x%04X\n", reg); return -EINVAL; } ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff); @@ -1270,8 +1275,8 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) case CB_COLOR7_BASE: r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm); if (r) { - dev_warn(p->dev, "bad SET_CONTEXT_REG " - "0x%04X\n", reg); + dev_warn_once(p->dev, "bad SET_CONTEXT_REG " + "0x%04X\n", reg); return -EINVAL; } tmp = (reg - CB_COLOR0_BASE) / 4; @@ -1285,8 +1290,8 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) case DB_DEPTH_BASE: r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm); if (r) { - dev_warn(p->dev, "bad SET_CONTEXT_REG " - "0x%04X\n", reg); + dev_warn_once(p->dev, "bad SET_CONTEXT_REG " + "0x%04X\n", reg); return -EINVAL; } track->db_offset = radeon_get_ib_value(p, idx) << 8; @@ -1298,8 +1303,8 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) case DB_HTILE_DATA_BASE: r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm); if (r) { - dev_warn(p->dev, "bad SET_CONTEXT_REG " - "0x%04X\n", reg); + dev_warn_once(p->dev, "bad SET_CONTEXT_REG " + "0x%04X\n", reg); return -EINVAL; } track->htile_offset = (u64)radeon_get_ib_value(p, idx) << 8; @@ -1368,8 +1373,8 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) case SQ_ALU_CONST_CACHE_VS_15: r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm); if (r) { - dev_warn(p->dev, "bad SET_CONTEXT_REG " - "0x%04X\n", reg); + dev_warn_once(p->dev, "bad SET_CONTEXT_REG " + "0x%04X\n", reg); return -EINVAL; } ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff); @@ -1377,8 +1382,8 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) case SX_MEMORY_EXPORT_BASE: r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm); if (r) { - dev_warn(p->dev, "bad SET_CONFIG_REG " - "0x%04X\n", reg); + dev_warn_once(p->dev, "bad SET_CONFIG_REG " + "0x%04X\n", reg); return -EINVAL; } ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff); @@ -1387,7 +1392,7 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) track->sx_misc_kill_all_prims = (radeon_get_ib_value(p, idx) & 0x1) != 0; break; default: - dev_warn(p->dev, "forbidden register 0x%08x at %d\n", reg, idx); + dev_warn_once(p->dev, "forbidden register 0x%08x at %d\n", reg, idx); return -EINVAL; } return 0; @@ -1543,43 +1548,43 @@ static int r600_check_texture_resource(struct radeon_cs_parser *p, u32 idx, llevel = 0; break; default: - dev_warn(p->dev, "this kernel doesn't support %d texture dim\n", G_038000_DIM(word0)); + dev_warn_once(p->dev, "this kernel doesn't support %d texture dim\n", G_038000_DIM(word0)); return -EINVAL; } if (!r600_fmt_is_valid_texture(format, p->family)) { - dev_warn(p->dev, "%s:%d texture invalid format %d\n", - __func__, __LINE__, format); + dev_warn_once(p->dev, "%s:%d texture invalid format %d\n", + __func__, __LINE__, format); return -EINVAL; } if (r600_get_array_mode_alignment(&array_check, &pitch_align, &height_align, &depth_align, &base_align)) { - dev_warn(p->dev, "%s:%d tex array mode (%d) invalid\n", - __func__, __LINE__, G_038000_TILE_MODE(word0)); + dev_warn_once(p->dev, "%s:%d tex array mode (%d) invalid\n", + __func__, __LINE__, G_038000_TILE_MODE(word0)); return -EINVAL; } /* XXX check height as well... */ if (!IS_ALIGNED(pitch, pitch_align)) { - dev_warn(p->dev, "%s:%d tex pitch (%d, 0x%x, %d) invalid\n", - __func__, __LINE__, pitch, pitch_align, G_038000_TILE_MODE(word0)); + dev_warn_once(p->dev, "%s:%d tex pitch (%d, 0x%x, %d) invalid\n", + __func__, __LINE__, pitch, pitch_align, G_038000_TILE_MODE(word0)); return -EINVAL; } if (!IS_ALIGNED(base_offset, base_align)) { - dev_warn(p->dev, "%s:%d tex base offset (0x%llx, 0x%llx, %d) invalid\n", - __func__, __LINE__, base_offset, base_align, G_038000_TILE_MODE(word0)); + dev_warn_once(p->dev, "%s:%d tex base offset (0x%llx, 0x%llx, %d) invalid\n", + __func__, __LINE__, base_offset, base_align, G_038000_TILE_MODE(word0)); return -EINVAL; } if (!IS_ALIGNED(mip_offset, base_align)) { - dev_warn(p->dev, "%s:%d tex mip offset (0x%llx, 0x%llx, %d) invalid\n", - __func__, __LINE__, mip_offset, base_align, G_038000_TILE_MODE(word0)); + dev_warn_once(p->dev, "%s:%d tex mip offset (0x%llx, 0x%llx, %d) invalid\n", + __func__, __LINE__, mip_offset, base_align, G_038000_TILE_MODE(word0)); return -EINVAL; } if (blevel > llevel) { - dev_warn(p->dev, "texture blevel %d > llevel %d\n", - blevel, llevel); + dev_warn_once(p->dev, "texture blevel %d > llevel %d\n", + blevel, llevel); } if (is_array) { barray = G_038014_BASE_ARRAY(word5); @@ -1592,16 +1597,16 @@ static int r600_check_texture_resource(struct radeon_cs_parser *p, u32 idx, &l0_size, &mipmap_size); /* using get ib will give us the offset into the texture bo */ if ((l0_size + word2) > radeon_bo_size(texture)) { - dev_warn(p->dev, "texture bo too small ((%d %d) (%d %d) %d %d %d -> %d have %ld)\n", - w0, h0, pitch_align, height_align, - array_check.array_mode, format, word2, - l0_size, radeon_bo_size(texture)); - dev_warn(p->dev, "alignments %d %d %d %lld\n", pitch, pitch_align, height_align, base_align); + dev_warn_once(p->dev, "texture bo too small ((%d %d) (%d %d) %d %d %d -> %d have %ld)\n", + w0, h0, pitch_align, height_align, + array_check.array_mode, format, word2, + l0_size, radeon_bo_size(texture)); + dev_warn_once(p->dev, "alignments %d %d %d %lld\n", pitch, pitch_align, height_align, base_align); return -EINVAL; } /* using get ib will give us the offset into the mipmap bo */ if ((mipmap_size + word3) > radeon_bo_size(mipmap)) { - /*dev_warn(p->dev, "mipmap bo too small (%d %d %d %d %d %d -> %d have %ld)\n", + /*dev_warn_once(p->dev, "mipmap bo too small (%d %d %d %d %d %d -> %d have %ld)\n", w0, h0, format, blevel, nlevels, word3, mipmap_size, radeon_bo_size(texture));*/ } return 0; @@ -1613,13 +1618,13 @@ static bool r600_is_safe_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) i = (reg >> 7); if (i >= ARRAY_SIZE(r600_reg_safe_bm)) { - dev_warn(p->dev, "forbidden register 0x%08x at %d\n", reg, idx); + dev_warn_once(p->dev, "forbidden register 0x%08x at %d\n", reg, idx); return false; } m = 1 << ((reg >> 2) & 31); if (!(r600_reg_safe_bm[i] & m)) return true; - dev_warn(p->dev, "forbidden register 0x%08x at %d\n", reg, idx); + dev_warn_once(p->dev, "forbidden register 0x%08x at %d\n", reg, idx); return false; } @@ -1648,7 +1653,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p, uint64_t offset; if (pkt->count != 1) { - DRM_ERROR("bad SET PREDICATION\n"); + dev_warn_once(p->dev, "bad SET PREDICATION\n"); return -EINVAL; } @@ -1660,13 +1665,13 @@ static int r600_packet3_check(struct radeon_cs_parser *p, return 0; if (pred_op > 2) { - DRM_ERROR("bad SET PREDICATION operation %d\n", pred_op); + dev_warn_once(p->dev, "bad SET PREDICATION operation %d\n", pred_op); return -EINVAL; } r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm); if (r) { - DRM_ERROR("bad SET PREDICATION\n"); + dev_warn_once(p->dev, "bad SET PREDICATION\n"); return -EINVAL; } @@ -1681,20 +1686,20 @@ static int r600_packet3_check(struct radeon_cs_parser *p, case PACKET3_START_3D_CMDBUF: if (p->family >= CHIP_RV770 || pkt->count) { - DRM_ERROR("bad START_3D\n"); + dev_warn_once(p->dev, "bad START_3D\n"); return -EINVAL; } break; case PACKET3_CONTEXT_CONTROL: if (pkt->count != 1) { - DRM_ERROR("bad CONTEXT_CONTROL\n"); + dev_warn_once(p->dev, "bad CONTEXT_CONTROL\n"); return -EINVAL; } break; case PACKET3_INDEX_TYPE: case PACKET3_NUM_INSTANCES: if (pkt->count) { - DRM_ERROR("bad INDEX_TYPE/NUM_INSTANCES\n"); + dev_warn_once(p->dev, "bad INDEX_TYPE/NUM_INSTANCES\n"); return -EINVAL; } break; @@ -1702,12 +1707,12 @@ static int r600_packet3_check(struct radeon_cs_parser *p, { uint64_t offset; if (pkt->count != 3) { - DRM_ERROR("bad DRAW_INDEX\n"); + dev_warn_once(p->dev, "bad DRAW_INDEX\n"); return -EINVAL; } r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm); if (r) { - DRM_ERROR("bad DRAW_INDEX\n"); + dev_warn_once(p->dev, "bad DRAW_INDEX\n"); return -EINVAL; } @@ -1720,37 +1725,37 @@ static int r600_packet3_check(struct radeon_cs_parser *p, r = r600_cs_track_check(p); if (r) { - dev_warn(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__); + dev_warn_once(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__); return r; } break; } case PACKET3_DRAW_INDEX_AUTO: if (pkt->count != 1) { - DRM_ERROR("bad DRAW_INDEX_AUTO\n"); + dev_warn_once(p->dev, "bad DRAW_INDEX_AUTO\n"); return -EINVAL; } r = r600_cs_track_check(p); if (r) { - dev_warn(p->dev, "%s:%d invalid cmd stream %d\n", __func__, __LINE__, idx); + dev_warn_once(p->dev, "%s:%d invalid cmd stream %d\n", __func__, __LINE__, idx); return r; } break; case PACKET3_DRAW_INDEX_IMMD_BE: case PACKET3_DRAW_INDEX_IMMD: if (pkt->count < 2) { - DRM_ERROR("bad DRAW_INDEX_IMMD\n"); + dev_warn_once(p->dev, "bad DRAW_INDEX_IMMD\n"); return -EINVAL; } r = r600_cs_track_check(p); if (r) { - dev_warn(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__); + dev_warn_once(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__); return r; } break; case PACKET3_WAIT_REG_MEM: if (pkt->count != 5) { - DRM_ERROR("bad WAIT_REG_MEM\n"); + dev_warn_once(p->dev, "bad WAIT_REG_MEM\n"); return -EINVAL; } /* bit 4 is reg (0) or mem (1) */ @@ -1759,7 +1764,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p, r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm); if (r) { - DRM_ERROR("bad WAIT_REG_MEM\n"); + dev_warn_once(p->dev, "bad WAIT_REG_MEM\n"); return -EINVAL; } @@ -1770,7 +1775,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p, ib[idx+1] = (ib[idx+1] & 0x3) | (offset & 0xfffffff0); ib[idx+2] = upper_32_bits(offset) & 0xff; } else if (idx_value & 0x100) { - DRM_ERROR("cannot use PFP on REG wait\n"); + dev_warn_once(p->dev, "cannot use PFP on REG wait\n"); return -EINVAL; } break; @@ -1779,24 +1784,24 @@ static int r600_packet3_check(struct radeon_cs_parser *p, u32 command, size; u64 offset, tmp; if (pkt->count != 4) { - DRM_ERROR("bad CP DMA\n"); + dev_warn_once(p->dev, "bad CP DMA\n"); return -EINVAL; } command = radeon_get_ib_value(p, idx+4); size = command & 0x1fffff; if (command & PACKET3_CP_DMA_CMD_SAS) { /* src address space is register */ - DRM_ERROR("CP DMA SAS not supported\n"); + dev_warn_once(p->dev, "CP DMA SAS not supported\n"); return -EINVAL; } else { if (command & PACKET3_CP_DMA_CMD_SAIC) { - DRM_ERROR("CP DMA SAIC only supported for registers\n"); + dev_warn_once(p->dev, "CP DMA SAIC only supported for registers\n"); return -EINVAL; } /* src address space is memory */ r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm); if (r) { - DRM_ERROR("bad CP DMA SRC\n"); + dev_warn_once(p->dev, "bad CP DMA SRC\n"); return -EINVAL; } @@ -1806,8 +1811,8 @@ static int r600_packet3_check(struct radeon_cs_parser *p, offset = reloc->gpu_offset + tmp; if ((tmp + size) > radeon_bo_size(reloc->robj)) { - dev_warn(p->dev, "CP DMA src buffer too small (%llu %lu)\n", - tmp + size, radeon_bo_size(reloc->robj)); + dev_warn_once(p->dev, "CP DMA src buffer too small (%llu %lu)\n", + tmp + size, radeon_bo_size(reloc->robj)); return -EINVAL; } @@ -1816,17 +1821,17 @@ static int r600_packet3_check(struct radeon_cs_parser *p, } if (command & PACKET3_CP_DMA_CMD_DAS) { /* dst address space is register */ - DRM_ERROR("CP DMA DAS not supported\n"); + dev_warn_once(p->dev, "CP DMA DAS not supported\n"); return -EINVAL; } else { /* dst address space is memory */ if (command & PACKET3_CP_DMA_CMD_DAIC) { - DRM_ERROR("CP DMA DAIC only supported for registers\n"); + dev_warn_once(p->dev, "CP DMA DAIC only supported for registers\n"); return -EINVAL; } r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm); if (r) { - DRM_ERROR("bad CP DMA DST\n"); + dev_warn_once(p->dev, "bad CP DMA DST\n"); return -EINVAL; } @@ -1836,8 +1841,8 @@ static int r600_packet3_check(struct radeon_cs_parser *p, offset = reloc->gpu_offset + tmp; if ((tmp + size) > radeon_bo_size(reloc->robj)) { - dev_warn(p->dev, "CP DMA dst buffer too small (%llu %lu)\n", - tmp + size, radeon_bo_size(reloc->robj)); + dev_warn_once(p->dev, "CP DMA dst buffer too small (%llu %lu)\n", + tmp + size, radeon_bo_size(reloc->robj)); return -EINVAL; } @@ -1848,7 +1853,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p, } case PACKET3_SURFACE_SYNC: if (pkt->count != 3) { - DRM_ERROR("bad SURFACE_SYNC\n"); + dev_warn_once(p->dev, "bad SURFACE_SYNC\n"); return -EINVAL; } /* 0xffffffff/0x0 is flush all cache flag */ @@ -1856,7 +1861,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p, radeon_get_ib_value(p, idx + 2) != 0) { r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm); if (r) { - DRM_ERROR("bad SURFACE_SYNC\n"); + dev_warn_once(p->dev, "bad SURFACE_SYNC\n"); return -EINVAL; } ib[idx+2] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff); @@ -1864,7 +1869,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p, break; case PACKET3_EVENT_WRITE: if (pkt->count != 2 && pkt->count != 0) { - DRM_ERROR("bad EVENT_WRITE\n"); + dev_warn_once(p->dev, "bad EVENT_WRITE\n"); return -EINVAL; } if (pkt->count) { @@ -1872,7 +1877,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p, r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm); if (r) { - DRM_ERROR("bad EVENT_WRITE\n"); + dev_warn_once(p->dev, "bad EVENT_WRITE\n"); return -EINVAL; } offset = reloc->gpu_offset + @@ -1888,12 +1893,12 @@ static int r600_packet3_check(struct radeon_cs_parser *p, uint64_t offset; if (pkt->count != 4) { - DRM_ERROR("bad EVENT_WRITE_EOP\n"); + dev_warn_once(p->dev, "bad EVENT_WRITE_EOP\n"); return -EINVAL; } r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm); if (r) { - DRM_ERROR("bad EVENT_WRITE\n"); + dev_warn_once(p->dev, "bad EVENT_WRITE\n"); return -EINVAL; } @@ -1911,7 +1916,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p, if ((start_reg < PACKET3_SET_CONFIG_REG_OFFSET) || (start_reg >= PACKET3_SET_CONFIG_REG_END) || (end_reg >= PACKET3_SET_CONFIG_REG_END)) { - DRM_ERROR("bad PACKET3_SET_CONFIG_REG\n"); + dev_warn_once(p->dev, "bad PACKET3_SET_CONFIG_REG\n"); return -EINVAL; } for (i = 0; i < pkt->count; i++) { @@ -1927,7 +1932,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p, if ((start_reg < PACKET3_SET_CONTEXT_REG_OFFSET) || (start_reg >= PACKET3_SET_CONTEXT_REG_END) || (end_reg >= PACKET3_SET_CONTEXT_REG_END)) { - DRM_ERROR("bad PACKET3_SET_CONTEXT_REG\n"); + dev_warn_once(p->dev, "bad PACKET3_SET_CONTEXT_REG\n"); return -EINVAL; } for (i = 0; i < pkt->count; i++) { @@ -1939,7 +1944,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p, break; case PACKET3_SET_RESOURCE: if (pkt->count % 7) { - DRM_ERROR("bad SET_RESOURCE\n"); + dev_warn_once(p->dev, "bad SET_RESOURCE\n"); return -EINVAL; } start_reg = (idx_value << 2) + PACKET3_SET_RESOURCE_OFFSET; @@ -1947,7 +1952,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p, if ((start_reg < PACKET3_SET_RESOURCE_OFFSET) || (start_reg >= PACKET3_SET_RESOURCE_END) || (end_reg >= PACKET3_SET_RESOURCE_END)) { - DRM_ERROR("bad SET_RESOURCE\n"); + dev_warn_once(p->dev, "bad SET_RESOURCE\n"); return -EINVAL; } for (i = 0; i < (pkt->count / 7); i++) { @@ -1959,7 +1964,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p, /* tex base */ r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm); if (r) { - DRM_ERROR("bad SET_RESOURCE\n"); + dev_warn_once(p->dev, "bad SET_RESOURCE\n"); return -EINVAL; } base_offset = (u32)((reloc->gpu_offset >> 8) & 0xffffffff); @@ -1973,7 +1978,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p, /* tex mip base */ r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm); if (r) { - DRM_ERROR("bad SET_RESOURCE\n"); + dev_warn_once(p->dev, "bad SET_RESOURCE\n"); return -EINVAL; } mip_offset = (u32)((reloc->gpu_offset >> 8) & 0xffffffff); @@ -1994,15 +1999,15 @@ static int r600_packet3_check(struct radeon_cs_parser *p, /* vtx base */ r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm); if (r) { - DRM_ERROR("bad SET_RESOURCE\n"); + dev_warn_once(p->dev, "bad SET_RESOURCE\n"); return -EINVAL; } offset = radeon_get_ib_value(p, idx+1+(i*7)+0); size = radeon_get_ib_value(p, idx+1+(i*7)+1) + 1; if (p->rdev && (size + offset) > radeon_bo_size(reloc->robj)) { /* force size to size of the buffer */ - dev_warn(p->dev, "vbo resource seems too big (%d) for the bo (%ld)\n", - size + offset, radeon_bo_size(reloc->robj)); + dev_warn_once(p->dev, "vbo resource seems too big (%d) for the bo (%ld)\n", + size + offset, radeon_bo_size(reloc->robj)); ib[idx+1+(i*7)+1] = radeon_bo_size(reloc->robj) - offset; } @@ -2015,7 +2020,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p, case SQ_TEX_VTX_INVALID_TEXTURE: case SQ_TEX_VTX_INVALID_BUFFER: default: - DRM_ERROR("bad SET_RESOURCE\n"); + dev_warn_once(p->dev, "bad SET_RESOURCE\n"); return -EINVAL; } } @@ -2027,7 +2032,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p, if ((start_reg < PACKET3_SET_ALU_CONST_OFFSET) || (start_reg >= PACKET3_SET_ALU_CONST_END) || (end_reg >= PACKET3_SET_ALU_CONST_END)) { - DRM_ERROR("bad SET_ALU_CONST\n"); + dev_warn_once(p->dev, "bad SET_ALU_CONST\n"); return -EINVAL; } } @@ -2038,7 +2043,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p, if ((start_reg < PACKET3_SET_BOOL_CONST_OFFSET) || (start_reg >= PACKET3_SET_BOOL_CONST_END) || (end_reg >= PACKET3_SET_BOOL_CONST_END)) { - DRM_ERROR("bad SET_BOOL_CONST\n"); + dev_warn_once(p->dev, "bad SET_BOOL_CONST\n"); return -EINVAL; } break; @@ -2048,7 +2053,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p, if ((start_reg < PACKET3_SET_LOOP_CONST_OFFSET) || (start_reg >= PACKET3_SET_LOOP_CONST_END) || (end_reg >= PACKET3_SET_LOOP_CONST_END)) { - DRM_ERROR("bad SET_LOOP_CONST\n"); + dev_warn_once(p->dev, "bad SET_LOOP_CONST\n"); return -EINVAL; } break; @@ -2058,13 +2063,13 @@ static int r600_packet3_check(struct radeon_cs_parser *p, if ((start_reg < PACKET3_SET_CTL_CONST_OFFSET) || (start_reg >= PACKET3_SET_CTL_CONST_END) || (end_reg >= PACKET3_SET_CTL_CONST_END)) { - DRM_ERROR("bad SET_CTL_CONST\n"); + dev_warn_once(p->dev, "bad SET_CTL_CONST\n"); return -EINVAL; } break; case PACKET3_SET_SAMPLER: if (pkt->count % 3) { - DRM_ERROR("bad SET_SAMPLER\n"); + dev_warn_once(p->dev, "bad SET_SAMPLER\n"); return -EINVAL; } start_reg = (idx_value << 2) + PACKET3_SET_SAMPLER_OFFSET; @@ -2072,22 +2077,22 @@ static int r600_packet3_check(struct radeon_cs_parser *p, if ((start_reg < PACKET3_SET_SAMPLER_OFFSET) || (start_reg >= PACKET3_SET_SAMPLER_END) || (end_reg >= PACKET3_SET_SAMPLER_END)) { - DRM_ERROR("bad SET_SAMPLER\n"); + dev_warn_once(p->dev, "bad SET_SAMPLER\n"); return -EINVAL; } break; case PACKET3_STRMOUT_BASE_UPDATE: /* RS780 and RS880 also need this */ if (p->family < CHIP_RS780) { - DRM_ERROR("STRMOUT_BASE_UPDATE only supported on 7xx\n"); + dev_warn_once(p->dev, "STRMOUT_BASE_UPDATE only supported on 7xx\n"); return -EINVAL; } if (pkt->count != 1) { - DRM_ERROR("bad STRMOUT_BASE_UPDATE packet count\n"); + dev_warn_once(p->dev, "bad STRMOUT_BASE_UPDATE packet count\n"); return -EINVAL; } if (idx_value > 3) { - DRM_ERROR("bad STRMOUT_BASE_UPDATE index\n"); + dev_warn_once(p->dev, "bad STRMOUT_BASE_UPDATE index\n"); return -EINVAL; } { @@ -2095,25 +2100,27 @@ static int r600_packet3_check(struct radeon_cs_parser *p, r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm); if (r) { - DRM_ERROR("bad STRMOUT_BASE_UPDATE reloc\n"); + dev_warn_once(p->dev, "bad STRMOUT_BASE_UPDATE reloc\n"); return -EINVAL; } if (reloc->robj != track->vgt_strmout_bo[idx_value]) { - DRM_ERROR("bad STRMOUT_BASE_UPDATE, bo does not match\n"); + dev_warn_once(p->dev, "bad STRMOUT_BASE_UPDATE, bo does not match\n"); return -EINVAL; } offset = (u64)radeon_get_ib_value(p, idx+1) << 8; if (offset != track->vgt_strmout_bo_offset[idx_value]) { - DRM_ERROR("bad STRMOUT_BASE_UPDATE, bo offset does not match: 0x%llx, 0x%x\n", - offset, track->vgt_strmout_bo_offset[idx_value]); + dev_warn_once(p->dev, + "bad STRMOUT_BASE_UPDATE, bo offset does not match: 0x%llx, 0x%x\n", + offset, track->vgt_strmout_bo_offset[idx_value]); return -EINVAL; } if ((offset + 4) > radeon_bo_size(reloc->robj)) { - DRM_ERROR("bad STRMOUT_BASE_UPDATE bo too small: 0x%llx, 0x%lx\n", - offset + 4, radeon_bo_size(reloc->robj)); + dev_warn_once(p->dev, + "bad STRMOUT_BASE_UPDATE bo too small: 0x%llx, 0x%lx\n", + offset + 4, radeon_bo_size(reloc->robj)); return -EINVAL; } ib[idx+1] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff); @@ -2121,17 +2128,17 @@ static int r600_packet3_check(struct radeon_cs_parser *p, break; case PACKET3_SURFACE_BASE_UPDATE: if (p->family >= CHIP_RV770 || p->family == CHIP_R600) { - DRM_ERROR("bad SURFACE_BASE_UPDATE\n"); + dev_warn_once(p->dev, "bad SURFACE_BASE_UPDATE\n"); return -EINVAL; } if (pkt->count) { - DRM_ERROR("bad SURFACE_BASE_UPDATE\n"); + dev_warn_once(p->dev, "bad SURFACE_BASE_UPDATE\n"); return -EINVAL; } break; case PACKET3_STRMOUT_BUFFER_UPDATE: if (pkt->count != 4) { - DRM_ERROR("bad STRMOUT_BUFFER_UPDATE (invalid count)\n"); + dev_warn_once(p->dev, "bad STRMOUT_BUFFER_UPDATE (invalid count)\n"); return -EINVAL; } /* Updating memory at DST_ADDRESS. */ @@ -2139,14 +2146,15 @@ static int r600_packet3_check(struct radeon_cs_parser *p, u64 offset; r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm); if (r) { - DRM_ERROR("bad STRMOUT_BUFFER_UPDATE (missing dst reloc)\n"); + dev_warn_once(p->dev, "bad STRMOUT_BUFFER_UPDATE (missing dst reloc)\n"); return -EINVAL; } offset = radeon_get_ib_value(p, idx+1); offset += ((u64)(radeon_get_ib_value(p, idx+2) & 0xff)) << 32; if ((offset + 4) > radeon_bo_size(reloc->robj)) { - DRM_ERROR("bad STRMOUT_BUFFER_UPDATE dst bo too small: 0x%llx, 0x%lx\n", - offset + 4, radeon_bo_size(reloc->robj)); + dev_warn_once(p->dev, + "bad STRMOUT_BUFFER_UPDATE dst bo too small: 0x%llx, 0x%lx\n", + offset + 4, radeon_bo_size(reloc->robj)); return -EINVAL; } offset += reloc->gpu_offset; @@ -2158,14 +2166,15 @@ static int r600_packet3_check(struct radeon_cs_parser *p, u64 offset; r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm); if (r) { - DRM_ERROR("bad STRMOUT_BUFFER_UPDATE (missing src reloc)\n"); + dev_warn_once(p->dev, "bad STRMOUT_BUFFER_UPDATE (missing src reloc)\n"); return -EINVAL; } offset = radeon_get_ib_value(p, idx+3); offset += ((u64)(radeon_get_ib_value(p, idx+4) & 0xff)) << 32; if ((offset + 4) > radeon_bo_size(reloc->robj)) { - DRM_ERROR("bad STRMOUT_BUFFER_UPDATE src bo too small: 0x%llx, 0x%lx\n", - offset + 4, radeon_bo_size(reloc->robj)); + dev_warn_once(p->dev, + "bad STRMOUT_BUFFER_UPDATE src bo too small: 0x%llx, 0x%lx\n", + offset + 4, radeon_bo_size(reloc->robj)); return -EINVAL; } offset += reloc->gpu_offset; @@ -2178,23 +2187,23 @@ static int r600_packet3_check(struct radeon_cs_parser *p, u64 offset; if (pkt->count != 3) { - DRM_ERROR("bad MEM_WRITE (invalid count)\n"); + dev_warn_once(p->dev, "bad MEM_WRITE (invalid count)\n"); return -EINVAL; } r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm); if (r) { - DRM_ERROR("bad MEM_WRITE (missing reloc)\n"); + dev_warn_once(p->dev, "bad MEM_WRITE (missing reloc)\n"); return -EINVAL; } offset = radeon_get_ib_value(p, idx+0); offset += ((u64)(radeon_get_ib_value(p, idx+1) & 0xff)) << 32UL; if (offset & 0x7) { - DRM_ERROR("bad MEM_WRITE (address not qwords aligned)\n"); + dev_warn_once(p->dev, "bad MEM_WRITE (address not qwords aligned)\n"); return -EINVAL; } if ((offset + 8) > radeon_bo_size(reloc->robj)) { - DRM_ERROR("bad MEM_WRITE bo too small: 0x%llx, 0x%lx\n", - offset + 8, radeon_bo_size(reloc->robj)); + dev_warn_once(p->dev, "bad MEM_WRITE bo too small: 0x%llx, 0x%lx\n", + offset + 8, radeon_bo_size(reloc->robj)); return -EINVAL; } offset += reloc->gpu_offset; @@ -2204,7 +2213,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p, } case PACKET3_COPY_DW: if (pkt->count != 4) { - DRM_ERROR("bad COPY_DW (invalid count)\n"); + dev_warn_once(p->dev, "bad COPY_DW (invalid count)\n"); return -EINVAL; } if (idx_value & 0x1) { @@ -2212,14 +2221,14 @@ static int r600_packet3_check(struct radeon_cs_parser *p, /* SRC is memory. */ r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm); if (r) { - DRM_ERROR("bad COPY_DW (missing src reloc)\n"); + dev_warn_once(p->dev, "bad COPY_DW (missing src reloc)\n"); return -EINVAL; } offset = radeon_get_ib_value(p, idx+1); offset += ((u64)(radeon_get_ib_value(p, idx+2) & 0xff)) << 32; if ((offset + 4) > radeon_bo_size(reloc->robj)) { - DRM_ERROR("bad COPY_DW src bo too small: 0x%llx, 0x%lx\n", - offset + 4, radeon_bo_size(reloc->robj)); + dev_warn_once(p->dev, "bad COPY_DW src bo too small: 0x%llx, 0x%lx\n", + offset + 4, radeon_bo_size(reloc->robj)); return -EINVAL; } offset += reloc->gpu_offset; @@ -2236,14 +2245,14 @@ static int r600_packet3_check(struct radeon_cs_parser *p, /* DST is memory. */ r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm); if (r) { - DRM_ERROR("bad COPY_DW (missing dst reloc)\n"); + dev_warn_once(p->dev, "bad COPY_DW (missing dst reloc)\n"); return -EINVAL; } offset = radeon_get_ib_value(p, idx+3); offset += ((u64)(radeon_get_ib_value(p, idx+4) & 0xff)) << 32; if ((offset + 4) > radeon_bo_size(reloc->robj)) { - DRM_ERROR("bad COPY_DW dst bo too small: 0x%llx, 0x%lx\n", - offset + 4, radeon_bo_size(reloc->robj)); + dev_warn_once(p->dev, "bad COPY_DW dst bo too small: 0x%llx, 0x%lx\n", + offset + 4, radeon_bo_size(reloc->robj)); return -EINVAL; } offset += reloc->gpu_offset; @@ -2259,7 +2268,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p, case PACKET3_NOP: break; default: - DRM_ERROR("Packet3 opcode %x not supported\n", pkt->opcode); + dev_warn_once(p->dev, "Packet3 opcode %x not supported\n", pkt->opcode); return -EINVAL; } return 0; @@ -2306,7 +2315,7 @@ int r600_cs_parse(struct radeon_cs_parser *p) r = r600_packet3_check(p, &pkt); break; default: - DRM_ERROR("Unknown packet type %d !\n", pkt.type); + dev_warn_once(p->dev, "Unknown packet type %d !\n", pkt.type); kfree(p->track); p->track = NULL; return -EINVAL; @@ -2346,13 +2355,13 @@ int r600_dma_cs_next_reloc(struct radeon_cs_parser *p, *cs_reloc = NULL; if (p->chunk_relocs == NULL) { - DRM_ERROR("No relocation chunk !\n"); + dev_warn_once(p->dev, "No relocation chunk !\n"); return -EINVAL; } idx = p->dma_reloc_idx; if (idx >= p->nrelocs) { - DRM_ERROR("Relocs at %d after relocations chunk end %d !\n", - idx, p->nrelocs); + dev_warn_once(p->dev, "Relocs at %d after relocations chunk end %d !\n", + idx, p->nrelocs); return -EINVAL; } *cs_reloc = &p->relocs[idx]; @@ -2385,8 +2394,8 @@ int r600_dma_cs_parse(struct radeon_cs_parser *p) do { if (p->idx >= ib_chunk->length_dw) { - DRM_ERROR("Can not parse packet at %d after CS end %d !\n", - p->idx, ib_chunk->length_dw); + dev_warn_once(p->dev, "Can not parse packet at %d after CS end %d !\n", + p->idx, ib_chunk->length_dw); return -EINVAL; } idx = p->idx; @@ -2399,7 +2408,7 @@ int r600_dma_cs_parse(struct radeon_cs_parser *p) case DMA_PACKET_WRITE: r = r600_dma_cs_next_reloc(p, &dst_reloc); if (r) { - DRM_ERROR("bad DMA_PACKET_WRITE\n"); + dev_warn_once(p->dev, "bad DMA_PACKET_WRITE\n"); return -EINVAL; } if (tiled) { @@ -2417,20 +2426,20 @@ int r600_dma_cs_parse(struct radeon_cs_parser *p) p->idx += count + 3; } if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) { - dev_warn(p->dev, "DMA write buffer too small (%llu %lu)\n", - dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj)); + dev_warn_once(p->dev, "DMA write buffer too small (%llu %lu)\n", + dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj)); return -EINVAL; } break; case DMA_PACKET_COPY: r = r600_dma_cs_next_reloc(p, &src_reloc); if (r) { - DRM_ERROR("bad DMA_PACKET_COPY\n"); + dev_warn_once(p->dev, "bad DMA_PACKET_COPY\n"); return -EINVAL; } r = r600_dma_cs_next_reloc(p, &dst_reloc); if (r) { - DRM_ERROR("bad DMA_PACKET_COPY\n"); + dev_warn_once(p->dev, "bad DMA_PACKET_COPY\n"); return -EINVAL; } if (tiled) { @@ -2484,31 +2493,31 @@ int r600_dma_cs_parse(struct radeon_cs_parser *p) } } if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) { - dev_warn(p->dev, "DMA copy src buffer too small (%llu %lu)\n", - src_offset + (count * 4), radeon_bo_size(src_reloc->robj)); + dev_warn_once(p->dev, "DMA copy src buffer too small (%llu %lu)\n", + src_offset + (count * 4), radeon_bo_size(src_reloc->robj)); return -EINVAL; } if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) { - dev_warn(p->dev, "DMA write dst buffer too small (%llu %lu)\n", - dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj)); + dev_warn_once(p->dev, "DMA write dst buffer too small (%llu %lu)\n", + dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj)); return -EINVAL; } break; case DMA_PACKET_CONSTANT_FILL: if (p->family < CHIP_RV770) { - DRM_ERROR("Constant Fill is 7xx only !\n"); + dev_warn_once(p->dev, "Constant Fill is 7xx only !\n"); return -EINVAL; } r = r600_dma_cs_next_reloc(p, &dst_reloc); if (r) { - DRM_ERROR("bad DMA_PACKET_WRITE\n"); + dev_warn_once(p->dev, "bad DMA_PACKET_WRITE\n"); return -EINVAL; } dst_offset = radeon_get_ib_value(p, idx+1); dst_offset |= ((u64)(radeon_get_ib_value(p, idx+3) & 0x00ff0000)) << 16; if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) { - dev_warn(p->dev, "DMA constant fill buffer too small (%llu %lu)\n", - dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj)); + dev_warn_once(p->dev, "DMA constant fill buffer too small (%llu %lu)\n", + dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj)); return -EINVAL; } ib[idx+1] += (u32)(dst_reloc->gpu_offset & 0xfffffffc); @@ -2519,7 +2528,7 @@ int r600_dma_cs_parse(struct radeon_cs_parser *p) p->idx += 1; break; default: - DRM_ERROR("Unknown packet type %d at %d !\n", cmd, idx); + dev_warn_once(p->dev, "Unknown packet type %d at %d !\n", cmd, idx); return -EINVAL; } } while (p->idx < p->chunk_ib->length_dw); diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c index b8e6202f1d5b..3f9c0011244f 100644 --- a/drivers/gpu/drm/radeon/radeon_cs.c +++ b/drivers/gpu/drm/radeon/radeon_cs.c @@ -834,7 +834,7 @@ void radeon_cs_dump_packet(struct radeon_cs_parser *p, ib = p->ib.ptr; idx = pkt->idx; for (i = 0; i <= (pkt->count + 1); i++, idx++) - DRM_INFO("ib[%d]=0x%08X\n", idx, ib[idx]); + dev_dbg(p->dev, "ib[%d]=0x%08X\n", idx, ib[idx]); } /** diff --git a/drivers/gpu/drm/radeon/radeon_legacy_encoders.c b/drivers/gpu/drm/radeon/radeon_legacy_encoders.c index d6aa1a3012a8..d1e8b9757a65 100644 --- a/drivers/gpu/drm/radeon/radeon_legacy_encoders.c +++ b/drivers/gpu/drm/radeon/radeon_legacy_encoders.c @@ -136,9 +136,9 @@ static void radeon_legacy_lvds_update(struct drm_encoder *encoder, int mode) } if (rdev->is_atom_bios) - radeon_atombios_encoder_dpms_scratch_regs(encoder, (mode == DRM_MODE_DPMS_ON) ? true : false); + radeon_atombios_encoder_dpms_scratch_regs(encoder, mode == DRM_MODE_DPMS_ON); else - radeon_combios_encoder_dpms_scratch_regs(encoder, (mode == DRM_MODE_DPMS_ON) ? true : false); + radeon_combios_encoder_dpms_scratch_regs(encoder, mode == DRM_MODE_DPMS_ON); } @@ -545,9 +545,9 @@ static void radeon_legacy_primary_dac_dpms(struct drm_encoder *encoder, int mode WREG32(RADEON_DAC_MACRO_CNTL, dac_macro_cntl); if (rdev->is_atom_bios) - radeon_atombios_encoder_dpms_scratch_regs(encoder, (mode == DRM_MODE_DPMS_ON) ? true : false); + radeon_atombios_encoder_dpms_scratch_regs(encoder, mode == DRM_MODE_DPMS_ON); else - radeon_combios_encoder_dpms_scratch_regs(encoder, (mode == DRM_MODE_DPMS_ON) ? true : false); + radeon_combios_encoder_dpms_scratch_regs(encoder, mode == DRM_MODE_DPMS_ON); } @@ -742,9 +742,9 @@ static void radeon_legacy_tmds_int_dpms(struct drm_encoder *encoder, int mode) WREG32(RADEON_FP_GEN_CNTL, fp_gen_cntl); if (rdev->is_atom_bios) - radeon_atombios_encoder_dpms_scratch_regs(encoder, (mode == DRM_MODE_DPMS_ON) ? true : false); + radeon_atombios_encoder_dpms_scratch_regs(encoder, mode == DRM_MODE_DPMS_ON); else - radeon_combios_encoder_dpms_scratch_regs(encoder, (mode == DRM_MODE_DPMS_ON) ? true : false); + radeon_combios_encoder_dpms_scratch_regs(encoder, mode == DRM_MODE_DPMS_ON); } @@ -908,9 +908,9 @@ static void radeon_legacy_tmds_ext_dpms(struct drm_encoder *encoder, int mode) WREG32(RADEON_FP2_GEN_CNTL, fp2_gen_cntl); if (rdev->is_atom_bios) - radeon_atombios_encoder_dpms_scratch_regs(encoder, (mode == DRM_MODE_DPMS_ON) ? true : false); + radeon_atombios_encoder_dpms_scratch_regs(encoder, mode == DRM_MODE_DPMS_ON); else - radeon_combios_encoder_dpms_scratch_regs(encoder, (mode == DRM_MODE_DPMS_ON) ? true : false); + radeon_combios_encoder_dpms_scratch_regs(encoder, mode == DRM_MODE_DPMS_ON); } @@ -1113,9 +1113,9 @@ static void radeon_legacy_tv_dac_dpms(struct drm_encoder *encoder, int mode) } if (rdev->is_atom_bios) - radeon_atombios_encoder_dpms_scratch_regs(encoder, (mode == DRM_MODE_DPMS_ON) ? true : false); + radeon_atombios_encoder_dpms_scratch_regs(encoder, mode == DRM_MODE_DPMS_ON); else - radeon_combios_encoder_dpms_scratch_regs(encoder, (mode == DRM_MODE_DPMS_ON) ? true : false); + radeon_combios_encoder_dpms_scratch_regs(encoder, mode == DRM_MODE_DPMS_ON); } diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c index b4fb7e70320b..a855a96dd2ea 100644 --- a/drivers/gpu/drm/radeon/radeon_pm.c +++ b/drivers/gpu/drm/radeon/radeon_pm.c @@ -907,8 +907,7 @@ static void radeon_dpm_thermal_work_handler(struct work_struct *work) static bool radeon_dpm_single_display(struct radeon_device *rdev) { - bool single_display = (rdev->pm.dpm.new_active_crtc_count < 2) ? - true : false; + bool single_display = rdev->pm.dpm.new_active_crtc_count < 2; /* check if the vblank period is too short to adjust the mclk */ if (single_display && rdev->asic->dpm.vblank_too_short) { diff --git a/drivers/gpu/drm/renesas/rcar-du/rcar_lvds.c b/drivers/gpu/drm/renesas/rcar-du/rcar_lvds.c index af58b814e588..001b3543924a 100644 --- a/drivers/gpu/drm/renesas/rcar-du/rcar_lvds.c +++ b/drivers/gpu/drm/renesas/rcar-du/rcar_lvds.c @@ -1013,7 +1013,7 @@ err_reset_assert: } static const struct dev_pm_ops rcar_lvds_pm_ops = { - SET_RUNTIME_PM_OPS(rcar_lvds_runtime_suspend, rcar_lvds_runtime_resume, NULL) + RUNTIME_PM_OPS(rcar_lvds_runtime_suspend, rcar_lvds_runtime_resume, NULL) }; static struct platform_driver rcar_lvds_platform_driver = { @@ -1021,7 +1021,7 @@ static struct platform_driver rcar_lvds_platform_driver = { .remove = rcar_lvds_remove, .driver = { .name = "rcar-lvds", - .pm = &rcar_lvds_pm_ops, + .pm = pm_ptr(&rcar_lvds_pm_ops), .of_match_table = rcar_lvds_of_table, }, }; diff --git a/drivers/gpu/drm/renesas/rcar-du/rcar_mipi_dsi.c b/drivers/gpu/drm/renesas/rcar-du/rcar_mipi_dsi.c index 1af4c73f7a88..5c73a513f678 100644 --- a/drivers/gpu/drm/renesas/rcar-du/rcar_mipi_dsi.c +++ b/drivers/gpu/drm/renesas/rcar-du/rcar_mipi_dsi.c @@ -576,7 +576,10 @@ static int rcar_mipi_dsi_startup(struct rcar_mipi_dsi *dsi, udelay(10); rcar_mipi_dsi_clr(dsi, CLOCKSET1, CLOCKSET1_UPDATEPLL); - ppisetr = PPISETR_DLEN_3 | PPISETR_CLEN; + rcar_mipi_dsi_clr(dsi, TXSETR, TXSETR_LANECNT_MASK); + rcar_mipi_dsi_set(dsi, TXSETR, dsi->lanes - 1); + + ppisetr = ((BIT(dsi->lanes) - 1) & PPISETR_DLEN_MASK) | PPISETR_CLEN; rcar_mipi_dsi_write(dsi, PPISETR, ppisetr); rcar_mipi_dsi_set(dsi, PHYSETUP, PHYSETUP_SHUTDOWNZ); @@ -934,9 +937,234 @@ static int rcar_mipi_dsi_host_detach(struct mipi_dsi_host *host, return 0; } +static ssize_t rcar_mipi_dsi_host_tx_transfer(struct mipi_dsi_host *host, + const struct mipi_dsi_msg *msg, + bool is_rx_xfer) +{ + const bool is_tx_long = mipi_dsi_packet_format_is_long(msg->type); + struct rcar_mipi_dsi *dsi = host_to_rcar_mipi_dsi(host); + struct mipi_dsi_packet packet; + u8 payload[16] = { 0 }; + u32 status; + int ret; + + ret = mipi_dsi_create_packet(&packet, msg); + if (ret) + return ret; + + /* Configure LP or HS command transfer. */ + rcar_mipi_dsi_write(dsi, TXCMSETR, (msg->flags & MIPI_DSI_MSG_USE_LPM) ? + TXCMSETR_SPDTYP : 0); + + /* Register access mode for RX transfer. */ + if (is_rx_xfer) + rcar_mipi_dsi_write(dsi, RXPSETR, 0); + + /* Do not use IRQ, poll for completion, the completion is quick. */ + rcar_mipi_dsi_write(dsi, TXCMIER, 0); + + /* + * Send the header: + * header[0] = Virtual Channel + Data Type + * header[1] = Word Count LSB (LP) or first param (SP) + * header[2] = Word Count MSB (LP) or second param (SP) + */ + rcar_mipi_dsi_write(dsi, TXCMPHDR, + (is_tx_long ? TXCMPHDR_FMT : 0) | + TXCMPHDR_VC(msg->channel) | + TXCMPHDR_DT(msg->type) | + TXCMPHDR_DATA1(packet.header[2]) | + TXCMPHDR_DATA0(packet.header[1])); + + if (is_tx_long) { + memcpy(payload, packet.payload, + min(msg->tx_len, sizeof(payload))); + + rcar_mipi_dsi_write(dsi, TXCMPPD0R, + (payload[3] << 24) | (payload[2] << 16) | + (payload[1] << 8) | payload[0]); + rcar_mipi_dsi_write(dsi, TXCMPPD1R, + (payload[7] << 24) | (payload[6] << 16) | + (payload[5] << 8) | payload[4]); + rcar_mipi_dsi_write(dsi, TXCMPPD2R, + (payload[11] << 24) | (payload[10] << 16) | + (payload[9] << 8) | payload[8]); + rcar_mipi_dsi_write(dsi, TXCMPPD3R, + (payload[15] << 24) | (payload[14] << 16) | + (payload[13] << 8) | payload[12]); + } + + /* Start the transfer, RX with BTA, TX without BTA. */ + if (is_rx_xfer) { + rcar_mipi_dsi_write(dsi, TXCMCR, TXCMCR_BTAREQ); + + /* Wait until the transmission, BTA, reception completed. */ + ret = read_poll_timeout(rcar_mipi_dsi_read, status, + (status & RXPSR_BTAREQEND), + 2000, 50000, false, dsi, RXPSR); + } else { + rcar_mipi_dsi_write(dsi, TXCMCR, TXCMCR_TXREQ); + + /* Wait until the transmission completed. */ + ret = read_poll_timeout(rcar_mipi_dsi_read, status, + (status & TXCMSR_TXREQEND), + 2000, 50000, false, dsi, TXCMSR); + } + + if (ret < 0) { + dev_err(dsi->dev, "Command transfer timeout (0x%08x)\n", + status); + return ret; + } + + return packet.size; +} + +static ssize_t rcar_mipi_dsi_host_rx_transfer(struct mipi_dsi_host *host, + const struct mipi_dsi_msg *msg) +{ + struct rcar_mipi_dsi *dsi = host_to_rcar_mipi_dsi(host); + u8 *rx_buf = (u8 *)(msg->rx_buf); + u32 reg, data, status, wc; + int i, ret; + + /* RX transfer received data validation and parsing starts here. */ + reg = rcar_mipi_dsi_read(dsi, TOSR); + if (reg & TOSR_TATO) { /* Turn-Around TimeOut. */ + /* Clear TATO Turn-Around TimeOut bit. */ + rcar_mipi_dsi_write(dsi, TOSR, TOSR_TATO); + return -ETIMEDOUT; + } + + reg = rcar_mipi_dsi_read(dsi, RXPSR); + + if (msg->flags & MIPI_DSI_MSG_REQ_ACK) { + /* Transfer with zero-length RX. */ + if (!(reg & RXPSR_RCVACK)) { + /* No ACK on RX response received. */ + return -EINVAL; + } + } else { + /* Transfer with non-zero-length RX. */ + if (!(reg & RXPSR_RCVRESP)) { + /* No packet header of RX response received. */ + return -EINVAL; + } + + if (reg & (RXPSR_CRCERR | RXPSR_WCERR | RXPSR_AXIERR | RXPSR_OVRERR)) { + /* Incorrect response payload. */ + return -ENODATA; + } + + data = rcar_mipi_dsi_read(dsi, RXPHDR); + if (data & RXPHDR_FMT) { /* Long Packet Response. */ + /* Read Long Packet Response length from packet header. */ + wc = data & 0xffff; + if (wc > msg->rx_len) { + dev_warn(dsi->dev, + "Long Packet Response longer than RX buffer (%d), limited to %zu Bytes\n", + wc, msg->rx_len); + wc = msg->rx_len; + } + + if (wc > 16) { + dev_warn(dsi->dev, + "Long Packet Response too long (%d), limited to 16 Bytes\n", + wc); + wc = 16; + } + + for (i = 0; i < msg->rx_len; i++) { + if (!(i % 4)) + data = rcar_mipi_dsi_read(dsi, RXPPD0R + i); + + rx_buf[i] = data & 0xff; + data >>= 8; + } + } else { /* Short Packet Response. */ + if (msg->rx_len >= 1) + rx_buf[0] = data & 0xff; + if (msg->rx_len >= 2) + rx_buf[1] = (data >> 8) & 0xff; + if (msg->rx_len >= 3) { + dev_warn(dsi->dev, + "Expected Short Packet Response too long (%zu), limited to 2 Bytes\n", + msg->rx_len); + } + } + } + + if (reg & RXPSR_RCVAKE) { + /* Acknowledge and Error report received. */ + return -EFAULT; + } + + /* Wait until the bus handover to host processor completed. */ + ret = read_poll_timeout(rcar_mipi_dsi_read, status, + !(status & PPIDL0SR_DIR), + 2000, 50000, false, dsi, PPIDL0SR); + if (ret < 0) { + dev_err(dsi->dev, "Command RX DIR timeout (0x%08x)\n", status); + return ret; + } + + /* Wait until the data lane is in LP11 stop state. */ + ret = read_poll_timeout(rcar_mipi_dsi_read, status, + status & PPIDL0SR_STPST, + 2000, 50000, false, dsi, PPIDL0SR); + if (ret < 0) { + dev_err(dsi->dev, "Command RX STPST timeout (0x%08x)\n", status); + return ret; + } + + return 0; +} + +static ssize_t rcar_mipi_dsi_host_transfer(struct mipi_dsi_host *host, + const struct mipi_dsi_msg *msg) +{ + const bool is_rx_xfer = (msg->flags & MIPI_DSI_MSG_REQ_ACK) || msg->rx_len; + struct rcar_mipi_dsi *dsi = host_to_rcar_mipi_dsi(host); + int ret; + + if (msg->tx_len > 16 || msg->rx_len > 16) { + /* ToDo: Implement Memory on AXI bus command mode. */ + dev_warn(dsi->dev, + "Register-based command mode supports only up to 16 Bytes long payload\n"); + return -EOPNOTSUPP; + } + + ret = rcar_mipi_dsi_host_tx_transfer(host, msg, is_rx_xfer); + + /* If TX transfer succeeded and this transfer has RX part. */ + if (ret >= 0 && is_rx_xfer) { + ret = rcar_mipi_dsi_host_rx_transfer(host, msg); + if (ret) + return ret; + + ret = msg->rx_len; + } + + /* + * Wait a bit between commands, otherwise panels based on ILI9881C + * TCON may fail to correctly receive all commands sent to them. + * Until we can actually test with another DSI device, keep the + * delay here, but eventually this delay might have to be moved + * into the ILI9881C panel driver. + */ + usleep_range(1000, 2000); + + /* Clear the completion interrupt. */ + if (!msg->rx_len) + rcar_mipi_dsi_write(dsi, TXCMSR, TXCMSR_TXREQEND); + + return ret; +} + static const struct mipi_dsi_host_ops rcar_mipi_dsi_host_ops = { .attach = rcar_mipi_dsi_host_attach, .detach = rcar_mipi_dsi_host_detach, + .transfer = rcar_mipi_dsi_host_transfer }; /* ----------------------------------------------------------------------------- diff --git a/drivers/gpu/drm/renesas/rcar-du/rcar_mipi_dsi_regs.h b/drivers/gpu/drm/renesas/rcar-du/rcar_mipi_dsi_regs.h index a6b276f1d6ee..76521276e2af 100644 --- a/drivers/gpu/drm/renesas/rcar-du/rcar_mipi_dsi_regs.h +++ b/drivers/gpu/drm/renesas/rcar-du/rcar_mipi_dsi_regs.h @@ -12,6 +12,130 @@ #define LINKSR_LPBUSY (1 << 1) #define LINKSR_HSBUSY (1 << 0) +#define TXSETR 0x100 +#define TXSETR_LANECNT_MASK (0x3 << 0) + +/* + * DSI Command Transfer Registers + */ +#define TXCMSETR 0x110 +#define TXCMSETR_SPDTYP (1 << 8) /* 0:HS 1:LP */ +#define TXCMSETR_LPPDACC (1 << 0) +#define TXCMCR 0x120 +#define TXCMCR_BTATYP (1 << 2) +#define TXCMCR_BTAREQ (1 << 1) +#define TXCMCR_TXREQ (1 << 0) +#define TXCMSR 0x130 +#define TXCMSR_CLSNERR (1 << 18) +#define TXCMSR_AXIERR (1 << 16) +#define TXCMSR_TXREQEND (1 << 0) +#define TXCMSCR 0x134 +#define TXCMSCR_CLSNERR (1 << 18) +#define TXCMSCR_AXIERR (1 << 16) +#define TXCMSCR_TXREQEND (1 << 0) +#define TXCMIER 0x138 +#define TXCMIER_CLSNERR (1 << 18) +#define TXCMIER_AXIERR (1 << 16) +#define TXCMIER_TXREQEND (1 << 0) +#define TXCMADDRSET0R 0x140 +#define TXCMPHDR 0x150 +#define TXCMPHDR_FMT (1 << 24) /* 0:SP 1:LP */ +#define TXCMPHDR_VC(n) (((n) & 0x3) << 22) +#define TXCMPHDR_DT(n) (((n) & 0x3f) << 16) +#define TXCMPHDR_DATA1(n) (((n) & 0xff) << 8) +#define TXCMPHDR_DATA0(n) (((n) & 0xff) << 0) +#define TXCMPPD0R 0x160 +#define TXCMPPD1R 0x164 +#define TXCMPPD2R 0x168 +#define TXCMPPD3R 0x16c + +#define RXSETR 0x200 +#define RXSETR_CRCEN (((n) & 0xf) << 24) +#define RXSETR_ECCEN (((n) & 0xf) << 16) +#define RXPSETR 0x210 +#define RXPSETR_LPPDACC (1 << 0) +#define RXPSR 0x220 +#define RXPSR_ECCERR1B (1 << 28) +#define RXPSR_UEXTRGERR (1 << 25) +#define RXPSR_RESPTOERR (1 << 24) +#define RXPSR_OVRERR (1 << 23) +#define RXPSR_AXIERR (1 << 22) +#define RXPSR_CRCERR (1 << 21) +#define RXPSR_WCERR (1 << 20) +#define RXPSR_UEXDTERR (1 << 19) +#define RXPSR_UEXPKTERR (1 << 18) +#define RXPSR_ECCERR (1 << 17) +#define RXPSR_MLFERR (1 << 16) +#define RXPSR_RCVACK (1 << 14) +#define RXPSR_RCVEOT (1 << 10) +#define RXPSR_RCVAKE (1 << 9) +#define RXPSR_RCVRESP (1 << 8) +#define RXPSR_BTAREQEND (1 << 0) +#define RXPSCR 0x224 +#define RXPSCR_ECCERR1B (1 << 28) +#define RXPSCR_UEXTRGERR (1 << 25) +#define RXPSCR_RESPTOERR (1 << 24) +#define RXPSCR_OVRERR (1 << 23) +#define RXPSCR_AXIERR (1 << 22) +#define RXPSCR_CRCERR (1 << 21) +#define RXPSCR_WCERR (1 << 20) +#define RXPSCR_UEXDTERR (1 << 19) +#define RXPSCR_UEXPKTERR (1 << 18) +#define RXPSCR_ECCERR (1 << 17) +#define RXPSCR_MLFERR (1 << 16) +#define RXPSCR_RCVACK (1 << 14) +#define RXPSCR_RCVEOT (1 << 10) +#define RXPSCR_RCVAKE (1 << 9) +#define RXPSCR_RCVRESP (1 << 8) +#define RXPSCR_BTAREQEND (1 << 0) +#define RXPIER 0x228 +#define RXPIER_ECCERR1B (1 << 28) +#define RXPIER_UEXTRGERR (1 << 25) +#define RXPIER_RESPTOERR (1 << 24) +#define RXPIER_OVRERR (1 << 23) +#define RXPIER_AXIERR (1 << 22) +#define RXPIER_CRCERR (1 << 21) +#define RXPIER_WCERR (1 << 20) +#define RXPIER_UEXDTERR (1 << 19) +#define RXPIER_UEXPKTERR (1 << 18) +#define RXPIER_ECCERR (1 << 17) +#define RXPIER_MLFERR (1 << 16) +#define RXPIER_RCVACK (1 << 14) +#define RXPIER_RCVEOT (1 << 10) +#define RXPIER_RCVAKE (1 << 9) +#define RXPIER_RCVRESP (1 << 8) +#define RXPIER_BTAREQEND (1 << 0) +#define RXPADDRSET0R 0x230 +#define RXPSIZESETR 0x238 +#define RXPSIZESETR_SIZE(n) (((n) & 0xf) << 3) +#define RXPHDR 0x240 +#define RXPHDR_FMT (1 << 24) /* 0:SP 1:LP */ +#define RXPHDR_VC(n) (((n) & 0x3) << 22) +#define RXPHDR_DT(n) (((n) & 0x3f) << 16) +#define RXPHDR_DATA1(n) (((n) & 0xff) << 8) +#define RXPHDR_DATA0(n) (((n) & 0xff) << 0) +#define RXPPD0R 0x250 +#define RXPPD1R 0x254 +#define RXPPD2R 0x258 +#define RXPPD3R 0x25c +#define AKEPR 0x300 +#define AKEPR_VC(n) (((n) & 0x3) << 22) +#define AKEPR_DT(n) (((n) & 0x3f) << 16) +#define AKEPR_ERRRPT(n) (((n) & 0xffff) << 0) +#define RXRESPTOSETR 0x400 +#define TACR 0x500 +#define TASR 0x510 +#define TASCR 0x514 +#define TAIER 0x518 +#define TOSR 0x610 +#define TOSR_TATO (1 << 2) +#define TOSR_LRXHTO (1 << 1) +#define TOSR_HRXTO (1 << 0) +#define TOSCR 0x614 +#define TOSCR_TATO (1 << 2) +#define TOSCR_LRXHTO (1 << 1) +#define TOSCR_HRXTO (1 << 0) + /* * Video Mode Register */ @@ -80,10 +204,7 @@ * PHY-Protocol Interface (PPI) Registers */ #define PPISETR 0x700 -#define PPISETR_DLEN_0 (0x1 << 0) -#define PPISETR_DLEN_1 (0x3 << 0) -#define PPISETR_DLEN_2 (0x7 << 0) -#define PPISETR_DLEN_3 (0xf << 0) +#define PPISETR_DLEN_MASK (0xf << 0) #define PPISETR_CLEN (1 << 8) #define PPICLCR 0x710 @@ -100,6 +221,10 @@ #define PPICLSCR_HSTOLP (1 << 27) #define PPICLSCR_TOHS (1 << 26) +#define PPIDL0SR 0x740 +#define PPIDL0SR_DIR (1 << 10) +#define PPIDL0SR_STPST (1 << 6) + #define PPIDLSR 0x760 #define PPIDLSR_STPST (0xf << 0) diff --git a/drivers/gpu/drm/rockchip/Kconfig b/drivers/gpu/drm/rockchip/Kconfig index ab525668939a..b7b025814e72 100644 --- a/drivers/gpu/drm/rockchip/Kconfig +++ b/drivers/gpu/drm/rockchip/Kconfig @@ -10,6 +10,7 @@ config DRM_ROCKCHIP select VIDEOMODE_HELPERS select DRM_ANALOGIX_DP if ROCKCHIP_ANALOGIX_DP select DRM_DISPLAY_DP_AUX_BUS if ROCKCHIP_ANALOGIX_DP + select DRM_DW_DP if ROCKCHIP_DW_DP select DRM_DW_HDMI if ROCKCHIP_DW_HDMI select DRM_DW_HDMI_QP if ROCKCHIP_DW_HDMI_QP select DRM_DW_MIPI_DSI if ROCKCHIP_DW_MIPI_DSI @@ -53,6 +54,7 @@ config ROCKCHIP_CDN_DP bool "Rockchip cdn DP" depends on EXTCON=y || (EXTCON=m && DRM_ROCKCHIP=m) select DRM_DISPLAY_HELPER + select DRM_BRIDGE_CONNECTOR select DRM_DISPLAY_DP_HELPER help This selects support for Rockchip SoC specific extensions @@ -60,6 +62,14 @@ config ROCKCHIP_CDN_DP RK3399 based SoC, you should select this option. +config ROCKCHIP_DW_DP + bool "Rockchip specific extensions for Synopsys DW DP" + help + This selects support for Rockchip SoC specific extensions + to enable Synopsys DesignWare Cores based DisplayPort transmit + controller support on Rockchip SoC, If you want to enable DP on + rk3588 based SoC, you should select this option. + config ROCKCHIP_DW_HDMI bool "Rockchip specific extensions for Synopsys DW HDMI" help diff --git a/drivers/gpu/drm/rockchip/Makefile b/drivers/gpu/drm/rockchip/Makefile index 2b867cebbc12..097f062399c7 100644 --- a/drivers/gpu/drm/rockchip/Makefile +++ b/drivers/gpu/drm/rockchip/Makefile @@ -14,6 +14,7 @@ rockchipdrm-$(CONFIG_ROCKCHIP_DW_HDMI) += dw_hdmi-rockchip.o rockchipdrm-$(CONFIG_ROCKCHIP_DW_HDMI_QP) += dw_hdmi_qp-rockchip.o rockchipdrm-$(CONFIG_ROCKCHIP_DW_MIPI_DSI) += dw-mipi-dsi-rockchip.o rockchipdrm-$(CONFIG_ROCKCHIP_DW_MIPI_DSI2) += dw-mipi-dsi2-rockchip.o +rockchipdrm-$(CONFIG_ROCKCHIP_DW_DP) += dw_dp-rockchip.o rockchipdrm-$(CONFIG_ROCKCHIP_INNO_HDMI) += inno_hdmi.o rockchipdrm-$(CONFIG_ROCKCHIP_LVDS) += rockchip_lvds.o rockchipdrm-$(CONFIG_ROCKCHIP_RGB) += rockchip_rgb.o diff --git a/drivers/gpu/drm/rockchip/dw_dp-rockchip.c b/drivers/gpu/drm/rockchip/dw_dp-rockchip.c new file mode 100644 index 000000000000..25ab4e46301e --- /dev/null +++ b/drivers/gpu/drm/rockchip/dw_dp-rockchip.c @@ -0,0 +1,150 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2020 Rockchip Electronics Co., Ltd. + * + * Author: Zhang Yubing <yubing.zhang@rock-chips.com> + * Author: Andy Yan <andy.yan@rock-chips.com> + */ + +#include <linux/component.h> +#include <linux/of_device.h> +#include <linux/platform_device.h> +#include <drm/bridge/dw_dp.h> +#include <drm/drm_atomic_helper.h> +#include <drm/drm_bridge.h> +#include <drm/drm_bridge_connector.h> +#include <drm/drm_of.h> +#include <drm/drm_print.h> +#include <drm/drm_probe_helper.h> +#include <drm/drm_simple_kms_helper.h> + +#include <linux/media-bus-format.h> +#include <linux/videodev2.h> + +#include "rockchip_drm_drv.h" +#include "rockchip_drm_vop.h" + +struct rockchip_dw_dp { + struct dw_dp *base; + struct device *dev; + struct rockchip_encoder encoder; +}; + +static int dw_dp_encoder_atomic_check(struct drm_encoder *encoder, + struct drm_crtc_state *crtc_state, + struct drm_connector_state *conn_state) +{ + struct rockchip_crtc_state *s = to_rockchip_crtc_state(crtc_state); + struct drm_atomic_state *state = conn_state->state; + struct drm_display_info *di = &conn_state->connector->display_info; + struct drm_bridge *bridge = drm_bridge_chain_get_first_bridge(encoder); + struct drm_bridge_state *bridge_state = drm_atomic_get_new_bridge_state(state, bridge); + u32 bus_format = bridge_state->input_bus_cfg.format; + + switch (bus_format) { + case MEDIA_BUS_FMT_UYYVYY10_0_5X30: + case MEDIA_BUS_FMT_UYYVYY8_0_5X24: + s->output_mode = ROCKCHIP_OUT_MODE_YUV420; + break; + case MEDIA_BUS_FMT_YUYV10_1X20: + case MEDIA_BUS_FMT_YUYV8_1X16: + s->output_mode = ROCKCHIP_OUT_MODE_S888_DUMMY; + break; + case MEDIA_BUS_FMT_RGB101010_1X30: + case MEDIA_BUS_FMT_RGB888_1X24: + case MEDIA_BUS_FMT_RGB666_1X24_CPADHI: + case MEDIA_BUS_FMT_YUV10_1X30: + case MEDIA_BUS_FMT_YUV8_1X24: + default: + s->output_mode = ROCKCHIP_OUT_MODE_AAAA; + break; + } + + s->output_type = DRM_MODE_CONNECTOR_DisplayPort; + s->bus_format = bus_format; + s->bus_flags = di->bus_flags; + s->color_space = V4L2_COLORSPACE_DEFAULT; + + return 0; +} + +static const struct drm_encoder_helper_funcs dw_dp_encoder_helper_funcs = { + .atomic_check = dw_dp_encoder_atomic_check, +}; + +static int dw_dp_rockchip_bind(struct device *dev, struct device *master, void *data) +{ + struct platform_device *pdev = to_platform_device(dev); + struct dw_dp_plat_data plat_data; + struct drm_device *drm_dev = data; + struct rockchip_dw_dp *dp; + struct drm_encoder *encoder; + struct drm_connector *connector; + int ret; + + dp = devm_kzalloc(dev, sizeof(*dp), GFP_KERNEL); + if (!dp) + return -ENOMEM; + + dp->dev = dev; + platform_set_drvdata(pdev, dp); + + plat_data.max_link_rate = 810000; + encoder = &dp->encoder.encoder; + encoder->possible_crtcs = drm_of_find_possible_crtcs(drm_dev, dev->of_node); + rockchip_drm_encoder_set_crtc_endpoint_id(&dp->encoder, dev->of_node, 0, 0); + + ret = drmm_encoder_init(drm_dev, encoder, NULL, DRM_MODE_ENCODER_TMDS, NULL); + if (ret) + return ret; + drm_encoder_helper_add(encoder, &dw_dp_encoder_helper_funcs); + + dp->base = dw_dp_bind(dev, encoder, &plat_data); + if (IS_ERR(dp->base)) { + ret = PTR_ERR(dp->base); + return ret; + } + + connector = drm_bridge_connector_init(drm_dev, encoder); + if (IS_ERR(connector)) { + ret = PTR_ERR(connector); + return dev_err_probe(dev, ret, "Failed to init bridge connector"); + } + + drm_connector_attach_encoder(connector, encoder); + + return 0; +} + +static const struct component_ops dw_dp_rockchip_component_ops = { + .bind = dw_dp_rockchip_bind, +}; + +static int dw_dp_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + + return component_add(dev, &dw_dp_rockchip_component_ops); +} + +static void dw_dp_remove(struct platform_device *pdev) +{ + struct rockchip_dw_dp *dp = platform_get_drvdata(pdev); + + component_del(dp->dev, &dw_dp_rockchip_component_ops); +} + +static const struct of_device_id dw_dp_of_match[] = { + { .compatible = "rockchip,rk3588-dp", }, + {} +}; +MODULE_DEVICE_TABLE(of, dw_dp_of_match); + +struct platform_driver dw_dp_driver = { + .probe = dw_dp_probe, + .remove = dw_dp_remove, + .driver = { + .name = "dw-dp", + .of_match_table = dw_dp_of_match, + }, +}; diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c index 180fad5d49ad..eb77bde9f628 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c @@ -529,6 +529,7 @@ static int __init rockchip_drm_init(void) ADD_ROCKCHIP_SUB_DRIVER(rockchip_dp_driver, CONFIG_ROCKCHIP_ANALOGIX_DP); ADD_ROCKCHIP_SUB_DRIVER(cdn_dp_driver, CONFIG_ROCKCHIP_CDN_DP); + ADD_ROCKCHIP_SUB_DRIVER(dw_dp_driver, CONFIG_ROCKCHIP_DW_DP); ADD_ROCKCHIP_SUB_DRIVER(dw_hdmi_rockchip_pltfm_driver, CONFIG_ROCKCHIP_DW_HDMI); ADD_ROCKCHIP_SUB_DRIVER(dw_hdmi_qp_rockchip_pltfm_driver, diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.h b/drivers/gpu/drm/rockchip/rockchip_drm_drv.h index c183e82a42a5..2e86ad00979c 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_drv.h +++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.h @@ -87,6 +87,7 @@ int rockchip_drm_encoder_set_crtc_endpoint_id(struct rockchip_encoder *rencoder, struct device_node *np, int port, int reg); int rockchip_drm_endpoint_is_subdriver(struct device_node *ep); extern struct platform_driver cdn_dp_driver; +extern struct platform_driver dw_dp_driver; extern struct platform_driver dw_hdmi_rockchip_pltfm_driver; extern struct platform_driver dw_hdmi_qp_rockchip_pltfm_driver; extern struct platform_driver dw_mipi_dsi_rockchip_driver; diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c index 186f6452a7d3..b50927a824b4 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c @@ -2579,12 +2579,13 @@ static int vop2_win_init(struct vop2 *vop2) } /* - * The window registers are only updated when config done is written. - * Until that they read back the old value. As we read-modify-write - * these registers mark them as non-volatile. This makes sure we read - * the new values from the regmap register cache. + * The window and video port registers are only updated when config + * done is written. Until that they read back the old value. As we + * read-modify-write these registers mark them as non-volatile. This + * makes sure we read the new values from the regmap register cache. */ static const struct regmap_range vop2_nonvolatile_range[] = { + regmap_reg_range(RK3568_VP0_CTRL_BASE, RK3588_VP3_CTRL_BASE + 255), regmap_reg_range(0x1000, 0x23ff), }; diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c index 8867b95ab089..5a4697f636f2 100644 --- a/drivers/gpu/drm/scheduler/sched_entity.c +++ b/drivers/gpu/drm/scheduler/sched_entity.c @@ -285,9 +285,9 @@ long drm_sched_entity_flush(struct drm_sched_entity *entity, long timeout) return 0; sched = entity->rq->sched; - /** - * The client will not queue more IBs during this fini, consume existing - * queued IBs or discard them on SIGKILL + /* + * The client will not queue more jobs during this fini - consume + * existing queued ones, or discard them on SIGKILL. */ if (current->flags & PF_EXITING) { if (timeout) @@ -300,7 +300,7 @@ long drm_sched_entity_flush(struct drm_sched_entity *entity, long timeout) drm_sched_entity_is_idle(entity)); } - /* For killed process disable any more IBs enqueue right now */ + /* For a killed process disallow further enqueueing of jobs. */ last_user = cmpxchg(&entity->last_user, current->group_leader, NULL); if ((!last_user || last_user == current->group_leader) && (current->flags & PF_EXITING) && (current->exit_code == SIGKILL)) @@ -324,9 +324,9 @@ EXPORT_SYMBOL(drm_sched_entity_flush); void drm_sched_entity_fini(struct drm_sched_entity *entity) { /* - * If consumption of existing IBs wasn't completed. Forcefully remove - * them here. Also makes sure that the scheduler won't touch this entity - * any more. + * If consumption of existing jobs wasn't completed forcefully remove + * them. Also makes sure that the scheduler won't touch this entity any + * more. */ drm_sched_entity_kill(entity); @@ -391,7 +391,8 @@ EXPORT_SYMBOL(drm_sched_entity_set_priority); * Add a callback to the current dependency of the entity to wake up the * scheduler when the entity becomes available. */ -static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity) +static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity, + struct drm_sched_job *sched_job) { struct drm_gpu_scheduler *sched = entity->rq->sched; struct dma_fence *fence = entity->dependency; @@ -421,6 +422,10 @@ static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity) entity->dependency = fence; } + if (trace_drm_sched_job_unschedulable_enabled() && + !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &entity->dependency->flags)) + trace_drm_sched_job_unschedulable(sched_job, entity->dependency); + if (!dma_fence_add_callback(entity->dependency, &entity->cb, drm_sched_entity_wakeup)) return true; @@ -461,10 +466,8 @@ struct drm_sched_job *drm_sched_entity_pop_job(struct drm_sched_entity *entity) while ((entity->dependency = drm_sched_job_dependency(sched_job, entity))) { - if (drm_sched_entity_add_dependency_cb(entity)) { - trace_drm_sched_job_unschedulable(sched_job, entity->dependency); + if (drm_sched_entity_add_dependency_cb(entity, sched_job)) return NULL; - } } /* skip jobs from entity that marked guilty */ diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index 5a550fd76bf0..46119aacb809 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -1424,6 +1424,22 @@ void drm_sched_fini(struct drm_gpu_scheduler *sched) * Prevents reinsertion and marks job_queue as idle, * it will be removed from the rq in drm_sched_entity_fini() * eventually + * + * FIXME: + * This lacks the proper spin_lock(&s_entity->lock) and + * is, therefore, a race condition. Most notably, it + * can race with drm_sched_entity_push_job(). The lock + * cannot be taken here, however, because this would + * lead to lock inversion -> deadlock. + * + * The best solution probably is to enforce the life + * time rule of all entities having to be torn down + * before their scheduler. Then, however, locking could + * be dropped alltogether from this function. + * + * For now, this remains a potential race in all + * drivers that keep entities alive for longer than + * the scheduler. */ s_entity->stopped = true; spin_unlock(&rq->lock); diff --git a/drivers/gpu/drm/scheduler/tests/sched_tests.h b/drivers/gpu/drm/scheduler/tests/sched_tests.h index 5b262126b776..7f31d35780cc 100644 --- a/drivers/gpu/drm/scheduler/tests/sched_tests.h +++ b/drivers/gpu/drm/scheduler/tests/sched_tests.h @@ -11,7 +11,6 @@ #include <linux/hrtimer.h> #include <linux/ktime.h> #include <linux/list.h> -#include <linux/atomic.h> #include <linux/mutex.h> #include <linux/types.h> diff --git a/drivers/gpu/drm/sitronix/st7571-i2c.c b/drivers/gpu/drm/sitronix/st7571-i2c.c index 453eb7e045e5..a6c4a6738ded 100644 --- a/drivers/gpu/drm/sitronix/st7571-i2c.c +++ b/drivers/gpu/drm/sitronix/st7571-i2c.c @@ -151,6 +151,7 @@ struct st7571_device { bool ignore_nak; bool grayscale; + bool inverted; u32 height_mm; u32 width_mm; u32 startline; @@ -218,10 +219,11 @@ static int st7571_send_command_list(struct st7571_device *st7571, return ret; } -static inline u8 st7571_transform_xy(const char *p, int x, int y) +static inline u8 st7571_transform_xy(const char *p, int x, int y, u8 bpp) { int xrest = x % 8; u8 result = 0; + u8 row_len = 16 * bpp; /* * Transforms an (x, y) pixel coordinate into a vertical 8-bit @@ -236,7 +238,7 @@ static inline u8 st7571_transform_xy(const char *p, int x, int y) for (int i = 0; i < 8; i++) { int row_idx = y + i; - u8 byte = p[row_idx * 16 + x]; + u8 byte = p[row_idx * row_len + x]; u8 bit = (byte >> xrest) & 1; result |= (bit << i); @@ -303,11 +305,11 @@ static void st7571_prepare_buffer_grayscale(struct st7571_device *st7571, struct iosys_map dst; switch (fb->format->format) { - case DRM_FORMAT_XRGB8888: /* Only support XRGB8888 in monochrome mode */ - dst_pitch = DIV_ROUND_UP(drm_rect_width(rect), 8); + case DRM_FORMAT_XRGB8888: + dst_pitch = DIV_ROUND_UP(drm_rect_width(rect), 4); iosys_map_set_vaddr(&dst, st7571->hwbuf); - drm_fb_xrgb8888_to_mono(&dst, &dst_pitch, vmap, fb, rect, fmtcnv_state); + drm_fb_xrgb8888_to_gray2(&dst, &dst_pitch, vmap, fb, rect, fmtcnv_state); break; case DRM_FORMAT_R1: @@ -333,7 +335,7 @@ static int st7571_fb_update_rect_monochrome(struct drm_framebuffer *fb, struct d for (int y = rect->y1; y < rect->y2; y += ST7571_PAGE_HEIGHT) { for (int x = rect->x1; x < rect->x2; x++) - row[x] = st7571_transform_xy(st7571->hwbuf, x, y); + row[x] = st7571_transform_xy(st7571->hwbuf, x, y, 1); st7571_set_position(st7571, rect->x1, y); @@ -358,14 +360,13 @@ static int st7571_fb_update_rect_grayscale(struct drm_framebuffer *fb, struct dr rect->y2 = min_t(unsigned int, round_up(rect->y2, ST7571_PAGE_HEIGHT), st7571->nlines); switch (format) { - case DRM_FORMAT_XRGB8888: - /* Threated as monochrome (R1) */ - fallthrough; case DRM_FORMAT_R1: - x1 = rect->x1; - x2 = rect->x2; + x1 = rect->x1 * 1; + x2 = rect->x2 * 1; break; case DRM_FORMAT_R2: + fallthrough; + case DRM_FORMAT_XRGB8888: x1 = rect->x1 * 2; x2 = rect->x2 * 2; break; @@ -373,7 +374,7 @@ static int st7571_fb_update_rect_grayscale(struct drm_framebuffer *fb, struct dr for (int y = rect->y1; y < rect->y2; y += ST7571_PAGE_HEIGHT) { for (int x = x1; x < x2; x++) - row[x] = st7571_transform_xy(st7571->hwbuf, x, y); + row[x] = st7571_transform_xy(st7571->hwbuf, x, y, 2); st7571_set_position(st7571, rect->x1, y); @@ -386,15 +387,15 @@ static int st7571_fb_update_rect_grayscale(struct drm_framebuffer *fb, struct dr * even if the format is monochrome. * * The bit values maps to the following grayscale: - * 0 0 = White - * 0 1 = Light gray - * 1 0 = Dark gray - * 1 1 = Black + * 0 0 = Black + * 0 1 = Dark gray + * 1 0 = Light gray + * 1 1 = White * * For monochrome formats, write the same value twice to get * either a black or white pixel. */ - if (format == DRM_FORMAT_R1 || format == DRM_FORMAT_XRGB8888) + if (format == DRM_FORMAT_R1) regmap_bulk_write(st7571->regmap, ST7571_DATA_MODE, row + x, 1); } } @@ -792,6 +793,7 @@ static int st7567_parse_dt(struct st7571_device *st7567) of_property_read_u32(np, "width-mm", &st7567->width_mm); of_property_read_u32(np, "height-mm", &st7567->height_mm); + st7567->inverted = of_property_read_bool(np, "sitronix,inverted"); st7567->pformat = &st7571_monochrome; st7567->bpp = 1; @@ -819,6 +821,7 @@ static int st7571_parse_dt(struct st7571_device *st7571) of_property_read_u32(np, "width-mm", &st7571->width_mm); of_property_read_u32(np, "height-mm", &st7571->height_mm); st7571->grayscale = of_property_read_bool(np, "sitronix,grayscale"); + st7571->inverted = of_property_read_bool(np, "sitronix,inverted"); if (st7571->grayscale) { st7571->pformat = &st7571_grayscale; @@ -873,7 +876,7 @@ static int st7567_lcd_init(struct st7571_device *st7567) ST7571_SET_POWER(0x6), /* Power Control, VC: ON, VR: ON, VF: OFF */ ST7571_SET_POWER(0x7), /* Power Control, VC: ON, VR: ON, VF: ON */ - ST7571_SET_REVERSE(0), + ST7571_SET_REVERSE(st7567->inverted ? 1 : 0), ST7571_SET_ENTIRE_DISPLAY_ON(0), }; @@ -917,7 +920,7 @@ static int st7571_lcd_init(struct st7571_device *st7571) ST7571_SET_COLOR_MODE(st7571->pformat->mode), ST7571_COMMAND_SET_NORMAL, - ST7571_SET_REVERSE(0), + ST7571_SET_REVERSE(st7571->inverted ? 1 : 0), ST7571_SET_ENTIRE_DISPLAY_ON(0), }; @@ -1024,7 +1027,7 @@ static void st7571_remove(struct i2c_client *client) drm_dev_unplug(&st7571->dev); } -struct st7571_panel_data st7567_config = { +static const struct st7571_panel_data st7567_config = { .init = st7567_lcd_init, .parse_dt = st7567_parse_dt, .constraints = { @@ -1036,7 +1039,7 @@ struct st7571_panel_data st7567_config = { }, }; -struct st7571_panel_data st7571_config = { +static const struct st7571_panel_data st7571_config = { .init = st7571_lcd_init, .parse_dt = st7571_parse_dt, .constraints = { diff --git a/drivers/gpu/drm/solomon/ssd130x-spi.c b/drivers/gpu/drm/solomon/ssd130x-spi.c index 7c935870f7d2..b52f5fd592a1 100644 --- a/drivers/gpu/drm/solomon/ssd130x-spi.c +++ b/drivers/gpu/drm/solomon/ssd130x-spi.c @@ -74,8 +74,7 @@ static int ssd130x_spi_probe(struct spi_device *spi) t = devm_kzalloc(dev, sizeof(*t), GFP_KERNEL); if (!t) - return dev_err_probe(dev, -ENOMEM, - "Failed to allocate SPI transport data\n"); + return -ENOMEM; t->spi = spi; t->dc = dc; diff --git a/drivers/gpu/drm/sti/sti_hqvdp.c b/drivers/gpu/drm/sti/sti_hqvdp.c index 03684062309b..b76606e9a82d 100644 --- a/drivers/gpu/drm/sti/sti_hqvdp.c +++ b/drivers/gpu/drm/sti/sti_hqvdp.c @@ -744,7 +744,7 @@ static bool sti_hqvdp_check_hw_scaling(struct sti_hqvdp *hqvdp, inv_zy = DIV_ROUND_UP(src_h, dst_h); - return (inv_zy <= lfw) ? true : false; + return inv_zy <= lfw; } /** diff --git a/drivers/gpu/drm/stm/drv.c b/drivers/gpu/drm/stm/drv.c index 8ebcaf953782..ab00d1a6140c 100644 --- a/drivers/gpu/drm/stm/drv.c +++ b/drivers/gpu/drm/stm/drv.c @@ -236,8 +236,18 @@ static void stm_drm_platform_shutdown(struct platform_device *pdev) drm_atomic_helper_shutdown(platform_get_drvdata(pdev)); } +static struct ltdc_plat_data stm_drm_plat_data = { + .pad_max_freq_hz = 90000000, +}; + +static struct ltdc_plat_data stm_drm_plat_data_mp25 = { + .pad_max_freq_hz = 150000000, +}; + static const struct of_device_id drv_dt_ids[] = { - { .compatible = "st,stm32-ltdc"}, + { .compatible = "st,stm32-ltdc", .data = &stm_drm_plat_data, }, + { .compatible = "st,stm32mp251-ltdc", .data = &stm_drm_plat_data_mp25, }, + { .compatible = "st,stm32mp255-ltdc", .data = &stm_drm_plat_data_mp25, }, { /* end node */ }, }; MODULE_DEVICE_TABLE(of, drv_dt_ids); diff --git a/drivers/gpu/drm/stm/ltdc.c b/drivers/gpu/drm/stm/ltdc.c index b9477fbec1c1..d1501e86a5b1 100644 --- a/drivers/gpu/drm/stm/ltdc.c +++ b/drivers/gpu/drm/stm/ltdc.c @@ -14,6 +14,7 @@ #include <linux/interrupt.h> #include <linux/media-bus-format.h> #include <linux/module.h> +#include <linux/of.h> #include <linux/of_graph.h> #include <linux/pinctrl/consumer.h> #include <linux/platform_device.h> @@ -51,6 +52,7 @@ #define HWVER_10300 0x010300 #define HWVER_20101 0x020101 #define HWVER_40100 0x040100 +#define HWVER_40101 0x040101 /* * The address of some registers depends on the HW version: such registers have @@ -836,6 +838,12 @@ ltdc_crtc_mode_valid(struct drm_crtc *crtc, int target_max = target + CLK_TOLERANCE_HZ; int result; + if (ldev->lvds_clk) { + result = clk_round_rate(ldev->lvds_clk, target); + drm_dbg_driver(crtc->dev, "lvds pixclk rate target %d, available %d\n", + target, result); + } + result = clk_round_rate(ldev->pixel_clk, target); drm_dbg_driver(crtc->dev, "clk rate target %d, available %d\n", target, result); @@ -1780,6 +1788,7 @@ static int ltdc_get_caps(struct drm_device *ddev) { struct ltdc_device *ldev = ddev->dev_private; u32 bus_width_log2, lcr, gc2r; + const struct ltdc_plat_data *pdata = of_device_get_match_data(ddev->dev); /* * at least 1 layer must be managed & the number of layers @@ -1795,6 +1804,8 @@ static int ltdc_get_caps(struct drm_device *ddev) ldev->caps.bus_width = 8 << bus_width_log2; regmap_read(ldev->regmap, LTDC_IDR, &ldev->caps.hw_version); + ldev->caps.pad_max_freq_hz = pdata->pad_max_freq_hz; + switch (ldev->caps.hw_version) { case HWVER_10200: case HWVER_10300: @@ -1812,7 +1823,6 @@ static int ltdc_get_caps(struct drm_device *ddev) * does not work on 2nd layer. */ ldev->caps.non_alpha_only_l1 = true; - ldev->caps.pad_max_freq_hz = 90000000; if (ldev->caps.hw_version == HWVER_10200) ldev->caps.pad_max_freq_hz = 65000000; ldev->caps.nb_irq = 2; @@ -1843,6 +1853,7 @@ static int ltdc_get_caps(struct drm_device *ddev) ldev->caps.fifo_threshold = false; break; case HWVER_40100: + case HWVER_40101: ldev->caps.layer_ofs = LAY_OFS_1; ldev->caps.layer_regs = ltdc_layer_regs_a2; ldev->caps.pix_fmt_hw = ltdc_pix_fmt_a2; @@ -1850,7 +1861,6 @@ static int ltdc_get_caps(struct drm_device *ddev) ldev->caps.pix_fmt_nb = ARRAY_SIZE(ltdc_drm_fmt_a2); ldev->caps.pix_fmt_flex = true; ldev->caps.non_alpha_only_l1 = false; - ldev->caps.pad_max_freq_hz = 90000000; ldev->caps.nb_irq = 2; ldev->caps.ycbcr_input = true; ldev->caps.ycbcr_output = true; @@ -1873,6 +1883,10 @@ void ltdc_suspend(struct drm_device *ddev) drm_dbg_driver(ddev, "\n"); clk_disable_unprepare(ldev->pixel_clk); + if (ldev->bus_clk) + clk_disable_unprepare(ldev->bus_clk); + if (ldev->lvds_clk) + clk_disable_unprepare(ldev->lvds_clk); } int ltdc_resume(struct drm_device *ddev) @@ -1888,7 +1902,21 @@ int ltdc_resume(struct drm_device *ddev) return ret; } - return 0; + if (ldev->bus_clk) { + ret = clk_prepare_enable(ldev->bus_clk); + if (ret) { + drm_err(ddev, "failed to enable bus clock (%d)\n", ret); + return ret; + } + } + + if (ldev->lvds_clk) { + ret = clk_prepare_enable(ldev->lvds_clk); + if (ret) + drm_err(ddev, "failed to prepare lvds clock\n"); + } + + return ret; } int ltdc_load(struct drm_device *ddev) @@ -1923,6 +1951,20 @@ int ltdc_load(struct drm_device *ddev) return -ENODEV; } + if (of_device_is_compatible(np, "st,stm32mp251-ltdc") || + of_device_is_compatible(np, "st,stm32mp255-ltdc")) { + ldev->bus_clk = devm_clk_get(dev, "bus"); + if (IS_ERR(ldev->bus_clk)) + return dev_err_probe(dev, PTR_ERR(ldev->bus_clk), + "Unable to get bus clock\n"); + + ret = clk_prepare_enable(ldev->bus_clk); + if (ret) { + drm_err(ddev, "Unable to prepare bus clock\n"); + return ret; + } + } + /* Get endpoints if any */ for (i = 0; i < nb_endpoints; i++) { ret = drm_of_find_panel_or_bridge(np, 0, i, &panel, &bridge); @@ -1956,6 +1998,10 @@ int ltdc_load(struct drm_device *ddev) } } + ldev->lvds_clk = devm_clk_get(dev, "lvds"); + if (IS_ERR(ldev->lvds_clk)) + ldev->lvds_clk = NULL; + rstc = devm_reset_control_get_exclusive(dev, NULL); mutex_init(&ldev->err_lock); @@ -2035,6 +2081,9 @@ int ltdc_load(struct drm_device *ddev) clk_disable_unprepare(ldev->pixel_clk); + if (ldev->bus_clk) + clk_disable_unprepare(ldev->bus_clk); + pinctrl_pm_select_sleep_state(ddev->dev); pm_runtime_enable(ddev->dev); @@ -2043,6 +2092,9 @@ int ltdc_load(struct drm_device *ddev) err: clk_disable_unprepare(ldev->pixel_clk); + if (ldev->bus_clk) + clk_disable_unprepare(ldev->bus_clk); + return ret; } diff --git a/drivers/gpu/drm/stm/ltdc.h b/drivers/gpu/drm/stm/ltdc.h index 9d488043ffdb..17b51a7ce28e 100644 --- a/drivers/gpu/drm/stm/ltdc.h +++ b/drivers/gpu/drm/stm/ltdc.h @@ -40,10 +40,16 @@ struct fps_info { ktime_t last_timestamp; }; +struct ltdc_plat_data { + int pad_max_freq_hz; /* max frequency supported by pad */ +}; + struct ltdc_device { void __iomem *regs; struct regmap *regmap; struct clk *pixel_clk; /* lcd pixel clock */ + struct clk *lvds_clk; /* lvds pixel clock */ + struct clk *bus_clk; /* bus clock */ struct mutex err_lock; /* protecting error_status */ struct ltdc_caps caps; u32 irq_status; diff --git a/drivers/gpu/drm/sysfb/drm_sysfb_modeset.c b/drivers/gpu/drm/sysfb/drm_sysfb_modeset.c index 963c380fea64..ddb4a7523ee6 100644 --- a/drivers/gpu/drm/sysfb/drm_sysfb_modeset.c +++ b/drivers/gpu/drm/sysfb/drm_sysfb_modeset.c @@ -238,8 +238,7 @@ void drm_sysfb_plane_helper_atomic_update(struct drm_plane *plane, struct drm_at struct drm_shadow_plane_state *shadow_plane_state = to_drm_shadow_plane_state(plane_state); struct drm_framebuffer *fb = plane_state->fb; unsigned int dst_pitch = sysfb->fb_pitch; - struct drm_crtc_state *crtc_state = crtc_state = - drm_atomic_get_new_crtc_state(state, plane_state->crtc); + struct drm_crtc_state *crtc_state = drm_atomic_get_new_crtc_state(state, plane_state->crtc); struct drm_sysfb_crtc_state *sysfb_crtc_state = to_drm_sysfb_crtc_state(crtc_state); const struct drm_format_info *dst_format = sysfb_crtc_state->format; struct drm_atomic_helper_damage_iter iter; diff --git a/drivers/gpu/drm/sysfb/vesadrm.c b/drivers/gpu/drm/sysfb/vesadrm.c index 1170e71e4208..16a4b52d45c6 100644 --- a/drivers/gpu/drm/sysfb/vesadrm.c +++ b/drivers/gpu/drm/sysfb/vesadrm.c @@ -289,7 +289,7 @@ static int vesadrm_primary_plane_helper_atomic_check(struct drm_plane *plane, break; } break; - }; + } return 0; } diff --git a/drivers/gpu/drm/tegra/gem.c b/drivers/gpu/drm/tegra/gem.c index 41a285ec889f..8ede07fb7a21 100644 --- a/drivers/gpu/drm/tegra/gem.c +++ b/drivers/gpu/drm/tegra/gem.c @@ -526,7 +526,7 @@ void tegra_bo_free_object(struct drm_gem_object *gem) if (drm_gem_is_imported(gem)) { dma_buf_unmap_attachment_unlocked(gem->import_attach, bo->sgt, DMA_TO_DEVICE); - dma_buf_detach(gem->dma_buf, gem->import_attach); + dma_buf_detach(gem->import_attach->dmabuf, gem->import_attach); } } diff --git a/drivers/gpu/drm/tests/drm_exec_test.c b/drivers/gpu/drm/tests/drm_exec_test.c index d6c4dd1194a0..3a20c788c51f 100644 --- a/drivers/gpu/drm/tests/drm_exec_test.c +++ b/drivers/gpu/drm/tests/drm_exec_test.c @@ -150,14 +150,22 @@ static void test_prepare(struct kunit *test) static void test_prepare_array(struct kunit *test) { struct drm_exec_priv *priv = test->priv; - struct drm_gem_object gobj1 = { }; - struct drm_gem_object gobj2 = { }; - struct drm_gem_object *array[] = { &gobj1, &gobj2 }; + struct drm_gem_object *gobj1; + struct drm_gem_object *gobj2; + struct drm_gem_object *array[] = { + (gobj1 = kunit_kzalloc(test, sizeof(*gobj1), GFP_KERNEL)), + (gobj2 = kunit_kzalloc(test, sizeof(*gobj2), GFP_KERNEL)), + }; struct drm_exec exec; int ret; - drm_gem_private_object_init(priv->drm, &gobj1, PAGE_SIZE); - drm_gem_private_object_init(priv->drm, &gobj2, PAGE_SIZE); + if (!gobj1 || !gobj2) { + KUNIT_FAIL(test, "Failed to allocate GEM objects.\n"); + return; + } + + drm_gem_private_object_init(priv->drm, gobj1, PAGE_SIZE); + drm_gem_private_object_init(priv->drm, gobj2, PAGE_SIZE); drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT, 0); drm_exec_until_all_locked(&exec) @@ -166,8 +174,8 @@ static void test_prepare_array(struct kunit *test) KUNIT_EXPECT_EQ(test, ret, 0); drm_exec_fini(&exec); - drm_gem_private_object_fini(&gobj1); - drm_gem_private_object_fini(&gobj2); + drm_gem_private_object_fini(gobj1); + drm_gem_private_object_fini(gobj2); } static void test_multiple_loops(struct kunit *test) diff --git a/drivers/gpu/drm/tests/drm_format_helper_test.c b/drivers/gpu/drm/tests/drm_format_helper_test.c index 7299fa8971ce..981dada8f3a8 100644 --- a/drivers/gpu/drm/tests/drm_format_helper_test.c +++ b/drivers/gpu/drm/tests/drm_format_helper_test.c @@ -1033,13 +1033,14 @@ static void drm_test_fb_xrgb8888_to_xrgb2101010(struct kunit *test) NULL : &result->dst_pitch; drm_fb_xrgb8888_to_xrgb2101010(&dst, dst_pitch, &src, &fb, ¶ms->clip, &fmtcnv_state); - buf = le32buf_to_cpu(test, buf, dst_size / sizeof(u32)); + buf = le32buf_to_cpu(test, (__force const __le32 *)buf, dst_size / sizeof(u32)); KUNIT_EXPECT_MEMEQ(test, buf, result->expected, dst_size); buf = dst.vaddr; /* restore original value of buf */ memset(buf, 0, dst_size); drm_fb_xrgb8888_to_xrgb2101010(&dst, dst_pitch, &src, &fb, ¶ms->clip, &fmtcnv_state); + buf = le32buf_to_cpu(test, (__force const __le32 *)buf, dst_size / sizeof(u32)); KUNIT_EXPECT_MEMEQ(test, buf, result->expected, dst_size); } diff --git a/drivers/gpu/drm/tidss/tidss_dispc.c b/drivers/gpu/drm/tidss/tidss_dispc.c index 3f6cff2ab1b2..7c8c15a5c39b 100644 --- a/drivers/gpu/drm/tidss/tidss_dispc.c +++ b/drivers/gpu/drm/tidss/tidss_dispc.c @@ -4,6 +4,7 @@ * Author: Jyri Sarha <jsarha@ti.com> */ +#include <linux/bitfield.h> #include <linux/clk.h> #include <linux/delay.h> #include <linux/dma-mapping.h> @@ -594,79 +595,53 @@ void tidss_disable_oldi(struct tidss_device *tidss, u32 hw_videoport) * number. For example 7:0 */ -static u32 FLD_MASK(u32 start, u32 end) -{ - return ((1 << (start - end + 1)) - 1) << end; -} - -static u32 FLD_VAL(u32 val, u32 start, u32 end) -{ - return (val << end) & FLD_MASK(start, end); -} - -static u32 FLD_GET(u32 val, u32 start, u32 end) -{ - return (val & FLD_MASK(start, end)) >> end; -} - -static u32 FLD_MOD(u32 orig, u32 val, u32 start, u32 end) -{ - return (orig & ~FLD_MASK(start, end)) | FLD_VAL(val, start, end); -} - -static u32 REG_GET(struct dispc_device *dispc, u32 idx, u32 start, u32 end) -{ - return FLD_GET(dispc_read(dispc, idx), start, end); -} - -static void REG_FLD_MOD(struct dispc_device *dispc, u32 idx, u32 val, - u32 start, u32 end) -{ - dispc_write(dispc, idx, FLD_MOD(dispc_read(dispc, idx), val, - start, end)); -} - -static u32 VID_REG_GET(struct dispc_device *dispc, u32 hw_plane, u32 idx, - u32 start, u32 end) -{ - return FLD_GET(dispc_vid_read(dispc, hw_plane, idx), start, end); -} - -static void VID_REG_FLD_MOD(struct dispc_device *dispc, u32 hw_plane, u32 idx, - u32 val, u32 start, u32 end) -{ - dispc_vid_write(dispc, hw_plane, idx, - FLD_MOD(dispc_vid_read(dispc, hw_plane, idx), - val, start, end)); -} - -static u32 VP_REG_GET(struct dispc_device *dispc, u32 vp, u32 idx, - u32 start, u32 end) -{ - return FLD_GET(dispc_vp_read(dispc, vp, idx), start, end); -} - -static void VP_REG_FLD_MOD(struct dispc_device *dispc, u32 vp, u32 idx, u32 val, - u32 start, u32 end) -{ - dispc_vp_write(dispc, vp, idx, FLD_MOD(dispc_vp_read(dispc, vp, idx), - val, start, end)); -} - -__maybe_unused -static u32 OVR_REG_GET(struct dispc_device *dispc, u32 ovr, u32 idx, - u32 start, u32 end) -{ - return FLD_GET(dispc_ovr_read(dispc, ovr, idx), start, end); -} - -static void OVR_REG_FLD_MOD(struct dispc_device *dispc, u32 ovr, u32 idx, - u32 val, u32 start, u32 end) -{ - dispc_ovr_write(dispc, ovr, idx, - FLD_MOD(dispc_ovr_read(dispc, ovr, idx), - val, start, end)); -} +#define REG_GET(dispc, idx, mask) \ + ((u32)FIELD_GET((mask), dispc_read((dispc), (idx)))) + +#define REG_FLD_MOD(dispc, idx, val, mask) \ + ({ \ + struct dispc_device *_dispc = (dispc); \ + u32 _idx = (idx); \ + u32 _reg = dispc_read(_dispc, _idx); \ + FIELD_MODIFY((mask), &_reg, (val)); \ + dispc_write(_dispc, _idx, _reg); \ + }) + +#define VID_REG_GET(dispc, hw_plane, idx, mask) \ + ((u32)FIELD_GET((mask), dispc_vid_read((dispc), (hw_plane), (idx)))) + +#define VID_REG_FLD_MOD(dispc, hw_plane, idx, val, mask) \ + ({ \ + struct dispc_device *_dispc = (dispc); \ + u32 _hw_plane = (hw_plane); \ + u32 _idx = (idx); \ + u32 _reg = dispc_vid_read(_dispc, _hw_plane, _idx); \ + FIELD_MODIFY((mask), &_reg, (val)); \ + dispc_vid_write(_dispc, _hw_plane, _idx, _reg); \ + }) + +#define VP_REG_GET(dispc, vp, idx, mask) \ + ((u32)FIELD_GET((mask), dispc_vp_read((dispc), (vp), (idx)))) + +#define VP_REG_FLD_MOD(dispc, vp, idx, val, mask) \ + ({ \ + struct dispc_device *_dispc = (dispc); \ + u32 _vp = (vp); \ + u32 _idx = (idx); \ + u32 _reg = dispc_vp_read(_dispc, _vp, _idx); \ + FIELD_MODIFY((mask), &_reg, (val)); \ + dispc_vp_write(_dispc, _vp, _idx, _reg); \ + }) + +#define OVR_REG_FLD_MOD(dispc, ovr, idx, val, mask) \ + ({ \ + struct dispc_device *_dispc = (dispc); \ + u32 _ovr = (ovr); \ + u32 _idx = (idx); \ + u32 _reg = dispc_ovr_read(_dispc, _ovr, _idx); \ + FIELD_MODIFY((mask), &_reg, (val)); \ + dispc_ovr_write(_dispc, _ovr, _idx, _reg); \ + }) static dispc_irq_t dispc_vp_irq_from_raw(u32 stat, u32 hw_videoport) { @@ -1139,7 +1114,8 @@ static void dispc_set_num_datalines(struct dispc_device *dispc, v = 3; } - VP_REG_FLD_MOD(dispc, hw_videoport, DISPC_VP_CONTROL, v, 10, 8); + VP_REG_FLD_MOD(dispc, hw_videoport, DISPC_VP_CONTROL, v, + DISPC_VP_CONTROL_DATALINES_MASK); } static void dispc_enable_am65x_oldi(struct dispc_device *dispc, u32 hw_videoport, @@ -1162,7 +1138,8 @@ static void dispc_enable_am65x_oldi(struct dispc_device *dispc, u32 hw_videoport oldi_cfg |= BIT(7); /* DEPOL */ - oldi_cfg = FLD_MOD(oldi_cfg, fmt->am65x_oldi_mode_reg_val, 3, 1); + FIELD_MODIFY(DISPC_VP_DSS_OLDI_CFG_MAP_MASK, &oldi_cfg, + fmt->am65x_oldi_mode_reg_val); oldi_cfg |= BIT(12); /* SOFTRST */ @@ -1224,14 +1201,14 @@ void dispc_vp_enable(struct dispc_device *dispc, u32 hw_videoport, vbp = mode->crtc_vtotal - mode->crtc_vsync_end; dispc_vp_write(dispc, hw_videoport, DISPC_VP_TIMING_H, - FLD_VAL(hsw - 1, 7, 0) | - FLD_VAL(hfp - 1, 19, 8) | - FLD_VAL(hbp - 1, 31, 20)); + FIELD_PREP(DISPC_VP_TIMING_H_SYNC_PULSE_MASK, hsw - 1) | + FIELD_PREP(DISPC_VP_TIMING_H_FRONT_PORCH_MASK, hfp - 1) | + FIELD_PREP(DISPC_VP_TIMING_H_BACK_PORCH_MASK, hbp - 1)); dispc_vp_write(dispc, hw_videoport, DISPC_VP_TIMING_V, - FLD_VAL(vsw - 1, 7, 0) | - FLD_VAL(vfp, 19, 8) | - FLD_VAL(vbp, 31, 20)); + FIELD_PREP(DISPC_VP_TIMING_V_SYNC_PULSE_MASK, vsw - 1) | + FIELD_PREP(DISPC_VP_TIMING_V_FRONT_PORCH_MASK, vfp) | + FIELD_PREP(DISPC_VP_TIMING_V_BACK_PORCH_MASK, vbp)); ivs = !!(mode->flags & DRM_MODE_FLAG_NVSYNC); @@ -1254,24 +1231,28 @@ void dispc_vp_enable(struct dispc_device *dispc, u32 hw_videoport, ieo = false; dispc_vp_write(dispc, hw_videoport, DISPC_VP_POL_FREQ, - FLD_VAL(align, 18, 18) | - FLD_VAL(onoff, 17, 17) | - FLD_VAL(rf, 16, 16) | - FLD_VAL(ieo, 15, 15) | - FLD_VAL(ipc, 14, 14) | - FLD_VAL(ihs, 13, 13) | - FLD_VAL(ivs, 12, 12)); + FIELD_PREP(DISPC_VP_POL_FREQ_ALIGN_MASK, align) | + FIELD_PREP(DISPC_VP_POL_FREQ_ONOFF_MASK, onoff) | + FIELD_PREP(DISPC_VP_POL_FREQ_RF_MASK, rf) | + FIELD_PREP(DISPC_VP_POL_FREQ_IEO_MASK, ieo) | + FIELD_PREP(DISPC_VP_POL_FREQ_IPC_MASK, ipc) | + FIELD_PREP(DISPC_VP_POL_FREQ_IHS_MASK, ihs) | + FIELD_PREP(DISPC_VP_POL_FREQ_IVS_MASK, ivs)); dispc_vp_write(dispc, hw_videoport, DISPC_VP_SIZE_SCREEN, - FLD_VAL(mode->crtc_hdisplay - 1, 11, 0) | - FLD_VAL(mode->crtc_vdisplay - 1, 27, 16)); + FIELD_PREP(DISPC_VP_SIZE_SCREEN_HDISPLAY_MASK, + mode->crtc_hdisplay - 1) | + FIELD_PREP(DISPC_VP_SIZE_SCREEN_VDISPLAY_MASK, + mode->crtc_vdisplay - 1)); - VP_REG_FLD_MOD(dispc, hw_videoport, DISPC_VP_CONTROL, 1, 0, 0); + VP_REG_FLD_MOD(dispc, hw_videoport, DISPC_VP_CONTROL, 1, + DISPC_VP_CONTROL_ENABLE_MASK); } void dispc_vp_disable(struct dispc_device *dispc, u32 hw_videoport) { - VP_REG_FLD_MOD(dispc, hw_videoport, DISPC_VP_CONTROL, 0, 0, 0); + VP_REG_FLD_MOD(dispc, hw_videoport, DISPC_VP_CONTROL, 0, + DISPC_VP_CONTROL_ENABLE_MASK); } void dispc_vp_unprepare(struct dispc_device *dispc, u32 hw_videoport) @@ -1285,13 +1266,16 @@ void dispc_vp_unprepare(struct dispc_device *dispc, u32 hw_videoport) bool dispc_vp_go_busy(struct dispc_device *dispc, u32 hw_videoport) { - return VP_REG_GET(dispc, hw_videoport, DISPC_VP_CONTROL, 5, 5); + return VP_REG_GET(dispc, hw_videoport, DISPC_VP_CONTROL, + DISPC_VP_CONTROL_GOBIT_MASK); } void dispc_vp_go(struct dispc_device *dispc, u32 hw_videoport) { - WARN_ON(VP_REG_GET(dispc, hw_videoport, DISPC_VP_CONTROL, 5, 5)); - VP_REG_FLD_MOD(dispc, hw_videoport, DISPC_VP_CONTROL, 1, 5, 5); + WARN_ON(VP_REG_GET(dispc, hw_videoport, DISPC_VP_CONTROL, + DISPC_VP_CONTROL_GOBIT_MASK)); + VP_REG_FLD_MOD(dispc, hw_videoport, DISPC_VP_CONTROL, 1, + DISPC_VP_CONTROL_GOBIT_MASK); } enum c8_to_c12_mode { C8_TO_C12_REPLICATE, C8_TO_C12_MAX, C8_TO_C12_MIN }; @@ -1491,11 +1475,11 @@ static void dispc_am65x_ovr_set_plane(struct dispc_device *dispc, u32 hw_id = dispc->feat->vid_info[hw_plane].hw_id; OVR_REG_FLD_MOD(dispc, hw_videoport, DISPC_OVR_ATTRIBUTES(layer), - hw_id, 4, 1); - OVR_REG_FLD_MOD(dispc, hw_videoport, DISPC_OVR_ATTRIBUTES(layer), - x, 17, 6); - OVR_REG_FLD_MOD(dispc, hw_videoport, DISPC_OVR_ATTRIBUTES(layer), - y, 30, 19); + hw_id, DISPC_OVR_ATTRIBUTES_CHANNELIN_MASK); + OVR_REG_FLD_MOD(dispc, hw_videoport, DISPC_OVR_ATTRIBUTES(layer), x, + DISPC_OVR_ATTRIBUTES_POSX_MASK); + OVR_REG_FLD_MOD(dispc, hw_videoport, DISPC_OVR_ATTRIBUTES(layer), y, + DISPC_OVR_ATTRIBUTES_POSY_MASK); } static void dispc_j721e_ovr_set_plane(struct dispc_device *dispc, @@ -1505,11 +1489,11 @@ static void dispc_j721e_ovr_set_plane(struct dispc_device *dispc, u32 hw_id = dispc->feat->vid_info[hw_plane].hw_id; OVR_REG_FLD_MOD(dispc, hw_videoport, DISPC_OVR_ATTRIBUTES(layer), - hw_id, 4, 1); - OVR_REG_FLD_MOD(dispc, hw_videoport, DISPC_OVR_ATTRIBUTES2(layer), - x, 13, 0); - OVR_REG_FLD_MOD(dispc, hw_videoport, DISPC_OVR_ATTRIBUTES2(layer), - y, 29, 16); + hw_id, DISPC_OVR_ATTRIBUTES_CHANNELIN_MASK); + OVR_REG_FLD_MOD(dispc, hw_videoport, DISPC_OVR_ATTRIBUTES2(layer), x, + DISPC_OVR_ATTRIBUTES2_POSX_MASK); + OVR_REG_FLD_MOD(dispc, hw_videoport, DISPC_OVR_ATTRIBUTES2(layer), y, + DISPC_OVR_ATTRIBUTES2_POSY_MASK); } void dispc_ovr_set_plane(struct dispc_device *dispc, u32 hw_plane, @@ -1544,7 +1528,7 @@ void dispc_ovr_enable_layer(struct dispc_device *dispc, return; OVR_REG_FLD_MOD(dispc, hw_videoport, DISPC_OVR_ATTRIBUTES(layer), - !!enable, 0, 0); + !!enable, DISPC_OVR_ATTRIBUTES_ENABLE_MASK); } /* CSC */ @@ -1580,14 +1564,14 @@ struct dispc_csc_coef { static void dispc_csc_offset_regval(const struct dispc_csc_coef *csc, u32 *regval) { -#define OVAL(x, y) (FLD_VAL(x, 15, 3) | FLD_VAL(y, 31, 19)) +#define OVAL(x, y) (FIELD_PREP(GENMASK(15, 3), x) | FIELD_PREP(GENMASK(31, 19), y)) regval[5] = OVAL(csc->preoffset[0], csc->preoffset[1]); regval[6] = OVAL(csc->preoffset[2], csc->postoffset[0]); regval[7] = OVAL(csc->postoffset[1], csc->postoffset[2]); #undef OVAL } -#define CVAL(x, y) (FLD_VAL(x, 10, 0) | FLD_VAL(y, 26, 16)) +#define CVAL(x, y) (FIELD_PREP(GENMASK(10, 0), x) | FIELD_PREP(GENMASK(26, 16), y)) static void dispc_csc_yuv2rgb_regval(const struct dispc_csc_coef *csc, u32 *regval) { @@ -1767,7 +1751,8 @@ static void dispc_vid_csc_setup(struct dispc_device *dispc, u32 hw_plane, static void dispc_vid_csc_enable(struct dispc_device *dispc, u32 hw_plane, bool enable) { - VID_REG_FLD_MOD(dispc, hw_plane, DISPC_VID_ATTRIBUTES, !!enable, 9, 9); + VID_REG_FLD_MOD(dispc, hw_plane, DISPC_VID_ATTRIBUTES, !!enable, + DISPC_VID_ATTRIBUTES_COLORCONVENABLE_MASK); } /* SCALER */ @@ -1826,7 +1811,8 @@ static void dispc_vid_write_fir_coefs(struct dispc_device *dispc, c1 = coefs->c1[phase]; c2 = coefs->c2[phase]; - c12 = FLD_VAL(c1, 19, 10) | FLD_VAL(c2, 29, 20); + c12 = FIELD_PREP(GENMASK(19, 10), c1) | FIELD_PREP(GENMASK(29, 20), + c2); dispc_vid_write(dispc, hw_plane, reg, c12); } @@ -2023,20 +2009,20 @@ static void dispc_vid_set_scaling(struct dispc_device *dispc, u32 fourcc) { /* HORIZONTAL RESIZE ENABLE */ - VID_REG_FLD_MOD(dispc, hw_plane, DISPC_VID_ATTRIBUTES, - sp->scale_x, 7, 7); + VID_REG_FLD_MOD(dispc, hw_plane, DISPC_VID_ATTRIBUTES, sp->scale_x, + DISPC_VID_ATTRIBUTES_HRESIZEENABLE_MASK); /* VERTICAL RESIZE ENABLE */ - VID_REG_FLD_MOD(dispc, hw_plane, DISPC_VID_ATTRIBUTES, - sp->scale_y, 8, 8); + VID_REG_FLD_MOD(dispc, hw_plane, DISPC_VID_ATTRIBUTES, sp->scale_y, + DISPC_VID_ATTRIBUTES_VRESIZEENABLE_MASK); /* Skip the rest if no scaling is used */ if (!sp->scale_x && !sp->scale_y) return; /* VERTICAL 5-TAPS */ - VID_REG_FLD_MOD(dispc, hw_plane, DISPC_VID_ATTRIBUTES, - sp->five_taps, 21, 21); + VID_REG_FLD_MOD(dispc, hw_plane, DISPC_VID_ATTRIBUTES, sp->five_taps, + DISPC_VID_ATTRIBUTES_VERTICALTAPS_MASK); if (dispc_fourcc_is_yuv(fourcc)) { if (sp->scale_x) { @@ -2126,7 +2112,7 @@ static void dispc_plane_set_pixel_format(struct dispc_device *dispc, if (dispc_color_formats[i].fourcc == fourcc) { VID_REG_FLD_MOD(dispc, hw_plane, DISPC_VID_ATTRIBUTES, dispc_color_formats[i].dss_code, - 6, 1); + DISPC_VID_ATTRIBUTES_FORMAT_MASK); return; } } @@ -2248,7 +2234,8 @@ void dispc_plane_setup(struct dispc_device *dispc, u32 hw_plane, dispc_vid_write(dispc, hw_plane, DISPC_VID_BA_EXT_1, (u64)dma_addr >> 32); dispc_vid_write(dispc, hw_plane, DISPC_VID_PICTURE_SIZE, - (scale.in_w - 1) | ((scale.in_h - 1) << 16)); + FIELD_PREP(DISPC_VID_PICTURE_SIZE_MEMSIZEY_MASK, scale.in_h - 1) | + FIELD_PREP(DISPC_VID_PICTURE_SIZE_MEMSIZEX_MASK, scale.in_w - 1)); /* For YUV422 format we use the macropixel size for pixel inc */ if (fourcc == DRM_FORMAT_YUYV || fourcc == DRM_FORMAT_UYVY) @@ -2285,8 +2272,10 @@ void dispc_plane_setup(struct dispc_device *dispc, u32 hw_plane, if (!lite) { dispc_vid_write(dispc, hw_plane, DISPC_VID_SIZE, - (state->crtc_w - 1) | - ((state->crtc_h - 1) << 16)); + FIELD_PREP(DISPC_VID_SIZE_SIZEY_MASK, + state->crtc_h - 1) | + FIELD_PREP(DISPC_VID_SIZE_SIZEX_MASK, + state->crtc_w - 1)); dispc_vid_set_scaling(dispc, hw_plane, &scale, fourcc); } @@ -2300,38 +2289,45 @@ void dispc_plane_setup(struct dispc_device *dispc, u32 hw_plane, } dispc_vid_write(dispc, hw_plane, DISPC_VID_GLOBAL_ALPHA, - 0xFF & (state->alpha >> 8)); + FIELD_PREP(DISPC_VID_GLOBAL_ALPHA_GLOBALALPHA_MASK, + state->alpha >> 8)); if (state->pixel_blend_mode == DRM_MODE_BLEND_PREMULTI) VID_REG_FLD_MOD(dispc, hw_plane, DISPC_VID_ATTRIBUTES, 1, - 28, 28); + DISPC_VID_ATTRIBUTES_PREMULTIPLYALPHA_MASK); else VID_REG_FLD_MOD(dispc, hw_plane, DISPC_VID_ATTRIBUTES, 0, - 28, 28); + DISPC_VID_ATTRIBUTES_PREMULTIPLYALPHA_MASK); } void dispc_plane_enable(struct dispc_device *dispc, u32 hw_plane, bool enable) { - VID_REG_FLD_MOD(dispc, hw_plane, DISPC_VID_ATTRIBUTES, !!enable, 0, 0); + VID_REG_FLD_MOD(dispc, hw_plane, DISPC_VID_ATTRIBUTES, !!enable, + DISPC_VID_ATTRIBUTES_ENABLE_MASK); } static u32 dispc_vid_get_fifo_size(struct dispc_device *dispc, u32 hw_plane) { - return VID_REG_GET(dispc, hw_plane, DISPC_VID_BUF_SIZE_STATUS, 15, 0); + return VID_REG_GET(dispc, hw_plane, DISPC_VID_BUF_SIZE_STATUS, + DISPC_VID_BUF_SIZE_STATUS_BUFSIZE_MASK); } static void dispc_vid_set_mflag_threshold(struct dispc_device *dispc, u32 hw_plane, u32 low, u32 high) { dispc_vid_write(dispc, hw_plane, DISPC_VID_MFLAG_THRESHOLD, - FLD_VAL(high, 31, 16) | FLD_VAL(low, 15, 0)); + FIELD_PREP(DISPC_VID_MFLAG_THRESHOLD_HT_MFLAG_MASK, high) | + FIELD_PREP(DISPC_VID_MFLAG_THRESHOLD_LT_MFLAG_MASK, low)); } static void dispc_vid_set_buf_threshold(struct dispc_device *dispc, u32 hw_plane, u32 low, u32 high) { dispc_vid_write(dispc, hw_plane, DISPC_VID_BUF_THRESHOLD, - FLD_VAL(high, 31, 16) | FLD_VAL(low, 15, 0)); + FIELD_PREP(DISPC_VID_BUF_THRESHOLD_BUFHIGHTHRESHOLD_MASK, + high) | + FIELD_PREP(DISPC_VID_BUF_THRESHOLD_BUFLOWTHRESHOLD_MASK, + low)); } static void dispc_k2g_plane_init(struct dispc_device *dispc) @@ -2341,9 +2337,11 @@ static void dispc_k2g_plane_init(struct dispc_device *dispc) dev_dbg(dispc->dev, "%s()\n", __func__); /* MFLAG_CTRL = ENABLED */ - REG_FLD_MOD(dispc, DISPC_GLOBAL_MFLAG_ATTRIBUTE, 2, 1, 0); + REG_FLD_MOD(dispc, DISPC_GLOBAL_MFLAG_ATTRIBUTE, 2, + DISPC_GLOBAL_MFLAG_ATTRIBUTE_MFLAG_CTRL_MASK); /* MFLAG_START = MFLAGNORMALSTARTMODE */ - REG_FLD_MOD(dispc, DISPC_GLOBAL_MFLAG_ATTRIBUTE, 0, 6, 6); + REG_FLD_MOD(dispc, DISPC_GLOBAL_MFLAG_ATTRIBUTE, 0, + DISPC_GLOBAL_MFLAG_ATTRIBUTE_MFLAG_START_MASK); for (hw_plane = 0; hw_plane < dispc->feat->num_vids; hw_plane++) { u32 size = dispc_vid_get_fifo_size(dispc, hw_plane); @@ -2380,7 +2378,7 @@ static void dispc_k2g_plane_init(struct dispc_device *dispc) * register is ignored. */ VID_REG_FLD_MOD(dispc, hw_plane, DISPC_VID_ATTRIBUTES, 1, - 19, 19); + DISPC_VID_ATTRIBUTES_BUFPRELOAD_MASK); } } @@ -2392,13 +2390,15 @@ static void dispc_k3_plane_init(struct dispc_device *dispc) dev_dbg(dispc->dev, "%s()\n", __func__); - REG_FLD_MOD(dispc, DSS_CBA_CFG, cba_lo_pri, 2, 0); - REG_FLD_MOD(dispc, DSS_CBA_CFG, cba_hi_pri, 5, 3); + REG_FLD_MOD(dispc, DSS_CBA_CFG, cba_lo_pri, DSS_CBA_CFG_PRI_LO_MASK); + REG_FLD_MOD(dispc, DSS_CBA_CFG, cba_hi_pri, DSS_CBA_CFG_PRI_HI_MASK); /* MFLAG_CTRL = ENABLED */ - REG_FLD_MOD(dispc, DISPC_GLOBAL_MFLAG_ATTRIBUTE, 2, 1, 0); + REG_FLD_MOD(dispc, DISPC_GLOBAL_MFLAG_ATTRIBUTE, 2, + DISPC_GLOBAL_MFLAG_ATTRIBUTE_MFLAG_CTRL_MASK); /* MFLAG_START = MFLAGNORMALSTARTMODE */ - REG_FLD_MOD(dispc, DISPC_GLOBAL_MFLAG_ATTRIBUTE, 0, 6, 6); + REG_FLD_MOD(dispc, DISPC_GLOBAL_MFLAG_ATTRIBUTE, 0, + DISPC_GLOBAL_MFLAG_ATTRIBUTE_MFLAG_START_MASK); for (hw_plane = 0; hw_plane < dispc->feat->num_vids; hw_plane++) { u32 size = dispc_vid_get_fifo_size(dispc, hw_plane); @@ -2431,7 +2431,7 @@ static void dispc_k3_plane_init(struct dispc_device *dispc) /* Prefech up to PRELOAD value */ VID_REG_FLD_MOD(dispc, hw_plane, DISPC_VID_ATTRIBUTES, 0, - 19, 19); + DISPC_VID_ATTRIBUTES_BUFPRELOAD_MASK); } } @@ -2461,7 +2461,8 @@ static void dispc_vp_init(struct dispc_device *dispc) /* Enable the gamma Shadow bit-field for all VPs*/ for (i = 0; i < dispc->feat->num_vps; i++) - VP_REG_FLD_MOD(dispc, i, DISPC_VP_CONFIG, 1, 2, 2); + VP_REG_FLD_MOD(dispc, i, DISPC_VP_CONFIG, 1, + DISPC_VP_CONFIG_GAMMAENABLE_MASK); } static void dispc_initial_config(struct dispc_device *dispc) @@ -2472,8 +2473,8 @@ static void dispc_initial_config(struct dispc_device *dispc) /* Note: Hardcoded DPI routing on J721E for now */ if (dispc->feat->subrev == DISPC_J721E) { dispc_write(dispc, DISPC_CONNECTIONS, - FLD_VAL(2, 3, 0) | /* VP1 to DPI0 */ - FLD_VAL(8, 7, 4) /* VP3 to DPI1 */ + FIELD_PREP(DISPC_CONNECTIONS_DPI_0_CONN_MASK, 2) | /* VP1 to DPI0 */ + FIELD_PREP(DISPC_CONNECTIONS_DPI_1_CONN_MASK, 8) /* VP3 to DPI1 */ ); } } @@ -2651,8 +2652,8 @@ static void dispc_k2g_cpr_from_ctm(const struct drm_color_ctm *ctm, cpr->m[CSC_BB] = dispc_S31_32_to_s2_8(ctm->matrix[8]); } -#define CVAL(xR, xG, xB) (FLD_VAL(xR, 9, 0) | FLD_VAL(xG, 20, 11) | \ - FLD_VAL(xB, 31, 22)) +#define CVAL(xR, xG, xB) (FIELD_PREP(GENMASK(9, 0), xR) | FIELD_PREP(GENMASK(20, 11), xG) | \ + FIELD_PREP(GENMASK(31, 22), xB)) static void dispc_k2g_vp_csc_cpr_regval(const struct dispc_csc_coef *csc, u32 *regval) @@ -2694,8 +2695,8 @@ static void dispc_k2g_vp_set_ctm(struct dispc_device *dispc, u32 hw_videoport, cprenable = 1; } - VP_REG_FLD_MOD(dispc, hw_videoport, DISPC_VP_CONFIG, - cprenable, 15, 15); + VP_REG_FLD_MOD(dispc, hw_videoport, DISPC_VP_CONFIG, cprenable, + DISPC_VP_CONFIG_CPR_MASK); } static s16 dispc_S31_32_to_s3_8(s64 coef) @@ -2760,8 +2761,8 @@ static void dispc_k3_vp_set_ctm(struct dispc_device *dispc, u32 hw_videoport, colorconvenable = 1; } - VP_REG_FLD_MOD(dispc, hw_videoport, DISPC_VP_CONFIG, - colorconvenable, 24, 24); + VP_REG_FLD_MOD(dispc, hw_videoport, DISPC_VP_CONFIG, colorconvenable, + DISPC_VP_CONFIG_COLORCONVENABLE_MASK); } static void dispc_vp_set_color_mgmt(struct dispc_device *dispc, @@ -2816,26 +2817,26 @@ int dispc_runtime_resume(struct dispc_device *dispc) clk_prepare_enable(dispc->fclk); - if (REG_GET(dispc, DSS_SYSSTATUS, 0, 0) == 0) + if (REG_GET(dispc, DSS_SYSSTATUS, DSS_SYSSTATUS_DISPC_FUNC_RESETDONE) == 0) dev_warn(dispc->dev, "DSS FUNC RESET not done!\n"); dev_dbg(dispc->dev, "OMAP DSS7 rev 0x%x\n", dispc_read(dispc, DSS_REVISION)); dev_dbg(dispc->dev, "VP RESETDONE %d,%d,%d\n", - REG_GET(dispc, DSS_SYSSTATUS, 1, 1), - REG_GET(dispc, DSS_SYSSTATUS, 2, 2), - REG_GET(dispc, DSS_SYSSTATUS, 3, 3)); + REG_GET(dispc, DSS_SYSSTATUS, GENMASK(1, 1)), + REG_GET(dispc, DSS_SYSSTATUS, GENMASK(2, 2)), + REG_GET(dispc, DSS_SYSSTATUS, GENMASK(3, 3))); if (dispc->feat->subrev == DISPC_AM625 || dispc->feat->subrev == DISPC_AM65X) dev_dbg(dispc->dev, "OLDI RESETDONE %d,%d,%d\n", - REG_GET(dispc, DSS_SYSSTATUS, 5, 5), - REG_GET(dispc, DSS_SYSSTATUS, 6, 6), - REG_GET(dispc, DSS_SYSSTATUS, 7, 7)); + REG_GET(dispc, DSS_SYSSTATUS, GENMASK(5, 5)), + REG_GET(dispc, DSS_SYSSTATUS, GENMASK(6, 6)), + REG_GET(dispc, DSS_SYSSTATUS, GENMASK(7, 7))); dev_dbg(dispc->dev, "DISPC IDLE %d\n", - REG_GET(dispc, DSS_SYSSTATUS, 9, 9)); + REG_GET(dispc, DSS_SYSSTATUS, DSS_SYSSTATUS_DISPC_IDLE_STATUS)); dispc_initial_config(dispc); @@ -2912,7 +2913,8 @@ static void dispc_softreset_k2g(struct dispc_device *dispc) spin_unlock_irqrestore(&dispc->tidss->irq_lock, flags); for (unsigned int vp_idx = 0; vp_idx < dispc->feat->num_vps; ++vp_idx) - VP_REG_FLD_MOD(dispc, vp_idx, DISPC_VP_CONTROL, 0, 0, 0); + VP_REG_FLD_MOD(dispc, vp_idx, DISPC_VP_CONTROL, 0, + DISPC_VP_CONTROL_ENABLE_MASK); } static int dispc_softreset(struct dispc_device *dispc) @@ -2926,7 +2928,7 @@ static int dispc_softreset(struct dispc_device *dispc) } /* Soft reset */ - REG_FLD_MOD(dispc, DSS_SYSCONFIG, 1, 1, 1); + REG_FLD_MOD(dispc, DSS_SYSCONFIG, 1, DSS_SYSCONFIG_SOFTRESET_MASK); /* Wait for reset to complete */ ret = readl_poll_timeout(dispc->base_common + DSS_SYSSTATUS, val, val & 1, 100, 5000); diff --git a/drivers/gpu/drm/tidss/tidss_dispc_regs.h b/drivers/gpu/drm/tidss/tidss_dispc_regs.h index 50a3f28250ef..382027dddce8 100644 --- a/drivers/gpu/drm/tidss/tidss_dispc_regs.h +++ b/drivers/gpu/drm/tidss/tidss_dispc_regs.h @@ -56,7 +56,12 @@ enum dispc_common_regs { #define DSS_REVISION REG(DSS_REVISION) #define DSS_SYSCONFIG REG(DSS_SYSCONFIG) +#define DSS_SYSCONFIG_SOFTRESET_MASK GENMASK(1, 1) + #define DSS_SYSSTATUS REG(DSS_SYSSTATUS) +#define DSS_SYSSTATUS_DISPC_IDLE_STATUS GENMASK(9, 9) +#define DSS_SYSSTATUS_DISPC_FUNC_RESETDONE GENMASK(0, 0) + #define DISPC_IRQ_EOI REG(DISPC_IRQ_EOI) #define DISPC_IRQSTATUS_RAW REG(DISPC_IRQSTATUS_RAW) #define DISPC_IRQSTATUS REG(DISPC_IRQSTATUS) @@ -70,9 +75,15 @@ enum dispc_common_regs { #define WB_IRQSTATUS REG(WB_IRQSTATUS) #define DISPC_GLOBAL_MFLAG_ATTRIBUTE REG(DISPC_GLOBAL_MFLAG_ATTRIBUTE) +#define DISPC_GLOBAL_MFLAG_ATTRIBUTE_MFLAG_START_MASK GENMASK(6, 6) +#define DISPC_GLOBAL_MFLAG_ATTRIBUTE_MFLAG_CTRL_MASK GENMASK(1, 0) + #define DISPC_GLOBAL_OUTPUT_ENABLE REG(DISPC_GLOBAL_OUTPUT_ENABLE) #define DISPC_GLOBAL_BUFFER REG(DISPC_GLOBAL_BUFFER) #define DSS_CBA_CFG REG(DSS_CBA_CFG) +#define DSS_CBA_CFG_PRI_HI_MASK GENMASK(5, 3) +#define DSS_CBA_CFG_PRI_LO_MASK GENMASK(2, 0) + #define DISPC_DBG_CONTROL REG(DISPC_DBG_CONTROL) #define DISPC_DBG_STATUS REG(DISPC_DBG_STATUS) #define DISPC_CLKGATING_DISABLE REG(DISPC_CLKGATING_DISABLE) @@ -88,6 +99,9 @@ enum dispc_common_regs { #define FBDC_CONSTANT_COLOR_0 REG(FBDC_CONSTANT_COLOR_0) #define FBDC_CONSTANT_COLOR_1 REG(FBDC_CONSTANT_COLOR_1) #define DISPC_CONNECTIONS REG(DISPC_CONNECTIONS) +#define DISPC_CONNECTIONS_DPI_1_CONN_MASK GENMASK(7, 4) +#define DISPC_CONNECTIONS_DPI_0_CONN_MASK GENMASK(3, 0) + #define DISPC_MSS_VP1 REG(DISPC_MSS_VP1) #define DISPC_MSS_VP3 REG(DISPC_MSS_VP3) @@ -102,13 +116,27 @@ enum dispc_common_regs { #define DISPC_VID_ACCUV2_0 0x18 #define DISPC_VID_ACCUV2_1 0x1c #define DISPC_VID_ATTRIBUTES 0x20 +#define DISPC_VID_ATTRIBUTES_PREMULTIPLYALPHA_MASK GENMASK(28, 28) +#define DISPC_VID_ATTRIBUTES_VERTICALTAPS_MASK GENMASK(21, 21) +#define DISPC_VID_ATTRIBUTES_BUFPRELOAD_MASK GENMASK(19, 19) +#define DISPC_VID_ATTRIBUTES_COLORCONVENABLE_MASK GENMASK(9, 9) +#define DISPC_VID_ATTRIBUTES_VRESIZEENABLE_MASK GENMASK(8, 8) +#define DISPC_VID_ATTRIBUTES_HRESIZEENABLE_MASK GENMASK(7, 7) +#define DISPC_VID_ATTRIBUTES_FORMAT_MASK GENMASK(6, 1) +#define DISPC_VID_ATTRIBUTES_ENABLE_MASK GENMASK(0, 0) + #define DISPC_VID_ATTRIBUTES2 0x24 #define DISPC_VID_BA_0 0x28 #define DISPC_VID_BA_1 0x2c #define DISPC_VID_BA_UV_0 0x30 #define DISPC_VID_BA_UV_1 0x34 #define DISPC_VID_BUF_SIZE_STATUS 0x38 +#define DISPC_VID_BUF_SIZE_STATUS_BUFSIZE_MASK GENMASK(15, 0) + #define DISPC_VID_BUF_THRESHOLD 0x3c +#define DISPC_VID_BUF_THRESHOLD_BUFHIGHTHRESHOLD_MASK GENMASK(31, 16) +#define DISPC_VID_BUF_THRESHOLD_BUFLOWTHRESHOLD_MASK GENMASK(15, 0) + #define DISPC_VID_CSC_COEF(n) (0x40 + (n) * 4) #define DISPC_VID_FIRH 0x5c @@ -137,15 +165,26 @@ enum dispc_common_regs { #define DISPC_VID_FIR_COEF_V12_C(phase) (0x1bc + (phase) * 4) #define DISPC_VID_GLOBAL_ALPHA 0x1fc +#define DISPC_VID_GLOBAL_ALPHA_GLOBALALPHA_MASK GENMASK(7, 0) + #define DISPC_VID_K2G_IRQENABLE 0x200 /* K2G */ #define DISPC_VID_K2G_IRQSTATUS 0x204 /* K2G */ #define DISPC_VID_MFLAG_THRESHOLD 0x208 +#define DISPC_VID_MFLAG_THRESHOLD_HT_MFLAG_MASK GENMASK(31, 16) +#define DISPC_VID_MFLAG_THRESHOLD_LT_MFLAG_MASK GENMASK(15, 0) + #define DISPC_VID_PICTURE_SIZE 0x20c +#define DISPC_VID_PICTURE_SIZE_MEMSIZEY_MASK GENMASK(27, 16) +#define DISPC_VID_PICTURE_SIZE_MEMSIZEX_MASK GENMASK(11, 0) + #define DISPC_VID_PIXEL_INC 0x210 #define DISPC_VID_K2G_POSITION 0x214 /* K2G */ #define DISPC_VID_PRELOAD 0x218 #define DISPC_VID_ROW_INC 0x21c #define DISPC_VID_SIZE 0x220 +#define DISPC_VID_SIZE_SIZEY_MASK GENMASK(27, 16) +#define DISPC_VID_SIZE_SIZEX_MASK GENMASK(11, 0) + #define DISPC_VID_BA_EXT_0 0x22c #define DISPC_VID_BA_EXT_1 0x230 #define DISPC_VID_BA_UV_EXT_0 0x234 @@ -173,11 +212,27 @@ enum dispc_common_regs { #define DISPC_OVR_TRANS_COLOR_MIN 0x18 #define DISPC_OVR_TRANS_COLOR_MIN2 0x1c #define DISPC_OVR_ATTRIBUTES(n) (0x20 + (n) * 4) +#define DISPC_OVR_ATTRIBUTES_POSY_MASK GENMASK(30, 19) +#define DISPC_OVR_ATTRIBUTES_POSX_MASK GENMASK(17, 6) +#define DISPC_OVR_ATTRIBUTES_CHANNELIN_MASK GENMASK(4, 1) +#define DISPC_OVR_ATTRIBUTES_ENABLE_MASK GENMASK(0, 0) + #define DISPC_OVR_ATTRIBUTES2(n) (0x34 + (n) * 4) /* J721E */ +#define DISPC_OVR_ATTRIBUTES2_POSY_MASK GENMASK(29, 16) +#define DISPC_OVR_ATTRIBUTES2_POSX_MASK GENMASK(13, 0) + /* VP */ #define DISPC_VP_CONFIG 0x0 +#define DISPC_VP_CONFIG_COLORCONVENABLE_MASK GENMASK(24, 24) +#define DISPC_VP_CONFIG_CPR_MASK GENMASK(15, 15) +#define DISPC_VP_CONFIG_GAMMAENABLE_MASK GENMASK(2, 2) + #define DISPC_VP_CONTROL 0x4 +#define DISPC_VP_CONTROL_DATALINES_MASK GENMASK(10, 8) +#define DISPC_VP_CONTROL_GOBIT_MASK GENMASK(5, 5) +#define DISPC_VP_CONTROL_ENABLE_MASK GENMASK(0, 0) + #define DISPC_VP_CSC_COEF0 0x8 #define DISPC_VP_CSC_COEF1 0xc #define DISPC_VP_CSC_COEF2 0x10 @@ -189,9 +244,28 @@ enum dispc_common_regs { #define DISPC_VP_DATA_CYCLE_2 0x1c #define DISPC_VP_LINE_NUMBER 0x44 #define DISPC_VP_POL_FREQ 0x4c +#define DISPC_VP_POL_FREQ_ALIGN_MASK GENMASK(18, 18) +#define DISPC_VP_POL_FREQ_ONOFF_MASK GENMASK(17, 17) +#define DISPC_VP_POL_FREQ_RF_MASK GENMASK(16, 16) +#define DISPC_VP_POL_FREQ_IEO_MASK GENMASK(15, 15) +#define DISPC_VP_POL_FREQ_IPC_MASK GENMASK(14, 14) +#define DISPC_VP_POL_FREQ_IHS_MASK GENMASK(13, 13) +#define DISPC_VP_POL_FREQ_IVS_MASK GENMASK(12, 12) + #define DISPC_VP_SIZE_SCREEN 0x50 +#define DISPC_VP_SIZE_SCREEN_HDISPLAY_MASK GENMASK(11, 0) +#define DISPC_VP_SIZE_SCREEN_VDISPLAY_MASK GENMASK(27, 16) + #define DISPC_VP_TIMING_H 0x54 +#define DISPC_VP_TIMING_H_SYNC_PULSE_MASK GENMASK(7, 0) +#define DISPC_VP_TIMING_H_FRONT_PORCH_MASK GENMASK(19, 8) +#define DISPC_VP_TIMING_H_BACK_PORCH_MASK GENMASK(31, 20) + #define DISPC_VP_TIMING_V 0x58 +#define DISPC_VP_TIMING_V_SYNC_PULSE_MASK GENMASK(7, 0) +#define DISPC_VP_TIMING_V_FRONT_PORCH_MASK GENMASK(19, 8) +#define DISPC_VP_TIMING_V_BACK_PORCH_MASK GENMASK(31, 20) + #define DISPC_VP_CSC_COEF3 0x5c #define DISPC_VP_CSC_COEF4 0x60 #define DISPC_VP_CSC_COEF5 0x64 @@ -220,6 +294,8 @@ enum dispc_common_regs { #define DISPC_VP_SAFETY_LFSR_SEED 0x110 #define DISPC_VP_GAMMA_TABLE 0x120 #define DISPC_VP_DSS_OLDI_CFG 0x160 +#define DISPC_VP_DSS_OLDI_CFG_MAP_MASK GENMASK(3, 1) + #define DISPC_VP_DSS_OLDI_STATUS 0x164 #define DISPC_VP_DSS_OLDI_LB 0x168 #define DISPC_VP_DSS_MERGE_SPLIT 0x16c /* J721E */ diff --git a/drivers/gpu/drm/tiny/Kconfig b/drivers/gpu/drm/tiny/Kconfig index 06e54694a7f2..7d9e85e932d7 100644 --- a/drivers/gpu/drm/tiny/Kconfig +++ b/drivers/gpu/drm/tiny/Kconfig @@ -82,6 +82,21 @@ config DRM_PANEL_MIPI_DBI https://github.com/notro/panel-mipi-dbi/wiki. To compile this driver as a module, choose M here. +config DRM_PIXPAPER + tristate "DRM support for PIXPAPER display panels" + depends on DRM && SPI + select DRM_CLIENT_SELECTION + select DRM_GEM_SHMEM_HELPER + select DRM_KMS_HELPER + help + DRM driver for the Mayqueen Pixpaper e-ink display panel. + + This driver supports small e-paper displays connected over SPI, + with a resolution of 122x250 and XRGB8888 framebuffer format. + It is intended for low-power embedded applications. + + If M is selected, the module will be built as pixpaper.ko. + config TINYDRM_HX8357D tristate "DRM support for HX8357D display panels" depends on DRM && SPI diff --git a/drivers/gpu/drm/tiny/Makefile b/drivers/gpu/drm/tiny/Makefile index 4a9ff61ec254..48d30bf6152f 100644 --- a/drivers/gpu/drm/tiny/Makefile +++ b/drivers/gpu/drm/tiny/Makefile @@ -6,6 +6,7 @@ obj-$(CONFIG_DRM_BOCHS) += bochs.o obj-$(CONFIG_DRM_CIRRUS_QEMU) += cirrus-qemu.o obj-$(CONFIG_DRM_GM12U320) += gm12u320.o obj-$(CONFIG_DRM_PANEL_MIPI_DBI) += panel-mipi-dbi.o +obj-$(CONFIG_DRM_PIXPAPER) += pixpaper.o obj-$(CONFIG_TINYDRM_HX8357D) += hx8357d.o obj-$(CONFIG_TINYDRM_ILI9163) += ili9163.o obj-$(CONFIG_TINYDRM_ILI9225) += ili9225.o diff --git a/drivers/gpu/drm/tiny/bochs.c b/drivers/gpu/drm/tiny/bochs.c index 8d3b7c4fa6a4..d2d5e9f1269f 100644 --- a/drivers/gpu/drm/tiny/bochs.c +++ b/drivers/gpu/drm/tiny/bochs.c @@ -252,7 +252,7 @@ static int bochs_hw_init(struct bochs_device *bochs) } bochs->ioports = 1; } else { - dev_err(dev->dev, "I/O ports are not supported\n"); + drm_err(dev, "I/O ports are not supported\n"); return -EIO; } diff --git a/drivers/gpu/drm/tiny/pixpaper.c b/drivers/gpu/drm/tiny/pixpaper.c new file mode 100644 index 000000000000..32598fb2fee7 --- /dev/null +++ b/drivers/gpu/drm/tiny/pixpaper.c @@ -0,0 +1,1165 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * DRM driver for PIXPAPER e-ink panel + * + * Author: LiangCheng Wang <zaq14760@gmail.com>, + */ +#include <linux/delay.h> +#include <linux/module.h> +#include <linux/spi/spi.h> + +#include <drm/clients/drm_client_setup.h> +#include <drm/drm_atomic.h> +#include <drm/drm_atomic_helper.h> +#include <drm/drm_drv.h> +#include <drm/drm_fbdev_shmem.h> +#include <drm/drm_framebuffer.h> +#include <drm/drm_gem_atomic_helper.h> +#include <drm/drm_gem_shmem_helper.h> +#include <drm/drm_gem_framebuffer_helper.h> +#include <drm/drm_probe_helper.h> + +/* + * Note on Undocumented Commands/Registers: + * + * Several commands and register parameters defined in this header are not + * documented in the datasheet. Their values and usage have been derived + * through analysis of existing userspace example programs. + * + * These 'unknown' definitions are crucial for the proper initialization + * and stable operation of the panel. Modifying these values without + * thorough understanding may lead to display anomalies, panel damage, + * or unexpected behavior. + */ + +/* Command definitions */ +#define PIXPAPER_CMD_PANEL_SETTING 0x00 /* R00H: Panel settings */ +#define PIXPAPER_CMD_POWER_SETTING 0x01 /* R01H: Power settings */ +#define PIXPAPER_CMD_POWER_OFF 0x02 /* R02H: Power off */ +#define PIXPAPER_CMD_POWER_OFF_SEQUENCE 0x03 /* R03H: Power off sequence */ +#define PIXPAPER_CMD_POWER_ON 0x04 /* R04H: Power on */ +#define PIXPAPER_CMD_BOOSTER_SOFT_START 0x06 /* R06H: Booster soft start */ +#define PIXPAPER_CMD_DEEP_SLEEP 0x07 /* R07H: Deep sleep */ +#define PIXPAPER_CMD_DATA_START_TRANSMISSION 0x10 +/* R10H: Data transmission start */ +#define PIXPAPER_CMD_DISPLAY_REFRESH 0x12 /* R12H: Display refresh */ +#define PIXPAPER_CMD_PLL_CONTROL 0x30 /* R30H: PLL control */ +#define PIXPAPER_CMD_TEMP_SENSOR_CALIB 0x41 +/* R41H: Temperature sensor calibration */ +#define PIXPAPER_CMD_UNKNOWN_4D 0x4D /* R4DH: Unknown command */ +#define PIXPAPER_CMD_VCOM_INTERVAL 0x50 /* R50H: VCOM interval */ +#define PIXPAPER_CMD_UNKNOWN_60 0x60 /* R60H: Unknown command */ +#define PIXPAPER_CMD_RESOLUTION_SETTING 0x61 /* R61H: Resolution settings */ +#define PIXPAPER_CMD_GATE_SOURCE_START 0x65 /* R65H: Gate/source start */ +#define PIXPAPER_CMD_UNKNOWN_B4 0xB4 /* RB4H: Unknown command */ +#define PIXPAPER_CMD_UNKNOWN_B5 0xB5 /* RB5H: Unknown command */ +#define PIXPAPER_CMD_UNKNOWN_E0 0xE0 /* RE0H: Unknown command */ +#define PIXPAPER_CMD_POWER_SAVING 0xE3 /* RE3H: Power saving */ +#define PIXPAPER_CMD_UNKNOWN_E7 0xE7 /* RE7H: Unknown command */ +#define PIXPAPER_CMD_UNKNOWN_E9 0xE9 /* RE9H: Unknown command */ + +/* R00H PSR - First Parameter */ +#define PIXPAPER_PSR_RST_N BIT(0) +/* Bit 0: RST_N, 1=no effect (default), 0=reset with booster OFF */ +#define PIXPAPER_PSR_SHD_N BIT(1) +/* Bit 1: SHD_N, 1=booster ON (default), 0=booster OFF */ +#define PIXPAPER_PSR_SHL BIT(2) +/* Bit 2: SHL, 1=shift right (default), 0=shift left */ +#define PIXPAPER_PSR_UD BIT(3) +/* Bit 3: UD, 1=scan up (default), 0=scan down */ +#define PIXPAPER_PSR_PST_MODE BIT(5) +/* Bit 5: PST_MODE, 0=frame scanning (default), 1=external */ +#define PIXPAPER_PSR_RES_MASK (3 << 6) +/* Bits 7-6: RES[1:0], resolution setting */ +#define PIXPAPER_PSR_RES_176x296 (0x0 << 6) /* 00: 176x296 */ +#define PIXPAPER_PSR_RES_128x296 (0x1 << 6) /* 01: 128x296 */ +#define PIXPAPER_PSR_RES_128x250 (0x2 << 6) /* 10: 128x250 */ +#define PIXPAPER_PSR_RES_112x204 (0x3 << 6) /* 11: 112x204 */ +#define PIXPAPER_PSR_CONFIG \ + (PIXPAPER_PSR_RST_N | PIXPAPER_PSR_SHD_N | PIXPAPER_PSR_SHL | \ + PIXPAPER_PSR_UD) +/* 0x0F: Default settings, resolution set by R61H */ + +/* R00H PSR - Second Parameter */ +#define PIXPAPER_PSR2_VC_LUTZ \ + (1 << 0) /* Bit 0: VC_LUTZ, 1=VCOM float after refresh (default), 0=no effect */ +#define PIXPAPER_PSR2_NORG \ + (1 << 1) /* Bit 1: NORG, 1=VCOM to GND before power off, 0=no effect (default) */ +#define PIXPAPER_PSR2_TIEG \ + (1 << 2) /* Bit 2: TIEG, 1=VGN to GND on power off, 0=no effect (default) */ +#define PIXPAPER_PSR2_TS_AUTO \ + (1 << 3) /* Bit 3: TS_AUTO, 1=sensor on RST_N low to high (default), 0=on booster */ +#define PIXPAPER_PSR2_VCMZ \ + (1 << 4) /* Bit 4: VCMZ, 1=VCOM always floating, 0=no effect (default) */ +#define PIXPAPER_PSR2_FOPT \ + (1 << 5) /* Bit 5: FOPT, 0=scan 1 frame (default), 1=no scan, HiZ */ +#define PIXPAPER_PSR_CONFIG2 \ + (PIXPAPER_PSR2_VC_LUTZ | \ + PIXPAPER_PSR2_TS_AUTO) /* 0x09: Default VCOM and temp sensor settings */ + +/* R01H PWR - Power Setting Register */ +/* First Parameter */ +#define PIXPAPER_PWR_VDG_EN \ + (1 << 0) /* Bit 0: VDG_EN, 1=internal DCDC for VGP/VGN (default), 0=external */ +#define PIXPAPER_PWR_VDS_EN \ + (1 << 1) /* Bit 1: VDS_EN, 1=internal regulator for VSP/VSN (default), 0=external */ +#define PIXPAPER_PWR_VSC_EN \ + (1 << 2) /* Bit 2: VSC_EN, 1=internal regulator for VSPL (default), 0=external */ +#define PIXPAPER_PWR_V_MODE \ + (1 << 3) /* Bit 3: V_MODE, 0=Mode0 (default), 1=Mode1 */ +#define PIXPAPER_PWR_CONFIG1 \ + (PIXPAPER_PWR_VDG_EN | PIXPAPER_PWR_VDS_EN | \ + PIXPAPER_PWR_VSC_EN) /* 0x07: Internal power for VGP/VGN, VSP/VSN, VSPL */ + +/* Second Parameter */ +#define PIXPAPER_PWR_VGPN_MASK \ + (3 << 0) /* Bits 1-0: VGPN, VGP/VGN voltage levels */ +#define PIXPAPER_PWR_VGPN_20V (0x0 << 0) /* 00: VGP=20V, VGN=-20V (default) */ +#define PIXPAPER_PWR_VGPN_17V (0x1 << 0) /* 01: VGP=17V, VGN=-17V */ +#define PIXPAPER_PWR_VGPN_15V (0x2 << 0) /* 10: VGP=15V, VGN=-15V */ +#define PIXPAPER_PWR_VGPN_10V (0x3 << 0) /* 11: VGP=10V, VGN=-10V */ +#define PIXPAPER_PWR_CONFIG2 PIXPAPER_PWR_VGPN_20V /* 0x00: VGP=20V, VGN=-20V */ + +/* Third, Fourth, Sixth Parameters (VSP_1, VSPL_0, VSPL_1) */ +#define PIXPAPER_PWR_VSP_8_2V 0x22 /* VSP_1/VSPL_1: 8.2V (34 decimal) */ +#define PIXPAPER_PWR_VSPL_15V 0x78 /* VSPL_0: 15V (120 decimal) */ + +/* Fifth Parameter (VSN_1) */ +#define PIXPAPER_PWR_VSN_4V 0x0A /* VSN_1: -4V (10 decimal) */ + +/* R03H PFS - Power Off Sequence Setting Register */ +/* First Parameter */ +#define PIXPAPER_PFS_T_VDS_OFF_MASK \ + (3 << 0) /* Bits 1-0: T_VDS_OFF, VSP/VSN power-off sequence */ +#define PIXPAPER_PFS_T_VDS_OFF_20MS (0x0 << 0) /* 00: 20 ms (default) */ +#define PIXPAPER_PFS_T_VDS_OFF_40MS (0x1 << 0) /* 01: 40 ms */ +#define PIXPAPER_PFS_T_VDS_OFF_60MS (0x2 << 0) /* 10: 60 ms */ +#define PIXPAPER_PFS_T_VDS_OFF_80MS (0x3 << 0) /* 11: 80 ms */ +#define PIXPAPER_PFS_T_VDPG_OFF_MASK \ + (3 << 4) /* Bits 5-4: T_VDPG_OFF, VGP/VGN power-off sequence */ +#define PIXPAPER_PFS_T_VDPG_OFF_20MS (0x0 << 4) /* 00: 20 ms (default) */ +#define PIXPAPER_PFS_T_VDPG_OFF_40MS (0x1 << 4) /* 01: 40 ms */ +#define PIXPAPER_PFS_T_VDPG_OFF_60MS (0x2 << 4) /* 10: 60 ms */ +#define PIXPAPER_PFS_T_VDPG_OFF_80MS (0x3 << 4) /* 11: 80 ms */ +#define PIXPAPER_PFS_CONFIG1 \ + (PIXPAPER_PFS_T_VDS_OFF_20MS | \ + PIXPAPER_PFS_T_VDPG_OFF_20MS) /* 0x10: Default 20 ms for VSP/VSN and VGP/VGN */ + +/* Second Parameter */ +#define PIXPAPER_PFS_VGP_EXT_MASK \ + (0xF << 0) /* Bits 3-0: VGP_EXT, VGP extension time */ +#define PIXPAPER_PFS_VGP_EXT_0MS (0x0 << 0) /* 0000: 0 ms */ +#define PIXPAPER_PFS_VGP_EXT_500MS (0x1 << 0) /* 0001: 500 ms */ +#define PIXPAPER_PFS_VGP_EXT_1000MS (0x2 << 0) /* 0010: 1000 ms */ +#define PIXPAPER_PFS_VGP_EXT_1500MS (0x3 << 0) /* 0011: 1500 ms */ +#define PIXPAPER_PFS_VGP_EXT_2000MS (0x4 << 0) /* 0100: 2000 ms (default) */ +#define PIXPAPER_PFS_VGP_EXT_2500MS (0x5 << 0) /* 0101: 2500 ms */ +#define PIXPAPER_PFS_VGP_EXT_3000MS (0x6 << 0) /* 0110: 3000 ms */ +#define PIXPAPER_PFS_VGP_EXT_3500MS (0x7 << 0) /* 0111: 3500 ms */ +#define PIXPAPER_PFS_VGP_EXT_4000MS (0x8 << 0) /* 1000: 4000 ms */ +#define PIXPAPER_PFS_VGP_EXT_4500MS (0x9 << 0) /* 1001: 4500 ms */ +#define PIXPAPER_PFS_VGP_EXT_5000MS (0xA << 0) /* 1010: 5000 ms */ +#define PIXPAPER_PFS_VGP_EXT_5500MS (0xB << 0) /* 1011: 5500 ms */ +#define PIXPAPER_PFS_VGP_EXT_6000MS (0xC << 0) /* 1100: 6000 ms */ +#define PIXPAPER_PFS_VGP_EXT_6500MS (0xD << 0) /* 1101: 6500 ms */ +#define PIXPAPER_PFS_VGP_LEN_MASK \ + (0xF << 4) /* Bits 7-4: VGP_LEN, VGP at 10V during power-off */ +#define PIXPAPER_PFS_VGP_LEN_0MS (0x0 << 4) /* 0000: 0 ms */ +#define PIXPAPER_PFS_VGP_LEN_500MS (0x1 << 4) /* 0001: 500 ms */ +#define PIXPAPER_PFS_VGP_LEN_1000MS (0x2 << 4) /* 0010: 1000 ms */ +#define PIXPAPER_PFS_VGP_LEN_1500MS (0x3 << 4) /* 0011: 1500 ms */ +#define PIXPAPER_PFS_VGP_LEN_2000MS (0x4 << 4) /* 0100: 2000 ms */ +#define PIXPAPER_PFS_VGP_LEN_2500MS (0x5 << 4) /* 0101: 2500 ms (default) */ +#define PIXPAPER_PFS_VGP_LEN_3000MS (0x6 << 4) /* 0110: 3000 ms */ +#define PIXPAPER_PFS_VGP_LEN_3500MS (0x7 << 4) /* 0111: 3500 ms */ +#define PIXPAPER_PFS_VGP_LEN_4000MS (0x8 << 4) /* 1000: 4000 ms */ +#define PIXPAPER_PFS_VGP_LEN_4500MS (0x9 << 4) /* 1001: 4500 ms */ +#define PIXPAPER_PFS_VGP_LEN_5000MS (0xA << 4) /* 1010: 5000 ms */ +#define PIXPAPER_PFS_VGP_LEN_5500MS (0xB << 4) /* 1011: 5500 ms */ +#define PIXPAPER_PFS_VGP_LEN_6000MS (0xC << 4) /* 1100: 6000 ms */ +#define PIXPAPER_PFS_VGP_LEN_6500MS (0xD << 4) /* 1101: 6500 ms */ +#define PIXPAPER_PFS_CONFIG2 \ + (PIXPAPER_PFS_VGP_EXT_1000MS | \ + PIXPAPER_PFS_VGP_LEN_2500MS) /* 0x54: VGP extension 1000 ms, VGP at 10V for 2500 ms */ + +/* Third Parameter */ +#define PIXPAPER_PFS_XON_LEN_MASK \ + (0xF << 0) /* Bits 3-0: XON_LEN, XON enable time */ +#define PIXPAPER_PFS_XON_LEN_0MS (0x0 << 0) /* 0000: 0 ms */ +#define PIXPAPER_PFS_XON_LEN_500MS (0x1 << 0) /* 0001: 500 ms */ +#define PIXPAPER_PFS_XON_LEN_1000MS (0x2 << 0) /* 0010: 1000 ms */ +#define PIXPAPER_PFS_XON_LEN_1500MS (0x3 << 0) /* 0011: 1500 ms */ +#define PIXPAPER_PFS_XON_LEN_2000MS (0x4 << 0) /* 0100: 2000 ms (default) */ +#define PIXPAPER_PFS_XON_LEN_2500MS (0x5 << 0) /* 0101: 2500 ms */ +#define PIXPAPER_PFS_XON_LEN_3000MS (0x6 << 0) /* 0110: 3000 ms */ +#define PIXPAPER_PFS_XON_LEN_3500MS (0x7 << 0) /* 0111: 3500 ms */ +#define PIXPAPER_PFS_XON_LEN_4000MS (0x8 << 0) /* 1000: 4000 ms */ +#define PIXPAPER_PFS_XON_LEN_4500MS (0x9 << 0) /* 1001: 4500 ms */ +#define PIXPAPER_PFS_XON_LEN_5000MS (0xA << 0) /* 1010: 5000 ms */ +#define PIXPAPER_PFS_XON_LEN_5500MS (0xB << 0) /* 1011: 5500 ms */ +#define PIXPAPER_PFS_XON_LEN_6000MS (0xC << 0) /* 1100: 6000 ms */ +#define PIXPAPER_PFS_XON_DLY_MASK \ + (0xF << 4) /* Bits 7-4: XON_DLY, XON delay time */ +#define PIXPAPER_PFS_XON_DLY_0MS (0x0 << 4) /* 0000: 0 ms */ +#define PIXPAPER_PFS_XON_DLY_500MS (0x1 << 4) /* 0001: 500 ms */ +#define PIXPAPER_PFS_XON_DLY_1000MS (0x2 << 4) /* 0010: 1000 ms */ +#define PIXPAPER_PFS_XON_DLY_1500MS (0x3 << 4) /* 0011: 1500 ms */ +#define PIXPAPER_PFS_XON_DLY_2000MS (0x4 << 4) /* 0100: 2000 ms (default) */ +#define PIXPAPER_PFS_XON_DLY_2500MS (0x5 << 4) /* 0101: 2500 ms */ +#define PIXPAPER_PFS_XON_DLY_3000MS (0x6 << 4) /* 0110: 3000 ms */ +#define PIXPAPER_PFS_XON_DLY_3500MS (0x7 << 4) /* 0111: 3500 ms */ +#define PIXPAPER_PFS_XON_DLY_4000MS (0x8 << 4) /* 1000: 4000 ms */ +#define PIXPAPER_PFS_XON_DLY_4500MS (0x9 << 4) /* 1001: 4500 ms */ +#define PIXPAPER_PFS_XON_DLY_5000MS (0xA << 4) /* 1010: 5000 ms */ +#define PIXPAPER_PFS_XON_DLY_5500MS (0xB << 4) /* 1011: 5500 ms */ +#define PIXPAPER_PFS_XON_DLY_6000MS (0xC << 4) /* 1100: 6000 ms */ +#define PIXPAPER_PFS_CONFIG3 \ + (PIXPAPER_PFS_XON_LEN_2000MS | \ + PIXPAPER_PFS_XON_DLY_2000MS) /* 0x44: XON enable and delay at 2000 ms */ + +/* R06H BTST - Booster Soft Start Command */ +/* First Parameter */ +#define PIXPAPER_BTST_PHA_SFT_MASK \ + (3 << 0) /* Bits 1-0: PHA_SFT, soft start period for phase A */ +#define PIXPAPER_BTST_PHA_SFT_10MS (0x0 << 0) /* 00: 10 ms (default) */ +#define PIXPAPER_BTST_PHA_SFT_20MS (0x1 << 0) /* 01: 20 ms */ +#define PIXPAPER_BTST_PHA_SFT_30MS (0x2 << 0) /* 10: 30 ms */ +#define PIXPAPER_BTST_PHA_SFT_40MS (0x3 << 0) /* 11: 40 ms */ +#define PIXPAPER_BTST_PHB_SFT_MASK \ + (3 << 2) /* Bits 3-2: PHB_SFT, soft start period for phase B */ +#define PIXPAPER_BTST_PHB_SFT_10MS (0x0 << 2) /* 00: 10 ms (default) */ +#define PIXPAPER_BTST_PHB_SFT_20MS (0x1 << 2) /* 01: 20 ms */ +#define PIXPAPER_BTST_PHB_SFT_30MS (0x2 << 2) /* 10: 30 ms */ +#define PIXPAPER_BTST_PHB_SFT_40MS (0x3 << 2) /* 11: 40 ms */ +#define PIXPAPER_BTST_CONFIG1 \ + (PIXPAPER_BTST_PHA_SFT_40MS | \ + PIXPAPER_BTST_PHB_SFT_40MS) /* 0x0F: 40 ms for phase A and B */ + +/* Second to Seventh Parameters (Driving Strength or Minimum OFF Time) */ +#define PIXPAPER_BTST_CONFIG2 0x0A /* Strength11 */ +#define PIXPAPER_BTST_CONFIG3 0x2F /* Period48 */ +#define PIXPAPER_BTST_CONFIG4 0x25 /* Strength38 */ +#define PIXPAPER_BTST_CONFIG5 0x22 /* Period35 */ +#define PIXPAPER_BTST_CONFIG6 0x2E /* Strength47 */ +#define PIXPAPER_BTST_CONFIG7 0x21 /* Period34 */ + +/* R12H: DRF (Display Refresh) */ +#define PIXPAPER_DRF_VCOM_AC 0x00 /* AC VCOM: VCOM follows LUTC (default) */ +#define PIXPAPER_DRF_VCOM_DC 0x01 /* DC VCOM: VCOM fixed to VCOMDC */ + +/* R30H PLL - PLL Control Register */ +/* First Parameter */ +#define PIXPAPER_PLL_FR_MASK (0x7 << 0) /* Bits 2-0: FR, frame rate */ +#define PIXPAPER_PLL_FR_12_5HZ (0x0 << 0) /* 000: 12.5 Hz */ +#define PIXPAPER_PLL_FR_25HZ (0x1 << 0) /* 001: 25 Hz */ +#define PIXPAPER_PLL_FR_50HZ (0x2 << 0) /* 010: 50 Hz (default) */ +#define PIXPAPER_PLL_FR_65HZ (0x3 << 0) /* 011: 65 Hz */ +#define PIXPAPER_PLL_FR_75HZ (0x4 << 0) /* 100: 75 Hz */ +#define PIXPAPER_PLL_FR_85HZ (0x5 << 0) /* 101: 85 Hz */ +#define PIXPAPER_PLL_FR_100HZ (0x6 << 0) /* 110: 100 Hz */ +#define PIXPAPER_PLL_FR_120HZ (0x7 << 0) /* 111: 120 Hz */ +#define PIXPAPER_PLL_DFR \ + (1 << 3) /* Bit 3: Dynamic frame rate, 0=disabled (default), 1=enabled */ +#define PIXPAPER_PLL_CONFIG \ + (PIXPAPER_PLL_FR_50HZ) /* 0x02: 50 Hz, dynamic frame rate disabled */ + +/* R41H TSE - Temperature Sensor Calibration Register */ +/* First Parameter */ +#define PIXPAPER_TSE_TO_MASK \ + (0xF << 0) /* Bits 3-0: TO[3:0], temperature offset */ +#define PIXPAPER_TSE_TO_POS_0C (0x0 << 0) /* 0000: +0°C (default) */ +#define PIXPAPER_TSE_TO_POS_0_5C (0x1 << 0) /* 0001: +0.5°C */ +#define PIXPAPER_TSE_TO_POS_1C (0x2 << 0) /* 0010: +1°C */ +#define PIXPAPER_TSE_TO_POS_1_5C (0x3 << 0) /* 0011: +1.5°C */ +#define PIXPAPER_TSE_TO_POS_2C (0x4 << 0) /* 0100: +2°C */ +#define PIXPAPER_TSE_TO_POS_2_5C (0x5 << 0) /* 0101: +2.5°C */ +#define PIXPAPER_TSE_TO_POS_3C (0x6 << 0) /* 0110: +3°C */ +#define PIXPAPER_TSE_TO_POS_3_5C (0x7 << 0) /* 0111: +3.5°C */ +#define PIXPAPER_TSE_TO_NEG_4C (0x8 << 0) /* 1000: -4°C */ +#define PIXPAPER_TSE_TO_NEG_3_5C (0x9 << 0) /* 1001: -3.5°C */ +#define PIXPAPER_TSE_TO_NEG_3C (0xA << 0) /* 1010: -3°C */ +#define PIXPAPER_TSE_TO_NEG_2_5C (0xB << 0) /* 1011: -2.5°C */ +#define PIXPAPER_TSE_TO_NEG_2C (0xC << 0) /* 1100: -2°C */ +#define PIXPAPER_TSE_TO_NEG_1_5C (0xD << 0) /* 1101: -1.5°C */ +#define PIXPAPER_TSE_TO_NEG_1C (0xE << 0) /* 1110: -1°C */ +#define PIXPAPER_TSE_TO_NEG_0_5C (0xF << 0) /* 1111: -0.5°C */ +#define PIXPAPER_TSE_TO_FINE_MASK \ + (0x3 << 4) /* Bits 5-4: TO[5:4], fine adjustment for positive offsets */ +#define PIXPAPER_TSE_TO_FINE_0C (0x0 << 4) /* 00: +0.0°C (default) */ +#define PIXPAPER_TSE_TO_FINE_0_25C (0x1 << 4) /* 01: +0.25°C */ +#define PIXPAPER_TSE_ENABLE \ + (0 << 7) /* Bit 7: TSE, 0=internal sensor enabled (default), 1=disabled (external) */ +#define PIXPAPER_TSE_DISABLE \ + (1 << 7) /* Bit 7: TSE, 1=internal sensor disabled, use external */ +#define PIXPAPER_TSE_CONFIG \ + (PIXPAPER_TSE_TO_POS_0C | PIXPAPER_TSE_TO_FINE_0C | \ + PIXPAPER_TSE_ENABLE) /* 0x00: Internal sensor enabled, +0°C offset */ + +/* R4DH */ +#define PIXPAPER_UNKNOWN_4D_CONFIG \ + 0x78 /* This value is essential for initialization, derived from userspace examples. */ + +/* R50H CDI - VCOM and DATA Interval Setting Register */ +/* First Parameter */ +#define PIXPAPER_CDI_INTERVAL_MASK \ + (0xF << 0) /* Bits 3-0: CDI[3:0], VCOM and data interval (hsync) */ +#define PIXPAPER_CDI_17_HSYNC (0x0 << 0) /* 0000: 17 hsync */ +#define PIXPAPER_CDI_16_HSYNC (0x1 << 0) /* 0001: 16 hsync */ +#define PIXPAPER_CDI_15_HSYNC (0x2 << 0) /* 0010: 15 hsync */ +#define PIXPAPER_CDI_14_HSYNC (0x3 << 0) /* 0011: 14 hsync */ +#define PIXPAPER_CDI_13_HSYNC (0x4 << 0) /* 0100: 13 hsync */ +#define PIXPAPER_CDI_12_HSYNC (0x5 << 0) /* 0101: 12 hsync */ +#define PIXPAPER_CDI_11_HSYNC (0x6 << 0) /* 0110: 11 hsync */ +#define PIXPAPER_CDI_10_HSYNC (0x7 << 0) /* 0111: 10 hsync (default) */ +#define PIXPAPER_CDI_9_HSYNC (0x8 << 0) /* 1000: 9 hsync */ +#define PIXPAPER_CDI_8_HSYNC (0x9 << 0) /* 1001: 8 hsync */ +#define PIXPAPER_CDI_7_HSYNC (0xA << 0) /* 1010: 7 hsync */ +#define PIXPAPER_CDI_6_HSYNC (0xB << 0) /* 1011: 6 hsync */ +#define PIXPAPER_CDI_5_HSYNC (0xC << 0) /* 1100: 5 hsync */ +#define PIXPAPER_CDI_4_HSYNC (0xD << 0) /* 1101: 4 hsync */ +#define PIXPAPER_CDI_3_HSYNC (0xE << 0) /* 1110: 3 hsync */ +#define PIXPAPER_CDI_2_HSYNC (0xF << 0) /* 1111: 2 hsync */ +#define PIXPAPER_CDI_DDX \ + (1 << 4) /* Bit 4: DDX, 0=grayscale mapping 0, 1=grayscale mapping 1 (default) */ +#define PIXPAPER_CDI_VBD_MASK \ + (0x7 << 5) /* Bits 7-5: VBD[2:0], border data selection */ +#define PIXPAPER_CDI_VBD_FLOAT (0x0 << 5) /* 000: Floating (DDX=0 or 1) */ +#define PIXPAPER_CDI_VBD_GRAY3_DDX0 \ + (0x1 << 5) /* 001: Gray3 (border_buf=011) when DDX=0 */ +#define PIXPAPER_CDI_VBD_GRAY2_DDX0 \ + (0x2 << 5) /* 010: Gray2 (border_buf=010) when DDX=0 */ +#define PIXPAPER_CDI_VBD_GRAY1_DDX0 \ + (0x3 << 5) /* 011: Gray1 (border_buf=001) when DDX=0 */ +#define PIXPAPER_CDI_VBD_GRAY0_DDX0 \ + (0x4 << 5) /* 100: Gray0 (border_buf=000) when DDX=0 */ +#define PIXPAPER_CDI_VBD_GRAY0_DDX1 \ + (0x0 << 5) /* 000: Gray0 (border_buf=000) when DDX=1 */ +#define PIXPAPER_CDI_VBD_GRAY1_DDX1 \ + (0x1 << 5) /* 001: Gray1 (border_buf=001) when DDX=1 */ +#define PIXPAPER_CDI_VBD_GRAY2_DDX1 \ + (0x2 << 5) /* 010: Gray2 (border_buf=010) when DDX=1 */ +#define PIXPAPER_CDI_VBD_GRAY3_DDX1 \ + (0x3 << 5) /* 011: Gray3 (border_buf=011) when DDX=1 */ +#define PIXPAPER_CDI_VBD_FLOAT_DDX1 (0x4 << 5) /* 100: Floating when DDX=1 */ +#define PIXPAPER_CDI_CONFIG \ + (PIXPAPER_CDI_10_HSYNC | PIXPAPER_CDI_DDX | \ + PIXPAPER_CDI_VBD_GRAY1_DDX1) /* 0x37: 10 hsync, DDX=1, border Gray1 */ + +/* R60H */ +#define PIXPAPER_UNKNOWN_60_CONFIG1 \ + 0x02 /* This value is essential for initialization, derived from userspace examples. */ +#define PIXPAPER_UNKNOWN_60_CONFIG2 \ + 0x02 /* This value is essential for initialization, derived from userspace examples. */ + +/* R61H TRES - Resolution Setting Register */ +#define PIXPAPER_TRES_HRES_H \ + ((PIXPAPER_PANEL_BUFFER_WIDTH >> 8) & \ + 0xFF) /* HRES[9:8]: High byte of horizontal resolution (128) */ +#define PIXPAPER_TRES_HRES_L \ + (PIXPAPER_PANEL_BUFFER_WIDTH & \ + 0xFF) /* HRES[7:0]: Low byte of horizontal resolution (128 = 0x80) */ +#define PIXPAPER_TRES_VRES_H \ + ((PIXPAPER_HEIGHT >> 8) & \ + 0xFF) /* VRES[9:8]: High byte of vertical resolution (250) */ +#define PIXPAPER_TRES_VRES_L \ + (PIXPAPER_HEIGHT & \ + 0xFF) /* VRES[7:0]: Low byte of vertical resolution (250 = 0xFA) */ + +/* R65H GSST - Gate/Source Start Setting Register */ +#define PIXPAPER_GSST_S_START 0x00 /* S_Start[7:0]: First source line (S0) */ +#define PIXPAPER_GSST_RESERVED 0x00 /* Reserved byte */ +#define PIXPAPER_GSST_G_START_H \ + 0x00 /* G_Start[8]: High bit of first gate line (G0) */ +#define PIXPAPER_GSST_G_START_L \ + 0x00 /* G_Start[7:0]: Low byte of first gate line (G0) */ + +/* RB4H */ +#define PIXPAPER_UNKNOWN_B4_CONFIG \ + 0xD0 /* This value is essential for initialization, derived from userspace examples. */ + +/* RB5H */ +#define PIXPAPER_UNKNOWN_B5_CONFIG \ + 0x03 /* This value is essential for initialization, derived from userspace examples. */ + +/* RE0H */ +#define PIXPAPER_UNKNOWN_E0_CONFIG \ + 0x00 /* This value is essential for initialization, derived from userspace examples. */ + +/* RE3H PWS - Power Saving Register */ +/* First Parameter */ +#define PIXPAPER_PWS_VCOM_W_MASK \ + (0xF \ + << 4) /* Bits 7-4: VCOM_W[3:0], VCOM power-saving width (line periods) */ +#define PIXPAPER_PWS_VCOM_W_0 (0x0 << 4) /* 0000: 0 line periods */ +#define PIXPAPER_PWS_VCOM_W_1 (0x1 << 4) /* 0001: 1 line period */ +#define PIXPAPER_PWS_VCOM_W_2 (0x2 << 4) /* 0010: 2 line periods */ +#define PIXPAPER_PWS_VCOM_W_3 (0x3 << 4) /* 0011: 3 line periods */ +#define PIXPAPER_PWS_VCOM_W_4 (0x4 << 4) /* 0100: 4 line periods */ +#define PIXPAPER_PWS_VCOM_W_5 (0x5 << 4) /* 0101: 5 line periods */ +#define PIXPAPER_PWS_VCOM_W_6 (0x6 << 4) /* 0110: 6 line periods */ +#define PIXPAPER_PWS_VCOM_W_7 (0x7 << 4) /* 0111: 7 line periods */ +#define PIXPAPER_PWS_VCOM_W_8 (0x8 << 4) /* 1000: 8 line periods */ +#define PIXPAPER_PWS_VCOM_W_9 (0x9 << 4) /* 1001: 9 line periods */ +#define PIXPAPER_PWS_VCOM_W_10 (0xA << 4) /* 1010: 10 line periods */ +#define PIXPAPER_PWS_VCOM_W_11 (0xB << 4) /* 1011: 11 line periods */ +#define PIXPAPER_PWS_VCOM_W_12 (0xC << 4) /* 1100: 12 line periods */ +#define PIXPAPER_PWS_VCOM_W_13 (0xD << 4) /* 1101: 13 line periods */ +#define PIXPAPER_PWS_VCOM_W_14 (0xE << 4) /* 1110: 14 line periods */ +#define PIXPAPER_PWS_VCOM_W_15 (0xF << 4) /* 1111: 15 line periods */ +#define PIXPAPER_PWS_SD_W_MASK \ + (0xF << 0) /* Bits 3-0: SD_W[3:0], source power-saving width (660 ns units) */ +#define PIXPAPER_PWS_SD_W_0 (0x0 << 0) /* 0000: 0 ns */ +#define PIXPAPER_PWS_SD_W_1 (0x1 << 0) /* 0001: 660 ns */ +#define PIXPAPER_PWS_SD_W_2 (0x2 << 0) /* 0010: 1320 ns */ +#define PIXPAPER_PWS_SD_W_3 (0x3 << 0) /* 0011: 1980 ns */ +#define PIXPAPER_PWS_SD_W_4 (0x4 << 0) /* 0100: 2640 ns */ +#define PIXPAPER_PWS_SD_W_5 (0x5 << 0) /* 0101: 3300 ns */ +#define PIXPAPER_PWS_SD_W_6 (0x6 << 0) /* 0110: 3960 ns */ +#define PIXPAPER_PWS_SD_W_7 (0x7 << 0) /* 0111: 4620 ns */ +#define PIXPAPER_PWS_SD_W_8 (0x8 << 0) /* 1000: 5280 ns */ +#define PIXPAPER_PWS_SD_W_9 (0x9 << 0) /* 1001: 5940 ns */ +#define PIXPAPER_PWS_SD_W_10 (0xA << 0) /* 1010: 6600 ns */ +#define PIXPAPER_PWS_SD_W_11 (0xB << 0) /* 1011: 7260 ns */ +#define PIXPAPER_PWS_SD_W_12 (0xC << 0) /* 1100: 7920 ns */ +#define PIXPAPER_PWS_SD_W_13 (0xD << 0) /* 1101: 8580 ns */ +#define PIXPAPER_PWS_SD_W_14 (0xE << 0) /* 1110: 9240 ns */ +#define PIXPAPER_PWS_SD_W_15 (0xF << 0) /* 1111: 9900 ns */ +#define PIXPAPER_PWS_CONFIG \ + (PIXPAPER_PWS_VCOM_W_2 | \ + PIXPAPER_PWS_SD_W_2) /* 0x22: VCOM 2 line periods (160 µs), source 1320 ns */ + +/* RE7H */ +#define PIXPAPER_UNKNOWN_E7_CONFIG \ + 0x1C /* This value is essential for initialization, derived from userspace examples. */ + +/* RE9H */ +#define PIXPAPER_UNKNOWN_E9_CONFIG \ + 0x01 /* This value is essential for initialization, derived from userspace examples. */ + +MODULE_IMPORT_NS("DMA_BUF"); + +/* + * The panel has a visible resolution of 122x250. + * However, the controller requires the horizontal resolution to be aligned to 128 pixels. + * No porch or sync timing values are provided in the datasheet, so we define minimal + * placeholder values to satisfy the DRM framework. + */ + +/* Panel visible resolution */ +#define PIXPAPER_WIDTH 122 +#define PIXPAPER_HEIGHT 250 + +/* Controller requires 128 horizontal pixels total (for memory alignment) */ +#define PIXPAPER_HTOTAL 128 +#define PIXPAPER_HFP 2 +#define PIXPAPER_HSYNC 2 +#define PIXPAPER_HBP (PIXPAPER_HTOTAL - PIXPAPER_WIDTH - PIXPAPER_HFP - PIXPAPER_HSYNC) + +/* + * According to the datasheet, the total vertical blanking must be 55 lines, + * regardless of how the vertical back porch is set. + * Here we allocate VFP=2, VSYNC=2, and VBP=51 to sum up to 55 lines. + * Total vertical lines = 250 (visible) + 55 (blanking) = 305. + */ +#define PIXPAPER_VTOTAL (250 + 55) +#define PIXPAPER_VFP 2 +#define PIXPAPER_VSYNC 2 +#define PIXPAPER_VBP (55 - PIXPAPER_VFP - PIXPAPER_VSYNC) + +/* + * Pixel clock calculation: + * pixel_clock = htotal * vtotal * refresh_rate + * = 128 * 305 * 50 + * = 1,952,000 Hz = 1952 kHz + */ +#define PIXPAPER_PIXEL_CLOCK 1952 + +#define PIXPAPER_WIDTH_MM 24 /* approximate from 23.7046mm */ +#define PIXPAPER_HEIGHT_MM 49 /* approximate from 48.55mm */ + +#define PIXPAPER_SPI_BITS_PER_WORD 8 +#define PIXPAPER_SPI_SPEED_DEFAULT 1000000 + +#define PIXPAPER_PANEL_BUFFER_WIDTH 128 +#define PIXPAPER_PANEL_BUFFER_TWO_BYTES_PER_ROW (PIXPAPER_PANEL_BUFFER_WIDTH / 4) + +#define PIXPAPER_COLOR_THRESHOLD_LOW_CHANNEL 60 +#define PIXPAPER_COLOR_THRESHOLD_HIGH_CHANNEL 200 +#define PIXPAPER_COLOR_THRESHOLD_YELLOW_MIN_GREEN 180 + +struct pixpaper_error_ctx { + int errno_code; +}; + +struct pixpaper_panel { + struct drm_device drm; + struct drm_plane plane; + struct drm_crtc crtc; + struct drm_encoder encoder; + struct drm_connector connector; + + struct spi_device *spi; + struct gpio_desc *reset; + struct gpio_desc *busy; + struct gpio_desc *dc; +}; + +static inline struct pixpaper_panel *to_pixpaper_panel(struct drm_device *drm) +{ + return container_of(drm, struct pixpaper_panel, drm); +} + +static void pixpaper_wait_for_panel(struct pixpaper_panel *panel) +{ + unsigned int timeout_ms = 10000; + unsigned long timeout_jiffies = jiffies + msecs_to_jiffies(timeout_ms); + + usleep_range(1000, 1500); + while (gpiod_get_value_cansleep(panel->busy) != 1) { + if (time_after(jiffies, timeout_jiffies)) { + drm_warn(&panel->drm, "Busy wait timed out\n"); + return; + } + usleep_range(100, 200); + } +} + +static void pixpaper_spi_sync(struct spi_device *spi, struct spi_message *msg, + struct pixpaper_error_ctx *err) +{ + if (err->errno_code) + return; + + int ret = spi_sync(spi, msg); + + if (ret < 0) + err->errno_code = ret; +} + +static void pixpaper_send_cmd(struct pixpaper_panel *panel, u8 cmd, + struct pixpaper_error_ctx *err) +{ + if (err->errno_code) + return; + + struct spi_transfer xfer = { + .tx_buf = &cmd, + .len = 1, + }; + struct spi_message msg; + + spi_message_init(&msg); + spi_message_add_tail(&xfer, &msg); + + gpiod_set_value_cansleep(panel->dc, 0); + usleep_range(1, 5); + pixpaper_spi_sync(panel->spi, &msg, err); +} + +static void pixpaper_send_data(struct pixpaper_panel *panel, u8 data, + struct pixpaper_error_ctx *err) +{ + if (err->errno_code) + return; + + struct spi_transfer xfer = { + .tx_buf = &data, + .len = 1, + }; + struct spi_message msg; + + spi_message_init(&msg); + spi_message_add_tail(&xfer, &msg); + + gpiod_set_value_cansleep(panel->dc, 1); + usleep_range(1, 5); + pixpaper_spi_sync(panel->spi, &msg, err); +} + +static int pixpaper_panel_hw_init(struct pixpaper_panel *panel) +{ + struct pixpaper_error_ctx err = { .errno_code = 0 }; + + gpiod_set_value_cansleep(panel->reset, 0); + msleep(50); + gpiod_set_value_cansleep(panel->reset, 1); + msleep(50); + + pixpaper_wait_for_panel(panel); + + pixpaper_send_cmd(panel, PIXPAPER_CMD_UNKNOWN_4D, &err); + pixpaper_send_data(panel, PIXPAPER_UNKNOWN_4D_CONFIG, &err); + if (err.errno_code) + goto init_fail; + pixpaper_wait_for_panel(panel); + + pixpaper_send_cmd(panel, PIXPAPER_CMD_PANEL_SETTING, &err); + pixpaper_send_data(panel, PIXPAPER_PSR_CONFIG, &err); + pixpaper_send_data(panel, PIXPAPER_PSR_CONFIG2, &err); + if (err.errno_code) + goto init_fail; + pixpaper_wait_for_panel(panel); + + pixpaper_send_cmd(panel, PIXPAPER_CMD_POWER_SETTING, &err); + pixpaper_send_data(panel, PIXPAPER_PWR_CONFIG1, &err); + pixpaper_send_data(panel, PIXPAPER_PWR_CONFIG2, &err); + pixpaper_send_data(panel, PIXPAPER_PWR_VSP_8_2V, &err); + pixpaper_send_data(panel, PIXPAPER_PWR_VSPL_15V, &err); + pixpaper_send_data(panel, PIXPAPER_PWR_VSN_4V, &err); + pixpaper_send_data(panel, PIXPAPER_PWR_VSP_8_2V, &err); + if (err.errno_code) + goto init_fail; + pixpaper_wait_for_panel(panel); + + pixpaper_send_cmd(panel, PIXPAPER_CMD_POWER_OFF_SEQUENCE, &err); + pixpaper_send_data(panel, PIXPAPER_PFS_CONFIG1, &err); + pixpaper_send_data(panel, PIXPAPER_PFS_CONFIG2, &err); + pixpaper_send_data(panel, PIXPAPER_PFS_CONFIG3, &err); + if (err.errno_code) + goto init_fail; + pixpaper_wait_for_panel(panel); + + pixpaper_send_cmd(panel, PIXPAPER_CMD_BOOSTER_SOFT_START, &err); + pixpaper_send_data(panel, PIXPAPER_BTST_CONFIG1, &err); + pixpaper_send_data(panel, PIXPAPER_BTST_CONFIG2, &err); + pixpaper_send_data(panel, PIXPAPER_BTST_CONFIG3, &err); + pixpaper_send_data(panel, PIXPAPER_BTST_CONFIG4, &err); + pixpaper_send_data(panel, PIXPAPER_BTST_CONFIG5, &err); + pixpaper_send_data(panel, PIXPAPER_BTST_CONFIG6, &err); + pixpaper_send_data(panel, PIXPAPER_BTST_CONFIG7, &err); + if (err.errno_code) + goto init_fail; + pixpaper_wait_for_panel(panel); + + pixpaper_send_cmd(panel, PIXPAPER_CMD_PLL_CONTROL, &err); + pixpaper_send_data(panel, PIXPAPER_PLL_CONFIG, &err); + if (err.errno_code) + goto init_fail; + pixpaper_wait_for_panel(panel); + + pixpaper_send_cmd(panel, PIXPAPER_CMD_TEMP_SENSOR_CALIB, &err); + pixpaper_send_data(panel, PIXPAPER_TSE_CONFIG, &err); + if (err.errno_code) + goto init_fail; + pixpaper_wait_for_panel(panel); + + pixpaper_send_cmd(panel, PIXPAPER_CMD_VCOM_INTERVAL, &err); + pixpaper_send_data(panel, PIXPAPER_CDI_CONFIG, &err); + if (err.errno_code) + goto init_fail; + pixpaper_wait_for_panel(panel); + + pixpaper_send_cmd(panel, PIXPAPER_CMD_UNKNOWN_60, &err); + pixpaper_send_data(panel, PIXPAPER_UNKNOWN_60_CONFIG1, &err); + pixpaper_send_data(panel, PIXPAPER_UNKNOWN_60_CONFIG2, &err); + if (err.errno_code) + goto init_fail; + pixpaper_wait_for_panel(panel); + + pixpaper_send_cmd(panel, PIXPAPER_CMD_RESOLUTION_SETTING, &err); + pixpaper_send_data(panel, PIXPAPER_TRES_HRES_H, &err); + pixpaper_send_data(panel, PIXPAPER_TRES_HRES_L, &err); + pixpaper_send_data(panel, PIXPAPER_TRES_VRES_H, &err); + pixpaper_send_data(panel, PIXPAPER_TRES_VRES_L, &err); + if (err.errno_code) + goto init_fail; + pixpaper_wait_for_panel(panel); + + pixpaper_send_cmd(panel, PIXPAPER_CMD_GATE_SOURCE_START, &err); + pixpaper_send_data(panel, PIXPAPER_GSST_S_START, &err); + pixpaper_send_data(panel, PIXPAPER_GSST_RESERVED, &err); + pixpaper_send_data(panel, PIXPAPER_GSST_G_START_H, &err); + pixpaper_send_data(panel, PIXPAPER_GSST_G_START_L, &err); + if (err.errno_code) + goto init_fail; + pixpaper_wait_for_panel(panel); + + pixpaper_send_cmd(panel, PIXPAPER_CMD_UNKNOWN_E7, &err); + pixpaper_send_data(panel, PIXPAPER_UNKNOWN_E7_CONFIG, &err); + if (err.errno_code) + goto init_fail; + pixpaper_wait_for_panel(panel); + + pixpaper_send_cmd(panel, PIXPAPER_CMD_POWER_SAVING, &err); + pixpaper_send_data(panel, PIXPAPER_PWS_CONFIG, &err); + if (err.errno_code) + goto init_fail; + pixpaper_wait_for_panel(panel); + + pixpaper_send_cmd(panel, PIXPAPER_CMD_UNKNOWN_E0, &err); + pixpaper_send_data(panel, PIXPAPER_UNKNOWN_E0_CONFIG, &err); + if (err.errno_code) + goto init_fail; + pixpaper_wait_for_panel(panel); + + pixpaper_send_cmd(panel, PIXPAPER_CMD_UNKNOWN_B4, &err); + pixpaper_send_data(panel, PIXPAPER_UNKNOWN_B4_CONFIG, &err); + if (err.errno_code) + goto init_fail; + pixpaper_wait_for_panel(panel); + + pixpaper_send_cmd(panel, PIXPAPER_CMD_UNKNOWN_B5, &err); + pixpaper_send_data(panel, PIXPAPER_UNKNOWN_B5_CONFIG, &err); + if (err.errno_code) + goto init_fail; + pixpaper_wait_for_panel(panel); + + pixpaper_send_cmd(panel, PIXPAPER_CMD_UNKNOWN_E9, &err); + pixpaper_send_data(panel, PIXPAPER_UNKNOWN_E9_CONFIG, &err); + if (err.errno_code) + goto init_fail; + pixpaper_wait_for_panel(panel); + + return 0; + +init_fail: + drm_err(&panel->drm, "Hardware initialization failed (err=%d)\n", + err.errno_code); + return err.errno_code; +} + +/* + * Convert framebuffer pixels to 2-bit e-paper format: + * 00 - White + * 01 - Black + * 10 - Yellow + * 11 - Red + */ +static u8 pack_pixels_to_byte(__le32 *src_pixels, int i, int j, + struct drm_framebuffer *fb) +{ + u8 packed_byte = 0; + int k; + + for (k = 0; k < 4; k++) { + int current_pixel_x = j * 4 + k; + u8 two_bit_val; + + if (current_pixel_x < PIXPAPER_WIDTH) { + u32 pixel_offset = + (i * (fb->pitches[0] / 4)) + current_pixel_x; + u32 pixel = le32_to_cpu(src_pixels[pixel_offset]); + u32 r = (pixel >> 16) & 0xFF; + u32 g = (pixel >> 8) & 0xFF; + u32 b = pixel & 0xFF; + + if (r < PIXPAPER_COLOR_THRESHOLD_LOW_CHANNEL && + g < PIXPAPER_COLOR_THRESHOLD_LOW_CHANNEL && + b < PIXPAPER_COLOR_THRESHOLD_LOW_CHANNEL) { + two_bit_val = 0b00; + } else if (r > PIXPAPER_COLOR_THRESHOLD_HIGH_CHANNEL && + g > PIXPAPER_COLOR_THRESHOLD_HIGH_CHANNEL && + b > PIXPAPER_COLOR_THRESHOLD_HIGH_CHANNEL) { + two_bit_val = 0b01; + } else if (r > PIXPAPER_COLOR_THRESHOLD_HIGH_CHANNEL && + g < PIXPAPER_COLOR_THRESHOLD_LOW_CHANNEL && + b < PIXPAPER_COLOR_THRESHOLD_LOW_CHANNEL) { + two_bit_val = 0b11; + } else if (r > PIXPAPER_COLOR_THRESHOLD_HIGH_CHANNEL && + g > PIXPAPER_COLOR_THRESHOLD_YELLOW_MIN_GREEN && + b < PIXPAPER_COLOR_THRESHOLD_LOW_CHANNEL) { + two_bit_val = 0b10; + } else { + two_bit_val = 0b01; + } + } else { + two_bit_val = 0b01; + } + + packed_byte |= two_bit_val << ((3 - k) * 2); + } + + return packed_byte; +} + +static int pixpaper_plane_helper_atomic_check(struct drm_plane *plane, + struct drm_atomic_state *state) +{ + struct drm_plane_state *new_plane_state = + drm_atomic_get_new_plane_state(state, plane); + struct drm_crtc *new_crtc = new_plane_state->crtc; + struct drm_crtc_state *new_crtc_state = NULL; + int ret; + + if (new_crtc) + new_crtc_state = drm_atomic_get_new_crtc_state(state, new_crtc); + + ret = drm_atomic_helper_check_plane_state(new_plane_state, + new_crtc_state, DRM_PLANE_NO_SCALING, + DRM_PLANE_NO_SCALING, false, false); + if (ret) + return ret; + else if (!new_plane_state->visible) + return 0; + + return 0; +} + +static int pixpaper_crtc_helper_atomic_check(struct drm_crtc *crtc, + struct drm_atomic_state *state) +{ + struct drm_crtc_state *crtc_state = + drm_atomic_get_new_crtc_state(state, crtc); + + if (!crtc_state->enable) + return 0; + + return drm_atomic_helper_check_crtc_primary_plane(crtc_state); +} + +static void pixpaper_crtc_atomic_enable(struct drm_crtc *crtc, + struct drm_atomic_state *state) +{ + struct pixpaper_panel *panel = to_pixpaper_panel(crtc->dev); + struct drm_device *drm = &panel->drm; + int idx; + struct pixpaper_error_ctx err = { .errno_code = 0 }; + + if (!drm_dev_enter(drm, &idx)) + return; + + pixpaper_send_cmd(panel, PIXPAPER_CMD_POWER_ON, &err); + if (err.errno_code) { + drm_err_once(drm, "Failed to send PON command: %d\n", err.errno_code); + goto exit_drm_dev; + } + + pixpaper_wait_for_panel(panel); + + drm_dbg(drm, "Panel enabled and powered on\n"); + +exit_drm_dev: + drm_dev_exit(idx); +} + +static void pixpaper_crtc_atomic_disable(struct drm_crtc *crtc, + struct drm_atomic_state *state) +{ + struct pixpaper_panel *panel = to_pixpaper_panel(crtc->dev); + struct drm_device *drm = &panel->drm; + struct pixpaper_error_ctx err = { .errno_code = 0 }; + int idx; + + if (!drm_dev_enter(drm, &idx)) + return; + + pixpaper_send_cmd(panel, PIXPAPER_CMD_POWER_OFF, &err); + if (err.errno_code) { + drm_err_once(drm, "Failed to send POF command: %d\n", err.errno_code); + goto exit_drm_dev; + } + pixpaper_wait_for_panel(panel); + + drm_dbg(drm, "Panel disabled\n"); + +exit_drm_dev: + drm_dev_exit(idx); +} + +static void pixpaper_plane_atomic_update(struct drm_plane *plane, + struct drm_atomic_state *state) +{ + struct drm_plane_state *plane_state = + drm_atomic_get_new_plane_state(state, plane); + struct drm_shadow_plane_state *shadow_plane_state = + to_drm_shadow_plane_state(plane_state); + struct drm_crtc *crtc = plane_state->crtc; + struct pixpaper_panel *panel = to_pixpaper_panel(crtc->dev); + + struct drm_device *drm = &panel->drm; + struct drm_framebuffer *fb = plane_state->fb; + struct iosys_map map = shadow_plane_state->data[0]; + void *vaddr = map.vaddr; + int i, j, idx; + __le32 *src_pixels = NULL; + struct pixpaper_error_ctx err = { .errno_code = 0 }; + + if (!drm_dev_enter(drm, &idx)) + return; + + drm_dbg(drm, "Starting frame update (phys=%dx%d, buf_w=%d)\n", + PIXPAPER_WIDTH, PIXPAPER_HEIGHT, PIXPAPER_PANEL_BUFFER_WIDTH); + + if (!fb || !plane_state->visible) { + drm_err_once(drm, "No framebuffer or plane not visible, skipping update\n"); + goto update_cleanup; + } + + src_pixels = (__le32 *)vaddr; + + pixpaper_send_cmd(panel, PIXPAPER_CMD_DATA_START_TRANSMISSION, &err); + if (err.errno_code) + goto update_cleanup; + + pixpaper_wait_for_panel(panel); + + for (i = 0; i < PIXPAPER_HEIGHT; i++) { + for (j = 0; j < PIXPAPER_PANEL_BUFFER_TWO_BYTES_PER_ROW; j++) { + u8 packed_byte = + pack_pixels_to_byte(src_pixels, i, j, fb); + + pixpaper_wait_for_panel(panel); + pixpaper_send_data(panel, packed_byte, &err); + } + } + pixpaper_wait_for_panel(panel); + + pixpaper_send_cmd(panel, PIXPAPER_CMD_POWER_ON, &err); + if (err.errno_code) { + drm_err_once(drm, "Failed to send PON command: %d\n", err.errno_code); + goto update_cleanup; + } + pixpaper_wait_for_panel(panel); + + pixpaper_send_cmd(panel, PIXPAPER_CMD_DISPLAY_REFRESH, &err); + pixpaper_send_data(panel, PIXPAPER_DRF_VCOM_AC, &err); + if (err.errno_code) { + drm_err_once(drm, "Failed sending data after DRF: %d\n", err.errno_code); + goto update_cleanup; + } + pixpaper_wait_for_panel(panel); + +update_cleanup: + if (err.errno_code && err.errno_code != -ETIMEDOUT) + drm_err_once(drm, "Frame update function failed with error %d\n", err.errno_code); + + drm_dev_exit(idx); +} + +static const struct drm_display_mode pixpaper_mode = { + .clock = PIXPAPER_PIXEL_CLOCK, + .hdisplay = PIXPAPER_WIDTH, + .hsync_start = PIXPAPER_WIDTH + PIXPAPER_HFP, + .hsync_end = PIXPAPER_WIDTH + PIXPAPER_HFP + PIXPAPER_HSYNC, + .htotal = PIXPAPER_HTOTAL, + .vdisplay = PIXPAPER_HEIGHT, + .vsync_start = PIXPAPER_HEIGHT + PIXPAPER_VFP, + .vsync_end = PIXPAPER_HEIGHT + PIXPAPER_VFP + PIXPAPER_VSYNC, + .vtotal = PIXPAPER_VTOTAL, + .width_mm = PIXPAPER_WIDTH_MM, + .height_mm = PIXPAPER_HEIGHT_MM, + .type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED, +}; + +static int pixpaper_connector_get_modes(struct drm_connector *connector) +{ + return drm_connector_helper_get_modes_fixed(connector, &pixpaper_mode); +} + +static const struct drm_plane_funcs pixpaper_plane_funcs = { + .update_plane = drm_atomic_helper_update_plane, + .disable_plane = drm_atomic_helper_disable_plane, + .destroy = drm_plane_cleanup, + DRM_GEM_SHADOW_PLANE_FUNCS, +}; + +static const struct drm_plane_helper_funcs pixpaper_plane_helper_funcs = { + DRM_GEM_SHADOW_PLANE_HELPER_FUNCS, + .atomic_check = pixpaper_plane_helper_atomic_check, + .atomic_update = pixpaper_plane_atomic_update, +}; + +static const struct drm_crtc_funcs pixpaper_crtc_funcs = { + .set_config = drm_atomic_helper_set_config, + .page_flip = drm_atomic_helper_page_flip, + .reset = drm_atomic_helper_crtc_reset, + .destroy = drm_crtc_cleanup, + .atomic_duplicate_state = drm_atomic_helper_crtc_duplicate_state, + .atomic_destroy_state = drm_atomic_helper_crtc_destroy_state, +}; + +static enum drm_mode_status +pixpaper_mode_valid(struct drm_crtc *crtc, const struct drm_display_mode *mode) +{ + if (mode->hdisplay == PIXPAPER_WIDTH && + mode->vdisplay == PIXPAPER_HEIGHT) { + return MODE_OK; + } + return MODE_BAD; +} + +static const struct drm_crtc_helper_funcs pixpaper_crtc_helper_funcs = { + .mode_valid = pixpaper_mode_valid, + .atomic_check = pixpaper_crtc_helper_atomic_check, + .atomic_enable = pixpaper_crtc_atomic_enable, + .atomic_disable = pixpaper_crtc_atomic_disable, +}; + +static const struct drm_encoder_funcs pixpaper_encoder_funcs = { + .destroy = drm_encoder_cleanup, +}; + +static const struct drm_connector_funcs pixpaper_connector_funcs = { + .reset = drm_atomic_helper_connector_reset, + .fill_modes = drm_helper_probe_single_connector_modes, + .destroy = drm_connector_cleanup, + .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, + .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, +}; + +static const struct drm_connector_helper_funcs pixpaper_connector_helper_funcs = { + .get_modes = pixpaper_connector_get_modes, +}; + +DEFINE_DRM_GEM_FOPS(pixpaper_fops); + +static struct drm_driver pixpaper_drm_driver = { + .driver_features = DRIVER_GEM | DRIVER_MODESET | DRIVER_ATOMIC, + .fops = &pixpaper_fops, + .name = "pixpaper", + .desc = "DRM driver for PIXPAPER e-ink", + .major = 1, + .minor = 0, + DRM_GEM_SHMEM_DRIVER_OPS, + DRM_FBDEV_SHMEM_DRIVER_OPS, +}; + +static const struct drm_mode_config_funcs pixpaper_mode_config_funcs = { + .fb_create = drm_gem_fb_create_with_dirty, + .atomic_check = drm_atomic_helper_check, + .atomic_commit = drm_atomic_helper_commit, +}; + +static int pixpaper_probe(struct spi_device *spi) +{ + struct device *dev = &spi->dev; + struct pixpaper_panel *panel; + struct drm_device *drm; + int ret; + + panel = devm_drm_dev_alloc(dev, &pixpaper_drm_driver, + struct pixpaper_panel, drm); + if (IS_ERR(panel)) + return PTR_ERR(panel); + + drm = &panel->drm; + panel->spi = spi; + spi_set_drvdata(spi, panel); + + spi->mode = SPI_MODE_0; + spi->bits_per_word = PIXPAPER_SPI_BITS_PER_WORD; + + if (!spi->max_speed_hz) { + drm_warn(drm, + "spi-max-frequency not specified in DT, using default %u Hz\n", + PIXPAPER_SPI_SPEED_DEFAULT); + spi->max_speed_hz = PIXPAPER_SPI_SPEED_DEFAULT; + } + + ret = spi_setup(spi); + if (ret < 0) { + drm_err(drm, "SPI setup failed: %d\n", ret); + return ret; + } + + if (!dev->dma_mask) + dev->dma_mask = &dev->coherent_dma_mask; + ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32)); + if (ret) { + drm_err(drm, "Failed to set DMA mask: %d\n", ret); + return ret; + } + + panel->reset = devm_gpiod_get(dev, "reset", GPIOD_OUT_HIGH); + if (IS_ERR(panel->reset)) + return PTR_ERR(panel->reset); + + panel->busy = devm_gpiod_get(dev, "busy", GPIOD_IN); + if (IS_ERR(panel->busy)) + return PTR_ERR(panel->busy); + + panel->dc = devm_gpiod_get(dev, "dc", GPIOD_OUT_HIGH); + if (IS_ERR(panel->dc)) + return PTR_ERR(panel->dc); + + ret = pixpaper_panel_hw_init(panel); + if (ret) { + drm_err(drm, "Panel hardware initialization failed: %d\n", ret); + return ret; + } + + ret = drmm_mode_config_init(drm); + if (ret) + return ret; + drm->mode_config.funcs = &pixpaper_mode_config_funcs; + drm->mode_config.min_width = PIXPAPER_WIDTH; + drm->mode_config.max_width = PIXPAPER_WIDTH; + drm->mode_config.min_height = PIXPAPER_HEIGHT; + drm->mode_config.max_height = PIXPAPER_HEIGHT; + + ret = drm_universal_plane_init(drm, &panel->plane, 1, + &pixpaper_plane_funcs, + (const uint32_t[]){ DRM_FORMAT_XRGB8888 }, + 1, NULL, DRM_PLANE_TYPE_PRIMARY, NULL); + if (ret) + return ret; + drm_plane_helper_add(&panel->plane, &pixpaper_plane_helper_funcs); + + ret = drm_crtc_init_with_planes(drm, &panel->crtc, &panel->plane, NULL, + &pixpaper_crtc_funcs, NULL); + if (ret) + return ret; + drm_crtc_helper_add(&panel->crtc, &pixpaper_crtc_helper_funcs); + + ret = drm_encoder_init(drm, &panel->encoder, &pixpaper_encoder_funcs, + DRM_MODE_ENCODER_NONE, NULL); + if (ret) + return ret; + panel->encoder.possible_crtcs = drm_crtc_mask(&panel->crtc); + + ret = drm_connector_init(drm, &panel->connector, + &pixpaper_connector_funcs, + DRM_MODE_CONNECTOR_SPI); + if (ret) + return ret; + + drm_connector_helper_add(&panel->connector, + &pixpaper_connector_helper_funcs); + drm_connector_attach_encoder(&panel->connector, &panel->encoder); + + drm_mode_config_reset(drm); + + ret = drm_dev_register(drm, 0); + if (ret) + return ret; + + drm_client_setup(drm, NULL); + + return 0; +} + +static void pixpaper_remove(struct spi_device *spi) +{ + struct pixpaper_panel *panel = spi_get_drvdata(spi); + + if (!panel) + return; + + drm_dev_unplug(&panel->drm); + drm_atomic_helper_shutdown(&panel->drm); +} + +static const struct spi_device_id pixpaper_ids[] = { { "pixpaper", 0 }, {} }; +MODULE_DEVICE_TABLE(spi, pixpaper_ids); + +static const struct of_device_id pixpaper_dt_ids[] = { + { .compatible = "mayqueen,pixpaper" }, + {} +}; +MODULE_DEVICE_TABLE(of, pixpaper_dt_ids); + +static struct spi_driver pixpaper_spi_driver = { + .driver = { + .name = "pixpaper", + .of_match_table = pixpaper_dt_ids, + }, + .id_table = pixpaper_ids, + .probe = pixpaper_probe, + .remove = pixpaper_remove, +}; + +module_spi_driver(pixpaper_spi_driver); + +MODULE_AUTHOR("LiangCheng Wang"); +MODULE_DESCRIPTION("DRM SPI driver for PIXPAPER e-ink panel"); +MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index f4d9e68b21e7..29423ceeec5c 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -1283,3 +1283,18 @@ int ttm_bo_populate(struct ttm_buffer_object *bo, return 0; } EXPORT_SYMBOL(ttm_bo_populate); + +int ttm_bo_setup_export(struct ttm_buffer_object *bo, + struct ttm_operation_ctx *ctx) +{ + int ret; + + ret = ttm_bo_reserve(bo, false, false, NULL); + if (ret != 0) + return ret; + + ret = ttm_bo_populate(bo, ctx); + ttm_bo_unreserve(bo); + return ret; +} +EXPORT_SYMBOL(ttm_bo_setup_export); diff --git a/drivers/gpu/drm/tyr/Kconfig b/drivers/gpu/drm/tyr/Kconfig new file mode 100644 index 000000000000..4b55308fd2eb --- /dev/null +++ b/drivers/gpu/drm/tyr/Kconfig @@ -0,0 +1,19 @@ +# SPDX-License-Identifier: GPL-2.0 or MIT + +config DRM_TYR + tristate "Tyr (Rust DRM support for ARM Mali CSF-based GPUs)" + depends on DRM=y + depends on RUST + depends on ARM || ARM64 || COMPILE_TEST + depends on !GENERIC_ATOMIC64 # for IOMMU_IO_PGTABLE_LPAE + default n + help + Rust DRM driver for ARM Mali CSF-based GPUs. + + This driver is for Mali (or Immortalis) Valhall Gxxx GPUs. + + Note that the Mali-G68 and Mali-G78, while Valhall architecture, will + be supported with the panfrost driver as they are not CSF GPUs. + + if M is selected, the module will be called tyr. This driver is work + in progress and may not be functional. diff --git a/drivers/gpu/drm/tyr/Makefile b/drivers/gpu/drm/tyr/Makefile new file mode 100644 index 000000000000..ba545f65f2c0 --- /dev/null +++ b/drivers/gpu/drm/tyr/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 or MIT + +obj-$(CONFIG_DRM_TYR) += tyr.o diff --git a/drivers/gpu/drm/tyr/driver.rs b/drivers/gpu/drm/tyr/driver.rs new file mode 100644 index 000000000000..d5625dd1e41c --- /dev/null +++ b/drivers/gpu/drm/tyr/driver.rs @@ -0,0 +1,205 @@ +// SPDX-License-Identifier: GPL-2.0 or MIT + +use kernel::c_str; +use kernel::clk::Clk; +use kernel::clk::OptionalClk; +use kernel::device::Bound; +use kernel::device::Core; +use kernel::device::Device; +use kernel::devres::Devres; +use kernel::drm; +use kernel::drm::ioctl; +use kernel::new_mutex; +use kernel::of; +use kernel::platform; +use kernel::prelude::*; +use kernel::regulator; +use kernel::regulator::Regulator; +use kernel::sizes::SZ_2M; +use kernel::sync::Arc; +use kernel::sync::Mutex; +use kernel::time; +use kernel::types::ARef; + +use crate::file::File; +use crate::gem::TyrObject; +use crate::gpu; +use crate::gpu::GpuInfo; +use crate::regs; + +pub(crate) type IoMem = kernel::io::mem::IoMem<SZ_2M>; + +/// Convenience type alias for the DRM device type for this driver. +pub(crate) type TyrDevice = drm::Device<TyrDriver>; + +#[pin_data(PinnedDrop)] +pub(crate) struct TyrDriver { + device: ARef<TyrDevice>, +} + +#[pin_data(PinnedDrop)] +pub(crate) struct TyrData { + pub(crate) pdev: ARef<platform::Device>, + + #[pin] + clks: Mutex<Clocks>, + + #[pin] + regulators: Mutex<Regulators>, + + /// Some information on the GPU. + /// + /// This is mainly queried by userspace, i.e.: Mesa. + pub(crate) gpu_info: GpuInfo, +} + +// Both `Clk` and `Regulator` do not implement `Send` or `Sync`, but they +// should. There are patches on the mailing list to address this, but they have +// not landed yet. +// +// For now, add this workaround so that this patch compiles with the promise +// that it will be removed in a future patch. +// +// SAFETY: This will be removed in a future patch. +unsafe impl Send for TyrData {} +// SAFETY: This will be removed in a future patch. +unsafe impl Sync for TyrData {} + +fn issue_soft_reset(dev: &Device<Bound>, iomem: &Devres<IoMem>) -> Result { + regs::GPU_CMD.write(dev, iomem, regs::GPU_CMD_SOFT_RESET)?; + + // TODO: We cannot poll, as there is no support in Rust currently, so we + // sleep. Change this when read_poll_timeout() is implemented in Rust. + kernel::time::delay::fsleep(time::Delta::from_millis(100)); + + if regs::GPU_IRQ_RAWSTAT.read(dev, iomem)? & regs::GPU_IRQ_RAWSTAT_RESET_COMPLETED == 0 { + dev_err!(dev, "GPU reset failed with errno\n"); + dev_err!( + dev, + "GPU_INT_RAWSTAT is {}\n", + regs::GPU_IRQ_RAWSTAT.read(dev, iomem)? + ); + + return Err(EIO); + } + + Ok(()) +} + +kernel::of_device_table!( + OF_TABLE, + MODULE_OF_TABLE, + <TyrDriver as platform::Driver>::IdInfo, + [ + (of::DeviceId::new(c_str!("rockchip,rk3588-mali")), ()), + (of::DeviceId::new(c_str!("arm,mali-valhall-csf")), ()) + ] +); + +impl platform::Driver for TyrDriver { + type IdInfo = (); + const OF_ID_TABLE: Option<of::IdTable<Self::IdInfo>> = Some(&OF_TABLE); + + fn probe( + pdev: &platform::Device<Core>, + _info: Option<&Self::IdInfo>, + ) -> Result<Pin<KBox<Self>>> { + let core_clk = Clk::get(pdev.as_ref(), Some(c_str!("core")))?; + let stacks_clk = OptionalClk::get(pdev.as_ref(), Some(c_str!("stacks")))?; + let coregroup_clk = OptionalClk::get(pdev.as_ref(), Some(c_str!("coregroup")))?; + + core_clk.prepare_enable()?; + stacks_clk.prepare_enable()?; + coregroup_clk.prepare_enable()?; + + let mali_regulator = Regulator::<regulator::Enabled>::get(pdev.as_ref(), c_str!("mali"))?; + let sram_regulator = Regulator::<regulator::Enabled>::get(pdev.as_ref(), c_str!("sram"))?; + + let request = pdev.io_request_by_index(0).ok_or(ENODEV)?; + let iomem = Arc::pin_init(request.iomap_sized::<SZ_2M>(), GFP_KERNEL)?; + + issue_soft_reset(pdev.as_ref(), &iomem)?; + gpu::l2_power_on(pdev.as_ref(), &iomem)?; + + let gpu_info = GpuInfo::new(pdev.as_ref(), &iomem)?; + gpu_info.log(pdev); + + let platform: ARef<platform::Device> = pdev.into(); + + let data = try_pin_init!(TyrData { + pdev: platform.clone(), + clks <- new_mutex!(Clocks { + core: core_clk, + stacks: stacks_clk, + coregroup: coregroup_clk, + }), + regulators <- new_mutex!(Regulators { + mali: mali_regulator, + sram: sram_regulator, + }), + gpu_info, + }); + + let tdev: ARef<TyrDevice> = drm::Device::new(pdev.as_ref(), data)?; + drm::driver::Registration::new_foreign_owned(&tdev, pdev.as_ref(), 0)?; + + let driver = KBox::pin_init(try_pin_init!(TyrDriver { device: tdev }), GFP_KERNEL)?; + + // We need this to be dev_info!() because dev_dbg!() does not work at + // all in Rust for now, and we need to see whether probe succeeded. + dev_info!(pdev.as_ref(), "Tyr initialized correctly.\n"); + Ok(driver) + } +} + +#[pinned_drop] +impl PinnedDrop for TyrDriver { + fn drop(self: Pin<&mut Self>) {} +} + +#[pinned_drop] +impl PinnedDrop for TyrData { + fn drop(self: Pin<&mut Self>) { + // TODO: the type-state pattern for Clks will fix this. + let clks = self.clks.lock(); + clks.core.disable_unprepare(); + clks.stacks.disable_unprepare(); + clks.coregroup.disable_unprepare(); + } +} + +// We need to retain the name "panthor" to achieve drop-in compatibility with +// the C driver in the userspace stack. +const INFO: drm::DriverInfo = drm::DriverInfo { + major: 1, + minor: 5, + patchlevel: 0, + name: c_str!("panthor"), + desc: c_str!("ARM Mali Tyr DRM driver"), +}; + +#[vtable] +impl drm::Driver for TyrDriver { + type Data = TyrData; + type File = File; + type Object = drm::gem::Object<TyrObject>; + + const INFO: drm::DriverInfo = INFO; + + kernel::declare_drm_ioctls! { + (PANTHOR_DEV_QUERY, drm_panthor_dev_query, ioctl::RENDER_ALLOW, File::dev_query), + } +} + +#[pin_data] +struct Clocks { + core: Clk, + stacks: OptionalClk, + coregroup: OptionalClk, +} + +#[pin_data] +struct Regulators { + mali: Regulator<regulator::Enabled>, + sram: Regulator<regulator::Enabled>, +} diff --git a/drivers/gpu/drm/tyr/file.rs b/drivers/gpu/drm/tyr/file.rs new file mode 100644 index 000000000000..0ef432947b73 --- /dev/null +++ b/drivers/gpu/drm/tyr/file.rs @@ -0,0 +1,56 @@ +// SPDX-License-Identifier: GPL-2.0 or MIT + +use kernel::drm; +use kernel::prelude::*; +use kernel::uaccess::UserSlice; +use kernel::uapi; + +use crate::driver::TyrDevice; +use crate::TyrDriver; + +#[pin_data] +pub(crate) struct File {} + +/// Convenience type alias for our DRM `File` type +pub(crate) type DrmFile = drm::file::File<File>; + +impl drm::file::DriverFile for File { + type Driver = TyrDriver; + + fn open(_dev: &drm::Device<Self::Driver>) -> Result<Pin<KBox<Self>>> { + KBox::try_pin_init(try_pin_init!(Self {}), GFP_KERNEL) + } +} + +impl File { + pub(crate) fn dev_query( + tdev: &TyrDevice, + devquery: &mut uapi::drm_panthor_dev_query, + _file: &DrmFile, + ) -> Result<u32> { + if devquery.pointer == 0 { + match devquery.type_ { + uapi::drm_panthor_dev_query_type_DRM_PANTHOR_DEV_QUERY_GPU_INFO => { + devquery.size = core::mem::size_of_val(&tdev.gpu_info) as u32; + Ok(0) + } + _ => Err(EINVAL), + } + } else { + match devquery.type_ { + uapi::drm_panthor_dev_query_type_DRM_PANTHOR_DEV_QUERY_GPU_INFO => { + let mut writer = UserSlice::new( + UserPtr::from_addr(devquery.pointer as usize), + devquery.size as usize, + ) + .writer(); + + writer.write(&tdev.gpu_info)?; + + Ok(0) + } + _ => Err(EINVAL), + } + } + } +} diff --git a/drivers/gpu/drm/tyr/gem.rs b/drivers/gpu/drm/tyr/gem.rs new file mode 100644 index 000000000000..1273bf89dbd5 --- /dev/null +++ b/drivers/gpu/drm/tyr/gem.rs @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0 or MIT + +use crate::driver::TyrDevice; +use crate::driver::TyrDriver; +use kernel::drm::gem; +use kernel::prelude::*; + +/// GEM Object inner driver data +#[pin_data] +pub(crate) struct TyrObject {} + +impl gem::DriverObject for TyrObject { + type Driver = TyrDriver; + + fn new(_dev: &TyrDevice, _size: usize) -> impl PinInit<Self, Error> { + try_pin_init!(TyrObject {}) + } +} diff --git a/drivers/gpu/drm/tyr/gpu.rs b/drivers/gpu/drm/tyr/gpu.rs new file mode 100644 index 000000000000..6c582910dd5d --- /dev/null +++ b/drivers/gpu/drm/tyr/gpu.rs @@ -0,0 +1,219 @@ +// SPDX-License-Identifier: GPL-2.0 or MIT + +use kernel::bits::genmask_u32; +use kernel::device::Bound; +use kernel::device::Device; +use kernel::devres::Devres; +use kernel::platform; +use kernel::prelude::*; +use kernel::time; +use kernel::transmute::AsBytes; + +use crate::driver::IoMem; +use crate::regs; + +/// Struct containing information that can be queried by userspace. This is read from +/// the GPU's registers. +/// +/// # Invariants +/// +/// - The layout of this struct identical to the C `struct drm_panthor_gpu_info`. +#[repr(C)] +pub(crate) struct GpuInfo { + pub(crate) gpu_id: u32, + pub(crate) gpu_rev: u32, + pub(crate) csf_id: u32, + pub(crate) l2_features: u32, + pub(crate) tiler_features: u32, + pub(crate) mem_features: u32, + pub(crate) mmu_features: u32, + pub(crate) thread_features: u32, + pub(crate) max_threads: u32, + pub(crate) thread_max_workgroup_size: u32, + pub(crate) thread_max_barrier_size: u32, + pub(crate) coherency_features: u32, + pub(crate) texture_features: [u32; 4], + pub(crate) as_present: u32, + pub(crate) pad0: u32, + pub(crate) shader_present: u64, + pub(crate) l2_present: u64, + pub(crate) tiler_present: u64, + pub(crate) core_features: u32, + pub(crate) pad: u32, +} + +impl GpuInfo { + pub(crate) fn new(dev: &Device<Bound>, iomem: &Devres<IoMem>) -> Result<Self> { + let gpu_id = regs::GPU_ID.read(dev, iomem)?; + let csf_id = regs::GPU_CSF_ID.read(dev, iomem)?; + let gpu_rev = regs::GPU_REVID.read(dev, iomem)?; + let core_features = regs::GPU_CORE_FEATURES.read(dev, iomem)?; + let l2_features = regs::GPU_L2_FEATURES.read(dev, iomem)?; + let tiler_features = regs::GPU_TILER_FEATURES.read(dev, iomem)?; + let mem_features = regs::GPU_MEM_FEATURES.read(dev, iomem)?; + let mmu_features = regs::GPU_MMU_FEATURES.read(dev, iomem)?; + let thread_features = regs::GPU_THREAD_FEATURES.read(dev, iomem)?; + let max_threads = regs::GPU_THREAD_MAX_THREADS.read(dev, iomem)?; + let thread_max_workgroup_size = regs::GPU_THREAD_MAX_WORKGROUP_SIZE.read(dev, iomem)?; + let thread_max_barrier_size = regs::GPU_THREAD_MAX_BARRIER_SIZE.read(dev, iomem)?; + let coherency_features = regs::GPU_COHERENCY_FEATURES.read(dev, iomem)?; + + let texture_features = regs::GPU_TEXTURE_FEATURES0.read(dev, iomem)?; + + let as_present = regs::GPU_AS_PRESENT.read(dev, iomem)?; + + let shader_present = u64::from(regs::GPU_SHADER_PRESENT_LO.read(dev, iomem)?); + let shader_present = + shader_present | u64::from(regs::GPU_SHADER_PRESENT_HI.read(dev, iomem)?) << 32; + + let tiler_present = u64::from(regs::GPU_TILER_PRESENT_LO.read(dev, iomem)?); + let tiler_present = + tiler_present | u64::from(regs::GPU_TILER_PRESENT_HI.read(dev, iomem)?) << 32; + + let l2_present = u64::from(regs::GPU_L2_PRESENT_LO.read(dev, iomem)?); + let l2_present = l2_present | u64::from(regs::GPU_L2_PRESENT_HI.read(dev, iomem)?) << 32; + + Ok(Self { + gpu_id, + gpu_rev, + csf_id, + l2_features, + tiler_features, + mem_features, + mmu_features, + thread_features, + max_threads, + thread_max_workgroup_size, + thread_max_barrier_size, + coherency_features, + // TODO: Add texture_features_{1,2,3}. + texture_features: [texture_features, 0, 0, 0], + as_present, + pad0: 0, + shader_present, + l2_present, + tiler_present, + core_features, + pad: 0, + }) + } + + pub(crate) fn log(&self, pdev: &platform::Device) { + let major = (self.gpu_id >> 16) & 0xff; + let minor = (self.gpu_id >> 8) & 0xff; + let status = self.gpu_id & 0xff; + + let model_name = if let Some(model) = GPU_MODELS + .iter() + .find(|&f| f.major == major && f.minor == minor) + { + model.name + } else { + "unknown" + }; + + dev_info!( + pdev.as_ref(), + "mali-{} id 0x{:x} major 0x{:x} minor 0x{:x} status 0x{:x}", + model_name, + self.gpu_id >> 16, + major, + minor, + status + ); + + dev_info!( + pdev.as_ref(), + "Features: L2:{:#x} Tiler:{:#x} Mem:{:#x} MMU:{:#x} AS:{:#x}", + self.l2_features, + self.tiler_features, + self.mem_features, + self.mmu_features, + self.as_present + ); + + dev_info!( + pdev.as_ref(), + "shader_present=0x{:016x} l2_present=0x{:016x} tiler_present=0x{:016x}", + self.shader_present, + self.l2_present, + self.tiler_present + ); + } + + /// Returns the number of virtual address bits supported by the GPU. + #[expect(dead_code)] + pub(crate) fn va_bits(&self) -> u32 { + self.mmu_features & genmask_u32(0..=7) + } + + /// Returns the number of physical address bits supported by the GPU. + #[expect(dead_code)] + pub(crate) fn pa_bits(&self) -> u32 { + (self.mmu_features >> 8) & genmask_u32(0..=7) + } +} + +// SAFETY: `GpuInfo`'s invariant guarantees that it is the same type that is +// already exposed to userspace by the C driver. This implies that it fulfills +// the requirements for `AsBytes`. +// +// This means: +// +// - No implicit padding, +// - No kernel pointers, +// - No interior mutability. +unsafe impl AsBytes for GpuInfo {} + +struct GpuModels { + name: &'static str, + major: u32, + minor: u32, +} + +const GPU_MODELS: [GpuModels; 1] = [GpuModels { + name: "g610", + major: 10, + minor: 7, +}]; + +#[allow(dead_code)] +pub(crate) struct GpuId { + pub(crate) arch_major: u32, + pub(crate) arch_minor: u32, + pub(crate) arch_rev: u32, + pub(crate) prod_major: u32, + pub(crate) ver_major: u32, + pub(crate) ver_minor: u32, + pub(crate) ver_status: u32, +} + +impl From<u32> for GpuId { + fn from(value: u32) -> Self { + GpuId { + arch_major: (value & genmask_u32(28..=31)) >> 28, + arch_minor: (value & genmask_u32(24..=27)) >> 24, + arch_rev: (value & genmask_u32(20..=23)) >> 20, + prod_major: (value & genmask_u32(16..=19)) >> 16, + ver_major: (value & genmask_u32(12..=15)) >> 12, + ver_minor: (value & genmask_u32(4..=11)) >> 4, + ver_status: value & genmask_u32(0..=3), + } + } +} + +/// Powers on the l2 block. +pub(crate) fn l2_power_on(dev: &Device<Bound>, iomem: &Devres<IoMem>) -> Result { + regs::L2_PWRON_LO.write(dev, iomem, 1)?; + + // TODO: We cannot poll, as there is no support in Rust currently, so we + // sleep. Change this when read_poll_timeout() is implemented in Rust. + kernel::time::delay::fsleep(time::Delta::from_millis(100)); + + if regs::L2_READY_LO.read(dev, iomem)? != 1 { + dev_err!(dev, "Failed to power on the GPU\n"); + return Err(EIO); + } + + Ok(()) +} diff --git a/drivers/gpu/drm/tyr/regs.rs b/drivers/gpu/drm/tyr/regs.rs new file mode 100644 index 000000000000..f46933aaa221 --- /dev/null +++ b/drivers/gpu/drm/tyr/regs.rs @@ -0,0 +1,108 @@ +// SPDX-License-Identifier: GPL-2.0 or MIT + +// We don't expect that all the registers and fields will be used, even in the +// future. +// +// Nevertheless, it is useful to have most of them defined, like the C driver +// does. +#![allow(dead_code)] + +use kernel::bits::bit_u32; +use kernel::device::Bound; +use kernel::device::Device; +use kernel::devres::Devres; +use kernel::prelude::*; + +use crate::driver::IoMem; + +/// Represents a register in the Register Set +/// +/// TODO: Replace this with the Nova `register!()` macro when it is available. +/// In particular, this will automatically give us 64bit register reads and +/// writes. +pub(crate) struct Register<const OFFSET: usize>; + +impl<const OFFSET: usize> Register<OFFSET> { + #[inline] + pub(crate) fn read(&self, dev: &Device<Bound>, iomem: &Devres<IoMem>) -> Result<u32> { + let value = (*iomem).access(dev)?.read32(OFFSET); + Ok(value) + } + + #[inline] + pub(crate) fn write(&self, dev: &Device<Bound>, iomem: &Devres<IoMem>, value: u32) -> Result { + (*iomem).access(dev)?.write32(value, OFFSET); + Ok(()) + } +} + +pub(crate) const GPU_ID: Register<0x0> = Register; +pub(crate) const GPU_L2_FEATURES: Register<0x4> = Register; +pub(crate) const GPU_CORE_FEATURES: Register<0x8> = Register; +pub(crate) const GPU_CSF_ID: Register<0x1c> = Register; +pub(crate) const GPU_REVID: Register<0x280> = Register; +pub(crate) const GPU_TILER_FEATURES: Register<0xc> = Register; +pub(crate) const GPU_MEM_FEATURES: Register<0x10> = Register; +pub(crate) const GPU_MMU_FEATURES: Register<0x14> = Register; +pub(crate) const GPU_AS_PRESENT: Register<0x18> = Register; +pub(crate) const GPU_IRQ_RAWSTAT: Register<0x20> = Register; + +pub(crate) const GPU_IRQ_RAWSTAT_FAULT: u32 = bit_u32(0); +pub(crate) const GPU_IRQ_RAWSTAT_PROTECTED_FAULT: u32 = bit_u32(1); +pub(crate) const GPU_IRQ_RAWSTAT_RESET_COMPLETED: u32 = bit_u32(8); +pub(crate) const GPU_IRQ_RAWSTAT_POWER_CHANGED_SINGLE: u32 = bit_u32(9); +pub(crate) const GPU_IRQ_RAWSTAT_POWER_CHANGED_ALL: u32 = bit_u32(10); +pub(crate) const GPU_IRQ_RAWSTAT_CLEAN_CACHES_COMPLETED: u32 = bit_u32(17); +pub(crate) const GPU_IRQ_RAWSTAT_DOORBELL_STATUS: u32 = bit_u32(18); +pub(crate) const GPU_IRQ_RAWSTAT_MCU_STATUS: u32 = bit_u32(19); + +pub(crate) const GPU_IRQ_CLEAR: Register<0x24> = Register; +pub(crate) const GPU_IRQ_MASK: Register<0x28> = Register; +pub(crate) const GPU_IRQ_STAT: Register<0x2c> = Register; +pub(crate) const GPU_CMD: Register<0x30> = Register; +pub(crate) const GPU_CMD_SOFT_RESET: u32 = 1 | (1 << 8); +pub(crate) const GPU_CMD_HARD_RESET: u32 = 1 | (2 << 8); +pub(crate) const GPU_THREAD_FEATURES: Register<0xac> = Register; +pub(crate) const GPU_THREAD_MAX_THREADS: Register<0xa0> = Register; +pub(crate) const GPU_THREAD_MAX_WORKGROUP_SIZE: Register<0xa4> = Register; +pub(crate) const GPU_THREAD_MAX_BARRIER_SIZE: Register<0xa8> = Register; +pub(crate) const GPU_TEXTURE_FEATURES0: Register<0xb0> = Register; +pub(crate) const GPU_SHADER_PRESENT_LO: Register<0x100> = Register; +pub(crate) const GPU_SHADER_PRESENT_HI: Register<0x104> = Register; +pub(crate) const GPU_TILER_PRESENT_LO: Register<0x110> = Register; +pub(crate) const GPU_TILER_PRESENT_HI: Register<0x114> = Register; +pub(crate) const GPU_L2_PRESENT_LO: Register<0x120> = Register; +pub(crate) const GPU_L2_PRESENT_HI: Register<0x124> = Register; +pub(crate) const L2_READY_LO: Register<0x160> = Register; +pub(crate) const L2_READY_HI: Register<0x164> = Register; +pub(crate) const L2_PWRON_LO: Register<0x1a0> = Register; +pub(crate) const L2_PWRON_HI: Register<0x1a4> = Register; +pub(crate) const L2_PWRTRANS_LO: Register<0x220> = Register; +pub(crate) const L2_PWRTRANS_HI: Register<0x204> = Register; +pub(crate) const L2_PWRACTIVE_LO: Register<0x260> = Register; +pub(crate) const L2_PWRACTIVE_HI: Register<0x264> = Register; + +pub(crate) const MCU_CONTROL: Register<0x700> = Register; +pub(crate) const MCU_CONTROL_ENABLE: u32 = 1; +pub(crate) const MCU_CONTROL_AUTO: u32 = 2; +pub(crate) const MCU_CONTROL_DISABLE: u32 = 0; + +pub(crate) const MCU_STATUS: Register<0x704> = Register; +pub(crate) const MCU_STATUS_DISABLED: u32 = 0; +pub(crate) const MCU_STATUS_ENABLED: u32 = 1; +pub(crate) const MCU_STATUS_HALT: u32 = 2; +pub(crate) const MCU_STATUS_FATAL: u32 = 3; + +pub(crate) const GPU_COHERENCY_FEATURES: Register<0x300> = Register; + +pub(crate) const JOB_IRQ_RAWSTAT: Register<0x1000> = Register; +pub(crate) const JOB_IRQ_CLEAR: Register<0x1004> = Register; +pub(crate) const JOB_IRQ_MASK: Register<0x1008> = Register; +pub(crate) const JOB_IRQ_STAT: Register<0x100c> = Register; + +pub(crate) const JOB_IRQ_GLOBAL_IF: u32 = bit_u32(31); + +pub(crate) const MMU_IRQ_RAWSTAT: Register<0x2000> = Register; +pub(crate) const MMU_IRQ_CLEAR: Register<0x2004> = Register; +pub(crate) const MMU_IRQ_MASK: Register<0x2008> = Register; +pub(crate) const MMU_IRQ_STAT: Register<0x200c> = Register; diff --git a/drivers/gpu/drm/tyr/tyr.rs b/drivers/gpu/drm/tyr/tyr.rs new file mode 100644 index 000000000000..861d1db43072 --- /dev/null +++ b/drivers/gpu/drm/tyr/tyr.rs @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0 or MIT + +//! Arm Mali Tyr DRM driver. +//! +//! The name "Tyr" is inspired by Norse mythology, reflecting Arm's tradition of +//! naming their GPUs after Nordic mythological figures and places. + +use crate::driver::TyrDriver; + +mod driver; +mod file; +mod gem; +mod gpu; +mod regs; + +kernel::module_platform_driver! { + type: TyrDriver, + name: "tyr", + authors: ["The Tyr driver authors"], + description: "Arm Mali Tyr DRM driver", + license: "Dual MIT/GPL", +} diff --git a/drivers/gpu/drm/v3d/v3d_drv.c b/drivers/gpu/drm/v3d/v3d_drv.c index 2def155ce496..c5a3bbbc74c5 100644 --- a/drivers/gpu/drm/v3d/v3d_drv.c +++ b/drivers/gpu/drm/v3d/v3d_drv.c @@ -157,12 +157,24 @@ v3d_open(struct drm_device *dev, struct drm_file *file) static void v3d_postclose(struct drm_device *dev, struct drm_file *file) { + struct v3d_dev *v3d = to_v3d_dev(dev); struct v3d_file_priv *v3d_priv = file->driver_priv; + unsigned long irqflags; enum v3d_queue q; - for (q = 0; q < V3D_MAX_QUEUES; q++) + for (q = 0; q < V3D_MAX_QUEUES; q++) { + struct v3d_queue_state *queue = &v3d->queue[q]; + struct v3d_job *job = queue->active_job; + drm_sched_entity_destroy(&v3d_priv->sched_entity[q]); + if (job && job->base.entity == &v3d_priv->sched_entity[q]) { + spin_lock_irqsave(&queue->queue_lock, irqflags); + job->file_priv = NULL; + spin_unlock_irqrestore(&queue->queue_lock, irqflags); + } + } + v3d_perfmon_close_file(v3d_priv); kfree(v3d_priv); } diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h index 82d84a96235f..0317f3d7452a 100644 --- a/drivers/gpu/drm/v3d/v3d_drv.h +++ b/drivers/gpu/drm/v3d/v3d_drv.h @@ -58,6 +58,10 @@ struct v3d_queue_state { /* Stores the GPU stats for this queue in the global context. */ struct v3d_stats stats; + + /* Currently active job for this queue */ + struct v3d_job *active_job; + spinlock_t queue_lock; }; /* Performance monitor object. The perform lifetime is controlled by userspace @@ -159,18 +163,8 @@ struct v3d_dev { struct work_struct overflow_mem_work; - struct v3d_bin_job *bin_job; - struct v3d_render_job *render_job; - struct v3d_tfu_job *tfu_job; - struct v3d_csd_job *csd_job; - struct v3d_queue_state queue[V3D_MAX_QUEUES]; - /* Spinlock used to synchronize the overflow memory - * management against bin job submission. - */ - spinlock_t job_lock; - /* Used to track the active perfmon if any. */ struct v3d_perfmon *active_perfmon; @@ -327,9 +321,9 @@ struct v3d_job { struct v3d_perfmon *perfmon; /* File descriptor of the process that submitted the job that could be used - * for collecting stats by process of GPU usage. + * to collect per-process information about the GPU. */ - struct drm_file *file; + struct v3d_file_priv *file_priv; /* Callback for the freeing of the job on refcount going to 0. */ void (*free)(struct kref *ref); @@ -570,7 +564,7 @@ void v3d_get_stats(const struct v3d_stats *stats, u64 timestamp, /* v3d_fence.c */ extern const struct dma_fence_ops v3d_fence_ops; -struct dma_fence *v3d_fence_create(struct v3d_dev *v3d, enum v3d_queue queue); +struct dma_fence *v3d_fence_create(struct v3d_dev *v3d, enum v3d_queue q); /* v3d_gem.c */ int v3d_gem_init(struct drm_device *dev); @@ -614,7 +608,7 @@ void v3d_timestamp_query_info_free(struct v3d_timestamp_query_info *query_info, unsigned int count); void v3d_performance_query_info_free(struct v3d_performance_query_info *query_info, unsigned int count); -void v3d_job_update_stats(struct v3d_job *job, enum v3d_queue queue); +void v3d_job_update_stats(struct v3d_job *job, enum v3d_queue q); int v3d_sched_init(struct v3d_dev *v3d); void v3d_sched_fini(struct v3d_dev *v3d); diff --git a/drivers/gpu/drm/v3d/v3d_fence.c b/drivers/gpu/drm/v3d/v3d_fence.c index 89840ed212c0..8f8471adae34 100644 --- a/drivers/gpu/drm/v3d/v3d_fence.c +++ b/drivers/gpu/drm/v3d/v3d_fence.c @@ -3,8 +3,9 @@ #include "v3d_drv.h" -struct dma_fence *v3d_fence_create(struct v3d_dev *v3d, enum v3d_queue queue) +struct dma_fence *v3d_fence_create(struct v3d_dev *v3d, enum v3d_queue q) { + struct v3d_queue_state *queue = &v3d->queue[q]; struct v3d_fence *fence; fence = kzalloc(sizeof(*fence), GFP_KERNEL); @@ -12,10 +13,10 @@ struct dma_fence *v3d_fence_create(struct v3d_dev *v3d, enum v3d_queue queue) return ERR_PTR(-ENOMEM); fence->dev = &v3d->drm; - fence->queue = queue; - fence->seqno = ++v3d->queue[queue].emit_seqno; - dma_fence_init(&fence->base, &v3d_fence_ops, &v3d->job_lock, - v3d->queue[queue].fence_context, fence->seqno); + fence->queue = q; + fence->seqno = ++queue->emit_seqno; + dma_fence_init(&fence->base, &v3d_fence_ops, &queue->queue_lock, + queue->fence_context, fence->seqno); return &fence->base; } diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c index 37bf5eecdd2c..c77d90aa9b82 100644 --- a/drivers/gpu/drm/v3d/v3d_gem.c +++ b/drivers/gpu/drm/v3d/v3d_gem.c @@ -271,10 +271,11 @@ v3d_gem_init(struct drm_device *dev) queue->fence_context = dma_fence_context_alloc(1); memset(&queue->stats, 0, sizeof(queue->stats)); seqcount_init(&queue->stats.lock); + + spin_lock_init(&queue->queue_lock); } spin_lock_init(&v3d->mm_lock); - spin_lock_init(&v3d->job_lock); ret = drmm_mutex_init(dev, &v3d->bo_lock); if (ret) return ret; @@ -324,6 +325,7 @@ void v3d_gem_destroy(struct drm_device *dev) { struct v3d_dev *v3d = to_v3d_dev(dev); + enum v3d_queue q; v3d_sched_fini(v3d); v3d_gemfs_fini(v3d); @@ -331,10 +333,8 @@ v3d_gem_destroy(struct drm_device *dev) /* Waiting for jobs to finish would need to be done before * unregistering V3D. */ - WARN_ON(v3d->bin_job); - WARN_ON(v3d->render_job); - WARN_ON(v3d->tfu_job); - WARN_ON(v3d->csd_job); + for (q = 0; q < V3D_MAX_QUEUES; q++) + WARN_ON(v3d->queue[q].active_job); drm_mm_takedown(&v3d->mm); diff --git a/drivers/gpu/drm/v3d/v3d_irq.c b/drivers/gpu/drm/v3d/v3d_irq.c index a515a301e480..31ecc5b4ba5a 100644 --- a/drivers/gpu/drm/v3d/v3d_irq.c +++ b/drivers/gpu/drm/v3d/v3d_irq.c @@ -42,6 +42,8 @@ v3d_overflow_mem_work(struct work_struct *work) container_of(work, struct v3d_dev, overflow_mem_work); struct drm_device *dev = &v3d->drm; struct v3d_bo *bo = v3d_bo_create(dev, NULL /* XXX: GMP */, 256 * 1024); + struct v3d_queue_state *queue = &v3d->queue[V3D_BIN]; + struct v3d_bin_job *bin_job; struct drm_gem_object *obj; unsigned long irqflags; @@ -60,15 +62,17 @@ v3d_overflow_mem_work(struct work_struct *work) * bin job got scheduled, that's fine. We'll just give them * some binner pool anyway. */ - spin_lock_irqsave(&v3d->job_lock, irqflags); - if (!v3d->bin_job) { - spin_unlock_irqrestore(&v3d->job_lock, irqflags); + spin_lock_irqsave(&queue->queue_lock, irqflags); + bin_job = (struct v3d_bin_job *)queue->active_job; + + if (!bin_job) { + spin_unlock_irqrestore(&queue->queue_lock, irqflags); goto out; } drm_gem_object_get(obj); - list_add_tail(&bo->unref_head, &v3d->bin_job->render->unref_list); - spin_unlock_irqrestore(&v3d->job_lock, irqflags); + list_add_tail(&bo->unref_head, &bin_job->render->unref_list); + spin_unlock_irqrestore(&queue->queue_lock, irqflags); v3d_mmu_flush_all(v3d); @@ -79,6 +83,20 @@ out: drm_gem_object_put(obj); } +static void +v3d_irq_signal_fence(struct v3d_dev *v3d, enum v3d_queue q, + void (*trace_irq)(struct drm_device *, uint64_t)) +{ + struct v3d_queue_state *queue = &v3d->queue[q]; + struct v3d_fence *fence = to_v3d_fence(queue->active_job->irq_fence); + + v3d_job_update_stats(queue->active_job, q); + trace_irq(&v3d->drm, fence->seqno); + + queue->active_job = NULL; + dma_fence_signal(&fence->base); +} + static irqreturn_t v3d_irq(int irq, void *arg) { @@ -102,41 +120,17 @@ v3d_irq(int irq, void *arg) } if (intsts & V3D_INT_FLDONE) { - struct v3d_fence *fence = - to_v3d_fence(v3d->bin_job->base.irq_fence); - - v3d_job_update_stats(&v3d->bin_job->base, V3D_BIN); - trace_v3d_bcl_irq(&v3d->drm, fence->seqno); - - v3d->bin_job = NULL; - dma_fence_signal(&fence->base); - + v3d_irq_signal_fence(v3d, V3D_BIN, trace_v3d_bcl_irq); status = IRQ_HANDLED; } if (intsts & V3D_INT_FRDONE) { - struct v3d_fence *fence = - to_v3d_fence(v3d->render_job->base.irq_fence); - - v3d_job_update_stats(&v3d->render_job->base, V3D_RENDER); - trace_v3d_rcl_irq(&v3d->drm, fence->seqno); - - v3d->render_job = NULL; - dma_fence_signal(&fence->base); - + v3d_irq_signal_fence(v3d, V3D_RENDER, trace_v3d_rcl_irq); status = IRQ_HANDLED; } if (intsts & V3D_INT_CSDDONE(v3d->ver)) { - struct v3d_fence *fence = - to_v3d_fence(v3d->csd_job->base.irq_fence); - - v3d_job_update_stats(&v3d->csd_job->base, V3D_CSD); - trace_v3d_csd_irq(&v3d->drm, fence->seqno); - - v3d->csd_job = NULL; - dma_fence_signal(&fence->base); - + v3d_irq_signal_fence(v3d, V3D_CSD, trace_v3d_csd_irq); status = IRQ_HANDLED; } @@ -168,15 +162,7 @@ v3d_hub_irq(int irq, void *arg) V3D_WRITE(V3D_HUB_INT_CLR, intsts); if (intsts & V3D_HUB_INT_TFUC) { - struct v3d_fence *fence = - to_v3d_fence(v3d->tfu_job->base.irq_fence); - - v3d_job_update_stats(&v3d->tfu_job->base, V3D_TFU); - trace_v3d_tfu_irq(&v3d->drm, fence->seqno); - - v3d->tfu_job = NULL; - dma_fence_signal(&fence->base); - + v3d_irq_signal_fence(v3d, V3D_TFU, trace_v3d_tfu_irq); status = IRQ_HANDLED; } diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c index f9d9a198d718..0ec06bfbbebb 100644 --- a/drivers/gpu/drm/v3d/v3d_sched.c +++ b/drivers/gpu/drm/v3d/v3d_sched.c @@ -139,7 +139,7 @@ static void v3d_job_start_stats(struct v3d_job *job, enum v3d_queue queue) { struct v3d_dev *v3d = job->v3d; - struct v3d_file_priv *file = job->file->driver_priv; + struct v3d_file_priv *file = job->file_priv; struct v3d_stats *global_stats = &v3d->queue[queue].stats; struct v3d_stats *local_stats = &file->stats[queue]; u64 now = local_clock(); @@ -194,11 +194,11 @@ v3d_stats_update(struct v3d_stats *stats, u64 now) } void -v3d_job_update_stats(struct v3d_job *job, enum v3d_queue queue) +v3d_job_update_stats(struct v3d_job *job, enum v3d_queue q) { struct v3d_dev *v3d = job->v3d; - struct v3d_file_priv *file = job->file->driver_priv; - struct v3d_stats *global_stats = &v3d->queue[queue].stats; + struct v3d_queue_state *queue = &v3d->queue[q]; + struct v3d_stats *global_stats = &queue->stats; u64 now = local_clock(); unsigned long flags; @@ -209,10 +209,10 @@ v3d_job_update_stats(struct v3d_job *job, enum v3d_queue queue) preempt_disable(); /* Don't update the local stats if the file context has already closed */ - if (file) - v3d_stats_update(&file->stats[queue], now); - else - drm_dbg(&v3d->drm, "The file descriptor was closed before job completion\n"); + spin_lock(&queue->queue_lock); + if (job->file_priv) + v3d_stats_update(&job->file_priv->stats[q], now); + spin_unlock(&queue->queue_lock); v3d_stats_update(global_stats, now); @@ -226,27 +226,28 @@ static struct dma_fence *v3d_bin_job_run(struct drm_sched_job *sched_job) { struct v3d_bin_job *job = to_bin_job(sched_job); struct v3d_dev *v3d = job->base.v3d; + struct v3d_queue_state *queue = &v3d->queue[V3D_BIN]; struct drm_device *dev = &v3d->drm; struct dma_fence *fence; unsigned long irqflags; if (unlikely(job->base.base.s_fence->finished.error)) { - spin_lock_irqsave(&v3d->job_lock, irqflags); - v3d->bin_job = NULL; - spin_unlock_irqrestore(&v3d->job_lock, irqflags); + spin_lock_irqsave(&queue->queue_lock, irqflags); + queue->active_job = NULL; + spin_unlock_irqrestore(&queue->queue_lock, irqflags); return NULL; } /* Lock required around bin_job update vs * v3d_overflow_mem_work(). */ - spin_lock_irqsave(&v3d->job_lock, irqflags); - v3d->bin_job = job; + spin_lock_irqsave(&queue->queue_lock, irqflags); + queue->active_job = &job->base; /* Clear out the overflow allocation, so we don't * reuse the overflow attached to a previous job. */ V3D_CORE_WRITE(0, V3D_PTB_BPOS, 0); - spin_unlock_irqrestore(&v3d->job_lock, irqflags); + spin_unlock_irqrestore(&queue->queue_lock, irqflags); v3d_invalidate_caches(v3d); @@ -290,11 +291,11 @@ static struct dma_fence *v3d_render_job_run(struct drm_sched_job *sched_job) struct dma_fence *fence; if (unlikely(job->base.base.s_fence->finished.error)) { - v3d->render_job = NULL; + v3d->queue[V3D_RENDER].active_job = NULL; return NULL; } - v3d->render_job = job; + v3d->queue[V3D_RENDER].active_job = &job->base; /* Can we avoid this flush? We need to be careful of * scheduling, though -- imagine job0 rendering to texture and @@ -338,11 +339,11 @@ v3d_tfu_job_run(struct drm_sched_job *sched_job) struct dma_fence *fence; if (unlikely(job->base.base.s_fence->finished.error)) { - v3d->tfu_job = NULL; + v3d->queue[V3D_TFU].active_job = NULL; return NULL; } - v3d->tfu_job = job; + v3d->queue[V3D_TFU].active_job = &job->base; fence = v3d_fence_create(v3d, V3D_TFU); if (IS_ERR(fence)) @@ -386,11 +387,11 @@ v3d_csd_job_run(struct drm_sched_job *sched_job) int i, csd_cfg0_reg; if (unlikely(job->base.base.s_fence->finished.error)) { - v3d->csd_job = NULL; + v3d->queue[V3D_CSD].active_job = NULL; return NULL; } - v3d->csd_job = job; + v3d->queue[V3D_CSD].active_job = &job->base; v3d_invalidate_caches(v3d); @@ -574,7 +575,7 @@ static void v3d_reset_performance_queries(struct v3d_cpu_job *job) { struct v3d_performance_query_info *performance_query = &job->performance_query; - struct v3d_file_priv *v3d_priv = job->base.file->driver_priv; + struct v3d_file_priv *v3d_priv = job->base.file_priv; struct v3d_dev *v3d = job->base.v3d; struct v3d_perfmon *perfmon; @@ -604,7 +605,7 @@ v3d_write_performance_query_result(struct v3d_cpu_job *job, void *data, { struct v3d_performance_query_info *performance_query = &job->performance_query; - struct v3d_file_priv *v3d_priv = job->base.file->driver_priv; + struct v3d_file_priv *v3d_priv = job->base.file_priv; struct v3d_performance_query *perf_query = &performance_query->queries[query]; struct v3d_dev *v3d = job->base.v3d; @@ -700,6 +701,7 @@ v3d_cpu_job_run(struct drm_sched_job *sched_job) trace_v3d_cpu_job_end(&v3d->drm, job->job_type); v3d_job_update_stats(&job->base, V3D_CPU); + /* Synchronous operation, so no fence to wait on. */ return NULL; } @@ -715,21 +717,24 @@ v3d_cache_clean_job_run(struct drm_sched_job *sched_job) v3d_job_update_stats(job, V3D_CACHE_CLEAN); + /* Synchronous operation, so no fence to wait on. */ return NULL; } static enum drm_gpu_sched_stat -v3d_gpu_reset_for_timeout(struct v3d_dev *v3d, struct drm_sched_job *sched_job) +v3d_gpu_reset_for_timeout(struct v3d_dev *v3d, struct drm_sched_job *sched_job, + enum v3d_queue q) { struct v3d_job *job = to_v3d_job(sched_job); - struct v3d_file_priv *v3d_priv = job->file->driver_priv; - enum v3d_queue q; + struct v3d_file_priv *v3d_priv = job->file_priv; + unsigned long irqflags; + enum v3d_queue i; mutex_lock(&v3d->reset_lock); /* block scheduler */ - for (q = 0; q < V3D_MAX_QUEUES; q++) - drm_sched_stop(&v3d->queue[q].sched, sched_job); + for (i = 0; i < V3D_MAX_QUEUES; i++) + drm_sched_stop(&v3d->queue[i].sched, sched_job); if (sched_job) drm_sched_increase_karma(sched_job); @@ -738,15 +743,17 @@ v3d_gpu_reset_for_timeout(struct v3d_dev *v3d, struct drm_sched_job *sched_job) v3d_reset(v3d); v3d->reset_counter++; - v3d_priv->reset_counter++; + spin_lock_irqsave(&v3d->queue[q].queue_lock, irqflags); + if (v3d_priv) + v3d_priv->reset_counter++; + spin_unlock_irqrestore(&v3d->queue[q].queue_lock, irqflags); - for (q = 0; q < V3D_MAX_QUEUES; q++) - drm_sched_resubmit_jobs(&v3d->queue[q].sched); + for (i = 0; i < V3D_MAX_QUEUES; i++) + drm_sched_resubmit_jobs(&v3d->queue[i].sched); /* Unblock schedulers and restart their jobs. */ - for (q = 0; q < V3D_MAX_QUEUES; q++) { - drm_sched_start(&v3d->queue[q].sched, 0); - } + for (i = 0; i < V3D_MAX_QUEUES; i++) + drm_sched_start(&v3d->queue[i].sched, 0); mutex_unlock(&v3d->reset_lock); @@ -774,7 +781,7 @@ v3d_cl_job_timedout(struct drm_sched_job *sched_job, enum v3d_queue q, return DRM_GPU_SCHED_STAT_NO_HANG; } - return v3d_gpu_reset_for_timeout(v3d, sched_job); + return v3d_gpu_reset_for_timeout(v3d, sched_job, q); } static enum drm_gpu_sched_stat @@ -796,11 +803,11 @@ v3d_render_job_timedout(struct drm_sched_job *sched_job) } static enum drm_gpu_sched_stat -v3d_generic_job_timedout(struct drm_sched_job *sched_job) +v3d_tfu_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); + return v3d_gpu_reset_for_timeout(job->v3d, sched_job, V3D_TFU); } static enum drm_gpu_sched_stat @@ -819,7 +826,7 @@ v3d_csd_job_timedout(struct drm_sched_job *sched_job) return DRM_GPU_SCHED_STAT_NO_HANG; } - return v3d_gpu_reset_for_timeout(v3d, sched_job); + return v3d_gpu_reset_for_timeout(v3d, sched_job, V3D_CSD); } static const struct drm_sched_backend_ops v3d_bin_sched_ops = { @@ -836,7 +843,7 @@ static const struct drm_sched_backend_ops v3d_render_sched_ops = { static const struct drm_sched_backend_ops v3d_tfu_sched_ops = { .run_job = v3d_tfu_job_run, - .timedout_job = v3d_generic_job_timedout, + .timedout_job = v3d_tfu_job_timedout, .free_job = v3d_sched_job_free, }; @@ -848,13 +855,11 @@ static const struct drm_sched_backend_ops v3d_csd_sched_ops = { static const struct drm_sched_backend_ops v3d_cache_clean_sched_ops = { .run_job = v3d_cache_clean_job_run, - .timedout_job = v3d_generic_job_timedout, .free_job = v3d_sched_job_free }; static const struct drm_sched_backend_ops v3d_cpu_sched_ops = { .run_job = v3d_cpu_job_run, - .timedout_job = v3d_generic_job_timedout, .free_job = v3d_cpu_job_free }; diff --git a/drivers/gpu/drm/v3d/v3d_submit.c b/drivers/gpu/drm/v3d/v3d_submit.c index 5171ffe9012d..f3652e90683c 100644 --- a/drivers/gpu/drm/v3d/v3d_submit.c +++ b/drivers/gpu/drm/v3d/v3d_submit.c @@ -166,7 +166,7 @@ v3d_job_init(struct v3d_dev *v3d, struct drm_file *file_priv, job->v3d = v3d; job->free = free; - job->file = file_priv; + job->file_priv = v3d_priv; ret = drm_sched_job_init(&job->base, &v3d_priv->sched_entity[queue], 1, v3d_priv, file_priv->client_id); diff --git a/drivers/gpu/drm/vkms/tests/vkms_config_test.c b/drivers/gpu/drm/vkms/tests/vkms_config_test.c index ff4566cf9925..b0d78a81d2df 100644 --- a/drivers/gpu/drm/vkms/tests/vkms_config_test.c +++ b/drivers/gpu/drm/vkms/tests/vkms_config_test.c @@ -200,6 +200,7 @@ static void vkms_config_test_get_planes(struct kunit *test) KUNIT_ASSERT_EQ(test, n_planes, 0); plane_cfg1 = vkms_config_create_plane(config); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, plane_cfg1); vkms_config_for_each_plane(config, plane_cfg) { n_planes++; if (plane_cfg != plane_cfg1) @@ -209,6 +210,7 @@ static void vkms_config_test_get_planes(struct kunit *test) n_planes = 0; plane_cfg2 = vkms_config_create_plane(config); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, plane_cfg2); vkms_config_for_each_plane(config, plane_cfg) { n_planes++; if (plane_cfg != plane_cfg1 && plane_cfg != plane_cfg2) @@ -242,6 +244,7 @@ static void vkms_config_test_get_crtcs(struct kunit *test) KUNIT_FAIL(test, "Unexpected CRTC"); crtc_cfg1 = vkms_config_create_crtc(config); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, crtc_cfg1); KUNIT_ASSERT_EQ(test, vkms_config_get_num_crtcs(config), 1); vkms_config_for_each_crtc(config, crtc_cfg) { if (crtc_cfg != crtc_cfg1) @@ -249,6 +252,7 @@ static void vkms_config_test_get_crtcs(struct kunit *test) } crtc_cfg2 = vkms_config_create_crtc(config); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, crtc_cfg2); KUNIT_ASSERT_EQ(test, vkms_config_get_num_crtcs(config), 2); vkms_config_for_each_crtc(config, crtc_cfg) { if (crtc_cfg != crtc_cfg1 && crtc_cfg != crtc_cfg2) @@ -280,6 +284,7 @@ static void vkms_config_test_get_encoders(struct kunit *test) KUNIT_ASSERT_EQ(test, n_encoders, 0); encoder_cfg1 = vkms_config_create_encoder(config); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, encoder_cfg1); vkms_config_for_each_encoder(config, encoder_cfg) { n_encoders++; if (encoder_cfg != encoder_cfg1) @@ -289,6 +294,7 @@ static void vkms_config_test_get_encoders(struct kunit *test) n_encoders = 0; encoder_cfg2 = vkms_config_create_encoder(config); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, encoder_cfg2); vkms_config_for_each_encoder(config, encoder_cfg) { n_encoders++; if (encoder_cfg != encoder_cfg1 && encoder_cfg != encoder_cfg2) @@ -324,6 +330,7 @@ static void vkms_config_test_get_connectors(struct kunit *test) KUNIT_ASSERT_EQ(test, n_connectors, 0); connector_cfg1 = vkms_config_create_connector(config); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, connector_cfg1); vkms_config_for_each_connector(config, connector_cfg) { n_connectors++; if (connector_cfg != connector_cfg1) @@ -333,6 +340,7 @@ static void vkms_config_test_get_connectors(struct kunit *test) n_connectors = 0; connector_cfg2 = vkms_config_create_connector(config); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, connector_cfg2); vkms_config_for_each_connector(config, connector_cfg) { n_connectors++; if (connector_cfg != connector_cfg1 && @@ -370,7 +378,7 @@ static void vkms_config_test_invalid_plane_number(struct kunit *test) /* Invalid: Too many planes */ for (n = 0; n <= 32; n++) - vkms_config_create_plane(config); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, vkms_config_create_plane(config)); KUNIT_EXPECT_FALSE(test, vkms_config_is_valid(config)); @@ -395,6 +403,7 @@ static void vkms_config_test_valid_plane_type(struct kunit *test) /* Invalid: No primary plane */ plane_cfg = vkms_config_create_plane(config); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, plane_cfg); vkms_config_plane_set_type(plane_cfg, DRM_PLANE_TYPE_OVERLAY); err = vkms_config_plane_attach_crtc(plane_cfg, crtc_cfg); KUNIT_EXPECT_EQ(test, err, 0); @@ -402,11 +411,13 @@ static void vkms_config_test_valid_plane_type(struct kunit *test) /* Invalid: Multiple primary planes */ plane_cfg = vkms_config_create_plane(config); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, plane_cfg); vkms_config_plane_set_type(plane_cfg, DRM_PLANE_TYPE_PRIMARY); err = vkms_config_plane_attach_crtc(plane_cfg, crtc_cfg); KUNIT_EXPECT_EQ(test, err, 0); plane_cfg = vkms_config_create_plane(config); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, plane_cfg); vkms_config_plane_set_type(plane_cfg, DRM_PLANE_TYPE_PRIMARY); err = vkms_config_plane_attach_crtc(plane_cfg, crtc_cfg); KUNIT_EXPECT_EQ(test, err, 0); @@ -419,11 +430,13 @@ static void vkms_config_test_valid_plane_type(struct kunit *test) /* Invalid: Multiple cursor planes */ plane_cfg = vkms_config_create_plane(config); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, plane_cfg); vkms_config_plane_set_type(plane_cfg, DRM_PLANE_TYPE_CURSOR); err = vkms_config_plane_attach_crtc(plane_cfg, crtc_cfg); KUNIT_EXPECT_EQ(test, err, 0); plane_cfg = vkms_config_create_plane(config); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, plane_cfg); vkms_config_plane_set_type(plane_cfg, DRM_PLANE_TYPE_CURSOR); err = vkms_config_plane_attach_crtc(plane_cfg, crtc_cfg); KUNIT_EXPECT_EQ(test, err, 0); @@ -437,12 +450,16 @@ static void vkms_config_test_valid_plane_type(struct kunit *test) /* Invalid: Second CRTC without primary plane */ crtc_cfg = vkms_config_create_crtc(config); encoder_cfg = vkms_config_create_encoder(config); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, crtc_cfg); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, encoder_cfg); + err = vkms_config_encoder_attach_crtc(encoder_cfg, crtc_cfg); KUNIT_EXPECT_EQ(test, err, 0); KUNIT_EXPECT_FALSE(test, vkms_config_is_valid(config)); /* Valid: Second CRTC with a primary plane */ plane_cfg = vkms_config_create_plane(config); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, plane_cfg); vkms_config_plane_set_type(plane_cfg, DRM_PLANE_TYPE_PRIMARY); err = vkms_config_plane_attach_crtc(plane_cfg, crtc_cfg); KUNIT_EXPECT_EQ(test, err, 0); @@ -486,7 +503,7 @@ static void vkms_config_test_invalid_crtc_number(struct kunit *test) /* Invalid: Too many CRTCs */ for (n = 0; n <= 32; n++) - vkms_config_create_crtc(config); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, vkms_config_create_crtc(config)); KUNIT_EXPECT_FALSE(test, vkms_config_is_valid(config)); @@ -509,7 +526,7 @@ static void vkms_config_test_invalid_encoder_number(struct kunit *test) /* Invalid: Too many encoders */ for (n = 0; n <= 32; n++) - vkms_config_create_encoder(config); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, vkms_config_create_encoder(config)); KUNIT_EXPECT_FALSE(test, vkms_config_is_valid(config)); @@ -531,12 +548,15 @@ static void vkms_config_test_valid_encoder_possible_crtcs(struct kunit *test) /* Invalid: Encoder without a possible CRTC */ encoder_cfg = vkms_config_create_encoder(config); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, encoder_cfg); KUNIT_EXPECT_FALSE(test, vkms_config_is_valid(config)); /* Valid: Second CRTC with shared encoder */ crtc_cfg2 = vkms_config_create_crtc(config); - plane_cfg = vkms_config_create_plane(config); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, crtc_cfg2); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, plane_cfg); + vkms_config_plane_set_type(plane_cfg, DRM_PLANE_TYPE_PRIMARY); err = vkms_config_plane_attach_crtc(plane_cfg, crtc_cfg2); KUNIT_EXPECT_EQ(test, err, 0); @@ -577,7 +597,7 @@ static void vkms_config_test_invalid_connector_number(struct kunit *test) /* Invalid: Too many connectors */ for (n = 0; n <= 32; n++) - connector_cfg = vkms_config_create_connector(config); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, vkms_config_create_connector(config)); KUNIT_EXPECT_FALSE(test, vkms_config_is_valid(config)); @@ -669,13 +689,19 @@ static void vkms_config_test_plane_attach_crtc(struct kunit *test) KUNIT_ASSERT_NOT_ERR_OR_NULL(test, config); overlay_cfg = vkms_config_create_plane(config); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, overlay_cfg); vkms_config_plane_set_type(overlay_cfg, DRM_PLANE_TYPE_OVERLAY); + primary_cfg = vkms_config_create_plane(config); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, primary_cfg); vkms_config_plane_set_type(primary_cfg, DRM_PLANE_TYPE_PRIMARY); + cursor_cfg = vkms_config_create_plane(config); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, cursor_cfg); vkms_config_plane_set_type(cursor_cfg, DRM_PLANE_TYPE_CURSOR); crtc_cfg = vkms_config_create_crtc(config); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, crtc_cfg); /* No primary or cursor planes */ KUNIT_EXPECT_NULL(test, vkms_config_crtc_primary_plane(config, crtc_cfg)); @@ -735,6 +761,11 @@ static void vkms_config_test_plane_get_possible_crtcs(struct kunit *test) crtc_cfg1 = vkms_config_create_crtc(config); crtc_cfg2 = vkms_config_create_crtc(config); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, plane_cfg1); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, plane_cfg2); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, crtc_cfg1); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, crtc_cfg2); + /* No possible CRTCs */ vkms_config_plane_for_each_possible_crtc(plane_cfg1, idx, possible_crtc) KUNIT_FAIL(test, "Unexpected possible CRTC"); @@ -799,6 +830,11 @@ static void vkms_config_test_encoder_get_possible_crtcs(struct kunit *test) crtc_cfg1 = vkms_config_create_crtc(config); crtc_cfg2 = vkms_config_create_crtc(config); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, encoder_cfg1); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, encoder_cfg2); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, crtc_cfg1); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, crtc_cfg2); + /* No possible CRTCs */ vkms_config_encoder_for_each_possible_crtc(encoder_cfg1, idx, possible_crtc) KUNIT_FAIL(test, "Unexpected possible CRTC"); @@ -863,6 +899,11 @@ static void vkms_config_test_connector_get_possible_encoders(struct kunit *test) encoder_cfg1 = vkms_config_create_encoder(config); encoder_cfg2 = vkms_config_create_encoder(config); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, connector_cfg1); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, connector_cfg2); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, encoder_cfg1); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, encoder_cfg2); + /* No possible encoders */ vkms_config_connector_for_each_possible_encoder(connector_cfg1, idx, possible_encoder) diff --git a/drivers/gpu/drm/vkms/tests/vkms_format_test.c b/drivers/gpu/drm/vkms/tests/vkms_format_test.c index 2e1daef94831..a7788fbc45dc 100644 --- a/drivers/gpu/drm/vkms/tests/vkms_format_test.c +++ b/drivers/gpu/drm/vkms/tests/vkms_format_test.c @@ -14,20 +14,20 @@ MODULE_IMPORT_NS("EXPORTED_FOR_KUNIT_TESTING"); /** - * struct pixel_yuv_u8 - Internal representation of a pixel color. - * @y: Luma value, stored in 8 bits, without padding, using + * struct pixel_yuv_u16 - Internal representation of a pixel color. + * @y: Luma value, stored in 16 bits, without padding, using * machine endianness - * @u: Blue difference chroma value, stored in 8 bits, without padding, using + * @u: Blue difference chroma value, stored in 16 bits, without padding, using * machine endianness - * @v: Red difference chroma value, stored in 8 bits, without padding, using + * @v: Red difference chroma value, stored in 16 bits, without padding, using * machine endianness */ -struct pixel_yuv_u8 { - u8 y, u, v; +struct pixel_yuv_u16 { + u16 y, u, v; }; /* - * struct yuv_u8_to_argb_u16_case - Reference values to test the color + * struct yuv_u16_to_argb_u16_case - Reference values to test the color * conversions in VKMS between YUV to ARGB * * @encoding: Encoding used to convert RGB to YUV @@ -39,13 +39,13 @@ struct pixel_yuv_u8 { * @format_pair.yuv: Same color as @format_pair.rgb, but converted to * YUV using @encoding and @range. */ -struct yuv_u8_to_argb_u16_case { +struct yuv_u16_to_argb_u16_case { enum drm_color_encoding encoding; enum drm_color_range range; size_t n_colors; struct format_pair { char *name; - struct pixel_yuv_u8 yuv; + struct pixel_yuv_u16 yuv; struct pixel_argb_u16 argb; } colors[TEST_BUFF_SIZE]; }; @@ -57,14 +57,14 @@ struct yuv_u8_to_argb_u16_case { * For more information got to the docs: * https://colour.readthedocs.io/en/master/generated/colour.RGB_to_YCbCr.html */ -static struct yuv_u8_to_argb_u16_case yuv_u8_to_argb_u16_cases[] = { +static struct yuv_u16_to_argb_u16_case yuv_u16_to_argb_u16_cases[] = { /* * colour.RGB_to_YCbCr(<rgb color in 16 bit form>, * K=colour.WEIGHTS_YCBCR["ITU-R BT.601"], * in_bits = 16, * in_legal = False, * in_int = True, - * out_bits = 8, + * out_bits = 16, * out_legal = False, * out_int = True) * @@ -76,13 +76,13 @@ static struct yuv_u8_to_argb_u16_case yuv_u8_to_argb_u16_cases[] = { .range = DRM_COLOR_YCBCR_FULL_RANGE, .n_colors = 6, .colors = { - { "white", { 0xff, 0x80, 0x80 }, { 0xffff, 0xffff, 0xffff, 0xffff }}, - { "gray", { 0x80, 0x80, 0x80 }, { 0xffff, 0x8080, 0x8080, 0x8080 }}, - { "black", { 0x00, 0x80, 0x80 }, { 0xffff, 0x0000, 0x0000, 0x0000 }}, - { "red", { 0x4c, 0x55, 0xff }, { 0xffff, 0xffff, 0x0000, 0x0000 }}, - { "green", { 0x96, 0x2c, 0x15 }, { 0xffff, 0x0000, 0xffff, 0x0000 }}, - { "blue", { 0x1d, 0xff, 0x6b }, { 0xffff, 0x0000, 0x0000, 0xffff }}, - }, + { "white", { 0xffff, 0x8000, 0x8000 }, { 0xffff, 0xffff, 0xffff, 0xffff }}, + { "gray", { 0x8080, 0x8000, 0x8000 }, { 0xffff, 0x8080, 0x8080, 0x8080 }}, + { "black", { 0x0000, 0x8000, 0x8000 }, { 0xffff, 0x0000, 0x0000, 0x0000 }}, + { "red", { 0x4c8b, 0x54ce, 0xffff }, { 0xffff, 0xffff, 0x0000, 0x0000 }}, + { "green", { 0x9645, 0x2b33, 0x14d1 }, { 0xffff, 0x0000, 0xffff, 0x0000 }}, + { "blue", { 0x1d2f, 0xffff, 0x6b2f }, { 0xffff, 0x0000, 0x0000, 0xffff }}, + } }, /* * colour.RGB_to_YCbCr(<rgb color in 16 bit form>, @@ -90,7 +90,7 @@ static struct yuv_u8_to_argb_u16_case yuv_u8_to_argb_u16_cases[] = { * in_bits = 16, * in_legal = False, * in_int = True, - * out_bits = 8, + * out_bits = 16, * out_legal = True, * out_int = True) * Tests cases for color conversion generated by converting RGB @@ -101,13 +101,13 @@ static struct yuv_u8_to_argb_u16_case yuv_u8_to_argb_u16_cases[] = { .range = DRM_COLOR_YCBCR_LIMITED_RANGE, .n_colors = 6, .colors = { - { "white", { 0xeb, 0x80, 0x80 }, { 0xffff, 0xffff, 0xffff, 0xffff }}, - { "gray", { 0x7e, 0x80, 0x80 }, { 0xffff, 0x8080, 0x8080, 0x8080 }}, - { "black", { 0x10, 0x80, 0x80 }, { 0xffff, 0x0000, 0x0000, 0x0000 }}, - { "red", { 0x51, 0x5a, 0xf0 }, { 0xffff, 0xffff, 0x0000, 0x0000 }}, - { "green", { 0x91, 0x36, 0x22 }, { 0xffff, 0x0000, 0xffff, 0x0000 }}, - { "blue", { 0x29, 0xf0, 0x6e }, { 0xffff, 0x0000, 0x0000, 0xffff }}, - }, + { "white", { 0xeb00, 0x8000, 0x8000 }, { 0xffff, 0xffff, 0xffff, 0xffff }}, + { "gray", { 0x7dee, 0x8000, 0x8000 }, { 0xffff, 0x8080, 0x8080, 0x8080 }}, + { "black", { 0x1000, 0x8000, 0x8000 }, { 0xffff, 0x0000, 0x0000, 0x0000 }}, + { "red", { 0x517b, 0x5a34, 0xf000 }, { 0xffff, 0xffff, 0x0000, 0x0000 }}, + { "green", { 0x908e, 0x35cc, 0x2237 }, { 0xffff, 0x0000, 0xffff, 0x0000 }}, + { "blue", { 0x28f7, 0xf000, 0x6dc9 }, { 0xffff, 0x0000, 0x0000, 0xffff }}, + } }, /* * colour.RGB_to_YCbCr(<rgb color in 16 bit form>, @@ -115,7 +115,7 @@ static struct yuv_u8_to_argb_u16_case yuv_u8_to_argb_u16_cases[] = { * in_bits = 16, * in_legal = False, * in_int = True, - * out_bits = 8, + * out_bits = 16, * out_legal = False, * out_int = True) * Tests cases for color conversion generated by converting RGB @@ -126,21 +126,21 @@ static struct yuv_u8_to_argb_u16_case yuv_u8_to_argb_u16_cases[] = { .range = DRM_COLOR_YCBCR_FULL_RANGE, .n_colors = 6, .colors = { - { "white", { 0xff, 0x80, 0x80 }, { 0xffff, 0xffff, 0xffff, 0xffff }}, - { "gray", { 0x80, 0x80, 0x80 }, { 0xffff, 0x8080, 0x8080, 0x8080 }}, - { "black", { 0x00, 0x80, 0x80 }, { 0xffff, 0x0000, 0x0000, 0x0000 }}, - { "red", { 0x36, 0x63, 0xff }, { 0xffff, 0xffff, 0x0000, 0x0000 }}, - { "green", { 0xb6, 0x1e, 0x0c }, { 0xffff, 0x0000, 0xffff, 0x0000 }}, - { "blue", { 0x12, 0xff, 0x74 }, { 0xffff, 0x0000, 0x0000, 0xffff }}, - }, + { "white", { 0xffff, 0x8000, 0x8000 }, { 0xffff, 0xffff, 0xffff, 0xffff }}, + { "gray", { 0x8080, 0x8000, 0x8000 }, { 0xffff, 0x8080, 0x8080, 0x8080 }}, + { "black", { 0x0000, 0x8000, 0x8000 }, { 0xffff, 0x0000, 0x0000, 0x0000 }}, + { "red", { 0x366d, 0x62ac, 0xffff }, { 0xffff, 0xffff, 0x0000, 0x0000 }}, + { "green", { 0xb717, 0x1d55, 0x0bbd }, { 0xffff, 0x0000, 0xffff, 0x0000 }}, + { "blue", { 0x127c, 0xffff, 0x7443 }, { 0xffff, 0x0000, 0x0000, 0xffff }}, + } }, /* * colour.RGB_to_YCbCr(<rgb color in 16 bit form>, * K=colour.WEIGHTS_YCBCR["ITU-R BT.709"], * in_bits = 16, - * int_legal = False, + * in_legal = False, * in_int = True, - * out_bits = 8, + * out_bits = 16, * out_legal = True, * out_int = True) * Tests cases for color conversion generated by converting RGB @@ -151,13 +151,13 @@ static struct yuv_u8_to_argb_u16_case yuv_u8_to_argb_u16_cases[] = { .range = DRM_COLOR_YCBCR_LIMITED_RANGE, .n_colors = 6, .colors = { - { "white", { 0xeb, 0x80, 0x80 }, { 0xffff, 0xffff, 0xffff, 0xffff }}, - { "gray", { 0x7e, 0x80, 0x80 }, { 0xffff, 0x8080, 0x8080, 0x8080 }}, - { "black", { 0x10, 0x80, 0x80 }, { 0xffff, 0x0000, 0x0000, 0x0000 }}, - { "red", { 0x3f, 0x66, 0xf0 }, { 0xffff, 0xffff, 0x0000, 0x0000 }}, - { "green", { 0xad, 0x2a, 0x1a }, { 0xffff, 0x0000, 0xffff, 0x0000 }}, - { "blue", { 0x20, 0xf0, 0x76 }, { 0xffff, 0x0000, 0x0000, 0xffff }}, - }, + { "white", { 0xeb00, 0x8000, 0x8000 }, { 0xffff, 0xffff, 0xffff, 0xffff }}, + { "gray", { 0x7dee, 0x8000, 0x8000 }, { 0xffff, 0x8080, 0x8080, 0x8080 }}, + { "black", { 0x1000, 0x8000, 0x8000 }, { 0xffff, 0x0000, 0x0000, 0x0000 }}, + { "red", { 0x3e8f, 0x6656, 0xf000 }, { 0xffff, 0xffff, 0x0000, 0x0000 }}, + { "green", { 0xaca1, 0x29aa, 0x1a45 }, { 0xffff, 0x0000, 0xffff, 0x0000 }}, + { "blue", { 0x1fd0, 0xf000, 0x75bb }, { 0xffff, 0x0000, 0x0000, 0xffff }}, + } }, /* * colour.RGB_to_YCbCr(<rgb color in 16 bit form>, @@ -165,7 +165,7 @@ static struct yuv_u8_to_argb_u16_case yuv_u8_to_argb_u16_cases[] = { * in_bits = 16, * in_legal = False, * in_int = True, - * out_bits = 8, + * out_bits = 16, * out_legal = False, * out_int = True) * Tests cases for color conversion generated by converting RGB @@ -176,13 +176,13 @@ static struct yuv_u8_to_argb_u16_case yuv_u8_to_argb_u16_cases[] = { .range = DRM_COLOR_YCBCR_FULL_RANGE, .n_colors = 6, .colors = { - { "white", { 0xff, 0x80, 0x80 }, { 0xffff, 0xffff, 0xffff, 0xffff }}, - { "gray", { 0x80, 0x80, 0x80 }, { 0xffff, 0x8080, 0x8080, 0x8080 }}, - { "black", { 0x00, 0x80, 0x80 }, { 0xffff, 0x0000, 0x0000, 0x0000 }}, - { "red", { 0x43, 0x5c, 0xff }, { 0xffff, 0xffff, 0x0000, 0x0000 }}, - { "green", { 0xad, 0x24, 0x0b }, { 0xffff, 0x0000, 0xffff, 0x0000 }}, - { "blue", { 0x0f, 0xff, 0x76 }, { 0xffff, 0x0000, 0x0000, 0xffff }}, - }, + { "white", { 0xffff, 0x8000, 0x8000 }, { 0xffff, 0xffff, 0xffff, 0xffff }}, + { "gray", { 0x8080, 0x8000, 0x8000 }, { 0xffff, 0x8080, 0x8080, 0x8080 }}, + { "black", { 0x0000, 0x8000, 0x8000 }, { 0xffff, 0x0000, 0x0000, 0x0000 }}, + { "red", { 0x4340, 0x5c41, 0xffff }, { 0xffff, 0xffff, 0x0000, 0x0000 }}, + { "green", { 0xad91, 0x23bf, 0x0a4c }, { 0xffff, 0x0000, 0xffff, 0x0000 }}, + { "blue", { 0x0f2e, 0xffff, 0x75b5 }, { 0xffff, 0x0000, 0x0000, 0xffff }}, + } }, /* * colour.RGB_to_YCbCr(<rgb color in 16 bit form>, @@ -190,7 +190,7 @@ static struct yuv_u8_to_argb_u16_case yuv_u8_to_argb_u16_cases[] = { * in_bits = 16, * in_legal = False, * in_int = True, - * out_bits = 8, + * out_bits = 16, * out_legal = True, * out_int = True) * Tests cases for color conversion generated by converting RGB @@ -201,32 +201,30 @@ static struct yuv_u8_to_argb_u16_case yuv_u8_to_argb_u16_cases[] = { .range = DRM_COLOR_YCBCR_LIMITED_RANGE, .n_colors = 6, .colors = { - { "white", { 0xeb, 0x80, 0x80 }, { 0xffff, 0xffff, 0xffff, 0xffff }}, - { "gray", { 0x7e, 0x80, 0x80 }, { 0xffff, 0x8080, 0x8080, 0x8080 }}, - { "black", { 0x10, 0x80, 0x80 }, { 0xffff, 0x0000, 0x0000, 0x0000 }}, - { "red", { 0x4a, 0x61, 0xf0 }, { 0xffff, 0xffff, 0x0000, 0x0000 }}, - { "green", { 0xa4, 0x2f, 0x19 }, { 0xffff, 0x0000, 0xffff, 0x0000 }}, - { "blue", { 0x1d, 0xf0, 0x77 }, { 0xffff, 0x0000, 0x0000, 0xffff }}, - }, + { "white", { 0xeb00, 0x8000, 0x8000 }, { 0xffff, 0xffff, 0xffff, 0xffff }}, + { "gray", { 0x7dee, 0x8000, 0x8000 }, { 0xffff, 0x8080, 0x8080, 0x8080 }}, + { "black", { 0x1000, 0x8000, 0x8000 }, { 0xffff, 0x0000, 0x0000, 0x0000 }}, + { "red", { 0x4988, 0x60b9, 0xf000 }, { 0xffff, 0xffff, 0x0000, 0x0000 }}, + { "green", { 0xa47b, 0x2f47, 0x1902 }, { 0xffff, 0x0000, 0xffff, 0x0000 }}, + { "blue", { 0x1cfd, 0xf000, 0x76fe }, { 0xffff, 0x0000, 0x0000, 0xffff }}, + } }, }; /* - * vkms_format_test_yuv_u8_to_argb_u16 - Testing the conversion between YUV + * vkms_format_test_yuv_u16_to_argb_u16 - Testing the conversion between YUV * colors to ARGB colors in VKMS * * This test will use the functions get_conversion_matrix_to_argb_u16 and - * argb_u16_from_yuv888 to convert YUV colors (stored in - * yuv_u8_to_argb_u16_cases) into ARGB colors. + * argb_u16_from_yuv161616 to convert YUV colors (stored in + * yuv_u16_to_argb_u16_cases) into ARGB colors. * * The conversion between YUV and RGB is not totally reversible, so there may be * some difference between the expected value and the result. - * In addition, there may be some rounding error as the input color is 8 bits - * and output color is 16 bits. */ -static void vkms_format_test_yuv_u8_to_argb_u16(struct kunit *test) +static void vkms_format_test_yuv_u16_to_argb_u16(struct kunit *test) { - const struct yuv_u8_to_argb_u16_case *param = test->param_value; + const struct yuv_u16_to_argb_u16_case *param = test->param_value; struct pixel_argb_u16 argb; for (size_t i = 0; i < param->n_colors; i++) { @@ -236,7 +234,8 @@ static void vkms_format_test_yuv_u8_to_argb_u16(struct kunit *test) get_conversion_matrix_to_argb_u16 (DRM_FORMAT_NV12, param->encoding, param->range, &matrix); - argb = argb_u16_from_yuv888(color->yuv.y, color->yuv.u, color->yuv.v, &matrix); + argb = argb_u16_from_yuv161616(&matrix, color->yuv.y, color->yuv.u, + color->yuv.v); KUNIT_EXPECT_LE_MSG(test, abs_diff(argb.a, color->argb.a), 0x1ff, "On the A channel of the color %s expected 0x%04x, got 0x%04x", @@ -253,19 +252,19 @@ static void vkms_format_test_yuv_u8_to_argb_u16(struct kunit *test) } } -static void vkms_format_test_yuv_u8_to_argb_u16_case_desc(struct yuv_u8_to_argb_u16_case *t, - char *desc) +static void vkms_format_test_yuv_u16_to_argb_u16_case_desc(struct yuv_u16_to_argb_u16_case *t, + char *desc) { snprintf(desc, KUNIT_PARAM_DESC_SIZE, "%s - %s", drm_get_color_encoding_name(t->encoding), drm_get_color_range_name(t->range)); } -KUNIT_ARRAY_PARAM(yuv_u8_to_argb_u16, yuv_u8_to_argb_u16_cases, - vkms_format_test_yuv_u8_to_argb_u16_case_desc +KUNIT_ARRAY_PARAM(yuv_u16_to_argb_u16, yuv_u16_to_argb_u16_cases, + vkms_format_test_yuv_u16_to_argb_u16_case_desc ); static struct kunit_case vkms_format_test_cases[] = { - KUNIT_CASE_PARAM(vkms_format_test_yuv_u8_to_argb_u16, yuv_u8_to_argb_u16_gen_params), + KUNIT_CASE_PARAM(vkms_format_test_yuv_u16_to_argb_u16, yuv_u16_to_argb_u16_gen_params), {} }; diff --git a/drivers/gpu/drm/vkms/vkms_formats.c b/drivers/gpu/drm/vkms/vkms_formats.c index 6d0227c6635a..dfb8e13cba87 100644 --- a/drivers/gpu/drm/vkms/vkms_formats.c +++ b/drivers/gpu/drm/vkms/vkms_formats.c @@ -259,16 +259,27 @@ static struct pixel_argb_u16 argb_u16_from_grayu16(u16 gray) return argb_u16_from_u16161616(0xFFFF, gray, gray, gray); } -VISIBLE_IF_KUNIT struct pixel_argb_u16 argb_u16_from_yuv888(u8 y, u8 channel_1, u8 channel_2, - const struct conversion_matrix *matrix) +static struct pixel_argb_u16 argb_u16_from_BGR565(const __le16 *pixel) +{ + struct pixel_argb_u16 out_pixel; + + out_pixel = argb_u16_from_RGB565(pixel); + swap(out_pixel.r, out_pixel.b); + + return out_pixel; +} + +VISIBLE_IF_KUNIT +struct pixel_argb_u16 argb_u16_from_yuv161616(const struct conversion_matrix *matrix, + u16 y, u16 channel_1, u16 channel_2) { u16 r, g, b; s64 fp_y, fp_channel_1, fp_channel_2; s64 fp_r, fp_g, fp_b; - fp_y = drm_int2fixp(((int)y - matrix->y_offset) * 257); - fp_channel_1 = drm_int2fixp(((int)channel_1 - 128) * 257); - fp_channel_2 = drm_int2fixp(((int)channel_2 - 128) * 257); + fp_y = drm_int2fixp((int)y - matrix->y_offset * 257); + fp_channel_1 = drm_int2fixp((int)channel_1 - 128 * 257); + fp_channel_2 = drm_int2fixp((int)channel_2 - 128 * 257); fp_r = drm_fixp_mul(matrix->matrix[0][0], fp_y) + drm_fixp_mul(matrix->matrix[0][1], fp_channel_1) + @@ -290,7 +301,65 @@ VISIBLE_IF_KUNIT struct pixel_argb_u16 argb_u16_from_yuv888(u8 y, u8 channel_1, return argb_u16_from_u16161616(0xffff, r, g, b); } -EXPORT_SYMBOL_IF_KUNIT(argb_u16_from_yuv888); +EXPORT_SYMBOL_IF_KUNIT(argb_u16_from_yuv161616); + +/** + * READ_LINE() - Generic generator for a read_line function which can be used for format with one + * plane and a block_h == block_w == 1. + * + * @function_name: Function name to generate + * @pixel_name: Temporary pixel name used in the @__VA_ARGS__ parameters + * @pixel_type: Used to specify the type you want to cast the pixel pointer + * @callback: Callback to call for each pixels. This fonction should take @__VA_ARGS__ as parameter + * and return a pixel_argb_u16 + * __VA_ARGS__: Argument to pass inside the callback. You can use @pixel_name to access current + * pixel. + */ +#define READ_LINE(function_name, pixel_name, pixel_type, callback, ...) \ +static void function_name(const struct vkms_plane_state *plane, int x_start, \ + int y_start, enum pixel_read_direction direction, int count, \ + struct pixel_argb_u16 out_pixel[]) \ +{ \ + struct pixel_argb_u16 *end = out_pixel + count; \ + int step = get_block_step_bytes(plane->frame_info->fb, direction, 0); \ + u8 *src_pixels; \ + \ + packed_pixels_addr_1x1(plane->frame_info, x_start, y_start, 0, &src_pixels); \ + \ + while (out_pixel < end) { \ + pixel_type *(pixel_name) = (pixel_type *)src_pixels; \ + *out_pixel = (callback)(__VA_ARGS__); \ + out_pixel += 1; \ + src_pixels += step; \ + } \ +} + +/** + * READ_LINE_ARGB8888() - Generic generator for ARGB8888 formats. + * The pixel type used is u8, so pixel_name[0]..pixel_name[n] are the n components of the pixel. + * + * @function_name: Function name to generate + * @pixel_name: temporary pixel to use in @a, @r, @g and @b parameters + * @a: alpha value + * @r: red value + * @g: green value + * @b: blue value + */ +#define READ_LINE_ARGB8888(function_name, pixel_name, a, r, g, b) \ + READ_LINE(function_name, pixel_name, u8, argb_u16_from_u8888, a, r, g, b) +/** + * READ_LINE_le16161616() - Generic generator for ARGB16161616 formats. + * The pixel type used is u16, so pixel_name[0]..pixel_name[n] are the n components of the pixel. + * + * @function_name: Function name to generate + * @pixel_name: temporary pixel to use in @a, @r, @g and @b parameters + * @a: alpha value + * @r: red value + * @g: green value + * @b: blue value + */ +#define READ_LINE_le16161616(function_name, pixel_name, a, r, g, b) \ + READ_LINE(function_name, pixel_name, __le16, argb_u16_from_le16161616, a, r, g, b) /* * The following functions are read_line function for each pixel format supported by VKMS. @@ -378,138 +447,27 @@ static void R4_read_line(const struct vkms_plane_state *plane, int x_start, Rx_read_line(plane, x_start, y_start, direction, count, out_pixel); } -static void R8_read_line(const struct vkms_plane_state *plane, int x_start, - int y_start, enum pixel_read_direction direction, int count, - struct pixel_argb_u16 out_pixel[]) -{ - struct pixel_argb_u16 *end = out_pixel + count; - u8 *src_pixels; - int step = get_block_step_bytes(plane->frame_info->fb, direction, 0); - - packed_pixels_addr_1x1(plane->frame_info, x_start, y_start, 0, &src_pixels); - - while (out_pixel < end) { - *out_pixel = argb_u16_from_gray8(*src_pixels); - src_pixels += step; - out_pixel += 1; - } -} - -static void ARGB8888_read_line(const struct vkms_plane_state *plane, int x_start, int y_start, - enum pixel_read_direction direction, int count, - struct pixel_argb_u16 out_pixel[]) -{ - struct pixel_argb_u16 *end = out_pixel + count; - u8 *src_pixels; - - packed_pixels_addr_1x1(plane->frame_info, x_start, y_start, 0, &src_pixels); - - int step = get_block_step_bytes(plane->frame_info->fb, direction, 0); - - while (out_pixel < end) { - u8 *px = (u8 *)src_pixels; - *out_pixel = argb_u16_from_u8888(px[3], px[2], px[1], px[0]); - out_pixel += 1; - src_pixels += step; - } -} - -static void XRGB8888_read_line(const struct vkms_plane_state *plane, int x_start, int y_start, - enum pixel_read_direction direction, int count, - struct pixel_argb_u16 out_pixel[]) -{ - struct pixel_argb_u16 *end = out_pixel + count; - u8 *src_pixels; - - packed_pixels_addr_1x1(plane->frame_info, x_start, y_start, 0, &src_pixels); - - int step = get_block_step_bytes(plane->frame_info->fb, direction, 0); - - while (out_pixel < end) { - u8 *px = (u8 *)src_pixels; - *out_pixel = argb_u16_from_u8888(255, px[2], px[1], px[0]); - out_pixel += 1; - src_pixels += step; - } -} - -static void ABGR8888_read_line(const struct vkms_plane_state *plane, int x_start, int y_start, - enum pixel_read_direction direction, int count, - struct pixel_argb_u16 out_pixel[]) -{ - struct pixel_argb_u16 *end = out_pixel + count; - u8 *src_pixels; - - packed_pixels_addr_1x1(plane->frame_info, x_start, y_start, 0, &src_pixels); - - int step = get_block_step_bytes(plane->frame_info->fb, direction, 0); - - while (out_pixel < end) { - u8 *px = (u8 *)src_pixels; - /* Switch blue and red pixels. */ - *out_pixel = argb_u16_from_u8888(px[3], px[0], px[1], px[2]); - out_pixel += 1; - src_pixels += step; - } -} - -static void ARGB16161616_read_line(const struct vkms_plane_state *plane, int x_start, - int y_start, enum pixel_read_direction direction, int count, - struct pixel_argb_u16 out_pixel[]) -{ - struct pixel_argb_u16 *end = out_pixel + count; - u8 *src_pixels; - - packed_pixels_addr_1x1(plane->frame_info, x_start, y_start, 0, &src_pixels); - - int step = get_block_step_bytes(plane->frame_info->fb, direction, 0); - while (out_pixel < end) { - u16 *px = (u16 *)src_pixels; - *out_pixel = argb_u16_from_u16161616(px[3], px[2], px[1], px[0]); - out_pixel += 1; - src_pixels += step; - } -} +READ_LINE_ARGB8888(XRGB8888_read_line, px, 0xFF, px[2], px[1], px[0]) +READ_LINE_ARGB8888(XBGR8888_read_line, px, 0xFF, px[0], px[1], px[2]) -static void XRGB16161616_read_line(const struct vkms_plane_state *plane, int x_start, - int y_start, enum pixel_read_direction direction, int count, - struct pixel_argb_u16 out_pixel[]) -{ - struct pixel_argb_u16 *end = out_pixel + count; - u8 *src_pixels; - - packed_pixels_addr_1x1(plane->frame_info, x_start, y_start, 0, &src_pixels); - - int step = get_block_step_bytes(plane->frame_info->fb, direction, 0); - - while (out_pixel < end) { - __le16 *px = (__le16 *)src_pixels; - *out_pixel = argb_u16_from_le16161616(cpu_to_le16(0xFFFF), px[2], px[1], px[0]); - out_pixel += 1; - src_pixels += step; - } -} - -static void RGB565_read_line(const struct vkms_plane_state *plane, int x_start, - int y_start, enum pixel_read_direction direction, int count, - struct pixel_argb_u16 out_pixel[]) -{ - struct pixel_argb_u16 *end = out_pixel + count; - u8 *src_pixels; +READ_LINE_ARGB8888(ARGB8888_read_line, px, px[3], px[2], px[1], px[0]) +READ_LINE_ARGB8888(ABGR8888_read_line, px, px[3], px[0], px[1], px[2]) +READ_LINE_ARGB8888(RGBA8888_read_line, px, px[0], px[3], px[2], px[1]) +READ_LINE_ARGB8888(BGRA8888_read_line, px, px[0], px[1], px[2], px[3]) - packed_pixels_addr_1x1(plane->frame_info, x_start, y_start, 0, &src_pixels); +READ_LINE_ARGB8888(RGB888_read_line, px, 0xFF, px[2], px[1], px[0]) +READ_LINE_ARGB8888(BGR888_read_line, px, 0xFF, px[0], px[1], px[2]) - int step = get_block_step_bytes(plane->frame_info->fb, direction, 0); +READ_LINE_le16161616(ARGB16161616_read_line, px, px[3], px[2], px[1], px[0]) +READ_LINE_le16161616(ABGR16161616_read_line, px, px[3], px[0], px[1], px[2]) +READ_LINE_le16161616(XRGB16161616_read_line, px, cpu_to_le16(0xFFFF), px[2], px[1], px[0]) +READ_LINE_le16161616(XBGR16161616_read_line, px, cpu_to_le16(0xFFFF), px[0], px[1], px[2]) - while (out_pixel < end) { - __le16 *px = (__le16 *)src_pixels; +READ_LINE(RGB565_read_line, px, __le16, argb_u16_from_RGB565, px) +READ_LINE(BGR565_read_line, px, __le16, argb_u16_from_BGR565, px) - *out_pixel = argb_u16_from_RGB565(px); - out_pixel += 1; - src_pixels += step; - } -} +READ_LINE(R8_read_line, px, u8, argb_u16_from_gray8, *px) /* * This callback can be used for YUV formats where U and V values are @@ -521,35 +479,57 @@ static void RGB565_read_line(const struct vkms_plane_state *plane, int x_start, * - Convert YUV and YVU with the same function (a column swap is needed when setting up * plane->conversion_matrix) */ -static void semi_planar_yuv_read_line(const struct vkms_plane_state *plane, int x_start, - int y_start, enum pixel_read_direction direction, int count, - struct pixel_argb_u16 out_pixel[]) -{ - u8 *y_plane; - u8 *uv_plane; - - packed_pixels_addr_1x1(plane->frame_info, x_start, y_start, 0, - &y_plane); - packed_pixels_addr_1x1(plane->frame_info, - x_start / plane->frame_info->fb->format->hsub, - y_start / plane->frame_info->fb->format->vsub, 1, - &uv_plane); - int step_y = get_block_step_bytes(plane->frame_info->fb, direction, 0); - int step_uv = get_block_step_bytes(plane->frame_info->fb, direction, 1); - int subsampling = get_subsampling(plane->frame_info->fb->format, direction); - int subsampling_offset = get_subsampling_offset(direction, x_start, y_start); - const struct conversion_matrix *conversion_matrix = &plane->conversion_matrix; - - for (int i = 0; i < count; i++) { - *out_pixel = argb_u16_from_yuv888(y_plane[0], uv_plane[0], uv_plane[1], - conversion_matrix); - out_pixel += 1; - y_plane += step_y; - if ((i + subsampling_offset + 1) % subsampling == 0) - uv_plane += step_uv; - } -} +/** + * READ_LINE_YUV_SEMIPLANAR() - Generic generator for a read_line function which can be used for yuv + * formats with two planes and block_w == block_h == 1. + * + * @function_name: Function name to generate + * @pixel_1_name: temporary pixel name for the first plane used in the @__VA_ARGS__ parameters + * @pixel_2_name: temporary pixel name for the second plane used in the @__VA_ARGS__ parameters + * @pixel_1_type: Used to specify the type you want to cast the pixel pointer on the plane 1 + * @pixel_2_type: Used to specify the type you want to cast the pixel pointer on the plane 2 + * @callback: Callback to call for each pixels. This function should take + * (struct conversion_matrix*, @__VA_ARGS__) as parameter and return a pixel_argb_u16 + * __VA_ARGS__: Argument to pass inside the callback. You can use @pixel_1_name and @pixel_2_name + * to access current pixel values + */ +#define READ_LINE_YUV_SEMIPLANAR(function_name, pixel_1_name, pixel_2_name, pixel_1_type, \ + pixel_2_type, callback, ...) \ +static void function_name(const struct vkms_plane_state *plane, int x_start, \ + int y_start, enum pixel_read_direction direction, int count, \ + struct pixel_argb_u16 out_pixel[]) \ +{ \ + u8 *plane_1; \ + u8 *plane_2; \ + \ + packed_pixels_addr_1x1(plane->frame_info, x_start, y_start, 0, \ + &plane_1); \ + packed_pixels_addr_1x1(plane->frame_info, \ + x_start / plane->frame_info->fb->format->hsub, \ + y_start / plane->frame_info->fb->format->vsub, 1, \ + &plane_2); \ + int step_1 = get_block_step_bytes(plane->frame_info->fb, direction, 0); \ + int step_2 = get_block_step_bytes(plane->frame_info->fb, direction, 1); \ + int subsampling = get_subsampling(plane->frame_info->fb->format, direction); \ + int subsampling_offset = get_subsampling_offset(direction, x_start, y_start); \ + const struct conversion_matrix *conversion_matrix = &plane->conversion_matrix; \ + \ + for (int i = 0; i < count; i++) { \ + pixel_1_type *(pixel_1_name) = (pixel_1_type *)plane_1; \ + pixel_2_type *(pixel_2_name) = (pixel_2_type *)plane_2; \ + *out_pixel = (callback)(conversion_matrix, __VA_ARGS__); \ + out_pixel += 1; \ + plane_1 += step_1; \ + if ((i + subsampling_offset + 1) % subsampling == 0) \ + plane_2 += step_2; \ + } \ +} + +READ_LINE_YUV_SEMIPLANAR(YUV888_semiplanar_read_line, y, uv, u8, u8, argb_u16_from_yuv161616, + y[0] * 257, uv[0] * 257, uv[1] * 257) +READ_LINE_YUV_SEMIPLANAR(YUV161616_semiplanar_read_line, y, uv, u16, u16, argb_u16_from_yuv161616, + y[0], uv[0], uv[1]) /* * This callback can be used for YUV format where each color component is * stored in a different plane (often called planar formats). It will @@ -586,8 +566,9 @@ static void planar_yuv_read_line(const struct vkms_plane_state *plane, int x_sta const struct conversion_matrix *conversion_matrix = &plane->conversion_matrix; for (int i = 0; i < count; i++) { - *out_pixel = argb_u16_from_yuv888(*y_plane, *channel_1_plane, *channel_2_plane, - conversion_matrix); + *out_pixel = argb_u16_from_yuv161616(conversion_matrix, + *y_plane * 257, *channel_1_plane * 257, + *channel_2_plane * 257); out_pixel += 1; y_plane += step_y; if ((i + subsampling_offset + 1) % subsampling == 0) { @@ -712,23 +693,43 @@ pixel_read_line_t get_pixel_read_line_function(u32 format) switch (format) { case DRM_FORMAT_ARGB8888: return &ARGB8888_read_line; - case DRM_FORMAT_XRGB8888: - return &XRGB8888_read_line; case DRM_FORMAT_ABGR8888: return &ABGR8888_read_line; + case DRM_FORMAT_BGRA8888: + return &BGRA8888_read_line; + case DRM_FORMAT_RGBA8888: + return &RGBA8888_read_line; + case DRM_FORMAT_XRGB8888: + return &XRGB8888_read_line; + case DRM_FORMAT_XBGR8888: + return &XBGR8888_read_line; + case DRM_FORMAT_RGB888: + return &RGB888_read_line; + case DRM_FORMAT_BGR888: + return &BGR888_read_line; case DRM_FORMAT_ARGB16161616: return &ARGB16161616_read_line; + case DRM_FORMAT_ABGR16161616: + return &ABGR16161616_read_line; case DRM_FORMAT_XRGB16161616: return &XRGB16161616_read_line; + case DRM_FORMAT_XBGR16161616: + return &XBGR16161616_read_line; case DRM_FORMAT_RGB565: return &RGB565_read_line; + case DRM_FORMAT_BGR565: + return &BGR565_read_line; case DRM_FORMAT_NV12: case DRM_FORMAT_NV16: case DRM_FORMAT_NV24: case DRM_FORMAT_NV21: case DRM_FORMAT_NV61: case DRM_FORMAT_NV42: - return &semi_planar_yuv_read_line; + return &YUV888_semiplanar_read_line; + case DRM_FORMAT_P010: + case DRM_FORMAT_P012: + case DRM_FORMAT_P016: + return &YUV161616_semiplanar_read_line; case DRM_FORMAT_YUV420: case DRM_FORMAT_YUV422: case DRM_FORMAT_YUV444: diff --git a/drivers/gpu/drm/vkms/vkms_formats.h b/drivers/gpu/drm/vkms/vkms_formats.h index b4fe62ab9c65..eeb208cdd6b1 100644 --- a/drivers/gpu/drm/vkms/vkms_formats.h +++ b/drivers/gpu/drm/vkms/vkms_formats.h @@ -14,8 +14,8 @@ void get_conversion_matrix_to_argb_u16(u32 format, enum drm_color_encoding encod struct conversion_matrix *matrix); #if IS_ENABLED(CONFIG_KUNIT) -struct pixel_argb_u16 argb_u16_from_yuv888(u8 y, u8 channel_1, u8 channel_2, - const struct conversion_matrix *matrix); +struct pixel_argb_u16 argb_u16_from_yuv161616(const struct conversion_matrix *matrix, + u16 y, u16 channel_1, u16 channel_2); #endif #endif /* _VKMS_FORMATS_H_ */ diff --git a/drivers/gpu/drm/vkms/vkms_plane.c b/drivers/gpu/drm/vkms/vkms_plane.c index e3fdd161d0f0..e592e47a5736 100644 --- a/drivers/gpu/drm/vkms/vkms_plane.c +++ b/drivers/gpu/drm/vkms/vkms_plane.c @@ -14,11 +14,19 @@ static const u32 vkms_formats[] = { DRM_FORMAT_ARGB8888, - DRM_FORMAT_XRGB8888, DRM_FORMAT_ABGR8888, + DRM_FORMAT_BGRA8888, + DRM_FORMAT_RGBA8888, + DRM_FORMAT_XRGB8888, + DRM_FORMAT_XBGR8888, + DRM_FORMAT_RGB888, + DRM_FORMAT_BGR888, DRM_FORMAT_XRGB16161616, + DRM_FORMAT_XBGR16161616, DRM_FORMAT_ARGB16161616, + DRM_FORMAT_ABGR16161616, DRM_FORMAT_RGB565, + DRM_FORMAT_BGR565, DRM_FORMAT_NV12, DRM_FORMAT_NV16, DRM_FORMAT_NV24, @@ -31,6 +39,9 @@ static const u32 vkms_formats[] = { DRM_FORMAT_YVU420, DRM_FORMAT_YVU422, DRM_FORMAT_YVU444, + DRM_FORMAT_P010, + DRM_FORMAT_P012, + DRM_FORMAT_P016, DRM_FORMAT_R1, DRM_FORMAT_R2, DRM_FORMAT_R4, diff --git a/drivers/gpu/drm/xe/Kconfig b/drivers/gpu/drm/xe/Kconfig index 714d5702dfd7..7219f6b884b6 100644 --- a/drivers/gpu/drm/xe/Kconfig +++ b/drivers/gpu/drm/xe/Kconfig @@ -40,12 +40,12 @@ config DRM_XE select DRM_TTM select DRM_TTM_HELPER select DRM_EXEC + select DRM_GPUSVM if !UML && DEVICE_PRIVATE select DRM_GPUVM select DRM_SCHED select MMU_NOTIFIER select WANT_DEV_COREDUMP select AUXILIARY_BUS - select HMM_MIRROR select REGMAP if I2C help Driver for Intel Xe2 series GPUs and later. Experimental support diff --git a/drivers/gpu/drm/xe/Kconfig.debug b/drivers/gpu/drm/xe/Kconfig.debug index 01735c6ece8b..87902b4bd6d3 100644 --- a/drivers/gpu/drm/xe/Kconfig.debug +++ b/drivers/gpu/drm/xe/Kconfig.debug @@ -104,6 +104,7 @@ config DRM_XE_DEBUG_GUC config DRM_XE_USERPTR_INVAL_INJECT bool "Inject userptr invalidation -EINVAL errors" + depends on DRM_GPUSVM default n help Choose this option when debugging error paths that diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile index bb135f457a6c..d9c6cf0f189e 100644 --- a/drivers/gpu/drm/xe/Makefile +++ b/drivers/gpu/drm/xe/Makefile @@ -84,6 +84,7 @@ xe-y += xe_bb.o \ xe_hw_error.o \ xe_hw_fence.o \ xe_irq.o \ + xe_late_bind_fw.o \ xe_lrc.o \ xe_migrate.o \ xe_mmio.o \ @@ -130,6 +131,7 @@ xe-y += xe_bb.o \ xe_tuning.o \ xe_uc.o \ xe_uc_fw.o \ + xe_validation.o \ xe_vm.o \ xe_vm_madvise.o \ xe_vram.o \ @@ -140,8 +142,8 @@ xe-y += xe_bb.o \ xe_wopcm.o xe-$(CONFIG_I2C) += xe_i2c.o -xe-$(CONFIG_HMM_MIRROR) += xe_hmm.o xe-$(CONFIG_DRM_XE_GPUSVM) += xe_svm.o +xe-$(CONFIG_DRM_GPUSVM) += xe_userptr.o # graphics hardware monitoring (HWMON) support xe-$(CONFIG_HWMON) += xe_hwmon.o @@ -326,6 +328,7 @@ ifeq ($(CONFIG_DEBUG_FS),y) xe_gt_stats.o \ xe_guc_debugfs.o \ xe_huc_debugfs.o \ + xe_tile_debugfs.o \ xe_uc_debugfs.o xe-$(CONFIG_PCI_IOV) += xe_gt_sriov_pf_debugfs.o diff --git a/drivers/gpu/drm/xe/abi/guc_actions_abi.h b/drivers/gpu/drm/xe/abi/guc_actions_abi.h index d8cf68a0516d..31090c69dfbe 100644 --- a/drivers/gpu/drm/xe/abi/guc_actions_abi.h +++ b/drivers/gpu/drm/xe/abi/guc_actions_abi.h @@ -117,6 +117,7 @@ enum xe_guc_action { XE_GUC_ACTION_ENTER_S_STATE = 0x501, XE_GUC_ACTION_EXIT_S_STATE = 0x502, XE_GUC_ACTION_GLOBAL_SCHED_POLICY_CHANGE = 0x506, + XE_GUC_ACTION_UPDATE_SCHEDULING_POLICIES_KLV = 0x509, XE_GUC_ACTION_SCHED_CONTEXT = 0x1000, XE_GUC_ACTION_SCHED_CONTEXT_MODE_SET = 0x1001, XE_GUC_ACTION_SCHED_CONTEXT_MODE_DONE = 0x1002, @@ -154,6 +155,8 @@ enum xe_guc_action { XE_GUC_ACTION_NOTIFY_FLUSH_LOG_BUFFER_TO_FILE = 0x8003, XE_GUC_ACTION_NOTIFY_CRASH_DUMP_POSTED = 0x8004, XE_GUC_ACTION_NOTIFY_EXCEPTION = 0x8005, + XE_GUC_ACTION_TEST_G2G_SEND = 0xF001, + XE_GUC_ACTION_TEST_G2G_RECV = 0xF002, XE_GUC_ACTION_LIMIT }; diff --git a/drivers/gpu/drm/xe/abi/guc_actions_slpc_abi.h b/drivers/gpu/drm/xe/abi/guc_actions_slpc_abi.h index b28c8fa061f7..ce5c59517528 100644 --- a/drivers/gpu/drm/xe/abi/guc_actions_slpc_abi.h +++ b/drivers/gpu/drm/xe/abi/guc_actions_slpc_abi.h @@ -210,6 +210,11 @@ struct slpc_shared_data { u8 reserved_mode_definition[4096]; } __packed; +enum slpc_power_profile { + SLPC_POWER_PROFILE_BASE = 0x0, + SLPC_POWER_PROFILE_POWER_SAVING = 0x1 +}; + /** * DOC: SLPC H2G MESSAGE FORMAT * diff --git a/drivers/gpu/drm/xe/abi/guc_klvs_abi.h b/drivers/gpu/drm/xe/abi/guc_klvs_abi.h index 0e78351c6ef5..265a135e7061 100644 --- a/drivers/gpu/drm/xe/abi/guc_klvs_abi.h +++ b/drivers/gpu/drm/xe/abi/guc_klvs_abi.h @@ -17,6 +17,7 @@ * | 0 | 31:16 | **KEY** - KLV key identifier | * | | | - `GuC Self Config KLVs`_ | * | | | - `GuC Opt In Feature KLVs`_ | + * | | | - `GuC Scheduling Policies KLVs`_ | * | | | - `GuC VGT Policy KLVs`_ | * | | | - `GuC VF Configuration KLVs`_ | * | | | | @@ -153,6 +154,30 @@ enum { #define GUC_KLV_OPT_IN_FEATURE_DYNAMIC_INHIBIT_CONTEXT_SWITCH_LEN 0u /** + * DOC: GuC Scheduling Policies KLVs + * + * `GuC KLV`_ keys available for use with UPDATE_SCHEDULING_POLICIES_KLV. + * + * _`GUC_KLV_SCHEDULING_POLICIES_RENDER_COMPUTE_YIELD` : 0x1001 + * Some platforms do not allow concurrent execution of RCS and CCS + * workloads from different address spaces. By default, the GuC prioritizes + * RCS submissions over CCS ones, which can lead to CCS workloads being + * significantly (or completely) starved of execution time. This KLV allows + * the driver to specify a quantum (in ms) and a ratio (percentage value + * between 0 and 100), and the GuC will prioritize the CCS for that + * percentage of each quantum. For example, specifying 100ms and 30% will + * make the GuC prioritize the CCS for 30ms of every 100ms. + * Note that this does not necessarly mean that RCS and CCS engines will + * only be active for their percentage of the quantum, as the restriction + * only kicks in if both classes are fully busy with non-compatible address + * spaces; i.e., if one engine is idle or running the same address space, + * a pending job on the other engine will still be submitted to the HW no + * matter what the ratio is + */ +#define GUC_KLV_SCHEDULING_POLICIES_RENDER_COMPUTE_YIELD_KEY 0x1001 +#define GUC_KLV_SCHEDULING_POLICIES_RENDER_COMPUTE_YIELD_LEN 2u + +/** * DOC: GuC VGT Policy KLVs * * `GuC KLV`_ keys available for use with PF2GUC_UPDATE_VGT_POLICY. diff --git a/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_stolen.h b/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_stolen.h index 41d39d67817a..f097fc6d5127 100644 --- a/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_stolen.h +++ b/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_stolen.h @@ -8,6 +8,7 @@ #include "xe_ttm_stolen_mgr.h" #include "xe_res_cursor.h" +#include "xe_validation.h" struct xe_bo; @@ -21,7 +22,7 @@ static inline int i915_gem_stolen_insert_node_in_range(struct xe_device *xe, u32 start, u32 end) { struct xe_bo *bo; - int err; + int err = 0; u32 flags = XE_BO_FLAG_PINNED | XE_BO_FLAG_STOLEN; if (start < SZ_4K) @@ -32,21 +33,13 @@ static inline int i915_gem_stolen_insert_node_in_range(struct xe_device *xe, start = ALIGN(start, align); } - bo = xe_bo_create_locked_range(xe, xe_device_get_root_tile(xe), - NULL, size, start, end, - ttm_bo_type_kernel, flags, 0); + bo = xe_bo_create_pin_range_novm(xe, xe_device_get_root_tile(xe), + size, start, end, ttm_bo_type_kernel, flags); if (IS_ERR(bo)) { err = PTR_ERR(bo); bo = NULL; return err; } - err = xe_bo_pin(bo); - xe_bo_unlock_vm_held(bo); - - if (err) { - xe_bo_put(fb->bo); - bo = NULL; - } fb->bo = bo; diff --git a/drivers/gpu/drm/xe/display/intel_fbdev_fb.c b/drivers/gpu/drm/xe/display/intel_fbdev_fb.c index 3dfab0c2b827..35a5b07eeba4 100644 --- a/drivers/gpu/drm/xe/display/intel_fbdev_fb.c +++ b/drivers/gpu/drm/xe/display/intel_fbdev_fb.c @@ -20,11 +20,11 @@ struct drm_gem_object *intel_fbdev_fb_bo_create(struct drm_device *drm, int size obj = ERR_PTR(-ENODEV); if (!IS_DGFX(xe) && !XE_GT_WA(xe_root_mmio_gt(xe), 22019338487_display)) { - obj = xe_bo_create_pin_map(xe, xe_device_get_root_tile(xe), - NULL, size, - ttm_bo_type_kernel, XE_BO_FLAG_SCANOUT | - XE_BO_FLAG_STOLEN | - XE_BO_FLAG_GGTT); + obj = xe_bo_create_pin_map_novm(xe, xe_device_get_root_tile(xe), + size, + ttm_bo_type_kernel, XE_BO_FLAG_SCANOUT | + XE_BO_FLAG_STOLEN | + XE_BO_FLAG_GGTT, false); if (!IS_ERR(obj)) drm_info(&xe->drm, "Allocated fbdev into stolen\n"); else @@ -32,10 +32,10 @@ struct drm_gem_object *intel_fbdev_fb_bo_create(struct drm_device *drm, int size } if (IS_ERR(obj)) { - obj = xe_bo_create_pin_map(xe, xe_device_get_root_tile(xe), NULL, size, - ttm_bo_type_kernel, XE_BO_FLAG_SCANOUT | - XE_BO_FLAG_VRAM_IF_DGFX(xe_device_get_root_tile(xe)) | - XE_BO_FLAG_GGTT); + obj = xe_bo_create_pin_map_novm(xe, xe_device_get_root_tile(xe), size, + ttm_bo_type_kernel, XE_BO_FLAG_SCANOUT | + XE_BO_FLAG_VRAM_IF_DGFX(xe_device_get_root_tile(xe)) | + XE_BO_FLAG_GGTT, false); } if (IS_ERR(obj)) { diff --git a/drivers/gpu/drm/xe/display/xe_dsb_buffer.c b/drivers/gpu/drm/xe/display/xe_dsb_buffer.c index 9f941fc2e36b..58581d7aaae6 100644 --- a/drivers/gpu/drm/xe/display/xe_dsb_buffer.c +++ b/drivers/gpu/drm/xe/display/xe_dsb_buffer.c @@ -43,11 +43,11 @@ bool intel_dsb_buffer_create(struct intel_crtc *crtc, struct intel_dsb_buffer *d return false; /* Set scanout flag for WC mapping */ - obj = xe_bo_create_pin_map(xe, xe_device_get_root_tile(xe), - NULL, PAGE_ALIGN(size), - ttm_bo_type_kernel, - XE_BO_FLAG_VRAM_IF_DGFX(xe_device_get_root_tile(xe)) | - XE_BO_FLAG_SCANOUT | XE_BO_FLAG_GGTT); + obj = xe_bo_create_pin_map_novm(xe, xe_device_get_root_tile(xe), + PAGE_ALIGN(size), + ttm_bo_type_kernel, + XE_BO_FLAG_VRAM_IF_DGFX(xe_device_get_root_tile(xe)) | + XE_BO_FLAG_SCANOUT | XE_BO_FLAG_GGTT, false); if (IS_ERR(obj)) { kfree(vma); return false; diff --git a/drivers/gpu/drm/xe/display/xe_fb_pin.c b/drivers/gpu/drm/xe/display/xe_fb_pin.c index f1f8b5ab53ef..1fd4a815e784 100644 --- a/drivers/gpu/drm/xe/display/xe_fb_pin.c +++ b/drivers/gpu/drm/xe/display/xe_fb_pin.c @@ -102,29 +102,29 @@ static int __xe_pin_fb_vma_dpt(const struct intel_framebuffer *fb, XE_PAGE_SIZE); if (IS_DGFX(xe)) - dpt = xe_bo_create_pin_map_at_aligned(xe, tile0, NULL, - dpt_size, ~0ull, - ttm_bo_type_kernel, - XE_BO_FLAG_VRAM0 | - XE_BO_FLAG_GGTT | - XE_BO_FLAG_PAGETABLE, - alignment); + dpt = xe_bo_create_pin_map_at_novm(xe, tile0, + dpt_size, ~0ull, + ttm_bo_type_kernel, + XE_BO_FLAG_VRAM0 | + XE_BO_FLAG_GGTT | + XE_BO_FLAG_PAGETABLE, + alignment, false); else - dpt = xe_bo_create_pin_map_at_aligned(xe, tile0, NULL, - dpt_size, ~0ull, - ttm_bo_type_kernel, - XE_BO_FLAG_STOLEN | - XE_BO_FLAG_GGTT | - XE_BO_FLAG_PAGETABLE, - alignment); + dpt = xe_bo_create_pin_map_at_novm(xe, tile0, + dpt_size, ~0ull, + ttm_bo_type_kernel, + XE_BO_FLAG_STOLEN | + XE_BO_FLAG_GGTT | + XE_BO_FLAG_PAGETABLE, + alignment, false); if (IS_ERR(dpt)) - dpt = xe_bo_create_pin_map_at_aligned(xe, tile0, NULL, - dpt_size, ~0ull, - ttm_bo_type_kernel, - XE_BO_FLAG_SYSTEM | - XE_BO_FLAG_GGTT | - XE_BO_FLAG_PAGETABLE, - alignment); + dpt = xe_bo_create_pin_map_at_novm(xe, tile0, + dpt_size, ~0ull, + ttm_bo_type_kernel, + XE_BO_FLAG_SYSTEM | + XE_BO_FLAG_GGTT | + XE_BO_FLAG_PAGETABLE, + alignment, false); if (IS_ERR(dpt)) return PTR_ERR(dpt); @@ -281,7 +281,9 @@ static struct i915_vma *__xe_pin_fb_vma(const struct intel_framebuffer *fb, struct i915_vma *vma = kzalloc(sizeof(*vma), GFP_KERNEL); struct drm_gem_object *obj = intel_fb_bo(&fb->base); struct xe_bo *bo = gem_to_xe_bo(obj); - int ret; + struct xe_validation_ctx ctx; + struct drm_exec exec; + int ret = 0; if (!vma) return ERR_PTR(-ENODEV); @@ -308,17 +310,22 @@ static struct i915_vma *__xe_pin_fb_vma(const struct intel_framebuffer *fb, * Pin the framebuffer, we can't use xe_bo_(un)pin functions as the * assumptions are incorrect for framebuffers */ - ret = ttm_bo_reserve(&bo->ttm, false, false, NULL); - if (ret) - goto err; - - if (IS_DGFX(xe)) - ret = xe_bo_migrate(bo, XE_PL_VRAM0); - else - ret = xe_bo_validate(bo, NULL, true); - if (!ret) - ttm_bo_pin(&bo->ttm); - ttm_bo_unreserve(&bo->ttm); + xe_validation_guard(&ctx, &xe->val, &exec, (struct xe_val_flags) {.interruptible = true}, + ret) { + ret = drm_exec_lock_obj(&exec, &bo->ttm.base); + drm_exec_retry_on_contention(&exec); + if (ret) + break; + + if (IS_DGFX(xe)) + ret = xe_bo_migrate(bo, XE_PL_VRAM0, NULL, &exec); + else + ret = xe_bo_validate(bo, NULL, true, &exec); + drm_exec_retry_on_contention(&exec); + xe_validation_retry_on_oom(&ctx, &ret); + if (!ret) + ttm_bo_pin(&bo->ttm); + } if (ret) goto err; diff --git a/drivers/gpu/drm/xe/display/xe_hdcp_gsc.c b/drivers/gpu/drm/xe/display/xe_hdcp_gsc.c index 30f1073141fc..4ae847b628e2 100644 --- a/drivers/gpu/drm/xe/display/xe_hdcp_gsc.c +++ b/drivers/gpu/drm/xe/display/xe_hdcp_gsc.c @@ -72,10 +72,10 @@ static int intel_hdcp_gsc_initialize_message(struct xe_device *xe, int ret = 0; /* allocate object of two page for HDCP command memory and store it */ - bo = xe_bo_create_pin_map(xe, xe_device_get_root_tile(xe), NULL, PAGE_SIZE * 2, - ttm_bo_type_kernel, - XE_BO_FLAG_SYSTEM | - XE_BO_FLAG_GGTT); + bo = xe_bo_create_pin_map_novm(xe, xe_device_get_root_tile(xe), PAGE_SIZE * 2, + ttm_bo_type_kernel, + XE_BO_FLAG_SYSTEM | + XE_BO_FLAG_GGTT, false); if (IS_ERR(bo)) { drm_err(&xe->drm, "Failed to allocate bo for HDCP streaming command!\n"); diff --git a/drivers/gpu/drm/xe/display/xe_plane_initial.c b/drivers/gpu/drm/xe/display/xe_plane_initial.c index 826ac3d578b7..94f00def811b 100644 --- a/drivers/gpu/drm/xe/display/xe_plane_initial.c +++ b/drivers/gpu/drm/xe/display/xe_plane_initial.c @@ -140,8 +140,8 @@ initial_plane_bo(struct xe_device *xe, page_size); size -= base; - bo = xe_bo_create_pin_map_at(xe, tile0, NULL, size, phys_base, - ttm_bo_type_kernel, flags); + bo = xe_bo_create_pin_map_at_novm(xe, tile0, size, phys_base, + ttm_bo_type_kernel, flags, 0, false); if (IS_ERR(bo)) { drm_dbg(&xe->drm, "Failed to create bo phys_base=%pa size %u with flags %x: %li\n", diff --git a/drivers/gpu/drm/xe/regs/xe_gt_regs.h b/drivers/gpu/drm/xe/regs/xe_gt_regs.h index f96b2e2b3064..06cb6b02ec64 100644 --- a/drivers/gpu/drm/xe/regs/xe_gt_regs.h +++ b/drivers/gpu/drm/xe/regs/xe_gt_regs.h @@ -522,6 +522,7 @@ #define TDL_CHICKEN XE_REG_MCR(0xe5f4, XE_REG_OPTION_MASKED) #define QID_WAIT_FOR_THREAD_NOT_RUN_DISABLE REG_BIT(12) +#define EUSTALL_PERF_SAMPLING_DISABLE REG_BIT(5) #define LSC_CHICKEN_BIT_0 XE_REG_MCR(0xe7c8) #define DISABLE_D8_D16_COASLESCE REG_BIT(30) diff --git a/drivers/gpu/drm/xe/regs/xe_lrc_layout.h b/drivers/gpu/drm/xe/regs/xe_lrc_layout.h index 1b101edb838b..b5eff383902c 100644 --- a/drivers/gpu/drm/xe/regs/xe_lrc_layout.h +++ b/drivers/gpu/drm/xe/regs/xe_lrc_layout.h @@ -40,7 +40,4 @@ #define INDIRECT_CTX_RING_START_UDW (0x08 + 1) #define INDIRECT_CTX_RING_CTL (0x0a + 1) -#define CTX_INDIRECT_CTX_OFFSET_MASK REG_GENMASK(15, 6) -#define CTX_INDIRECT_CTX_OFFSET_DEFAULT REG_FIELD_PREP(CTX_INDIRECT_CTX_OFFSET_MASK, 0xd) - #endif diff --git a/drivers/gpu/drm/xe/tests/xe_bo.c b/drivers/gpu/drm/xe/tests/xe_bo.c index bb469096d072..2294cf89f3e1 100644 --- a/drivers/gpu/drm/xe/tests/xe_bo.c +++ b/drivers/gpu/drm/xe/tests/xe_bo.c @@ -23,7 +23,7 @@ static int ccs_test_migrate(struct xe_tile *tile, struct xe_bo *bo, bool clear, u64 get_val, u64 assign_val, - struct kunit *test) + struct kunit *test, struct drm_exec *exec) { struct dma_fence *fence; struct ttm_tt *ttm; @@ -35,7 +35,7 @@ static int ccs_test_migrate(struct xe_tile *tile, struct xe_bo *bo, u32 offset; /* Move bo to VRAM if not already there. */ - ret = xe_bo_validate(bo, NULL, false); + ret = xe_bo_validate(bo, NULL, false, exec); if (ret) { KUNIT_FAIL(test, "Failed to validate bo.\n"); return ret; @@ -60,7 +60,7 @@ static int ccs_test_migrate(struct xe_tile *tile, struct xe_bo *bo, } /* Evict to system. CCS data should be copied. */ - ret = xe_bo_evict(bo); + ret = xe_bo_evict(bo, exec); if (ret) { KUNIT_FAIL(test, "Failed to evict bo.\n"); return ret; @@ -132,14 +132,15 @@ static void ccs_test_run_tile(struct xe_device *xe, struct xe_tile *tile, /* TODO: Sanity check */ unsigned int bo_flags = XE_BO_FLAG_VRAM_IF_DGFX(tile); + struct drm_exec *exec = XE_VALIDATION_OPT_OUT; if (IS_DGFX(xe)) kunit_info(test, "Testing vram id %u\n", tile->id); else kunit_info(test, "Testing system memory\n"); - bo = xe_bo_create_user(xe, NULL, NULL, SZ_1M, DRM_XE_GEM_CPU_CACHING_WC, - bo_flags); + bo = xe_bo_create_user(xe, NULL, SZ_1M, DRM_XE_GEM_CPU_CACHING_WC, + bo_flags, exec); if (IS_ERR(bo)) { KUNIT_FAIL(test, "Failed to create bo.\n"); return; @@ -149,18 +150,18 @@ static void ccs_test_run_tile(struct xe_device *xe, struct xe_tile *tile, kunit_info(test, "Verifying that CCS data is cleared on creation.\n"); ret = ccs_test_migrate(tile, bo, false, 0ULL, 0xdeadbeefdeadbeefULL, - test); + test, exec); if (ret) goto out_unlock; kunit_info(test, "Verifying that CCS data survives migration.\n"); ret = ccs_test_migrate(tile, bo, false, 0xdeadbeefdeadbeefULL, - 0xdeadbeefdeadbeefULL, test); + 0xdeadbeefdeadbeefULL, test, exec); if (ret) goto out_unlock; kunit_info(test, "Verifying that CCS data can be properly cleared.\n"); - ret = ccs_test_migrate(tile, bo, true, 0ULL, 0ULL, test); + ret = ccs_test_migrate(tile, bo, true, 0ULL, 0ULL, test, exec); out_unlock: xe_bo_unlock(bo); @@ -210,6 +211,7 @@ static int evict_test_run_tile(struct xe_device *xe, struct xe_tile *tile, struc struct xe_bo *bo, *external; unsigned int bo_flags = XE_BO_FLAG_VRAM_IF_DGFX(tile); struct xe_vm *vm = xe_migrate_get_vm(xe_device_get_root_tile(xe)->migrate); + struct drm_exec *exec = XE_VALIDATION_OPT_OUT; struct xe_gt *__gt; int err, i, id; @@ -218,25 +220,25 @@ static int evict_test_run_tile(struct xe_device *xe, struct xe_tile *tile, struc for (i = 0; i < 2; ++i) { xe_vm_lock(vm, false); - bo = xe_bo_create_user(xe, NULL, vm, 0x10000, + bo = xe_bo_create_user(xe, vm, 0x10000, DRM_XE_GEM_CPU_CACHING_WC, - bo_flags); + bo_flags, exec); xe_vm_unlock(vm); if (IS_ERR(bo)) { KUNIT_FAIL(test, "bo create err=%pe\n", bo); break; } - external = xe_bo_create_user(xe, NULL, NULL, 0x10000, + external = xe_bo_create_user(xe, NULL, 0x10000, DRM_XE_GEM_CPU_CACHING_WC, - bo_flags); + bo_flags, NULL); if (IS_ERR(external)) { KUNIT_FAIL(test, "external bo create err=%pe\n", external); goto cleanup_bo; } xe_bo_lock(external, false); - err = xe_bo_pin_external(external); + err = xe_bo_pin_external(external, false, exec); xe_bo_unlock(external); if (err) { KUNIT_FAIL(test, "external bo pin err=%pe\n", @@ -294,7 +296,7 @@ static int evict_test_run_tile(struct xe_device *xe, struct xe_tile *tile, struc if (i) { down_read(&vm->lock); xe_vm_lock(vm, false); - err = xe_bo_validate(bo, bo->vm, false); + err = xe_bo_validate(bo, bo->vm, false, exec); xe_vm_unlock(vm); up_read(&vm->lock); if (err) { @@ -303,7 +305,7 @@ static int evict_test_run_tile(struct xe_device *xe, struct xe_tile *tile, struc goto cleanup_all; } xe_bo_lock(external, false); - err = xe_bo_validate(external, NULL, false); + err = xe_bo_validate(external, NULL, false, exec); xe_bo_unlock(external); if (err) { KUNIT_FAIL(test, "external bo valid err=%pe\n", @@ -495,9 +497,9 @@ static int shrink_test_run_device(struct xe_device *xe) INIT_LIST_HEAD(&link->link); /* We can create bos using WC caching here. But it is slower. */ - bo = xe_bo_create_user(xe, NULL, NULL, XE_BO_SHRINK_SIZE, + bo = xe_bo_create_user(xe, NULL, XE_BO_SHRINK_SIZE, DRM_XE_GEM_CPU_CACHING_WB, - XE_BO_FLAG_SYSTEM); + XE_BO_FLAG_SYSTEM, NULL); if (IS_ERR(bo)) { if (bo != ERR_PTR(-ENOMEM) && bo != ERR_PTR(-ENOSPC) && bo != ERR_PTR(-EINTR) && bo != ERR_PTR(-ERESTARTSYS)) diff --git a/drivers/gpu/drm/xe/tests/xe_dma_buf.c b/drivers/gpu/drm/xe/tests/xe_dma_buf.c index 3c5ad8cc65a0..a7e548a2bdfb 100644 --- a/drivers/gpu/drm/xe/tests/xe_dma_buf.c +++ b/drivers/gpu/drm/xe/tests/xe_dma_buf.c @@ -27,7 +27,8 @@ static bool is_dynamic(struct dma_buf_test_params *params) } static void check_residency(struct kunit *test, struct xe_bo *exported, - struct xe_bo *imported, struct dma_buf *dmabuf) + struct xe_bo *imported, struct dma_buf *dmabuf, + struct drm_exec *exec) { struct dma_buf_test_params *params = to_dma_buf_test_params(test->priv); u32 mem_type; @@ -62,7 +63,7 @@ static void check_residency(struct kunit *test, struct xe_bo *exported, * importer is on a different device. If they're on the same device, * the exporter and the importer should be the same bo. */ - ret = xe_bo_evict(exported); + ret = xe_bo_evict(exported, exec); if (ret) { if (ret != -EINTR && ret != -ERESTARTSYS) KUNIT_FAIL(test, "Evicting exporter failed with err=%d.\n", @@ -77,7 +78,7 @@ static void check_residency(struct kunit *test, struct xe_bo *exported, } /* Re-validate the importer. This should move also exporter in. */ - ret = xe_bo_validate(imported, NULL, false); + ret = xe_bo_validate(imported, NULL, false, exec); if (ret) { if (ret != -EINTR && ret != -ERESTARTSYS) KUNIT_FAIL(test, "Validating importer failed with err=%d.\n", @@ -85,15 +86,7 @@ static void check_residency(struct kunit *test, struct xe_bo *exported, return; } - /* - * If on different devices, the exporter is kept in system if - * possible, saving a migration step as the transfer is just - * likely as fast from system memory. - */ - if (params->mem_mask & XE_BO_FLAG_SYSTEM) - KUNIT_EXPECT_TRUE(test, xe_bo_is_mem_type(exported, XE_PL_TT)); - else - KUNIT_EXPECT_TRUE(test, xe_bo_is_mem_type(exported, mem_type)); + KUNIT_EXPECT_TRUE(test, xe_bo_is_mem_type(exported, mem_type)); if (params->force_different_devices) KUNIT_EXPECT_TRUE(test, xe_bo_is_mem_type(imported, XE_PL_TT)); @@ -121,8 +114,8 @@ static void xe_test_dmabuf_import_same_driver(struct xe_device *xe) size = SZ_64K; kunit_info(test, "running %s\n", __func__); - bo = xe_bo_create_user(xe, NULL, NULL, size, DRM_XE_GEM_CPU_CACHING_WC, - params->mem_mask); + bo = xe_bo_create_user(xe, NULL, size, DRM_XE_GEM_CPU_CACHING_WC, + params->mem_mask, NULL); if (IS_ERR(bo)) { KUNIT_FAIL(test, "xe_bo_create() failed with err=%ld\n", PTR_ERR(bo)); @@ -150,11 +143,12 @@ static void xe_test_dmabuf_import_same_driver(struct xe_device *xe) KUNIT_FAIL(test, "xe_gem_prime_import() succeeded when it shouldn't have\n"); } else { + struct drm_exec *exec = XE_VALIDATION_OPT_OUT; int err; /* Is everything where we expect it to be? */ xe_bo_lock(import_bo, false); - err = xe_bo_validate(import_bo, NULL, false); + err = xe_bo_validate(import_bo, NULL, false, exec); /* Pinning in VRAM is not allowed. */ if (!is_dynamic(params) && @@ -167,7 +161,7 @@ static void xe_test_dmabuf_import_same_driver(struct xe_device *xe) err == -ERESTARTSYS); if (!err) - check_residency(test, bo, import_bo, dmabuf); + check_residency(test, bo, import_bo, dmabuf, exec); xe_bo_unlock(import_bo); } drm_gem_object_put(import); diff --git a/drivers/gpu/drm/xe/tests/xe_guc_g2g_test.c b/drivers/gpu/drm/xe/tests/xe_guc_g2g_test.c new file mode 100644 index 000000000000..3b213fcae916 --- /dev/null +++ b/drivers/gpu/drm/xe/tests/xe_guc_g2g_test.c @@ -0,0 +1,776 @@ +// SPDX-License-Identifier: GPL-2.0 AND MIT +/* + * Copyright © 2025 Intel Corporation + */ + +#include <linux/delay.h> + +#include <kunit/test.h> +#include <kunit/visibility.h> + +#include "tests/xe_kunit_helpers.h" +#include "tests/xe_pci_test.h" +#include "tests/xe_test.h" + +#include "xe_bo.h" +#include "xe_device.h" +#include "xe_pm.h" + +/* + * There are different ways to allocate the G2G buffers. The plan for this test + * is to make sure that all the possible options work. The particular option + * chosen by the driver may vary from one platform to another, it may also change + * with time. So to ensure consistency of testing, the relevant driver code is + * replicated here to guarantee it won't change without the test being updated + * to keep testing the other options. + * + * In order to test the actual code being used by the driver, there is also the + * 'default' scheme. That will use the official driver routines to test whatever + * method the driver is using on the current platform at the current time. + */ +enum { + /* Driver defined allocation scheme */ + G2G_CTB_TYPE_DEFAULT, + /* Single buffer in host memory */ + G2G_CTB_TYPE_HOST, + /* Single buffer in a specific tile, loops across all tiles */ + G2G_CTB_TYPE_TILE, +}; + +/* + * Payload is opaque to GuC. So KMD can define any structure or size it wants. + */ +struct g2g_test_payload { + u32 tx_dev; + u32 tx_tile; + u32 rx_dev; + u32 rx_tile; + u32 seqno; +}; + +static void g2g_test_send(struct kunit *test, struct xe_guc *guc, + u32 far_tile, u32 far_dev, + struct g2g_test_payload *payload) +{ + struct xe_device *xe = guc_to_xe(guc); + struct xe_gt *gt = guc_to_gt(guc); + u32 *action, total; + size_t payload_len; + int ret; + + static_assert(IS_ALIGNED(sizeof(*payload), sizeof(u32))); + payload_len = sizeof(*payload) / sizeof(u32); + + total = 4 + payload_len; + action = kunit_kmalloc_array(test, total, sizeof(*action), GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, action); + + action[0] = XE_GUC_ACTION_TEST_G2G_SEND; + action[1] = far_tile; + action[2] = far_dev; + action[3] = payload_len; + memcpy(action + 4, payload, payload_len * sizeof(u32)); + + atomic_inc(&xe->g2g_test_count); + + /* + * Should specify the expected response notification here. Problem is that + * the response will be coming from a different GuC. By the end, it should + * all add up as long as an equal number of messages are sent from each GuC + * and to each GuC. However, in the middle negative reservation space errors + * and such like can occur. Rather than add intrusive changes to the CT layer + * it is simpler to just not bother counting it at all. The system should be + * idle when running the selftest, and the selftest's notification total size + * is well within the G2H allocation size. So there should be no issues with + * needing to block for space, which is all the tracking code is really for. + */ + ret = xe_guc_ct_send(&guc->ct, action, total, 0, 0); + kunit_kfree(test, action); + KUNIT_ASSERT_EQ_MSG(test, 0, ret, "G2G send failed: %d [%d:%d -> %d:%d]\n", ret, + gt_to_tile(gt)->id, G2G_DEV(gt), far_tile, far_dev); +} + +/* + * NB: Can't use KUNIT_ASSERT and friends in here as this is called asynchronously + * from the G2H notification handler. Need that to actually complete rather than + * thread-abort in order to keep the rest of the driver alive! + */ +int xe_guc_g2g_test_notification(struct xe_guc *guc, u32 *msg, u32 len) +{ + struct xe_device *xe = guc_to_xe(guc); + struct xe_gt *rx_gt = guc_to_gt(guc), *test_gt, *tx_gt = NULL; + u32 tx_tile, tx_dev, rx_tile, rx_dev, idx, got_len; + struct g2g_test_payload *payload; + size_t payload_len; + int ret = 0, i; + + payload_len = sizeof(*payload) / sizeof(u32); + + if (unlikely(len != (G2H_LEN_DW_G2G_NOTIFY_MIN + payload_len))) { + xe_gt_err(rx_gt, "G2G test notification invalid length %u", len); + ret = -EPROTO; + goto done; + } + + tx_tile = msg[0]; + tx_dev = msg[1]; + got_len = msg[2]; + payload = (struct g2g_test_payload *)(msg + 3); + + rx_tile = gt_to_tile(rx_gt)->id; + rx_dev = G2G_DEV(rx_gt); + + if (got_len != payload_len) { + xe_gt_err(rx_gt, "G2G: Invalid payload length: %u vs %zu\n", got_len, payload_len); + ret = -EPROTO; + goto done; + } + + if (payload->tx_dev != tx_dev || payload->tx_tile != tx_tile || + payload->rx_dev != rx_dev || payload->rx_tile != rx_tile) { + xe_gt_err(rx_gt, "G2G: Invalid payload: %d:%d -> %d:%d vs %d:%d -> %d:%d! [%d]\n", + payload->tx_tile, payload->tx_dev, payload->rx_tile, payload->rx_dev, + tx_tile, tx_dev, rx_tile, rx_dev, payload->seqno); + ret = -EPROTO; + goto done; + } + + if (!xe->g2g_test_array) { + xe_gt_err(rx_gt, "G2G: Missing test array!\n"); + ret = -ENOMEM; + goto done; + } + + for_each_gt(test_gt, xe, i) { + if (gt_to_tile(test_gt)->id != tx_tile) + continue; + + if (G2G_DEV(test_gt) != tx_dev) + continue; + + if (tx_gt) { + xe_gt_err(rx_gt, "G2G: Got duplicate TX GTs: %d vs %d for %d:%d!\n", + tx_gt->info.id, test_gt->info.id, tx_tile, tx_dev); + ret = -EINVAL; + goto done; + } + + tx_gt = test_gt; + } + if (!tx_gt) { + xe_gt_err(rx_gt, "G2G: Failed to find a TX GT for %d:%d!\n", tx_tile, tx_dev); + ret = -EINVAL; + goto done; + } + + idx = (tx_gt->info.id * xe->info.gt_count) + rx_gt->info.id; + + if (xe->g2g_test_array[idx] != payload->seqno - 1) { + xe_gt_err(rx_gt, "G2G: Seqno mismatch %d vs %d for %d:%d -> %d:%d!\n", + xe->g2g_test_array[idx], payload->seqno - 1, + tx_tile, tx_dev, rx_tile, rx_dev); + ret = -EINVAL; + goto done; + } + + xe->g2g_test_array[idx] = payload->seqno; + +done: + atomic_dec(&xe->g2g_test_count); + return ret; +} + +/* + * Send the given seqno from all GuCs to all other GuCs in tile/GT order + */ +static void g2g_test_in_order(struct kunit *test, struct xe_device *xe, u32 seqno) +{ + struct xe_gt *near_gt, *far_gt; + int i, j; + + for_each_gt(near_gt, xe, i) { + u32 near_tile = gt_to_tile(near_gt)->id; + u32 near_dev = G2G_DEV(near_gt); + + for_each_gt(far_gt, xe, j) { + u32 far_tile = gt_to_tile(far_gt)->id; + u32 far_dev = G2G_DEV(far_gt); + struct g2g_test_payload payload; + + if (far_gt->info.id == near_gt->info.id) + continue; + + payload.tx_dev = near_dev; + payload.tx_tile = near_tile; + payload.rx_dev = far_dev; + payload.rx_tile = far_tile; + payload.seqno = seqno; + g2g_test_send(test, &near_gt->uc.guc, far_tile, far_dev, &payload); + } + } +} + +#define WAIT_TIME_MS 100 +#define WAIT_COUNT (1000 / WAIT_TIME_MS) + +static void g2g_wait_for_complete(void *_xe) +{ + struct xe_device *xe = (struct xe_device *)_xe; + struct kunit *test = kunit_get_current_test(); + int wait = 0; + + /* Wait for all G2H messages to be received */ + while (atomic_read(&xe->g2g_test_count)) { + if (++wait > WAIT_COUNT) + break; + + msleep(WAIT_TIME_MS); + } + + KUNIT_ASSERT_EQ_MSG(test, 0, atomic_read(&xe->g2g_test_count), + "Timed out waiting for notifications\n"); + kunit_info(test, "Got all notifications back\n"); +} + +#undef WAIT_TIME_MS +#undef WAIT_COUNT + +static void g2g_clean_array(void *_xe) +{ + struct xe_device *xe = (struct xe_device *)_xe; + + xe->g2g_test_array = NULL; +} + +#define NUM_LOOPS 16 + +static void g2g_run_test(struct kunit *test, struct xe_device *xe) +{ + u32 seqno, max_array; + int ret, i, j; + + max_array = xe->info.gt_count * xe->info.gt_count; + xe->g2g_test_array = kunit_kcalloc(test, max_array, sizeof(u32), GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, xe->g2g_test_array); + + ret = kunit_add_action_or_reset(test, g2g_clean_array, xe); + KUNIT_ASSERT_EQ_MSG(test, 0, ret, "Failed to register clean up action\n"); + + /* + * Send incrementing seqnos from all GuCs to all other GuCs in tile/GT order. + * Tile/GT order doesn't really mean anything to the hardware but it is going + * to be a fixed sequence every time. + * + * Verify that each one comes back having taken the correct route. + */ + ret = kunit_add_action(test, g2g_wait_for_complete, xe); + KUNIT_ASSERT_EQ_MSG(test, 0, ret, "Failed to register clean up action\n"); + for (seqno = 1; seqno < NUM_LOOPS; seqno++) + g2g_test_in_order(test, xe, seqno); + seqno--; + + kunit_release_action(test, &g2g_wait_for_complete, xe); + + /* Check for the final seqno in each slot */ + for (i = 0; i < xe->info.gt_count; i++) { + for (j = 0; j < xe->info.gt_count; j++) { + u32 idx = (j * xe->info.gt_count) + i; + + if (i == j) + KUNIT_ASSERT_EQ_MSG(test, 0, xe->g2g_test_array[idx], + "identity seqno modified: %d for %dx%d!\n", + xe->g2g_test_array[idx], i, j); + else + KUNIT_ASSERT_EQ_MSG(test, seqno, xe->g2g_test_array[idx], + "invalid seqno: %d vs %d for %dx%d!\n", + xe->g2g_test_array[idx], seqno, i, j); + } + } + + kunit_kfree(test, xe->g2g_test_array); + kunit_release_action(test, &g2g_clean_array, xe); + + kunit_info(test, "Test passed\n"); +} + +#undef NUM_LOOPS + +static void g2g_ct_stop(struct xe_guc *guc) +{ + struct xe_gt *remote_gt, *gt = guc_to_gt(guc); + struct xe_device *xe = gt_to_xe(gt); + int i, t; + + for_each_gt(remote_gt, xe, i) { + u32 tile, dev; + + if (remote_gt->info.id == gt->info.id) + continue; + + tile = gt_to_tile(remote_gt)->id; + dev = G2G_DEV(remote_gt); + + for (t = 0; t < XE_G2G_TYPE_LIMIT; t++) + guc_g2g_deregister(guc, tile, dev, t); + } +} + +/* Size of a single allocation that contains all G2G CTBs across all GTs */ +static u32 g2g_ctb_size(struct kunit *test, struct xe_device *xe) +{ + unsigned int count = xe->info.gt_count; + u32 num_channels = (count * (count - 1)) / 2; + + kunit_info(test, "Size: (%d * %d / 2) * %d * 0x%08X + 0x%08X => 0x%08X [%d]\n", + count, count - 1, XE_G2G_TYPE_LIMIT, G2G_BUFFER_SIZE, G2G_DESC_AREA_SIZE, + num_channels * XE_G2G_TYPE_LIMIT * G2G_BUFFER_SIZE + G2G_DESC_AREA_SIZE, + num_channels * XE_G2G_TYPE_LIMIT); + + return num_channels * XE_G2G_TYPE_LIMIT * G2G_BUFFER_SIZE + G2G_DESC_AREA_SIZE; +} + +/* + * Use the driver's regular CTB allocation scheme. + */ +static void g2g_alloc_default(struct kunit *test, struct xe_device *xe) +{ + struct xe_gt *gt; + int i; + + kunit_info(test, "Default [tiles = %d, GTs = %d]\n", + xe->info.tile_count, xe->info.gt_count); + + for_each_gt(gt, xe, i) { + struct xe_guc *guc = >->uc.guc; + int ret; + + ret = guc_g2g_alloc(guc); + KUNIT_ASSERT_EQ_MSG(test, 0, ret, "G2G alloc failed: %pe", ERR_PTR(ret)); + continue; + } +} + +static void g2g_distribute(struct kunit *test, struct xe_device *xe, struct xe_bo *bo) +{ + struct xe_gt *root_gt, *gt; + int i; + + root_gt = xe_device_get_gt(xe, 0); + root_gt->uc.guc.g2g.bo = bo; + root_gt->uc.guc.g2g.owned = true; + kunit_info(test, "[%d.%d] Assigned 0x%p\n", gt_to_tile(root_gt)->id, root_gt->info.id, bo); + + for_each_gt(gt, xe, i) { + if (gt->info.id != 0) { + gt->uc.guc.g2g.owned = false; + gt->uc.guc.g2g.bo = xe_bo_get(bo); + kunit_info(test, "[%d.%d] Pinned 0x%p\n", + gt_to_tile(gt)->id, gt->info.id, gt->uc.guc.g2g.bo); + } + + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, gt->uc.guc.g2g.bo); + } +} + +/* + * Allocate a single blob on the host and split between all G2G CTBs. + */ +static void g2g_alloc_host(struct kunit *test, struct xe_device *xe) +{ + struct xe_bo *bo; + u32 g2g_size; + + kunit_info(test, "Host [tiles = %d, GTs = %d]\n", xe->info.tile_count, xe->info.gt_count); + + g2g_size = g2g_ctb_size(test, xe); + bo = xe_managed_bo_create_pin_map(xe, xe_device_get_root_tile(xe), g2g_size, + XE_BO_FLAG_SYSTEM | + XE_BO_FLAG_GGTT | + XE_BO_FLAG_GGTT_ALL | + XE_BO_FLAG_GGTT_INVALIDATE); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, bo); + kunit_info(test, "[HST] G2G buffer create: 0x%p\n", bo); + + xe_map_memset(xe, &bo->vmap, 0, 0, g2g_size); + + g2g_distribute(test, xe, bo); +} + +/* + * Allocate a single blob on the given tile and split between all G2G CTBs. + */ +static void g2g_alloc_tile(struct kunit *test, struct xe_device *xe, struct xe_tile *tile) +{ + struct xe_bo *bo; + u32 g2g_size; + + KUNIT_ASSERT_TRUE(test, IS_DGFX(xe)); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, tile); + + kunit_info(test, "Tile %d [tiles = %d, GTs = %d]\n", + tile->id, xe->info.tile_count, xe->info.gt_count); + + g2g_size = g2g_ctb_size(test, xe); + bo = xe_managed_bo_create_pin_map(xe, tile, g2g_size, + XE_BO_FLAG_VRAM_IF_DGFX(tile) | + XE_BO_FLAG_GGTT | + XE_BO_FLAG_GGTT_ALL | + XE_BO_FLAG_GGTT_INVALIDATE); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, bo); + kunit_info(test, "[%d.*] G2G buffer create: 0x%p\n", tile->id, bo); + + xe_map_memset(xe, &bo->vmap, 0, 0, g2g_size); + + g2g_distribute(test, xe, bo); +} + +static void g2g_free(struct kunit *test, struct xe_device *xe) +{ + struct xe_gt *gt; + struct xe_bo *bo; + int i; + + for_each_gt(gt, xe, i) { + bo = gt->uc.guc.g2g.bo; + if (!bo) + continue; + + if (gt->uc.guc.g2g.owned) { + xe_managed_bo_unpin_map_no_vm(bo); + kunit_info(test, "[%d.%d] Unmapped 0x%p\n", + gt_to_tile(gt)->id, gt->info.id, bo); + } else { + xe_bo_put(bo); + kunit_info(test, "[%d.%d] Unpinned 0x%p\n", + gt_to_tile(gt)->id, gt->info.id, bo); + } + + gt->uc.guc.g2g.bo = NULL; + } +} + +static void g2g_stop(struct kunit *test, struct xe_device *xe) +{ + struct xe_gt *gt; + int i; + + for_each_gt(gt, xe, i) { + struct xe_guc *guc = >->uc.guc; + + if (!guc->g2g.bo) + continue; + + g2g_ct_stop(guc); + } + + g2g_free(test, xe); +} + +/* + * Generate a unique id for each bi-directional CTB for each pair of + * near and far tiles/devices. The id can then be used as an index into + * a single allocation that is sub-divided into multiple CTBs. + * + * For example, with two devices per tile and two tiles, the table should + * look like: + * Far <tile>.<dev> + * 0.0 0.1 1.0 1.1 + * N 0.0 --/-- 00/01 02/03 04/05 + * e 0.1 01/00 --/-- 06/07 08/09 + * a 1.0 03/02 07/06 --/-- 10/11 + * r 1.1 05/04 09/08 11/10 --/-- + * + * Where each entry is Rx/Tx channel id. + * + * So GuC #3 (tile 1, dev 1) talking to GuC #2 (tile 1, dev 0) would + * be reading from channel #11 and writing to channel #10. Whereas, + * GuC #2 talking to GuC #3 would be read on #10 and write to #11. + */ +static int g2g_slot_flat(u32 near_tile, u32 near_dev, u32 far_tile, u32 far_dev, + u32 type, u32 max_inst, bool have_dev) +{ + u32 near = near_tile, far = far_tile; + u32 idx = 0, x, y, direction; + int i; + + if (have_dev) { + near = (near << 1) | near_dev; + far = (far << 1) | far_dev; + } + + /* No need to send to one's self */ + if (far == near) + return -1; + + if (far > near) { + /* Top right table half */ + x = far; + y = near; + + /* T/R is 'forwards' direction */ + direction = type; + } else { + /* Bottom left table half */ + x = near; + y = far; + + /* B/L is 'backwards' direction */ + direction = (1 - type); + } + + /* Count the rows prior to the target */ + for (i = y; i > 0; i--) + idx += max_inst - i; + + /* Count this row up to the target */ + idx += (x - 1 - y); + + /* Slots are in Rx/Tx pairs */ + idx *= 2; + + /* Pick Rx/Tx direction */ + idx += direction; + + return idx; +} + +static int g2g_register_flat(struct xe_guc *guc, u32 far_tile, u32 far_dev, u32 type, bool have_dev) +{ + struct xe_gt *gt = guc_to_gt(guc); + struct xe_device *xe = gt_to_xe(gt); + u32 near_tile = gt_to_tile(gt)->id; + u32 near_dev = G2G_DEV(gt); + u32 max = xe->info.gt_count; + int idx; + u32 base, desc, buf; + + if (!guc->g2g.bo) + return -ENODEV; + + idx = g2g_slot_flat(near_tile, near_dev, far_tile, far_dev, type, max, have_dev); + xe_assert(xe, idx >= 0); + + base = guc_bo_ggtt_addr(guc, guc->g2g.bo); + desc = base + idx * G2G_DESC_SIZE; + buf = base + idx * G2G_BUFFER_SIZE + G2G_DESC_AREA_SIZE; + + xe_assert(xe, (desc - base + G2G_DESC_SIZE) <= G2G_DESC_AREA_SIZE); + xe_assert(xe, (buf - base + G2G_BUFFER_SIZE) <= xe_bo_size(guc->g2g.bo)); + + return guc_action_register_g2g_buffer(guc, type, far_tile, far_dev, + desc, buf, G2G_BUFFER_SIZE); +} + +static void g2g_start(struct kunit *test, struct xe_guc *guc) +{ + struct xe_gt *remote_gt, *gt = guc_to_gt(guc); + struct xe_device *xe = gt_to_xe(gt); + unsigned int i; + int t, ret; + bool have_dev; + + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, guc->g2g.bo); + + /* GuC interface will need extending if more GT device types are ever created. */ + KUNIT_ASSERT_TRUE(test, + (gt->info.type == XE_GT_TYPE_MAIN) || + (gt->info.type == XE_GT_TYPE_MEDIA)); + + /* Channel numbering depends on whether there are multiple GTs per tile */ + have_dev = xe->info.gt_count > xe->info.tile_count; + + for_each_gt(remote_gt, xe, i) { + u32 tile, dev; + + if (remote_gt->info.id == gt->info.id) + continue; + + tile = gt_to_tile(remote_gt)->id; + dev = G2G_DEV(remote_gt); + + for (t = 0; t < XE_G2G_TYPE_LIMIT; t++) { + ret = g2g_register_flat(guc, tile, dev, t, have_dev); + KUNIT_ASSERT_EQ_MSG(test, 0, ret, "G2G register failed: %pe", ERR_PTR(ret)); + } + } +} + +static void g2g_reinit(struct kunit *test, struct xe_device *xe, int ctb_type, struct xe_tile *tile) +{ + struct xe_gt *gt; + int i, found = 0; + + g2g_stop(test, xe); + + for_each_gt(gt, xe, i) { + struct xe_guc *guc = >->uc.guc; + + KUNIT_ASSERT_NULL(test, guc->g2g.bo); + } + + switch (ctb_type) { + case G2G_CTB_TYPE_DEFAULT: + g2g_alloc_default(test, xe); + break; + + case G2G_CTB_TYPE_HOST: + g2g_alloc_host(test, xe); + break; + + case G2G_CTB_TYPE_TILE: + g2g_alloc_tile(test, xe, tile); + break; + + default: + KUNIT_ASSERT_TRUE(test, false); + } + + for_each_gt(gt, xe, i) { + struct xe_guc *guc = >->uc.guc; + + if (!guc->g2g.bo) + continue; + + if (ctb_type == G2G_CTB_TYPE_DEFAULT) + guc_g2g_start(guc); + else + g2g_start(test, guc); + found++; + } + + KUNIT_ASSERT_GT_MSG(test, found, 1, "insufficient G2G channels running: %d", found); + + kunit_info(test, "Testing across %d GTs\n", found); +} + +static void g2g_recreate_ctb(void *_xe) +{ + struct xe_device *xe = (struct xe_device *)_xe; + struct kunit *test = kunit_get_current_test(); + + g2g_stop(test, xe); + + if (xe_guc_g2g_wanted(xe)) + g2g_reinit(test, xe, G2G_CTB_TYPE_DEFAULT, NULL); +} + +static void g2g_pm_runtime_put(void *_xe) +{ + struct xe_device *xe = (struct xe_device *)_xe; + + xe_pm_runtime_put(xe); +} + +static void g2g_pm_runtime_get(struct kunit *test) +{ + struct xe_device *xe = test->priv; + int ret; + + xe_pm_runtime_get(xe); + ret = kunit_add_action_or_reset(test, g2g_pm_runtime_put, xe); + KUNIT_ASSERT_EQ_MSG(test, 0, ret, "Failed to register runtime PM action\n"); +} + +static void g2g_check_skip(struct kunit *test) +{ + struct xe_device *xe = test->priv; + struct xe_gt *gt; + int i; + + if (IS_SRIOV_VF(xe)) + kunit_skip(test, "not supported from a VF"); + + if (xe->info.gt_count <= 1) + kunit_skip(test, "not enough GTs"); + + for_each_gt(gt, xe, i) { + struct xe_guc *guc = >->uc.guc; + + if (guc->fw.build_type == CSS_UKERNEL_INFO_BUILDTYPE_PROD) + kunit_skip(test, + "G2G test interface not available in production firmware builds\n"); + } +} + +/* + * Simple test that does not try to recreate the CTBs. + * Requires that the platform already enables G2G comms + * but has no risk of leaving the system in a broken state + * afterwards. + */ +static void xe_live_guc_g2g_kunit_default(struct kunit *test) +{ + struct xe_device *xe = test->priv; + + if (!xe_guc_g2g_wanted(xe)) + kunit_skip(test, "G2G not enabled"); + + g2g_check_skip(test); + + g2g_pm_runtime_get(test); + + kunit_info(test, "Testing default CTBs\n"); + g2g_run_test(test, xe); + + kunit_release_action(test, &g2g_pm_runtime_put, xe); +} + +/* + * More complex test that re-creates the CTBs in various location to + * test access to each location from each GuC. Can be run even on + * systems that do not enable G2G by default. On the other hand, + * because it recreates the CTBs, if something goes wrong it could + * leave the system with broken G2G comms. + */ +static void xe_live_guc_g2g_kunit_allmem(struct kunit *test) +{ + struct xe_device *xe = test->priv; + int ret; + + g2g_check_skip(test); + + g2g_pm_runtime_get(test); + + /* Make sure to leave the system as we found it */ + ret = kunit_add_action_or_reset(test, g2g_recreate_ctb, xe); + KUNIT_ASSERT_EQ_MSG(test, 0, ret, "Failed to register CTB re-creation action\n"); + + kunit_info(test, "Testing CTB type 'default'...\n"); + g2g_reinit(test, xe, G2G_CTB_TYPE_DEFAULT, NULL); + g2g_run_test(test, xe); + + kunit_info(test, "Testing CTB type 'host'...\n"); + g2g_reinit(test, xe, G2G_CTB_TYPE_HOST, NULL); + g2g_run_test(test, xe); + + if (IS_DGFX(xe)) { + struct xe_tile *tile; + int id; + + for_each_tile(tile, xe, id) { + kunit_info(test, "Testing CTB type 'tile: #%d'...\n", id); + + g2g_reinit(test, xe, G2G_CTB_TYPE_TILE, tile); + g2g_run_test(test, xe); + } + } else { + kunit_info(test, "Skipping local memory on integrated platform\n"); + } + + kunit_release_action(test, g2g_recreate_ctb, xe); + kunit_release_action(test, g2g_pm_runtime_put, xe); +} + +static struct kunit_case xe_guc_g2g_tests[] = { + KUNIT_CASE_PARAM(xe_live_guc_g2g_kunit_default, xe_pci_live_device_gen_param), + KUNIT_CASE_PARAM(xe_live_guc_g2g_kunit_allmem, xe_pci_live_device_gen_param), + {} +}; + +VISIBLE_IF_KUNIT +struct kunit_suite xe_guc_g2g_test_suite = { + .name = "xe_guc_g2g", + .test_cases = xe_guc_g2g_tests, + .init = xe_kunit_helper_xe_device_live_test_init, +}; +EXPORT_SYMBOL_IF_KUNIT(xe_guc_g2g_test_suite); diff --git a/drivers/gpu/drm/xe/tests/xe_live_test_mod.c b/drivers/gpu/drm/xe/tests/xe_live_test_mod.c index 81277c77016d..c55e46f1ae92 100644 --- a/drivers/gpu/drm/xe/tests/xe_live_test_mod.c +++ b/drivers/gpu/drm/xe/tests/xe_live_test_mod.c @@ -10,12 +10,14 @@ extern struct kunit_suite xe_bo_shrink_test_suite; extern struct kunit_suite xe_dma_buf_test_suite; extern struct kunit_suite xe_migrate_test_suite; extern struct kunit_suite xe_mocs_test_suite; +extern struct kunit_suite xe_guc_g2g_test_suite; kunit_test_suite(xe_bo_test_suite); kunit_test_suite(xe_bo_shrink_test_suite); kunit_test_suite(xe_dma_buf_test_suite); kunit_test_suite(xe_migrate_test_suite); kunit_test_suite(xe_mocs_test_suite); +kunit_test_suite(xe_guc_g2g_test_suite); MODULE_AUTHOR("Intel Corporation"); MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/xe/tests/xe_migrate.c b/drivers/gpu/drm/xe/tests/xe_migrate.c index edd1e701aa1c..5904d658d1f2 100644 --- a/drivers/gpu/drm/xe/tests/xe_migrate.c +++ b/drivers/gpu/drm/xe/tests/xe_migrate.c @@ -70,7 +70,7 @@ static int run_sanity_job(struct xe_migrate *m, struct xe_device *xe, } } while (0) static void test_copy(struct xe_migrate *m, struct xe_bo *bo, - struct kunit *test, u32 region) + struct kunit *test, u32 region, struct drm_exec *exec) { struct xe_device *xe = tile_to_xe(m->tile); u64 retval, expected = 0; @@ -84,14 +84,15 @@ static void test_copy(struct xe_migrate *m, struct xe_bo *bo, ttm_bo_type_kernel, region | XE_BO_FLAG_NEEDS_CPU_ACCESS | - XE_BO_FLAG_PINNED); + XE_BO_FLAG_PINNED, + exec); if (IS_ERR(remote)) { KUNIT_FAIL(test, "Failed to allocate remote bo for %s: %pe\n", str, remote); return; } - err = xe_bo_validate(remote, NULL, false); + err = xe_bo_validate(remote, NULL, false, exec); if (err) { KUNIT_FAIL(test, "Failed to validate system bo for %s: %i\n", str, err); @@ -161,13 +162,13 @@ out_unlock: } static void test_copy_sysmem(struct xe_migrate *m, struct xe_bo *bo, - struct kunit *test) + struct drm_exec *exec, struct kunit *test) { - test_copy(m, bo, test, XE_BO_FLAG_SYSTEM); + test_copy(m, bo, test, XE_BO_FLAG_SYSTEM, exec); } static void test_copy_vram(struct xe_migrate *m, struct xe_bo *bo, - struct kunit *test) + struct drm_exec *exec, struct kunit *test) { u32 region; @@ -178,10 +179,11 @@ static void test_copy_vram(struct xe_migrate *m, struct xe_bo *bo, region = XE_BO_FLAG_VRAM1; else region = XE_BO_FLAG_VRAM0; - test_copy(m, bo, test, region); + test_copy(m, bo, test, region, exec); } -static void xe_migrate_sanity_test(struct xe_migrate *m, struct kunit *test) +static void xe_migrate_sanity_test(struct xe_migrate *m, struct kunit *test, + struct drm_exec *exec) { struct xe_tile *tile = m->tile; struct xe_device *xe = tile_to_xe(tile); @@ -202,7 +204,8 @@ static void xe_migrate_sanity_test(struct xe_migrate *m, struct kunit *test) big = xe_bo_create_pin_map(xe, tile, m->q->vm, SZ_4M, ttm_bo_type_kernel, - XE_BO_FLAG_VRAM_IF_DGFX(tile)); + XE_BO_FLAG_VRAM_IF_DGFX(tile), + exec); if (IS_ERR(big)) { KUNIT_FAIL(test, "Failed to allocate bo: %li\n", PTR_ERR(big)); goto vunmap; @@ -210,7 +213,8 @@ static void xe_migrate_sanity_test(struct xe_migrate *m, struct kunit *test) pt = xe_bo_create_pin_map(xe, tile, m->q->vm, XE_PAGE_SIZE, ttm_bo_type_kernel, - XE_BO_FLAG_VRAM_IF_DGFX(tile)); + XE_BO_FLAG_VRAM_IF_DGFX(tile), + exec); if (IS_ERR(pt)) { KUNIT_FAIL(test, "Failed to allocate fake pt: %li\n", PTR_ERR(pt)); @@ -220,7 +224,8 @@ static void xe_migrate_sanity_test(struct xe_migrate *m, struct kunit *test) tiny = xe_bo_create_pin_map(xe, tile, m->q->vm, 2 * SZ_4K, ttm_bo_type_kernel, - XE_BO_FLAG_VRAM_IF_DGFX(tile)); + XE_BO_FLAG_VRAM_IF_DGFX(tile), + exec); if (IS_ERR(tiny)) { KUNIT_FAIL(test, "Failed to allocate tiny fake pt: %li\n", PTR_ERR(tiny)); @@ -290,10 +295,10 @@ static void xe_migrate_sanity_test(struct xe_migrate *m, struct kunit *test) check(retval, expected, "Command clear small last value", test); kunit_info(test, "Copying small buffer object to system\n"); - test_copy_sysmem(m, tiny, test); + test_copy_sysmem(m, tiny, exec, test); if (xe->info.tile_count > 1) { kunit_info(test, "Copying small buffer object to other vram\n"); - test_copy_vram(m, tiny, test); + test_copy_vram(m, tiny, exec, test); } /* Clear a big bo */ @@ -312,10 +317,10 @@ static void xe_migrate_sanity_test(struct xe_migrate *m, struct kunit *test) check(retval, expected, "Command clear big last value", test); kunit_info(test, "Copying big buffer object to system\n"); - test_copy_sysmem(m, big, test); + test_copy_sysmem(m, big, exec, test); if (xe->info.tile_count > 1) { kunit_info(test, "Copying big buffer object to other vram\n"); - test_copy_vram(m, big, test); + test_copy_vram(m, big, exec, test); } out: @@ -343,10 +348,11 @@ static int migrate_test_run_device(struct xe_device *xe) for_each_tile(tile, xe, id) { struct xe_migrate *m = tile->migrate; + struct drm_exec *exec = XE_VALIDATION_OPT_OUT; kunit_info(test, "Testing tile id %d.\n", id); xe_vm_lock(m->q->vm, false); - xe_migrate_sanity_test(m, test); + xe_migrate_sanity_test(m, test, exec); xe_vm_unlock(m->q->vm); } @@ -490,7 +496,7 @@ err_sync: static void test_migrate(struct xe_device *xe, struct xe_tile *tile, struct xe_bo *sys_bo, struct xe_bo *vram_bo, struct xe_bo *ccs_bo, - struct kunit *test) + struct drm_exec *exec, struct kunit *test) { struct dma_fence *fence; u64 expected, retval; @@ -509,7 +515,7 @@ static void test_migrate(struct xe_device *xe, struct xe_tile *tile, dma_fence_put(fence); kunit_info(test, "Evict vram buffer object\n"); - ret = xe_bo_evict(vram_bo); + ret = xe_bo_evict(vram_bo, exec); if (ret) { KUNIT_FAIL(test, "Failed to evict bo.\n"); return; @@ -538,7 +544,7 @@ static void test_migrate(struct xe_device *xe, struct xe_tile *tile, dma_fence_put(fence); kunit_info(test, "Restore vram buffer object\n"); - ret = xe_bo_validate(vram_bo, NULL, false); + ret = xe_bo_validate(vram_bo, NULL, false, exec); if (ret) { KUNIT_FAIL(test, "Failed to validate vram bo for: %li\n", ret); return; @@ -636,13 +642,14 @@ static void validate_ccs_test_run_tile(struct xe_device *xe, struct xe_tile *til { struct xe_bo *sys_bo, *vram_bo = NULL, *ccs_bo = NULL; unsigned int bo_flags = XE_BO_FLAG_VRAM_IF_DGFX(tile); + struct drm_exec *exec; long ret; - sys_bo = xe_bo_create_user(xe, NULL, NULL, SZ_4M, + sys_bo = xe_bo_create_user(xe, NULL, SZ_4M, DRM_XE_GEM_CPU_CACHING_WC, XE_BO_FLAG_SYSTEM | XE_BO_FLAG_NEEDS_CPU_ACCESS | - XE_BO_FLAG_PINNED); + XE_BO_FLAG_PINNED, NULL); if (IS_ERR(sys_bo)) { KUNIT_FAIL(test, "xe_bo_create() failed with err=%ld\n", @@ -650,8 +657,9 @@ static void validate_ccs_test_run_tile(struct xe_device *xe, struct xe_tile *til return; } + exec = XE_VALIDATION_OPT_OUT; xe_bo_lock(sys_bo, false); - ret = xe_bo_validate(sys_bo, NULL, false); + ret = xe_bo_validate(sys_bo, NULL, false, exec); if (ret) { KUNIT_FAIL(test, "Failed to validate system bo for: %li\n", ret); goto free_sysbo; @@ -664,10 +672,10 @@ static void validate_ccs_test_run_tile(struct xe_device *xe, struct xe_tile *til } xe_bo_unlock(sys_bo); - ccs_bo = xe_bo_create_user(xe, NULL, NULL, SZ_4M, + ccs_bo = xe_bo_create_user(xe, NULL, SZ_4M, DRM_XE_GEM_CPU_CACHING_WC, bo_flags | XE_BO_FLAG_NEEDS_CPU_ACCESS | - XE_BO_FLAG_PINNED); + XE_BO_FLAG_PINNED, NULL); if (IS_ERR(ccs_bo)) { KUNIT_FAIL(test, "xe_bo_create() failed with err=%ld\n", @@ -676,7 +684,7 @@ static void validate_ccs_test_run_tile(struct xe_device *xe, struct xe_tile *til } xe_bo_lock(ccs_bo, false); - ret = xe_bo_validate(ccs_bo, NULL, false); + ret = xe_bo_validate(ccs_bo, NULL, false, exec); if (ret) { KUNIT_FAIL(test, "Failed to validate system bo for: %li\n", ret); goto free_ccsbo; @@ -689,10 +697,10 @@ static void validate_ccs_test_run_tile(struct xe_device *xe, struct xe_tile *til } xe_bo_unlock(ccs_bo); - vram_bo = xe_bo_create_user(xe, NULL, NULL, SZ_4M, + vram_bo = xe_bo_create_user(xe, NULL, SZ_4M, DRM_XE_GEM_CPU_CACHING_WC, bo_flags | XE_BO_FLAG_NEEDS_CPU_ACCESS | - XE_BO_FLAG_PINNED); + XE_BO_FLAG_PINNED, NULL); if (IS_ERR(vram_bo)) { KUNIT_FAIL(test, "xe_bo_create() failed with err=%ld\n", PTR_ERR(vram_bo)); @@ -700,7 +708,7 @@ static void validate_ccs_test_run_tile(struct xe_device *xe, struct xe_tile *til } xe_bo_lock(vram_bo, false); - ret = xe_bo_validate(vram_bo, NULL, false); + ret = xe_bo_validate(vram_bo, NULL, false, exec); if (ret) { KUNIT_FAIL(test, "Failed to validate vram bo for: %li\n", ret); goto free_vrambo; @@ -713,7 +721,7 @@ static void validate_ccs_test_run_tile(struct xe_device *xe, struct xe_tile *til } test_clear(xe, tile, sys_bo, vram_bo, test); - test_migrate(xe, tile, sys_bo, vram_bo, ccs_bo, test); + test_migrate(xe, tile, sys_bo, vram_bo, ccs_bo, exec, test); xe_bo_unlock(vram_bo); xe_bo_lock(vram_bo, false); diff --git a/drivers/gpu/drm/xe/tests/xe_pci.c b/drivers/gpu/drm/xe/tests/xe_pci.c index db30c5156d0c..aa29ac759d5d 100644 --- a/drivers/gpu/drm/xe/tests/xe_pci.c +++ b/drivers/gpu/drm/xe/tests/xe_pci.c @@ -12,12 +12,219 @@ #include <kunit/test-bug.h> #include <kunit/visibility.h> +#define PLATFORM_CASE(platform__, graphics_step__) \ + { \ + .platform = XE_ ## platform__, \ + .subplatform = XE_SUBPLATFORM_NONE, \ + .step = { .graphics = STEP_ ## graphics_step__ } \ + } + +#define SUBPLATFORM_CASE(platform__, subplatform__, graphics_step__) \ + { \ + .platform = XE_ ## platform__, \ + .subplatform = XE_SUBPLATFORM_ ## platform__ ## _ ## subplatform__, \ + .step = { .graphics = STEP_ ## graphics_step__ } \ + } + +#define GMDID_CASE(platform__, graphics_verx100__, graphics_step__, \ + media_verx100__, media_step__) \ + { \ + .platform = XE_ ## platform__, \ + .subplatform = XE_SUBPLATFORM_NONE, \ + .graphics_verx100 = graphics_verx100__, \ + .media_verx100 = media_verx100__, \ + .step = { .graphics = STEP_ ## graphics_step__, \ + .media = STEP_ ## media_step__ } \ + } + +static const struct xe_pci_fake_data cases[] = { + PLATFORM_CASE(TIGERLAKE, B0), + PLATFORM_CASE(DG1, A0), + PLATFORM_CASE(DG1, B0), + PLATFORM_CASE(ALDERLAKE_S, A0), + PLATFORM_CASE(ALDERLAKE_S, B0), + PLATFORM_CASE(ALDERLAKE_S, C0), + PLATFORM_CASE(ALDERLAKE_S, D0), + PLATFORM_CASE(ALDERLAKE_P, A0), + PLATFORM_CASE(ALDERLAKE_P, B0), + PLATFORM_CASE(ALDERLAKE_P, C0), + SUBPLATFORM_CASE(ALDERLAKE_S, RPLS, D0), + SUBPLATFORM_CASE(ALDERLAKE_P, RPLU, E0), + SUBPLATFORM_CASE(DG2, G10, C0), + SUBPLATFORM_CASE(DG2, G11, B1), + SUBPLATFORM_CASE(DG2, G12, A1), + GMDID_CASE(METEORLAKE, 1270, A0, 1300, A0), + GMDID_CASE(METEORLAKE, 1271, A0, 1300, A0), + GMDID_CASE(METEORLAKE, 1274, A0, 1300, A0), + GMDID_CASE(LUNARLAKE, 2004, A0, 2000, A0), + GMDID_CASE(LUNARLAKE, 2004, B0, 2000, A0), + GMDID_CASE(BATTLEMAGE, 2001, A0, 1301, A1), + GMDID_CASE(PANTHERLAKE, 3000, A0, 3000, A0), +}; + +KUNIT_ARRAY_PARAM(platform, cases, xe_pci_fake_data_desc); + +/** + * xe_pci_fake_data_gen_params - Generate struct xe_pci_fake_data parameters + * @prev: the pointer to the previous parameter to iterate from or NULL + * @desc: output buffer with minimum size of KUNIT_PARAM_DESC_SIZE + * + * This function prepares struct xe_pci_fake_data parameter. + * + * To be used only as a parameter generator function in &KUNIT_CASE_PARAM. + * + * Return: pointer to the next parameter or NULL if no more parameters + */ +const void *xe_pci_fake_data_gen_params(const void *prev, char *desc) +{ + return platform_gen_params(prev, desc); +} +EXPORT_SYMBOL_IF_KUNIT(xe_pci_fake_data_gen_params); + +static const struct xe_device_desc *lookup_desc(enum xe_platform p) +{ + const struct xe_device_desc *desc; + const struct pci_device_id *ids; + + for (ids = pciidlist; ids->driver_data; ids++) { + desc = (const void *)ids->driver_data; + if (desc->platform == p) + return desc; + } + return NULL; +} + +static const struct xe_subplatform_desc *lookup_sub_desc(enum xe_platform p, enum xe_subplatform s) +{ + const struct xe_device_desc *desc = lookup_desc(p); + const struct xe_subplatform_desc *spd; + + if (desc && desc->subplatforms) + for (spd = desc->subplatforms; spd->subplatform; spd++) + if (spd->subplatform == s) + return spd; + return NULL; +} + +static const char *lookup_platform_name(enum xe_platform p) +{ + const struct xe_device_desc *desc = lookup_desc(p); + + return desc ? desc->platform_name : "INVALID"; +} + +static const char *__lookup_subplatform_name(enum xe_platform p, enum xe_subplatform s) +{ + const struct xe_subplatform_desc *desc = lookup_sub_desc(p, s); + + return desc ? desc->name : "INVALID"; +} + +static const char *lookup_subplatform_name(enum xe_platform p, enum xe_subplatform s) +{ + return s == XE_SUBPLATFORM_NONE ? "" : __lookup_subplatform_name(p, s); +} + +static const char *subplatform_prefix(enum xe_subplatform s) +{ + return s == XE_SUBPLATFORM_NONE ? "" : " "; +} + +static const char *step_prefix(enum xe_step step) +{ + return step == STEP_NONE ? "" : " "; +} + +static const char *step_name(enum xe_step step) +{ + return step == STEP_NONE ? "" : xe_step_name(step); +} + +static const char *sriov_prefix(enum xe_sriov_mode mode) +{ + return mode <= XE_SRIOV_MODE_NONE ? "" : " "; +} + +static const char *sriov_name(enum xe_sriov_mode mode) +{ + return mode <= XE_SRIOV_MODE_NONE ? "" : xe_sriov_mode_to_string(mode); +} + +static const char *lookup_graphics_name(unsigned int verx100) +{ + const struct xe_ip *ip = find_graphics_ip(verx100); + + return ip ? ip->name : ""; +} + +static const char *lookup_media_name(unsigned int verx100) +{ + const struct xe_ip *ip = find_media_ip(verx100); + + return ip ? ip->name : ""; +} + +/** + * xe_pci_fake_data_desc - Describe struct xe_pci_fake_data parameter + * @param: the &struct xe_pci_fake_data parameter to describe + * @desc: output buffer with minimum size of KUNIT_PARAM_DESC_SIZE + * + * This function prepares description of the struct xe_pci_fake_data parameter. + * + * It is tailored for use in parameterized KUnit tests where parameter generator + * is based on the struct xe_pci_fake_data arrays. + */ +void xe_pci_fake_data_desc(const struct xe_pci_fake_data *param, char *desc) +{ + if (param->graphics_verx100 || param->media_verx100) + snprintf(desc, KUNIT_PARAM_DESC_SIZE, "%s%s%s %u.%02u(%s)%s%s %u.%02u(%s)%s%s%s%s", + lookup_platform_name(param->platform), + subplatform_prefix(param->subplatform), + lookup_subplatform_name(param->platform, param->subplatform), + param->graphics_verx100 / 100, param->graphics_verx100 % 100, + lookup_graphics_name(param->graphics_verx100), + step_prefix(param->step.graphics), step_name(param->step.graphics), + param->media_verx100 / 100, param->media_verx100 % 100, + lookup_media_name(param->media_verx100), + step_prefix(param->step.media), step_name(param->step.media), + sriov_prefix(param->sriov_mode), sriov_name(param->sriov_mode)); + else + snprintf(desc, KUNIT_PARAM_DESC_SIZE, "%s%s%s%s%s%s%s", + lookup_platform_name(param->platform), + subplatform_prefix(param->subplatform), + lookup_subplatform_name(param->platform, param->subplatform), + step_prefix(param->step.graphics), step_name(param->step.graphics), + sriov_prefix(param->sriov_mode), sriov_name(param->sriov_mode)); +} +EXPORT_SYMBOL_IF_KUNIT(xe_pci_fake_data_desc); + static void xe_ip_kunit_desc(const struct xe_ip *param, char *desc) { snprintf(desc, KUNIT_PARAM_DESC_SIZE, "%u.%02u %s", param->verx100 / 100, param->verx100 % 100, param->name); } +/* + * Pre-GMDID Graphics and Media IPs definitions. + * + * Mimic the way GMDID IPs are declared so the same + * param generator can be used for both + */ +static const struct xe_ip pre_gmdid_graphics_ips[] = { + graphics_ip_xelp, + graphics_ip_xelpp, + graphics_ip_xehpg, + graphics_ip_xehpc, +}; + +static const struct xe_ip pre_gmdid_media_ips[] = { + media_ip_xem, + media_ip_xehpm, +}; + +KUNIT_ARRAY_PARAM(pre_gmdid_graphics_ip, pre_gmdid_graphics_ips, xe_ip_kunit_desc); +KUNIT_ARRAY_PARAM(pre_gmdid_media_ip, pre_gmdid_media_ips, xe_ip_kunit_desc); + KUNIT_ARRAY_PARAM(graphics_ip, graphics_ips, xe_ip_kunit_desc); KUNIT_ARRAY_PARAM(media_ip, media_ips, xe_ip_kunit_desc); @@ -46,6 +253,13 @@ KUNIT_ARRAY_PARAM(pci_id, pciidlist, xe_pci_id_kunit_desc); */ const void *xe_pci_graphics_ip_gen_param(const void *prev, char *desc) { + const void *next = pre_gmdid_graphics_ip_gen_params(prev, desc); + + if (next) + return next; + if (is_insidevar(prev, pre_gmdid_graphics_ips)) + prev = NULL; + return graphics_ip_gen_params(prev, desc); } EXPORT_SYMBOL_IF_KUNIT(xe_pci_graphics_ip_gen_param); @@ -63,6 +277,13 @@ EXPORT_SYMBOL_IF_KUNIT(xe_pci_graphics_ip_gen_param); */ const void *xe_pci_media_ip_gen_param(const void *prev, char *desc) { + const void *next = pre_gmdid_media_ip_gen_params(prev, desc); + + if (next) + return next; + if (is_insidevar(prev, pre_gmdid_media_ips)) + prev = NULL; + return media_ip_gen_params(prev, desc); } EXPORT_SYMBOL_IF_KUNIT(xe_pci_media_ip_gen_param); @@ -94,10 +315,10 @@ static void fake_read_gmdid(struct xe_device *xe, enum xe_gmdid_type type, if (type == GMDID_MEDIA) { *ver = data->media_verx100; - *revid = xe_step_to_gmdid(data->media_step); + *revid = xe_step_to_gmdid(data->step.media); } else { *ver = data->graphics_verx100; - *revid = xe_step_to_gmdid(data->graphics_step); + *revid = xe_step_to_gmdid(data->step.graphics); } } diff --git a/drivers/gpu/drm/xe/tests/xe_pci_test.h b/drivers/gpu/drm/xe/tests/xe_pci_test.h index ce4d2b86b778..5e9a7ffc747f 100644 --- a/drivers/gpu/drm/xe/tests/xe_pci_test.h +++ b/drivers/gpu/drm/xe/tests/xe_pci_test.h @@ -10,6 +10,7 @@ #include "xe_platform_types.h" #include "xe_sriov_types.h" +#include "xe_step_types.h" struct xe_device; @@ -17,13 +18,14 @@ struct xe_pci_fake_data { enum xe_sriov_mode sriov_mode; enum xe_platform platform; enum xe_subplatform subplatform; + struct xe_step_info step; u32 graphics_verx100; u32 media_verx100; - u32 graphics_step; - u32 media_step; }; int xe_pci_fake_device_init(struct xe_device *xe); +const void *xe_pci_fake_data_gen_params(const void *prev, char *desc); +void xe_pci_fake_data_desc(const struct xe_pci_fake_data *param, char *desc); const void *xe_pci_graphics_ip_gen_param(const void *prev, char *desc); const void *xe_pci_media_ip_gen_param(const void *prev, char *desc); diff --git a/drivers/gpu/drm/xe/tests/xe_wa_test.c b/drivers/gpu/drm/xe/tests/xe_wa_test.c index 416258c193f6..49d191043dfa 100644 --- a/drivers/gpu/drm/xe/tests/xe_wa_test.c +++ b/drivers/gpu/drm/xe/tests/xe_wa_test.c @@ -15,87 +15,10 @@ #include "xe_tuning.h" #include "xe_wa.h" -struct platform_test_case { - const char *name; - enum xe_platform platform; - enum xe_subplatform subplatform; - u32 graphics_verx100; - u32 media_verx100; - struct xe_step_info step; -}; - -#define PLATFORM_CASE(platform__, graphics_step__) \ - { \ - .name = #platform__ " (" #graphics_step__ ")", \ - .platform = XE_ ## platform__, \ - .subplatform = XE_SUBPLATFORM_NONE, \ - .step = { .graphics = STEP_ ## graphics_step__ } \ - } - - -#define SUBPLATFORM_CASE(platform__, subplatform__, graphics_step__) \ - { \ - .name = #platform__ "_" #subplatform__ " (" #graphics_step__ ")", \ - .platform = XE_ ## platform__, \ - .subplatform = XE_SUBPLATFORM_ ## platform__ ## _ ## subplatform__, \ - .step = { .graphics = STEP_ ## graphics_step__ } \ - } - -#define GMDID_CASE(platform__, graphics_verx100__, graphics_step__, \ - media_verx100__, media_step__) \ - { \ - .name = #platform__ " (g:" #graphics_step__ ", m:" #media_step__ ")",\ - .platform = XE_ ## platform__, \ - .subplatform = XE_SUBPLATFORM_NONE, \ - .graphics_verx100 = graphics_verx100__, \ - .media_verx100 = media_verx100__, \ - .step = { .graphics = STEP_ ## graphics_step__, \ - .media = STEP_ ## media_step__ } \ - } - -static const struct platform_test_case cases[] = { - PLATFORM_CASE(TIGERLAKE, B0), - PLATFORM_CASE(DG1, A0), - PLATFORM_CASE(DG1, B0), - PLATFORM_CASE(ALDERLAKE_S, A0), - PLATFORM_CASE(ALDERLAKE_S, B0), - PLATFORM_CASE(ALDERLAKE_S, C0), - PLATFORM_CASE(ALDERLAKE_S, D0), - PLATFORM_CASE(ALDERLAKE_P, A0), - PLATFORM_CASE(ALDERLAKE_P, B0), - PLATFORM_CASE(ALDERLAKE_P, C0), - SUBPLATFORM_CASE(ALDERLAKE_S, RPLS, D0), - SUBPLATFORM_CASE(ALDERLAKE_P, RPLU, E0), - SUBPLATFORM_CASE(DG2, G10, C0), - SUBPLATFORM_CASE(DG2, G11, B1), - SUBPLATFORM_CASE(DG2, G12, A1), - GMDID_CASE(METEORLAKE, 1270, A0, 1300, A0), - GMDID_CASE(METEORLAKE, 1271, A0, 1300, A0), - GMDID_CASE(METEORLAKE, 1274, A0, 1300, A0), - GMDID_CASE(LUNARLAKE, 2004, A0, 2000, A0), - GMDID_CASE(LUNARLAKE, 2004, B0, 2000, A0), - GMDID_CASE(BATTLEMAGE, 2001, A0, 1301, A1), - GMDID_CASE(PANTHERLAKE, 3000, A0, 3000, A0), -}; - -static void platform_desc(const struct platform_test_case *t, char *desc) -{ - strscpy(desc, t->name, KUNIT_PARAM_DESC_SIZE); -} - -KUNIT_ARRAY_PARAM(platform, cases, platform_desc); - static int xe_wa_test_init(struct kunit *test) { - const struct platform_test_case *param = test->param_value; - struct xe_pci_fake_data data = { - .platform = param->platform, - .subplatform = param->subplatform, - .graphics_verx100 = param->graphics_verx100, - .media_verx100 = param->media_verx100, - .graphics_step = param->step.graphics, - .media_step = param->step.media, - }; + const struct xe_pci_fake_data *param = test->param_value; + struct xe_pci_fake_data data = *param; struct xe_device *xe; struct device *dev; int ret; @@ -120,13 +43,6 @@ static int xe_wa_test_init(struct kunit *test) return 0; } -static void xe_wa_test_exit(struct kunit *test) -{ - struct xe_device *xe = test->priv; - - drm_kunit_helper_free_device(test, xe->drm.dev); -} - static void xe_wa_gt(struct kunit *test) { struct xe_device *xe = test->priv; @@ -144,14 +60,13 @@ static void xe_wa_gt(struct kunit *test) } static struct kunit_case xe_wa_tests[] = { - KUNIT_CASE_PARAM(xe_wa_gt, platform_gen_params), + KUNIT_CASE_PARAM(xe_wa_gt, xe_pci_fake_data_gen_params), {} }; static struct kunit_suite xe_rtp_test_suite = { .name = "xe_wa", .init = xe_wa_test_init, - .exit = xe_wa_test_exit, .test_cases = xe_wa_tests, }; diff --git a/drivers/gpu/drm/xe/xe_bb.c b/drivers/gpu/drm/xe/xe_bb.c index feb6e013dc38..6d20229c11de 100644 --- a/drivers/gpu/drm/xe/xe_bb.c +++ b/drivers/gpu/drm/xe/xe_bb.c @@ -64,7 +64,7 @@ struct xe_bb *xe_bb_ccs_new(struct xe_gt *gt, u32 dwords, enum xe_sriov_vf_ccs_rw_ctxs ctx_id) { struct xe_bb *bb = kmalloc(sizeof(*bb), GFP_KERNEL); - struct xe_tile *tile = gt_to_tile(gt); + struct xe_device *xe = gt_to_xe(gt); struct xe_sa_manager *bb_pool; int err; @@ -78,7 +78,7 @@ struct xe_bb *xe_bb_ccs_new(struct xe_gt *gt, u32 dwords, * So, this extra DW acts as a guard here. */ - bb_pool = tile->sriov.vf.ccs[ctx_id].mem.ccs_bb_pool; + bb_pool = xe->sriov.vf.ccs.contexts[ctx_id].mem.ccs_bb_pool; bb->bo = xe_sa_bo_new(bb_pool, 4 * (dwords + 1)); if (IS_ERR(bb->bo)) { diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c index 4faf15d5fa6d..8422f3cab113 100644 --- a/drivers/gpu/drm/xe/xe_bo.c +++ b/drivers/gpu/drm/xe/xe_bo.c @@ -188,6 +188,8 @@ static void try_add_system(struct xe_device *xe, struct xe_bo *bo, bo->placements[*c] = (struct ttm_place) { .mem_type = XE_PL_TT, + .flags = (bo_flags & XE_BO_FLAG_VRAM_MASK) ? + TTM_PL_FLAG_FALLBACK : 0, }; *c += 1; } @@ -972,11 +974,11 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict, * CCS meta data is migrated from TT -> SMEM. So, let us detach the * BBs from BO as it is no longer needed. */ - if (IS_VF_CCS_BB_VALID(xe, bo) && old_mem_type == XE_PL_TT && + if (IS_VF_CCS_READY(xe) && old_mem_type == XE_PL_TT && new_mem->mem_type == XE_PL_SYSTEM) xe_sriov_vf_ccs_detach_bo(bo); - if (IS_SRIOV_VF(xe) && + if (IS_VF_CCS_READY(xe) && ((move_lacks_source && new_mem->mem_type == XE_PL_TT) || (old_mem_type == XE_PL_SYSTEM && new_mem->mem_type == XE_PL_TT)) && handle_system_ccs) @@ -992,7 +994,7 @@ out: if (timeout < 0) ret = timeout; - if (IS_VF_CCS_BB_VALID(xe, bo)) + if (IS_VF_CCS_READY(xe)) xe_sriov_vf_ccs_detach_bo(bo); xe_tt_unmap_sg(xe, ttm_bo->ttm); @@ -1139,42 +1141,47 @@ out_unref: int xe_bo_notifier_prepare_pinned(struct xe_bo *bo) { struct xe_device *xe = ttm_to_xe_device(bo->ttm.bdev); + struct xe_validation_ctx ctx; + struct drm_exec exec; struct xe_bo *backup; int ret = 0; - xe_bo_lock(bo, false); + xe_validation_guard(&ctx, &xe->val, &exec, (struct xe_val_flags) {.exclusive = true}, ret) { + ret = drm_exec_lock_obj(&exec, &bo->ttm.base); + drm_exec_retry_on_contention(&exec); + xe_assert(xe, !ret); + xe_assert(xe, !bo->backup_obj); - xe_assert(xe, !bo->backup_obj); + /* + * Since this is called from the PM notifier we might have raced with + * someone unpinning this after we dropped the pinned list lock and + * grabbing the above bo lock. + */ + if (!xe_bo_is_pinned(bo)) + break; - /* - * Since this is called from the PM notifier we might have raced with - * someone unpinning this after we dropped the pinned list lock and - * grabbing the above bo lock. - */ - if (!xe_bo_is_pinned(bo)) - goto out_unlock_bo; + if (!xe_bo_is_vram(bo)) + break; - if (!xe_bo_is_vram(bo)) - goto out_unlock_bo; + if (bo->flags & XE_BO_FLAG_PINNED_NORESTORE) + break; - if (bo->flags & XE_BO_FLAG_PINNED_NORESTORE) - goto out_unlock_bo; + backup = xe_bo_init_locked(xe, NULL, NULL, bo->ttm.base.resv, NULL, xe_bo_size(bo), + DRM_XE_GEM_CPU_CACHING_WB, ttm_bo_type_kernel, + XE_BO_FLAG_SYSTEM | XE_BO_FLAG_NEEDS_CPU_ACCESS | + XE_BO_FLAG_PINNED, &exec); + if (IS_ERR(backup)) { + drm_exec_retry_on_contention(&exec); + ret = PTR_ERR(backup); + xe_validation_retry_on_oom(&ctx, &ret); + break; + } - backup = ___xe_bo_create_locked(xe, NULL, NULL, bo->ttm.base.resv, NULL, xe_bo_size(bo), - DRM_XE_GEM_CPU_CACHING_WB, ttm_bo_type_kernel, - XE_BO_FLAG_SYSTEM | XE_BO_FLAG_NEEDS_CPU_ACCESS | - XE_BO_FLAG_PINNED); - if (IS_ERR(backup)) { - ret = PTR_ERR(backup); - goto out_unlock_bo; + backup->parent_obj = xe_bo_get(bo); /* Released by bo_destroy */ + ttm_bo_pin(&backup->ttm); + bo->backup_obj = backup; } - backup->parent_obj = xe_bo_get(bo); /* Released by bo_destroy */ - ttm_bo_pin(&backup->ttm); - bo->backup_obj = backup; - -out_unlock_bo: - xe_bo_unlock(bo); return ret; } @@ -1200,57 +1207,12 @@ int xe_bo_notifier_unprepare_pinned(struct xe_bo *bo) return 0; } -/** - * xe_bo_evict_pinned() - Evict a pinned VRAM object to system memory - * @bo: The buffer object to move. - * - * On successful completion, the object memory will be moved to system memory. - * - * This is needed to for special handling of pinned VRAM object during - * suspend-resume. - * - * Return: 0 on success. Negative error code on failure. - */ -int xe_bo_evict_pinned(struct xe_bo *bo) +static int xe_bo_evict_pinned_copy(struct xe_bo *bo, struct xe_bo *backup) { - struct xe_device *xe = ttm_to_xe_device(bo->ttm.bdev); - struct xe_bo *backup = bo->backup_obj; - bool backup_created = false; + struct xe_device *xe = xe_bo_device(bo); bool unmap = false; int ret = 0; - xe_bo_lock(bo, false); - - if (WARN_ON(!bo->ttm.resource)) { - ret = -EINVAL; - goto out_unlock_bo; - } - - if (WARN_ON(!xe_bo_is_pinned(bo))) { - ret = -EINVAL; - goto out_unlock_bo; - } - - if (!xe_bo_is_vram(bo)) - goto out_unlock_bo; - - if (bo->flags & XE_BO_FLAG_PINNED_NORESTORE) - goto out_unlock_bo; - - if (!backup) { - backup = ___xe_bo_create_locked(xe, NULL, NULL, bo->ttm.base.resv, - NULL, xe_bo_size(bo), - DRM_XE_GEM_CPU_CACHING_WB, ttm_bo_type_kernel, - XE_BO_FLAG_SYSTEM | XE_BO_FLAG_NEEDS_CPU_ACCESS | - XE_BO_FLAG_PINNED); - if (IS_ERR(backup)) { - ret = PTR_ERR(backup); - goto out_unlock_bo; - } - backup->parent_obj = xe_bo_get(bo); /* Released by bo_destroy */ - backup_created = true; - } - if (xe_bo_is_user(bo) || (bo->flags & XE_BO_FLAG_PINNED_LATE_RESTORE)) { struct xe_migrate *migrate; struct dma_fence *fence; @@ -1260,14 +1222,11 @@ int xe_bo_evict_pinned(struct xe_bo *bo) else migrate = mem_type_to_migrate(xe, bo->ttm.resource->mem_type); + xe_assert(xe, bo->ttm.base.resv == backup->ttm.base.resv); ret = dma_resv_reserve_fences(bo->ttm.base.resv, 1); if (ret) goto out_backup; - ret = dma_resv_reserve_fences(backup->ttm.base.resv, 1); - if (ret) - goto out_backup; - fence = xe_migrate_copy(migrate, bo, backup, bo->ttm.resource, backup->ttm.resource, false); if (IS_ERR(fence)) { @@ -1277,8 +1236,6 @@ int xe_bo_evict_pinned(struct xe_bo *bo) dma_resv_add_fence(bo->ttm.base.resv, fence, DMA_RESV_USAGE_KERNEL); - dma_resv_add_fence(backup->ttm.base.resv, fence, - DMA_RESV_USAGE_KERNEL); dma_fence_put(fence); } else { ret = xe_bo_vmap(backup); @@ -1288,7 +1245,7 @@ int xe_bo_evict_pinned(struct xe_bo *bo) if (iosys_map_is_null(&bo->vmap)) { ret = xe_bo_vmap(bo); if (ret) - goto out_backup; + goto out_vunmap; unmap = true; } @@ -1298,15 +1255,78 @@ int xe_bo_evict_pinned(struct xe_bo *bo) if (!bo->backup_obj) bo->backup_obj = backup; - -out_backup: +out_vunmap: xe_bo_vunmap(backup); - if (ret && backup_created) - xe_bo_put(backup); -out_unlock_bo: +out_backup: if (unmap) xe_bo_vunmap(bo); - xe_bo_unlock(bo); + + return ret; +} + +/** + * xe_bo_evict_pinned() - Evict a pinned VRAM object to system memory + * @bo: The buffer object to move. + * + * On successful completion, the object memory will be moved to system memory. + * + * This is needed to for special handling of pinned VRAM object during + * suspend-resume. + * + * Return: 0 on success. Negative error code on failure. + */ +int xe_bo_evict_pinned(struct xe_bo *bo) +{ + struct xe_device *xe = ttm_to_xe_device(bo->ttm.bdev); + struct xe_validation_ctx ctx; + struct drm_exec exec; + struct xe_bo *backup = bo->backup_obj; + bool backup_created = false; + int ret = 0; + + xe_validation_guard(&ctx, &xe->val, &exec, (struct xe_val_flags) {.exclusive = true}, ret) { + ret = drm_exec_lock_obj(&exec, &bo->ttm.base); + drm_exec_retry_on_contention(&exec); + xe_assert(xe, !ret); + + if (WARN_ON(!bo->ttm.resource)) { + ret = -EINVAL; + break; + } + + if (WARN_ON(!xe_bo_is_pinned(bo))) { + ret = -EINVAL; + break; + } + + if (!xe_bo_is_vram(bo)) + break; + + if (bo->flags & XE_BO_FLAG_PINNED_NORESTORE) + break; + + if (!backup) { + backup = xe_bo_init_locked(xe, NULL, NULL, bo->ttm.base.resv, NULL, + xe_bo_size(bo), + DRM_XE_GEM_CPU_CACHING_WB, ttm_bo_type_kernel, + XE_BO_FLAG_SYSTEM | XE_BO_FLAG_NEEDS_CPU_ACCESS | + XE_BO_FLAG_PINNED, &exec); + if (IS_ERR(backup)) { + drm_exec_retry_on_contention(&exec); + ret = PTR_ERR(backup); + xe_validation_retry_on_oom(&ctx, &ret); + break; + } + backup->parent_obj = xe_bo_get(bo); /* Released by bo_destroy */ + backup_created = true; + } + + ret = xe_bo_evict_pinned_copy(bo, backup); + } + + if (ret && backup_created) + xe_bo_put(backup); + return ret; } @@ -1356,10 +1376,6 @@ int xe_bo_restore_pinned(struct xe_bo *bo) if (ret) goto out_unlock_bo; - ret = dma_resv_reserve_fences(backup->ttm.base.resv, 1); - if (ret) - goto out_unlock_bo; - fence = xe_migrate_copy(migrate, backup, bo, backup->ttm.resource, bo->ttm.resource, false); @@ -1370,8 +1386,6 @@ int xe_bo_restore_pinned(struct xe_bo *bo) dma_resv_add_fence(bo->ttm.base.resv, fence, DMA_RESV_USAGE_KERNEL); - dma_resv_add_fence(backup->ttm.base.resv, fence, - DMA_RESV_USAGE_KERNEL); dma_fence_put(fence); } else { ret = xe_bo_vmap(backup); @@ -1527,7 +1541,7 @@ static void xe_ttm_bo_delete_mem_notify(struct ttm_buffer_object *ttm_bo) if (!xe_bo_is_xe_bo(ttm_bo)) return; - if (IS_VF_CCS_BB_VALID(ttm_to_xe_device(ttm_bo->bdev), bo)) + if (IS_VF_CCS_READY(ttm_to_xe_device(ttm_bo->bdev))) xe_sriov_vf_ccs_detach_bo(bo); /* @@ -1723,65 +1737,234 @@ static bool should_migrate_to_smem(struct xe_bo *bo) bo->attr.atomic_access == DRM_XE_ATOMIC_CPU; } -static vm_fault_t xe_gem_fault(struct vm_fault *vmf) +/* Populate the bo if swapped out, or migrate if the access mode requires that. */ +static int xe_bo_fault_migrate(struct xe_bo *bo, struct ttm_operation_ctx *ctx, + struct drm_exec *exec) +{ + struct ttm_buffer_object *tbo = &bo->ttm; + int err = 0; + + if (ttm_manager_type(tbo->bdev, tbo->resource->mem_type)->use_tt) { + xe_assert(xe_bo_device(bo), + dma_resv_test_signaled(tbo->base.resv, DMA_RESV_USAGE_KERNEL) || + (tbo->ttm && ttm_tt_is_populated(tbo->ttm))); + err = ttm_bo_populate(&bo->ttm, ctx); + } else if (should_migrate_to_smem(bo)) { + xe_assert(xe_bo_device(bo), bo->flags & XE_BO_FLAG_SYSTEM); + err = xe_bo_migrate(bo, XE_PL_TT, ctx, exec); + } + + return err; +} + +/* Call into TTM to populate PTEs, and register bo for PTE removal on runtime suspend. */ +static vm_fault_t __xe_bo_cpu_fault(struct vm_fault *vmf, struct xe_device *xe, struct xe_bo *bo) +{ + vm_fault_t ret; + + trace_xe_bo_cpu_fault(bo); + + ret = ttm_bo_vm_fault_reserved(vmf, vmf->vma->vm_page_prot, + TTM_BO_VM_NUM_PREFAULT); + /* + * When TTM is actually called to insert PTEs, ensure no blocking conditions + * remain, in which case TTM may drop locks and return VM_FAULT_RETRY. + */ + xe_assert(xe, ret != VM_FAULT_RETRY); + + if (ret == VM_FAULT_NOPAGE && + mem_type_is_vram(bo->ttm.resource->mem_type)) { + mutex_lock(&xe->mem_access.vram_userfault.lock); + if (list_empty(&bo->vram_userfault_link)) + list_add(&bo->vram_userfault_link, + &xe->mem_access.vram_userfault.list); + mutex_unlock(&xe->mem_access.vram_userfault.lock); + } + + return ret; +} + +static vm_fault_t xe_err_to_fault_t(int err) +{ + switch (err) { + case 0: + case -EINTR: + case -ERESTARTSYS: + case -EAGAIN: + return VM_FAULT_NOPAGE; + case -ENOMEM: + case -ENOSPC: + return VM_FAULT_OOM; + default: + break; + } + return VM_FAULT_SIGBUS; +} + +static bool xe_ttm_bo_is_imported(struct ttm_buffer_object *tbo) +{ + dma_resv_assert_held(tbo->base.resv); + + return tbo->ttm && + (tbo->ttm->page_flags & (TTM_TT_FLAG_EXTERNAL | TTM_TT_FLAG_EXTERNAL_MAPPABLE)) == + TTM_TT_FLAG_EXTERNAL; +} + +static vm_fault_t xe_bo_cpu_fault_fastpath(struct vm_fault *vmf, struct xe_device *xe, + struct xe_bo *bo, bool needs_rpm) +{ + struct ttm_buffer_object *tbo = &bo->ttm; + vm_fault_t ret = VM_FAULT_RETRY; + struct xe_validation_ctx ctx; + struct ttm_operation_ctx tctx = { + .interruptible = true, + .no_wait_gpu = true, + .gfp_retry_mayfail = true, + + }; + int err; + + if (needs_rpm && !xe_pm_runtime_get_if_active(xe)) + return VM_FAULT_RETRY; + + err = xe_validation_ctx_init(&ctx, &xe->val, NULL, + (struct xe_val_flags) { + .interruptible = true, + .no_block = true + }); + if (err) + goto out_pm; + + if (!dma_resv_trylock(tbo->base.resv)) + goto out_validation; + + if (xe_ttm_bo_is_imported(tbo)) { + ret = VM_FAULT_SIGBUS; + drm_dbg(&xe->drm, "CPU trying to access an imported buffer object.\n"); + goto out_unlock; + } + + err = xe_bo_fault_migrate(bo, &tctx, NULL); + if (err) { + /* Return VM_FAULT_RETRY on these errors. */ + if (err != -ENOMEM && err != -ENOSPC && err != -EBUSY) + ret = xe_err_to_fault_t(err); + goto out_unlock; + } + + if (dma_resv_test_signaled(bo->ttm.base.resv, DMA_RESV_USAGE_KERNEL)) + ret = __xe_bo_cpu_fault(vmf, xe, bo); + +out_unlock: + dma_resv_unlock(tbo->base.resv); +out_validation: + xe_validation_ctx_fini(&ctx); +out_pm: + if (needs_rpm) + xe_pm_runtime_put(xe); + + return ret; +} + +static vm_fault_t xe_bo_cpu_fault(struct vm_fault *vmf) { struct ttm_buffer_object *tbo = vmf->vma->vm_private_data; struct drm_device *ddev = tbo->base.dev; struct xe_device *xe = to_xe_device(ddev); struct xe_bo *bo = ttm_to_xe_bo(tbo); bool needs_rpm = bo->flags & XE_BO_FLAG_VRAM_MASK; + bool retry_after_wait = false; + struct xe_validation_ctx ctx; + struct drm_exec exec; vm_fault_t ret; - int idx, r = 0; + int err = 0; + int idx; - if (needs_rpm) - xe_pm_runtime_get(xe); + if (!drm_dev_enter(&xe->drm, &idx)) + return ttm_bo_vm_dummy_page(vmf, vmf->vma->vm_page_prot); - ret = ttm_bo_vm_reserve(tbo, vmf); - if (ret) + ret = xe_bo_cpu_fault_fastpath(vmf, xe, bo, needs_rpm); + if (ret != VM_FAULT_RETRY) goto out; - if (drm_dev_enter(ddev, &idx)) { - trace_xe_bo_cpu_fault(bo); + if (fault_flag_allow_retry_first(vmf->flags)) { + if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT) + goto out; + retry_after_wait = true; + xe_bo_get(bo); + mmap_read_unlock(vmf->vma->vm_mm); + } else { + ret = VM_FAULT_NOPAGE; + } + + /* + * The fastpath failed and we were not required to return and retry immediately. + * We're now running in one of two modes: + * + * 1) retry_after_wait == true: The mmap_read_lock() is dropped, and we're trying + * to resolve blocking waits. But we can't resolve the fault since the + * mmap_read_lock() is dropped. After retrying the fault, the aim is that the fastpath + * should succeed. But it may fail since we drop the bo lock. + * + * 2) retry_after_wait == false: The fastpath failed, typically even after + * a retry. Do whatever's necessary to resolve the fault. + * + * This construct is recommended to avoid excessive waits under the mmap_lock. + */ - if (should_migrate_to_smem(bo)) { - xe_assert(xe, bo->flags & XE_BO_FLAG_SYSTEM); + if (needs_rpm) + xe_pm_runtime_get(xe); - r = xe_bo_migrate(bo, XE_PL_TT); - if (r == -EBUSY || r == -ERESTARTSYS || r == -EINTR) - ret = VM_FAULT_NOPAGE; - else if (r) - ret = VM_FAULT_SIGBUS; + xe_validation_guard(&ctx, &xe->val, &exec, (struct xe_val_flags) {.interruptible = true}, + err) { + struct ttm_operation_ctx tctx = { + .interruptible = true, + .no_wait_gpu = false, + .gfp_retry_mayfail = retry_after_wait, + }; + long lerr; + + err = drm_exec_lock_obj(&exec, &tbo->base); + drm_exec_retry_on_contention(&exec); + if (err) + break; + + if (xe_ttm_bo_is_imported(tbo)) { + err = -EFAULT; + drm_dbg(&xe->drm, "CPU trying to access an imported buffer object.\n"); + break; } - if (!ret) - ret = ttm_bo_vm_fault_reserved(vmf, - vmf->vma->vm_page_prot, - TTM_BO_VM_NUM_PREFAULT); - drm_dev_exit(idx); - if (ret == VM_FAULT_RETRY && - !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) - goto out; + err = xe_bo_fault_migrate(bo, &tctx, &exec); + if (err) { + drm_exec_retry_on_contention(&exec); + xe_validation_retry_on_oom(&ctx, &err); + break; + } - /* - * ttm_bo_vm_reserve() already has dma_resv_lock. - */ - if (ret == VM_FAULT_NOPAGE && - mem_type_is_vram(tbo->resource->mem_type)) { - mutex_lock(&xe->mem_access.vram_userfault.lock); - if (list_empty(&bo->vram_userfault_link)) - list_add(&bo->vram_userfault_link, - &xe->mem_access.vram_userfault.list); - mutex_unlock(&xe->mem_access.vram_userfault.lock); + lerr = dma_resv_wait_timeout(tbo->base.resv, + DMA_RESV_USAGE_KERNEL, true, + MAX_SCHEDULE_TIMEOUT); + if (lerr < 0) { + err = lerr; + break; } - } else { - ret = ttm_bo_vm_dummy_page(vmf, vmf->vma->vm_page_prot); + + if (!retry_after_wait) + ret = __xe_bo_cpu_fault(vmf, xe, bo); } + /* if retry_after_wait == true, we *must* return VM_FAULT_RETRY. */ + if (err && !retry_after_wait) + ret = xe_err_to_fault_t(err); - dma_resv_unlock(tbo->base.resv); -out: if (needs_rpm) xe_pm_runtime_put(xe); + if (retry_after_wait) + xe_bo_put(bo); +out: + drm_dev_exit(idx); + return ret; } @@ -1825,7 +2008,7 @@ int xe_bo_read(struct xe_bo *bo, u64 offset, void *dst, int size) } static const struct vm_operations_struct xe_gem_vm_ops = { - .fault = xe_gem_fault, + .fault = xe_bo_cpu_fault, .open = ttm_bo_vm_open, .close = ttm_bo_vm_close, .access = xe_bo_vm_access, @@ -1873,11 +2056,32 @@ void xe_bo_free(struct xe_bo *bo) kfree(bo); } -struct xe_bo *___xe_bo_create_locked(struct xe_device *xe, struct xe_bo *bo, - struct xe_tile *tile, struct dma_resv *resv, - struct ttm_lru_bulk_move *bulk, size_t size, - u16 cpu_caching, enum ttm_bo_type type, - u32 flags) +/** + * xe_bo_init_locked() - Initialize or create an xe_bo. + * @xe: The xe device. + * @bo: An already allocated buffer object or NULL + * if the function should allocate a new one. + * @tile: The tile to select for migration of this bo, and the tile used for + * GGTT binding if any. Only to be non-NULL for ttm_bo_type_kernel bos. + * @resv: Pointer to a locked shared reservation object to use fo this bo, + * or NULL for the xe_bo to use its own. + * @bulk: The bulk move to use for LRU bumping, or NULL for external bos. + * @size: The storage size to use for the bo. + * @cpu_caching: The cpu caching used for system memory backing store. + * @type: The TTM buffer object type. + * @flags: XE_BO_FLAG_ flags. + * @exec: The drm_exec transaction to use for exhaustive eviction. + * + * Initialize or create an xe buffer object. On failure, any allocated buffer + * object passed in @bo will have been unreferenced. + * + * Return: The buffer object on success. Negative error pointer on failure. + */ +struct xe_bo *xe_bo_init_locked(struct xe_device *xe, struct xe_bo *bo, + struct xe_tile *tile, struct dma_resv *resv, + struct ttm_lru_bulk_move *bulk, size_t size, + u16 cpu_caching, enum ttm_bo_type type, + u32 flags, struct drm_exec *exec) { struct ttm_operation_ctx ctx = { .interruptible = true, @@ -1946,6 +2150,7 @@ struct xe_bo *___xe_bo_create_locked(struct xe_device *xe, struct xe_bo *bo, ctx.resv = resv; } + xe_validation_assert_exec(xe, exec, &bo->ttm.base); if (!(flags & XE_BO_FLAG_FIXED_PLACEMENT)) { err = __xe_bo_placement_for_flags(xe, bo, bo->flags); if (WARN_ON(err)) { @@ -2047,7 +2252,7 @@ __xe_bo_create_locked(struct xe_device *xe, struct xe_tile *tile, struct xe_vm *vm, size_t size, u64 start, u64 end, u16 cpu_caching, enum ttm_bo_type type, u32 flags, - u64 alignment) + u64 alignment, struct drm_exec *exec) { struct xe_bo *bo = NULL; int err; @@ -2068,11 +2273,11 @@ __xe_bo_create_locked(struct xe_device *xe, } } - bo = ___xe_bo_create_locked(xe, bo, tile, vm ? xe_vm_resv(vm) : NULL, - vm && !xe_vm_in_fault_mode(vm) && - flags & XE_BO_FLAG_USER ? - &vm->lru_bulk_move : NULL, size, - cpu_caching, type, flags); + bo = xe_bo_init_locked(xe, bo, tile, vm ? xe_vm_resv(vm) : NULL, + vm && !xe_vm_in_fault_mode(vm) && + flags & XE_BO_FLAG_USER ? + &vm->lru_bulk_move : NULL, size, + cpu_caching, type, flags, exec); if (IS_ERR(bo)) return bo; @@ -2106,9 +2311,10 @@ __xe_bo_create_locked(struct xe_device *xe, if (flags & XE_BO_FLAG_FIXED_PLACEMENT) { err = xe_ggtt_insert_bo_at(t->mem.ggtt, bo, - start + xe_bo_size(bo), U64_MAX); + start + xe_bo_size(bo), U64_MAX, + exec); } else { - err = xe_ggtt_insert_bo(t->mem.ggtt, bo); + err = xe_ggtt_insert_bo(t->mem.ggtt, bo, exec); } if (err) goto err_unlock_put_bo; @@ -2125,82 +2331,166 @@ err_unlock_put_bo: return ERR_PTR(err); } -struct xe_bo * -xe_bo_create_locked_range(struct xe_device *xe, - struct xe_tile *tile, struct xe_vm *vm, - size_t size, u64 start, u64 end, - enum ttm_bo_type type, u32 flags, u64 alignment) -{ - return __xe_bo_create_locked(xe, tile, vm, size, start, end, 0, type, - flags, alignment); -} - +/** + * xe_bo_create_locked() - Create a BO + * @xe: The xe device. + * @tile: The tile to select for migration of this bo, and the tile used for + * GGTT binding if any. Only to be non-NULL for ttm_bo_type_kernel bos. + * @vm: The local vm or NULL for external objects. + * @size: The storage size to use for the bo. + * @type: The TTM buffer object type. + * @flags: XE_BO_FLAG_ flags. + * @exec: The drm_exec transaction to use for exhaustive eviction. + * + * Create a locked xe BO with no range- nor alignment restrictions. + * + * Return: The buffer object on success. Negative error pointer on failure. + */ struct xe_bo *xe_bo_create_locked(struct xe_device *xe, struct xe_tile *tile, struct xe_vm *vm, size_t size, - enum ttm_bo_type type, u32 flags) + enum ttm_bo_type type, u32 flags, + struct drm_exec *exec) { return __xe_bo_create_locked(xe, tile, vm, size, 0, ~0ULL, 0, type, - flags, 0); + flags, 0, exec); } -struct xe_bo *xe_bo_create_user(struct xe_device *xe, struct xe_tile *tile, - struct xe_vm *vm, size_t size, - u16 cpu_caching, - u32 flags) +static struct xe_bo *xe_bo_create_novm(struct xe_device *xe, struct xe_tile *tile, + size_t size, u16 cpu_caching, + enum ttm_bo_type type, u32 flags, + u64 alignment, bool intr) { - struct xe_bo *bo = __xe_bo_create_locked(xe, tile, vm, size, 0, ~0ULL, - cpu_caching, ttm_bo_type_device, - flags | XE_BO_FLAG_USER, 0); - if (!IS_ERR(bo)) - xe_bo_unlock_vm_held(bo); + struct xe_validation_ctx ctx; + struct drm_exec exec; + struct xe_bo *bo; + int ret = 0; - return bo; + xe_validation_guard(&ctx, &xe->val, &exec, (struct xe_val_flags) {.interruptible = intr}, + ret) { + bo = __xe_bo_create_locked(xe, tile, NULL, size, 0, ~0ULL, + cpu_caching, type, flags, alignment, &exec); + drm_exec_retry_on_contention(&exec); + if (IS_ERR(bo)) { + ret = PTR_ERR(bo); + xe_validation_retry_on_oom(&ctx, &ret); + } else { + xe_bo_unlock(bo); + } + } + + return ret ? ERR_PTR(ret) : bo; } -struct xe_bo *xe_bo_create(struct xe_device *xe, struct xe_tile *tile, - struct xe_vm *vm, size_t size, - enum ttm_bo_type type, u32 flags) +/** + * xe_bo_create_user() - Create a user BO + * @xe: The xe device. + * @vm: The local vm or NULL for external objects. + * @size: The storage size to use for the bo. + * @cpu_caching: The caching mode to be used for system backing store. + * @flags: XE_BO_FLAG_ flags. + * @exec: The drm_exec transaction to use for exhaustive eviction, or NULL + * if such a transaction should be initiated by the call. + * + * Create a bo on behalf of user-space. + * + * Return: The buffer object on success. Negative error pointer on failure. + */ +struct xe_bo *xe_bo_create_user(struct xe_device *xe, + struct xe_vm *vm, size_t size, + u16 cpu_caching, + u32 flags, struct drm_exec *exec) { - struct xe_bo *bo = xe_bo_create_locked(xe, tile, vm, size, type, flags); + struct xe_bo *bo; + + flags |= XE_BO_FLAG_USER; - if (!IS_ERR(bo)) - xe_bo_unlock_vm_held(bo); + if (vm || exec) { + xe_assert(xe, exec); + bo = __xe_bo_create_locked(xe, NULL, vm, size, 0, ~0ULL, + cpu_caching, ttm_bo_type_device, + flags, 0, exec); + if (!IS_ERR(bo)) + xe_bo_unlock_vm_held(bo); + } else { + bo = xe_bo_create_novm(xe, NULL, size, cpu_caching, + ttm_bo_type_device, flags, 0, true); + } return bo; } -struct xe_bo *xe_bo_create_pin_map_at(struct xe_device *xe, struct xe_tile *tile, - struct xe_vm *vm, - size_t size, u64 offset, - enum ttm_bo_type type, u32 flags) +/** + * xe_bo_create_pin_range_novm() - Create and pin a BO with range options. + * @xe: The xe device. + * @tile: The tile to select for migration of this bo, and the tile used for + * GGTT binding if any. Only to be non-NULL for ttm_bo_type_kernel bos. + * @size: The storage size to use for the bo. + * @start: Start of fixed VRAM range or 0. + * @end: End of fixed VRAM range or ~0ULL. + * @type: The TTM buffer object type. + * @flags: XE_BO_FLAG_ flags. + * + * Create an Xe BO with range- and options. If @start and @end indicate + * a fixed VRAM range, this must be a ttm_bo_type_kernel bo with VRAM placement + * only. + * + * Return: The buffer object on success. Negative error pointer on failure. + */ +struct xe_bo *xe_bo_create_pin_range_novm(struct xe_device *xe, struct xe_tile *tile, + size_t size, u64 start, u64 end, + enum ttm_bo_type type, u32 flags) { - return xe_bo_create_pin_map_at_aligned(xe, tile, vm, size, offset, - type, flags, 0); + struct xe_validation_ctx ctx; + struct drm_exec exec; + struct xe_bo *bo; + int err = 0; + + xe_validation_guard(&ctx, &xe->val, &exec, (struct xe_val_flags) {}, err) { + bo = __xe_bo_create_locked(xe, tile, NULL, size, start, end, + 0, type, flags, 0, &exec); + if (IS_ERR(bo)) { + drm_exec_retry_on_contention(&exec); + err = PTR_ERR(bo); + xe_validation_retry_on_oom(&ctx, &err); + break; + } + + err = xe_bo_pin(bo, &exec); + xe_bo_unlock(bo); + if (err) { + xe_bo_put(bo); + drm_exec_retry_on_contention(&exec); + xe_validation_retry_on_oom(&ctx, &err); + break; + } + } + + return err ? ERR_PTR(err) : bo; } -struct xe_bo *xe_bo_create_pin_map_at_aligned(struct xe_device *xe, - struct xe_tile *tile, - struct xe_vm *vm, - size_t size, u64 offset, - enum ttm_bo_type type, u32 flags, - u64 alignment) +static struct xe_bo *xe_bo_create_pin_map_at_aligned(struct xe_device *xe, + struct xe_tile *tile, + struct xe_vm *vm, + size_t size, u64 offset, + enum ttm_bo_type type, u32 flags, + u64 alignment, struct drm_exec *exec) { struct xe_bo *bo; int err; u64 start = offset == ~0ull ? 0 : offset; - u64 end = offset == ~0ull ? offset : start + size; + u64 end = offset == ~0ull ? ~0ull : start + size; if (flags & XE_BO_FLAG_STOLEN && xe_ttm_stolen_cpu_access_needs_ggtt(xe)) flags |= XE_BO_FLAG_GGTT; - bo = xe_bo_create_locked_range(xe, tile, vm, size, start, end, type, - flags | XE_BO_FLAG_NEEDS_CPU_ACCESS | XE_BO_FLAG_PINNED, - alignment); + bo = __xe_bo_create_locked(xe, tile, vm, size, start, end, 0, type, + flags | XE_BO_FLAG_NEEDS_CPU_ACCESS | XE_BO_FLAG_PINNED, + alignment, exec); if (IS_ERR(bo)) return bo; - err = xe_bo_pin(bo); + err = xe_bo_pin(bo, exec); if (err) goto err_put; @@ -2220,11 +2510,100 @@ err_put: return ERR_PTR(err); } +/** + * xe_bo_create_pin_map_at_novm() - Create pinned and mapped bo at optional VRAM offset + * @xe: The xe device. + * @tile: The tile to select for migration of this bo, and the tile used for + * GGTT binding if any. Only to be non-NULL for ttm_bo_type_kernel bos. + * @size: The storage size to use for the bo. + * @offset: Optional VRAM offset or %~0ull for don't care. + * @type: The TTM buffer object type. + * @flags: XE_BO_FLAG_ flags. + * @alignment: GGTT alignment. + * @intr: Whether to execute any waits for backing store interruptible. + * + * Create a pinned and optionally mapped bo with VRAM offset and GGTT alignment + * options. The bo will be external and not associated with a VM. + * + * Return: The buffer object on success. Negative error pointer on failure. + * In particular, the function may return ERR_PTR(%-EINTR) if @intr was set + * to true on entry. + */ +struct xe_bo * +xe_bo_create_pin_map_at_novm(struct xe_device *xe, struct xe_tile *tile, + size_t size, u64 offset, enum ttm_bo_type type, u32 flags, + u64 alignment, bool intr) +{ + struct xe_validation_ctx ctx; + struct drm_exec exec; + struct xe_bo *bo; + int ret = 0; + + xe_validation_guard(&ctx, &xe->val, &exec, (struct xe_val_flags) {.interruptible = intr}, + ret) { + bo = xe_bo_create_pin_map_at_aligned(xe, tile, NULL, size, offset, + type, flags, alignment, &exec); + if (IS_ERR(bo)) { + drm_exec_retry_on_contention(&exec); + ret = PTR_ERR(bo); + xe_validation_retry_on_oom(&ctx, &ret); + } + } + + return ret ? ERR_PTR(ret) : bo; +} + +/** + * xe_bo_create_pin_map() - Create pinned and mapped bo + * @xe: The xe device. + * @tile: The tile to select for migration of this bo, and the tile used for + * @vm: The vm to associate the buffer object with. The vm's resv must be locked + * with the transaction represented by @exec. + * GGTT binding if any. Only to be non-NULL for ttm_bo_type_kernel bos. + * @size: The storage size to use for the bo. + * @type: The TTM buffer object type. + * @flags: XE_BO_FLAG_ flags. + * @exec: The drm_exec transaction to use for exhaustive eviction, and + * previously used for locking @vm's resv. + * + * Create a pinned and mapped bo. The bo will be external and not associated + * with a VM. + * + * Return: The buffer object on success. Negative error pointer on failure. + * In particular, the function may return ERR_PTR(%-EINTR) if @exec was + * configured for interruptible locking. + */ struct xe_bo *xe_bo_create_pin_map(struct xe_device *xe, struct xe_tile *tile, struct xe_vm *vm, size_t size, - enum ttm_bo_type type, u32 flags) + enum ttm_bo_type type, u32 flags, + struct drm_exec *exec) +{ + return xe_bo_create_pin_map_at_aligned(xe, tile, vm, size, ~0ull, type, flags, + 0, exec); +} + +/** + * xe_bo_create_pin_map_novm() - Create pinned and mapped bo + * @xe: The xe device. + * @tile: The tile to select for migration of this bo, and the tile used for + * GGTT binding if any. Only to be non-NULL for ttm_bo_type_kernel bos. + * @size: The storage size to use for the bo. + * @type: The TTM buffer object type. + * @flags: XE_BO_FLAG_ flags. + * @intr: Whether to execut any waits for backing store interruptible. + * + * Create a pinned and mapped bo. The bo will be external and not associated + * with a VM. + * + * Return: The buffer object on success. Negative error pointer on failure. + * In particular, the function may return ERR_PTR(%-EINTR) if @intr was set + * to true on entry. + */ +struct xe_bo *xe_bo_create_pin_map_novm(struct xe_device *xe, struct xe_tile *tile, + size_t size, enum ttm_bo_type type, u32 flags, + bool intr) { - return xe_bo_create_pin_map_at(xe, tile, vm, size, ~0ull, type, flags); + return xe_bo_create_pin_map_at_novm(xe, tile, size, ~0ull, type, flags, 0, intr); } static void __xe_bo_unpin_map_no_vm(void *arg) @@ -2239,8 +2618,7 @@ struct xe_bo *xe_managed_bo_create_pin_map(struct xe_device *xe, struct xe_tile int ret; KUNIT_STATIC_STUB_REDIRECT(xe_managed_bo_create_pin_map, xe, tile, size, flags); - - bo = xe_bo_create_pin_map(xe, tile, NULL, size, ttm_bo_type_kernel, flags); + bo = xe_bo_create_pin_map_novm(xe, tile, size, ttm_bo_type_kernel, flags, true); if (IS_ERR(bo)) return bo; @@ -2251,6 +2629,11 @@ struct xe_bo *xe_managed_bo_create_pin_map(struct xe_device *xe, struct xe_tile return bo; } +void xe_managed_bo_unpin_map_no_vm(struct xe_bo *bo) +{ + devm_release_action(xe_bo_device(bo)->drm.dev, __xe_bo_unpin_map_no_vm, bo); +} + struct xe_bo *xe_managed_bo_create_from_data(struct xe_device *xe, struct xe_tile *tile, const void *data, size_t size, u32 flags) { @@ -2322,6 +2705,8 @@ uint64_t vram_region_gpu_offset(struct ttm_resource *res) /** * xe_bo_pin_external - pin an external BO * @bo: buffer object to be pinned + * @in_place: Pin in current placement, don't attempt to migrate. + * @exec: The drm_exec transaction to use for exhaustive eviction. * * Pin an external (not tied to a VM, can be exported via dma-buf / prime FD) * BO. Unique call compared to xe_bo_pin as this function has it own set of @@ -2329,7 +2714,7 @@ uint64_t vram_region_gpu_offset(struct ttm_resource *res) * * Returns 0 for success, negative error code otherwise. */ -int xe_bo_pin_external(struct xe_bo *bo) +int xe_bo_pin_external(struct xe_bo *bo, bool in_place, struct drm_exec *exec) { struct xe_device *xe = xe_bo_device(bo); int err; @@ -2338,9 +2723,11 @@ int xe_bo_pin_external(struct xe_bo *bo) xe_assert(xe, xe_bo_is_user(bo)); if (!xe_bo_is_pinned(bo)) { - err = xe_bo_validate(bo, NULL, false); - if (err) - return err; + if (!in_place) { + err = xe_bo_validate(bo, NULL, false, exec); + if (err) + return err; + } spin_lock(&xe->pinned.lock); list_add_tail(&bo->pinned_link, &xe->pinned.late.external); @@ -2360,7 +2747,17 @@ int xe_bo_pin_external(struct xe_bo *bo) return 0; } -int xe_bo_pin(struct xe_bo *bo) +/** + * xe_bo_pin() - Pin a kernel bo after potentially migrating it + * @bo: The kernel bo to pin. + * @exec: The drm_exec transaction to use for exhaustive eviction. + * + * Attempts to migrate a bo to @bo->placement. If that succeeds, + * pins the bo. + * + * Return: %0 on success, negative error code on migration failure. + */ +int xe_bo_pin(struct xe_bo *bo, struct drm_exec *exec) { struct ttm_place *place = &bo->placements[0]; struct xe_device *xe = xe_bo_device(bo); @@ -2382,7 +2779,7 @@ int xe_bo_pin(struct xe_bo *bo) /* We only expect at most 1 pin */ xe_assert(xe, !xe_bo_is_pinned(bo)); - err = xe_bo_validate(bo, NULL, false); + err = xe_bo_validate(bo, NULL, false, exec); if (err) return err; @@ -2475,6 +2872,7 @@ void xe_bo_unpin(struct xe_bo *bo) * NULL. Used together with @allow_res_evict. * @allow_res_evict: Whether it's allowed to evict bos sharing @vm's * reservation object. + * @exec: The drm_exec transaction to use for exhaustive eviction. * * Make sure the bo is in allowed placement, migrating it if necessary. If * needed, other bos will be evicted. If bos selected for eviction shares @@ -2484,7 +2882,8 @@ void xe_bo_unpin(struct xe_bo *bo) * Return: 0 on success, negative error code on failure. May return * -EINTR or -ERESTARTSYS if internal waits are interrupted by a signal. */ -int xe_bo_validate(struct xe_bo *bo, struct xe_vm *vm, bool allow_res_evict) +int xe_bo_validate(struct xe_bo *bo, struct xe_vm *vm, bool allow_res_evict, + struct drm_exec *exec) { struct ttm_operation_ctx ctx = { .interruptible = true, @@ -2493,6 +2892,9 @@ int xe_bo_validate(struct xe_bo *bo, struct xe_vm *vm, bool allow_res_evict) }; int ret; + if (xe_bo_is_pinned(bo)) + return 0; + if (vm) { lockdep_assert_held(&vm->lock); xe_vm_assert_held(vm); @@ -2503,6 +2905,7 @@ int xe_bo_validate(struct xe_bo *bo, struct xe_vm *vm, bool allow_res_evict) xe_vm_set_validating(vm, allow_res_evict); trace_xe_bo_validate(bo); + xe_validation_assert_exec(xe_bo_device(bo), exec, &bo->ttm.base); ret = ttm_bo_validate(&bo->ttm, &bo->placement, &ctx); xe_vm_clear_validating(vm, allow_res_evict); @@ -2698,8 +3101,9 @@ int xe_gem_create_ioctl(struct drm_device *dev, void *data, struct xe_device *xe = to_xe_device(dev); struct xe_file *xef = to_xe_file(file); struct drm_xe_gem_create *args = data; + struct xe_validation_ctx ctx; + struct drm_exec exec; struct xe_vm *vm = NULL; - ktime_t end = 0; struct xe_bo *bo; unsigned int bo_flags; u32 handle; @@ -2773,25 +3177,26 @@ int xe_gem_create_ioctl(struct drm_device *dev, void *data, return -ENOENT; } -retry: - if (vm) { - err = xe_vm_lock(vm, true); - if (err) - goto out_vm; + err = 0; + xe_validation_guard(&ctx, &xe->val, &exec, (struct xe_val_flags) {.interruptible = true}, + err) { + if (vm) { + err = xe_vm_drm_exec_lock(vm, &exec); + drm_exec_retry_on_contention(&exec); + if (err) + break; + } + bo = xe_bo_create_user(xe, vm, args->size, args->cpu_caching, + bo_flags, &exec); + drm_exec_retry_on_contention(&exec); + if (IS_ERR(bo)) { + err = PTR_ERR(bo); + xe_validation_retry_on_oom(&ctx, &err); + break; + } } - - bo = xe_bo_create_user(xe, NULL, vm, args->size, args->cpu_caching, - bo_flags); - - if (vm) - xe_vm_unlock(vm); - - if (IS_ERR(bo)) { - err = PTR_ERR(bo); - if (xe_vm_validate_should_retry(NULL, err, &end)) - goto retry; + if (err) goto out_vm; - } if (args->extensions) { err = gem_create_user_extensions(xe, bo, args->extensions, 0); @@ -2940,6 +3345,9 @@ static void xe_place_from_ttm_type(u32 mem_type, struct ttm_place *place) * xe_bo_migrate - Migrate an object to the desired region id * @bo: The buffer object to migrate. * @mem_type: The TTM region type to migrate to. + * @tctx: A pointer to a struct ttm_operation_ctx or NULL if + * a default interruptibe ctx is to be used. + * @exec: The drm_exec transaction to use for exhaustive eviction. * * Attempt to migrate the buffer object to the desired memory region. The * buffer object may not be pinned, and must be locked. @@ -2951,7 +3359,8 @@ static void xe_place_from_ttm_type(u32 mem_type, struct ttm_place *place) * Return: 0 on success. Negative error code on failure. In particular may * return -EINTR or -ERESTARTSYS if signal pending. */ -int xe_bo_migrate(struct xe_bo *bo, u32 mem_type) +int xe_bo_migrate(struct xe_bo *bo, u32 mem_type, struct ttm_operation_ctx *tctx, + struct drm_exec *exec) { struct xe_device *xe = ttm_to_xe_device(bo->ttm.bdev); struct ttm_operation_ctx ctx = { @@ -2963,6 +3372,7 @@ int xe_bo_migrate(struct xe_bo *bo, u32 mem_type) struct ttm_place requested; xe_bo_assert_held(bo); + tctx = tctx ? tctx : &ctx; if (bo->ttm.resource->mem_type == mem_type) return 0; @@ -2989,19 +3399,22 @@ int xe_bo_migrate(struct xe_bo *bo, u32 mem_type) add_vram(xe, bo, &requested, bo->flags, mem_type, &c); } - return ttm_bo_validate(&bo->ttm, &placement, &ctx); + if (!tctx->no_wait_gpu) + xe_validation_assert_exec(xe_bo_device(bo), exec, &bo->ttm.base); + return ttm_bo_validate(&bo->ttm, &placement, tctx); } /** * xe_bo_evict - Evict an object to evict placement * @bo: The buffer object to migrate. + * @exec: The drm_exec transaction to use for exhaustive eviction. * * On successful completion, the object memory will be moved to evict * placement. This function blocks until the object has been fully moved. * * Return: 0 on success. Negative error code on failure. */ -int xe_bo_evict(struct xe_bo *bo) +int xe_bo_evict(struct xe_bo *bo, struct drm_exec *exec) { struct ttm_operation_ctx ctx = { .interruptible = false, @@ -3161,11 +3574,11 @@ int xe_bo_dumb_create(struct drm_file *file_priv, args->size = ALIGN(mul_u32_u32(args->pitch, args->height), page_size); - bo = xe_bo_create_user(xe, NULL, NULL, args->size, + bo = xe_bo_create_user(xe, NULL, args->size, DRM_XE_GEM_CPU_CACHING_WC, XE_BO_FLAG_VRAM_IF_DGFX(xe_device_get_root_tile(xe)) | XE_BO_FLAG_SCANOUT | - XE_BO_FLAG_NEEDS_CPU_ACCESS); + XE_BO_FLAG_NEEDS_CPU_ACCESS, NULL); if (IS_ERR(bo)) return PTR_ERR(bo); diff --git a/drivers/gpu/drm/xe/xe_bo.h b/drivers/gpu/drm/xe/xe_bo.h index 8cce413b5235..a77af42b5f9e 100644 --- a/drivers/gpu/drm/xe/xe_bo.h +++ b/drivers/gpu/drm/xe/xe_bo.h @@ -10,6 +10,7 @@ #include "xe_bo_types.h" #include "xe_macros.h" +#include "xe_validation.h" #include "xe_vm_types.h" #include "xe_vm.h" #include "xe_vram_types.h" @@ -88,40 +89,34 @@ struct sg_table; struct xe_bo *xe_bo_alloc(void); void xe_bo_free(struct xe_bo *bo); -struct xe_bo *___xe_bo_create_locked(struct xe_device *xe, struct xe_bo *bo, - struct xe_tile *tile, struct dma_resv *resv, - struct ttm_lru_bulk_move *bulk, size_t size, - u16 cpu_caching, enum ttm_bo_type type, - u32 flags); -struct xe_bo * -xe_bo_create_locked_range(struct xe_device *xe, - struct xe_tile *tile, struct xe_vm *vm, - size_t size, u64 start, u64 end, - enum ttm_bo_type type, u32 flags, u64 alignment); +struct xe_bo *xe_bo_init_locked(struct xe_device *xe, struct xe_bo *bo, + struct xe_tile *tile, struct dma_resv *resv, + struct ttm_lru_bulk_move *bulk, size_t size, + u16 cpu_caching, enum ttm_bo_type type, + u32 flags, struct drm_exec *exec); struct xe_bo *xe_bo_create_locked(struct xe_device *xe, struct xe_tile *tile, struct xe_vm *vm, size_t size, - enum ttm_bo_type type, u32 flags); -struct xe_bo *xe_bo_create(struct xe_device *xe, struct xe_tile *tile, - struct xe_vm *vm, size_t size, - enum ttm_bo_type type, u32 flags); -struct xe_bo *xe_bo_create_user(struct xe_device *xe, struct xe_tile *tile, - struct xe_vm *vm, size_t size, - u16 cpu_caching, - u32 flags); + enum ttm_bo_type type, u32 flags, + struct drm_exec *exec); +struct xe_bo *xe_bo_create_user(struct xe_device *xe, struct xe_vm *vm, size_t size, + u16 cpu_caching, u32 flags, struct drm_exec *exec); struct xe_bo *xe_bo_create_pin_map(struct xe_device *xe, struct xe_tile *tile, struct xe_vm *vm, size_t size, - enum ttm_bo_type type, u32 flags); -struct xe_bo *xe_bo_create_pin_map_at(struct xe_device *xe, struct xe_tile *tile, - struct xe_vm *vm, size_t size, u64 offset, - enum ttm_bo_type type, u32 flags); -struct xe_bo *xe_bo_create_pin_map_at_aligned(struct xe_device *xe, - struct xe_tile *tile, - struct xe_vm *vm, - size_t size, u64 offset, - enum ttm_bo_type type, u32 flags, - u64 alignment); + enum ttm_bo_type type, u32 flags, + struct drm_exec *exec); +struct xe_bo *xe_bo_create_pin_map_novm(struct xe_device *xe, struct xe_tile *tile, + size_t size, enum ttm_bo_type type, u32 flags, + bool intr); +struct xe_bo *xe_bo_create_pin_range_novm(struct xe_device *xe, struct xe_tile *tile, + size_t size, u64 start, u64 end, + enum ttm_bo_type type, u32 flags); +struct xe_bo * +xe_bo_create_pin_map_at_novm(struct xe_device *xe, struct xe_tile *tile, + size_t size, u64 offset, enum ttm_bo_type type, + u32 flags, u64 alignment, bool intr); struct xe_bo *xe_managed_bo_create_pin_map(struct xe_device *xe, struct xe_tile *tile, size_t size, u32 flags); +void xe_managed_bo_unpin_map_no_vm(struct xe_bo *bo); struct xe_bo *xe_managed_bo_create_from_data(struct xe_device *xe, struct xe_tile *tile, const void *data, size_t size, u32 flags); int xe_managed_bo_reinit_in_vram(struct xe_device *xe, struct xe_tile *tile, struct xe_bo **src); @@ -200,11 +195,12 @@ static inline void xe_bo_unlock_vm_held(struct xe_bo *bo) } } -int xe_bo_pin_external(struct xe_bo *bo); -int xe_bo_pin(struct xe_bo *bo); +int xe_bo_pin_external(struct xe_bo *bo, bool in_place, struct drm_exec *exec); +int xe_bo_pin(struct xe_bo *bo, struct drm_exec *exec); void xe_bo_unpin_external(struct xe_bo *bo); void xe_bo_unpin(struct xe_bo *bo); -int xe_bo_validate(struct xe_bo *bo, struct xe_vm *vm, bool allow_res_evict); +int xe_bo_validate(struct xe_bo *bo, struct xe_vm *vm, bool allow_res_evict, + struct drm_exec *exec); static inline bool xe_bo_is_pinned(struct xe_bo *bo) { @@ -285,8 +281,9 @@ uint64_t vram_region_gpu_offset(struct ttm_resource *res); bool xe_bo_can_migrate(struct xe_bo *bo, u32 mem_type); -int xe_bo_migrate(struct xe_bo *bo, u32 mem_type); -int xe_bo_evict(struct xe_bo *bo); +int xe_bo_migrate(struct xe_bo *bo, u32 mem_type, struct ttm_operation_ctx *ctc, + struct drm_exec *exec); +int xe_bo_evict(struct xe_bo *bo, struct drm_exec *exec); int xe_bo_evict_pinned(struct xe_bo *bo); int xe_bo_notifier_prepare_pinned(struct xe_bo *bo); @@ -315,6 +312,21 @@ static inline size_t xe_bo_ccs_pages_start(struct xe_bo *bo) return PAGE_ALIGN(xe_bo_size(bo)); } +/** + * xe_bo_has_valid_ccs_bb - Check if CCS's BBs were setup for the BO. + * @bo: the &xe_bo to check + * + * The CCS's BBs should only be setup by the driver VF, but it is safe + * to call this function also by non-VF driver. + * + * Return: true iff the CCS's BBs are setup, false otherwise. + */ +static inline bool xe_bo_has_valid_ccs_bb(struct xe_bo *bo) +{ + return bo->bb_ccs[XE_SRIOV_VF_CCS_READ_CTX] && + bo->bb_ccs[XE_SRIOV_VF_CCS_WRITE_CTX]; +} + static inline bool xe_bo_has_pages(struct xe_bo *bo) { if ((bo->ttm.ttm && ttm_tt_is_populated(bo->ttm.ttm)) || diff --git a/drivers/gpu/drm/xe/xe_bo_types.h b/drivers/gpu/drm/xe/xe_bo_types.h index 314652afdca7..d4fe3c8dca5b 100644 --- a/drivers/gpu/drm/xe/xe_bo_types.h +++ b/drivers/gpu/drm/xe/xe_bo_types.h @@ -25,7 +25,9 @@ struct xe_vm; /* TODO: To be selected with VM_MADVISE */ #define XE_BO_PRIORITY_NORMAL 1 -/** @xe_bo: XE buffer object */ +/** + * struct xe_bo - Xe buffer object + */ struct xe_bo { /** @ttm: TTM base buffer object */ struct ttm_buffer_object ttm; @@ -47,7 +49,7 @@ struct xe_bo { struct xe_ggtt_node *ggtt_node[XE_MAX_TILES_PER_DEVICE]; /** @vmap: iosys map of this buffer */ struct iosys_map vmap; - /** @ttm_kmap: TTM bo kmap object for internal use only. Keep off. */ + /** @kmap: TTM bo kmap object for internal use only. Keep off. */ struct ttm_bo_kmap_obj kmap; /** @pinned_link: link to present / evicted list of pinned BO */ struct list_head pinned_link; @@ -82,10 +84,10 @@ struct xe_bo { /** @created: Whether the bo has passed initial creation */ bool created; - /** @ccs_cleared */ + /** @ccs_cleared: true means that CCS region of BO is already cleared */ bool ccs_cleared; - /** @bb_ccs_rw: BB instructions of CCS read/write. Valid only for VF */ + /** @bb_ccs: BB instructions of CCS read/write. Valid only for VF */ struct xe_bb *bb_ccs[XE_SRIOV_VF_CCS_CTX_COUNT]; /** @@ -99,9 +101,10 @@ struct xe_bo { struct drm_pagemap_devmem devmem_allocation; /** @vram_userfault_link: Link into @mem_access.vram_userfault.list */ - struct list_head vram_userfault_link; + struct list_head vram_userfault_link; - /** @min_align: minimum alignment needed for this BO if different + /** + * @min_align: minimum alignment needed for this BO if different * from default */ u64 min_align; diff --git a/drivers/gpu/drm/xe/xe_configfs.c b/drivers/gpu/drm/xe/xe_configfs.c index 1025d3979b06..8a9b950e7a6d 100644 --- a/drivers/gpu/drm/xe/xe_configfs.c +++ b/drivers/gpu/drm/xe/xe_configfs.c @@ -4,6 +4,7 @@ */ #include <linux/bitops.h> +#include <linux/ctype.h> #include <linux/configfs.h> #include <linux/cleanup.h> #include <linux/find.h> @@ -12,6 +13,7 @@ #include <linux/pci.h> #include <linux/string.h> +#include "instructions/xe_mi_commands.h" #include "xe_configfs.h" #include "xe_hw_engine_types.h" #include "xe_module.h" @@ -21,7 +23,7 @@ * DOC: Xe Configfs * * Overview - * ========= + * ======== * * Configfs is a filesystem-based manager of kernel objects. XE KMD registers a * configfs subsystem called ``xe`` that creates a directory in the mounted @@ -34,7 +36,7 @@ * * To create a device, the ``xe`` module should already be loaded, but some * attributes can only be set before binding the device. It can be accomplished - * by blocking the driver autoprobe: + * by blocking the driver autoprobe:: * * # echo 0 > /sys/bus/pci/drivers_autoprobe * # modprobe xe @@ -115,6 +117,45 @@ * * This attribute can only be set before binding to the device. * + * Context restore BB + * ------------------ + * + * Allow to execute a batch buffer during any context switches. When the + * GPU is restoring the context, it executes additional commands. It's useful + * for testing additional workarounds and validating certain HW behaviors: it's + * not intended for normal execution and will taint the kernel with TAINT_TEST + * when used. + * + * Currently this is implemented only for post and mid context restore. + * Examples: + * + * #. Execute a LRI command to write 0xDEADBEEF to register 0x4f10 after the + * normal context restore:: + * + * # echo 'rcs cmd 11000001 4F100 DEADBEEF' \ + * > /sys/kernel/config/xe/0000:03:00.0/ctx_restore_post_bb + * + * #. Execute a LRI command to write 0xDEADBEEF to register 0x4f10 at the + * beginning of the context restore:: + * + * # echo 'rcs cmd 11000001 4F100 DEADBEEF' \ + * > /sys/kernel/config/xe/0000:03:00.0/ctx_restore_mid_bb + + * #. Load certain values in a couple of registers (it can be used as a simpler + * alternative to the `cmd`) action:: + * + * # cat > /sys/kernel/config/xe/0000:03:00.0/ctx_restore_post_bb <<EOF + * rcs reg 4F100 DEADBEEF + * rcs reg 4F104 FFFFFFFF + * EOF + * + * .. note:: + * + * When using multiple lines, make sure to use a command that is + * implemented with a single write syscall, like HEREDOC. + * + * These attributes can only be set before binding to the device. + * * Remove devices * ============== * @@ -123,17 +164,27 @@ * # rmdir /sys/kernel/config/xe/0000:03:00.0/ */ +/* Similar to struct xe_bb, but not tied to HW (yet) */ +struct wa_bb { + u32 *cs; + u32 len; /* in dwords */ +}; + struct xe_config_group_device { struct config_group group; struct xe_config_device { u64 engines_allowed; + struct wa_bb ctx_restore_post_bb[XE_ENGINE_CLASS_MAX]; + struct wa_bb ctx_restore_mid_bb[XE_ENGINE_CLASS_MAX]; bool survivability_mode; bool enable_psmi; } config; /* protects attributes */ struct mutex lock; + /* matching descriptor */ + const struct xe_device_desc *desc; }; static const struct xe_config_device device_defaults = { @@ -150,6 +201,7 @@ static void set_device_defaults(struct xe_config_device *config) struct engine_info { const char *cls; u64 mask; + enum xe_engine_class engine_class; }; /* Some helpful macros to aid on the sizing of buffer allocation when parsing */ @@ -157,12 +209,12 @@ struct engine_info { #define MAX_ENGINE_INSTANCE_CHARS 2 static const struct engine_info engine_info[] = { - { .cls = "rcs", .mask = XE_HW_ENGINE_RCS_MASK }, - { .cls = "bcs", .mask = XE_HW_ENGINE_BCS_MASK }, - { .cls = "vcs", .mask = XE_HW_ENGINE_VCS_MASK }, - { .cls = "vecs", .mask = XE_HW_ENGINE_VECS_MASK }, - { .cls = "ccs", .mask = XE_HW_ENGINE_CCS_MASK }, - { .cls = "gsccs", .mask = XE_HW_ENGINE_GSCCS_MASK }, + { .cls = "rcs", .mask = XE_HW_ENGINE_RCS_MASK, .engine_class = XE_ENGINE_CLASS_RENDER }, + { .cls = "bcs", .mask = XE_HW_ENGINE_BCS_MASK, .engine_class = XE_ENGINE_CLASS_COPY }, + { .cls = "vcs", .mask = XE_HW_ENGINE_VCS_MASK, .engine_class = XE_ENGINE_CLASS_VIDEO_DECODE }, + { .cls = "vecs", .mask = XE_HW_ENGINE_VECS_MASK, .engine_class = XE_ENGINE_CLASS_VIDEO_ENHANCE }, + { .cls = "ccs", .mask = XE_HW_ENGINE_CCS_MASK, .engine_class = XE_ENGINE_CLASS_COMPUTE }, + { .cls = "gsccs", .mask = XE_HW_ENGINE_GSCCS_MASK, .engine_class = XE_ENGINE_CLASS_OTHER }, }; static struct xe_config_group_device *to_xe_config_group_device(struct config_item *item) @@ -251,7 +303,18 @@ static ssize_t engines_allowed_show(struct config_item *item, char *page) return p - page; } -static bool lookup_engine_mask(const char *pattern, u64 *mask) +/* + * Lookup engine_info. If @mask is not NULL, reduce the mask according to the + * instance in @pattern. + * + * Examples of inputs: + * - lookup_engine_info("rcs0", &mask): return "rcs" entry from @engine_info and + * mask == BIT_ULL(XE_HW_ENGINE_RCS0) + * - lookup_engine_info("rcs*", &mask): return "rcs" entry from @engine_info and + * mask == XE_HW_ENGINE_RCS_MASK + * - lookup_engine_info("rcs", NULL): return "rcs" entry from @engine_info + */ +static const struct engine_info *lookup_engine_info(const char *pattern, u64 *mask) { for (size_t i = 0; i < ARRAY_SIZE(engine_info); i++) { u8 instance; @@ -261,44 +324,62 @@ static bool lookup_engine_mask(const char *pattern, u64 *mask) continue; pattern += strlen(engine_info[i].cls); + if (!mask && !*pattern) + return &engine_info[i]; if (!strcmp(pattern, "*")) { *mask = engine_info[i].mask; - return true; + return &engine_info[i]; } if (kstrtou8(pattern, 10, &instance)) - return false; + return NULL; bit = __ffs64(engine_info[i].mask) + instance; if (bit >= fls64(engine_info[i].mask)) - return false; + return NULL; *mask = BIT_ULL(bit); - return true; + return &engine_info[i]; } - return false; + return NULL; +} + +static int parse_engine(const char *s, const char *end_chars, u64 *mask, + const struct engine_info **pinfo) +{ + char buf[MAX_ENGINE_CLASS_CHARS + MAX_ENGINE_INSTANCE_CHARS + 1]; + const struct engine_info *info; + size_t len; + + len = strcspn(s, end_chars); + if (len >= sizeof(buf)) + return -EINVAL; + + memcpy(buf, s, len); + buf[len] = '\0'; + + info = lookup_engine_info(buf, mask); + if (!info) + return -ENOENT; + + if (pinfo) + *pinfo = info; + + return len; } static ssize_t engines_allowed_store(struct config_item *item, const char *page, size_t len) { struct xe_config_group_device *dev = to_xe_config_group_device(item); - size_t patternlen, p; + ssize_t patternlen, p; u64 mask, val = 0; for (p = 0; p < len; p += patternlen + 1) { - char buf[MAX_ENGINE_CLASS_CHARS + MAX_ENGINE_INSTANCE_CHARS + 1]; - - patternlen = strcspn(page + p, ",\n"); - if (patternlen >= sizeof(buf)) - return -EINVAL; - - memcpy(buf, page + p, patternlen); - buf[patternlen] = '\0'; - - if (!lookup_engine_mask(buf, &mask)) + patternlen = parse_engine(page + p, ",\n", &mask, NULL); + if (patternlen < 0) return -EINVAL; val |= mask; @@ -339,11 +420,250 @@ static ssize_t enable_psmi_store(struct config_item *item, const char *page, siz return len; } +static bool wa_bb_read_advance(bool dereference, char **p, + const char *append, size_t len, + size_t *max_size) +{ + if (dereference) { + if (len >= *max_size) + return false; + *max_size -= len; + if (append) + memcpy(*p, append, len); + } + + *p += len; + + return true; +} + +static ssize_t wa_bb_show(struct xe_config_group_device *dev, + struct wa_bb wa_bb[static XE_ENGINE_CLASS_MAX], + char *data, size_t sz) +{ + char *p = data; + + guard(mutex)(&dev->lock); + + for (size_t i = 0; i < ARRAY_SIZE(engine_info); i++) { + enum xe_engine_class ec = engine_info[i].engine_class; + size_t len; + + if (!wa_bb[ec].len) + continue; + + len = snprintf(p, sz, "%s:", engine_info[i].cls); + if (!wa_bb_read_advance(data, &p, NULL, len, &sz)) + return -ENOBUFS; + + for (size_t j = 0; j < wa_bb[ec].len; j++) { + len = snprintf(p, sz, " %08x", wa_bb[ec].cs[j]); + if (!wa_bb_read_advance(data, &p, NULL, len, &sz)) + return -ENOBUFS; + } + + if (!wa_bb_read_advance(data, &p, "\n", 1, &sz)) + return -ENOBUFS; + } + + if (!wa_bb_read_advance(data, &p, "", 1, &sz)) + return -ENOBUFS; + + /* Reserve one more to match check for '\0' */ + if (!data) + p++; + + return p - data; +} + +static ssize_t ctx_restore_mid_bb_show(struct config_item *item, char *page) +{ + struct xe_config_group_device *dev = to_xe_config_group_device(item); + + return wa_bb_show(dev, dev->config.ctx_restore_mid_bb, page, SZ_4K); +} + +static ssize_t ctx_restore_post_bb_show(struct config_item *item, char *page) +{ + struct xe_config_group_device *dev = to_xe_config_group_device(item); + + return wa_bb_show(dev, dev->config.ctx_restore_post_bb, page, SZ_4K); +} + +static void wa_bb_append(struct wa_bb *wa_bb, u32 val) +{ + if (wa_bb->cs) + wa_bb->cs[wa_bb->len] = val; + + wa_bb->len++; +} + +static ssize_t parse_hex(const char *line, u32 *pval) +{ + char numstr[12]; + const char *p; + ssize_t numlen; + + p = line + strspn(line, " \t"); + if (!*p || *p == '\n') + return 0; + + numlen = strcspn(p, " \t\n"); + if (!numlen || numlen >= sizeof(numstr) - 1) + return -EINVAL; + + memcpy(numstr, p, numlen); + numstr[numlen] = '\0'; + p += numlen; + + if (kstrtou32(numstr, 16, pval)) + return -EINVAL; + + return p - line; +} + +/* + * Parse lines with the format + * + * <engine-class> cmd <u32> <u32...> + * <engine-class> reg <u32_addr> <u32_val> + * + * and optionally save them in @wa_bb[i].cs is non-NULL. + * + * Return the number of dwords parsed. + */ +static ssize_t parse_wa_bb_lines(const char *lines, + struct wa_bb wa_bb[static XE_ENGINE_CLASS_MAX]) +{ + ssize_t dwords = 0, ret; + const char *p; + + for (p = lines; *p; p++) { + const struct engine_info *info = NULL; + u32 val, val2; + + /* Also allow empty lines */ + p += strspn(p, " \t\n"); + if (!*p) + break; + + ret = parse_engine(p, " \t\n", NULL, &info); + if (ret < 0) + return ret; + + p += ret; + p += strspn(p, " \t"); + + if (str_has_prefix(p, "cmd")) { + for (p += strlen("cmd"); *p;) { + ret = parse_hex(p, &val); + if (ret < 0) + return -EINVAL; + if (!ret) + break; + + p += ret; + dwords++; + wa_bb_append(&wa_bb[info->engine_class], val); + } + } else if (str_has_prefix(p, "reg")) { + p += strlen("reg"); + ret = parse_hex(p, &val); + if (ret <= 0) + return -EINVAL; + + p += ret; + ret = parse_hex(p, &val2); + if (ret <= 0) + return -EINVAL; + + p += ret; + dwords += 3; + wa_bb_append(&wa_bb[info->engine_class], + MI_LOAD_REGISTER_IMM | MI_LRI_NUM_REGS(1)); + wa_bb_append(&wa_bb[info->engine_class], val); + wa_bb_append(&wa_bb[info->engine_class], val2); + } else { + return -EINVAL; + } + } + + return dwords; +} + +static ssize_t wa_bb_store(struct wa_bb wa_bb[static XE_ENGINE_CLASS_MAX], + struct xe_config_group_device *dev, + const char *page, size_t len) +{ + /* tmp_wa_bb must match wa_bb's size */ + struct wa_bb tmp_wa_bb[XE_ENGINE_CLASS_MAX] = { }; + ssize_t count, class; + u32 *tmp; + + /* 1. Count dwords - wa_bb[i].cs is NULL for all classes */ + count = parse_wa_bb_lines(page, tmp_wa_bb); + if (count < 0) + return count; + + guard(mutex)(&dev->lock); + + if (is_bound(dev)) + return -EBUSY; + + /* + * 2. Allocate a u32 array and set the pointers to the right positions + * according to the length of each class' wa_bb + */ + tmp = krealloc(wa_bb[0].cs, count * sizeof(u32), GFP_KERNEL); + if (!tmp) + return -ENOMEM; + + if (!count) { + memset(wa_bb, 0, sizeof(tmp_wa_bb)); + return len; + } + + for (class = 0, count = 0; class < XE_ENGINE_CLASS_MAX; ++class) { + tmp_wa_bb[class].cs = tmp + count; + count += tmp_wa_bb[class].len; + tmp_wa_bb[class].len = 0; + } + + /* 3. Parse wa_bb lines again, this time saving the values */ + count = parse_wa_bb_lines(page, tmp_wa_bb); + if (count < 0) + return count; + + memcpy(wa_bb, tmp_wa_bb, sizeof(tmp_wa_bb)); + + return len; +} + +static ssize_t ctx_restore_mid_bb_store(struct config_item *item, + const char *data, size_t sz) +{ + struct xe_config_group_device *dev = to_xe_config_group_device(item); + + return wa_bb_store(dev->config.ctx_restore_mid_bb, dev, data, sz); +} + +static ssize_t ctx_restore_post_bb_store(struct config_item *item, + const char *data, size_t sz) +{ + struct xe_config_group_device *dev = to_xe_config_group_device(item); + + return wa_bb_store(dev->config.ctx_restore_post_bb, dev, data, sz); +} + +CONFIGFS_ATTR(, ctx_restore_mid_bb); +CONFIGFS_ATTR(, ctx_restore_post_bb); CONFIGFS_ATTR(, enable_psmi); CONFIGFS_ATTR(, engines_allowed); CONFIGFS_ATTR(, survivability_mode); static struct configfs_attribute *xe_config_device_attrs[] = { + &attr_ctx_restore_mid_bb, + &attr_ctx_restore_post_bb, &attr_enable_psmi, &attr_engines_allowed, &attr_survivability_mode, @@ -355,6 +675,8 @@ static void xe_config_device_release(struct config_item *item) struct xe_config_group_device *dev = to_xe_config_group_device(item); mutex_destroy(&dev->lock); + + kfree(dev->config.ctx_restore_post_bb[0].cs); kfree(dev); } @@ -362,8 +684,26 @@ static struct configfs_item_operations xe_config_device_ops = { .release = xe_config_device_release, }; +static bool xe_config_device_is_visible(struct config_item *item, + struct configfs_attribute *attr, int n) +{ + struct xe_config_group_device *dev = to_xe_config_group_device(item); + + if (attr == &attr_survivability_mode) { + if (!dev->desc->is_dgfx || dev->desc->platform < XE_BATTLEMAGE) + return false; + } + + return true; +} + +static struct configfs_group_operations xe_config_device_group_ops = { + .is_visible = xe_config_device_is_visible, +}; + static const struct config_item_type xe_config_device_type = { .ct_item_ops = &xe_config_device_ops, + .ct_group_ops = &xe_config_device_group_ops, .ct_attrs = xe_config_device_attrs, .ct_owner = THIS_MODULE, }; @@ -442,6 +782,7 @@ static struct config_group *xe_config_make_device_group(struct config_group *gro if (!dev) return ERR_PTR(-ENOMEM); + dev->desc = match; set_device_defaults(&dev->config); config_group_init_type_name(&dev->group, name, &xe_config_device_type); @@ -451,12 +792,12 @@ static struct config_group *xe_config_make_device_group(struct config_group *gro return &dev->group; } -static struct configfs_group_operations xe_config_device_group_ops = { +static struct configfs_group_operations xe_config_group_ops = { .make_group = xe_config_make_device_group, }; static const struct config_item_type xe_configfs_type = { - .ct_group_ops = &xe_config_device_group_ops, + .ct_group_ops = &xe_config_group_ops, .ct_owner = THIS_MODULE, }; @@ -543,23 +884,6 @@ bool xe_configfs_get_survivability_mode(struct pci_dev *pdev) } /** - * xe_configfs_clear_survivability_mode - clear configfs survivability mode - * @pdev: pci device - */ -void xe_configfs_clear_survivability_mode(struct pci_dev *pdev) -{ - struct xe_config_group_device *dev = find_xe_config_group_device(pdev); - - if (!dev) - return; - - guard(mutex)(&dev->lock); - dev->config.survivability_mode = 0; - - config_group_put(&dev->group); -} - -/** * xe_configfs_get_engines_allowed - get engine allowed mask from configfs * @pdev: pci device * @@ -594,11 +918,63 @@ bool xe_configfs_get_psmi_enabled(struct pci_dev *pdev) return false; ret = dev->config.enable_psmi; - config_item_put(&dev->group.cg_item); + config_group_put(&dev->group); return ret; } +/** + * xe_configfs_get_ctx_restore_mid_bb - get configfs ctx_restore_mid_bb setting + * @pdev: pci device + * @class: hw engine class + * @cs: pointer to the bb to use - only valid during probe + * + * Return: Number of dwords used in the mid_ctx_restore setting in configfs + */ +u32 xe_configfs_get_ctx_restore_mid_bb(struct pci_dev *pdev, + enum xe_engine_class class, + const u32 **cs) +{ + struct xe_config_group_device *dev = find_xe_config_group_device(pdev); + u32 len; + + if (!dev) + return 0; + + if (cs) + *cs = dev->config.ctx_restore_mid_bb[class].cs; + + len = dev->config.ctx_restore_mid_bb[class].len; + config_group_put(&dev->group); + + return len; +} + +/** + * xe_configfs_get_ctx_restore_post_bb - get configfs ctx_restore_post_bb setting + * @pdev: pci device + * @class: hw engine class + * @cs: pointer to the bb to use - only valid during probe + * + * Return: Number of dwords used in the post_ctx_restore setting in configfs + */ +u32 xe_configfs_get_ctx_restore_post_bb(struct pci_dev *pdev, + enum xe_engine_class class, + const u32 **cs) +{ + struct xe_config_group_device *dev = find_xe_config_group_device(pdev); + u32 len; + + if (!dev) + return 0; + + *cs = dev->config.ctx_restore_post_bb[class].cs; + len = dev->config.ctx_restore_post_bb[class].len; + config_group_put(&dev->group); + + return len; +} + int __init xe_configfs_init(void) { int ret; @@ -614,7 +990,7 @@ int __init xe_configfs_init(void) return 0; } -void __exit xe_configfs_exit(void) +void xe_configfs_exit(void) { configfs_unregister_subsystem(&xe_configfs); mutex_destroy(&xe_configfs.su_mutex); diff --git a/drivers/gpu/drm/xe/xe_configfs.h b/drivers/gpu/drm/xe/xe_configfs.h index 58c8c3164000..c61e0e47ed94 100644 --- a/drivers/gpu/drm/xe/xe_configfs.h +++ b/drivers/gpu/drm/xe/xe_configfs.h @@ -8,6 +8,8 @@ #include <linux/limits.h> #include <linux/types.h> +#include <xe_hw_engine_types.h> + struct pci_dev; #if IS_ENABLED(CONFIG_CONFIGFS_FS) @@ -15,17 +17,23 @@ int xe_configfs_init(void); void xe_configfs_exit(void); void xe_configfs_check_device(struct pci_dev *pdev); bool xe_configfs_get_survivability_mode(struct pci_dev *pdev); -void xe_configfs_clear_survivability_mode(struct pci_dev *pdev); u64 xe_configfs_get_engines_allowed(struct pci_dev *pdev); bool xe_configfs_get_psmi_enabled(struct pci_dev *pdev); +u32 xe_configfs_get_ctx_restore_mid_bb(struct pci_dev *pdev, enum xe_engine_class, + const u32 **cs); +u32 xe_configfs_get_ctx_restore_post_bb(struct pci_dev *pdev, enum xe_engine_class, + const u32 **cs); #else static inline int xe_configfs_init(void) { return 0; } static inline void xe_configfs_exit(void) { } static inline void xe_configfs_check_device(struct pci_dev *pdev) { } static inline bool xe_configfs_get_survivability_mode(struct pci_dev *pdev) { return false; } -static inline void xe_configfs_clear_survivability_mode(struct pci_dev *pdev) { } static inline u64 xe_configfs_get_engines_allowed(struct pci_dev *pdev) { return U64_MAX; } static inline bool xe_configfs_get_psmi_enabled(struct pci_dev *pdev) { return false; } +static inline u32 xe_configfs_get_ctx_restore_mid_bb(struct pci_dev *pdev, enum xe_engine_class, + const u32 **cs) { return 0; } +static inline u32 xe_configfs_get_ctx_restore_post_bb(struct pci_dev *pdev, enum xe_engine_class, + const u32 **cs) { return 0; } #endif #endif diff --git a/drivers/gpu/drm/xe/xe_debugfs.c b/drivers/gpu/drm/xe/xe_debugfs.c index 8d6df6bd885e..cd977dbd1ef6 100644 --- a/drivers/gpu/drm/xe/xe_debugfs.c +++ b/drivers/gpu/drm/xe/xe_debugfs.c @@ -24,7 +24,9 @@ #include "xe_pxp_debugfs.h" #include "xe_sriov.h" #include "xe_sriov_pf.h" +#include "xe_sriov_vf.h" #include "xe_step.h" +#include "xe_tile_debugfs.h" #include "xe_wa.h" #include "xe_vsec.h" @@ -38,7 +40,7 @@ DECLARE_FAULT_ATTR(gt_reset_failure); DECLARE_FAULT_ATTR(inject_csc_hw_error); static void read_residency_counter(struct xe_device *xe, struct xe_mmio *mmio, - u32 offset, char *name, struct drm_printer *p) + u32 offset, const char *name, struct drm_printer *p) { u64 residency = 0; int ret; @@ -134,9 +136,9 @@ static int dgfx_pkg_residencies_show(struct seq_file *m, void *data) p = drm_seq_file_printer(m); xe_pm_runtime_get(xe); mmio = xe_root_tile_mmio(xe); - struct { + static const struct { u32 offset; - char *name; + const char *name; } residencies[] = { {BMG_G2_RESIDENCY_OFFSET, "Package G2"}, {BMG_G6_RESIDENCY_OFFSET, "Package G6"}, @@ -163,9 +165,9 @@ static int dgfx_pcie_link_residencies_show(struct seq_file *m, void *data) xe_pm_runtime_get(xe); mmio = xe_root_tile_mmio(xe); - struct { + static const struct { u32 offset; - char *name; + const char *name; } residencies[] = { {BMG_PCIE_LINK_L0_RESIDENCY_OFFSET, "PCIE LINK L0 RESIDENCY"}, {BMG_PCIE_LINK_L1_RESIDENCY_OFFSET, "PCIE LINK L1 RESIDENCY"}, @@ -329,23 +331,44 @@ static const struct file_operations atomic_svm_timeslice_ms_fops = { .write = atomic_svm_timeslice_ms_set, }; -static void create_tile_debugfs(struct xe_tile *tile, struct dentry *root) +static ssize_t disable_late_binding_show(struct file *f, char __user *ubuf, + size_t size, loff_t *pos) { - char name[8]; + struct xe_device *xe = file_inode(f)->i_private; + struct xe_late_bind *late_bind = &xe->late_bind; + char buf[32]; + int len; - snprintf(name, sizeof(name), "tile%u", tile->id); - tile->debugfs = debugfs_create_dir(name, root); - if (IS_ERR(tile->debugfs)) - return; + len = scnprintf(buf, sizeof(buf), "%d\n", late_bind->disable); + + return simple_read_from_buffer(ubuf, size, pos, buf, len); +} + +static ssize_t disable_late_binding_set(struct file *f, const char __user *ubuf, + size_t size, loff_t *pos) +{ + struct xe_device *xe = file_inode(f)->i_private; + struct xe_late_bind *late_bind = &xe->late_bind; + u32 uval; + ssize_t ret; - /* - * Store the xe_tile pointer as private data of the tile/ directory - * node so other tile specific attributes under that directory may - * refer to it by looking at its parent node private data. - */ - tile->debugfs->d_inode->i_private = tile; + ret = kstrtouint_from_user(ubuf, size, sizeof(uval), &uval); + if (ret) + return ret; + + if (uval > 1) + return -EINVAL; + + late_bind->disable = !!uval; + return size; } +static const struct file_operations disable_late_binding_fops = { + .owner = THIS_MODULE, + .read = disable_late_binding_show, + .write = disable_late_binding_set, +}; + void xe_debugfs_register(struct xe_device *xe) { struct ttm_device *bdev = &xe->ttm; @@ -362,7 +385,7 @@ void xe_debugfs_register(struct xe_device *xe) ARRAY_SIZE(debugfs_list), root, minor); - if (xe->info.platform == XE_BATTLEMAGE) { + if (xe->info.platform == XE_BATTLEMAGE && !IS_SRIOV_VF(xe)) { drm_debugfs_create_files(debugfs_residencies, ARRAY_SIZE(debugfs_residencies), root, minor); @@ -379,6 +402,9 @@ void xe_debugfs_register(struct xe_device *xe) debugfs_create_file("atomic_svm_timeslice_ms", 0600, root, xe, &atomic_svm_timeslice_ms_fops); + debugfs_create_file("disable_late_binding", 0600, root, xe, + &disable_late_binding_fops); + for (mem_type = XE_PL_VRAM0; mem_type <= XE_PL_VRAM1; ++mem_type) { man = ttm_manager_type(bdev, mem_type); @@ -398,7 +424,7 @@ void xe_debugfs_register(struct xe_device *xe) ttm_resource_manager_create_debugfs(man, root, "stolen_mm"); for_each_tile(tile, xe, tile_id) - create_tile_debugfs(tile, root); + xe_tile_debugfs_register(tile); for_each_gt(gt, xe, id) xe_gt_debugfs_register(gt); @@ -411,4 +437,6 @@ void xe_debugfs_register(struct xe_device *xe) if (IS_SRIOV_PF(xe)) xe_sriov_pf_debugfs_register(xe, root); + else if (IS_SRIOV_VF(xe)) + xe_sriov_vf_debugfs_register(xe, root); } diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c index 9e4773a17ef8..fdb7b7498920 100644 --- a/drivers/gpu/drm/xe/xe_device.c +++ b/drivers/gpu/drm/xe/xe_device.c @@ -45,6 +45,7 @@ #include "xe_hwmon.h" #include "xe_i2c.h" #include "xe_irq.h" +#include "xe_late_bind_fw.h" #include "xe_mmio.h" #include "xe_module.h" #include "xe_nvm.h" @@ -457,6 +458,8 @@ struct xe_device *xe_device_create(struct pci_dev *pdev, if (err) goto err; + xe_validation_device_init(&xe->val); + init_waitqueue_head(&xe->ufence_wq); init_rwsem(&xe->usm.lock); @@ -530,7 +533,7 @@ static bool xe_driver_flr_disabled(struct xe_device *xe) * re-init and saving/restoring (or re-populating) the wiped memory. Since we * perform the FLR as the very last action before releasing access to the HW * during the driver release flow, we don't attempt recovery at all, because - * if/when a new instance of i915 is bound to the device it will do a full + * if/when a new instance of Xe is bound to the device it will do a full * re-init anyway. */ static void __xe_driver_flr(struct xe_device *xe) @@ -901,6 +904,10 @@ int xe_device_probe(struct xe_device *xe) if (err) return err; + err = xe_late_bind_init(&xe->late_bind); + if (err) + return err; + err = xe_oa_init(xe); if (err) return err; @@ -950,7 +957,7 @@ int xe_device_probe(struct xe_device *xe) xe_vsec_init(xe); - err = xe_sriov_late_init(xe); + err = xe_sriov_init_late(xe); if (err) goto err_unregister_display; diff --git a/drivers/gpu/drm/xe/xe_device_sysfs.c b/drivers/gpu/drm/xe/xe_device_sysfs.c index 6ee422594b56..c5151c86a98a 100644 --- a/drivers/gpu/drm/xe/xe_device_sysfs.c +++ b/drivers/gpu/drm/xe/xe_device_sysfs.c @@ -71,6 +71,15 @@ vram_d3cold_threshold_store(struct device *dev, struct device_attribute *attr, static DEVICE_ATTR_RW(vram_d3cold_threshold); +static struct attribute *vram_attrs[] = { + &dev_attr_vram_d3cold_threshold.attr, + NULL +}; + +static const struct attribute_group vram_attr_group = { + .attrs = vram_attrs, +}; + static ssize_t lb_fan_control_version_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -149,41 +158,16 @@ out: } static DEVICE_ATTR_ADMIN_RO(lb_voltage_regulator_version); -static int late_bind_create_files(struct device *dev) -{ - struct xe_device *xe = pdev_to_xe_device(to_pci_dev(dev)); - struct xe_tile *root = xe_device_get_root_tile(xe); - u32 cap = 0; - int ret; - - xe_pm_runtime_get(xe); - - ret = xe_pcode_read(root, PCODE_MBOX(PCODE_LATE_BINDING, GET_CAPABILITY_STATUS, 0), - &cap, NULL); - if (ret) { - if (ret == -ENXIO) { - drm_dbg(&xe->drm, "Late binding not supported by firmware\n"); - ret = 0; - } - goto out; - } - - if (REG_FIELD_GET(V1_FAN_SUPPORTED, cap)) { - ret = sysfs_create_file(&dev->kobj, &dev_attr_lb_fan_control_version.attr); - if (ret) - goto out; - } - - if (REG_FIELD_GET(VR_PARAMS_SUPPORTED, cap)) - ret = sysfs_create_file(&dev->kobj, &dev_attr_lb_voltage_regulator_version.attr); -out: - xe_pm_runtime_put(xe); - - return ret; -} +static struct attribute *late_bind_attrs[] = { + &dev_attr_lb_fan_control_version.attr, + &dev_attr_lb_voltage_regulator_version.attr, + NULL +}; -static void late_bind_remove_files(struct device *dev) +static umode_t late_bind_attr_is_visible(struct kobject *kobj, + struct attribute *attr, int n) { + struct device *dev = kobj_to_dev(kobj); struct xe_device *xe = pdev_to_xe_device(to_pci_dev(dev)); struct xe_tile *root = xe_device_get_root_tile(xe); u32 cap = 0; @@ -193,18 +177,25 @@ static void late_bind_remove_files(struct device *dev) ret = xe_pcode_read(root, PCODE_MBOX(PCODE_LATE_BINDING, GET_CAPABILITY_STATUS, 0), &cap, NULL); + xe_pm_runtime_put(xe); if (ret) - goto out; + return 0; - if (REG_FIELD_GET(V1_FAN_SUPPORTED, cap)) - sysfs_remove_file(&dev->kobj, &dev_attr_lb_fan_control_version.attr); + if (attr == &dev_attr_lb_fan_control_version.attr && + REG_FIELD_GET(V1_FAN_SUPPORTED, cap)) + return attr->mode; + if (attr == &dev_attr_lb_voltage_regulator_version.attr && + REG_FIELD_GET(VR_PARAMS_SUPPORTED, cap)) + return attr->mode; - if (REG_FIELD_GET(VR_PARAMS_SUPPORTED, cap)) - sysfs_remove_file(&dev->kobj, &dev_attr_lb_voltage_regulator_version.attr); -out: - xe_pm_runtime_put(xe); + return 0; } +static const struct attribute_group late_bind_attr_group = { + .attrs = late_bind_attrs, + .is_visible = late_bind_attr_is_visible, +}; + /** * DOC: PCIe Gen5 Limitations * @@ -278,24 +269,15 @@ auto_link_downgrade_status_show(struct device *dev, struct device_attribute *att } static DEVICE_ATTR_ADMIN_RO(auto_link_downgrade_status); -static const struct attribute *auto_link_downgrade_attrs[] = { +static struct attribute *auto_link_downgrade_attrs[] = { &dev_attr_auto_link_downgrade_capable.attr, &dev_attr_auto_link_downgrade_status.attr, NULL }; -static void xe_device_sysfs_fini(void *arg) -{ - struct xe_device *xe = arg; - - if (xe->d3cold.capable) - sysfs_remove_file(&xe->drm.dev->kobj, &dev_attr_vram_d3cold_threshold.attr); - - if (xe->info.platform == XE_BATTLEMAGE) { - sysfs_remove_files(&xe->drm.dev->kobj, auto_link_downgrade_attrs); - late_bind_remove_files(xe->drm.dev); - } -} +static const struct attribute_group auto_link_downgrade_attr_group = { + .attrs = auto_link_downgrade_attrs, +}; int xe_device_sysfs_init(struct xe_device *xe) { @@ -303,20 +285,20 @@ int xe_device_sysfs_init(struct xe_device *xe) int ret; if (xe->d3cold.capable) { - ret = sysfs_create_file(&dev->kobj, &dev_attr_vram_d3cold_threshold.attr); + ret = devm_device_add_group(dev, &vram_attr_group); if (ret) return ret; } - if (xe->info.platform == XE_BATTLEMAGE) { - ret = sysfs_create_files(&dev->kobj, auto_link_downgrade_attrs); + if (xe->info.platform == XE_BATTLEMAGE && !IS_SRIOV_VF(xe)) { + ret = devm_device_add_group(dev, &auto_link_downgrade_attr_group); if (ret) return ret; - ret = late_bind_create_files(dev); + ret = devm_device_add_group(dev, &late_bind_attr_group); if (ret) return ret; } - return devm_add_action_or_reset(dev, xe_device_sysfs_fini, xe); + return 0; } diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h index 79d3a59762d9..a6c361db11d9 100644 --- a/drivers/gpu/drm/xe/xe_device_types.h +++ b/drivers/gpu/drm/xe/xe_device_types.h @@ -14,6 +14,7 @@ #include "xe_devcoredump_types.h" #include "xe_heci_gsc.h" +#include "xe_late_bind_fw_types.h" #include "xe_lmtt_types.h" #include "xe_memirq_types.h" #include "xe_oa_types.h" @@ -26,6 +27,7 @@ #include "xe_sriov_vf_ccs_types.h" #include "xe_step_types.h" #include "xe_survivability_mode_types.h" +#include "xe_validation.h" #if IS_ENABLED(CONFIG_DRM_XE_DEBUG) #define TEST_VM_OPS_ERROR @@ -183,9 +185,6 @@ struct xe_tile { struct { /** @sriov.vf.ggtt_balloon: GGTT regions excluded from use. */ struct xe_ggtt_node *ggtt_balloon[2]; - - /** @sriov.vf.ccs: CCS read and write contexts for VF. */ - struct xe_tile_vf_ccs ccs[XE_SRIOV_VF_CCS_CTX_COUNT]; } vf; } sriov; @@ -282,6 +281,8 @@ struct xe_device { u8 has_heci_cscfi:1; /** @info.has_heci_gscfi: device has heci gscfi */ u8 has_heci_gscfi:1; + /** @info.has_late_bind: Device has firmware late binding support */ + u8 has_late_bind:1; /** @info.has_llc: Device has a shared CPU+GPU last level cache */ u8 has_llc:1; /** @info.has_mbx_power_limits: Device has support to manage power limits using @@ -507,6 +508,12 @@ struct xe_device { /** @pm_notifier: Our PM notifier to perform actions in response to various PM events. */ struct notifier_block pm_notifier; + /** @pm_block: Completion to block validating tasks on suspend / hibernate prepare */ + struct completion pm_block; + /** @rebind_resume_list: List of wq items to kick on resume. */ + struct list_head rebind_resume_list; + /** @rebind_resume_lock: Lock to protect the rebind_resume_list */ + struct mutex rebind_resume_lock; /** @pmt: Support the PMT driver callback interface */ struct { @@ -529,6 +536,9 @@ struct xe_device { /** @nvm: discrete graphics non-volatile memory */ struct intel_dg_nvm_dev *nvm; + /** @late_bind: xe mei late bind interface */ + struct xe_late_bind late_bind; + /** @oa: oa observation subsystem */ struct xe_oa oa; @@ -580,6 +590,8 @@ struct xe_device { */ atomic64_t global_total_pages; #endif + /** @val: The domain for exhaustive eviction, which is currently per device. */ + struct xe_validation_device val; /** @psmi: GPU debugging via additional validation HW */ struct { @@ -589,6 +601,13 @@ struct xe_device { u8 region_mask; } psmi; +#if IS_ENABLED(CONFIG_DRM_XE_KUNIT_TEST) + /** @g2g_test_array: for testing G2G communications */ + u32 *g2g_test_array; + /** @g2g_test_count: for testing G2G communications */ + atomic_t g2g_test_count; +#endif + /* private: */ #if IS_ENABLED(CONFIG_DRM_XE_DISPLAY) diff --git a/drivers/gpu/drm/xe/xe_dma_buf.c b/drivers/gpu/drm/xe/xe_dma_buf.c index 346f857f3837..a7d67725c3ee 100644 --- a/drivers/gpu/drm/xe/xe_dma_buf.c +++ b/drivers/gpu/drm/xe/xe_dma_buf.c @@ -51,6 +51,7 @@ static int xe_dma_buf_pin(struct dma_buf_attachment *attach) struct drm_gem_object *obj = attach->dmabuf->priv; struct xe_bo *bo = gem_to_xe_bo(obj); struct xe_device *xe = xe_bo_device(bo); + struct drm_exec *exec = XE_VALIDATION_UNSUPPORTED; int ret; /* @@ -63,7 +64,7 @@ static int xe_dma_buf_pin(struct dma_buf_attachment *attach) return -EINVAL; } - ret = xe_bo_migrate(bo, XE_PL_TT); + ret = xe_bo_migrate(bo, XE_PL_TT, NULL, exec); if (ret) { if (ret != -EINTR && ret != -ERESTARTSYS) drm_dbg(&xe->drm, @@ -72,7 +73,7 @@ static int xe_dma_buf_pin(struct dma_buf_attachment *attach) return ret; } - ret = xe_bo_pin_external(bo); + ret = xe_bo_pin_external(bo, true, exec); xe_assert(xe, !ret); return 0; @@ -92,6 +93,7 @@ static struct sg_table *xe_dma_buf_map(struct dma_buf_attachment *attach, struct dma_buf *dma_buf = attach->dmabuf; struct drm_gem_object *obj = dma_buf->priv; struct xe_bo *bo = gem_to_xe_bo(obj); + struct drm_exec *exec = XE_VALIDATION_UNSUPPORTED; struct sg_table *sgt; int r = 0; @@ -100,9 +102,9 @@ static struct sg_table *xe_dma_buf_map(struct dma_buf_attachment *attach, if (!xe_bo_is_pinned(bo)) { if (!attach->peer2peer) - r = xe_bo_migrate(bo, XE_PL_TT); + r = xe_bo_migrate(bo, XE_PL_TT, NULL, exec); else - r = xe_bo_validate(bo, NULL, false); + r = xe_bo_validate(bo, NULL, false, exec); if (r) return ERR_PTR(r); } @@ -161,15 +163,26 @@ static int xe_dma_buf_begin_cpu_access(struct dma_buf *dma_buf, struct xe_bo *bo = gem_to_xe_bo(obj); bool reads = (direction == DMA_BIDIRECTIONAL || direction == DMA_FROM_DEVICE); + struct xe_validation_ctx ctx; + struct drm_exec exec; + int ret = 0; if (!reads) return 0; /* Can we do interruptible lock here? */ - xe_bo_lock(bo, false); - (void)xe_bo_migrate(bo, XE_PL_TT); - xe_bo_unlock(bo); + xe_validation_guard(&ctx, &xe_bo_device(bo)->val, &exec, (struct xe_val_flags) {}, ret) { + ret = drm_exec_lock_obj(&exec, &bo->ttm.base); + drm_exec_retry_on_contention(&exec); + if (ret) + break; + + ret = xe_bo_migrate(bo, XE_PL_TT, NULL, &exec); + drm_exec_retry_on_contention(&exec); + xe_validation_retry_on_oom(&ctx, &ret); + } + /* If we failed, cpu-access takes place in current placement. */ return 0; } @@ -191,10 +204,22 @@ struct dma_buf *xe_gem_prime_export(struct drm_gem_object *obj, int flags) { struct xe_bo *bo = gem_to_xe_bo(obj); struct dma_buf *buf; + struct ttm_operation_ctx ctx = { + .interruptible = true, + .no_wait_gpu = true, + /* We opt to avoid OOM on system pages allocations */ + .gfp_retry_mayfail = true, + .allow_res_evict = false, + }; + int ret; if (bo->vm) return ERR_PTR(-EPERM); + ret = ttm_bo_setup_export(&bo->ttm, &ctx); + if (ret) + return ERR_PTR(ret); + buf = drm_gem_prime_export(obj, flags); if (!IS_ERR(buf)) buf->ops = &xe_dmabuf_ops; @@ -208,32 +233,45 @@ xe_dma_buf_init_obj(struct drm_device *dev, struct xe_bo *storage, { struct dma_resv *resv = dma_buf->resv; struct xe_device *xe = to_xe_device(dev); + struct xe_validation_ctx ctx; + struct drm_gem_object *dummy_obj; + struct drm_exec exec; struct xe_bo *bo; - int ret; - - dma_resv_lock(resv, NULL); - bo = ___xe_bo_create_locked(xe, storage, NULL, resv, NULL, dma_buf->size, - 0, /* Will require 1way or 2way for vm_bind */ - ttm_bo_type_sg, XE_BO_FLAG_SYSTEM); - if (IS_ERR(bo)) { - ret = PTR_ERR(bo); - goto error; + int ret = 0; + + dummy_obj = drm_gpuvm_resv_object_alloc(&xe->drm); + if (!dummy_obj) + return ERR_PTR(-ENOMEM); + + dummy_obj->resv = resv; + xe_validation_guard(&ctx, &xe->val, &exec, (struct xe_val_flags) {}, ret) { + ret = drm_exec_lock_obj(&exec, dummy_obj); + drm_exec_retry_on_contention(&exec); + if (ret) + break; + + bo = xe_bo_init_locked(xe, storage, NULL, resv, NULL, dma_buf->size, + 0, /* Will require 1way or 2way for vm_bind */ + ttm_bo_type_sg, XE_BO_FLAG_SYSTEM, &exec); + drm_exec_retry_on_contention(&exec); + if (IS_ERR(bo)) { + ret = PTR_ERR(bo); + xe_validation_retry_on_oom(&ctx, &ret); + break; + } } - dma_resv_unlock(resv); - - return &bo->ttm.base; + drm_gem_object_put(dummy_obj); -error: - dma_resv_unlock(resv); - return ERR_PTR(ret); + return ret ? ERR_PTR(ret) : &bo->ttm.base; } static void xe_dma_buf_move_notify(struct dma_buf_attachment *attach) { struct drm_gem_object *obj = attach->importer_priv; struct xe_bo *bo = gem_to_xe_bo(obj); + struct drm_exec *exec = XE_VALIDATION_UNSUPPORTED; - XE_WARN_ON(xe_bo_evict(bo)); + XE_WARN_ON(xe_bo_evict(bo, exec)); } static const struct dma_buf_attach_ops xe_dma_buf_attach_ops = { diff --git a/drivers/gpu/drm/xe/xe_eu_stall.c b/drivers/gpu/drm/xe/xe_eu_stall.c index fdd514fec5ef..f5cfdf29fde3 100644 --- a/drivers/gpu/drm/xe/xe_eu_stall.c +++ b/drivers/gpu/drm/xe/xe_eu_stall.c @@ -617,9 +617,8 @@ static int xe_eu_stall_data_buf_alloc(struct xe_eu_stall_data_stream *stream, size = stream->per_xecore_buf_size * last_xecore; - bo = xe_bo_create_pin_map_at_aligned(tile->xe, tile, NULL, - size, ~0ull, ttm_bo_type_kernel, - XE_BO_FLAG_SYSTEM | XE_BO_FLAG_GGTT, SZ_64); + bo = xe_bo_create_pin_map_at_novm(tile->xe, tile, size, ~0ull, ttm_bo_type_kernel, + XE_BO_FLAG_SYSTEM | XE_BO_FLAG_GGTT, SZ_64, false); if (IS_ERR(bo)) { kfree(stream->xecore_buf); return PTR_ERR(bo); diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c index 44364c042ad7..7715e74bb945 100644 --- a/drivers/gpu/drm/xe/xe_exec.c +++ b/drivers/gpu/drm/xe/xe_exec.c @@ -19,6 +19,7 @@ #include "xe_ring_ops_types.h" #include "xe_sched_job.h" #include "xe_sync.h" +#include "xe_svm.h" #include "xe_vm.h" /** @@ -97,9 +98,13 @@ static int xe_exec_fn(struct drm_gpuvm_exec *vm_exec) { struct xe_vm *vm = container_of(vm_exec->vm, struct xe_vm, gpuvm); + int ret; /* The fence slot added here is intended for the exec sched job. */ - return xe_vm_validate_rebind(vm, &vm_exec->exec, 1); + xe_vm_set_validation_exec(vm, &vm_exec->exec); + ret = xe_vm_validate_rebind(vm, &vm_exec->exec, 1); + xe_vm_set_validation_exec(vm, NULL); + return ret; } int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file) @@ -115,10 +120,10 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file) struct drm_gpuvm_exec vm_exec = {.extra.fn = xe_exec_fn}; struct drm_exec *exec = &vm_exec.exec; u32 i, num_syncs, num_ufence = 0; + struct xe_validation_ctx ctx; struct xe_sched_job *job; struct xe_vm *vm; bool write_locked, skip_retry = false; - ktime_t end = 0; int err = 0; struct xe_hw_engine_group *group; enum xe_hw_engine_group_execution_mode mode, previous_mode; @@ -237,17 +242,21 @@ retry: goto err_unlock_list; } - vm_exec.vm = &vm->gpuvm; - vm_exec.flags = DRM_EXEC_INTERRUPTIBLE_WAIT; - if (xe_vm_in_lr_mode(vm)) { - drm_exec_init(exec, vm_exec.flags, 0); - } else { - err = drm_gpuvm_exec_lock(&vm_exec); - if (err) { - if (xe_vm_validate_should_retry(exec, err, &end)) - err = -EAGAIN; + /* + * It's OK to block interruptible here with the vm lock held, since + * on task freezing during suspend / hibernate, the call will + * return -ERESTARTSYS and the IOCTL will be rerun. + */ + err = wait_for_completion_interruptible(&xe->pm_block); + if (err) + goto err_unlock_list; + + if (!xe_vm_in_lr_mode(vm)) { + vm_exec.vm = &vm->gpuvm; + vm_exec.flags = DRM_EXEC_INTERRUPTIBLE_WAIT; + err = xe_validation_exec_lock(&ctx, &vm_exec, &xe->val); + if (err) goto err_unlock_list; - } } if (xe_vm_is_closed_or_banned(q->vm)) { @@ -294,7 +303,7 @@ retry: if (err) goto err_put_job; - err = down_read_interruptible(&vm->userptr.notifier_lock); + err = xe_svm_notifier_lock_interruptible(vm); if (err) goto err_put_job; @@ -336,12 +345,13 @@ retry: err_repin: if (!xe_vm_in_lr_mode(vm)) - up_read(&vm->userptr.notifier_lock); + xe_svm_notifier_unlock(vm); err_put_job: if (err) xe_sched_job_put(job); err_exec: - drm_exec_fini(exec); + if (!xe_vm_in_lr_mode(vm)) + xe_validation_ctx_fini(&ctx); err_unlock_list: up_read(&vm->lock); if (err == -EAGAIN && !skip_retry) diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c index 063c89d981e5..37b2b93b73d6 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue.c +++ b/drivers/gpu/drm/xe/xe_exec_queue.c @@ -199,6 +199,16 @@ err_lrc: return err; } +static void __xe_exec_queue_fini(struct xe_exec_queue *q) +{ + int i; + + q->ops->fini(q); + + for (i = 0; i < q->width; ++i) + xe_lrc_put(q->lrc[i]); +} + struct xe_exec_queue *xe_exec_queue_create(struct xe_device *xe, struct xe_vm *vm, u32 logical_mask, u16 width, struct xe_hw_engine *hwe, u32 flags, @@ -229,11 +239,13 @@ struct xe_exec_queue *xe_exec_queue_create(struct xe_device *xe, struct xe_vm *v if (xe_exec_queue_uses_pxp(q)) { err = xe_pxp_exec_queue_add(xe->pxp, q); if (err) - goto err_post_alloc; + goto err_post_init; } return q; +err_post_init: + __xe_exec_queue_fini(q); err_post_alloc: __xe_exec_queue_free(q); return ERR_PTR(err); @@ -331,13 +343,11 @@ void xe_exec_queue_destroy(struct kref *ref) xe_exec_queue_put(eq); } - q->ops->fini(q); + q->ops->destroy(q); } void xe_exec_queue_fini(struct xe_exec_queue *q) { - int i; - /* * Before releasing our ref to lrc and xef, accumulate our run ticks * and wakeup any waiters. @@ -346,9 +356,7 @@ void xe_exec_queue_fini(struct xe_exec_queue *q) if (q->xef && atomic_dec_and_test(&q->xef->exec_queue.pending_removal)) wake_up_var(&q->xef->exec_queue.pending_removal); - for (i = 0; i < q->width; ++i) - xe_lrc_put(q->lrc[i]); - + __xe_exec_queue_fini(q); __xe_exec_queue_free(q); } diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h index ba443a497b38..27b76cf9da89 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue_types.h +++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h @@ -181,8 +181,14 @@ struct xe_exec_queue_ops { int (*init)(struct xe_exec_queue *q); /** @kill: Kill inflight submissions for backend */ void (*kill)(struct xe_exec_queue *q); - /** @fini: Fini exec queue for submission backend */ + /** @fini: Undoes the init() for submission backend */ void (*fini)(struct xe_exec_queue *q); + /** + * @destroy: Destroy exec queue for submission backend. The backend + * function must call xe_exec_queue_fini() (which will in turn call the + * fini() backend function) to ensure the queue is properly cleaned up. + */ + void (*destroy)(struct xe_exec_queue *q); /** @set_priority: Set priority for exec queue */ int (*set_priority)(struct xe_exec_queue *q, enum xe_exec_queue_priority priority); diff --git a/drivers/gpu/drm/xe/xe_execlist.c b/drivers/gpu/drm/xe/xe_execlist.c index 788f56b066b6..f83d421ac9d3 100644 --- a/drivers/gpu/drm/xe/xe_execlist.c +++ b/drivers/gpu/drm/xe/xe_execlist.c @@ -385,10 +385,20 @@ err_free: return err; } -static void execlist_exec_queue_fini_async(struct work_struct *w) +static void execlist_exec_queue_fini(struct xe_exec_queue *q) +{ + struct xe_execlist_exec_queue *exl = q->execlist; + + drm_sched_entity_fini(&exl->entity); + drm_sched_fini(&exl->sched); + + kfree(exl); +} + +static void execlist_exec_queue_destroy_async(struct work_struct *w) { struct xe_execlist_exec_queue *ee = - container_of(w, struct xe_execlist_exec_queue, fini_async); + container_of(w, struct xe_execlist_exec_queue, destroy_async); struct xe_exec_queue *q = ee->q; struct xe_execlist_exec_queue *exl = q->execlist; struct xe_device *xe = gt_to_xe(q->gt); @@ -401,10 +411,6 @@ static void execlist_exec_queue_fini_async(struct work_struct *w) list_del(&exl->active_link); spin_unlock_irqrestore(&exl->port->lock, flags); - drm_sched_entity_fini(&exl->entity); - drm_sched_fini(&exl->sched); - kfree(exl); - xe_exec_queue_fini(q); } @@ -413,10 +419,10 @@ static void execlist_exec_queue_kill(struct xe_exec_queue *q) /* NIY */ } -static void execlist_exec_queue_fini(struct xe_exec_queue *q) +static void execlist_exec_queue_destroy(struct xe_exec_queue *q) { - INIT_WORK(&q->execlist->fini_async, execlist_exec_queue_fini_async); - queue_work(system_unbound_wq, &q->execlist->fini_async); + INIT_WORK(&q->execlist->destroy_async, execlist_exec_queue_destroy_async); + queue_work(system_unbound_wq, &q->execlist->destroy_async); } static int execlist_exec_queue_set_priority(struct xe_exec_queue *q, @@ -467,6 +473,7 @@ static const struct xe_exec_queue_ops execlist_exec_queue_ops = { .init = execlist_exec_queue_init, .kill = execlist_exec_queue_kill, .fini = execlist_exec_queue_fini, + .destroy = execlist_exec_queue_destroy, .set_priority = execlist_exec_queue_set_priority, .set_timeslice = execlist_exec_queue_set_timeslice, .set_preempt_timeout = execlist_exec_queue_set_preempt_timeout, diff --git a/drivers/gpu/drm/xe/xe_execlist_types.h b/drivers/gpu/drm/xe/xe_execlist_types.h index 415140936f11..92c4ba52db0c 100644 --- a/drivers/gpu/drm/xe/xe_execlist_types.h +++ b/drivers/gpu/drm/xe/xe_execlist_types.h @@ -42,7 +42,7 @@ struct xe_execlist_exec_queue { bool has_run; - struct work_struct fini_async; + struct work_struct destroy_async; enum xe_exec_queue_priority active_priority; struct list_head active_link; diff --git a/drivers/gpu/drm/xe/xe_ggtt.c b/drivers/gpu/drm/xe/xe_ggtt.c index 71c7690a92b3..7fdd0a97a628 100644 --- a/drivers/gpu/drm/xe/xe_ggtt.c +++ b/drivers/gpu/drm/xe/xe_ggtt.c @@ -28,6 +28,7 @@ #include "xe_pm.h" #include "xe_res_cursor.h" #include "xe_sriov.h" +#include "xe_tile_printk.h" #include "xe_tile_sriov_vf.h" #include "xe_tlb_inval.h" #include "xe_wa.h" @@ -269,7 +270,7 @@ int xe_ggtt_init_early(struct xe_ggtt *ggtt) gsm_size = probe_gsm_size(pdev); if (gsm_size == 0) { - drm_err(&xe->drm, "Hardware reported no preallocated GSM\n"); + xe_tile_err(ggtt->tile, "Hardware reported no preallocated GSM\n"); return -ENOMEM; } @@ -466,8 +467,8 @@ static void xe_ggtt_dump_node(struct xe_ggtt *ggtt, if (IS_ENABLED(CONFIG_DRM_XE_DEBUG)) { string_get_size(node->size, 1, STRING_UNITS_2, buf, sizeof(buf)); - xe_gt_dbg(ggtt->tile->primary_gt, "GGTT %#llx-%#llx (%s) %s\n", - node->start, node->start + node->size, buf, description); + xe_tile_dbg(ggtt->tile, "GGTT %#llx-%#llx (%s) %s\n", + node->start, node->start + node->size, buf, description); } } @@ -499,9 +500,8 @@ int xe_ggtt_node_insert_balloon_locked(struct xe_ggtt_node *node, u64 start, u64 err = drm_mm_reserve_node(&ggtt->mm, &node->base); - if (xe_gt_WARN(ggtt->tile->primary_gt, err, - "Failed to balloon GGTT %#llx-%#llx (%pe)\n", - node->base.start, node->base.start + node->base.size, ERR_PTR(err))) + if (xe_tile_WARN(ggtt->tile, err, "Failed to balloon GGTT %#llx-%#llx (%pe)\n", + node->base.start, node->base.start + node->base.size, ERR_PTR(err))) return err; xe_ggtt_dump_node(ggtt, &node->base, "balloon"); @@ -731,7 +731,7 @@ void xe_ggtt_map_bo_unlocked(struct xe_ggtt *ggtt, struct xe_bo *bo) } static int __xe_ggtt_insert_bo_at(struct xe_ggtt *ggtt, struct xe_bo *bo, - u64 start, u64 end) + u64 start, u64 end, struct drm_exec *exec) { u64 alignment = bo->min_align > 0 ? bo->min_align : XE_PAGE_SIZE; u8 tile_id = ggtt->tile->id; @@ -746,7 +746,7 @@ static int __xe_ggtt_insert_bo_at(struct xe_ggtt *ggtt, struct xe_bo *bo, return 0; } - err = xe_bo_validate(bo, NULL, false); + err = xe_bo_validate(bo, NULL, false, exec); if (err) return err; @@ -788,25 +788,28 @@ out: * @bo: the &xe_bo to be inserted * @start: address where it will be inserted * @end: end of the range where it will be inserted + * @exec: The drm_exec transaction to use for exhaustive eviction. * * Return: 0 on success or a negative error code on failure. */ int xe_ggtt_insert_bo_at(struct xe_ggtt *ggtt, struct xe_bo *bo, - u64 start, u64 end) + u64 start, u64 end, struct drm_exec *exec) { - return __xe_ggtt_insert_bo_at(ggtt, bo, start, end); + return __xe_ggtt_insert_bo_at(ggtt, bo, start, end, exec); } /** * xe_ggtt_insert_bo - Insert BO into GGTT * @ggtt: the &xe_ggtt where bo will be inserted * @bo: the &xe_bo to be inserted + * @exec: The drm_exec transaction to use for exhaustive eviction. * * Return: 0 on success or a negative error code on failure. */ -int xe_ggtt_insert_bo(struct xe_ggtt *ggtt, struct xe_bo *bo) +int xe_ggtt_insert_bo(struct xe_ggtt *ggtt, struct xe_bo *bo, + struct drm_exec *exec) { - return __xe_ggtt_insert_bo_at(ggtt, bo, 0, U64_MAX); + return __xe_ggtt_insert_bo_at(ggtt, bo, 0, U64_MAX, exec); } /** diff --git a/drivers/gpu/drm/xe/xe_ggtt.h b/drivers/gpu/drm/xe/xe_ggtt.h index fbe1e397d05d..75fc7a1efea7 100644 --- a/drivers/gpu/drm/xe/xe_ggtt.h +++ b/drivers/gpu/drm/xe/xe_ggtt.h @@ -10,6 +10,7 @@ struct drm_printer; struct xe_tile; +struct drm_exec; struct xe_ggtt *xe_ggtt_alloc(struct xe_tile *tile); int xe_ggtt_init_early(struct xe_ggtt *ggtt); @@ -31,9 +32,9 @@ bool xe_ggtt_node_allocated(const struct xe_ggtt_node *node); void xe_ggtt_map_bo(struct xe_ggtt *ggtt, struct xe_ggtt_node *node, struct xe_bo *bo, u16 pat_index); void xe_ggtt_map_bo_unlocked(struct xe_ggtt *ggtt, struct xe_bo *bo); -int xe_ggtt_insert_bo(struct xe_ggtt *ggtt, struct xe_bo *bo); +int xe_ggtt_insert_bo(struct xe_ggtt *ggtt, struct xe_bo *bo, struct drm_exec *exec); int xe_ggtt_insert_bo_at(struct xe_ggtt *ggtt, struct xe_bo *bo, - u64 start, u64 end); + u64 start, u64 end, struct drm_exec *exec); void xe_ggtt_remove_bo(struct xe_ggtt *ggtt, struct xe_bo *bo); u64 xe_ggtt_largest_hole(struct xe_ggtt *ggtt, u64 alignment, u64 *spare); diff --git a/drivers/gpu/drm/xe/xe_gsc.c b/drivers/gpu/drm/xe/xe_gsc.c index f5ae28af60d4..83d61bf8ec62 100644 --- a/drivers/gpu/drm/xe/xe_gsc.c +++ b/drivers/gpu/drm/xe/xe_gsc.c @@ -136,10 +136,10 @@ static int query_compatibility_version(struct xe_gsc *gsc) u64 ggtt_offset; int err; - bo = xe_bo_create_pin_map(xe, tile, NULL, GSC_VER_PKT_SZ * 2, - ttm_bo_type_kernel, - XE_BO_FLAG_SYSTEM | - XE_BO_FLAG_GGTT); + bo = xe_bo_create_pin_map_novm(xe, tile, GSC_VER_PKT_SZ * 2, + ttm_bo_type_kernel, + XE_BO_FLAG_SYSTEM | + XE_BO_FLAG_GGTT, false); if (IS_ERR(bo)) { xe_gt_err(gt, "failed to allocate bo for GSC version query\n"); return PTR_ERR(bo); diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c index 34505a6d93ed..3e0ad7e5b5df 100644 --- a/drivers/gpu/drm/xe/xe_gt.c +++ b/drivers/gpu/drm/xe/xe_gt.c @@ -98,7 +98,7 @@ void xe_gt_sanitize(struct xe_gt *gt) * FIXME: if xe_uc_sanitize is called here, on TGL driver will not * reload */ - gt->uc.guc.submission_state.enabled = false; + xe_guc_submit_disable(>->uc.guc); } static void xe_gt_enable_host_l2_vram(struct xe_gt *gt) diff --git a/drivers/gpu/drm/xe/xe_gt_debugfs.c b/drivers/gpu/drm/xe/xe_gt_debugfs.c index bf3a67b5951c..f253e2df4907 100644 --- a/drivers/gpu/drm/xe/xe_gt_debugfs.c +++ b/drivers/gpu/drm/xe/xe_gt_debugfs.c @@ -31,6 +31,7 @@ #include "xe_reg_whitelist.h" #include "xe_sa.h" #include "xe_sriov.h" +#include "xe_sriov_vf_ccs.h" #include "xe_tuning.h" #include "xe_uc_debugfs.h" #include "xe_wa.h" @@ -123,45 +124,6 @@ static int powergate_info(struct xe_gt *gt, struct drm_printer *p) return ret; } -static int sa_info(struct xe_gt *gt, struct drm_printer *p) -{ - struct xe_tile *tile = gt_to_tile(gt); - - xe_pm_runtime_get(gt_to_xe(gt)); - drm_suballoc_dump_debug_info(&tile->mem.kernel_bb_pool->base, p, - xe_sa_manager_gpu_addr(tile->mem.kernel_bb_pool)); - xe_pm_runtime_put(gt_to_xe(gt)); - - return 0; -} - -static int sa_info_vf_ccs(struct xe_gt *gt, struct drm_printer *p) -{ - struct xe_tile *tile = gt_to_tile(gt); - struct xe_sa_manager *bb_pool; - enum xe_sriov_vf_ccs_rw_ctxs ctx_id; - - if (!IS_VF_CCS_READY(gt_to_xe(gt))) - return 0; - - xe_pm_runtime_get(gt_to_xe(gt)); - - for_each_ccs_rw_ctx(ctx_id) { - bb_pool = tile->sriov.vf.ccs[ctx_id].mem.ccs_bb_pool; - if (!bb_pool) - break; - - drm_printf(p, "ccs %s bb suballoc info\n", ctx_id ? "write" : "read"); - drm_printf(p, "-------------------------\n"); - drm_suballoc_dump_debug_info(&bb_pool->base, p, xe_sa_manager_gpu_addr(bb_pool)); - drm_puts(p, "\n"); - } - - xe_pm_runtime_put(gt_to_xe(gt)); - - return 0; -} - static int topology(struct xe_gt *gt, struct drm_printer *p) { xe_pm_runtime_get(gt_to_xe(gt)); @@ -316,7 +278,6 @@ static int hwconfig(struct xe_gt *gt, struct drm_printer *p) * - without access to the PF specific data */ static const struct drm_info_list vf_safe_debugfs_list[] = { - {"sa_info", .show = xe_gt_debugfs_simple_show, .data = sa_info}, {"topology", .show = xe_gt_debugfs_simple_show, .data = topology}, {"ggtt", .show = xe_gt_debugfs_simple_show, .data = ggtt}, {"register-save-restore", .show = xe_gt_debugfs_simple_show, .data = register_save_restore}, @@ -327,17 +288,9 @@ static const struct drm_info_list vf_safe_debugfs_list[] = { {"default_lrc_bcs", .show = xe_gt_debugfs_simple_show, .data = bcs_default_lrc}, {"default_lrc_vcs", .show = xe_gt_debugfs_simple_show, .data = vcs_default_lrc}, {"default_lrc_vecs", .show = xe_gt_debugfs_simple_show, .data = vecs_default_lrc}, - {"stats", .show = xe_gt_debugfs_simple_show, .data = xe_gt_stats_print_info}, {"hwconfig", .show = xe_gt_debugfs_simple_show, .data = hwconfig}, }; -/* - * only for GT debugfs files which are valid on VF. Not valid on PF. - */ -static const struct drm_info_list vf_only_debugfs_list[] = { - {"sa_info_vf_ccs", .show = xe_gt_debugfs_simple_show, .data = sa_info_vf_ccs}, -}; - /* everything else should be added here */ static const struct drm_info_list pf_only_debugfs_list[] = { {"hw_engines", .show = xe_gt_debugfs_simple_show, .data = hw_engines}, @@ -363,6 +316,24 @@ static ssize_t write_to_gt_call(const char __user *userbuf, size_t count, loff_t return count; } +static ssize_t stats_write(struct file *file, const char __user *userbuf, + size_t count, loff_t *ppos) +{ + struct seq_file *s = file->private_data; + struct xe_gt *gt = s->private; + + return write_to_gt_call(userbuf, count, ppos, xe_gt_stats_clear, gt); +} + +static int stats_show(struct seq_file *s, void *unused) +{ + struct drm_printer p = drm_seq_file_printer(s); + struct xe_gt *gt = s->private; + + return xe_gt_stats_print_info(gt, &p); +} +DEFINE_SHOW_STORE_ATTRIBUTE(stats); + static void force_reset(struct xe_gt *gt) { struct xe_device *xe = gt_to_xe(gt); @@ -448,6 +419,7 @@ void xe_gt_debugfs_register(struct xe_gt *gt) root->d_inode->i_private = gt; /* VF safe */ + debugfs_create_file("stats", 0600, root, gt, &stats_fops); debugfs_create_file("force_reset", 0600, root, gt, &force_reset_fops); debugfs_create_file("force_reset_sync", 0600, root, gt, &force_reset_sync_fops); @@ -459,11 +431,6 @@ void xe_gt_debugfs_register(struct xe_gt *gt) drm_debugfs_create_files(pf_only_debugfs_list, ARRAY_SIZE(pf_only_debugfs_list), root, minor); - else - drm_debugfs_create_files(vf_only_debugfs_list, - ARRAY_SIZE(vf_only_debugfs_list), - root, minor); - xe_uc_debugfs_register(>->uc, root); diff --git a/drivers/gpu/drm/xe/xe_gt_freq.c b/drivers/gpu/drm/xe/xe_gt_freq.c index 60d9354e7dbf..4ff1b6b58d6b 100644 --- a/drivers/gpu/drm/xe/xe_gt_freq.c +++ b/drivers/gpu/drm/xe/xe_gt_freq.c @@ -227,6 +227,33 @@ static ssize_t max_freq_store(struct kobject *kobj, } static struct kobj_attribute attr_max_freq = __ATTR_RW(max_freq); +static ssize_t power_profile_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buff) +{ + struct device *dev = kobj_to_dev(kobj); + + xe_guc_pc_get_power_profile(dev_to_pc(dev), buff); + + return strlen(buff); +} + +static ssize_t power_profile_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buff, size_t count) +{ + struct device *dev = kobj_to_dev(kobj); + struct xe_guc_pc *pc = dev_to_pc(dev); + int err; + + xe_pm_runtime_get(dev_to_xe(dev)); + err = xe_guc_pc_set_power_profile(pc, buff); + xe_pm_runtime_put(dev_to_xe(dev)); + + return err ?: count; +} +static struct kobj_attribute attr_power_profile = __ATTR_RW(power_profile); + static const struct attribute *freq_attrs[] = { &attr_act_freq.attr, &attr_cur_freq.attr, @@ -236,6 +263,7 @@ static const struct attribute *freq_attrs[] = { &attr_rpn_freq.attr, &attr_min_freq.attr, &attr_max_freq.attr, + &attr_power_profile.attr, NULL }; diff --git a/drivers/gpu/drm/xe/xe_gt_mcr.c b/drivers/gpu/drm/xe/xe_gt_mcr.c index 683ac021a06d..8fb1cae91724 100644 --- a/drivers/gpu/drm/xe/xe_gt_mcr.c +++ b/drivers/gpu/drm/xe/xe_gt_mcr.c @@ -362,7 +362,7 @@ fallback: * @group: pointer to storage for steering group ID * @instance: pointer to storage for steering instance ID */ -void xe_gt_mcr_get_dss_steering(struct xe_gt *gt, unsigned int dss, u16 *group, u16 *instance) +void xe_gt_mcr_get_dss_steering(const struct xe_gt *gt, unsigned int dss, u16 *group, u16 *instance) { xe_gt_assert(gt, dss < XE_MAX_DSS_FUSE_BITS); diff --git a/drivers/gpu/drm/xe/xe_gt_mcr.h b/drivers/gpu/drm/xe/xe_gt_mcr.h index bc06520befab..283a1c9770e2 100644 --- a/drivers/gpu/drm/xe/xe_gt_mcr.h +++ b/drivers/gpu/drm/xe/xe_gt_mcr.h @@ -31,7 +31,8 @@ bool xe_gt_mcr_get_nonterminated_steering(struct xe_gt *gt, u8 *group, u8 *instance); void xe_gt_mcr_steering_dump(struct xe_gt *gt, struct drm_printer *p); -void xe_gt_mcr_get_dss_steering(struct xe_gt *gt, unsigned int dss, u16 *group, u16 *instance); +void xe_gt_mcr_get_dss_steering(const struct xe_gt *gt, + unsigned int dss, u16 *group, u16 *instance); u32 xe_gt_mcr_steering_info_to_dss_id(struct xe_gt *gt, u16 group, u16 instance); /* diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c index d02d22fb3659..a054d6010ae0 100644 --- a/drivers/gpu/drm/xe/xe_gt_pagefault.c +++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c @@ -87,10 +87,8 @@ static int xe_pf_begin(struct drm_exec *exec, struct xe_vma *vma, if (!bo) return 0; - err = need_vram_move ? xe_bo_migrate(bo, vram->placement) : - xe_bo_validate(bo, vm, true); - - return err; + return need_vram_move ? xe_bo_migrate(bo, vram->placement, NULL, exec) : + xe_bo_validate(bo, vm, true, exec); } static int handle_vma_pagefault(struct xe_gt *gt, struct xe_vma *vma, @@ -98,9 +96,9 @@ static int handle_vma_pagefault(struct xe_gt *gt, struct xe_vma *vma, { struct xe_vm *vm = xe_vma_vm(vma); struct xe_tile *tile = gt_to_tile(gt); + struct xe_validation_ctx ctx; struct drm_exec exec; struct dma_fence *fence; - ktime_t end = 0; int err, needs_vram; lockdep_assert_held_write(&vm->lock); @@ -129,22 +127,22 @@ retry_userptr: } /* Lock VM and BOs dma-resv */ - drm_exec_init(&exec, 0, 0); + xe_validation_ctx_init(&ctx, &vm->xe->val, &exec, (struct xe_val_flags) {}); drm_exec_until_all_locked(&exec) { err = xe_pf_begin(&exec, vma, needs_vram == 1, tile->mem.vram); drm_exec_retry_on_contention(&exec); - if (xe_vm_validate_should_retry(&exec, err, &end)) - err = -EAGAIN; + xe_validation_retry_on_oom(&ctx, &err); if (err) goto unlock_dma_resv; /* Bind VMA only to the GT that has faulted */ trace_xe_vma_pf_bind(vma); + xe_vm_set_validation_exec(vm, &exec); fence = xe_vma_rebind(vm, vma, BIT(tile->id)); + xe_vm_set_validation_exec(vm, NULL); if (IS_ERR(fence)) { err = PTR_ERR(fence); - if (xe_vm_validate_should_retry(&exec, err, &end)) - err = -EAGAIN; + xe_validation_retry_on_oom(&ctx, &err); goto unlock_dma_resv; } } @@ -153,7 +151,7 @@ retry_userptr: dma_fence_put(fence); unlock_dma_resv: - drm_exec_fini(&exec); + xe_validation_ctx_fini(&ctx); if (err == -EAGAIN) goto retry_userptr; @@ -535,6 +533,7 @@ static int handle_acc(struct xe_gt *gt, struct acc *acc) { struct xe_device *xe = gt_to_xe(gt); struct xe_tile *tile = gt_to_tile(gt); + struct xe_validation_ctx ctx; struct drm_exec exec; struct xe_vm *vm; struct xe_vma *vma; @@ -564,15 +563,14 @@ static int handle_acc(struct xe_gt *gt, struct acc *acc) goto unlock_vm; /* Lock VM and BOs dma-resv */ - drm_exec_init(&exec, 0, 0); + xe_validation_ctx_init(&ctx, &vm->xe->val, &exec, (struct xe_val_flags) {}); drm_exec_until_all_locked(&exec) { ret = xe_pf_begin(&exec, vma, IS_DGFX(vm->xe), tile->mem.vram); drm_exec_retry_on_contention(&exec); - if (ret) - break; + xe_validation_retry_on_oom(&ctx, &ret); } - drm_exec_fini(&exec); + xe_validation_ctx_fini(&ctx); unlock_vm: up_read(&vm->lock); xe_vm_put(vm); diff --git a/drivers/gpu/drm/xe/xe_gt_printk.h b/drivers/gpu/drm/xe/xe_gt_printk.h index 11da0228cea7..1313d32862db 100644 --- a/drivers/gpu/drm/xe/xe_gt_printk.h +++ b/drivers/gpu/drm/xe/xe_gt_printk.h @@ -6,18 +6,22 @@ #ifndef _XE_GT_PRINTK_H_ #define _XE_GT_PRINTK_H_ -#include <drm/drm_print.h> - #include "xe_gt_types.h" +#include "xe_tile_printk.h" + +#define __XE_GT_PRINTK_FMT(_gt, _fmt, _args...) "GT%u: " _fmt, (_gt)->info.id, ##_args #define xe_gt_printk(_gt, _level, _fmt, ...) \ - drm_##_level(>_to_xe(_gt)->drm, "GT%u: " _fmt, (_gt)->info.id, ##__VA_ARGS__) + xe_tile_printk((_gt)->tile, _level, __XE_GT_PRINTK_FMT((_gt), _fmt, ##__VA_ARGS__)) + +#define xe_gt_err(_gt, _fmt, ...) \ + xe_gt_printk((_gt), err, _fmt, ##__VA_ARGS__) #define xe_gt_err_once(_gt, _fmt, ...) \ xe_gt_printk((_gt), err_once, _fmt, ##__VA_ARGS__) -#define xe_gt_err(_gt, _fmt, ...) \ - xe_gt_printk((_gt), err, _fmt, ##__VA_ARGS__) +#define xe_gt_err_ratelimited(_gt, _fmt, ...) \ + xe_gt_printk((_gt), err_ratelimited, _fmt, ##__VA_ARGS__) #define xe_gt_warn(_gt, _fmt, ...) \ xe_gt_printk((_gt), warn, _fmt, ##__VA_ARGS__) @@ -31,20 +35,20 @@ #define xe_gt_dbg(_gt, _fmt, ...) \ xe_gt_printk((_gt), dbg, _fmt, ##__VA_ARGS__) -#define xe_gt_err_ratelimited(_gt, _fmt, ...) \ - xe_gt_printk((_gt), err_ratelimited, _fmt, ##__VA_ARGS__) +#define xe_gt_WARN_type(_gt, _type, _condition, _fmt, ...) \ + xe_tile_WARN##_type((_gt)->tile, _condition, _fmt, ## __VA_ARGS__) #define xe_gt_WARN(_gt, _condition, _fmt, ...) \ - drm_WARN(>_to_xe(_gt)->drm, _condition, "GT%u: " _fmt, (_gt)->info.id, ##__VA_ARGS__) + xe_gt_WARN_type((_gt),, _condition, __XE_GT_PRINTK_FMT((_gt), _fmt, ##__VA_ARGS__)) #define xe_gt_WARN_ONCE(_gt, _condition, _fmt, ...) \ - drm_WARN_ONCE(>_to_xe(_gt)->drm, _condition, "GT%u: " _fmt, (_gt)->info.id, ##__VA_ARGS__) + xe_gt_WARN_type((_gt), _ONCE, _condition, __XE_GT_PRINTK_FMT((_gt), _fmt, ##__VA_ARGS__)) #define xe_gt_WARN_ON(_gt, _condition) \ - xe_gt_WARN((_gt), _condition, "%s(%s)", "gt_WARN_ON", __stringify(_condition)) + xe_gt_WARN((_gt), _condition, "%s(%s)", "WARN_ON", __stringify(_condition)) #define xe_gt_WARN_ON_ONCE(_gt, _condition) \ - xe_gt_WARN_ONCE((_gt), _condition, "%s(%s)", "gt_WARN_ON_ONCE", __stringify(_condition)) + xe_gt_WARN_ONCE((_gt), _condition, "%s(%s)", "WARN_ON_ONCE", __stringify(_condition)) static inline void __xe_gt_printfn_err(struct drm_printer *p, struct va_format *vaf) { @@ -67,12 +71,12 @@ static inline void __xe_gt_printfn_dbg(struct drm_printer *p, struct va_format * /* * The original xe_gt_dbg() callsite annotations are useless here, - * redirect to the tweaked drm_dbg_printer() instead. + * redirect to the tweaked xe_tile_dbg_printer() instead. */ - dbg = drm_dbg_printer(>_to_xe(gt)->drm, DRM_UT_DRIVER, NULL); + dbg = xe_tile_dbg_printer((gt)->tile); dbg.origin = p->origin; - drm_printf(&dbg, "GT%u: %pV", gt->info.id, vaf); + drm_printf(&dbg, __XE_GT_PRINTK_FMT(gt, "%pV", vaf)); } /** diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c index c8f0320d032f..6344b5205c08 100644 --- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c +++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c @@ -1478,23 +1478,16 @@ static int pf_provision_vf_lmem(struct xe_gt *gt, unsigned int vfid, u64 size) return 0; xe_gt_assert(gt, pf_get_lmem_alignment(gt) == SZ_2M); - bo = xe_bo_create_locked(xe, tile, NULL, - ALIGN(size, PAGE_SIZE), - ttm_bo_type_kernel, - XE_BO_FLAG_VRAM_IF_DGFX(tile) | - XE_BO_FLAG_NEEDS_2M | - XE_BO_FLAG_PINNED | - XE_BO_FLAG_PINNED_LATE_RESTORE); + bo = xe_bo_create_pin_range_novm(xe, tile, + ALIGN(size, PAGE_SIZE), 0, ~0ull, + ttm_bo_type_kernel, + XE_BO_FLAG_VRAM_IF_DGFX(tile) | + XE_BO_FLAG_NEEDS_2M | + XE_BO_FLAG_PINNED | + XE_BO_FLAG_PINNED_LATE_RESTORE); if (IS_ERR(bo)) return PTR_ERR(bo); - err = xe_bo_pin(bo); - xe_bo_unlock(bo); - if (unlikely(err)) { - xe_bo_put(bo); - return err; - } - config->lmem_obj = bo; if (xe_device_has_lmtt(xe)) { @@ -1636,7 +1629,6 @@ static u64 pf_estimate_fair_lmem(struct xe_gt *gt, unsigned int num_vfs) u64 fair; fair = div_u64(available, num_vfs); - fair = rounddown_pow_of_two(fair); /* XXX: ttm_vram_mgr & drm_buddy limitation */ fair = ALIGN_DOWN(fair, alignment); #ifdef MAX_FAIR_LMEM fair = min_t(u64, MAX_FAIR_LMEM, fair); diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.c index c712111aa30d..44cc612b0a75 100644 --- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.c +++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.c @@ -55,12 +55,12 @@ static int pf_send_guc_save_vf_state(struct xe_gt *gt, unsigned int vfid, xe_gt_assert(gt, size % sizeof(u32) == 0); xe_gt_assert(gt, size == ndwords * sizeof(u32)); - bo = xe_bo_create_pin_map(xe, tile, NULL, - ALIGN(size, PAGE_SIZE), - ttm_bo_type_kernel, - XE_BO_FLAG_SYSTEM | - XE_BO_FLAG_GGTT | - XE_BO_FLAG_GGTT_INVALIDATE); + bo = xe_bo_create_pin_map_novm(xe, tile, + ALIGN(size, PAGE_SIZE), + ttm_bo_type_kernel, + XE_BO_FLAG_SYSTEM | + XE_BO_FLAG_GGTT | + XE_BO_FLAG_GGTT_INVALIDATE, false); if (IS_ERR(bo)) return PTR_ERR(bo); @@ -91,12 +91,12 @@ static int pf_send_guc_restore_vf_state(struct xe_gt *gt, unsigned int vfid, xe_gt_assert(gt, size % sizeof(u32) == 0); xe_gt_assert(gt, size == ndwords * sizeof(u32)); - bo = xe_bo_create_pin_map(xe, tile, NULL, - ALIGN(size, PAGE_SIZE), - ttm_bo_type_kernel, - XE_BO_FLAG_SYSTEM | - XE_BO_FLAG_GGTT | - XE_BO_FLAG_GGTT_INVALIDATE); + bo = xe_bo_create_pin_map_novm(xe, tile, + ALIGN(size, PAGE_SIZE), + ttm_bo_type_kernel, + XE_BO_FLAG_SYSTEM | + XE_BO_FLAG_GGTT | + XE_BO_FLAG_GGTT_INVALIDATE, false); if (IS_ERR(bo)) return PTR_ERR(bo); diff --git a/drivers/gpu/drm/xe/xe_gt_stats.c b/drivers/gpu/drm/xe/xe_gt_stats.c index 30f942671c2b..5f74706bab81 100644 --- a/drivers/gpu/drm/xe/xe_gt_stats.c +++ b/drivers/gpu/drm/xe/xe_gt_stats.c @@ -26,11 +26,46 @@ void xe_gt_stats_incr(struct xe_gt *gt, const enum xe_gt_stats_id id, int incr) atomic64_add(incr, >->stats.counters[id]); } +#define DEF_STAT_STR(ID, name) [XE_GT_STATS_ID_##ID] = name + static const char *const stat_description[__XE_GT_STATS_NUM_IDS] = { - "svm_pagefault_count", - "tlb_inval_count", - "vma_pagefault_count", - "vma_pagefault_kb", + DEF_STAT_STR(SVM_PAGEFAULT_COUNT, "svm_pagefault_count"), + DEF_STAT_STR(TLB_INVAL, "tlb_inval_count"), + DEF_STAT_STR(SVM_TLB_INVAL_COUNT, "svm_tlb_inval_count"), + DEF_STAT_STR(SVM_TLB_INVAL_US, "svm_tlb_inval_us"), + DEF_STAT_STR(VMA_PAGEFAULT_COUNT, "vma_pagefault_count"), + DEF_STAT_STR(VMA_PAGEFAULT_KB, "vma_pagefault_kb"), + DEF_STAT_STR(SVM_4K_PAGEFAULT_COUNT, "svm_4K_pagefault_count"), + DEF_STAT_STR(SVM_64K_PAGEFAULT_COUNT, "svm_64K_pagefault_count"), + DEF_STAT_STR(SVM_2M_PAGEFAULT_COUNT, "svm_2M_pagefault_count"), + DEF_STAT_STR(SVM_4K_VALID_PAGEFAULT_COUNT, "svm_4K_valid_pagefault_count"), + DEF_STAT_STR(SVM_64K_VALID_PAGEFAULT_COUNT, "svm_64K_valid_pagefault_count"), + DEF_STAT_STR(SVM_2M_VALID_PAGEFAULT_COUNT, "svm_2M_valid_pagefault_count"), + DEF_STAT_STR(SVM_4K_PAGEFAULT_US, "svm_4K_pagefault_us"), + DEF_STAT_STR(SVM_64K_PAGEFAULT_US, "svm_64K_pagefault_us"), + DEF_STAT_STR(SVM_2M_PAGEFAULT_US, "svm_2M_pagefault_us"), + DEF_STAT_STR(SVM_4K_MIGRATE_COUNT, "svm_4K_migrate_count"), + DEF_STAT_STR(SVM_64K_MIGRATE_COUNT, "svm_64K_migrate_count"), + DEF_STAT_STR(SVM_2M_MIGRATE_COUNT, "svm_2M_migrate_count"), + DEF_STAT_STR(SVM_4K_MIGRATE_US, "svm_4K_migrate_us"), + DEF_STAT_STR(SVM_64K_MIGRATE_US, "svm_64K_migrate_us"), + DEF_STAT_STR(SVM_2M_MIGRATE_US, "svm_2M_migrate_us"), + DEF_STAT_STR(SVM_DEVICE_COPY_US, "svm_device_copy_us"), + DEF_STAT_STR(SVM_4K_DEVICE_COPY_US, "svm_4K_device_copy_us"), + DEF_STAT_STR(SVM_64K_DEVICE_COPY_US, "svm_64K_device_copy_us"), + DEF_STAT_STR(SVM_2M_DEVICE_COPY_US, "svm_2M_device_copy_us"), + DEF_STAT_STR(SVM_CPU_COPY_US, "svm_cpu_copy_us"), + DEF_STAT_STR(SVM_4K_CPU_COPY_US, "svm_4K_cpu_copy_us"), + DEF_STAT_STR(SVM_64K_CPU_COPY_US, "svm_64K_cpu_copy_us"), + DEF_STAT_STR(SVM_2M_CPU_COPY_US, "svm_2M_cpu_copy_us"), + DEF_STAT_STR(SVM_DEVICE_COPY_KB, "svm_device_copy_kb"), + DEF_STAT_STR(SVM_CPU_COPY_KB, "svm_cpu_copy_kb"), + DEF_STAT_STR(SVM_4K_GET_PAGES_US, "svm_4K_get_pages_us"), + DEF_STAT_STR(SVM_64K_GET_PAGES_US, "svm_64K_get_pages_us"), + DEF_STAT_STR(SVM_2M_GET_PAGES_US, "svm_2M_get_pages_us"), + DEF_STAT_STR(SVM_4K_BIND_US, "svm_4K_bind_us"), + DEF_STAT_STR(SVM_64K_BIND_US, "svm_64K_bind_us"), + DEF_STAT_STR(SVM_2M_BIND_US, "svm_2M_bind_us"), }; /** @@ -50,3 +85,17 @@ int xe_gt_stats_print_info(struct xe_gt *gt, struct drm_printer *p) return 0; } + +/** + * xe_gt_stats_clear - Clear the GT stats + * @gt: GT structure + * + * This clear (zeros) all the available GT stats. + */ +void xe_gt_stats_clear(struct xe_gt *gt) +{ + int id; + + for (id = 0; id < ARRAY_SIZE(gt->stats.counters); ++id) + atomic64_set(>->stats.counters[id], 0); +} diff --git a/drivers/gpu/drm/xe/xe_gt_stats.h b/drivers/gpu/drm/xe/xe_gt_stats.h index 38325ef53617..e8aea32bc971 100644 --- a/drivers/gpu/drm/xe/xe_gt_stats.h +++ b/drivers/gpu/drm/xe/xe_gt_stats.h @@ -13,6 +13,7 @@ struct drm_printer; #ifdef CONFIG_DEBUG_FS int xe_gt_stats_print_info(struct xe_gt *gt, struct drm_printer *p); +void xe_gt_stats_clear(struct xe_gt *gt); void xe_gt_stats_incr(struct xe_gt *gt, const enum xe_gt_stats_id id, int incr); #else static inline void diff --git a/drivers/gpu/drm/xe/xe_gt_stats_types.h b/drivers/gpu/drm/xe/xe_gt_stats_types.h index be3244d7133c..d8348a8de2e1 100644 --- a/drivers/gpu/drm/xe/xe_gt_stats_types.h +++ b/drivers/gpu/drm/xe/xe_gt_stats_types.h @@ -9,8 +9,41 @@ enum xe_gt_stats_id { XE_GT_STATS_ID_SVM_PAGEFAULT_COUNT, XE_GT_STATS_ID_TLB_INVAL, + XE_GT_STATS_ID_SVM_TLB_INVAL_COUNT, + XE_GT_STATS_ID_SVM_TLB_INVAL_US, XE_GT_STATS_ID_VMA_PAGEFAULT_COUNT, XE_GT_STATS_ID_VMA_PAGEFAULT_KB, + XE_GT_STATS_ID_SVM_4K_PAGEFAULT_COUNT, + XE_GT_STATS_ID_SVM_64K_PAGEFAULT_COUNT, + XE_GT_STATS_ID_SVM_2M_PAGEFAULT_COUNT, + XE_GT_STATS_ID_SVM_4K_VALID_PAGEFAULT_COUNT, + XE_GT_STATS_ID_SVM_64K_VALID_PAGEFAULT_COUNT, + XE_GT_STATS_ID_SVM_2M_VALID_PAGEFAULT_COUNT, + XE_GT_STATS_ID_SVM_4K_PAGEFAULT_US, + XE_GT_STATS_ID_SVM_64K_PAGEFAULT_US, + XE_GT_STATS_ID_SVM_2M_PAGEFAULT_US, + XE_GT_STATS_ID_SVM_4K_MIGRATE_COUNT, + XE_GT_STATS_ID_SVM_64K_MIGRATE_COUNT, + XE_GT_STATS_ID_SVM_2M_MIGRATE_COUNT, + XE_GT_STATS_ID_SVM_4K_MIGRATE_US, + XE_GT_STATS_ID_SVM_64K_MIGRATE_US, + XE_GT_STATS_ID_SVM_2M_MIGRATE_US, + XE_GT_STATS_ID_SVM_DEVICE_COPY_US, + XE_GT_STATS_ID_SVM_4K_DEVICE_COPY_US, + XE_GT_STATS_ID_SVM_64K_DEVICE_COPY_US, + XE_GT_STATS_ID_SVM_2M_DEVICE_COPY_US, + XE_GT_STATS_ID_SVM_CPU_COPY_US, + XE_GT_STATS_ID_SVM_4K_CPU_COPY_US, + XE_GT_STATS_ID_SVM_64K_CPU_COPY_US, + XE_GT_STATS_ID_SVM_2M_CPU_COPY_US, + XE_GT_STATS_ID_SVM_DEVICE_COPY_KB, + XE_GT_STATS_ID_SVM_CPU_COPY_KB, + XE_GT_STATS_ID_SVM_4K_GET_PAGES_US, + XE_GT_STATS_ID_SVM_64K_GET_PAGES_US, + XE_GT_STATS_ID_SVM_2M_GET_PAGES_US, + XE_GT_STATS_ID_SVM_4K_BIND_US, + XE_GT_STATS_ID_SVM_64K_BIND_US, + XE_GT_STATS_ID_SVM_2M_BIND_US, /* must be the last entry */ __XE_GT_STATS_NUM_IDS, }; diff --git a/drivers/gpu/drm/xe/xe_gt_topology.c b/drivers/gpu/drm/xe/xe_gt_topology.c index a0baa560dd71..4e61c5e39bcb 100644 --- a/drivers/gpu/drm/xe/xe_gt_topology.c +++ b/drivers/gpu/drm/xe/xe_gt_topology.c @@ -12,6 +12,7 @@ #include "regs/xe_gt_regs.h" #include "xe_assert.h" #include "xe_gt.h" +#include "xe_gt_mcr.h" #include "xe_gt_printk.h" #include "xe_mmio.h" #include "xe_wa.h" @@ -122,6 +123,21 @@ gen_l3_mask_from_pattern(struct xe_device *xe, xe_l3_bank_mask_t dst, } } +bool xe_gt_topology_report_l3(struct xe_gt *gt) +{ + /* + * No known userspace needs/uses the L3 bank mask reported by + * the media GT, and the hardware itself is known to report bogus + * values on several platforms. Only report L3 bank mask as part + * of the media GT's topology on pre-Xe3 platforms since that's + * already part of our ABI. + */ + if (xe_gt_is_media_type(gt) && MEDIA_VER(gt_to_xe(gt)) >= 30) + return false; + + return true; +} + static void load_l3_bank_mask(struct xe_gt *gt, xe_l3_bank_mask_t l3_bank_mask) { @@ -129,16 +145,7 @@ load_l3_bank_mask(struct xe_gt *gt, xe_l3_bank_mask_t l3_bank_mask) struct xe_mmio *mmio = >->mmio; u32 fuse3 = xe_mmio_read32(mmio, MIRROR_FUSE3); - /* - * PTL platforms with media version 30.00 do not provide proper values - * for the media GT's L3 bank registers. Skip the readout since we - * don't have any way to obtain real values. - * - * This may get re-described as an official workaround in the future, - * but there's no tracking number assigned yet so we use a custom - * OOB workaround descriptor. - */ - if (XE_GT_WA(gt, no_media_l3)) + if (!xe_gt_topology_report_l3(gt)) return; if (GRAPHICS_VER(xe) >= 30) { @@ -275,8 +282,9 @@ xe_gt_topology_dump(struct xe_gt *gt, struct drm_printer *p) drm_printf(p, "EU type: %s\n", eu_type_to_str(gt->fuse_topo.eu_type)); - drm_printf(p, "L3 bank mask: %*pb\n", XE_MAX_L3_BANK_MASK_BITS, - gt->fuse_topo.l3_bank_mask); + if (xe_gt_topology_report_l3(gt)) + drm_printf(p, "L3 bank mask: %*pb\n", XE_MAX_L3_BANK_MASK_BITS, + gt->fuse_topo.l3_bank_mask); } /* @@ -328,3 +336,19 @@ bool xe_gt_has_compute_dss(struct xe_gt *gt, unsigned int dss) { return test_bit(dss, gt->fuse_topo.c_dss_mask); } + +bool xe_gt_has_discontiguous_dss_groups(const struct xe_gt *gt) +{ + unsigned int xecore; + int last_group = -1; + u16 group, instance; + + for_each_dss_steering(xecore, gt, group, instance) { + if (last_group != group) { + if (group - last_group > 1) + return true; + last_group = group; + } + } + return false; +} diff --git a/drivers/gpu/drm/xe/xe_gt_topology.h b/drivers/gpu/drm/xe/xe_gt_topology.h index c8140704ad4c..5e62f5949b7b 100644 --- a/drivers/gpu/drm/xe/xe_gt_topology.h +++ b/drivers/gpu/drm/xe/xe_gt_topology.h @@ -47,4 +47,8 @@ xe_gt_topology_has_dss_in_quadrant(struct xe_gt *gt, int quad); bool xe_gt_has_geometry_dss(struct xe_gt *gt, unsigned int dss); bool xe_gt_has_compute_dss(struct xe_gt *gt, unsigned int dss); +bool xe_gt_has_discontiguous_dss_groups(const struct xe_gt *gt); + +bool xe_gt_topology_report_l3(struct xe_gt *gt); + #endif /* _XE_GT_TOPOLOGY_H_ */ diff --git a/drivers/gpu/drm/xe/xe_guc.c b/drivers/gpu/drm/xe/xe_guc.c index 37d06c51180c..00789844ea4d 100644 --- a/drivers/gpu/drm/xe/xe_guc.c +++ b/drivers/gpu/drm/xe/xe_guc.c @@ -74,8 +74,7 @@ static u32 guc_ctl_debug_flags(struct xe_guc *guc) if (!GUC_LOG_LEVEL_IS_VERBOSE(level)) flags |= GUC_LOG_DISABLED; else - flags |= GUC_LOG_LEVEL_TO_VERBOSITY(level) << - GUC_LOG_VERBOSITY_SHIFT; + flags |= FIELD_PREP(GUC_LOG_VERBOSITY, GUC_LOG_LEVEL_TO_VERBOSITY(level)); return flags; } @@ -122,22 +121,14 @@ static u32 guc_ctl_log_params_flags(struct xe_guc *guc) BUILD_BUG_ON(!CAPTURE_BUFFER_SIZE); BUILD_BUG_ON(!IS_ALIGNED(CAPTURE_BUFFER_SIZE, CAPTURE_UNIT)); - BUILD_BUG_ON((CRASH_BUFFER_SIZE / LOG_UNIT - 1) > - (GUC_LOG_CRASH_MASK >> GUC_LOG_CRASH_SHIFT)); - BUILD_BUG_ON((DEBUG_BUFFER_SIZE / LOG_UNIT - 1) > - (GUC_LOG_DEBUG_MASK >> GUC_LOG_DEBUG_SHIFT)); - BUILD_BUG_ON((CAPTURE_BUFFER_SIZE / CAPTURE_UNIT - 1) > - (GUC_LOG_CAPTURE_MASK >> GUC_LOG_CAPTURE_SHIFT)); - flags = GUC_LOG_VALID | GUC_LOG_NOTIFY_ON_HALF_FULL | CAPTURE_FLAG | LOG_FLAG | - ((CRASH_BUFFER_SIZE / LOG_UNIT - 1) << GUC_LOG_CRASH_SHIFT) | - ((DEBUG_BUFFER_SIZE / LOG_UNIT - 1) << GUC_LOG_DEBUG_SHIFT) | - ((CAPTURE_BUFFER_SIZE / CAPTURE_UNIT - 1) << - GUC_LOG_CAPTURE_SHIFT) | - (offset << GUC_LOG_BUF_ADDR_SHIFT); + FIELD_PREP(GUC_LOG_CRASH, CRASH_BUFFER_SIZE / LOG_UNIT - 1) | + FIELD_PREP(GUC_LOG_DEBUG, DEBUG_BUFFER_SIZE / LOG_UNIT - 1) | + FIELD_PREP(GUC_LOG_CAPTURE, CAPTURE_BUFFER_SIZE / CAPTURE_UNIT - 1) | + FIELD_PREP(GUC_LOG_BUF_ADDR, offset); #undef LOG_UNIT #undef LOG_FLAG @@ -150,7 +141,7 @@ static u32 guc_ctl_log_params_flags(struct xe_guc *guc) static u32 guc_ctl_ads_flags(struct xe_guc *guc) { u32 ads = guc_bo_ggtt_addr(guc, guc->ads.bo) >> PAGE_SHIFT; - u32 flags = ads << GUC_ADS_ADDR_SHIFT; + u32 flags = FIELD_PREP(GUC_ADS_ADDR, ads); return flags; } @@ -709,10 +700,6 @@ static int xe_guc_realloc_post_hwconfig(struct xe_guc *guc) if (ret) return ret; - ret = xe_managed_bo_reinit_in_vram(xe, tile, &guc->ct.bo); - if (ret) - return ret; - return 0; } @@ -847,6 +834,10 @@ int xe_guc_init_post_hwconfig(struct xe_guc *guc) if (ret) return ret; + ret = xe_guc_ct_init_post_hwconfig(&guc->ct); + if (ret) + return ret; + guc_init_params_post_hwconfig(guc); ret = xe_guc_submit_init(guc, ~0); @@ -888,9 +879,7 @@ int xe_guc_post_load_init(struct xe_guc *guc) return ret; } - guc->submission_state.enabled = true; - - return 0; + return xe_guc_submit_enable(guc); } int xe_guc_reset(struct xe_guc *guc) @@ -1066,7 +1055,7 @@ static s32 guc_pc_get_cur_freq(struct xe_guc_pc *guc_pc) #endif #define GUC_LOAD_TIME_WARN_MS 200 -static void guc_wait_ucode(struct xe_guc *guc) +static int guc_wait_ucode(struct xe_guc *guc) { struct xe_gt *gt = guc_to_gt(guc); struct xe_mmio *mmio = >->mmio; @@ -1173,7 +1162,7 @@ static void guc_wait_ucode(struct xe_guc *guc) break; } - xe_device_declare_wedged(gt_to_xe(gt)); + return -EPROTO; } else if (delta_ms > GUC_LOAD_TIME_WARN_MS) { xe_gt_warn(gt, "excessive init time: %lldms! [status = 0x%08X, timeouts = %d]\n", delta_ms, status, count); @@ -1185,7 +1174,10 @@ static void guc_wait_ucode(struct xe_guc *guc) delta_ms, xe_guc_pc_get_act_freq(guc_pc), guc_pc_get_cur_freq(guc_pc), before_freq, status, count); } + + return 0; } +ALLOW_ERROR_INJECTION(guc_wait_ucode, ERRNO); static int __xe_guc_upload(struct xe_guc *guc) { @@ -1217,14 +1209,16 @@ static int __xe_guc_upload(struct xe_guc *guc) goto out; /* Wait for authentication */ - guc_wait_ucode(guc); + ret = guc_wait_ucode(guc); + if (ret) + goto out; xe_uc_fw_change_status(&guc->fw, XE_UC_FIRMWARE_RUNNING); return 0; out: xe_uc_fw_change_status(&guc->fw, XE_UC_FIRMWARE_LOAD_FAIL); - return 0 /* FIXME: ret, don't want to stop load currently */; + return ret; } static int vf_guc_min_load_for_hwconfig(struct xe_guc *guc) @@ -1602,7 +1596,7 @@ void xe_guc_sanitize(struct xe_guc *guc) { xe_uc_fw_sanitize(&guc->fw); xe_guc_ct_disable(&guc->ct); - guc->submission_state.enabled = false; + xe_guc_submit_disable(guc); } int xe_guc_reset_prepare(struct xe_guc *guc) @@ -1695,3 +1689,7 @@ void xe_guc_declare_wedged(struct xe_guc *guc) xe_guc_ct_stop(&guc->ct); xe_guc_submit_wedge(guc); } + +#if IS_ENABLED(CONFIG_DRM_XE_KUNIT_TEST) +#include "tests/xe_guc_g2g_test.c" +#endif diff --git a/drivers/gpu/drm/xe/xe_guc.h b/drivers/gpu/drm/xe/xe_guc.h index 22cf019a11bf..1cca05967e62 100644 --- a/drivers/gpu/drm/xe/xe_guc.h +++ b/drivers/gpu/drm/xe/xe_guc.h @@ -53,6 +53,10 @@ void xe_guc_stop(struct xe_guc *guc); int xe_guc_start(struct xe_guc *guc); void xe_guc_declare_wedged(struct xe_guc *guc); +#if IS_ENABLED(CONFIG_DRM_XE_KUNIT_TEST) +int xe_guc_g2g_test_notification(struct xe_guc *guc, u32 *payload, u32 len); +#endif + static inline u16 xe_engine_class_to_guc_class(enum xe_engine_class class) { switch (class) { diff --git a/drivers/gpu/drm/xe/xe_guc_ads.c b/drivers/gpu/drm/xe/xe_guc_ads.c index 5631722f34f5..58e0b0294a5b 100644 --- a/drivers/gpu/drm/xe/xe_guc_ads.c +++ b/drivers/gpu/drm/xe/xe_guc_ads.c @@ -339,7 +339,7 @@ static void guc_waklv_init(struct xe_guc_ads *ads) if (XE_GT_WA(gt, 13011645652)) { u32 data = 0xC40; - guc_waklv_enable(ads, &data, sizeof(data) / sizeof(u32), &offset, &remain, + guc_waklv_enable(ads, &data, 1, &offset, &remain, GUC_WA_KLV_NP_RD_WRITE_TO_CLEAR_RCSM_AT_CGP_LATE_RESTORE); } @@ -355,7 +355,7 @@ static void guc_waklv_init(struct xe_guc_ads *ads) 0x0, 0xF, }; - guc_waklv_enable(ads, data, sizeof(data) / sizeof(u32), &offset, &remain, + guc_waklv_enable(ads, data, ARRAY_SIZE(data), &offset, &remain, GUC_WA_KLV_RESTORE_UNSAVED_MEDIA_CONTROL_REG); } diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c index 848065a25c44..18f6327bf552 100644 --- a/drivers/gpu/drm/xe/xe_guc_ct.c +++ b/drivers/gpu/drm/xe/xe_guc_ct.c @@ -39,6 +39,8 @@ static void receive_g2h(struct xe_guc_ct *ct); static void g2h_worker_func(struct work_struct *w); static void safe_mode_worker_func(struct work_struct *w); static void ct_exit_safe_mode(struct xe_guc_ct *ct); +static void guc_ct_change_state(struct xe_guc_ct *ct, + enum xe_guc_ct_state state); #if IS_ENABLED(CONFIG_DRM_XE_DEBUG) enum { @@ -252,6 +254,13 @@ int xe_guc_ct_init_noalloc(struct xe_guc_ct *ct) } ALLOW_ERROR_INJECTION(xe_guc_ct_init_noalloc, ERRNO); /* See xe_pci_probe() */ +static void guc_action_disable_ct(void *arg) +{ + struct xe_guc_ct *ct = arg; + + guc_ct_change_state(ct, XE_GUC_CT_STATE_DISABLED); +} + int xe_guc_ct_init(struct xe_guc_ct *ct) { struct xe_device *xe = ct_to_xe(ct); @@ -268,10 +277,39 @@ int xe_guc_ct_init(struct xe_guc_ct *ct) return PTR_ERR(bo); ct->bo = bo; - return 0; + + return devm_add_action_or_reset(xe->drm.dev, guc_action_disable_ct, ct); } ALLOW_ERROR_INJECTION(xe_guc_ct_init, ERRNO); /* See xe_pci_probe() */ +/** + * xe_guc_ct_init_post_hwconfig - Reinitialize the GuC CTB in VRAM + * @ct: the &xe_guc_ct + * + * Allocate a new BO in VRAM and free the previous BO that was allocated + * in system memory (SMEM). Applicable only for DGFX products. + * + * Return: 0 on success, or a negative errno on failure. + */ +int xe_guc_ct_init_post_hwconfig(struct xe_guc_ct *ct) +{ + struct xe_device *xe = ct_to_xe(ct); + struct xe_gt *gt = ct_to_gt(ct); + struct xe_tile *tile = gt_to_tile(gt); + int ret; + + xe_assert(xe, !xe_guc_ct_enabled(ct)); + + if (IS_DGFX(xe)) { + ret = xe_managed_bo_reinit_in_vram(xe, tile, &ct->bo); + if (ret) + return ret; + } + + devm_remove_action(xe->drm.dev, guc_action_disable_ct, ct); + return devm_add_action_or_reset(xe->drm.dev, guc_action_disable_ct, ct); +} + #define desc_read(xe_, guc_ctb__, field_) \ xe_map_rd_field(xe_, &guc_ctb__->desc, 0, \ struct guc_ct_buffer_desc, field_) @@ -1040,11 +1078,15 @@ static bool retry_failure(struct xe_guc_ct *ct, int ret) return true; } +#define GUC_SEND_RETRY_LIMIT 50 +#define GUC_SEND_RETRY_MSLEEP 5 + static int guc_ct_send_recv(struct xe_guc_ct *ct, const u32 *action, u32 len, u32 *response_buffer, bool no_fail) { struct xe_gt *gt = ct_to_gt(ct); struct g2h_fence g2h_fence; + unsigned int retries = 0; int ret = 0; /* @@ -1109,6 +1151,12 @@ retry_same_fence: xe_gt_dbg(gt, "H2G action %#x retrying: reason %#x\n", action[0], g2h_fence.reason); mutex_unlock(&ct->lock); + if (++retries > GUC_SEND_RETRY_LIMIT) { + xe_gt_err(gt, "H2G action %#x reached retry limit=%u, aborting\n", + action[0], GUC_SEND_RETRY_LIMIT); + return -ELOOP; + } + msleep(GUC_SEND_RETRY_MSLEEP * retries); goto retry; } if (g2h_fence.fail) { @@ -1438,6 +1486,11 @@ static int process_g2h_msg(struct xe_guc_ct *ct, u32 *msg, u32 len) case XE_GUC_ACTION_NOTIFY_EXCEPTION: ret = guc_crash_process_msg(ct, action); break; +#if IS_ENABLED(CONFIG_DRM_XE_KUNIT_TEST) + case XE_GUC_ACTION_TEST_G2G_RECV: + ret = xe_guc_g2g_test_notification(guc, payload, adj_len); + break; +#endif default: xe_gt_err(gt, "unexpected G2H action 0x%04x\n", action); } diff --git a/drivers/gpu/drm/xe/xe_guc_ct.h b/drivers/gpu/drm/xe/xe_guc_ct.h index 18d4225e6502..cf41210ab30a 100644 --- a/drivers/gpu/drm/xe/xe_guc_ct.h +++ b/drivers/gpu/drm/xe/xe_guc_ct.h @@ -13,6 +13,7 @@ struct xe_device; int xe_guc_ct_init_noalloc(struct xe_guc_ct *ct); int xe_guc_ct_init(struct xe_guc_ct *ct); +int xe_guc_ct_init_post_hwconfig(struct xe_guc_ct *ct); int xe_guc_ct_enable(struct xe_guc_ct *ct); void xe_guc_ct_disable(struct xe_guc_ct *ct); void xe_guc_ct_stop(struct xe_guc_ct *ct); diff --git a/drivers/gpu/drm/xe/xe_guc_engine_activity.c b/drivers/gpu/drm/xe/xe_guc_engine_activity.c index 92e1f9f41b8c..2b99c1ebdd58 100644 --- a/drivers/gpu/drm/xe/xe_guc_engine_activity.c +++ b/drivers/gpu/drm/xe/xe_guc_engine_activity.c @@ -94,16 +94,17 @@ static int allocate_engine_activity_buffers(struct xe_guc *guc, struct xe_tile *tile = gt_to_tile(gt); struct xe_bo *bo, *metadata_bo; - metadata_bo = xe_bo_create_pin_map(gt_to_xe(gt), tile, NULL, PAGE_ALIGN(metadata_size), - ttm_bo_type_kernel, XE_BO_FLAG_SYSTEM | - XE_BO_FLAG_GGTT | XE_BO_FLAG_GGTT_INVALIDATE); + metadata_bo = xe_bo_create_pin_map_novm(gt_to_xe(gt), tile, PAGE_ALIGN(metadata_size), + ttm_bo_type_kernel, XE_BO_FLAG_SYSTEM | + XE_BO_FLAG_GGTT | XE_BO_FLAG_GGTT_INVALIDATE, + false); if (IS_ERR(metadata_bo)) return PTR_ERR(metadata_bo); - bo = xe_bo_create_pin_map(gt_to_xe(gt), tile, NULL, PAGE_ALIGN(size), - ttm_bo_type_kernel, XE_BO_FLAG_VRAM_IF_DGFX(tile) | - XE_BO_FLAG_GGTT | XE_BO_FLAG_GGTT_INVALIDATE); + bo = xe_bo_create_pin_map_novm(gt_to_xe(gt), tile, PAGE_ALIGN(size), + ttm_bo_type_kernel, XE_BO_FLAG_VRAM_IF_DGFX(tile) | + XE_BO_FLAG_GGTT | XE_BO_FLAG_GGTT_INVALIDATE, false); if (IS_ERR(bo)) { xe_bo_unpin_map_no_vm(metadata_bo); diff --git a/drivers/gpu/drm/xe/xe_guc_exec_queue_types.h b/drivers/gpu/drm/xe/xe_guc_exec_queue_types.h index a3f421e2adc0..c30c0e3ccbbb 100644 --- a/drivers/gpu/drm/xe/xe_guc_exec_queue_types.h +++ b/drivers/gpu/drm/xe/xe_guc_exec_queue_types.h @@ -35,8 +35,8 @@ struct xe_guc_exec_queue { struct xe_sched_msg static_msgs[MAX_STATIC_MSG_TYPE]; /** @lr_tdr: long running TDR worker */ struct work_struct lr_tdr; - /** @fini_async: do final fini async from this worker */ - struct work_struct fini_async; + /** @destroy_async: do final destroy async from this worker */ + struct work_struct destroy_async; /** @resume_time: time of last resume */ u64 resume_time; /** @state: GuC specific state for this xe_exec_queue */ diff --git a/drivers/gpu/drm/xe/xe_guc_fwif.h b/drivers/gpu/drm/xe/xe_guc_fwif.h index 0508f1064178..50c4c2406132 100644 --- a/drivers/gpu/drm/xe/xe_guc_fwif.h +++ b/drivers/gpu/drm/xe/xe_guc_fwif.h @@ -15,6 +15,7 @@ #define G2H_LEN_DW_SCHED_CONTEXT_MODE_SET 4 #define G2H_LEN_DW_DEREGISTER_CONTEXT 3 #define G2H_LEN_DW_TLB_INVALIDATE 3 +#define G2H_LEN_DW_G2G_NOTIFY_MIN 3 #define GUC_ID_MAX 65535 #define GUC_ID_UNKNOWN 0xffffffff @@ -65,6 +66,7 @@ struct guc_ctxt_registration_info { u32 hwlrca_hi; }; #define CONTEXT_REGISTRATION_FLAG_KMD BIT(0) +#define CONTEXT_REGISTRATION_FLAG_TYPE GENMASK(2, 1) /* 32-bit KLV structure as used by policy updates and others */ struct guc_klv_generic_dw_t { @@ -89,13 +91,10 @@ struct guc_update_exec_queue_policy { #define GUC_LOG_NOTIFY_ON_HALF_FULL BIT(1) #define GUC_LOG_CAPTURE_ALLOC_UNITS BIT(2) #define GUC_LOG_LOG_ALLOC_UNITS BIT(3) -#define GUC_LOG_CRASH_SHIFT 4 -#define GUC_LOG_CRASH_MASK (0x3 << GUC_LOG_CRASH_SHIFT) -#define GUC_LOG_DEBUG_SHIFT 6 -#define GUC_LOG_DEBUG_MASK (0xF << GUC_LOG_DEBUG_SHIFT) -#define GUC_LOG_CAPTURE_SHIFT 10 -#define GUC_LOG_CAPTURE_MASK (0x3 << GUC_LOG_CAPTURE_SHIFT) -#define GUC_LOG_BUF_ADDR_SHIFT 12 +#define GUC_LOG_CRASH REG_GENMASK(5, 4) +#define GUC_LOG_DEBUG REG_GENMASK(9, 6) +#define GUC_LOG_CAPTURE REG_GENMASK(11, 10) +#define GUC_LOG_BUF_ADDR REG_GENMASK(31, 12) #define GUC_CTL_WA 1 #define GUC_WA_GAM_CREDITS BIT(10) @@ -117,21 +116,14 @@ struct guc_update_exec_queue_policy { #define GUC_CTL_DISABLE_SCHEDULER BIT(14) #define GUC_CTL_DEBUG 3 -#define GUC_LOG_VERBOSITY_SHIFT 0 -#define GUC_LOG_VERBOSITY_LOW (0 << GUC_LOG_VERBOSITY_SHIFT) -#define GUC_LOG_VERBOSITY_MED (1 << GUC_LOG_VERBOSITY_SHIFT) -#define GUC_LOG_VERBOSITY_HIGH (2 << GUC_LOG_VERBOSITY_SHIFT) -#define GUC_LOG_VERBOSITY_ULTRA (3 << GUC_LOG_VERBOSITY_SHIFT) -#define GUC_LOG_VERBOSITY_MIN 0 +#define GUC_LOG_VERBOSITY REG_GENMASK(1, 0) #define GUC_LOG_VERBOSITY_MAX 3 -#define GUC_LOG_VERBOSITY_MASK 0x0000000f -#define GUC_LOG_DESTINATION_MASK (3 << 4) -#define GUC_LOG_DISABLED (1 << 6) -#define GUC_PROFILE_ENABLED (1 << 7) +#define GUC_LOG_DESTINATION REG_GENMASK(5, 4) +#define GUC_LOG_DISABLED BIT(6) +#define GUC_PROFILE_ENABLED BIT(7) #define GUC_CTL_ADS 4 -#define GUC_ADS_ADDR_SHIFT 1 -#define GUC_ADS_ADDR_MASK (0xFFFFF << GUC_ADS_ADDR_SHIFT) +#define GUC_ADS_ADDR REG_GENMASK(21, 1) #define GUC_CTL_DEVID 5 diff --git a/drivers/gpu/drm/xe/xe_guc_log.h b/drivers/gpu/drm/xe/xe_guc_log.h index f1e2b0be90a9..98a47ac42b08 100644 --- a/drivers/gpu/drm/xe/xe_guc_log.h +++ b/drivers/gpu/drm/xe/xe_guc_log.h @@ -17,7 +17,7 @@ struct xe_device; #define DEBUG_BUFFER_SIZE SZ_8M #define CAPTURE_BUFFER_SIZE SZ_2M #else -#define CRASH_BUFFER_SIZE SZ_8K +#define CRASH_BUFFER_SIZE SZ_16K #define DEBUG_BUFFER_SIZE SZ_64K #define CAPTURE_BUFFER_SIZE SZ_1M #endif diff --git a/drivers/gpu/drm/xe/xe_guc_pc.c b/drivers/gpu/drm/xe/xe_guc_pc.c index 88557e86d637..53fdf59524c4 100644 --- a/drivers/gpu/drm/xe/xe_guc_pc.c +++ b/drivers/gpu/drm/xe/xe_guc_pc.c @@ -79,6 +79,11 @@ * Xe driver enables SLPC with all of its defaults features and frequency * selection, which varies per platform. * + * Power profiles add another level of control to SLPC. When power saving + * profile is chosen, SLPC will use conservative thresholds to ramp frequency, + * thus saving power. Base profile is default and ensures balanced performance + * for any workload. + * * Render-C States: * ================ * @@ -1171,6 +1176,61 @@ static int pc_action_set_strategy(struct xe_guc_pc *pc, u32 val) return ret; } +static const char *power_profile_to_string(struct xe_guc_pc *pc) +{ + switch (pc->power_profile) { + case SLPC_POWER_PROFILE_BASE: + return "base"; + case SLPC_POWER_PROFILE_POWER_SAVING: + return "power_saving"; + default: + return "invalid"; + } +} + +void xe_guc_pc_get_power_profile(struct xe_guc_pc *pc, char *profile) +{ + switch (pc->power_profile) { + case SLPC_POWER_PROFILE_BASE: + sprintf(profile, "[%s] %s\n", "base", "power_saving"); + break; + case SLPC_POWER_PROFILE_POWER_SAVING: + sprintf(profile, "%s [%s]\n", "base", "power_saving"); + break; + default: + sprintf(profile, "invalid"); + } +} + +int xe_guc_pc_set_power_profile(struct xe_guc_pc *pc, const char *buf) +{ + int ret = 0; + u32 val; + + if (strncmp("base", buf, strlen("base")) == 0) + val = SLPC_POWER_PROFILE_BASE; + else if (strncmp("power_saving", buf, strlen("power_saving")) == 0) + val = SLPC_POWER_PROFILE_POWER_SAVING; + else + return -EINVAL; + + guard(mutex)(&pc->freq_lock); + xe_pm_runtime_get_noresume(pc_to_xe(pc)); + + ret = pc_action_set_param(pc, + SLPC_PARAM_POWER_PROFILE, + val); + if (ret) + xe_gt_err_once(pc_to_gt(pc), "Failed to set power profile to %d: %pe\n", + val, ERR_PTR(ret)); + else + pc->power_profile = val; + + xe_pm_runtime_put(pc_to_xe(pc)); + + return ret; +} + /** * xe_guc_pc_start - Start GuC's Power Conservation component * @pc: Xe_GuC_PC instance @@ -1249,6 +1309,11 @@ int xe_guc_pc_start(struct xe_guc_pc *pc) /* Enable SLPC Optimized Strategy for compute */ ret = pc_action_set_strategy(pc, SLPC_OPTIMIZED_STRATEGY_COMPUTE); + /* Set cached value of power_profile */ + ret = xe_guc_pc_set_power_profile(pc, power_profile_to_string(pc)); + if (unlikely(ret)) + xe_gt_err(gt, "Failed to set SLPC power profile: %pe\n", ERR_PTR(ret)); + out: xe_force_wake_put(gt_to_fw(gt), fw_ref); return ret; @@ -1327,6 +1392,8 @@ int xe_guc_pc_init(struct xe_guc_pc *pc) pc->bo = bo; + pc->power_profile = SLPC_POWER_PROFILE_BASE; + return devm_add_action_or_reset(xe->drm.dev, xe_guc_pc_fini_hw, pc); } diff --git a/drivers/gpu/drm/xe/xe_guc_pc.h b/drivers/gpu/drm/xe/xe_guc_pc.h index 52ecdd5ddbff..0e31396f103c 100644 --- a/drivers/gpu/drm/xe/xe_guc_pc.h +++ b/drivers/gpu/drm/xe/xe_guc_pc.h @@ -31,6 +31,8 @@ int xe_guc_pc_get_min_freq(struct xe_guc_pc *pc, u32 *freq); int xe_guc_pc_set_min_freq(struct xe_guc_pc *pc, u32 freq); int xe_guc_pc_get_max_freq(struct xe_guc_pc *pc, u32 *freq); int xe_guc_pc_set_max_freq(struct xe_guc_pc *pc, u32 freq); +int xe_guc_pc_set_power_profile(struct xe_guc_pc *pc, const char *buf); +void xe_guc_pc_get_power_profile(struct xe_guc_pc *pc, char *profile); enum xe_gt_idle_state xe_guc_pc_c_status(struct xe_guc_pc *pc); u64 xe_guc_pc_rc6_residency(struct xe_guc_pc *pc); diff --git a/drivers/gpu/drm/xe/xe_guc_pc_types.h b/drivers/gpu/drm/xe/xe_guc_pc_types.h index c02053948a57..5e4ea53fbee6 100644 --- a/drivers/gpu/drm/xe/xe_guc_pc_types.h +++ b/drivers/gpu/drm/xe/xe_guc_pc_types.h @@ -37,6 +37,8 @@ struct xe_guc_pc { struct mutex freq_lock; /** @freq_ready: Only handle freq changes, if they are really ready */ bool freq_ready; + /** @power_profile: Base or power_saving profile */ + u32 power_profile; }; #endif /* _XE_GUC_PC_TYPES_H_ */ diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c index 1185b23b1384..53024eb5670b 100644 --- a/drivers/gpu/drm/xe/xe_guc_submit.c +++ b/drivers/gpu/drm/xe/xe_guc_submit.c @@ -32,6 +32,7 @@ #include "xe_guc_ct.h" #include "xe_guc_exec_queue_types.h" #include "xe_guc_id_mgr.h" +#include "xe_guc_klv_helpers.h" #include "xe_guc_submit_types.h" #include "xe_hw_engine.h" #include "xe_hw_fence.h" @@ -316,6 +317,71 @@ int xe_guc_submit_init(struct xe_guc *guc, unsigned int num_ids) return drmm_add_action_or_reset(&xe->drm, guc_submit_fini, guc); } +/* + * Given that we want to guarantee enough RCS throughput to avoid missing + * frames, we set the yield policy to 20% of each 80ms interval. + */ +#define RC_YIELD_DURATION 80 /* in ms */ +#define RC_YIELD_RATIO 20 /* in percent */ +static u32 *emit_render_compute_yield_klv(u32 *emit) +{ + *emit++ = PREP_GUC_KLV_TAG(SCHEDULING_POLICIES_RENDER_COMPUTE_YIELD); + *emit++ = RC_YIELD_DURATION; + *emit++ = RC_YIELD_RATIO; + + return emit; +} + +#define SCHEDULING_POLICY_MAX_DWORDS 16 +static int guc_init_global_schedule_policy(struct xe_guc *guc) +{ + u32 data[SCHEDULING_POLICY_MAX_DWORDS]; + u32 *emit = data; + u32 count = 0; + int ret; + + if (GUC_SUBMIT_VER(guc) < MAKE_GUC_VER(1, 1, 0)) + return 0; + + *emit++ = XE_GUC_ACTION_UPDATE_SCHEDULING_POLICIES_KLV; + + if (CCS_MASK(guc_to_gt(guc))) + emit = emit_render_compute_yield_klv(emit); + + count = emit - data; + if (count > 1) { + xe_assert(guc_to_xe(guc), count <= SCHEDULING_POLICY_MAX_DWORDS); + + ret = xe_guc_ct_send_block(&guc->ct, data, count); + if (ret < 0) { + xe_gt_err(guc_to_gt(guc), + "failed to enable GuC scheduling policies: %pe\n", + ERR_PTR(ret)); + return ret; + } + } + + return 0; +} + +int xe_guc_submit_enable(struct xe_guc *guc) +{ + int ret; + + ret = guc_init_global_schedule_policy(guc); + if (ret) + return ret; + + guc->submission_state.enabled = true; + + return 0; +} + +void xe_guc_submit_disable(struct xe_guc *guc) +{ + guc->submission_state.enabled = false; +} + static void __release_guc_id(struct xe_guc *guc, struct xe_exec_queue *q, u32 xa_count) { int i; @@ -558,10 +624,8 @@ static void register_exec_queue(struct xe_exec_queue *q, int ctx_type) info.engine_submit_mask = q->logical_mask; info.hwlrca_lo = lower_32_bits(xe_lrc_descriptor(lrc)); info.hwlrca_hi = upper_32_bits(xe_lrc_descriptor(lrc)); - info.flags = CONTEXT_REGISTRATION_FLAG_KMD; - - if (ctx_type != GUC_CONTEXT_NORMAL) - info.flags |= BIT(ctx_type); + info.flags = CONTEXT_REGISTRATION_FLAG_KMD | + FIELD_PREP(CONTEXT_REGISTRATION_FLAG_TYPE, ctx_type); if (xe_exec_queue_is_parallel(q)) { u64 ggtt_addr = xe_lrc_parallel_ggtt_addr(lrc); @@ -1355,48 +1419,57 @@ rearm: return DRM_GPU_SCHED_STAT_NO_HANG; } -static void __guc_exec_queue_fini_async(struct work_struct *w) +static void guc_exec_queue_fini(struct xe_exec_queue *q) +{ + struct xe_guc_exec_queue *ge = q->guc; + struct xe_guc *guc = exec_queue_to_guc(q); + + release_guc_id(guc, q); + xe_sched_entity_fini(&ge->entity); + xe_sched_fini(&ge->sched); + + /* + * RCU free due sched being exported via DRM scheduler fences + * (timeline name). + */ + kfree_rcu(ge, rcu); +} + +static void __guc_exec_queue_destroy_async(struct work_struct *w) { struct xe_guc_exec_queue *ge = - container_of(w, struct xe_guc_exec_queue, fini_async); + container_of(w, struct xe_guc_exec_queue, destroy_async); struct xe_exec_queue *q = ge->q; struct xe_guc *guc = exec_queue_to_guc(q); xe_pm_runtime_get(guc_to_xe(guc)); trace_xe_exec_queue_destroy(q); - release_guc_id(guc, q); if (xe_exec_queue_is_lr(q)) cancel_work_sync(&ge->lr_tdr); /* Confirm no work left behind accessing device structures */ cancel_delayed_work_sync(&ge->sched.base.work_tdr); - xe_sched_entity_fini(&ge->entity); - xe_sched_fini(&ge->sched); - /* - * RCU free due sched being exported via DRM scheduler fences - * (timeline name). - */ - kfree_rcu(ge, rcu); xe_exec_queue_fini(q); + xe_pm_runtime_put(guc_to_xe(guc)); } -static void guc_exec_queue_fini_async(struct xe_exec_queue *q) +static void guc_exec_queue_destroy_async(struct xe_exec_queue *q) { struct xe_guc *guc = exec_queue_to_guc(q); struct xe_device *xe = guc_to_xe(guc); - INIT_WORK(&q->guc->fini_async, __guc_exec_queue_fini_async); + INIT_WORK(&q->guc->destroy_async, __guc_exec_queue_destroy_async); /* We must block on kernel engines so slabs are empty on driver unload */ if (q->flags & EXEC_QUEUE_FLAG_PERMANENT || exec_queue_wedged(q)) - __guc_exec_queue_fini_async(&q->guc->fini_async); + __guc_exec_queue_destroy_async(&q->guc->destroy_async); else - queue_work(xe->destroy_wq, &q->guc->fini_async); + queue_work(xe->destroy_wq, &q->guc->destroy_async); } -static void __guc_exec_queue_fini(struct xe_guc *guc, struct xe_exec_queue *q) +static void __guc_exec_queue_destroy(struct xe_guc *guc, struct xe_exec_queue *q) { /* * Might be done from within the GPU scheduler, need to do async as we @@ -1405,7 +1478,7 @@ static void __guc_exec_queue_fini(struct xe_guc *guc, struct xe_exec_queue *q) * this we and don't really care when everything is fini'd, just that it * is. */ - guc_exec_queue_fini_async(q); + guc_exec_queue_destroy_async(q); } static void __guc_exec_queue_process_msg_cleanup(struct xe_sched_msg *msg) @@ -1419,7 +1492,7 @@ static void __guc_exec_queue_process_msg_cleanup(struct xe_sched_msg *msg) if (exec_queue_registered(q)) disable_scheduling_deregister(guc, q); else - __guc_exec_queue_fini(guc, q); + __guc_exec_queue_destroy(guc, q); } static bool guc_exec_queue_allowed_to_change_state(struct xe_exec_queue *q) @@ -1652,14 +1725,14 @@ static bool guc_exec_queue_try_add_msg(struct xe_exec_queue *q, #define STATIC_MSG_CLEANUP 0 #define STATIC_MSG_SUSPEND 1 #define STATIC_MSG_RESUME 2 -static void guc_exec_queue_fini(struct xe_exec_queue *q) +static void guc_exec_queue_destroy(struct xe_exec_queue *q) { struct xe_sched_msg *msg = q->guc->static_msgs + STATIC_MSG_CLEANUP; if (!(q->flags & EXEC_QUEUE_FLAG_PERMANENT) && !exec_queue_wedged(q)) guc_exec_queue_add_msg(q, msg, CLEANUP); else - __guc_exec_queue_fini(exec_queue_to_guc(q), q); + __guc_exec_queue_destroy(exec_queue_to_guc(q), q); } static int guc_exec_queue_set_priority(struct xe_exec_queue *q, @@ -1789,6 +1862,7 @@ static const struct xe_exec_queue_ops guc_exec_queue_ops = { .init = guc_exec_queue_init, .kill = guc_exec_queue_kill, .fini = guc_exec_queue_fini, + .destroy = guc_exec_queue_destroy, .set_priority = guc_exec_queue_set_priority, .set_timeslice = guc_exec_queue_set_timeslice, .set_preempt_timeout = guc_exec_queue_set_preempt_timeout, @@ -1810,7 +1884,7 @@ static void guc_exec_queue_stop(struct xe_guc *guc, struct xe_exec_queue *q) if (exec_queue_extra_ref(q) || xe_exec_queue_is_lr(q)) xe_exec_queue_put(q); else if (exec_queue_destroyed(q)) - __guc_exec_queue_fini(guc, q); + __guc_exec_queue_destroy(guc, q); } if (q->guc->suspend_pending) { set_exec_queue_suspended(q); @@ -2029,7 +2103,7 @@ g2h_exec_queue_lookup(struct xe_guc *guc, u32 guc_id) q = xa_load(&guc->submission_state.exec_queue_lookup, guc_id); if (unlikely(!q)) { - xe_gt_err(gt, "Not engine present for guc_id %u\n", guc_id); + xe_gt_err(gt, "No exec queue found for guc_id %u\n", guc_id); return NULL; } @@ -2139,7 +2213,7 @@ static void handle_deregister_done(struct xe_guc *guc, struct xe_exec_queue *q) if (exec_queue_extra_ref(q) || xe_exec_queue_is_lr(q)) xe_exec_queue_put(q); else - __guc_exec_queue_fini(guc, q); + __guc_exec_queue_destroy(guc, q); } int xe_guc_deregister_done_handler(struct xe_guc *guc, u32 *msg, u32 len) @@ -2528,7 +2602,7 @@ static void guc_exec_queue_print(struct xe_exec_queue *q, struct drm_printer *p) } /** - * xe_guc_register_exec_queue - Register exec queue for a given context type. + * xe_guc_register_vf_exec_queue - Register exec queue for a given context type. * @q: Execution queue * @ctx_type: Type of the context * @@ -2539,15 +2613,17 @@ static void guc_exec_queue_print(struct xe_exec_queue *q, struct drm_printer *p) * * Returns - None. */ -void xe_guc_register_exec_queue(struct xe_exec_queue *q, int ctx_type) +void xe_guc_register_vf_exec_queue(struct xe_exec_queue *q, int ctx_type) { struct xe_guc *guc = exec_queue_to_guc(q); struct xe_device *xe = guc_to_xe(guc); + struct xe_gt *gt = guc_to_gt(guc); - xe_assert(xe, IS_SRIOV_VF(xe)); - xe_assert(xe, !IS_DGFX(xe)); - xe_assert(xe, (ctx_type > GUC_CONTEXT_NORMAL && - ctx_type < GUC_CONTEXT_COUNT)); + xe_gt_assert(gt, IS_SRIOV_VF(xe)); + xe_gt_assert(gt, !IS_DGFX(xe)); + xe_gt_assert(gt, ctx_type == GUC_CONTEXT_COMPRESSION_SAVE || + ctx_type == GUC_CONTEXT_COMPRESSION_RESTORE); + xe_gt_assert(gt, GUC_SUBMIT_VER(guc) >= MAKE_GUC_VER(1, 23, 0)); register_exec_queue(q, ctx_type); enable_scheduling(q); diff --git a/drivers/gpu/drm/xe/xe_guc_submit.h b/drivers/gpu/drm/xe/xe_guc_submit.h index 6b5df5d0956b..78c3f07e31a0 100644 --- a/drivers/gpu/drm/xe/xe_guc_submit.h +++ b/drivers/gpu/drm/xe/xe_guc_submit.h @@ -13,6 +13,8 @@ struct xe_exec_queue; struct xe_guc; int xe_guc_submit_init(struct xe_guc *guc, unsigned int num_ids); +int xe_guc_submit_enable(struct xe_guc *guc); +void xe_guc_submit_disable(struct xe_guc *guc); int xe_guc_submit_reset_prepare(struct xe_guc *guc); void xe_guc_submit_reset_wait(struct xe_guc *guc); @@ -46,7 +48,7 @@ xe_guc_exec_queue_snapshot_print(struct xe_guc_submit_exec_queue_snapshot *snaps void xe_guc_exec_queue_snapshot_free(struct xe_guc_submit_exec_queue_snapshot *snapshot); void xe_guc_submit_print(struct xe_guc *guc, struct drm_printer *p); -void xe_guc_register_exec_queue(struct xe_exec_queue *q, int ctx_type); +void xe_guc_register_vf_exec_queue(struct xe_exec_queue *q, int ctx_type); int xe_guc_contexts_hwsp_rebase(struct xe_guc *guc, void *scratch); diff --git a/drivers/gpu/drm/xe/xe_hmm.c b/drivers/gpu/drm/xe/xe_hmm.c deleted file mode 100644 index 57b71956ddf4..000000000000 --- a/drivers/gpu/drm/xe/xe_hmm.c +++ /dev/null @@ -1,325 +0,0 @@ -// SPDX-License-Identifier: MIT -/* - * Copyright © 2024 Intel Corporation - */ - -#include <linux/scatterlist.h> -#include <linux/mmu_notifier.h> -#include <linux/dma-mapping.h> -#include <linux/memremap.h> -#include <linux/swap.h> -#include <linux/hmm.h> -#include <linux/mm.h> -#include "xe_hmm.h" -#include "xe_vm.h" -#include "xe_bo.h" - -static u64 xe_npages_in_range(unsigned long start, unsigned long end) -{ - return (end - start) >> PAGE_SHIFT; -} - -static int xe_alloc_sg(struct xe_device *xe, struct sg_table *st, - struct hmm_range *range, struct rw_semaphore *notifier_sem) -{ - unsigned long i, npages, hmm_pfn; - unsigned long num_chunks = 0; - int ret; - - /* HMM docs says this is needed. */ - ret = down_read_interruptible(notifier_sem); - if (ret) - return ret; - - if (mmu_interval_read_retry(range->notifier, range->notifier_seq)) { - up_read(notifier_sem); - return -EAGAIN; - } - - npages = xe_npages_in_range(range->start, range->end); - for (i = 0; i < npages;) { - unsigned long len; - - hmm_pfn = range->hmm_pfns[i]; - xe_assert(xe, hmm_pfn & HMM_PFN_VALID); - - len = 1UL << hmm_pfn_to_map_order(hmm_pfn); - - /* If order > 0 the page may extend beyond range->start */ - len -= (hmm_pfn & ~HMM_PFN_FLAGS) & (len - 1); - i += len; - num_chunks++; - } - up_read(notifier_sem); - - return sg_alloc_table(st, num_chunks, GFP_KERNEL); -} - -/** - * xe_build_sg() - build a scatter gather table for all the physical pages/pfn - * in a hmm_range. dma-map pages if necessary. dma-address is save in sg table - * and will be used to program GPU page table later. - * @xe: the xe device who will access the dma-address in sg table - * @range: the hmm range that we build the sg table from. range->hmm_pfns[] - * has the pfn numbers of pages that back up this hmm address range. - * @st: pointer to the sg table. - * @notifier_sem: The xe notifier lock. - * @write: whether we write to this range. This decides dma map direction - * for system pages. If write we map it bi-diretional; otherwise - * DMA_TO_DEVICE - * - * All the contiguous pfns will be collapsed into one entry in - * the scatter gather table. This is for the purpose of efficiently - * programming GPU page table. - * - * The dma_address in the sg table will later be used by GPU to - * access memory. So if the memory is system memory, we need to - * do a dma-mapping so it can be accessed by GPU/DMA. - * - * FIXME: This function currently only support pages in system - * memory. If the memory is GPU local memory (of the GPU who - * is going to access memory), we need gpu dpa (device physical - * address), and there is no need of dma-mapping. This is TBD. - * - * FIXME: dma-mapping for peer gpu device to access remote gpu's - * memory. Add this when you support p2p - * - * This function allocates the storage of the sg table. It is - * caller's responsibility to free it calling sg_free_table. - * - * Returns 0 if successful; -ENOMEM if fails to allocate memory - */ -static int xe_build_sg(struct xe_device *xe, struct hmm_range *range, - struct sg_table *st, - struct rw_semaphore *notifier_sem, - bool write) -{ - unsigned long npages = xe_npages_in_range(range->start, range->end); - struct device *dev = xe->drm.dev; - struct scatterlist *sgl; - struct page *page; - unsigned long i, j; - - lockdep_assert_held(notifier_sem); - - i = 0; - for_each_sg(st->sgl, sgl, st->nents, j) { - unsigned long hmm_pfn, size; - - hmm_pfn = range->hmm_pfns[i]; - page = hmm_pfn_to_page(hmm_pfn); - xe_assert(xe, !is_device_private_page(page)); - - size = 1UL << hmm_pfn_to_map_order(hmm_pfn); - size -= page_to_pfn(page) & (size - 1); - i += size; - - if (unlikely(j == st->nents - 1)) { - xe_assert(xe, i >= npages); - if (i > npages) - size -= (i - npages); - - sg_mark_end(sgl); - } else { - xe_assert(xe, i < npages); - } - - sg_set_page(sgl, page, size << PAGE_SHIFT, 0); - } - - return dma_map_sgtable(dev, st, write ? DMA_BIDIRECTIONAL : DMA_TO_DEVICE, - DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_NO_KERNEL_MAPPING); -} - -static void xe_hmm_userptr_set_mapped(struct xe_userptr_vma *uvma) -{ - struct xe_userptr *userptr = &uvma->userptr; - struct xe_vm *vm = xe_vma_vm(&uvma->vma); - - lockdep_assert_held_write(&vm->lock); - lockdep_assert_held(&vm->userptr.notifier_lock); - - mutex_lock(&userptr->unmap_mutex); - xe_assert(vm->xe, !userptr->mapped); - userptr->mapped = true; - mutex_unlock(&userptr->unmap_mutex); -} - -void xe_hmm_userptr_unmap(struct xe_userptr_vma *uvma) -{ - struct xe_userptr *userptr = &uvma->userptr; - struct xe_vma *vma = &uvma->vma; - bool write = !xe_vma_read_only(vma); - struct xe_vm *vm = xe_vma_vm(vma); - struct xe_device *xe = vm->xe; - - if (!lockdep_is_held_type(&vm->userptr.notifier_lock, 0) && - !lockdep_is_held_type(&vm->lock, 0) && - !(vma->gpuva.flags & XE_VMA_DESTROYED)) { - /* Don't unmap in exec critical section. */ - xe_vm_assert_held(vm); - /* Don't unmap while mapping the sg. */ - lockdep_assert_held(&vm->lock); - } - - mutex_lock(&userptr->unmap_mutex); - if (userptr->sg && userptr->mapped) - dma_unmap_sgtable(xe->drm.dev, userptr->sg, - write ? DMA_BIDIRECTIONAL : DMA_TO_DEVICE, 0); - userptr->mapped = false; - mutex_unlock(&userptr->unmap_mutex); -} - -/** - * xe_hmm_userptr_free_sg() - Free the scatter gather table of userptr - * @uvma: the userptr vma which hold the scatter gather table - * - * With function xe_userptr_populate_range, we allocate storage of - * the userptr sg table. This is a helper function to free this - * sg table, and dma unmap the address in the table. - */ -void xe_hmm_userptr_free_sg(struct xe_userptr_vma *uvma) -{ - struct xe_userptr *userptr = &uvma->userptr; - - xe_assert(xe_vma_vm(&uvma->vma)->xe, userptr->sg); - xe_hmm_userptr_unmap(uvma); - sg_free_table(userptr->sg); - userptr->sg = NULL; -} - -/** - * xe_hmm_userptr_populate_range() - Populate physical pages of a virtual - * address range - * - * @uvma: userptr vma which has information of the range to populate. - * @is_mm_mmap_locked: True if mmap_read_lock is already acquired by caller. - * - * This function populate the physical pages of a virtual - * address range. The populated physical pages is saved in - * userptr's sg table. It is similar to get_user_pages but call - * hmm_range_fault. - * - * This function also read mmu notifier sequence # ( - * mmu_interval_read_begin), for the purpose of later - * comparison (through mmu_interval_read_retry). - * - * This must be called with mmap read or write lock held. - * - * This function allocates the storage of the userptr sg table. - * It is caller's responsibility to free it calling sg_free_table. - * - * returns: 0 for success; negative error no on failure - */ -int xe_hmm_userptr_populate_range(struct xe_userptr_vma *uvma, - bool is_mm_mmap_locked) -{ - unsigned long timeout = - jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT); - unsigned long *pfns; - struct xe_userptr *userptr; - struct xe_vma *vma = &uvma->vma; - u64 userptr_start = xe_vma_userptr(vma); - u64 userptr_end = userptr_start + xe_vma_size(vma); - struct xe_vm *vm = xe_vma_vm(vma); - struct hmm_range hmm_range = { - .pfn_flags_mask = 0, /* ignore pfns */ - .default_flags = HMM_PFN_REQ_FAULT, - .start = userptr_start, - .end = userptr_end, - .notifier = &uvma->userptr.notifier, - .dev_private_owner = vm->xe, - }; - bool write = !xe_vma_read_only(vma); - unsigned long notifier_seq; - u64 npages; - int ret; - - userptr = &uvma->userptr; - - if (is_mm_mmap_locked) - mmap_assert_locked(userptr->notifier.mm); - - if (vma->gpuva.flags & XE_VMA_DESTROYED) - return 0; - - notifier_seq = mmu_interval_read_begin(&userptr->notifier); - if (notifier_seq == userptr->notifier_seq) - return 0; - - if (userptr->sg) - xe_hmm_userptr_free_sg(uvma); - - npages = xe_npages_in_range(userptr_start, userptr_end); - pfns = kvmalloc_array(npages, sizeof(*pfns), GFP_KERNEL); - if (unlikely(!pfns)) - return -ENOMEM; - - if (write) - hmm_range.default_flags |= HMM_PFN_REQ_WRITE; - - if (!mmget_not_zero(userptr->notifier.mm)) { - ret = -EFAULT; - goto free_pfns; - } - - hmm_range.hmm_pfns = pfns; - - while (true) { - hmm_range.notifier_seq = mmu_interval_read_begin(&userptr->notifier); - - if (!is_mm_mmap_locked) - mmap_read_lock(userptr->notifier.mm); - - ret = hmm_range_fault(&hmm_range); - - if (!is_mm_mmap_locked) - mmap_read_unlock(userptr->notifier.mm); - - if (ret == -EBUSY) { - if (time_after(jiffies, timeout)) - break; - - continue; - } - break; - } - - mmput(userptr->notifier.mm); - - if (ret) - goto free_pfns; - - ret = xe_alloc_sg(vm->xe, &userptr->sgt, &hmm_range, &vm->userptr.notifier_lock); - if (ret) - goto free_pfns; - - ret = down_read_interruptible(&vm->userptr.notifier_lock); - if (ret) - goto free_st; - - if (mmu_interval_read_retry(hmm_range.notifier, hmm_range.notifier_seq)) { - ret = -EAGAIN; - goto out_unlock; - } - - ret = xe_build_sg(vm->xe, &hmm_range, &userptr->sgt, - &vm->userptr.notifier_lock, write); - if (ret) - goto out_unlock; - - userptr->sg = &userptr->sgt; - xe_hmm_userptr_set_mapped(uvma); - userptr->notifier_seq = hmm_range.notifier_seq; - up_read(&vm->userptr.notifier_lock); - kvfree(pfns); - return 0; - -out_unlock: - up_read(&vm->userptr.notifier_lock); -free_st: - sg_free_table(&userptr->sgt); -free_pfns: - kvfree(pfns); - return ret; -} diff --git a/drivers/gpu/drm/xe/xe_hmm.h b/drivers/gpu/drm/xe/xe_hmm.h deleted file mode 100644 index 0ea98d8e7bbc..000000000000 --- a/drivers/gpu/drm/xe/xe_hmm.h +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: MIT - * - * Copyright © 2024 Intel Corporation - */ - -#ifndef _XE_HMM_H_ -#define _XE_HMM_H_ - -#include <linux/types.h> - -struct xe_userptr_vma; - -int xe_hmm_userptr_populate_range(struct xe_userptr_vma *uvma, bool is_mm_mmap_locked); - -void xe_hmm_userptr_free_sg(struct xe_userptr_vma *uvma); - -void xe_hmm_userptr_unmap(struct xe_userptr_vma *uvma); -#endif diff --git a/drivers/gpu/drm/xe/xe_hwmon.c b/drivers/gpu/drm/xe/xe_hwmon.c index 32a76ae6e9dc..b6790589e623 100644 --- a/drivers/gpu/drm/xe/xe_hwmon.c +++ b/drivers/gpu/drm/xe/xe_hwmon.c @@ -286,7 +286,7 @@ static struct xe_reg xe_hwmon_get_reg(struct xe_hwmon *hwmon, enum xe_hwmon_reg */ static void xe_hwmon_power_max_read(struct xe_hwmon *hwmon, u32 attr, int channel, long *value) { - u64 reg_val = 0, min, max; + u32 reg_val = 0; struct xe_device *xe = hwmon->xe; struct xe_reg rapl_limit, pkg_power_sku; struct xe_mmio *mmio = xe_root_tile_mmio(xe); @@ -294,7 +294,7 @@ static void xe_hwmon_power_max_read(struct xe_hwmon *hwmon, u32 attr, int channe mutex_lock(&hwmon->hwmon_lock); if (hwmon->xe->info.has_mbx_power_limits) { - xe_hwmon_pcode_read_power_limit(hwmon, attr, channel, (u32 *)®_val); + xe_hwmon_pcode_read_power_limit(hwmon, attr, channel, ®_val); } else { rapl_limit = xe_hwmon_get_reg(hwmon, REG_PKG_RAPL_LIMIT, channel); pkg_power_sku = xe_hwmon_get_reg(hwmon, REG_PKG_POWER_SKU, channel); @@ -304,19 +304,21 @@ static void xe_hwmon_power_max_read(struct xe_hwmon *hwmon, u32 attr, int channe /* Check if PL limits are disabled. */ if (!(reg_val & PWR_LIM_EN)) { *value = PL_DISABLE; - drm_info(&hwmon->xe->drm, "%s disabled for channel %d, val 0x%016llx\n", + drm_info(&hwmon->xe->drm, "%s disabled for channel %d, val 0x%08x\n", PWR_ATTR_TO_STR(attr), channel, reg_val); goto unlock; } reg_val = REG_FIELD_GET(PWR_LIM_VAL, reg_val); - *value = mul_u64_u32_shr(reg_val, SF_POWER, hwmon->scl_shift_power); + *value = mul_u32_u32(reg_val, SF_POWER) >> hwmon->scl_shift_power; /* For platforms with mailbox power limit support clamping would be done by pcode. */ if (!hwmon->xe->info.has_mbx_power_limits) { - reg_val = xe_mmio_read64_2x32(mmio, pkg_power_sku); - min = REG_FIELD_GET(PKG_MIN_PWR, reg_val); - max = REG_FIELD_GET(PKG_MAX_PWR, reg_val); + u64 pkg_pwr, min, max; + + pkg_pwr = xe_mmio_read64_2x32(mmio, pkg_power_sku); + min = REG_FIELD_GET(PKG_MIN_PWR, pkg_pwr); + max = REG_FIELD_GET(PKG_MAX_PWR, pkg_pwr); min = mul_u64_u32_shr(min, SF_POWER, hwmon->scl_shift_power); max = mul_u64_u32_shr(max, SF_POWER, hwmon->scl_shift_power); if (min && max) @@ -493,8 +495,8 @@ xe_hwmon_power_max_interval_show(struct device *dev, struct device_attribute *at { struct xe_hwmon *hwmon = dev_get_drvdata(dev); struct xe_mmio *mmio = xe_root_tile_mmio(hwmon->xe); - u32 x, y, x_w = 2; /* 2 bits */ - u64 r, tau4, out; + u32 reg_val, x, y, x_w = 2; /* 2 bits */ + u64 tau4, out; int channel = (to_sensor_dev_attr(attr)->index % 2) ? CHANNEL_PKG : CHANNEL_CARD; u32 power_attr = (to_sensor_dev_attr(attr)->index > 1) ? PL2_HWMON_ATTR : PL1_HWMON_ATTR; @@ -505,23 +507,24 @@ xe_hwmon_power_max_interval_show(struct device *dev, struct device_attribute *at mutex_lock(&hwmon->hwmon_lock); if (hwmon->xe->info.has_mbx_power_limits) { - ret = xe_hwmon_pcode_read_power_limit(hwmon, power_attr, channel, (u32 *)&r); + ret = xe_hwmon_pcode_read_power_limit(hwmon, power_attr, channel, ®_val); if (ret) { drm_err(&hwmon->xe->drm, - "power interval read fail, ch %d, attr %d, r 0%llx, ret %d\n", - channel, power_attr, r, ret); - r = 0; + "power interval read fail, ch %d, attr %d, val 0x%08x, ret %d\n", + channel, power_attr, reg_val, ret); + reg_val = 0; } } else { - r = xe_mmio_read32(mmio, xe_hwmon_get_reg(hwmon, REG_PKG_RAPL_LIMIT, channel)); + reg_val = xe_mmio_read32(mmio, xe_hwmon_get_reg(hwmon, REG_PKG_RAPL_LIMIT, + channel)); } mutex_unlock(&hwmon->hwmon_lock); xe_pm_runtime_put(hwmon->xe); - x = REG_FIELD_GET(PWR_LIM_TIME_X, r); - y = REG_FIELD_GET(PWR_LIM_TIME_Y, r); + x = REG_FIELD_GET(PWR_LIM_TIME_X, reg_val); + y = REG_FIELD_GET(PWR_LIM_TIME_Y, reg_val); /* * tau = (1 + (x / 4)) * power(2,y), x = bits(23:22), y = bits(21:17) @@ -1294,13 +1297,6 @@ xe_hwmon_get_preregistration_info(struct xe_hwmon *hwmon) xe_hwmon_fan_input_read(hwmon, channel, &fan_speed); } -static void xe_hwmon_mutex_destroy(void *arg) -{ - struct xe_hwmon *hwmon = arg; - - mutex_destroy(&hwmon->hwmon_lock); -} - int xe_hwmon_register(struct xe_device *xe) { struct device *dev = xe->drm.dev; @@ -1319,8 +1315,7 @@ int xe_hwmon_register(struct xe_device *xe) if (!hwmon) return -ENOMEM; - mutex_init(&hwmon->hwmon_lock); - ret = devm_add_action_or_reset(dev, xe_hwmon_mutex_destroy, hwmon); + ret = devm_mutex_init(dev, &hwmon->hwmon_lock); if (ret) return ret; diff --git a/drivers/gpu/drm/xe/xe_i2c.c b/drivers/gpu/drm/xe/xe_i2c.c index 044dda517b7c..48dfcb41fa08 100644 --- a/drivers/gpu/drm/xe/xe_i2c.c +++ b/drivers/gpu/drm/xe/xe_i2c.c @@ -259,7 +259,7 @@ void xe_i2c_pm_resume(struct xe_device *xe, bool d3cold) return; if (d3cold) - xe_mmio_rmw32(mmio, I2C_CONFIG_CMD, 0, PCI_COMMAND_MEMORY); + xe_mmio_rmw32(mmio, I2C_CONFIG_CMD, 0, PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER); xe_mmio_rmw32(mmio, I2C_CONFIG_PMCSR, PCI_PM_CTRL_STATE_MASK, (__force u32)PCI_D0); drm_dbg(&xe->drm, "pmcsr: 0x%08x\n", xe_mmio_read32(mmio, I2C_CONFIG_PMCSR)); diff --git a/drivers/gpu/drm/xe/xe_late_bind_fw.c b/drivers/gpu/drm/xe/xe_late_bind_fw.c new file mode 100644 index 000000000000..38f3feb2aecd --- /dev/null +++ b/drivers/gpu/drm/xe/xe_late_bind_fw.c @@ -0,0 +1,464 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2025 Intel Corporation + */ + +#include <linux/component.h> +#include <linux/delay.h> +#include <linux/firmware.h> + +#include <drm/drm_managed.h> +#include <drm/intel/i915_component.h> +#include <drm/intel/intel_lb_mei_interface.h> +#include <drm/drm_print.h> + +#include "xe_device.h" +#include "xe_late_bind_fw.h" +#include "xe_pcode.h" +#include "xe_pcode_api.h" +#include "xe_pm.h" + +/* + * The component should load quite quickly in most cases, but it could take + * a bit. Using a very big timeout just to cover the worst case scenario + */ +#define LB_INIT_TIMEOUT_MS 20000 + +/* + * Retry interval set to 6 seconds, in steps of 200 ms, to allow time for + * other OS components to release the MEI CL handle + */ +#define LB_FW_LOAD_RETRY_MAXCOUNT 30 +#define LB_FW_LOAD_RETRY_PAUSE_MS 200 + +static const u32 fw_id_to_type[] = { + [XE_LB_FW_FAN_CONTROL] = INTEL_LB_TYPE_FAN_CONTROL, + }; + +static const char * const fw_id_to_name[] = { + [XE_LB_FW_FAN_CONTROL] = "fan_control", + }; + +static struct xe_device * +late_bind_to_xe(struct xe_late_bind *late_bind) +{ + return container_of(late_bind, struct xe_device, late_bind); +} + +static struct xe_device * +late_bind_fw_to_xe(struct xe_late_bind_fw *lb_fw) +{ + return container_of(lb_fw, struct xe_device, late_bind.late_bind_fw[lb_fw->id]); +} + +/* Refer to the "Late Bind based Firmware Layout" documentation entry for details */ +static int parse_cpd_header(struct xe_late_bind_fw *lb_fw, + const void *data, size_t size, const char *manifest_entry) +{ + struct xe_device *xe = late_bind_fw_to_xe(lb_fw); + const struct gsc_cpd_header_v2 *header = data; + const struct gsc_manifest_header *manifest; + const struct gsc_cpd_entry *entry; + size_t min_size = sizeof(*header); + u32 offset; + int i; + + /* manifest_entry is mandatory */ + xe_assert(xe, manifest_entry); + + if (size < min_size || header->header_marker != GSC_CPD_HEADER_MARKER) + return -ENOENT; + + if (header->header_length < sizeof(struct gsc_cpd_header_v2)) { + drm_err(&xe->drm, "%s late binding fw: Invalid CPD header length %u!\n", + fw_id_to_name[lb_fw->id], header->header_length); + return -EINVAL; + } + + min_size = header->header_length + sizeof(struct gsc_cpd_entry) * header->num_of_entries; + if (size < min_size) { + drm_err(&xe->drm, "%s late binding fw: too small! %zu < %zu\n", + fw_id_to_name[lb_fw->id], size, min_size); + return -ENODATA; + } + + /* Look for the manifest first */ + entry = (void *)header + header->header_length; + for (i = 0; i < header->num_of_entries; i++, entry++) + if (strcmp(entry->name, manifest_entry) == 0) + offset = entry->offset & GSC_CPD_ENTRY_OFFSET_MASK; + + if (!offset) { + drm_err(&xe->drm, "%s late binding fw: Failed to find manifest_entry\n", + fw_id_to_name[lb_fw->id]); + return -ENODATA; + } + + min_size = offset + sizeof(struct gsc_manifest_header); + if (size < min_size) { + drm_err(&xe->drm, "%s late binding fw: too small! %zu < %zu\n", + fw_id_to_name[lb_fw->id], size, min_size); + return -ENODATA; + } + + manifest = data + offset; + + lb_fw->version = manifest->fw_version; + + return 0; +} + +/* Refer to the "Late Bind based Firmware Layout" documentation entry for details */ +static int parse_lb_layout(struct xe_late_bind_fw *lb_fw, + const void *data, size_t size, const char *fpt_entry) +{ + struct xe_device *xe = late_bind_fw_to_xe(lb_fw); + const struct csc_fpt_header *header = data; + const struct csc_fpt_entry *entry; + size_t min_size = sizeof(*header); + u32 offset; + int i; + + /* fpt_entry is mandatory */ + xe_assert(xe, fpt_entry); + + if (size < min_size || header->header_marker != CSC_FPT_HEADER_MARKER) + return -ENOENT; + + if (header->header_length < sizeof(struct csc_fpt_header)) { + drm_err(&xe->drm, "%s late binding fw: Invalid FPT header length %u!\n", + fw_id_to_name[lb_fw->id], header->header_length); + return -EINVAL; + } + + min_size = header->header_length + sizeof(struct csc_fpt_entry) * header->num_of_entries; + if (size < min_size) { + drm_err(&xe->drm, "%s late binding fw: too small! %zu < %zu\n", + fw_id_to_name[lb_fw->id], size, min_size); + return -ENODATA; + } + + /* Look for the cpd header first */ + entry = (void *)header + header->header_length; + for (i = 0; i < header->num_of_entries; i++, entry++) + if (strcmp(entry->name, fpt_entry) == 0) + offset = entry->offset; + + if (!offset) { + drm_err(&xe->drm, "%s late binding fw: Failed to find fpt_entry\n", + fw_id_to_name[lb_fw->id]); + return -ENODATA; + } + + min_size = offset + sizeof(struct gsc_cpd_header_v2); + if (size < min_size) { + drm_err(&xe->drm, "%s late binding fw: too small! %zu < %zu\n", + fw_id_to_name[lb_fw->id], size, min_size); + return -ENODATA; + } + + return parse_cpd_header(lb_fw, data + offset, size - offset, "LTES.man"); +} + +static const char *xe_late_bind_parse_status(uint32_t status) +{ + switch (status) { + case INTEL_LB_STATUS_SUCCESS: + return "success"; + case INTEL_LB_STATUS_4ID_MISMATCH: + return "4Id Mismatch"; + case INTEL_LB_STATUS_ARB_FAILURE: + return "ARB Failure"; + case INTEL_LB_STATUS_GENERAL_ERROR: + return "General Error"; + case INTEL_LB_STATUS_INVALID_PARAMS: + return "Invalid Params"; + case INTEL_LB_STATUS_INVALID_SIGNATURE: + return "Invalid Signature"; + case INTEL_LB_STATUS_INVALID_PAYLOAD: + return "Invalid Payload"; + case INTEL_LB_STATUS_TIMEOUT: + return "Timeout"; + default: + return "Unknown error"; + } +} + +static int xe_late_bind_fw_num_fans(struct xe_late_bind *late_bind) +{ + struct xe_device *xe = late_bind_to_xe(late_bind); + struct xe_tile *root_tile = xe_device_get_root_tile(xe); + u32 uval; + + if (!xe_pcode_read(root_tile, + PCODE_MBOX(FAN_SPEED_CONTROL, FSC_READ_NUM_FANS, 0), &uval, NULL)) + return uval; + else + return 0; +} + +void xe_late_bind_wait_for_worker_completion(struct xe_late_bind *late_bind) +{ + struct xe_device *xe = late_bind_to_xe(late_bind); + struct xe_late_bind_fw *lbfw; + int fw_id; + + for (fw_id = 0; fw_id < XE_LB_FW_MAX_ID; fw_id++) { + lbfw = &late_bind->late_bind_fw[fw_id]; + if (lbfw->payload && late_bind->wq) { + drm_dbg(&xe->drm, "Flush work: load %s firmware\n", + fw_id_to_name[lbfw->id]); + flush_work(&lbfw->work); + } + } +} + +static void xe_late_bind_work(struct work_struct *work) +{ + struct xe_late_bind_fw *lbfw = container_of(work, struct xe_late_bind_fw, work); + struct xe_late_bind *late_bind = container_of(lbfw, struct xe_late_bind, + late_bind_fw[lbfw->id]); + struct xe_device *xe = late_bind_to_xe(late_bind); + int retry = LB_FW_LOAD_RETRY_MAXCOUNT; + int ret; + int slept; + + xe_device_assert_mem_access(xe); + + /* we can queue this before the component is bound */ + for (slept = 0; slept < LB_INIT_TIMEOUT_MS; slept += 100) { + if (late_bind->component.ops) + break; + msleep(100); + } + + if (!late_bind->component.ops) { + drm_err(&xe->drm, "Late bind component not bound\n"); + /* Do not re-attempt fw load */ + drmm_kfree(&xe->drm, (void *)lbfw->payload); + lbfw->payload = NULL; + goto out; + } + + drm_dbg(&xe->drm, "Load %s firmware\n", fw_id_to_name[lbfw->id]); + + do { + ret = late_bind->component.ops->push_payload(late_bind->component.mei_dev, + lbfw->type, + lbfw->flags, + lbfw->payload, + lbfw->payload_size); + if (!ret) + break; + msleep(LB_FW_LOAD_RETRY_PAUSE_MS); + } while (--retry && ret == -EBUSY); + + if (!ret) { + drm_dbg(&xe->drm, "Load %s firmware successful\n", + fw_id_to_name[lbfw->id]); + goto out; + } + + if (ret > 0) + drm_err(&xe->drm, "Load %s firmware failed with err %d, %s\n", + fw_id_to_name[lbfw->id], ret, xe_late_bind_parse_status(ret)); + else + drm_err(&xe->drm, "Load %s firmware failed with err %d", + fw_id_to_name[lbfw->id], ret); + /* Do not re-attempt fw load */ + drmm_kfree(&xe->drm, (void *)lbfw->payload); + lbfw->payload = NULL; + +out: + xe_pm_runtime_put(xe); +} + +int xe_late_bind_fw_load(struct xe_late_bind *late_bind) +{ + struct xe_device *xe = late_bind_to_xe(late_bind); + struct xe_late_bind_fw *lbfw; + int fw_id; + + if (!late_bind->component_added) + return -ENODEV; + + if (late_bind->disable) + return 0; + + for (fw_id = 0; fw_id < XE_LB_FW_MAX_ID; fw_id++) { + lbfw = &late_bind->late_bind_fw[fw_id]; + if (lbfw->payload) { + xe_pm_runtime_get_noresume(xe); + queue_work(late_bind->wq, &lbfw->work); + } + } + return 0; +} + +static int __xe_late_bind_fw_init(struct xe_late_bind *late_bind, u32 fw_id) +{ + struct xe_device *xe = late_bind_to_xe(late_bind); + struct pci_dev *pdev = to_pci_dev(xe->drm.dev); + struct xe_late_bind_fw *lb_fw; + const struct firmware *fw; + u32 num_fans; + int ret; + + if (fw_id >= XE_LB_FW_MAX_ID) + return -EINVAL; + + lb_fw = &late_bind->late_bind_fw[fw_id]; + + lb_fw->id = fw_id; + lb_fw->type = fw_id_to_type[lb_fw->id]; + lb_fw->flags &= ~INTEL_LB_FLAG_IS_PERSISTENT; + + if (lb_fw->type == INTEL_LB_TYPE_FAN_CONTROL) { + num_fans = xe_late_bind_fw_num_fans(late_bind); + drm_dbg(&xe->drm, "Number of Fans: %d\n", num_fans); + if (!num_fans) + return 0; + } + + snprintf(lb_fw->blob_path, sizeof(lb_fw->blob_path), "xe/%s_8086_%04x_%04x_%04x.bin", + fw_id_to_name[lb_fw->id], pdev->device, + pdev->subsystem_vendor, pdev->subsystem_device); + + drm_dbg(&xe->drm, "Request late binding firmware %s\n", lb_fw->blob_path); + ret = firmware_request_nowarn(&fw, lb_fw->blob_path, xe->drm.dev); + if (ret) { + drm_dbg(&xe->drm, "%s late binding fw not available for current device", + fw_id_to_name[lb_fw->id]); + return 0; + } + + if (fw->size > XE_LB_MAX_PAYLOAD_SIZE) { + drm_err(&xe->drm, "Firmware %s size %zu is larger than max pay load size %u\n", + lb_fw->blob_path, fw->size, XE_LB_MAX_PAYLOAD_SIZE); + release_firmware(fw); + return -ENODATA; + } + + ret = parse_lb_layout(lb_fw, fw->data, fw->size, "LTES"); + if (ret) + return ret; + + lb_fw->payload_size = fw->size; + lb_fw->payload = drmm_kzalloc(&xe->drm, lb_fw->payload_size, GFP_KERNEL); + if (!lb_fw->payload) { + release_firmware(fw); + return -ENOMEM; + } + + drm_info(&xe->drm, "Using %s firmware from %s version %u.%u.%u.%u\n", + fw_id_to_name[lb_fw->id], lb_fw->blob_path, + lb_fw->version.major, lb_fw->version.minor, + lb_fw->version.hotfix, lb_fw->version.build); + + memcpy((void *)lb_fw->payload, fw->data, lb_fw->payload_size); + release_firmware(fw); + INIT_WORK(&lb_fw->work, xe_late_bind_work); + + return 0; +} + +static int xe_late_bind_fw_init(struct xe_late_bind *late_bind) +{ + int ret; + int fw_id; + + late_bind->wq = alloc_ordered_workqueue("late-bind-ordered-wq", 0); + if (!late_bind->wq) + return -ENOMEM; + + for (fw_id = 0; fw_id < XE_LB_FW_MAX_ID; fw_id++) { + ret = __xe_late_bind_fw_init(late_bind, fw_id); + if (ret) + return ret; + } + + return 0; +} + +static int xe_late_bind_component_bind(struct device *xe_kdev, + struct device *mei_kdev, void *data) +{ + struct xe_device *xe = kdev_to_xe_device(xe_kdev); + struct xe_late_bind *late_bind = &xe->late_bind; + + late_bind->component.ops = data; + late_bind->component.mei_dev = mei_kdev; + + return 0; +} + +static void xe_late_bind_component_unbind(struct device *xe_kdev, + struct device *mei_kdev, void *data) +{ + struct xe_device *xe = kdev_to_xe_device(xe_kdev); + struct xe_late_bind *late_bind = &xe->late_bind; + + xe_late_bind_wait_for_worker_completion(late_bind); + + late_bind->component.ops = NULL; +} + +static const struct component_ops xe_late_bind_component_ops = { + .bind = xe_late_bind_component_bind, + .unbind = xe_late_bind_component_unbind, +}; + +static void xe_late_bind_remove(void *arg) +{ + struct xe_late_bind *late_bind = arg; + struct xe_device *xe = late_bind_to_xe(late_bind); + + xe_late_bind_wait_for_worker_completion(late_bind); + + late_bind->component_added = false; + + component_del(xe->drm.dev, &xe_late_bind_component_ops); + if (late_bind->wq) { + destroy_workqueue(late_bind->wq); + late_bind->wq = NULL; + } +} + +/** + * xe_late_bind_init() - add xe mei late binding component + * @late_bind: pointer to late bind structure. + * + * Return: 0 if the initialization was successful, a negative errno otherwise. + */ +int xe_late_bind_init(struct xe_late_bind *late_bind) +{ + struct xe_device *xe = late_bind_to_xe(late_bind); + int err; + + if (!xe->info.has_late_bind) + return 0; + + if (!IS_ENABLED(CONFIG_INTEL_MEI_LB) || !IS_ENABLED(CONFIG_INTEL_MEI_GSC)) { + drm_info(&xe->drm, "Can't init xe mei late bind missing mei component\n"); + return 0; + } + + err = component_add_typed(xe->drm.dev, &xe_late_bind_component_ops, + INTEL_COMPONENT_LB); + if (err < 0) { + drm_err(&xe->drm, "Failed to add mei late bind component (%pe)\n", ERR_PTR(err)); + return err; + } + + late_bind->component_added = true; + + err = devm_add_action_or_reset(xe->drm.dev, xe_late_bind_remove, late_bind); + if (err) + return err; + + err = xe_late_bind_fw_init(late_bind); + if (err) + return err; + + return xe_late_bind_fw_load(late_bind); +} diff --git a/drivers/gpu/drm/xe/xe_late_bind_fw.h b/drivers/gpu/drm/xe/xe_late_bind_fw.h new file mode 100644 index 000000000000..07e437390539 --- /dev/null +++ b/drivers/gpu/drm/xe/xe_late_bind_fw.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2025 Intel Corporation + */ + +#ifndef _XE_LATE_BIND_FW_H_ +#define _XE_LATE_BIND_FW_H_ + +#include <linux/types.h> + +struct xe_late_bind; + +int xe_late_bind_init(struct xe_late_bind *late_bind); +int xe_late_bind_fw_load(struct xe_late_bind *late_bind); +void xe_late_bind_wait_for_worker_completion(struct xe_late_bind *late_bind); + +#endif diff --git a/drivers/gpu/drm/xe/xe_late_bind_fw_types.h b/drivers/gpu/drm/xe/xe_late_bind_fw_types.h new file mode 100644 index 000000000000..0f5da89ce98b --- /dev/null +++ b/drivers/gpu/drm/xe/xe_late_bind_fw_types.h @@ -0,0 +1,75 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2025 Intel Corporation + */ + +#ifndef _XE_LATE_BIND_TYPES_H_ +#define _XE_LATE_BIND_TYPES_H_ + +#include <linux/iosys-map.h> +#include <linux/mutex.h> +#include <linux/types.h> +#include <linux/workqueue.h> +#include "xe_uc_fw_abi.h" + +#define XE_LB_MAX_PAYLOAD_SIZE SZ_4K + +/** + * xe_late_bind_fw_id - enum to determine late binding fw index + */ +enum xe_late_bind_fw_id { + XE_LB_FW_FAN_CONTROL = 0, + XE_LB_FW_MAX_ID +}; + +/** + * struct xe_late_bind_fw + */ +struct xe_late_bind_fw { + /** @id: firmware index */ + u32 id; + /** @blob_path: firmware binary path */ + char blob_path[PATH_MAX]; + /** @type: firmware type */ + u32 type; + /** @flags: firmware flags */ + u32 flags; + /** @payload: to store the late binding blob */ + const u8 *payload; + /** @payload_size: late binding blob payload_size */ + size_t payload_size; + /** @work: worker to upload latebind blob */ + struct work_struct work; + /** @version: late binding blob manifest version */ + struct gsc_version version; +}; + +/** + * struct xe_late_bind_component - Late Binding services component + * @mei_dev: device that provide Late Binding service. + * @ops: Ops implemented by Late Binding driver, used by Xe driver. + * + * Communication between Xe and MEI drivers for Late Binding services + */ +struct xe_late_bind_component { + struct device *mei_dev; + const struct intel_lb_component_ops *ops; +}; + +/** + * struct xe_late_bind + */ +struct xe_late_bind { + /** @component: struct for communication with mei component */ + struct xe_late_bind_component component; + /** @late_bind_fw: late binding firmware array */ + struct xe_late_bind_fw late_bind_fw[XE_LB_FW_MAX_ID]; + /** @wq: workqueue to submit request to download late bind blob */ + struct workqueue_struct *wq; + /** @component_added: whether the component has been added */ + bool component_added; + /** @disable: to block late binding reload during pm resume flow*/ + bool disable; +}; + +#endif diff --git a/drivers/gpu/drm/xe/xe_lmtt.c b/drivers/gpu/drm/xe/xe_lmtt.c index f2bfbfa3efa1..62fc5a1a332d 100644 --- a/drivers/gpu/drm/xe/xe_lmtt.c +++ b/drivers/gpu/drm/xe/xe_lmtt.c @@ -67,12 +67,12 @@ static struct xe_lmtt_pt *lmtt_pt_alloc(struct xe_lmtt *lmtt, unsigned int level goto out; } - bo = xe_bo_create_pin_map(lmtt_to_xe(lmtt), lmtt_to_tile(lmtt), NULL, - PAGE_ALIGN(lmtt->ops->lmtt_pte_size(level) * - lmtt->ops->lmtt_pte_num(level)), - ttm_bo_type_kernel, - XE_BO_FLAG_VRAM_IF_DGFX(lmtt_to_tile(lmtt)) | - XE_BO_FLAG_NEEDS_64K); + bo = xe_bo_create_pin_map_novm(lmtt_to_xe(lmtt), lmtt_to_tile(lmtt), + PAGE_ALIGN(lmtt->ops->lmtt_pte_size(level) * + lmtt->ops->lmtt_pte_num(level)), + ttm_bo_type_kernel, + XE_BO_FLAG_VRAM_IF_DGFX(lmtt_to_tile(lmtt)) | + XE_BO_FLAG_NEEDS_64K, false); if (IS_ERR(bo)) { err = PTR_ERR(bo); goto out_free_pt; diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c index 8f6c3ba47882..47e9df775072 100644 --- a/drivers/gpu/drm/xe/xe_lrc.c +++ b/drivers/gpu/drm/xe/xe_lrc.c @@ -8,6 +8,7 @@ #include <generated/xe_wa_oob.h> #include <linux/ascii85.h> +#include <linux/panic.h> #include "instructions/xe_mi_commands.h" #include "instructions/xe_gfxpipe_commands.h" @@ -16,6 +17,7 @@ #include "regs/xe_lrc_layout.h" #include "xe_bb.h" #include "xe_bo.h" +#include "xe_configfs.h" #include "xe_device.h" #include "xe_drm_client.h" #include "xe_exec_queue_types.h" @@ -75,11 +77,17 @@ lrc_to_xe(struct xe_lrc *lrc) static bool gt_engine_needs_indirect_ctx(struct xe_gt *gt, enum xe_engine_class class) { + struct xe_device *xe = gt_to_xe(gt); + if (XE_GT_WA(gt, 16010904313) && (class == XE_ENGINE_CLASS_RENDER || class == XE_ENGINE_CLASS_COMPUTE)) return true; + if (xe_configfs_get_ctx_restore_mid_bb(to_pci_dev(xe->drm.dev), + class, NULL)) + return true; + return false; } @@ -1102,6 +1110,64 @@ static ssize_t setup_timestamp_wa(struct xe_lrc *lrc, struct xe_hw_engine *hwe, return cmd - batch; } +static ssize_t setup_configfs_post_ctx_restore_bb(struct xe_lrc *lrc, + struct xe_hw_engine *hwe, + u32 *batch, size_t max_len) +{ + struct xe_device *xe = gt_to_xe(lrc->gt); + const u32 *user_batch; + u32 *cmd = batch; + u32 count; + + count = xe_configfs_get_ctx_restore_post_bb(to_pci_dev(xe->drm.dev), + hwe->class, &user_batch); + if (!count) + return 0; + + if (count > max_len) + return -ENOSPC; + + /* + * This should be used only for tests and validation. Taint the kernel + * as anything could be submitted directly in context switches + */ + add_taint(TAINT_TEST, LOCKDEP_STILL_OK); + + memcpy(cmd, user_batch, count * sizeof(u32)); + cmd += count; + + return cmd - batch; +} + +static ssize_t setup_configfs_mid_ctx_restore_bb(struct xe_lrc *lrc, + struct xe_hw_engine *hwe, + u32 *batch, size_t max_len) +{ + struct xe_device *xe = gt_to_xe(lrc->gt); + const u32 *user_batch; + u32 *cmd = batch; + u32 count; + + count = xe_configfs_get_ctx_restore_mid_bb(to_pci_dev(xe->drm.dev), + hwe->class, &user_batch); + if (!count) + return 0; + + if (count > max_len) + return -ENOSPC; + + /* + * This should be used only for tests and validation. Taint the kernel + * as anything could be submitted directly in context switches + */ + add_taint(TAINT_TEST, LOCKDEP_STILL_OK); + + memcpy(cmd, user_batch, count * sizeof(u32)); + cmd += count; + + return cmd - batch; +} + static ssize_t setup_invalidate_state_cache_wa(struct xe_lrc *lrc, struct xe_hw_engine *hwe, u32 *batch, size_t max_len) @@ -1203,6 +1269,7 @@ int xe_lrc_setup_wa_bb_with_scratch(struct xe_lrc *lrc, struct xe_hw_engine *hwe { .setup = setup_timestamp_wa }, { .setup = setup_invalidate_state_cache_wa }, { .setup = setup_utilization_wa }, + { .setup = setup_configfs_post_ctx_restore_bb }, }; struct bo_setup_state state = { .lrc = lrc, @@ -1249,8 +1316,12 @@ static int setup_wa_bb(struct xe_lrc *lrc, struct xe_hw_engine *hwe) static int setup_indirect_ctx(struct xe_lrc *lrc, struct xe_hw_engine *hwe) { - static struct bo_setup rcs_funcs[] = { + static const struct bo_setup rcs_funcs[] = { { .setup = setup_timestamp_wa }, + { .setup = setup_configfs_mid_ctx_restore_bb }, + }; + static const struct bo_setup xcs_funcs[] = { + { .setup = setup_configfs_mid_ctx_restore_bb }, }; struct bo_setup_state state = { .lrc = lrc, @@ -1268,6 +1339,9 @@ setup_indirect_ctx(struct xe_lrc *lrc, struct xe_hw_engine *hwe) hwe->class == XE_ENGINE_CLASS_COMPUTE) { state.funcs = rcs_funcs; state.num_funcs = ARRAY_SIZE(rcs_funcs); + } else { + state.funcs = xcs_funcs; + state.num_funcs = ARRAY_SIZE(xcs_funcs); } if (xe_gt_WARN_ON(lrc->gt, !state.funcs)) @@ -1294,14 +1368,15 @@ setup_indirect_ctx(struct xe_lrc *lrc, struct xe_hw_engine *hwe) finish_bo(&state); kfree(state.buffer); + /* + * Enable INDIRECT_CTX leaving INDIRECT_CTX_OFFSET at its default: it + * varies per engine class, but the default is good enough + */ xe_lrc_write_ctx_reg(lrc, CTX_CS_INDIRECT_CTX, (xe_bo_ggtt_addr(lrc->bo) + state.offset) | /* Size in CLs. */ (state.written * sizeof(u32) / 64)); - xe_lrc_write_ctx_reg(lrc, - CTX_CS_INDIRECT_CTX_OFFSET, - CTX_INDIRECT_CTX_OFFSET_DEFAULT); return 0; } @@ -1340,9 +1415,10 @@ static int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe, if (vm && vm->xef) /* userspace */ bo_flags |= XE_BO_FLAG_PINNED_LATE_RESTORE; - lrc->bo = xe_bo_create_pin_map(xe, tile, NULL, bo_size, - ttm_bo_type_kernel, - bo_flags); + lrc->bo = xe_bo_create_pin_map_novm(xe, tile, + bo_size, + ttm_bo_type_kernel, + bo_flags, false); if (IS_ERR(lrc->bo)) return PTR_ERR(lrc->bo); diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c index 9643442ef101..1d667fa36cf3 100644 --- a/drivers/gpu/drm/xe/xe_migrate.c +++ b/drivers/gpu/drm/xe/xe_migrate.c @@ -35,6 +35,7 @@ #include "xe_sched_job.h" #include "xe_sync.h" #include "xe_trace_bo.h" +#include "xe_validation.h" #include "xe_vm.h" #include "xe_vram.h" @@ -173,7 +174,7 @@ static void xe_migrate_program_identity(struct xe_device *xe, struct xe_vm *vm, } static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m, - struct xe_vm *vm) + struct xe_vm *vm, struct drm_exec *exec) { struct xe_device *xe = tile_to_xe(tile); u16 pat_index = xe->pat.idx[XE_CACHE_WB]; @@ -200,7 +201,7 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m, num_entries * XE_PAGE_SIZE, ttm_bo_type_kernel, XE_BO_FLAG_VRAM_IF_DGFX(tile) | - XE_BO_FLAG_PAGETABLE); + XE_BO_FLAG_PAGETABLE, exec); if (IS_ERR(bo)) return PTR_ERR(bo); @@ -393,6 +394,24 @@ struct xe_migrate *xe_migrate_alloc(struct xe_tile *tile) return m; } +static int xe_migrate_lock_prepare_vm(struct xe_tile *tile, struct xe_migrate *m, struct xe_vm *vm) +{ + struct xe_device *xe = tile_to_xe(tile); + struct xe_validation_ctx ctx; + struct drm_exec exec; + int err = 0; + + xe_validation_guard(&ctx, &xe->val, &exec, (struct xe_val_flags) {}, err) { + err = xe_vm_drm_exec_lock(vm, &exec); + drm_exec_retry_on_contention(&exec); + err = xe_migrate_prepare_vm(tile, m, vm, &exec); + drm_exec_retry_on_contention(&exec); + xe_validation_retry_on_oom(&ctx, &err); + } + + return err; +} + /** * xe_migrate_init() - Initialize a migrate context * @m: The migration context @@ -413,11 +432,9 @@ int xe_migrate_init(struct xe_migrate *m) if (IS_ERR(vm)) return PTR_ERR(vm); - xe_vm_lock(vm, false); - err = xe_migrate_prepare_vm(tile, m, vm); - xe_vm_unlock(vm); + err = xe_migrate_lock_prepare_vm(tile, m, vm); if (err) - goto err_out; + return err; if (xe->info.has_usm) { struct xe_hw_engine *hwe = xe_gt_hw_engine(primary_gt, @@ -842,11 +859,15 @@ struct dma_fence *xe_migrate_copy(struct xe_migrate *m, batch_size += pte_update_size(m, pte_flags, src, &src_it, &src_L0, &src_L0_ofs, &src_L0_pt, 0, 0, avail_pts); - - pte_flags = dst_is_vram ? PTE_UPDATE_FLAG_IS_VRAM : 0; - batch_size += pte_update_size(m, pte_flags, dst, &dst_it, &src_L0, - &dst_L0_ofs, &dst_L0_pt, 0, - avail_pts, avail_pts); + if (copy_only_ccs) { + dst_L0_ofs = src_L0_ofs; + } else { + pte_flags = dst_is_vram ? PTE_UPDATE_FLAG_IS_VRAM : 0; + batch_size += pte_update_size(m, pte_flags, dst, + &dst_it, &src_L0, + &dst_L0_ofs, &dst_L0_pt, + 0, avail_pts, avail_pts); + } if (copy_system_ccs) { xe_assert(xe, type_device); @@ -876,7 +897,7 @@ struct dma_fence *xe_migrate_copy(struct xe_migrate *m, if (dst_is_vram && xe_migrate_allow_identity(src_L0, &dst_it)) xe_res_next(&dst_it, src_L0); - else + else if (!copy_only_ccs) emit_pte(m, bb, dst_L0_pt, dst_is_vram, copy_system_ccs, &dst_it, src_L0, dst); @@ -908,7 +929,7 @@ struct dma_fence *xe_migrate_copy(struct xe_migrate *m, if (!fence) { err = xe_sched_job_add_deps(job, src_bo->ttm.base.resv, DMA_RESV_USAGE_BOOKKEEP); - if (!err && src_bo != dst_bo) + if (!err && src_bo->ttm.base.resv != dst_bo->ttm.base.resv) err = xe_sched_job_add_deps(job, dst_bo->ttm.base.resv, DMA_RESV_USAGE_BOOKKEEP); if (err) diff --git a/drivers/gpu/drm/xe/xe_nvm.c b/drivers/gpu/drm/xe/xe_nvm.c index 9ca4a5ae1693..33f4ac82fc80 100644 --- a/drivers/gpu/drm/xe/xe_nvm.c +++ b/drivers/gpu/drm/xe/xe_nvm.c @@ -35,6 +35,10 @@ static const struct intel_dg_nvm_region regions[INTEL_DG_NVM_REGIONS] = { static void xe_nvm_release_dev(struct device *dev) { + struct auxiliary_device *aux = container_of(dev, struct auxiliary_device, dev); + struct intel_dg_nvm_dev *nvm = container_of(aux, struct intel_dg_nvm_dev, aux_dev); + + kfree(nvm); } static bool xe_nvm_non_posted_erase(struct xe_device *xe) @@ -162,6 +166,5 @@ void xe_nvm_fini(struct xe_device *xe) auxiliary_device_delete(&nvm->aux_dev); auxiliary_device_uninit(&nvm->aux_dev); - kfree(nvm); xe->nvm = NULL; } diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c index a188bad172ad..a4894eb0d7f3 100644 --- a/drivers/gpu/drm/xe/xe_oa.c +++ b/drivers/gpu/drm/xe/xe_oa.c @@ -883,9 +883,9 @@ static int xe_oa_alloc_oa_buffer(struct xe_oa_stream *stream, size_t size) { struct xe_bo *bo; - bo = xe_bo_create_pin_map(stream->oa->xe, stream->gt->tile, NULL, - size, ttm_bo_type_kernel, - XE_BO_FLAG_SYSTEM | XE_BO_FLAG_GGTT); + bo = xe_bo_create_pin_map_novm(stream->oa->xe, stream->gt->tile, + size, ttm_bo_type_kernel, + XE_BO_FLAG_SYSTEM | XE_BO_FLAG_GGTT, false); if (IS_ERR(bo)) return PTR_ERR(bo); diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c index 7ae316534eb6..67c808bb22a8 100644 --- a/drivers/gpu/drm/xe/xe_pci.c +++ b/drivers/gpu/drm/xe/xe_pci.c @@ -334,6 +334,7 @@ static const struct xe_device_desc bmg_desc = { .has_mbx_power_limits = true, .has_gsc_nvm = 1, .has_heci_cscfi = 1, + .has_late_bind = true, .has_sriov = true, .max_gt_per_tile = 2, .needs_scratch = true, @@ -511,6 +512,26 @@ static void read_gmdid(struct xe_device *xe, enum xe_gmdid_type type, u32 *ver, *revid = REG_FIELD_GET(GMD_ID_REVID, val); } +static const struct xe_ip *find_graphics_ip(unsigned int verx100) +{ + KUNIT_STATIC_STUB_REDIRECT(find_graphics_ip, verx100); + + for (int i = 0; i < ARRAY_SIZE(graphics_ips); i++) + if (graphics_ips[i].verx100 == verx100) + return &graphics_ips[i]; + return NULL; +} + +static const struct xe_ip *find_media_ip(unsigned int verx100) +{ + KUNIT_STATIC_STUB_REDIRECT(find_media_ip, verx100); + + for (int i = 0; i < ARRAY_SIZE(media_ips); i++) + if (media_ips[i].verx100 == verx100) + return &media_ips[i]; + return NULL; +} + /* * Read IP version from hardware and select graphics/media IP descriptors * based on the result. @@ -528,14 +549,7 @@ static void handle_gmdid(struct xe_device *xe, read_gmdid(xe, GMDID_GRAPHICS, &ver, graphics_revid); - for (int i = 0; i < ARRAY_SIZE(graphics_ips); i++) { - if (ver == graphics_ips[i].verx100) { - *graphics_ip = &graphics_ips[i]; - - break; - } - } - + *graphics_ip = find_graphics_ip(ver); if (!*graphics_ip) { drm_err(&xe->drm, "Hardware reports unknown graphics version %u.%02u\n", ver / 100, ver % 100); @@ -546,14 +560,7 @@ static void handle_gmdid(struct xe_device *xe, if (ver == 0) return; - for (int i = 0; i < ARRAY_SIZE(media_ips); i++) { - if (ver == media_ips[i].verx100) { - *media_ip = &media_ips[i]; - - break; - } - } - + *media_ip = find_media_ip(ver); if (!*media_ip) { drm_err(&xe->drm, "Hardware reports unknown media version %u.%02u\n", ver / 100, ver % 100); @@ -582,6 +589,7 @@ static int xe_info_init_early(struct xe_device *xe, xe->info.has_gsc_nvm = desc->has_gsc_nvm; xe->info.has_heci_gscfi = desc->has_heci_gscfi; xe->info.has_heci_cscfi = desc->has_heci_cscfi; + xe->info.has_late_bind = desc->has_late_bind; xe->info.has_llc = desc->has_llc; xe->info.has_pxp = desc->has_pxp; xe->info.has_sriov = desc->has_sriov; diff --git a/drivers/gpu/drm/xe/xe_pci_types.h b/drivers/gpu/drm/xe/xe_pci_types.h index b63002fc0f67..9b9766a3baa3 100644 --- a/drivers/gpu/drm/xe/xe_pci_types.h +++ b/drivers/gpu/drm/xe/xe_pci_types.h @@ -39,6 +39,7 @@ struct xe_device_desc { u8 has_gsc_nvm:1; u8 has_heci_gscfi:1; u8 has_heci_cscfi:1; + u8 has_late_bind:1; u8 has_llc:1; u8 has_mbx_power_limits:1; u8 has_pxp:1; diff --git a/drivers/gpu/drm/xe/xe_pm.c b/drivers/gpu/drm/xe/xe_pm.c index d4b54cd34cff..d6625c71115b 100644 --- a/drivers/gpu/drm/xe/xe_pm.c +++ b/drivers/gpu/drm/xe/xe_pm.c @@ -21,10 +21,12 @@ #include "xe_gt_idle.h" #include "xe_i2c.h" #include "xe_irq.h" +#include "xe_late_bind_fw.h" #include "xe_pcode.h" #include "xe_pxp.h" #include "xe_sriov_vf_ccs.h" #include "xe_trace.h" +#include "xe_vm.h" #include "xe_wa.h" /** @@ -128,6 +130,8 @@ int xe_pm_suspend(struct xe_device *xe) if (err) goto err; + xe_late_bind_wait_for_worker_completion(&xe->late_bind); + for_each_gt(gt, xe, id) xe_gt_suspend_prepare(gt); @@ -212,9 +216,11 @@ int xe_pm_resume(struct xe_device *xe) xe_pxp_pm_resume(xe->pxp); - if (IS_SRIOV_VF(xe)) + if (IS_VF_CCS_READY(xe)) xe_sriov_vf_ccs_register_context(xe); + xe_late_bind_fw_load(&xe->late_bind); + drm_dbg(&xe->drm, "Device resumed\n"); return 0; err: @@ -301,6 +307,19 @@ static u32 vram_threshold_value(struct xe_device *xe) return DEFAULT_VRAM_THRESHOLD; } +static void xe_pm_wake_rebind_workers(struct xe_device *xe) +{ + struct xe_vm *vm, *next; + + mutex_lock(&xe->rebind_resume_lock); + list_for_each_entry_safe(vm, next, &xe->rebind_resume_list, + preempt.pm_activate_link) { + list_del_init(&vm->preempt.pm_activate_link); + xe_vm_resume_rebind_worker(vm); + } + mutex_unlock(&xe->rebind_resume_lock); +} + static int xe_pm_notifier_callback(struct notifier_block *nb, unsigned long action, void *data) { @@ -310,30 +329,30 @@ static int xe_pm_notifier_callback(struct notifier_block *nb, switch (action) { case PM_HIBERNATION_PREPARE: case PM_SUSPEND_PREPARE: + reinit_completion(&xe->pm_block); xe_pm_runtime_get(xe); err = xe_bo_evict_all_user(xe); - if (err) { + if (err) drm_dbg(&xe->drm, "Notifier evict user failed (%d)\n", err); - xe_pm_runtime_put(xe); - break; - } err = xe_bo_notifier_prepare_all_pinned(xe); - if (err) { + if (err) drm_dbg(&xe->drm, "Notifier prepare pin failed (%d)\n", err); - xe_pm_runtime_put(xe); - } + /* + * Keep the runtime pm reference until post hibernation / post suspend to + * avoid a runtime suspend interfering with evicted objects or backup + * allocations. + */ break; case PM_POST_HIBERNATION: case PM_POST_SUSPEND: + complete_all(&xe->pm_block); + xe_pm_wake_rebind_workers(xe); xe_bo_notifier_unprepare_all_pinned(xe); xe_pm_runtime_put(xe); break; } - if (err) - return NOTIFY_BAD; - return NOTIFY_DONE; } @@ -355,6 +374,14 @@ int xe_pm_init(struct xe_device *xe) if (err) return err; + err = drmm_mutex_init(&xe->drm, &xe->rebind_resume_lock); + if (err) + goto err_unregister; + + init_completion(&xe->pm_block); + complete_all(&xe->pm_block); + INIT_LIST_HEAD(&xe->rebind_resume_list); + /* For now suspend/resume is only allowed with GuC */ if (!xe_device_uc_enabled(xe)) return 0; @@ -576,9 +603,12 @@ int xe_pm_runtime_resume(struct xe_device *xe) xe_pxp_pm_resume(xe->pxp); - if (IS_SRIOV_VF(xe)) + if (IS_VF_CCS_READY(xe)) xe_sriov_vf_ccs_register_context(xe); + if (xe->d3cold.allowed) + xe_late_bind_fw_load(&xe->late_bind); + out: xe_rpm_lockmap_release(xe); xe_pm_write_callback_task(xe, NULL); diff --git a/drivers/gpu/drm/xe/xe_printk.h b/drivers/gpu/drm/xe/xe_printk.h new file mode 100644 index 000000000000..c5be2385aa95 --- /dev/null +++ b/drivers/gpu/drm/xe/xe_printk.h @@ -0,0 +1,129 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2025 Intel Corporation + */ + +#ifndef _XE_PRINTK_H_ +#define _XE_PRINTK_H_ + +#include <drm/drm_print.h> + +#include "xe_device_types.h" + +#define __XE_PRINTK_FMT(_xe, _fmt, _args...) _fmt, ##_args + +#define xe_printk(_xe, _level, _fmt, ...) \ + drm_##_level(&(_xe)->drm, __XE_PRINTK_FMT((_xe), _fmt, ## __VA_ARGS__)) + +#define xe_err(_xe, _fmt, ...) \ + xe_printk((_xe), err, _fmt, ##__VA_ARGS__) + +#define xe_err_once(_xe, _fmt, ...) \ + xe_printk((_xe), err_once, _fmt, ##__VA_ARGS__) + +#define xe_err_ratelimited(_xe, _fmt, ...) \ + xe_printk((_xe), err_ratelimited, _fmt, ##__VA_ARGS__) + +#define xe_warn(_xe, _fmt, ...) \ + xe_printk((_xe), warn, _fmt, ##__VA_ARGS__) + +#define xe_notice(_xe, _fmt, ...) \ + xe_printk((_xe), notice, _fmt, ##__VA_ARGS__) + +#define xe_info(_xe, _fmt, ...) \ + xe_printk((_xe), info, _fmt, ##__VA_ARGS__) + +#define xe_dbg(_xe, _fmt, ...) \ + xe_printk((_xe), dbg, _fmt, ##__VA_ARGS__) + +#define xe_WARN_type(_xe, _type, _condition, _fmt, ...) \ + drm_WARN##_type(&(_xe)->drm, _condition, _fmt, ## __VA_ARGS__) + +#define xe_WARN(_xe, _condition, _fmt, ...) \ + xe_WARN_type((_xe),, _condition, __XE_PRINTK_FMT((_xe), _fmt, ## __VA_ARGS__)) + +#define xe_WARN_ONCE(_xe, _condition, _fmt, ...) \ + xe_WARN_type((_xe), _ONCE, _condition, __XE_PRINTK_FMT((_xe), _fmt, ## __VA_ARGS__)) + +#define xe_WARN_ON(_xe, _condition) \ + xe_WARN((_xe), _condition, "%s(%s)", "WARN_ON", __stringify(_condition)) + +#define xe_WARN_ON_ONCE(_xe, _condition) \ + xe_WARN_ONCE((_xe), _condition, "%s(%s)", "WARN_ON_ONCE", __stringify(_condition)) + +static inline void __xe_printfn_err(struct drm_printer *p, struct va_format *vaf) +{ + struct xe_device *xe = p->arg; + + xe_err(xe, "%pV", vaf); +} + +static inline void __xe_printfn_info(struct drm_printer *p, struct va_format *vaf) +{ + struct xe_device *xe = p->arg; + + xe_info(xe, "%pV", vaf); +} + +static inline void __xe_printfn_dbg(struct drm_printer *p, struct va_format *vaf) +{ + struct xe_device *xe = p->arg; + struct drm_printer ddp; + + /* + * The original xe_dbg() callsite annotations are useless here, + * redirect to the tweaked drm_dbg_printer() instead. + */ + ddp = drm_dbg_printer(&xe->drm, DRM_UT_DRIVER, NULL); + ddp.origin = p->origin; + + drm_printf(&ddp, __XE_PRINTK_FMT(xe, "%pV", vaf)); +} + +/** + * xe_err_printer - Construct a &drm_printer that outputs to xe_err() + * @xe: the &xe_device pointer to use in xe_err() + * + * Return: The &drm_printer object. + */ +static inline struct drm_printer xe_err_printer(struct xe_device *xe) +{ + struct drm_printer p = { + .printfn = __xe_printfn_err, + .arg = xe, + }; + return p; +} + +/** + * xe_info_printer - Construct a &drm_printer that outputs to xe_info() + * @xe: the &xe_device pointer to use in xe_info() + * + * Return: The &drm_printer object. + */ +static inline struct drm_printer xe_info_printer(struct xe_device *xe) +{ + struct drm_printer p = { + .printfn = __xe_printfn_info, + .arg = xe, + }; + return p; +} + +/** + * xe_dbg_printer - Construct a &drm_printer that outputs like xe_dbg() + * @xe: the &xe_device pointer to use in xe_dbg() + * + * Return: The &drm_printer object. + */ +static inline struct drm_printer xe_dbg_printer(struct xe_device *xe) +{ + struct drm_printer p = { + .printfn = __xe_printfn_dbg, + .arg = xe, + .origin = (const void *)_THIS_IP_, + }; + return p; +} + +#endif diff --git a/drivers/gpu/drm/xe/xe_psmi.c b/drivers/gpu/drm/xe/xe_psmi.c index a2c9ff5bfd59..45d142191d60 100644 --- a/drivers/gpu/drm/xe/xe_psmi.c +++ b/drivers/gpu/drm/xe/xe_psmi.c @@ -68,9 +68,7 @@ static void psmi_cleanup(struct xe_device *xe) static struct xe_bo *psmi_alloc_object(struct xe_device *xe, unsigned int id, size_t bo_size) { - struct xe_bo *bo = NULL; struct xe_tile *tile; - int err; if (!id || !bo_size) return NULL; @@ -78,22 +76,12 @@ static struct xe_bo *psmi_alloc_object(struct xe_device *xe, tile = &xe->tiles[id - 1]; /* VRAM: Allocate GEM object for the capture buffer */ - bo = xe_bo_create_locked(xe, tile, NULL, bo_size, - ttm_bo_type_kernel, - XE_BO_FLAG_VRAM_IF_DGFX(tile) | - XE_BO_FLAG_PINNED | - XE_BO_FLAG_PINNED_LATE_RESTORE | - XE_BO_FLAG_NEEDS_CPU_ACCESS); - - if (!IS_ERR(bo)) { - /* Buffer written by HW, ensure stays resident */ - err = xe_bo_pin(bo); - if (err) - bo = ERR_PTR(err); - xe_bo_unlock(bo); - } - - return bo; + return xe_bo_create_pin_range_novm(xe, tile, bo_size, 0, ~0ull, + ttm_bo_type_kernel, + XE_BO_FLAG_VRAM_IF_DGFX(tile) | + XE_BO_FLAG_PINNED | + XE_BO_FLAG_PINNED_LATE_RESTORE | + XE_BO_FLAG_NEEDS_CPU_ACCESS); } /* diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c index c129048a9a09..a1c88f9a6c76 100644 --- a/drivers/gpu/drm/xe/xe_pt.c +++ b/drivers/gpu/drm/xe/xe_pt.c @@ -13,17 +13,17 @@ #include "xe_drm_client.h" #include "xe_exec_queue.h" #include "xe_gt.h" -#include "xe_tlb_inval_job.h" #include "xe_migrate.h" #include "xe_pt_types.h" #include "xe_pt_walk.h" #include "xe_res_cursor.h" #include "xe_sched_job.h" -#include "xe_sync.h" #include "xe_svm.h" +#include "xe_sync.h" #include "xe_tlb_inval_job.h" #include "xe_trace.h" #include "xe_ttm_stolen_mgr.h" +#include "xe_userptr.h" #include "xe_vm.h" struct xe_pt_dir { @@ -89,6 +89,7 @@ static void xe_pt_free(struct xe_pt *pt) * @vm: The vm to create for. * @tile: The tile to create for. * @level: The page-table level. + * @exec: The drm_exec object used to lock the vm. * * Allocate and initialize a single struct xe_pt metadata structure. Also * create the corresponding page-table bo, but don't initialize it. If the @@ -100,7 +101,7 @@ static void xe_pt_free(struct xe_pt *pt) * error. */ struct xe_pt *xe_pt_create(struct xe_vm *vm, struct xe_tile *tile, - unsigned int level) + unsigned int level, struct drm_exec *exec) { struct xe_pt *pt; struct xe_bo *bo; @@ -124,9 +125,11 @@ struct xe_pt *xe_pt_create(struct xe_vm *vm, struct xe_tile *tile, bo_flags |= XE_BO_FLAG_PINNED_LATE_RESTORE; pt->level = level; + + drm_WARN_ON(&vm->xe->drm, IS_ERR_OR_NULL(exec)); bo = xe_bo_create_pin_map(vm->xe, tile, vm, SZ_4K, ttm_bo_type_kernel, - bo_flags); + bo_flags, exec); if (IS_ERR(bo)) { err = PTR_ERR(bo); goto err_kfree; @@ -590,7 +593,8 @@ xe_pt_stage_bind_entry(struct xe_ptw *parent, pgoff_t offset, if (covers || !*child) { u64 flags = 0; - xe_child = xe_pt_create(xe_walk->vm, xe_walk->tile, level - 1); + xe_child = xe_pt_create(xe_walk->vm, xe_walk->tile, level - 1, + xe_vm_validation_exec(vm)); if (IS_ERR(xe_child)) return PTR_ERR(xe_child); @@ -729,7 +733,7 @@ xe_pt_stage_bind(struct xe_tile *tile, struct xe_vma *vma, return -EAGAIN; } if (xe_svm_range_has_dma_mapping(range)) { - xe_res_first_dma(range->base.dma_addr, 0, + xe_res_first_dma(range->base.pages.dma_addr, 0, range->base.itree.last + 1 - range->base.itree.start, &curs); xe_svm_range_debug(range, "BIND PREPARE - MIXED"); @@ -760,8 +764,8 @@ xe_pt_stage_bind(struct xe_tile *tile, struct xe_vma *vma, if (!xe_vma_is_null(vma) && !range) { if (xe_vma_is_userptr(vma)) - xe_res_first_sg(to_userptr_vma(vma)->userptr.sg, 0, - xe_vma_size(vma), &curs); + xe_res_first_dma(to_userptr_vma(vma)->userptr.pages.dma_addr, 0, + xe_vma_size(vma), &curs); else if (xe_bo_is_vram(bo) || xe_bo_is_stolen(bo)) xe_res_first(bo->ttm.resource, xe_vma_bo_offset(vma), xe_vma_size(vma), &curs); @@ -914,7 +918,7 @@ bool xe_pt_zap_ptes(struct xe_tile *tile, struct xe_vma *vma) if (xe_vma_bo(vma)) xe_bo_assert_held(xe_vma_bo(vma)); else if (xe_vma_is_userptr(vma)) - lockdep_assert_held(&xe_vma_vm(vma)->userptr.notifier_lock); + lockdep_assert_held(&xe_vma_vm(vma)->svm.gpusvm.notifier_lock); if (!(pt_mask & BIT(tile->id))) return false; @@ -1049,7 +1053,7 @@ static void xe_pt_commit_locks_assert(struct xe_vma *vma) xe_pt_commit_prepare_locks_assert(vma); if (xe_vma_is_userptr(vma)) - lockdep_assert_held_read(&vm->userptr.notifier_lock); + xe_svm_assert_held_read(vm); } static void xe_pt_commit(struct xe_vma *vma, @@ -1376,6 +1380,7 @@ static int xe_pt_pre_commit(struct xe_migrate_pt_update *pt_update) pt_update_ops, rftree); } +#if IS_ENABLED(CONFIG_DRM_GPUSVM) #ifdef CONFIG_DRM_XE_USERPTR_INVAL_INJECT static bool xe_pt_userptr_inject_eagain(struct xe_userptr_vma *uvma) @@ -1406,7 +1411,7 @@ static int vma_check_userptr(struct xe_vm *vm, struct xe_vma *vma, struct xe_userptr_vma *uvma; unsigned long notifier_seq; - lockdep_assert_held_read(&vm->userptr.notifier_lock); + xe_svm_assert_held_read(vm); if (!xe_vma_is_userptr(vma)) return 0; @@ -1415,7 +1420,7 @@ static int vma_check_userptr(struct xe_vm *vm, struct xe_vma *vma, if (xe_pt_userptr_inject_eagain(uvma)) xe_vma_userptr_force_invalidate(uvma); - notifier_seq = uvma->userptr.notifier_seq; + notifier_seq = uvma->userptr.pages.notifier_seq; if (!mmu_interval_read_retry(&uvma->userptr.notifier, notifier_seq)) @@ -1431,12 +1436,12 @@ static int vma_check_userptr(struct xe_vm *vm, struct xe_vma *vma, return 0; } -static int op_check_userptr(struct xe_vm *vm, struct xe_vma_op *op, - struct xe_vm_pgtable_update_ops *pt_update) +static int op_check_svm_userptr(struct xe_vm *vm, struct xe_vma_op *op, + struct xe_vm_pgtable_update_ops *pt_update) { int err = 0; - lockdep_assert_held_read(&vm->userptr.notifier_lock); + xe_svm_assert_held_read(vm); switch (op->base.op) { case DRM_GPUVA_OP_MAP: @@ -1454,9 +1459,40 @@ static int op_check_userptr(struct xe_vm *vm, struct xe_vma_op *op, case DRM_GPUVA_OP_UNMAP: break; case DRM_GPUVA_OP_PREFETCH: - err = vma_check_userptr(vm, gpuva_to_vma(op->base.prefetch.va), - pt_update); + if (xe_vma_is_cpu_addr_mirror(gpuva_to_vma(op->base.prefetch.va))) { + struct xe_svm_range *range = op->map_range.range; + unsigned long i; + + xe_assert(vm->xe, + xe_vma_is_cpu_addr_mirror(gpuva_to_vma(op->base.prefetch.va))); + xa_for_each(&op->prefetch_range.range, i, range) { + xe_svm_range_debug(range, "PRE-COMMIT"); + + if (!xe_svm_range_pages_valid(range)) { + xe_svm_range_debug(range, "PRE-COMMIT - RETRY"); + return -ENODATA; + } + } + } else { + err = vma_check_userptr(vm, gpuva_to_vma(op->base.prefetch.va), pt_update); + } + break; +#if IS_ENABLED(CONFIG_DRM_XE_GPUSVM) + case DRM_GPUVA_OP_DRIVER: + if (op->subop == XE_VMA_SUBOP_MAP_RANGE) { + struct xe_svm_range *range = op->map_range.range; + + xe_assert(vm->xe, xe_vma_is_cpu_addr_mirror(op->map_range.vma)); + + xe_svm_range_debug(range, "PRE-COMMIT"); + + if (!xe_svm_range_pages_valid(range)) { + xe_svm_range_debug(range, "PRE-COMMIT - RETRY"); + return -EAGAIN; + } + } break; +#endif default: drm_warn(&vm->xe->drm, "NOT POSSIBLE"); } @@ -1464,7 +1500,7 @@ static int op_check_userptr(struct xe_vm *vm, struct xe_vma_op *op, return err; } -static int xe_pt_userptr_pre_commit(struct xe_migrate_pt_update *pt_update) +static int xe_pt_svm_userptr_pre_commit(struct xe_migrate_pt_update *pt_update) { struct xe_vm *vm = pt_update->vops->vm; struct xe_vma_ops *vops = pt_update->vops; @@ -1477,69 +1513,18 @@ static int xe_pt_userptr_pre_commit(struct xe_migrate_pt_update *pt_update) if (err) return err; - down_read(&vm->userptr.notifier_lock); + xe_svm_notifier_lock(vm); list_for_each_entry(op, &vops->list, link) { - err = op_check_userptr(vm, op, pt_update_ops); + err = op_check_svm_userptr(vm, op, pt_update_ops); if (err) { - up_read(&vm->userptr.notifier_lock); + xe_svm_notifier_unlock(vm); break; } } return err; } - -#if IS_ENABLED(CONFIG_DRM_XE_GPUSVM) -static int xe_pt_svm_pre_commit(struct xe_migrate_pt_update *pt_update) -{ - struct xe_vm *vm = pt_update->vops->vm; - struct xe_vma_ops *vops = pt_update->vops; - struct xe_vma_op *op; - unsigned long i; - int err; - - err = xe_pt_pre_commit(pt_update); - if (err) - return err; - - xe_svm_notifier_lock(vm); - - list_for_each_entry(op, &vops->list, link) { - struct xe_svm_range *range = NULL; - - if (op->subop == XE_VMA_SUBOP_UNMAP_RANGE) - continue; - - if (op->base.op == DRM_GPUVA_OP_PREFETCH) { - xe_assert(vm->xe, - xe_vma_is_cpu_addr_mirror(gpuva_to_vma(op->base.prefetch.va))); - xa_for_each(&op->prefetch_range.range, i, range) { - xe_svm_range_debug(range, "PRE-COMMIT"); - - if (!xe_svm_range_pages_valid(range)) { - xe_svm_range_debug(range, "PRE-COMMIT - RETRY"); - xe_svm_notifier_unlock(vm); - return -ENODATA; - } - } - } else { - xe_assert(vm->xe, xe_vma_is_cpu_addr_mirror(op->map_range.vma)); - xe_assert(vm->xe, op->subop == XE_VMA_SUBOP_MAP_RANGE); - range = op->map_range.range; - - xe_svm_range_debug(range, "PRE-COMMIT"); - - if (!xe_svm_range_pages_valid(range)) { - xe_svm_range_debug(range, "PRE-COMMIT - RETRY"); - xe_svm_notifier_unlock(vm); - return -EAGAIN; - } - } - } - - return 0; -} #endif struct xe_pt_stage_unbind_walk { @@ -1843,7 +1828,7 @@ static int bind_op_prepare(struct xe_vm *vm, struct xe_tile *tile, xe_vma_start(vma), xe_vma_end(vma)); ++pt_update_ops->current_op; - pt_update_ops->needs_userptr_lock |= xe_vma_is_userptr(vma); + pt_update_ops->needs_svm_lock |= xe_vma_is_userptr(vma); /* * If rebind, we have to invalidate TLB on !LR vms to invalidate @@ -1951,7 +1936,7 @@ static int unbind_op_prepare(struct xe_tile *tile, xe_pt_update_ops_rfence_interval(pt_update_ops, xe_vma_start(vma), xe_vma_end(vma)); ++pt_update_ops->current_op; - pt_update_ops->needs_userptr_lock |= xe_vma_is_userptr(vma); + pt_update_ops->needs_svm_lock |= xe_vma_is_userptr(vma); pt_update_ops->needs_invalidation = true; xe_pt_commit_prepare_unbind(vma, pt_op->entries, pt_op->num_entries); @@ -2199,7 +2184,7 @@ static void bind_op_commit(struct xe_vm *vm, struct xe_tile *tile, vma->tile_invalidated & ~BIT(tile->id)); vma->tile_staged &= ~BIT(tile->id); if (xe_vma_is_userptr(vma)) { - lockdep_assert_held_read(&vm->userptr.notifier_lock); + xe_svm_assert_held_read(vm); to_userptr_vma(vma)->userptr.initial_bind = true; } @@ -2235,7 +2220,7 @@ static void unbind_op_commit(struct xe_vm *vm, struct xe_tile *tile, if (!vma->tile_present) { list_del_init(&vma->combined_links.rebind); if (xe_vma_is_userptr(vma)) { - lockdep_assert_held_read(&vm->userptr.notifier_lock); + xe_svm_assert_held_read(vm); spin_lock(&vm->userptr.invalidated_lock); list_del_init(&to_userptr_vma(vma)->userptr.invalidate_link); @@ -2338,20 +2323,14 @@ static const struct xe_migrate_pt_update_ops migrate_ops = { .pre_commit = xe_pt_pre_commit, }; -static const struct xe_migrate_pt_update_ops userptr_migrate_ops = { - .populate = xe_vm_populate_pgtable, - .clear = xe_migrate_clear_pgtable_callback, - .pre_commit = xe_pt_userptr_pre_commit, -}; - -#if IS_ENABLED(CONFIG_DRM_XE_GPUSVM) -static const struct xe_migrate_pt_update_ops svm_migrate_ops = { +#if IS_ENABLED(CONFIG_DRM_GPUSVM) +static const struct xe_migrate_pt_update_ops svm_userptr_migrate_ops = { .populate = xe_vm_populate_pgtable, .clear = xe_migrate_clear_pgtable_callback, - .pre_commit = xe_pt_svm_pre_commit, + .pre_commit = xe_pt_svm_userptr_pre_commit, }; #else -static const struct xe_migrate_pt_update_ops svm_migrate_ops; +static const struct xe_migrate_pt_update_ops svm_userptr_migrate_ops; #endif static struct xe_dep_scheduler *to_dep_scheduler(struct xe_exec_queue *q, @@ -2389,9 +2368,7 @@ xe_pt_update_ops_run(struct xe_tile *tile, struct xe_vma_ops *vops) int err = 0, i; struct xe_migrate_pt_update update = { .ops = pt_update_ops->needs_svm_lock ? - &svm_migrate_ops : - pt_update_ops->needs_userptr_lock ? - &userptr_migrate_ops : + &svm_userptr_migrate_ops : &migrate_ops, .vops = vops, .tile_id = tile->id, @@ -2533,8 +2510,6 @@ xe_pt_update_ops_run(struct xe_tile *tile, struct xe_vma_ops *vops) if (pt_update_ops->needs_svm_lock) xe_svm_notifier_unlock(vm); - if (pt_update_ops->needs_userptr_lock) - up_read(&vm->userptr.notifier_lock); xe_tlb_inval_job_put(mjob); xe_tlb_inval_job_put(ijob); diff --git a/drivers/gpu/drm/xe/xe_pt.h b/drivers/gpu/drm/xe/xe_pt.h index 5ecf003d513c..4daeebaab5a1 100644 --- a/drivers/gpu/drm/xe/xe_pt.h +++ b/drivers/gpu/drm/xe/xe_pt.h @@ -10,6 +10,7 @@ #include "xe_pt_types.h" struct dma_fence; +struct drm_exec; struct xe_bo; struct xe_device; struct xe_exec_queue; @@ -29,7 +30,7 @@ struct xe_vma_ops; unsigned int xe_pt_shift(unsigned int level); struct xe_pt *xe_pt_create(struct xe_vm *vm, struct xe_tile *tile, - unsigned int level); + unsigned int level, struct drm_exec *exec); void xe_pt_populate_empty(struct xe_tile *tile, struct xe_vm *vm, struct xe_pt *pt); diff --git a/drivers/gpu/drm/xe/xe_pt_types.h b/drivers/gpu/drm/xe/xe_pt_types.h index 17cdd7c7e9f5..881f01e14db8 100644 --- a/drivers/gpu/drm/xe/xe_pt_types.h +++ b/drivers/gpu/drm/xe/xe_pt_types.h @@ -105,8 +105,6 @@ struct xe_vm_pgtable_update_ops { u32 current_op; /** @needs_svm_lock: Needs SVM lock */ bool needs_svm_lock; - /** @needs_userptr_lock: Needs userptr lock */ - bool needs_userptr_lock; /** @needs_invalidation: Needs invalidation */ bool needs_invalidation; /** diff --git a/drivers/gpu/drm/xe/xe_pxp.c b/drivers/gpu/drm/xe/xe_pxp.c index 3d62008c99f1..bdbdbbf6a678 100644 --- a/drivers/gpu/drm/xe/xe_pxp.c +++ b/drivers/gpu/drm/xe/xe_pxp.c @@ -688,6 +688,7 @@ start: return ret; } +ALLOW_ERROR_INJECTION(xe_pxp_exec_queue_add, ERRNO); static void __pxp_exec_queue_remove(struct xe_pxp *pxp, struct xe_exec_queue *q, bool lock) { diff --git a/drivers/gpu/drm/xe/xe_pxp_submit.c b/drivers/gpu/drm/xe/xe_pxp_submit.c index ca95f2a4d4ef..e60526e30030 100644 --- a/drivers/gpu/drm/xe/xe_pxp_submit.c +++ b/drivers/gpu/drm/xe/xe_pxp_submit.c @@ -54,8 +54,9 @@ static int allocate_vcs_execution_resources(struct xe_pxp *pxp) * Each termination is 16 DWORDS, so 4K is enough to contain a * termination for each sessions. */ - bo = xe_bo_create_pin_map(xe, tile, NULL, SZ_4K, ttm_bo_type_kernel, - XE_BO_FLAG_SYSTEM | XE_BO_FLAG_PINNED | XE_BO_FLAG_GGTT); + bo = xe_bo_create_pin_map_novm(xe, tile, SZ_4K, ttm_bo_type_kernel, + XE_BO_FLAG_SYSTEM | XE_BO_FLAG_PINNED | XE_BO_FLAG_GGTT, + false); if (IS_ERR(bo)) { err = PTR_ERR(bo); goto out_queue; @@ -87,7 +88,9 @@ static int allocate_gsc_client_resources(struct xe_gt *gt, { struct xe_tile *tile = gt_to_tile(gt); struct xe_device *xe = tile_to_xe(tile); + struct xe_validation_ctx ctx; struct xe_hw_engine *hwe; + struct drm_exec exec; struct xe_vm *vm; struct xe_bo *bo; struct xe_exec_queue *q; @@ -106,15 +109,26 @@ static int allocate_gsc_client_resources(struct xe_gt *gt, return PTR_ERR(vm); /* We allocate a single object for the batch and the in/out memory */ - xe_vm_lock(vm, false); - bo = xe_bo_create_pin_map(xe, tile, vm, PXP_BB_SIZE + inout_size * 2, - ttm_bo_type_kernel, - XE_BO_FLAG_SYSTEM | XE_BO_FLAG_PINNED | XE_BO_FLAG_NEEDS_UC); - xe_vm_unlock(vm); - if (IS_ERR(bo)) { - err = PTR_ERR(bo); - goto vm_out; + + xe_validation_guard(&ctx, &xe->val, &exec, (struct xe_val_flags){}, err) { + err = xe_vm_drm_exec_lock(vm, &exec); + drm_exec_retry_on_contention(&exec); + if (err) + break; + + bo = xe_bo_create_pin_map(xe, tile, vm, PXP_BB_SIZE + inout_size * 2, + ttm_bo_type_kernel, + XE_BO_FLAG_SYSTEM | XE_BO_FLAG_PINNED | + XE_BO_FLAG_NEEDS_UC, &exec); + drm_exec_retry_on_contention(&exec); + if (IS_ERR(bo)) { + err = PTR_ERR(bo); + xe_validation_retry_on_oom(&ctx, &err); + break; + } } + if (err) + goto vm_out; fence = xe_vm_bind_kernel_bo(vm, bo, NULL, 0, XE_CACHE_WB); if (IS_ERR(fence)) { diff --git a/drivers/gpu/drm/xe/xe_query.c b/drivers/gpu/drm/xe/xe_query.c index 4dbe5732cb7f..e1b603aba61b 100644 --- a/drivers/gpu/drm/xe/xe_query.c +++ b/drivers/gpu/drm/xe/xe_query.c @@ -21,6 +21,7 @@ #include "xe_force_wake.h" #include "xe_ggtt.h" #include "xe_gt.h" +#include "xe_gt_topology.h" #include "xe_guc_hwconfig.h" #include "xe_macros.h" #include "xe_mmio.h" @@ -477,7 +478,7 @@ static size_t calc_topo_query_size(struct xe_device *xe) sizeof_field(struct xe_gt, fuse_topo.eu_mask_per_dss); /* L3bank mask may not be available for some GTs */ - if (!XE_GT_WA(gt, no_media_l3)) + if (xe_gt_topology_report_l3(gt)) query_size += sizeof(struct drm_xe_query_topology_mask) + sizeof_field(struct xe_gt, fuse_topo.l3_bank_mask); } @@ -540,7 +541,7 @@ static int query_gt_topology(struct xe_device *xe, * mask, then it's better to omit L3 from the query rather than * reporting bogus or zeroed information to userspace. */ - if (!XE_GT_WA(gt, no_media_l3)) { + if (xe_gt_topology_report_l3(gt)) { topo.type = DRM_XE_TOPO_L3_BANK; err = copy_mask(&query_ptr, &topo, gt->fuse_topo.l3_bank_mask, sizeof(gt->fuse_topo.l3_bank_mask)); diff --git a/drivers/gpu/drm/xe/xe_rtp.c b/drivers/gpu/drm/xe/xe_rtp.c index 47ea1521dc80..b5f430d59f80 100644 --- a/drivers/gpu/drm/xe/xe_rtp.c +++ b/drivers/gpu/drm/xe/xe_rtp.c @@ -370,3 +370,9 @@ bool xe_rtp_match_psmi_enabled(const struct xe_gt *gt, { return xe_configfs_get_psmi_enabled(to_pci_dev(gt_to_xe(gt)->drm.dev)); } + +bool xe_rtp_match_gt_has_discontiguous_dss_groups(const struct xe_gt *gt, + const struct xe_hw_engine *hwe) +{ + return xe_gt_has_discontiguous_dss_groups(gt); +} diff --git a/drivers/gpu/drm/xe/xe_rtp.h b/drivers/gpu/drm/xe/xe_rtp.h index 7951fefdbe04..ac12ddf6cde6 100644 --- a/drivers/gpu/drm/xe/xe_rtp.h +++ b/drivers/gpu/drm/xe/xe_rtp.h @@ -480,4 +480,7 @@ bool xe_rtp_match_not_sriov_vf(const struct xe_gt *gt, bool xe_rtp_match_psmi_enabled(const struct xe_gt *gt, const struct xe_hw_engine *hwe); +bool xe_rtp_match_gt_has_discontiguous_dss_groups(const struct xe_gt *gt, + const struct xe_hw_engine *hwe); + #endif diff --git a/drivers/gpu/drm/xe/xe_sriov.c b/drivers/gpu/drm/xe/xe_sriov.c index 87911fb4eea7..7d2d6de2aabf 100644 --- a/drivers/gpu/drm/xe/xe_sriov.c +++ b/drivers/gpu/drm/xe/xe_sriov.c @@ -160,19 +160,15 @@ const char *xe_sriov_function_name(unsigned int n, char *buf, size_t size) } /** - * xe_sriov_late_init() - SR-IOV late initialization functions. + * xe_sriov_init_late() - SR-IOV late initialization functions. * @xe: the &xe_device to initialize * - * On VF this function will initialize code for CCS migration. - * * Return: 0 on success or a negative error code on failure. */ -int xe_sriov_late_init(struct xe_device *xe) +int xe_sriov_init_late(struct xe_device *xe) { - int err = 0; - - if (IS_VF_CCS_INIT_NEEDED(xe)) - err = xe_sriov_vf_ccs_init(xe); + if (IS_SRIOV_VF(xe)) + return xe_sriov_vf_init_late(xe); - return err; + return 0; } diff --git a/drivers/gpu/drm/xe/xe_sriov.h b/drivers/gpu/drm/xe/xe_sriov.h index 0e0c1abf2d14..6db45df55615 100644 --- a/drivers/gpu/drm/xe/xe_sriov.h +++ b/drivers/gpu/drm/xe/xe_sriov.h @@ -18,7 +18,7 @@ const char *xe_sriov_function_name(unsigned int n, char *buf, size_t len); void xe_sriov_probe_early(struct xe_device *xe); void xe_sriov_print_info(struct xe_device *xe, struct drm_printer *p); int xe_sriov_init(struct xe_device *xe); -int xe_sriov_late_init(struct xe_device *xe); +int xe_sriov_init_late(struct xe_device *xe); static inline enum xe_sriov_mode xe_device_sriov_mode(const struct xe_device *xe) { diff --git a/drivers/gpu/drm/xe/xe_sriov_vf.c b/drivers/gpu/drm/xe/xe_sriov_vf.c index 5de81f213d83..cdd9f8e78b2a 100644 --- a/drivers/gpu/drm/xe/xe_sriov_vf.c +++ b/drivers/gpu/drm/xe/xe_sriov_vf.c @@ -3,6 +3,7 @@ * Copyright © 2023-2024 Intel Corporation */ +#include <drm/drm_debugfs.h> #include <drm/drm_managed.h> #include "xe_assert.h" @@ -10,6 +11,7 @@ #include "xe_gt.h" #include "xe_gt_sriov_printk.h" #include "xe_gt_sriov_vf.h" +#include "xe_guc.h" #include "xe_guc_ct.h" #include "xe_guc_submit.h" #include "xe_irq.h" @@ -18,6 +20,7 @@ #include "xe_sriov.h" #include "xe_sriov_printk.h" #include "xe_sriov_vf.h" +#include "xe_sriov_vf_ccs.h" #include "xe_tile_sriov_vf.h" /** @@ -127,16 +130,66 @@ * | | | */ -static bool vf_migration_supported(struct xe_device *xe) +/** + * xe_sriov_vf_migration_supported - Report whether SR-IOV VF migration is + * supported or not. + * @xe: the &xe_device to check + * + * Returns: true if VF migration is supported, false otherwise. + */ +bool xe_sriov_vf_migration_supported(struct xe_device *xe) +{ + xe_assert(xe, IS_SRIOV_VF(xe)); + return xe->sriov.vf.migration.enabled; +} + +static void vf_disable_migration(struct xe_device *xe, const char *fmt, ...) +{ + struct va_format vaf; + va_list va_args; + + xe_assert(xe, IS_SRIOV_VF(xe)); + + va_start(va_args, fmt); + vaf.fmt = fmt; + vaf.va = &va_args; + xe_sriov_notice(xe, "migration disabled: %pV\n", &vaf); + va_end(va_args); + + xe->sriov.vf.migration.enabled = false; +} + +static void migration_worker_func(struct work_struct *w); + +static void vf_migration_init_early(struct xe_device *xe) { /* * TODO: Add conditions to allow specific platforms, when they're * supported at production quality. */ - return IS_ENABLED(CONFIG_DRM_XE_DEBUG); -} + if (!IS_ENABLED(CONFIG_DRM_XE_DEBUG)) + return vf_disable_migration(xe, + "experimental feature not available on production builds"); + + if (GRAPHICS_VER(xe) < 20) + return vf_disable_migration(xe, "requires gfx version >= 20, but only %u found", + GRAPHICS_VER(xe)); + + if (!IS_DGFX(xe)) { + struct xe_uc_fw_version guc_version; + + xe_gt_sriov_vf_guc_versions(xe_device_get_gt(xe, 0), NULL, &guc_version); + if (MAKE_GUC_VER_STRUCT(guc_version) < MAKE_GUC_VER(1, 23, 0)) + return vf_disable_migration(xe, + "CCS migration requires GuC ABI >= 1.23 but only %u.%u found", + guc_version.major, guc_version.minor); + } -static void migration_worker_func(struct work_struct *w); + INIT_WORK(&xe->sriov.vf.migration.worker, migration_worker_func); + + xe->sriov.vf.migration.enabled = true; + xe_sriov_dbg(xe, "migration support enabled\n"); +} /** * xe_sriov_vf_init_early - Initialize SR-IOV VF specific data. @@ -144,10 +197,7 @@ static void migration_worker_func(struct work_struct *w); */ void xe_sriov_vf_init_early(struct xe_device *xe) { - INIT_WORK(&xe->sriov.vf.migration.worker, migration_worker_func); - - if (!vf_migration_supported(xe)) - xe_sriov_info(xe, "migration not supported by this module version\n"); + vf_migration_init_early(xe); } /** @@ -302,8 +352,8 @@ static void vf_post_migration_recovery(struct xe_device *xe) xe_pm_runtime_get(xe); vf_post_migration_shutdown(xe); - if (!vf_migration_supported(xe)) { - xe_sriov_err(xe, "migration not supported by this module version\n"); + if (!xe_sriov_vf_migration_supported(xe)) { + xe_sriov_err(xe, "migration is not supported\n"); err = -ENOTRECOVERABLE; goto fail; } @@ -378,3 +428,48 @@ void xe_sriov_vf_start_migration_recovery(struct xe_device *xe) drm_info(&xe->drm, "VF migration recovery %s\n", started ? "scheduled" : "already in progress"); } + +/** + * xe_sriov_vf_init_late() - SR-IOV VF late initialization functions. + * @xe: the &xe_device to initialize + * + * This function initializes code for CCS migration. + * + * Return: 0 on success or a negative error code on failure. + */ +int xe_sriov_vf_init_late(struct xe_device *xe) +{ + int err = 0; + + if (xe_sriov_vf_migration_supported(xe)) + err = xe_sriov_vf_ccs_init(xe); + + return err; +} + +static int sa_info_vf_ccs(struct seq_file *m, void *data) +{ + struct drm_info_node *node = m->private; + struct xe_device *xe = to_xe_device(node->minor->dev); + struct drm_printer p = drm_seq_file_printer(m); + + xe_sriov_vf_ccs_print(xe, &p); + return 0; +} + +static const struct drm_info_list debugfs_list[] = { + { .name = "sa_info_vf_ccs", .show = sa_info_vf_ccs }, +}; + +/** + * xe_sriov_vf_debugfs_register - Register VF debugfs attributes. + * @xe: the &xe_device + * @root: the root &dentry + * + * Prepare debugfs attributes exposed by the VF. + */ +void xe_sriov_vf_debugfs_register(struct xe_device *xe, struct dentry *root) +{ + drm_debugfs_create_files(debugfs_list, ARRAY_SIZE(debugfs_list), + root, xe->drm.primary); +} diff --git a/drivers/gpu/drm/xe/xe_sriov_vf.h b/drivers/gpu/drm/xe/xe_sriov_vf.h index 7b8622cff2b7..9e752105ec2a 100644 --- a/drivers/gpu/drm/xe/xe_sriov_vf.h +++ b/drivers/gpu/drm/xe/xe_sriov_vf.h @@ -6,9 +6,15 @@ #ifndef _XE_SRIOV_VF_H_ #define _XE_SRIOV_VF_H_ +#include <linux/types.h> + +struct dentry; struct xe_device; void xe_sriov_vf_init_early(struct xe_device *xe); +int xe_sriov_vf_init_late(struct xe_device *xe); void xe_sriov_vf_start_migration_recovery(struct xe_device *xe); +bool xe_sriov_vf_migration_supported(struct xe_device *xe); +void xe_sriov_vf_debugfs_register(struct xe_device *xe, struct dentry *root); #endif diff --git a/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c b/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c index 4872e43eb440..8dec616c37c9 100644 --- a/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c +++ b/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c @@ -13,8 +13,10 @@ #include "xe_guc_submit.h" #include "xe_lrc.h" #include "xe_migrate.h" +#include "xe_pm.h" #include "xe_sa.h" #include "xe_sriov_printk.h" +#include "xe_sriov_vf.h" #include "xe_sriov_vf_ccs.h" #include "xe_sriov_vf_ccs_types.h" @@ -135,7 +137,7 @@ static u64 get_ccs_bb_pool_size(struct xe_device *xe) return round_up(bb_pool_size * 2, SZ_1M); } -static int alloc_bb_pool(struct xe_tile *tile, struct xe_tile_vf_ccs *ctx) +static int alloc_bb_pool(struct xe_tile *tile, struct xe_sriov_vf_ccs_ctx *ctx) { struct xe_device *xe = tile_to_xe(tile); struct xe_sa_manager *sa_manager; @@ -167,7 +169,7 @@ static int alloc_bb_pool(struct xe_tile *tile, struct xe_tile_vf_ccs *ctx) return 0; } -static void ccs_rw_update_ring(struct xe_tile_vf_ccs *ctx) +static void ccs_rw_update_ring(struct xe_sriov_vf_ccs_ctx *ctx) { u64 addr = xe_sa_manager_gpu_addr(ctx->mem.ccs_bb_pool); struct xe_lrc *lrc = xe_exec_queue_lrc(ctx->mig_q); @@ -184,9 +186,8 @@ static void ccs_rw_update_ring(struct xe_tile_vf_ccs *ctx) xe_lrc_set_ring_tail(lrc, lrc->ring.tail); } -static int register_save_restore_context(struct xe_tile_vf_ccs *ctx) +static int register_save_restore_context(struct xe_sriov_vf_ccs_ctx *ctx) { - int err = -EINVAL; int ctx_type; switch (ctx->ctx_id) { @@ -197,10 +198,10 @@ static int register_save_restore_context(struct xe_tile_vf_ccs *ctx) ctx_type = GUC_CONTEXT_COMPRESSION_RESTORE; break; default: - return err; + return -EINVAL; } - xe_guc_register_exec_queue(ctx->mig_q, ctx_type); + xe_guc_register_vf_exec_queue(ctx->mig_q, ctx_type); return 0; } @@ -215,16 +216,14 @@ static int register_save_restore_context(struct xe_tile_vf_ccs *ctx) */ int xe_sriov_vf_ccs_register_context(struct xe_device *xe) { - struct xe_tile *tile = xe_device_get_root_tile(xe); enum xe_sriov_vf_ccs_rw_ctxs ctx_id; - struct xe_tile_vf_ccs *ctx; + struct xe_sriov_vf_ccs_ctx *ctx; int err; - if (!IS_VF_CCS_READY(xe)) - return 0; + xe_assert(xe, IS_VF_CCS_READY(xe)); for_each_ccs_rw_ctx(ctx_id) { - ctx = &tile->sriov.vf.ccs[ctx_id]; + ctx = &xe->sriov.vf.ccs.contexts[ctx_id]; err = register_save_restore_context(ctx); if (err) return err; @@ -235,7 +234,7 @@ int xe_sriov_vf_ccs_register_context(struct xe_device *xe) static void xe_sriov_vf_ccs_fini(void *arg) { - struct xe_tile_vf_ccs *ctx = arg; + struct xe_sriov_vf_ccs_ctx *ctx = arg; struct xe_lrc *lrc = xe_exec_queue_lrc(ctx->mig_q); /* @@ -259,17 +258,19 @@ int xe_sriov_vf_ccs_init(struct xe_device *xe) { struct xe_tile *tile = xe_device_get_root_tile(xe); enum xe_sriov_vf_ccs_rw_ctxs ctx_id; - struct xe_tile_vf_ccs *ctx; + struct xe_sriov_vf_ccs_ctx *ctx; struct xe_exec_queue *q; u32 flags; int err; xe_assert(xe, IS_SRIOV_VF(xe)); - xe_assert(xe, !IS_DGFX(xe)); - xe_assert(xe, xe_device_has_flat_ccs(xe)); + xe_assert(xe, xe_sriov_vf_migration_supported(xe)); + + if (IS_DGFX(xe) || !xe_device_has_flat_ccs(xe)) + return 0; for_each_ccs_rw_ctx(ctx_id) { - ctx = &tile->sriov.vf.ccs[ctx_id]; + ctx = &xe->sriov.vf.ccs.contexts[ctx_id]; ctx->ctx_id = ctx_id; flags = EXEC_QUEUE_FLAG_KERNEL | @@ -324,13 +325,12 @@ int xe_sriov_vf_ccs_attach_bo(struct xe_bo *bo) { struct xe_device *xe = xe_bo_device(bo); enum xe_sriov_vf_ccs_rw_ctxs ctx_id; - struct xe_tile_vf_ccs *ctx; + struct xe_sriov_vf_ccs_ctx *ctx; struct xe_tile *tile; struct xe_bb *bb; int err = 0; - if (!IS_VF_CCS_READY(xe)) - return 0; + xe_assert(xe, IS_VF_CCS_READY(xe)); tile = xe_device_get_root_tile(xe); @@ -339,7 +339,7 @@ int xe_sriov_vf_ccs_attach_bo(struct xe_bo *bo) /* bb should be NULL here. Assert if not NULL */ xe_assert(xe, !bb); - ctx = &tile->sriov.vf.ccs[ctx_id]; + ctx = &xe->sriov.vf.ccs.contexts[ctx_id]; err = xe_migrate_ccs_rw_copy(tile, ctx->mig_q, bo, ctx_id); } return err; @@ -361,7 +361,9 @@ int xe_sriov_vf_ccs_detach_bo(struct xe_bo *bo) enum xe_sriov_vf_ccs_rw_ctxs ctx_id; struct xe_bb *bb; - if (!IS_VF_CCS_READY(xe)) + xe_assert(xe, IS_VF_CCS_READY(xe)); + + if (!xe_bo_has_valid_ccs_bb(bo)) return 0; for_each_ccs_rw_ctx(ctx_id) { @@ -375,3 +377,34 @@ int xe_sriov_vf_ccs_detach_bo(struct xe_bo *bo) } return 0; } + +/** + * xe_sriov_vf_ccs_print - Print VF CCS details. + * @xe: the &xe_device + * @p: the &drm_printer + * + * This function is for VF use only. + */ +void xe_sriov_vf_ccs_print(struct xe_device *xe, struct drm_printer *p) +{ + struct xe_sa_manager *bb_pool; + enum xe_sriov_vf_ccs_rw_ctxs ctx_id; + + if (!IS_VF_CCS_READY(xe)) + return; + + xe_pm_runtime_get(xe); + + for_each_ccs_rw_ctx(ctx_id) { + bb_pool = xe->sriov.vf.ccs.contexts[ctx_id].mem.ccs_bb_pool; + if (!bb_pool) + break; + + drm_printf(p, "ccs %s bb suballoc info\n", ctx_id ? "write" : "read"); + drm_printf(p, "-------------------------\n"); + drm_suballoc_dump_debug_info(&bb_pool->base, p, xe_sa_manager_gpu_addr(bb_pool)); + drm_puts(p, "\n"); + } + + xe_pm_runtime_put(xe); +} diff --git a/drivers/gpu/drm/xe/xe_sriov_vf_ccs.h b/drivers/gpu/drm/xe/xe_sriov_vf_ccs.h index 1f1baf685fec..0745c0ff0228 100644 --- a/drivers/gpu/drm/xe/xe_sriov_vf_ccs.h +++ b/drivers/gpu/drm/xe/xe_sriov_vf_ccs.h @@ -6,6 +6,11 @@ #ifndef _XE_SRIOV_VF_CCS_H_ #define _XE_SRIOV_VF_CCS_H_ +#include "xe_device_types.h" +#include "xe_sriov.h" +#include "xe_sriov_vf_ccs_types.h" + +struct drm_printer; struct xe_device; struct xe_bo; @@ -13,5 +18,17 @@ int xe_sriov_vf_ccs_init(struct xe_device *xe); int xe_sriov_vf_ccs_attach_bo(struct xe_bo *bo); int xe_sriov_vf_ccs_detach_bo(struct xe_bo *bo); int xe_sriov_vf_ccs_register_context(struct xe_device *xe); +void xe_sriov_vf_ccs_print(struct xe_device *xe, struct drm_printer *p); + +static inline bool xe_sriov_vf_ccs_ready(struct xe_device *xe) +{ + xe_assert(xe, IS_SRIOV_VF(xe)); + return xe->sriov.vf.ccs.initialized; +} + +#define IS_VF_CCS_READY(xe) ({ \ + struct xe_device *xe__ = (xe); \ + IS_SRIOV_VF(xe__) && xe_sriov_vf_ccs_ready(xe__); \ + }) #endif diff --git a/drivers/gpu/drm/xe/xe_sriov_vf_ccs_types.h b/drivers/gpu/drm/xe/xe_sriov_vf_ccs_types.h index 93435a6f4cb6..22c499943d2a 100644 --- a/drivers/gpu/drm/xe/xe_sriov_vf_ccs_types.h +++ b/drivers/gpu/drm/xe/xe_sriov_vf_ccs_types.h @@ -6,48 +6,46 @@ #ifndef _XE_SRIOV_VF_CCS_TYPES_H_ #define _XE_SRIOV_VF_CCS_TYPES_H_ +#include <linux/types.h> + #define for_each_ccs_rw_ctx(id__) \ for ((id__) = 0; (id__) < XE_SRIOV_VF_CCS_CTX_COUNT; (id__)++) -#define IS_VF_CCS_READY(xe) ({ \ - struct xe_device *___xe = (xe); \ - xe_assert(___xe, IS_SRIOV_VF(___xe)); \ - ___xe->sriov.vf.ccs.initialized; \ - }) - -#define IS_VF_CCS_INIT_NEEDED(xe) ({\ - struct xe_device *___xe = (xe); \ - IS_SRIOV_VF(___xe) && !IS_DGFX(___xe) && \ - xe_device_has_flat_ccs(___xe) && GRAPHICS_VER(___xe) >= 20; \ - }) - enum xe_sriov_vf_ccs_rw_ctxs { XE_SRIOV_VF_CCS_READ_CTX, XE_SRIOV_VF_CCS_WRITE_CTX, XE_SRIOV_VF_CCS_CTX_COUNT }; -#define IS_VF_CCS_BB_VALID(xe, bo) ({ \ - struct xe_device *___xe = (xe); \ - struct xe_bo *___bo = (bo); \ - IS_SRIOV_VF(___xe) && \ - ___bo->bb_ccs[XE_SRIOV_VF_CCS_READ_CTX] && \ - ___bo->bb_ccs[XE_SRIOV_VF_CCS_WRITE_CTX]; \ - }) - struct xe_migrate; struct xe_sa_manager; -struct xe_tile_vf_ccs { - /** @id: Id to which context it belongs to */ +/** + * struct xe_sriov_vf_ccs_ctx - VF CCS migration context data. + */ +struct xe_sriov_vf_ccs_ctx { + /** @ctx_id: Id to which context it belongs to */ enum xe_sriov_vf_ccs_rw_ctxs ctx_id; + /** @mig_q: exec queues used for migration */ struct xe_exec_queue *mig_q; + /** @mem: memory data */ struct { - /** @ccs_bb_pool: Pool from which batch buffers are allocated. */ + /** @mem.ccs_bb_pool: Pool from which batch buffers are allocated. */ struct xe_sa_manager *ccs_bb_pool; } mem; }; +/** + * struct xe_sriov_vf_ccs - The VF CCS migration support data. + */ +struct xe_sriov_vf_ccs { + /** @contexts: CCS read and write contexts for VF. */ + struct xe_sriov_vf_ccs_ctx contexts[XE_SRIOV_VF_CCS_CTX_COUNT]; + + /** @initialized: Initialization of VF CCS is completed or not. */ + bool initialized; +}; + #endif diff --git a/drivers/gpu/drm/xe/xe_sriov_vf_types.h b/drivers/gpu/drm/xe/xe_sriov_vf_types.h index 24a873c50c49..426cc5841958 100644 --- a/drivers/gpu/drm/xe/xe_sriov_vf_types.h +++ b/drivers/gpu/drm/xe/xe_sriov_vf_types.h @@ -9,6 +9,8 @@ #include <linux/types.h> #include <linux/workqueue_types.h> +#include "xe_sriov_vf_ccs_types.h" + /** * struct xe_sriov_vf_relay_version - PF ABI version details. */ @@ -35,13 +37,15 @@ struct xe_device_vf { struct work_struct worker; /** @migration.gt_flags: Per-GT request flags for VF migration recovery */ unsigned long gt_flags; + /** + * @migration.enabled: flag indicating if migration support + * was enabled or not due to missing prerequisites + */ + bool enabled; } migration; /** @ccs: VF CCS state data */ - struct { - /** @ccs.initialized: Initilalization of VF CCS is completed or not */ - bool initialized; - } ccs; + struct xe_sriov_vf_ccs ccs; }; #endif diff --git a/drivers/gpu/drm/xe/xe_survivability_mode.c b/drivers/gpu/drm/xe/xe_survivability_mode.c index 53c5af4b810c..1662bfddd4bc 100644 --- a/drivers/gpu/drm/xe/xe_survivability_mode.c +++ b/drivers/gpu/drm/xe/xe_survivability_mode.c @@ -44,6 +44,8 @@ * * # echo 1 > /sys/kernel/config/xe/0000:03:00.0/survivability_mode * + * It is the responsibility of the user to clear the mode once firmware flash is complete. + * * Refer :ref:`xe_configfs` for more details on how to use configfs * * Survivability mode is indicated by the below admin-only readable sysfs which provides additional @@ -180,7 +182,6 @@ static void xe_survivability_mode_fini(void *arg) struct pci_dev *pdev = to_pci_dev(xe->drm.dev); struct device *dev = &pdev->dev; - xe_configfs_clear_survivability_mode(pdev); sysfs_remove_file(&dev->kobj, &dev_attr_survivability_mode.attr); } @@ -288,19 +289,10 @@ bool xe_survivability_mode_is_requested(struct xe_device *xe) u32 data; bool survivability_mode; - if (!IS_DGFX(xe) || IS_SRIOV_VF(xe)) + if (!IS_DGFX(xe) || IS_SRIOV_VF(xe) || xe->info.platform < XE_BATTLEMAGE) return false; survivability_mode = xe_configfs_get_survivability_mode(pdev); - - if (xe->info.platform < XE_BATTLEMAGE) { - if (survivability_mode) { - dev_err(&pdev->dev, "Survivability Mode is not supported on this card\n"); - xe_configfs_clear_survivability_mode(pdev); - } - return false; - } - /* Enable survivability mode if set via configfs */ if (survivability_mode) return true; diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c index 76c6d74c1208..7f2f1f041f1d 100644 --- a/drivers/gpu/drm/xe/xe_svm.c +++ b/drivers/gpu/drm/xe/xe_svm.c @@ -6,6 +6,7 @@ #include <drm/drm_drv.h> #include "xe_bo.h" +#include "xe_exec_queue_types.h" #include "xe_gt_stats.h" #include "xe_migrate.h" #include "xe_module.h" @@ -25,9 +26,9 @@ static bool xe_svm_range_in_vram(struct xe_svm_range *range) * memory. */ - struct drm_gpusvm_range_flags flags = { + struct drm_gpusvm_pages_flags flags = { /* Pairs with WRITE_ONCE in drm_gpusvm.c */ - .__flags = READ_ONCE(range->base.flags.__flags), + .__flags = READ_ONCE(range->base.pages.flags.__flags), }; return flags.has_devmem_pages; @@ -49,15 +50,15 @@ static struct xe_vm *range_to_vm(struct drm_gpusvm_range *r) return gpusvm_to_vm(r->gpusvm); } -#define range_debug(r__, operaton__) \ +#define range_debug(r__, operation__) \ vm_dbg(&range_to_vm(&(r__)->base)->xe->drm, \ "%s: asid=%u, gpusvm=%p, vram=%d,%d, seqno=%lu, " \ "start=0x%014lx, end=0x%014lx, size=%lu", \ - (operaton__), range_to_vm(&(r__)->base)->usm.asid, \ + (operation__), range_to_vm(&(r__)->base)->usm.asid, \ (r__)->base.gpusvm, \ xe_svm_range_in_vram((r__)) ? 1 : 0, \ xe_svm_range_has_vram_binding((r__)) ? 1 : 0, \ - (r__)->base.notifier_seq, \ + (r__)->base.pages.notifier_seq, \ xe_svm_range_start((r__)), xe_svm_range_end((r__)), \ xe_svm_range_size((r__))) @@ -112,6 +113,11 @@ xe_svm_garbage_collector_add_range(struct xe_vm *vm, struct xe_svm_range *range, &vm->svm.garbage_collector.work); } +static void xe_svm_tlb_inval_count_stats_incr(struct xe_gt *gt) +{ + xe_gt_stats_incr(gt, XE_GT_STATS_ID_SVM_TLB_INVAL_COUNT, 1); +} + static u8 xe_svm_range_notifier_event_begin(struct xe_vm *vm, struct drm_gpusvm_range *r, const struct mmu_notifier_range *mmu_range, @@ -128,7 +134,7 @@ xe_svm_range_notifier_event_begin(struct xe_vm *vm, struct drm_gpusvm_range *r, range_debug(range, "NOTIFIER"); /* Skip if already unmapped or if no binding exist */ - if (range->base.flags.unmapped || !range->tile_present) + if (range->base.pages.flags.unmapped || !range->tile_present) return 0; range_debug(range, "NOTIFIER - EXECUTE"); @@ -144,13 +150,19 @@ xe_svm_range_notifier_event_begin(struct xe_vm *vm, struct drm_gpusvm_range *r, */ for_each_tile(tile, xe, id) if (xe_pt_zap_ptes_range(tile, vm, range)) { - tile_mask |= BIT(id); /* * WRITE_ONCE pairs with READ_ONCE in * xe_vm_has_valid_gpu_mapping() */ WRITE_ONCE(range->tile_invalidated, range->tile_invalidated | BIT(id)); + + if (!(tile_mask & BIT(id))) { + xe_svm_tlb_inval_count_stats_incr(tile->primary_gt); + if (tile->media_gt) + xe_svm_tlb_inval_count_stats_incr(tile->media_gt); + tile_mask |= BIT(id); + } } return tile_mask; @@ -170,6 +182,24 @@ xe_svm_range_notifier_event_end(struct xe_vm *vm, struct drm_gpusvm_range *r, mmu_range); } +static s64 xe_svm_stats_ktime_us_delta(ktime_t start) +{ + return IS_ENABLED(CONFIG_DEBUG_FS) ? + ktime_us_delta(ktime_get(), start) : 0; +} + +static void xe_svm_tlb_inval_us_stats_incr(struct xe_gt *gt, ktime_t start) +{ + s64 us_delta = xe_svm_stats_ktime_us_delta(start); + + xe_gt_stats_incr(gt, XE_GT_STATS_ID_SVM_TLB_INVAL_US, us_delta); +} + +static ktime_t xe_svm_stats_ktime_get(void) +{ + return IS_ENABLED(CONFIG_DEBUG_FS) ? ktime_get() : 0; +} + static void xe_svm_invalidate(struct drm_gpusvm *gpusvm, struct drm_gpusvm_notifier *notifier, const struct mmu_notifier_range *mmu_range) @@ -177,8 +207,10 @@ static void xe_svm_invalidate(struct drm_gpusvm *gpusvm, struct xe_vm *vm = gpusvm_to_vm(gpusvm); struct xe_device *xe = vm->xe; struct drm_gpusvm_range *r, *first; + struct xe_tile *tile; + ktime_t start = xe_svm_stats_ktime_get(); u64 adj_start = mmu_range->start, adj_end = mmu_range->end; - u8 tile_mask = 0; + u8 tile_mask = 0, id; long err; xe_svm_assert_in_notifier(vm); @@ -231,6 +263,13 @@ range_notifier_event_end: r = first; drm_gpusvm_for_each_range(r, notifier, adj_start, adj_end) xe_svm_range_notifier_event_end(vm, r, mmu_range); + for_each_tile(tile, xe, id) { + if (tile_mask & BIT(id)) { + xe_svm_tlb_inval_us_stats_incr(tile->primary_gt, start); + if (tile->media_gt) + xe_svm_tlb_inval_us_stats_incr(tile->media_gt, start); + } + } } static int __xe_svm_garbage_collector(struct xe_vm *vm, @@ -308,8 +347,8 @@ static int xe_svm_garbage_collector(struct xe_vm *vm) if (xe_vm_is_closed_or_banned(vm)) return -ENOENT; - spin_lock(&vm->svm.garbage_collector.lock); for (;;) { + spin_lock(&vm->svm.garbage_collector.lock); range = list_first_entry_or_null(&vm->svm.garbage_collector.range_list, typeof(*range), garbage_collector_link); @@ -338,8 +377,6 @@ static int xe_svm_garbage_collector(struct xe_vm *vm) else return err; } - - spin_lock(&vm->svm.garbage_collector.lock); } spin_unlock(&vm->svm.garbage_collector.lock); @@ -384,11 +421,66 @@ enum xe_svm_copy_dir { XE_SVM_COPY_TO_SRAM, }; +static void xe_svm_copy_kb_stats_incr(struct xe_gt *gt, + const enum xe_svm_copy_dir dir, + int kb) +{ + if (dir == XE_SVM_COPY_TO_VRAM) + xe_gt_stats_incr(gt, XE_GT_STATS_ID_SVM_DEVICE_COPY_KB, kb); + else + xe_gt_stats_incr(gt, XE_GT_STATS_ID_SVM_CPU_COPY_KB, kb); +} + +static void xe_svm_copy_us_stats_incr(struct xe_gt *gt, + const enum xe_svm_copy_dir dir, + unsigned long npages, + ktime_t start) +{ + s64 us_delta = xe_svm_stats_ktime_us_delta(start); + + if (dir == XE_SVM_COPY_TO_VRAM) { + switch (npages) { + case 1: + xe_gt_stats_incr(gt, XE_GT_STATS_ID_SVM_4K_DEVICE_COPY_US, + us_delta); + break; + case 16: + xe_gt_stats_incr(gt, XE_GT_STATS_ID_SVM_64K_DEVICE_COPY_US, + us_delta); + break; + case 512: + xe_gt_stats_incr(gt, XE_GT_STATS_ID_SVM_2M_DEVICE_COPY_US, + us_delta); + break; + } + xe_gt_stats_incr(gt, XE_GT_STATS_ID_SVM_DEVICE_COPY_US, + us_delta); + } else { + switch (npages) { + case 1: + xe_gt_stats_incr(gt, XE_GT_STATS_ID_SVM_4K_CPU_COPY_US, + us_delta); + break; + case 16: + xe_gt_stats_incr(gt, XE_GT_STATS_ID_SVM_64K_CPU_COPY_US, + us_delta); + break; + case 512: + xe_gt_stats_incr(gt, XE_GT_STATS_ID_SVM_2M_CPU_COPY_US, + us_delta); + break; + } + xe_gt_stats_incr(gt, XE_GT_STATS_ID_SVM_CPU_COPY_US, + us_delta); + } +} + static int xe_svm_copy(struct page **pages, struct drm_pagemap_addr *pagemap_addr, unsigned long npages, const enum xe_svm_copy_dir dir) { struct xe_vram_region *vr = NULL; + struct xe_gt *gt = NULL; struct xe_device *xe; struct dma_fence *fence = NULL; unsigned long i; @@ -396,6 +488,7 @@ static int xe_svm_copy(struct page **pages, u64 vram_addr = XE_VRAM_ADDR_INVALID; int err = 0, pos = 0; bool sram = dir == XE_SVM_COPY_TO_SRAM; + ktime_t start = xe_svm_stats_ktime_get(); /* * This flow is complex: it locates physically contiguous device pages, @@ -422,6 +515,7 @@ static int xe_svm_copy(struct page **pages, if (!vr && spage) { vr = page_to_vr(spage); + gt = xe_migrate_exec_queue(vr->migrate)->gt; xe = vr->xe; } XE_WARN_ON(spage && page_to_vr(spage) != vr); @@ -461,6 +555,9 @@ static int xe_svm_copy(struct page **pages, int incr = (match && last) ? 1 : 0; if (vram_addr != XE_VRAM_ADDR_INVALID) { + xe_svm_copy_kb_stats_incr(gt, dir, + (i - pos + incr) * + (PAGE_SIZE / SZ_1K)); if (sram) { vm_dbg(&xe->drm, "COPY TO SRAM - 0x%016llx -> 0x%016llx, NPAGES=%ld", @@ -499,6 +596,8 @@ static int xe_svm_copy(struct page **pages, /* Extra mismatched device page, copy it */ if (!match && last && vram_addr != XE_VRAM_ADDR_INVALID) { + xe_svm_copy_kb_stats_incr(gt, dir, + (PAGE_SIZE / SZ_1K)); if (sram) { vm_dbg(&xe->drm, "COPY TO SRAM - 0x%016llx -> 0x%016llx, NPAGES=%d", @@ -532,6 +631,14 @@ err_out: dma_fence_put(fence); } + /* + * XXX: We can't derive the GT here (or anywhere in this functions, but + * compute always uses the primary GT so accumlate stats on the likely + * GT of the fault. + */ + if (gt) + xe_svm_copy_us_stats_incr(gt, dir, npages, start); + return err; #undef XE_MIGRATE_CHUNK_SIZE #undef XE_VRAM_ADDR_INVALID @@ -630,22 +737,26 @@ int xe_svm_init(struct xe_vm *vm) { int err; - spin_lock_init(&vm->svm.garbage_collector.lock); - INIT_LIST_HEAD(&vm->svm.garbage_collector.range_list); - INIT_WORK(&vm->svm.garbage_collector.work, - xe_svm_garbage_collector_work_func); - - err = drm_gpusvm_init(&vm->svm.gpusvm, "Xe SVM", &vm->xe->drm, - current->mm, xe_svm_devm_owner(vm->xe), 0, - vm->size, xe_modparam.svm_notifier_size * SZ_1M, - &gpusvm_ops, fault_chunk_sizes, - ARRAY_SIZE(fault_chunk_sizes)); - if (err) - return err; - - drm_gpusvm_driver_set_lock(&vm->svm.gpusvm, &vm->lock); + if (vm->flags & XE_VM_FLAG_FAULT_MODE) { + spin_lock_init(&vm->svm.garbage_collector.lock); + INIT_LIST_HEAD(&vm->svm.garbage_collector.range_list); + INIT_WORK(&vm->svm.garbage_collector.work, + xe_svm_garbage_collector_work_func); + + err = drm_gpusvm_init(&vm->svm.gpusvm, "Xe SVM", &vm->xe->drm, + current->mm, xe_svm_devm_owner(vm->xe), 0, + vm->size, + xe_modparam.svm_notifier_size * SZ_1M, + &gpusvm_ops, fault_chunk_sizes, + ARRAY_SIZE(fault_chunk_sizes)); + drm_gpusvm_driver_set_lock(&vm->svm.gpusvm, &vm->lock); + } else { + err = drm_gpusvm_init(&vm->svm.gpusvm, "Xe SVM (simple)", + &vm->xe->drm, NULL, NULL, 0, 0, 0, NULL, + NULL, 0); + } - return 0; + return err; } /** @@ -716,7 +827,7 @@ bool xe_svm_range_validate(struct xe_vm *vm, xe_svm_notifier_lock(vm); ret = (range->tile_present & ~range->tile_invalidated & tile_mask) == tile_mask && - (devmem_preferred == range->base.flags.has_devmem_pages); + (devmem_preferred == range->base.pages.flags.has_devmem_pages); xe_svm_notifier_unlock(vm); @@ -755,49 +866,48 @@ static int xe_drm_pagemap_populate_mm(struct drm_pagemap *dpagemap, struct xe_device *xe = vr->xe; struct device *dev = xe->drm.dev; struct drm_buddy_block *block; + struct xe_validation_ctx vctx; struct list_head *blocks; + struct drm_exec exec; struct xe_bo *bo; - ktime_t time_end = 0; - int err, idx; + int err = 0, idx; if (!drm_dev_enter(&xe->drm, &idx)) return -ENODEV; xe_pm_runtime_get(xe); - retry: - bo = xe_bo_create_locked(vr->xe, NULL, NULL, end - start, - ttm_bo_type_device, - (IS_DGFX(xe) ? XE_BO_FLAG_VRAM(vr) : XE_BO_FLAG_SYSTEM) | - XE_BO_FLAG_CPU_ADDR_MIRROR); - if (IS_ERR(bo)) { - err = PTR_ERR(bo); - if (xe_vm_validate_should_retry(NULL, err, &time_end)) - goto retry; - goto out_pm_put; - } - - drm_pagemap_devmem_init(&bo->devmem_allocation, dev, mm, - &dpagemap_devmem_ops, dpagemap, end - start); - - blocks = &to_xe_ttm_vram_mgr_resource(bo->ttm.resource)->blocks; - list_for_each_entry(block, blocks, link) - block->private = vr; + xe_validation_guard(&vctx, &xe->val, &exec, (struct xe_val_flags) {}, err) { + bo = xe_bo_create_locked(xe, NULL, NULL, end - start, + ttm_bo_type_device, + (IS_DGFX(xe) ? XE_BO_FLAG_VRAM(vr) : XE_BO_FLAG_SYSTEM) | + XE_BO_FLAG_CPU_ADDR_MIRROR, &exec); + drm_exec_retry_on_contention(&exec); + if (IS_ERR(bo)) { + err = PTR_ERR(bo); + xe_validation_retry_on_oom(&vctx, &err); + break; + } - xe_bo_get(bo); + drm_pagemap_devmem_init(&bo->devmem_allocation, dev, mm, + &dpagemap_devmem_ops, dpagemap, end - start); - /* Ensure the device has a pm ref while there are device pages active. */ - xe_pm_runtime_get_noresume(xe); - err = drm_pagemap_migrate_to_devmem(&bo->devmem_allocation, mm, - start, end, timeslice_ms, - xe_svm_devm_owner(xe)); - if (err) - xe_svm_devmem_release(&bo->devmem_allocation); + blocks = &to_xe_ttm_vram_mgr_resource(bo->ttm.resource)->blocks; + list_for_each_entry(block, blocks, link) + block->private = vr; - xe_bo_unlock(bo); - xe_bo_put(bo); + xe_bo_get(bo); -out_pm_put: + /* Ensure the device has a pm ref while there are device pages active. */ + xe_pm_runtime_get_noresume(xe); + err = drm_pagemap_migrate_to_devmem(&bo->devmem_allocation, mm, + start, end, timeslice_ms, + xe_svm_devm_owner(xe)); + if (err) + xe_svm_devmem_release(&bo->devmem_allocation); + xe_bo_unlock(bo); + xe_bo_put(bo); + } xe_pm_runtime_put(xe); drm_dev_exit(idx); @@ -827,17 +937,17 @@ bool xe_svm_range_needs_migrate_to_vram(struct xe_svm_range *range, struct xe_vm struct xe_vm *vm = range_to_vm(&range->base); u64 range_size = xe_svm_range_size(range); - if (!range->base.flags.migrate_devmem || !preferred_region_is_vram) + if (!range->base.pages.flags.migrate_devmem || !preferred_region_is_vram) return false; xe_assert(vm->xe, IS_DGFX(vm->xe)); - if (preferred_region_is_vram && xe_svm_range_in_vram(range)) { + if (xe_svm_range_in_vram(range)) { drm_info(&vm->xe->drm, "Range is already in VRAM\n"); return false; } - if (preferred_region_is_vram && range_size < SZ_64K && !supports_4K_migration(vm->xe)) { + if (range_size < SZ_64K && !supports_4K_migration(vm->xe)) { drm_dbg(&vm->xe->drm, "Platform doesn't support SZ_4K range migration\n"); return false; } @@ -845,27 +955,77 @@ bool xe_svm_range_needs_migrate_to_vram(struct xe_svm_range *range, struct xe_vm return true; } +#define DECL_SVM_RANGE_COUNT_STATS(elem, stat) \ +static void xe_svm_range_##elem##_count_stats_incr(struct xe_gt *gt, \ + struct xe_svm_range *range) \ +{ \ + switch (xe_svm_range_size(range)) { \ + case SZ_4K: \ + xe_gt_stats_incr(gt, XE_GT_STATS_ID_SVM_4K_##stat##_COUNT, 1); \ + break; \ + case SZ_64K: \ + xe_gt_stats_incr(gt, XE_GT_STATS_ID_SVM_64K_##stat##_COUNT, 1); \ + break; \ + case SZ_2M: \ + xe_gt_stats_incr(gt, XE_GT_STATS_ID_SVM_2M_##stat##_COUNT, 1); \ + break; \ + } \ +} \ + +DECL_SVM_RANGE_COUNT_STATS(fault, PAGEFAULT) +DECL_SVM_RANGE_COUNT_STATS(valid_fault, VALID_PAGEFAULT) +DECL_SVM_RANGE_COUNT_STATS(migrate, MIGRATE) + +#define DECL_SVM_RANGE_US_STATS(elem, stat) \ +static void xe_svm_range_##elem##_us_stats_incr(struct xe_gt *gt, \ + struct xe_svm_range *range, \ + ktime_t start) \ +{ \ + s64 us_delta = xe_svm_stats_ktime_us_delta(start); \ +\ + switch (xe_svm_range_size(range)) { \ + case SZ_4K: \ + xe_gt_stats_incr(gt, XE_GT_STATS_ID_SVM_4K_##stat##_US, \ + us_delta); \ + break; \ + case SZ_64K: \ + xe_gt_stats_incr(gt, XE_GT_STATS_ID_SVM_64K_##stat##_US, \ + us_delta); \ + break; \ + case SZ_2M: \ + xe_gt_stats_incr(gt, XE_GT_STATS_ID_SVM_2M_##stat##_US, \ + us_delta); \ + break; \ + } \ +} \ + +DECL_SVM_RANGE_US_STATS(migrate, MIGRATE) +DECL_SVM_RANGE_US_STATS(get_pages, GET_PAGES) +DECL_SVM_RANGE_US_STATS(bind, BIND) +DECL_SVM_RANGE_US_STATS(fault, PAGEFAULT) + static int __xe_svm_handle_pagefault(struct xe_vm *vm, struct xe_vma *vma, struct xe_gt *gt, u64 fault_addr, bool need_vram) { + int devmem_possible = IS_DGFX(vm->xe) && + IS_ENABLED(CONFIG_DRM_XE_PAGEMAP); struct drm_gpusvm_ctx ctx = { .read_only = xe_vma_read_only(vma), - .devmem_possible = IS_DGFX(vm->xe) && - IS_ENABLED(CONFIG_DRM_XE_PAGEMAP), - .check_pages_threshold = IS_DGFX(vm->xe) && - IS_ENABLED(CONFIG_DRM_XE_PAGEMAP) ? SZ_64K : 0, - .devmem_only = need_vram && IS_ENABLED(CONFIG_DRM_XE_PAGEMAP), - .timeslice_ms = need_vram && IS_DGFX(vm->xe) && - IS_ENABLED(CONFIG_DRM_XE_PAGEMAP) ? + .devmem_possible = devmem_possible, + .check_pages_threshold = devmem_possible ? SZ_64K : 0, + .devmem_only = need_vram && devmem_possible, + .timeslice_ms = need_vram && devmem_possible ? vm->xe->atomic_svm_timeslice_ms : 0, }; + struct xe_validation_ctx vctx; + struct drm_exec exec; struct xe_svm_range *range; struct dma_fence *fence; struct drm_pagemap *dpagemap; struct xe_tile *tile = gt_to_tile(gt); int migrate_try_count = ctx.devmem_only ? 3 : 1; - ktime_t end = 0; + ktime_t start = xe_svm_stats_ktime_get(), bind_start, get_pages_start; int err; lockdep_assert_held_write(&vm->lock); @@ -884,23 +1044,34 @@ retry: if (IS_ERR(range)) return PTR_ERR(range); - if (ctx.devmem_only && !range->base.flags.migrate_devmem) - return -EACCES; + xe_svm_range_fault_count_stats_incr(gt, range); - if (xe_svm_range_is_valid(range, tile, ctx.devmem_only)) - return 0; + if (ctx.devmem_only && !range->base.pages.flags.migrate_devmem) { + err = -EACCES; + goto out; + } + + if (xe_svm_range_is_valid(range, tile, ctx.devmem_only)) { + xe_svm_range_valid_fault_count_stats_incr(gt, range); + range_debug(range, "PAGE FAULT - VALID"); + goto out; + } range_debug(range, "PAGE FAULT"); dpagemap = xe_vma_resolve_pagemap(vma, tile); if (--migrate_try_count >= 0 && xe_svm_range_needs_migrate_to_vram(range, vma, !!dpagemap || ctx.devmem_only)) { + ktime_t migrate_start = xe_svm_stats_ktime_get(); + /* TODO : For multi-device dpagemap will be used to find the * remote tile and remote device. Will need to modify * xe_svm_alloc_vram to use dpagemap for future multi-device * support. */ + xe_svm_range_migrate_count_stats_incr(gt, range); err = xe_svm_alloc_vram(tile, range, &ctx); + xe_svm_range_migrate_us_stats_incr(gt, range, migrate_start); ctx.timeslice_ms <<= 1; /* Double timeslice if we have to retry */ if (err) { if (migrate_try_count || !ctx.devmem_only) { @@ -917,6 +1088,8 @@ retry: } } + get_pages_start = xe_svm_stats_ktime_get(); + range_debug(range, "GET PAGES"); err = xe_svm_range_get_pages(vm, range, &ctx); /* Corner where CPU mappings have changed */ @@ -936,32 +1109,45 @@ retry: } if (err) { range_debug(range, "PAGE FAULT - FAIL PAGE COLLECT"); - goto err_out; + goto out; } + xe_svm_range_get_pages_us_stats_incr(gt, range, get_pages_start); range_debug(range, "PAGE FAULT - BIND"); -retry_bind: - xe_vm_lock(vm, false); - fence = xe_vm_range_rebind(vm, vma, range, BIT(tile->id)); - if (IS_ERR(fence)) { - xe_vm_unlock(vm); - err = PTR_ERR(fence); - if (err == -EAGAIN) { - ctx.timeslice_ms <<= 1; /* Double timeslice if we have to retry */ - range_debug(range, "PAGE FAULT - RETRY BIND"); - goto retry; + bind_start = xe_svm_stats_ktime_get(); + xe_validation_guard(&vctx, &vm->xe->val, &exec, (struct xe_val_flags) {}, err) { + err = xe_vm_drm_exec_lock(vm, &exec); + drm_exec_retry_on_contention(&exec); + + xe_vm_set_validation_exec(vm, &exec); + fence = xe_vm_range_rebind(vm, vma, range, BIT(tile->id)); + xe_vm_set_validation_exec(vm, NULL); + if (IS_ERR(fence)) { + drm_exec_retry_on_contention(&exec); + err = PTR_ERR(fence); + xe_validation_retry_on_oom(&vctx, &err); + xe_svm_range_bind_us_stats_incr(gt, range, bind_start); + break; } - if (xe_vm_validate_should_retry(NULL, err, &end)) - goto retry_bind; - goto err_out; } - xe_vm_unlock(vm); + if (err) + goto err_out; dma_fence_wait(fence, false); dma_fence_put(fence); + xe_svm_range_bind_us_stats_incr(gt, range, bind_start); + +out: + xe_svm_range_fault_us_stats_incr(gt, range, start); + return 0; err_out: + if (err == -EAGAIN) { + ctx.timeslice_ms <<= 1; /* Double timeslice if we have to retry */ + range_debug(range, "PAGE FAULT - RETRY BIND"); + goto retry; + } return err; } @@ -1089,7 +1275,7 @@ struct xe_svm_range *xe_svm_range_find_or_insert(struct xe_vm *vm, u64 addr, r = drm_gpusvm_range_find_or_insert(&vm->svm.gpusvm, max(addr, xe_vma_start(vma)), xe_vma_start(vma), xe_vma_end(vma), ctx); if (IS_ERR(r)) - return ERR_PTR(PTR_ERR(r)); + return ERR_CAST(r); return to_xe_range(r); } @@ -1221,7 +1407,7 @@ int xe_svm_alloc_vram(struct xe_tile *tile, struct xe_svm_range *range, { struct drm_pagemap *dpagemap; - xe_assert(tile_to_xe(tile), range->base.flags.migrate_devmem); + xe_assert(tile_to_xe(tile), range->base.pages.flags.migrate_devmem); range_debug(range, "ALLOCATE VRAM"); dpagemap = tile_local_pagemap(tile); diff --git a/drivers/gpu/drm/xe/xe_svm.h b/drivers/gpu/drm/xe/xe_svm.h index 9d6a8840a8b7..cef6ee7d6fe3 100644 --- a/drivers/gpu/drm/xe/xe_svm.h +++ b/drivers/gpu/drm/xe/xe_svm.h @@ -105,7 +105,7 @@ struct drm_pagemap *xe_vma_resolve_pagemap(struct xe_vma *vma, struct xe_tile *t static inline bool xe_svm_range_has_dma_mapping(struct xe_svm_range *range) { lockdep_assert_held(&range->base.gpusvm->notifier_lock); - return range->base.flags.has_dma_mapping; + return range->base.pages.flags.has_dma_mapping; } /** @@ -155,19 +155,11 @@ static inline unsigned long xe_svm_range_size(struct xe_svm_range *range) return drm_gpusvm_range_size(&range->base); } -#define xe_svm_assert_in_notifier(vm__) \ - lockdep_assert_held_write(&(vm__)->svm.gpusvm.notifier_lock) - -#define xe_svm_notifier_lock(vm__) \ - drm_gpusvm_notifier_lock(&(vm__)->svm.gpusvm) - -#define xe_svm_notifier_unlock(vm__) \ - drm_gpusvm_notifier_unlock(&(vm__)->svm.gpusvm) - void xe_svm_flush(struct xe_vm *vm); #else #include <linux/interval_tree.h> +#include "xe_vm.h" struct drm_pagemap_addr; struct drm_gpusvm_ctx; @@ -184,7 +176,9 @@ struct xe_vram_region; struct xe_svm_range { struct { struct interval_tree_node itree; - const struct drm_pagemap_addr *dma_addr; + struct { + const struct drm_pagemap_addr *dma_addr; + } pages; } base; u32 tile_present; u32 tile_invalidated; @@ -204,12 +198,21 @@ int xe_devm_add(struct xe_tile *tile, struct xe_vram_region *vr) static inline int xe_svm_init(struct xe_vm *vm) { +#if IS_ENABLED(CONFIG_DRM_GPUSVM) + return drm_gpusvm_init(&vm->svm.gpusvm, "Xe SVM (simple)", &vm->xe->drm, + NULL, NULL, 0, 0, 0, NULL, NULL, 0); +#else return 0; +#endif } static inline void xe_svm_fini(struct xe_vm *vm) { +#if IS_ENABLED(CONFIG_DRM_GPUSVM) + xe_assert(vm->xe, xe_vm_is_closed(vm)); + drm_gpusvm_fini(&vm->svm.gpusvm); +#endif } static inline @@ -326,19 +329,47 @@ struct drm_pagemap *xe_vma_resolve_pagemap(struct xe_vma *vma, struct xe_tile *t return NULL; } -#define xe_svm_assert_in_notifier(...) do {} while (0) +static inline void xe_svm_flush(struct xe_vm *vm) +{ +} #define xe_svm_range_has_dma_mapping(...) false +#endif /* CONFIG_DRM_XE_GPUSVM */ + +#if IS_ENABLED(CONFIG_DRM_GPUSVM) /* Need to support userptr without XE_GPUSVM */ +#define xe_svm_assert_in_notifier(vm__) \ + lockdep_assert_held_write(&(vm__)->svm.gpusvm.notifier_lock) + +#define xe_svm_assert_held_read(vm__) \ + lockdep_assert_held_read(&(vm__)->svm.gpusvm.notifier_lock) + +#define xe_svm_notifier_lock(vm__) \ + drm_gpusvm_notifier_lock(&(vm__)->svm.gpusvm) + +#define xe_svm_notifier_lock_interruptible(vm__) \ + down_read_interruptible(&(vm__)->svm.gpusvm.notifier_lock) + +#define xe_svm_notifier_unlock(vm__) \ + drm_gpusvm_notifier_unlock(&(vm__)->svm.gpusvm) + +#else +#define xe_svm_assert_in_notifier(...) do {} while (0) + +static inline void xe_svm_assert_held_read(struct xe_vm *vm) +{ +} static inline void xe_svm_notifier_lock(struct xe_vm *vm) { } -static inline void xe_svm_notifier_unlock(struct xe_vm *vm) +static inline int xe_svm_notifier_lock_interruptible(struct xe_vm *vm) { + return 0; } -static inline void xe_svm_flush(struct xe_vm *vm) +static inline void xe_svm_notifier_unlock(struct xe_vm *vm) { } -#endif +#endif /* CONFIG_DRM_GPUSVM */ + #endif diff --git a/drivers/gpu/drm/xe/xe_tile_debugfs.c b/drivers/gpu/drm/xe/xe_tile_debugfs.c new file mode 100644 index 000000000000..5523874cba7b --- /dev/null +++ b/drivers/gpu/drm/xe/xe_tile_debugfs.c @@ -0,0 +1,135 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2025 Intel Corporation + */ + +#include <linux/debugfs.h> +#include <drm/drm_debugfs.h> + +#include "xe_pm.h" +#include "xe_sa.h" +#include "xe_tile_debugfs.h" + +static struct xe_tile *node_to_tile(struct drm_info_node *node) +{ + return node->dent->d_parent->d_inode->i_private; +} + +/** + * tile_debugfs_simple_show - A show callback for struct drm_info_list + * @m: the &seq_file + * @data: data used by the drm debugfs helpers + * + * This callback can be used in struct drm_info_list to describe debugfs + * files that are &xe_tile specific. + * + * It is assumed that those debugfs files will be created on directory entry + * which struct dentry d_inode->i_private points to &xe_tile. + * + * /sys/kernel/debug/dri/0/ + * ├── tile0/ # tile = dentry->d_inode->i_private + * │ │ ├── id # tile = dentry->d_parent->d_inode->i_private + * + * This function assumes that &m->private will be set to the &struct + * drm_info_node corresponding to the instance of the info on a given &struct + * drm_minor (see struct drm_info_list.show for details). + * + * This function also assumes that struct drm_info_list.data will point to the + * function code that will actually print a file content:: + * + * int (*print)(struct xe_tile *, struct drm_printer *) + * + * Example:: + * + * int tile_id(struct xe_tile *tile, struct drm_printer *p) + * { + * drm_printf(p, "%u\n", tile->id); + * return 0; + * } + * + * static const struct drm_info_list info[] = { + * { name = "id", .show = tile_debugfs_simple_show, .data = tile_id }, + * }; + * + * dir = debugfs_create_dir("tile0", parent); + * dir->d_inode->i_private = tile; + * drm_debugfs_create_files(info, ARRAY_SIZE(info), dir, minor); + * + * Return: 0 on success or a negative error code on failure. + */ +static int tile_debugfs_simple_show(struct seq_file *m, void *data) +{ + struct drm_printer p = drm_seq_file_printer(m); + struct drm_info_node *node = m->private; + struct xe_tile *tile = node_to_tile(node); + int (*print)(struct xe_tile *, struct drm_printer *) = node->info_ent->data; + + return print(tile, &p); +} + +/** + * tile_debugfs_show_with_rpm - A show callback for struct drm_info_list + * @m: the &seq_file + * @data: data used by the drm debugfs helpers + * + * Similar to tile_debugfs_simple_show() but implicitly takes a RPM ref. + * + * Return: 0 on success or a negative error code on failure. + */ +static int tile_debugfs_show_with_rpm(struct seq_file *m, void *data) +{ + struct drm_info_node *node = m->private; + struct xe_tile *tile = node_to_tile(node); + struct xe_device *xe = tile_to_xe(tile); + int ret; + + xe_pm_runtime_get(xe); + ret = tile_debugfs_simple_show(m, data); + xe_pm_runtime_put(xe); + + return ret; +} + +static int sa_info(struct xe_tile *tile, struct drm_printer *p) +{ + drm_suballoc_dump_debug_info(&tile->mem.kernel_bb_pool->base, p, + xe_sa_manager_gpu_addr(tile->mem.kernel_bb_pool)); + + return 0; +} + +/* only for debugfs files which can be safely used on the VF */ +static const struct drm_info_list vf_safe_debugfs_list[] = { + { "sa_info", .show = tile_debugfs_show_with_rpm, .data = sa_info }, +}; + +/** + * xe_tile_debugfs_register - Register tile's debugfs attributes + * @tile: the &xe_tile to register + * + * Create debugfs sub-directory with a name that includes a tile ID and + * then creates set of debugfs files (attributes) specific to this tile. + */ +void xe_tile_debugfs_register(struct xe_tile *tile) +{ + struct xe_device *xe = tile_to_xe(tile); + struct drm_minor *minor = xe->drm.primary; + struct dentry *root = minor->debugfs_root; + char name[8]; + + snprintf(name, sizeof(name), "tile%u", tile->id); + tile->debugfs = debugfs_create_dir(name, root); + if (IS_ERR(tile->debugfs)) + return; + + /* + * Store the xe_tile pointer as private data of the tile/ directory + * node so other tile specific attributes under that directory may + * refer to it by looking at its parent node private data. + */ + tile->debugfs->d_inode->i_private = tile; + + drm_debugfs_create_files(vf_safe_debugfs_list, + ARRAY_SIZE(vf_safe_debugfs_list), + tile->debugfs, minor); +} diff --git a/drivers/gpu/drm/xe/xe_tile_debugfs.h b/drivers/gpu/drm/xe/xe_tile_debugfs.h new file mode 100644 index 000000000000..0e5f724de37f --- /dev/null +++ b/drivers/gpu/drm/xe/xe_tile_debugfs.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2025 Intel Corporation + */ + +#ifndef _XE_TILE_DEBUGFS_H_ +#define _XE_TILE_DEBUGFS_H_ + +struct xe_tile; + +void xe_tile_debugfs_register(struct xe_tile *tile); + +#endif diff --git a/drivers/gpu/drm/xe/xe_tile_printk.h b/drivers/gpu/drm/xe/xe_tile_printk.h new file mode 100644 index 000000000000..63640a42685d --- /dev/null +++ b/drivers/gpu/drm/xe/xe_tile_printk.h @@ -0,0 +1,127 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2025 Intel Corporation + */ + +#ifndef _xe_tile_printk_H_ +#define _xe_tile_printk_H_ + +#include "xe_printk.h" + +#define __XE_TILE_PRINTK_FMT(_tile, _fmt, _args...) "Tile%u: " _fmt, (_tile)->id, ##_args + +#define xe_tile_printk(_tile, _level, _fmt, ...) \ + xe_printk((_tile)->xe, _level, __XE_TILE_PRINTK_FMT((_tile), _fmt, ##__VA_ARGS__)) + +#define xe_tile_err(_tile, _fmt, ...) \ + xe_tile_printk((_tile), err, _fmt, ##__VA_ARGS__) + +#define xe_tile_err_once(_tile, _fmt, ...) \ + xe_tile_printk((_tile), err_once, _fmt, ##__VA_ARGS__) + +#define xe_tile_err_ratelimited(_tile, _fmt, ...) \ + xe_tile_printk((_tile), err_ratelimited, _fmt, ##__VA_ARGS__) + +#define xe_tile_warn(_tile, _fmt, ...) \ + xe_tile_printk((_tile), warn, _fmt, ##__VA_ARGS__) + +#define xe_tile_notice(_tile, _fmt, ...) \ + xe_tile_printk((_tile), notice, _fmt, ##__VA_ARGS__) + +#define xe_tile_info(_tile, _fmt, ...) \ + xe_tile_printk((_tile), info, _fmt, ##__VA_ARGS__) + +#define xe_tile_dbg(_tile, _fmt, ...) \ + xe_tile_printk((_tile), dbg, _fmt, ##__VA_ARGS__) + +#define xe_tile_WARN_type(_tile, _type, _condition, _fmt, ...) \ + xe_WARN##_type((_tile)->xe, _condition, _fmt, ## __VA_ARGS__) + +#define xe_tile_WARN(_tile, _condition, _fmt, ...) \ + xe_tile_WARN_type((_tile),, _condition, __XE_TILE_PRINTK_FMT((_tile), _fmt, ##__VA_ARGS__)) + +#define xe_tile_WARN_ONCE(_tile, _condition, _fmt, ...) \ + xe_tile_WARN_type((_tile), _ONCE, _condition, __XE_TILE_PRINTK_FMT((_tile), _fmt, ##__VA_ARGS__)) + +#define xe_tile_WARN_ON(_tile, _condition) \ + xe_tile_WARN((_tile), _condition, "%s(%s)", "WARN_ON", __stringify(_condition)) + +#define xe_tile_WARN_ON_ONCE(_tile, _condition) \ + xe_tile_WARN_ONCE((_tile), _condition, "%s(%s)", "WARN_ON_ONCE", __stringify(_condition)) + +static inline void __xe_tile_printfn_err(struct drm_printer *p, struct va_format *vaf) +{ + struct xe_tile *tile = p->arg; + + xe_tile_err(tile, "%pV", vaf); +} + +static inline void __xe_tile_printfn_info(struct drm_printer *p, struct va_format *vaf) +{ + struct xe_tile *tile = p->arg; + + xe_tile_info(tile, "%pV", vaf); +} + +static inline void __xe_tile_printfn_dbg(struct drm_printer *p, struct va_format *vaf) +{ + struct xe_tile *tile = p->arg; + struct drm_printer dbg; + + /* + * The original xe_tile_dbg() callsite annotations are useless here, + * redirect to the tweaked xe_dbg_printer() instead. + */ + dbg = xe_dbg_printer(tile->xe); + dbg.origin = p->origin; + + drm_printf(&dbg, __XE_TILE_PRINTK_FMT(tile, "%pV", vaf)); +} + +/** + * xe_tile_err_printer - Construct a &drm_printer that outputs to xe_tile_err() + * @tile: the &xe_tile pointer to use in xe_tile_err() + * + * Return: The &drm_printer object. + */ +static inline struct drm_printer xe_tile_err_printer(struct xe_tile *tile) +{ + struct drm_printer p = { + .printfn = __xe_tile_printfn_err, + .arg = tile, + }; + return p; +} + +/** + * xe_tile_info_printer - Construct a &drm_printer that outputs to xe_tile_info() + * @tile: the &xe_tile pointer to use in xe_tile_info() + * + * Return: The &drm_printer object. + */ +static inline struct drm_printer xe_tile_info_printer(struct xe_tile *tile) +{ + struct drm_printer p = { + .printfn = __xe_tile_printfn_info, + .arg = tile, + }; + return p; +} + +/** + * xe_tile_dbg_printer - Construct a &drm_printer that outputs like xe_tile_dbg() + * @tile: the &xe_tile pointer to use in xe_tile_dbg() + * + * Return: The &drm_printer object. + */ +static inline struct drm_printer xe_tile_dbg_printer(struct xe_tile *tile) +{ + struct drm_printer p = { + .printfn = __xe_tile_printfn_dbg, + .arg = tile, + .origin = (const void *)_THIS_IP_, + }; + return p; +} + +#endif diff --git a/drivers/gpu/drm/xe/xe_tile_sysfs.c b/drivers/gpu/drm/xe/xe_tile_sysfs.c index b804234a6551..9e1236a9ec67 100644 --- a/drivers/gpu/drm/xe/xe_tile_sysfs.c +++ b/drivers/gpu/drm/xe/xe_tile_sysfs.c @@ -44,16 +44,18 @@ int xe_tile_sysfs_init(struct xe_tile *tile) kt->tile = tile; err = kobject_add(&kt->base, &dev->kobj, "tile%d", tile->id); - if (err) { - kobject_put(&kt->base); - return err; - } + if (err) + goto err_object; tile->sysfs = &kt->base; err = xe_vram_freq_sysfs_init(tile); if (err) - return err; + goto err_object; return devm_add_action_or_reset(xe->drm.dev, tile_sysfs_fini, tile); + +err_object: + kobject_put(&kt->base); + return err; } diff --git a/drivers/gpu/drm/xe/xe_tlb_inval.c b/drivers/gpu/drm/xe/xe_tlb_inval.c index e6e97b5a7b5c..918a59e686ea 100644 --- a/drivers/gpu/drm/xe/xe_tlb_inval.c +++ b/drivers/gpu/drm/xe/xe_tlb_inval.c @@ -10,11 +10,10 @@ #include "xe_force_wake.h" #include "xe_gt.h" #include "xe_gt_printk.h" +#include "xe_gt_stats.h" #include "xe_guc.h" #include "xe_guc_ct.h" #include "xe_guc_tlb_inval.h" -#include "xe_gt_stats.h" -#include "xe_tlb_inval.h" #include "xe_mmio.h" #include "xe_pm.h" #include "xe_tlb_inval.h" diff --git a/drivers/gpu/drm/xe/xe_uc_fw.c b/drivers/gpu/drm/xe/xe_uc_fw.c index 9bbdde604923..622b76078567 100644 --- a/drivers/gpu/drm/xe/xe_uc_fw.c +++ b/drivers/gpu/drm/xe/xe_uc_fw.c @@ -115,8 +115,8 @@ struct fw_blobs_by_type { #define XE_GT_TYPE_ANY XE_GT_TYPE_UNINITIALIZED #define XE_GUC_FIRMWARE_DEFS(fw_def, mmp_ver, major_ver) \ - fw_def(PANTHERLAKE, GT_TYPE_ANY, major_ver(xe, guc, ptl, 70, 47, 0)) \ - fw_def(BATTLEMAGE, GT_TYPE_ANY, major_ver(xe, guc, bmg, 70, 45, 2)) \ + fw_def(PANTHERLAKE, GT_TYPE_ANY, major_ver(xe, guc, ptl, 70, 49, 4)) \ + fw_def(BATTLEMAGE, GT_TYPE_ANY, major_ver(xe, guc, bmg, 70, 49, 4)) \ fw_def(LUNARLAKE, GT_TYPE_ANY, major_ver(xe, guc, lnl, 70, 45, 2)) \ fw_def(METEORLAKE, GT_TYPE_ANY, major_ver(i915, guc, mtl, 70, 44, 1)) \ fw_def(DG2, GT_TYPE_ANY, major_ver(i915, guc, dg2, 70, 45, 2)) \ @@ -328,7 +328,7 @@ static void uc_fw_fini(struct drm_device *drm, void *arg) xe_uc_fw_change_status(uc_fw, XE_UC_FIRMWARE_SELECTED); } -static int guc_read_css_info(struct xe_uc_fw *uc_fw, struct uc_css_header *css) +static int guc_read_css_info(struct xe_uc_fw *uc_fw, struct uc_css_guc_info *guc_info) { struct xe_gt *gt = uc_fw_to_gt(uc_fw); struct xe_uc_fw_version *release = &uc_fw->versions.found[XE_UC_FW_VER_RELEASE]; @@ -343,11 +343,12 @@ static int guc_read_css_info(struct xe_uc_fw *uc_fw, struct uc_css_header *css) return -EINVAL; } - compatibility->major = FIELD_GET(CSS_SW_VERSION_UC_MAJOR, css->submission_version); - compatibility->minor = FIELD_GET(CSS_SW_VERSION_UC_MINOR, css->submission_version); - compatibility->patch = FIELD_GET(CSS_SW_VERSION_UC_PATCH, css->submission_version); + compatibility->major = FIELD_GET(CSS_SW_VERSION_UC_MAJOR, guc_info->submission_version); + compatibility->minor = FIELD_GET(CSS_SW_VERSION_UC_MINOR, guc_info->submission_version); + compatibility->patch = FIELD_GET(CSS_SW_VERSION_UC_PATCH, guc_info->submission_version); - uc_fw->private_data_size = css->private_data_size; + uc_fw->build_type = FIELD_GET(CSS_UKERNEL_INFO_BUILDTYPE, guc_info->ukernel_info); + uc_fw->private_data_size = guc_info->private_data_size; return 0; } @@ -416,8 +417,8 @@ static int parse_css_header(struct xe_uc_fw *uc_fw, const void *fw_data, size_t css = (struct uc_css_header *)fw_data; /* Check integrity of size values inside CSS header */ - size = (css->header_size_dw - css->key_size_dw - css->modulus_size_dw - - css->exponent_size_dw) * sizeof(u32); + size = (css->header_size_dw - css->rsa_info.key_size_dw - css->rsa_info.modulus_size_dw - + css->rsa_info.exponent_size_dw) * sizeof(u32); if (unlikely(size != sizeof(struct uc_css_header))) { drm_warn(&xe->drm, "%s firmware %s: unexpected header size: %zu != %zu\n", @@ -430,7 +431,7 @@ static int parse_css_header(struct xe_uc_fw *uc_fw, const void *fw_data, size_t uc_fw->ucode_size = (css->size_dw - css->header_size_dw) * sizeof(u32); /* now RSA */ - uc_fw->rsa_size = css->key_size_dw * sizeof(u32); + uc_fw->rsa_size = css->rsa_info.key_size_dw * sizeof(u32); /* At least, it should have header, uCode and RSA. Size of all three. */ size = sizeof(struct uc_css_header) + uc_fw->ucode_size + @@ -443,12 +444,12 @@ static int parse_css_header(struct xe_uc_fw *uc_fw, const void *fw_data, size_t } /* Get version numbers from the CSS header */ - release->major = FIELD_GET(CSS_SW_VERSION_UC_MAJOR, css->sw_version); - release->minor = FIELD_GET(CSS_SW_VERSION_UC_MINOR, css->sw_version); - release->patch = FIELD_GET(CSS_SW_VERSION_UC_PATCH, css->sw_version); + release->major = FIELD_GET(CSS_SW_VERSION_UC_MAJOR, css->guc_info.sw_version); + release->minor = FIELD_GET(CSS_SW_VERSION_UC_MINOR, css->guc_info.sw_version); + release->patch = FIELD_GET(CSS_SW_VERSION_UC_PATCH, css->guc_info.sw_version); if (uc_fw->type == XE_UC_FW_TYPE_GUC) - return guc_read_css_info(uc_fw, css); + return guc_read_css_info(uc_fw, &css->guc_info); return 0; } diff --git a/drivers/gpu/drm/xe/xe_uc_fw_abi.h b/drivers/gpu/drm/xe/xe_uc_fw_abi.h index 87ade41209d0..3c9a63d13032 100644 --- a/drivers/gpu/drm/xe/xe_uc_fw_abi.h +++ b/drivers/gpu/drm/xe/xe_uc_fw_abi.h @@ -44,6 +44,39 @@ * in fw. So driver will load a truncated firmware in this case. */ +struct uc_css_rsa_info { + u32 key_size_dw; + u32 modulus_size_dw; + u32 exponent_size_dw; +} __packed; + +struct uc_css_guc_info { + u32 time; +#define CSS_TIME_HOUR (0xFF << 0) +#define CSS_TIME_MIN (0xFF << 8) +#define CSS_TIME_SEC (0xFFFF << 16) + u32 reserved0[5]; + u32 sw_version; +#define CSS_SW_VERSION_UC_MAJOR (0xFF << 16) +#define CSS_SW_VERSION_UC_MINOR (0xFF << 8) +#define CSS_SW_VERSION_UC_PATCH (0xFF << 0) + u32 submission_version; + u32 reserved1[11]; + u32 header_info; +#define CSS_HEADER_INFO_SVN (0xFF) +#define CSS_HEADER_INFO_COPY_VALID (0x1 << 31) + u32 private_data_size; + u32 ukernel_info; +#define CSS_UKERNEL_INFO_DEVICEID (0xFFFF << 16) +#define CSS_UKERNEL_INFO_PRODKEY (0xFF << 8) +#define CSS_UKERNEL_INFO_BUILDTYPE (0x3 << 2) +#define CSS_UKERNEL_INFO_BUILDTYPE_PROD 0 +#define CSS_UKERNEL_INFO_BUILDTYPE_PREPROD 1 +#define CSS_UKERNEL_INFO_BUILDTYPE_DEBUG 2 +#define CSS_UKERNEL_INFO_ENCSTATUS (0x1 << 1) +#define CSS_UKERNEL_INFO_COPY_VALID (0x1 << 0) +} __packed; + struct uc_css_header { u32 module_type; /* @@ -52,36 +85,21 @@ struct uc_css_header { */ u32 header_size_dw; u32 header_version; - u32 module_id; + u32 reserved0; u32 module_vendor; u32 date; -#define CSS_DATE_DAY (0xFF << 0) -#define CSS_DATE_MONTH (0xFF << 8) -#define CSS_DATE_YEAR (0xFFFF << 16) +#define CSS_DATE_DAY (0xFF << 0) +#define CSS_DATE_MONTH (0xFF << 8) +#define CSS_DATE_YEAR (0xFFFF << 16) u32 size_dw; /* uCode plus header_size_dw */ - u32 key_size_dw; - u32 modulus_size_dw; - u32 exponent_size_dw; - u32 time; -#define CSS_TIME_HOUR (0xFF << 0) -#define CSS_DATE_MIN (0xFF << 8) -#define CSS_DATE_SEC (0xFFFF << 16) - char username[8]; - char buildnumber[12]; - u32 sw_version; -#define CSS_SW_VERSION_UC_MAJOR (0xFF << 16) -#define CSS_SW_VERSION_UC_MINOR (0xFF << 8) -#define CSS_SW_VERSION_UC_PATCH (0xFF << 0) union { - u32 submission_version; /* only applies to GuC */ - u32 reserved2; + u32 reserved1[3]; + struct uc_css_rsa_info rsa_info; }; - u32 reserved0[12]; union { - u32 private_data_size; /* only applies to GuC */ - u32 reserved1; + u32 reserved2[22]; + struct uc_css_guc_info guc_info; }; - u32 header_info; } __packed; static_assert(sizeof(struct uc_css_header) == 128); @@ -318,4 +336,70 @@ struct gsc_manifest_header { u32 exponent_size; /* in dwords */ } __packed; +/** + * DOC: Late binding Firmware Layout + * + * The Late binding binary starts with FPT header, which contains locations + * of various partitions of the binary. Here we're interested in finding out + * manifest version. To the manifest version, we need to locate CPD header + * one of the entry in CPD header points to manifest header. Manifest header + * contains the version. + * + * +================================================+ + * | FPT Header | + * +================================================+ + * | FPT entries[] | + * | entry1 | + * | ... | + * | entryX | + * | "LTES" | + * | ... | + * | offset >-----------------------------|------o + * +================================================+ | + * | + * +================================================+ | + * | CPD Header |<-----o + * +================================================+ + * | CPD entries[] | + * | entry1 | + * | ... | + * | entryX | + * | "LTES.man" | + * | ... | + * | offset >----------------------------|------o + * +================================================+ | + * | + * +================================================+ | + * | Manifest Header |<-----o + * | ... | + * | FW version | + * | ... | + * +================================================+ + */ + +/* FPT Headers */ +struct csc_fpt_header { + u32 header_marker; +#define CSC_FPT_HEADER_MARKER 0x54504624 + u32 num_of_entries; + u8 header_version; + u8 entry_version; + u8 header_length; /* in bytes */ + u8 flags; + u16 ticks_to_add; + u16 tokens_to_add; + u32 uma_size; + u32 crc32; + struct gsc_version fitc_version; +} __packed; + +struct csc_fpt_entry { + u8 name[4]; /* partition name */ + u32 reserved1; + u32 offset; /* offset from beginning of CSE region */ + u32 length; /* partition length in bytes */ + u32 reserved2[3]; + u32 partition_flags; +} __packed; + #endif diff --git a/drivers/gpu/drm/xe/xe_uc_fw_types.h b/drivers/gpu/drm/xe/xe_uc_fw_types.h index 914026015019..77a1dcf8b4ed 100644 --- a/drivers/gpu/drm/xe/xe_uc_fw_types.h +++ b/drivers/gpu/drm/xe/xe_uc_fw_types.h @@ -147,6 +147,9 @@ struct xe_uc_fw { /** @private_data_size: size of private data found in uC css header */ u32 private_data_size; + + /** @build_type: Firmware build type (see CSS_UKERNEL_INFO_BUILDTYPE for definitions) */ + u32 build_type; }; #endif diff --git a/drivers/gpu/drm/xe/xe_userptr.c b/drivers/gpu/drm/xe/xe_userptr.c new file mode 100644 index 000000000000..91d09af71ced --- /dev/null +++ b/drivers/gpu/drm/xe/xe_userptr.c @@ -0,0 +1,319 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2025 Intel Corporation + */ + +#include "xe_userptr.h" + +#include <linux/mm.h> + +#include "xe_trace_bo.h" + +/** + * xe_vma_userptr_check_repin() - Advisory check for repin needed + * @uvma: The userptr vma + * + * Check if the userptr vma has been invalidated since last successful + * repin. The check is advisory only and can the function can be called + * without the vm->svm.gpusvm.notifier_lock held. There is no guarantee that the + * vma userptr will remain valid after a lockless check, so typically + * the call needs to be followed by a proper check under the notifier_lock. + * + * Return: 0 if userptr vma is valid, -EAGAIN otherwise; repin recommended. + */ +int xe_vma_userptr_check_repin(struct xe_userptr_vma *uvma) +{ + return mmu_interval_check_retry(&uvma->userptr.notifier, + uvma->userptr.pages.notifier_seq) ? + -EAGAIN : 0; +} + +/** + * __xe_vm_userptr_needs_repin() - Check whether the VM does have userptrs + * that need repinning. + * @vm: The VM. + * + * This function checks for whether the VM has userptrs that need repinning, + * and provides a release-type barrier on the svm.gpusvm.notifier_lock after + * checking. + * + * Return: 0 if there are no userptrs needing repinning, -EAGAIN if there are. + */ +int __xe_vm_userptr_needs_repin(struct xe_vm *vm) +{ + lockdep_assert_held_read(&vm->svm.gpusvm.notifier_lock); + + return (list_empty(&vm->userptr.repin_list) && + list_empty(&vm->userptr.invalidated)) ? 0 : -EAGAIN; +} + +int xe_vma_userptr_pin_pages(struct xe_userptr_vma *uvma) +{ + struct xe_vma *vma = &uvma->vma; + struct xe_vm *vm = xe_vma_vm(vma); + struct xe_device *xe = vm->xe; + struct drm_gpusvm_ctx ctx = { + .read_only = xe_vma_read_only(vma), + }; + + lockdep_assert_held(&vm->lock); + xe_assert(xe, xe_vma_is_userptr(vma)); + + if (vma->gpuva.flags & XE_VMA_DESTROYED) + return 0; + + return drm_gpusvm_get_pages(&vm->svm.gpusvm, &uvma->userptr.pages, + uvma->userptr.notifier.mm, + &uvma->userptr.notifier, + xe_vma_userptr(vma), + xe_vma_userptr(vma) + xe_vma_size(vma), + &ctx); +} + +static void __vma_userptr_invalidate(struct xe_vm *vm, struct xe_userptr_vma *uvma) +{ + struct xe_userptr *userptr = &uvma->userptr; + struct xe_vma *vma = &uvma->vma; + struct dma_resv_iter cursor; + struct dma_fence *fence; + struct drm_gpusvm_ctx ctx = { + .in_notifier = true, + .read_only = xe_vma_read_only(vma), + }; + long err; + + /* + * Tell exec and rebind worker they need to repin and rebind this + * userptr. + */ + if (!xe_vm_in_fault_mode(vm) && + !(vma->gpuva.flags & XE_VMA_DESTROYED)) { + spin_lock(&vm->userptr.invalidated_lock); + list_move_tail(&userptr->invalidate_link, + &vm->userptr.invalidated); + spin_unlock(&vm->userptr.invalidated_lock); + } + + /* + * Preempt fences turn into schedule disables, pipeline these. + * Note that even in fault mode, we need to wait for binds and + * unbinds to complete, and those are attached as BOOKMARK fences + * to the vm. + */ + dma_resv_iter_begin(&cursor, xe_vm_resv(vm), + DMA_RESV_USAGE_BOOKKEEP); + dma_resv_for_each_fence_unlocked(&cursor, fence) + dma_fence_enable_sw_signaling(fence); + dma_resv_iter_end(&cursor); + + err = dma_resv_wait_timeout(xe_vm_resv(vm), + DMA_RESV_USAGE_BOOKKEEP, + false, MAX_SCHEDULE_TIMEOUT); + XE_WARN_ON(err <= 0); + + if (xe_vm_in_fault_mode(vm) && userptr->initial_bind) { + err = xe_vm_invalidate_vma(vma); + XE_WARN_ON(err); + } + + drm_gpusvm_unmap_pages(&vm->svm.gpusvm, &uvma->userptr.pages, + xe_vma_size(vma) >> PAGE_SHIFT, &ctx); +} + +static bool vma_userptr_invalidate(struct mmu_interval_notifier *mni, + const struct mmu_notifier_range *range, + unsigned long cur_seq) +{ + struct xe_userptr_vma *uvma = container_of(mni, typeof(*uvma), userptr.notifier); + struct xe_vma *vma = &uvma->vma; + struct xe_vm *vm = xe_vma_vm(vma); + + xe_assert(vm->xe, xe_vma_is_userptr(vma)); + trace_xe_vma_userptr_invalidate(vma); + + if (!mmu_notifier_range_blockable(range)) + return false; + + vm_dbg(&xe_vma_vm(vma)->xe->drm, + "NOTIFIER: addr=0x%016llx, range=0x%016llx", + xe_vma_start(vma), xe_vma_size(vma)); + + down_write(&vm->svm.gpusvm.notifier_lock); + mmu_interval_set_seq(mni, cur_seq); + + __vma_userptr_invalidate(vm, uvma); + up_write(&vm->svm.gpusvm.notifier_lock); + trace_xe_vma_userptr_invalidate_complete(vma); + + return true; +} + +static const struct mmu_interval_notifier_ops vma_userptr_notifier_ops = { + .invalidate = vma_userptr_invalidate, +}; + +#if IS_ENABLED(CONFIG_DRM_XE_USERPTR_INVAL_INJECT) +/** + * xe_vma_userptr_force_invalidate() - force invalidate a userptr + * @uvma: The userptr vma to invalidate + * + * Perform a forced userptr invalidation for testing purposes. + */ +void xe_vma_userptr_force_invalidate(struct xe_userptr_vma *uvma) +{ + struct xe_vm *vm = xe_vma_vm(&uvma->vma); + + /* Protect against concurrent userptr pinning */ + lockdep_assert_held(&vm->lock); + /* Protect against concurrent notifiers */ + lockdep_assert_held(&vm->svm.gpusvm.notifier_lock); + /* + * Protect against concurrent instances of this function and + * the critical exec sections + */ + xe_vm_assert_held(vm); + + if (!mmu_interval_read_retry(&uvma->userptr.notifier, + uvma->userptr.pages.notifier_seq)) + uvma->userptr.pages.notifier_seq -= 2; + __vma_userptr_invalidate(vm, uvma); +} +#endif + +int xe_vm_userptr_pin(struct xe_vm *vm) +{ + struct xe_userptr_vma *uvma, *next; + int err = 0; + + xe_assert(vm->xe, !xe_vm_in_fault_mode(vm)); + lockdep_assert_held_write(&vm->lock); + + /* Collect invalidated userptrs */ + spin_lock(&vm->userptr.invalidated_lock); + xe_assert(vm->xe, list_empty(&vm->userptr.repin_list)); + list_for_each_entry_safe(uvma, next, &vm->userptr.invalidated, + userptr.invalidate_link) { + list_del_init(&uvma->userptr.invalidate_link); + list_add_tail(&uvma->userptr.repin_link, + &vm->userptr.repin_list); + } + spin_unlock(&vm->userptr.invalidated_lock); + + /* Pin and move to bind list */ + list_for_each_entry_safe(uvma, next, &vm->userptr.repin_list, + userptr.repin_link) { + err = xe_vma_userptr_pin_pages(uvma); + if (err == -EFAULT) { + list_del_init(&uvma->userptr.repin_link); + /* + * We might have already done the pin once already, but + * then had to retry before the re-bind happened, due + * some other condition in the caller, but in the + * meantime the userptr got dinged by the notifier such + * that we need to revalidate here, but this time we hit + * the EFAULT. In such a case make sure we remove + * ourselves from the rebind list to avoid going down in + * flames. + */ + if (!list_empty(&uvma->vma.combined_links.rebind)) + list_del_init(&uvma->vma.combined_links.rebind); + + /* Wait for pending binds */ + xe_vm_lock(vm, false); + dma_resv_wait_timeout(xe_vm_resv(vm), + DMA_RESV_USAGE_BOOKKEEP, + false, MAX_SCHEDULE_TIMEOUT); + + down_read(&vm->svm.gpusvm.notifier_lock); + err = xe_vm_invalidate_vma(&uvma->vma); + up_read(&vm->svm.gpusvm.notifier_lock); + xe_vm_unlock(vm); + if (err) + break; + } else { + if (err) + break; + + list_del_init(&uvma->userptr.repin_link); + list_move_tail(&uvma->vma.combined_links.rebind, + &vm->rebind_list); + } + } + + if (err) { + down_write(&vm->svm.gpusvm.notifier_lock); + spin_lock(&vm->userptr.invalidated_lock); + list_for_each_entry_safe(uvma, next, &vm->userptr.repin_list, + userptr.repin_link) { + list_del_init(&uvma->userptr.repin_link); + list_move_tail(&uvma->userptr.invalidate_link, + &vm->userptr.invalidated); + } + spin_unlock(&vm->userptr.invalidated_lock); + up_write(&vm->svm.gpusvm.notifier_lock); + } + return err; +} + +/** + * xe_vm_userptr_check_repin() - Check whether the VM might have userptrs + * that need repinning. + * @vm: The VM. + * + * This function does an advisory check for whether the VM has userptrs that + * need repinning. + * + * Return: 0 if there are no indications of userptrs needing repinning, + * -EAGAIN if there are. + */ +int xe_vm_userptr_check_repin(struct xe_vm *vm) +{ + return (list_empty_careful(&vm->userptr.repin_list) && + list_empty_careful(&vm->userptr.invalidated)) ? 0 : -EAGAIN; +} + +int xe_userptr_setup(struct xe_userptr_vma *uvma, unsigned long start, + unsigned long range) +{ + struct xe_userptr *userptr = &uvma->userptr; + int err; + + INIT_LIST_HEAD(&userptr->invalidate_link); + INIT_LIST_HEAD(&userptr->repin_link); + + err = mmu_interval_notifier_insert(&userptr->notifier, current->mm, + start, range, + &vma_userptr_notifier_ops); + if (err) + return err; + + userptr->pages.notifier_seq = LONG_MAX; + + return 0; +} + +void xe_userptr_remove(struct xe_userptr_vma *uvma) +{ + struct xe_vm *vm = xe_vma_vm(&uvma->vma); + struct xe_userptr *userptr = &uvma->userptr; + + drm_gpusvm_free_pages(&vm->svm.gpusvm, &uvma->userptr.pages, + xe_vma_size(&uvma->vma) >> PAGE_SHIFT); + + /* + * Since userptr pages are not pinned, we can't remove + * the notifier until we're sure the GPU is not accessing + * them anymore + */ + mmu_interval_notifier_remove(&userptr->notifier); +} + +void xe_userptr_destroy(struct xe_userptr_vma *uvma) +{ + struct xe_vm *vm = xe_vma_vm(&uvma->vma); + + spin_lock(&vm->userptr.invalidated_lock); + xe_assert(vm->xe, list_empty(&uvma->userptr.repin_link)); + list_del(&uvma->userptr.invalidate_link); + spin_unlock(&vm->userptr.invalidated_lock); +} diff --git a/drivers/gpu/drm/xe/xe_userptr.h b/drivers/gpu/drm/xe/xe_userptr.h new file mode 100644 index 000000000000..ef801234991e --- /dev/null +++ b/drivers/gpu/drm/xe/xe_userptr.h @@ -0,0 +1,107 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2025 Intel Corporation + */ + +#ifndef _XE_USERPTR_H_ +#define _XE_USERPTR_H_ + +#include <linux/list.h> +#include <linux/mutex.h> +#include <linux/notifier.h> +#include <linux/scatterlist.h> +#include <linux/spinlock.h> + +#include <drm/drm_gpusvm.h> + +struct xe_vm; +struct xe_vma; +struct xe_userptr_vma; + +/** struct xe_userptr_vm - User pointer VM level state */ +struct xe_userptr_vm { + /** + * @userptr.repin_list: list of VMAs which are user pointers, + * and needs repinning. Protected by @lock. + */ + struct list_head repin_list; + /** + * @userptr.invalidated_lock: Protects the + * @userptr.invalidated list. + */ + spinlock_t invalidated_lock; + /** + * @userptr.invalidated: List of invalidated userptrs, not yet + * picked + * up for revalidation. Protected from access with the + * @invalidated_lock. Removing items from the list + * additionally requires @lock in write mode, and adding + * items to the list requires either the @svm.gpusvm.notifier_lock in + * write mode, OR @lock in write mode. + */ + struct list_head invalidated; +}; + +/** struct xe_userptr - User pointer */ +struct xe_userptr { + /** @invalidate_link: Link for the vm::userptr.invalidated list */ + struct list_head invalidate_link; + /** @userptr: link into VM repin list if userptr. */ + struct list_head repin_link; + /** + * @pages: gpusvm pages for this user pointer. + */ + struct drm_gpusvm_pages pages; + /** + * @notifier: MMU notifier for user pointer (invalidation call back) + */ + struct mmu_interval_notifier notifier; + + /** + * @initial_bind: user pointer has been bound at least once. + * write: vm->svm.gpusvm.notifier_lock in read mode and vm->resv held. + * read: vm->svm.gpusvm.notifier_lock in write mode or vm->resv held. + */ + bool initial_bind; +#if IS_ENABLED(CONFIG_DRM_XE_USERPTR_INVAL_INJECT) + u32 divisor; +#endif +}; + +#if IS_ENABLED(CONFIG_DRM_GPUSVM) +void xe_userptr_remove(struct xe_userptr_vma *uvma); +int xe_userptr_setup(struct xe_userptr_vma *uvma, unsigned long start, + unsigned long range); +void xe_userptr_destroy(struct xe_userptr_vma *uvma); + +int xe_vm_userptr_pin(struct xe_vm *vm); +int __xe_vm_userptr_needs_repin(struct xe_vm *vm); +int xe_vm_userptr_check_repin(struct xe_vm *vm); +int xe_vma_userptr_pin_pages(struct xe_userptr_vma *uvma); +int xe_vma_userptr_check_repin(struct xe_userptr_vma *uvma); +#else +static inline void xe_userptr_remove(struct xe_userptr_vma *uvma) {} + +static inline int xe_userptr_setup(struct xe_userptr_vma *uvma, + unsigned long start, unsigned long range) +{ + return -ENODEV; +} + +static inline void xe_userptr_destroy(struct xe_userptr_vma *uvma) {} + +static inline int xe_vm_userptr_pin(struct xe_vm *vm) { return 0; } +static inline int __xe_vm_userptr_needs_repin(struct xe_vm *vm) { return 0; } +static inline int xe_vm_userptr_check_repin(struct xe_vm *vm) { return 0; } +static inline int xe_vma_userptr_pin_pages(struct xe_userptr_vma *uvma) { return -ENODEV; } +static inline int xe_vma_userptr_check_repin(struct xe_userptr_vma *uvma) { return -ENODEV; }; +#endif + +#if IS_ENABLED(CONFIG_DRM_XE_USERPTR_INVAL_INJECT) +void xe_vma_userptr_force_invalidate(struct xe_userptr_vma *uvma); +#else +static inline void xe_vma_userptr_force_invalidate(struct xe_userptr_vma *uvma) +{ +} +#endif +#endif diff --git a/drivers/gpu/drm/xe/xe_validation.c b/drivers/gpu/drm/xe/xe_validation.c new file mode 100644 index 000000000000..826cd09966ef --- /dev/null +++ b/drivers/gpu/drm/xe/xe_validation.c @@ -0,0 +1,278 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2024 Intel Corporation + */ +#include "xe_bo.h" +#include <drm/drm_exec.h> +#include <drm/drm_gem.h> +#include <drm/drm_gpuvm.h> + +#include "xe_assert.h" +#include "xe_validation.h" + +#ifdef CONFIG_DRM_XE_DEBUG +/** + * xe_validation_assert_exec() - Assert that the drm_exec pointer is suitable + * for validation. + * @xe: Pointer to the xe device. + * @exec: The drm_exec pointer to check. + * @obj: Pointer to the object subject to validation. + * + * NULL exec pointers are not allowed. + * For XE_VALIDATION_UNIMPLEMENTED, no checking. + * For XE_VLIDATION_OPT_OUT, check that the caller is a kunit test + * For XE_VALIDATION_UNSUPPORTED, check that the object subject to + * validation is a dma-buf, for which support for ww locking is + * not in place in the dma-buf layer. + */ +void xe_validation_assert_exec(const struct xe_device *xe, + const struct drm_exec *exec, + const struct drm_gem_object *obj) +{ + xe_assert(xe, exec); + if (IS_ERR(exec)) { + switch (PTR_ERR(exec)) { + case __XE_VAL_UNIMPLEMENTED: + break; + case __XE_VAL_UNSUPPORTED: + xe_assert(xe, !!obj->dma_buf); + break; +#if IS_ENABLED(CONFIG_KUNIT) + case __XE_VAL_OPT_OUT: + xe_assert(xe, current->kunit_test); + break; +#endif + default: + xe_assert(xe, false); + } + } +} +#endif + +static int xe_validation_lock(struct xe_validation_ctx *ctx) +{ + struct xe_validation_device *val = ctx->val; + int ret = 0; + + if (ctx->val_flags.interruptible) { + if (ctx->request_exclusive) + ret = down_write_killable(&val->lock); + else + ret = down_read_interruptible(&val->lock); + } else { + if (ctx->request_exclusive) + down_write(&val->lock); + else + down_read(&val->lock); + } + + if (!ret) { + ctx->lock_held = true; + ctx->lock_held_exclusive = ctx->request_exclusive; + } + + return ret; +} + +static int xe_validation_trylock(struct xe_validation_ctx *ctx) +{ + struct xe_validation_device *val = ctx->val; + bool locked; + + if (ctx->request_exclusive) + locked = down_write_trylock(&val->lock); + else + locked = down_read_trylock(&val->lock); + + if (locked) { + ctx->lock_held = true; + ctx->lock_held_exclusive = ctx->request_exclusive; + } + + return locked ? 0 : -EWOULDBLOCK; +} + +static void xe_validation_unlock(struct xe_validation_ctx *ctx) +{ + if (!ctx->lock_held) + return; + + if (ctx->lock_held_exclusive) + up_write(&ctx->val->lock); + else + up_read(&ctx->val->lock); + + ctx->lock_held = false; +} + +/** + * xe_validation_ctx_init() - Initialize an xe_validation_ctx + * @ctx: The xe_validation_ctx to initialize. + * @val: The xe_validation_device representing the validation domain. + * @exec: The struct drm_exec to use for the transaction. May be NULL. + * @flags: The flags to use for initialization. + * + * Initialize and lock a an xe_validation transaction using the validation domain + * represented by @val. Also initialize the drm_exec object forwarding parts of + * @flags to the drm_exec initialization. The @flags.exclusive flag should + * typically be set to false to avoid locking out other validators from the + * domain until an OOM is hit. For testing- or final attempt purposes it can, + * however, be set to true. + * + * Return: %0 on success, %-EINTR if interruptible initial locking failed with a + * signal pending. If @flags.no_block is set to true, a failed trylock + * returns %-EWOULDBLOCK. + */ +int xe_validation_ctx_init(struct xe_validation_ctx *ctx, struct xe_validation_device *val, + struct drm_exec *exec, const struct xe_val_flags flags) +{ + int ret; + + ctx->exec = exec; + ctx->val = val; + ctx->lock_held = false; + ctx->lock_held_exclusive = false; + ctx->request_exclusive = flags.exclusive; + ctx->val_flags = flags; + ctx->exec_flags = 0; + ctx->nr = 0; + + if (flags.no_block) + ret = xe_validation_trylock(ctx); + else + ret = xe_validation_lock(ctx); + if (ret) + return ret; + + if (exec) { + if (flags.interruptible) + ctx->exec_flags |= DRM_EXEC_INTERRUPTIBLE_WAIT; + if (flags.exec_ignore_duplicates) + ctx->exec_flags |= DRM_EXEC_IGNORE_DUPLICATES; + drm_exec_init(exec, ctx->exec_flags, ctx->nr); + } + + return 0; +} + +#ifdef CONFIG_DEBUG_WW_MUTEX_SLOWPATH +/* + * This abuses both drm_exec and ww_mutex internals and should be + * replaced by checking for -EDEADLK when we can make TTM + * stop converting -EDEADLK to -ENOMEM. + * An alternative is to not have exhaustive eviction with + * CONFIG_DEBUG_WW_MUTEX_SLOWPATH until that happens. + */ +static bool xe_validation_contention_injected(struct drm_exec *exec) +{ + return !!exec->ticket.contending_lock; +} + +#else + +static bool xe_validation_contention_injected(struct drm_exec *exec) +{ + return false; +} + +#endif + +static bool __xe_validation_should_retry(struct xe_validation_ctx *ctx, int ret) +{ + if (ret == -ENOMEM && + ((ctx->request_exclusive && + xe_validation_contention_injected(ctx->exec)) || + !ctx->request_exclusive)) { + ctx->request_exclusive = true; + return true; + } + + return false; +} + +/** + * xe_validation_exec_lock() - Perform drm_gpuvm_exec_lock within a validation + * transaction. + * @ctx: An uninitialized xe_validation_ctx. + * @vm_exec: An initialized struct vm_exec. + * @val: The validation domain. + * + * The drm_gpuvm_exec_lock() function internally initializes its drm_exec + * transaction and therefore doesn't lend itself very well to be using + * xe_validation_ctx_init(). Provide a helper that takes an uninitialized + * xe_validation_ctx and calls drm_gpuvm_exec_lock() with OOM retry. + * + * Return: %0 on success, negative error code on failure. + */ +int xe_validation_exec_lock(struct xe_validation_ctx *ctx, + struct drm_gpuvm_exec *vm_exec, + struct xe_validation_device *val) +{ + int ret; + + memset(ctx, 0, sizeof(*ctx)); + ctx->exec = &vm_exec->exec; + ctx->exec_flags = vm_exec->flags; + ctx->val = val; + if (ctx->exec_flags & DRM_EXEC_INTERRUPTIBLE_WAIT) + ctx->val_flags.interruptible = 1; + if (ctx->exec_flags & DRM_EXEC_IGNORE_DUPLICATES) + ctx->val_flags.exec_ignore_duplicates = 1; +retry: + ret = xe_validation_lock(ctx); + if (ret) + return ret; + + ret = drm_gpuvm_exec_lock(vm_exec); + if (ret) { + xe_validation_unlock(ctx); + if (__xe_validation_should_retry(ctx, ret)) + goto retry; + } + + return ret; +} + +/** + * xe_validation_ctx_fini() - Finalize a validation transaction + * @ctx: The Validation transaction to finalize. + * + * Finalize a validation transaction and its related drm_exec transaction. + */ +void xe_validation_ctx_fini(struct xe_validation_ctx *ctx) +{ + if (ctx->exec) + drm_exec_fini(ctx->exec); + xe_validation_unlock(ctx); +} + +/** + * xe_validation_should_retry() - Determine if a validation transaction should retry + * @ctx: The validation transaction. + * @ret: Pointer to a return value variable. + * + * Determines whether a validation transaction should retry based on the + * internal transaction state and the return value pointed to by @ret. + * If a validation should be retried, the transaction is prepared for that, + * and the validation locked might be re-locked in exclusive mode, and *@ret + * is set to %0. If the re-locking errors, typically due to interruptible + * locking with signal pending, *@ret is instead set to -EINTR and the + * function returns %false. + * + * Return: %true if validation should be retried, %false otherwise. + */ +bool xe_validation_should_retry(struct xe_validation_ctx *ctx, int *ret) +{ + if (__xe_validation_should_retry(ctx, *ret)) { + drm_exec_fini(ctx->exec); + *ret = 0; + if (ctx->request_exclusive != ctx->lock_held_exclusive) { + xe_validation_unlock(ctx); + *ret = xe_validation_lock(ctx); + } + drm_exec_init(ctx->exec, ctx->exec_flags, ctx->nr); + return !*ret; + } + + return false; +} diff --git a/drivers/gpu/drm/xe/xe_validation.h b/drivers/gpu/drm/xe/xe_validation.h new file mode 100644 index 000000000000..fec331d791e7 --- /dev/null +++ b/drivers/gpu/drm/xe/xe_validation.h @@ -0,0 +1,192 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2024 Intel Corporation + */ +#ifndef _XE_VALIDATION_H_ +#define _XE_VALIDATION_H_ + +#include <linux/dma-resv.h> +#include <linux/types.h> +#include <linux/rwsem.h> + +struct drm_exec; +struct drm_gem_object; +struct drm_gpuvm_exec; +struct xe_device; + +#ifdef CONFIG_PROVE_LOCKING +/** + * xe_validation_lockdep() - Assert that a drm_exec locking transaction can + * be initialized at this point. + */ +static inline void xe_validation_lockdep(void) +{ + struct ww_acquire_ctx ticket; + + ww_acquire_init(&ticket, &reservation_ww_class); + ww_acquire_fini(&ticket); +} +#else +static inline void xe_validation_lockdep(void) +{ +} +#endif + +/* + * Various values of the drm_exec pointer where we've not (yet) + * implemented full ww locking. + * + * XE_VALIDATION_UNIMPLEMENTED means implementation is pending. + * A lockdep check is made to assure that a drm_exec locking + * transaction can actually take place where the macro is + * used. If this asserts, the exec pointer needs to be assigned + * higher up in the callchain and passed down. + * + * XE_VALIDATION_UNSUPPORTED is for dma-buf code only where + * the dma-buf layer doesn't support WW locking. + * + * XE_VALIDATION_OPT_OUT is for simplification of kunit tests where + * exhaustive eviction isn't necessary. + */ +#define __XE_VAL_UNIMPLEMENTED -EINVAL +#define XE_VALIDATION_UNIMPLEMENTED (xe_validation_lockdep(), \ + (struct drm_exec *)ERR_PTR(__XE_VAL_UNIMPLEMENTED)) + +#define __XE_VAL_UNSUPPORTED -EOPNOTSUPP +#define XE_VALIDATION_UNSUPPORTED ((struct drm_exec *)ERR_PTR(__XE_VAL_UNSUPPORTED)) + +#define __XE_VAL_OPT_OUT -ENOMEM +#define XE_VALIDATION_OPT_OUT (xe_validation_lockdep(), \ + (struct drm_exec *)ERR_PTR(__XE_VAL_OPT_OUT)) +#ifdef CONFIG_DRM_XE_DEBUG +void xe_validation_assert_exec(const struct xe_device *xe, const struct drm_exec *exec, + const struct drm_gem_object *obj); +#else +#define xe_validation_assert_exec(_xe, _exec, _obj) \ + do { \ + (void)_xe; (void)_exec; (void)_obj; \ + } while (0) +#endif + +/** + * struct xe_validation_device - The domain for exhaustive eviction + * @lock: The lock used to exclude other processes from allocating graphics memory + * + * The struct xe_validation_device represents the domain for which we want to use + * exhaustive eviction. The @lock is typically grabbed in read mode for allocations + * but when graphics memory allocation fails, it is retried with the write mode held. + */ +struct xe_validation_device { + struct rw_semaphore lock; +}; + +/** + * struct xe_val_flags - Flags for xe_validation_ctx_init(). + * @exclusive: Start the validation transaction by locking out all other validators. + * @no_block: Don't block on initialization. + * @interruptible: Block interruptible if blocking. Implies initializing the drm_exec + * context with the DRM_EXEC_INTERRUPTIBLE_WAIT flag. + * @exec_ignore_duplicates: Initialize the drm_exec context with the + * DRM_EXEC_IGNORE_DUPLICATES flag. + */ +struct xe_val_flags { + u32 exclusive :1; + u32 no_block :1; + u32 interruptible :1; + u32 exec_ignore_duplicates :1; +}; + +/** + * struct xe_validation_ctx - A struct drm_exec subclass with support for + * exhaustive eviction + * @exec: The drm_exec object base class. Note that we use a pointer instead of + * embedding to avoid diamond inheritance. + * @val: The exhaustive eviction domain. + * @val_flags: Copy of the struct xe_val_flags passed to xe_validation_ctx_init. + * @lock_held: Whether The domain lock is currently held. + * @lock_held_exclusive: Whether the domain lock is held in exclusive mode. + * @request_exclusive: Whether to lock exclusively (write mode) the next time + * the domain lock is locked. + * @exec_flags: The drm_exec flags used for drm_exec (re-)initialization. + * @nr: The drm_exec nr parameter used for drm_exec (re-)initializaiton. + */ +struct xe_validation_ctx { + struct drm_exec *exec; + struct xe_validation_device *val; + struct xe_val_flags val_flags; + bool lock_held; + bool lock_held_exclusive; + bool request_exclusive; + u32 exec_flags; + unsigned int nr; +}; + +int xe_validation_ctx_init(struct xe_validation_ctx *ctx, struct xe_validation_device *val, + struct drm_exec *exec, const struct xe_val_flags flags); + +int xe_validation_exec_lock(struct xe_validation_ctx *ctx, struct drm_gpuvm_exec *vm_exec, + struct xe_validation_device *val); + +void xe_validation_ctx_fini(struct xe_validation_ctx *ctx); + +bool xe_validation_should_retry(struct xe_validation_ctx *ctx, int *ret); + +/** + * xe_validation_retry_on_oom() - Retry on oom in an xe_validaton transaction + * @_ctx: Pointer to the xe_validation_ctx + * @_ret: The current error value possibly holding -ENOMEM + * + * Use this in way similar to drm_exec_retry_on_contention(). + * If @_ret contains -ENOMEM the tranaction is restarted once in a way that + * blocks other transactions and allows exhastive eviction. If the transaction + * was already restarted once, Just return the -ENOMEM. May also set + * _ret to -EINTR if not retrying and waits are interruptible. + * May only be used within a drm_exec_until_all_locked() loop. + */ +#define xe_validation_retry_on_oom(_ctx, _ret) \ + do { \ + if (xe_validation_should_retry(_ctx, _ret)) \ + goto *__drm_exec_retry_ptr; \ + } while (0) + +/** + * xe_validation_device_init - Initialize a struct xe_validation_device + * @val: The xe_validation_device to init. + */ +static inline void +xe_validation_device_init(struct xe_validation_device *val) +{ + init_rwsem(&val->lock); +} + +/* + * Make guard() and scoped_guard() work with xe_validation_ctx + * so that we can exit transactions without caring about the + * cleanup. + */ +DEFINE_CLASS(xe_validation, struct xe_validation_ctx *, + if (_T) xe_validation_ctx_fini(_T);, + ({_ret = xe_validation_ctx_init(_ctx, _val, _exec, _flags); + _ret ? NULL : _ctx; }), + struct xe_validation_ctx *_ctx, struct xe_validation_device *_val, + struct drm_exec *_exec, const struct xe_val_flags _flags, int _ret); +static inline void *class_xe_validation_lock_ptr(class_xe_validation_t *_T) +{return *_T; } +#define class_xe_validation_is_conditional true + +/** + * xe_validation_guard() - An auto-cleanup xe_validation_ctx transaction + * @_ctx: The xe_validation_ctx. + * @_val: The xe_validation_device. + * @_exec: The struct drm_exec object + * @_flags: Flags for the xe_validation_ctx initialization. + * @_ret: Return in / out parameter. May be set by this macro. Typicall 0 when called. + * + * This macro is will initiate a drm_exec transaction with additional support for + * exhaustive eviction. + */ +#define xe_validation_guard(_ctx, _val, _exec, _flags, _ret) \ + scoped_guard(xe_validation, _ctx, _val, _exec, _flags, _ret) \ + drm_exec_until_all_locked(_exec) + +#endif diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index 3ff3c67aa79d..0cacab20ff85 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -41,7 +41,6 @@ #include "xe_tlb_inval.h" #include "xe_trace_bo.h" #include "xe_wa.h" -#include "xe_hmm.h" static struct drm_gem_object *xe_vm_obj(struct xe_vm *vm) { @@ -49,34 +48,17 @@ static struct drm_gem_object *xe_vm_obj(struct xe_vm *vm) } /** - * xe_vma_userptr_check_repin() - Advisory check for repin needed - * @uvma: The userptr vma + * xe_vm_drm_exec_lock() - Lock the vm's resv with a drm_exec transaction + * @vm: The vm whose resv is to be locked. + * @exec: The drm_exec transaction. * - * Check if the userptr vma has been invalidated since last successful - * repin. The check is advisory only and can the function can be called - * without the vm->userptr.notifier_lock held. There is no guarantee that the - * vma userptr will remain valid after a lockless check, so typically - * the call needs to be followed by a proper check under the notifier_lock. + * Helper to lock the vm's resv as part of a drm_exec transaction. * - * Return: 0 if userptr vma is valid, -EAGAIN otherwise; repin recommended. + * Return: %0 on success. See drm_exec_lock_obj() for error codes. */ -int xe_vma_userptr_check_repin(struct xe_userptr_vma *uvma) +int xe_vm_drm_exec_lock(struct xe_vm *vm, struct drm_exec *exec) { - return mmu_interval_check_retry(&uvma->userptr.notifier, - uvma->userptr.notifier_seq) ? - -EAGAIN : 0; -} - -int xe_vma_userptr_pin_pages(struct xe_userptr_vma *uvma) -{ - struct xe_vma *vma = &uvma->vma; - struct xe_vm *vm = xe_vma_vm(vma); - struct xe_device *xe = vm->xe; - - lockdep_assert_held(&vm->lock); - xe_assert(xe, xe_vma_is_userptr(vma)); - - return xe_hmm_userptr_populate_range(uvma, false); + return drm_exec_lock_obj(exec, xe_vm_obj(vm)); } static bool preempt_fences_waiting(struct xe_vm *vm) @@ -228,6 +210,7 @@ int xe_vm_add_compute_exec_queue(struct xe_vm *vm, struct xe_exec_queue *q) .num_fences = 1, }; struct drm_exec *exec = &vm_exec.exec; + struct xe_validation_ctx ctx; struct dma_fence *pfence; int err; bool wait; @@ -235,14 +218,14 @@ int xe_vm_add_compute_exec_queue(struct xe_vm *vm, struct xe_exec_queue *q) xe_assert(vm->xe, xe_vm_in_preempt_fence_mode(vm)); down_write(&vm->lock); - err = drm_gpuvm_exec_lock(&vm_exec); + err = xe_validation_exec_lock(&ctx, &vm_exec, &vm->xe->val); if (err) goto out_up_write; pfence = xe_preempt_fence_create(q, q->lr.context, ++q->lr.seqno); - if (!pfence) { - err = -ENOMEM; + if (IS_ERR(pfence)) { + err = PTR_ERR(pfence); goto out_fini; } @@ -250,7 +233,7 @@ int xe_vm_add_compute_exec_queue(struct xe_vm *vm, struct xe_exec_queue *q) ++vm->preempt.num_exec_queues; q->lr.pfence = pfence; - down_read(&vm->userptr.notifier_lock); + xe_svm_notifier_lock(vm); drm_gpuvm_resv_add_fence(&vm->gpuvm, exec, pfence, DMA_RESV_USAGE_BOOKKEEP, DMA_RESV_USAGE_BOOKKEEP); @@ -264,10 +247,10 @@ int xe_vm_add_compute_exec_queue(struct xe_vm *vm, struct xe_exec_queue *q) if (wait) dma_fence_enable_sw_signaling(pfence); - up_read(&vm->userptr.notifier_lock); + xe_svm_notifier_unlock(vm); out_fini: - drm_exec_fini(exec); + xe_validation_ctx_fini(&ctx); out_up_write: up_write(&vm->lock); @@ -300,25 +283,6 @@ void xe_vm_remove_compute_exec_queue(struct xe_vm *vm, struct xe_exec_queue *q) up_write(&vm->lock); } -/** - * __xe_vm_userptr_needs_repin() - Check whether the VM does have userptrs - * that need repinning. - * @vm: The VM. - * - * This function checks for whether the VM has userptrs that need repinning, - * and provides a release-type barrier on the userptr.notifier_lock after - * checking. - * - * Return: 0 if there are no userptrs needing repinning, -EAGAIN if there are. - */ -int __xe_vm_userptr_needs_repin(struct xe_vm *vm) -{ - lockdep_assert_held_read(&vm->userptr.notifier_lock); - - return (list_empty(&vm->userptr.repin_list) && - list_empty(&vm->userptr.invalidated)) ? 0 : -EAGAIN; -} - #define XE_VM_REBIND_RETRY_TIMEOUT_MS 1000 /** @@ -350,39 +314,6 @@ void xe_vm_kill(struct xe_vm *vm, bool unlocked) /* TODO: Inform user the VM is banned */ } -/** - * xe_vm_validate_should_retry() - Whether to retry after a validate error. - * @exec: The drm_exec object used for locking before validation. - * @err: The error returned from ttm_bo_validate(). - * @end: A ktime_t cookie that should be set to 0 before first use and - * that should be reused on subsequent calls. - * - * With multiple active VMs, under memory pressure, it is possible that - * ttm_bo_validate() run into -EDEADLK and in such case returns -ENOMEM. - * Until ttm properly handles locking in such scenarios, best thing the - * driver can do is retry with a timeout. Check if that is necessary, and - * if so unlock the drm_exec's objects while keeping the ticket to prepare - * for a rerun. - * - * Return: true if a retry after drm_exec_init() is recommended; - * false otherwise. - */ -bool xe_vm_validate_should_retry(struct drm_exec *exec, int err, ktime_t *end) -{ - ktime_t cur; - - if (err != -ENOMEM) - return false; - - cur = ktime_get(); - *end = *end ? : ktime_add_ms(cur, XE_VM_REBIND_RETRY_TIMEOUT_MS); - if (!ktime_before(cur, *end)) - return false; - - msleep(20); - return true; -} - static int xe_gpuvm_validate(struct drm_gpuvm_bo *vm_bo, struct drm_exec *exec) { struct xe_vm *vm = gpuvm_to_vm(vm_bo->vm); @@ -394,7 +325,10 @@ static int xe_gpuvm_validate(struct drm_gpuvm_bo *vm_bo, struct drm_exec *exec) list_move_tail(&gpuva_to_vma(gpuva)->combined_links.rebind, &vm->rebind_list); - ret = xe_bo_validate(gem_to_xe_bo(vm_bo->obj), vm, false); + if (!try_wait_for_completion(&vm->xe->pm_block)) + return -EAGAIN; + + ret = xe_bo_validate(gem_to_xe_bo(vm_bo->obj), vm, false, exec); if (ret) return ret; @@ -480,13 +414,40 @@ static int xe_preempt_work_begin(struct drm_exec *exec, struct xe_vm *vm, return xe_vm_validate_rebind(vm, exec, vm->preempt.num_exec_queues); } +static bool vm_suspend_rebind_worker(struct xe_vm *vm) +{ + struct xe_device *xe = vm->xe; + bool ret = false; + + mutex_lock(&xe->rebind_resume_lock); + if (!try_wait_for_completion(&vm->xe->pm_block)) { + ret = true; + list_move_tail(&vm->preempt.pm_activate_link, &xe->rebind_resume_list); + } + mutex_unlock(&xe->rebind_resume_lock); + + return ret; +} + +/** + * xe_vm_resume_rebind_worker() - Resume the rebind worker. + * @vm: The vm whose preempt worker to resume. + * + * Resume a preempt worker that was previously suspended by + * vm_suspend_rebind_worker(). + */ +void xe_vm_resume_rebind_worker(struct xe_vm *vm) +{ + queue_work(vm->xe->ordered_wq, &vm->preempt.rebind_work); +} + static void preempt_rebind_work_func(struct work_struct *w) { struct xe_vm *vm = container_of(w, struct xe_vm, preempt.rebind_work); + struct xe_validation_ctx ctx; struct drm_exec exec; unsigned int fence_count = 0; LIST_HEAD(preempt_fences); - ktime_t end = 0; int err = 0; long wait; int __maybe_unused tries = 0; @@ -503,24 +464,30 @@ static void preempt_rebind_work_func(struct work_struct *w) } retry: + if (!try_wait_for_completion(&vm->xe->pm_block) && vm_suspend_rebind_worker(vm)) { + up_write(&vm->lock); + return; + } + if (xe_vm_userptr_check_repin(vm)) { err = xe_vm_userptr_pin(vm); if (err) goto out_unlock_outer; } - drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT, 0); + err = xe_validation_ctx_init(&ctx, &vm->xe->val, &exec, + (struct xe_val_flags) {.interruptible = true}); + if (err) + goto out_unlock_outer; drm_exec_until_all_locked(&exec) { bool done = false; err = xe_preempt_work_begin(&exec, vm, &done); drm_exec_retry_on_contention(&exec); + xe_validation_retry_on_oom(&ctx, &err); if (err || done) { - drm_exec_fini(&exec); - if (err && xe_vm_validate_should_retry(&exec, err, &end)) - err = -EAGAIN; - + xe_validation_ctx_fini(&ctx); goto out_unlock_outer; } } @@ -529,7 +496,9 @@ retry: if (err) goto out_unlock; + xe_vm_set_validation_exec(vm, &exec); err = xe_vm_rebind(vm, true); + xe_vm_set_validation_exec(vm, NULL); if (err) goto out_unlock; @@ -547,9 +516,9 @@ retry: (!(__tries)++ || __xe_vm_userptr_needs_repin(__vm)) : \ __xe_vm_userptr_needs_repin(__vm)) - down_read(&vm->userptr.notifier_lock); + xe_svm_notifier_lock(vm); if (retry_required(tries, vm)) { - up_read(&vm->userptr.notifier_lock); + xe_svm_notifier_unlock(vm); err = -EAGAIN; goto out_unlock; } @@ -563,10 +532,10 @@ retry: /* Point of no return. */ arm_preempt_fences(vm, &preempt_fences); resume_and_reinstall_preempt_fences(vm, &exec); - up_read(&vm->userptr.notifier_lock); + xe_svm_notifier_unlock(vm); out_unlock: - drm_exec_fini(&exec); + xe_validation_ctx_fini(&ctx); out_unlock_outer: if (err == -EAGAIN) { trace_xe_vm_rebind_worker_retry(vm); @@ -584,203 +553,6 @@ out_unlock_outer: trace_xe_vm_rebind_worker_exit(vm); } -static void __vma_userptr_invalidate(struct xe_vm *vm, struct xe_userptr_vma *uvma) -{ - struct xe_userptr *userptr = &uvma->userptr; - struct xe_vma *vma = &uvma->vma; - struct dma_resv_iter cursor; - struct dma_fence *fence; - long err; - - /* - * Tell exec and rebind worker they need to repin and rebind this - * userptr. - */ - if (!xe_vm_in_fault_mode(vm) && - !(vma->gpuva.flags & XE_VMA_DESTROYED)) { - spin_lock(&vm->userptr.invalidated_lock); - list_move_tail(&userptr->invalidate_link, - &vm->userptr.invalidated); - spin_unlock(&vm->userptr.invalidated_lock); - } - - /* - * Preempt fences turn into schedule disables, pipeline these. - * Note that even in fault mode, we need to wait for binds and - * unbinds to complete, and those are attached as BOOKMARK fences - * to the vm. - */ - dma_resv_iter_begin(&cursor, xe_vm_resv(vm), - DMA_RESV_USAGE_BOOKKEEP); - dma_resv_for_each_fence_unlocked(&cursor, fence) - dma_fence_enable_sw_signaling(fence); - dma_resv_iter_end(&cursor); - - err = dma_resv_wait_timeout(xe_vm_resv(vm), - DMA_RESV_USAGE_BOOKKEEP, - false, MAX_SCHEDULE_TIMEOUT); - XE_WARN_ON(err <= 0); - - if (xe_vm_in_fault_mode(vm) && userptr->initial_bind) { - err = xe_vm_invalidate_vma(vma); - XE_WARN_ON(err); - } - - xe_hmm_userptr_unmap(uvma); -} - -static bool vma_userptr_invalidate(struct mmu_interval_notifier *mni, - const struct mmu_notifier_range *range, - unsigned long cur_seq) -{ - struct xe_userptr_vma *uvma = container_of(mni, typeof(*uvma), userptr.notifier); - struct xe_vma *vma = &uvma->vma; - struct xe_vm *vm = xe_vma_vm(vma); - - xe_assert(vm->xe, xe_vma_is_userptr(vma)); - trace_xe_vma_userptr_invalidate(vma); - - if (!mmu_notifier_range_blockable(range)) - return false; - - vm_dbg(&xe_vma_vm(vma)->xe->drm, - "NOTIFIER: addr=0x%016llx, range=0x%016llx", - xe_vma_start(vma), xe_vma_size(vma)); - - down_write(&vm->userptr.notifier_lock); - mmu_interval_set_seq(mni, cur_seq); - - __vma_userptr_invalidate(vm, uvma); - up_write(&vm->userptr.notifier_lock); - trace_xe_vma_userptr_invalidate_complete(vma); - - return true; -} - -static const struct mmu_interval_notifier_ops vma_userptr_notifier_ops = { - .invalidate = vma_userptr_invalidate, -}; - -#if IS_ENABLED(CONFIG_DRM_XE_USERPTR_INVAL_INJECT) -/** - * xe_vma_userptr_force_invalidate() - force invalidate a userptr - * @uvma: The userptr vma to invalidate - * - * Perform a forced userptr invalidation for testing purposes. - */ -void xe_vma_userptr_force_invalidate(struct xe_userptr_vma *uvma) -{ - struct xe_vm *vm = xe_vma_vm(&uvma->vma); - - /* Protect against concurrent userptr pinning */ - lockdep_assert_held(&vm->lock); - /* Protect against concurrent notifiers */ - lockdep_assert_held(&vm->userptr.notifier_lock); - /* - * Protect against concurrent instances of this function and - * the critical exec sections - */ - xe_vm_assert_held(vm); - - if (!mmu_interval_read_retry(&uvma->userptr.notifier, - uvma->userptr.notifier_seq)) - uvma->userptr.notifier_seq -= 2; - __vma_userptr_invalidate(vm, uvma); -} -#endif - -int xe_vm_userptr_pin(struct xe_vm *vm) -{ - struct xe_userptr_vma *uvma, *next; - int err = 0; - - xe_assert(vm->xe, !xe_vm_in_fault_mode(vm)); - lockdep_assert_held_write(&vm->lock); - - /* Collect invalidated userptrs */ - spin_lock(&vm->userptr.invalidated_lock); - xe_assert(vm->xe, list_empty(&vm->userptr.repin_list)); - list_for_each_entry_safe(uvma, next, &vm->userptr.invalidated, - userptr.invalidate_link) { - list_del_init(&uvma->userptr.invalidate_link); - list_add_tail(&uvma->userptr.repin_link, - &vm->userptr.repin_list); - } - spin_unlock(&vm->userptr.invalidated_lock); - - /* Pin and move to bind list */ - list_for_each_entry_safe(uvma, next, &vm->userptr.repin_list, - userptr.repin_link) { - err = xe_vma_userptr_pin_pages(uvma); - if (err == -EFAULT) { - list_del_init(&uvma->userptr.repin_link); - /* - * We might have already done the pin once already, but - * then had to retry before the re-bind happened, due - * some other condition in the caller, but in the - * meantime the userptr got dinged by the notifier such - * that we need to revalidate here, but this time we hit - * the EFAULT. In such a case make sure we remove - * ourselves from the rebind list to avoid going down in - * flames. - */ - if (!list_empty(&uvma->vma.combined_links.rebind)) - list_del_init(&uvma->vma.combined_links.rebind); - - /* Wait for pending binds */ - xe_vm_lock(vm, false); - dma_resv_wait_timeout(xe_vm_resv(vm), - DMA_RESV_USAGE_BOOKKEEP, - false, MAX_SCHEDULE_TIMEOUT); - - down_read(&vm->userptr.notifier_lock); - err = xe_vm_invalidate_vma(&uvma->vma); - up_read(&vm->userptr.notifier_lock); - xe_vm_unlock(vm); - if (err) - break; - } else { - if (err) - break; - - list_del_init(&uvma->userptr.repin_link); - list_move_tail(&uvma->vma.combined_links.rebind, - &vm->rebind_list); - } - } - - if (err) { - down_write(&vm->userptr.notifier_lock); - spin_lock(&vm->userptr.invalidated_lock); - list_for_each_entry_safe(uvma, next, &vm->userptr.repin_list, - userptr.repin_link) { - list_del_init(&uvma->userptr.repin_link); - list_move_tail(&uvma->userptr.invalidate_link, - &vm->userptr.invalidated); - } - spin_unlock(&vm->userptr.invalidated_lock); - up_write(&vm->userptr.notifier_lock); - } - return err; -} - -/** - * xe_vm_userptr_check_repin() - Check whether the VM might have userptrs - * that need repinning. - * @vm: The VM. - * - * This function does an advisory check for whether the VM has userptrs that - * need repinning. - * - * Return: 0 if there are no indications of userptrs needing repinning, - * -EAGAIN if there are. - */ -int xe_vm_userptr_check_repin(struct xe_vm *vm) -{ - return (list_empty_careful(&vm->userptr.repin_list) && - list_empty_careful(&vm->userptr.invalidated)) ? 0 : -EAGAIN; -} - static int xe_vma_ops_alloc(struct xe_vma_ops *vops, bool array_of_binds) { int i; @@ -1245,25 +1017,17 @@ static struct xe_vma *xe_vma_create(struct xe_vm *vm, drm_gpuvm_bo_put(vm_bo); } else /* userptr or null */ { if (!is_null && !is_cpu_addr_mirror) { - struct xe_userptr *userptr = &to_userptr_vma(vma)->userptr; + struct xe_userptr_vma *uvma = to_userptr_vma(vma); u64 size = end - start + 1; int err; - INIT_LIST_HEAD(&userptr->invalidate_link); - INIT_LIST_HEAD(&userptr->repin_link); vma->gpuva.gem.offset = bo_offset_or_userptr; - mutex_init(&userptr->unmap_mutex); - err = mmu_interval_notifier_insert(&userptr->notifier, - current->mm, - xe_vma_userptr(vma), size, - &vma_userptr_notifier_ops); + err = xe_userptr_setup(uvma, xe_vma_userptr(vma), size); if (err) { xe_vma_free(vma); return ERR_PTR(err); } - - userptr->notifier_seq = LONG_MAX; } xe_vm_get(vm); @@ -1283,18 +1047,8 @@ static void xe_vma_destroy_late(struct xe_vma *vma) if (xe_vma_is_userptr(vma)) { struct xe_userptr_vma *uvma = to_userptr_vma(vma); - struct xe_userptr *userptr = &uvma->userptr; - if (userptr->sg) - xe_hmm_userptr_free_sg(uvma); - - /* - * Since userptr pages are not pinned, we can't remove - * the notifier until we're sure the GPU is not accessing - * them anymore - */ - mmu_interval_notifier_remove(&userptr->notifier); - mutex_destroy(&userptr->unmap_mutex); + xe_userptr_remove(uvma); xe_vm_put(vm); } else if (xe_vma_is_null(vma) || xe_vma_is_cpu_addr_mirror(vma)) { xe_vm_put(vm); @@ -1331,11 +1085,7 @@ static void xe_vma_destroy(struct xe_vma *vma, struct dma_fence *fence) if (xe_vma_is_userptr(vma)) { xe_assert(vm->xe, vma->gpuva.flags & XE_VMA_DESTROYED); - - spin_lock(&vm->userptr.invalidated_lock); - xe_assert(vm->xe, list_empty(&to_userptr_vma(vma)->userptr.repin_link)); - list_del(&to_userptr_vma(vma)->userptr.invalidate_link); - spin_unlock(&vm->userptr.invalidated_lock); + xe_userptr_destroy(to_userptr_vma(vma)); } else if (!xe_vma_is_null(vma) && !xe_vma_is_cpu_addr_mirror(vma)) { xe_bo_assert_held(xe_vma_bo(vma)); @@ -1383,20 +1133,19 @@ int xe_vm_lock_vma(struct drm_exec *exec, struct xe_vma *vma) static void xe_vma_destroy_unlocked(struct xe_vma *vma) { + struct xe_device *xe = xe_vma_vm(vma)->xe; + struct xe_validation_ctx ctx; struct drm_exec exec; - int err; + int err = 0; - drm_exec_init(&exec, 0, 0); - drm_exec_until_all_locked(&exec) { + xe_validation_guard(&ctx, &xe->val, &exec, (struct xe_val_flags) {}, err) { err = xe_vm_lock_vma(&exec, vma); drm_exec_retry_on_contention(&exec); if (XE_WARN_ON(err)) break; + xe_vma_destroy(vma, NULL); } - - xe_vma_destroy(vma, NULL); - - drm_exec_fini(&exec); + xe_assert(xe, !err); } struct xe_vma * @@ -1621,6 +1370,7 @@ static void vm_destroy_work_func(struct work_struct *w); * @xe: xe device. * @tile: tile to set up for. * @vm: vm to set up for. + * @exec: The struct drm_exec object used to lock the vm resv. * * Sets up a pagetable tree with one page-table per level and a single * leaf PTE. All pagetable entries point to the single page-table or, @@ -1630,20 +1380,19 @@ static void vm_destroy_work_func(struct work_struct *w); * Return: 0 on success, negative error code on error. */ static int xe_vm_create_scratch(struct xe_device *xe, struct xe_tile *tile, - struct xe_vm *vm) + struct xe_vm *vm, struct drm_exec *exec) { u8 id = tile->id; int i; for (i = MAX_HUGEPTE_LEVEL; i < vm->pt_root[id]->level; i++) { - vm->scratch_pt[id][i] = xe_pt_create(vm, tile, i); + vm->scratch_pt[id][i] = xe_pt_create(vm, tile, i, exec); if (IS_ERR(vm->scratch_pt[id][i])) { int err = PTR_ERR(vm->scratch_pt[id][i]); vm->scratch_pt[id][i] = NULL; return err; } - xe_pt_populate_empty(tile, vm, vm->scratch_pt[id][i]); } @@ -1671,9 +1420,26 @@ static void xe_vm_free_scratch(struct xe_vm *vm) } } +static void xe_vm_pt_destroy(struct xe_vm *vm) +{ + struct xe_tile *tile; + u8 id; + + xe_vm_assert_held(vm); + + for_each_tile(tile, vm->xe, id) { + if (vm->pt_root[id]) { + xe_pt_destroy(vm->pt_root[id], vm->flags, NULL); + vm->pt_root[id] = NULL; + } + } +} + struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags, struct xe_file *xef) { struct drm_gem_object *vm_resv_obj; + struct xe_validation_ctx ctx; + struct drm_exec exec; struct xe_vm *vm; int err, number_tiles = 0; struct xe_tile *tile; @@ -1717,7 +1483,6 @@ struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags, struct xe_file *xef) INIT_LIST_HEAD(&vm->userptr.repin_list); INIT_LIST_HEAD(&vm->userptr.invalidated); - init_rwsem(&vm->userptr.notifier_lock); spin_lock_init(&vm->userptr.invalidated_lock); ttm_lru_bulk_move_init(&vm->lru_bulk_move); @@ -1741,13 +1506,12 @@ struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags, struct xe_file *xef) if (flags & XE_VM_FLAG_LR_MODE) { INIT_WORK(&vm->preempt.rebind_work, preempt_rebind_work_func); xe_pm_runtime_get_noresume(xe); + INIT_LIST_HEAD(&vm->preempt.pm_activate_link); } - if (flags & XE_VM_FLAG_FAULT_MODE) { - err = xe_svm_init(vm); - if (err) - goto err_no_resv; - } + err = xe_svm_init(vm); + if (err) + goto err_no_resv; vm_resv_obj = drm_gpuvm_resv_object_alloc(&xe->drm); if (!vm_resv_obj) { @@ -1760,49 +1524,68 @@ struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags, struct xe_file *xef) drm_gem_object_put(vm_resv_obj); - err = xe_vm_lock(vm, true); - if (err) - goto err_close; - - if (IS_DGFX(xe) && xe->info.vram_flags & XE_VRAM_FLAGS_NEED64K) - vm->flags |= XE_VM_FLAG_64K; - - for_each_tile(tile, xe, id) { - if (flags & XE_VM_FLAG_MIGRATION && - tile->id != XE_VM_FLAG_TILE_ID(flags)) - continue; + err = 0; + xe_validation_guard(&ctx, &xe->val, &exec, (struct xe_val_flags) {.interruptible = true}, + err) { + err = xe_vm_drm_exec_lock(vm, &exec); + drm_exec_retry_on_contention(&exec); - vm->pt_root[id] = xe_pt_create(vm, tile, xe->info.vm_max_level); - if (IS_ERR(vm->pt_root[id])) { - err = PTR_ERR(vm->pt_root[id]); - vm->pt_root[id] = NULL; - goto err_unlock_close; - } - } + if (IS_DGFX(xe) && xe->info.vram_flags & XE_VRAM_FLAGS_NEED64K) + vm->flags |= XE_VM_FLAG_64K; - if (xe_vm_has_scratch(vm)) { for_each_tile(tile, xe, id) { - if (!vm->pt_root[id]) + if (flags & XE_VM_FLAG_MIGRATION && + tile->id != XE_VM_FLAG_TILE_ID(flags)) continue; - err = xe_vm_create_scratch(xe, tile, vm); + vm->pt_root[id] = xe_pt_create(vm, tile, xe->info.vm_max_level, + &exec); + if (IS_ERR(vm->pt_root[id])) { + err = PTR_ERR(vm->pt_root[id]); + vm->pt_root[id] = NULL; + xe_vm_pt_destroy(vm); + drm_exec_retry_on_contention(&exec); + xe_validation_retry_on_oom(&ctx, &err); + break; + } + } + if (err) + break; + + if (xe_vm_has_scratch(vm)) { + for_each_tile(tile, xe, id) { + if (!vm->pt_root[id]) + continue; + + err = xe_vm_create_scratch(xe, tile, vm, &exec); + if (err) { + xe_vm_free_scratch(vm); + xe_vm_pt_destroy(vm); + drm_exec_retry_on_contention(&exec); + xe_validation_retry_on_oom(&ctx, &err); + break; + } + } if (err) - goto err_unlock_close; + break; + vm->batch_invalidate_tlb = true; } - vm->batch_invalidate_tlb = true; - } - if (vm->flags & XE_VM_FLAG_LR_MODE) - vm->batch_invalidate_tlb = false; + if (vm->flags & XE_VM_FLAG_LR_MODE) { + INIT_WORK(&vm->preempt.rebind_work, preempt_rebind_work_func); + vm->batch_invalidate_tlb = false; + } - /* Fill pt_root after allocating scratch tables */ - for_each_tile(tile, xe, id) { - if (!vm->pt_root[id]) - continue; + /* Fill pt_root after allocating scratch tables */ + for_each_tile(tile, xe, id) { + if (!vm->pt_root[id]) + continue; - xe_pt_populate_empty(tile, vm, vm->pt_root[id]); + xe_pt_populate_empty(tile, vm, vm->pt_root[id]); + } } - xe_vm_unlock(vm); + if (err) + goto err_close; /* Kernel migration VM shouldn't have a circular loop.. */ if (!(flags & XE_VM_FLAG_MIGRATION)) { @@ -1835,7 +1618,7 @@ struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags, struct xe_file *xef) &xe->usm.next_asid, GFP_KERNEL); up_write(&xe->usm.lock); if (err < 0) - goto err_unlock_close; + goto err_close; vm->usm.asid = asid; } @@ -1844,8 +1627,6 @@ struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags, struct xe_file *xef) return vm; -err_unlock_close: - xe_vm_unlock(vm); err_close: xe_vm_close_and_put(vm); return ERR_PTR(err); @@ -1922,8 +1703,12 @@ void xe_vm_close_and_put(struct xe_vm *vm) xe_assert(xe, !vm->preempt.num_exec_queues); xe_vm_close(vm); - if (xe_vm_in_preempt_fence_mode(vm)) + if (xe_vm_in_preempt_fence_mode(vm)) { + mutex_lock(&xe->rebind_resume_lock); + list_del_init(&vm->preempt.pm_activate_link); + mutex_unlock(&xe->rebind_resume_lock); flush_work(&vm->preempt.rebind_work); + } if (xe_vm_in_fault_mode(vm)) xe_svm_close(vm); @@ -1948,9 +1733,9 @@ void xe_vm_close_and_put(struct xe_vm *vm) vma = gpuva_to_vma(gpuva); if (xe_vma_has_no_bo(vma)) { - down_read(&vm->userptr.notifier_lock); + xe_svm_notifier_lock(vm); vma->gpuva.flags |= XE_VMA_DESTROYED; - up_read(&vm->userptr.notifier_lock); + xe_svm_notifier_unlock(vm); } xe_vm_remove_vma(vm, vma); @@ -1974,13 +1759,7 @@ void xe_vm_close_and_put(struct xe_vm *vm) * destroy the pagetables immediately. */ xe_vm_free_scratch(vm); - - for_each_tile(tile, xe, id) { - if (vm->pt_root[id]) { - xe_pt_destroy(vm->pt_root[id], vm->flags, NULL); - vm->pt_root[id] = NULL; - } - } + xe_vm_pt_destroy(vm); xe_vm_unlock(vm); /* @@ -1994,8 +1773,7 @@ void xe_vm_close_and_put(struct xe_vm *vm) xe_vma_destroy_unlocked(vma); } - if (xe_vm_in_fault_mode(vm)) - xe_svm_fini(vm); + xe_svm_fini(vm); up_write(&vm->lock); @@ -2288,6 +2066,8 @@ int xe_vm_query_vmas_attrs_ioctl(struct drm_device *dev, void *data, struct drm_ err = copy_to_user(attrs_user, mem_attrs, args->sizeof_mem_range_attr * args->num_mem_ranges); + if (err) + err = -EFAULT; free_mem_attrs: kvfree(mem_attrs); @@ -2336,9 +2116,9 @@ static const u32 region_to_mem_type[] = { static void prep_vma_destroy(struct xe_vm *vm, struct xe_vma *vma, bool post_commit) { - down_read(&vm->userptr.notifier_lock); + xe_svm_notifier_lock(vm); vma->gpuva.flags |= XE_VMA_DESTROYED; - up_read(&vm->userptr.notifier_lock); + xe_svm_notifier_unlock(vm); if (post_commit) xe_vm_remove_vma(vm, vma); } @@ -2599,6 +2379,7 @@ static struct xe_vma *new_vma(struct xe_vm *vm, struct drm_gpuva_op_map *op, struct xe_vma_mem_attr *attr, unsigned int flags) { struct xe_bo *bo = op->gem.obj ? gem_to_xe_bo(op->gem.obj) : NULL; + struct xe_validation_ctx ctx; struct drm_exec exec; struct xe_vma *vma; int err = 0; @@ -2606,9 +2387,9 @@ static struct xe_vma *new_vma(struct xe_vm *vm, struct drm_gpuva_op_map *op, lockdep_assert_held_write(&vm->lock); if (bo) { - drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT, 0); - drm_exec_until_all_locked(&exec) { - err = 0; + err = 0; + xe_validation_guard(&ctx, &vm->xe->val, &exec, + (struct xe_val_flags) {.interruptible = true}, err) { if (!bo->vm) { err = drm_exec_lock_obj(&exec, xe_vm_obj(vm)); drm_exec_retry_on_contention(&exec); @@ -2617,27 +2398,35 @@ static struct xe_vma *new_vma(struct xe_vm *vm, struct drm_gpuva_op_map *op, err = drm_exec_lock_obj(&exec, &bo->ttm.base); drm_exec_retry_on_contention(&exec); } - if (err) { - drm_exec_fini(&exec); + if (err) return ERR_PTR(err); - } - } - } - vma = xe_vma_create(vm, bo, op->gem.offset, - op->va.addr, op->va.addr + - op->va.range - 1, attr, flags); - if (IS_ERR(vma)) - goto err_unlock; - if (xe_vma_is_userptr(vma)) - err = xe_vma_userptr_pin_pages(to_userptr_vma(vma)); - else if (!xe_vma_has_no_bo(vma) && !bo->vm) - err = add_preempt_fences(vm, bo); + vma = xe_vma_create(vm, bo, op->gem.offset, + op->va.addr, op->va.addr + + op->va.range - 1, attr, flags); + if (IS_ERR(vma)) + return vma; -err_unlock: - if (bo) - drm_exec_fini(&exec); + if (!bo->vm) { + err = add_preempt_fences(vm, bo); + if (err) { + prep_vma_destroy(vm, vma, false); + xe_vma_destroy(vma, NULL); + } + } + } + if (err) + return ERR_PTR(err); + } else { + vma = xe_vma_create(vm, NULL, op->gem.offset, + op->va.addr, op->va.addr + + op->va.range - 1, attr, flags); + if (IS_ERR(vma)) + return vma; + if (xe_vma_is_userptr(vma)) + err = xe_vma_userptr_pin_pages(to_userptr_vma(vma)); + } if (err) { prep_vma_destroy(vm, vma, false); xe_vma_destroy_unlocked(vma); @@ -2981,9 +2770,9 @@ static void xe_vma_op_unwind(struct xe_vm *vm, struct xe_vma_op *op, struct xe_vma *vma = gpuva_to_vma(op->base.unmap.va); if (vma) { - down_read(&vm->userptr.notifier_lock); + xe_svm_notifier_lock(vm); vma->gpuva.flags &= ~XE_VMA_DESTROYED; - up_read(&vm->userptr.notifier_lock); + xe_svm_notifier_unlock(vm); if (post_commit) xe_vm_insert_vma(vm, vma); } @@ -3002,9 +2791,9 @@ static void xe_vma_op_unwind(struct xe_vm *vm, struct xe_vma_op *op, xe_vma_destroy_unlocked(op->remap.next); } if (vma) { - down_read(&vm->userptr.notifier_lock); + xe_svm_notifier_lock(vm); vma->gpuva.flags &= ~XE_VMA_DESTROYED; - up_read(&vm->userptr.notifier_lock); + xe_svm_notifier_unlock(vm); if (post_commit) xe_vm_insert_vma(vm, vma); } @@ -3054,7 +2843,7 @@ static int vma_lock_and_validate(struct drm_exec *exec, struct xe_vma *vma, err = drm_exec_lock_obj(exec, &bo->ttm.base); if (!err && validate) err = xe_bo_validate(bo, vm, - !xe_vm_in_preempt_fence_mode(vm)); + !xe_vm_in_preempt_fence_mode(vm), exec); } return err; @@ -3172,7 +2961,9 @@ static int op_lock_and_prep(struct drm_exec *exec, struct xe_vm *vm, false); if (!err && !xe_vma_has_no_bo(vma)) err = xe_bo_migrate(xe_vma_bo(vma), - region_to_mem_type[region]); + region_to_mem_type[region], + NULL, + exec); break; } default: @@ -3435,35 +3226,37 @@ static void vm_bind_ioctl_ops_fini(struct xe_vm *vm, struct xe_vma_ops *vops, static struct dma_fence *vm_bind_ioctl_ops_execute(struct xe_vm *vm, struct xe_vma_ops *vops) { + struct xe_validation_ctx ctx; struct drm_exec exec; struct dma_fence *fence; - int err; + int err = 0; lockdep_assert_held_write(&vm->lock); - drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT | - DRM_EXEC_IGNORE_DUPLICATES, 0); - drm_exec_until_all_locked(&exec) { + xe_validation_guard(&ctx, &vm->xe->val, &exec, + ((struct xe_val_flags) { + .interruptible = true, + .exec_ignore_duplicates = true, + }), err) { err = vm_bind_ioctl_ops_lock_and_prep(&exec, vm, vops); drm_exec_retry_on_contention(&exec); - if (err) { - fence = ERR_PTR(err); - goto unlock; - } + xe_validation_retry_on_oom(&ctx, &err); + if (err) + return ERR_PTR(err); + xe_vm_set_validation_exec(vm, &exec); fence = ops_execute(vm, vops); + xe_vm_set_validation_exec(vm, NULL); if (IS_ERR(fence)) { if (PTR_ERR(fence) == -ENODATA) vm_bind_ioctl_ops_fini(vm, vops, NULL); - goto unlock; + return fence; } vm_bind_ioctl_ops_fini(vm, vops, fence); } -unlock: - drm_exec_fini(&exec); - return fence; + return err ? ERR_PTR(err) : fence; } ALLOW_ERROR_INJECTION(vm_bind_ioctl_ops_execute, ERRNO); @@ -3579,6 +3372,8 @@ static int vm_bind_ioctl_check_args(struct xe_device *xe, struct xe_vm *vm, op == DRM_XE_VM_BIND_OP_MAP_USERPTR) || XE_IOCTL_DBG(xe, coh_mode == XE_COH_NONE && op == DRM_XE_VM_BIND_OP_MAP_USERPTR) || + XE_IOCTL_DBG(xe, op == DRM_XE_VM_BIND_OP_MAP_USERPTR && + !IS_ENABLED(CONFIG_DRM_GPUSVM)) || XE_IOCTL_DBG(xe, obj && op == DRM_XE_VM_BIND_OP_PREFETCH) || XE_IOCTL_DBG(xe, prefetch_region && @@ -4014,10 +3809,14 @@ release_vm_lock: */ int xe_vm_lock(struct xe_vm *vm, bool intr) { + int ret; + if (intr) - return dma_resv_lock_interruptible(xe_vm_resv(vm), NULL); + ret = dma_resv_lock_interruptible(xe_vm_resv(vm), NULL); + else + ret = dma_resv_lock(xe_vm_resv(vm), NULL); - return dma_resv_lock(xe_vm_resv(vm), NULL); + return ret; } /** @@ -4124,13 +3923,13 @@ int xe_vm_invalidate_vma(struct xe_vma *vma) */ if (IS_ENABLED(CONFIG_PROVE_LOCKING)) { if (xe_vma_is_userptr(vma)) { - lockdep_assert(lockdep_is_held_type(&vm->userptr.notifier_lock, 0) || - (lockdep_is_held_type(&vm->userptr.notifier_lock, 1) && + lockdep_assert(lockdep_is_held_type(&vm->svm.gpusvm.notifier_lock, 0) || + (lockdep_is_held_type(&vm->svm.gpusvm.notifier_lock, 1) && lockdep_is_held(&xe_vm_resv(vm)->lock.base))); WARN_ON_ONCE(!mmu_interval_check_retry (&to_userptr_vma(vma)->userptr.notifier, - to_userptr_vma(vma)->userptr.notifier_seq)); + to_userptr_vma(vma)->userptr.pages.notifier_seq)); WARN_ON_ONCE(!dma_resv_test_signaled(xe_vm_resv(vm), DMA_RESV_USAGE_BOOKKEEP)); diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h index b3e5bec0fa58..ef8a5019574e 100644 --- a/drivers/gpu/drm/xe/xe_vm.h +++ b/drivers/gpu/drm/xe/xe_vm.h @@ -220,12 +220,6 @@ static inline bool xe_vm_in_preempt_fence_mode(struct xe_vm *vm) int xe_vm_add_compute_exec_queue(struct xe_vm *vm, struct xe_exec_queue *q); void xe_vm_remove_compute_exec_queue(struct xe_vm *vm, struct xe_exec_queue *q); -int xe_vm_userptr_pin(struct xe_vm *vm); - -int __xe_vm_userptr_needs_repin(struct xe_vm *vm); - -int xe_vm_userptr_check_repin(struct xe_vm *vm); - int xe_vm_rebind(struct xe_vm *vm, bool rebind_worker); struct dma_fence *xe_vma_rebind(struct xe_vm *vm, struct xe_vma *vma, u8 tile_mask); @@ -266,12 +260,6 @@ static inline void xe_vm_reactivate_rebind(struct xe_vm *vm) } } -int xe_vma_userptr_pin_pages(struct xe_userptr_vma *uvma); - -int xe_vma_userptr_check_repin(struct xe_userptr_vma *uvma); - -bool xe_vm_validate_should_retry(struct drm_exec *exec, int err, ktime_t *end); - int xe_vm_lock_vma(struct drm_exec *exec, struct xe_vma *vma); int xe_vm_validate_rebind(struct xe_vm *vm, struct drm_exec *exec, @@ -281,6 +269,8 @@ struct dma_fence *xe_vm_bind_kernel_bo(struct xe_vm *vm, struct xe_bo *bo, struct xe_exec_queue *q, u64 addr, enum xe_cache_level cache_lvl); +void xe_vm_resume_rebind_worker(struct xe_vm *vm); + /** * xe_vm_resv() - Return's the vm's reservation object * @vm: The vm @@ -300,6 +290,8 @@ void xe_vm_kill(struct xe_vm *vm, bool unlocked); */ #define xe_vm_assert_held(vm) dma_resv_assert_held(xe_vm_resv(vm)) +int xe_vm_drm_exec_lock(struct xe_vm *vm, struct drm_exec *exec); + #if IS_ENABLED(CONFIG_DRM_XE_DEBUG_VM) #define vm_dbg drm_dbg #else @@ -329,7 +321,7 @@ static inline void xe_vm_set_validating(struct xe_vm *vm, bool allow_res_evict) if (vm && !allow_res_evict) { xe_vm_assert_held(vm); /* Pairs with READ_ONCE in xe_vm_is_validating() */ - WRITE_ONCE(vm->validating, current); + WRITE_ONCE(vm->validation.validating, current); } } @@ -347,7 +339,7 @@ static inline void xe_vm_clear_validating(struct xe_vm *vm, bool allow_res_evict { if (vm && !allow_res_evict) { /* Pairs with READ_ONCE in xe_vm_is_validating() */ - WRITE_ONCE(vm->validating, NULL); + WRITE_ONCE(vm->validation.validating, NULL); } } @@ -365,7 +357,7 @@ static inline void xe_vm_clear_validating(struct xe_vm *vm, bool allow_res_evict static inline bool xe_vm_is_validating(struct xe_vm *vm) { /* Pairs with WRITE_ONCE in xe_vm_is_validating() */ - if (READ_ONCE(vm->validating) == current) { + if (READ_ONCE(vm->validation.validating) == current) { xe_vm_assert_held(vm); return true; } @@ -373,6 +365,34 @@ static inline bool xe_vm_is_validating(struct xe_vm *vm) } /** + * xe_vm_set_validation_exec() - Accessor to set the drm_exec object + * @vm: The vm we want to register a drm_exec object with. + * @exec: The exec object we want to register. + * + * Set the drm_exec object used to lock the vm's resv. + */ +static inline void xe_vm_set_validation_exec(struct xe_vm *vm, struct drm_exec *exec) +{ + xe_vm_assert_held(vm); + xe_assert(vm->xe, !!exec ^ !!vm->validation._exec); + vm->validation._exec = exec; +} + +/** + * xe_vm_set_validation_exec() - Accessor to read the drm_exec object + * @vm: The vm we want to register a drm_exec object with. + * + * Return: The drm_exec object used to lock the vm's resv. The value + * is a valid pointer, %NULL, or one of the special values defined in + * xe_validation.h. + */ +static inline struct drm_exec *xe_vm_validation_exec(struct xe_vm *vm) +{ + xe_vm_assert_held(vm); + return vm->validation._exec; +} + +/** * xe_vm_has_valid_gpu_mapping() - Advisory helper to check if VMA or SVM range has * a valid GPU mapping * @tile: The tile which the GPU mapping belongs to @@ -391,11 +411,4 @@ static inline bool xe_vm_is_validating(struct xe_vm *vm) #define xe_vm_has_valid_gpu_mapping(tile, tile_present, tile_invalidated) \ ((READ_ONCE(tile_present) & ~READ_ONCE(tile_invalidated)) & BIT((tile)->id)) -#if IS_ENABLED(CONFIG_DRM_XE_USERPTR_INVAL_INJECT) -void xe_vma_userptr_force_invalidate(struct xe_userptr_vma *uvma); -#else -static inline void xe_vma_userptr_force_invalidate(struct xe_userptr_vma *uvma) -{ -} -#endif #endif diff --git a/drivers/gpu/drm/xe/xe_vm_madvise.c b/drivers/gpu/drm/xe/xe_vm_madvise.c index 09c5783ee523..cad3cf627c3f 100644 --- a/drivers/gpu/drm/xe/xe_vm_madvise.c +++ b/drivers/gpu/drm/xe/xe_vm_madvise.c @@ -18,9 +18,8 @@ struct xe_vmas_in_madvise_range { u64 range; struct xe_vma **vmas; int num_vmas; - bool has_svm_vmas; bool has_bo_vmas; - bool has_userptr_vmas; + bool has_svm_userptr_vmas; }; static int get_vmas(struct xe_vm *vm, struct xe_vmas_in_madvise_range *madvise_range) @@ -46,10 +45,8 @@ static int get_vmas(struct xe_vm *vm, struct xe_vmas_in_madvise_range *madvise_r if (xe_vma_bo(vma)) madvise_range->has_bo_vmas = true; - else if (xe_vma_is_cpu_addr_mirror(vma)) - madvise_range->has_svm_vmas = true; - else if (xe_vma_is_userptr(vma)) - madvise_range->has_userptr_vmas = true; + else if (xe_vma_is_cpu_addr_mirror(vma) || xe_vma_is_userptr(vma)) + madvise_range->has_svm_userptr_vmas = true; if (madvise_range->num_vmas == max_vmas) { max_vmas <<= 1; @@ -127,8 +124,6 @@ static void madvise_atomic(struct xe_device *xe, struct xe_vm *vm, vmas[i]->attr.atomic_access = op->atomic.val; } - vmas[i]->attr.atomic_access = op->atomic.val; - bo = xe_vma_bo(vmas[i]); if (!bo || bo->attr.atomic_access == op->atomic.val) continue; @@ -201,12 +196,12 @@ static u8 xe_zap_ptes_in_madvise_range(struct xe_vm *vm, u64 start, u64 end) if (xe_pt_zap_ptes(tile, vma)) { tile_mask |= BIT(id); - /* - * WRITE_ONCE pairs with READ_ONCE - * in xe_vm_has_valid_gpu_mapping() - */ - WRITE_ONCE(vma->tile_invalidated, - vma->tile_invalidated | BIT(id)); + /* + * WRITE_ONCE pairs with READ_ONCE + * in xe_vm_has_valid_gpu_mapping() + */ + WRITE_ONCE(vma->tile_invalidated, + vma->tile_invalidated | BIT(id)); } } } @@ -256,7 +251,7 @@ static bool madvise_args_are_sane(struct xe_device *xe, const struct drm_xe_madv if (XE_IOCTL_DBG(xe, args->preferred_mem_loc.pad)) return false; - if (XE_IOCTL_DBG(xe, args->atomic.reserved)) + if (XE_IOCTL_DBG(xe, args->preferred_mem_loc.reserved)) return false; break; } @@ -409,29 +404,20 @@ int xe_vm_madvise_ioctl(struct drm_device *dev, void *data, struct drm_file *fil } } - if (madvise_range.has_userptr_vmas) { - err = down_read_interruptible(&vm->userptr.notifier_lock); + if (madvise_range.has_svm_userptr_vmas) { + err = xe_svm_notifier_lock_interruptible(vm); if (err) goto err_fini; } - if (madvise_range.has_svm_vmas) { - err = down_read_interruptible(&vm->svm.gpusvm.notifier_lock); - if (err) - goto unlock_userptr; - } - attr_type = array_index_nospec(args->type, ARRAY_SIZE(madvise_funcs)); madvise_funcs[attr_type](xe, vm, madvise_range.vmas, madvise_range.num_vmas, args); err = xe_vm_invalidate_madvise_range(vm, args->start, args->start + args->range); - if (madvise_range.has_svm_vmas) + if (madvise_range.has_svm_userptr_vmas) xe_svm_notifier_unlock(vm); -unlock_userptr: - if (madvise_range.has_userptr_vmas) - up_read(&vm->userptr.notifier_lock); err_fini: if (madvise_range.has_bo_vmas) drm_exec_fini(&exec); diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h index b5108d010786..da39940501d8 100644 --- a/drivers/gpu/drm/xe/xe_vm_types.h +++ b/drivers/gpu/drm/xe/xe_vm_types.h @@ -17,6 +17,7 @@ #include "xe_device_types.h" #include "xe_pt_types.h" #include "xe_range_fence.h" +#include "xe_userptr.h" struct xe_bo; struct xe_svm_range; @@ -46,37 +47,6 @@ struct xe_vm_pgtable_update_op; #define XE_VMA_DUMPABLE (DRM_GPUVA_USERBITS << 8) #define XE_VMA_SYSTEM_ALLOCATOR (DRM_GPUVA_USERBITS << 9) -/** struct xe_userptr - User pointer */ -struct xe_userptr { - /** @invalidate_link: Link for the vm::userptr.invalidated list */ - struct list_head invalidate_link; - /** @userptr: link into VM repin list if userptr. */ - struct list_head repin_link; - /** - * @notifier: MMU notifier for user pointer (invalidation call back) - */ - struct mmu_interval_notifier notifier; - /** @sgt: storage for a scatter gather table */ - struct sg_table sgt; - /** @sg: allocated scatter gather table */ - struct sg_table *sg; - /** @notifier_seq: notifier sequence number */ - unsigned long notifier_seq; - /** @unmap_mutex: Mutex protecting dma-unmapping */ - struct mutex unmap_mutex; - /** - * @initial_bind: user pointer has been bound at least once. - * write: vm->userptr.notifier_lock in read mode and vm->resv held. - * read: vm->userptr.notifier_lock in write mode or vm->resv held. - */ - bool initial_bind; - /** @mapped: Whether the @sgt sg-table is dma-mapped. Protected by @unmap_mutex. */ - bool mapped; -#if IS_ENABLED(CONFIG_DRM_XE_USERPTR_INVAL_INJECT) - u32 divisor; -#endif -}; - /** * struct xe_vma_mem_attr - memory attributes associated with vma */ @@ -140,10 +110,10 @@ struct xe_vma { /** * @tile_invalidated: Tile mask of binding are invalidated for this VMA. - * protected by BO's resv and for userptrs, vm->userptr.notifier_lock in - * write mode for writing or vm->userptr.notifier_lock in read mode and + * protected by BO's resv and for userptrs, vm->svm.gpusvm.notifier_lock in + * write mode for writing or vm->svm.gpusvm.notifier_lock in read mode and * the vm->resv. For stable reading, BO's resv or userptr - * vm->userptr.notifier_lock in read mode is required. Can be + * vm->svm.gpusvm.notifier_lock in read mode is required. Can be * opportunistically read with READ_ONCE outside of locks. */ u8 tile_invalidated; @@ -154,7 +124,7 @@ struct xe_vma { /** * @tile_present: Tile mask of binding are present for this VMA. * protected by vm->lock, vm->resv and for userptrs, - * vm->userptr.notifier_lock for writing. Needs either for reading, + * vm->svm.gpusvm.notifier_lock for writing. Needs either for reading, * but if reading is done under the vm->lock only, it needs to be held * in write mode. */ @@ -289,33 +259,7 @@ struct xe_vm { const struct xe_pt_ops *pt_ops; /** @userptr: user pointer state */ - struct { - /** - * @userptr.repin_list: list of VMAs which are user pointers, - * and needs repinning. Protected by @lock. - */ - struct list_head repin_list; - /** - * @notifier_lock: protects notifier in write mode and - * submission in read mode. - */ - struct rw_semaphore notifier_lock; - /** - * @userptr.invalidated_lock: Protects the - * @userptr.invalidated list. - */ - spinlock_t invalidated_lock; - /** - * @userptr.invalidated: List of invalidated userptrs, not yet - * picked - * up for revalidation. Protected from access with the - * @invalidated_lock. Removing items from the list - * additionally requires @lock in write mode, and adding - * items to the list requires either the @userptr.notifier_lock in - * write mode, OR @lock in write mode. - */ - struct list_head invalidated; - } userptr; + struct xe_userptr_vm userptr; /** @preempt: preempt state */ struct { @@ -338,6 +282,11 @@ struct xe_vm { * BOs */ struct work_struct rebind_work; + /** + * @preempt.pm_activate_link: Link to list of rebind workers to be + * kicked on resume. + */ + struct list_head pm_activate_link; } preempt; /** @um: unified memory state */ @@ -358,18 +307,34 @@ struct xe_vm { } error_capture; /** + * @validation: Validation data only valid with the vm resv held. + * Note: This is really task state of the task holding the vm resv, + * and moving forward we should + * come up with a better way of passing this down the call- + * chain. + */ + struct { + /** + * @validation.validating: The task that is currently making bos resident. + * for this vm. + * Protected by the VM's resv for writing. Opportunistic reading can be done + * using READ_ONCE. Note: This is a workaround for the + * TTM eviction_valuable() callback not being passed a struct + * ttm_operation_context(). Future work might want to address this. + */ + struct task_struct *validating; + /** + * @validation.exec The drm_exec context used when locking the vm resv. + * Protected by the vm's resv. + */ + struct drm_exec *_exec; + } validation; + + /** * @tlb_flush_seqno: Required TLB flush seqno for the next exec. * protected by the vm resv. */ u64 tlb_flush_seqno; - /** - * @validating: The task that is currently making bos resident for this vm. - * Protected by the VM's resv for writing. Opportunistic reading can be done - * using READ_ONCE. Note: This is a workaround for the - * TTM eviction_valuable() callback not being passed a struct - * ttm_operation_context(). Future work might want to address this. - */ - struct task_struct *validating; /** @batch_invalidate_tlb: Always invalidate TLB before batch start */ bool batch_invalidate_tlb; /** @xef: XE file handle for tracking this VM's drm client */ diff --git a/drivers/gpu/drm/xe/xe_wa.c b/drivers/gpu/drm/xe/xe_wa.c index 52c7df4c3afd..cd03891654a1 100644 --- a/drivers/gpu/drm/xe/xe_wa.c +++ b/drivers/gpu/drm/xe/xe_wa.c @@ -39,7 +39,8 @@ * Register Immediate commands) once when initializing the device and saved in * the default context. That default context is then used on every context * creation to have a "primed golden context", i.e. a context image that - * already contains the changes needed to all the registers. + * already contains the changes needed to all the registers. See + * drivers/gpu/drm/xe/xe_lrc.c for default context handling. * * - Engine workarounds: the list of these WAs is applied whenever the specific * engine is reset. It's also possible that a set of engine classes share a @@ -48,10 +49,10 @@ * them need to keeep the workaround programming: the approach taken in the * driver is to tie those workarounds to the first compute/render engine that * is registered. When executing with GuC submission, engine resets are - * outside of kernel driver control, hence the list of registers involved in + * outside of kernel driver control, hence the list of registers involved is * written once, on engine initialization, and then passed to GuC, that * saves/restores their values before/after the reset takes place. See - * ``drivers/gpu/drm/xe/xe_guc_ads.c`` for reference. + * drivers/gpu/drm/xe/xe_guc_ads.c for reference. * * - GT workarounds: the list of these WAs is applied whenever these registers * revert to their default values: on GPU reset, suspend/resume [1]_, etc. @@ -66,21 +67,39 @@ * hardware on every HW context restore. These buffers are created and * programmed in the default context so the hardware always go through those * programming sequences when switching contexts. The support for workaround - * batchbuffers is enabled these hardware mechanisms: + * batchbuffers is enabled via these hardware mechanisms: * - * #. INDIRECT_CTX: A batchbuffer and an offset are provided in the default - * context, pointing the hardware to jump to that location when that offset - * is reached in the context restore. Workaround batchbuffer in the driver - * currently uses this mechanism for all platforms. + * #. INDIRECT_CTX (also known as **mid context restore bb**): A batchbuffer + * and an offset are provided in the default context, pointing the hardware + * to jump to that location when that offset is reached in the context + * restore. When a context is being restored, this is executed after the + * ring context, in the middle (or beginning) of the engine context image. * - * #. BB_PER_CTX_PTR: A batchbuffer is provided in the default context, - * pointing the hardware to a buffer to continue executing after the - * engine registers are restored in a context restore sequence. This is - * currently not used in the driver. + * #. BB_PER_CTX_PTR (also known as **post context restore bb**): A + * batchbuffer is provided in the default context, pointing the hardware to + * a buffer to continue executing after the engine registers are restored + * in a context restore sequence. + * + * Below is the timeline for a context restore sequence: + * + * .. code:: + * + * INDIRECT_CTX_OFFSET + * |----------->| + * .------------.------------.-------------.------------.--------------.-----------. + * |Ring | Engine | Mid-context | Engine | Post-context | Ring | + * |Restore | Restore (1)| BB Restore | Restore (2)| BB Restore | Execution | + * `------------'------------'-------------'------------'--------------'-----------' * * - Other/OOB: There are WAs that, due to their nature, cannot be applied from * a central place. Those are peppered around the rest of the code, as needed. - * Workarounds related to the display IP are the main example. + * There's a central place to control which workarounds are enabled: + * drivers/gpu/drm/xe/xe_wa_oob.rules for GT workarounds and + * drivers/gpu/drm/xe/xe_device_wa_oob.rules for device/SoC workarounds. + * These files only record which workarounds are enabled: during early device + * initialization those rules are evaluated and recorded by the driver. Then + * later the driver checks with ``XE_GT_WA()`` and ``XE_DEVICE_WA()`` to + * implement them. * * .. [1] Technically, some registers are powercontext saved & restored, so they * survive a suspend/resume. In practice, writing them again is not too @@ -612,6 +631,13 @@ static const struct xe_rtp_entry_sr engine_was[] = { FUNC(xe_rtp_match_first_render_or_compute)), XE_RTP_ACTIONS(SET(TDL_TSL_CHICKEN, RES_CHK_SPR_DIS)) }, + { XE_RTP_NAME("18041344222"), + XE_RTP_RULES(GRAPHICS_VERSION_RANGE(2001, 2002), + FUNC(xe_rtp_match_first_render_or_compute), + FUNC(xe_rtp_match_not_sriov_vf), + FUNC(xe_rtp_match_gt_has_discontiguous_dss_groups)), + XE_RTP_ACTIONS(SET(TDL_CHICKEN, EUSTALL_PERF_SAMPLING_DISABLE)) + }, /* Xe2_LPM */ @@ -672,6 +698,13 @@ static const struct xe_rtp_entry_sr engine_was[] = { XE_RTP_RULES(GRAPHICS_VERSION(3003), FUNC(xe_rtp_match_first_render_or_compute)), XE_RTP_ACTIONS(SET(HALF_SLICE_CHICKEN7, CLEAR_OPTIMIZATION_DISABLE)) }, + { XE_RTP_NAME("18041344222"), + XE_RTP_RULES(GRAPHICS_VERSION_RANGE(3000, 3001), + FUNC(xe_rtp_match_first_render_or_compute), + FUNC(xe_rtp_match_not_sriov_vf), + FUNC(xe_rtp_match_gt_has_discontiguous_dss_groups)), + XE_RTP_ACTIONS(SET(TDL_CHICKEN, EUSTALL_PERF_SAMPLING_DISABLE)) + }, }; static const struct xe_rtp_entry_sr lrc_was[] = { @@ -879,6 +912,10 @@ static const struct xe_rtp_entry_sr lrc_was[] = { DIS_PARTIAL_AUTOSTRIP | DIS_AUTOSTRIP)) }, + { XE_RTP_NAME("22021007897"), + XE_RTP_RULES(GRAPHICS_VERSION_RANGE(3000, 3003), ENGINE_CLASS(RENDER)), + XE_RTP_ACTIONS(SET(COMMON_SLICE_CHICKEN4, SBE_PUSH_CONSTANT_BEHIND_FIX_ENABLE)) + }, }; static __maybe_unused const struct xe_rtp_entry oob_was[] = { diff --git a/drivers/gpu/drm/xe/xe_wa_oob.rules b/drivers/gpu/drm/xe/xe_wa_oob.rules index 0cf2b3c03532..f3a6d5d239ce 100644 --- a/drivers/gpu/drm/xe/xe_wa_oob.rules +++ b/drivers/gpu/drm/xe/xe_wa_oob.rules @@ -32,7 +32,8 @@ 16022287689 GRAPHICS_VERSION(2001) GRAPHICS_VERSION(2004) 13011645652 GRAPHICS_VERSION(2004) - GRAPHICS_VERSION(3001) + GRAPHICS_VERSION_RANGE(3000, 3001) + GRAPHICS_VERSION(3003) 14022293748 GRAPHICS_VERSION_RANGE(2001, 2002) GRAPHICS_VERSION(2004) GRAPHICS_VERSION_RANGE(3000, 3001) @@ -48,7 +49,6 @@ 16023588340 GRAPHICS_VERSION(2001), FUNC(xe_rtp_match_not_sriov_vf) 14019789679 GRAPHICS_VERSION(1255) GRAPHICS_VERSION_RANGE(1270, 2004) -no_media_l3 MEDIA_VERSION_RANGE(3000, 3002) 14022866841 GRAPHICS_VERSION(3000), GRAPHICS_STEP(A0, B0) MEDIA_VERSION(3000), MEDIA_STEP(A0, B0) 16021333562 GRAPHICS_VERSION_RANGE(1200, 1274) diff --git a/drivers/gpu/nova-core/Kconfig b/drivers/gpu/nova-core/Kconfig index 8726d80d6ba4..20d3e6d0d796 100644 --- a/drivers/gpu/nova-core/Kconfig +++ b/drivers/gpu/nova-core/Kconfig @@ -1,5 +1,6 @@ config NOVA_CORE tristate "Nova Core GPU driver" + depends on 64BIT depends on PCI depends on RUST depends on RUST_FW_LOADER_ABSTRACTIONS diff --git a/drivers/gpu/nova-core/driver.rs b/drivers/gpu/nova-core/driver.rs index 274989ea1fb4..1380b47617f7 100644 --- a/drivers/gpu/nova-core/driver.rs +++ b/drivers/gpu/nova-core/driver.rs @@ -34,14 +34,19 @@ impl pci::Driver for NovaCore { pdev.enable_device_mem()?; pdev.set_master(); - let bar = Arc::pin_init( + let devres_bar = Arc::pin_init( pdev.iomap_region_sized::<BAR0_SIZE>(0, c_str!("nova-core/bar0")), GFP_KERNEL, )?; + // Used to provided a `&Bar0` to `Gpu::new` without tying it to the lifetime of + // `devres_bar`. + let bar_clone = Arc::clone(&devres_bar); + let bar = bar_clone.access(pdev.as_ref())?; + let this = KBox::pin_init( try_pin_init!(Self { - gpu <- Gpu::new(pdev, bar)?, + gpu <- Gpu::new(pdev, devres_bar, bar), _reg: auxiliary::Registration::new( pdev.as_ref(), c_str!("nova-drm"), @@ -54,4 +59,8 @@ impl pci::Driver for NovaCore { Ok(this) } + + fn unbind(pdev: &pci::Device<Core>, this: Pin<&Self>) { + this.gpu.unbind(pdev.as_ref()); + } } diff --git a/drivers/gpu/nova-core/falcon.rs b/drivers/gpu/nova-core/falcon.rs index 50437c67c14a..37e6298195e4 100644 --- a/drivers/gpu/nova-core/falcon.rs +++ b/drivers/gpu/nova-core/falcon.rs @@ -4,16 +4,17 @@ use core::ops::Deref; use hal::FalconHal; -use kernel::bindings; use kernel::device; +use kernel::dma::DmaAddress; use kernel::prelude::*; +use kernel::sync::aref::ARef; use kernel::time::Delta; -use kernel::types::ARef; use crate::dma::DmaObject; use crate::driver::Bar0; use crate::gpu::Chipset; use crate::regs; +use crate::regs::macros::RegisterBase; use crate::util; pub(crate) mod gsp; @@ -274,14 +275,25 @@ impl From<bool> for FalconFbifMemType { } } -/// Trait defining the parameters of a given Falcon instance. -pub(crate) trait FalconEngine: Sync { - /// Base I/O address for the falcon, relative from which its registers are accessed. - const BASE: usize; +/// Type used to represent the `PFALCON` registers address base for a given falcon engine. +pub(crate) struct PFalconBase(()); + +/// Type used to represent the `PFALCON2` registers address base for a given falcon engine. +pub(crate) struct PFalcon2Base(()); + +/// Trait defining the parameters of a given Falcon engine. +/// +/// Each engine provides one base for `PFALCON` and `PFALCON2` registers. The `ID` constant is used +/// to identify a given Falcon instance with register I/O methods. +pub(crate) trait FalconEngine: + Send + Sync + RegisterBase<PFalconBase> + RegisterBase<PFalcon2Base> + Sized +{ + /// Singleton of the engine, used to identify it with register I/O methods. + const ID: Self; } /// Represents a portion of the firmware to be loaded into a particular memory (e.g. IMEM or DMEM). -#[derive(Debug)] +#[derive(Debug, Clone)] pub(crate) struct FalconLoadTarget { /// Offset from the start of the source object to copy from. pub(crate) src_start: u32, @@ -292,7 +304,7 @@ pub(crate) struct FalconLoadTarget { } /// Parameters for the falcon boot ROM. -#[derive(Debug)] +#[derive(Debug, Clone)] pub(crate) struct FalconBromParams { /// Offset in `DMEM`` of the firmware's signature. pub(crate) pkc_data_offset: u32, @@ -343,13 +355,13 @@ impl<E: FalconEngine + 'static> Falcon<E> { bar: &Bar0, need_riscv: bool, ) -> Result<Self> { - let hwcfg1 = regs::NV_PFALCON_FALCON_HWCFG1::read(bar, E::BASE); + let hwcfg1 = regs::NV_PFALCON_FALCON_HWCFG1::read(bar, &E::ID); // Check that the revision and security model contain valid values. let _ = hwcfg1.core_rev()?; let _ = hwcfg1.security_model()?; if need_riscv { - let hwcfg2 = regs::NV_PFALCON_FALCON_HWCFG2::read(bar, E::BASE); + let hwcfg2 = regs::NV_PFALCON_FALCON_HWCFG2::read(bar, &E::ID); if !hwcfg2.riscv() { dev_err!( dev, @@ -369,7 +381,7 @@ impl<E: FalconEngine + 'static> Falcon<E> { fn reset_wait_mem_scrubbing(&self, bar: &Bar0) -> Result { // TIMEOUT: memory scrubbing should complete in less than 20ms. util::wait_on(Delta::from_millis(20), || { - if regs::NV_PFALCON_FALCON_HWCFG2::read(bar, E::BASE).mem_scrubbing_done() { + if regs::NV_PFALCON_FALCON_HWCFG2::read(bar, &E::ID).mem_scrubbing_done() { Some(()) } else { None @@ -379,12 +391,12 @@ impl<E: FalconEngine + 'static> Falcon<E> { /// Reset the falcon engine. fn reset_eng(&self, bar: &Bar0) -> Result { - let _ = regs::NV_PFALCON_FALCON_HWCFG2::read(bar, E::BASE); + let _ = regs::NV_PFALCON_FALCON_HWCFG2::read(bar, &E::ID); // According to OpenRM's `kflcnPreResetWait_GA102` documentation, HW sometimes does not set // RESET_READY so a non-failing timeout is used. let _ = util::wait_on(Delta::from_micros(150), || { - let r = regs::NV_PFALCON_FALCON_HWCFG2::read(bar, E::BASE); + let r = regs::NV_PFALCON_FALCON_HWCFG2::read(bar, &E::ID); if r.reset_ready() { Some(()) } else { @@ -392,13 +404,13 @@ impl<E: FalconEngine + 'static> Falcon<E> { } }); - regs::NV_PFALCON_FALCON_ENGINE::alter(bar, E::BASE, |v| v.set_reset(true)); + regs::NV_PFALCON_FALCON_ENGINE::alter(bar, &E::ID, |v| v.set_reset(true)); // TODO[DLAY]: replace with udelay() or equivalent once available. // TIMEOUT: falcon engine should not take more than 10us to reset. let _: Result = util::wait_on(Delta::from_micros(10), || None); - regs::NV_PFALCON_FALCON_ENGINE::alter(bar, E::BASE, |v| v.set_reset(false)); + regs::NV_PFALCON_FALCON_ENGINE::alter(bar, &E::ID, |v| v.set_reset(false)); self.reset_wait_mem_scrubbing(bar)?; @@ -413,7 +425,7 @@ impl<E: FalconEngine + 'static> Falcon<E> { regs::NV_PFALCON_FALCON_RM::default() .set_value(regs::NV_PMC_BOOT_0::read(bar).into()) - .write(bar, E::BASE); + .write(bar, &E::ID); Ok(()) } @@ -443,7 +455,7 @@ impl<E: FalconEngine + 'static> Falcon<E> { fw.dma_handle_with_offset(load_offsets.src_start as usize)?, ), }; - if dma_start % bindings::dma_addr_t::from(DMA_LEN) > 0 { + if dma_start % DmaAddress::from(DMA_LEN) > 0 { dev_err!( self.dev, "DMA transfer start addresses must be a multiple of {}", @@ -451,44 +463,57 @@ impl<E: FalconEngine + 'static> Falcon<E> { ); return Err(EINVAL); } - if load_offsets.len % DMA_LEN > 0 { - dev_err!( - self.dev, - "DMA transfer length must be a multiple of {}", - DMA_LEN - ); - return Err(EINVAL); - } + + // DMA transfers can only be done in units of 256 bytes. Compute how many such transfers we + // need to perform. + let num_transfers = load_offsets.len.div_ceil(DMA_LEN); + + // Check that the area we are about to transfer is within the bounds of the DMA object. + // Upper limit of transfer is `(num_transfers * DMA_LEN) + load_offsets.src_start`. + match num_transfers + .checked_mul(DMA_LEN) + .and_then(|size| size.checked_add(load_offsets.src_start)) + { + None => { + dev_err!(self.dev, "DMA transfer length overflow"); + return Err(EOVERFLOW); + } + Some(upper_bound) if upper_bound as usize > fw.size() => { + dev_err!(self.dev, "DMA transfer goes beyond range of DMA object"); + return Err(EINVAL); + } + Some(_) => (), + }; // Set up the base source DMA address. regs::NV_PFALCON_FALCON_DMATRFBASE::default() .set_base((dma_start >> 8) as u32) - .write(bar, E::BASE); + .write(bar, &E::ID); regs::NV_PFALCON_FALCON_DMATRFBASE1::default() .set_base((dma_start >> 40) as u16) - .write(bar, E::BASE); + .write(bar, &E::ID); let cmd = regs::NV_PFALCON_FALCON_DMATRFCMD::default() .set_size(DmaTrfCmdSize::Size256B) .set_imem(target_mem == FalconMem::Imem) .set_sec(if sec { 1 } else { 0 }); - for pos in (0..load_offsets.len).step_by(DMA_LEN as usize) { + for pos in (0..num_transfers).map(|i| i * DMA_LEN) { // Perform a transfer of size `DMA_LEN`. regs::NV_PFALCON_FALCON_DMATRFMOFFS::default() .set_offs(load_offsets.dst_start + pos) - .write(bar, E::BASE); + .write(bar, &E::ID); regs::NV_PFALCON_FALCON_DMATRFFBOFFS::default() .set_offs(src_start + pos) - .write(bar, E::BASE); - cmd.write(bar, E::BASE); + .write(bar, &E::ID); + cmd.write(bar, &E::ID); // Wait for the transfer to complete. // TIMEOUT: arbitrarily large value, no DMA transfer to the falcon's small memories // should ever take that long. util::wait_on(Delta::from_secs(2), || { - let r = regs::NV_PFALCON_FALCON_DMATRFCMD::read(bar, E::BASE); + let r = regs::NV_PFALCON_FALCON_DMATRFCMD::read(bar, &E::ID); if r.idle() { Some(()) } else { @@ -502,9 +527,9 @@ impl<E: FalconEngine + 'static> Falcon<E> { /// Perform a DMA load into `IMEM` and `DMEM` of `fw`, and prepare the falcon to run it. pub(crate) fn dma_load<F: FalconFirmware<Target = E>>(&self, bar: &Bar0, fw: &F) -> Result { - regs::NV_PFALCON_FBIF_CTL::alter(bar, E::BASE, |v| v.set_allow_phys_no_ctx(true)); - regs::NV_PFALCON_FALCON_DMACTL::default().write(bar, E::BASE); - regs::NV_PFALCON_FBIF_TRANSCFG::alter(bar, E::BASE, |v| { + regs::NV_PFALCON_FBIF_CTL::alter(bar, &E::ID, |v| v.set_allow_phys_no_ctx(true)); + regs::NV_PFALCON_FALCON_DMACTL::default().write(bar, &E::ID); + regs::NV_PFALCON_FBIF_TRANSCFG::alter(bar, &E::ID, 0, |v| { v.set_target(FalconFbifTarget::CoherentSysmem) .set_mem_type(FalconFbifMemType::Physical) }); @@ -517,7 +542,7 @@ impl<E: FalconEngine + 'static> Falcon<E> { // Set `BootVec` to start of non-secure code. regs::NV_PFALCON_FALCON_BOOTVEC::default() .set_value(fw.boot_addr()) - .write(bar, E::BASE); + .write(bar, &E::ID); Ok(()) } @@ -538,27 +563,27 @@ impl<E: FalconEngine + 'static> Falcon<E> { if let Some(mbox0) = mbox0 { regs::NV_PFALCON_FALCON_MAILBOX0::default() .set_value(mbox0) - .write(bar, E::BASE); + .write(bar, &E::ID); } if let Some(mbox1) = mbox1 { regs::NV_PFALCON_FALCON_MAILBOX1::default() .set_value(mbox1) - .write(bar, E::BASE); + .write(bar, &E::ID); } - match regs::NV_PFALCON_FALCON_CPUCTL::read(bar, E::BASE).alias_en() { + match regs::NV_PFALCON_FALCON_CPUCTL::read(bar, &E::ID).alias_en() { true => regs::NV_PFALCON_FALCON_CPUCTL_ALIAS::default() .set_startcpu(true) - .write(bar, E::BASE), + .write(bar, &E::ID), false => regs::NV_PFALCON_FALCON_CPUCTL::default() .set_startcpu(true) - .write(bar, E::BASE), + .write(bar, &E::ID), } // TIMEOUT: arbitrarily large value, firmwares should complete in less than 2 seconds. util::wait_on(Delta::from_secs(2), || { - let r = regs::NV_PFALCON_FALCON_CPUCTL::read(bar, E::BASE); + let r = regs::NV_PFALCON_FALCON_CPUCTL::read(bar, &E::ID); if r.halted() { Some(()) } else { @@ -567,8 +592,8 @@ impl<E: FalconEngine + 'static> Falcon<E> { })?; let (mbox0, mbox1) = ( - regs::NV_PFALCON_FALCON_MAILBOX0::read(bar, E::BASE).value(), - regs::NV_PFALCON_FALCON_MAILBOX1::read(bar, E::BASE).value(), + regs::NV_PFALCON_FALCON_MAILBOX0::read(bar, &E::ID).value(), + regs::NV_PFALCON_FALCON_MAILBOX1::read(bar, &E::ID).value(), ); Ok((mbox0, mbox1)) diff --git a/drivers/gpu/nova-core/falcon/gsp.rs b/drivers/gpu/nova-core/falcon/gsp.rs index d622e9a64470..f17599cb49fa 100644 --- a/drivers/gpu/nova-core/falcon/gsp.rs +++ b/drivers/gpu/nova-core/falcon/gsp.rs @@ -2,23 +2,31 @@ use crate::{ driver::Bar0, - falcon::{Falcon, FalconEngine}, - regs, + falcon::{Falcon, FalconEngine, PFalcon2Base, PFalconBase}, + regs::{self, macros::RegisterBase}, }; /// Type specifying the `Gsp` falcon engine. Cannot be instantiated. pub(crate) struct Gsp(()); -impl FalconEngine for Gsp { +impl RegisterBase<PFalconBase> for Gsp { const BASE: usize = 0x00110000; } +impl RegisterBase<PFalcon2Base> for Gsp { + const BASE: usize = 0x00111000; +} + +impl FalconEngine for Gsp { + const ID: Self = Gsp(()); +} + impl Falcon<Gsp> { /// Clears the SWGEN0 bit in the Falcon's IRQ status clear register to /// allow GSP to signal CPU for processing new messages in message queue. pub(crate) fn clear_swgen0_intr(&self, bar: &Bar0) { regs::NV_PFALCON_FALCON_IRQSCLR::default() .set_swgen0(true) - .write(bar, Gsp::BASE); + .write(bar, &Gsp::ID); } } diff --git a/drivers/gpu/nova-core/falcon/hal.rs b/drivers/gpu/nova-core/falcon/hal.rs index b233bc365882..bba288455617 100644 --- a/drivers/gpu/nova-core/falcon/hal.rs +++ b/drivers/gpu/nova-core/falcon/hal.rs @@ -13,7 +13,7 @@ mod ga102; /// Implements chipset-specific low-level operations. The trait is generic against [`FalconEngine`] /// so its `BASE` parameter can be used in order to avoid runtime bound checks when accessing /// registers. -pub(crate) trait FalconHal<E: FalconEngine>: Sync { +pub(crate) trait FalconHal<E: FalconEngine>: Send + Sync { /// Activates the Falcon core if the engine is a risvc/falcon dual engine. fn select_core(&self, _falcon: &Falcon<E>, _bar: &Bar0) -> Result { Ok(()) diff --git a/drivers/gpu/nova-core/falcon/hal/ga102.rs b/drivers/gpu/nova-core/falcon/hal/ga102.rs index 52c33d3f22a8..0b1cbe7853b3 100644 --- a/drivers/gpu/nova-core/falcon/hal/ga102.rs +++ b/drivers/gpu/nova-core/falcon/hal/ga102.rs @@ -16,15 +16,15 @@ use crate::util; use super::FalconHal; fn select_core_ga102<E: FalconEngine>(bar: &Bar0) -> Result { - let bcr_ctrl = regs::NV_PRISCV_RISCV_BCR_CTRL::read(bar, E::BASE); + let bcr_ctrl = regs::NV_PRISCV_RISCV_BCR_CTRL::read(bar, &E::ID); if bcr_ctrl.core_select() != PeregrineCoreSelect::Falcon { regs::NV_PRISCV_RISCV_BCR_CTRL::default() .set_core_select(PeregrineCoreSelect::Falcon) - .write(bar, E::BASE); + .write(bar, &E::ID); // TIMEOUT: falcon core should take less than 10ms to report being enabled. util::wait_on(Delta::from_millis(10), || { - let r = regs::NV_PRISCV_RISCV_BCR_CTRL::read(bar, E::BASE); + let r = regs::NV_PRISCV_RISCV_BCR_CTRL::read(bar, &E::ID); if r.valid() { Some(()) } else { @@ -42,50 +42,47 @@ fn signature_reg_fuse_version_ga102( engine_id_mask: u16, ucode_id: u8, ) -> Result<u32> { - // TODO[REGA]: The ucode fuse versions are contained in the - // FUSE_OPT_FPF_<ENGINE>_UCODE<X>_VERSION registers, which are an array. Our register - // definition macros do not allow us to manage them properly, so we need to hardcode their - // addresses for now. Clean this up once we support register arrays. + const NV_FUSE_OPT_FPF_SIZE: u8 = regs::NV_FUSE_OPT_FPF_SIZE as u8; // Each engine has 16 ucode version registers numbered from 1 to 16. - if ucode_id == 0 || ucode_id > 16 { - dev_err!(dev, "invalid ucode id {:#x}", ucode_id); - return Err(EINVAL); - } + let ucode_idx = match ucode_id { + 1..=NV_FUSE_OPT_FPF_SIZE => (ucode_id - 1) as usize, + _ => { + dev_err!(dev, "invalid ucode id {:#x}", ucode_id); + return Err(EINVAL); + } + }; - // Base address of the FUSE registers array corresponding to the engine. - let reg_fuse_base = if engine_id_mask & 0x0001 != 0 { - regs::NV_FUSE_OPT_FPF_SEC2_UCODE1_VERSION::OFFSET + // `ucode_idx` is guaranteed to be in the range [0..15], making the `read` calls provable valid + // at build-time. + let reg_fuse_version = if engine_id_mask & 0x0001 != 0 { + regs::NV_FUSE_OPT_FPF_SEC2_UCODE1_VERSION::read(bar, ucode_idx).data() } else if engine_id_mask & 0x0004 != 0 { - regs::NV_FUSE_OPT_FPF_NVDEC_UCODE1_VERSION::OFFSET + regs::NV_FUSE_OPT_FPF_NVDEC_UCODE1_VERSION::read(bar, ucode_idx).data() } else if engine_id_mask & 0x0400 != 0 { - regs::NV_FUSE_OPT_FPF_GSP_UCODE1_VERSION::OFFSET + regs::NV_FUSE_OPT_FPF_GSP_UCODE1_VERSION::read(bar, ucode_idx).data() } else { dev_err!(dev, "unexpected engine_id_mask {:#x}", engine_id_mask); return Err(EINVAL); }; - // Read `reg_fuse_base[ucode_id - 1]`. - let reg_fuse_version = - bar.read32(reg_fuse_base + ((ucode_id - 1) as usize * core::mem::size_of::<u32>())); - // TODO[NUMM]: replace with `last_set_bit` once it lands. - Ok(u32::BITS - reg_fuse_version.leading_zeros()) + Ok(u16::BITS - reg_fuse_version.leading_zeros()) } fn program_brom_ga102<E: FalconEngine>(bar: &Bar0, params: &FalconBromParams) -> Result { regs::NV_PFALCON2_FALCON_BROM_PARAADDR::default() .set_value(params.pkc_data_offset) - .write(bar, E::BASE); + .write(bar, &E::ID, 0); regs::NV_PFALCON2_FALCON_BROM_ENGIDMASK::default() .set_value(u32::from(params.engine_id_mask)) - .write(bar, E::BASE); + .write(bar, &E::ID); regs::NV_PFALCON2_FALCON_BROM_CURR_UCODE_ID::default() .set_ucode_id(params.ucode_id) - .write(bar, E::BASE); + .write(bar, &E::ID); regs::NV_PFALCON2_FALCON_MOD_SEL::default() .set_algo(FalconModSelAlgo::Rsa3k) - .write(bar, E::BASE); + .write(bar, &E::ID); Ok(()) } diff --git a/drivers/gpu/nova-core/falcon/sec2.rs b/drivers/gpu/nova-core/falcon/sec2.rs index 5147d9e2a7fe..815786c8480d 100644 --- a/drivers/gpu/nova-core/falcon/sec2.rs +++ b/drivers/gpu/nova-core/falcon/sec2.rs @@ -1,10 +1,19 @@ // SPDX-License-Identifier: GPL-2.0 -use crate::falcon::FalconEngine; +use crate::falcon::{FalconEngine, PFalcon2Base, PFalconBase}; +use crate::regs::macros::RegisterBase; /// Type specifying the `Sec2` falcon engine. Cannot be instantiated. pub(crate) struct Sec2(()); -impl FalconEngine for Sec2 { +impl RegisterBase<PFalconBase> for Sec2 { const BASE: usize = 0x00840000; } + +impl RegisterBase<PFalcon2Base> for Sec2 { + const BASE: usize = 0x00841000; +} + +impl FalconEngine for Sec2 { + const ID: Self = Sec2(()); +} diff --git a/drivers/gpu/nova-core/fb.rs b/drivers/gpu/nova-core/fb.rs index 4a702525fff4..68559902ae78 100644 --- a/drivers/gpu/nova-core/fb.rs +++ b/drivers/gpu/nova-core/fb.rs @@ -4,7 +4,7 @@ use core::ops::Range; use kernel::prelude::*; use kernel::sizes::*; -use kernel::types::ARef; +use kernel::sync::aref::ARef; use kernel::{dev_warn, device}; use crate::dma::DmaObject; diff --git a/drivers/gpu/nova-core/firmware.rs b/drivers/gpu/nova-core/firmware.rs index 2931912ddba0..4179a74a2342 100644 --- a/drivers/gpu/nova-core/firmware.rs +++ b/drivers/gpu/nova-core/firmware.rs @@ -4,48 +4,36 @@ //! to be loaded into a given execution unit. use core::marker::PhantomData; +use core::mem::size_of; use kernel::device; use kernel::firmware; use kernel::prelude::*; use kernel::str::CString; +use kernel::transmute::FromBytes; use crate::dma::DmaObject; use crate::falcon::FalconFirmware; use crate::gpu; -use crate::gpu::Chipset; +pub(crate) mod booter; pub(crate) mod fwsec; - -pub(crate) const FIRMWARE_VERSION: &str = "535.113.01"; - -/// Structure encapsulating the firmware blobs required for the GPU to operate. -#[expect(dead_code)] -pub(crate) struct Firmware { - booter_load: firmware::Firmware, - booter_unload: firmware::Firmware, - bootloader: firmware::Firmware, - gsp: firmware::Firmware, -} - -impl Firmware { - pub(crate) fn new(dev: &device::Device, chipset: Chipset, ver: &str) -> Result<Firmware> { - let mut chip_name = CString::try_from_fmt(fmt!("{chipset}"))?; - chip_name.make_ascii_lowercase(); - let chip_name = &*chip_name; - - let request = |name_| { - CString::try_from_fmt(fmt!("nvidia/{chip_name}/gsp/{name_}-{ver}.bin")) - .and_then(|path| firmware::Firmware::request(&path, dev)) - }; - - Ok(Firmware { - booter_load: request("booter_load")?, - booter_unload: request("booter_unload")?, - bootloader: request("bootloader")?, - gsp: request("gsp")?, - }) - } +pub(crate) mod gsp; +pub(crate) mod riscv; + +pub(crate) const FIRMWARE_VERSION: &str = "570.144"; + +/// Requests the GPU firmware `name` suitable for `chipset`, with version `ver`. +fn request_firmware( + dev: &device::Device, + chipset: gpu::Chipset, + name: &str, + ver: &str, +) -> Result<firmware::Firmware> { + let chip_name = chipset.name(); + + CString::try_from_fmt(fmt!("nvidia/{chip_name}/gsp/{name}-{ver}.bin")) + .and_then(|path| firmware::Firmware::request(&path, dev)) } /// Structure used to describe some firmwares, notably FWSEC-FRTS. @@ -150,6 +138,65 @@ impl<F: FalconFirmware> FirmwareDmaObject<F, Unsigned> { } } +/// Header common to most firmware files. +#[repr(C)] +#[derive(Debug, Clone)] +struct BinHdr { + /// Magic number, must be `0x10de`. + bin_magic: u32, + /// Version of the header. + bin_ver: u32, + /// Size in bytes of the binary (to be ignored). + bin_size: u32, + /// Offset of the start of the application-specific header. + header_offset: u32, + /// Offset of the start of the data payload. + data_offset: u32, + /// Size in bytes of the data payload. + data_size: u32, +} + +// SAFETY: all bit patterns are valid for this type, and it doesn't use interior mutability. +unsafe impl FromBytes for BinHdr {} + +// A firmware blob starting with a `BinHdr`. +struct BinFirmware<'a> { + hdr: BinHdr, + fw: &'a [u8], +} + +impl<'a> BinFirmware<'a> { + /// Interpret `fw` as a firmware image starting with a [`BinHdr`], and returns the + /// corresponding [`BinFirmware`] that can be used to extract its payload. + fn new(fw: &'a firmware::Firmware) -> Result<Self> { + const BIN_MAGIC: u32 = 0x10de; + let fw = fw.data(); + + fw.get(0..size_of::<BinHdr>()) + // Extract header. + .and_then(BinHdr::from_bytes_copy) + // Validate header. + .and_then(|hdr| { + if hdr.bin_magic == BIN_MAGIC { + Some(hdr) + } else { + None + } + }) + .map(|hdr| Self { hdr, fw }) + .ok_or(EINVAL) + } + + /// Returns the data payload of the firmware, or `None` if the data range is out of bounds of + /// the firmware image. + fn data(&self) -> Option<&[u8]> { + let fw_start = self.hdr.data_offset as usize; + let fw_size = self.hdr.data_size as usize; + + self.fw.get(fw_start..fw_start + fw_size) + } +} + pub(crate) struct ModInfoBuilder<const N: usize>(firmware::ModInfoBuilder<N>); impl<const N: usize> ModInfoBuilder<N> { @@ -180,8 +227,8 @@ impl<const N: usize> ModInfoBuilder<N> { let mut this = Self(firmware::ModInfoBuilder::new(module_name)); let mut i = 0; - while i < gpu::Chipset::NAMES.len() { - this = this.make_entry_chipset(gpu::Chipset::NAMES[i]); + while i < gpu::Chipset::ALL.len() { + this = this.make_entry_chipset(gpu::Chipset::ALL[i].name()); i += 1; } diff --git a/drivers/gpu/nova-core/firmware/booter.rs b/drivers/gpu/nova-core/firmware/booter.rs new file mode 100644 index 000000000000..b4ff1b17e4a0 --- /dev/null +++ b/drivers/gpu/nova-core/firmware/booter.rs @@ -0,0 +1,375 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Support for loading and patching the `Booter` firmware. `Booter` is a Heavy Secured firmware +//! running on [`Sec2`], that is used on Turing/Ampere to load the GSP firmware into the GSP falcon +//! (and optionally unload it through a separate firmware image). + +use core::marker::PhantomData; +use core::mem::size_of; +use core::ops::Deref; + +use kernel::device; +use kernel::prelude::*; +use kernel::transmute::FromBytes; + +use crate::dma::DmaObject; +use crate::driver::Bar0; +use crate::falcon::sec2::Sec2; +use crate::falcon::{Falcon, FalconBromParams, FalconFirmware, FalconLoadParams, FalconLoadTarget}; +use crate::firmware::{BinFirmware, FirmwareDmaObject, FirmwareSignature, Signed, Unsigned}; +use crate::gpu::Chipset; + +/// Local convenience function to return a copy of `S` by reinterpreting the bytes starting at +/// `offset` in `slice`. +fn frombytes_at<S: FromBytes + Sized>(slice: &[u8], offset: usize) -> Result<S> { + slice + .get(offset..offset + size_of::<S>()) + .and_then(S::from_bytes_copy) + .ok_or(EINVAL) +} + +/// Heavy-Secured firmware header. +/// +/// Such firmwares have an application-specific payload that needs to be patched with a given +/// signature. +#[repr(C)] +#[derive(Debug, Clone)] +struct HsHeaderV2 { + /// Offset to the start of the signatures. + sig_prod_offset: u32, + /// Size in bytes of the signatures. + sig_prod_size: u32, + /// Offset to a `u32` containing the location at which to patch the signature in the microcode + /// image. + patch_loc_offset: u32, + /// Offset to a `u32` containing the index of the signature to patch. + patch_sig_offset: u32, + /// Start offset to the signature metadata. + meta_data_offset: u32, + /// Size in bytes of the signature metadata. + meta_data_size: u32, + /// Offset to a `u32` containing the number of signatures in the signatures section. + num_sig_offset: u32, + /// Offset of the application-specific header. + header_offset: u32, + /// Size in bytes of the application-specific header. + header_size: u32, +} + +// SAFETY: all bit patterns are valid for this type, and it doesn't use interior mutability. +unsafe impl FromBytes for HsHeaderV2 {} + +/// Heavy-Secured Firmware image container. +/// +/// This provides convenient access to the fields of [`HsHeaderV2`] that are actually indices to +/// read from in the firmware data. +struct HsFirmwareV2<'a> { + hdr: HsHeaderV2, + fw: &'a [u8], +} + +impl<'a> HsFirmwareV2<'a> { + /// Interprets the header of `bin_fw` as a [`HsHeaderV2`] and returns an instance of + /// `HsFirmwareV2` for further parsing. + /// + /// Fails if the header pointed at by `bin_fw` is not within the bounds of the firmware image. + fn new(bin_fw: &BinFirmware<'a>) -> Result<Self> { + frombytes_at::<HsHeaderV2>(bin_fw.fw, bin_fw.hdr.header_offset as usize) + .map(|hdr| Self { hdr, fw: bin_fw.fw }) + } + + /// Returns the location at which the signatures should be patched in the microcode image. + /// + /// Fails if the offset of the patch location is outside the bounds of the firmware + /// image. + fn patch_location(&self) -> Result<u32> { + frombytes_at::<u32>(self.fw, self.hdr.patch_loc_offset as usize) + } + + /// Returns an iterator to the signatures of the firmware. The iterator can be empty if the + /// firmware is unsigned. + /// + /// Fails if the pointed signatures are outside the bounds of the firmware image. + fn signatures_iter(&'a self) -> Result<impl Iterator<Item = BooterSignature<'a>>> { + let num_sig = frombytes_at::<u32>(self.fw, self.hdr.num_sig_offset as usize)?; + let iter = match self.hdr.sig_prod_size.checked_div(num_sig) { + // If there are no signatures, return an iterator that will yield zero elements. + None => (&[] as &[u8]).chunks_exact(1), + Some(sig_size) => { + let patch_sig = frombytes_at::<u32>(self.fw, self.hdr.patch_sig_offset as usize)?; + let signatures_start = (self.hdr.sig_prod_offset + patch_sig) as usize; + + self.fw + // Get signatures range. + .get(signatures_start..signatures_start + self.hdr.sig_prod_size as usize) + .ok_or(EINVAL)? + .chunks_exact(sig_size as usize) + } + }; + + // Map the byte slices into signatures. + Ok(iter.map(BooterSignature)) + } +} + +/// Signature parameters, as defined in the firmware. +#[repr(C)] +struct HsSignatureParams { + /// Fuse version to use. + fuse_ver: u32, + /// Mask of engine IDs this firmware applies to. + engine_id_mask: u32, + /// ID of the microcode. + ucode_id: u32, +} + +// SAFETY: all bit patterns are valid for this type, and it doesn't use interior mutability. +unsafe impl FromBytes for HsSignatureParams {} + +impl HsSignatureParams { + /// Returns the signature parameters contained in `hs_fw`. + /// + /// Fails if the meta data parameter of `hs_fw` is outside the bounds of the firmware image, or + /// if its size doesn't match that of [`HsSignatureParams`]. + fn new(hs_fw: &HsFirmwareV2<'_>) -> Result<Self> { + let start = hs_fw.hdr.meta_data_offset as usize; + let end = start + .checked_add(hs_fw.hdr.meta_data_size as usize) + .ok_or(EINVAL)?; + + hs_fw + .fw + .get(start..end) + .and_then(Self::from_bytes_copy) + .ok_or(EINVAL) + } +} + +/// Header for code and data load offsets. +#[repr(C)] +#[derive(Debug, Clone)] +struct HsLoadHeaderV2 { + // Offset at which the code starts. + os_code_offset: u32, + // Total size of the code, for all apps. + os_code_size: u32, + // Offset at which the data starts. + os_data_offset: u32, + // Size of the data. + os_data_size: u32, + // Number of apps following this header. Each app is described by a [`HsLoadHeaderV2App`]. + num_apps: u32, +} + +// SAFETY: all bit patterns are valid for this type, and it doesn't use interior mutability. +unsafe impl FromBytes for HsLoadHeaderV2 {} + +impl HsLoadHeaderV2 { + /// Returns the load header contained in `hs_fw`. + /// + /// Fails if the header pointed at by `hs_fw` is not within the bounds of the firmware image. + fn new(hs_fw: &HsFirmwareV2<'_>) -> Result<Self> { + frombytes_at::<Self>(hs_fw.fw, hs_fw.hdr.header_offset as usize) + } +} + +/// Header for app code loader. +#[repr(C)] +#[derive(Debug, Clone)] +struct HsLoadHeaderV2App { + /// Offset at which to load the app code. + offset: u32, + /// Length in bytes of the app code. + len: u32, +} + +// SAFETY: all bit patterns are valid for this type, and it doesn't use interior mutability. +unsafe impl FromBytes for HsLoadHeaderV2App {} + +impl HsLoadHeaderV2App { + /// Returns the [`HsLoadHeaderV2App`] for app `idx` of `hs_fw`. + /// + /// Fails if `idx` is larger than the number of apps declared in `hs_fw`, or if the header is + /// not within the bounds of the firmware image. + fn new(hs_fw: &HsFirmwareV2<'_>, idx: u32) -> Result<Self> { + let load_hdr = HsLoadHeaderV2::new(hs_fw)?; + if idx >= load_hdr.num_apps { + Err(EINVAL) + } else { + frombytes_at::<Self>( + hs_fw.fw, + (hs_fw.hdr.header_offset as usize) + // Skip the load header... + .checked_add(size_of::<HsLoadHeaderV2>()) + // ... and jump to app header `idx`. + .and_then(|offset| { + offset.checked_add((idx as usize).checked_mul(size_of::<Self>())?) + }) + .ok_or(EINVAL)?, + ) + } + } +} + +/// Signature for Booter firmware. Their size is encoded into the header and not known a compile +/// time, so we just wrap a byte slices on which we can implement [`FirmwareSignature`]. +struct BooterSignature<'a>(&'a [u8]); + +impl<'a> AsRef<[u8]> for BooterSignature<'a> { + fn as_ref(&self) -> &[u8] { + self.0 + } +} + +impl<'a> FirmwareSignature<BooterFirmware> for BooterSignature<'a> {} + +/// The `Booter` loader firmware, responsible for loading the GSP. +pub(crate) struct BooterFirmware { + // Load parameters for `IMEM` falcon memory. + imem_load_target: FalconLoadTarget, + // Load parameters for `DMEM` falcon memory. + dmem_load_target: FalconLoadTarget, + // BROM falcon parameters. + brom_params: FalconBromParams, + // Device-mapped firmware image. + ucode: FirmwareDmaObject<Self, Signed>, +} + +impl FirmwareDmaObject<BooterFirmware, Unsigned> { + fn new_booter(dev: &device::Device<device::Bound>, data: &[u8]) -> Result<Self> { + DmaObject::from_data(dev, data).map(|ucode| Self(ucode, PhantomData)) + } +} + +#[derive(Copy, Clone, Debug, PartialEq)] +pub(crate) enum BooterKind { + Loader, + #[expect(unused)] + Unloader, +} + +impl BooterFirmware { + /// Parses the Booter firmware contained in `fw`, and patches the correct signature so it is + /// ready to be loaded and run on `falcon`. + pub(crate) fn new( + dev: &device::Device<device::Bound>, + kind: BooterKind, + chipset: Chipset, + ver: &str, + falcon: &Falcon<<Self as FalconFirmware>::Target>, + bar: &Bar0, + ) -> Result<Self> { + let fw_name = match kind { + BooterKind::Loader => "booter_load", + BooterKind::Unloader => "booter_unload", + }; + let fw = super::request_firmware(dev, chipset, fw_name, ver)?; + let bin_fw = BinFirmware::new(&fw)?; + + // The binary firmware embeds a Heavy-Secured firmware. + let hs_fw = HsFirmwareV2::new(&bin_fw)?; + + // The Heavy-Secured firmware embeds a firmware load descriptor. + let load_hdr = HsLoadHeaderV2::new(&hs_fw)?; + + // Offset in `ucode` where to patch the signature. + let patch_loc = hs_fw.patch_location()?; + + let sig_params = HsSignatureParams::new(&hs_fw)?; + let brom_params = FalconBromParams { + // `load_hdr.os_data_offset` is an absolute index, but `pkc_data_offset` is from the + // signature patch location. + pkc_data_offset: patch_loc + .checked_sub(load_hdr.os_data_offset) + .ok_or(EINVAL)?, + engine_id_mask: u16::try_from(sig_params.engine_id_mask).map_err(|_| EINVAL)?, + ucode_id: u8::try_from(sig_params.ucode_id).map_err(|_| EINVAL)?, + }; + let app0 = HsLoadHeaderV2App::new(&hs_fw, 0)?; + + // Object containing the firmware microcode to be signature-patched. + let ucode = bin_fw + .data() + .ok_or(EINVAL) + .and_then(|data| FirmwareDmaObject::<Self, _>::new_booter(dev, data))?; + + let ucode_signed = { + let mut signatures = hs_fw.signatures_iter()?.peekable(); + + if signatures.peek().is_none() { + // If there are no signatures, then the firmware is unsigned. + ucode.no_patch_signature() + } else { + // Obtain the version from the fuse register, and extract the corresponding + // signature. + let reg_fuse_version = falcon.signature_reg_fuse_version( + bar, + brom_params.engine_id_mask, + brom_params.ucode_id, + )?; + + // `0` means the last signature should be used. + const FUSE_VERSION_USE_LAST_SIG: u32 = 0; + let signature = match reg_fuse_version { + FUSE_VERSION_USE_LAST_SIG => signatures.last(), + // Otherwise hardware fuse version needs to be subtracted to obtain the index. + reg_fuse_version => { + let Some(idx) = sig_params.fuse_ver.checked_sub(reg_fuse_version) else { + dev_err!(dev, "invalid fuse version for Booter firmware\n"); + return Err(EINVAL); + }; + signatures.nth(idx as usize) + } + } + .ok_or(EINVAL)?; + + ucode.patch_signature(&signature, patch_loc as usize)? + } + }; + + Ok(Self { + imem_load_target: FalconLoadTarget { + src_start: app0.offset, + dst_start: 0, + len: app0.len, + }, + dmem_load_target: FalconLoadTarget { + src_start: load_hdr.os_data_offset, + dst_start: 0, + len: load_hdr.os_data_size, + }, + brom_params, + ucode: ucode_signed, + }) + } +} + +impl FalconLoadParams for BooterFirmware { + fn imem_load_params(&self) -> FalconLoadTarget { + self.imem_load_target.clone() + } + + fn dmem_load_params(&self) -> FalconLoadTarget { + self.dmem_load_target.clone() + } + + fn brom_params(&self) -> FalconBromParams { + self.brom_params.clone() + } + + fn boot_addr(&self) -> u32 { + self.imem_load_target.src_start + } +} + +impl Deref for BooterFirmware { + type Target = DmaObject; + + fn deref(&self) -> &Self::Target { + &self.ucode.0 + } +} + +impl FalconFirmware for BooterFirmware { + type Target = Sec2; +} diff --git a/drivers/gpu/nova-core/firmware/fwsec.rs b/drivers/gpu/nova-core/firmware/fwsec.rs index 0dff3cfa90af..8edbb5c0572c 100644 --- a/drivers/gpu/nova-core/firmware/fwsec.rs +++ b/drivers/gpu/nova-core/firmware/fwsec.rs @@ -202,9 +202,6 @@ pub(crate) struct FwsecFirmware { ucode: FirmwareDmaObject<Self, Signed>, } -// We need to load full DMEM pages. -const DMEM_LOAD_SIZE_ALIGN: u32 = 256; - impl FalconLoadParams for FwsecFirmware { fn imem_load_params(&self) -> FalconLoadTarget { FalconLoadTarget { @@ -218,11 +215,7 @@ impl FalconLoadParams for FwsecFirmware { FalconLoadTarget { src_start: self.desc.imem_load_size, dst_start: self.desc.dmem_phys_base, - // TODO[NUMM]: replace with `align_up` once it lands. - len: self - .desc - .dmem_load_size - .next_multiple_of(DMEM_LOAD_SIZE_ALIGN), + len: self.desc.dmem_load_size, } } @@ -253,8 +246,8 @@ impl FalconFirmware for FwsecFirmware { impl FirmwareDmaObject<FwsecFirmware, Unsigned> { fn new_fwsec(dev: &Device<device::Bound>, bios: &Vbios, cmd: FwsecCommand) -> Result<Self> { - let desc = bios.fwsec_image().header(dev)?; - let ucode = bios.fwsec_image().ucode(dev, desc)?; + let desc = bios.fwsec_image().header()?; + let ucode = bios.fwsec_image().ucode(desc)?; let mut dma_object = DmaObject::from_data(dev, ucode)?; let hdr_offset = (desc.imem_load_size + desc.interface_offset) as usize; @@ -343,7 +336,7 @@ impl FwsecFirmware { let ucode_dma = FirmwareDmaObject::<Self, _>::new_fwsec(dev, bios, cmd)?; // Patch signature if needed. - let desc = bios.fwsec_image().header(dev)?; + let desc = bios.fwsec_image().header()?; let ucode_signed = if desc.signature_count != 0 { let sig_base_img = (desc.imem_load_size + desc.pkc_data_offset) as usize; let desc_sig_versions = u32::from(desc.signature_versions); @@ -382,7 +375,7 @@ impl FwsecFirmware { dev_dbg!(dev, "patching signature with index {}\n", signature_idx); let signature = bios .fwsec_image() - .sigs(dev, desc) + .sigs(desc) .and_then(|sigs| sigs.get(signature_idx).ok_or(EINVAL))?; ucode_dma.patch_signature(signature, sig_base_img)? diff --git a/drivers/gpu/nova-core/firmware/gsp.rs b/drivers/gpu/nova-core/firmware/gsp.rs new file mode 100644 index 000000000000..9b70095434c6 --- /dev/null +++ b/drivers/gpu/nova-core/firmware/gsp.rs @@ -0,0 +1,243 @@ +// SPDX-License-Identifier: GPL-2.0 + +use core::mem::size_of_val; + +use kernel::device; +use kernel::dma::{DataDirection, DmaAddress}; +use kernel::kvec; +use kernel::prelude::*; +use kernel::scatterlist::{Owned, SGTable}; + +use crate::dma::DmaObject; +use crate::firmware::riscv::RiscvFirmware; +use crate::gpu::{Architecture, Chipset}; +use crate::gsp::GSP_PAGE_SIZE; + +/// Ad-hoc and temporary module to extract sections from ELF images. +/// +/// Some firmware images are currently packaged as ELF files, where sections names are used as keys +/// to specific and related bits of data. Future firmware versions are scheduled to move away from +/// that scheme before nova-core becomes stable, which means this module will eventually be +/// removed. +mod elf { + use core::mem::size_of; + + use kernel::bindings; + use kernel::str::CStr; + use kernel::transmute::FromBytes; + + /// Newtype to provide a [`FromBytes`] implementation. + #[repr(transparent)] + struct Elf64Hdr(bindings::elf64_hdr); + // SAFETY: all bit patterns are valid for this type, and it doesn't use interior mutability. + unsafe impl FromBytes for Elf64Hdr {} + + #[repr(transparent)] + struct Elf64SHdr(bindings::elf64_shdr); + // SAFETY: all bit patterns are valid for this type, and it doesn't use interior mutability. + unsafe impl FromBytes for Elf64SHdr {} + + /// Tries to extract section with name `name` from the ELF64 image `elf`, and returns it. + pub(super) fn elf64_section<'a, 'b>(elf: &'a [u8], name: &'b str) -> Option<&'a [u8]> { + let hdr = &elf + .get(0..size_of::<bindings::elf64_hdr>()) + .and_then(Elf64Hdr::from_bytes)? + .0; + + // Get all the section headers. + let mut shdr = { + let shdr_num = usize::from(hdr.e_shnum); + let shdr_start = usize::try_from(hdr.e_shoff).ok()?; + let shdr_end = shdr_num + .checked_mul(size_of::<Elf64SHdr>()) + .and_then(|v| v.checked_add(shdr_start))?; + + elf.get(shdr_start..shdr_end) + .map(|slice| slice.chunks_exact(size_of::<Elf64SHdr>()))? + }; + + // Get the strings table. + let strhdr = shdr + .clone() + .nth(usize::from(hdr.e_shstrndx)) + .and_then(Elf64SHdr::from_bytes)?; + + // Find the section which name matches `name` and return it. + shdr.find(|&sh| { + let Some(hdr) = Elf64SHdr::from_bytes(sh) else { + return false; + }; + + let Some(name_idx) = strhdr + .0 + .sh_offset + .checked_add(u64::from(hdr.0.sh_name)) + .and_then(|idx| usize::try_from(idx).ok()) + else { + return false; + }; + + // Get the start of the name. + elf.get(name_idx..) + // Stop at the first `0`. + .and_then(|nstr| nstr.get(0..=nstr.iter().position(|b| *b == 0)?)) + // Convert into CStr. This should never fail because of the line above. + .and_then(|nstr| CStr::from_bytes_with_nul(nstr).ok()) + // Convert into str. + .and_then(|c_str| c_str.to_str().ok()) + // Check that the name matches. + .map(|str| str == name) + .unwrap_or(false) + }) + // Return the slice containing the section. + .and_then(|sh| { + let hdr = Elf64SHdr::from_bytes(sh)?; + let start = usize::try_from(hdr.0.sh_offset).ok()?; + let end = usize::try_from(hdr.0.sh_size) + .ok() + .and_then(|sh_size| start.checked_add(sh_size))?; + + elf.get(start..end) + }) + } +} + +/// GSP firmware with 3-level radix page tables for the GSP bootloader. +/// +/// The bootloader expects firmware to be mapped starting at address 0 in GSP's virtual address +/// space: +/// +/// ```text +/// Level 0: 1 page, 1 entry -> points to first level 1 page +/// Level 1: Multiple pages/entries -> each entry points to a level 2 page +/// Level 2: Multiple pages/entries -> each entry points to a firmware page +/// ``` +/// +/// Each page is 4KB, each entry is 8 bytes (64-bit DMA address). +/// Also known as "Radix3" firmware. +#[pin_data] +pub(crate) struct GspFirmware { + /// The GSP firmware inside a [`VVec`], device-mapped via a SG table. + #[pin] + fw: SGTable<Owned<VVec<u8>>>, + /// Level 2 page table whose entries contain DMA addresses of firmware pages. + #[pin] + level2: SGTable<Owned<VVec<u8>>>, + /// Level 1 page table whose entries contain DMA addresses of level 2 pages. + #[pin] + level1: SGTable<Owned<VVec<u8>>>, + /// Level 0 page table (single 4KB page) with one entry: DMA address of first level 1 page. + level0: DmaObject, + /// Size in bytes of the firmware contained in [`Self::fw`]. + size: usize, + /// Device-mapped GSP signatures matching the GPU's [`Chipset`]. + signatures: DmaObject, + /// GSP bootloader, verifies the GSP firmware before loading and running it. + bootloader: RiscvFirmware, +} + +impl GspFirmware { + /// Loads the GSP firmware binaries, map them into `dev`'s address-space, and creates the page + /// tables expected by the GSP bootloader to load it. + pub(crate) fn new<'a, 'b>( + dev: &'a device::Device<device::Bound>, + chipset: Chipset, + ver: &'b str, + ) -> Result<impl PinInit<Self, Error> + 'a> { + let fw = super::request_firmware(dev, chipset, "gsp", ver)?; + + let fw_section = elf::elf64_section(fw.data(), ".fwimage").ok_or(EINVAL)?; + + let sigs_section = match chipset.arch() { + Architecture::Ampere => ".fwsignature_ga10x", + _ => return Err(ENOTSUPP), + }; + let signatures = elf::elf64_section(fw.data(), sigs_section) + .ok_or(EINVAL) + .and_then(|data| DmaObject::from_data(dev, data))?; + + let size = fw_section.len(); + + // Move the firmware into a vmalloc'd vector and map it into the device address + // space. + let fw_vvec = VVec::with_capacity(fw_section.len(), GFP_KERNEL) + .and_then(|mut v| { + v.extend_from_slice(fw_section, GFP_KERNEL)?; + Ok(v) + }) + .map_err(|_| ENOMEM)?; + + let bl = super::request_firmware(dev, chipset, "bootloader", ver)?; + let bootloader = RiscvFirmware::new(dev, &bl)?; + + Ok(try_pin_init!(Self { + fw <- SGTable::new(dev, fw_vvec, DataDirection::ToDevice, GFP_KERNEL), + level2 <- { + // Allocate the level 2 page table, map the firmware onto it, and map it into the + // device address space. + VVec::<u8>::with_capacity( + fw.iter().count() * core::mem::size_of::<u64>(), + GFP_KERNEL, + ) + .map_err(|_| ENOMEM) + .and_then(|level2| map_into_lvl(&fw, level2)) + .map(|level2| SGTable::new(dev, level2, DataDirection::ToDevice, GFP_KERNEL))? + }, + level1 <- { + // Allocate the level 1 page table, map the level 2 page table onto it, and map it + // into the device address space. + VVec::<u8>::with_capacity( + level2.iter().count() * core::mem::size_of::<u64>(), + GFP_KERNEL, + ) + .map_err(|_| ENOMEM) + .and_then(|level1| map_into_lvl(&level2, level1)) + .map(|level1| SGTable::new(dev, level1, DataDirection::ToDevice, GFP_KERNEL))? + }, + level0: { + // Allocate the level 0 page table as a device-visible DMA object, and map the + // level 1 page table onto it. + + // Level 0 page table data. + let mut level0_data = kvec![0u8; GSP_PAGE_SIZE]?; + + // Fill level 1 page entry. + #[allow(clippy::useless_conversion)] + let level1_entry = u64::from(level1.iter().next().unwrap().dma_address()); + let dst = &mut level0_data[..size_of_val(&level1_entry)]; + dst.copy_from_slice(&level1_entry.to_le_bytes()); + + // Turn the level0 page table into a [`DmaObject`]. + DmaObject::from_data(dev, &level0_data)? + }, + size, + signatures, + bootloader, + })) + } + + #[expect(unused)] + /// Returns the DMA handle of the radix3 level 0 page table. + pub(crate) fn radix3_dma_handle(&self) -> DmaAddress { + self.level0.dma_handle() + } +} + +/// Build a page table from a scatter-gather list. +/// +/// Takes each DMA-mapped region from `sg_table` and writes page table entries +/// for all 4KB pages within that region. For example, a 16KB SG entry becomes +/// 4 consecutive page table entries. +fn map_into_lvl(sg_table: &SGTable<Owned<VVec<u8>>>, mut dst: VVec<u8>) -> Result<VVec<u8>> { + for sg_entry in sg_table.iter() { + // Number of pages we need to map. + let num_pages = (sg_entry.dma_len() as usize).div_ceil(GSP_PAGE_SIZE); + + for i in 0..num_pages { + let entry = sg_entry.dma_address() + (i as u64 * GSP_PAGE_SIZE as u64); + dst.extend_from_slice(&entry.to_le_bytes(), GFP_KERNEL)?; + } + } + + Ok(dst) +} diff --git a/drivers/gpu/nova-core/firmware/riscv.rs b/drivers/gpu/nova-core/firmware/riscv.rs new file mode 100644 index 000000000000..afb08f5bc4ba --- /dev/null +++ b/drivers/gpu/nova-core/firmware/riscv.rs @@ -0,0 +1,91 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Support for firmware binaries designed to run on a RISC-V core. Such firmwares files have a +//! dedicated header. + +use core::mem::size_of; + +use kernel::device; +use kernel::firmware::Firmware; +use kernel::prelude::*; +use kernel::transmute::FromBytes; + +use crate::dma::DmaObject; +use crate::firmware::BinFirmware; + +/// Descriptor for microcode running on a RISC-V core. +#[repr(C)] +#[derive(Debug)] +struct RmRiscvUCodeDesc { + version: u32, + bootloader_offset: u32, + bootloader_size: u32, + bootloader_param_offset: u32, + bootloader_param_size: u32, + riscv_elf_offset: u32, + riscv_elf_size: u32, + app_version: u32, + manifest_offset: u32, + manifest_size: u32, + monitor_data_offset: u32, + monitor_data_size: u32, + monitor_code_offset: u32, + monitor_code_size: u32, +} + +// SAFETY: all bit patterns are valid for this type, and it doesn't use interior mutability. +unsafe impl FromBytes for RmRiscvUCodeDesc {} + +impl RmRiscvUCodeDesc { + /// Interprets the header of `bin_fw` as a [`RmRiscvUCodeDesc`] and returns it. + /// + /// Fails if the header pointed at by `bin_fw` is not within the bounds of the firmware image. + fn new(bin_fw: &BinFirmware<'_>) -> Result<Self> { + let offset = bin_fw.hdr.header_offset as usize; + + bin_fw + .fw + .get(offset..offset + size_of::<Self>()) + .and_then(Self::from_bytes_copy) + .ok_or(EINVAL) + } +} + +/// A parsed firmware for a RISC-V core, ready to be loaded and run. +#[expect(unused)] +pub(crate) struct RiscvFirmware { + /// Offset at which the code starts in the firmware image. + code_offset: u32, + /// Offset at which the data starts in the firmware image. + data_offset: u32, + /// Offset at which the manifest starts in the firmware image. + manifest_offset: u32, + /// Application version. + app_version: u32, + /// Device-mapped firmware image. + ucode: DmaObject, +} + +impl RiscvFirmware { + /// Parses the RISC-V firmware image contained in `fw`. + pub(crate) fn new(dev: &device::Device<device::Bound>, fw: &Firmware) -> Result<Self> { + let bin_fw = BinFirmware::new(fw)?; + + let riscv_desc = RmRiscvUCodeDesc::new(&bin_fw)?; + + let ucode = { + let start = bin_fw.hdr.data_offset as usize; + let len = bin_fw.hdr.data_size as usize; + + DmaObject::from_data(dev, fw.data().get(start..start + len).ok_or(EINVAL)?)? + }; + + Ok(Self { + ucode, + code_offset: riscv_desc.monitor_code_offset, + data_offset: riscv_desc.monitor_data_offset, + manifest_offset: riscv_desc.manifest_offset, + app_version: riscv_desc.app_version, + }) + } +} diff --git a/drivers/gpu/nova-core/gpu.rs b/drivers/gpu/nova-core/gpu.rs index b5c9786619a9..5da9ad726483 100644 --- a/drivers/gpu/nova-core/gpu.rs +++ b/drivers/gpu/nova-core/gpu.rs @@ -3,15 +3,11 @@ use kernel::{device, devres::Devres, error::code::*, pci, prelude::*, sync::Arc}; use crate::driver::Bar0; -use crate::falcon::{gsp::Gsp, sec2::Sec2, Falcon}; -use crate::fb::FbLayout; +use crate::falcon::{gsp::Gsp as GspFalcon, sec2::Sec2 as Sec2Falcon, Falcon}; use crate::fb::SysmemFlush; -use crate::firmware::fwsec::{FwsecCommand, FwsecFirmware}; -use crate::firmware::{Firmware, FIRMWARE_VERSION}; use crate::gfw; +use crate::gsp::Gsp; use crate::regs; -use crate::util; -use crate::vbios::Vbios; use core::fmt; macro_rules! define_chipset { @@ -28,13 +24,23 @@ macro_rules! define_chipset { $( Chipset::$variant, )* ]; - pub(crate) const NAMES: [&'static str; Self::ALL.len()] = [ - $( util::const_bytes_to_str( - util::to_lowercase_bytes::<{ stringify!($variant).len() }>( - stringify!($variant) - ).as_slice() - ), )* - ]; + ::kernel::macros::paste!( + /// Returns the name of this chipset, in lowercase. + /// + /// # Examples + /// + /// ``` + /// let chipset = Chipset::GA102; + /// assert_eq!(chipset.name(), "ga102"); + /// ``` + pub(crate) const fn name(&self) -> &'static str { + match *self { + $( + Chipset::$variant => stringify!([<$variant:lower>]), + )* + } + } + ); } // TODO[FPRI]: replace with something like derive(FromPrimitive) @@ -163,150 +169,74 @@ impl Spec { } /// Structure holding the resources required to operate the GPU. -#[pin_data(PinnedDrop)] +#[pin_data] pub(crate) struct Gpu { spec: Spec, /// MMIO mapping of PCI BAR 0 bar: Arc<Devres<Bar0>>, - fw: Firmware, /// System memory page required for flushing all pending GPU-side memory writes done through /// PCIE into system memory, via sysmembar (A GPU-initiated HW memory-barrier operation). sysmem_flush: SysmemFlush, -} - -#[pinned_drop] -impl PinnedDrop for Gpu { - fn drop(self: Pin<&mut Self>) { - // Unregister the sysmem flush page before we release it. - self.bar - .try_access_with(|b| self.sysmem_flush.unregister(b)); - } + /// GSP falcon instance, used for GSP boot up and cleanup. + gsp_falcon: Falcon<GspFalcon>, + /// SEC2 falcon instance, used for GSP boot up and cleanup. + sec2_falcon: Falcon<Sec2Falcon>, + /// GSP runtime data. Temporarily an empty placeholder. + #[pin] + gsp: Gsp, } impl Gpu { - /// Helper function to load and run the FWSEC-FRTS firmware and confirm that it has properly - /// created the WPR2 region. - /// - /// TODO: this needs to be moved into a larger type responsible for booting the whole GSP - /// (`GspBooter`?). - fn run_fwsec_frts( - dev: &device::Device<device::Bound>, - falcon: &Falcon<Gsp>, - bar: &Bar0, - bios: &Vbios, - fb_layout: &FbLayout, - ) -> Result<()> { - // Check that the WPR2 region does not already exists - if it does, we cannot run - // FWSEC-FRTS until the GPU is reset. - if regs::NV_PFB_PRI_MMU_WPR2_ADDR_HI::read(bar).higher_bound() != 0 { - dev_err!( - dev, - "WPR2 region already exists - GPU needs to be reset to proceed\n" - ); - return Err(EBUSY); - } + pub(crate) fn new<'a>( + pdev: &'a pci::Device<device::Bound>, + devres_bar: Arc<Devres<Bar0>>, + bar: &'a Bar0, + ) -> impl PinInit<Self, Error> + 'a { + try_pin_init!(Self { + spec: Spec::new(bar).inspect(|spec| { + dev_info!( + pdev.as_ref(), + "NVIDIA (Chipset: {}, Architecture: {:?}, Revision: {})\n", + spec.chipset, + spec.chipset.arch(), + spec.revision + ); + })?, - let fwsec_frts = FwsecFirmware::new( - dev, - falcon, - bar, - bios, - FwsecCommand::Frts { - frts_addr: fb_layout.frts.start, - frts_size: fb_layout.frts.end - fb_layout.frts.start, + // We must wait for GFW_BOOT completion before doing any significant setup on the GPU. + _: { + gfw::wait_gfw_boot_completion(bar) + .inspect_err(|_| dev_err!(pdev.as_ref(), "GFW boot did not complete"))?; }, - )?; - // Run FWSEC-FRTS to create the WPR2 region. - fwsec_frts.run(dev, falcon, bar)?; + sysmem_flush: SysmemFlush::register(pdev.as_ref(), bar, spec.chipset)?, - // SCRATCH_E contains the error code for FWSEC-FRTS. - let frts_status = regs::NV_PBUS_SW_SCRATCH_0E::read(bar).frts_err_code(); - if frts_status != 0 { - dev_err!( - dev, - "FWSEC-FRTS returned with error code {:#x}", - frts_status - ); + gsp_falcon: Falcon::new( + pdev.as_ref(), + spec.chipset, + bar, + spec.chipset > Chipset::GA100, + ) + .inspect(|falcon| falcon.clear_swgen0_intr(bar))?, - return Err(EIO); - } + sec2_falcon: Falcon::new(pdev.as_ref(), spec.chipset, bar, true)?, - // Check that the WPR2 region has been created as we requested. - let (wpr2_lo, wpr2_hi) = ( - regs::NV_PFB_PRI_MMU_WPR2_ADDR_LO::read(bar).lower_bound(), - regs::NV_PFB_PRI_MMU_WPR2_ADDR_HI::read(bar).higher_bound(), - ); + gsp <- Gsp::new(), - match (wpr2_lo, wpr2_hi) { - (_, 0) => { - dev_err!(dev, "WPR2 region not created after running FWSEC-FRTS\n"); + _: { gsp.boot(pdev, bar, spec.chipset, gsp_falcon, sec2_falcon)? }, - Err(EIO) - } - (wpr2_lo, _) if wpr2_lo != fb_layout.frts.start => { - dev_err!( - dev, - "WPR2 region created at unexpected address {:#x}; expected {:#x}\n", - wpr2_lo, - fb_layout.frts.start, - ); - - Err(EIO) - } - (wpr2_lo, wpr2_hi) => { - dev_dbg!(dev, "WPR2: {:#x}-{:#x}\n", wpr2_lo, wpr2_hi); - dev_dbg!(dev, "GPU instance built\n"); - - Ok(()) - } - } + bar: devres_bar, + }) } - pub(crate) fn new( - pdev: &pci::Device<device::Bound>, - devres_bar: Arc<Devres<Bar0>>, - ) -> Result<impl PinInit<Self>> { - let bar = devres_bar.access(pdev.as_ref())?; - let spec = Spec::new(bar)?; - let fw = Firmware::new(pdev.as_ref(), spec.chipset, FIRMWARE_VERSION)?; - - dev_info!( - pdev.as_ref(), - "NVIDIA (Chipset: {}, Architecture: {:?}, Revision: {})\n", - spec.chipset, - spec.chipset.arch(), - spec.revision - ); - - // We must wait for GFW_BOOT completion before doing any significant setup on the GPU. - gfw::wait_gfw_boot_completion(bar) - .inspect_err(|_| dev_err!(pdev.as_ref(), "GFW boot did not complete"))?; - - let sysmem_flush = SysmemFlush::register(pdev.as_ref(), bar, spec.chipset)?; - - let gsp_falcon = Falcon::<Gsp>::new( - pdev.as_ref(), - spec.chipset, - bar, - spec.chipset > Chipset::GA100, - )?; - gsp_falcon.clear_swgen0_intr(bar); - - let _sec2_falcon = Falcon::<Sec2>::new(pdev.as_ref(), spec.chipset, bar, true)?; - - let fb_layout = FbLayout::new(spec.chipset, bar)?; - dev_dbg!(pdev.as_ref(), "{:#x?}\n", fb_layout); - - let bios = Vbios::new(pdev, bar)?; - - Self::run_fwsec_frts(pdev.as_ref(), &gsp_falcon, bar, &bios, &fb_layout)?; - - Ok(pin_init!(Self { - spec, - bar: devres_bar, - fw, - sysmem_flush, - })) + /// Called when the corresponding [`Device`](device::Device) is unbound. + /// + /// Note: This method must only be called from `Driver::unbind`. + pub(crate) fn unbind(&self, dev: &device::Device<device::Core>) { + kernel::warn_on!(self + .bar + .access(dev) + .inspect(|bar| self.sysmem_flush.unregister(bar)) + .is_err()); } } diff --git a/drivers/gpu/nova-core/gsp.rs b/drivers/gpu/nova-core/gsp.rs new file mode 100644 index 000000000000..64e472e7a9d3 --- /dev/null +++ b/drivers/gpu/nova-core/gsp.rs @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0 + +mod boot; + +use kernel::prelude::*; + +mod fw; + +pub(crate) const GSP_PAGE_SHIFT: usize = 12; +pub(crate) const GSP_PAGE_SIZE: usize = 1 << GSP_PAGE_SHIFT; + +/// GSP runtime data. +/// +/// This is an empty pinned placeholder for now. +#[pin_data] +pub(crate) struct Gsp {} + +impl Gsp { + pub(crate) fn new() -> impl PinInit<Self> { + pin_init!(Self {}) + } +} diff --git a/drivers/gpu/nova-core/gsp/boot.rs b/drivers/gpu/nova-core/gsp/boot.rs new file mode 100644 index 000000000000..2800f3aee37d --- /dev/null +++ b/drivers/gpu/nova-core/gsp/boot.rs @@ -0,0 +1,137 @@ +// SPDX-License-Identifier: GPL-2.0 + +use kernel::device; +use kernel::pci; +use kernel::prelude::*; + +use crate::driver::Bar0; +use crate::falcon::{gsp::Gsp, sec2::Sec2, Falcon}; +use crate::fb::FbLayout; +use crate::firmware::{ + booter::{BooterFirmware, BooterKind}, + fwsec::{FwsecCommand, FwsecFirmware}, + gsp::GspFirmware, + FIRMWARE_VERSION, +}; +use crate::gpu::Chipset; +use crate::regs; +use crate::vbios::Vbios; + +impl super::Gsp { + /// Helper function to load and run the FWSEC-FRTS firmware and confirm that it has properly + /// created the WPR2 region. + fn run_fwsec_frts( + dev: &device::Device<device::Bound>, + falcon: &Falcon<Gsp>, + bar: &Bar0, + bios: &Vbios, + fb_layout: &FbLayout, + ) -> Result<()> { + // Check that the WPR2 region does not already exists - if it does, we cannot run + // FWSEC-FRTS until the GPU is reset. + if regs::NV_PFB_PRI_MMU_WPR2_ADDR_HI::read(bar).higher_bound() != 0 { + dev_err!( + dev, + "WPR2 region already exists - GPU needs to be reset to proceed\n" + ); + return Err(EBUSY); + } + + let fwsec_frts = FwsecFirmware::new( + dev, + falcon, + bar, + bios, + FwsecCommand::Frts { + frts_addr: fb_layout.frts.start, + frts_size: fb_layout.frts.end - fb_layout.frts.start, + }, + )?; + + // Run FWSEC-FRTS to create the WPR2 region. + fwsec_frts.run(dev, falcon, bar)?; + + // SCRATCH_E contains the error code for FWSEC-FRTS. + let frts_status = regs::NV_PBUS_SW_SCRATCH_0E_FRTS_ERR::read(bar).frts_err_code(); + if frts_status != 0 { + dev_err!( + dev, + "FWSEC-FRTS returned with error code {:#x}", + frts_status + ); + + return Err(EIO); + } + + // Check that the WPR2 region has been created as we requested. + let (wpr2_lo, wpr2_hi) = ( + regs::NV_PFB_PRI_MMU_WPR2_ADDR_LO::read(bar).lower_bound(), + regs::NV_PFB_PRI_MMU_WPR2_ADDR_HI::read(bar).higher_bound(), + ); + + match (wpr2_lo, wpr2_hi) { + (_, 0) => { + dev_err!(dev, "WPR2 region not created after running FWSEC-FRTS\n"); + + Err(EIO) + } + (wpr2_lo, _) if wpr2_lo != fb_layout.frts.start => { + dev_err!( + dev, + "WPR2 region created at unexpected address {:#x}; expected {:#x}\n", + wpr2_lo, + fb_layout.frts.start, + ); + + Err(EIO) + } + (wpr2_lo, wpr2_hi) => { + dev_dbg!(dev, "WPR2: {:#x}-{:#x}\n", wpr2_lo, wpr2_hi); + dev_dbg!(dev, "GPU instance built\n"); + + Ok(()) + } + } + } + + /// Attempt to boot the GSP. + /// + /// This is a GPU-dependent and complex procedure that involves loading firmware files from + /// user-space, patching them with signatures, and building firmware-specific intricate data + /// structures that the GSP will use at runtime. + /// + /// Upon return, the GSP is up and running, and its runtime object given as return value. + pub(crate) fn boot( + self: Pin<&mut Self>, + pdev: &pci::Device<device::Bound>, + bar: &Bar0, + chipset: Chipset, + gsp_falcon: &Falcon<Gsp>, + sec2_falcon: &Falcon<Sec2>, + ) -> Result { + let dev = pdev.as_ref(); + + let bios = Vbios::new(dev, bar)?; + + let _gsp_fw = KBox::pin_init( + GspFirmware::new(dev, chipset, FIRMWARE_VERSION)?, + GFP_KERNEL, + )?; + + let fb_layout = FbLayout::new(chipset, bar)?; + dev_dbg!(dev, "{:#x?}\n", fb_layout); + + Self::run_fwsec_frts(dev, gsp_falcon, bar, &bios, &fb_layout)?; + + let _booter_loader = BooterFirmware::new( + dev, + BooterKind::Loader, + chipset, + FIRMWARE_VERSION, + sec2_falcon, + bar, + )?; + + Ok(()) + } +} diff --git a/drivers/gpu/nova-core/gsp/fw.rs b/drivers/gpu/nova-core/gsp/fw.rs new file mode 100644 index 000000000000..34226dd00982 --- /dev/null +++ b/drivers/gpu/nova-core/gsp/fw.rs @@ -0,0 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 + +mod r570_144; + +// Alias to avoid repeating the version number with every use. +#[expect(unused)] +use r570_144 as bindings; diff --git a/drivers/gpu/nova-core/gsp/fw/r570_144.rs b/drivers/gpu/nova-core/gsp/fw/r570_144.rs new file mode 100644 index 000000000000..35cb0370a7c9 --- /dev/null +++ b/drivers/gpu/nova-core/gsp/fw/r570_144.rs @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Firmware bindings. +//! +//! Imports the generated bindings by `bindgen`. +//! +//! This module may not be directly used. Please abstract or re-export the needed symbols in the +//! parent module instead. + +#![cfg_attr(test, allow(deref_nullptr))] +#![cfg_attr(test, allow(unaligned_references))] +#![cfg_attr(test, allow(unsafe_op_in_unsafe_fn))] +#![allow( + dead_code, + unused_imports, + clippy::all, + clippy::undocumented_unsafe_blocks, + clippy::ptr_as_ptr, + clippy::ref_as_ptr, + missing_docs, + non_camel_case_types, + non_upper_case_globals, + non_snake_case, + improper_ctypes, + unreachable_pub, + unsafe_op_in_unsafe_fn +)] +use kernel::ffi; +include!("r570_144/bindings.rs"); diff --git a/drivers/gpu/nova-core/gsp/fw/r570_144/bindings.rs b/drivers/gpu/nova-core/gsp/fw/r570_144/bindings.rs new file mode 100644 index 000000000000..cec594032515 --- /dev/null +++ b/drivers/gpu/nova-core/gsp/fw/r570_144/bindings.rs @@ -0,0 +1 @@ +// SPDX-License-Identifier: GPL-2.0 diff --git a/drivers/gpu/nova-core/nova_core.rs b/drivers/gpu/nova-core/nova_core.rs index cb2bbb30cba1..fffcaee2249f 100644 --- a/drivers/gpu/nova-core/nova_core.rs +++ b/drivers/gpu/nova-core/nova_core.rs @@ -9,6 +9,7 @@ mod fb; mod firmware; mod gfw; mod gpu; +mod gsp; mod regs; mod util; mod vbios; diff --git a/drivers/gpu/nova-core/regs.rs b/drivers/gpu/nova-core/regs.rs index d49fddf6a3c6..206dab2e1335 100644 --- a/drivers/gpu/nova-core/regs.rs +++ b/drivers/gpu/nova-core/regs.rs @@ -5,11 +5,11 @@ #![allow(non_camel_case_types)] #[macro_use] -mod macros; +pub(crate) mod macros; use crate::falcon::{ DmaTrfCmdSize, FalconCoreRev, FalconCoreRevSubversion, FalconFbifMemType, FalconFbifTarget, - FalconModSelAlgo, FalconSecurityModel, PeregrineCoreSelect, + FalconModSelAlgo, FalconSecurityModel, PFalcon2Base, PFalconBase, PeregrineCoreSelect, }; use crate::gpu::{Architecture, Chipset}; use kernel::prelude::*; @@ -28,7 +28,7 @@ impl NV_PMC_BOOT_0 { /// Combines `architecture_0` and `architecture_1` to obtain the architecture of the chip. pub(crate) fn architecture(self) -> Result<Architecture> { Architecture::try_from( - self.architecture_0() | (self.architecture_1() << Self::ARCHITECTURE_0.len()), + self.architecture_0() | (self.architecture_1() << Self::ARCHITECTURE_0_RANGE.len()), ) } @@ -36,7 +36,8 @@ impl NV_PMC_BOOT_0 { pub(crate) fn chipset(self) -> Result<Chipset> { self.architecture() .map(|arch| { - ((arch as u32) << Self::IMPLEMENTATION.len()) | u32::from(self.implementation()) + ((arch as u32) << Self::IMPLEMENTATION_RANGE.len()) + | u32::from(self.implementation()) }) .and_then(Chipset::try_from) } @@ -44,8 +45,10 @@ impl NV_PMC_BOOT_0 { // PBUS -// TODO[REGA]: this is an array of registers. -register!(NV_PBUS_SW_SCRATCH_0E@0x00001438 { +register!(NV_PBUS_SW_SCRATCH @ 0x00001400[64] {}); + +register!(NV_PBUS_SW_SCRATCH_0E_FRTS_ERR => NV_PBUS_SW_SCRATCH[0xe], + "scratch register 0xe used as FRTS firmware error code" { 31:16 frts_err_code as u16; }); @@ -123,13 +126,12 @@ register!(NV_PGC6_AON_SECURE_SCRATCH_GROUP_05_PRIV_LEVEL_MASK @ 0x00118128, 0:0 read_protection_level0 as bool, "Set after FWSEC lowers its protection level"; }); -// TODO[REGA]: This is an array of registers. -register!(NV_PGC6_AON_SECURE_SCRATCH_GROUP_05 @ 0x00118234 { - 31:0 value as u32; -}); +// OpenRM defines this as a register array, but doesn't specify its size and only uses its first +// element. Be conservative until we know the actual size or need to use more registers. +register!(NV_PGC6_AON_SECURE_SCRATCH_GROUP_05 @ 0x00118234[1] {}); register!( - NV_PGC6_AON_SECURE_SCRATCH_GROUP_05_0_GFW_BOOT => NV_PGC6_AON_SECURE_SCRATCH_GROUP_05, + NV_PGC6_AON_SECURE_SCRATCH_GROUP_05_0_GFW_BOOT => NV_PGC6_AON_SECURE_SCRATCH_GROUP_05[0], "Scratch group 05 register 0 used as GFW boot progress indicator" { 7:0 progress as u8, "Progress of GFW boot (0xff means completed)"; } @@ -180,38 +182,40 @@ impl NV_PDISP_VGA_WORKSPACE_BASE { // FUSE -register!(NV_FUSE_OPT_FPF_NVDEC_UCODE1_VERSION @ 0x00824100 { +pub(crate) const NV_FUSE_OPT_FPF_SIZE: usize = 16; + +register!(NV_FUSE_OPT_FPF_NVDEC_UCODE1_VERSION @ 0x00824100[NV_FUSE_OPT_FPF_SIZE] { 15:0 data as u16; }); -register!(NV_FUSE_OPT_FPF_SEC2_UCODE1_VERSION @ 0x00824140 { +register!(NV_FUSE_OPT_FPF_SEC2_UCODE1_VERSION @ 0x00824140[NV_FUSE_OPT_FPF_SIZE] { 15:0 data as u16; }); -register!(NV_FUSE_OPT_FPF_GSP_UCODE1_VERSION @ 0x008241c0 { +register!(NV_FUSE_OPT_FPF_GSP_UCODE1_VERSION @ 0x008241c0[NV_FUSE_OPT_FPF_SIZE] { 15:0 data as u16; }); // PFALCON -register!(NV_PFALCON_FALCON_IRQSCLR @ +0x00000004 { +register!(NV_PFALCON_FALCON_IRQSCLR @ PFalconBase[0x00000004] { 4:4 halt as bool; 6:6 swgen0 as bool; }); -register!(NV_PFALCON_FALCON_MAILBOX0 @ +0x00000040 { +register!(NV_PFALCON_FALCON_MAILBOX0 @ PFalconBase[0x00000040] { 31:0 value as u32; }); -register!(NV_PFALCON_FALCON_MAILBOX1 @ +0x00000044 { +register!(NV_PFALCON_FALCON_MAILBOX1 @ PFalconBase[0x00000044] { 31:0 value as u32; }); -register!(NV_PFALCON_FALCON_RM @ +0x00000084 { +register!(NV_PFALCON_FALCON_RM @ PFalconBase[0x00000084] { 31:0 value as u32; }); -register!(NV_PFALCON_FALCON_HWCFG2 @ +0x000000f4 { +register!(NV_PFALCON_FALCON_HWCFG2 @ PFalconBase[0x000000f4] { 10:10 riscv as bool; 12:12 mem_scrubbing as bool, "Set to 0 after memory scrubbing is completed"; 31:31 reset_ready as bool, "Signal indicating that reset is completed (GA102+)"; @@ -224,17 +228,17 @@ impl NV_PFALCON_FALCON_HWCFG2 { } } -register!(NV_PFALCON_FALCON_CPUCTL @ +0x00000100 { +register!(NV_PFALCON_FALCON_CPUCTL @ PFalconBase[0x00000100] { 1:1 startcpu as bool; 4:4 halted as bool; 6:6 alias_en as bool; }); -register!(NV_PFALCON_FALCON_BOOTVEC @ +0x00000104 { +register!(NV_PFALCON_FALCON_BOOTVEC @ PFalconBase[0x00000104] { 31:0 value as u32; }); -register!(NV_PFALCON_FALCON_DMACTL @ +0x0000010c { +register!(NV_PFALCON_FALCON_DMACTL @ PFalconBase[0x0000010c] { 0:0 require_ctx as bool; 1:1 dmem_scrubbing as bool; 2:2 imem_scrubbing as bool; @@ -242,15 +246,15 @@ register!(NV_PFALCON_FALCON_DMACTL @ +0x0000010c { 7:7 secure_stat as bool; }); -register!(NV_PFALCON_FALCON_DMATRFBASE @ +0x00000110 { +register!(NV_PFALCON_FALCON_DMATRFBASE @ PFalconBase[0x00000110] { 31:0 base as u32; }); -register!(NV_PFALCON_FALCON_DMATRFMOFFS @ +0x00000114 { +register!(NV_PFALCON_FALCON_DMATRFMOFFS @ PFalconBase[0x00000114] { 23:0 offs as u32; }); -register!(NV_PFALCON_FALCON_DMATRFCMD @ +0x00000118 { +register!(NV_PFALCON_FALCON_DMATRFCMD @ PFalconBase[0x00000118] { 0:0 full as bool; 1:1 idle as bool; 3:2 sec as u8; @@ -261,60 +265,62 @@ register!(NV_PFALCON_FALCON_DMATRFCMD @ +0x00000118 { 16:16 set_dmtag as u8; }); -register!(NV_PFALCON_FALCON_DMATRFFBOFFS @ +0x0000011c { +register!(NV_PFALCON_FALCON_DMATRFFBOFFS @ PFalconBase[0x0000011c] { 31:0 offs as u32; }); -register!(NV_PFALCON_FALCON_DMATRFBASE1 @ +0x00000128 { +register!(NV_PFALCON_FALCON_DMATRFBASE1 @ PFalconBase[0x00000128] { 8:0 base as u16; }); -register!(NV_PFALCON_FALCON_HWCFG1 @ +0x0000012c { +register!(NV_PFALCON_FALCON_HWCFG1 @ PFalconBase[0x0000012c] { 3:0 core_rev as u8 ?=> FalconCoreRev, "Core revision"; 5:4 security_model as u8 ?=> FalconSecurityModel, "Security model"; 7:6 core_rev_subversion as u8 ?=> FalconCoreRevSubversion, "Core revision subversion"; }); -register!(NV_PFALCON_FALCON_CPUCTL_ALIAS @ +0x00000130 { +register!(NV_PFALCON_FALCON_CPUCTL_ALIAS @ PFalconBase[0x00000130] { 1:1 startcpu as bool; }); // Actually known as `NV_PSEC_FALCON_ENGINE` and `NV_PGSP_FALCON_ENGINE` depending on the falcon // instance. -register!(NV_PFALCON_FALCON_ENGINE @ +0x000003c0 { +register!(NV_PFALCON_FALCON_ENGINE @ PFalconBase[0x000003c0] { 0:0 reset as bool; }); -// TODO[REGA]: this is an array of registers. -register!(NV_PFALCON_FBIF_TRANSCFG @ +0x00000600 { +register!(NV_PFALCON_FBIF_TRANSCFG @ PFalconBase[0x00000600[8]] { 1:0 target as u8 ?=> FalconFbifTarget; 2:2 mem_type as bool => FalconFbifMemType; }); -register!(NV_PFALCON_FBIF_CTL @ +0x00000624 { +register!(NV_PFALCON_FBIF_CTL @ PFalconBase[0x00000624] { 7:7 allow_phys_no_ctx as bool; }); -register!(NV_PFALCON2_FALCON_MOD_SEL @ +0x00001180 { +/* PFALCON2 */ + +register!(NV_PFALCON2_FALCON_MOD_SEL @ PFalcon2Base[0x00000180] { 7:0 algo as u8 ?=> FalconModSelAlgo; }); -register!(NV_PFALCON2_FALCON_BROM_CURR_UCODE_ID @ +0x00001198 { +register!(NV_PFALCON2_FALCON_BROM_CURR_UCODE_ID @ PFalcon2Base[0x00000198] { 7:0 ucode_id as u8; }); -register!(NV_PFALCON2_FALCON_BROM_ENGIDMASK @ +0x0000119c { +register!(NV_PFALCON2_FALCON_BROM_ENGIDMASK @ PFalcon2Base[0x0000019c] { 31:0 value as u32; }); -// TODO[REGA]: this is an array of registers. -register!(NV_PFALCON2_FALCON_BROM_PARAADDR @ +0x00001210 { +// OpenRM defines this as a register array, but doesn't specify its size and only uses its first +// element. Be conservative until we know the actual size or need to use more registers. +register!(NV_PFALCON2_FALCON_BROM_PARAADDR @ PFalcon2Base[0x00000210[1]] { 31:0 value as u32; }); // PRISCV -register!(NV_PRISCV_RISCV_BCR_CTRL @ +0x00001668 { +register!(NV_PRISCV_RISCV_BCR_CTRL @ PFalconBase[0x00001668] { 0:0 valid as bool; 4:4 core_select as bool => PeregrineCoreSelect; 8:8 br_fetch as bool; diff --git a/drivers/gpu/nova-core/regs/macros.rs b/drivers/gpu/nova-core/regs/macros.rs index a3e6de1779d4..754c14ee7f40 100644 --- a/drivers/gpu/nova-core/regs/macros.rs +++ b/drivers/gpu/nova-core/regs/macros.rs @@ -1,17 +1,27 @@ // SPDX-License-Identifier: GPL-2.0 -//! Macro to define register layout and accessors. +//! `register!` macro to define register layout and accessors. //! //! A single register typically includes several fields, which are accessed through a combination //! of bit-shift and mask operations that introduce a class of potential mistakes, notably because //! not all possible field values are necessarily valid. //! -//! The macro in this module allow to define, using an intruitive and readable syntax, a dedicated -//! type for each register with its own field accessors that can return an error is a field's value -//! is invalid. +//! The `register!` macro in this module provides an intuitive and readable syntax for defining a +//! dedicated type for each register. Each such type comes with its own field accessors that can +//! return an error if a field's value is invalid. -/// Defines a dedicated type for a register with an absolute offset, alongside with getter and -/// setter methods for its fields and methods to read and write it from an `Io` region. +/// Trait providing a base address to be added to the offset of a relative register to obtain +/// its actual offset. +/// +/// The `T` generic argument is used to distinguish which base to use, in case a type provides +/// several bases. It is given to the `register!` macro to restrict the use of the register to +/// implementors of this particular variant. +pub(crate) trait RegisterBase<T> { + const BASE: usize; +} + +/// Defines a dedicated type for a register with an absolute offset, including getter and setter +/// methods for its fields and methods to read and write it from an `Io` region. /// /// Example: /// @@ -24,7 +34,7 @@ /// ``` /// /// This defines a `BOOT_0` type which can be read or written from offset `0x100` of an `Io` -/// region. It is composed of 3 fields, for instance `minor_revision` is made of the 4 less +/// region. It is composed of 3 fields, for instance `minor_revision` is made of the 4 least /// significant bits of the register. Each field can be accessed and modified using accessor /// methods: /// @@ -33,130 +43,344 @@ /// let boot0 = BOOT_0::read(&bar); /// pr_info!("chip revision: {}.{}", boot0.major_revision(), boot0.minor_revision()); /// -/// // `Chipset::try_from` will be called with the value of the field and returns an error if the -/// // value is invalid. +/// // `Chipset::try_from` is called with the value of the `chipset` field and returns an +/// // error if it is invalid. /// let chipset = boot0.chipset()?; /// /// // Update some fields and write the value back. /// boot0.set_major_revision(3).set_minor_revision(10).write(&bar); /// -/// // Or just read and update the register in a single step: +/// // Or, just read and update the register in a single step: /// BOOT_0::alter(&bar, |r| r.set_major_revision(3).set_minor_revision(10)); /// ``` /// -/// Fields can be defined as follows: +/// Fields are defined as follows: /// -/// - `as <type>` simply returns the field value casted as the requested integer type, typically -/// `u32`, `u16`, `u8` or `bool`. Note that `bool` fields must have a range of 1 bit. +/// - `as <type>` simply returns the field value casted to <type>, typically `u32`, `u16`, `u8` or +/// `bool`. Note that `bool` fields must have a range of 1 bit. /// - `as <type> => <into_type>` calls `<into_type>`'s `From::<<type>>` implementation and returns /// the result. /// - `as <type> ?=> <try_into_type>` calls `<try_into_type>`'s `TryFrom::<<type>>` implementation -/// and returns the result. This is useful on fields for which not all values are value. +/// and returns the result. This is useful with fields for which not all values are valid. /// /// The documentation strings are optional. If present, they will be added to the type's /// definition, or the field getter and setter methods they are attached to. /// -/// Putting a `+` before the address of the register makes it relative to a base: the `read` and -/// `write` methods take a `base` argument that is added to the specified address before access, -/// and `try_read` and `try_write` methods are also created, allowing access with offsets unknown -/// at compile-time: +/// It is also possible to create a alias register by using the `=> ALIAS` syntax. This is useful +/// for cases where a register's interpretation depends on the context: /// /// ```no_run -/// register!(CPU_CTL @ +0x0000010, "CPU core control" { -/// 0:0 start as bool, "Start the CPU core"; +/// register!(SCRATCH @ 0x00000200, "Scratch register" { +/// 31:0 value as u32, "Raw value"; /// }); /// -/// // Flip the `start` switch for the CPU core which base address is at `CPU_BASE`. -/// let cpuctl = CPU_CTL::read(&bar, CPU_BASE); -/// pr_info!("CPU CTL: {:#x}", cpuctl); -/// cpuctl.set_start(true).write(&bar, CPU_BASE); +/// register!(SCRATCH_BOOT_STATUS => SCRATCH, "Boot status of the firmware" { +/// 0:0 completed as bool, "Whether the firmware has completed booting"; +/// }); /// ``` /// -/// It is also possible to create a alias register by using the `=> ALIAS` syntax. This is useful -/// for cases where a register's interpretation depends on the context: +/// In this example, `SCRATCH_0_BOOT_STATUS` uses the same I/O address as `SCRATCH`, while also +/// providing its own `completed` field. +/// +/// ## Relative registers +/// +/// A register can be defined as being accessible from a fixed offset of a provided base. For +/// instance, imagine the following I/O space: +/// +/// ```text +/// +-----------------------------+ +/// | ... | +/// | | +/// 0x100--->+------------CPU0-------------+ +/// | | +/// 0x110--->+-----------------------------+ +/// | CPU_CTL | +/// +-----------------------------+ +/// | ... | +/// | | +/// | | +/// 0x200--->+------------CPU1-------------+ +/// | | +/// 0x210--->+-----------------------------+ +/// | CPU_CTL | +/// +-----------------------------+ +/// | ... | +/// +-----------------------------+ +/// ``` +/// +/// `CPU0` and `CPU1` both have a `CPU_CTL` register that starts at offset `0x10` of their I/O +/// space segment. Since both instances of `CPU_CTL` share the same layout, we don't want to define +/// them twice and would prefer a way to select which one to use from a single definition +/// +/// This can be done using the `Base[Offset]` syntax when specifying the register's address. +/// +/// `Base` is an arbitrary type (typically a ZST) to be used as a generic parameter of the +/// [`RegisterBase`] trait to provide the base as a constant, i.e. each type providing a base for +/// this register needs to implement `RegisterBase<Base>`. Here is the above example translated +/// into code: /// /// ```no_run -/// register!(SCRATCH_0 @ 0x0000100, "Scratch register 0" { -/// 31:0 value as u32, "Raw value"; +/// // Type used to identify the base. +/// pub(crate) struct CpuCtlBase; /// -/// register!(SCRATCH_0_BOOT_STATUS => SCRATCH_0, "Boot status of the firmware" { -/// 0:0 completed as bool, "Whether the firmware has completed booting"; +/// // ZST describing `CPU0`. +/// struct Cpu0; +/// impl RegisterBase<CpuCtlBase> for Cpu0 { +/// const BASE: usize = 0x100; +/// } +/// // Singleton of `CPU0` used to identify it. +/// const CPU0: Cpu0 = Cpu0; +/// +/// // ZST describing `CPU1`. +/// struct Cpu1; +/// impl RegisterBase<CpuCtlBase> for Cpu1 { +/// const BASE: usize = 0x200; +/// } +/// // Singleton of `CPU1` used to identify it. +/// const CPU1: Cpu1 = Cpu1; +/// +/// // This makes `CPU_CTL` accessible from all implementors of `RegisterBase<CpuCtlBase>`. +/// register!(CPU_CTL @ CpuCtlBase[0x10], "CPU core control" { +/// 0:0 start as bool, "Start the CPU core"; +/// }); +/// +/// // The `read`, `write` and `alter` methods of relative registers take an extra `base` argument +/// // that is used to resolve its final address by adding its `BASE` to the offset of the +/// // register. +/// +/// // Start `CPU0`. +/// CPU_CTL::alter(bar, &CPU0, |r| r.set_start(true)); +/// +/// // Start `CPU1`. +/// CPU_CTL::alter(bar, &CPU1, |r| r.set_start(true)); +/// +/// // Aliases can also be defined for relative register. +/// register!(CPU_CTL_ALIAS => CpuCtlBase[CPU_CTL], "Alias to CPU core control" { +/// 1:1 alias_start as bool, "Start the aliased CPU core"; +/// }); +/// +/// // Start the aliased `CPU0`. +/// CPU_CTL_ALIAS::alter(bar, &CPU0, |r| r.set_alias_start(true)); +/// ``` +/// +/// ## Arrays of registers +/// +/// Some I/O areas contain consecutive values that can be interpreted in the same way. These areas +/// can be defined as an array of identical registers, allowing them to be accessed by index with +/// compile-time or runtime bound checking. Simply define their address as `Address[Size]`, and add +/// an `idx` parameter to their `read`, `write` and `alter` methods: +/// +/// ```no_run +/// # fn no_run() -> Result<(), Error> { +/// # fn get_scratch_idx() -> usize { +/// # 0x15 +/// # } +/// // Array of 64 consecutive registers with the same layout starting at offset `0x80`. +/// register!(SCRATCH @ 0x00000080[64], "Scratch registers" { +/// 31:0 value as u32; +/// }); +/// +/// // Read scratch register 0, i.e. I/O address `0x80`. +/// let scratch_0 = SCRATCH::read(bar, 0).value(); +/// // Read scratch register 15, i.e. I/O address `0x80 + (15 * 4)`. +/// let scratch_15 = SCRATCH::read(bar, 15).value(); +/// +/// // This is out of bounds and won't build. +/// // let scratch_128 = SCRATCH::read(bar, 128).value(); +/// +/// // Runtime-obtained array index. +/// let scratch_idx = get_scratch_idx(); +/// // Access on a runtime index returns an error if it is out-of-bounds. +/// let some_scratch = SCRATCH::try_read(bar, scratch_idx)?.value(); +/// +/// // Alias to a particular register in an array. +/// // Here `SCRATCH[8]` is used to convey the firmware exit code. +/// register!(FIRMWARE_STATUS => SCRATCH[8], "Firmware exit status code" { +/// 7:0 status as u8; +/// }); +/// +/// let status = FIRMWARE_STATUS::read(bar).status(); +/// +/// // Non-contiguous register arrays can be defined by adding a stride parameter. +/// // Here, each of the 16 registers of the array are separated by 8 bytes, meaning that the +/// // registers of the two declarations below are interleaved. +/// register!(SCRATCH_INTERLEAVED_0 @ 0x000000c0[16 ; 8], "Scratch registers bank 0" { +/// 31:0 value as u32; +/// }); +/// register!(SCRATCH_INTERLEAVED_1 @ 0x000000c4[16 ; 8], "Scratch registers bank 1" { +/// 31:0 value as u32; +/// }); +/// # Ok(()) +/// # } /// ``` /// -/// In this example, `SCRATCH_0_BOOT_STATUS` uses the same I/O address as `SCRATCH_0`, while also -/// providing its own `completed` method. +/// ## Relative arrays of registers +/// +/// Combining the two features described in the sections above, arrays of registers accessible from +/// a base can also be defined: +/// +/// ```no_run +/// # fn no_run() -> Result<(), Error> { +/// # fn get_scratch_idx() -> usize { +/// # 0x15 +/// # } +/// // Type used as parameter of `RegisterBase` to specify the base. +/// pub(crate) struct CpuCtlBase; +/// +/// // ZST describing `CPU0`. +/// struct Cpu0; +/// impl RegisterBase<CpuCtlBase> for Cpu0 { +/// const BASE: usize = 0x100; +/// } +/// // Singleton of `CPU0` used to identify it. +/// const CPU0: Cpu0 = Cpu0; +/// +/// // ZST describing `CPU1`. +/// struct Cpu1; +/// impl RegisterBase<CpuCtlBase> for Cpu1 { +/// const BASE: usize = 0x200; +/// } +/// // Singleton of `CPU1` used to identify it. +/// const CPU1: Cpu1 = Cpu1; +/// +/// // 64 per-cpu scratch registers, arranged as an contiguous array. +/// register!(CPU_SCRATCH @ CpuCtlBase[0x00000080[64]], "Per-CPU scratch registers" { +/// 31:0 value as u32; +/// }); +/// +/// let cpu0_scratch_0 = CPU_SCRATCH::read(bar, &Cpu0, 0).value(); +/// let cpu1_scratch_15 = CPU_SCRATCH::read(bar, &Cpu1, 15).value(); +/// +/// // This won't build. +/// // let cpu0_scratch_128 = CPU_SCRATCH::read(bar, &Cpu0, 128).value(); +/// +/// // Runtime-obtained array index. +/// let scratch_idx = get_scratch_idx(); +/// // Access on a runtime value returns an error if it is out-of-bounds. +/// let cpu0_some_scratch = CPU_SCRATCH::try_read(bar, &Cpu0, scratch_idx)?.value(); +/// +/// // `SCRATCH[8]` is used to convey the firmware exit code. +/// register!(CPU_FIRMWARE_STATUS => CpuCtlBase[CPU_SCRATCH[8]], +/// "Per-CPU firmware exit status code" { +/// 7:0 status as u8; +/// }); +/// +/// let cpu0_status = CPU_FIRMWARE_STATUS::read(bar, &Cpu0).status(); +/// +/// // Non-contiguous register arrays can be defined by adding a stride parameter. +/// // Here, each of the 16 registers of the array are separated by 8 bytes, meaning that the +/// // registers of the two declarations below are interleaved. +/// register!(CPU_SCRATCH_INTERLEAVED_0 @ CpuCtlBase[0x00000d00[16 ; 8]], +/// "Scratch registers bank 0" { +/// 31:0 value as u32; +/// }); +/// register!(CPU_SCRATCH_INTERLEAVED_1 @ CpuCtlBase[0x00000d04[16 ; 8]], +/// "Scratch registers bank 1" { +/// 31:0 value as u32; +/// }); +/// # Ok(()) +/// # } +/// ``` macro_rules! register { // Creates a register at a fixed offset of the MMIO space. + ($name:ident @ $offset:literal $(, $comment:literal)? { $($fields:tt)* } ) => { + register!(@core $name $(, $comment)? { $($fields)* } ); + register!(@io_fixed $name @ $offset); + }; + + // Creates an alias register of fixed offset register `alias` with its own fields. + ($name:ident => $alias:ident $(, $comment:literal)? { $($fields:tt)* } ) => { + register!(@core $name $(, $comment)? { $($fields)* } ); + register!(@io_fixed $name @ $alias::OFFSET); + }; + + // Creates a register at a relative offset from a base address provider. + ($name:ident @ $base:ty [ $offset:literal ] $(, $comment:literal)? { $($fields:tt)* } ) => { + register!(@core $name $(, $comment)? { $($fields)* } ); + register!(@io_relative $name @ $base [ $offset ]); + }; + + // Creates an alias register of relative offset register `alias` with its own fields. + ($name:ident => $base:ty [ $alias:ident ] $(, $comment:literal)? { $($fields:tt)* }) => { + register!(@core $name $(, $comment)? { $($fields)* } ); + register!(@io_relative $name @ $base [ $alias::OFFSET ]); + }; + + // Creates an array of registers at a fixed offset of the MMIO space. ( - $name:ident @ $offset:literal $(, $comment:literal)? { + $name:ident @ $offset:literal [ $size:expr ; $stride:expr ] $(, $comment:literal)? { $($fields:tt)* } ) => { - register!(@common $name @ $offset $(, $comment)?); - register!(@field_accessors $name { $($fields)* }); - register!(@io $name @ $offset); + static_assert!(::core::mem::size_of::<u32>() <= $stride); + register!(@core $name $(, $comment)? { $($fields)* } ); + register!(@io_array $name @ $offset [ $size ; $stride ]); }; - // Creates a alias register of fixed offset register `alias` with its own fields. + // Shortcut for contiguous array of registers (stride == size of element). ( - $name:ident => $alias:ident $(, $comment:literal)? { + $name:ident @ $offset:literal [ $size:expr ] $(, $comment:literal)? { $($fields:tt)* } ) => { - register!(@common $name @ $alias::OFFSET $(, $comment)?); - register!(@field_accessors $name { $($fields)* }); - register!(@io $name @ $alias::OFFSET); + register!($name @ $offset [ $size ; ::core::mem::size_of::<u32>() ] $(, $comment)? { + $($fields)* + } ); + }; + + // Creates an array of registers at a relative offset from a base address provider. + ( + $name:ident @ $base:ty [ $offset:literal [ $size:expr ; $stride:expr ] ] + $(, $comment:literal)? { $($fields:tt)* } + ) => { + static_assert!(::core::mem::size_of::<u32>() <= $stride); + register!(@core $name $(, $comment)? { $($fields)* } ); + register!(@io_relative_array $name @ $base [ $offset [ $size ; $stride ] ]); }; - // Creates a register at a relative offset from a base address. + // Shortcut for contiguous array of relative registers (stride == size of element). ( - $name:ident @ + $offset:literal $(, $comment:literal)? { + $name:ident @ $base:ty [ $offset:literal [ $size:expr ] ] $(, $comment:literal)? { $($fields:tt)* } ) => { - register!(@common $name @ $offset $(, $comment)?); - register!(@field_accessors $name { $($fields)* }); - register!(@io$name @ + $offset); + register!($name @ $base [ $offset [ $size ; ::core::mem::size_of::<u32>() ] ] + $(, $comment)? { $($fields)* } ); }; - // Creates a alias register of relative offset register `alias` with its own fields. + // Creates an alias of register `idx` of relative array of registers `alias` with its own + // fields. ( - $name:ident => + $alias:ident $(, $comment:literal)? { + $name:ident => $base:ty [ $alias:ident [ $idx:expr ] ] $(, $comment:literal)? { $($fields:tt)* } ) => { - register!(@common $name @ $alias::OFFSET $(, $comment)?); - register!(@field_accessors $name { $($fields)* }); - register!(@io $name @ + $alias::OFFSET); + static_assert!($idx < $alias::SIZE); + register!(@core $name $(, $comment)? { $($fields)* } ); + register!(@io_relative $name @ $base [ $alias::OFFSET + $idx * $alias::STRIDE ] ); + }; + + // Creates an alias of register `idx` of array of registers `alias` with its own fields. + // This rule belongs to the (non-relative) register arrays set, but needs to be put last + // to avoid it being interpreted in place of the relative register array alias rule. + ($name:ident => $alias:ident [ $idx:expr ] $(, $comment:literal)? { $($fields:tt)* }) => { + static_assert!($idx < $alias::SIZE); + register!(@core $name $(, $comment)? { $($fields)* } ); + register!(@io_fixed $name @ $alias::OFFSET + $idx * $alias::STRIDE ); }; // All rules below are helpers. - // Defines the wrapper `$name` type, as well as its relevant implementations (`Debug`, `BitOr`, - // and conversion to regular `u32`). - (@common $name:ident @ $offset:expr $(, $comment:literal)?) => { + // Defines the wrapper `$name` type, as well as its relevant implementations (`Debug`, + // `Default`, `BitOr`, and conversion to the value type) and field accessor methods. + (@core $name:ident $(, $comment:literal)? { $($fields:tt)* }) => { $( #[doc=$comment] )? #[repr(transparent)] - #[derive(Clone, Copy, Default)] + #[derive(Clone, Copy)] pub(crate) struct $name(u32); - #[allow(dead_code)] - impl $name { - pub(crate) const OFFSET: usize = $offset; - } - - // TODO[REGA]: display the raw hex value, then the value of all the fields. This requires - // matching the fields, which will complexify the syntax considerably... - impl ::core::fmt::Debug for $name { - fn fmt(&self, f: &mut ::core::fmt::Formatter<'_>) -> ::core::fmt::Result { - f.debug_tuple(stringify!($name)) - .field(&format_args!("0x{0:x}", &self.0)) - .finish() - } - } - impl ::core::ops::BitOr for $name { type Output = Self; @@ -170,6 +394,34 @@ macro_rules! register { reg.0 } } + + register!(@fields_dispatcher $name { $($fields)* }); + }; + + // Captures the fields and passes them to all the implementers that require field information. + // + // Used to simplify the matching rules for implementers, so they don't need to match the entire + // complex fields rule even though they only make use of part of it. + (@fields_dispatcher $name:ident { + $($hi:tt:$lo:tt $field:ident as $type:tt + $(?=> $try_into_type:ty)? + $(=> $into_type:ty)? + $(, $comment:literal)? + ; + )* + } + ) => { + register!(@field_accessors $name { + $( + $hi:$lo $field as $type + $(?=> $try_into_type)? + $(=> $into_type)? + $(, $comment)? + ; + )* + }); + register!(@debug $name { $($field;)* }); + register!(@default $name { $($field;)* }); }; // Defines all the field getter/methods methods for `$name`. @@ -228,7 +480,7 @@ macro_rules! register { $(, $comment:literal)?; ) => { register!( - @leaf_accessor $name $hi:$lo $field as bool + @leaf_accessor $name $hi:$lo $field { |f| <$into_type>::from(if f != 0 { true } else { false }) } $into_type => $into_type $(, $comment)?; ); @@ -246,7 +498,7 @@ macro_rules! register { @field_accessor $name:ident $hi:tt:$lo:tt $field:ident as $type:tt ?=> $try_into_type:ty $(, $comment:literal)?; ) => { - register!(@leaf_accessor $name $hi:$lo $field as $type + register!(@leaf_accessor $name $hi:$lo $field { |f| <$try_into_type>::try_from(f as $type) } $try_into_type => ::core::result::Result< $try_into_type, @@ -260,11 +512,11 @@ macro_rules! register { @field_accessor $name:ident $hi:tt:$lo:tt $field:ident as $type:tt => $into_type:ty $(, $comment:literal)?; ) => { - register!(@leaf_accessor $name $hi:$lo $field as $type + register!(@leaf_accessor $name $hi:$lo $field { |f| <$into_type>::from(f as $type) } $into_type => $into_type $(, $comment)?;); }; - // Shortcut for fields defined as non-`bool` without the `=>` or `?=>` syntax. + // Shortcut for non-boolean fields defined without the `=>` or `?=>` syntax. ( @field_accessor $name:ident $hi:tt:$lo:tt $field:ident as $type:tt $(, $comment:literal)?; @@ -274,11 +526,11 @@ macro_rules! register { // Generates the accessor methods for a single field. ( - @leaf_accessor $name:ident $hi:tt:$lo:tt $field:ident as $type:ty + @leaf_accessor $name:ident $hi:tt:$lo:tt $field:ident { $process:expr } $to_type:ty => $res_type:ty $(, $comment:literal)?; ) => { ::kernel::macros::paste!( - const [<$field:upper>]: ::core::ops::RangeInclusive<u8> = $lo..=$hi; + const [<$field:upper _RANGE>]: ::core::ops::RangeInclusive<u8> = $lo..=$hi; const [<$field:upper _MASK>]: u32 = ((((1 << $hi) - 1) << 1) + 1) - ((1 << $lo) - 1); const [<$field:upper _SHIFT>]: u32 = Self::[<$field:upper _MASK>].trailing_zeros(); ); @@ -287,7 +539,7 @@ macro_rules! register { #[doc="Returns the value of this field:"] #[doc=$comment] )? - #[inline] + #[inline(always)] pub(crate) fn $field(self) -> $res_type { ::kernel::macros::paste!( const MASK: u32 = $name::[<$field:upper _MASK>]; @@ -303,7 +555,7 @@ macro_rules! register { #[doc="Sets the value of this field:"] #[doc=$comment] )? - #[inline] + #[inline(always)] pub(crate) fn [<set_ $field>](mut self, value: $to_type) -> Self { const MASK: u32 = $name::[<$field:upper _MASK>]; const SHIFT: u32 = $name::[<$field:upper _SHIFT>]; @@ -315,25 +567,64 @@ macro_rules! register { ); }; - // Creates the IO accessors for a fixed offset register. - (@io $name:ident @ $offset:expr) => { + // Generates the `Debug` implementation for `$name`. + (@debug $name:ident { $($field:ident;)* }) => { + impl ::core::fmt::Debug for $name { + fn fmt(&self, f: &mut ::core::fmt::Formatter<'_>) -> ::core::fmt::Result { + f.debug_struct(stringify!($name)) + .field("<raw>", &format_args!("{:#x}", &self.0)) + $( + .field(stringify!($field), &self.$field()) + )* + .finish() + } + } + }; + + // Generates the `Default` implementation for `$name`. + (@default $name:ident { $($field:ident;)* }) => { + /// Returns a value for the register where all fields are set to their default value. + impl ::core::default::Default for $name { + fn default() -> Self { + #[allow(unused_mut)] + let mut value = Self(Default::default()); + + ::kernel::macros::paste!( + $( + value.[<set_ $field>](Default::default()); + )* + ); + + value + } + } + }; + + // Generates the IO accessors for a fixed offset register. + (@io_fixed $name:ident @ $offset:expr) => { #[allow(dead_code)] impl $name { - #[inline] + pub(crate) const OFFSET: usize = $offset; + + /// Read the register from its address in `io`. + #[inline(always)] pub(crate) fn read<const SIZE: usize, T>(io: &T) -> Self where T: ::core::ops::Deref<Target = ::kernel::io::Io<SIZE>>, { Self(io.read32($offset)) } - #[inline] + /// Write the value contained in `self` to the register address in `io`. + #[inline(always)] pub(crate) fn write<const SIZE: usize, T>(self, io: &T) where T: ::core::ops::Deref<Target = ::kernel::io::Io<SIZE>>, { io.write32(self.0, $offset) } - #[inline] + /// Read the register from its address in `io` and run `f` on its value to obtain a new + /// value to write back. + #[inline(always)] pub(crate) fn alter<const SIZE: usize, T, F>( io: &T, f: F, @@ -347,76 +638,322 @@ macro_rules! register { } }; - // Create the IO accessors for a relative offset register. - (@io $name:ident @ + $offset:literal) => { + // Generates the IO accessors for a relative offset register. + (@io_relative $name:ident @ $base:ty [ $offset:expr ]) => { #[allow(dead_code)] impl $name { - #[inline] + pub(crate) const OFFSET: usize = $offset; + + /// Read the register from `io`, using the base address provided by `base` and adding + /// the register's offset to it. + #[inline(always)] + pub(crate) fn read<const SIZE: usize, T, B>( + io: &T, + #[allow(unused_variables)] + base: &B, + ) -> Self where + T: ::core::ops::Deref<Target = ::kernel::io::Io<SIZE>>, + B: crate::regs::macros::RegisterBase<$base>, + { + const OFFSET: usize = $name::OFFSET; + + let value = io.read32( + <B as crate::regs::macros::RegisterBase<$base>>::BASE + OFFSET + ); + + Self(value) + } + + /// Write the value contained in `self` to `io`, using the base address provided by + /// `base` and adding the register's offset to it. + #[inline(always)] + pub(crate) fn write<const SIZE: usize, T, B>( + self, + io: &T, + #[allow(unused_variables)] + base: &B, + ) where + T: ::core::ops::Deref<Target = ::kernel::io::Io<SIZE>>, + B: crate::regs::macros::RegisterBase<$base>, + { + const OFFSET: usize = $name::OFFSET; + + io.write32( + self.0, + <B as crate::regs::macros::RegisterBase<$base>>::BASE + OFFSET + ); + } + + /// Read the register from `io`, using the base address provided by `base` and adding + /// the register's offset to it, then run `f` on its value to obtain a new value to + /// write back. + #[inline(always)] + pub(crate) fn alter<const SIZE: usize, T, B, F>( + io: &T, + base: &B, + f: F, + ) where + T: ::core::ops::Deref<Target = ::kernel::io::Io<SIZE>>, + B: crate::regs::macros::RegisterBase<$base>, + F: ::core::ops::FnOnce(Self) -> Self, + { + let reg = f(Self::read(io, base)); + reg.write(io, base); + } + } + }; + + // Generates the IO accessors for an array of registers. + (@io_array $name:ident @ $offset:literal [ $size:expr ; $stride:expr ]) => { + #[allow(dead_code)] + impl $name { + pub(crate) const OFFSET: usize = $offset; + pub(crate) const SIZE: usize = $size; + pub(crate) const STRIDE: usize = $stride; + + /// Read the array register at index `idx` from its address in `io`. + #[inline(always)] pub(crate) fn read<const SIZE: usize, T>( io: &T, - base: usize, + idx: usize, ) -> Self where T: ::core::ops::Deref<Target = ::kernel::io::Io<SIZE>>, { - Self(io.read32(base + $offset)) + build_assert!(idx < Self::SIZE); + + let offset = Self::OFFSET + (idx * Self::STRIDE); + let value = io.read32(offset); + + Self(value) } - #[inline] + /// Write the value contained in `self` to the array register with index `idx` in `io`. + #[inline(always)] pub(crate) fn write<const SIZE: usize, T>( self, io: &T, - base: usize, + idx: usize ) where T: ::core::ops::Deref<Target = ::kernel::io::Io<SIZE>>, { - io.write32(self.0, base + $offset) + build_assert!(idx < Self::SIZE); + + let offset = Self::OFFSET + (idx * Self::STRIDE); + + io.write32(self.0, offset); } - #[inline] + /// Read the array register at index `idx` in `io` and run `f` on its value to obtain a + /// new value to write back. + #[inline(always)] pub(crate) fn alter<const SIZE: usize, T, F>( io: &T, - base: usize, + idx: usize, f: F, ) where T: ::core::ops::Deref<Target = ::kernel::io::Io<SIZE>>, F: ::core::ops::FnOnce(Self) -> Self, { - let reg = f(Self::read(io, base)); - reg.write(io, base); + let reg = f(Self::read(io, idx)); + reg.write(io, idx); } - #[inline] + /// Read the array register at index `idx` from its address in `io`. + /// + /// The validity of `idx` is checked at run-time, and `EINVAL` is returned is the + /// access was out-of-bounds. + #[inline(always)] pub(crate) fn try_read<const SIZE: usize, T>( io: &T, - base: usize, + idx: usize, ) -> ::kernel::error::Result<Self> where T: ::core::ops::Deref<Target = ::kernel::io::Io<SIZE>>, { - io.try_read32(base + $offset).map(Self) + if idx < Self::SIZE { + Ok(Self::read(io, idx)) + } else { + Err(EINVAL) + } } - #[inline] + /// Write the value contained in `self` to the array register with index `idx` in `io`. + /// + /// The validity of `idx` is checked at run-time, and `EINVAL` is returned is the + /// access was out-of-bounds. + #[inline(always)] pub(crate) fn try_write<const SIZE: usize, T>( self, io: &T, - base: usize, - ) -> ::kernel::error::Result<()> where + idx: usize, + ) -> ::kernel::error::Result where T: ::core::ops::Deref<Target = ::kernel::io::Io<SIZE>>, { - io.try_write32(self.0, base + $offset) + if idx < Self::SIZE { + Ok(self.write(io, idx)) + } else { + Err(EINVAL) + } } - #[inline] + /// Read the array register at index `idx` in `io` and run `f` on its value to obtain a + /// new value to write back. + /// + /// The validity of `idx` is checked at run-time, and `EINVAL` is returned is the + /// access was out-of-bounds. + #[inline(always)] pub(crate) fn try_alter<const SIZE: usize, T, F>( io: &T, - base: usize, + idx: usize, + f: F, + ) -> ::kernel::error::Result where + T: ::core::ops::Deref<Target = ::kernel::io::Io<SIZE>>, + F: ::core::ops::FnOnce(Self) -> Self, + { + if idx < Self::SIZE { + Ok(Self::alter(io, idx, f)) + } else { + Err(EINVAL) + } + } + } + }; + + // Generates the IO accessors for an array of relative registers. + ( + @io_relative_array $name:ident @ $base:ty + [ $offset:literal [ $size:expr ; $stride:expr ] ] + ) => { + #[allow(dead_code)] + impl $name { + pub(crate) const OFFSET: usize = $offset; + pub(crate) const SIZE: usize = $size; + pub(crate) const STRIDE: usize = $stride; + + /// Read the array register at index `idx` from `io`, using the base address provided + /// by `base` and adding the register's offset to it. + #[inline(always)] + pub(crate) fn read<const SIZE: usize, T, B>( + io: &T, + #[allow(unused_variables)] + base: &B, + idx: usize, + ) -> Self where + T: ::core::ops::Deref<Target = ::kernel::io::Io<SIZE>>, + B: crate::regs::macros::RegisterBase<$base>, + { + build_assert!(idx < Self::SIZE); + + let offset = <B as crate::regs::macros::RegisterBase<$base>>::BASE + + Self::OFFSET + (idx * Self::STRIDE); + let value = io.read32(offset); + + Self(value) + } + + /// Write the value contained in `self` to `io`, using the base address provided by + /// `base` and adding the offset of array register `idx` to it. + #[inline(always)] + pub(crate) fn write<const SIZE: usize, T, B>( + self, + io: &T, + #[allow(unused_variables)] + base: &B, + idx: usize + ) where + T: ::core::ops::Deref<Target = ::kernel::io::Io<SIZE>>, + B: crate::regs::macros::RegisterBase<$base>, + { + build_assert!(idx < Self::SIZE); + + let offset = <B as crate::regs::macros::RegisterBase<$base>>::BASE + + Self::OFFSET + (idx * Self::STRIDE); + + io.write32(self.0, offset); + } + + /// Read the array register at index `idx` from `io`, using the base address provided + /// by `base` and adding the register's offset to it, then run `f` on its value to + /// obtain a new value to write back. + #[inline(always)] + pub(crate) fn alter<const SIZE: usize, T, B, F>( + io: &T, + base: &B, + idx: usize, + f: F, + ) where + T: ::core::ops::Deref<Target = ::kernel::io::Io<SIZE>>, + B: crate::regs::macros::RegisterBase<$base>, + F: ::core::ops::FnOnce(Self) -> Self, + { + let reg = f(Self::read(io, base, idx)); + reg.write(io, base, idx); + } + + /// Read the array register at index `idx` from `io`, using the base address provided + /// by `base` and adding the register's offset to it. + /// + /// The validity of `idx` is checked at run-time, and `EINVAL` is returned is the + /// access was out-of-bounds. + #[inline(always)] + pub(crate) fn try_read<const SIZE: usize, T, B>( + io: &T, + base: &B, + idx: usize, + ) -> ::kernel::error::Result<Self> where + T: ::core::ops::Deref<Target = ::kernel::io::Io<SIZE>>, + B: crate::regs::macros::RegisterBase<$base>, + { + if idx < Self::SIZE { + Ok(Self::read(io, base, idx)) + } else { + Err(EINVAL) + } + } + + /// Write the value contained in `self` to `io`, using the base address provided by + /// `base` and adding the offset of array register `idx` to it. + /// + /// The validity of `idx` is checked at run-time, and `EINVAL` is returned is the + /// access was out-of-bounds. + #[inline(always)] + pub(crate) fn try_write<const SIZE: usize, T, B>( + self, + io: &T, + base: &B, + idx: usize, + ) -> ::kernel::error::Result where + T: ::core::ops::Deref<Target = ::kernel::io::Io<SIZE>>, + B: crate::regs::macros::RegisterBase<$base>, + { + if idx < Self::SIZE { + Ok(self.write(io, base, idx)) + } else { + Err(EINVAL) + } + } + + /// Read the array register at index `idx` from `io`, using the base address provided + /// by `base` and adding the register's offset to it, then run `f` on its value to + /// obtain a new value to write back. + /// + /// The validity of `idx` is checked at run-time, and `EINVAL` is returned is the + /// access was out-of-bounds. + #[inline(always)] + pub(crate) fn try_alter<const SIZE: usize, T, B, F>( + io: &T, + base: &B, + idx: usize, f: F, - ) -> ::kernel::error::Result<()> where + ) -> ::kernel::error::Result where T: ::core::ops::Deref<Target = ::kernel::io::Io<SIZE>>, + B: crate::regs::macros::RegisterBase<$base>, F: ::core::ops::FnOnce(Self) -> Self, { - let reg = f(Self::try_read(io, base)?); - reg.try_write(io, base) + if idx < Self::SIZE { + Ok(Self::alter(io, base, idx, f)) + } else { + Err(EINVAL) + } } } }; diff --git a/drivers/gpu/nova-core/util.rs b/drivers/gpu/nova-core/util.rs index 76cedf3710d7..bf35f00cb732 100644 --- a/drivers/gpu/nova-core/util.rs +++ b/drivers/gpu/nova-core/util.rs @@ -3,26 +3,6 @@ use kernel::prelude::*; use kernel::time::{Delta, Instant, Monotonic}; -pub(crate) const fn to_lowercase_bytes<const N: usize>(s: &str) -> [u8; N] { - let src = s.as_bytes(); - let mut dst = [0; N]; - let mut i = 0; - - while i < src.len() && i < N { - dst[i] = (src[i] as char).to_ascii_lowercase() as u8; - i += 1; - } - - dst -} - -pub(crate) const fn const_bytes_to_str(bytes: &[u8]) -> &str { - match core::str::from_utf8(bytes) { - Ok(string) => string, - Err(_) => kernel::build_error!("Bytes are not valid UTF-8."), - } -} - /// Wait until `cond` is true or `timeout` elapsed. /// /// When `cond` evaluates to `Some`, its return value is returned. diff --git a/drivers/gpu/nova-core/vbios.rs b/drivers/gpu/nova-core/vbios.rs index 5b5d9f38cbb3..e6a060714205 100644 --- a/drivers/gpu/nova-core/vbios.rs +++ b/drivers/gpu/nova-core/vbios.rs @@ -8,8 +8,8 @@ use crate::firmware::FalconUCodeDescV3; use core::convert::TryFrom; use kernel::device; use kernel::error::Result; -use kernel::pci; use kernel::prelude::*; +use kernel::types::ARef; /// The offset of the VBIOS ROM in the BAR0 space. const ROM_OFFSET: usize = 0x300000; @@ -31,7 +31,7 @@ const FALCON_UCODE_ENTRY_APPID_FWSEC_PROD: u8 = 0x85; /// Vbios Reader for constructing the VBIOS data. struct VbiosIterator<'a> { - pdev: &'a pci::Device, + dev: &'a device::Device, bar0: &'a Bar0, /// VBIOS data vector: As BIOS images are scanned, they are added to this vector for reference /// or copying into other data structures. It is the entire scanned contents of the VBIOS which @@ -46,9 +46,9 @@ struct VbiosIterator<'a> { } impl<'a> VbiosIterator<'a> { - fn new(pdev: &'a pci::Device, bar0: &'a Bar0) -> Result<Self> { + fn new(dev: &'a device::Device, bar0: &'a Bar0) -> Result<Self> { Ok(Self { - pdev, + dev, bar0, data: KVec::new(), current_offset: 0, @@ -64,7 +64,7 @@ impl<'a> VbiosIterator<'a> { // Ensure length is a multiple of 4 for 32-bit reads if len % core::mem::size_of::<u32>() != 0 { dev_err!( - self.pdev.as_ref(), + self.dev, "VBIOS read length {} is not a multiple of 4\n", len ); @@ -89,7 +89,7 @@ impl<'a> VbiosIterator<'a> { /// Read bytes at a specific offset, filling any gap. fn read_more_at_offset(&mut self, offset: usize, len: usize) -> Result { if offset > BIOS_MAX_SCAN_LEN { - dev_err!(self.pdev.as_ref(), "Error: exceeded BIOS scan limit.\n"); + dev_err!(self.dev, "Error: exceeded BIOS scan limit.\n"); return Err(EINVAL); } @@ -115,7 +115,7 @@ impl<'a> VbiosIterator<'a> { if offset + len > data_len { self.read_more_at_offset(offset, len).inspect_err(|e| { dev_err!( - self.pdev.as_ref(), + self.dev, "Failed to read more at offset {:#x}: {:?}\n", offset, e @@ -123,9 +123,9 @@ impl<'a> VbiosIterator<'a> { })?; } - BiosImage::new(self.pdev, &self.data[offset..offset + len]).inspect_err(|err| { + BiosImage::new(self.dev, &self.data[offset..offset + len]).inspect_err(|err| { dev_err!( - self.pdev.as_ref(), + self.dev, "Failed to {} at offset {:#x}: {:?}\n", context, offset, @@ -146,10 +146,7 @@ impl<'a> Iterator for VbiosIterator<'a> { } if self.current_offset > BIOS_MAX_SCAN_LEN { - dev_err!( - self.pdev.as_ref(), - "Error: exceeded BIOS scan limit, stopping scan\n" - ); + dev_err!(self.dev, "Error: exceeded BIOS scan limit, stopping scan\n"); return None; } @@ -192,18 +189,18 @@ impl Vbios { /// Probe for VBIOS extraction. /// /// Once the VBIOS object is built, `bar0` is not read for [`Vbios`] purposes anymore. - pub(crate) fn new(pdev: &pci::Device, bar0: &Bar0) -> Result<Vbios> { + pub(crate) fn new(dev: &device::Device, bar0: &Bar0) -> Result<Vbios> { // Images to extract from iteration let mut pci_at_image: Option<PciAtBiosImage> = None; let mut first_fwsec_image: Option<FwSecBiosBuilder> = None; let mut second_fwsec_image: Option<FwSecBiosBuilder> = None; // Parse all VBIOS images in the ROM - for image_result in VbiosIterator::new(pdev, bar0)? { + for image_result in VbiosIterator::new(dev, bar0)? { let full_image = image_result?; dev_dbg!( - pdev.as_ref(), + dev, "Found BIOS image: size: {:#x}, type: {}, last: {}\n", full_image.image_size_bytes(), full_image.image_type_str(), @@ -234,14 +231,14 @@ impl Vbios { (second_fwsec_image, first_fwsec_image, pci_at_image) { second - .setup_falcon_data(pdev, &pci_at, &first) - .inspect_err(|e| dev_err!(pdev.as_ref(), "Falcon data setup failed: {:?}\n", e))?; + .setup_falcon_data(&pci_at, &first) + .inspect_err(|e| dev_err!(dev, "Falcon data setup failed: {:?}\n", e))?; Ok(Vbios { - fwsec_image: second.build(pdev)?, + fwsec_image: second.build()?, }) } else { dev_err!( - pdev.as_ref(), + dev, "Missing required images for falcon data setup, skipping\n" ); Err(EINVAL) @@ -284,9 +281,9 @@ struct PcirStruct { } impl PcirStruct { - fn new(pdev: &pci::Device, data: &[u8]) -> Result<Self> { + fn new(dev: &device::Device, data: &[u8]) -> Result<Self> { if data.len() < core::mem::size_of::<PcirStruct>() { - dev_err!(pdev.as_ref(), "Not enough data for PcirStruct\n"); + dev_err!(dev, "Not enough data for PcirStruct\n"); return Err(EINVAL); } @@ -295,11 +292,7 @@ impl PcirStruct { // Signature should be "PCIR" (0x52494350) or "NPDS" (0x5344504e). if &signature != b"PCIR" && &signature != b"NPDS" { - dev_err!( - pdev.as_ref(), - "Invalid signature for PcirStruct: {:?}\n", - signature - ); + dev_err!(dev, "Invalid signature for PcirStruct: {:?}\n", signature); return Err(EINVAL); } @@ -308,7 +301,7 @@ impl PcirStruct { let image_len = u16::from_le_bytes([data[16], data[17]]); if image_len == 0 { - dev_err!(pdev.as_ref(), "Invalid image length: 0\n"); + dev_err!(dev, "Invalid image length: 0\n"); return Err(EINVAL); } @@ -345,7 +338,7 @@ impl PcirStruct { /// its header) is in the [`PciAtBiosImage`] and the falcon data it is pointing to is in the /// [`FwSecBiosImage`]. #[derive(Debug, Clone, Copy)] -#[expect(dead_code)] +#[repr(C)] struct BitHeader { /// 0h: BIT Header Identifier (BMP=0x7FFF/BIT=0xB8FF) id: u16, @@ -365,7 +358,7 @@ struct BitHeader { impl BitHeader { fn new(data: &[u8]) -> Result<Self> { - if data.len() < 12 { + if data.len() < core::mem::size_of::<Self>() { return Err(EINVAL); } @@ -467,7 +460,7 @@ struct PciRomHeader { } impl PciRomHeader { - fn new(pdev: &pci::Device, data: &[u8]) -> Result<Self> { + fn new(dev: &device::Device, data: &[u8]) -> Result<Self> { if data.len() < 26 { // Need at least 26 bytes to read pciDataStrucPtr and sizeOfBlock. return Err(EINVAL); @@ -479,7 +472,7 @@ impl PciRomHeader { match signature { 0xAA55 | 0xBB77 | 0x4E56 => {} _ => { - dev_err!(pdev.as_ref(), "ROM signature unknown {:#x}\n", signature); + dev_err!(dev, "ROM signature unknown {:#x}\n", signature); return Err(EINVAL); } } @@ -538,9 +531,9 @@ struct NpdeStruct { } impl NpdeStruct { - fn new(pdev: &pci::Device, data: &[u8]) -> Option<Self> { + fn new(dev: &device::Device, data: &[u8]) -> Option<Self> { if data.len() < core::mem::size_of::<Self>() { - dev_dbg!(pdev.as_ref(), "Not enough data for NpdeStruct\n"); + dev_dbg!(dev, "Not enough data for NpdeStruct\n"); return None; } @@ -549,17 +542,13 @@ impl NpdeStruct { // Signature should be "NPDE" (0x4544504E). if &signature != b"NPDE" { - dev_dbg!( - pdev.as_ref(), - "Invalid signature for NpdeStruct: {:?}\n", - signature - ); + dev_dbg!(dev, "Invalid signature for NpdeStruct: {:?}\n", signature); return None; } let subimage_len = u16::from_le_bytes([data[8], data[9]]); if subimage_len == 0 { - dev_dbg!(pdev.as_ref(), "Invalid subimage length: 0\n"); + dev_dbg!(dev, "Invalid subimage length: 0\n"); return None; } @@ -584,7 +573,7 @@ impl NpdeStruct { /// Try to find NPDE in the data, the NPDE is right after the PCIR. fn find_in_data( - pdev: &pci::Device, + dev: &device::Device, data: &[u8], rom_header: &PciRomHeader, pcir: &PcirStruct, @@ -596,12 +585,12 @@ impl NpdeStruct { // Check if we have enough data if npde_start + core::mem::size_of::<Self>() > data.len() { - dev_dbg!(pdev.as_ref(), "Not enough data for NPDE\n"); + dev_dbg!(dev, "Not enough data for NPDE\n"); return None; } // Try to create NPDE from the data - NpdeStruct::new(pdev, &data[npde_start..]) + NpdeStruct::new(dev, &data[npde_start..]) } } @@ -669,10 +658,10 @@ impl BiosImage { /// Create a [`BiosImageBase`] from a byte slice and convert it to a [`BiosImage`] which /// triggers the constructor of the specific BiosImage enum variant. - fn new(pdev: &pci::Device, data: &[u8]) -> Result<Self> { - let base = BiosImageBase::new(pdev, data)?; + fn new(dev: &device::Device, data: &[u8]) -> Result<Self> { + let base = BiosImageBase::new(dev, data)?; let image = base.into_image().inspect_err(|e| { - dev_err!(pdev.as_ref(), "Failed to create BiosImage: {:?}\n", e); + dev_err!(dev, "Failed to create BiosImage: {:?}\n", e); })?; Ok(image) @@ -754,9 +743,10 @@ impl TryFrom<BiosImageBase> for BiosImage { /// /// Each BiosImage type has a BiosImageBase type along with other image-specific fields. Note that /// Rust favors composition of types over inheritance. -#[derive(Debug)] #[expect(dead_code)] struct BiosImageBase { + /// Used for logging. + dev: ARef<device::Device>, /// PCI ROM Expansion Header rom_header: PciRomHeader, /// PCI Data Structure @@ -773,16 +763,16 @@ impl BiosImageBase { } /// Creates a new BiosImageBase from raw byte data. - fn new(pdev: &pci::Device, data: &[u8]) -> Result<Self> { + fn new(dev: &device::Device, data: &[u8]) -> Result<Self> { // Ensure we have enough data for the ROM header. if data.len() < 26 { - dev_err!(pdev.as_ref(), "Not enough data for ROM header\n"); + dev_err!(dev, "Not enough data for ROM header\n"); return Err(EINVAL); } // Parse the ROM header. - let rom_header = PciRomHeader::new(pdev, &data[0..26]) - .inspect_err(|e| dev_err!(pdev.as_ref(), "Failed to create PciRomHeader: {:?}\n", e))?; + let rom_header = PciRomHeader::new(dev, &data[0..26]) + .inspect_err(|e| dev_err!(dev, "Failed to create PciRomHeader: {:?}\n", e))?; // Get the PCI Data Structure using the pointer from the ROM header. let pcir_offset = rom_header.pci_data_struct_offset as usize; @@ -791,28 +781,29 @@ impl BiosImageBase { .ok_or(EINVAL) .inspect_err(|_| { dev_err!( - pdev.as_ref(), + dev, "PCIR offset {:#x} out of bounds (data length: {})\n", pcir_offset, data.len() ); dev_err!( - pdev.as_ref(), + dev, "Consider reading more data for construction of BiosImage\n" ); })?; - let pcir = PcirStruct::new(pdev, pcir_data) - .inspect_err(|e| dev_err!(pdev.as_ref(), "Failed to create PcirStruct: {:?}\n", e))?; + let pcir = PcirStruct::new(dev, pcir_data) + .inspect_err(|e| dev_err!(dev, "Failed to create PcirStruct: {:?}\n", e))?; // Look for NPDE structure if this is not an NBSI image (type != 0x70). - let npde = NpdeStruct::find_in_data(pdev, data, &rom_header, &pcir); + let npde = NpdeStruct::find_in_data(dev, data, &rom_header, &pcir); // Create a copy of the data. let mut data_copy = KVec::new(); data_copy.extend_from_slice(data, GFP_KERNEL)?; Ok(BiosImageBase { + dev: dev.into(), rom_header, pcir, npde, @@ -848,7 +839,7 @@ impl PciAtBiosImage { /// /// This is just a 4 byte structure that contains a pointer to the Falcon data in the FWSEC /// image. - fn falcon_data_ptr(&self, pdev: &pci::Device) -> Result<u32> { + fn falcon_data_ptr(&self) -> Result<u32> { let token = self.get_bit_token(BIT_TOKEN_ID_FALCON_DATA)?; // Make sure we don't go out of bounds @@ -859,14 +850,14 @@ impl PciAtBiosImage { // read the 4 bytes at the offset specified in the token let offset = token.data_offset as usize; let bytes: [u8; 4] = self.base.data[offset..offset + 4].try_into().map_err(|_| { - dev_err!(pdev.as_ref(), "Failed to convert data slice to array"); + dev_err!(self.base.dev, "Failed to convert data slice to array"); EINVAL })?; let data_ptr = u32::from_le_bytes(bytes); if (data_ptr as usize) < self.base.data.len() { - dev_err!(pdev.as_ref(), "Falcon data pointer out of bounds\n"); + dev_err!(self.base.dev, "Falcon data pointer out of bounds\n"); return Err(EINVAL); } @@ -892,7 +883,7 @@ impl TryFrom<BiosImageBase> for PciAtBiosImage { /// The [`PmuLookupTableEntry`] structure is a single entry in the [`PmuLookupTable`]. /// /// See the [`PmuLookupTable`] description for more information. -#[expect(dead_code)] +#[repr(C, packed)] struct PmuLookupTableEntry { application_id: u8, target_id: u8, @@ -901,7 +892,7 @@ struct PmuLookupTableEntry { impl PmuLookupTableEntry { fn new(data: &[u8]) -> Result<Self> { - if data.len() < 6 { + if data.len() < core::mem::size_of::<Self>() { return Err(EINVAL); } @@ -928,7 +919,7 @@ struct PmuLookupTable { } impl PmuLookupTable { - fn new(pdev: &pci::Device, data: &[u8]) -> Result<Self> { + fn new(dev: &device::Device, data: &[u8]) -> Result<Self> { if data.len() < 4 { return Err(EINVAL); } @@ -940,10 +931,7 @@ impl PmuLookupTable { let required_bytes = header_len + (entry_count * entry_len); if data.len() < required_bytes { - dev_err!( - pdev.as_ref(), - "PmuLookupTable data length less than required\n" - ); + dev_err!(dev, "PmuLookupTable data length less than required\n"); return Err(EINVAL); } @@ -956,11 +944,7 @@ impl PmuLookupTable { // Debug logging of entries (dumps the table data to dmesg) for i in (header_len..required_bytes).step_by(entry_len) { - dev_dbg!( - pdev.as_ref(), - "PMU entry: {:02x?}\n", - &data[i..][..entry_len] - ); + dev_dbg!(dev, "PMU entry: {:02x?}\n", &data[i..][..entry_len]); } Ok(PmuLookupTable { @@ -997,11 +981,10 @@ impl PmuLookupTable { impl FwSecBiosBuilder { fn setup_falcon_data( &mut self, - pdev: &pci::Device, pci_at_image: &PciAtBiosImage, first_fwsec: &FwSecBiosBuilder, ) -> Result { - let mut offset = pci_at_image.falcon_data_ptr(pdev)? as usize; + let mut offset = pci_at_image.falcon_data_ptr()? as usize; let mut pmu_in_first_fwsec = false; // The falcon data pointer assumes that the PciAt and FWSEC images @@ -1024,10 +1007,15 @@ impl FwSecBiosBuilder { self.falcon_data_offset = Some(offset); if pmu_in_first_fwsec { - self.pmu_lookup_table = - Some(PmuLookupTable::new(pdev, &first_fwsec.base.data[offset..])?); + self.pmu_lookup_table = Some(PmuLookupTable::new( + &self.base.dev, + &first_fwsec.base.data[offset..], + )?); } else { - self.pmu_lookup_table = Some(PmuLookupTable::new(pdev, &self.base.data[offset..])?); + self.pmu_lookup_table = Some(PmuLookupTable::new( + &self.base.dev, + &self.base.data[offset..], + )?); } match self @@ -1040,7 +1028,7 @@ impl FwSecBiosBuilder { let mut ucode_offset = entry.data as usize; ucode_offset -= pci_at_image.base.data.len(); if ucode_offset < first_fwsec.base.data.len() { - dev_err!(pdev.as_ref(), "Falcon Ucode offset not in second Fwsec.\n"); + dev_err!(self.base.dev, "Falcon Ucode offset not in second Fwsec.\n"); return Err(EINVAL); } ucode_offset -= first_fwsec.base.data.len(); @@ -1048,7 +1036,7 @@ impl FwSecBiosBuilder { } Err(e) => { dev_err!( - pdev.as_ref(), + self.base.dev, "PmuLookupTableEntry not found, error: {:?}\n", e ); @@ -1059,7 +1047,7 @@ impl FwSecBiosBuilder { } /// Build the final FwSecBiosImage from this builder - fn build(self, pdev: &pci::Device) -> Result<FwSecBiosImage> { + fn build(self) -> Result<FwSecBiosImage> { let ret = FwSecBiosImage { base: self.base, falcon_ucode_offset: self.falcon_ucode_offset.ok_or(EINVAL)?, @@ -1067,8 +1055,8 @@ impl FwSecBiosBuilder { if cfg!(debug_assertions) { // Print the desc header for debugging - let desc = ret.header(pdev.as_ref())?; - dev_dbg!(pdev.as_ref(), "PmuLookupTableEntry desc: {:#?}\n", desc); + let desc = ret.header()?; + dev_dbg!(ret.base.dev, "PmuLookupTableEntry desc: {:#?}\n", desc); } Ok(ret) @@ -1077,13 +1065,16 @@ impl FwSecBiosBuilder { impl FwSecBiosImage { /// Get the FwSec header ([`FalconUCodeDescV3`]). - pub(crate) fn header(&self, dev: &device::Device) -> Result<&FalconUCodeDescV3> { + pub(crate) fn header(&self) -> Result<&FalconUCodeDescV3> { // Get the falcon ucode offset that was found in setup_falcon_data. let falcon_ucode_offset = self.falcon_ucode_offset; // Make sure the offset is within the data bounds. if falcon_ucode_offset + core::mem::size_of::<FalconUCodeDescV3>() > self.base.data.len() { - dev_err!(dev, "fwsec-frts header not contained within BIOS bounds\n"); + dev_err!( + self.base.dev, + "fwsec-frts header not contained within BIOS bounds\n" + ); return Err(ERANGE); } @@ -1095,7 +1086,7 @@ impl FwSecBiosImage { let ver = (hdr & 0xff00) >> 8; if ver != 3 { - dev_err!(dev, "invalid fwsec firmware version: {:?}\n", ver); + dev_err!(self.base.dev, "invalid fwsec firmware version: {:?}\n", ver); return Err(EINVAL); } @@ -1115,7 +1106,7 @@ impl FwSecBiosImage { } /// Get the ucode data as a byte slice - pub(crate) fn ucode(&self, dev: &device::Device, desc: &FalconUCodeDescV3) -> Result<&[u8]> { + pub(crate) fn ucode(&self, desc: &FalconUCodeDescV3) -> Result<&[u8]> { let falcon_ucode_offset = self.falcon_ucode_offset; // The ucode data follows the descriptor. @@ -1127,15 +1118,16 @@ impl FwSecBiosImage { .data .get(ucode_data_offset..ucode_data_offset + size) .ok_or(ERANGE) - .inspect_err(|_| dev_err!(dev, "fwsec ucode data not contained within BIOS bounds\n")) + .inspect_err(|_| { + dev_err!( + self.base.dev, + "fwsec ucode data not contained within BIOS bounds\n" + ) + }) } /// Get the signatures as a byte slice - pub(crate) fn sigs( - &self, - dev: &device::Device, - desc: &FalconUCodeDescV3, - ) -> Result<&[Bcrt30Rsa3kSignature]> { + pub(crate) fn sigs(&self, desc: &FalconUCodeDescV3) -> Result<&[Bcrt30Rsa3kSignature]> { // The signatures data follows the descriptor. let sigs_data_offset = self.falcon_ucode_offset + core::mem::size_of::<FalconUCodeDescV3>(); let sigs_size = @@ -1144,7 +1136,7 @@ impl FwSecBiosImage { // Make sure the data is within bounds. if sigs_data_offset + sigs_size > self.base.data.len() { dev_err!( - dev, + self.base.dev, "fwsec signatures data not contained within BIOS bounds\n" ); return Err(ERANGE); |