diff options
| author | Dave Airlie <airlied@redhat.com> | 2023-06-15 14:11:22 +1000 |
|---|---|---|
| committer | Dave Airlie <airlied@redhat.com> | 2023-06-15 14:11:22 +1000 |
| commit | 901bdf5ea1a836400ee69aa32b04e9c209271ec7 (patch) | |
| tree | ccb1851c8a71e776dbccf1ccae132dc9b5f093c6 /drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | |
| parent | ba57b9b11f78530146f02b776854b2b6b6d344a4 (diff) | |
| parent | 3b718dcaf163d17fe907ea098c8449e0cd6bc271 (diff) | |
| download | lwn-901bdf5ea1a836400ee69aa32b04e9c209271ec7.tar.gz lwn-901bdf5ea1a836400ee69aa32b04e9c209271ec7.zip | |
Merge tag 'amd-drm-next-6.5-2023-06-09' of https://gitlab.freedesktop.org/agd5f/linux into drm-next
amd-drm-next-6.5-2023-06-02:
amdgpu:
- SR-IOV fixes
- Warning fixes
- Misc code cleanups and spelling fixes
- DCN 3.2 updates
- Improved DC FAMS support for better power management
- Improved DC SubVP support for better power management
- DCN 3.1.x fixes
- Max IB size query
- DC GPU reset fixes
- RAS updates
- DCN 3.0.x fixes
- S/G display fixes
- CP shadow buffer support
- Implement connector force callback
- Z8 power improvements
- PSP 13.0.10 vbflash support
- Mode2 reset fixes
- Store MQDs in VRAM to improve queue switch latency
- VCN 3.x fixes
- JPEG 3.x fixes
- Enable DC_FP on LoongArch
- GFXOFF fixes
- GC 9.4.3 partition support
- SDMA 4.4.2 partition support
- VCN/JPEG 4.0.3 partition support
- VCN 4.0.3 updates
- NBIO 7.9 updates
- GC 9.4.3 updates
- Take NUMA into account when allocating memory
- Handle NUMA for partitions
- SMU 13.0.6 updates
- GC 9.4.3 RAS updates
- Stop including unused swiotlb.h
- SMU 13.0.7 fixes
- Fix clock output ordering on some APUs
- Clean up DC FPGA code
- GFX9 preemption fixes
- Misc irq fixes
- S0ix fixes
- Add new DRM_AMDGPU_WERROR config parameter to help with CI
- PCIe fix for RDNA2
- kdoc fixes
- Documentation updates
amdkfd:
- Query TTM mem limit rather than hardcoding it
- GC 9.4.3 partition support
- Handle NUMA for partitions
radeon:
- Fix possible double free
- Stop including unused swiotlb.h
- Fix possible division by zero
ttm:
- Add query for TTM mem limit
- Add NUMA awareness to pools
- Export ttm_pool_fini()
UAPI:
- Add new ctx query flag to better handle GPU resets
Mesa MR: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22290
- Add new interface to query and set shadow buffer for RDNA3
Mesa MR: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21986
- Add new INFO query for max IB size
Proposed userspace: https://gitlab.freedesktop.org/bnieuwenhuizen/mesa/-/commits/ib-rejection-v3
amd-drm-next-6.5-2023-06-09:
amdgpu:
- S0ix fixes
- Initial SMU13 Overdrive support
- kdoc fixes
- Misc clode cleanups
- Flexible array fixes
- Display OTG fixes
- SMU 13.0.6 updates
- Revert some broken clock counter updates
- Misc display fixes
- GFX9 preemption fixes
- Add support for newer EEPROM bad page table format
- Add missing radeon secondary id
- Add support for new colorspace KMS API
- CSA fix
- Stable pstate fixes for APUs
- make vbl interface admin only
- Handle PCI accelerator class
amdkfd:
- Add debugger support for gdb
radeon:
- Fix possible UAF
drm:
- Add Colorspace functionality
UAPI:
- Add debugger interface for enabling gdb
Proposed userspace: https://github.com/ROCm-Developer-Tools/ROCdbgapi/tree/wip-dbgapi
- Add KMS colorspace API
Discussion: https://lists.freedesktop.org/archives/dri-devel/2023-June/408128.html
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230609174817.7764-1-alexander.deucher@amd.com
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_object.c')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 54 |
1 files changed, 34 insertions, 20 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 2bd1a54ee866..f76649e523a0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -79,9 +79,10 @@ static void amdgpu_bo_user_destroy(struct ttm_buffer_object *tbo) static void amdgpu_bo_vm_destroy(struct ttm_buffer_object *tbo) { struct amdgpu_device *adev = amdgpu_ttm_adev(tbo->bdev); - struct amdgpu_bo *bo = ttm_to_amdgpu_bo(tbo); + struct amdgpu_bo *shadow_bo = ttm_to_amdgpu_bo(tbo), *bo; struct amdgpu_bo_vm *vmbo; + bo = shadow_bo->parent; vmbo = to_amdgpu_bo_vm(bo); /* in case amdgpu_device_recover_vram got NULL of bo->parent */ if (!list_empty(&vmbo->shadow_list)) { @@ -130,15 +131,25 @@ void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain) u32 c = 0; if (domain & AMDGPU_GEM_DOMAIN_VRAM) { - unsigned visible_pfn = adev->gmc.visible_vram_size >> PAGE_SHIFT; - - places[c].fpfn = 0; - places[c].lpfn = 0; + unsigned int visible_pfn = adev->gmc.visible_vram_size >> PAGE_SHIFT; + int8_t mem_id = KFD_XCP_MEM_ID(adev, abo->xcp_id); + + if (adev->gmc.mem_partitions && mem_id >= 0) { + places[c].fpfn = adev->gmc.mem_partitions[mem_id].range.fpfn; + /* + * memory partition range lpfn is inclusive start + size - 1 + * TTM place lpfn is exclusive start + size + */ + places[c].lpfn = adev->gmc.mem_partitions[mem_id].range.lpfn + 1; + } else { + places[c].fpfn = 0; + places[c].lpfn = 0; + } places[c].mem_type = TTM_PL_VRAM; places[c].flags = 0; if (flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED) - places[c].lpfn = visible_pfn; + places[c].lpfn = min_not_zero(places[c].lpfn, visible_pfn); else if (adev->gmc.real_vram_size != adev->gmc.visible_vram_size) places[c].flags |= TTM_PL_FLAG_TOPDOWN; @@ -574,6 +585,13 @@ int amdgpu_bo_create(struct amdgpu_device *adev, bo->flags = bp->flags; + if (adev->gmc.mem_partitions) + /* For GPUs with spatial partitioning, bo->xcp_id=-1 means any partition */ + bo->xcp_id = bp->xcp_id_plus1 - 1; + else + /* For GPUs without spatial partitioning */ + bo->xcp_id = 0; + if (!amdgpu_bo_support_uswc(bo->flags)) bo->flags &= ~AMDGPU_GEM_CREATE_CPU_GTT_USWC; @@ -610,7 +628,7 @@ int amdgpu_bo_create(struct amdgpu_device *adev, bo->tbo.resource->mem_type == TTM_PL_VRAM) { struct dma_fence *fence; - r = amdgpu_fill_buffer(bo, 0, bo->tbo.base.resv, &fence); + r = amdgpu_fill_buffer(bo, 0, bo->tbo.base.resv, &fence, true); if (unlikely(r)) goto fail_unreserve; @@ -694,11 +712,6 @@ int amdgpu_bo_create_vm(struct amdgpu_device *adev, return r; *vmbo_ptr = to_amdgpu_bo_vm(bo_ptr); - INIT_LIST_HEAD(&(*vmbo_ptr)->shadow_list); - /* Set destroy callback to amdgpu_bo_vm_destroy after vmbo->shadow_list - * is initialized. - */ - bo_ptr->tbo.destroy = &amdgpu_bo_vm_destroy; return r; } @@ -715,6 +728,8 @@ void amdgpu_bo_add_to_shadow_list(struct amdgpu_bo_vm *vmbo) mutex_lock(&adev->shadow_list_lock); list_add_tail(&vmbo->shadow_list, &adev->shadow_list); + vmbo->shadow->parent = amdgpu_bo_ref(&vmbo->bo); + vmbo->shadow->tbo.destroy = &amdgpu_bo_vm_destroy; mutex_unlock(&adev->shadow_list_lock); } @@ -935,7 +950,7 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain, bo->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED; amdgpu_bo_placement_from_domain(bo, domain); for (i = 0; i < bo->placement.num_placement; i++) { - unsigned fpfn, lpfn; + unsigned int fpfn, lpfn; fpfn = min_offset >> PAGE_SHIFT; lpfn = max_offset >> PAGE_SHIFT; @@ -1016,7 +1031,7 @@ void amdgpu_bo_unpin(struct amdgpu_bo *bo) } } -static const char *amdgpu_vram_names[] = { +static const char * const amdgpu_vram_names[] = { "UNKNOWN", "GDDR1", "DDR2", @@ -1044,7 +1059,7 @@ static const char *amdgpu_vram_names[] = { int amdgpu_bo_init(struct amdgpu_device *adev) { /* On A+A platform, VRAM can be mapped as WB */ - if (!adev->gmc.xgmi.connected_to_cpu) { + if (!adev->gmc.xgmi.connected_to_cpu && !adev->gmc.is_app_apu) { /* reserve PAT memory space to WC for VRAM */ int r = arch_io_reserve_memtype_wc(adev->gmc.aper_base, adev->gmc.aper_size); @@ -1080,8 +1095,7 @@ void amdgpu_bo_fini(struct amdgpu_device *adev) amdgpu_ttm_fini(adev); if (drm_dev_enter(adev_to_drm(adev), &idx)) { - - if (!adev->gmc.xgmi.connected_to_cpu) { + if (!adev->gmc.xgmi.connected_to_cpu && !adev->gmc.is_app_apu) { arch_phys_wc_del(adev->gmc.vram_mtrr); arch_io_free_memtype_wc(adev->gmc.aper_base, adev->gmc.aper_size); } @@ -1148,8 +1162,8 @@ void amdgpu_bo_get_tiling_flags(struct amdgpu_bo *bo, u64 *tiling_flags) * Returns: * 0 for success or a negative error code on failure. */ -int amdgpu_bo_set_metadata (struct amdgpu_bo *bo, void *metadata, - uint32_t metadata_size, uint64_t flags) +int amdgpu_bo_set_metadata(struct amdgpu_bo *bo, void *metadata, + u32 metadata_size, uint64_t flags) { struct amdgpu_bo_user *ubo; void *buffer; @@ -1338,7 +1352,7 @@ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo) if (WARN_ON_ONCE(!dma_resv_trylock(bo->base.resv))) return; - r = amdgpu_fill_buffer(abo, AMDGPU_POISON, bo->base.resv, &fence); + r = amdgpu_fill_buffer(abo, AMDGPU_POISON, bo->base.resv, &fence, true); if (!WARN_ON(r)) { amdgpu_bo_fence(abo, fence, false); dma_fence_put(fence); |