Commit 306eca05 authored by Dave Airlie's avatar Dave Airlie
Browse files

Merge tag 'amd-drm-fixes-6.9-2024-05-01' of... 

Merge tag 'amd-drm-fixes-6.9-2024-05-01' of https://gitlab.freedesktop.org/agd5f/linux

 into drm-fixes

amd-drm-fixes-6.9-2024-05-01:

amdgpu:
- Fix VRAM memory accounting
- DCN 3.1 fixes
- DCN 2.0 fix
- DCN 3.1.5 fix
- DCN 3.5 fix
- DCN 3.2.1 fix
- DP fixes
- Seamless boot fix
- Fix call order in amdgpu_ttm_move()
- Fix doorbell regression
- Disable panel replay temporarily

amdkfd:
- Flush wq before creating kfd process

Signed-off-by: default avatarDave Airlie <airlied@redhat.com>

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240501135054.1919108-1-alexander.deucher@amd.com
parents e67572cd ab72d594

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c

+1 −1
Original line number Diff line number Diff line
@@ -220,7 +220,7 @@ int amdgpu_amdkfd_reserve_mem_limit(struct amdgpu_device *adev, 
	    (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)) {

	     vram_size - reserved_for_pt - atomic64_read(&adev->vram_pin_size))) {

		ret = -ENOMEM;

		goto release;

	}

drivers/gpu/drm/amd/amdgpu/amdgpu_object.c

+9 −5
Original line number Diff line number Diff line
@@ -1243,14 +1243,18 @@ int amdgpu_bo_get_metadata(struct amdgpu_bo *bo, void *buffer, 
 * amdgpu_bo_move_notify - notification about a memory move

 * @bo: pointer to a buffer object

 * @evict: if this move is evicting the buffer from the graphics address space

 * @new_mem: new resource for backing the BO

 *

 * Marks the corresponding &amdgpu_bo buffer object as invalid, also performs

 * bookkeeping.

 * TTM driver callback which is called when ttm moves a buffer.

 */

void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, bool evict)

void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,

			   bool evict,

			   struct ttm_resource *new_mem)

{

	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev);

	struct ttm_resource *old_mem = bo->resource;

	struct amdgpu_bo *abo;



	if (!amdgpu_bo_is_amdgpu_bo(bo))
@@ -1262,12 +1266,12 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, bool evict) 
	amdgpu_bo_kunmap(abo);



	if (abo->tbo.base.dma_buf && !abo->tbo.base.import_attach &&

	    bo->resource->mem_type != TTM_PL_SYSTEM)

	    old_mem && old_mem->mem_type != TTM_PL_SYSTEM)

		dma_buf_move_notify(abo->tbo.base.dma_buf);



	/* remember the eviction */

	if (evict)

		atomic64_inc(&adev->num_evictions);

	/* move_notify is called before move happens */

	trace_amdgpu_bo_move(abo, new_mem ? new_mem->mem_type : -1,

			     old_mem ? old_mem->mem_type : -1);

}



void amdgpu_bo_get_memory(struct amdgpu_bo *bo,

drivers/gpu/drm/amd/amdgpu/amdgpu_object.h

+3 −1
Original line number Diff line number Diff line
@@ -328,7 +328,9 @@ int amdgpu_bo_set_metadata (struct amdgpu_bo *bo, void *metadata, 
int amdgpu_bo_get_metadata(struct amdgpu_bo *bo, void *buffer,

			   size_t buffer_size, uint32_t *metadata_size,

			   uint64_t *flags);

void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, bool evict);

void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,

			   bool evict,

			   struct ttm_resource *new_mem);

void amdgpu_bo_release_notify(struct ttm_buffer_object *bo);

vm_fault_t amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo);

void amdgpu_bo_fence(struct amdgpu_bo *bo, struct dma_fence *fence,

drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c

+27 −23
Original line number Diff line number Diff line
@@ -419,7 +419,7 @@ 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_PREEMPT || res->mem_type == AMDGPU_PL_DOORBELL)

		return true;



	if (res->mem_type != TTM_PL_VRAM)
@@ -481,14 +481,16 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict, 


	if (!old_mem || (old_mem->mem_type == TTM_PL_SYSTEM &&

			 bo->ttm == NULL)) {

		amdgpu_bo_move_notify(bo, evict, new_mem);

		ttm_bo_move_null(bo, new_mem);

		goto out;

		return 0;

	}

	if (old_mem->mem_type == TTM_PL_SYSTEM &&

	    (new_mem->mem_type == TTM_PL_TT ||

	     new_mem->mem_type == AMDGPU_PL_PREEMPT)) {

		amdgpu_bo_move_notify(bo, evict, new_mem);

		ttm_bo_move_null(bo, new_mem);

		goto out;

		return 0;

	}

	if ((old_mem->mem_type == TTM_PL_TT ||

	     old_mem->mem_type == AMDGPU_PL_PREEMPT) &&
@@ -498,9 +500,10 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict, 
			return r;



		amdgpu_ttm_backend_unbind(bo->bdev, bo->ttm);

		amdgpu_bo_move_notify(bo, evict, new_mem);

		ttm_resource_free(bo, &bo->resource);

		ttm_bo_assign_mem(bo, new_mem);

		goto out;

		return 0;

	}



	if (old_mem->mem_type == AMDGPU_PL_GDS ||
@@ -512,8 +515,9 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict, 
	    new_mem->mem_type == AMDGPU_PL_OA ||

	    new_mem->mem_type == AMDGPU_PL_DOORBELL) {

		/* Nothing to save here */

		amdgpu_bo_move_notify(bo, evict, new_mem);

		ttm_bo_move_null(bo, new_mem);

		goto out;

		return 0;

	}



	if (bo->type == ttm_bo_type_device &&
@@ -525,8 +529,8 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict, 
		abo->flags &= ~AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;

	}



	if (adev->mman.buffer_funcs_enabled) {

		if (((old_mem->mem_type == TTM_PL_SYSTEM &&

	if (adev->mman.buffer_funcs_enabled &&

	    ((old_mem->mem_type == TTM_PL_SYSTEM &&

	      new_mem->mem_type == TTM_PL_VRAM) ||

	     (old_mem->mem_type == TTM_PL_VRAM &&

	      new_mem->mem_type == TTM_PL_SYSTEM))) {
@@ -537,10 +541,11 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict, 
		return -EMULTIHOP;

	}



	amdgpu_bo_move_notify(bo, evict, new_mem);

	if (adev->mman.buffer_funcs_enabled)

		r = amdgpu_move_blit(bo, evict, new_mem, old_mem);

	} else {

	else

		r = -ENODEV;

	}



	if (r) {

		/* Check that all memory is CPU accessible */
@@ -555,11 +560,10 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict, 
			return r;

	}



	trace_amdgpu_bo_move(abo, new_mem->mem_type, old_mem->mem_type);

out:

	/* update statistics */

	/* update statistics after the move */

	if (evict)

		atomic64_inc(&adev->num_evictions);

	atomic64_add(bo->base.size, &adev->num_bytes_moved);

	amdgpu_bo_move_notify(bo, evict);

	return 0;

}
@@ -1559,7 +1563,7 @@ static int amdgpu_ttm_access_memory(struct ttm_buffer_object *bo, 
static void

amdgpu_bo_delete_mem_notify(struct ttm_buffer_object *bo)

{

	amdgpu_bo_move_notify(bo, false);

	amdgpu_bo_move_notify(bo, false, NULL);

}



static struct ttm_device_funcs amdgpu_bo_driver = {

drivers/gpu/drm/amd/amdkfd/kfd_process.c

+8 −0
Original line number Diff line number Diff line
@@ -829,6 +829,14 @@ struct kfd_process *kfd_create_process(struct task_struct *thread) 
	if (process) {

		pr_debug("Process already found\n");

	} else {

		/* If the process just called exec(3), it is possible that the

		 * cleanup of the kfd_process (following the release of the mm

		 * of the old process image) is still in the cleanup work queue.

		 * Make sure to drain any job before trying to recreate any

		 * resource for this process.

		 */

		flush_workqueue(kfd_process_wq);



		process = create_process(thread);

		if (IS_ERR(process))

			goto out;