mirrors/linux
2
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2026-08-31 07:03:28 -04:00
Code Issues Packages Projects Releases Wiki Activity

drm/amdgpu: skip BOs being torn down during GTT recovery

Browse Source 
A GPU reset can race with BO teardown after the BO's GTT resource has
been marked for deletion but before its drm_mm node is removed. In this
window, amdgpu_gtt_mgr_recover() can treat the node as a live BO and try
to restore its GART mapping while its TT backing is being destroyed.

Recolor the GTT node from amdgpu_bo_delete_mem_notify() so that recovery
skips it, reusing the existing color for ranges without a BO. The range
stays allocated until the resource is freed.

This prevents reset recovery from accessing a BO whose backing storage
is no longer valid.

v2: refine commit message. (David Francis)
v3: Remove new BO color. (Christian)

Signed-off-by: Yifan Zhang <yifan1.zhang@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Perry Yuan <perry.yuan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Yifan Zhang
2026-07-23 13:11:14 +08:00
committed by Alex Deucher
parent a4b0720e4f
commit 24775b2e8b
3 changed files with 27 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
View File

@@ -102,6 +102,29 @@ bool amdgpu_gtt_mgr_has_gart_addr(struct ttm_resource *res)
return drm_mm_node_allocated(&node->mm_nodes[0]);
}
/**
* amdgpu_gtt_mgr_mark_bo_teardown - exclude a BO from GART recovery
*
* @tbo: TTM BO whose TT backing is about to be destroyed
*
* Keep the GART range allocated until the resource is freed, but make recovery
* treat it like a range without a BO so it isn't touched after TT teardown has
* started.
*/
void amdgpu_gtt_mgr_mark_bo_teardown(struct ttm_buffer_object *tbo)
{
struct amdgpu_device *adev = amdgpu_ttm_adev(tbo->bdev);
struct ttm_range_mgr_node *node = to_ttm_range_mgr_node(tbo->resource);
struct amdgpu_gtt_mgr *mgr = &adev->mman.gtt_mgr;
dma_resv_assert_held(tbo->base.resv);
spin_lock(&mgr->lock);
if (drm_mm_node_allocated(&node->mm_nodes[0]))
node->mm_nodes[0].color = GART_ENTRY_WITHOUT_BO_COLOR;
spin_unlock(&mgr->lock);
}
/**
* amdgpu_gtt_mgr_new - allocate a new node
*

3
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
View File

@@ -1694,6 +1694,9 @@ static int amdgpu_ttm_access_memory(struct ttm_buffer_object *bo,
static void
amdgpu_bo_delete_mem_notify(struct ttm_buffer_object *bo)
{
if (bo->resource && bo->resource->mem_type == TTM_PL_TT)
amdgpu_gtt_mgr_mark_bo_teardown(bo);
amdgpu_bo_move_notify(bo, false, NULL);
}

1
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
View File

@@ -145,6 +145,7 @@ int amdgpu_vram_mgr_init(struct amdgpu_device *adev);
void amdgpu_vram_mgr_fini(struct amdgpu_device *adev);
bool amdgpu_gtt_mgr_has_gart_addr(struct ttm_resource *mem);
void amdgpu_gtt_mgr_mark_bo_teardown(struct ttm_buffer_object *tbo);
void amdgpu_gtt_mgr_recover(struct amdgpu_gtt_mgr *mgr);
int amdgpu_gtt_mgr_alloc_entries(struct amdgpu_gtt_mgr *mgr,