superrob1500
/
mirror-linux
mirror of https://github.com/torvalds/linux
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

drm/amdgpu/userq: remove the vital queue unmap logging 

Mesa userqueues free does not wait for the free to complete and go ahead
in unmapping the vital bos while kernel is still in queue free and
corresponding cleanup.

So ideally we don't need the logging for that and hence remove the warn
message as this is expected behaviour and functionally, we are making
sure to wait for the required fences before unmap.

Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 758a868043dcb07eca923bc451c16da3e73dc47c)
master
Sunil Khatri 2026-05-25 13:18:00 +05:30 committed by Alex Deucher
parent 352ea59028
commit 2a07f3fa49
3 changed files with 5 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
View File

@ -1344,8 +1344,7 @@ int amdgpu_userq_start_sched_for_enforce_isolation(struct amdgpu_device *adev,
}
void amdgpu_userq_gem_va_unmap_validate(struct amdgpu_device *adev,
struct amdgpu_bo_va_mapping *mapping,
uint64_t saddr)
struct amdgpu_bo_va_mapping *mapping)
{
u32 ip_mask = amdgpu_userq_get_supported_ip_mask(adev);
struct amdgpu_bo_va *bo_va = mapping->bo_va;
@ -1354,12 +1353,9 @@ void amdgpu_userq_gem_va_unmap_validate(struct amdgpu_device *adev,
if (!ip_mask)
return;
dev_warn_once(adev->dev, "now unmapping a vital queue va:%llx\n", saddr);
/**
* The userq VA mapping reservation should include the eviction fence,
* if the eviction fence can't signal successfully during unmapping,
* then driver will warn to flag this improper unmap of the userq VA.
* Note: The eviction fence may be attached to different BOs, and this
* The userq VA mapping reservation should include the eviction fence.
* Note: The eviction fence may be attached to different BOs and this
* unmap is only for one kind of userq VAs, so at this point suppose
* the eviction fence is always unsignaled.
*/

3
drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h
View File

@ -182,6 +182,5 @@ int amdgpu_userq_input_va_validate(struct amdgpu_device *adev,
u64 addr, u64 expected_size, u64 *va_out);
void amdgpu_userq_gem_va_unmap_validate(struct amdgpu_device *adev,
struct amdgpu_bo_va_mapping *mapping,
uint64_t saddr);
struct amdgpu_bo_va_mapping *mapping);
#endif

2
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
View File

@ -2006,7 +2006,7 @@ int amdgpu_vm_bo_unmap(struct amdgpu_device *adev,
* from user space.
*/
if (unlikely(bo_va->userq_va_mapped))
amdgpu_userq_gem_va_unmap_validate(adev, mapping, saddr);
amdgpu_userq_gem_va_unmap_validate(adev, mapping);
list_del(&mapping->list);
amdgpu_vm_it_remove(mapping, &vm->va);