drm/amdgpu: fix task hang from failed job submission during process kill

During process kill, drm_sched_entity_flush() will kill the vm
entities. The following job submissions of this process will fail, and
the resources of these jobs have not been released, nor have the fences
been signalled, causing tasks to hang and timeout.

Fix by check entity status in amdgpu_vm_ready() and avoid submit jobs to
stopped entity.

v2: add amdgpu_vm_ready() check before amdgpu_vm_clear_freed() in
function amdgpu_cs_vm_handling().

Fixes: 1f02f2044b ("drm/amdgpu: Avoid extra evict-restore process.")
Signed-off-by: Liu01 Tong <Tong.Liu01@amd.com>
Signed-off-by: Lin.Cao <lincao12@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit f101c13a87)
This commit is contained in:
Liu01 Tong 2025-08-11 14:52:37 +08:00 committed by Alex Deucher
parent 040bc6d0e0
commit aa5fc4362f
2 changed files with 14 additions and 4 deletions

View File

@ -1139,6 +1139,9 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
}
}
if (!amdgpu_vm_ready(vm))
return -EINVAL;
r = amdgpu_vm_clear_freed(adev, vm, NULL);
if (r)
return r;

View File

@ -654,11 +654,10 @@ int amdgpu_vm_validate(struct amdgpu_device *adev, struct amdgpu_vm *vm,
* Check if all VM PDs/PTs are ready for updates
*
* Returns:
* True if VM is not evicting.
* True if VM is not evicting and all VM entities are not stopped
*/
bool amdgpu_vm_ready(struct amdgpu_vm *vm)
{
bool empty;
bool ret;
amdgpu_vm_eviction_lock(vm);
@ -666,10 +665,18 @@ bool amdgpu_vm_ready(struct amdgpu_vm *vm)
amdgpu_vm_eviction_unlock(vm);
spin_lock(&vm->status_lock);
empty = list_empty(&vm->evicted);
ret &= list_empty(&vm->evicted);
spin_unlock(&vm->status_lock);
return ret && empty;
spin_lock(&vm->immediate.lock);
ret &= !vm->immediate.stopped;
spin_unlock(&vm->immediate.lock);
spin_lock(&vm->delayed.lock);
ret &= !vm->delayed.stopped;
spin_unlock(&vm->delayed.lock);
return ret;
}
/**