summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorLiu01 Tong <Tong.Liu01@amd.com>2025-08-11 14:52:37 +0800
committerAlex Deucher <alexander.deucher@amd.com>2025-08-12 16:16:36 -0400
commitaa5fc4362fac9351557eb27c745579159a2e4520 (patch)
tree3dcd330e4601ece7821d6698e9bd9933fdf4247d
parent040bc6d0e0e9c814c9c663f6f1544ebaff6824a8 (diff)
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: 1f02f2044bda ("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 f101c13a8720c73e67f8f9d511fbbeda95bcedb1)
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c3
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c15
2 files changed, 14 insertions, 4 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index a2adaacf6adb..d3f220be2ef9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -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;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 5cacf5717016..0b87798daebd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -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;
}
/**