[PATCH v2] drm/amdgpu: fix task hang from failed job submission during process kill

[PATCH v2] drm/amdgpu: fix task hang from failed job submission during process kill

[Liu01 Tong]

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().

Signed-off-by: Liu01 Tong <Tong.Liu01@amd.com>
Signed-off-by: Lin.Cao <lincao12@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c |  3 +++
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 15 +++++++++++----
 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 e1e48e6f1f35..cdc02860011c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -1138,6 +1138,9 @@ 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 283dd44f04b0..bf42246a3db2 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;
 }
 
 /**
-- 
2.34.1

Re: [PATCH v2] drm/amdgpu: fix task hang from failed job submission during process kill

[Christian König]

On 12.08.25 10:31, Liu01 Tong wrote:
> 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().
> 
> 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>

> ---
>  drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c |  3 +++
>  drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 15 +++++++++++----
>  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 e1e48e6f1f35..cdc02860011c 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
> @@ -1138,6 +1138,9 @@ 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 283dd44f04b0..bf42246a3db2 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;
>  }
>  
>  /**

Re: [PATCH v2] drm/amdgpu: fix task hang from failed job submission during process kill

[Matthew Schwartz]

On 8/12/25 1:31 AM, Liu01 Tong wrote:
> 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().
> 
> Signed-off-by: Liu01 Tong <Tong.Liu01@amd.com>
> Signed-off-by: Lin.Cao <lincao12@amd.com>

Closes: https://lore.kernel.org/regressions/f2b70e6e-bff6-42f3-82a2-81eed892cc30@linux.dev/
Tested-by: Matthew Schwartz <matthew.schwartz@linux.dev>

Thanks,
Matt

> ---
>  drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c |  3 +++
>  drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 15 +++++++++++----
>  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 e1e48e6f1f35..cdc02860011c 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
> @@ -1138,6 +1138,9 @@ 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 283dd44f04b0..bf42246a3db2 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;
>  }
>  
>  /**