The early commit b8adc31cc0ca ("drm/amdgpu: Avoid extra evict-restore
process.") changed amdgpu_vm_wait_idle to use drm_sched_entity_flush
instead of dma_resv_wait_timeout to avoid KFD eviction fence signaling.
But this introduce a race condition when processes are killed.
During process kill, drm_sched_entity_flush() will kill the vm entities.
Concurrent job submissions of this process will fail.
Fix by skipping vm entity flushing when the process is being killed.
Signed-off-by: Liu01 Tong <tong.li...@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 283dd44f04b0..ae43a378f866 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -2415,6 +2415,13 @@ void amdgpu_vm_adjust_size(struct amdgpu_device *adev,
uint32_t min_vm_size,
*/
long amdgpu_vm_wait_idle(struct amdgpu_vm *vm, long timeout)
{
+ /* If the process is being killed, skip flush VM entities
+ * as entities of concurrent job submission of this process
+ * might be in an inconsistent state
+ */
+ if (current->flags & PF_EXITING)
+ return timeout;
+
timeout = drm_sched_entity_flush(&vm->immediate, timeout);
if (timeout <= 0)
return timeout;
--
2.34.1
