On 2024-06-04 21:33, Yunxiang Li wrote:
We need to take the reset domain lock before talking to MES. While in
this case we can take the lock inside the mes helper. We can't do so for
most other mes helpers since they are used during reset. So for
consistency sake we add the lock here.
Signed-off-by: Yunxiang Li <Yunxiang.Li@xxxxxxx>
Reviewed-by: Felix Kuehling <felix.kuehling@xxxxxxx>
---
drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c | 9 +++++++--
1 file changed, 7 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
index 86ea610b16f3..21f5a1fb3bf8 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -28,6 +28,7 @@
#include "kfd_priv.h"
#include "kfd_kernel_queue.h"
#include "amdgpu_amdkfd.h"
+#include "amdgpu_reset.h"
static inline struct process_queue_node *get_queue_by_qid(
struct process_queue_manager *pqm, unsigned int qid)
@@ -87,8 +88,12 @@ void kfd_process_dequeue_from_device(struct kfd_process_device *pdd)
return;
dev->dqm->ops.process_termination(dev->dqm, &pdd->qpd);
- if (dev->kfd->shared_resources.enable_mes)
- amdgpu_mes_flush_shader_debugger(dev->adev, pdd->proc_ctx_gpu_addr);
+ if (dev->kfd->shared_resources.enable_mes &&
+ down_read_trylock(&dev->adev->reset_domain->sem)) {
+ amdgpu_mes_flush_shader_debugger(dev->adev,
+ pdd->proc_ctx_gpu_addr);
+ up_read(&dev->adev->reset_domain->sem);
+ }
pdd->already_dequeued = true;
}
