To improve coverage also annotate the gpu reset code itself, since
that's called from other places than drm/scheduler (which is already
annotated). Annotations nests, so this doesn't break anything, and
allows easier testing.
Cc: linux-media@xxxxxxxxxxxxxxx
Cc: linaro-mm-sig@xxxxxxxxxxxxxxxx
Cc: linux-rdma@xxxxxxxxxxxxxxx
Cc: amd-gfx@xxxxxxxxxxxxxxxxxxxxx
Cc: intel-gfx@xxxxxxxxxxxxxxxxxxxxx
Cc: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
Cc: Maarten Lankhorst <maarten.lankhorst@xxxxxxxxxxxxxxx>
Cc: Christian König <christian.koenig@xxxxxxx>
Signed-off-by: Daniel Vetter <daniel.vetter@xxxxxxxx>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 11 ++++++++---
1 file changed, 8 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index e8b41756c9f9..029a026ecfa9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4496,6 +4496,9 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
int i, r = 0;
bool need_emergency_restart = false;
bool audio_suspended = false;
+ bool fence_cookie;
+
+ fence_cookie = dma_fence_begin_signalling();
/**
* Special case: RAS triggered and full reset isn't supported
@@ -4529,6 +4532,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
DRM_INFO("Bailing on TDR for s_job:%llx, hive: %llx as another already in progress",
job ? job->base.id : -1, hive->hive_id);
amdgpu_put_xgmi_hive(hive);
+ dma_fence_end_signalling(fence_cookie);
return 0;
}
mutex_lock(&hive->hive_lock);
@@ -4541,8 +4545,10 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
*/
INIT_LIST_HEAD(&device_list);
if (adev->gmc.xgmi.num_physical_nodes > 1) {
- if (!hive)
+ if (!hive) {
+ dma_fence_end_signalling(fence_cookie);
return -ENODEV;
+ }
if (!list_is_first(&adev->gmc.xgmi.head, &hive->device_list))
list_rotate_to_front(&adev->gmc.xgmi.head, &hive->device_list);
device_list_handle = &hive->device_list;
@@ -4556,8 +4562,6 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
if (!amdgpu_device_lock_adev(tmp_adev, hive)) {
dev_info(tmp_adev->dev, "Bailing on TDR for s_job:%llx, as another already in progress",
job ? job->base.id : -1);
- r = 0;
- goto skip_recovery;
}
/*
@@ -4699,6 +4703,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
if (r)
dev_info(adev->dev, "GPU reset end with ret = %d\n", r);
+ dma_fence_end_signalling(fence_cookie);
return r;
}
--
2.28.0
