A ring might become unusable after reset, if that the case
drm_sched_entity_select_rq will choose another, working rq
to run the job if there is one.
Also, skip recovery of ring which is not ready.
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@xxxxxxx>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 16 +++++++++++++++-
1 file changed, 15 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index d11489e..3124ca1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3355,10 +3355,24 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
else
r = amdgpu_device_reset(adev);
+ /*
+ * After reboot a ring might fail in which case this will
+ * move the job to different rq if possible
+ */
+ if (job) {
+ drm_sched_entity_select_rq(job->base.entity);
+ if (job->base.entity->rq) {
+ job->base.sched = job->base.entity->rq->sched;
+ } else {
+ job->base.sched = NULL;
+ r = -ENOENT;
+ }
+ }
+
for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
struct amdgpu_ring *ring = adev->rings[i];
- if (!ring || !ring->sched.thread)
+ if (!ring || !ring->ready || !ring->sched.thread)
continue;
/* only need recovery sched of the given job's ring
--
2.7.4
_______________________________________________
amd-gfx mailing list
amd-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
