amd/scheduler:imple job skip feature(v3)

jobs are skipped under two cases
1)when the entity behind this job marked guilty, the job
poped from this entity's queue will be dropped in sched_main loop.

2)in job_recovery(), skip the scheduling job if its karma detected
above limit, and also skipped as well for other jobs sharing the
same fence context. this approach is becuase job_recovery() cannot
access job->entity due to entity may already dead.

v2:
some logic fix

v3:
when entity detected guilty, don't drop the job in the poping
stage, instead set its fence error as -ECANCELED

in run_job(), skip the scheduling either:1) fence->error < 0
or 2) there was a VRAM LOST occurred on this job.
this way we can unify the job skipping logic.

with this feature we can introduce new gpu recover feature.

Signed-off-by: Monk Liu <Monk.Liu@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

1 files changed, 8 insertions, 5 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index f60662e03761..0a90c768dbc1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -180,7 +180,7 @@ static struct dma_fence *amdgpu_job_dependency(struct amd_sched_job *sched_job,
 
 static struct dma_fence *amdgpu_job_run(struct amd_sched_job *sched_job)
 {
-        struct dma_fence *fence = NULL;
+        struct dma_fence *fence = NULL, *finished;
         struct amdgpu_device *adev;
         struct amdgpu_job *job;
         int r;
@@ -190,15 +190,18 @@ static struct dma_fence *amdgpu_job_run(struct amd_sched_job *sched_job)
                 return NULL;
         }
         job = to_amdgpu_job(sched_job);
+        finished = &job->base.s_fence->finished;
         adev = job->adev;
 
         BUG_ON(amdgpu_sync_peek_fence(&job->sync, NULL));
 
         trace_amdgpu_sched_run_job(job);
-        /* skip ib schedule when vram is lost */
-        if (job->vram_lost_counter != atomic_read(&adev->vram_lost_counter)) {
-                dma_fence_set_error(&job->base.s_fence->finished, -ECANCELED);
-                DRM_ERROR("Skip scheduling IBs!\n");
+
+        if (job->vram_lost_counter != atomic_read(&adev->vram_lost_counter))
+                dma_fence_set_error(finished, -ECANCELED);/* skip IB as well if VRAM lost */
+
+        if (finished->error < 0) {
+                DRM_INFO("Skip scheduling IBs!\n");
         } else {
                 r = amdgpu_ib_schedule(job->ring, job->num_ibs, job->ibs, job,
                                        &fence);