Every job of a gang except the leader holds a reference to the
scheduled fence of the leader in job->gang_submit. Only
amdgpu_job_free(), used for jobs which never ran, drops it, so for every
gang submission which completes the scheduler fence of the leader, and
with it its hardware fence, is leaked. amdgpu_job_free() in turn checks
for the leader only after drm_sched_job_cleanup() cleared the scheduler
fence, so a leader freed there drops a reference it never took.
On navi31, 100 submissions of a GFX + COMPUTE gang grow the slab cache
drm_sched_fence is merged into by 60 to 180 objects each time, while
100 GFX only submissions don't.
Drop the reference when the scheduler frees the job as well, and check
for the leader before the scheduler fence is cleared in both places.
Fixes: 68ce8b242242 ("drm/amdgpu: add gang submit backend v2")
Fixes: f7d66fb2ea43 ("drm/amdgpu: cleanup scheduler job initialization v2")
Signed-off-by: Jesse Zhang <[email protected]>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 12 ++++++++++--
1 file changed, 10 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 0056a93c400a..f8e67c1b5a4c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -311,10 +311,19 @@ void amdgpu_job_free_resources(struct amdgpu_job *job)
amdgpu_ib_free(&job->ibs[i], f);
}
+/* Must be called before drm_sched_job_cleanup() clears the scheduler fence */
+static void amdgpu_job_put_gang(struct amdgpu_job *job)
+{
+ /* The gang leader doesn't hold a reference to itself */
+ if (job->gang_submit != &job->base.s_fence->scheduled)
+ dma_fence_put(job->gang_submit);
+}
+
static void amdgpu_job_free_cb(struct drm_sched_job *s_job)
{
struct amdgpu_job *job = to_amdgpu_job(s_job);
+ amdgpu_job_put_gang(job);
drm_sched_job_cleanup(s_job);
amdgpu_sync_free(&job->explicit_sync);
@@ -349,13 +358,12 @@ void amdgpu_job_set_gang_leader(struct amdgpu_job *job,
void amdgpu_job_free(struct amdgpu_job *job)
{
+ amdgpu_job_put_gang(job);
if (job->base.entity)
drm_sched_job_cleanup(&job->base);
amdgpu_job_free_resources(job);
amdgpu_sync_free(&job->explicit_sync);
- if (job->gang_submit != &job->base.s_fence->scheduled)
- dma_fence_put(job->gang_submit);
if (dma_fence_was_initialized(&job->hw_fence->base))
dma_fence_put(&job->hw_fence->base);
--
2.50.1
