mirrors/linux-stable
1
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git synced 2024-09-28 21:33:52 +00:00
Code Issues Releases Wiki Activity

drm/msm/gpu: Skip retired submits in recover worker

Browse source 
If we somehow raced with submit retiring, either while waiting for
worker to have a chance to run or acquiring the gpu lock, then the
recover worker should just bail.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Patchwork: https://patchwork.freedesktop.org/patch/568034/
This commit is contained in:
Rob Clark 2023-11-17 07:24:28 -08:00
parent 4bea53b9c7
commit 12578c075f
1 changed files with 22 additions and 19 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

41
drivers/gpu/drm/msm/msm_gpu.c
View file

@ -365,29 +365,31 @@ static void recover_worker(struct kthread_work *work)
DRM_DEV_ERROR(dev->dev, "%s: hangcheck recover!\n", gpu->name);
submit = find_submit(cur_ring, cur_ring->memptrs->fence + 1);
if (submit) {
/* Increment the fault counts */
submit->queue->faults++;
if (submit->aspace)
submit->aspace->faults++;
get_comm_cmdline(submit, &comm, &cmd);
/*
* If the submit retired while we were waiting for the worker to run,
* or waiting to acquire the gpu lock, then nothing more to do.
*/
if (!submit)
goto out_unlock;
if (comm && cmd) {
DRM_DEV_ERROR(dev->dev, "%s: offending task: %s (%s)\n",
gpu->name, comm, cmd);
/* Increment the fault counts */
submit->queue->faults++;
if (submit->aspace)
submit->aspace->faults++;
msm_rd_dump_submit(priv->hangrd, submit,
"offending task: %s (%s)", comm, cmd);
} else {
msm_rd_dump_submit(priv->hangrd, submit, NULL);
}
get_comm_cmdline(submit, &comm, &cmd);
if (comm && cmd) {
DRM_DEV_ERROR(dev->dev, "%s: offending task: %s (%s)\n",
gpu->name, comm, cmd);
msm_rd_dump_submit(priv->hangrd, submit,
"offending task: %s (%s)", comm, cmd);
} else {
/*
* We couldn't attribute this fault to any particular context,
* so increment the global fault count instead.
*/
gpu->global_faults++;
DRM_DEV_ERROR(dev->dev, "%s: offending task: unknown\n", gpu->name);
msm_rd_dump_submit(priv->hangrd, submit, NULL);
}
/* Record the crash state */
@ -440,6 +442,7 @@ static void recover_worker(struct kthread_work *work)
pm_runtime_put(&gpu->pdev->dev);
out_unlock:
mutex_unlock(&gpu->lock);
msm_gpu_retire(gpu);