lkml.org 
[lkml]   [2023]   [Nov]   [17]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH] drm/msm/gpu: Skip retired submits in recover worker
Date
From: Rob Clark <robdclark@chromium.org>

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>
---
drivers/gpu/drm/msm/msm_gpu.c | 41 +++++++++++++++++++----------------
1 file changed, 22 insertions(+), 19 deletions(-)

diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 3fad5d58262f..fd3dceed86f8 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -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);
--
2.41.0
\
 
 \ /
  Last update: 2023-11-20 14:02    [W:0.038 / U:0.480 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site