diff options
| author | Rob Clark <robdclark@chromium.org> | 2022-02-01 08:16:12 -0800 |
|---|---|---|
| committer | Rob Clark <robdclark@chromium.org> | 2022-02-20 09:44:52 -0800 |
| commit | bc2112583a0b473f5c4ba87c00da84abd5d0b3fd (patch) | |
| tree | 8133227a378c16995316b7e4132a9928322e0662 /drivers/gpu/drm/msm/msm_gpu.c | |
| parent | f98f915b7e0f83fd108bcf716c77f316ee27f484 (diff) | |
drm/msm/gpu: Track global faults per address-space
Other processes don't need to know about faults that they are isolated
from by virtue of address space isolation. They are only interested in
whether some of their state might have been corrupted.
But to be safe, also track unattributed faults. This case should really
never happen unless there is a kernel bug (and that would never happen,
right?)
v2: Instead of adding a new param, just change the behavior of the
existing param to match what userspace actually wants [anholt]
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/5934
Signed-off-by: Rob Clark <robdclark@chromium.org>
Link: https://lore.kernel.org/r/20220201161618.778455-3-robdclark@gmail.com
Reviewed-by: Emma Anholt <emma@anholt.net>
Signed-off-by: Rob Clark <robdclark@chromium.org>
Diffstat (limited to 'drivers/gpu/drm/msm/msm_gpu.c')
| -rw-r--r-- | drivers/gpu/drm/msm/msm_gpu.c | 8 |
1 files changed, 7 insertions, 1 deletions
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c index 998e705c15ef..173ebd449f2f 100644 --- a/drivers/gpu/drm/msm/msm_gpu.c +++ b/drivers/gpu/drm/msm/msm_gpu.c @@ -370,8 +370,8 @@ static void recover_worker(struct kthread_work *work) struct task_struct *task; /* Increment the fault counts */ - gpu->global_faults++; submit->queue->faults++; + submit->aspace->faults++; task = get_pid_task(submit->pid, PIDTYPE_PID); if (task) { @@ -389,6 +389,12 @@ static void recover_worker(struct kthread_work *work) } else { msm_rd_dump_submit(priv->hangrd, submit, NULL); } + } else { + /* + * We couldn't attribute this fault to any particular context, + * so increment the global fault count instead. + */ + gpu->global_faults++; } /* Record the crash state */ |