diff options
| author | Maíra Canal <mcanal@igalia.com> | 2025-03-13 11:43:27 -0300 |
|---|---|---|
| committer | Maíra Canal <mcanal@igalia.com> | 2025-03-13 16:50:43 -0300 |
| commit | c3e4a25602f8b941b154f52a4da13ae77b4664c4 (patch) | |
| tree | 25b7e8f75d3ad3c19940309500e4671130ab379e /drivers/gpu/drm/v3d | |
| parent | 80cbee810e4e13cdbd3ae9654e9ecddf17f3e828 (diff) | |
drm/v3d: Set job pointer to NULL when the job's fence has an error
Similar to commit e4b5ccd392b9 ("drm/v3d: Ensure job pointer is set to
NULL after job completion"), ensure the job pointer is set to `NULL` when
a job's fence has an error. Failing to do so can trigger kernel warnings
in specific scenarios, such as:
1. v3d_csd_job_run() assigns `v3d->csd_job = job`
2. CSD job exceeds hang limit, causing a timeout → v3d_gpu_reset_for_timeout()
3. GPU reset
4. drm_sched_resubmit_jobs() sets the job's fence to `-ECANCELED`.
5. v3d_csd_job_run() detects the fence error and returns NULL, not
submitting the job to the GPU
6. User-space runs `modprobe -r v3d`
7. v3d_gem_destroy()
v3d_gem_destroy() triggers a warning indicating that the CSD job never
ended, as we didn't set `v3d->csd_job` to NULL after the timeout. The same
can also happen to BIN, RENDER, and TFU jobs.
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Signed-off-by: Maíra Canal <mcanal@igalia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250313-v3d-gpu-reset-fixes-v4-2-c1e780d8e096@igalia.com
Diffstat (limited to 'drivers/gpu/drm/v3d')
| -rw-r--r-- | drivers/gpu/drm/v3d/v3d_sched.c | 18 |
1 files changed, 14 insertions, 4 deletions
diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c index 84c0c142d760..05608c894ed9 100644 --- a/drivers/gpu/drm/v3d/v3d_sched.c +++ b/drivers/gpu/drm/v3d/v3d_sched.c @@ -226,8 +226,12 @@ static struct dma_fence *v3d_bin_job_run(struct drm_sched_job *sched_job) struct dma_fence *fence; unsigned long irqflags; - if (unlikely(job->base.base.s_fence->finished.error)) + if (unlikely(job->base.base.s_fence->finished.error)) { + spin_lock_irqsave(&v3d->job_lock, irqflags); + v3d->bin_job = NULL; + spin_unlock_irqrestore(&v3d->job_lock, irqflags); return NULL; + } /* Lock required around bin_job update vs * v3d_overflow_mem_work(). @@ -281,8 +285,10 @@ static struct dma_fence *v3d_render_job_run(struct drm_sched_job *sched_job) struct drm_device *dev = &v3d->drm; struct dma_fence *fence; - if (unlikely(job->base.base.s_fence->finished.error)) + if (unlikely(job->base.base.s_fence->finished.error)) { + v3d->render_job = NULL; return NULL; + } v3d->render_job = job; @@ -327,8 +333,10 @@ v3d_tfu_job_run(struct drm_sched_job *sched_job) struct drm_device *dev = &v3d->drm; struct dma_fence *fence; - if (unlikely(job->base.base.s_fence->finished.error)) + if (unlikely(job->base.base.s_fence->finished.error)) { + v3d->tfu_job = NULL; return NULL; + } v3d->tfu_job = job; @@ -373,8 +381,10 @@ v3d_csd_job_run(struct drm_sched_job *sched_job) struct dma_fence *fence; int i, csd_cfg0_reg; - if (unlikely(job->base.base.s_fence->finished.error)) + if (unlikely(job->base.base.s_fence->finished.error)) { + v3d->csd_job = NULL; return NULL; + } v3d->csd_job = job; |