@@ -327,11 +327,15 @@ 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))
+ return NULL;
+
+ v3d->tfu_job = job;
+
fence = v3d_fence_create(v3d, V3D_TFU);
if (IS_ERR(fence))
return NULL;
- v3d->tfu_job = job;
if (job->base.irq_fence)
dma_fence_put(job->base.irq_fence);
job->base.irq_fence = dma_fence_get(fence);
@@ -369,6 +373,9 @@ 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))
+ return NULL;
+
v3d->csd_job = job;
v3d_invalidate_caches(v3d);
The V3D driver still relies on `drm_sched_increase_karma()` and `drm_sched_resubmit_jobs()` for resubmissions when a timeout occurs. The function `drm_sched_increase_karma()` marks the job as guilty, while `drm_sched_resubmit_jobs()` sets an error (-ECANCELED) in the DMA fence of that guilty job. Because of this, we must check whether the job’s DMA fence has been flagged with an error before executing the job. Otherwise, the same guilty job may be resubmitted indefinitely, causing repeated GPU resets. This patch adds a check for an error on the job's fence to prevent running a guilty job that was previously flagged when the GPU timed out. Note that the CPU and CACHE_CLEAN queues do not require this check, as their jobs are executed synchronously once the DRM scheduler starts them. Cc: stable@vger.kernel.org Fixes: d223f98f0209 ("drm/v3d: Add support for compute shader dispatch.") Fixes: 1584f16ca96e ("drm/v3d: Add support for submitting jobs to the TFU.") Signed-off-by: Maíra Canal <mcanal@igalia.com> --- drivers/gpu/drm/v3d/v3d_sched.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-)