The drm scheduler currently expects that the stop/start sequence is always executed in the timeout handling, as the job at the head of the hardware execution list is always removed from the ring mirror before the driver function is called and only inserted back into the list when starting the scheduler.
This adds some unnecessary overhead if the timeout handler determines that the GPU is still executing jobs normally and just wished to extend the timeout, but a better solution requires a major rearchitecture of the scheduler, which is not applicable as a fix.
Fixes: 135517d3565b drm/scheduler: Avoid accessing freed bad job.) Signed-off-by: Lucas Stach l.stach@pengutronix.de --- drivers/gpu/drm/etnaviv/etnaviv_sched.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-)
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c index 4e3e95dce6d8..cd46c882269c 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c @@ -89,12 +89,15 @@ static void etnaviv_sched_timedout_job(struct drm_sched_job *sched_job) u32 dma_addr; int change;
+ /* block scheduler */ + drm_sched_stop(&gpu->sched, sched_job); + /* * If the GPU managed to complete this jobs fence, the timout is * spurious. Bail out. */ if (dma_fence_is_signaled(submit->out_fence)) - return; + goto out_no_timeout;
/* * If the GPU is still making forward progress on the front-end (which @@ -105,12 +108,9 @@ static void etnaviv_sched_timedout_job(struct drm_sched_job *sched_job) change = dma_addr - gpu->hangcheck_dma_addr; if (change < 0 || change > 16) { gpu->hangcheck_dma_addr = dma_addr; - return; + goto out_no_timeout; }
- /* block scheduler */ - drm_sched_stop(&gpu->sched, sched_job); - if(sched_job) drm_sched_increase_karma(sched_job);
@@ -120,6 +120,7 @@ static void etnaviv_sched_timedout_job(struct drm_sched_job *sched_job)
drm_sched_resubmit_jobs(&gpu->sched);
+out_no_timeout: /* restart scheduler after GPU is usable again */ drm_sched_start(&gpu->sched, true); }