summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm
diff options
context:
space:
mode:
authorLucas Stach <l.stach@pengutronix.de>2021-12-22 01:17:28 +0100
committerLucas Stach <l.stach@pengutronix.de>2021-12-23 20:21:33 +0100
commitcdd156955f946beaa5f3a00d8ccf90e5a197becc (patch)
tree638df9e2b7ba10dbae634dc4c29779631f469ba1 /drivers/gpu/drm
parent6dfa2fab8ddd46faa771a102672176bee7a065de (diff)
drm/etnaviv: consider completed fence seqno in hang check
Some GPU heavy test programs manage to trigger the hangcheck quite often. If there are no other GPU users in the system and the test program exhibits a very regular structure in the commandstreams that are being submitted, we can end up with two distinct submits managing to trigger the hangcheck with the FE in a very similar address range. This leads the hangcheck to believe that the GPU is stuck, while in reality the GPU is already busy working on a different job. To avoid those spurious GPU resets, also remember and consider the last completed fence seqno in the hang check. Reported-by: Joerg Albert <joerg.albert@iav.de> Signed-off-by: Lucas Stach <l.stach@pengutronix.de> Reviewed-by: Christian Gmeiner <christian.gmeiner@gmail.com>
Diffstat (limited to 'drivers/gpu/drm')
-rw-r--r--drivers/gpu/drm/etnaviv/etnaviv_gpu.h1
-rw-r--r--drivers/gpu/drm/etnaviv/etnaviv_sched.c4
2 files changed, 4 insertions, 1 deletions
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
index 1c75c8ed5bce..85eddd492774 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
@@ -130,6 +130,7 @@ struct etnaviv_gpu {
/* hang detection */
u32 hangcheck_dma_addr;
+ u32 hangcheck_fence;
void __iomem *mmio;
int irq;
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
index 180bb633d5c5..58f593b278c1 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
@@ -107,8 +107,10 @@ static enum drm_gpu_sched_stat etnaviv_sched_timedout_job(struct drm_sched_job
*/
dma_addr = gpu_read(gpu, VIVS_FE_DMA_ADDRESS);
change = dma_addr - gpu->hangcheck_dma_addr;
- if (change < 0 || change > 16) {
+ if (gpu->completed_fence != gpu->hangcheck_fence ||
+ change < 0 || change > 16) {
gpu->hangcheck_dma_addr = dma_addr;
+ gpu->hangcheck_fence = gpu->completed_fence;
goto out_no_timeout;
}