Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 2c83a726 authored by Lucas Stach's avatar Lucas Stach
Browse files

drm/etnaviv: bring back progress check in job timeout handler 



When the hangcheck handler was replaced by the DRM scheduler timeout
handling we dropped the forward progress check, as this might allow
clients to hog the GPU for a long time with a big job.

It turns out that even reasonably well behaved clients like the
Armada Xorg driver occasionally trip over the 500ms timeout. Bring
back the forward progress check to get rid of the userspace regression.

We would still like to fix userspace to submit smaller batches
if possible, but that is for another day.

Cc: <stable@vger.kernel.org>
Fixes: 6d7a20c0 (drm/etnaviv: replace hangcheck with scheduler timeout)
Reported-by: default avatarRussell King <linux@armlinux.org.uk>
Signed-off-by: default avatarLucas Stach <l.stach@pengutronix.de>
Reviewed-by: default avatarEric Anholt <eric@anholt.net>
parent bf6ba3ae

drivers/gpu/drm/etnaviv/etnaviv_gpu.h

+3 −0
Original line number Diff line number Diff line
@@ -131,6 +131,9 @@ struct etnaviv_gpu { 
	struct work_struct sync_point_work;

	int sync_point_event;



	/* hang detection */

	u32 hangcheck_dma_addr;



	void __iomem *mmio;

	int irq;

drivers/gpu/drm/etnaviv/etnaviv_sched.c

+24 −0
Original line number Diff line number Diff line
@@ -10,6 +10,7 @@ 
#include "etnaviv_gem.h"

#include "etnaviv_gpu.h"

#include "etnaviv_sched.h"

#include "state.xml.h"



static int etnaviv_job_hang_limit = 0;

module_param_named(job_hang_limit, etnaviv_job_hang_limit, int , 0444);
@@ -85,6 +86,29 @@ static void etnaviv_sched_timedout_job(struct drm_sched_job *sched_job) 
{

	struct etnaviv_gem_submit *submit = to_etnaviv_submit(sched_job);

	struct etnaviv_gpu *gpu = submit->gpu;

	u32 dma_addr;

	int change;



	/*

	 * If the GPU managed to complete this jobs fence, the timout is

	 * spurious. Bail out.

	 */

	if (fence_completed(gpu, submit->out_fence->seqno))

		return;



	/*

	 * If the GPU is still making forward progress on the front-end (which

	 * should never loop) we shift out the timeout to give it a chance to

	 * finish the job.

	 */

	dma_addr = gpu_read(gpu, VIVS_FE_DMA_ADDRESS);

	change = dma_addr - gpu->hangcheck_dma_addr;

	if (change < 0 || change > 16) {

		gpu->hangcheck_dma_addr = dma_addr;

		schedule_delayed_work(&sched_job->work_tdr,

				      sched_job->sched->timeout);

		return;

	}



	/* block scheduler */

	kthread_park(gpu->sched.thread);