On Tue, Jan 16, 2024 at 7:12 PM Erico Nunes <nunes.erico@xxxxxxxxx> wrote:
>
> Marking the context as guilty currently only makes the application which
> hits a single timeout problem to stop its rendering context entirely.
> All jobs submitted later are dropped from the guilty context.
>
> Lima runs on fairly underpowered hardware for modern standards and it is
> not entirely unreasonable that a rendering job may time out occasionally
> due to high system load or too demanding application stack. In this case
> it would be generally preferred to report the error but try to keep the
> application going.
>
> Other similar embedded GPU drivers don't make use of the guilty context
> flag. Now that there are reliability improvements to the lima timeout
> recovery handling, drop the guilty contexts to let the application keep
> running in this case.
>
> Signed-off-by: Erico Nunes <nunes.erico@xxxxxxxxx>
Reviewed-by: Vasily Khoruzhick <anarsoul@xxxxxxxxx>
> ---
> drivers/gpu/drm/lima/lima_ctx.c | 2 +-
> drivers/gpu/drm/lima/lima_ctx.h | 1 -
> drivers/gpu/drm/lima/lima_sched.c | 5 ++---
> drivers/gpu/drm/lima/lima_sched.h | 3 +--
> 4 files changed, 4 insertions(+), 7 deletions(-)
>
> diff --git a/drivers/gpu/drm/lima/lima_ctx.c b/drivers/gpu/drm/lima/lima_ctx.c
> index 8389f2d7d021..0e668fc1e0f9 100644
> --- a/drivers/gpu/drm/lima/lima_ctx.c
> +++ b/drivers/gpu/drm/lima/lima_ctx.c
> @@ -19,7 +19,7 @@ int lima_ctx_create(struct lima_device *dev, struct lima_ctx_mgr *mgr, u32 *id)
> kref_init(&ctx->refcnt);
>
> for (i = 0; i < lima_pipe_num; i++) {
> - err = lima_sched_context_init(dev->pipe + i, ctx->context + i, &ctx->guilty);
> + err = lima_sched_context_init(dev->pipe + i, ctx->context + i);
> if (err)
> goto err_out0;
> }
> diff --git a/drivers/gpu/drm/lima/lima_ctx.h b/drivers/gpu/drm/lima/lima_ctx.h
> index 74e2be09090f..5b1063ce968b 100644
> --- a/drivers/gpu/drm/lima/lima_ctx.h
> +++ b/drivers/gpu/drm/lima/lima_ctx.h
> @@ -13,7 +13,6 @@ struct lima_ctx {
> struct kref refcnt;
> struct lima_device *dev;
> struct lima_sched_context context[lima_pipe_num];
> - atomic_t guilty;
>
> /* debug info */
> char pname[TASK_COMM_LEN];
> diff --git a/drivers/gpu/drm/lima/lima_sched.c b/drivers/gpu/drm/lima/lima_sched.c
> index 9449b81bcd5b..496c79713fe8 100644
> --- a/drivers/gpu/drm/lima/lima_sched.c
> +++ b/drivers/gpu/drm/lima/lima_sched.c
> @@ -154,13 +154,12 @@ void lima_sched_task_fini(struct lima_sched_task *task)
> }
>
> int lima_sched_context_init(struct lima_sched_pipe *pipe,
> - struct lima_sched_context *context,
> - atomic_t *guilty)
> + struct lima_sched_context *context)
> {
> struct drm_gpu_scheduler *sched = &pipe->base;
>
> return drm_sched_entity_init(&context->base, DRM_SCHED_PRIORITY_NORMAL,
> - &sched, 1, guilty);
> + &sched, 1, NULL);
> }
>
> void lima_sched_context_fini(struct lima_sched_pipe *pipe,
> diff --git a/drivers/gpu/drm/lima/lima_sched.h b/drivers/gpu/drm/lima/lima_sched.h
> index 34050facb110..677e908b53f8 100644
> --- a/drivers/gpu/drm/lima/lima_sched.h
> +++ b/drivers/gpu/drm/lima/lima_sched.h
> @@ -93,8 +93,7 @@ int lima_sched_task_init(struct lima_sched_task *task,
> void lima_sched_task_fini(struct lima_sched_task *task);
>
> int lima_sched_context_init(struct lima_sched_pipe *pipe,
> - struct lima_sched_context *context,
> - atomic_t *guilty);
> + struct lima_sched_context *context);
> void lima_sched_context_fini(struct lima_sched_pipe *pipe,
> struct lima_sched_context *context);
> struct dma_fence *lima_sched_context_queue_task(struct lima_sched_task *task);
> --
> 2.43.0
>
