All of lore.kernel.org
 help / color / mirror / Atom feed
From: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
To: amd-gfx@lists.freedesktop.org, dri-devel@lists.freedesktop.org
Cc: ckoenig.leichtzumerken@gmail.com, Shirish.S@amd.com
Subject: [PATCH 1/2] drm/sched: Set error to s_fence if HW job submission failed.
Date: Thu, 24 Oct 2019 15:57:29 -0400	[thread overview]
Message-ID: <1571947050-26276-1-git-send-email-andrey.grodzovsky@amd.com> (raw)

Problem:
When run_job fails and HW fence returned is NULL we still signal
the s_fence to avoid hangs but the user has no way of knowing if
the actual HW job was ran and finished.

Fix:
Allow .run_job implementations to return ERR_PTR in the fence pointer
returned and then set this error for s_fence->finished fence so whoever
wait on this fence can inspect the signaled fence for an error.

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
---
 drivers/gpu/drm/scheduler/sched_main.c | 19 ++++++++++++++++---
 1 file changed, 16 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 9a0ee74..f39b97e 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -479,6 +479,7 @@ void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched)
 	struct drm_sched_job *s_job, *tmp;
 	uint64_t guilty_context;
 	bool found_guilty = false;
+	struct dma_fence *fence;
 
 	list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) {
 		struct drm_sched_fence *s_fence = s_job->s_fence;
@@ -492,7 +493,16 @@ void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched)
 			dma_fence_set_error(&s_fence->finished, -ECANCELED);
 
 		dma_fence_put(s_job->s_fence->parent);
-		s_job->s_fence->parent = sched->ops->run_job(s_job);
+		fence = sched->ops->run_job(s_job);
+
+		if (IS_ERR_OR_NULL(fence)) {
+			s_job->s_fence->parent = NULL;
+			dma_fence_set_error(&s_fence->finished, PTR_ERR(fence));
+		} else {
+			s_job->s_fence->parent = fence;
+		}
+
+
 	}
 }
 EXPORT_SYMBOL(drm_sched_resubmit_jobs);
@@ -720,7 +730,7 @@ static int drm_sched_main(void *param)
 		fence = sched->ops->run_job(sched_job);
 		drm_sched_fence_scheduled(s_fence);
 
-		if (fence) {
+		if (!IS_ERR_OR_NULL(fence)) {
 			s_fence->parent = dma_fence_get(fence);
 			r = dma_fence_add_callback(fence, &sched_job->cb,
 						   drm_sched_process_job);
@@ -730,8 +740,11 @@ static int drm_sched_main(void *param)
 				DRM_ERROR("fence add callback failed (%d)\n",
 					  r);
 			dma_fence_put(fence);
-		} else
+		} else {
+
+			dma_fence_set_error(&s_fence->finished, PTR_ERR(fence));
 			drm_sched_process_job(NULL, &sched_job->cb);
+		}
 
 		wake_up(&sched->job_scheduled);
 	}
-- 
2.7.4

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel

WARNING: multiple messages have this Message-ID (diff)
From: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
To: <amd-gfx@lists.freedesktop.org>, <dri-devel@lists.freedesktop.org>
Cc: ckoenig.leichtzumerken@gmail.com, Shirish.S@amd.com
Subject: [PATCH 1/2] drm/sched: Set error to s_fence if HW job submission failed.
Date: Thu, 24 Oct 2019 15:57:29 -0400	[thread overview]
Message-ID: <1571947050-26276-1-git-send-email-andrey.grodzovsky@amd.com> (raw)
Message-ID: <20191024195729.bSreImwJpCvVQan-etSimsWVPOPky9mh76o5lO_g3T8@z> (raw)

Problem:
When run_job fails and HW fence returned is NULL we still signal
the s_fence to avoid hangs but the user has no way of knowing if
the actual HW job was ran and finished.

Fix:
Allow .run_job implementations to return ERR_PTR in the fence pointer
returned and then set this error for s_fence->finished fence so whoever
wait on this fence can inspect the signaled fence for an error.

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
---
 drivers/gpu/drm/scheduler/sched_main.c | 19 ++++++++++++++++---
 1 file changed, 16 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 9a0ee74..f39b97e 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -479,6 +479,7 @@ void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched)
 	struct drm_sched_job *s_job, *tmp;
 	uint64_t guilty_context;
 	bool found_guilty = false;
+	struct dma_fence *fence;
 
 	list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) {
 		struct drm_sched_fence *s_fence = s_job->s_fence;
@@ -492,7 +493,16 @@ void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched)
 			dma_fence_set_error(&s_fence->finished, -ECANCELED);
 
 		dma_fence_put(s_job->s_fence->parent);
-		s_job->s_fence->parent = sched->ops->run_job(s_job);
+		fence = sched->ops->run_job(s_job);
+
+		if (IS_ERR_OR_NULL(fence)) {
+			s_job->s_fence->parent = NULL;
+			dma_fence_set_error(&s_fence->finished, PTR_ERR(fence));
+		} else {
+			s_job->s_fence->parent = fence;
+		}
+
+
 	}
 }
 EXPORT_SYMBOL(drm_sched_resubmit_jobs);
@@ -720,7 +730,7 @@ static int drm_sched_main(void *param)
 		fence = sched->ops->run_job(sched_job);
 		drm_sched_fence_scheduled(s_fence);
 
-		if (fence) {
+		if (!IS_ERR_OR_NULL(fence)) {
 			s_fence->parent = dma_fence_get(fence);
 			r = dma_fence_add_callback(fence, &sched_job->cb,
 						   drm_sched_process_job);
@@ -730,8 +740,11 @@ static int drm_sched_main(void *param)
 				DRM_ERROR("fence add callback failed (%d)\n",
 					  r);
 			dma_fence_put(fence);
-		} else
+		} else {
+
+			dma_fence_set_error(&s_fence->finished, PTR_ERR(fence));
 			drm_sched_process_job(NULL, &sched_job->cb);
+		}
 
 		wake_up(&sched->job_scheduled);
 	}
-- 
2.7.4

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel

WARNING: multiple messages have this Message-ID (diff)
From: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
To: <amd-gfx@lists.freedesktop.org>, <dri-devel@lists.freedesktop.org>
Cc: ckoenig.leichtzumerken@gmail.com,
	Andrey Grodzovsky <andrey.grodzovsky@amd.com>,
	Shirish.S@amd.com
Subject: [PATCH 1/2] drm/sched: Set error to s_fence if HW job submission failed.
Date: Thu, 24 Oct 2019 15:57:29 -0400	[thread overview]
Message-ID: <1571947050-26276-1-git-send-email-andrey.grodzovsky@amd.com> (raw)
Message-ID: <20191024195729.3SVgyW6L4yNQmHf5cVc6ArJH6YLtOeku17wRk12sXQ4@z> (raw)

Problem:
When run_job fails and HW fence returned is NULL we still signal
the s_fence to avoid hangs but the user has no way of knowing if
the actual HW job was ran and finished.

Fix:
Allow .run_job implementations to return ERR_PTR in the fence pointer
returned and then set this error for s_fence->finished fence so whoever
wait on this fence can inspect the signaled fence for an error.

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
---
 drivers/gpu/drm/scheduler/sched_main.c | 19 ++++++++++++++++---
 1 file changed, 16 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 9a0ee74..f39b97e 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -479,6 +479,7 @@ void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched)
 	struct drm_sched_job *s_job, *tmp;
 	uint64_t guilty_context;
 	bool found_guilty = false;
+	struct dma_fence *fence;
 
 	list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) {
 		struct drm_sched_fence *s_fence = s_job->s_fence;
@@ -492,7 +493,16 @@ void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched)
 			dma_fence_set_error(&s_fence->finished, -ECANCELED);
 
 		dma_fence_put(s_job->s_fence->parent);
-		s_job->s_fence->parent = sched->ops->run_job(s_job);
+		fence = sched->ops->run_job(s_job);
+
+		if (IS_ERR_OR_NULL(fence)) {
+			s_job->s_fence->parent = NULL;
+			dma_fence_set_error(&s_fence->finished, PTR_ERR(fence));
+		} else {
+			s_job->s_fence->parent = fence;
+		}
+
+
 	}
 }
 EXPORT_SYMBOL(drm_sched_resubmit_jobs);
@@ -720,7 +730,7 @@ static int drm_sched_main(void *param)
 		fence = sched->ops->run_job(sched_job);
 		drm_sched_fence_scheduled(s_fence);
 
-		if (fence) {
+		if (!IS_ERR_OR_NULL(fence)) {
 			s_fence->parent = dma_fence_get(fence);
 			r = dma_fence_add_callback(fence, &sched_job->cb,
 						   drm_sched_process_job);
@@ -730,8 +740,11 @@ static int drm_sched_main(void *param)
 				DRM_ERROR("fence add callback failed (%d)\n",
 					  r);
 			dma_fence_put(fence);
-		} else
+		} else {
+
+			dma_fence_set_error(&s_fence->finished, PTR_ERR(fence));
 			drm_sched_process_job(NULL, &sched_job->cb);
+		}
 
 		wake_up(&sched->job_scheduled);
 	}
-- 
2.7.4

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

             reply	other threads:[~2019-10-24 19:57 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-10-24 19:57 Andrey Grodzovsky [this message]
2019-10-24 19:57 ` [PATCH 1/2] drm/sched: Set error to s_fence if HW job submission failed Andrey Grodzovsky
2019-10-24 19:57 ` Andrey Grodzovsky
2019-10-24 19:57 ` [PATCH 2/2] drm/amdgpu: If amdgpu_ib_schedule fails return back the error Andrey Grodzovsky
2019-10-24 19:57   ` Andrey Grodzovsky
2019-10-24 19:57   ` Andrey Grodzovsky
     [not found] ` <1571947050-26276-1-git-send-email-andrey.grodzovsky-5C7GfCeVMHo@public.gmane.org>
2019-10-25  8:44   ` [PATCH 1/2] drm/sched: Set error to s_fence if HW job submission failed Christian König
2019-10-25  8:44     ` Christian König
2019-10-25  8:44     ` Christian König
2019-10-25 14:57     ` Grodzovsky, Andrey
2019-10-25 14:57       ` Grodzovsky, Andrey
     [not found]       ` <1638959e-08ef-3a24-babc-5cbddcae0575-5C7GfCeVMHo@public.gmane.org>
2019-10-25 15:55         ` Koenig, Christian
2019-10-25 15:55           ` Koenig, Christian
2019-10-25 15:55           ` Koenig, Christian
2019-10-25 15:56           ` Grodzovsky, Andrey
2019-10-25 15:56             ` Grodzovsky, Andrey
2019-10-25 15:58             ` Koenig, Christian
2019-10-25 15:58               ` Koenig, Christian

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1571947050-26276-1-git-send-email-andrey.grodzovsky@amd.com \
    --to=andrey.grodzovsky@amd.com \
    --cc=Shirish.S@amd.com \
    --cc=amd-gfx@lists.freedesktop.org \
    --cc=ckoenig.leichtzumerken@gmail.com \
    --cc=dri-devel@lists.freedesktop.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.