linux-kernel - [PATCH v4 03/10] drm/panfrost: Handle job HW submit errors

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20251001022039.1215976-4-adrian.larumbe@collabora.com>
Date: Wed,  1 Oct 2025 03:20:24 +0100
From: Adrián Larumbe <adrian.larumbe@...labora.com>
To: linux-kernel@...r.kernel.org
Cc: dri-devel@...ts.freedesktop.org,
	Steven Price <steven.price@....com>,
	Boris Brezillon <boris.brezillon@...labora.com>,
	kernel@...labora.com,
	Adrián Larumbe <adrian.larumbe@...labora.com>,
	Rob Herring <robh@...nel.org>,
	Maarten Lankhorst <maarten.lankhorst@...ux.intel.com>,
	Maxime Ripard <mripard@...nel.org>,
	Thomas Zimmermann <tzimmermann@...e.de>,
	David Airlie <airlied@...il.com>,
	Simona Vetter <simona@...ll.ch>
Subject: [PATCH v4 03/10] drm/panfrost: Handle job HW submit errors

Avoid waiting for the DRM scheduler job timedout handler, and instead, let
the DRM scheduler core signal the error fence immediately when HW job
submission fails.

That means we must also decrement the runtime-PM refcnt for the device,
because the job will never be enqueued or inflight.

Reviewed-by: Boris Brezillon <boris.brezillon@...labora.com>
Signed-off-by: Adrián Larumbe <adrian.larumbe@...labora.com>
---
 drivers/gpu/drm/panfrost/panfrost_job.c | 20 ++++++++++++++++----
 1 file changed, 16 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c
index a0123d0a1b7d..3f60adc9b69d 100644
--- a/drivers/gpu/drm/panfrost/panfrost_job.c
+++ b/drivers/gpu/drm/panfrost/panfrost_job.c
@@ -196,7 +196,7 @@ panfrost_enqueue_job(struct panfrost_device *pfdev, int slot,
 	return 1;
 }
 
-static void panfrost_job_hw_submit(struct panfrost_job *job, int js)
+static int panfrost_job_hw_submit(struct panfrost_job *job, int js)
 {
 	struct panfrost_device *pfdev = job->pfdev;
 	unsigned int subslot;
@@ -208,10 +208,11 @@ static void panfrost_job_hw_submit(struct panfrost_job *job, int js)
 
 	ret = pm_runtime_get_sync(pfdev->base.dev);
 	if (ret < 0)
-		return;
+		goto err_hwsubmit;
 
 	if (WARN_ON(job_read(pfdev, JS_COMMAND_NEXT(js)))) {
-		return;
+		ret = -EINVAL;
+		goto err_hwsubmit;
 	}
 
 	cfg = panfrost_mmu_as_get(pfdev, job->mmu);
@@ -262,6 +263,12 @@ static void panfrost_job_hw_submit(struct panfrost_job *job, int js)
 			job, js, subslot, jc_head, cfg & 0xf);
 	}
 	spin_unlock(&pfdev->js->job_lock);
+
+	return 0;
+
+err_hwsubmit:
+	pm_runtime_put_autosuspend(pfdev->base.dev);
+	return ret;
 }
 
 static int panfrost_acquire_object_fences(struct drm_gem_object **bos,
@@ -384,6 +391,7 @@ static struct dma_fence *panfrost_job_run(struct drm_sched_job *sched_job)
 	struct panfrost_device *pfdev = job->pfdev;
 	int slot = panfrost_job_get_slot(job);
 	struct dma_fence *fence = NULL;
+	int ret;
 
 	if (job->ctx->destroyed)
 		return ERR_PTR(-ECANCELED);
@@ -405,7 +413,11 @@ static struct dma_fence *panfrost_job_run(struct drm_sched_job *sched_job)
 		dma_fence_put(job->done_fence);
 	job->done_fence = dma_fence_get(fence);
 
-	panfrost_job_hw_submit(job, slot);
+	ret = panfrost_job_hw_submit(job, slot);
+	if (ret) {
+		dma_fence_put(fence);
+		return ERR_PTR(ret);
+	}
 
 	return fence;
 }
-- 
2.51.0