linux-kernel - [PATCH v2 3/3] drm/amdgpu: Make use of drm_wedge_app

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: <20250511224745.834446-4-andrealmeid@igalia.com>
Date: Sun, 11 May 2025 19:47:45 -0300
From: André Almeida <andrealmeid@...lia.com>
To: "Alex Deucher" <alexander.deucher@....com>,
	Christian König <christian.koenig@....com>,
	siqueira@...lia.com,
	airlied@...il.com,
	simona@...ll.ch,
	"Raag Jadav" <raag.jadav@...el.com>,
	rodrigo.vivi@...el.com,
	jani.nikula@...ux.intel.com,
	Xaver Hugl <xaver.hugl@...il.com>,
	"Pierre-Loup A . Griffais" <pgriffais@...vesoftware.com>
Cc: dri-devel@...ts.freedesktop.org,
	linux-kernel@...r.kernel.org,
	kernel-dev@...lia.com,
	amd-gfx@...ts.freedesktop.org,
	intel-xe@...ts.freedesktop.org,
	intel-gfx@...ts.freedesktop.org,
	André Almeida <andrealmeid@...lia.com>
Subject: [PATCH v2 3/3] drm/amdgpu: Make use of drm_wedge_app_info

To notify userspace about which app (if any) made the device get in a
wedge state, make use of drm_wedge_app_info parameter, filling it with
the app PID and name.

Signed-off-by: André Almeida <andrealmeid@...lia.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 19 +++++++++++++++++--
 drivers/gpu/drm/amd/amdgpu/amdgpu_job.c    |  6 +++++-
 2 files changed, 22 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index c8a51418d0e7..e6d8f6d0ec47 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -6215,8 +6215,23 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 
 	atomic_set(&adev->reset_domain->reset_res, r);
 
-	if (!r)
-		drm_dev_wedged_event(adev_to_drm(adev), DRM_WEDGE_RECOVERY_NONE, NULL);
+	if (!r) {
+		struct drm_wedge_app_info aux, *info = NULL;
+
+		if (job) {
+			struct amdgpu_task_info *ti;
+
+			ti = amdgpu_vm_get_task_info_pasid(adev, job->pasid);
+			if (ti) {
+				aux.pid = ti->pid;
+				aux.comm = ti->process_name;
+				info = &aux;
+				amdgpu_vm_put_task_info(ti);
+			}
+		}
+
+		drm_dev_wedged_event(adev_to_drm(adev), DRM_WEDGE_RECOVERY_NONE, info);
+	}
 
 	return r;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index a47b2eb301e5..98efa3318ddb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -89,6 +89,7 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
 {
 	struct amdgpu_ring *ring = to_amdgpu_ring(s_job->sched);
 	struct amdgpu_job *job = to_amdgpu_job(s_job);
+	struct drm_wedge_app_info aux, *info = NULL;
 	struct amdgpu_task_info *ti;
 	struct amdgpu_device *adev = ring->adev;
 	int idx;
@@ -127,6 +128,9 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
 		dev_err(adev->dev,
 			"Process information: process %s pid %d thread %s pid %d\n",
 			ti->process_name, ti->tgid, ti->task_name, ti->pid);
+		aux.pid = ti->pid;
+		aux.comm = ti->process_name;
+		info = &aux;
 		amdgpu_vm_put_task_info(ti);
 	}
 
@@ -166,7 +170,7 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
 			if (amdgpu_ring_sched_ready(ring))
 				drm_sched_start(&ring->sched, 0);
 			dev_err(adev->dev, "Ring %s reset succeeded\n", ring->sched.name);
-			drm_dev_wedged_event(adev_to_drm(adev), DRM_WEDGE_RECOVERY_NONE, NULL);
+			drm_dev_wedged_event(adev_to_drm(adev), DRM_WEDGE_RECOVERY_NONE, info);
 			goto exit;
 		}
 		dev_err(adev->dev, "Ring %s reset failure\n", ring->sched.name);
-- 
2.49.0