summaryrefslogtreecommitdiff
path: root/drivers/gpu
diff options
context:
space:
mode:
authorSunil Khatri <sunil.khatri@amd.com>2026-09-17 18:56:45 +0530
committerAlex Deucher <alexander.deucher@amd.com>2026-09-23 13:01:31 -0400
commit13d44ca033cb74756c2aef0ade54a75cdf2f6271 (patch)
tree7a6b65d91a3807aa011d72e4dd203a2850d3d4c4 /drivers/gpu
parent5dc3f516cb610dd626178f36f9b25782e7a842dc (diff)
downloadlinux-next-13d44ca033cb74756c2aef0ade54a75cdf2f6271.tar.gz
linux-next-13d44ca033cb74756c2aef0ade54a75cdf2f6271.zip
drm/amdgpu/userq: fix double jiffies conversion in hang detect timeout
Function amdgpu_userq_start_hang_detect_work() calls msecs_to_jiffies() on adev->gfx_timeout/compute_timeout/sdma_timeout before arming hang_detect_work. These timeout values already hold jiffies values from amdgpu_device_get_job_timeout_settings() at device init. This silently shrinks the real hang-detect deadline to (2 * HZ) ms instead of the intended timeout. e.g. 500ms instead of the 2000ms default on a CONFIG_HZ=250 kernel, only coincidentally correct at HZ=1000. The shortened window is easily exceeded by ordinary fence-completion latency, causing hang_detect_work to fire and trigger a per-queue or full GPU reset for queues that are not actually hung. Pass the jiffies value directly to queue_delayed_work() instead of converting it a second time. Fixes: fc3336be9c62 ("drm/amd/amdgpu: Add independent hang detect work for user queue fence") Signed-off-by: Sunil Khatri <sunil.khatri@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Diffstat (limited to 'drivers/gpu')
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c12
1 files changed, 6 insertions, 6 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
index 5d07320a29b2..75d5ceaa53c6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
@@ -184,27 +184,27 @@ static void amdgpu_userq_hang_detect_work(struct work_struct *work)
void amdgpu_userq_start_hang_detect_work(struct amdgpu_usermode_queue *queue)
{
struct amdgpu_device *adev;
- unsigned long timeout_ms;
+ unsigned long timeout_jiffies;
adev = queue->userq_mgr->adev;
/* Determine timeout based on queue type */
switch (queue->queue_type) {
case AMDGPU_RING_TYPE_GFX:
- timeout_ms = adev->gfx_timeout;
+ timeout_jiffies = adev->gfx_timeout;
break;
case AMDGPU_RING_TYPE_COMPUTE:
- timeout_ms = adev->compute_timeout;
+ timeout_jiffies = adev->compute_timeout;
break;
case AMDGPU_RING_TYPE_SDMA:
- timeout_ms = adev->sdma_timeout;
+ timeout_jiffies = adev->sdma_timeout;
break;
default:
- timeout_ms = adev->gfx_timeout;
+ timeout_jiffies = adev->gfx_timeout;
break;
}
queue_delayed_work(adev->reset_domain->wq, &queue->hang_detect_work,
- msecs_to_jiffies(timeout_ms));
+ timeout_jiffies);
}
void amdgpu_userq_process_fence_irq(struct amdgpu_device *adev, u32 doorbell)