From 88f8575bca5fc70ba8608cfc49811f9b4d1eb6f9 Mon Sep 17 00:00:00 2001 From: Dennis Li Date: Fri, 5 Mar 2021 16:30:54 -0500 Subject: drm/amdgpu: enable watchdog feature for SQ of aldebaran SQ's watchdog timer monitors forward progress, a mask of which waves caused the watchdog timeout is recorded into ras status registers and then trigger a system fatal error event. v2: 1. change *query_timeout_status to *query_sq_timeout_status. 2. move query_sq_timeout_status into amdgpu_ras_do_recovery. 3. add module parameters to enable/disable fatal error event and modify the watchdog timer. v3: 1. remove unused parameters of *enable_watchdog_timer Signed-off-by: Dennis Li Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index c669435ccc74..c1516d871881 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -1467,6 +1467,9 @@ static void amdgpu_ras_error_status_query(struct amdgpu_device *adev, case AMDGPU_RAS_BLOCK__GFX: if (adev->gfx.funcs->query_ras_error_status) adev->gfx.funcs->query_ras_error_status(adev); + + if (adev->gfx.funcs->query_sq_timeout_status) + adev->gfx.funcs->query_sq_timeout_status(adev); break; case AMDGPU_RAS_BLOCK__MMHUB: if (adev->mmhub.funcs->query_ras_error_status) -- cgit v1.2.3