Move gpu_reset_counter after drm_sched_stop to avoid race
condition caused by job submitted between reset_count +1 and
drm_sched_stop.
Signed-off-by: Jingwen Chen <jingwen.ch...@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index f0f7ed42ee7f..703b96cf3560 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4447,7 +4447,6 @@ static bool amdgpu_device_lock_adev(struct amdgpu_device
*adev,
down_write(&adev->reset_sem);
}
- atomic_inc(&adev->gpu_reset_counter);
switch (amdgpu_asic_reset_method(adev)) {
case AMD_RESET_METHOD_MODE1:
adev->mp1_state = PP_MP1_STATE_SHUTDOWN;
@@ -4708,6 +4707,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
if (need_emergency_restart)
amdgpu_job_stop_all_jobs_on_sched(&ring->sched);
}
+ atomic_inc(&tmp_adev->gpu_reset_counter);
}
if (need_emergency_restart)
@@ -5050,6 +5050,7 @@ pci_ers_result_t amdgpu_pci_error_detected(struct pci_dev
*pdev, pci_channel_sta
drm_sched_stop(&ring->sched, NULL);
}
+ atomic_inc(&adev->gpu_reset_counter);
return PCI_ERS_RESULT_NEED_RESET;
case pci_channel_io_perm_failure:
/* Permanent error, prepare for device removal */
--
2.25.1
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
