From: xinhui pan <xinhui.pan@amd.com>
Date: Wed, 8 May 2019 11:31:06 +0000 (+0800)
Subject: drm/amdgpu: Revert "drm/amdgpu: skip gpu reset when ras error occured"
X-Git-Url: http://git.lede-project.org./?a=commitdiff_plain;h=b152e8e13e883656c0012504c451d483579aa842;p=openwrt%2Fstaging%2Fblogic.git

drm/amdgpu: Revert "drm/amdgpu: skip gpu reset when ras error occured"

Enable this now to reset the GPU on RAS errors.

This reverts commit 138352e5752aa3e694951d70c8fe8730219f4edf.

Signed-off-by: xinhui pan <xinhui.pan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
index eaef5edefc34..e60a554656ca 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
@@ -187,13 +187,10 @@ int amdgpu_ras_reserve_bad_pages(struct amdgpu_device *adev);
 static inline int amdgpu_ras_reset_gpu(struct amdgpu_device *adev,
 		bool is_baco)
 {
-	/* remove me when gpu reset works on vega20 A1. */
-#if 0
 	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
 
 	if (atomic_cmpxchg(&ras->in_recovery, 0, 1) == 0)
 		schedule_work(&ras->recovery_work);
-#endif
 	return 0;
 }