From 207ac684792560acdb9e06f9d707ebf63c84b0e0 Mon Sep 17 00:00:00 2001
From: Evan Quan <evan.quan@amd.com>
Date: Thu, 15 Oct 2020 14:57:46 +0800
Subject: [PATCH] drm/amdgpu: correct the gpu reset handling for job != NULL case
Git-commit: 207ac684792560acdb9e06f9d707ebf63c84b0e0
Patch-mainline: v5.10-rc1
References: git-fixes

Current code wrongly treat all cases as job == NULL.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-and-tested-by: Jane Jian <Jane.Jian@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Acked-by: Takashi Iwai <tiwai@suse.de>

---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3783,7 +3783,7 @@ retry:	/* Rest of adevs pre asic reset f
 
 		amdgpu_device_lock_adev(tmp_adev, false);
 		r = amdgpu_device_pre_asic_reset(tmp_adev,
-						 NULL,
+						 (tmp_adev == adev) ? job : NULL,
 						 &need_full_reset);
 		/*TODO Should we stop ?*/
 		if (r) {