From: Yang Wang <kevinyang.wang@amd.com>
Date: Tue, 7 May 2024 02:28:04 +0000 (+0800)
Subject: drm/amdgpu: fix RAS unload driver issue in SRIOV
X-Git-Tag: v6.11-rc1~141^2~25^2~307
X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=329cec8f18fc8bed7570b68b18936724af2f5593;p=thirdparty%2Fkernel%2Flinux.git

drm/amdgpu: fix RAS unload driver issue in SRIOV

Fix null pointer issue when unload driver in SRIOV mode.

Adjust the function position to ensure that the amdgpu_mca/aca_xxx_init()
related functions can be initialized properly.

Signed-off-by: Yang Wang <kevinyang.wang@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 7b30f448eab63..2c5ad9530299c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -3605,10 +3605,6 @@ int amdgpu_ras_late_init(struct amdgpu_device *adev)
 	struct amdgpu_ras_block_object *obj;
 	int r;
 
-	/* Guest side doesn't need init ras feature */
-	if (amdgpu_sriov_vf(adev))
-		return 0;
-
 	amdgpu_ras_event_mgr_init(adev);
 
 	if (amdgpu_aca_is_enabled(adev)) {
@@ -3619,7 +3615,8 @@ int amdgpu_ras_late_init(struct amdgpu_device *adev)
 		if (r)
 			return r;
 
-		amdgpu_ras_set_aca_debug_mode(adev, false);
+		if (!amdgpu_sriov_vf(adev))
+			amdgpu_ras_set_aca_debug_mode(adev, false);
 	} else {
 		if (amdgpu_in_reset(adev))
 			r = amdgpu_mca_reset(adev);
@@ -3628,9 +3625,14 @@ int amdgpu_ras_late_init(struct amdgpu_device *adev)
 		if (r)
 			return r;
 
-		amdgpu_ras_set_mca_debug_mode(adev, false);
+		if (!amdgpu_sriov_vf(adev))
+			amdgpu_ras_set_mca_debug_mode(adev, false);
 	}
 
+	/* Guest side doesn't need init ras feature */
+	if (amdgpu_sriov_vf(adev))
+		return 0;
+
 	list_for_each_entry_safe(node, tmp, &adev->ras_list, node) {
 		obj = node->ras_obj;
 		if (!obj) {