[PATCH] drm/amdgpu: fix RAS unload driver issue in SRIOV

[Zhang, Hawking]

[AMD Official Use Only - General]

Reviewed-by: Hawking Zhang <Hawking.Zhang at amd.com>

Regards,
Hawking
-----Original Message-----
From: Wang, Yang(Kevin) <KevinYang.Wang at amd.com>
Sent: Tuesday, May 7, 2024 10:50
To: amd-gfx at lists.freedesktop.org
Cc: Zhang, Hawking <Hawking.Zhang at amd.com>; Zhou1, Tao <Tao.Zhou1 at amd.com>; Li, Candice <Candice.Li at amd.com>
Subject: [PATCH] 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 at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 36509fa9fecf..36deac3b1440 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -3611,10 +3611,6 @@ 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)) {
@@ -3625,7 +3621,8 @@ 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);
@@ -3634,9 +3631,14 @@ 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) {
--
2.34.1