From 55a8d1fc5e5326c260d63d6ecab63215a6840cfd Mon Sep 17 00:00:00 2001
From: Tao Zhou <tao.zhou1@amd.com>
Date: Mon, 30 Oct 2023 20:44:37 +0800
Subject: drm/amdgpu: check recovery status of xgmi hive in
ras_reset_error_count
Git-commit: 18eae367cb74d05b5e37ce77ef4025b735df012e
Patch-mainline: v6.7-rc1
References: jsc#PED-3527 jsc#PED-5475 jsc#PED-6068 jsc#PED-6070 jsc#PED-6116 jsc#PED-6120 jsc#PED-5065 jsc#PED-5477 jsc#PED-5511 jsc#PED-6041 jsc#PED-6069 jsc#PED-6071
Handle xgmi hive case.
Suggested-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Stanley.Yang <Stanley.Yang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Patrik Jakobsson <pjakobsson@suse.de>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 11 ++++++++++-
1 file changed, 10 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 3af50754800d..b7fe5951b166 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1222,6 +1222,8 @@ int amdgpu_ras_reset_error_count(struct amdgpu_device *adev,
struct amdgpu_ras_block_object *block_obj = amdgpu_ras_get_ras_block(adev, block, 0);
struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
const struct amdgpu_mca_smu_funcs *mca_funcs = adev->mca.mca_funcs;
+ struct amdgpu_hive_info *hive;
+ int hive_ras_recovery = 0;
if (!block_obj || !block_obj->hw_ops) {
dev_dbg_once(adev->dev, "%s doesn't config RAS function\n",
@@ -1233,8 +1235,15 @@ int amdgpu_ras_reset_error_count(struct amdgpu_device *adev,
!amdgpu_ras_get_mca_debug_mode(adev))
return -EOPNOTSUPP;
+ hive = amdgpu_get_xgmi_hive(adev);
+ if (hive) {
+ hive_ras_recovery = atomic_read(&hive->ras_recovery);
+ amdgpu_put_xgmi_hive(hive);
+ }
+
/* skip ras error reset in gpu reset */
- if ((amdgpu_in_reset(adev) || atomic_read(&ras->in_recovery)) &&
+ if ((amdgpu_in_reset(adev) || atomic_read(&ras->in_recovery) ||
+ hive_ras_recovery) &&
mca_funcs && mca_funcs->mca_set_debug_mode)
return -EOPNOTSUPP;
--
2.43.0