From 8d3f8197d910bd606a94a68a6c4c7f7bcd3b26ce Mon Sep 17 00:00:00 2001
From: Hawking Zhang <Hawking.Zhang@amd.com>
Date: Mon, 31 Jul 2023 23:43:12 +0800
Subject: drm/amdgpu: Only create err_count sysfs when hw_op is supported
Git-commit: f957138cc30ae904346f117013fc7b428700c1f7
Patch-mainline: v6.6-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
Some IP blocks only support partial ras feature and don't
have ras counter and/or ras error status register at all.
Driver should not create err_count sysfs node for those
IP blocks.
Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@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 | 31 ++++++++++++++-----------
1 file changed, 18 insertions(+), 13 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 62011a521833..fa53a51db69f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -2777,23 +2777,28 @@ int amdgpu_ras_block_late_init(struct amdgpu_device *adev,
goto cleanup;
}
- r = amdgpu_ras_sysfs_create(adev, ras_block);
- if (r)
- goto interrupt;
+ if (ras_obj->hw_ops &&
+ (ras_obj->hw_ops->query_ras_error_count ||
+ ras_obj->hw_ops->query_ras_error_status)) {
+ r = amdgpu_ras_sysfs_create(adev, ras_block);
+ if (r)
+ goto interrupt;
- /* Those are the cached values at init.
- */
- query_info = kzalloc(sizeof(struct ras_query_if), GFP_KERNEL);
- if (!query_info)
- return -ENOMEM;
- memcpy(&query_info->head, ras_block, sizeof(struct ras_common_if));
+ /* Those are the cached values at init.
+ */
+ query_info = kzalloc(sizeof(*query_info), GFP_KERNEL);
+ if (!query_info)
+ return -ENOMEM;
+ memcpy(&query_info->head, ras_block, sizeof(struct ras_common_if));
- if (amdgpu_ras_query_error_count(adev, &ce_count, &ue_count, query_info) == 0) {
- atomic_set(&con->ras_ce_count, ce_count);
- atomic_set(&con->ras_ue_count, ue_count);
+ if (amdgpu_ras_query_error_count(adev, &ce_count, &ue_count, query_info) == 0) {
+ atomic_set(&con->ras_ce_count, ce_count);
+ atomic_set(&con->ras_ue_count, ue_count);
+ }
+
+ kfree(query_info);
}
- kfree(query_info);
return 0;
interrupt:
--
2.43.0