[AMD Official Use Only]
Reviewed-by: Hawking Zhang <hawking.zh...@amd.com>
Regards,
Hawking
-----Original Message-----
From: Stanley.Yang <stanley.y...@amd.com>
Sent: Tuesday, December 7, 2021 14:40
To: amd-gfx@lists.freedesktop.org; Zhang, Hawking <hawking.zh...@amd.com>;
Clements, John <john.cleme...@amd.com>; Zhou1, Tao <tao.zh...@amd.com>; Li,
Candice <candice...@amd.com>; Chai, Thomas <yipeng.c...@amd.com>
Cc: Yang, Stanley <stanley.y...@amd.com>
Subject: [PATCH Review 1/1] drm/amdgpu: skip umc ras error count harvest
remove in recovery stat check, skip umc ras err cnt harvest in
amdgpu_ras_log_on_err_counter
Signed-off-by: Stanley.Yang <stanley.y...@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 15 ++++++++++-----
1 file changed, 10 insertions(+), 5 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 1043d41b6807..a95d200adff9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -897,11 +897,6 @@ static void amdgpu_ras_get_ecc_info(struct amdgpu_device
*adev, struct ras_err_d
struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
int ret = 0;
- /* skip get ecc info during gpu recovery */
- if (atomic_read(&ras->in_recovery) == 1 &&
- adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 2))
- return;
-
/*
* choosing right query method according to
* whether smu support query error information @@ -1752,6 +1747,16 @@
static void amdgpu_ras_log_on_err_counter(struct amdgpu_device *adev)
if (info.head.block == AMDGPU_RAS_BLOCK__PCIE_BIF)
continue;
+ /*
+ * this is a workaround for aldebaran, skip send msg to
+ * smu to get ecc_info table due to smu handle get ecc
+ * info table failed temporarily.
+ * should be removed until smu fix handle ecc_info table.
+ */
+ if ((info.head.block == AMDGPU_RAS_BLOCK__UMC) &&
+ (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0,
2)))
+ continue;
+
amdgpu_ras_query_error_status(adev, &info);
}
}
--
2.17.1
