mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
synced 2026-05-05 18:13:26 -04:00
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.Yang@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
committed by
Alex Deucher
parent
30c1e39197
commit
cf63b70272
@@ -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);
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user