github-mirror/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2026-05-31 02:24:24 +02:00
Code Issues Actions Packages Projects Releases Wiki Activity Graph

drm/amdgpu: optimize timeout implemention in ras_eeprom_update_record_num

Browse Source 
The busy status returned by ras_eeprom_update_record_num may not be
an error, increase timeout to exclude false busy status. Also add more
comments to make the code readable.

v2: define a macro for the timeout value.

Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Tao Zhou 2025-11-06 16:26:56 +08:00 committed by Alex Deucher
parent eed3015274
commit 7fb41ab3c9
1 changed files with 13 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
View File

@ -124,6 +124,8 @@
RAS_TABLE_V2_1_INFO_SIZE) \
/ RAS_TABLE_RECORD_SIZE)
#define RAS_SMU_MESSAGE_TIMEOUT_MS 1000 /* 1s */
/* Given a zero-based index of an EEPROM RAS record, yields the EEPROM
* offset off of RAS_TABLE_START. That is, this is something you can
* add to control->i2c_address, and then tell I2C layer to read
@ -874,7 +876,7 @@ amdgpu_ras_eeprom_update_header(struct amdgpu_ras_eeprom_control *control)
int amdgpu_ras_eeprom_update_record_num(struct amdgpu_ras_eeprom_control *control)
{
struct amdgpu_device *adev = to_amdgpu_device(control);
int ret, timeout = 1000;
int ret, retry = 20;
if (!amdgpu_ras_smu_eeprom_supported(adev))
return 0;
@ -882,17 +884,23 @@ int amdgpu_ras_eeprom_update_record_num(struct amdgpu_ras_eeprom_control *contro
control->ras_num_recs_old = control->ras_num_recs;
do {
/* 1000ms timeout is long enough, smu_get_badpage_count won't
* return -EBUSY before timeout.
*/
ret = amdgpu_ras_smu_get_badpage_count(adev,
&(control->ras_num_recs), 12);
&(control->ras_num_recs), RAS_SMU_MESSAGE_TIMEOUT_MS);
if (!ret &&
(control->ras_num_recs_old == control->ras_num_recs)) {
/* record number update in PMFW needs some time */
/* record number update in PMFW needs some time,
* smu_get_badpage_count may return immediately without
* count update, sleep for a while and retry again.
*/
msleep(50);
timeout -= 50;
retry--;
} else {
break;
}
} while (timeout);
} while (retry);
/* no update of record number is not a real failure,
* don't print warning here