iv/linux
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

drm/amdgpu: change to save bad pages in UMC error interrupt callback

Browse Source 
Instead of saving bad pages in amdgpu_ras_reset_gpu, it will reduce
the unnecessary calling of amdgpu_ras_save_bad_pages.

Signed-off-by: Dennis Li <Dennis.Li@amd.com>
Reviewed-by: Hawking Zhang <hawking.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Dennis Li
2020-10-19 14:19:57 +08:00
committed by Alex Deucher
parent 9c94b5ef75
commit 22503d803d
3 changed files with 6 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
View File

@ -1668,7 +1668,7 @@ out:
* write error record array to eeprom, the function should be
* protected by recovery_lock
*/
static int amdgpu_ras_save_bad_pages(struct amdgpu_device *adev)
int amdgpu_ras_save_bad_pages(struct amdgpu_device *adev)
{
struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
struct ras_err_handler_data *data;
@ -1841,9 +1841,6 @@ int amdgpu_ras_reserve_bad_pages(struct amdgpu_device *adev)
data->last_reserved = i + 1;
bo = NULL;
}
/* continue to save bad pages to eeprom even reesrve_vram fails */
ret = amdgpu_ras_save_bad_pages(adev);
out:
mutex_unlock(&con->recovery_lock);
return ret;

1
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
View File

@ -506,6 +506,7 @@ bool amdgpu_ras_check_err_threshold(struct amdgpu_device *adev);
int amdgpu_ras_add_bad_pages(struct amdgpu_device *adev,
struct eeprom_table_record *bps, int pages);
int amdgpu_ras_save_bad_pages(struct amdgpu_device *adev);
int amdgpu_ras_reserve_bad_pages(struct amdgpu_device *adev);
static inline int amdgpu_ras_reset_gpu(struct amdgpu_device *adev)

7
drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
View File

@ -126,10 +126,11 @@ int amdgpu_umc_process_ras_data_cb(struct amdgpu_device *adev,
err_data->ue_count);
if ((amdgpu_bad_page_threshold != 0) &&
err_data->err_addr_cnt &&
err_data->err_addr_cnt) {
amdgpu_ras_add_bad_pages(adev, err_data->err_addr,
err_data->err_addr_cnt))
dev_warn(adev->dev, "Failed to add ras bad page!\n");
err_data->err_addr_cnt);
amdgpu_ras_save_bad_pages(adev);
}
amdgpu_ras_reset_gpu(adev);
}