Minki/linux
1
0
Fork 1
mirror of https://github.com/torvalds/linux.git synced 2024-11-27 14:41:39 +00:00
Code Issues Packages Projects Releases Wiki Activity

drm/amdgpu: add RAS page retirement functions for MCA

Browse Source 
Define page retirement functions for MCA platform.

v2: remove page retirement handling from MCA poison handler,
    let MCA notifier do page retirement.

v3: remove specific poison handler for MCA to simplify code.

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 2022-10-17 18:22:13 +08:00 committed by Alex Deucher
parent 2513574853
commit cbe4d43ea5
2 changed files with 55 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

53
drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
View File

@ -22,6 +22,59 @@
*/
#include "amdgpu.h"
#include "umc_v6_7.h"
static int amdgpu_umc_convert_error_address(struct amdgpu_device *adev,
struct ras_err_data *err_data, uint64_t err_addr,
uint32_t ch_inst, uint32_t umc_inst)
{
switch (adev->ip_versions[UMC_HWIP][0]) {
case IP_VERSION(6, 7, 0):
umc_v6_7_convert_error_address(adev,
err_data, err_addr, ch_inst, umc_inst);
break;
default:
dev_warn(adev->dev,
"UMC address to Physical address translation is not supported\n");
return AMDGPU_RAS_FAIL;
}
return AMDGPU_RAS_SUCCESS;
}
int amdgpu_umc_page_retirement_mca(struct amdgpu_device *adev,
uint64_t err_addr, uint32_t ch_inst, uint32_t umc_inst)
{
struct ras_err_data err_data = {0, 0, 0, NULL};
int ret = AMDGPU_RAS_FAIL;
err_data.err_addr =
kcalloc(adev->umc.max_ras_err_cnt_per_query,
sizeof(struct eeprom_table_record), GFP_KERNEL);
if (!err_data.err_addr) {
dev_warn(adev->dev,
"Failed to alloc memory for umc error record in MCA notifier!\n");
return AMDGPU_RAS_FAIL;
}
/*
* Translate UMC channel address to Physical address
*/
ret = amdgpu_umc_convert_error_address(adev, &err_data, err_addr,
ch_inst, umc_inst);
if (ret)
goto out;
if (amdgpu_bad_page_threshold != 0) {
amdgpu_ras_add_bad_pages(adev, err_data.err_addr,
err_data.err_addr_cnt);
amdgpu_ras_save_bad_pages(adev);
}
out:
kfree(err_data.err_addr);
return ret;
}
static int amdgpu_umc_do_page_retirement(struct amdgpu_device *adev,
void *ras_error_status,

2
drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h
View File

@ -98,4 +98,6 @@ void amdgpu_umc_fill_error_record(struct ras_err_data *err_data,
int amdgpu_umc_process_ras_data_cb(struct amdgpu_device *adev,
void *ras_error_status,
struct amdgpu_iv_entry *entry);
int amdgpu_umc_page_retirement_mca(struct amdgpu_device *adev,
uint64_t err_addr, uint32_t ch_inst, uint32_t umc_inst);
#endif