UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity

drm/amdgpu: use RAS error address convert api in mca notifier 

Use the convert interface 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 2022-09-21 16:46:19 +08:00 committed by Alex Deucher
parent 1014bd1cb3
commit cd4c99f103
1 changed files with 15 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
View File

@ -2834,11 +2834,8 @@ static int amdgpu_bad_page_notifier(struct notifier_block *nb,
struct mce *m = (struct mce *)data; struct mce *m = (struct mce *)data;
struct amdgpu_device *adev = NULL; struct amdgpu_device *adev = NULL;
uint32_t gpu_id = 0; uint32_t gpu_id = 0;
uint32_t umc_inst = 0; uint32_t umc_inst = 0, ch_inst = 0;
uint32_t ch_inst, channel_index = 0;
struct ras_err_data err_data = {0, 0, 0, NULL}; struct ras_err_data err_data = {0, 0, 0, NULL};
struct eeprom_table_record err_rec;
uint64_t retired_page;
/* /*
* If the error was generated in UMC_V2, which belongs to GPU UMCs, * If the error was generated in UMC_V2, which belongs to GPU UMCs,
@ -2877,21 +2874,22 @@ static int amdgpu_bad_page_notifier(struct notifier_block *nb,
dev_info(adev->dev, "Uncorrectable error detected in UMC inst: %d, chan_idx: %d", dev_info(adev->dev, "Uncorrectable error detected in UMC inst: %d, chan_idx: %d",
umc_inst, ch_inst); umc_inst, ch_inst);
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 address record in mca notifier!\n");
return NOTIFY_DONE;
}
/* /*
* Translate UMC channel address to Physical address * Translate UMC channel address to Physical address
*/ */
channel_index = if (adev->umc.ras &&
adev->umc.channel_idx_tbl[umc_inst * adev->umc.channel_inst_num adev->umc.ras->convert_ras_error_address)
+ ch_inst]; adev->umc.ras->convert_ras_error_address(adev,
&err_data, 0, ch_inst, umc_inst, m->addr);
retired_page = ADDR_OF_8KB_BLOCK(m->addr) |
ADDR_OF_256B_BLOCK(channel_index) |
OFFSET_IN_256B_BLOCK(m->addr);
memset(&err_rec, 0x0, sizeof(struct eeprom_table_record));
err_data.err_addr = &err_rec;
amdgpu_umc_fill_error_record(&err_data, m->addr,
retired_page, channel_index, umc_inst);
if (amdgpu_bad_page_threshold != 0) { if (amdgpu_bad_page_threshold != 0) {
amdgpu_ras_add_bad_pages(adev, err_data.err_addr, amdgpu_ras_add_bad_pages(adev, err_data.err_addr,
@ -2899,6 +2897,7 @@ static int amdgpu_bad_page_notifier(struct notifier_block *nb,
amdgpu_ras_save_bad_pages(adev); amdgpu_ras_save_bad_pages(adev);
} }
kfree(err_data.err_addr);
return NOTIFY_OK; return NOTIFY_OK;
} }