git/linux-cryptodev-2.6
1
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/herbert/cryptodev-2.6.git synced 2026-04-23 05:56:14 -04:00
Code Issues Packages Projects Releases Wiki Activity

drm/amdgpu: break GPU recovery once it's in bad state(v4)

Browse Source 
When GPU executes recovery and retriving bad GPU tag
from external eerpom device, the recovery will be broken
and error message is printed as well for user's awareness.

v2: Refine warning message in threshold reaching case, and
    fix spelling typo.

v3: Fix explicit calling of bad gpu.

v4: Rename function names.

Signed-off-by: Guchun Chen <guchun.chen@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Guchun Chen
2020-07-23 16:20:02 +08:00
committed by Alex Deucher
parent 9c06f91ff2
commit e8fbaf0342
5 changed files with 79 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

40
drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
View File

@@ -386,6 +386,46 @@ static uint32_t __correct_eeprom_dest_address(uint32_t curr_address)
return curr_address;
}
int amdgpu_ras_eeprom_check_err_threshold(
struct amdgpu_ras_eeprom_control *control,
bool *exceed_err_limit)
{
struct amdgpu_device *adev = to_amdgpu_device(control);
unsigned char buff[EEPROM_ADDRESS_SIZE +
EEPROM_TABLE_HEADER_SIZE] = { 0 };
struct amdgpu_ras_eeprom_table_header *hdr = &control->tbl_hdr;
struct i2c_msg msg = {
.addr = control->i2c_address,
.flags = I2C_M_RD,
.len = EEPROM_ADDRESS_SIZE + EEPROM_TABLE_HEADER_SIZE,
.buf = buff,
};
int ret;
*exceed_err_limit = false;
/* read EEPROM table header */
mutex_lock(&control->tbl_mutex);
ret = i2c_transfer(&adev->pm.smu_i2c, &msg, 1);
if (ret < 1) {
dev_err(adev->dev, "Failed to read EEPROM table header.\n");
goto err;
}
__decode_table_header_from_buff(hdr, &buff[2]);
if (hdr->header == EEPROM_TABLE_HDR_BAD) {
dev_warn(adev->dev, "This GPU is in BAD status.");
dev_warn(adev->dev, "Please retire it or setting one bigger "
"threshold value when reloading driver.\n");
*exceed_err_limit = true;
}
err:
mutex_unlock(&control->tbl_mutex);
return 0;
}
int amdgpu_ras_eeprom_process_recods(struct amdgpu_ras_eeprom_control *control,
struct eeprom_table_record *records,
bool write,