If the number of badpage records exceed the threshold, driver has
updated both epprom header and control->tbl_hdr.header before gpu reset,
therefore GPU recovery thread no need to read epprom header directly.
Signed-off-by: Dennis Li <dennis...@amd.com>
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index 19d9aa76cfbf..4310ad63890c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -439,41 +439,19 @@ int amdgpu_ras_eeprom_check_err_threshold(
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;
if (!__is_ras_eeprom_supported(adev))
return 0;
- /* 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) {
+ if (control->tbl_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;
}
--
2.17.1
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
