torvalds/linux
3
0
Fork 0
mirror of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2026-03-22 07:27:12 +08:00
Code Issues Packages Projects Releases Wiki Activity

drm/amdgpu: refine eeprom data check

Browse Source 
add eeprom data checksum check before driver unload. reset eeprom
and save correct data to eeprom when check failed

Signed-off-by: ganglxie <ganglxie@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
ganglxie
2025-07-02 16:56:22 +08:00
committed by Alex Deucher
parent 340231cdce
commit 660261df61
3 changed files with 31 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
View File

@@ -2512,6 +2512,7 @@ amdgpu_pci_remove(struct pci_dev *pdev)
struct drm_device *dev = pci_get_drvdata(pdev);
struct amdgpu_device *adev = drm_to_adev(dev);
amdgpu_ras_eeprom_check_and_recover(adev);
amdgpu_xcp_dev_unplug(adev);
amdgpu_gmc_prepare_nps_mode_change(adev);
drm_dev_unplug(dev);

28
drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
View File

@@ -1531,3 +1531,31 @@ int amdgpu_ras_eeprom_check(struct amdgpu_ras_eeprom_control *control)
return res < 0 ? res : 0;
}
void amdgpu_ras_eeprom_check_and_recover(struct amdgpu_device *adev)
{
struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
struct amdgpu_ras_eeprom_control *control;
int res;
if (!__is_ras_eeprom_supported(adev) || !ras)
return;
control = &ras->eeprom_control;
if (!control->is_eeprom_valid)
return;
res = __verify_ras_table_checksum(control);
if (res) {
dev_warn(adev->dev,
"RAS table incorrect checksum or error:%d, try to recover\n",
res);
if (!amdgpu_ras_eeprom_reset_table(control))
if (!amdgpu_ras_save_bad_pages(adev, NULL))
if (!__verify_ras_table_checksum(control)) {
dev_info(adev->dev, "RAS table recovery succeed\n");
return;
}
dev_err(adev->dev, "RAS table recovery failed\n");
control->is_eeprom_valid = false;
}
return;
}

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

@@ -161,6 +161,8 @@ void amdgpu_ras_debugfs_set_ret_size(struct amdgpu_ras_eeprom_control *control);
int amdgpu_ras_eeprom_check(struct amdgpu_ras_eeprom_control *control);
void amdgpu_ras_eeprom_check_and_recover(struct amdgpu_device *adev);
extern const struct file_operations amdgpu_ras_debugfs_eeprom_size_ops;
extern const struct file_operations amdgpu_ras_debugfs_eeprom_table_ops;