git/linux-net
1
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git/ synced 2026-04-18 06:33:43 -04:00
Code Issues Packages Projects Releases Wiki Activity

drm/amdgpu: suspend ras module before gpu reset

Browse Source 
During gpu reset, all GPU-related resources are
inaccessible. To avoid affecting ras functionality,
suspend ras module before gpu reset and resume
it after gpu reset is complete.

V2:
  Rename functions to avoid misunderstanding.

V3:
  Move flush_delayed_work to amdgpu_ras_process_pause,
  Move schedule_delayed_work to amdgpu_ras_process_unpause.

V4:
  Rename functions.

V5:
  Move the function to amdgpu_ras.c.

Signed-off-by: YiPeng Chai <YiPeng.Chai@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Acked-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
YiPeng Chai
2025-10-28 16:18:31 +08:00
committed by Alex Deucher
parent d4432f16d3
commit d95ca7f515
10 changed files with 148 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
View File

@@ -71,6 +71,7 @@
#include "amdgpu_xgmi.h"
#include "amdgpu_ras.h"
#include "amdgpu_ras_mgr.h"
#include "amdgpu_pmu.h"
#include "amdgpu_fru_eeprom.h"
#include "amdgpu_reset.h"
@@ -6660,6 +6661,9 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
goto end_reset;
}
/* Cannot be called after locking reset domain */
amdgpu_ras_pre_reset(adev, &device_list);
/* We need to lock reset domain only once both for XGMI and single device */
amdgpu_device_recovery_get_reset_lock(adev, &device_list);
@@ -6691,6 +6695,7 @@ skip_sched_resume:
reset_unlock:
amdgpu_device_recovery_put_reset_lock(adev, &device_list);
end_reset:
amdgpu_ras_post_reset(adev, &device_list);
if (hive) {
mutex_unlock(&hive->hive_lock);
amdgpu_put_xgmi_hive(hive);