github-mirror/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2026-05-28 17:13:52 +02:00
Code Issues Actions Packages Projects Releases Wiki Activity Graph

drm/amdgpu: Do a basic health check before reset

Browse Source 
Check if the device is present in the bus before trying to recover. It
could be that device itself is lost from the bus in some hang
situations.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Lijo Lazar 2024-03-13 15:07:10 +05:30 committed by Alex Deucher
parent f1b8479dc9
commit dfe9c3cde2
1 changed files with 24 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
View File

@ -5532,6 +5532,23 @@ static inline void amdgpu_device_stop_pending_resets(struct amdgpu_device *adev)
}
static int amdgpu_device_health_check(struct list_head *device_list_handle)
{
struct amdgpu_device *tmp_adev;
int ret = 0;
u32 status;
list_for_each_entry(tmp_adev, device_list_handle, reset_list) {
pci_read_config_dword(tmp_adev->pdev, PCI_COMMAND, &status);
if (PCI_POSSIBLE_ERROR(status)) {
dev_err(tmp_adev->dev, "device lost from bus!");
ret = -ENODEV;
}
}
return ret;
}
/**
* amdgpu_device_gpu_recover - reset the asic and recover scheduler
*
@ -5603,6 +5620,12 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
device_list_handle = &device_list;
}
if (!amdgpu_sriov_vf(adev)) {
r = amdgpu_device_health_check(device_list_handle);
if (r)
goto end_reset;
}
/* We need to lock reset domain only once both for XGMI and single device */
tmp_adev = list_first_entry(device_list_handle, struct amdgpu_device,
reset_list);
@ -5768,6 +5791,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
reset_list);
amdgpu_device_unlock_reset_domain(tmp_adev->reset_domain);
end_reset:
if (hive) {
mutex_unlock(&hive->hive_lock);
amdgpu_put_xgmi_hive(hive);