amdgpu_detect_virtualization reads register, amdgpu_device_rreg access
adev->reset_domain->sem if kernel defined CONFIG_LOCKDEP, below is the
random boot hang backtrace on Vega10. It may get random NULL pointer
access backtrace if amdgpu_sriov_runtime is true too.
Move amdgpu_reset_create_reset_domain before calling to RREG32.
BUG: kernel NULL pointer dereference, address:
#PF: supervisor read access in kernel mode
#PF: error_code(0x0000) - not-present page
PGD 0 P4D 0
Oops: 0000 [#1] PREEMPT SMP NOPTI
Workqueue: events work_for_cpu_fn
RIP: 0010:down_read_trylock+0x13/0xf0
Call Trace:
<TASK>
amdgpu_device_skip_hw_access+0x38/0x80 [amdgpu]
amdgpu_device_rreg+0x1b/0x170 [amdgpu]
amdgpu_detect_virtualization+0x73/0x100 [amdgpu]
amdgpu_device_init.cold.60+0xbe/0x16b1 [amdgpu]
? pci_bus_read_config_word+0x43/0x70
amdgpu_driver_load_kms+0x15/0x120 [amdgpu]
amdgpu_pci_probe+0x1a1/0x3a0 [amdgpu]
Fixes: 1228996f0 ("drm/amdgpu: Move reset sem into reset_domain")
Signed-off-by: Philip Yang <Philip.Yang@xxxxxxx>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 18 +++++++++---------
1 file changed, 9 insertions(+), 9 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 71876ff466df..a35c6acfe2ab 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3665,6 +3665,15 @@ int amdgpu_device_init(struct amdgpu_device *adev,
if (amdgpu_mes && adev->asic_type >= CHIP_NAVI10)
adev->enable_mes = true;
+ /*
+ * Reset domain needs to be present early, before XGMI hive discovered
+ * (if any) and intitialized to use reset sem and in_gpu reset flag
+ * early on during init and before calling to RREG32.
+ */
+ adev->reset_domain = amdgpu_reset_create_reset_domain(SINGLE_DEVICE, "amdgpu-reset-dev");
+ if (!adev->reset_domain)
+ return -ENOMEM;
+
/* detect hw virtualization here */
amdgpu_detect_virtualization(adev);
@@ -3674,15 +3683,6 @@ int amdgpu_device_init(struct amdgpu_device *adev,
return r;
}
- /*
- * Reset domain needs to be present early, before XGMI hive discovered
- * (if any) and intitialized to use reset sem and in_gpu reset flag
- * early on during init.
- */
- adev->reset_domain = amdgpu_reset_create_reset_domain(SINGLE_DEVICE, "amdgpu-reset-dev");
- if (!adev->reset_domain)
- return -ENOMEM;
-
/* early init functions */
r = amdgpu_device_ip_early_init(adev);
if (r)
--
2.35.1
