From 7ba6a309e9fd281ae0148e57a45cdcd49101bf6f Mon Sep 17 00:00:00 2001
From: Philip Yang <Philip.Yang@amd.com>
Date: Tue, 15 Mar 2022 14:38:51 -0400
Subject: drm/amdgpu: Move reset domain init before calling RREG32
Git-commit: 436afdfa35dc8aaf43959593f6c433d0ad29abc3
Patch-mainline: v5.18-rc1
References: jsc#PED-1166 jsc#PED-1168 jsc#PED-1170 jsc#PED-1218 jsc#PED-1220 jsc#PED-1222 jsc#PED-1223 jsc#PED-1225

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: d0fb18b535679a ("drm/amdgpu: Move reset sem into reset_domain")
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Patrik Jakobsson <pjakobsson@suse.de>
---
 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 1b313a95c7e5..3987ecb24ef4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3666,6 +3666,15 @@ 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);
 
@@ -3675,15 +3684,6 @@ 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)
-- 
2.38.1