From 8f2e795ce64c90899039f85de606e218b36487f1 Mon Sep 17 00:00:00 2001
From: "Stanley.Yang" <Stanley.Yang@amd.com>
Date: Fri, 26 Nov 2021 17:24:39 +0800
Subject: drm/amdgpu: fix disable ras feature failed when unload drvier v2
Git-commit: 232d1d43b522b64266a16606e918ce92a8a0b244
Patch-mainline: v5.17-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
v2:
still need call ras_disable_all_featrures to handle
ras initilization failure case.
Function amdgpu_device_fini_hw is called before amdgpu_device_fini_sw,
so ras ta will unload before send ras disable command, ras dsiable operation
must before hw fini.
Signed-off-by: Stanley.Yang <Stanley.Yang@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@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 | 5 +++--
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 1 -
2 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index da21db47411e..ab9250cea846 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2733,8 +2733,6 @@ static int amdgpu_device_ip_fini(struct amdgpu_device *adev)
if (amdgpu_sriov_vf(adev) && adev->virt.ras_init_done)
amdgpu_virt_release_ras_err_handler_data(adev);
- amdgpu_ras_pre_fini(adev);
-
if (adev->gmc.xgmi.num_physical_nodes > 1)
amdgpu_xgmi_remove_device(adev);
@@ -3850,6 +3848,9 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev)
amdgpu_ucode_sysfs_fini(adev);
sysfs_remove_files(&adev->dev->kobj, amdgpu_dev_attributes);
+ /* disable ras feature must before hw fini */
+ amdgpu_ras_pre_fini(adev);
+
amdgpu_device_ip_fini_early(adev);
amdgpu_irq_fini_hw(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 68335b6c3c42..54a227cfafa5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -2503,7 +2503,6 @@ void amdgpu_ras_late_fini(struct amdgpu_device *adev,
amdgpu_ras_sysfs_remove(adev, ras_block);
if (ih_info->cb)
amdgpu_ras_interrupt_remove_handler(adev, ih_info);
- amdgpu_ras_feature_enable(adev, ras_block, 0);
}
/* do some init work after IP late init as dependence.
--
2.38.1