From f905c1ab8a531782ccebd6c0f8df2e5e2335c0b2 Mon Sep 17 00:00:00 2001
From: Jack Zhang <Jack.Zhang1@amd.com>
Date: Mon, 18 May 2020 11:15:52 +0800
Subject: drm/amdgpu fix incorrect sysfs remove behavior for xgmi
Git-commit: a89b5dae3e68e5a543c5bcbeb04cf9a1dec2e687
Patch-mainline: v5.8-rc1
References: jsc#SLE-12680, jsc#SLE-12880, jsc#SLE-12882, jsc#SLE-12883, jsc#SLE-13496, jsc#SLE-15322

Under xgmi setup,some sysfs fail to create for the second time of kmd
driver loading. It's due to sysfs nodes are not removed appropriately
in the last unlod time.

Changes of this patch:
1. remove sysfs for dev_attr_xgmi_error
2. remove sysfs_link adev->dev->kobj with target name.
   And it only needs to be removed once for a xgmi setup
3. remove sysfs_link hive->kobj with target name

In amdgpu_xgmi_remove_device:
1. amdgpu_xgmi_sysfs_rem_dev_info needs to be run per device
2. amdgpu_xgmi_sysfs_destroy needs to be run on the last node of
device.

v2: initialize array with memset

Signed-off-by: Jack Zhang <Jack.Zhang1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Patrik Jakobsson <pjakobsson@suse.de>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c | 23 ++++++++++++++++-------
 1 file changed, 16 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
index e9e59bc68c9f..91837a991319 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
@@ -325,9 +325,18 @@ static int amdgpu_xgmi_sysfs_add_dev_info(struct amdgpu_device *adev,
 static void amdgpu_xgmi_sysfs_rem_dev_info(struct amdgpu_device *adev,
 					  struct amdgpu_hive_info *hive)
 {
+	char node[10];
+	memset(node, 0, sizeof(node));
+
 	device_remove_file(adev->dev, &dev_attr_xgmi_device_id);
-	sysfs_remove_link(&adev->dev->kobj, adev->ddev->unique);
-	sysfs_remove_link(hive->kobj, adev->ddev->unique);
+	device_remove_file(adev->dev, &dev_attr_xgmi_error);
+
+	if (adev != hive->adev)
+		sysfs_remove_link(&adev->dev->kobj,"xgmi_hive_info");
+
+	sprintf(node, "node%d", hive->number_devices);
+	sysfs_remove_link(hive->kobj, node);
+
 }
 
 
@@ -583,14 +592,14 @@ int amdgpu_xgmi_remove_device(struct amdgpu_device *adev)
 	if (!hive)
 		return -EINVAL;
 
-	if (!(hive->number_devices--)) {
+	task_barrier_rem_task(&hive->tb);
+	amdgpu_xgmi_sysfs_rem_dev_info(adev, hive);
+	mutex_unlock(&hive->hive_lock);
+
+	if(!(--hive->number_devices)){
 		amdgpu_xgmi_sysfs_destroy(adev, hive);
 		mutex_destroy(&hive->hive_lock);
 		mutex_destroy(&hive->reset_lock);
-	} else {
-		task_barrier_rem_task(&hive->tb);
-		amdgpu_xgmi_sysfs_rem_dev_info(adev, hive);
-		mutex_unlock(&hive->hive_lock);
 	}
 
 	return psp_xgmi_terminate(&adev->psp);
-- 
2.28.0