net: hns3: fix oops when unload drivers paralleling

[ Upstream commit 92e5995773 ]

When unload hclge driver, it tries to disable sriov first for each
ae_dev node from hnae3_ae_dev_list. If user unloads hns3 driver at
the time, because it removes all the ae_dev nodes, and it may cause
oops.

But we can't simply use hnae3_common_lock for this. Because in the
process flow of pci_disable_sriov(), it will trigger the remove flow
of VF, which will also take hnae3_common_lock.

To fixes it, introduce a new mutex to protect the unload process.

Fixes: 0dd8a25f35 ("net: hns3: disable sriov before unload hclge layer")
Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Jijie Shao <shaojijie@huawei.com>
Link: https://patch.msgid.link/20250118094741.3046663-1-shaojijie@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>

drivers/net/ethernet/hisilicon/hns3/hnae3.c

@@ -40,6 +40,21 @@ EXPORT_SYMBOL(hnae3_unregister_ae_algo_prepare);
  */
 static DEFINE_MUTEX(hnae3_common_lock);
 
+/* ensure the drivers being unloaded one by one */
+static DEFINE_MUTEX(hnae3_unload_lock);
+
+void hnae3_acquire_unload_lock(void)
+{
+	mutex_lock(&hnae3_unload_lock);
+}
+EXPORT_SYMBOL(hnae3_acquire_unload_lock);
+
+void hnae3_release_unload_lock(void)
+{
+	mutex_unlock(&hnae3_unload_lock);
+}
+EXPORT_SYMBOL(hnae3_release_unload_lock);
+
 static bool hnae3_client_match(enum hnae3_client_type client_type)
 {
 	if (client_type == HNAE3_CLIENT_KNIC ||

drivers/net/ethernet/hisilicon/hns3/hnae3.h

@@ -946,4 +946,6 @@ int hnae3_register_client(struct hnae3_client *client);
 void hnae3_set_client_init_flag(struct hnae3_client *client,
 				struct hnae3_ae_dev *ae_dev,
 				unsigned int inited);
+void hnae3_acquire_unload_lock(void);
+void hnae3_release_unload_lock(void);
 #endif

drivers/net/ethernet/hisilicon/hns3/hns3_enet.c

@@ -6008,9 +6008,11 @@ module_init(hns3_init_module);
  */
 static void __exit hns3_exit_module(void)
 {
+	hnae3_acquire_unload_lock();
 	pci_unregister_driver(&hns3_driver);
 	hnae3_unregister_client(&client);
 	hns3_dbg_unregister_debugfs();
+	hnae3_release_unload_lock();
 }
 module_exit(hns3_exit_module);
 

drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c

@@ -12814,9 +12814,11 @@ static int __init hclge_init(void)
 
 static void __exit hclge_exit(void)
 {
+	hnae3_acquire_unload_lock();
 	hnae3_unregister_ae_algo_prepare(&ae_algo);
 	hnae3_unregister_ae_algo(&ae_algo);
 	destroy_workqueue(hclge_wq);
+	hnae3_release_unload_lock();
 }
 module_init(hclge_init);
 module_exit(hclge_exit);

drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c

@@ -3345,8 +3345,10 @@ static int __init hclgevf_init(void)
 
 static void __exit hclgevf_exit(void)
 {
+	hnae3_acquire_unload_lock();
 	hnae3_unregister_ae_algo(&ae_algovf);
 	destroy_workqueue(hclgevf_wq);
+	hnae3_release_unload_lock();
 }
 module_init(hclgevf_init);
 module_exit(hclgevf_exit);