net: hns3: fix kernel crash problem in concurrent scenario

BugLink: https://bugs.launchpad.net/bugs/2074091
[ Upstream commit 12cda920212a49fa22d9e8b9492ac4ea013310a4 ]

When link status change, the nic driver need to notify the roce
driver to handle this event, but at this time, the roce driver
may uninit, then cause kernel crash.

To fix the problem, when link status change, need to check
whether the roce registered, and when uninit, need to wait link
update finish.

Fixes: 45e92b7e4e27 ("net: hns3: add calling roce callback function when link status change")
Signed-off-by: Yonglong Liu <liuyonglong@huawei.com>
Signed-off-by: Jijie Shao <shaojijie@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Portia Stephens <portia.stephens@canonical.com>
Signed-off-by: Roxana Nicolescu <roxana.nicolescu@canonical.com>

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index c55b5430b75a902ee3ef192369711d3bc842bcb9..09e007d3d1daca8f524503bf6d96ec6d320e8126 100644 (file)
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -3029,9 +3029,7 @@ static void hclge_push_link_status(struct hclge_dev *hdev)
 
 static void hclge_update_link_status(struct hclge_dev *hdev)
 {
-       struct hnae3_handle *rhandle = &hdev->vport[0].roce;
        struct hnae3_handle *handle = &hdev->vport[0].nic;
-       struct hnae3_client *rclient = hdev->roce_client;
        struct hnae3_client *client = hdev->nic_client;
        int state;
        int ret;
@@ -3055,8 +3053,15 @@ static void hclge_update_link_status(struct hclge_dev *hdev)
 
                client->ops->link_status_change(handle, state);
                hclge_config_mac_tnl_int(hdev, state);
-               if (rclient && rclient->ops->link_status_change)
-                       rclient->ops->link_status_change(rhandle, state);
+
+               if (test_bit(HCLGE_STATE_ROCE_REGISTERED, &hdev->state)) {
+                       struct hnae3_handle *rhandle = &hdev->vport[0].roce;
+                       struct hnae3_client *rclient = hdev->roce_client;
+
+                       if (rclient && rclient->ops->link_status_change)
+                               rclient->ops->link_status_change(rhandle,
+                                                                state);
+               }
 
                hclge_push_link_status(hdev);
        }
@@ -11232,6 +11237,12 @@ clear_roce:
        return ret;
 }
 
+static bool hclge_uninit_need_wait(struct hclge_dev *hdev)
+{
+       return test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state) ||
+              test_bit(HCLGE_STATE_LINK_UPDATING, &hdev->state);
+}
+
 static void hclge_uninit_client_instance(struct hnae3_client *client,
                                         struct hnae3_ae_dev *ae_dev)
 {
@@ -11240,7 +11251,7 @@ static void hclge_uninit_client_instance(struct hnae3_client *client,
 
        if (hdev->roce_client) {
                clear_bit(HCLGE_STATE_ROCE_REGISTERED, &hdev->state);
-               while (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state))
+               while (hclge_uninit_need_wait(hdev))
                        msleep(HCLGE_WAIT_RESET_DONE);
 
                hdev->roce_client->ops->uninit_instance(&vport->roce, 0);