Patch "net: hns3: fix kernel crash problem in concurrent scenario" has been added to the 6.1-stable tree

[Sasha Levin <sashal@xxxxxxxxxx>]

This is a note to let you know that I've just added the patch titled

    net: hns3: fix kernel crash problem in concurrent scenario

to the 6.1-stable tree which can be found at:
    http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary

The filename of the patch is:
     net-hns3-fix-kernel-crash-problem-in-concurrent-scen.patch
and it can be found in the queue-6.1 subdirectory.

If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.



commit bc374fae8d27614ba806f4a57fe418af03b061f6
Author: Yonglong Liu <liuyonglong@xxxxxxxxxx>
Date:   Wed Jun 5 15:20:57 2024 +0800

    net: hns3: fix kernel crash problem in concurrent scenario
    
    [ 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@xxxxxxxxxx>
    Signed-off-by: Jijie Shao <shaojijie@xxxxxxxxxx>
    Reviewed-by: Simon Horman <horms@xxxxxxxxxx>
    Signed-off-by: David S. Miller <davem@xxxxxxxxxxxxx>
    Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index a2655adc764cd..01e24b69e9203 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -3129,9 +3129,7 @@ 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;
@@ -3155,8 +3153,15 @@ 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);
 	}
@@ -11339,6 +11344,12 @@ static int hclge_init_client_instance(struct hnae3_client *client,
 	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)
 {
@@ -11347,7 +11358,7 @@ 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);