net: usbnet: Avoid potential RCU stall on LINK_CHANGE event

The Gemalto Cinterion PLS83-W modem (cdc_ether) is emitting confusing link
up and down events when the WWAN interface is activated on the modem-side.

Interrupt URBs will in consecutive polls grab:
* Link Connected
* Link Disconnected
* Link Connected

Where the last Connected is then a stable link state.

When the system is under load this may cause the unlink_urbs() work in
__handle_link_change() to not complete before the next usbnet_link_change()
call turns the carrier on again, allowing rx_submit() to queue new SKBs.

In that event the URB queue is filled faster than it can drain, ending up
in a RCU stall:

    rcu: INFO: rcu_sched detected expedited stalls on CPUs/tasks: { 0-.... } 33108 jiffies s: 201 root: 0x1/.
    rcu: blocking rcu_node structures (internal RCU debug):
    Sending NMI from CPU 1 to CPUs 0:
    NMI backtrace for cpu 0

    Call trace:
     arch_local_irq_enable+0x4/0x8
     local_bh_enable+0x18/0x20
     __netdev_alloc_skb+0x18c/0x1cc
     rx_submit+0x68/0x1f8 [usbnet]
     rx_alloc_submit+0x4c/0x74 [usbnet]
     usbnet_bh+0x1d8/0x218 [usbnet]
     usbnet_bh_tasklet+0x10/0x18 [usbnet]
     tasklet_action_common+0xa8/0x110
     tasklet_action+0x2c/0x34
     handle_softirqs+0x2cc/0x3a0
     __do_softirq+0x10/0x18
     ____do_softirq+0xc/0x14
     call_on_irq_stack+0x24/0x34
     do_softirq_own_stack+0x18/0x20
     __irq_exit_rcu+0xa8/0xb8
     irq_exit_rcu+0xc/0x30
     el1_interrupt+0x34/0x48
     el1h_64_irq_handler+0x14/0x1c
     el1h_64_irq+0x68/0x6c
     _raw_spin_unlock_irqrestore+0x38/0x48
     xhci_urb_dequeue+0x1ac/0x45c [xhci_hcd]
     unlink1+0xd4/0xdc [usbcore]
     usb_hcd_unlink_urb+0x70/0xb0 [usbcore]
     usb_unlink_urb+0x24/0x44 [usbcore]
     unlink_urbs.constprop.0.isra.0+0x64/0xa8 [usbnet]
     __handle_link_change+0x34/0x70 [usbnet]
     usbnet_deferred_kevent+0x1c0/0x320 [usbnet]
     process_scheduled_works+0x2d0/0x48c
     worker_thread+0x150/0x1dc
     kthread+0xd8/0xe8
     ret_from_fork+0x10/0x20

Get around the problem by delaying the carrier on to the scheduled work.

This needs a new flag to keep track of the necessary action.

The carrier ok check cannot be removed as it remains required for the
LINK_RESET event flow.

Fixes: 4b49f58fff00 ("usbnet: handle link change")
Cc: stable@vger.kernel.org
Signed-off-by: John Ernberg <john.ernberg@actia.se>
Link: https://patch.msgid.link/20250723102526.1305339-1-john.ernberg@actia.se
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index c04e715a4c2ade3bc5587b0df71643a25cf88c55..bc1d8631ffe01b69d67d3a7c94e2b1ebd2d11001 100644 (file)
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -1122,6 +1122,9 @@ static void __handle_link_change(struct usbnet *dev)
                 * tx queue is stopped by netcore after link becomes off
                 */
        } else {
+               if (test_and_clear_bit(EVENT_LINK_CARRIER_ON, &dev->flags))
+                       netif_carrier_on(dev->net);
+
                /* submitting URBs for reading packets */
                tasklet_schedule(&dev->bh);
        }
@@ -2009,10 +2012,12 @@ EXPORT_SYMBOL(usbnet_manage_power);
 void usbnet_link_change(struct usbnet *dev, bool link, bool need_reset)
 {
        /* update link after link is reseted */
-       if (link && !need_reset)
-               netif_carrier_on(dev->net);
-       else
+       if (link && !need_reset) {
+               set_bit(EVENT_LINK_CARRIER_ON, &dev->flags);
+       } else {
+               clear_bit(EVENT_LINK_CARRIER_ON, &dev->flags);
                netif_carrier_off(dev->net);
+       }
 
        if (need_reset && link)
                usbnet_defer_kevent(dev, EVENT_LINK_RESET);

diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h
index 0b9f1e598e3a6bb0285e35918a361d74cd1dd71f..4bc6bb01a0eb8b5553a2969b0deb1b31e5757019 100644 (file)
--- a/include/linux/usb/usbnet.h
+++ b/include/linux/usb/usbnet.h
@@ -76,6 +76,7 @@ struct usbnet {
 #              define EVENT_LINK_CHANGE        11
 #              define EVENT_SET_RX_MODE        12
 #              define EVENT_NO_IP_ALIGN        13
+#              define EVENT_LINK_CARRIER_ON    14
 /* This one is special, as it indicates that the device is going away
  * there are cyclic dependencies between tasklet, timer and bh
  * that must be broken