netconsole: resume previously deactivated target

Attempt to resume a previously deactivated target when the associated
interface comes back (NETDEV_REGISTER) or when it changes name
(NETDEV_CHANGENAME) by calling netpoll_setup on the device.

Depending on how the target was setup (by mac or interface name), the
corresponding field is compared with the device being brought up. Targets
that match the incoming device, are scheduled for resume on a workqueue.

Resuming happens on a workqueue as we can't execute netpoll_setup in the
context of the netdev event. A standalone workqueue (as opposed to the
global one) is used to allow for proper cleanup process during
netconsole module cleanup as we need to be able to flush all pending
work before traversing the target list given that targets are temporarily
removed from the list during resume_target.

Target transitions to STATE_DISABLED in case of failures resuming it to
avoid retrying the same target indefinitely.

Signed-off-by: Andre Carvalho <asantostc@gmail.com>
Reviewed-by: Breno Leitao <leitao@debian.org>
Tested-by: Breno Leitao <leitao@debian.org>
Link: https://patch.msgid.link/20260118-netcons-retrigger-v11-6-4de36aebcf48@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index 46d990f3d904094834af6ffa72a4588d4d67d4e0..82c232f9ede242c709a13d2aaea4232a84c457db 100644 (file)
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -39,6 +39,7 @@
 #include <linux/u64_stats_sync.h>
 #include <linux/utsname.h>
 #include <linux/rtnetlink.h>
+#include <linux/workqueue.h>
 
 MODULE_AUTHOR("Matt Mackall <mpm@selenic.com>");
 MODULE_DESCRIPTION("Console driver for network interfaces");
@@ -85,6 +86,8 @@ static DEFINE_SPINLOCK(target_list_lock);
 /* This needs to be a mutex because netpoll_cleanup might sleep */
 static DEFINE_MUTEX(target_cleanup_list_lock);
 
+static struct workqueue_struct *netconsole_wq;
+
 /*
  * Console driver for netconsoles.  Register only consoles that have
  * an associated target of the same type.
@@ -138,10 +141,14 @@ enum target_state {
  * @stats:     Packet send stats for the target. Used for debugging.
  * @state:     State of the target.
  *             Visible from userspace (read-write).
- *             We maintain a strict 1:1 correspondence between this and
- *             whether the corresponding netpoll is active or inactive.
+ *             From a userspace perspective, the target is either enabled or
+ *             disabled. Internally, although both STATE_DISABLED and
+ *             STATE_DEACTIVATED correspond to inactive targets, the latter is
+ *             due to automatic interface state changes and will try
+ *             recover automatically, if the interface comes back
+ *             online.
  *             Also, other parameters of a target may be modified at
- *             runtime only when it is disabled (state == STATE_DISABLED).
+ *             runtime only when it is disabled (state != STATE_ENABLED).
  * @extended:  Denotes whether console is extended or not.
  * @release:   Denotes whether kernel release version should be prepended
  *             to the message. Depends on extended console.
@@ -155,6 +162,7 @@ enum target_state {
  *             local_mac       (read-only)
  *             remote_mac      (read-write)
  * @buf:       The buffer used to send the full msg to the network stack
+ * @resume_wq: Workqueue to resume deactivated target
  */
 struct netconsole_target {
        struct list_head        list;
@@ -177,6 +185,7 @@ struct netconsole_target {
        struct netpoll          np;
        /* protected by target_list_lock */
        char                    buf[MAX_PRINT_CHUNK];
+       struct work_struct      resume_wq;
 };
 
 #ifdef CONFIG_NETCONSOLE_DYNAMIC
@@ -267,6 +276,70 @@ static bool bound_by_mac(struct netconsole_target *nt)
        return is_valid_ether_addr(nt->np.dev_mac);
 }
 
+/* Attempts to resume logging to a deactivated target. */
+static void resume_target(struct netconsole_target *nt)
+{
+       if (netpoll_setup(&nt->np)) {
+               /* netpoll fails setup once, do not try again. */
+               nt->state = STATE_DISABLED;
+               return;
+       }
+
+       nt->state = STATE_ENABLED;
+       pr_info("network logging resumed on interface %s\n", nt->np.dev_name);
+}
+
+/* Checks if a deactivated target matches a device. */
+static bool deactivated_target_match(struct netconsole_target *nt,
+                                    struct net_device *ndev)
+{
+       if (nt->state != STATE_DEACTIVATED)
+               return false;
+
+       if (bound_by_mac(nt))
+               return !memcmp(nt->np.dev_mac, ndev->dev_addr, ETH_ALEN);
+       return !strncmp(nt->np.dev_name, ndev->name, IFNAMSIZ);
+}
+
+/* Process work scheduled for target resume. */
+static void process_resume_target(struct work_struct *work)
+{
+       struct netconsole_target *nt;
+       unsigned long flags;
+
+       nt = container_of(work, struct netconsole_target, resume_wq);
+
+       dynamic_netconsole_mutex_lock();
+
+       spin_lock_irqsave(&target_list_lock, flags);
+       /* Check if target is still deactivated as it may have been disabled
+        * while resume was being scheduled.
+        */
+       if (nt->state != STATE_DEACTIVATED) {
+               spin_unlock_irqrestore(&target_list_lock, flags);
+               goto out_unlock;
+       }
+
+       /* resume_target is IRQ unsafe, remove target from
+        * target_list in order to resume it with IRQ enabled.
+        */
+       list_del_init(&nt->list);
+       spin_unlock_irqrestore(&target_list_lock, flags);
+
+       resume_target(nt);
+
+       /* At this point the target is either enabled or disabled and
+        * was cleaned up before getting deactivated. Either way, add it
+        * back to target list.
+        */
+       spin_lock_irqsave(&target_list_lock, flags);
+       list_add(&nt->list, &target_list);
+       spin_unlock_irqrestore(&target_list_lock, flags);
+
+out_unlock:
+       dynamic_netconsole_mutex_unlock();
+}
+
 /* Allocate and initialize with defaults.
  * Note that these targets get their config_item fields zeroed-out.
  */
@@ -289,6 +362,7 @@ static struct netconsole_target *alloc_and_init(void)
        nt->np.remote_port = 6666;
        eth_broadcast_addr(nt->np.remote_mac);
        nt->state = STATE_DISABLED;
+       INIT_WORK(&nt->resume_wq, process_resume_target);
 
        return nt;
 }
@@ -1353,13 +1427,29 @@ static struct config_group *make_netconsole_target(struct config_group *group,
 static void drop_netconsole_target(struct config_group *group,
                                   struct config_item *item)
 {
-       unsigned long flags;
        struct netconsole_target *nt = to_target(item);
+       unsigned long flags;
+
+       dynamic_netconsole_mutex_lock();
 
        spin_lock_irqsave(&target_list_lock, flags);
+       /* Disable deactivated target to prevent races between resume attempt
+        * and target removal.
+        */
+       if (nt->state == STATE_DEACTIVATED)
+               nt->state = STATE_DISABLED;
        list_del(&nt->list);
        spin_unlock_irqrestore(&target_list_lock, flags);
 
+       dynamic_netconsole_mutex_unlock();
+
+       /* Now that the target has been marked disabled no further work
+        * can be scheduled. Existing work will skip as targets are not
+        * deactivated anymore. Cancel any scheduled resume and wait for
+        * completion.
+        */
+       cancel_work_sync(&nt->resume_wq);
+
        /*
         * The target may have never been enabled, or was manually disabled
         * before being removed so netpoll may have already been cleaned up.
@@ -1461,13 +1551,14 @@ out:
 static int netconsole_netdev_event(struct notifier_block *this,
                                   unsigned long event, void *ptr)
 {
-       unsigned long flags;
-       struct netconsole_target *nt, *tmp;
        struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+       struct netconsole_target *nt, *tmp;
        bool stopped = false;
+       unsigned long flags;
 
        if (!(event == NETDEV_CHANGENAME || event == NETDEV_UNREGISTER ||
-             event == NETDEV_RELEASE || event == NETDEV_JOIN))
+             event == NETDEV_RELEASE || event == NETDEV_JOIN ||
+             event == NETDEV_REGISTER))
                goto done;
 
        mutex_lock(&target_cleanup_list_lock);
@@ -1496,6 +1587,13 @@ static int netconsole_netdev_event(struct notifier_block *this,
                                stopped = true;
                        }
                }
+               if ((event == NETDEV_REGISTER || event == NETDEV_CHANGENAME) &&
+                   deactivated_target_match(nt, dev))
+                       /* Schedule resume on a workqueue as it will attempt
+                        * to UP the device, which can't be done as part of this
+                        * notifier.
+                        */
+                       queue_work(netconsole_wq, &nt->resume_wq);
                netconsole_target_put(nt);
        }
        spin_unlock_irqrestore(&target_list_lock, flags);
@@ -1964,6 +2062,7 @@ fail:
 /* Cleanup netpoll for given target (from boot/module param) and free it */
 static void free_param_target(struct netconsole_target *nt)
 {
+       cancel_work_sync(&nt->resume_wq);
        netpoll_cleanup(&nt->np);
 #ifdef CONFIG_NETCONSOLE_DYNAMIC
        kfree(nt->userdata);
@@ -2018,6 +2117,12 @@ static int __init init_netconsole(void)
                }
        }
 
+       netconsole_wq = alloc_workqueue("netconsole", WQ_UNBOUND, 0);
+       if (!netconsole_wq) {
+               err = -ENOMEM;
+               goto fail;
+       }
+
        err = register_netdevice_notifier(&netconsole_netdev_notifier);
        if (err)
                goto fail;
@@ -2040,6 +2145,8 @@ undonotifier:
 fail:
        pr_err("cleaning up\n");
 
+       if (netconsole_wq)
+               flush_workqueue(netconsole_wq);
        /*
         * Remove all targets and destroy them (only targets created
         * from the boot/module option exist here). Skipping the list
@@ -2050,6 +2157,9 @@ fail:
                free_param_target(nt);
        }
 
+       if (netconsole_wq)
+               destroy_workqueue(netconsole_wq);
+
        return err;
 }
 
@@ -2063,6 +2173,7 @@ static void __exit cleanup_netconsole(void)
                unregister_console(&netconsole);
        dynamic_netconsole_exit();
        unregister_netdevice_notifier(&netconsole_netdev_notifier);
+       flush_workqueue(netconsole_wq);
 
        /*
         * Targets created via configfs pin references on our module
@@ -2076,6 +2187,8 @@ static void __exit cleanup_netconsole(void)
                list_del(&nt->list);
                free_param_target(nt);
        }
+
+       destroy_workqueue(netconsole_wq);
 }
 
 /*