net: turn the rx_mode work into a generic netdev_work facility

The rx_mode update runs from a workqueue: drivers have their
ndo_set_rx_mode_async() callback executed by a single global
work item under RTNL and ops lock. This is a useful pattern.

Support multiple "events" that need to be serviced and make RX_MODE
sync the first one. Call the events "core" because later on
we will let drivers define and schedule their own.

Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20260624182018.2445732-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 117 insertions, 0 deletions

diff --git a/net/core/netdev_work.c b/net/core/netdev_work.c
new file mode 100644
index 000000000000..c121c24dc493
--- /dev/null
+++ b/net/core/netdev_work.c
@@ -0,0 +1,117 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/list.h>
+#include <linux/netdevice.h>
+#include <linux/rtnetlink.h>
+#include <linux/spinlock.h>
+#include <linux/workqueue.h>
+#include <net/netdev_lock.h>
+
+#include "dev.h"
+
+static void netdev_work_proc(struct work_struct *work);
+
+/* @netdev_work_lock protects:
+ *  - @netdev_work_list
+ *  - within the list entries (struct net_device fields):
+ *	- work_node
+ *	- work_tracker
+ *	- work_core_pending
+ */
+static LIST_HEAD(netdev_work_list);
+static DEFINE_SPINLOCK(netdev_work_lock);
+static DECLARE_WORK(netdev_work, netdev_work_proc);
+
+void __netdev_work_core_sched(struct net_device *dev, unsigned long event)
+{
+	spin_lock_bh(&netdev_work_lock);
+	if (list_empty(&dev->work_node)) {
+		list_add_tail(&dev->work_node, &netdev_work_list);
+		netdev_hold(dev, &dev->work_tracker, GFP_ATOMIC);
+	}
+	dev->work_core_pending |= event;
+	spin_unlock_bh(&netdev_work_lock);
+
+	schedule_work(&netdev_work);
+}
+
+/**
+ * __netdev_work_core_cancel() - cancel selected core work for a netdev
+ * @dev: net_device
+ * @mask: events to cancel
+ *
+ * Clear @mask from the device's work pending mask. If no work is left pending
+ * the device is dequeued.
+ *
+ * No expectations on locking, but also no guarantees provided. If the caller
+ * wants to touch @dev afterwards (e.g. call the work that got canceled)
+ * they have to ensure @dev does not get freed.
+ *
+ * Returns: the subset of @mask that was actually pending, so the caller can run
+ * those events inline.
+ */
+unsigned long
+__netdev_work_core_cancel(struct net_device *dev, unsigned long mask)
+{
+	unsigned long event;
+
+	spin_lock_bh(&netdev_work_lock);
+	event = dev->work_core_pending & mask;
+	dev->work_core_pending &= ~mask;
+	if (!list_empty(&dev->work_node) && !dev->work_core_pending) {
+		list_del_init(&dev->work_node);
+		netdev_put(dev, &dev->work_tracker);
+	}
+	spin_unlock_bh(&netdev_work_lock);
+
+	return event;
+}
+
+static void netdev_work_proc(struct work_struct *work)
+{
+	rtnl_lock();
+
+	while (true) {
+		netdevice_tracker tracker;
+		struct net_device *dev;
+		unsigned long core = 0;
+
+		spin_lock_bh(&netdev_work_lock);
+		if (list_empty(&netdev_work_list)) {
+			spin_unlock_bh(&netdev_work_lock);
+			break;
+		}
+		dev = list_first_entry(&netdev_work_list, struct net_device,
+				       work_node);
+		/* Take a temporary reference so @dev can't be freed while we
+		 * drop the lock to grab its ops lock; the work reference is
+		 * only released once we claim the work below.
+		 * The re-locking dance is to ensure that ops lock is enough
+		 * to ensure canceling work is not racy with dequeue.
+		 */
+		netdev_hold(dev, &tracker, GFP_ATOMIC);
+		spin_unlock_bh(&netdev_work_lock);
+
+		netdev_lock_ops(dev);
+		spin_lock_bh(&netdev_work_lock);
+		if (!list_empty(&dev->work_node)) {
+			list_del_init(&dev->work_node);
+			core = dev->work_core_pending;
+			dev->work_core_pending = 0;
+			/* We took another ref above */
+			netdev_put(dev, &dev->work_tracker);
+
+			if (!dev_isalive(dev))
+				core = 0;
+		}
+		spin_unlock_bh(&netdev_work_lock);
+
+		if (core & NETDEV_WORK_RX_MODE)
+			netif_rx_mode_run(dev);
+		netdev_unlock_ops(dev);
+
+		netdev_put(dev, &tracker);
+	}
+
+	rtnl_unlock();
+}