[PATCH net-next v21 01/13] netdev: add netdev_rx_queue_restart()

[Mina Almasry]

Add netdev_rx_queue_restart(), which resets an rx queue using the
queue API recently merged[1].

The queue API was merged to enable the core net stack to reset individual
rx queues to actuate changes in the rx queue's configuration. In later
patches in this series, we will use netdev_rx_queue_restart() to reset
rx queues after binding or unbinding dmabuf configuration, which will
cause reallocation of the page_pool to repopulate its memory using the
new configuration.

[1] https://lore.kernel.org/netdev/20240430231420.699177-1-shailend@google.com/T/

Signed-off-by: David Wei <dw at davidwei.uk>
Signed-off-by: Mina Almasry <almasrymina at google.com>
Reviewed-by: Pavel Begunkov <asml.silence at gmail.com>
Reviewed-by: Jakub Kicinski <kuba at kernel.org>

---

v18:
- Add more color to commit message (Xuan Zhuo).

v17:
- Use ASSERT_RTNL() (Jakub).

v13:
- Add reviewed-by from Pavel (thanks!)
- Fixed comment (Pavel)

v11:
- Fix not checking dev->queue_mgmt_ops (Pavel).
- Fix ndo_queue_mem_free call that passed the wrong pointer (David).

v9: https://lore.kernel.org/all/20240502045410.3524155-4-dw@davidwei.uk/
(submitted by David).
- fixed SPDX license identifier (Simon).
- Rebased on top of merged queue API definition, and changed
  implementation to match that.
- Replace rtnl_lock() with rtnl_is_locked() to make it useable from my
  netlink code where rtnl is already locked.

---
 include/net/netdev_rx_queue.h |  3 ++
 net/core/Makefile             |  1 +
 net/core/netdev_rx_queue.c    | 74 +++++++++++++++++++++++++++++++++++
 3 files changed, 78 insertions(+)
 create mode 100644 net/core/netdev_rx_queue.c

diff --git a/include/net/netdev_rx_queue.h b/include/net/netdev_rx_queue.h
index aa1716fb0e53..e78ca52d67fb 100644
--- a/include/net/netdev_rx_queue.h
+++ b/include/net/netdev_rx_queue.h
@@ -54,4 +54,7 @@ get_netdev_rx_queue_index(struct netdev_rx_queue *queue)
 	return index;
 }
 #endif
+
+int netdev_rx_queue_restart(struct net_device *dev, unsigned int rxq);
+
 #endif
diff --git a/net/core/Makefile b/net/core/Makefile
index 62be9aef2528..f82232b358a2 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -19,6 +19,7 @@ obj-$(CONFIG_NETDEV_ADDR_LIST_TEST) += dev_addr_lists_test.o
 
 obj-y += net-sysfs.o
 obj-y += hotdata.o
+obj-y += netdev_rx_queue.o
 obj-$(CONFIG_PAGE_POOL) += page_pool.o page_pool_user.o
 obj-$(CONFIG_PROC_FS) += net-procfs.o
 obj-$(CONFIG_NET_PKTGEN) += pktgen.o
diff --git a/net/core/netdev_rx_queue.c b/net/core/netdev_rx_queue.c
new file mode 100644
index 000000000000..da11720a5983
--- /dev/null
+++ b/net/core/netdev_rx_queue.c
@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/netdevice.h>
+#include <net/netdev_queues.h>
+#include <net/netdev_rx_queue.h>
+
+int netdev_rx_queue_restart(struct net_device *dev, unsigned int rxq_idx)
+{
+	void *new_mem, *old_mem;
+	int err;
+
+	if (!dev->queue_mgmt_ops || !dev->queue_mgmt_ops->ndo_queue_stop ||
+	    !dev->queue_mgmt_ops->ndo_queue_mem_free ||
+	    !dev->queue_mgmt_ops->ndo_queue_mem_alloc ||
+	    !dev->queue_mgmt_ops->ndo_queue_start)
+		return -EOPNOTSUPP;
+
+	ASSERT_RTNL();
+
+	new_mem = kvzalloc(dev->queue_mgmt_ops->ndo_queue_mem_size, GFP_KERNEL);
+	if (!new_mem)
+		return -ENOMEM;
+
+	old_mem = kvzalloc(dev->queue_mgmt_ops->ndo_queue_mem_size, GFP_KERNEL);
+	if (!old_mem) {
+		err = -ENOMEM;
+		goto err_free_new_mem;
+	}
+
+	err = dev->queue_mgmt_ops->ndo_queue_mem_alloc(dev, new_mem, rxq_idx);
+	if (err)
+		goto err_free_old_mem;
+
+	err = dev->queue_mgmt_ops->ndo_queue_stop(dev, old_mem, rxq_idx);
+	if (err)
+		goto err_free_new_queue_mem;
+
+	err = dev->queue_mgmt_ops->ndo_queue_start(dev, new_mem, rxq_idx);
+	if (err)
+		goto err_start_queue;
+
+	dev->queue_mgmt_ops->ndo_queue_mem_free(dev, old_mem);
+
+	kvfree(old_mem);
+	kvfree(new_mem);
+
+	return 0;
+
+err_start_queue:
+	/* Restarting the queue with old_mem should be successful as we haven't
+	 * changed any of the queue configuration, and there is not much we can
+	 * do to recover from a failure here.
+	 *
+	 * WARN if we fail to recover the old rx queue, and at least free
+	 * old_mem so we don't also leak that.
+	 */
+	if (dev->queue_mgmt_ops->ndo_queue_start(dev, old_mem, rxq_idx)) {
+		WARN(1,
+		     "Failed to restart old queue in error path. RX queue %d may be unhealthy.",
+		     rxq_idx);
+		dev->queue_mgmt_ops->ndo_queue_mem_free(dev, old_mem);
+	}
+
+err_free_new_queue_mem:
+	dev->queue_mgmt_ops->ndo_queue_mem_free(dev, new_mem);
+
+err_free_old_mem:
+	kvfree(old_mem);
+
+err_free_new_mem:
+	kvfree(new_mem);
+
+	return err;
+}
-- 
2.46.0.184.g6999bdac58-goog