Re: [PATCH net-next v17 01/14] netdev: add netdev_rx_queue_restart()

[Xuan Zhuo]

On Tue, 30 Jul 2024 02:26:05 +0000, Mina Almasry <almasrymina@xxxxxxxxxx> wrote:
> Add netdev_rx_queue_restart() function to netdev_rx_queue.h


Can you say more? As far as I understand, we just release the buffer
submitted to the rx ring and get a new page pool.

But I personally feel that the interface here is a bit too complicated. In
particular, we also need to copy the rx struct memory, which means it is a
dangerous operation for many pointers.

Thanks.


>
> Signed-off-by: David Wei <dw@xxxxxxxxxxx>
> Signed-off-by: Mina Almasry <almasrymina@xxxxxxxxxx>
> Reviewed-by: Pavel Begunkov <asml.silence@xxxxxxxxx>
> Reviewed-by: Jakub Kicinski <kuba@xxxxxxxxxx>
>
> ---
>
> 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@xxxxxxxxxxx/
> (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 aa1716fb0e53c..e78ca52d67fbf 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 62be9aef25285..f82232b358a2c 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 0000000000000..da11720a59830
> --- /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.rc1.232.g9752f9e123-goog
>
>