bpf.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jason Wang <jasowang@redhat.com>
To: Xuan Zhuo <xuanzhuo@linux.alibaba.com>, netdev@vger.kernel.org
Cc: "Michael S. Tsirkin" <mst@redhat.com>,
	"David S. Miller" <davem@davemloft.net>,
	"Jakub Kicinski" <kuba@kernel.org>,
	"Björn Töpel" <bjorn@kernel.org>,
	"Magnus Karlsson" <magnus.karlsson@intel.com>,
	"Jonathan Lemon" <jonathan.lemon@gmail.com>,
	"Alexei Starovoitov" <ast@kernel.org>,
	"Daniel Borkmann" <daniel@iogearbox.net>,
	"Jesper Dangaard Brouer" <hawk@kernel.org>,
	"John Fastabend" <john.fastabend@gmail.com>,
	virtualization@lists.linux-foundation.org, bpf@vger.kernel.org,
	"dust . li" <dust.li@linux.alibaba.com>
Subject: Re: [PATCH net-next v4 08/10] virtio-net: xsk zero copy xmit setup
Date: Wed, 14 Apr 2021 12:01:46 +0800	[thread overview]
Message-ID: <ec6d7825-ddfb-ae7e-1105-fffd6afecfcb@redhat.com> (raw)
In-Reply-To: <20210413031523.73507-9-xuanzhuo@linux.alibaba.com>


在 2021/4/13 上午11:15, Xuan Zhuo 写道:
> xsk is a high-performance packet receiving and sending technology.
>
> This patch implements the binding and unbinding operations of xsk and
> the virtio-net queue for xsk zero copy xmit.
>
> The xsk zero copy xmit depends on tx napi.


It's better to describe why zero copy depends on tx napi.


>   So if tx napi is not true,
> an error will be reported. And the entire operation is under the
> protection of rtnl_lock.
>
> If xsk is active, it will prevent ethtool from modifying tx napi.
>
> Signed-off-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
> Reviewed-by: Dust Li <dust.li@linux.alibaba.com>
> ---
>   drivers/net/virtio_net.c | 78 +++++++++++++++++++++++++++++++++++++++-
>   1 file changed, 77 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> index f52a25091322..8242a9e9f17d 100644
> --- a/drivers/net/virtio_net.c
> +++ b/drivers/net/virtio_net.c
> @@ -22,6 +22,7 @@
>   #include <net/route.h>
>   #include <net/xdp.h>
>   #include <net/net_failover.h>
> +#include <net/xdp_sock_drv.h>
>   
>   static int napi_weight = NAPI_POLL_WEIGHT;
>   module_param(napi_weight, int, 0444);
> @@ -133,6 +134,11 @@ struct send_queue {
>   	struct virtnet_sq_stats stats;
>   
>   	struct napi_struct napi;
> +
> +	struct {
> +		/* xsk pool */


This comment is unnecessary since the code explains itself.


> +		struct xsk_buff_pool __rcu *pool;
> +	} xsk;
>   };
>   
>   /* Internal representation of a receive virtqueue */
> @@ -2249,8 +2255,19 @@ static int virtnet_set_coalesce(struct net_device *dev,
>   	if (napi_weight ^ vi->sq[0].napi.weight) {
>   		if (dev->flags & IFF_UP)
>   			return -EBUSY;
> -		for (i = 0; i < vi->max_queue_pairs; i++)
> +		for (i = 0; i < vi->max_queue_pairs; i++) {
> +			/* xsk xmit depend on the tx napi. So if xsk is active,
> +			 * prevent modifications to tx napi.
> +			 */
> +			rcu_read_lock();
> +			if (rcu_dereference(vi->sq[i].xsk.pool)) {


Let's use rtnl_derefernece() then the rcu_read_lock()/unlock() is not 
needed.


> +				rcu_read_unlock();
> +				continue;
> +			}
> +			rcu_read_unlock();
> +
>   			vi->sq[i].napi.weight = napi_weight;
> +		}
>   	}
>   
>   	return 0;
> @@ -2518,11 +2535,70 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
>   	return err;
>   }
>   
> +static int virtnet_xsk_pool_enable(struct net_device *dev,
> +				   struct xsk_buff_pool *pool,
> +				   u16 qid)
> +{
> +	struct virtnet_info *vi = netdev_priv(dev);
> +	struct send_queue *sq;
> +
> +	if (qid >= vi->curr_queue_pairs)
> +		return -EINVAL;
> +
> +	sq = &vi->sq[qid];
> +
> +	/* xsk zerocopy depend on the tx napi.
> +	 *
> +	 * xsk zerocopy xmit is driven by the tx interrupt. When the device is
> +	 * not busy, napi will be called continuously to send data. When the
> +	 * device is busy, wait for the notification interrupt after the
> +	 * hardware has finished processing the data, and continue to send data
> +	 * in napi.
> +	 */
> +	if (!sq->napi.weight)
> +		return -EPERM;
> +
> +	rcu_read_lock();
> +	/* Here is already protected by rtnl_lock, so rcu_assign_pointer is
> +	 * safe.
> +	 */
> +	rcu_assign_pointer(sq->xsk.pool, pool);
> +	rcu_read_unlock();


Any reason for the rcu lock here? And don't we need to synchronize rcu here?


> +
> +	return 0;
> +}
> +
> +static int virtnet_xsk_pool_disable(struct net_device *dev, u16 qid)
> +{
> +	struct virtnet_info *vi = netdev_priv(dev);
> +	struct send_queue *sq;
> +
> +	if (qid >= vi->curr_queue_pairs)
> +		return -EINVAL;
> +
> +	sq = &vi->sq[qid];
> +
> +	/* Here is already protected by rtnl_lock, so rcu_assign_pointer is
> +	 * safe.
> +	 */
> +	rcu_assign_pointer(sq->xsk.pool, NULL);
> +
> +	synchronize_net(); /* Sync with the XSK wakeup and with NAPI. */


Let's move the comment above the code.

Thanks


> +
> +	return 0;
> +}
> +
>   static int virtnet_xdp(struct net_device *dev, struct netdev_bpf *xdp)
>   {
>   	switch (xdp->command) {
>   	case XDP_SETUP_PROG:
>   		return virtnet_xdp_set(dev, xdp->prog, xdp->extack);
> +	case XDP_SETUP_XSK_POOL:
> +		if (xdp->xsk.pool)
> +			return virtnet_xsk_pool_enable(dev, xdp->xsk.pool,
> +						       xdp->xsk.queue_id);
> +		else
> +			return virtnet_xsk_pool_disable(dev, xdp->xsk.queue_id);
>   	default:
>   		return -EINVAL;
>   	}


  reply	other threads:[~2021-04-14  4:02 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-04-13  3:15 [PATCH net-next v4 00/10] virtio-net support xdp socket zero copy xmit Xuan Zhuo
2021-04-13  3:15 ` [PATCH net-next v4 01/10] netdevice: priv_flags extend to 64bit Xuan Zhuo
2021-04-13 18:26   ` Jakub Kicinski
2021-04-13  3:15 ` [PATCH net-next v4 02/10] netdevice: add priv_flags IFF_NOT_USE_DMA_ADDR Xuan Zhuo
2021-04-13  3:15 ` [PATCH net-next v4 03/10] virtio-net: " Xuan Zhuo
2021-04-13  3:15 ` [PATCH net-next v4 04/10] xsk: support get page by addr Xuan Zhuo
2021-04-14  6:59   ` Magnus Karlsson
2021-04-13  3:15 ` [PATCH net-next v4 05/10] xsk: XDP_SETUP_XSK_POOL support option IFF_NOT_USE_DMA_ADDR Xuan Zhuo
2021-04-14  7:00   ` Magnus Karlsson
2021-04-13  3:15 ` [PATCH net-next v4 06/10] virtio-net: unify the code for recycling the xmit ptr Xuan Zhuo
2021-04-14  3:32   ` Jason Wang
2021-04-13  3:15 ` [PATCH net-next v4 07/10] virtio-net: virtnet_poll_tx support budget check Xuan Zhuo
2021-04-14  3:34   ` Jason Wang
2021-04-13  3:15 ` [PATCH net-next v4 08/10] virtio-net: xsk zero copy xmit setup Xuan Zhuo
2021-04-14  4:01   ` Jason Wang [this message]
2021-04-14  7:36   ` Magnus Karlsson
2021-04-14  7:51     ` Jason Wang
2021-04-13  3:15 ` [PATCH net-next v4 09/10] virtio-net: xsk zero copy xmit implement wakeup and xmit Xuan Zhuo
2021-04-14  5:46   ` Jason Wang
2021-04-13  3:15 ` [PATCH net-next v4 10/10] virtio-net: xsk zero copy xmit kick by threshold Xuan Zhuo
2021-04-14  5:51   ` Jason Wang

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=ec6d7825-ddfb-ae7e-1105-fffd6afecfcb@redhat.com \
    --to=jasowang@redhat.com \
    --cc=ast@kernel.org \
    --cc=bjorn@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=davem@davemloft.net \
    --cc=dust.li@linux.alibaba.com \
    --cc=hawk@kernel.org \
    --cc=john.fastabend@gmail.com \
    --cc=jonathan.lemon@gmail.com \
    --cc=kuba@kernel.org \
    --cc=magnus.karlsson@intel.com \
    --cc=mst@redhat.com \
    --cc=netdev@vger.kernel.org \
    --cc=virtualization@lists.linux-foundation.org \
    --cc=xuanzhuo@linux.alibaba.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).