KVM Archive on lore.kernel.org
 help / color / Atom feed
From: Jason Wang <jasowang@redhat.com>
To: prashantbhole.linux@gmail.com,
	"Michael S . Tsirkin" <mst@redhat.com>,
	"David S . Miller" <davem@davemloft.net>
Cc: David Ahern <dsahern@gmail.com>,
	kvm@vger.kernel.org, netdev@vger.kernel.org
Subject: Re: [PATCH net-next 2/3] vhost_net: user tap recvmsg api to access ptr ring
Date: Sat, 12 Oct 2019 15:54:53 +0800
Message-ID: <9cb43497-1f43-562e-74af-21370492fe14@redhat.com> (raw)
In-Reply-To: <20191012015357.1775-3-prashantbhole.linux@gmail.com>


On 2019/10/12 上午9:53, prashantbhole.linux@gmail.com wrote:
> From: Prashant Bhole <prashantbhole.linux@gmail.com>
>
> Currently vhost_net directly accesses ptr ring of tap driver to
> fetch Rx packet pointers. In order to avoid it this patch modifies
> tap driver's recvmsg api to do additional task of fetching Rx packet
> pointers.
>
> A special struct tun_msg_ctl is already being usedd via msg_control
> for tun Rx XDP batching. This patch extends tun_msg_ctl usage to
> send sub commands to recvmsg api. recvmsg can now produce/unproduce
> pointers from ptr ring as an additional task.
>
> This will be useful in future in implementation of virtio-net XDP
> offload feature. Where packets will be XDP batch processed in
> tun_recvmsg.
>
> Signed-off-by: Prashant Bhole <prashantbhole.linux@gmail.com>
> ---
>   drivers/net/tap.c      | 22 +++++++++++++++++++-
>   drivers/net/tun.c      | 24 +++++++++++++++++++++-
>   drivers/vhost/net.c    | 46 +++++++++++++++++++++++++++++++++---------
>   include/linux/if_tun.h |  3 +++
>   4 files changed, 83 insertions(+), 12 deletions(-)
>
> diff --git a/drivers/net/tap.c b/drivers/net/tap.c
> index 01bd260ce60c..3d0bf382dbbc 100644
> --- a/drivers/net/tap.c
> +++ b/drivers/net/tap.c
> @@ -1234,8 +1234,28 @@ static int tap_recvmsg(struct socket *sock, struct msghdr *m,
>   		       size_t total_len, int flags)
>   {
>   	struct tap_queue *q = container_of(sock, struct tap_queue, sock);
> -	struct sk_buff *skb = m->msg_control;
> +	struct tun_msg_ctl *ctl = m->msg_control;
> +	struct sk_buff *skb = NULL;
>   	int ret;
> +
> +	if (ctl) {
> +		switch (ctl->cmd) {
> +		case TUN_CMD_PACKET:
> +			skb = ctl->ptr;
> +			break;
> +		case TUN_CMD_PRODUCE_PTRS:


I think we need a better name of the command to avoid uncovering the 
implementation details of the lower socket.


> +			return ptr_ring_consume_batched(&q->ring,
> +							ctl->ptr_array,
> +							ctl->num);
> +		case TUN_CMD_UNPRODUCE_PTRS:
> +			ptr_ring_unconsume(&q->ring, ctl->ptr_array, ctl->num,
> +					   tun_ptr_free);
> +			return 0;
> +		default:
> +			return -EINVAL;
> +		}
> +	}
> +
>   	if (flags & ~(MSG_DONTWAIT|MSG_TRUNC)) {
>   		kfree_skb(skb);
>   		return -EINVAL;
> diff --git a/drivers/net/tun.c b/drivers/net/tun.c
> index 29711671959b..7d4886f53389 100644
> --- a/drivers/net/tun.c
> +++ b/drivers/net/tun.c
> @@ -2577,7 +2577,8 @@ static int tun_recvmsg(struct socket *sock, struct msghdr *m, size_t total_len,
>   {
>   	struct tun_file *tfile = container_of(sock, struct tun_file, socket);
>   	struct tun_struct *tun = tun_get(tfile);
> -	void *ptr = m->msg_control;
> +	struct tun_msg_ctl *ctl = m->msg_control;
> +	void *ptr = NULL;
>   	int ret;
>   
>   	if (!tun) {
> @@ -2585,6 +2586,27 @@ static int tun_recvmsg(struct socket *sock, struct msghdr *m, size_t total_len,
>   		goto out_free;
>   	}
>   
> +	if (ctl) {
> +		switch (ctl->cmd) {
> +		case TUN_CMD_PACKET:
> +			ptr = ctl->ptr;
> +			break;
> +		case TUN_CMD_PRODUCE_PTRS:
> +			ret = ptr_ring_consume_batched(&tfile->tx_ring,
> +						       ctl->ptr_array,
> +						       ctl->num);
> +			goto out;
> +		case TUN_CMD_UNPRODUCE_PTRS:
> +			ptr_ring_unconsume(&tfile->tx_ring, ctl->ptr_array,
> +					   ctl->num, tun_ptr_free);
> +			ret = 0;
> +			goto out;
> +		default:
> +			ret = -EINVAL;
> +			goto out_put_tun;
> +		}
> +	}
> +
>   	if (flags & ~(MSG_DONTWAIT|MSG_TRUNC|MSG_ERRQUEUE)) {
>   		ret = -EINVAL;
>   		goto out_put_tun;
> diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
> index 5946d2775bd0..5e5c1063606c 100644
> --- a/drivers/vhost/net.c
> +++ b/drivers/vhost/net.c
> @@ -175,24 +175,44 @@ static void *vhost_net_buf_consume(struct vhost_net_buf *rxq)
>   
>   static int vhost_net_buf_produce(struct vhost_net_virtqueue *nvq)
>   {
> +	struct vhost_virtqueue *vq = &nvq->vq;
> +	struct socket *sock = vq->private_data;
>   	struct vhost_net_buf *rxq = &nvq->rxq;
> +	struct tun_msg_ctl ctl = {
> +		.cmd = TUN_CMD_PRODUCE_PTRS,
> +		.ptr_array = rxq->queue,
> +		.num = VHOST_NET_BATCH,
> +	};
> +	struct msghdr msg = {
> +		.msg_control = &ctl,
> +	};
>   
>   	rxq->head = 0;
> -	rxq->tail = ptr_ring_consume_batched(nvq->rx_ring, rxq->queue,
> -					      VHOST_NET_BATCH);
> +	rxq->tail = sock->ops->recvmsg(sock, &msg, 0, 0);
> +	if (rxq->tail < 0)
> +		rxq->tail = 0;
> +
>   	return rxq->tail;
>   }
>   
>   static void vhost_net_buf_unproduce(struct vhost_net_virtqueue *nvq)
>   {
> +	struct vhost_virtqueue *vq = &nvq->vq;
> +	struct socket *sock = vq->private_data;
>   	struct vhost_net_buf *rxq = &nvq->rxq;
> +	struct tun_msg_ctl ctl = {
> +		.cmd = TUN_CMD_UNPRODUCE_PTRS,
> +		.ptr_array = rxq->queue + rxq->head,
> +		.num = vhost_net_buf_get_size(rxq),
> +	};
> +	struct msghdr msg = {
> +		.msg_control = &ctl,
> +	};
>   
> -	if (nvq->rx_ring && !vhost_net_buf_is_empty(rxq)) {
> -		ptr_ring_unconsume(nvq->rx_ring, rxq->queue + rxq->head,
> -				   vhost_net_buf_get_size(rxq),
> -				   tun_ptr_free);
> -		rxq->head = rxq->tail = 0;
> -	}
> +	if (!vhost_net_buf_is_empty(rxq))
> +		sock->ops->recvmsg(sock, &msg, 0, 0);
> +
> +	rxq->head = rxq->tail = 0;
>   }
>   
>   static int vhost_net_buf_peek_len(void *ptr)
> @@ -1109,6 +1129,9 @@ static void handle_rx(struct vhost_net *net)
>   		.flags = 0,
>   		.gso_type = VIRTIO_NET_HDR_GSO_NONE
>   	};
> +	struct tun_msg_ctl ctl = {
> +		.cmd = TUN_CMD_PACKET,
> +	};
>   	size_t total_len = 0;
>   	int err, mergeable;
>   	s16 headcount;
> @@ -1166,8 +1189,11 @@ static void handle_rx(struct vhost_net *net)
>   			goto out;
>   		}
>   		busyloop_intr = false;
> -		if (nvq->rx_ring)
> -			msg.msg_control = vhost_net_buf_consume(&nvq->rxq);
> +		if (nvq->rx_ring) {
> +			ctl.cmd = TUN_CMD_PACKET;


Looks duplicated with the above initialization.


> +			ctl.ptr = vhost_net_buf_consume(&nvq->rxq);
> +			msg.msg_control = &ctl;
> +		}
>   		/* On overrun, truncate and discard */
>   		if (unlikely(headcount > UIO_MAXIOV)) {
>   			iov_iter_init(&msg.msg_iter, READ, vq->iov, 1, 1);
> diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h
> index bdfa671612db..8608d4095143 100644
> --- a/include/linux/if_tun.h
> +++ b/include/linux/if_tun.h
> @@ -13,10 +13,13 @@
>   
>   #define TUN_CMD_PACKET 1
>   #define TUN_CMD_BATCH  2
> +#define TUN_CMD_PRODUCE_PTRS	3
> +#define TUN_CMD_UNPRODUCE_PTRS	4
>   struct tun_msg_ctl {
>   	unsigned short cmd;
>   	unsigned short num;
>   	void *ptr;
> +	void **ptr_array;


Using a union or just using void * is sufficient (rename it to void *data)?

Thanks


>   };
>   
>   struct tun_xdp_hdr {

  reply index

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-10-12  1:53 [PATCH net-next 0/3] vhost_net: access ptr ring using tap recvmsg prashantbhole.linux
2019-10-12  1:53 ` [PATCH net-next 1/3] tuntap: reorganize tun_msg_ctl usage prashantbhole.linux
2019-10-12  7:44   ` Jason Wang
2019-10-15  0:33     ` Prashant Bhole
2019-10-12  1:53 ` [PATCH net-next 2/3] vhost_net: user tap recvmsg api to access ptr ring prashantbhole.linux
2019-10-12  7:54   ` Jason Wang [this message]
2019-10-12 20:41   ` Michael S. Tsirkin
2019-10-15  0:57     ` Prashant Bhole
2019-10-12  1:53 ` [PATCH net-next 3/3] tuntap: remove usage of ptr ring in vhost_net prashantbhole.linux
2019-10-12  7:57 ` [PATCH net-next 0/3] vhost_net: access ptr ring using tap recvmsg Jason Wang
2019-10-12 20:38   ` Michael S. Tsirkin

Reply instructions:

You may reply publically 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=9cb43497-1f43-562e-74af-21370492fe14@redhat.com \
    --to=jasowang@redhat.com \
    --cc=davem@davemloft.net \
    --cc=dsahern@gmail.com \
    --cc=kvm@vger.kernel.org \
    --cc=mst@redhat.com \
    --cc=netdev@vger.kernel.org \
    --cc=prashantbhole.linux@gmail.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

KVM Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/kvm/0 kvm/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 kvm kvm/ https://lore.kernel.org/kvm \
		kvm@vger.kernel.org kvm@archiver.kernel.org
	public-inbox-index kvm

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.kvm


AGPL code for this site: git clone https://public-inbox.org/ public-inbox