All of lore.kernel.org
 help / color / mirror / Atom feed
From: Prashant Bhole <prashantbhole.linux@gmail.com>
To: "David S . Miller" <davem@davemloft.net>,
	"Michael S . Tsirkin" <mst@redhat.com>,
	Alexei Starovoitov <ast@kernel.org>,
	Daniel Borkmann <daniel@iogearbox.net>,
	Jesper Dangaard Brouer <hawk@kernel.org>
Cc: Prashant Bhole <prashantbhole.linux@gmail.com>,
	Jason Wang <jasowang@redhat.com>, David Ahern <dsahern@gmail.com>,
	Jakub Kicinski <jakub.kicinski@netronome.com>,
	John Fastabend <john.fastabend@gmail.com>,
	Toshiaki Makita <toshiaki.makita1@gmail.com>,
	Martin KaFai Lau <kafai@fb.com>, Song Liu <songliubraving@fb.com>,
	Yonghong Song <yhs@fb.com>, Andrii Nakryiko <andriin@fb.com>,
	netdev@vger.kernel.org
Subject: [RFC v2 net-next 09/12] vhost_net: user tap recvmsg api to access ptr ring
Date: Thu, 26 Dec 2019 11:31:57 +0900	[thread overview]
Message-ID: <20191226023200.21389-10-prashantbhole.linux@gmail.com> (raw)
In-Reply-To: <20191226023200.21389-1-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 passed via msg_control
for tun Rx XDP batching. This patch extends tun_msg_ctl usage to
send sub commands to recvmsg api. Now tun_recvmsg will handle commands
to consume and unconsume packet pointers from ptr ring.

This will be useful in implementation of tx path XDP in tun driver,
where XDP program will process the packet before it is passed to
vhost_net.

Signed-off-by: Prashant Bhole <prashantbhole.linux@gmail.com>
---
 drivers/net/tap.c      | 22 ++++++++++++++++++-
 drivers/net/tun.c      | 24 ++++++++++++++++++++-
 drivers/vhost/net.c    | 48 +++++++++++++++++++++++++++++++-----------
 include/linux/if_tun.h | 18 ++++++++++++++++
 4 files changed, 98 insertions(+), 14 deletions(-)

diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index a0a5dc18109a..a5ce44db11a3 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -1224,8 +1224,28 @@ 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->type) {
+		case TUN_MSG_PKT:
+			skb = ctl->ptr;
+			break;
+		case TUN_MSG_CONSUME_PKTS:
+			return ptr_ring_consume_batched(&q->ring,
+							ctl->ptr,
+							ctl->num);
+		case TUN_MSG_UNCONSUME_PKTS:
+			ptr_ring_unconsume(&q->ring, ctl->ptr, 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 1e436d9ec4e1..4f28f2387435 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->type) {
+		case TUN_MSG_PKT:
+			ptr = ctl->ptr;
+			break;
+		case TUN_MSG_CONSUME_PKTS:
+			ret = ptr_ring_consume_batched(&tfile->tx_ring,
+						       ctl->ptr,
+						       ctl->num);
+			goto out;
+		case TUN_MSG_UNCONSUME_PKTS:
+			ptr_ring_unconsume(&tfile->tx_ring, ctl->ptr,
+					   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 e158159671fa..482548d00105 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 = {
+		.type = TUN_MSG_CONSUME_PKTS,
+		.ptr = (void *) 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 (WARN_ON_ONCE(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 = {
+		.type = TUN_MSG_UNCONSUME_PKTS,
+		.ptr = (void *) (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 +1129,7 @@ static void handle_rx(struct vhost_net *net)
 		.flags = 0,
 		.gso_type = VIRTIO_NET_HDR_GSO_NONE
 	};
+	struct tun_msg_ctl ctl;
 	size_t total_len = 0;
 	int err, mergeable;
 	s16 headcount;
@@ -1166,8 +1187,11 @@ 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.type = TUN_MSG_PKT;
+			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);
@@ -1346,8 +1370,8 @@ static struct socket *vhost_net_stop_vq(struct vhost_net *n,
 	mutex_lock(&vq->mutex);
 	sock = vq->private_data;
 	vhost_net_disable_vq(n, vq);
-	vq->private_data = NULL;
 	vhost_net_buf_unproduce(nvq);
+	vq->private_data = NULL;
 	nvq->rx_ring = NULL;
 	mutex_unlock(&vq->mutex);
 	return sock;
@@ -1538,8 +1562,8 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
 		}
 
 		vhost_net_disable_vq(n, vq);
-		vq->private_data = sock;
 		vhost_net_buf_unproduce(nvq);
+		vq->private_data = sock;
 		r = vhost_vq_init_access(vq);
 		if (r)
 			goto err_used;
diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h
index 5bda8cf457b6..bb94843e3829 100644
--- a/include/linux/if_tun.h
+++ b/include/linux/if_tun.h
@@ -11,8 +11,26 @@
 
 #define TUN_XDP_FLAG 0x1UL
 
+/*
+ * tun_msg_ctl types
+ */
+
 #define TUN_MSG_UBUF 1
 #define TUN_MSG_PTR  2
+/*
+ * Used for passing a packet pointer from vhost to tun
+ */
+#define TUN_MSG_PKT  3
+/*
+ * Used for passing an array of pointer from vhost to tun.
+ * tun consumes packets from ptr ring and stores in pointer array.
+ */
+#define TUN_MSG_CONSUME_PKTS    4
+/*
+ * Used for passing an array of pointer from vhost to tun.
+ * tun consumes get pointer from array and puts back into ptr ring.
+ */
+#define TUN_MSG_UNCONSUME_PKTS  5
 struct tun_msg_ctl {
 	unsigned short type;
 	unsigned short num;
-- 
2.21.0


  parent reply	other threads:[~2019-12-26  2:33 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-12-26  2:31 [RFC v2 net-next 00/12] XDP in tx path Prashant Bhole
2019-12-26  2:31 ` [RFC v2 net-next 01/12] net: introduce BPF_XDP_EGRESS attach type for XDP Prashant Bhole
2019-12-27 14:27   ` Jesper Dangaard Brouer
2019-12-28  0:15     ` Prashant Bhole
2020-01-07 11:35       ` Toke Høiland-Jørgensen
2020-01-11  0:53         ` Prashant Bhole
2019-12-26  2:31 ` [RFC v2 net-next 02/12] tools: sync kernel uapi/linux/if_link.h header Prashant Bhole
2019-12-26  2:31 ` [RFC v2 net-next 03/12] libbpf: api for getting/setting link xdp options Prashant Bhole
2019-12-30  4:49   ` Andrii Nakryiko
2020-01-03 11:04     ` Prashant Bhole
2019-12-26  2:31 ` [RFC v2 net-next 04/12] libbpf: set xdp program in tx path Prashant Bhole
2019-12-26  2:31 ` [RFC v2 net-next 05/12] samples/bpf: xdp1, add XDP tx support Prashant Bhole
2019-12-26  2:31 ` [RFC v2 net-next 06/12] net: core: rename netif_receive_generic_xdp() to do_generic_xdp_core() Prashant Bhole
2019-12-26  2:31 ` [RFC v2 net-next 07/12] net: core: export do_xdp_generic_core() Prashant Bhole
2019-12-26  2:31 ` [RFC v2 net-next 08/12] tuntap: check tun_msg_ctl type at necessary places Prashant Bhole
2019-12-26  2:31 ` Prashant Bhole [this message]
2019-12-26  9:05   ` [RFC v2 net-next 09/12] vhost_net: user tap recvmsg api to access ptr ring kbuild test robot
2019-12-26  2:31 ` [RFC v2 net-next 10/12] tuntap: remove usage of ptr ring in vhost_net Prashant Bhole
2019-12-26  2:31 ` [RFC v2 net-next 11/12] tun: set tx path XDP program Prashant Bhole
2019-12-26  2:32 ` [RFC v2 net-next 12/12] tun: run XDP program in tx path Prashant Bhole
2019-12-26 19:23 ` [RFC v2 net-next 00/12] XDP " Tom Herbert
2019-12-27  1:35   ` Prashant Bhole

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=20191226023200.21389-10-prashantbhole.linux@gmail.com \
    --to=prashantbhole.linux@gmail.com \
    --cc=andriin@fb.com \
    --cc=ast@kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=davem@davemloft.net \
    --cc=dsahern@gmail.com \
    --cc=hawk@kernel.org \
    --cc=jakub.kicinski@netronome.com \
    --cc=jasowang@redhat.com \
    --cc=john.fastabend@gmail.com \
    --cc=kafai@fb.com \
    --cc=mst@redhat.com \
    --cc=netdev@vger.kernel.org \
    --cc=songliubraving@fb.com \
    --cc=toshiaki.makita1@gmail.com \
    --cc=yhs@fb.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.