linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jason Wang <jasowang@redhat.com>
To: netdev@vger.kernel.org, linux-kernel@vger.kernel.org
Cc: kvm@vger.kernel.org, virtualization@lists.linux-foundation.org,
	mst@redhat.com, jasowang@redhat.com
Subject: [PATCH net-next V2 08/11] tun: switch to new type of msg_control
Date: Wed, 12 Sep 2018 11:17:06 +0800	[thread overview]
Message-ID: <20180912031709.14112-9-jasowang@redhat.com> (raw)
In-Reply-To: <20180912031709.14112-1-jasowang@redhat.com>

This patch introduces to a new tun/tap specific msg_control:

#define TUN_MSG_UBUF 1
#define TUN_MSG_PTR  2
struct tun_msg_ctl {
       int type;
       void *ptr;
};

This allows us to pass different kinds of msg_control through
sendmsg(). The first supported type is ubuf (TUN_MSG_UBUF) which will
be used by the existed vhost_net zerocopy code. The second is XDP
buff, which allows vhost_net to pass XDP buff to TUN. This could be
used to implement accepting an array of XDP buffs from vhost_net in
the following patches.

Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 drivers/net/tap.c      | 18 ++++++++++++------
 drivers/net/tun.c      |  6 +++++-
 drivers/vhost/net.c    |  7 +++++--
 include/linux/if_tun.h | 14 ++++++++++++++
 4 files changed, 36 insertions(+), 9 deletions(-)

diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index f0f7cd977667..7996ed7cbf18 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -619,7 +619,7 @@ static inline struct sk_buff *tap_alloc_skb(struct sock *sk, size_t prepad,
 #define TAP_RESERVE HH_DATA_OFF(ETH_HLEN)
 
 /* Get packet from user space buffer */
-static ssize_t tap_get_user(struct tap_queue *q, struct msghdr *m,
+static ssize_t tap_get_user(struct tap_queue *q, void *msg_control,
 			    struct iov_iter *from, int noblock)
 {
 	int good_linear = SKB_MAX_HEAD(TAP_RESERVE);
@@ -663,7 +663,7 @@ static ssize_t tap_get_user(struct tap_queue *q, struct msghdr *m,
 	if (unlikely(len < ETH_HLEN))
 		goto err;
 
-	if (m && m->msg_control && sock_flag(&q->sk, SOCK_ZEROCOPY)) {
+	if (msg_control && sock_flag(&q->sk, SOCK_ZEROCOPY)) {
 		struct iov_iter i;
 
 		copylen = vnet_hdr.hdr_len ?
@@ -724,11 +724,11 @@ static ssize_t tap_get_user(struct tap_queue *q, struct msghdr *m,
 	tap = rcu_dereference(q->tap);
 	/* copy skb_ubuf_info for callback when skb has no error */
 	if (zerocopy) {
-		skb_shinfo(skb)->destructor_arg = m->msg_control;
+		skb_shinfo(skb)->destructor_arg = msg_control;
 		skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY;
 		skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG;
-	} else if (m && m->msg_control) {
-		struct ubuf_info *uarg = m->msg_control;
+	} else if (msg_control) {
+		struct ubuf_info *uarg = msg_control;
 		uarg->callback(uarg, false);
 	}
 
@@ -1150,7 +1150,13 @@ static int tap_sendmsg(struct socket *sock, struct msghdr *m,
 		       size_t total_len)
 {
 	struct tap_queue *q = container_of(sock, struct tap_queue, sock);
-	return tap_get_user(q, m, &m->msg_iter, m->msg_flags & MSG_DONTWAIT);
+	struct tun_msg_ctl *ctl = m->msg_control;
+
+	if (ctl && ctl->type != TUN_MSG_UBUF)
+		return -EINVAL;
+
+	return tap_get_user(q, ctl ? ctl->ptr : NULL, &m->msg_iter,
+			    m->msg_flags & MSG_DONTWAIT);
 }
 
 static int tap_recvmsg(struct socket *sock, struct msghdr *m,
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 3ae539374f6b..89779b58c7ca 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -2431,11 +2431,15 @@ static int tun_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
 	int ret;
 	struct tun_file *tfile = container_of(sock, struct tun_file, socket);
 	struct tun_struct *tun = tun_get(tfile);
+	struct tun_msg_ctl *ctl = m->msg_control;
 
 	if (!tun)
 		return -EBADFD;
 
-	ret = tun_get_user(tun, tfile, m->msg_control, &m->msg_iter,
+	if (ctl && ctl->type != TUN_MSG_UBUF)
+		return -EINVAL;
+
+	ret = tun_get_user(tun, tfile, ctl ? ctl->ptr : NULL, &m->msg_iter,
 			   m->msg_flags & MSG_DONTWAIT,
 			   m->msg_flags & MSG_MORE);
 	tun_put(tun);
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 4e656f89cb22..fb01ce6d981c 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -620,6 +620,7 @@ static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock)
 		.msg_controllen = 0,
 		.msg_flags = MSG_DONTWAIT,
 	};
+	struct tun_msg_ctl ctl;
 	size_t len, total_len = 0;
 	int err;
 	struct vhost_net_ubuf_ref *uninitialized_var(ubufs);
@@ -664,8 +665,10 @@ static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock)
 			ubuf->ctx = nvq->ubufs;
 			ubuf->desc = nvq->upend_idx;
 			refcount_set(&ubuf->refcnt, 1);
-			msg.msg_control = ubuf;
-			msg.msg_controllen = sizeof(ubuf);
+			msg.msg_control = &ctl;
+			ctl.type = TUN_MSG_UBUF;
+			ctl.ptr = ubuf;
+			msg.msg_controllen = sizeof(ctl);
 			ubufs = nvq->ubufs;
 			atomic_inc(&ubufs->refcount);
 			nvq->upend_idx = (nvq->upend_idx + 1) % UIO_MAXIOV;
diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h
index 3d2996dc7d85..12e3eebf0ce6 100644
--- a/include/linux/if_tun.h
+++ b/include/linux/if_tun.h
@@ -16,9 +16,23 @@
 #define __IF_TUN_H
 
 #include <uapi/linux/if_tun.h>
+#include <uapi/linux/virtio_net.h>
 
 #define TUN_XDP_FLAG 0x1UL
 
+#define TUN_MSG_UBUF 1
+#define TUN_MSG_PTR  2
+struct tun_msg_ctl {
+	unsigned short type;
+	unsigned short num;
+	void *ptr;
+};
+
+struct tun_xdp_hdr {
+	int buflen;
+	struct virtio_net_hdr gso;
+};
+
 #if defined(CONFIG_TUN) || defined(CONFIG_TUN_MODULE)
 struct socket *tun_get_socket(struct file *);
 struct ptr_ring *tun_get_tx_ring(struct file *file);
-- 
2.17.1


  parent reply	other threads:[~2018-09-12  3:18 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-09-12  3:16 [PATCH net-next V2 00/11] vhost_net TX batching Jason Wang
2018-09-12  3:16 ` [PATCH net-next V2 01/11] net: sock: introduce SOCK_XDP Jason Wang
2018-09-12  3:17 ` [PATCH net-next V2 02/11] tuntap: switch to use XDP_PACKET_HEADROOM Jason Wang
2018-09-12  3:17 ` [PATCH net-next V2 03/11] tuntap: enable bh early during processing XDP Jason Wang
2018-09-12  3:17 ` [PATCH net-next V2 04/11] tuntap: simplify error handling in tun_build_skb() Jason Wang
2018-09-12  3:17 ` [PATCH net-next V2 05/11] tuntap: tweak on the path of skb XDP case " Jason Wang
2018-09-12  3:17 ` [PATCH net-next V2 06/11] tuntap: split out XDP logic Jason Wang
2018-09-12  3:17 ` [PATCH net-next V2 07/11] tuntap: move XDP flushing out of tun_do_xdp() Jason Wang
2018-09-12  3:17 ` Jason Wang [this message]
2018-09-12  3:17 ` [PATCH net-next V2 09/11] tuntap: accept an array of XDP buffs through sendmsg() Jason Wang
2018-09-12  3:17 ` [PATCH net-next V2 10/11] tap: " Jason Wang
2018-09-12  3:17 ` [PATCH net-next V2 11/11] vhost_net: batch submitting XDP buffers to underlayer sockets Jason Wang
2018-09-13 18:04   ` Michael S. Tsirkin
2018-09-14  3:11     ` Jason Wang
2018-09-13 16:28 ` [PATCH net-next V2 00/11] vhost_net TX batching David Miller
2018-09-13 18:02   ` Michael S. Tsirkin
2018-09-13 18:05     ` David Miller

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=20180912031709.14112-9-jasowang@redhat.com \
    --to=jasowang@redhat.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mst@redhat.com \
    --cc=netdev@vger.kernel.org \
    --cc=virtualization@lists.linux-foundation.org \
    /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).