From 1c32c5ad6fac8cee1a77449f5abf211e911ff830 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 1 Mar 2011 02:36:47 +0000 Subject: [PATCH] inet: Add ip_make_skb and ip_finish_skb This patch adds the helper ip_make_skb which is like ip_append_data and ip_push_pending_frames all rolled into one, except that it does not send the skb produced. The sending part is carried out by ip_send_skb, which the transport protocol can call after it has tweaked the skb. It is meant to be called in cases where corking is not used should have a one-to-one correspondence to sendmsg. This patch also adds the helper ip_finish_skb which is meant to be replace ip_push_pending_frames when corking is required. Previously the protocol stack would peek at the socket write queue and add its header to the first packet. With ip_finish_skb, the protocol stack can directly operate on the final skb instead, just like the non-corking case with ip_make_skb. Signed-off-by: Herbert Xu Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/ip.h | 16 +++++++++++ net/ipv4/ip_output.c | 65 ++++++++++++++++++++++++++++++++++---------- 2 files changed, 67 insertions(+), 14 deletions(-) diff --git a/include/net/ip.h b/include/net/ip.h index 67fac78a186b..a4f631108c54 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -116,8 +116,24 @@ extern int ip_append_data(struct sock *sk, extern int ip_generic_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb); extern ssize_t ip_append_page(struct sock *sk, struct page *page, int offset, size_t size, int flags); +extern struct sk_buff *__ip_make_skb(struct sock *sk, + struct sk_buff_head *queue, + struct inet_cork *cork); +extern int ip_send_skb(struct sk_buff *skb); extern int ip_push_pending_frames(struct sock *sk); extern void ip_flush_pending_frames(struct sock *sk); +extern struct sk_buff *ip_make_skb(struct sock *sk, + int getfrag(void *from, char *to, int offset, int len, + int odd, struct sk_buff *skb), + void *from, int length, int transhdrlen, + struct ipcm_cookie *ipc, + struct rtable **rtp, + unsigned int flags); + +static inline struct sk_buff *ip_finish_skb(struct sock *sk) +{ + return __ip_make_skb(sk, &sk->sk_write_queue, &inet_sk(sk)->cork); +} /* datagram.c */ extern int ip4_datagram_connect(struct sock *sk, diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 1dd5ecc9a27e..460308c35028 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1267,9 +1267,9 @@ static void ip_cork_release(struct inet_cork *cork) * Combined all pending IP fragments on the socket as one IP datagram * and push them out. */ -static int __ip_push_pending_frames(struct sock *sk, - struct sk_buff_head *queue, - struct inet_cork *cork) +struct sk_buff *__ip_make_skb(struct sock *sk, + struct sk_buff_head *queue, + struct inet_cork *cork) { struct sk_buff *skb, *tmp_skb; struct sk_buff **tail_skb; @@ -1280,7 +1280,6 @@ static int __ip_push_pending_frames(struct sock *sk, struct iphdr *iph; __be16 df = 0; __u8 ttl; - int err = 0; if ((skb = __skb_dequeue(queue)) == NULL) goto out; @@ -1351,28 +1350,37 @@ static int __ip_push_pending_frames(struct sock *sk, icmp_out_count(net, ((struct icmphdr *) skb_transport_header(skb))->type); - /* Netfilter gets whole the not fragmented skb. */ + ip_cork_release(cork); +out: + return skb; +} + +int ip_send_skb(struct sk_buff *skb) +{ + struct net *net = sock_net(skb->sk); + int err; + err = ip_local_out(skb); if (err) { if (err > 0) err = net_xmit_errno(err); if (err) - goto error; + IP_INC_STATS(net, IPSTATS_MIB_OUTDISCARDS); } -out: - ip_cork_release(cork); return err; - -error: - IP_INC_STATS(net, IPSTATS_MIB_OUTDISCARDS); - goto out; } int ip_push_pending_frames(struct sock *sk) { - return __ip_push_pending_frames(sk, &sk->sk_write_queue, - &inet_sk(sk)->cork); + struct sk_buff *skb; + + skb = ip_finish_skb(sk); + if (!skb) + return 0; + + /* Netfilter gets whole the not fragmented skb. */ + return ip_send_skb(skb); } /* @@ -1395,6 +1403,35 @@ void ip_flush_pending_frames(struct sock *sk) __ip_flush_pending_frames(sk, &sk->sk_write_queue, &inet_sk(sk)->cork); } +struct sk_buff *ip_make_skb(struct sock *sk, + int getfrag(void *from, char *to, int offset, + int len, int odd, struct sk_buff *skb), + void *from, int length, int transhdrlen, + struct ipcm_cookie *ipc, struct rtable **rtp, + unsigned int flags) +{ + struct inet_cork cork = {}; + struct sk_buff_head queue; + int err; + + if (flags & MSG_PROBE) + return NULL; + + __skb_queue_head_init(&queue); + + err = ip_setup_cork(sk, &cork, ipc, rtp); + if (err) + return ERR_PTR(err); + + err = __ip_append_data(sk, &queue, &cork, getfrag, + from, length, transhdrlen, flags); + if (err) { + __ip_flush_pending_frames(sk, &queue, &cork); + return ERR_PTR(err); + } + + return __ip_make_skb(sk, &queue, &cork); +} /* * Fetch data from kernel space and fill in checksum if needed.