From a60e3cc7c92973a31fad0fd04dc5cf4355d3d1ef Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Thu, 21 May 2015 17:00:00 +0200 Subject: [PATCH] net: make skb_splice_bits more configureable Prepare skb_splice_bits to be able to deal with AF_UNIX sockets. AF_UNIX sockets don't use lock_sock/release_sock and thus we have to use a callback to make the locking and unlocking configureable. Signed-off-by: Hannes Frederic Sowa Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 11 +++++++++-- net/core/skbuff.c | 45 ++++++++++++++++++++++++++++----------------- net/ipv4/tcp.c | 5 +++-- 3 files changed, 40 insertions(+), 21 deletions(-) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index f708936..6b41c15 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -35,6 +35,7 @@ #include #include #include +#include /* A. Checksumming of received packets by device. * @@ -2699,9 +2700,15 @@ int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len); int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len); __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, u8 *to, int len, __wsum csum); -int skb_splice_bits(struct sk_buff *skb, unsigned int offset, +ssize_t skb_socket_splice(struct sock *sk, + struct pipe_inode_info *pipe, + struct splice_pipe_desc *spd); +int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset, struct pipe_inode_info *pipe, unsigned int len, - unsigned int flags); + unsigned int flags, + ssize_t (*splice_cb)(struct sock *, + struct pipe_inode_info *, + struct splice_pipe_desc *)); void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to); unsigned int skb_zerocopy_headlen(const struct sk_buff *from); int skb_zerocopy(struct sk_buff *to, struct sk_buff *from, diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 4f2babe..02769fa 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1870,15 +1870,39 @@ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, return false; } +ssize_t skb_socket_splice(struct sock *sk, + struct pipe_inode_info *pipe, + struct splice_pipe_desc *spd) +{ + int ret; + + /* Drop the socket lock, otherwise we have reverse + * locking dependencies between sk_lock and i_mutex + * here as compared to sendfile(). We enter here + * with the socket lock held, and splice_to_pipe() will + * grab the pipe inode lock. For sendfile() emulation, + * we call into ->sendpage() with the i_mutex lock held + * and networking will grab the socket lock. + */ + release_sock(sk); + ret = splice_to_pipe(pipe, spd); + lock_sock(sk); + + return ret; +} + /* * Map data from the skb to a pipe. Should handle both the linear part, * the fragments, and the frag list. It does NOT handle frag lists within * the frag list, if such a thing exists. We'd probably need to recurse to * handle that cleanly. */ -int skb_splice_bits(struct sk_buff *skb, unsigned int offset, +int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset, struct pipe_inode_info *pipe, unsigned int tlen, - unsigned int flags) + unsigned int flags, + ssize_t (*splice_cb)(struct sock *, + struct pipe_inode_info *, + struct splice_pipe_desc *)) { struct partial_page partial[MAX_SKB_FRAGS]; struct page *pages[MAX_SKB_FRAGS]; @@ -1891,7 +1915,6 @@ int skb_splice_bits(struct sk_buff *skb, unsigned int offset, .spd_release = sock_spd_release, }; struct sk_buff *frag_iter; - struct sock *sk = skb->sk; int ret = 0; /* @@ -1914,20 +1937,8 @@ int skb_splice_bits(struct sk_buff *skb, unsigned int offset, } done: - if (spd.nr_pages) { - /* - * Drop the socket lock, otherwise we have reverse - * locking dependencies between sk_lock and i_mutex - * here as compared to sendfile(). We enter here - * with the socket lock held, and splice_to_pipe() will - * grab the pipe inode lock. For sendfile() emulation, - * we call into ->sendpage() with the i_mutex lock held - * and networking will grab the socket lock. - */ - release_sock(sk); - ret = splice_to_pipe(pipe, &spd); - lock_sock(sk); - } + if (spd.nr_pages) + ret = splice_cb(sk, pipe, &spd); return ret; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 90afcec..65f791f 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -695,8 +695,9 @@ static int tcp_splice_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, struct tcp_splice_state *tss = rd_desc->arg.data; int ret; - ret = skb_splice_bits(skb, offset, tss->pipe, min(rd_desc->count, len), - tss->flags); + ret = skb_splice_bits(skb, skb->sk, offset, tss->pipe, + min(rd_desc->count, len), tss->flags, + skb_socket_splice); if (ret > 0) rd_desc->count -= ret; return ret; -- 2.7.4