Merge branch 'af_unix_sendpage'

Hannes Frederic Sowa says:

====================
net: af_unix: zerocopy stream bits

This series implements zerocopy support for AF_UNIX SOCK_STREAM sockets.

Changelog in the specific patches. Thanks to all the reviewers!
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

fs/splice.c

@@ -261,6 +261,7 @@ ssize_t splice_to_pipe(struct pipe_inode_info *pipe,
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(splice_to_pipe);
 
 void spd_release_page(struct splice_pipe_desc *spd, unsigned int i)
 {

include/linux/skbuff.h

@@ -35,6 +35,7 @@
 #include <linux/netdev_features.h>
 #include <linux/sched.h>
 #include <net/flow_dissector.h>
+#include <linux/splice.h>
 
 /* A. Checksumming of received packets by device.
  *
@@ -861,6 +862,9 @@ int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb,
 					int len, int odd, struct sk_buff *skb),
 			    void *from, int length);
 
+int skb_append_pagefrags(struct sk_buff *skb, struct page *page,
+			 int offset, size_t size);
+
 struct skb_seq_state {
 	__u32		lower_offset;
 	__u32		upper_offset;
@@ -2696,9 +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,

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;
 
 	/*
@@ -1914,23 +1937,12 @@ 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;
 }
+EXPORT_SYMBOL_GPL(skb_splice_bits);
 
 /**
  *	skb_store_bits - store bits from kernel buffer to skb
@@ -2915,6 +2927,24 @@ int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb,
 }
 EXPORT_SYMBOL(skb_append_datato_frags);
 
+int skb_append_pagefrags(struct sk_buff *skb, struct page *page,
+			 int offset, size_t size)
+{
+	int i = skb_shinfo(skb)->nr_frags;
+
+	if (skb_can_coalesce(skb, i, page, offset)) {
+		skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], size);
+	} else if (i < MAX_SKB_FRAGS) {
+		get_page(page);
+		skb_fill_page_desc(skb, i, page, offset, size);
+	} else {
+		return -EMSGSIZE;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(skb_append_pagefrags);
+
 /**
  *	skb_pull_rcsum - pull skb and update receive checksum
  *	@skb: buffer to update

net/ipv4/ip_output.c

@@ -1233,11 +1233,9 @@ ssize_t	ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
 	}
 
 	while (size > 0) {
-		int i;
-
-		if (skb_is_gso(skb))
+		if (skb_is_gso(skb)) {
 			len = size;
-		else {
+		} else {
 
 			/* Check if the remaining data fits into current packet. */
 			len = mtu - skb->len;
@@ -1289,15 +1287,10 @@ ssize_t	ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
 			continue;
 		}
 
-		i = skb_shinfo(skb)->nr_frags;
 		if (len > size)
 			len = size;
-		if (skb_can_coalesce(skb, i, page, offset)) {
-			skb_frag_size_add(&skb_shinfo(skb)->frags[i-1], len);
-		} else if (i < MAX_SKB_FRAGS) {
-			get_page(page);
-			skb_fill_page_desc(skb, i, page, offset, len);
-		} else {
+
+		if (skb_append_pagefrags(skb, page, offset, len)) {
 			err = -EMSGSIZE;
 			goto error;
 		}

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;