From 306b13eb3cf9515a8214bbf5d69d811371d05792 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Fri, 28 Jul 2017 16:22:41 -0700 Subject: proto_ops: Add locked held versions of sendmsg and sendpage Add new proto_ops sendmsg_locked and sendpage_locked that can be called when the socket lock is already held. Correspondingly, add kernel_sendmsg_locked and kernel_sendpage_locked as front end functions. These functions will be used in zero proxy so that we can take the socket lock in a ULP sendmsg/sendpage and then directly call the backend transport proto_ops functions. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/net.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index dda2cc939a53..b5c15b31709b 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -190,8 +190,16 @@ struct proto_ops { struct pipe_inode_info *pipe, size_t len, unsigned int flags); int (*set_peek_off)(struct sock *sk, int val); int (*peek_len)(struct socket *sock); + + /* The following functions are called internally by kernel with + * sock lock already held. + */ int (*read_sock)(struct sock *sk, read_descriptor_t *desc, sk_read_actor_t recv_actor); + int (*sendpage_locked)(struct sock *sk, struct page *page, + int offset, size_t size, int flags); + int (*sendmsg_locked)(struct sock *sk, struct msghdr *msg, + size_t size); }; #define DECLARE_SOCKADDR(type, dst, src) \ @@ -279,6 +287,8 @@ do { \ int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len); +int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg, + struct kvec *vec, size_t num, size_t len); int kernel_recvmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len, int flags); @@ -297,6 +307,8 @@ int kernel_setsockopt(struct socket *sock, int level, int optname, char *optval, unsigned int optlen); int kernel_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags); +int kernel_sendpage_locked(struct sock *sk, struct page *page, int offset, + size_t size, int flags); int kernel_sock_ioctl(struct socket *sock, int cmd, unsigned long arg); int kernel_sock_shutdown(struct socket *sock, enum sock_shutdown_cmd how); -- cgit v1.2.3 From 20bf50de3028cb15fa81e1d1e63ab6e0c85257fc Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Fri, 28 Jul 2017 16:22:42 -0700 Subject: skbuff: Function to send an skbuf on a socket Add skb_send_sock to send an skbuff on a socket within the kernel. Arguments include an offset so that an skbuf might be sent in mulitple calls (e.g. send buffer limit is hit). Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/skbuff.h | 3 ++ net/core/skbuff.c | 101 +++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 104 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 4093552be1de..18e76bf9574e 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3113,6 +3113,9 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, u8 *to, 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); +int skb_send_sock_locked(struct sock *sk, struct sk_buff *skb, int offset, + int len); +int skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len); 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 c27da51d14e4..9c0e015ff3fe 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1982,6 +1982,107 @@ int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset, } EXPORT_SYMBOL_GPL(skb_splice_bits); +/* Send skb data on a socket. Socket must be locked. */ +int skb_send_sock_locked(struct sock *sk, struct sk_buff *skb, int offset, + int len) +{ + unsigned int orig_len = len; + struct sk_buff *head = skb; + unsigned short fragidx; + int slen, ret; + +do_frag_list: + + /* Deal with head data */ + while (offset < skb_headlen(skb) && len) { + struct kvec kv; + struct msghdr msg; + + slen = min_t(int, len, skb_headlen(skb) - offset); + kv.iov_base = skb->data + offset; + kv.iov_len = len; + memset(&msg, 0, sizeof(msg)); + + ret = kernel_sendmsg_locked(sk, &msg, &kv, 1, slen); + if (ret <= 0) + goto error; + + offset += ret; + len -= ret; + } + + /* All the data was skb head? */ + if (!len) + goto out; + + /* Make offset relative to start of frags */ + offset -= skb_headlen(skb); + + /* Find where we are in frag list */ + for (fragidx = 0; fragidx < skb_shinfo(skb)->nr_frags; fragidx++) { + skb_frag_t *frag = &skb_shinfo(skb)->frags[fragidx]; + + if (offset < frag->size) + break; + + offset -= frag->size; + } + + for (; len && fragidx < skb_shinfo(skb)->nr_frags; fragidx++) { + skb_frag_t *frag = &skb_shinfo(skb)->frags[fragidx]; + + slen = min_t(size_t, len, frag->size - offset); + + while (slen) { + ret = kernel_sendpage_locked(sk, frag->page.p, + frag->page_offset + offset, + slen, MSG_DONTWAIT); + if (ret <= 0) + goto error; + + len -= ret; + offset += ret; + slen -= ret; + } + + offset = 0; + } + + if (len) { + /* Process any frag lists */ + + if (skb == head) { + if (skb_has_frag_list(skb)) { + skb = skb_shinfo(skb)->frag_list; + goto do_frag_list; + } + } else if (skb->next) { + skb = skb->next; + goto do_frag_list; + } + } + +out: + return orig_len - len; + +error: + return orig_len == len ? ret : orig_len - len; +} +EXPORT_SYMBOL_GPL(skb_send_sock_locked); + +/* Send skb data on a socket. */ +int skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len) +{ + int ret = 0; + + lock_sock(sk); + ret = skb_send_sock_locked(sk, skb, offset, len); + release_sock(sk); + + return ret; +} +EXPORT_SYMBOL_GPL(skb_send_sock); + /** * skb_store_bits - store bits from kernel buffer to skb * @skb: destination buffer -- cgit v1.2.3