/net/ipv4/tcp.c

Large files files are truncated, but you can click here to view the full file

/*
 * INET		An implementation of the TCP/IP protocol suite for the LINUX
 *		operating system.  INET is implemented using the  BSD Socket
 *		interface as the means of communication with the user level.
 *
 *		Implementation of the Transmission Control Protocol(TCP).
 *
 * Authors:	Ross Biro
 *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
 *		Mark Evans, <evansmp@uhura.aston.ac.uk>
 *		Corey Minyard <wf-rch!minyard@relay.EU.net>
 *		Florian La Roche, <flla@stud.uni-sb.de>
 *		Charles Hedrick, <hedrick@klinzhai.rutgers.edu>
 *		Linus Torvalds, <torvalds@cs.helsinki.fi>
 *		Alan Cox, <gw4pts@gw4pts.ampr.org>
 *		Matthew Dillon, <dillon@apollo.west.oic.com>
 *		Arnt Gulbrandsen, <agulbra@nvg.unit.no>
 *		Jorge Cwik, <jorge@laser.satlink.net>
 *
 * Fixes:
 *		Alan Cox	:	Numerous verify_area() calls
 *		Alan Cox	:	Set the ACK bit on a reset
 *		Alan Cox	:	Stopped it crashing if it closed while
 *					sk->inuse=1 and was trying to connect
 *					(tcp_err()).
 *		Alan Cox	:	All icmp error handling was broken
 *					pointers passed where wrong and the
 *					socket was looked up backwards. Nobody
 *					tested any icmp error code obviously.
 *		Alan Cox	:	tcp_err() now handled properly. It
 *					wakes people on errors. poll
 *					behaves and the icmp error race
 *					has gone by moving it into sock.c
 *		Alan Cox	:	tcp_send_reset() fixed to work for
 *					everything not just packets for
 *					unknown sockets.
 *		Alan Cox	:	tcp option processing.
 *		Alan Cox	:	Reset tweaked (still not 100%) [Had
 *					syn rule wrong]
 *		Herp Rosmanith  :	More reset fixes
 *		Alan Cox	:	No longer acks invalid rst frames.
 *					Acking any kind of RST is right out.
 *		Alan Cox	:	Sets an ignore me flag on an rst
 *					receive otherwise odd bits of prattle
 *					escape still
 *		Alan Cox	:	Fixed another acking RST frame bug.
 *					Should stop LAN workplace lockups.
 *		Alan Cox	: 	Some tidyups using the new skb list
 *					facilities
 *		Alan Cox	:	sk->keepopen now seems to work
 *		Alan Cox	:	Pulls options out correctly on accepts
 *		Alan Cox	:	Fixed assorted sk->rqueue->next errors
 *		Alan Cox	:	PSH doesn't end a TCP read. Switched a
 *					bit to skb ops.
 *		Alan Cox	:	Tidied tcp_data to avoid a potential
 *					nasty.
 *		Alan Cox	:	Added some better commenting, as the
 *					tcp is hard to follow
 *		Alan Cox	:	Removed incorrect check for 20 * psh
 *	Michael O'Reilly	:	ack < copied bug fix.
 *	Johannes Stille		:	Misc tcp fixes (not all in yet).
 *		Alan Cox	:	FIN with no memory -> CRASH
 *		Alan Cox	:	Added socket option proto entries.
 *					Also added awareness of them to accept.
 *		Alan Cox	:	Added TCP options (SOL_TCP)
 *		Alan Cox	:	Switched wakeup calls to callbacks,
 *					so the kernel can layer network
 *					sockets.
 *		Alan Cox	:	Use ip_tos/ip_ttl settings.
 *		Alan Cox	:	Handle FIN (more) properly (we hope).
 *		Alan Cox	:	RST frames sent on unsynchronised
 *					state ack error.
 *		Alan Cox	:	Put in missing check for SYN bit.
 *		Alan Cox	:	Added tcp_select_window() aka NET2E
 *					window non shrink trick.
 *		Alan Cox	:	Added a couple of small NET2E timer
 *					fixes
 *		Charles Hedrick :	TCP fixes
 *		Toomas Tamm	:	TCP window fixes
 *		Alan Cox	:	Small URG fix to rlogin ^C ack fight
 *		Charles Hedrick	:	Rewrote most of it to actually work
 *		Linus		:	Rewrote tcp_read() and URG handling
 *					completely
 *		Gerhard Koerting:	Fixed some missing timer handling
 *		Matthew Dillon  :	Reworked TCP machine states as per RFC
 *		Gerhard Koerting:	PC/TCP workarounds
 *		Adam Caldwell	:	Assorted timer/timing errors
 *		Matthew Dillon	:	Fixed another RST bug
 *		Alan Cox	:	Move to kernel side addressing changes.
 *		Alan Cox	:	Beginning work on TCP fastpathing
 *					(not yet usable)
 *		Arnt Gulbrandsen:	Turbocharged tcp_check() routine.
 *		Alan Cox	:	TCP fast path debugging
 *		Alan Cox	:	Window clamping
 *		Michael Riepe	:	Bug in tcp_check()
 *		Matt Dillon	:	More TCP improvements and RST bug fixes
 *		Matt Dillon	:	Yet more small nasties remove from the
 *					TCP code (Be very nice to this man if
 *					tcp finally works 100%) 8)
 *		Alan Cox	:	BSD accept semantics.
 *		Alan Cox	:	Reset on closedown bug.
 *	Peter De Schrijver	:	ENOTCONN check missing in tcp_sendto().
 *		Michael Pall	:	Handle poll() after URG properly in
 *					all cases.
 *		Michael Pall	:	Undo the last fix in tcp_read_urg()
 *					(multi URG PUSH broke rlogin).
 *		Michael Pall	:	Fix the multi URG PUSH problem in
 *					tcp_readable(), poll() after URG
 *					works now.
 *		Michael Pall	:	recv(...,MSG_OOB) never blocks in the
 *					BSD api.
 *		Alan Cox	:	Changed the semantics of sk->socket to
 *					fix a race and a signal problem with
 *					accept() and async I/O.
 *		Alan Cox	:	Relaxed the rules on tcp_sendto().
 *		Yury Shevchuk	:	Really fixed accept() blocking problem.
 *		Craig I. Hagan  :	Allow for BSD compatible TIME_WAIT for
 *					clients/servers which listen in on
 *					fixed ports.
 *		Alan Cox	:	Cleaned the above up and shrank it to
 *					a sensible code size.
 *		Alan Cox	:	Self connect lockup fix.
 *		Alan Cox	:	No connect to multicast.
 *		Ross Biro	:	Close unaccepted children on master
 *					socket close.
 *		Alan Cox	:	Reset tracing code.
 *		Alan Cox	:	Spurious resets on shutdown.
 *		Alan Cox	:	Giant 15 minute/60 second timer error
 *		Alan Cox	:	Small whoops in polling before an
 *					accept.
 *		Alan Cox	:	Kept the state trace facility since
 *					it's handy for debugging.
 *		Alan Cox	:	More reset handler fixes.
 *		Alan Cox	:	Started rewriting the code based on
 *					the RFC's for other useful protocol
 *					references see: Comer, KA9Q NOS, and
 *					for a reference on the difference
 *					between specifications and how BSD
 *					works see the 4.4lite source.
 *		A.N.Kuznetsov	:	Don't time wait on completion of tidy
 *					close.
 *		Linus Torvalds	:	Fin/Shutdown & copied_seq changes.
 *		Linus Torvalds	:	Fixed BSD port reuse to work first syn
 *		Alan Cox	:	Reimplemented timers as per the RFC
 *					and using multiple timers for sanity.
 *		Alan Cox	:	Small bug fixes, and a lot of new
 *					comments.
 *		Alan Cox	:	Fixed dual reader crash by locking
 *					the buffers (much like datagram.c)
 *		Alan Cox	:	Fixed stuck sockets in probe. A probe
 *					now gets fed up of retrying without
 *					(even a no space) answer.
 *		Alan Cox	:	Extracted closing code better
 *		Alan Cox	:	Fixed the closing state machine to
 *					resemble the RFC.
 *		Alan Cox	:	More 'per spec' fixes.
 *		Jorge Cwik	:	Even faster checksumming.
 *		Alan Cox	:	tcp_data() doesn't ack illegal PSH
 *					only frames. At least one pc tcp stack
 *					generates them.
 *		Alan Cox	:	Cache last socket.
 *		Alan Cox	:	Per route irtt.
 *		Matt Day	:	poll()->select() match BSD precisely on error
 *		Alan Cox	:	New buffers
 *		Marc Tamsky	:	Various sk->prot->retransmits and
 *					sk->retransmits misupdating fixed.
 *					Fixed tcp_write_timeout: stuck close,
 *					and TCP syn retries gets used now.
 *		Mark Yarvis	:	In tcp_read_wakeup(), don't send an
 *					ack if state is TCP_CLOSED.
 *		Alan Cox	:	Look up device on a retransmit - routes may
 *					change. Doesn't yet cope with MSS shrink right
 *					but it's a start!
 *		Marc Tamsky	:	Closing in closing fixes.
 *		Mike Shaver	:	RFC1122 verifications.
 *		Alan Cox	:	rcv_saddr errors.
 *		Alan Cox	:	Block double connect().
 *		Alan Cox	:	Small hooks for enSKIP.
 *		Alexey Kuznetsov:	Path MTU discovery.
 *		Alan Cox	:	Support soft errors.
 *		Alan Cox	:	Fix MTU discovery pathological case
 *					when the remote claims no mtu!
 *		Marc Tamsky	:	TCP_CLOSE fix.
 *		Colin (G3TNE)	:	Send a reset on syn ack replies in
 *					window but wrong (fixes NT lpd problems)
 *		Pedro Roque	:	Better TCP window handling, delayed ack.
 *		Joerg Reuter	:	No modification of locked buffers in
 *					tcp_do_retransmit()
 *		Eric Schenk	:	Changed receiver side silly window
 *					avoidance algorithm to BSD style
 *					algorithm. This doubles throughput
 *					against machines running Solaris,
 *					and seems to result in general
 *					improvement.
 *	Stefan Magdalinski	:	adjusted tcp_readable() to fix FIONREAD
 *	Willy Konynenberg	:	Transparent proxying support.
 *	Mike McLagan		:	Routing by source
 *		Keith Owens	:	Do proper merging with partial SKB's in
 *					tcp_do_sendmsg to avoid burstiness.
 *		Eric Schenk	:	Fix fast close down bug with
 *					shutdown() followed by close().
 *		Andi Kleen 	:	Make poll agree with SIGIO
 *	Salvatore Sanfilippo	:	Support SO_LINGER with linger == 1 and
 *					lingertime == 0 (RFC 793 ABORT Call)
 *	Hirokazu Takahashi	:	Use copy_from_user() instead of
 *					csum_and_copy_from_user() if possible.
 *
 *		This program is free software; you can redistribute it and/or
 *		modify it under the terms of the GNU General Public License
 *		as published by the Free Software Foundation; either version
 *		2 of the License, or(at your option) any later version.
 *
 * Description of States:
 *
 *	TCP_SYN_SENT		sent a connection request, waiting for ack
 *
 *	TCP_SYN_RECV		received a connection request, sent ack,
 *				waiting for final ack in three-way handshake.
 *
 *	TCP_ESTABLISHED		connection established
 *
 *	TCP_FIN_WAIT1		our side has shutdown, waiting to complete
 *				transmission of remaining buffered data
 *
 *	TCP_FIN_WAIT2		all buffered data sent, waiting for remote
 *				to shutdown
 *
 *	TCP_CLOSING		both sides have shutdown but we still have
 *				data we have to finish sending
 *
 *	TCP_TIME_WAIT		timeout to catch resent junk before entering
 *				closed, can only be entered from FIN_WAIT2
 *				or CLOSING.  Required because the other end
 *				may not have gotten our last ACK causing it
 *				to retransmit the data packet (which we ignore)
 *
 *	TCP_CLOSE_WAIT		remote side has shutdown and is waiting for
 *				us to finish writing our data and to shutdown
 *				(we have to close() to move on to LAST_ACK)
 *
 *	TCP_LAST_ACK		out side has shutdown after remote has
 *				shutdown.  There may still be data in our
 *				buffer that we have to finish sending
 *
 *	TCP_CLOSE		socket is finished
 */

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/fcntl.h>
#include <linux/poll.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/skbuff.h>
#include <linux/scatterlist.h>
#include <linux/splice.h>
#include <linux/net.h>
#include <linux/socket.h>
#include <linux/random.h>
#include <linux/bootmem.h>
#include <linux/highmem.h>
#include <linux/swap.h>
#include <linux/cache.h>
#include <linux/err.h>
#include <linux/crypto.h>
#include <linux/time.h>
#include <linux/slab.h>
#include <linux/uid_stat.h>

#include <net/icmp.h>
#include <net/tcp.h>
#include <net/xfrm.h>
#include <net/ip.h>
#include <net/ip6_route.h>
#include <net/ipv6.h>
#include <net/transp_v6.h>
#include <net/netdma.h>
#include <net/sock.h>

#include <asm/uaccess.h>
#include <asm/ioctls.h>

int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT;

struct percpu_counter tcp_orphan_count;
EXPORT_SYMBOL_GPL(tcp_orphan_count);

long sysctl_tcp_mem[3] __read_mostly;
int sysctl_tcp_wmem[3] __read_mostly;
int sysctl_tcp_rmem[3] __read_mostly;

EXPORT_SYMBOL(sysctl_tcp_mem);
EXPORT_SYMBOL(sysctl_tcp_rmem);
EXPORT_SYMBOL(sysctl_tcp_wmem);

atomic_long_t tcp_memory_allocated;	/* Current allocated memory. */
EXPORT_SYMBOL(tcp_memory_allocated);

/*
 * Current number of TCP sockets.
 */
struct percpu_counter tcp_sockets_allocated;
EXPORT_SYMBOL(tcp_sockets_allocated);

/*
 * TCP splice context
 */
struct tcp_splice_state {
	struct pipe_inode_info *pipe;
	size_t len;
	unsigned int flags;
};

/*
 * Pressure flag: try to collapse.
 * Technical note: it is used by multiple contexts non atomically.
 * All the __sk_mem_schedule() is of this nature: accounting
 * is strict, actions are advisory and have some latency.
 */
int tcp_memory_pressure __read_mostly;
EXPORT_SYMBOL(tcp_memory_pressure);

void tcp_enter_memory_pressure(struct sock *sk)
{
	if (!tcp_memory_pressure) {
		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMEMORYPRESSURES);
		tcp_memory_pressure = 1;
	}
}
EXPORT_SYMBOL(tcp_enter_memory_pressure);

/* Convert seconds to retransmits based on initial and max timeout */
static u8 secs_to_retrans(int seconds, int timeout, int rto_max)
{
	u8 res = 0;

	if (seconds > 0) {
		int period = timeout;

		res = 1;
		while (seconds > period && res < 255) {
			res++;
			timeout <<= 1;
			if (timeout > rto_max)
				timeout = rto_max;
			period += timeout;
		}
	}
	return res;
}

/* Convert retransmits to seconds based on initial and max timeout */
static int retrans_to_secs(u8 retrans, int timeout, int rto_max)
{
	int period = 0;

	if (retrans > 0) {
		period = timeout;
		while (--retrans) {
			timeout <<= 1;
			if (timeout > rto_max)
				timeout = rto_max;
			period += timeout;
		}
	}
	return period;
}

/*
 *	Wait for a TCP event.
 *
 *	Note that we don't need to lock the socket, as the upper poll layers
 *	take care of normal races (between the test and the event) and we don't
 *	go look at any of the socket buffers directly.
 */
unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
{
	unsigned int mask;
	struct sock *sk = sock->sk;
	struct tcp_sock *tp = tcp_sk(sk);

	sock_poll_wait(file, sk_sleep(sk), wait);
	if (sk->sk_state == TCP_LISTEN)
		return inet_csk_listen_poll(sk);

	/* Socket is not locked. We are protected from async events
	 * by poll logic and correct handling of state changes
	 * made by other threads is impossible in any case.
	 */

	mask = 0;

	/*
	 * POLLHUP is certainly not done right. But poll() doesn't
	 * have a notion of HUP in just one direction, and for a
	 * socket the read side is more interesting.
	 *
	 * Some poll() documentation says that POLLHUP is incompatible
	 * with the POLLOUT/POLLWR flags, so somebody should check this
	 * all. But careful, it tends to be safer to return too many
	 * bits than too few, and you can easily break real applications
	 * if you don't tell them that something has hung up!
	 *
	 * Check-me.
	 *
	 * Check number 1. POLLHUP is _UNMASKABLE_ event (see UNIX98 and
	 * our fs/select.c). It means that after we received EOF,
	 * poll always returns immediately, making impossible poll() on write()
	 * in state CLOSE_WAIT. One solution is evident --- to set POLLHUP
	 * if and only if shutdown has been made in both directions.
	 * Actually, it is interesting to look how Solaris and DUX
	 * solve this dilemma. I would prefer, if POLLHUP were maskable,
	 * then we could set it on SND_SHUTDOWN. BTW examples given
	 * in Stevens' books assume exactly this behaviour, it explains
	 * why POLLHUP is incompatible with POLLOUT.	--ANK
	 *
	 * NOTE. Check for TCP_CLOSE is added. The goal is to prevent
	 * blocking on fresh not-connected or disconnected socket. --ANK
	 */
	if (sk->sk_shutdown == SHUTDOWN_MASK || sk->sk_state == TCP_CLOSE)
		mask |= POLLHUP;
	if (sk->sk_shutdown & RCV_SHUTDOWN)
		mask |= POLLIN | POLLRDNORM | POLLRDHUP;

	/* Connected? */
	if ((1 << sk->sk_state) & ~(TCPF_SYN_SENT | TCPF_SYN_RECV)) {
		int target = sock_rcvlowat(sk, 0, INT_MAX);

		if (tp->urg_seq == tp->copied_seq &&
		    !sock_flag(sk, SOCK_URGINLINE) &&
		    tp->urg_data)
			target++;

		/* Potential race condition. If read of tp below will
		 * escape above sk->sk_state, we can be illegally awaken
		 * in SYN_* states. */
		if (tp->rcv_nxt - tp->copied_seq >= target)
			mask |= POLLIN | POLLRDNORM;

		if (!(sk->sk_shutdown & SEND_SHUTDOWN)) {
			if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk)) {
				mask |= POLLOUT | POLLWRNORM;
			} else {  /* send SIGIO later */
				set_bit(SOCK_ASYNC_NOSPACE,
					&sk->sk_socket->flags);
				set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);

				/* Race breaker. If space is freed after
				 * wspace test but before the flags are set,
				 * IO signal will be lost.
				 */
				if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk))
					mask |= POLLOUT | POLLWRNORM;
			}
		} else
			mask |= POLLOUT | POLLWRNORM;

		if (tp->urg_data & TCP_URG_VALID)
			mask |= POLLPRI;
	}
	/* This barrier is coupled with smp_wmb() in tcp_reset() */
	smp_rmb();
	if (sk->sk_err)
		mask |= POLLERR;

	return mask;
}
EXPORT_SYMBOL(tcp_poll);

int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
{
	struct tcp_sock *tp = tcp_sk(sk);
	int answ;

	switch (cmd) {
	case SIOCINQ:
		if (sk->sk_state == TCP_LISTEN)
			return -EINVAL;

		lock_sock(sk);
		if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))
			answ = 0;
		else if (sock_flag(sk, SOCK_URGINLINE) ||
			 !tp->urg_data ||
			 before(tp->urg_seq, tp->copied_seq) ||
			 !before(tp->urg_seq, tp->rcv_nxt)) {
			struct sk_buff *skb;

			answ = tp->rcv_nxt - tp->copied_seq;

			/* Subtract 1, if FIN is in queue. */
			skb = skb_peek_tail(&sk->sk_receive_queue);
			if (answ && skb)
				answ -= tcp_hdr(skb)->fin;
		} else
			answ = tp->urg_seq - tp->copied_seq;
		release_sock(sk);
		break;
	case SIOCATMARK:
		answ = tp->urg_data && tp->urg_seq == tp->copied_seq;
		break;
	case SIOCOUTQ:
		if (sk->sk_state == TCP_LISTEN)
			return -EINVAL;

		if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))
			answ = 0;
		else
			answ = tp->write_seq - tp->snd_una;
		break;
	case SIOCOUTQNSD:
		if (sk->sk_state == TCP_LISTEN)
			return -EINVAL;

		if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))
			answ = 0;
		else
			answ = tp->write_seq - tp->snd_nxt;
		break;
	default:
		return -ENOIOCTLCMD;
	}

	return put_user(answ, (int __user *)arg);
}
EXPORT_SYMBOL(tcp_ioctl);

static inline void tcp_mark_push(struct tcp_sock *tp, struct sk_buff *skb)
{
	TCP_SKB_CB(skb)->flags |= TCPHDR_PSH;
	tp->pushed_seq = tp->write_seq;
}

static inline int forced_push(struct tcp_sock *tp)
{
	return after(tp->write_seq, tp->pushed_seq + (tp->max_window >> 1));
}

static inline void skb_entail(struct sock *sk, struct sk_buff *skb)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);

	skb->csum    = 0;
	tcb->seq     = tcb->end_seq = tp->write_seq;
	tcb->flags   = TCPHDR_ACK;
	tcb->sacked  = 0;
	skb_header_release(skb);
	tcp_add_write_queue_tail(sk, skb);
	sk->sk_wmem_queued += skb->truesize;
	sk_mem_charge(sk, skb->truesize);
	if (tp->nonagle & TCP_NAGLE_PUSH)
		tp->nonagle &= ~TCP_NAGLE_PUSH;
}

static inline void tcp_mark_urg(struct tcp_sock *tp, int flags)
{
	if (flags & MSG_OOB)
		tp->snd_up = tp->write_seq;
}

static inline void tcp_push(struct sock *sk, int flags, int mss_now,
			    int nonagle)
{
	if (tcp_send_head(sk)) {
		struct tcp_sock *tp = tcp_sk(sk);

		if (!(flags & MSG_MORE) || forced_push(tp))
			tcp_mark_push(tp, tcp_write_queue_tail(sk));

		tcp_mark_urg(tp, flags);
		__tcp_push_pending_frames(sk, mss_now,
					  (flags & MSG_MORE) ? TCP_NAGLE_CORK : nonagle);
	}
}

static int tcp_splice_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb,
				unsigned int offset, size_t len)
{
	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);
	if (ret > 0)
		rd_desc->count -= ret;
	return ret;
}

static int __tcp_splice_read(struct sock *sk, struct tcp_splice_state *tss)
{
	/* Store TCP splice context information in read_descriptor_t. */
	read_descriptor_t rd_desc = {
		.arg.data = tss,
		.count	  = tss->len,
	};

	return tcp_read_sock(sk, &rd_desc, tcp_splice_data_recv);
}

/**
 *  tcp_splice_read - splice data from TCP socket to a pipe
 * @sock:	socket to splice from
 * @ppos:	position (not valid)
 * @pipe:	pipe to splice to
 * @len:	number of bytes to splice
 * @flags:	splice modifier flags
 *
 * Description:
 *    Will read pages from given socket and fill them into a pipe.
 *
 **/
ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos,
			struct pipe_inode_info *pipe, size_t len,
			unsigned int flags)
{
	struct sock *sk = sock->sk;
	struct tcp_splice_state tss = {
		.pipe = pipe,
		.len = len,
		.flags = flags,
	};
	long timeo;
	ssize_t spliced;
	int ret;

	sock_rps_record_flow(sk);
	/*
	 * We can't seek on a socket input
	 */
	if (unlikely(*ppos))
		return -ESPIPE;

	ret = spliced = 0;

	lock_sock(sk);

	timeo = sock_rcvtimeo(sk, sock->file->f_flags & O_NONBLOCK);
	while (tss.len) {
		ret = __tcp_splice_read(sk, &tss);
		if (ret < 0)
			break;
		else if (!ret) {
			if (spliced)
				break;
			if (sock_flag(sk, SOCK_DONE))
				break;
			if (sk->sk_err) {
				ret = sock_error(sk);
				break;
			}
			if (sk->sk_shutdown & RCV_SHUTDOWN)
				break;
			if (sk->sk_state == TCP_CLOSE) {
				/*
				 * This occurs when user tries to read
				 * from never connected socket.
				 */
				if (!sock_flag(sk, SOCK_DONE))
					ret = -ENOTCONN;
				break;
			}
			if (!timeo) {
				ret = -EAGAIN;
				break;
			}
			sk_wait_data(sk, &timeo);
			if (signal_pending(current)) {
				ret = sock_intr_errno(timeo);
				break;
			}
			continue;
		}
		tss.len -= ret;
		spliced += ret;

		if (!timeo)
			break;
		release_sock(sk);
		lock_sock(sk);

		if (sk->sk_err || sk->sk_state == TCP_CLOSE ||
		    (sk->sk_shutdown & RCV_SHUTDOWN) ||
		    signal_pending(current))
			break;
	}

	release_sock(sk);

	if (spliced)
		return spliced;

	return ret;
}
EXPORT_SYMBOL(tcp_splice_read);

struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp)
{
	struct sk_buff *skb;

	/* The TCP header must be at least 32-bit aligned.  */
	size = ALIGN(size, 4);

	skb = alloc_skb_fclone(size + sk->sk_prot->max_header, gfp);
	if (skb) {
		if (sk_wmem_schedule(sk, skb->truesize)) {
			/*
			 * Make sure that we have exactly size bytes
			 * available to the caller, no more, no less.
			 */
			skb_reserve(skb, skb_tailroom(skb) - size);
			return skb;
		}
		__kfree_skb(skb);
	} else {
		sk->sk_prot->enter_memory_pressure(sk);
		sk_stream_moderate_sndbuf(sk);
	}
	return NULL;
}

static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now,
				       int large_allowed)
{
	struct tcp_sock *tp = tcp_sk(sk);
	u32 xmit_size_goal, old_size_goal;

	xmit_size_goal = mss_now;

	if (large_allowed && sk_can_gso(sk)) {
		xmit_size_goal = ((sk->sk_gso_max_size - 1) -
				  inet_csk(sk)->icsk_af_ops->net_header_len -
				  inet_csk(sk)->icsk_ext_hdr_len -
				  tp->tcp_header_len);

		xmit_size_goal = tcp_bound_to_half_wnd(tp, xmit_size_goal);

		/* We try hard to avoid divides here */
		old_size_goal = tp->xmit_size_goal_segs * mss_now;

		if (likely(old_size_goal <= xmit_size_goal &&
			   old_size_goal + mss_now > xmit_size_goal)) {
			xmit_size_goal = old_size_goal;
		} else {
			tp->xmit_size_goal_segs = xmit_size_goal / mss_now;
			xmit_size_goal = tp->xmit_size_goal_segs * mss_now;
		}
	}

	return max(xmit_size_goal, mss_now);
}

static int tcp_send_mss(struct sock *sk, int *size_goal, int flags)
{
	int mss_now;

	mss_now = tcp_current_mss(sk);
	*size_goal = tcp_xmit_size_goal(sk, mss_now, !(flags & MSG_OOB));

	return mss_now;
}

static ssize_t do_tcp_sendpages(struct sock *sk, struct page **pages, int poffset,
			 size_t psize, int flags)
{
	struct tcp_sock *tp = tcp_sk(sk);
	int mss_now, size_goal;
	int err;
	ssize_t copied;
	long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);

	/* Wait for a connection to finish. */
	if ((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT))
		if ((err = sk_stream_wait_connect(sk, &timeo)) != 0)
			goto out_err;

	clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);

	mss_now = tcp_send_mss(sk, &size_goal, flags);
	copied = 0;

	err = -EPIPE;
	if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
		goto out_err;

	while (psize > 0) {
		struct sk_buff *skb = tcp_write_queue_tail(sk);
		struct page *page = pages[poffset / PAGE_SIZE];
		int copy, i, can_coalesce;
		int offset = poffset % PAGE_SIZE;
		int size = min_t(size_t, psize, PAGE_SIZE - offset);

		if (!tcp_send_head(sk) || (copy = size_goal - skb->len) <= 0) {
new_segment:
			if (!sk_stream_memory_free(sk))
				goto wait_for_sndbuf;

			skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation);
			if (!skb)
				goto wait_for_memory;

			skb_entail(sk, skb);
			copy = size_goal;
		}

		if (copy > size)
			copy = size;

		i = skb_shinfo(skb)->nr_frags;
		can_coalesce = skb_can_coalesce(skb, i, page, offset);
		if (!can_coalesce && i >= MAX_SKB_FRAGS) {
			tcp_mark_push(tp, skb);
			goto new_segment;
		}
		if (!sk_wmem_schedule(sk, copy))
			goto wait_for_memory;

		if (can_coalesce) {
			skb_shinfo(skb)->frags[i - 1].size += copy;
		} else {
			get_page(page);
			skb_fill_page_desc(skb, i, page, offset, copy);
		}

		skb->len += copy;
		skb->data_len += copy;
		skb->truesize += copy;
		sk->sk_wmem_queued += copy;
		sk_mem_charge(sk, copy);
		skb->ip_summed = CHECKSUM_PARTIAL;
		tp->write_seq += copy;
		TCP_SKB_CB(skb)->end_seq += copy;
		skb_shinfo(skb)->gso_segs = 0;

		if (!copied)
			TCP_SKB_CB(skb)->flags &= ~TCPHDR_PSH;

		copied += copy;
		poffset += copy;
		if (!(psize -= copy))
			goto out;

		if (skb->len < size_goal || (flags & MSG_OOB))
			continue;

		if (forced_push(tp)) {
			tcp_mark_push(tp, skb);
			__tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_PUSH);
		} else if (skb == tcp_send_head(sk))
			tcp_push_one(sk, mss_now);
		continue;

wait_for_sndbuf:
		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
wait_for_memory:
		tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH);

		if ((err = sk_stream_wait_memory(sk, &timeo)) != 0)
			goto do_error;

		mss_now = tcp_send_mss(sk, &size_goal, flags);
	}

out:
	if (copied && !(flags & MSG_SENDPAGE_NOTLAST))
		tcp_push(sk, flags, mss_now, tp->nonagle);
	return copied;

do_error:
	if (copied)
		goto out;
out_err:
	return sk_stream_error(sk, flags, err);
}

int tcp_sendpage(struct sock *sk, struct page *page, int offset,
		 size_t size, int flags)
{
	ssize_t res;

	if (!(sk->sk_route_caps & NETIF_F_SG) ||
	    !(sk->sk_route_caps & NETIF_F_ALL_CSUM))
		return sock_no_sendpage(sk->sk_socket, page, offset, size,
					flags);

	lock_sock(sk);
	res = do_tcp_sendpages(sk, &page, offset, size, flags);
	release_sock(sk);
	return res;
}
EXPORT_SYMBOL(tcp_sendpage);

#define TCP_PAGE(sk)	(sk->sk_sndmsg_page)
#define TCP_OFF(sk)	(sk->sk_sndmsg_off)

static inline int select_size(struct sock *sk, int sg)
{
	struct tcp_sock *tp = tcp_sk(sk);
	int tmp = tp->mss_cache;

	if (sg) {
		if (sk_can_gso(sk))
			tmp = 0;
		else {
			int pgbreak = SKB_MAX_HEAD(MAX_TCP_HEADER);

			if (tmp >= pgbreak &&
			    tmp <= pgbreak + (MAX_SKB_FRAGS - 1) * PAGE_SIZE)
				tmp = pgbreak;
		}
	}

	return tmp;
}

int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
		size_t size)
{
	struct iovec *iov;
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *skb;
	int iovlen, flags;
	int mss_now, size_goal;
	int sg, err, copied;
	long timeo;

	lock_sock(sk);

	flags = msg->msg_flags;
	timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);

	/* Wait for a connection to finish. */
	if ((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT))
		if ((err = sk_stream_wait_connect(sk, &timeo)) != 0)
			goto out_err;

	/* This should be in poll */
	clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);

	mss_now = tcp_send_mss(sk, &size_goal, flags);

	/* Ok commence sending. */
	iovlen = msg->msg_iovlen;
	iov = msg->msg_iov;
	copied = 0;

	err = -EPIPE;
	if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
		goto out_err;

	sg = sk->sk_route_caps & NETIF_F_SG;

	while (--iovlen >= 0) {
		size_t seglen = iov->iov_len;
		unsigned char __user *from = iov->iov_base;

		iov++;

		while (seglen > 0) {
			int copy = 0;
			int max = size_goal;

			skb = tcp_write_queue_tail(sk);
			if (tcp_send_head(sk)) {
				if (skb->ip_summed == CHECKSUM_NONE)
					max = mss_now;
				copy = max - skb->len;
			}

			if (copy <= 0) {
new_segment:
				/* Allocate new segment. If the interface is SG,
				 * allocate skb fitting to single page.
				 */
				if (!sk_stream_memory_free(sk))
					goto wait_for_sndbuf;

				skb = sk_stream_alloc_skb(sk,
							  select_size(sk, sg),
							  sk->sk_allocation);
				if (!skb)
					goto wait_for_memory;

				/*
				 * Check whether we can use HW checksum.
				 */
				if (sk->sk_route_caps & NETIF_F_ALL_CSUM)
					skb->ip_summed = CHECKSUM_PARTIAL;

				skb_entail(sk, skb);
				copy = size_goal;
				max = size_goal;
			}

			/* Try to append data to the end of skb. */
			if (copy > seglen)
				copy = seglen;

			/* Where to copy to? */
			if (skb_tailroom(skb) > 0) {
				/* We have some space in skb head. Superb! */
				if (copy > skb_tailroom(skb))
					copy = skb_tailroom(skb);
				err = skb_add_data_nocache(sk, skb, from, copy);
				if (err)
					goto do_fault;
			} else {
				int merge = 0;
				int i = skb_shinfo(skb)->nr_frags;
				struct page *page = TCP_PAGE(sk);
				int off = TCP_OFF(sk);

				if (skb_can_coalesce(skb, i, page, off) &&
				    off != PAGE_SIZE) {
					/* We can extend the last page
					 * fragment. */
					merge = 1;
				} else if (i == MAX_SKB_FRAGS || !sg) {
					/* Need to add new fragment and cannot
					 * do this because interface is non-SG,
					 * or because all the page slots are
					 * busy. */
					tcp_mark_push(tp, skb);
					goto new_segment;
				} else if (page) {
					if (off == PAGE_SIZE) {
						put_page(page);
						TCP_PAGE(sk) = page = NULL;
						off = 0;
					}
				} else
					off = 0;

				if (copy > PAGE_SIZE - off)
					copy = PAGE_SIZE - off;

				if (!sk_wmem_schedule(sk, copy))
					goto wait_for_memory;

				if (!page) {
					/* Allocate new cache page. */
					if (!(page = sk_stream_alloc_page(sk)))
						goto wait_for_memory;
				}

				/* Time to copy data. We are close to
				 * the end! */
				err = skb_copy_to_page_nocache(sk, from, skb,
							       page, off, copy);
				if (err) {
					/* If this page was new, give it to the
					 * socket so it does not get leaked.
					 */
					if (!TCP_PAGE(sk)) {
						TCP_PAGE(sk) = page;
						TCP_OFF(sk) = 0;
					}
					goto do_error;
				}

				/* Update the skb. */
				if (merge) {
					skb_shinfo(skb)->frags[i - 1].size +=
									copy;
				} else {
					skb_fill_page_desc(skb, i, page, off, copy);
					if (TCP_PAGE(sk)) {
						get_page(page);
					} else if (off + copy < PAGE_SIZE) {
						get_page(page);
						TCP_PAGE(sk) = page;
					}
				}

				TCP_OFF(sk) = off + copy;
			}

			if (!copied)
				TCP_SKB_CB(skb)->flags &= ~TCPHDR_PSH;

			tp->write_seq += copy;
			TCP_SKB_CB(skb)->end_seq += copy;
			skb_shinfo(skb)->gso_segs = 0;

			from += copy;
			copied += copy;
			if ((seglen -= copy) == 0 && iovlen == 0)
				goto out;

			if (skb->len < max || (flags & MSG_OOB))
				continue;

			if (forced_push(tp)) {
				tcp_mark_push(tp, skb);
				__tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_PUSH);
			} else if (skb == tcp_send_head(sk))
				tcp_push_one(sk, mss_now);
			continue;

wait_for_sndbuf:
			set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
wait_for_memory:
			if (copied)
				tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH);

			if ((err = sk_stream_wait_memory(sk, &timeo)) != 0)
				goto do_error;

			mss_now = tcp_send_mss(sk, &size_goal, flags);
		}
	}

out:
	if (copied)
		tcp_push(sk, flags, mss_now, tp->nonagle);
	release_sock(sk);

	if (copied > 0)
		uid_stat_tcp_snd(current_uid(), copied);
	return copied;

do_fault:
	if (!skb->len) {
		tcp_unlink_write_queue(skb, sk);
		/* It is the one place in all of TCP, except connection
		 * reset, where we can be unlinking the send_head.
		 */
		tcp_check_send_head(sk, skb);
		sk_wmem_free_skb(sk, skb);
	}

do_error:
	if (copied)
		goto out;
out_err:
	err = sk_stream_error(sk, flags, err);
	release_sock(sk);
	return err;
}
EXPORT_SYMBOL(tcp_sendmsg);

/*
 *	Handle reading urgent data. BSD has very simple semantics for
 *	this, no blocking and very strange errors 8)
 */

static int tcp_recv_urg(struct sock *sk, struct msghdr *msg, int len, int flags)
{
	struct tcp_sock *tp = tcp_sk(sk);

	/* No URG data to read. */
	if (sock_flag(sk, SOCK_URGINLINE) || !tp->urg_data ||
	    tp->urg_data == TCP_URG_READ)
		return -EINVAL;	/* Yes this is right ! */

	if (sk->sk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DONE))
		return -ENOTCONN;

	if (tp->urg_data & TCP_URG_VALID) {
		int err = 0;
		char c = tp->urg_data;

		if (!(flags & MSG_PEEK))
			tp->urg_data = TCP_URG_READ;

		/* Read urgent data. */
		msg->msg_flags |= MSG_OOB;

		if (len > 0) {
			if (!(flags & MSG_TRUNC))
				err = memcpy_toiovec(msg->msg_iov, &c, 1);
			len = 1;
		} else
			msg->msg_flags |= MSG_TRUNC;

		return err ? -EFAULT : len;
	}

	if (sk->sk_state == TCP_CLOSE || (sk->sk_shutdown & RCV_SHUTDOWN))
		return 0;

	/* Fixed the recv(..., MSG_OOB) behaviour.  BSD docs and
	 * the available implementations agree in this case:
	 * this call should never block, independent of the
	 * blocking state of the socket.
	 * Mike <pall@rz.uni-karlsruhe.de>
	 */
	return -EAGAIN;
}

/* Clean up the receive buffer for full frames taken by the user,
 * then send an ACK if necessary.  COPIED is the number of bytes
 * tcp_recvmsg has given to the user so far, it speeds up the
 * calculation of whether or not we must ACK for the sake of
 * a window update.
 */
void tcp_cleanup_rbuf(struct sock *sk, int copied)
{
	struct tcp_sock *tp = tcp_sk(sk);
	int time_to_ack = 0;

#if TCP_DEBUG
	struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);

	WARN(skb && !before(tp->copied_seq, TCP_SKB_CB(skb)->end_seq),
	     "cleanup rbuf bug: copied %X seq %X rcvnxt %X\n",
	     tp->copied_seq, TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt);
#endif

	if (inet_csk_ack_scheduled(sk)) {
		const struct inet_connection_sock *icsk = inet_csk(sk);
		   /* Delayed ACKs frequently hit locked sockets during bulk
		    * receive. */
		if (icsk->icsk_ack.blocked ||
		    /* Once-per-two-segments ACK was not sent by tcp_input.c */
		    tp->rcv_nxt - tp->rcv_wup > icsk->icsk_ack.rcv_mss ||
		    /*
		     * If this read emptied read buffer, we send ACK, if
		     * connection is not bidirectional, user drained
		     * receive buffer and there was a small segment
		     * in queue.
		     */
		    (copied > 0 &&
		     ((icsk->icsk_ack.pending & ICSK_ACK_PUSHED2) ||
		      ((icsk->icsk_ack.pending & ICSK_ACK_PUSHED) &&
		       !icsk->icsk_ack.pingpong)) &&
		      !atomic_read(&sk->sk_rmem_alloc)))
			time_to_ack = 1;
	}

	/* We send an ACK if we can now advertise a non-zero window
	 * which has been raised "significantly".
	 *
	 * Even if window raised up to infinity, do not send window open ACK
	 * in states, where we will not receive more. It is useless.
	 */
	if (copied > 0 && !time_to_ack && !(sk->sk_shutdown & RCV_SHUTDOWN)) {
		__u32 rcv_window_now = tcp_receive_window(tp);

		/* Optimize, __tcp_select_window() is not cheap. */
		if (2*rcv_window_now <= tp->window_clamp) {
			__u32 new_window = __tcp_select_window(sk);

			/* Send ACK now, if this read freed lots of space
			 * in our buffer. Certainly, new_window is new window.
			 * We can advertise it now, if it is not less than current one.
			 * "Lots" means "at least twice" here.
			 */
			if (new_window && new_window >= 2 * rcv_window_now)
				time_to_ack = 1;
		}
	}
	if (time_to_ack)
		tcp_send_ack(sk);
}

static void tcp_prequeue_process(struct sock *sk)
{
	struct sk_buff *skb;
	struct tcp_sock *tp = tcp_sk(sk);

	NET_INC_STATS_USER(sock_net(sk), LINUX_MIB_TCPPREQUEUED);

	/* RX process wants to run with disabled BHs, though it is not
	 * necessary */
	local_bh_disable();
	while ((skb = __skb_dequeue(&tp->ucopy.prequeue)) != NULL)
		sk_backlog_rcv(sk, skb);
	local_bh_enable();

	/* Clear memory counter. */
	tp->ucopy.memory = 0;
}

#ifdef CONFIG_NET_DMA
static void tcp_service_net_dma(struct sock *sk, bool wait)
{
	dma_cookie_t done, used;
	dma_cookie_t last_issued;
	struct tcp_sock *tp = tcp_sk(sk);

	if (!tp->ucopy.dma_chan)
		return;

	last_issued = tp->ucopy.dma_cookie;
	dma_async_memcpy_issue_pending(tp->ucopy.dma_chan);

	do {
		if (dma_async_memcpy_complete(tp->ucopy.dma_chan,
					      last_issued, &done,
					      &used) == DMA_SUCCESS) {
			/* Safe to free early-copied skbs now */
			__skb_queue_purge(&sk->sk_async_wait_queue);
			break;
		} else {
			struct sk_buff *skb;
			while ((skb = skb_peek(&sk->sk_async_wait_queue)) &&
			       (dma_async_is_complete(skb->dma_cookie, done,
						      used) == DMA_SUCCESS)) {
				__skb_dequeue(&sk->sk_async_wait_queue);
				kfree_skb(skb);
			}
		}
	} while (wait);
}
#endif

static inline struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off)
{
	struct sk_buff *skb;
	u32 offset;

	skb_queue_walk(&sk->sk_receive_queue, skb) {
		offset = seq - TCP_SKB_CB(skb)->seq;
		if (tcp_hdr(skb)->syn)
			offset--;
		if (offset < skb->len || tcp_hdr(skb)->fin) {
			*off = offset;
			return skb;
		}
	}
	return NULL;
}

/*
 * This routine provides an alternative to tcp_recvmsg() for routines
 * that would like to handle copying from skbuffs directly in 'sendfile'
 * fashion.
 * Note:
 *	- It is assumed that the socket was locked by the caller.
 *	- The routine does not block.
 *	- At present, there is no support for reading OOB data
 *	  or for 'peeking' the socket using this routine
 *	  (although both would be easy to implement).
 */
int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
		  sk_read_actor_t recv_actor)
{
	struct sk_buff *skb;
	struct tcp_sock *tp = tcp_sk(sk);
	u32 seq = tp->copied_seq;
	u32 offset;
	int copied = 0;

	if (sk->sk_state == TCP_LISTEN)
		return -ENOTCONN;
	while ((skb = tcp_recv_skb(sk, seq, &offset)) != NULL) {
		if (offset < skb->len) {
			int used;
			size_t len;

			len = skb->len - offset;
			/* Stop reading if we hit a patch of urgent data */
			if (tp->urg_data) {
				u32 urg_offset = tp->urg_seq - seq;
				if (urg_offset < len)
					len = urg_offset;
				if (!len)
					break;
			}
			used = recv_actor(desc, skb, offset, len);
			if (used < 0) {
				if (!copied)
					copied = used;
				break;
			} else if (used <= len) {
				seq += used;
				copied += used;
				offset += used;
			}
			/*
			 * If recv_actor drops the lock (e.g. TCP splice
			 * receive) the skb pointer might be invalid when
			 * getting here: tcp_collapse might have deleted it
			 * while aggregating skbs from the socket queue.
			 */
			skb = tcp_recv_skb(sk, seq-1, &offset);
			if (!skb || (offset+1 != skb->len))
				break;
		}
		if (tcp_hdr(skb)->fin) {
			sk_eat_skb(sk, skb, 0);
			++seq;
			break;
		}
		sk_eat_skb(sk, skb, 0);
		if (!desc->count)
			break;
		tp->copied_seq = seq;
	}
	tp->copied_seq = seq;

	tcp_rcv_space_adjust(sk);

	/* Clean up data we have read: This will do ACK frames. */
	if (copied > 0) {
		tcp_cleanup_rbuf(sk, copied);
		uid_stat_tcp_rcv(current_uid(), copied);
	}

	return copied;
}
EXPORT_SYMBOL(tcp_read_sock);

/*
 *	This routine copies from a sock struct into the user buffer.
 *
 *	Technical note: in 2.3 we work on _locked_ socket, so that
 *	tricks with *seq access order and skb->users are not required.
 *	Probably, code can be easily improved even more.
 */

int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
		size_t len, int nonblock, int flags, int *addr_len)
{
	struct tcp_sock *tp = tcp_sk(sk);
	int copied = 0;
	u32 peek_seq;
	u32 *seq;
	unsigned long used;
	int err;
	int target;		/* Read at least this many bytes */
	long timeo;
	struct task_struct *user_recv = NULL;
	int copied_early = 0;
	struct sk_buff *skb;
	u32 urg_hole = 0;

	lock_sock(sk);

	err = -ENOTCONN;
	if (sk->sk_state == TCP_LISTEN)
		goto out;

	timeo = sock_rcvtimeo(sk, nonblock);

	/* Urgent data needs to be handled specially. */
	if (flags & MSG_OOB)
		goto recv_urg;

	seq = &tp->copied_seq;
	if (flags & MSG_PEEK) {
		peek_seq = tp->copied_seq;
		seq = &peek_seq;
	}

	target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);

#ifdef CONFIG_NET_DMA
	tp->ucopy.dma_chan = NULL;
	preempt_disable();
	skb = skb_peek_tail(&sk->sk_receive_queue);
	{
		int available = 0;

		if (skb)
			available = TCP_SKB_CB(skb)->seq + skb->len - (*seq);
		if ((available < target) &&
		    (len > sysctl_tcp_dma_copybreak) && !(flags & MSG_PEEK) &&
		    !sysctl_tcp_low_latency &&
		    dma_find_channel(DMA_MEMCPY)) {
			preempt_enable_no_resched();
			tp->ucopy.pinned_list =
					dma_pin_iovec_pages(msg->msg_iov, len);
		} else {
			preempt_enable_no_resched();
		}
	}
#endif

	do {
		u32 offset;

		/* Are we at urgent data? Stop if we have read anything or have SIGURG pending. */
		if (tp->urg_data && tp->urg_seq == *seq) {
			if (copied)
				break;
			if (signal_pending(current)) {
				copied = timeo ? sock_intr_errno(timeo) : -EAGAIN;
				break;
			}
		}

		/* Next get a buffer. */

		skb_queue_walk(&sk->sk_receive_queue, skb) {
			/* Now that we have two receive queues this
			 * shouldn't happen.
			 */
			if (WARN(before(*seq, TCP_SKB_CB(skb)->seq),
				 "recvmsg bug: copied %X seq %X rcvnxt %X fl %X\n",
				 *seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt,
				 flags))
				break;

			offset = *seq - TCP_SKB_CB(skb)->seq;
			if (tcp_hdr(skb)->syn)
				offset--;
			if (offset < skb->len)
				goto found_ok_skb;
			if (tcp_hdr(skb)->fin)
				goto found_fin_ok;
			WARN(!(flags & MSG_PEEK),
			     "recvmsg bug 2: copied %X seq %X rcvnxt %X fl %X\n",
			     *seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt, flags);
		}

		/* Well, if we have backlog, try to process it now yet. */

		if (copied >= target && !sk->sk_backlog.tail)
			break;

		if (copied) {
			if (sk->sk_err ||
			    sk->sk_state == TCP_CLOSE ||
			    (sk->sk_shutdown & RCV_SHUTDOWN) ||
			    !timeo ||
			    signal_pending(current))
				break;
		} else {
			if (sock_flag(sk, SOCK_DONE))
				break;

			if (sk->sk_err) {
				copied = sock_error(sk);
				break;
			}

			if (sk->sk_shutdown & RCV_SHUTDOWN)
				break;

			if (sk->sk_state == TCP_CLOSE) {
				if (!sock_flag(sk, SOCK_DONE)) {
					/* This occurs when user tries to read
					 * from never connected socket.
					 */
					copied = -ENOTCONN;
					break;
				}
				break;
			}

			if (!timeo) {
				copied = -EAGAIN;
				break;
			}

			if (signal_pending(current)) {
				copied = sock_intr_errno(timeo);
				break;
			}
		}

		tcp_cleanup_rbuf(sk, copied);

		if (!sysctl_tcp_low_latency && tp->ucopy.task == user_recv) {
			/* Install new reader */
			if (!user_recv && !(flags & (MSG_TRUNC | MSG_PEEK))) {
				user_recv = current;
				tp->ucopy.task = user_recv;
				tp->ucopy.iov = msg->msg_iov;
			}

			tp->ucopy.len = len;

			WARN_ON(tp->copied_seq != tp->rcv_nxt &&
				!(flags & (MSG_PEEK | MSG_TRUNC)));

			/* Ugly... If prequeue is not empty, we have to
			 * process it before releasing socket, otherwise
			 * order will be broken at second iteration.
			 * More elegant solution is required!!!
			 *
			 * Look: we have the following (pseudo)queues:
			 *
			 * 1. packets in flight
			 * 2. backlog
			 * 3. prequeue
			 * 4. receive_queue
			 *
			 * Each queue can be processed only if the next ones
			 * are empty. At this point we have empty receive_queue.
			 * But prequeue _can_ be not empty after 2nd iteration,
			 * when we jumped to start of loop because backlog
			 * processing added something to receive_queue.
			 * We cannot release_sock(), because backlog contains
			 * packets arrived _after_ prequeued ones.
			 *
			 * Shortly, algorithm is clear --- to process all
			 * the queues in order. We could make it more directly,
			 * requeueing packets from backlog to prequeue, if
			 * is not empty. It is more elegant, but eats cycles,
			 * unfortunately.
			 */
			if (!skb_queue_empty(&tp->ucopy.prequeue))
				goto do_prequeue;

			/* __ Set realtime policy in scheduler __ */
		}

#ifdef CONFIG_NET_DMA
		if (tp->ucopy.dma_chan)
			dma_async_memcpy_issue_pending(tp->ucopy.dma_chan);
#endif
		if (copied >= target) {
			/* Do not sleep, just process backlog. */
			release_sock(sk);
			lock_sock(sk);
		} else
			sk_wait_data(sk, &timeo);

#ifdef CONFIG_NET_DMA
		tcp_service_net_dma(sk, false);  /* Don't block */
		tp->ucopy.wakeup = 0;
#endif

		if (user_recv) {
			int chunk;

			/* __ Restore normal policy in scheduler __ */

			if ((chunk = len - tp->ucopy.len) != 0) {
				NET_ADD_STATS_USER(sock_net(sk), LINUX_MIB_TCPDIRECTCOPYFROMBACKLOG, chunk);
				len -= chunk;
				copied += chunk;
			}

			if (tp->rcv_nxt == tp->copied_seq &&
			    !skb_queue_empty(&tp->ucopy.prequeue)) {
do_prequeue:
				tcp_prequeue_process(sk);

				if ((chunk = len - tp->ucopy.len) != 0) {
					NET_ADD_STATS_USER(sock_net(sk), LINUX_MIB_TCPDIRECTCOPYFROMPREQUEUE, chunk);
					len -= chunk;
					copied += chunk;
				}
			}
		}
		if ((flags & MSG_PEEK) &&
		    (peek_seq - copied - urg_hole != tp->copied_seq)) {
			if (net_ratelimit())
				printk(KERN_DEBUG "TCP(%s:%d): Application bug, race in MSG_PEEK.\n",
				       current->comm, task_pid_nr(current));
			peek_seq = tp->copied_seq;
		}
		continue;

	found_ok_skb:
		/* Ok so how much can we use? */
		used = skb->len - offset;
		if (len < used)
			used = len;

		/* Do we have urgent data here? */
		if (tp->urg_data) {
			u32 urg_offset = tp->urg_seq - *seq;
			if (urg_offset < used) {
				if (!urg_offset) {
					if (!sock_flag(sk, SOCK_URGINLINE)) {
						++*seq;
						urg_hole++;
						offset++;
						used--;
						if (!used)
							goto skip_copy;
					}
				} else
					used = urg_offset;
			}
		}

		if (!(flags & MSG_TRUNC)) {
#ifdef CONFIG_NET_DMA
			if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
				tp->ucopy.dma_chan = dma_find_channel(DMA_MEMCPY);

			if (tp->ucopy.dma_chan) {
				tp->ucopy.dma_cookie = dma_skb_copy_datagram_iovec(
					tp->ucopy.dma_chan, skb, offset,
					msg->msg_iov, used,
					tp->ucopy.pinned_list);

				if (tp->ucopy.dma_cookie < 0) {

					printk(KERN_ALERT "dma_cookie < 0\n");

					/* Exception. Bailout! */
					if (!copied)
						copied = -EFAULT;
					break;
				}

				dma_async_memcpy_issue_pending(tp->ucopy.dma_chan);

				if ((offset + used) == skb->len)
					copied_early = 1;

			} else
#endif
			{
				err = skb_copy_datagram_iovec(skb, offset,
						msg->msg_iov, used);
				if (err) {
					/* Exception. Bailout! */
					if (!copied)
						copied = -EFAULT;
					break;
				}
			}
		}

		*seq += used;
		copied += used;
		len -= used;

		tcp_rcv_space_adjust(sk);

skip_copy:
		if (tp->urg_data && after(tp->copied_seq, tp->urg_seq)) {
			tp->urg_data = 0;
			tcp_fast_path_check(sk);
		}
		if (used + offset < skb->len)
			continue;

		if (tcp_hdr(skb)->fin)
			goto found_fin_ok;
		if (!(flags & MSG_PEEK)) {
			sk_eat_skb(sk, skb, copied_early);
			copied_early = 0;
		}
		continue;

	found_fin_ok:
		/* Process the FIN. */
		++*seq;
		if (!(flags & MSG_PEEK)) {
			sk_eat_skb(sk, skb, copied_early);
			copied_early = 0;
		}
		break;
	} while (len > 0);

	if (user_recv) {
		if (!skb_queue_empty(&tp->ucopy.prequeue)) {
			int chunk;

			tp->ucopy.len = copied > 0 ? len : 0;

			tcp_prequeue_process(sk);

			if (copied > 0 && (chunk = len - tp->ucopy.len) != 0) {
				NET_ADD_STATS_USER(sock_net(sk), LINUX_MIB_TCPDIRECTCOPYFROMPREQUEUE, chunk);
				len -= chunk;
				copied += chunk;
			}
		}

		tp->ucopy.task = NULL;
		tp->ucopy.len = 0;
	}

#ifdef CONFIG_NET_DMA
	tcp_service_net_dma(sk, true);  /* Wait for queue to drain */
	tp->ucopy.dma_chan = NULL;

	if (tp->ucopy.pinned_list) {
		dma_unpin_iovec_pages(tp->ucopy.pinned_list);
		tp->ucopy.pinned_list = NULL;
	}
#endif

	/* According to UNIX98, msg_name/msg_namelen are ignored
	 * on connected socket. I was just happy when found this 8) --ANK
	 */

	/* Clean up data we have read: This will do ACK frames. */
	tcp_cleanup_rbuf(sk, copied);

	release_sock(sk);

	if (copied > 0)
		uid_stat_tcp_rcv(current_uid(), copied);
	return copied;

out:
	release_sock(sk);
	return err;

recv_urg:
	err = tcp_recv_urg(sk, msg, len, flags);
	if (err > 0)
		uid_stat_tcp_rcv(current_uid(), err);
	goto out;
}
EXPORT_SYMBOL(tcp_recvmsg);

void tcp_set_state(struct sock *sk, int state)
{
	int oldstate = sk->sk_state;

	switch (state) {
	case TCP_ESTABLISHED:
		if (oldstate != TCP_ESTABLISHED)
			TCP_INC_STATS(sock_net(sk), TCP_MIB_CURRESTAB);
		break;

	case TCP_CLOSE:
		if (oldstate == TCP_CLOSE_WAIT || oldstate == TCP_ESTABLISHED)
			TCP_INC_STATS(sock_net(sk), TCP_MIB_ESTABRESETS);

		sk->sk_prot->unhash(sk);
		if (inet_csk(sk)->icsk_bind_hash &&
		    !(sk->sk_userlocks & SOCK_BINDPORT_LOCK))
			inet_put_port(sk);
		/* fall through */
	default:
		if (oldstate == TCP_ESTABLISHED)
			TCP_DEC_STATS(sock_net(sk), TCP_MIB_CURRESTAB);
	}

	/* Change state AFTER socket is unhashed to avoid closed
	 * socket sitting in hash tables.
	 */
	sk->sk_state = state;

#ifdef STATE_TRACE
	SOCK_DEBUG(sk, "TCP sk=%p, State %s -> %s\n", sk, statename[oldstate], statename[state]);
#endif
}
EXPORT_SYMBOL_GPL(tcp_set_state);

/*
 *	State processing on a close. This implements the state shift for
 *	sending our FIN frame. Note that we only send a FIN for some
 *	states. A shutdown() may have already sent the FIN, or we may be
 *	closed.
 */

static const unsigned char new_state[16] = {
  /* current state:        new state:      action:	*/
  /* (Invalid)		*/ TCP_CLOSE,
  /* TCP_ESTABLISHED	*/ TCP_FIN_WAIT1 | TCP_ACTION_FIN,
  /* TCP_SYN_SENT	*/ TCP_CLOSE,
  /* TCP_SYN_RECV	*/ TCP_FIN_WAIT1 | TCP_ACTION_FIN,
  /* TCP_FIN_WAIT1	*/ TCP_FIN_WAIT1,
  /* TCP_FIN_WAIT2	*/ TCP_FIN_WAIT2,
  /* TCP_TIME_WAIT	*/ TCP_CLOSE,
  /* TCP_CLOSE		*/ TCP_CLOSE,
  /* TCP_CLOSE_WAIT	*/ TCP_LAST_ACK  | TCP_ACTION_FIN,
  /* TCP_LAST_ACK	*/ TCP_LAST_ACK,
  /* TCP_LISTEN		*/ TCP_CLOSE,
  /* TCP_CLOSING	*/ TCP_CLOSING,
};

static int tcp_close_state(struct sock *sk)
{
	int next = (int)new_state[sk->sk_state];
	int ns = next & TCP_STATE_MASK;

	tcp_set_state(sk, ns);

	return next & TCP_ACTION_FIN;
}

/*
 *	Shutdown the sending side of a connection. Much like close except
 *	that we don't receive shut down or sock_set_flag(sk, SOCK_DEAD).
 */

void tcp_shutdown(struct sock *sk, int how)
{
	/*	We need to grab some memory, and put together a FIN,
	 *	and then put it into the queue to be sent.
	 *		Tim MacKenzie(tym@dibbler.cs.monash.edu.au) 4 Dec '92.
	 */
	if (!(how & SEND_SHUTDOWN))
		return…