tcp.c

linux 内核源代码

/*
 * 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).
 *
 * Version:	$Id: tcp.c,v 1.216 2002/02/01 22:01:04 davem Exp $
 *
 * Authors:	Ross Biro
 *		Fred N. van Kempen, <[e-mail]>
 *		Mark Evans, <[e-mail]>
 *		Corey Minyard <wf-rch![e-mail]>
 *		Florian La Roche, <[e-mail]>
 *		Charles Hedrick, <[e-mail]>
 *		Linus Torvalds, <[e-mail]>
 *		Alan Cox, <[e-mail]>
 *		Matthew Dillon, <[e-mail]>
 *		Arnt Gulbrandsen, <[e-mail]>
 *		Jorge Cwik, <[e-mail]>
 *
 * 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/random.h>
#include <linux/bootmem.h>
#include <linux/cache.h>
#include <linux/err.h>
#include <linux/crypto.h>

#include <net/icmp.h>
#include <net/tcp.h>
#include <net/xfrm.h>
#include <net/ip.h>
#include <net/netdma.h>

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

int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT;

DEFINE_SNMP_STAT(struct tcp_mib, tcp_statistics) __read_mostly;

atomic_t tcp_orphan_count = ATOMIC_INIT(0);

EXPORT_SYMBOL_GPL(tcp_orphan_count);

int 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_t tcp_memory_allocated;	/* Current allocated memory. */
atomic_t tcp_sockets_allocated;	/* Current number of TCP sockets. */

EXPORT_SYMBOL(tcp_memory_allocated);
EXPORT_SYMBOL(tcp_sockets_allocated);

/*
 * Pressure flag: try to collapse.
 * Technical note: it is used by multiple contexts non atomically.
 * All the sk_stream_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(void)
{
	if (!tcp_memory_pressure) {
		NET_INC_STATS(LINUX_MIB_TCPMEMORYPRESSURES);
		tcp_memory_pressure = 1;
	}
}

EXPORT_SYMBOL(tcp_enter_memory_pressure);

/*
 *	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);

	poll_wait(file, sk->sk_sleep, 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 another threads is impossible in any case.
	 */

	mask = 0;
	if (sk->sk_err)
		mask = POLLERR;

	/*
	 * 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 PULLHUP were maskable,
	 * then we could set it on SND_SHUTDOWN. BTW examples given
	 * in Stevens' books assume exactly this behaviour, it explains
	 * why PULLHUP 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)) {
		/* 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) &&
		    (tp->urg_seq != tp->copied_seq ||
		     tp->rcv_nxt != tp->copied_seq + 1 ||
		     sock_flag(sk, SOCK_URGINLINE) || !tp->urg_data))
			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;
			}
		}

		if (tp->urg_data & TCP_URG_VALID)
			mask |= POLLPRI;
	}
	return mask;
}

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

			/* Subtract 1, if FIN is in queue. */
			if (answ && !skb_queue_empty(&sk->sk_receive_queue))
				answ -=
		       tcp_hdr((struct sk_buff *)sk->sk_receive_queue.prev)->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;
	default:
		return -ENOIOCTLCMD;
	}

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

static inline void tcp_mark_push(struct tcp_sock *tp, struct sk_buff *skb)
{
	TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_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   = TCPCB_FLAG_ACK;
	tcb->sacked  = 0;
	skb_header_release(skb);
	tcp_add_write_queue_tail(sk, skb);
	sk_charge_skb(sk, skb);
	if (tp->nonagle & TCP_NAGLE_PUSH)
		tp->nonagle &= ~TCP_NAGLE_PUSH;
}

static inline void tcp_mark_urg(struct tcp_sock *tp, int flags,
				struct sk_buff *skb)
{
	if (flags & MSG_OOB) {
		tp->urg_mode = 1;
		tp->snd_up = tp->write_seq;
		TCP_SKB_CB(skb)->sacked |= TCPCB_URG;
	}
}

static inline void tcp_push(struct sock *sk, int flags, int mss_now,