sock.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.
 *
 *		Generic socket support routines. Memory allocators, socket lock/release
 *		handler for protocols to use and generic option handler.
 *
 *
 * Version:	$Id: sock.c,v 1.117 2002/02/01 22:01:03 davem Exp $
 *
 * Authors:	Ross Biro
 *		Fred N. van Kempen, <[e-mail]>
 *		Florian La Roche, <[e-mail]>
 *		Alan Cox, <[e-mail]>
 *
 * Fixes:
 *		Alan Cox	: 	Numerous verify_area() problems
 *		Alan Cox	:	Connecting on a connecting socket
 *					now returns an error for tcp.
 *		Alan Cox	:	sock->protocol is set correctly.
 *					and is not sometimes left as 0.
 *		Alan Cox	:	connect handles icmp errors on a
 *					connect properly. Unfortunately there
 *					is a restart syscall nasty there. I
 *					can't match BSD without hacking the C
 *					library. Ideas urgently sought!
 *		Alan Cox	:	Disallow bind() to addresses that are
 *					not ours - especially broadcast ones!!
 *		Alan Cox	:	Socket 1024 _IS_ ok for users. (fencepost)
 *		Alan Cox	:	sock_wfree/sock_rfree don't destroy sockets,
 *					instead they leave that for the DESTROY timer.
 *		Alan Cox	:	Clean up error flag in accept
 *		Alan Cox	:	TCP ack handling is buggy, the DESTROY timer
 *					was buggy. Put a remove_sock() in the handler
 *					for memory when we hit 0. Also altered the timer
 *					code. The ACK stuff can wait and needs major
 *					TCP layer surgery.
 *		Alan Cox	:	Fixed TCP ack bug, removed remove sock
 *					and fixed timer/inet_bh race.
 *		Alan Cox	:	Added zapped flag for TCP
 *		Alan Cox	:	Move kfree_skb into skbuff.c and tidied up surplus code
 *		Alan Cox	:	for new sk_buff allocations wmalloc/rmalloc now call alloc_skb
 *		Alan Cox	:	kfree_s calls now are kfree_skbmem so we can track skb resources
 *		Alan Cox	:	Supports socket option broadcast now as does udp. Packet and raw need fixing.
 *		Alan Cox	:	Added RCVBUF,SNDBUF size setting. It suddenly occurred to me how easy it was so...
 *		Rick Sladkey	:	Relaxed UDP rules for matching packets.
 *		C.E.Hawkins	:	IFF_PROMISC/SIOCGHWADDR support
 *	Pauline Middelink	:	identd support
 *		Alan Cox	:	Fixed connect() taking signals I think.
 *		Alan Cox	:	SO_LINGER supported
 *		Alan Cox	:	Error reporting fixes
 *		Anonymous	:	inet_create tidied up (sk->reuse setting)
 *		Alan Cox	:	inet sockets don't set sk->type!
 *		Alan Cox	:	Split socket option code
 *		Alan Cox	:	Callbacks
 *		Alan Cox	:	Nagle flag for Charles & Johannes stuff
 *		Alex		:	Removed restriction on inet fioctl
 *		Alan Cox	:	Splitting INET from NET core
 *		Alan Cox	:	Fixed bogus SO_TYPE handling in getsockopt()
 *		Adam Caldwell	:	Missing return in SO_DONTROUTE/SO_DEBUG code
 *		Alan Cox	:	Split IP from generic code
 *		Alan Cox	:	New kfree_skbmem()
 *		Alan Cox	:	Make SO_DEBUG superuser only.
 *		Alan Cox	:	Allow anyone to clear SO_DEBUG
 *					(compatibility fix)
 *		Alan Cox	:	Added optimistic memory grabbing for AF_UNIX throughput.
 *		Alan Cox	:	Allocator for a socket is settable.
 *		Alan Cox	:	SO_ERROR includes soft errors.
 *		Alan Cox	:	Allow NULL arguments on some SO_ opts
 *		Alan Cox	: 	Generic socket allocation to make hooks
 *					easier (suggested by Craig Metz).
 *		Michael Pall	:	SO_ERROR returns positive errno again
 *              Steve Whitehouse:       Added default destructor to free
 *                                      protocol private data.
 *              Steve Whitehouse:       Added various other default routines
 *                                      common to several socket families.
 *              Chris Evans     :       Call suser() check last on F_SETOWN
 *		Jay Schulist	:	Added SO_ATTACH_FILTER and SO_DETACH_FILTER.
 *		Andi Kleen	:	Add sock_kmalloc()/sock_kfree_s()
 *		Andi Kleen	:	Fix write_space callback
 *		Chris Evans	:	Security fixes - signedness again
 *		Arnaldo C. Melo :       cleanups, use skb_queue_purge
 *
 * To Fix:
 *
 *
 *		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.
 */

#include <linux/capability.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/in.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/sched.h>
#include <linux/timer.h>
#include <linux/string.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/interrupt.h>
#include <linux/poll.h>
#include <linux/tcp.h>
#include <linux/init.h>
#include <linux/highmem.h>

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

#include <linux/netdevice.h>
#include <net/protocol.h>
#include <linux/skbuff.h>
#include <net/net_namespace.h>
#include <net/request_sock.h>
#include <net/sock.h>
#include <net/xfrm.h>
#include <linux/ipsec.h>

#include <linux/filter.h>

#ifdef CONFIG_INET
#include <net/tcp.h>
#endif

/*
 * Each address family might have different locking rules, so we have
 * one slock key per address family:
 */
static struct lock_class_key af_family_keys[AF_MAX];
static struct lock_class_key af_family_slock_keys[AF_MAX];

#ifdef CONFIG_DEBUG_LOCK_ALLOC
/*
 * Make lock validator output more readable. (we pre-construct these
 * strings build-time, so that runtime initialization of socket
 * locks is fast):
 */
static const char *af_family_key_strings[AF_MAX+1] = {
  "sk_lock-AF_UNSPEC", "sk_lock-AF_UNIX"     , "sk_lock-AF_INET"     ,
  "sk_lock-AF_AX25"  , "sk_lock-AF_IPX"      , "sk_lock-AF_APPLETALK",
  "sk_lock-AF_NETROM", "sk_lock-AF_BRIDGE"   , "sk_lock-AF_ATMPVC"   ,
  "sk_lock-AF_X25"   , "sk_lock-AF_INET6"    , "sk_lock-AF_ROSE"     ,
  "sk_lock-AF_DECnet", "sk_lock-AF_NETBEUI"  , "sk_lock-AF_SECURITY" ,
  "sk_lock-AF_KEY"   , "sk_lock-AF_NETLINK"  , "sk_lock-AF_PACKET"   ,
  "sk_lock-AF_ASH"   , "sk_lock-AF_ECONET"   , "sk_lock-AF_ATMSVC"   ,
  "sk_lock-21"       , "sk_lock-AF_SNA"      , "sk_lock-AF_IRDA"     ,
  "sk_lock-AF_PPPOX" , "sk_lock-AF_WANPIPE"  , "sk_lock-AF_LLC"      ,
  "sk_lock-27"       , "sk_lock-28"          , "sk_lock-29"          ,
  "sk_lock-AF_TIPC"  , "sk_lock-AF_BLUETOOTH", "sk_lock-IUCV"        ,
  "sk_lock-AF_RXRPC" , "sk_lock-AF_MAX"
};
static const char *af_family_slock_key_strings[AF_MAX+1] = {
  "slock-AF_UNSPEC", "slock-AF_UNIX"     , "slock-AF_INET"     ,
  "slock-AF_AX25"  , "slock-AF_IPX"      , "slock-AF_APPLETALK",
  "slock-AF_NETROM", "slock-AF_BRIDGE"   , "slock-AF_ATMPVC"   ,
  "slock-AF_X25"   , "slock-AF_INET6"    , "slock-AF_ROSE"     ,
  "slock-AF_DECnet", "slock-AF_NETBEUI"  , "slock-AF_SECURITY" ,
  "slock-AF_KEY"   , "slock-AF_NETLINK"  , "slock-AF_PACKET"   ,
  "slock-AF_ASH"   , "slock-AF_ECONET"   , "slock-AF_ATMSVC"   ,
  "slock-21"       , "slock-AF_SNA"      , "slock-AF_IRDA"     ,
  "slock-AF_PPPOX" , "slock-AF_WANPIPE"  , "slock-AF_LLC"      ,
  "slock-27"       , "slock-28"          , "slock-29"          ,
  "slock-AF_TIPC"  , "slock-AF_BLUETOOTH", "slock-AF_IUCV"     ,
  "slock-AF_RXRPC" , "slock-AF_MAX"
};
static const char *af_family_clock_key_strings[AF_MAX+1] = {
  "clock-AF_UNSPEC", "clock-AF_UNIX"     , "clock-AF_INET"     ,
  "clock-AF_AX25"  , "clock-AF_IPX"      , "clock-AF_APPLETALK",
  "clock-AF_NETROM", "clock-AF_BRIDGE"   , "clock-AF_ATMPVC"   ,
  "clock-AF_X25"   , "clock-AF_INET6"    , "clock-AF_ROSE"     ,
  "clock-AF_DECnet", "clock-AF_NETBEUI"  , "clock-AF_SECURITY" ,
  "clock-AF_KEY"   , "clock-AF_NETLINK"  , "clock-AF_PACKET"   ,
  "clock-AF_ASH"   , "clock-AF_ECONET"   , "clock-AF_ATMSVC"   ,
  "clock-21"       , "clock-AF_SNA"      , "clock-AF_IRDA"     ,
  "clock-AF_PPPOX" , "clock-AF_WANPIPE"  , "clock-AF_LLC"      ,
  "clock-27"       , "clock-28"          , "clock-29"          ,
  "clock-AF_TIPC"  , "clock-AF_BLUETOOTH", "clock-AF_IUCV"     ,
  "clock-AF_RXRPC" , "clock-AF_MAX"
};
#endif

/*
 * sk_callback_lock locking rules are per-address-family,
 * so split the lock classes by using a per-AF key:
 */
static struct lock_class_key af_callback_keys[AF_MAX];

/* Take into consideration the size of the struct sk_buff overhead in the
 * determination of these values, since that is non-constant across
 * platforms.  This makes socket queueing behavior and performance
 * not depend upon such differences.
 */
#define _SK_MEM_PACKETS		256
#define _SK_MEM_OVERHEAD	(sizeof(struct sk_buff) + 256)
#define SK_WMEM_MAX		(_SK_MEM_OVERHEAD * _SK_MEM_PACKETS)
#define SK_RMEM_MAX		(_SK_MEM_OVERHEAD * _SK_MEM_PACKETS)

/* Run time adjustable parameters. */
__u32 sysctl_wmem_max __read_mostly = SK_WMEM_MAX;
__u32 sysctl_rmem_max __read_mostly = SK_RMEM_MAX;
__u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX;
__u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX;

/* Maximal space eaten by iovec or ancilliary data plus some space */
int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512);

static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen)
{
	struct timeval tv;

	if (optlen < sizeof(tv))
		return -EINVAL;
	if (copy_from_user(&tv, optval, sizeof(tv)))
		return -EFAULT;
	if (tv.tv_usec < 0 || tv.tv_usec >= USEC_PER_SEC)
		return -EDOM;

	if (tv.tv_sec < 0) {
		static int warned __read_mostly;

		*timeo_p = 0;
		if (warned < 10 && net_ratelimit())
			warned++;
			printk(KERN_INFO "sock_set_timeout: `%s' (pid %d) "
			       "tries to set negative timeout\n",
				current->comm, task_pid_nr(current));
		return 0;
	}
	*timeo_p = MAX_SCHEDULE_TIMEOUT;
	if (tv.tv_sec == 0 && tv.tv_usec == 0)
		return 0;
	if (tv.tv_sec < (MAX_SCHEDULE_TIMEOUT/HZ - 1))
		*timeo_p = tv.tv_sec*HZ + (tv.tv_usec+(1000000/HZ-1))/(1000000/HZ);
	return 0;
}

static void sock_warn_obsolete_bsdism(const char *name)
{
	static int warned;
	static char warncomm[TASK_COMM_LEN];
	if (strcmp(warncomm, current->comm) && warned < 5) {
		strcpy(warncomm,  current->comm);
		printk(KERN_WARNING "process `%s' is using obsolete "
		       "%s SO_BSDCOMPAT\n", warncomm, name);
		warned++;
	}
}

static void sock_disable_timestamp(struct sock *sk)
{
	if (sock_flag(sk, SOCK_TIMESTAMP)) {
		sock_reset_flag(sk, SOCK_TIMESTAMP);
		net_disable_timestamp();
	}
}


int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
	int err = 0;
	int skb_len;

	/* Cast skb->rcvbuf to unsigned... It's pointless, but reduces
	   number of warnings when compiling with -W --ANK
	 */
	if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >=
	    (unsigned)sk->sk_rcvbuf) {
		err = -ENOMEM;
		goto out;
	}

	err = sk_filter(sk, skb);
	if (err)
		goto out;

	skb->dev = NULL;
	skb_set_owner_r(skb, sk);

	/* Cache the SKB length before we tack it onto the receive
	 * queue.  Once it is added it no longer belongs to us and
	 * may be freed by other threads of control pulling packets
	 * from the queue.
	 */
	skb_len = skb->len;

	skb_queue_tail(&sk->sk_receive_queue, skb);

	if (!sock_flag(sk, SOCK_DEAD))
		sk->sk_data_ready(sk, skb_len);
out:
	return err;
}
EXPORT_SYMBOL(sock_queue_rcv_skb);

int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested)
{
	int rc = NET_RX_SUCCESS;

	if (sk_filter(sk, skb))
		goto discard_and_relse;

	skb->dev = NULL;

	if (nested)
		bh_lock_sock_nested(sk);
	else
		bh_lock_sock(sk);
	if (!sock_owned_by_user(sk)) {
		/*
		 * trylock + unlock semantics:
		 */
		mutex_acquire(&sk->sk_lock.dep_map, 0, 1, _RET_IP_);

		rc = sk->sk_backlog_rcv(sk, skb);

		mutex_release(&sk->sk_lock.dep_map, 1, _RET_IP_);
	} else
		sk_add_backlog(sk, skb);
	bh_unlock_sock(sk);
out:
	sock_put(sk);
	return rc;
discard_and_relse:
	kfree_skb(skb);
	goto out;
}
EXPORT_SYMBOL(sk_receive_skb);

struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie)
{
	struct dst_entry *dst = sk->sk_dst_cache;

	if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) {
		sk->sk_dst_cache = NULL;
		dst_release(dst);
		return NULL;
	}

	return dst;
}
EXPORT_SYMBOL(__sk_dst_check);

struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie)
{
	struct dst_entry *dst = sk_dst_get(sk);

	if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) {
		sk_dst_reset(sk);
		dst_release(dst);
		return NULL;
	}

	return dst;
}
EXPORT_SYMBOL(sk_dst_check);

static int sock_bindtodevice(struct sock *sk, char __user *optval, int optlen)
{
	int ret = -ENOPROTOOPT;
#ifdef CONFIG_NETDEVICES
	struct net *net = sk->sk_net;
	char devname[IFNAMSIZ];
	int index;

	/* Sorry... */
	ret = -EPERM;
	if (!capable(CAP_NET_RAW))
		goto out;

	ret = -EINVAL;
	if (optlen < 0)
		goto out;

	/* Bind this socket to a particular device like "eth0",
	 * as specified in the passed interface name. If the
	 * name is "" or the option length is zero the socket
	 * is not bound.
	 */
	if (optlen > IFNAMSIZ - 1)
		optlen = IFNAMSIZ - 1;
	memset(devname, 0, sizeof(devname));

	ret = -EFAULT;
	if (copy_from_user(devname, optval, optlen))
		goto out;

	if (devname[0] == '\0') {
		index = 0;
	} else {
		struct net_device *dev = dev_get_by_name(net, devname);

		ret = -ENODEV;
		if (!dev)
			goto out;

		index = dev->ifindex;
		dev_put(dev);
	}

	lock_sock(sk);
	sk->sk_bound_dev_if = index;
	sk_dst_reset(sk);
	release_sock(sk);

	ret = 0;

out:
#endif

	return ret;
}

/*
 *	This is meant for all protocols to use and covers goings on
 *	at the socket level. Everything here is generic.
 */

int sock_setsockopt(struct socket *sock, int level, int optname,
		    char __user *optval, int optlen)
{
	struct sock *sk=sock->sk;
	int val;
	int valbool;
	struct linger ling;
	int ret = 0;

	/*
	 *	Options without arguments
	 */

#ifdef SO_DONTLINGER		/* Compatibility item... */
	if (optname == SO_DONTLINGER) {
		lock_sock(sk);
		sock_reset_flag(sk, SOCK_LINGER);
		release_sock(sk);
		return 0;
	}
#endif

	if (optname == SO_BINDTODEVICE)
		return sock_bindtodevice(sk, optval, optlen);

	if (optlen < sizeof(int))
		return -EINVAL;

	if (get_user(val, (int __user *)optval))
		return -EFAULT;

	valbool = val?1:0;

	lock_sock(sk);

	switch(optname) {
	case SO_DEBUG:
		if (val && !capable(CAP_NET_ADMIN)) {
			ret = -EACCES;
		}
		else if (valbool)
			sock_set_flag(sk, SOCK_DBG);
		else
			sock_reset_flag(sk, SOCK_DBG);
		break;
	case SO_REUSEADDR:
		sk->sk_reuse = valbool;
		break;
	case SO_TYPE:
	case SO_ERROR:
		ret = -ENOPROTOOPT;
		break;
	case SO_DONTROUTE:
		if (valbool)
			sock_set_flag(sk, SOCK_LOCALROUTE);
		else
			sock_reset_flag(sk, SOCK_LOCALROUTE);
		break;
	case SO_BROADCAST:
		sock_valbool_flag(sk, SOCK_BROADCAST, valbool);
		break;
	case SO_SNDBUF:
		/* Don't error on this BSD doesn't and if you think
		   about it this is right. Otherwise apps have to
		   play 'guess the biggest size' games. RCVBUF/SNDBUF
		   are treated in BSD as hints */

		if (val > sysctl_wmem_max)
			val = sysctl_wmem_max;
set_sndbuf:
		sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
		if ((val * 2) < SOCK_MIN_SNDBUF)
			sk->sk_sndbuf = SOCK_MIN_SNDBUF;
		else
			sk->sk_sndbuf = val * 2;

		/*
		 *	Wake up sending tasks if we
		 *	upped the value.
		 */
		sk->sk_write_space(sk);
		break;

	case SO_SNDBUFFORCE:
		if (!capable(CAP_NET_ADMIN)) {
			ret = -EPERM;
			break;
		}
		goto set_sndbuf;

	case SO_RCVBUF:
		/* Don't error on this BSD doesn't and if you think
		   about it this is right. Otherwise apps have to
		   play 'guess the biggest size' games. RCVBUF/SNDBUF
		   are treated in BSD as hints */

		if (val > sysctl_rmem_max)
			val = sysctl_rmem_max;
set_rcvbuf: