Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 3f421baa authored by Arnaldo Carvalho de Melo's avatar Arnaldo Carvalho de Melo Committed by David S. Miller
Browse files

[NET]: Just move the inet_connection_sock function from tcp sources



Completing the previous changeset, this also generalises tcp_v4_synq_add,
renaming it to inet_csk_reqsk_queue_hash_add, already geing used in the
DCCP tree, which I plan to merge RSN.

Signed-off-by: default avatarArnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent 463c84b9
Loading
Loading
Loading
Loading
+1 −6
Original line number Diff line number Diff line
@@ -333,15 +333,10 @@ static inline struct in6_addr *tcp_v6_rcv_saddr(const struct sock *sk)
	return sk->sk_family == AF_INET6 ? __tcp_v6_rcv_saddr(sk) : NULL;
}

static inline int inet_twsk_ipv6only(const struct sock *sk)
{
	return inet_twsk(sk)->tw_ipv6only;
}

static inline int inet_v6_ipv6only(const struct sock *sk)
{
	return likely(sk->sk_state != TCP_TIME_WAIT) ?
		ipv6_only_sock(sk) : inet_twsk_ipv6only(sk);
		ipv6_only_sock(sk) : inet_twsk(sk)->tw_ipv6only;
}
#else
#define __ipv6_only_sock(sk)	0
+152 −0
Original line number Diff line number Diff line
@@ -16,9 +16,15 @@
#define _INET_CONNECTION_SOCK_H

#include <linux/ip.h>
#include <linux/string.h>
#include <linux/timer.h>
#include <net/request_sock.h>

#define INET_CSK_DEBUG 1

/* Cancel timers, when they are not required. */
#undef INET_CSK_CLEAR_TIMERS

struct inet_bind_bucket;
struct inet_hashinfo;

@@ -61,17 +67,107 @@ struct inet_connection_sock {
	} icsk_ack;
};

#define ICSK_TIME_RETRANS	1	/* Retransmit timer */
#define ICSK_TIME_DACK		2	/* Delayed ack timer */
#define ICSK_TIME_PROBE0	3	/* Zero window probe timer */
#define ICSK_TIME_KEEPOPEN	4	/* Keepalive timer */

static inline struct inet_connection_sock *inet_csk(const struct sock *sk)
{
	return (struct inet_connection_sock *)sk;
}

enum inet_csk_ack_state_t {
	ICSK_ACK_SCHED	= 1,
	ICSK_ACK_TIMER  = 2,
	ICSK_ACK_PUSHED = 4
};

extern void inet_csk_init_xmit_timers(struct sock *sk,
				      void (*retransmit_handler)(unsigned long),
				      void (*delack_handler)(unsigned long),
				      void (*keepalive_handler)(unsigned long));
extern void inet_csk_clear_xmit_timers(struct sock *sk);

static inline void inet_csk_schedule_ack(struct sock *sk)
{
	inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_SCHED;
}

static inline int inet_csk_ack_scheduled(const struct sock *sk)
{
	return inet_csk(sk)->icsk_ack.pending & ICSK_ACK_SCHED;
}

static inline void inet_csk_delack_init(struct sock *sk)
{
	memset(&inet_csk(sk)->icsk_ack, 0, sizeof(inet_csk(sk)->icsk_ack));
}

extern void inet_csk_delete_keepalive_timer(struct sock *sk);
extern void inet_csk_reset_keepalive_timer(struct sock *sk, unsigned long timeout);

#ifdef INET_CSK_DEBUG
extern const char inet_csk_timer_bug_msg[];
#endif

static inline void inet_csk_clear_xmit_timer(struct sock *sk, const int what)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	
	if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0) {
		icsk->icsk_pending = 0;
#ifdef INET_CSK_CLEAR_TIMERS
		sk_stop_timer(sk, &icsk->icsk_retransmit_timer);
#endif
	} else if (what == ICSK_TIME_DACK) {
		icsk->icsk_ack.blocked = icsk->icsk_ack.pending = 0;
#ifdef INET_CSK_CLEAR_TIMERS
		sk_stop_timer(sk, &icsk->icsk_delack_timer);
#endif
	}
#ifdef INET_CSK_DEBUG
	else {
		pr_debug(inet_csk_timer_bug_msg);
	}
#endif
}

/*
 *	Reset the retransmission timer
 */
static inline void inet_csk_reset_xmit_timer(struct sock *sk, const int what,
					     unsigned long when,
					     const unsigned long max_when)
{
	struct inet_connection_sock *icsk = inet_csk(sk);

	if (when > max_when) {
#ifdef INET_CSK_DEBUG
		pr_debug("reset_xmit_timer: sk=%p %d when=0x%lx, caller=%p\n",
			 sk, what, when, current_text_addr());
#endif
		when = max_when;
	}

	if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0) {
		icsk->icsk_pending = what;
		icsk->icsk_timeout = jiffies + when;
		sk_reset_timer(sk, &icsk->icsk_retransmit_timer, icsk->icsk_timeout);
	} else if (what == ICSK_TIME_DACK) {
		icsk->icsk_ack.pending |= ICSK_ACK_TIMER;
		icsk->icsk_ack.timeout = jiffies + when;
		sk_reset_timer(sk, &icsk->icsk_delack_timer, icsk->icsk_ack.timeout);
	}
#ifdef INET_CSK_DEBUG
	else {
		pr_debug(inet_csk_timer_bug_msg);
	}
#endif
}

extern struct sock *inet_csk_accept(struct sock *sk, int flags, int *err);

extern struct request_sock *inet_csk_search_req(const struct sock *sk,
						struct request_sock ***prevp,
						const __u16 rport,
@@ -83,4 +179,60 @@ extern int inet_csk_get_port(struct inet_hashinfo *hashinfo,
extern struct dst_entry* inet_csk_route_req(struct sock *sk,
					    const struct request_sock *req);

static inline void inet_csk_reqsk_queue_add(struct sock *sk,
					    struct request_sock *req,
					    struct sock *child)
{
	reqsk_queue_add(&inet_csk(sk)->icsk_accept_queue, req, sk, child);
}

extern void inet_csk_reqsk_queue_hash_add(struct sock *sk,
					  struct request_sock *req,
					  const unsigned timeout);

static inline void inet_csk_reqsk_queue_removed(struct sock *sk,
						struct request_sock *req)
{
	if (reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req) == 0)
		inet_csk_delete_keepalive_timer(sk);
}

static inline void inet_csk_reqsk_queue_added(struct sock *sk,
					      const unsigned long timeout)
{
	if (reqsk_queue_added(&inet_csk(sk)->icsk_accept_queue) == 0)
		inet_csk_reset_keepalive_timer(sk, timeout);
}

static inline int inet_csk_reqsk_queue_len(const struct sock *sk)
{
	return reqsk_queue_len(&inet_csk(sk)->icsk_accept_queue);
}

static inline int inet_csk_reqsk_queue_young(const struct sock *sk)
{
	return reqsk_queue_len_young(&inet_csk(sk)->icsk_accept_queue);
}

static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk)
{
	return reqsk_queue_is_full(&inet_csk(sk)->icsk_accept_queue);
}

static inline void inet_csk_reqsk_queue_unlink(struct sock *sk,
					       struct request_sock *req,
					       struct request_sock **prev)
{
	reqsk_queue_unlink(&inet_csk(sk)->icsk_accept_queue, req, prev);
}

static inline void inet_csk_reqsk_queue_drop(struct sock *sk,
					     struct request_sock *req,
					     struct request_sock **prev)
{
	inet_csk_reqsk_queue_unlink(sk, req, prev);
	inet_csk_reqsk_queue_removed(sk, req);
	reqsk_free(req);
}

#endif /* _INET_CONNECTION_SOCK_H */
+8 −152
Original line number Diff line number Diff line
@@ -19,18 +19,16 @@
#define _TCP_H

#define TCP_DEBUG 1
#define INET_CSK_DEBUG 1
#define FASTRETRANS_DEBUG 1

/* Cancel timers, when they are not required. */
#undef INET_CSK_CLEAR_TIMERS

#include <linux/config.h>
#include <linux/list.h>
#include <linux/tcp.h>
#include <linux/slab.h>
#include <linux/cache.h>
#include <linux/percpu.h>

#include <net/inet_connection_sock.h>
#include <net/inet_hashtables.h>
#include <net/checksum.h>
#include <net/request_sock.h>
@@ -206,11 +204,6 @@ extern void tcp_tw_deschedule(struct inet_timewait_sock *tw);
#define TCPOLEN_SACK_BASE_ALIGNED	4
#define TCPOLEN_SACK_PERBLOCK		8

#define ICSK_TIME_RETRANS	1	/* Retransmit timer */
#define ICSK_TIME_DACK		2	/* Delayed ack timer */
#define ICSK_TIME_PROBE0	3	/* Zero window probe timer */
#define ICSK_TIME_KEEPOPEN	4	/* Keepalive timer */

/* Flags in tp->nonagle */
#define TCP_NAGLE_OFF		1	/* Nagle's algo is disabled */
#define TCP_NAGLE_CORK		2	/* Socket is corked	    */
@@ -257,12 +250,6 @@ extern atomic_t tcp_memory_allocated;
extern atomic_t tcp_sockets_allocated;
extern int tcp_memory_pressure;

#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
#define AF_INET_FAMILY(fam) ((fam) == AF_INET)
#else
#define AF_INET_FAMILY(fam) 1
#endif

/*
 *	Pointers to address related TCP functions
 *	(i.e. things that depend on the address family)
@@ -373,22 +360,6 @@ extern int tcp_rcv_established(struct sock *sk,

extern void			tcp_rcv_space_adjust(struct sock *sk);

enum inet_csk_ack_state_t {
	ICSK_ACK_SCHED	= 1,
	ICSK_ACK_TIMER  = 2,
	ICSK_ACK_PUSHED = 4
};

static inline void inet_csk_schedule_ack(struct sock *sk)
{
	inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_SCHED;
}

static inline int inet_csk_ack_scheduled(const struct sock *sk)
{
	return inet_csk(sk)->icsk_ack.pending & ICSK_ACK_SCHED;
}

static inline void tcp_dec_quickack_mode(struct sock *sk,
					 const unsigned int pkts)
{
@@ -406,11 +377,6 @@ static inline void tcp_dec_quickack_mode(struct sock *sk,

extern void tcp_enter_quickack_mode(struct sock *sk);

static inline void inet_csk_delack_init(struct sock *sk)
{
	memset(&inet_csk(sk)->icsk_ack, 0, sizeof(inet_csk(sk)->icsk_ack));
}

static inline void tcp_clear_options(struct tcp_options_received *rx_opt)
{
 	rx_opt->tstamp_ok = rx_opt->sack_ok = rx_opt->wscale_ok = rx_opt->snd_wscale = 0;
@@ -442,7 +408,6 @@ extern void tcp_update_metrics(struct sock *sk);

extern void			tcp_close(struct sock *sk, 
					  long timeout);
extern struct sock *		inet_csk_accept(struct sock *sk, int flags, int *err);
extern unsigned int		tcp_poll(struct file * file, struct socket *sock, struct poll_table_struct *wait);

extern int			tcp_getsockopt(struct sock *sk, int level, 
@@ -541,15 +506,9 @@ static inline void tcp_clear_xmit_timers(struct sock *sk)
	inet_csk_clear_xmit_timers(sk);
}

extern void inet_csk_delete_keepalive_timer(struct sock *sk);
extern void inet_csk_reset_keepalive_timer(struct sock *sk, unsigned long timeout);
extern unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu);
extern unsigned int tcp_current_mss(struct sock *sk, int large);

#ifdef INET_CSK_DEBUG
extern const char inet_csk_timer_bug_msg[];
#endif

/* tcp_diag.c */
extern void tcp_get_info(struct sock *, struct tcp_info *);

@@ -559,60 +518,6 @@ typedef int (*sk_read_actor_t)(read_descriptor_t *, struct sk_buff *,
extern int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
			 sk_read_actor_t recv_actor);

static inline void inet_csk_clear_xmit_timer(struct sock *sk, const int what)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	
	if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0) {
		icsk->icsk_pending = 0;
#ifdef INET_CSK_CLEAR_TIMERS
		sk_stop_timer(sk, &icsk->icsk_retransmit_timer);
#endif
	} else if (what == ICSK_TIME_DACK) {
		icsk->icsk_ack.blocked = icsk->icsk_ack.pending = 0;
#ifdef INET_CSK_CLEAR_TIMERS
		sk_stop_timer(sk, &icsk->icsk_delack_timer);
#endif
	}
#ifdef INET_CSK_DEBUG
	else {
		pr_debug(inet_csk_timer_bug_msg);
	}
#endif
}

/*
 *	Reset the retransmission timer
 */
static inline void inet_csk_reset_xmit_timer(struct sock *sk, const int what,
					     unsigned long when)
{
	struct inet_connection_sock *icsk = inet_csk(sk);

	if (when > TCP_RTO_MAX) {
#ifdef INET_CSK_DEBUG
		pr_debug("reset_xmit_timer: sk=%p %d when=0x%lx, caller=%p\n",
			 sk, what, when, current_text_addr());
#endif
		when = TCP_RTO_MAX;
	}

	if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0) {
		icsk->icsk_pending = what;
		icsk->icsk_timeout = jiffies + when;
		sk_reset_timer(sk, &icsk->icsk_retransmit_timer, icsk->icsk_timeout);
	} else if (what == ICSK_TIME_DACK) {
		icsk->icsk_ack.pending |= ICSK_ACK_TIMER;
		icsk->icsk_ack.timeout = jiffies + when;
		sk_reset_timer(sk, &icsk->icsk_delack_timer, icsk->icsk_ack.timeout);
	}
#ifdef INET_CSK_DEBUG
	else {
		pr_debug(inet_csk_timer_bug_msg);
	}
#endif
}

/* Initialize RCV_MSS value.
 * RCV_MSS is an our guess about MSS used by the peer.
 * We haven't any direct information about the MSS.
@@ -765,7 +670,8 @@ static inline void tcp_packets_out_inc(struct sock *sk,

	tp->packets_out += tcp_skb_pcount(skb);
	if (!orig)
		inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, inet_csk(sk)->icsk_rto);
		inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
					  inet_csk(sk)->icsk_rto, TCP_RTO_MAX);
}

static inline void tcp_packets_out_dec(struct tcp_sock *tp, 
@@ -934,7 +840,8 @@ static __inline__ void tcp_check_probe_timer(struct sock *sk, struct tcp_sock *t
{
	const struct inet_connection_sock *icsk = inet_csk(sk);
	if (!tp->packets_out && !icsk->icsk_pending)
		inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0, icsk->icsk_rto);
		inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
					  icsk->icsk_rto, TCP_RTO_MAX);
}

static __inline__ void tcp_push_pending_frames(struct sock *sk,
@@ -1017,7 +924,8 @@ static __inline__ int tcp_prequeue(struct sock *sk, struct sk_buff *skb)
			wake_up_interruptible(sk->sk_sleep);
			if (!inet_csk_ack_scheduled(sk))
				inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
						          (3 * TCP_RTO_MIN) / 4);
						          (3 * TCP_RTO_MIN) / 4,
							  TCP_RTO_MAX);
		}
		return 1;
	}
@@ -1181,58 +1089,6 @@ static inline int tcp_full_space(const struct sock *sk)
	return tcp_win_from_space(sk->sk_rcvbuf); 
}

static inline void inet_csk_reqsk_queue_add(struct sock *sk,
					    struct request_sock *req,
					    struct sock *child)
{
	reqsk_queue_add(&inet_csk(sk)->icsk_accept_queue, req, sk, child);
}

static inline void inet_csk_reqsk_queue_removed(struct sock *sk,
						struct request_sock *req)
{
	if (reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req) == 0)
		inet_csk_delete_keepalive_timer(sk);
}

static inline void inet_csk_reqsk_queue_added(struct sock *sk,
					      const unsigned long timeout)
{
	if (reqsk_queue_added(&inet_csk(sk)->icsk_accept_queue) == 0)
		inet_csk_reset_keepalive_timer(sk, timeout);
}

static inline int inet_csk_reqsk_queue_len(const struct sock *sk)
{
	return reqsk_queue_len(&inet_csk(sk)->icsk_accept_queue);
}

static inline int inet_csk_reqsk_queue_young(const struct sock *sk)
{
	return reqsk_queue_len_young(&inet_csk(sk)->icsk_accept_queue);
}

static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk)
{
	return reqsk_queue_is_full(&inet_csk(sk)->icsk_accept_queue);
}

static inline void inet_csk_reqsk_queue_unlink(struct sock *sk,
					       struct request_sock *req,
					       struct request_sock **prev)
{
	reqsk_queue_unlink(&inet_csk(sk)->icsk_accept_queue, req, prev);
}

static inline void inet_csk_reqsk_queue_drop(struct sock *sk,
					     struct request_sock *req,
					     struct request_sock **prev)
{
	inet_csk_reqsk_queue_unlink(sk, req, prev);
	inet_csk_reqsk_queue_removed(sk, req);
	reqsk_free(req);
}

static __inline__ void tcp_openreq_init(struct request_sock *req,
					struct tcp_options_received *rx_opt,
					struct sk_buff *skb)
+1 −1
Original line number Diff line number Diff line
@@ -5,7 +5,7 @@
obj-y     := route.o inetpeer.o protocol.o \
	     ip_input.o ip_fragment.o ip_forward.o ip_options.o \
	     ip_output.o ip_sockglue.o inet_hashtables.o \
	     inet_timewait_sock.o \
	     inet_timewait_sock.o inet_connection_sock.o \
	     tcp.o tcp_input.o tcp_output.o tcp_timer.o tcp_ipv4.o \
	     tcp_minisocks.o tcp_cong.o \
	     datagram.o raw.o udp.o arp.o icmp.o devinet.o af_inet.o igmp.o \
+401 −0
Original line number Diff line number Diff line
/*
 * 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.
 *
 *		Support for INET connection oriented protocols.
 *
 * Authors:	See the TCP sources
 *
 *		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/config.h>
#include <linux/module.h>
#include <linux/jhash.h>

#include <net/inet_connection_sock.h>
#include <net/inet_hashtables.h>
#include <net/inet_timewait_sock.h>
#include <net/ip.h>
#include <net/route.h>
#include <net/tcp_states.h>

#ifdef INET_CSK_DEBUG
const char inet_csk_timer_bug_msg[] = "inet_csk BUG: unknown timer value\n";
EXPORT_SYMBOL(inet_csk_timer_bug_msg);
#endif

/*
 * This array holds the first and last local port number.
 * For high-usage systems, use sysctl to change this to
 * 32768-61000
 */
int sysctl_local_port_range[2] = { 1024, 4999 };

static inline int inet_csk_bind_conflict(struct sock *sk, struct inet_bind_bucket *tb)
{
	const u32 sk_rcv_saddr = inet_rcv_saddr(sk);
	struct sock *sk2;
	struct hlist_node *node;
	int reuse = sk->sk_reuse;

	sk_for_each_bound(sk2, node, &tb->owners) {
		if (sk != sk2 &&
		    !inet_v6_ipv6only(sk2) &&
		    (!sk->sk_bound_dev_if ||
		     !sk2->sk_bound_dev_if ||
		     sk->sk_bound_dev_if == sk2->sk_bound_dev_if)) {
			if (!reuse || !sk2->sk_reuse ||
			    sk2->sk_state == TCP_LISTEN) {
				const u32 sk2_rcv_saddr = inet_rcv_saddr(sk2);
				if (!sk2_rcv_saddr || !sk_rcv_saddr ||
				    sk2_rcv_saddr == sk_rcv_saddr)
					break;
			}
		}
	}
	return node != NULL;
}

/* Obtain a reference to a local port for the given sock,
 * if snum is zero it means select any available local port.
 */
int inet_csk_get_port(struct inet_hashinfo *hashinfo,
		      struct sock *sk, unsigned short snum)
{
	struct inet_bind_hashbucket *head;
	struct hlist_node *node;
	struct inet_bind_bucket *tb;
	int ret;

	local_bh_disable();
	if (!snum) {
		int low = sysctl_local_port_range[0];
		int high = sysctl_local_port_range[1];
		int remaining = (high - low) + 1;
		int rover;

		spin_lock(&hashinfo->portalloc_lock);
		if (hashinfo->port_rover < low)
			rover = low;
		else
			rover = hashinfo->port_rover;
		do {
			rover++;
			if (rover > high)
				rover = low;
			head = &hashinfo->bhash[inet_bhashfn(rover, hashinfo->bhash_size)];
			spin_lock(&head->lock);
			inet_bind_bucket_for_each(tb, node, &head->chain)
				if (tb->port == rover)
					goto next;
			break;
		next:
			spin_unlock(&head->lock);
		} while (--remaining > 0);
		hashinfo->port_rover = rover;
		spin_unlock(&hashinfo->portalloc_lock);

		/* Exhausted local port range during search?  It is not
		 * possible for us to be holding one of the bind hash
		 * locks if this test triggers, because if 'remaining'
		 * drops to zero, we broke out of the do/while loop at
		 * the top level, not from the 'break;' statement.
		 */
		ret = 1;
		if (remaining <= 0)
			goto fail;

		/* OK, here is the one we will use.  HEAD is
		 * non-NULL and we hold it's mutex.
		 */
		snum = rover;
	} else {
		head = &hashinfo->bhash[inet_bhashfn(snum, hashinfo->bhash_size)];
		spin_lock(&head->lock);
		inet_bind_bucket_for_each(tb, node, &head->chain)
			if (tb->port == snum)
				goto tb_found;
	}
	tb = NULL;
	goto tb_not_found;
tb_found:
	if (!hlist_empty(&tb->owners)) {
		if (sk->sk_reuse > 1)
			goto success;
		if (tb->fastreuse > 0 &&
		    sk->sk_reuse && sk->sk_state != TCP_LISTEN) {
			goto success;
		} else {
			ret = 1;
			if (inet_csk_bind_conflict(sk, tb))
				goto fail_unlock;
		}
	}
tb_not_found:
	ret = 1;
	if (!tb && (tb = inet_bind_bucket_create(hashinfo->bind_bucket_cachep, head, snum)) == NULL)
		goto fail_unlock;
	if (hlist_empty(&tb->owners)) {
		if (sk->sk_reuse && sk->sk_state != TCP_LISTEN)
			tb->fastreuse = 1;
		else
			tb->fastreuse = 0;
	} else if (tb->fastreuse &&
		   (!sk->sk_reuse || sk->sk_state == TCP_LISTEN))
		tb->fastreuse = 0;
success:
	if (!inet_csk(sk)->icsk_bind_hash)
		inet_bind_hash(sk, tb, snum);
	BUG_TRAP(inet_csk(sk)->icsk_bind_hash == tb);
 	ret = 0;

fail_unlock:
	spin_unlock(&head->lock);
fail:
	local_bh_enable();
	return ret;
}

EXPORT_SYMBOL_GPL(inet_csk_get_port);

/*
 * Wait for an incoming connection, avoid race conditions. This must be called
 * with the socket locked.
 */
static int inet_csk_wait_for_connect(struct sock *sk, long timeo)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	DEFINE_WAIT(wait);
	int err;

	/*
	 * True wake-one mechanism for incoming connections: only
	 * one process gets woken up, not the 'whole herd'.
	 * Since we do not 'race & poll' for established sockets
	 * anymore, the common case will execute the loop only once.
	 *
	 * Subtle issue: "add_wait_queue_exclusive()" will be added
	 * after any current non-exclusive waiters, and we know that
	 * it will always _stay_ after any new non-exclusive waiters
	 * because all non-exclusive waiters are added at the
	 * beginning of the wait-queue. As such, it's ok to "drop"
	 * our exclusiveness temporarily when we get woken up without
	 * having to remove and re-insert us on the wait queue.
	 */
	for (;;) {
		prepare_to_wait_exclusive(sk->sk_sleep, &wait,
					  TASK_INTERRUPTIBLE);
		release_sock(sk);
		if (reqsk_queue_empty(&icsk->icsk_accept_queue))
			timeo = schedule_timeout(timeo);
		lock_sock(sk);
		err = 0;
		if (!reqsk_queue_empty(&icsk->icsk_accept_queue))
			break;
		err = -EINVAL;
		if (sk->sk_state != TCP_LISTEN)
			break;
		err = sock_intr_errno(timeo);
		if (signal_pending(current))
			break;
		err = -EAGAIN;
		if (!timeo)
			break;
	}
	finish_wait(sk->sk_sleep, &wait);
	return err;
}

/*
 * This will accept the next outstanding connection.
 */
struct sock *inet_csk_accept(struct sock *sk, int flags, int *err)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	struct sock *newsk;
	int error;

	lock_sock(sk);

	/* We need to make sure that this socket is listening,
	 * and that it has something pending.
	 */
	error = -EINVAL;
	if (sk->sk_state != TCP_LISTEN)
		goto out_err;

	/* Find already established connection */
	if (reqsk_queue_empty(&icsk->icsk_accept_queue)) {
		long timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK);

		/* If this is a non blocking socket don't sleep */
		error = -EAGAIN;
		if (!timeo)
			goto out_err;

		error = inet_csk_wait_for_connect(sk, timeo);
		if (error)
			goto out_err;
	}

	newsk = reqsk_queue_get_child(&icsk->icsk_accept_queue, sk);
	BUG_TRAP(newsk->sk_state != TCP_SYN_RECV);
out:
	release_sock(sk);
	return newsk;
out_err:
	newsk = NULL;
	*err = error;
	goto out;
}

EXPORT_SYMBOL(inet_csk_accept);

/*
 * Using different timers for retransmit, delayed acks and probes
 * We may wish use just one timer maintaining a list of expire jiffies 
 * to optimize.
 */
void inet_csk_init_xmit_timers(struct sock *sk,
			       void (*retransmit_handler)(unsigned long),
			       void (*delack_handler)(unsigned long),
			       void (*keepalive_handler)(unsigned long))
{
	struct inet_connection_sock *icsk = inet_csk(sk);

	init_timer(&icsk->icsk_retransmit_timer);
	init_timer(&icsk->icsk_delack_timer);
	init_timer(&sk->sk_timer);

	icsk->icsk_retransmit_timer.function = retransmit_handler;
	icsk->icsk_delack_timer.function     = delack_handler;
	sk->sk_timer.function		     = keepalive_handler;

	icsk->icsk_retransmit_timer.data = 
		icsk->icsk_delack_timer.data =
			sk->sk_timer.data  = (unsigned long)sk;

	icsk->icsk_pending = icsk->icsk_ack.pending = 0;
}

EXPORT_SYMBOL(inet_csk_init_xmit_timers);

void inet_csk_clear_xmit_timers(struct sock *sk)
{
	struct inet_connection_sock *icsk = inet_csk(sk);

	icsk->icsk_pending = icsk->icsk_ack.pending = icsk->icsk_ack.blocked = 0;

	sk_stop_timer(sk, &icsk->icsk_retransmit_timer);
	sk_stop_timer(sk, &icsk->icsk_delack_timer);
	sk_stop_timer(sk, &sk->sk_timer);
}

EXPORT_SYMBOL(inet_csk_clear_xmit_timers);

void inet_csk_delete_keepalive_timer(struct sock *sk)
{
	sk_stop_timer(sk, &sk->sk_timer);
}

EXPORT_SYMBOL(inet_csk_delete_keepalive_timer);

void inet_csk_reset_keepalive_timer(struct sock *sk, unsigned long len)
{
	sk_reset_timer(sk, &sk->sk_timer, jiffies + len);
}

EXPORT_SYMBOL(inet_csk_reset_keepalive_timer);

struct dst_entry* inet_csk_route_req(struct sock *sk,
				     const struct request_sock *req)
{
	struct rtable *rt;
	const struct inet_request_sock *ireq = inet_rsk(req);
	struct ip_options *opt = inet_rsk(req)->opt;
	struct flowi fl = { .oif = sk->sk_bound_dev_if,
			    .nl_u = { .ip4_u =
				      { .daddr = ((opt && opt->srr) ?
						  opt->faddr :
						  ireq->rmt_addr),
					.saddr = ireq->loc_addr,
					.tos = RT_CONN_FLAGS(sk) } },
			    .proto = sk->sk_protocol,
			    .uli_u = { .ports =
				       { .sport = inet_sk(sk)->sport,
					 .dport = ireq->rmt_port } } };

	if (ip_route_output_flow(&rt, &fl, sk, 0)) {
		IP_INC_STATS_BH(IPSTATS_MIB_OUTNOROUTES);
		return NULL;
	}
	if (opt && opt->is_strictroute && rt->rt_dst != rt->rt_gateway) {
		ip_rt_put(rt);
		IP_INC_STATS_BH(IPSTATS_MIB_OUTNOROUTES);
		return NULL;
	}
	return &rt->u.dst;
}

EXPORT_SYMBOL_GPL(inet_csk_route_req);

static inline u32 inet_synq_hash(const u32 raddr, const u16 rport,
				 const u32 rnd, const u16 synq_hsize)
{
	return jhash_2words(raddr, (u32)rport, rnd) & (synq_hsize - 1);
}

#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
#define AF_INET_FAMILY(fam) ((fam) == AF_INET)
#else
#define AF_INET_FAMILY(fam) 1
#endif

struct request_sock *inet_csk_search_req(const struct sock *sk,
					 struct request_sock ***prevp,
					 const __u16 rport, const __u32 raddr,
					 const __u32 laddr)
{
	const struct inet_connection_sock *icsk = inet_csk(sk);
	struct listen_sock *lopt = icsk->icsk_accept_queue.listen_opt;
	struct request_sock *req, **prev;

	for (prev = &lopt->syn_table[inet_synq_hash(raddr, rport, lopt->hash_rnd,
						    lopt->nr_table_entries)];
	     (req = *prev) != NULL;
	     prev = &req->dl_next) {
		const struct inet_request_sock *ireq = inet_rsk(req);

		if (ireq->rmt_port == rport &&
		    ireq->rmt_addr == raddr &&
		    ireq->loc_addr == laddr &&
		    AF_INET_FAMILY(req->rsk_ops->family)) {
			BUG_TRAP(!req->sk);
			*prevp = prev;
			break;
		}
	}

	return req;
}

EXPORT_SYMBOL_GPL(inet_csk_search_req);

void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req,
				   const unsigned timeout)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	struct listen_sock *lopt = icsk->icsk_accept_queue.listen_opt;
	const u32 h = inet_synq_hash(inet_rsk(req)->rmt_addr, inet_rsk(req)->rmt_port,
				     lopt->hash_rnd, lopt->nr_table_entries);

	reqsk_queue_hash_req(&icsk->icsk_accept_queue, h, req, timeout);
	inet_csk_reqsk_queue_added(sk, timeout);
}

EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_hash_add);
Loading