123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814 |
- /*
- * 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/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>
- #include <net/xfrm.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 struct holds the first and last local port number.
- */
- struct local_ports sysctl_local_ports __read_mostly = {
- .lock = __SEQLOCK_UNLOCKED(sysctl_local_ports.lock),
- .range = { 32768, 61000 },
- };
- unsigned long *sysctl_local_reserved_ports;
- EXPORT_SYMBOL(sysctl_local_reserved_ports);
- void inet_get_local_port_range(int *low, int *high)
- {
- unsigned int seq;
- do {
- seq = read_seqbegin(&sysctl_local_ports.lock);
- *low = sysctl_local_ports.range[0];
- *high = sysctl_local_ports.range[1];
- } while (read_seqretry(&sysctl_local_ports.lock, seq));
- }
- EXPORT_SYMBOL(inet_get_local_port_range);
- int inet_csk_bind_conflict(const struct sock *sk,
- const struct inet_bind_bucket *tb)
- {
- struct sock *sk2;
- struct hlist_node *node;
- int reuse = sk->sk_reuse;
- /*
- * Unlike other sk lookup places we do not check
- * for sk_net here, since _all_ the socks listed
- * in tb->owners list belong to the same net - the
- * one this bucket belongs to.
- */
- 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 __be32 sk2_rcv_saddr = sk_rcv_saddr(sk2);
- if (!sk2_rcv_saddr || !sk_rcv_saddr(sk) ||
- sk2_rcv_saddr == sk_rcv_saddr(sk))
- break;
- }
- }
- }
- return node != NULL;
- }
- EXPORT_SYMBOL_GPL(inet_csk_bind_conflict);
- /* 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 sock *sk, unsigned short snum)
- {
- struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
- struct inet_bind_hashbucket *head;
- struct hlist_node *node;
- struct inet_bind_bucket *tb;
- int ret, attempts = 5;
- struct net *net = sock_net(sk);
- int smallest_size = -1, smallest_rover;
- local_bh_disable();
- if (!snum) {
- int remaining, rover, low, high;
- again:
- inet_get_local_port_range(&low, &high);
- remaining = (high - low) + 1;
- smallest_rover = rover = net_random() % remaining + low;
- smallest_size = -1;
- do {
- if (inet_is_reserved_local_port(rover))
- goto next_nolock;
- head = &hashinfo->bhash[inet_bhashfn(net, rover,
- hashinfo->bhash_size)];
- spin_lock(&head->lock);
- inet_bind_bucket_for_each(tb, node, &head->chain)
- if (net_eq(ib_net(tb), net) && tb->port == rover) {
- if (tb->fastreuse > 0 &&
- sk->sk_reuse &&
- sk->sk_state != TCP_LISTEN &&
- (tb->num_owners < smallest_size || smallest_size == -1)) {
- smallest_size = tb->num_owners;
- smallest_rover = rover;
- if (atomic_read(&hashinfo->bsockets) > (high - low) + 1) {
- snum = smallest_rover;
- goto tb_found;
- }
- }
- if (!inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb)) {
- snum = rover;
- goto tb_found;
- }
- goto next;
- }
- break;
- next:
- spin_unlock(&head->lock);
- next_nolock:
- if (++rover > high)
- rover = low;
- } while (--remaining > 0);
- /* 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) {
- if (smallest_size != -1) {
- snum = smallest_rover;
- goto have_snum;
- }
- goto fail;
- }
- /* OK, here is the one we will use. HEAD is
- * non-NULL and we hold it's mutex.
- */
- snum = rover;
- } else {
- have_snum:
- head = &hashinfo->bhash[inet_bhashfn(net, snum,
- hashinfo->bhash_size)];
- spin_lock(&head->lock);
- inet_bind_bucket_for_each(tb, node, &head->chain)
- if (net_eq(ib_net(tb), net) && tb->port == snum)
- goto tb_found;
- }
- tb = NULL;
- goto tb_not_found;
- tb_found:
- if (!hlist_empty(&tb->owners)) {
- if (sk->sk_reuse == SK_FORCE_REUSE)
- goto success;
- if (tb->fastreuse > 0 &&
- sk->sk_reuse && sk->sk_state != TCP_LISTEN &&
- smallest_size == -1) {
- goto success;
- } else {
- ret = 1;
- if (inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb)) {
- if (sk->sk_reuse && sk->sk_state != TCP_LISTEN &&
- smallest_size != -1 && --attempts >= 0) {
- spin_unlock(&head->lock);
- goto again;
- }
- goto fail_unlock;
- }
- }
- }
- tb_not_found:
- ret = 1;
- if (!tb && (tb = inet_bind_bucket_create(hashinfo->bind_bucket_cachep,
- net, 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);
- WARN_ON(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_sleep(sk), &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_sleep(sk), &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);
- WARN_ON(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);
- setup_timer(&icsk->icsk_retransmit_timer, retransmit_handler,
- (unsigned long)sk);
- setup_timer(&icsk->icsk_delack_timer, delack_handler,
- (unsigned long)sk);
- setup_timer(&sk->sk_timer, keepalive_handler, (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,
- struct flowi4 *fl4,
- const struct request_sock *req)
- {
- struct rtable *rt;
- const struct inet_request_sock *ireq = inet_rsk(req);
- struct ip_options_rcu *opt = inet_rsk(req)->opt;
- struct net *net = sock_net(sk);
- flowi4_init_output(fl4, sk->sk_bound_dev_if, ireq->ir_mark,
- RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
- sk->sk_protocol, inet_sk_flowi_flags(sk),
- (opt && opt->opt.srr) ? opt->opt.faddr : ireq->rmt_addr,
- ireq->loc_addr, ireq->rmt_port, inet_sk(sk)->inet_sport,
- sk->sk_uid);
- security_req_classify_flow(req, flowi4_to_flowi(fl4));
- rt = ip_route_output_flow(net, fl4, sk);
- if (IS_ERR(rt))
- goto no_route;
- if (opt && opt->opt.is_strictroute && fl4->daddr != rt->rt_gateway)
- goto route_err;
- return &rt->dst;
- route_err:
- ip_rt_put(rt);
- no_route:
- IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES);
- return NULL;
- }
- EXPORT_SYMBOL_GPL(inet_csk_route_req);
- struct dst_entry *inet_csk_route_child_sock(struct sock *sk,
- struct sock *newsk,
- const struct request_sock *req)
- {
- const struct inet_request_sock *ireq = inet_rsk(req);
- struct inet_sock *newinet = inet_sk(newsk);
- struct ip_options_rcu *opt = ireq->opt;
- struct net *net = sock_net(sk);
- struct flowi4 *fl4;
- struct rtable *rt;
- fl4 = &newinet->cork.fl.u.ip4;
- flowi4_init_output(fl4, sk->sk_bound_dev_if, ireq->ir_mark,
- RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
- sk->sk_protocol, inet_sk_flowi_flags(sk),
- (opt && opt->opt.srr) ? opt->opt.faddr : ireq->rmt_addr,
- ireq->loc_addr, ireq->rmt_port, inet_sk(sk)->inet_sport,
- sk->sk_uid);
- security_req_classify_flow(req, flowi4_to_flowi(fl4));
- rt = ip_route_output_flow(net, fl4, sk);
- if (IS_ERR(rt))
- goto no_route;
- if (opt && opt->opt.is_strictroute && fl4->daddr != rt->rt_gateway)
- goto route_err;
- return &rt->dst;
- route_err:
- ip_rt_put(rt);
- no_route:
- IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES);
- return NULL;
- }
- EXPORT_SYMBOL_GPL(inet_csk_route_child_sock);
- static inline u32 inet_synq_hash(const __be32 raddr, const __be16 rport,
- const u32 rnd, const u32 synq_hsize)
- {
- return jhash_2words((__force u32)raddr, (__force u32)rport, rnd) & (synq_hsize - 1);
- }
- #if IS_ENABLED(CONFIG_IPV6)
- #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 __be16 rport, const __be32 raddr,
- const __be32 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)) {
- WARN_ON(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,
- unsigned long 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);
- /* Only thing we need from tcp.h */
- extern int sysctl_tcp_synack_retries;
- /* Decide when to expire the request and when to resend SYN-ACK */
- static inline void syn_ack_recalc(struct request_sock *req, const int thresh,
- const int max_retries,
- const u8 rskq_defer_accept,
- int *expire, int *resend)
- {
- if (!rskq_defer_accept) {
- *expire = req->retrans >= thresh;
- *resend = 1;
- return;
- }
- *expire = req->retrans >= thresh &&
- (!inet_rsk(req)->acked || req->retrans >= max_retries);
- /*
- * Do not resend while waiting for data after ACK,
- * start to resend on end of deferring period to give
- * last chance for data or ACK to create established socket.
- */
- *resend = !inet_rsk(req)->acked ||
- req->retrans >= rskq_defer_accept - 1;
- }
- void inet_csk_reqsk_queue_prune(struct sock *parent,
- const unsigned long interval,
- const unsigned long timeout,
- const unsigned long max_rto)
- {
- struct inet_connection_sock *icsk = inet_csk(parent);
- struct request_sock_queue *queue = &icsk->icsk_accept_queue;
- struct listen_sock *lopt = queue->listen_opt;
- int max_retries = icsk->icsk_syn_retries ? : sysctl_tcp_synack_retries;
- int thresh = max_retries;
- unsigned long now = jiffies;
- struct request_sock **reqp, *req;
- int i, budget;
- if (lopt == NULL || lopt->qlen == 0)
- return;
- /* Normally all the openreqs are young and become mature
- * (i.e. converted to established socket) for first timeout.
- * If synack was not acknowledged for 3 seconds, it means
- * one of the following things: synack was lost, ack was lost,
- * rtt is high or nobody planned to ack (i.e. synflood).
- * When server is a bit loaded, queue is populated with old
- * open requests, reducing effective size of queue.
- * When server is well loaded, queue size reduces to zero
- * after several minutes of work. It is not synflood,
- * it is normal operation. The solution is pruning
- * too old entries overriding normal timeout, when
- * situation becomes dangerous.
- *
- * Essentially, we reserve half of room for young
- * embrions; and abort old ones without pity, if old
- * ones are about to clog our table.
- */
- if (lopt->qlen>>(lopt->max_qlen_log-1)) {
- int young = (lopt->qlen_young<<1);
- while (thresh > 2) {
- if (lopt->qlen < young)
- break;
- thresh--;
- young <<= 1;
- }
- }
- if (queue->rskq_defer_accept)
- max_retries = queue->rskq_defer_accept;
- budget = 2 * (lopt->nr_table_entries / (timeout / interval));
- i = lopt->clock_hand;
- do {
- reqp=&lopt->syn_table[i];
- while ((req = *reqp) != NULL) {
- if (time_after_eq(now, req->expires)) {
- int expire = 0, resend = 0;
- syn_ack_recalc(req, thresh, max_retries,
- queue->rskq_defer_accept,
- &expire, &resend);
- if (req->rsk_ops->syn_ack_timeout)
- req->rsk_ops->syn_ack_timeout(parent, req);
- if (!expire &&
- (!resend ||
- !req->rsk_ops->rtx_syn_ack(parent, req, NULL) ||
- inet_rsk(req)->acked)) {
- unsigned long timeo;
- if (req->retrans++ == 0)
- lopt->qlen_young--;
- timeo = min((timeout << req->retrans), max_rto);
- req->expires = now + timeo;
- reqp = &req->dl_next;
- continue;
- }
- /* Drop this request */
- inet_csk_reqsk_queue_unlink(parent, req, reqp);
- reqsk_queue_removed(queue, req);
- reqsk_free(req);
- continue;
- }
- reqp = &req->dl_next;
- }
- i = (i + 1) & (lopt->nr_table_entries - 1);
- } while (--budget > 0);
- lopt->clock_hand = i;
- if (lopt->qlen)
- inet_csk_reset_keepalive_timer(parent, interval);
- }
- EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_prune);
- /**
- * inet_csk_clone_lock - clone an inet socket, and lock its clone
- * @sk: the socket to clone
- * @req: request_sock
- * @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc)
- *
- * Caller must unlock socket even in error path (bh_unlock_sock(newsk))
- */
- struct sock *inet_csk_clone_lock(const struct sock *sk,
- const struct request_sock *req,
- const gfp_t priority)
- {
- struct sock *newsk = sk_clone_lock(sk, priority);
- if (newsk != NULL) {
- struct inet_connection_sock *newicsk = inet_csk(newsk);
- newsk->sk_state = TCP_SYN_RECV;
- newicsk->icsk_bind_hash = NULL;
- inet_sk(newsk)->inet_dport = inet_rsk(req)->rmt_port;
- inet_sk(newsk)->inet_num = ntohs(inet_rsk(req)->loc_port);
- inet_sk(newsk)->inet_sport = inet_rsk(req)->loc_port;
- newsk->sk_write_space = sk_stream_write_space;
- inet_sk(newsk)->mc_list = NULL;
- newsk->sk_mark = inet_rsk(req)->ir_mark;
- newicsk->icsk_retransmits = 0;
- newicsk->icsk_backoff = 0;
- newicsk->icsk_probes_out = 0;
- /* Deinitialize accept_queue to trap illegal accesses. */
- memset(&newicsk->icsk_accept_queue, 0, sizeof(newicsk->icsk_accept_queue));
- security_inet_csk_clone(newsk, req);
- }
- return newsk;
- }
- EXPORT_SYMBOL_GPL(inet_csk_clone_lock);
- /*
- * At this point, there should be no process reference to this
- * socket, and thus no user references at all. Therefore we
- * can assume the socket waitqueue is inactive and nobody will
- * try to jump onto it.
- */
- void inet_csk_destroy_sock(struct sock *sk)
- {
- WARN_ON(sk->sk_state != TCP_CLOSE);
- WARN_ON(!sock_flag(sk, SOCK_DEAD));
- /* It cannot be in hash table! */
- WARN_ON(!sk_unhashed(sk));
- /* If it has not 0 inet_sk(sk)->inet_num, it must be bound */
- WARN_ON(inet_sk(sk)->inet_num && !inet_csk(sk)->icsk_bind_hash);
- sk->sk_prot->destroy(sk);
- sk_stream_kill_queues(sk);
- xfrm_sk_free_policy(sk);
- sk_refcnt_debug_release(sk);
- percpu_counter_dec(sk->sk_prot->orphan_count);
- sock_put(sk);
- }
- EXPORT_SYMBOL(inet_csk_destroy_sock);
- /* This function allows to force a closure of a socket after the call to
- * tcp/dccp_create_openreq_child().
- */
- void inet_csk_prepare_forced_close(struct sock *sk)
- {
- /* sk_clone_lock locked the socket and set refcnt to 2 */
- bh_unlock_sock(sk);
- sock_put(sk);
- /* The below has to be done to allow calling inet_csk_destroy_sock */
- sock_set_flag(sk, SOCK_DEAD);
- percpu_counter_inc(sk->sk_prot->orphan_count);
- inet_sk(sk)->inet_num = 0;
- }
- EXPORT_SYMBOL(inet_csk_prepare_forced_close);
- int inet_csk_listen_start(struct sock *sk, const int nr_table_entries)
- {
- struct inet_sock *inet = inet_sk(sk);
- struct inet_connection_sock *icsk = inet_csk(sk);
- int rc = reqsk_queue_alloc(&icsk->icsk_accept_queue, nr_table_entries);
- if (rc != 0)
- return rc;
- sk->sk_max_ack_backlog = 0;
- sk->sk_ack_backlog = 0;
- inet_csk_delack_init(sk);
- /* There is race window here: we announce ourselves listening,
- * but this transition is still not validated by get_port().
- * It is OK, because this socket enters to hash table only
- * after validation is complete.
- */
- sk->sk_state = TCP_LISTEN;
- if (!sk->sk_prot->get_port(sk, inet->inet_num)) {
- inet->inet_sport = htons(inet->inet_num);
- sk_dst_reset(sk);
- sk->sk_prot->hash(sk);
- return 0;
- }
- sk->sk_state = TCP_CLOSE;
- __reqsk_queue_destroy(&icsk->icsk_accept_queue);
- return -EADDRINUSE;
- }
- EXPORT_SYMBOL_GPL(inet_csk_listen_start);
- /*
- * This routine closes sockets which have been at least partially
- * opened, but not yet accepted.
- */
- void inet_csk_listen_stop(struct sock *sk)
- {
- struct inet_connection_sock *icsk = inet_csk(sk);
- struct request_sock *acc_req;
- struct request_sock *req;
- inet_csk_delete_keepalive_timer(sk);
- /* make all the listen_opt local to us */
- acc_req = reqsk_queue_yank_acceptq(&icsk->icsk_accept_queue);
- /* Following specs, it would be better either to send FIN
- * (and enter FIN-WAIT-1, it is normal close)
- * or to send active reset (abort).
- * Certainly, it is pretty dangerous while synflood, but it is
- * bad justification for our negligence 8)
- * To be honest, we are not able to make either
- * of the variants now. --ANK
- */
- reqsk_queue_destroy(&icsk->icsk_accept_queue);
- while ((req = acc_req) != NULL) {
- struct sock *child = req->sk;
- acc_req = req->dl_next;
- local_bh_disable();
- bh_lock_sock(child);
- WARN_ON(sock_owned_by_user(child));
- sock_hold(child);
- sk->sk_prot->disconnect(child, O_NONBLOCK);
- sock_orphan(child);
- percpu_counter_inc(sk->sk_prot->orphan_count);
- inet_csk_destroy_sock(child);
- bh_unlock_sock(child);
- local_bh_enable();
- sock_put(child);
- sk_acceptq_removed(sk);
- __reqsk_free(req);
- }
- WARN_ON(sk->sk_ack_backlog);
- }
- EXPORT_SYMBOL_GPL(inet_csk_listen_stop);
- void inet_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr)
- {
- struct sockaddr_in *sin = (struct sockaddr_in *)uaddr;
- const struct inet_sock *inet = inet_sk(sk);
- sin->sin_family = AF_INET;
- sin->sin_addr.s_addr = inet->inet_daddr;
- sin->sin_port = inet->inet_dport;
- }
- EXPORT_SYMBOL_GPL(inet_csk_addr2sockaddr);
- #ifdef CONFIG_COMPAT
- int inet_csk_compat_getsockopt(struct sock *sk, int level, int optname,
- char __user *optval, int __user *optlen)
- {
- const struct inet_connection_sock *icsk = inet_csk(sk);
- if (icsk->icsk_af_ops->compat_getsockopt != NULL)
- return icsk->icsk_af_ops->compat_getsockopt(sk, level, optname,
- optval, optlen);
- return icsk->icsk_af_ops->getsockopt(sk, level, optname,
- optval, optlen);
- }
- EXPORT_SYMBOL_GPL(inet_csk_compat_getsockopt);
- int inet_csk_compat_setsockopt(struct sock *sk, int level, int optname,
- char __user *optval, unsigned int optlen)
- {
- const struct inet_connection_sock *icsk = inet_csk(sk);
- if (icsk->icsk_af_ops->compat_setsockopt != NULL)
- return icsk->icsk_af_ops->compat_setsockopt(sk, level, optname,
- optval, optlen);
- return icsk->icsk_af_ops->setsockopt(sk, level, optname,
- optval, optlen);
- }
- EXPORT_SYMBOL_GPL(inet_csk_compat_setsockopt);
- #endif
|