* 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/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";
#endif
/*
- * This array holds the first and last local port number.
- * For high-usage systems, use sysctl to change this to
- * 32768-61000
+ * This struct holds the first and last local port number.
*/
-int sysctl_local_port_range[2] = { 1024, 4999 };
+struct local_ports sysctl_local_ports __read_mostly = {
+ .lock = SEQLOCK_UNLOCKED,
+ .range = { 32768, 61000 },
+};
-static inline int inet_csk_bind_conflict(struct sock *sk, struct inet_bind_bucket *tb)
+unsigned long *sysctl_local_reserved_ports;
+EXPORT_SYMBOL(sysctl_local_reserved_ports);
+
+void inet_get_local_port_range(int *low, int *high)
+{
+ unsigned 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)
{
- const u32 sk_rcv_saddr = inet_rcv_saddr(sk);
+ const __be32 sk_rcv_saddr = inet_rcv_saddr(sk);
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)) {
if (!reuse || !sk2->sk_reuse ||
sk2->sk_state == TCP_LISTEN) {
- const u32 sk2_rcv_saddr = inet_rcv_saddr(sk2);
+ const __be32 sk2_rcv_saddr = inet_rcv_saddr(sk2);
if (!sk2_rcv_saddr || !sk_rcv_saddr ||
sk2_rcv_saddr == sk_rcv_saddr)
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 inet_hashinfo *hashinfo,
- struct sock *sk, unsigned short snum)
+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;
+ int ret, attempts = 5;
+ struct net *net = sock_net(sk);
+ int smallest_size = -1, smallest_rover;
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;
+ 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 {
- rover++;
- if (rover > high)
- rover = low;
- head = &hashinfo->bhash[inet_bhashfn(rover, hashinfo->bhash_size)];
+ 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 (tb->port == rover)
+ 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) {
+ spin_unlock(&head->lock);
+ snum = smallest_rover;
+ goto have_snum;
+ }
+ }
goto next;
+ }
break;
next:
spin_unlock(&head->lock);
+ next_nolock:
+ if (++rover > high)
+ rover = low;
} 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
* the top level, not from the 'break;' statement.
*/
ret = 1;
- if (remaining <= 0)
+ 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 {
- head = &hashinfo->bhash[inet_bhashfn(snum, hashinfo->bhash_size)];
+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 (tb->port == snum)
+ 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 > 1)
- goto success;
if (tb->fastreuse > 0 &&
- sk->sk_reuse && sk->sk_state != TCP_LISTEN) {
+ sk->sk_reuse && sk->sk_state != TCP_LISTEN &&
+ smallest_size == -1) {
goto success;
} else {
ret = 1;
- if (inet_csk_bind_conflict(sk, tb))
+ 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, head, snum)) == NULL)
+ 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)
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;
+ WARN_ON(inet_csk(sk)->icsk_bind_hash != tb);
+ ret = 0;
fail_unlock:
spin_unlock(&head->lock);
* having to remove and re-insert us on the wait queue.
*/
for (;;) {
- prepare_to_wait_exclusive(sk->sk_sleep, &wait,
+ prepare_to_wait_exclusive(sk_sleep(sk), &wait,
TASK_INTERRUPTIBLE);
release_sock(sk);
if (reqsk_queue_empty(&icsk->icsk_accept_queue))
if (!timeo)
break;
}
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
return err;
}
}
newsk = reqsk_queue_get_child(&icsk->icsk_accept_queue, sk);
- BUG_TRAP(newsk->sk_state != TCP_SYN_RECV);
+ WARN_ON(newsk->sk_state == TCP_SYN_RECV);
out:
release_sock(sk);
return newsk;
/*
* Using different timers for retransmit, delayed acks and probes
- * We may wish use just one timer maintaining a list of expire jiffies
+ * We may wish use just one timer maintaining a list of expire jiffies
* to optimize.
*/
void inet_csk_init_xmit_timers(struct sock *sk,
{
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;
-
+ 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_reset_keepalive_timer);
-struct dst_entry* inet_csk_route_req(struct sock *sk,
+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,
+ .mark = sk->sk_mark,
.nl_u = { .ip4_u =
{ .daddr = ((opt && opt->srr) ?
opt->faddr :
.saddr = ireq->loc_addr,
.tos = RT_CONN_FLAGS(sk) } },
.proto = sk->sk_protocol,
+ .flags = inet_sk_flowi_flags(sk),
.uli_u = { .ports =
- { .sport = inet_sk(sk)->sport,
+ { .sport = inet_sk(sk)->inet_sport,
.dport = ireq->rmt_port } } };
+ struct net *net = sock_net(sk);
- 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;
- }
+ security_req_classify_flow(req, &fl);
+ if (ip_route_output_flow(net, &rt, &fl, sk, 0))
+ goto no_route;
+ if (opt && opt->is_strictroute && rt->rt_dst != rt->rt_gateway)
+ goto route_err;
return &rt->u.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);
-static inline u32 inet_synq_hash(const u32 raddr, const u16 rport,
- const u32 rnd, const u16 synq_hsize)
+static inline u32 inet_synq_hash(const __be32 raddr, const __be16 rport,
+ const u32 rnd, const u32 synq_hsize)
{
- return jhash_2words(raddr, (u32)rport, rnd) & (synq_hsize - 1);
+ return jhash_2words((__force u32)raddr, (__force u32)rport, rnd) & (synq_hsize - 1);
}
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
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 __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;
ireq->rmt_addr == raddr &&
ireq->loc_addr == laddr &&
AF_INET_FAMILY(req->rsk_ops->family)) {
- BUG_TRAP(!req->sk);
+ WARN_ON(req->sk);
*prevp = prev;
break;
}
EXPORT_SYMBOL_GPL(inet_csk_search_req);
void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req,
- const unsigned timeout)
+ unsigned long timeout)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct listen_sock *lopt = icsk->icsk_accept_queue.listen_opt;
inet_csk_reqsk_queue_added(sk, timeout);
}
+/* Only thing we need from tcp.h */
+extern int sysctl_tcp_synack_retries;
+
EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_hash_add);
+
+/* 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);
+
+struct sock *inet_csk_clone(struct sock *sk, const struct request_sock *req,
+ const gfp_t priority)
+{
+ struct sock *newsk = sk_clone(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;
+
+ 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);
+
+/*
+ * 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);
+
+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