*
* Implementation of the Transmission Control Protocol(TCP).
*
- * Version: $Id: tcp_timer.c,v 1.88 2002/02/01 22:01:04 davem Exp $
- *
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Mark Evans, <evansmp@uhura.aston.ac.uk>
#include <linux/module.h>
#include <net/tcp.h>
-int sysctl_tcp_syn_retries = TCP_SYN_RETRIES;
-int sysctl_tcp_synack_retries = TCP_SYNACK_RETRIES;
-int sysctl_tcp_keepalive_time = TCP_KEEPALIVE_TIME;
-int sysctl_tcp_keepalive_probes = TCP_KEEPALIVE_PROBES;
-int sysctl_tcp_keepalive_intvl = TCP_KEEPALIVE_INTVL;
-int sysctl_tcp_retries1 = TCP_RETR1;
-int sysctl_tcp_retries2 = TCP_RETR2;
-int sysctl_tcp_orphan_retries;
+int sysctl_tcp_syn_retries __read_mostly = TCP_SYN_RETRIES;
+int sysctl_tcp_synack_retries __read_mostly = TCP_SYNACK_RETRIES;
+int sysctl_tcp_keepalive_time __read_mostly = TCP_KEEPALIVE_TIME;
+int sysctl_tcp_keepalive_probes __read_mostly = TCP_KEEPALIVE_PROBES;
+int sysctl_tcp_keepalive_intvl __read_mostly = TCP_KEEPALIVE_INTVL;
+int sysctl_tcp_retries1 __read_mostly = TCP_RETR1;
+int sysctl_tcp_retries2 __read_mostly = TCP_RETR2;
+int sysctl_tcp_orphan_retries __read_mostly;
static void tcp_write_timer(unsigned long);
static void tcp_delack_timer(unsigned long);
sk->sk_error_report(sk);
tcp_done(sk);
- NET_INC_STATS_BH(LINUX_MIB_TCPABORTONTIMEOUT);
+ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPABORTONTIMEOUT);
}
/* Do not allow orphaned sockets to eat all our resources.
* to prevent DoS attacks. It is called when a retransmission timeout
* or zero probe timeout occurs on orphaned socket.
*
- * Criterium is still not confirmed experimentally and may change.
+ * Criteria is still not confirmed experimentally and may change.
* We kill the socket, if:
* 1. If number of orphaned sockets exceeds an administratively configured
* limit.
static int tcp_out_of_resources(struct sock *sk, int do_reset)
{
struct tcp_sock *tp = tcp_sk(sk);
- int orphans = atomic_read(&tcp_orphan_count);
+ int orphans = percpu_counter_read_positive(&tcp_orphan_count);
- /* If peer does not open window for long time, or did not transmit
+ /* If peer does not open window for long time, or did not transmit
* anything for long time, penalize it. */
if ((s32)(tcp_time_stamp - tp->lsndtime) > 2*TCP_RTO_MAX || !do_reset)
orphans <<= 1;
if (sk->sk_err_soft)
orphans <<= 1;
- if (orphans >= sysctl_tcp_max_orphans ||
- (sk->sk_wmem_queued > SOCK_MIN_SNDBUF &&
- atomic_read(&tcp_memory_allocated) > sysctl_tcp_mem[2])) {
+ if (tcp_too_many_orphans(sk, orphans)) {
if (net_ratelimit())
printk(KERN_INFO "Out of socket memory\n");
if (do_reset)
tcp_send_active_reset(sk, GFP_ATOMIC);
tcp_done(sk);
- NET_INC_STATS_BH(LINUX_MIB_TCPABORTONMEMORY);
+ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY);
return 1;
}
return 0;
return retries;
}
+static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk)
+{
+ /* Black hole detection */
+ if (sysctl_tcp_mtu_probing) {
+ if (!icsk->icsk_mtup.enabled) {
+ icsk->icsk_mtup.enabled = 1;
+ tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
+ } else {
+ struct tcp_sock *tp = tcp_sk(sk);
+ int mss;
+
+ mss = tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low) >> 1;
+ mss = min(sysctl_tcp_base_mss, mss);
+ mss = max(mss, 68 - tp->tcp_header_len);
+ icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss);
+ tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
+ }
+ }
+}
+
/* A write timeout has occurred. Process the after effects. */
static int tcp_write_timeout(struct sock *sk)
{
- const struct inet_connection_sock *icsk = inet_csk(sk);
+ struct inet_connection_sock *icsk = inet_csk(sk);
int retry_until;
if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
retry_until = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries;
} else {
if (icsk->icsk_retransmits >= sysctl_tcp_retries1) {
- /* NOTE. draft-ietf-tcpimpl-pmtud-01.txt requires pmtu black
- hole detection. :-(
-
- It is place to make it. It is not made. I do not want
- to make it. It is disguisting. It does not work in any
- case. Let me to cite the same draft, which requires for
- us to implement this:
-
- "The one security concern raised by this memo is that ICMP black holes
- are often caused by over-zealous security administrators who block
- all ICMP messages. It is vitally important that those who design and
- deploy security systems understand the impact of strict filtering on
- upper-layer protocols. The safest web site in the world is worthless
- if most TCP implementations cannot transfer data from it. It would
- be far nicer to have all of the black holes fixed rather than fixing
- all of the TCP implementations."
-
- Golden words :-).
- */
+ /* Black hole detection */
+ tcp_mtu_probing(icsk, sk);
dst_negative_advice(&sk->sk_dst_cache);
}
retry_until = sysctl_tcp_retries2;
if (sock_flag(sk, SOCK_DEAD)) {
const int alive = (icsk->icsk_rto < TCP_RTO_MAX);
-
+
retry_until = tcp_orphan_retries(sk, alive);
if (tcp_out_of_resources(sk, alive || icsk->icsk_retransmits < retry_until))
static void tcp_delack_timer(unsigned long data)
{
- struct sock *sk = (struct sock*)data;
+ struct sock *sk = (struct sock *)data;
struct tcp_sock *tp = tcp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
if (sock_owned_by_user(sk)) {
/* Try again later. */
icsk->icsk_ack.blocked = 1;
- NET_INC_STATS_BH(LINUX_MIB_DELAYEDACKLOCKED);
+ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_DELAYEDACKLOCKED);
sk_reset_timer(sk, &icsk->icsk_delack_timer, jiffies + TCP_DELACK_MIN);
goto out_unlock;
}
- sk_stream_mem_reclaim(sk);
+ sk_mem_reclaim_partial(sk);
if (sk->sk_state == TCP_CLOSE || !(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
goto out;
if (!skb_queue_empty(&tp->ucopy.prequeue)) {
struct sk_buff *skb;
- NET_INC_STATS_BH(LINUX_MIB_TCPSCHEDULERFAILED);
+ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSCHEDULERFAILED);
while ((skb = __skb_dequeue(&tp->ucopy.prequeue)) != NULL)
- sk->sk_backlog_rcv(sk, skb);
+ sk_backlog_rcv(sk, skb);
tp->ucopy.memory = 0;
}
icsk->icsk_ack.ato = TCP_ATO_MIN;
}
tcp_send_ack(sk);
- NET_INC_STATS_BH(LINUX_MIB_DELAYEDACKS);
+ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_DELAYEDACKS);
}
TCP_CHECK_TIMER(sk);
out:
if (tcp_memory_pressure)
- sk_stream_mem_reclaim(sk);
+ sk_mem_reclaim(sk);
out_unlock:
bh_unlock_sock(sk);
sock_put(sk);
static void tcp_probe_timer(struct sock *sk)
{
+ struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
int max_probes;
- if (tp->packets_out || !sk->sk_send_head) {
- tp->probes_out = 0;
+ if (tp->packets_out || !tcp_send_head(sk)) {
+ icsk->icsk_probes_out = 0;
return;
}
* FIXME: We ought not to do it, Solaris 2.5 actually has fixing
* this behaviour in Solaris down as a bug fix. [AC]
*
- * Let me to explain. probes_out is zeroed by incoming ACKs
+ * Let me to explain. icsk_probes_out is zeroed by incoming ACKs
* even if they advertise zero window. Hence, connection is killed only
* if we received no ACKs for normal connection timeout. It is not killed
* only because window stays zero for some time, window may be zero
max_probes = sysctl_tcp_retries2;
if (sock_flag(sk, SOCK_DEAD)) {
- const struct inet_connection_sock *icsk = inet_csk(sk);
const int alive = ((icsk->icsk_rto << icsk->icsk_backoff) < TCP_RTO_MAX);
-
+
max_probes = tcp_orphan_retries(sk, alive);
- if (tcp_out_of_resources(sk, alive || tp->probes_out <= max_probes))
+ if (tcp_out_of_resources(sk, alive || icsk->icsk_probes_out <= max_probes))
return;
}
- if (tp->probes_out > max_probes) {
+ if (icsk->icsk_probes_out > max_probes) {
tcp_write_err(sk);
} else {
/* Only send another probe if we didn't close things up. */
if (!tp->packets_out)
goto out;
- BUG_TRAP(!skb_queue_empty(&sk->sk_write_queue));
+ WARN_ON(tcp_write_queue_empty(sk));
if (!tp->snd_wnd && !sock_flag(sk, SOCK_DEAD) &&
!((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))) {
* we cannot allow such beasts to hang infinitely.
*/
#ifdef TCP_DEBUG
- if (net_ratelimit()) {
- struct inet_sock *inet = inet_sk(sk);
- printk(KERN_DEBUG "TCP: Treason uncloaked! Peer %u.%u.%u.%u:%u/%u shrinks window %u:%u. Repaired.\n",
- NIPQUAD(inet->daddr), htons(inet->dport),
+ struct inet_sock *inet = inet_sk(sk);
+ if (sk->sk_family == AF_INET) {
+ LIMIT_NETDEBUG(KERN_DEBUG "TCP: Peer %pI4:%u/%u unexpectedly shrunk window %u:%u (repaired)\n",
+ &inet->daddr, ntohs(inet->dport),
inet->num, tp->snd_una, tp->snd_nxt);
}
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+ else if (sk->sk_family == AF_INET6) {
+ struct ipv6_pinfo *np = inet6_sk(sk);
+ LIMIT_NETDEBUG(KERN_DEBUG "TCP: Peer %pI6:%u/%u unexpectedly shrunk window %u:%u (repaired)\n",
+ &np->daddr, ntohs(inet->dport),
+ inet->num, tp->snd_una, tp->snd_nxt);
+ }
+#endif
#endif
if (tcp_time_stamp - tp->rcv_tstamp > TCP_RTO_MAX) {
tcp_write_err(sk);
goto out;
}
tcp_enter_loss(sk, 0);
- tcp_retransmit_skb(sk, skb_peek(&sk->sk_write_queue));
+ tcp_retransmit_skb(sk, tcp_write_queue_head(sk));
__sk_dst_reset(sk);
goto out_reset_timer;
}
goto out;
if (icsk->icsk_retransmits == 0) {
- if (tp->ca_state == TCP_CA_Disorder || tp->ca_state == TCP_CA_Recovery) {
- if (tp->rx_opt.sack_ok) {
- if (tp->ca_state == TCP_CA_Recovery)
- NET_INC_STATS_BH(LINUX_MIB_TCPSACKRECOVERYFAIL);
- else
- NET_INC_STATS_BH(LINUX_MIB_TCPSACKFAILURES);
- } else {
- if (tp->ca_state == TCP_CA_Recovery)
- NET_INC_STATS_BH(LINUX_MIB_TCPRENORECOVERYFAIL);
- else
- NET_INC_STATS_BH(LINUX_MIB_TCPRENOFAILURES);
- }
- } else if (tp->ca_state == TCP_CA_Loss) {
- NET_INC_STATS_BH(LINUX_MIB_TCPLOSSFAILURES);
+ int mib_idx;
+
+ if (icsk->icsk_ca_state == TCP_CA_Disorder) {
+ if (tcp_is_sack(tp))
+ mib_idx = LINUX_MIB_TCPSACKFAILURES;
+ else
+ mib_idx = LINUX_MIB_TCPRENOFAILURES;
+ } else if (icsk->icsk_ca_state == TCP_CA_Recovery) {
+ if (tcp_is_sack(tp))
+ mib_idx = LINUX_MIB_TCPSACKRECOVERYFAIL;
+ else
+ mib_idx = LINUX_MIB_TCPRENORECOVERYFAIL;
+ } else if (icsk->icsk_ca_state == TCP_CA_Loss) {
+ mib_idx = LINUX_MIB_TCPLOSSFAILURES;
} else {
- NET_INC_STATS_BH(LINUX_MIB_TCPTIMEOUTS);
+ mib_idx = LINUX_MIB_TCPTIMEOUTS;
}
+ NET_INC_STATS_BH(sock_net(sk), mib_idx);
}
if (tcp_use_frto(sk)) {
tcp_enter_loss(sk, 0);
}
- if (tcp_retransmit_skb(sk, skb_peek(&sk->sk_write_queue)) > 0) {
+ if (tcp_retransmit_skb(sk, tcp_write_queue_head(sk)) > 0) {
/* Retransmission failed because of local congestion,
* do not backoff.
*/
static void tcp_write_timer(unsigned long data)
{
- struct sock *sk = (struct sock*)data;
+ struct sock *sk = (struct sock *)data;
struct inet_connection_sock *icsk = inet_csk(sk);
int event;
TCP_CHECK_TIMER(sk);
out:
- sk_stream_mem_reclaim(sk);
+ sk_mem_reclaim(sk);
out_unlock:
bh_unlock_sock(sk);
sock_put(sk);
}
-void reqsk_queue_prune(struct request_sock_queue *queue, struct sock *parent,
- const unsigned long interval, const unsigned long timeout,
- const unsigned long max_rto, int max_retries)
-{
- struct inet_connection_sock *icsk = inet_csk(parent);
- struct listen_sock *lopt = queue->listen_opt;
- 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)) {
- if ((req->retrans < thresh ||
- (inet_rsk(req)->acked && req->retrans < max_retries))
- && !req->rsk_ops->rtx_syn_ack(parent, req, NULL)) {
- 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(&icsk->icsk_accept_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(reqsk_queue_prune);
-
/*
* Timer for listening sockets
*/
static void tcp_synack_timer(struct sock *sk)
{
- struct inet_connection_sock *icsk = inet_csk(sk);
- const int max_retries = icsk->icsk_syn_retries ? : sysctl_tcp_synack_retries;
-
- reqsk_queue_prune(&icsk->icsk_accept_queue, sk, TCP_SYNQ_INTERVAL,
- TCP_TIMEOUT_INIT, TCP_RTO_MAX, max_retries);
+ inet_csk_reqsk_queue_prune(sk, TCP_SYNQ_INTERVAL,
+ TCP_TIMEOUT_INIT, TCP_RTO_MAX);
}
void tcp_set_keepalive(struct sock *sk, int val)
static void tcp_keepalive_timer (unsigned long data)
{
struct sock *sk = (struct sock *) data;
+ struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
__u32 elapsed;
/* Only process if socket is not in use. */
bh_lock_sock(sk);
if (sock_owned_by_user(sk)) {
- /* Try again later. */
+ /* Try again later. */
inet_csk_reset_keepalive_timer (sk, HZ/20);
goto out;
}
elapsed = keepalive_time_when(tp);
/* It is alive without keepalive 8) */
- if (tp->packets_out || sk->sk_send_head)
+ if (tp->packets_out || tcp_send_head(sk))
goto resched;
elapsed = tcp_time_stamp - tp->rcv_tstamp;
if (elapsed >= keepalive_time_when(tp)) {
- if ((!tp->keepalive_probes && tp->probes_out >= sysctl_tcp_keepalive_probes) ||
- (tp->keepalive_probes && tp->probes_out >= tp->keepalive_probes)) {
+ if ((!tp->keepalive_probes && icsk->icsk_probes_out >= sysctl_tcp_keepalive_probes) ||
+ (tp->keepalive_probes && icsk->icsk_probes_out >= tp->keepalive_probes)) {
tcp_send_active_reset(sk, GFP_ATOMIC);
tcp_write_err(sk);
goto out;
}
if (tcp_write_wakeup(sk) <= 0) {
- tp->probes_out++;
+ icsk->icsk_probes_out++;
elapsed = keepalive_intvl_when(tp);
} else {
/* If keepalive was lost due to local congestion,
}
TCP_CHECK_TIMER(sk);
- sk_stream_mem_reclaim(sk);
+ sk_mem_reclaim(sk);
resched:
inet_csk_reset_keepalive_timer (sk, elapsed);
goto out;
-death:
+death:
tcp_done(sk);
out: