#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);
* 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.
struct tcp_sock *tp = tcp_sk(sk);
int orphans = atomic_read(&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");
/* 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);
+ struct tcp_sock *tp = tcp_sk(sk);
int retry_until;
+ int mss;
if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
if (icsk->icsk_retransmits)
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 */
+ if (sysctl_tcp_mtu_probing) {
+ if (!icsk->icsk_mtup.enabled) {
+ icsk->icsk_mtup.enabled = 1;
+ tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
+ } else {
+ mss = min(sysctl_tcp_base_mss,
+ tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low)/2);
+ 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);
+ }
+ }
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_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));
+ BUG_TRAP(!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()) {
+ if (1) {
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),
+ LIMIT_NETDEBUG(KERN_DEBUG "TCP: Treason uncloaked! Peer %u.%u.%u.%u:%u/%u shrinks window %u:%u. Repaired.\n",
+ NIPQUAD(inet->daddr), ntohs(inet->dport),
inet->num, tp->snd_una, tp->snd_nxt);
}
#endif
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)
+ if (icsk->icsk_ca_state == TCP_CA_Disorder ||
+ icsk->icsk_ca_state == TCP_CA_Recovery) {
+ if (tcp_is_sack(tp)) {
+ if (icsk->icsk_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)
+ if (icsk->icsk_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) {
+ } else if (icsk->icsk_ca_state == TCP_CA_Loss) {
NET_INC_STATS_BH(LINUX_MIB_TCPLOSSFAILURES);
} else {
NET_INC_STATS_BH(LINUX_MIB_TCPTIMEOUTS);
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_synack_timer(struct sock *sk)
{
- struct tcp_sock *tp = tcp_sk(sk);
- struct inet_connection_sock *icsk = inet_csk(sk);
- struct listen_sock *lopt = icsk->icsk_accept_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 (tp->defer_accept)
- max_retries = tp->defer_accept;
-
- budget = 2*(TCP_SYNQ_HSIZE/(TCP_TIMEOUT_INIT/TCP_SYNQ_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(sk, req, NULL)) {
- unsigned long timeo;
-
- if (req->retrans++ == 0)
- lopt->qlen_young--;
- timeo = min((TCP_TIMEOUT_INIT << req->retrans),
- TCP_RTO_MAX);
- req->expires = now + timeo;
- reqp = &req->dl_next;
- continue;
- }
-
- /* Drop this request */
- inet_csk_reqsk_queue_unlink(sk, req, reqp);
- reqsk_queue_removed(&icsk->icsk_accept_queue, req);
- reqsk_free(req);
- continue;
- }
- reqp = &req->dl_next;
- }
-
- i = (i+1)&(TCP_SYNQ_HSIZE-1);
-
- } while (--budget > 0);
-
- lopt->clock_hand = i;
-
- if (lopt->qlen)
- inet_csk_reset_keepalive_timer(sk, TCP_SYNQ_INTERVAL);
+ 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,
inet_csk_reset_keepalive_timer (sk, elapsed);
goto out;
-death:
+death:
tcp_done(sk);
out: