*
* Implementation of the Transmission Control Protocol(TCP).
*
- * Version: $Id: tcp_minisocks.c,v 1.15 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>
* Jorge Cwik, <jorge@laser.satlink.net>
*/
-#include <linux/config.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/sysctl.h>
#define SYNC_INIT 1
#endif
-int sysctl_tcp_syncookies = SYNC_INIT;
-int sysctl_tcp_abort_on_overflow;
+int sysctl_tcp_syncookies __read_mostly = SYNC_INIT;
+EXPORT_SYMBOL(sysctl_tcp_syncookies);
+
+int sysctl_tcp_abort_on_overflow __read_mostly;
struct inet_timewait_death_row tcp_death_row = {
.sysctl_max_tw_buckets = NR_FILE * 2,
.period = TCP_TIMEWAIT_LEN / INET_TWDR_TWKILL_SLOTS,
- .death_lock = SPIN_LOCK_UNLOCKED,
+ .death_lock = __SPIN_LOCK_UNLOCKED(tcp_death_row.death_lock),
.hashinfo = &tcp_hashinfo,
.tw_timer = TIMER_INITIALIZER(inet_twdr_hangman, 0,
(unsigned long)&tcp_death_row),
.twkill_work = __WORK_INITIALIZER(tcp_death_row.twkill_work,
- inet_twdr_twkill_work,
- &tcp_death_row),
+ inet_twdr_twkill_work),
/* Short-time timewait calendar */
.twcal_hand = -1,
return (seq == e_win && seq == end_seq);
}
-/*
+/*
* * Main purpose of TIME-WAIT state is to close connection gracefully,
* when one of ends sits in LAST-ACK or CLOSING retransmitting FIN
* (and, probably, tail of data) and one or more our ACKs are lost.
tw->tw_substate = TCP_TIME_WAIT;
tcptw->tw_rcv_nxt = TCP_SKB_CB(skb)->end_seq;
if (tmp_opt.saw_tstamp) {
- tcptw->tw_ts_recent_stamp = xtime.tv_sec;
+ tcptw->tw_ts_recent_stamp = get_seconds();
tcptw->tw_ts_recent = tmp_opt.rcv_tsval;
}
* "When a connection is [...] on TIME-WAIT state [...]
* [a TCP] MAY accept a new SYN from the remote TCP to
* reopen the connection directly, if it:
- *
+ *
* (1) assigns its initial sequence number for the new
* connection to be larger than the largest sequence
* number it used on the previous connection incarnation,
* and
*
- * (2) returns to TIME-WAIT state if the SYN turns out
+ * (2) returns to TIME-WAIT state if the SYN turns out
* to be an old duplicate".
*/
if (tmp_opt.saw_tstamp) {
tcptw->tw_ts_recent = tmp_opt.rcv_tsval;
- tcptw->tw_ts_recent_stamp = xtime.tv_sec;
+ tcptw->tw_ts_recent_stamp = get_seconds();
}
inet_twsk_put(tw);
}
if (paws_reject)
- NET_INC_STATS_BH(LINUX_MIB_PAWSESTABREJECTED);
+ NET_INC_STATS_BH(twsk_net(tw), LINUX_MIB_PAWSESTABREJECTED);
- if(!th->rst) {
+ if (!th->rst) {
/* In this case we must reset the TIMEWAIT timer.
*
* If it is ACKless SYN it may be both old duplicate
return TCP_TW_SUCCESS;
}
-/*
+/*
* Move a socket to time-wait or dead fin-wait-2 state.
- */
+ */
void tcp_time_wait(struct sock *sk, int state, int timeo)
{
struct inet_timewait_sock *tw = NULL;
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
if (tw->tw_family == PF_INET6) {
struct ipv6_pinfo *np = inet6_sk(sk);
- struct tcp6_timewait_sock *tcp6tw = tcp6_twsk((struct sock *)tw);
+ struct inet6_timewait_sock *tw6;
- ipv6_addr_copy(&tcp6tw->tw_v6_daddr, &np->daddr);
- ipv6_addr_copy(&tcp6tw->tw_v6_rcv_saddr, &np->rcv_saddr);
+ tw->tw_ipv6_offset = inet6_tw_offset(sk->sk_prot);
+ tw6 = inet6_twsk((struct sock *)tw);
+ ipv6_addr_copy(&tw6->tw_v6_daddr, &np->daddr);
+ ipv6_addr_copy(&tw6->tw_v6_rcv_saddr, &np->rcv_saddr);
tw->tw_ipv6only = np->ipv6only;
}
#endif
+
+#ifdef CONFIG_TCP_MD5SIG
+ /*
+ * The timewait bucket does not have the key DB from the
+ * sock structure. We just make a quick copy of the
+ * md5 key being used (if indeed we are using one)
+ * so the timewait ack generating code has the key.
+ */
+ do {
+ struct tcp_md5sig_key *key;
+ memset(tcptw->tw_md5_key, 0, sizeof(tcptw->tw_md5_key));
+ tcptw->tw_md5_keylen = 0;
+ key = tp->af_specific->md5_lookup(sk, sk);
+ if (key != NULL) {
+ memcpy(&tcptw->tw_md5_key, key->key, key->keylen);
+ tcptw->tw_md5_keylen = key->keylen;
+ if (tcp_alloc_md5sig_pool() == NULL)
+ BUG();
+ }
+ } while (0);
+#endif
+
/* Linkage updates. */
__inet_twsk_hashdance(tw, sk, &tcp_hashinfo);
* socket up. We've got bigger problems than
* non-graceful socket closings.
*/
- if (net_ratelimit())
- printk(KERN_INFO "TCP: time wait bucket table overflow\n");
+ LIMIT_NETDEBUG(KERN_INFO "TCP: time wait bucket table overflow\n");
}
tcp_update_metrics(sk);
tcp_done(sk);
}
+void tcp_twsk_destructor(struct sock *sk)
+{
+#ifdef CONFIG_TCP_MD5SIG
+ struct tcp_timewait_sock *twsk = tcp_twsk(sk);
+ if (twsk->tw_md5_keylen)
+ tcp_put_md5sig_pool();
+#endif
+}
+
+EXPORT_SYMBOL_GPL(tcp_twsk_destructor);
+
+static inline void TCP_ECN_openreq_child(struct tcp_sock *tp,
+ struct request_sock *req)
+{
+ tp->ecn_flags = inet_rsk(req)->ecn_ok ? TCP_ECN_OK : 0;
+}
+
/* This is not only more efficient than what we used to do, it eliminates
* a lot of code duplication between IPv4/IPv6 SYN recv processing. -DaveM
*
if (newsk != NULL) {
const struct inet_request_sock *ireq = inet_rsk(req);
struct tcp_request_sock *treq = tcp_rsk(req);
- struct inet_connection_sock *newicsk = inet_csk(sk);
+ struct inet_connection_sock *newicsk = inet_csk(newsk);
struct tcp_sock *newtp;
/* Now setup tcp_sock */
newtp = tcp_sk(newsk);
newtp->pred_flags = 0;
- newtp->rcv_nxt = treq->rcv_isn + 1;
- newtp->snd_nxt = newtp->snd_una = newtp->snd_sml = treq->snt_isn + 1;
+ newtp->rcv_wup = newtp->copied_seq = newtp->rcv_nxt = treq->rcv_isn + 1;
+ newtp->snd_sml = newtp->snd_una = newtp->snd_nxt = treq->snt_isn + 1;
tcp_prequeue_init(newtp);
newicsk->icsk_rto = TCP_TIMEOUT_INIT;
newtp->packets_out = 0;
- newtp->left_out = 0;
newtp->retrans_out = 0;
newtp->sacked_out = 0;
newtp->fackets_out = 0;
tcp_set_ca_state(newsk, TCP_CA_Open);
tcp_init_xmit_timers(newsk);
skb_queue_head_init(&newtp->out_of_order_queue);
- newtp->rcv_wup = treq->rcv_isn + 1;
newtp->write_seq = treq->snt_isn + 1;
newtp->pushed_seq = newtp->write_seq;
- newtp->copied_seq = treq->rcv_isn + 1;
newtp->rx_opt.saw_tstamp = 0;
keepalive_time_when(newtp));
newtp->rx_opt.tstamp_ok = ireq->tstamp_ok;
- if((newtp->rx_opt.sack_ok = ireq->sack_ok) != 0) {
+ if ((newtp->rx_opt.sack_ok = ireq->sack_ok) != 0) {
if (sysctl_tcp_fack)
- newtp->rx_opt.sack_ok |= 2;
+ tcp_enable_fack(newtp);
}
newtp->window_clamp = req->window_clamp;
newtp->rcv_ssthresh = req->rcv_wnd;
newtp->rx_opt.snd_wscale = newtp->rx_opt.rcv_wscale = 0;
newtp->window_clamp = min(newtp->window_clamp, 65535U);
}
- newtp->snd_wnd = ntohs(skb->h.th->window) << newtp->rx_opt.snd_wscale;
+ newtp->snd_wnd = (ntohs(tcp_hdr(skb)->window) <<
+ newtp->rx_opt.snd_wscale);
newtp->max_window = newtp->snd_wnd;
if (newtp->rx_opt.tstamp_ok) {
newtp->rx_opt.ts_recent = req->ts_recent;
- newtp->rx_opt.ts_recent_stamp = xtime.tv_sec;
+ newtp->rx_opt.ts_recent_stamp = get_seconds();
newtp->tcp_header_len = sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED;
} else {
newtp->rx_opt.ts_recent_stamp = 0;
newtp->tcp_header_len = sizeof(struct tcphdr);
}
+#ifdef CONFIG_TCP_MD5SIG
+ newtp->md5sig_info = NULL; /*XXX*/
+ if (newtp->af_specific->md5_lookup(sk, newsk))
+ newtp->tcp_header_len += TCPOLEN_MD5SIG_ALIGNED;
+#endif
if (skb->len >= TCP_MIN_RCVMSS+newtp->tcp_header_len)
newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len;
newtp->rx_opt.mss_clamp = req->mss;
TCP_ECN_openreq_child(newtp, req);
- if (newtp->ecn_flags&TCP_ECN_OK)
- sock_set_flag(newsk, SOCK_NO_LARGESEND);
- TCP_INC_STATS_BH(TCP_MIB_PASSIVEOPENS);
+ TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_PASSIVEOPENS);
}
return newsk;
}
-/*
+/*
* Process an incoming packet for SYN_RECV sockets represented
* as a request_sock.
*/
struct request_sock *req,
struct request_sock **prev)
{
- struct tcphdr *th = skb->h.th;
- u32 flg = tcp_flag_word(th) & (TCP_FLAG_RST|TCP_FLAG_SYN|TCP_FLAG_ACK);
+ const struct tcphdr *th = tcp_hdr(skb);
+ __be32 flg = tcp_flag_word(th) & (TCP_FLAG_RST|TCP_FLAG_SYN|TCP_FLAG_ACK);
int paws_reject = 0;
struct tcp_options_received tmp_opt;
struct sock *child;
* it can be estimated (approximately)
* from another data.
*/
- tmp_opt.ts_recent_stamp = xtime.tv_sec - ((TCP_TIMEOUT_INIT/HZ)<<req->retrans);
+ tmp_opt.ts_recent_stamp = get_seconds() - ((TCP_TIMEOUT_INIT/HZ)<<req->retrans);
paws_reject = tcp_paws_check(&tmp_opt, th->rst);
}
}
* Enforce "SYN-ACK" according to figure 8, figure 6
* of RFC793, fixed by RFC1122.
*/
- req->rsk_ops->rtx_syn_ack(sk, req, NULL);
+ req->rsk_ops->rtx_syn_ack(sk, req);
return NULL;
}
if (!(flg & TCP_FLAG_RST))
req->rsk_ops->send_ack(skb, req);
if (paws_reject)
- NET_INC_STATS_BH(LINUX_MIB_PAWSESTABREJECTED);
+ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED);
return NULL;
}
/* RFC793: "second check the RST bit" and
* "fourth, check the SYN bit"
*/
- if (flg & (TCP_FLAG_RST|TCP_FLAG_SYN))
+ if (flg & (TCP_FLAG_RST|TCP_FLAG_SYN)) {
+ TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_ATTEMPTFAILS);
goto embryonic_reset;
+ }
/* ACK sequence verified above, just make sure ACK is
* set. If ACK not set, just silently drop the packet.
req, NULL);
if (child == NULL)
goto listen_overflow;
+#ifdef CONFIG_TCP_MD5SIG
+ else {
+ /* Copy over the MD5 key from the original socket */
+ struct tcp_md5sig_key *key;
+ struct tcp_sock *tp = tcp_sk(sk);
+ key = tp->af_specific->md5_lookup(sk, child);
+ if (key != NULL) {
+ /*
+ * We're using one, so create a matching key on the
+ * newsk structure. If we fail to get memory then we
+ * end up not copying the key across. Shucks.
+ */
+ char *newkey = kmemdup(key->key, key->keylen,
+ GFP_ATOMIC);
+ if (newkey) {
+ if (!tcp_alloc_md5sig_pool())
+ BUG();
+ tp->af_specific->md5_add(child, child,
+ newkey,
+ key->keylen);
+ }
+ }
+ }
+#endif
inet_csk_reqsk_queue_unlink(sk, req, prev);
inet_csk_reqsk_queue_removed(sk, req);
}
embryonic_reset:
- NET_INC_STATS_BH(LINUX_MIB_EMBRYONICRSTS);
+ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_EMBRYONICRSTS);
if (!(flg & TCP_FLAG_RST))
- req->rsk_ops->send_reset(skb);
+ req->rsk_ops->send_reset(sk, skb);
inet_csk_reqsk_queue_drop(sk, req, prev);
return NULL;
int state = child->sk_state;
if (!sock_owned_by_user(child)) {
- ret = tcp_rcv_state_process(child, skb, skb->h.th, skb->len);
-
+ ret = tcp_rcv_state_process(child, skb, tcp_hdr(skb),
+ skb->len);
/* Wakeup parent, send SIGIO */
if (state == TCP_SYN_RECV && child->sk_state != state)
parent->sk_data_ready(parent, 0);