linux_dsm_epyc7002/net/ipv4/tcp_minisocks.c

743 lines
23 KiB
C
Raw Normal View History

/*
* 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.
*
* Implementation of the Transmission Control Protocol(TCP).
*
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Mark Evans, <evansmp@uhura.aston.ac.uk>
* Corey Minyard <wf-rch!minyard@relay.EU.net>
* Florian La Roche, <flla@stud.uni-sb.de>
* Charles Hedrick, <hedrick@klinzhai.rutgers.edu>
* Linus Torvalds, <torvalds@cs.helsinki.fi>
* Alan Cox, <gw4pts@gw4pts.ampr.org>
* Matthew Dillon, <dillon@apollo.west.oic.com>
* Arnt Gulbrandsen, <agulbra@nvg.unit.no>
* Jorge Cwik, <jorge@laser.satlink.net>
*/
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/sysctl.h>
#include <linux/workqueue.h>
#include <net/tcp.h>
#include <net/inet_common.h>
#include <net/xfrm.h>
int sysctl_tcp_syncookies __read_mostly = 1;
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(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,
2006-11-22 21:55:48 +07:00
inet_twdr_twkill_work),
/* Short-time timewait calendar */
.twcal_hand = -1,
.twcal_timer = TIMER_INITIALIZER(inet_twdr_twcal_tick, 0,
(unsigned long)&tcp_death_row),
};
EXPORT_SYMBOL_GPL(tcp_death_row);
static __inline__ int tcp_in_window(u32 seq, u32 end_seq, u32 s_win, u32 e_win)
{
if (seq == s_win)
return 1;
if (after(end_seq, s_win) && before(seq, e_win))
return 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.
* * What is TIME-WAIT timeout? It is associated with maximal packet
* lifetime in the internet, which results in wrong conclusion, that
* it is set to catch "old duplicate segments" wandering out of their path.
* It is not quite correct. This timeout is calculated so that it exceeds
* maximal retransmission timeout enough to allow to lose one (or more)
* segments sent by peer and our ACKs. This time may be calculated from RTO.
* * When TIME-WAIT socket receives RST, it means that another end
* finally closed and we are allowed to kill TIME-WAIT too.
* * Second purpose of TIME-WAIT is catching old duplicate segments.
* Well, certainly it is pure paranoia, but if we load TIME-WAIT
* with this semantics, we MUST NOT kill TIME-WAIT state with RSTs.
* * If we invented some more clever way to catch duplicates
* (f.e. based on PAWS), we could truncate TIME-WAIT to several RTOs.
*
* The algorithm below is based on FORMAL INTERPRETATION of RFCs.
* When you compare it to RFCs, please, read section SEGMENT ARRIVES
* from the very beginning.
*
* NOTE. With recycling (and later with fin-wait-2) TW bucket
* is _not_ stateless. It means, that strictly speaking we must
* spinlock it. I do not want! Well, probability of misbehaviour
* is ridiculously low and, seems, we could use some mb() tricks
* to avoid misread sequence numbers, states etc. --ANK
*/
enum tcp_tw_status
tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
const struct tcphdr *th)
{
struct tcp_options_received tmp_opt;
u8 *hash_location;
struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw);
int paws_reject = 0;
tmp_opt.saw_tstamp = 0;
if (th->doff > (sizeof(*th) >> 2) && tcptw->tw_ts_recent_stamp) {
tcp_parse_options(skb, &tmp_opt, &hash_location, 0);
if (tmp_opt.saw_tstamp) {
tmp_opt.ts_recent = tcptw->tw_ts_recent;
tmp_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp;
paws_reject = tcp_paws_reject(&tmp_opt, th->rst);
}
}
if (tw->tw_substate == TCP_FIN_WAIT2) {
/* Just repeat all the checks of tcp_rcv_state_process() */
/* Out of window, send ACK */
if (paws_reject ||
!tcp_in_window(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq,
tcptw->tw_rcv_nxt,
tcptw->tw_rcv_nxt + tcptw->tw_rcv_wnd))
return TCP_TW_ACK;
if (th->rst)
goto kill;
if (th->syn && !before(TCP_SKB_CB(skb)->seq, tcptw->tw_rcv_nxt))
goto kill_with_rst;
/* Dup ACK? */
if (!th->ack ||
!after(TCP_SKB_CB(skb)->end_seq, tcptw->tw_rcv_nxt) ||
TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq) {
inet_twsk_put(tw);
return TCP_TW_SUCCESS;
}
/* New data or FIN. If new data arrive after half-duplex close,
* reset.
*/
if (!th->fin ||
TCP_SKB_CB(skb)->end_seq != tcptw->tw_rcv_nxt + 1) {
kill_with_rst:
inet_twsk_deschedule(tw, &tcp_death_row);
inet_twsk_put(tw);
return TCP_TW_RST;
}
/* FIN arrived, enter true time-wait state. */
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 = get_seconds();
tcptw->tw_ts_recent = tmp_opt.rcv_tsval;
}
/* I am shamed, but failed to make it more elegant.
* Yes, it is direct reference to IP, which is impossible
* to generalize to IPv6. Taking into account that IPv6
* do not understand recycling in any case, it not
* a big problem in practice. --ANK */
if (tw->tw_family == AF_INET &&
tcp_death_row.sysctl_tw_recycle && tcptw->tw_ts_recent_stamp &&
tcp_v4_tw_remember_stamp(tw))
inet_twsk_schedule(tw, &tcp_death_row, tw->tw_timeout,
TCP_TIMEWAIT_LEN);
else
inet_twsk_schedule(tw, &tcp_death_row, TCP_TIMEWAIT_LEN,
TCP_TIMEWAIT_LEN);
return TCP_TW_ACK;
}
/*
* Now real TIME-WAIT state.
*
* RFC 1122:
* "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
* to be an old duplicate".
*/
if (!paws_reject &&
(TCP_SKB_CB(skb)->seq == tcptw->tw_rcv_nxt &&
(TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq || th->rst))) {
/* In window segment, it may be only reset or bare ack. */
if (th->rst) {
/* This is TIME_WAIT assassination, in two flavors.
* Oh well... nobody has a sufficient solution to this
* protocol bug yet.
*/
if (sysctl_tcp_rfc1337 == 0) {
kill:
inet_twsk_deschedule(tw, &tcp_death_row);
inet_twsk_put(tw);
return TCP_TW_SUCCESS;
}
}
inet_twsk_schedule(tw, &tcp_death_row, TCP_TIMEWAIT_LEN,
TCP_TIMEWAIT_LEN);
if (tmp_opt.saw_tstamp) {
tcptw->tw_ts_recent = tmp_opt.rcv_tsval;
tcptw->tw_ts_recent_stamp = get_seconds();
}
inet_twsk_put(tw);
return TCP_TW_SUCCESS;
}
/* Out of window segment.
All the segments are ACKed immediately.
The only exception is new SYN. We accept it, if it is
not old duplicate and we are not in danger to be killed
by delayed old duplicates. RFC check is that it has
newer sequence number works at rates <40Mbit/sec.
However, if paws works, it is reliable AND even more,
we even may relax silly seq space cutoff.
RED-PEN: we violate main RFC requirement, if this SYN will appear
old duplicate (i.e. we receive RST in reply to SYN-ACK),
we must return socket to time-wait state. It is not good,
but not fatal yet.
*/
if (th->syn && !th->rst && !th->ack && !paws_reject &&
(after(TCP_SKB_CB(skb)->seq, tcptw->tw_rcv_nxt) ||
(tmp_opt.saw_tstamp &&
(s32)(tcptw->tw_ts_recent - tmp_opt.rcv_tsval) < 0))) {
u32 isn = tcptw->tw_snd_nxt + 65535 + 2;
if (isn == 0)
isn++;
TCP_SKB_CB(skb)->when = isn;
return TCP_TW_SYN;
}
if (paws_reject)
NET_INC_STATS_BH(twsk_net(tw), LINUX_MIB_PAWSESTABREJECTED);
if (!th->rst) {
/* In this case we must reset the TIMEWAIT timer.
*
* If it is ACKless SYN it may be both old duplicate
* and new good SYN with random sequence number <rcv_nxt.
* Do not reschedule in the last case.
*/
if (paws_reject || th->ack)
inet_twsk_schedule(tw, &tcp_death_row, TCP_TIMEWAIT_LEN,
TCP_TIMEWAIT_LEN);
/* Send ACK. Note, we do not put the bucket,
* it will be released by caller.
*/
return TCP_TW_ACK;
}
inet_twsk_put(tw);
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;
const struct inet_connection_sock *icsk = inet_csk(sk);
const struct tcp_sock *tp = tcp_sk(sk);
int recycle_ok = 0;
if (tcp_death_row.sysctl_tw_recycle && tp->rx_opt.ts_recent_stamp)
recycle_ok = icsk->icsk_af_ops->remember_stamp(sk);
if (tcp_death_row.tw_count < tcp_death_row.sysctl_max_tw_buckets)
tw = inet_twsk_alloc(sk, state);
if (tw != NULL) {
struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw);
const int rto = (icsk->icsk_rto << 2) - (icsk->icsk_rto >> 1);
tw->tw_rcv_wscale = tp->rx_opt.rcv_wscale;
tcptw->tw_rcv_nxt = tp->rcv_nxt;
tcptw->tw_snd_nxt = tp->snd_nxt;
tcptw->tw_rcv_wnd = tcp_receive_window(tp);
tcptw->tw_ts_recent = tp->rx_opt.ts_recent;
tcptw->tw_ts_recent_stamp = tp->rx_opt.ts_recent_stamp;
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
if (tw->tw_family == PF_INET6) {
struct ipv6_pinfo *np = inet6_sk(sk);
struct inet6_timewait_sock *tw6;
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(sk) == NULL)
BUG();
}
} while (0);
#endif
/* Linkage updates. */
__inet_twsk_hashdance(tw, sk, &tcp_hashinfo);
/* Get the TIME_WAIT timeout firing. */
if (timeo < rto)
timeo = rto;
if (recycle_ok) {
tw->tw_timeout = rto;
} else {
tw->tw_timeout = TCP_TIMEWAIT_LEN;
if (state == TCP_TIME_WAIT)
timeo = TCP_TIMEWAIT_LEN;
}
inet_twsk_schedule(tw, &tcp_death_row, timeo,
TCP_TIMEWAIT_LEN);
inet_twsk_put(tw);
} else {
/* Sorry, if we're out of memory, just CLOSE this
* socket up. We've got bigger problems than
* non-graceful socket closings.
*/
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_free_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
*
* Actually, we could lots of memory writes here. tp of listening
* socket contains all necessary default parameters.
*/
struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, struct sk_buff *skb)
{
struct sock *newsk = inet_csk_clone(sk, req, GFP_ATOMIC);
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(newsk);
TCPCT part 1d: define TCP cookie option, extend existing struct's Data structures are carefully composed to require minimal additions. For example, the struct tcp_options_received cookie_plus variable fits between existing 16-bit and 8-bit variables, requiring no additional space (taking alignment into consideration). There are no additions to tcp_request_sock, and only 1 pointer in tcp_sock. This is a significantly revised implementation of an earlier (year-old) patch that no longer applies cleanly, with permission of the original author (Adam Langley): http://thread.gmane.org/gmane.linux.network/102586 The principle difference is using a TCP option to carry the cookie nonce, instead of a user configured offset in the data. This is more flexible and less subject to user configuration error. Such a cookie option has been suggested for many years, and is also useful without SYN data, allowing several related concepts to use the same extension option. "Re: SYN floods (was: does history repeat itself?)", September 9, 1996. http://www.merit.net/mail.archives/nanog/1996-09/msg00235.html "Re: what a new TCP header might look like", May 12, 1998. ftp://ftp.isi.edu/end2end/end2end-interest-1998.mail These functions will also be used in subsequent patches that implement additional features. Requires: TCPCT part 1a: add request_values parameter for sending SYNACK TCPCT part 1b: generate Responder Cookie secret TCPCT part 1c: sysctl_tcp_cookie_size, socket option TCP_COOKIE_TRANSACTIONS Signed-off-by: William.Allen.Simpson@gmail.com Signed-off-by: David S. Miller <davem@davemloft.net>
2009-12-03 01:17:05 +07:00
struct tcp_sock *newtp = tcp_sk(newsk);
struct tcp_sock *oldtp = tcp_sk(sk);
struct tcp_cookie_values *oldcvp = oldtp->cookie_values;
/* TCP Cookie Transactions require space for the cookie pair,
* as it differs for each connection. There is no need to
* copy any s_data_payload stored at the original socket.
* Failure will prevent resuming the connection.
*
* Presumed copied, in order of appearance:
* cookie_in_always, cookie_out_never
*/
if (oldcvp != NULL) {
struct tcp_cookie_values *newcvp =
kzalloc(sizeof(*newtp->cookie_values),
GFP_ATOMIC);
if (newcvp != NULL) {
kref_init(&newcvp->kref);
newcvp->cookie_desired =
oldcvp->cookie_desired;
newtp->cookie_values = newcvp;
} else {
/* Not Yet Implemented */
newtp->cookie_values = NULL;
}
}
/* Now setup tcp_sock */
newtp->pred_flags = 0;
TCPCT part 1d: define TCP cookie option, extend existing struct's Data structures are carefully composed to require minimal additions. For example, the struct tcp_options_received cookie_plus variable fits between existing 16-bit and 8-bit variables, requiring no additional space (taking alignment into consideration). There are no additions to tcp_request_sock, and only 1 pointer in tcp_sock. This is a significantly revised implementation of an earlier (year-old) patch that no longer applies cleanly, with permission of the original author (Adam Langley): http://thread.gmane.org/gmane.linux.network/102586 The principle difference is using a TCP option to carry the cookie nonce, instead of a user configured offset in the data. This is more flexible and less subject to user configuration error. Such a cookie option has been suggested for many years, and is also useful without SYN data, allowing several related concepts to use the same extension option. "Re: SYN floods (was: does history repeat itself?)", September 9, 1996. http://www.merit.net/mail.archives/nanog/1996-09/msg00235.html "Re: what a new TCP header might look like", May 12, 1998. ftp://ftp.isi.edu/end2end/end2end-interest-1998.mail These functions will also be used in subsequent patches that implement additional features. Requires: TCPCT part 1a: add request_values parameter for sending SYNACK TCPCT part 1b: generate Responder Cookie secret TCPCT part 1c: sysctl_tcp_cookie_size, socket option TCP_COOKIE_TRANSACTIONS Signed-off-by: William.Allen.Simpson@gmail.com Signed-off-by: David S. Miller <davem@davemloft.net>
2009-12-03 01:17:05 +07:00
newtp->rcv_wup = newtp->copied_seq =
newtp->rcv_nxt = treq->rcv_isn + 1;
newtp->snd_sml = newtp->snd_una =
newtp->snd_nxt = newtp->snd_up =
treq->snt_isn + 1 + tcp_s_data_size(oldtp);
tcp_prequeue_init(newtp);
tcp_init_wl(newtp, treq->rcv_isn);
newtp->srtt = 0;
newtp->mdev = TCP_TIMEOUT_INIT;
newicsk->icsk_rto = TCP_TIMEOUT_INIT;
newtp->packets_out = 0;
newtp->retrans_out = 0;
newtp->sacked_out = 0;
newtp->fackets_out = 0;
newtp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
/* So many TCP implementations out there (incorrectly) count the
* initial SYN frame in their delayed-ACK and congestion control
* algorithms that we must have the following bandaid to talk
* efficiently to them. -DaveM
*/
newtp->snd_cwnd = 2;
newtp->snd_cwnd_cnt = 0;
newtp->bytes_acked = 0;
newtp->frto_counter = 0;
newtp->frto_highmark = 0;
newicsk->icsk_ca_ops = &tcp_init_congestion_ops;
tcp_set_ca_state(newsk, TCP_CA_Open);
tcp_init_xmit_timers(newsk);
skb_queue_head_init(&newtp->out_of_order_queue);
TCPCT part 1d: define TCP cookie option, extend existing struct's Data structures are carefully composed to require minimal additions. For example, the struct tcp_options_received cookie_plus variable fits between existing 16-bit and 8-bit variables, requiring no additional space (taking alignment into consideration). There are no additions to tcp_request_sock, and only 1 pointer in tcp_sock. This is a significantly revised implementation of an earlier (year-old) patch that no longer applies cleanly, with permission of the original author (Adam Langley): http://thread.gmane.org/gmane.linux.network/102586 The principle difference is using a TCP option to carry the cookie nonce, instead of a user configured offset in the data. This is more flexible and less subject to user configuration error. Such a cookie option has been suggested for many years, and is also useful without SYN data, allowing several related concepts to use the same extension option. "Re: SYN floods (was: does history repeat itself?)", September 9, 1996. http://www.merit.net/mail.archives/nanog/1996-09/msg00235.html "Re: what a new TCP header might look like", May 12, 1998. ftp://ftp.isi.edu/end2end/end2end-interest-1998.mail These functions will also be used in subsequent patches that implement additional features. Requires: TCPCT part 1a: add request_values parameter for sending SYNACK TCPCT part 1b: generate Responder Cookie secret TCPCT part 1c: sysctl_tcp_cookie_size, socket option TCP_COOKIE_TRANSACTIONS Signed-off-by: William.Allen.Simpson@gmail.com Signed-off-by: David S. Miller <davem@davemloft.net>
2009-12-03 01:17:05 +07:00
newtp->write_seq = newtp->pushed_seq =
treq->snt_isn + 1 + tcp_s_data_size(oldtp);
newtp->rx_opt.saw_tstamp = 0;
newtp->rx_opt.dsack = 0;
newtp->rx_opt.num_sacks = 0;
newtp->urg_data = 0;
if (sock_flag(newsk, SOCK_KEEPOPEN))
inet_csk_reset_keepalive_timer(newsk,
keepalive_time_when(newtp));
newtp->rx_opt.tstamp_ok = ireq->tstamp_ok;
if ((newtp->rx_opt.sack_ok = ireq->sack_ok) != 0) {
if (sysctl_tcp_fack)
tcp_enable_fack(newtp);
}
newtp->window_clamp = req->window_clamp;
newtp->rcv_ssthresh = req->rcv_wnd;
newtp->rcv_wnd = req->rcv_wnd;
newtp->rx_opt.wscale_ok = ireq->wscale_ok;
if (newtp->rx_opt.wscale_ok) {
newtp->rx_opt.snd_wscale = ireq->snd_wscale;
newtp->rx_opt.rcv_wscale = ireq->rcv_wscale;
} else {
newtp->rx_opt.snd_wscale = newtp->rx_opt.rcv_wscale = 0;
newtp->window_clamp = min(newtp->window_clamp, 65535U);
}
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 = 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_MSS_DEFAULT + 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);
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 sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
struct request_sock *req,
struct request_sock **prev)
{
struct tcp_options_received tmp_opt;
u8 *hash_location;
struct sock *child;
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;
tmp_opt.saw_tstamp = 0;
if (th->doff > (sizeof(struct tcphdr)>>2)) {
tcp_parse_options(skb, &tmp_opt, &hash_location, 0);
if (tmp_opt.saw_tstamp) {
tmp_opt.ts_recent = req->ts_recent;
/* We do not store true stamp, but it is not required,
* it can be estimated (approximately)
* from another data.
*/
tmp_opt.ts_recent_stamp = get_seconds() - ((TCP_TIMEOUT_INIT/HZ)<<req->retrans);
paws_reject = tcp_paws_reject(&tmp_opt, th->rst);
}
}
/* Check for pure retransmitted SYN. */
if (TCP_SKB_CB(skb)->seq == tcp_rsk(req)->rcv_isn &&
flg == TCP_FLAG_SYN &&
!paws_reject) {
/*
* RFC793 draws (Incorrectly! It was fixed in RFC1122)
* this case on figure 6 and figure 8, but formal
* protocol description says NOTHING.
* To be more exact, it says that we should send ACK,
* because this segment (at least, if it has no data)
* is out of window.
*
* CONCLUSION: RFC793 (even with RFC1122) DOES NOT
* describe SYN-RECV state. All the description
* is wrong, we cannot believe to it and should
* rely only on common sense and implementation
* experience.
*
* Enforce "SYN-ACK" according to figure 8, figure 6
* of RFC793, fixed by RFC1122.
*/
req->rsk_ops->rtx_syn_ack(sk, req, NULL);
return NULL;
}
/* Further reproduces section "SEGMENT ARRIVES"
for state SYN-RECEIVED of RFC793.
It is broken, however, it does not work only
when SYNs are crossed.
You would think that SYN crossing is impossible here, since
we should have a SYN_SENT socket (from connect()) on our end,
but this is not true if the crossed SYNs were sent to both
ends by a malicious third party. We must defend against this,
and to do that we first verify the ACK (as per RFC793, page
36) and reset if it is invalid. Is this a true full defense?
To convince ourselves, let us consider a way in which the ACK
test can still pass in this 'malicious crossed SYNs' case.
Malicious sender sends identical SYNs (and thus identical sequence
numbers) to both A and B:
A: gets SYN, seq=7
B: gets SYN, seq=7
By our good fortune, both A and B select the same initial
send sequence number of seven :-)
A: sends SYN|ACK, seq=7, ack_seq=8
B: sends SYN|ACK, seq=7, ack_seq=8
So we are now A eating this SYN|ACK, ACK test passes. So
does sequence test, SYN is truncated, and thus we consider
it a bare ACK.
tcp: Revert 'process defer accept as established' changes. This reverts two changesets, ec3c0982a2dd1e671bad8e9d26c28dcba0039d87 ("[TCP]: TCP_DEFER_ACCEPT updates - process as established") and the follow-on bug fix 9ae27e0adbf471c7a6b80102e38e1d5a346b3b38 ("tcp: Fix slab corruption with ipv6 and tcp6fuzz"). This change causes several problems, first reported by Ingo Molnar as a distcc-over-loopback regression where connections were getting stuck. Ilpo Järvinen first spotted the locking problems. The new function added by this code, tcp_defer_accept_check(), only has the child socket locked, yet it is modifying state of the parent listening socket. Fixing that is non-trivial at best, because we can't simply just grab the parent listening socket lock at this point, because it would create an ABBA deadlock. The normal ordering is parent listening socket --> child socket, but this code path would require the reverse lock ordering. Next is a problem noticed by Vitaliy Gusev, he noted: ---------------------------------------- >--- a/net/ipv4/tcp_timer.c >+++ b/net/ipv4/tcp_timer.c >@@ -481,6 +481,11 @@ static void tcp_keepalive_timer (unsigned long data) > goto death; > } > >+ if (tp->defer_tcp_accept.request && sk->sk_state == TCP_ESTABLISHED) { >+ tcp_send_active_reset(sk, GFP_ATOMIC); >+ goto death; Here socket sk is not attached to listening socket's request queue. tcp_done() will not call inet_csk_destroy_sock() (and tcp_v4_destroy_sock() which should release this sk) as socket is not DEAD. Therefore socket sk will be lost for freeing. ---------------------------------------- Finally, Alexey Kuznetsov argues that there might not even be any real value or advantage to these new semantics even if we fix all of the bugs: ---------------------------------------- Hiding from accept() sockets with only out-of-order data only is the only thing which is impossible with old approach. Is this really so valuable? My opinion: no, this is nothing but a new loophole to consume memory without control. ---------------------------------------- So revert this thing for now. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-06-13 06:31:35 +07:00
If icsk->icsk_accept_queue.rskq_defer_accept, we silently drop this
bare ACK. Otherwise, we create an established connection. Both
ends (listening sockets) accept the new incoming connection and try
to talk to each other. 8-)
Note: This case is both harmless, and rare. Possibility is about the
same as us discovering intelligent life on another plant tomorrow.
But generally, we should (RFC lies!) to accept ACK
from SYNACK both here and in tcp_rcv_state_process().
tcp_rcv_state_process() does not, hence, we do not too.
Note that the case is absolutely generic:
we cannot optimize anything here without
violating protocol. All the checks must be made
before attempt to create socket.
*/
/* RFC793 page 36: "If the connection is in any non-synchronized state ...
* and the incoming segment acknowledges something not yet
* sent (the segment carries an unacceptable ACK) ...
* a reset is sent."
*
* Invalid ACK: reset will be sent by listening socket
*/
if ((flg & TCP_FLAG_ACK) &&
TCPCT part 1d: define TCP cookie option, extend existing struct's Data structures are carefully composed to require minimal additions. For example, the struct tcp_options_received cookie_plus variable fits between existing 16-bit and 8-bit variables, requiring no additional space (taking alignment into consideration). There are no additions to tcp_request_sock, and only 1 pointer in tcp_sock. This is a significantly revised implementation of an earlier (year-old) patch that no longer applies cleanly, with permission of the original author (Adam Langley): http://thread.gmane.org/gmane.linux.network/102586 The principle difference is using a TCP option to carry the cookie nonce, instead of a user configured offset in the data. This is more flexible and less subject to user configuration error. Such a cookie option has been suggested for many years, and is also useful without SYN data, allowing several related concepts to use the same extension option. "Re: SYN floods (was: does history repeat itself?)", September 9, 1996. http://www.merit.net/mail.archives/nanog/1996-09/msg00235.html "Re: what a new TCP header might look like", May 12, 1998. ftp://ftp.isi.edu/end2end/end2end-interest-1998.mail These functions will also be used in subsequent patches that implement additional features. Requires: TCPCT part 1a: add request_values parameter for sending SYNACK TCPCT part 1b: generate Responder Cookie secret TCPCT part 1c: sysctl_tcp_cookie_size, socket option TCP_COOKIE_TRANSACTIONS Signed-off-by: William.Allen.Simpson@gmail.com Signed-off-by: David S. Miller <davem@davemloft.net>
2009-12-03 01:17:05 +07:00
(TCP_SKB_CB(skb)->ack_seq !=
tcp_rsk(req)->snt_isn + 1 + tcp_s_data_size(tcp_sk(sk))))
return sk;
/* Also, it would be not so bad idea to check rcv_tsecr, which
* is essentially ACK extension and too early or too late values
* should cause reset in unsynchronized states.
*/
/* RFC793: "first check sequence number". */
if (paws_reject || !tcp_in_window(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq,
tcp_rsk(req)->rcv_isn + 1, tcp_rsk(req)->rcv_isn + 1 + req->rcv_wnd)) {
/* Out of window: send ACK and drop. */
if (!(flg & TCP_FLAG_RST))
tcp: Fix kernel panic when calling tcp_v(4/6)_md5_do_lookup If the following packet flow happen, kernel will panic. MathineA MathineB SYN ----------------------> SYN+ACK <---------------------- ACK(bad seq) ----------------------> When a bad seq ACK is received, tcp_v4_md5_do_lookup(skb->sk, ip_hdr(skb)->daddr)) is finally called by tcp_v4_reqsk_send_ack(), but the first parameter(skb->sk) is NULL at that moment, so kernel panic happens. This patch fixes this bug. OOPS output is as following: [ 302.812793] IP: [<c05cfaa6>] tcp_v4_md5_do_lookup+0x12/0x42 [ 302.817075] Oops: 0000 [#1] SMP [ 302.819815] Modules linked in: ipv6 loop dm_multipath rtc_cmos rtc_core rtc_lib pcspkr pcnet32 mii i2c_piix4 parport_pc i2c_core parport ac button ata_piix libata dm_mod mptspi mptscsih mptbase scsi_transport_spi sd_mod scsi_mod crc_t10dif ext3 jbd mbcache uhci_hcd ohci_hcd ehci_hcd [last unloaded: scsi_wait_scan] [ 302.849946] [ 302.851198] Pid: 0, comm: swapper Not tainted (2.6.27-rc1-guijf #5) [ 302.855184] EIP: 0060:[<c05cfaa6>] EFLAGS: 00010296 CPU: 0 [ 302.858296] EIP is at tcp_v4_md5_do_lookup+0x12/0x42 [ 302.861027] EAX: 0000001e EBX: 00000000 ECX: 00000046 EDX: 00000046 [ 302.864867] ESI: ceb69e00 EDI: 1467a8c0 EBP: cf75f180 ESP: c0792e54 [ 302.868333] DS: 007b ES: 007b FS: 00d8 GS: 0000 SS: 0068 [ 302.871287] Process swapper (pid: 0, ti=c0792000 task=c0712340 task.ti=c0746000) [ 302.875592] Stack: c06f413a 00000000 cf75f180 ceb69e00 00000000 c05d0d86 000016d0 ceac5400 [ 302.883275] c05d28f8 000016d0 ceb69e00 ceb69e20 681bf6e3 00001000 00000000 0a67a8c0 [ 302.890971] ceac5400 c04250a3 c06f413a c0792eb0 c0792edc cf59a620 cf59a620 cf59a634 [ 302.900140] Call Trace: [ 302.902392] [<c05d0d86>] tcp_v4_reqsk_send_ack+0x17/0x35 [ 302.907060] [<c05d28f8>] tcp_check_req+0x156/0x372 [ 302.910082] [<c04250a3>] printk+0x14/0x18 [ 302.912868] [<c05d0aa1>] tcp_v4_do_rcv+0x1d3/0x2bf [ 302.917423] [<c05d26be>] tcp_v4_rcv+0x563/0x5b9 [ 302.920453] [<c05bb20f>] ip_local_deliver_finish+0xe8/0x183 [ 302.923865] [<c05bb10a>] ip_rcv_finish+0x286/0x2a3 [ 302.928569] [<c059e438>] dev_alloc_skb+0x11/0x25 [ 302.931563] [<c05a211f>] netif_receive_skb+0x2d6/0x33a [ 302.934914] [<d0917941>] pcnet32_poll+0x333/0x680 [pcnet32] [ 302.938735] [<c05a3b48>] net_rx_action+0x5c/0xfe [ 302.941792] [<c042856b>] __do_softirq+0x5d/0xc1 [ 302.944788] [<c042850e>] __do_softirq+0x0/0xc1 [ 302.948999] [<c040564b>] do_softirq+0x55/0x88 [ 302.951870] [<c04501b1>] handle_fasteoi_irq+0x0/0xa4 [ 302.954986] [<c04284da>] irq_exit+0x35/0x69 [ 302.959081] [<c0405717>] do_IRQ+0x99/0xae [ 302.961896] [<c040422b>] common_interrupt+0x23/0x28 [ 302.966279] [<c040819d>] default_idle+0x2a/0x3d [ 302.969212] [<c0402552>] cpu_idle+0xb2/0xd2 [ 302.972169] ======================= [ 302.974274] Code: fc ff 84 d2 0f 84 df fd ff ff e9 34 fe ff ff 83 c4 0c 5b 5e 5f 5d c3 90 90 57 89 d7 56 53 89 c3 50 68 3a 41 6f c0 e8 e9 55 e5 ff <8b> 93 9c 04 00 00 58 85 d2 59 74 1e 8b 72 10 31 db 31 c9 85 f6 [ 303.011610] EIP: [<c05cfaa6>] tcp_v4_md5_do_lookup+0x12/0x42 SS:ESP 0068:c0792e54 [ 303.018360] Kernel panic - not syncing: Fatal exception in interrupt Signed-off-by: Gui Jianfeng <guijianfeng@cn.fujitsu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-07 13:50:04 +07:00
req->rsk_ops->send_ack(sk, skb, req);
if (paws_reject)
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED);
return NULL;
}
/* In sequence, PAWS is OK. */
if (tmp_opt.saw_tstamp && !after(TCP_SKB_CB(skb)->seq, tcp_rsk(req)->rcv_isn + 1))
req->ts_recent = tmp_opt.rcv_tsval;
if (TCP_SKB_CB(skb)->seq == tcp_rsk(req)->rcv_isn) {
/* Truncate SYN, it is out of window starting
at tcp_rsk(req)->rcv_isn + 1. */
flg &= ~TCP_FLAG_SYN;
}
/* RFC793: "second check the RST bit" and
* "fourth, check the SYN bit"
*/
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.
*/
if (!(flg & TCP_FLAG_ACK))
return NULL;
tcp: Revert 'process defer accept as established' changes. This reverts two changesets, ec3c0982a2dd1e671bad8e9d26c28dcba0039d87 ("[TCP]: TCP_DEFER_ACCEPT updates - process as established") and the follow-on bug fix 9ae27e0adbf471c7a6b80102e38e1d5a346b3b38 ("tcp: Fix slab corruption with ipv6 and tcp6fuzz"). This change causes several problems, first reported by Ingo Molnar as a distcc-over-loopback regression where connections were getting stuck. Ilpo Järvinen first spotted the locking problems. The new function added by this code, tcp_defer_accept_check(), only has the child socket locked, yet it is modifying state of the parent listening socket. Fixing that is non-trivial at best, because we can't simply just grab the parent listening socket lock at this point, because it would create an ABBA deadlock. The normal ordering is parent listening socket --> child socket, but this code path would require the reverse lock ordering. Next is a problem noticed by Vitaliy Gusev, he noted: ---------------------------------------- >--- a/net/ipv4/tcp_timer.c >+++ b/net/ipv4/tcp_timer.c >@@ -481,6 +481,11 @@ static void tcp_keepalive_timer (unsigned long data) > goto death; > } > >+ if (tp->defer_tcp_accept.request && sk->sk_state == TCP_ESTABLISHED) { >+ tcp_send_active_reset(sk, GFP_ATOMIC); >+ goto death; Here socket sk is not attached to listening socket's request queue. tcp_done() will not call inet_csk_destroy_sock() (and tcp_v4_destroy_sock() which should release this sk) as socket is not DEAD. Therefore socket sk will be lost for freeing. ---------------------------------------- Finally, Alexey Kuznetsov argues that there might not even be any real value or advantage to these new semantics even if we fix all of the bugs: ---------------------------------------- Hiding from accept() sockets with only out-of-order data only is the only thing which is impossible with old approach. Is this really so valuable? My opinion: no, this is nothing but a new loophole to consume memory without control. ---------------------------------------- So revert this thing for now. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-06-13 06:31:35 +07:00
/* While TCP_DEFER_ACCEPT is active, drop bare ACK. */
if (req->retrans < inet_csk(sk)->icsk_accept_queue.rskq_defer_accept &&
TCP_SKB_CB(skb)->end_seq == tcp_rsk(req)->rcv_isn + 1) {
inet_rsk(req)->acked = 1;
return NULL;
}
/* OK, ACK is valid, create big socket and
* feed this segment to it. It will repeat all
* the tests. THIS SEGMENT MUST MOVE SOCKET TO
* ESTABLISHED STATE. If it will be dropped after
* socket is created, wait for troubles.
*/
child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL);
if (child == NULL)
goto listen_overflow;
inet_csk_reqsk_queue_unlink(sk, req, prev);
inet_csk_reqsk_queue_removed(sk, req);
inet_csk_reqsk_queue_add(sk, req, child);
return child;
listen_overflow:
if (!sysctl_tcp_abort_on_overflow) {
inet_rsk(req)->acked = 1;
return NULL;
}
embryonic_reset:
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_EMBRYONICRSTS);
if (!(flg & TCP_FLAG_RST))
req->rsk_ops->send_reset(sk, skb);
inet_csk_reqsk_queue_drop(sk, req, prev);
return NULL;
}
/*
* Queue segment on the new socket if the new socket is active,
* otherwise we just shortcircuit this and continue with
* the new socket.
*/
int tcp_child_process(struct sock *parent, struct sock *child,
struct sk_buff *skb)
{
int ret = 0;
int state = child->sk_state;
if (!sock_owned_by_user(child)) {
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);
} else {
/* Alas, it is possible again, because we do lookup
* in main socket hash table and lock on listening
* socket does not protect us more.
*/
__sk_add_backlog(child, skb);
}
bh_unlock_sock(child);
sock_put(child);
return ret;
}
EXPORT_SYMBOL(tcp_check_req);
EXPORT_SYMBOL(tcp_child_process);
EXPORT_SYMBOL(tcp_create_openreq_child);
EXPORT_SYMBOL(tcp_timewait_state_process);