![Tejun Heo](/assets/img/avatar_default.png)
percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
744 lines
23 KiB
C
744 lines
23 KiB
C
/*
|
|
* 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/slab.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,
|
|
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);
|
|
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;
|
|
|
|
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);
|
|
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.
|
|
|
|
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) &&
|
|
(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))
|
|
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;
|
|
|
|
/* 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);
|