litmus-rt.git - The LITMUS^RT kernel.

The LITMUS^RT kernel.

Bjoern Brandenburg

about summary refs log tree commit diff stats

diff options

author	Dave Martin <dave.martin@linaro.org>	2011-03-03 05:41:12 -0500
committer	Russell King <rmk+kernel@arm.linux.org.uk>	2011-03-10 11:49:06 -0500
commit	6f685c5cdd29649cf8cc8f57c72791159f936e07 (patch)
tree	892575c8f378609771752e12e88d4f2699084c70 /mm/truncate.c
parent	23bfdacf4eb525ff3404161429cedaa281c23e47 (diff)

ARM: 6781/1: Thumb-2: Work around buggy Thumb-2 short branch relocations in gas

Various binutils versions can resolve Thumb-2 branches to locally-defined, preemptible global symbols as short-range "b.n" branch instructions. This is a problem, because there's no guarantee the final destination of the symbol, or any candidate locations for a trampoline, are within range of the branch. For this reason, the kernel does not support fixing up the R_ARM_THM_JUMP11 (102) relocation in modules at all, and it makes little sense to add support. The symptom is that the kernel fails with an "unsupported relocation" error when loading some modules. Until fixed tools are available, passing -fno-optimize-sibling-calls to gcc should prevent gcc generating code which hits this problem, at the cost of a bit of extra runtime stack usage in some cases. The problem is described in more detail at: https://bugs.launchpad.net/binutils-linaro/+bug/725126 Only Thumb-2 kernels are affected. This patch adds a new CONFIG_THUMB2_AVOID_R_ARM_THM_JUMP11 config option which adds -fno-optimize-sibling-calls to CFLAGS_MODULE when building a Thumb-2 kernel. Signed-off-by: Dave Martin <dave.martin@linaro.org> Acked-by: Nicolas Pitre <nicolas.pitre@linaro.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

Diffstat (limited to 'mm/truncate.c')

0 files changed, 0 insertions, 0 deletions

et/ll_poll.h to include/net/busy_poll.h' href='/cgit/cgit.cgi/litmus-rt-ext-res.git/commit/net/ipv4/tcp_ipv4.c?id=076bb0c82a44fbe46fe2c8527a5b5b64b69f679d'>076bb0c82a44

38
39

71
72

86
87
88

89
90

97
98

104
105

106
107

108
109

140
141

142
143
144

146
147

162
163
164

165
166

168
169

170
171

172
173

197
198
199

200
201

202
203

205
206

208
209

212
213

224
225
226

239
240
241

242
243

259
260
261

263
264

268
269
270

273
274
275

278
279

280
281

310
311

333
334

335
336

347
348
349

354
355
356

364
365

371
372
373

382
383

384
385
386

392
393
394

432
433

434
435
436

438
439

479
480

506
507

508
509

570
571
572

591
592
593

595
596

598
599

612
613
614

620
621

624
625
626

627
628

644
645

675
676

677
678

679
680

685
686

688
689

696
697

718
719

723
724

725
726

728
729

731
732
733

735
736
737

738
739

764
765

766
767

769
770

771
772

773
774

790
791

793
794

798
799

810
811

812
813

814
815

816
817

821
822

823
824

837
838

842
843

846
847

848
849

850
851
852

860
861

868
869

874
875

879
880
881

887
888

890
891
892

896
897
898

901
902

907
908

909
910

911
912

913
914

932
933
934

935
936

941
942

943
944

956
957
958

969
970

971
972

974
975

978
979
980

981
982

983
984

990
991

994
995

997
998

999
1000
1001

1004
1005

1010
1011

1024
1025

1030
1031

1033
1034
1035

1043
1044

1049
1050

1055
1056
1057

1058
1059

1060
1061
1062

1074
1075

1080
1081
1082

1083
1084

1085
1086

1090
1091

1092
1093

1128
1129

1138
1139

1141
1142

1144
1145

1147
1148
1149

1150
1151

1153
1154

1156
1157
1158

1206
1207

1208
1209

1212
1213

1215
1216

1219
1220
1221

1229
1230
1231

1232
1233

1250
1251

1254
1255

1320
1321

1322
1323

1334
1335

1342
1343

1359
1360

1370
1371

1372
1373
1374

1444
1445
1446

1451
1452

1460
1461

1469
1470

1471
1472
1473

1481
1482

1487
1488
1489

1503
1504

1506
1507

1516
1517

1533
1534

1554
1555

1579
1580
1581

1589
1590

1603
1604

1605
1606

1607
1608

1613
1614

1624
1625

1627
1628
1629

1630
1631
1632

1638
1639

1644
1645
1646

1648
1649
1650

1651
1652

1658
1659

1669
1670

1678
1679

1680
1681

1682
1683

1691
1692

1694
1695
1696

1697
1698

1705
1706

1711
1712

1716
1717
1718

1724
1725

1750
1751

1753
1754

1761
1762

1789
1790
1791

1793
1794

1797
1798

1804
1805
1806

1817
1818

1821
1822

1830
1831
1832

1846
1847

1852
1853
1854

1861
1862

1864
1865

1878
1879

1883
1884

1885
1886

1940
1941

1975
1976

1978
1979
1980

1985
1986

1990
1991

1995
1996

1998
1999

2001
2002

2003
2004
2005

2015
2016

2019
2020

2032
2033

2052
2053
2054

2071
2072

2105
2106
2107

2109
2110

2118
2119

2147
2148
2149

2160
2161

2164
2165
2166

2173
2174

2176
2177

2187
2188
2189

2203
2204

2211
2212

2217
2218

2222
2223

2227
2228
2229

2237
2238

2246
2247

2251
2252

2254
2255
2256

2257
2258
2259

2261
2262

2275
2276

2304
2305

2310
2311

2314
2315

2316
2317

2347
2348

2356
2357

2358
2359
2360

2414
2415

2428
2429

2439
2440

2466
2467

2488
2489

2490
2491
2492

2495
2496

2516
2517

2532
2533
2534

2554
2555

2556
2557
2558

2562
2563
2564

2565
2566

2567
2568

2570
2571
2572

2583
2584
2585

2587
2588

2617
2618

2619
2620

2623
2624
2625

2627
2628

2672
2673

2675
2676

2691
2692

2694
2695
2696

2697
2698

2714
2715

2739
2740

2744
2745
2746

2751
2752

2775
2776

2788
2789
2790

2791
2792
2793

2794
2795

/*
 * 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).
 *
 *		IPv4 specific functions
 *
 *
 *		code split from:
 *		linux/ipv4/tcp.c
 *		linux/ipv4/tcp_input.c
 *		linux/ipv4/tcp_output.c
 *
 *		See tcp.c for author information
 *
 *	This program is free software; you can redistribute it and/or
 *      modify it under the terms of the GNU General Public License
 *      as published by the Free Software Foundation; either version
 *      2 of the License, or (at your option) any later version.
 */

/*
 * Changes:
 *		David S. Miller	:	New socket lookup architecture.
 *					This code is dedicated to John Dyson.
 *		David S. Miller :	Change semantics of established hash,
 *					half is devoted to TIME_WAIT sockets
 *					and the rest go in the other half.
 *		Andi Kleen :		Add support for syncookies and fixed
 *					some bugs: ip options weren't passed to
 *					the TCP layer, missed a check for an
 *					ACK bit.
 *		Andi Kleen :		Implemented fast path mtu discovery.
 *	     				Fixed many serious bugs in the
 *					request_sock handling and moved
 *					most of it into the af independent code.
 *					Added tail drop and some other bugfixes.
 *					Added new listen semantics.
 *		Mike McLagan	:	Routing by source
 *	Juan Jose Ciarlante:		ip_dynaddr bits
 *		Andi Kleen:		various fixes.
 *	Vitaly E. Lavrov	:	Transparent proxy revived after year
 *					coma.
 *	Andi Kleen		:	Fix new listen.
 *	Andi Kleen		:	Fix accept error reporting.
 *	YOSHIFUJI Hideaki @USAGI and:	Support IPV6_V6ONLY socket option, which
 *	Alexey Kuznetsov		allow both IPv4 and IPv6 sockets to bind
 *					a single port at the same time.
 */

#define pr_fmt(fmt) "TCP: " fmt

#include <linux/bottom_half.h>
#include <linux/types.h>
#include <linux/fcntl.h>
#include <linux/module.h>
#include <linux/random.h>
#include <linux/cache.h>
#include <linux/jhash.h>
#include <linux/init.h>
#include <linux/times.h>
#include <linux/slab.h>

#include <net/net_namespace.h>
#include <net/icmp.h>
#include <net/inet_hashtables.h>
#include <net/tcp.h>
#include <net/transp_v6.h>
#include <net/ipv6.h>
#include <net/inet_common.h>
#include <net/timewait_sock.h>
#include <net/xfrm.h>
#include <net/netdma.h>
#include <net/secure_seq.h>
#include <net/tcp_memcontrol.h>
#include <net/busy_poll.h>

#include <linux/inet.h>
#include <linux/ipv6.h>
#include <linux/stddef.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>

#include <linux/crypto.h>
#include <linux/scatterlist.h>

int sysctl_tcp_tw_reuse __read_mostly;
int sysctl_tcp_low_latency __read_mostly;
EXPORT_SYMBOL(sysctl_tcp_low_latency);


#ifdef CONFIG_TCP_MD5SIG
static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
			       __be32 daddr, __be32 saddr, const struct tcphdr *th);
#endif

struct inet_hashinfo tcp_hashinfo;
EXPORT_SYMBOL(tcp_hashinfo);

static inline __u32 tcp_v4_init_sequence(const struct sk_buff *skb)
{
	return secure_tcp_sequence_number(ip_hdr(skb)->daddr,
					  ip_hdr(skb)->saddr,
					  tcp_hdr(skb)->dest,
					  tcp_hdr(skb)->source);
}

int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
{
	const struct tcp_timewait_sock *tcptw = tcp_twsk(sktw);
	struct tcp_sock *tp = tcp_sk(sk);

	/* With PAWS, it is safe from the viewpoint
	   of data integrity. Even without PAWS it is safe provided sequence
	   spaces do not overlap i.e. at data rates <= 80Mbit/sec.

	   Actually, the idea is close to VJ's one, only timestamp cache is
	   held not per host, but per port pair and TW bucket is used as state
	   holder.

	   If TW bucket has been already destroyed we fall back to VJ's scheme
	   and use initial timestamp retrieved from peer table.
	 */
	if (tcptw->tw_ts_recent_stamp &&
	    (twp == NULL || (sysctl_tcp_tw_reuse &&
			     get_seconds() - tcptw->tw_ts_recent_stamp > 1))) {
		tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2;
		if (tp->write_seq == 0)
			tp->write_seq = 1;
		tp->rx_opt.ts_recent	   = tcptw->tw_ts_recent;
		tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp;
		sock_hold(sktw);
		return 1;
	}

	return 0;
}
EXPORT_SYMBOL_GPL(tcp_twsk_unique);

/* This will initiate an outgoing connection. */
int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
	struct sockaddr_in *usin = (struct sockaddr_in *)uaddr;
	struct inet_sock *inet = inet_sk(sk);
	struct tcp_sock *tp = tcp_sk(sk);
	__be16 orig_sport, orig_dport;
	__be32 daddr, nexthop;
	struct flowi4 *fl4;
	struct rtable *rt;
	int err;
	struct ip_options_rcu *inet_opt;

	if (addr_len < sizeof(struct sockaddr_in))
		return -EINVAL;

	if (usin->sin_family != AF_INET)
		return -EAFNOSUPPORT;

	nexthop = daddr = usin->sin_addr.s_addr;
	inet_opt = rcu_dereference_protected(inet->inet_opt,
					     sock_owned_by_user(sk));
	if (inet_opt && inet_opt->opt.srr) {
		if (!daddr)
			return -EINVAL;
		nexthop = inet_opt->opt.faddr;
	}

	orig_sport = inet->inet_sport;
	orig_dport = usin->sin_port;
	fl4 = &inet->cork.fl.u.ip4;
	rt = ip_route_connect(fl4, nexthop, inet->inet_saddr,
			      RT_CONN_FLAGS(sk), sk->sk_bound_dev_if,
			      IPPROTO_TCP,
			      orig_sport, orig_dport, sk, true);
	if (IS_ERR(rt)) {
		err = PTR_ERR(rt);
		if (err == -ENETUNREACH)
			IP_INC_STATS_BH(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
		return err;
	}

	if (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST)) {
		ip_rt_put(rt);
		return -ENETUNREACH;
	}

	if (!inet_opt || !inet_opt->opt.srr)
		daddr = fl4->daddr;

	if (!inet->inet_saddr)
		inet->inet_saddr = fl4->saddr;
	inet->inet_rcv_saddr = inet->inet_saddr;

	if (tp->rx_opt.ts_recent_stamp && inet->inet_daddr != daddr) {
		/* Reset inherited state */
		tp->rx_opt.ts_recent	   = 0;
		tp->rx_opt.ts_recent_stamp = 0;
		if (likely(!tp->repair))
			tp->write_seq	   = 0;
	}

	if (tcp_death_row.sysctl_tw_recycle &&
	    !tp->rx_opt.ts_recent_stamp && fl4->daddr == daddr)
		tcp_fetch_timewait_stamp(sk, &rt->dst);

	inet->inet_dport = usin->sin_port;
	inet->inet_daddr = daddr;

	inet_csk(sk)->icsk_ext_hdr_len = 0;
	if (inet_opt)
		inet_csk(sk)->icsk_ext_hdr_len = inet_opt->opt.optlen;

	tp->rx_opt.mss_clamp = TCP_MSS_DEFAULT;

	/* Socket identity is still unknown (sport may be zero).
	 * However we set state to SYN-SENT and not releasing socket
	 * lock select source port, enter ourselves into the hash tables and
	 * complete initialization after this.
	 */
	tcp_set_state(sk, TCP_SYN_SENT);
	err = inet_hash_connect(&tcp_death_row, sk);
	if (err)
		goto failure;

	rt = ip_route_newports(fl4, rt, orig_sport, orig_dport,
			       inet->inet_sport, inet->inet_dport, sk);
	if (IS_ERR(rt)) {
		err = PTR_ERR(rt);
		rt = NULL;
		goto failure;
	}
	/* OK, now commit destination to socket.  */
	sk->sk_gso_type = SKB_GSO_TCPV4;
	sk_setup_caps(sk, &rt->dst);

	if (!tp->write_seq && likely(!tp->repair))
		tp->write_seq = secure_tcp_sequence_number(inet->inet_saddr,
							   inet->inet_daddr,
							   inet->inet_sport,
							   usin->sin_port);

	inet->inet_id = tp->write_seq ^ jiffies;

	err = tcp_connect(sk);

	rt = NULL;
	if (err)
		goto failure;

	return 0;

failure:
	/*
	 * This unhashes the socket and releases the local port,
	 * if necessary.
	 */
	tcp_set_state(sk, TCP_CLOSE);
	ip_rt_put(rt);
	sk->sk_route_caps = 0;
	inet->inet_dport = 0;
	return err;
}
EXPORT_SYMBOL(tcp_v4_connect);

/*
 * This routine reacts to ICMP_FRAG_NEEDED mtu indications as defined in RFC1191.
 * It can be called through tcp_release_cb() if socket was owned by user
 * at the time tcp_v4_err() was called to handle ICMP message.
 */
static void tcp_v4_mtu_reduced(struct sock *sk)
{
	struct dst_entry *dst;
	struct inet_sock *inet = inet_sk(sk);
	u32 mtu = tcp_sk(sk)->mtu_info;

	dst = inet_csk_update_pmtu(sk, mtu);
	if (!dst)
		return;

	/* Something is about to be wrong... Remember soft error
	 * for the case, if this connection will not able to recover.
	 */
	if (mtu < dst_mtu(dst) && ip_dont_fragment(sk, dst))
		sk->sk_err_soft = EMSGSIZE;

	mtu = dst_mtu(dst);

	if (inet->pmtudisc != IP_PMTUDISC_DONT &&
	    ip_sk_accept_pmtu(sk) &&
	    inet_csk(sk)->icsk_pmtu_cookie > mtu) {
		tcp_sync_mss(sk, mtu);

		/* Resend the TCP packet because it's
		 * clear that the old packet has been
		 * dropped. This is the new "fast" path mtu
		 * discovery.
		 */
		tcp_simple_retransmit(sk);
	} /* else let the usual retransmit timer handle it */
}

static void do_redirect(struct sk_buff *skb, struct sock *sk)
{
	struct dst_entry *dst = __sk_dst_check(sk, 0);

	if (dst)
		dst->ops->redirect(dst, sk, skb);
}

/*
 * This routine is called by the ICMP module when it gets some
 * sort of error condition.  If err < 0 then the socket should
 * be closed and the error returned to the user.  If err > 0
 * it's just the icmp type << 8 | icmp code.  After adjustment
 * header points to the first 8 bytes of the tcp header.  We need
 * to find the appropriate port.
 *
 * The locking strategy used here is very "optimistic". When
 * someone else accesses the socket the ICMP is just dropped
 * and for some paths there is no check at all.
 * A more general error queue to queue errors for later handling
 * is probably better.
 *
 */

void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
{
	const struct iphdr *iph = (const struct iphdr *)icmp_skb->data;
	struct tcphdr *th = (struct tcphdr *)(icmp_skb->data + (iph->ihl << 2));
	struct inet_connection_sock *icsk;
	struct tcp_sock *tp;
	struct inet_sock *inet;
	const int type = icmp_hdr(icmp_skb)->type;
	const int code = icmp_hdr(icmp_skb)->code;
	struct sock *sk;
	struct sk_buff *skb;
	struct request_sock *req;
	__u32 seq;
	__u32 remaining;
	int err;
	struct net *net = dev_net(icmp_skb->dev);

	if (icmp_skb->len < (iph->ihl << 2) + 8) {
		ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS);
		return;
	}

	sk = inet_lookup(net, &tcp_hashinfo, iph->daddr, th->dest,
			iph->saddr, th->source, inet_iif(icmp_skb));
	if (!sk) {
		ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS);
		return;
	}
	if (sk->sk_state == TCP_TIME_WAIT) {
		inet_twsk_put(inet_twsk(sk));
		return;
	}

	bh_lock_sock(sk);
	/* If too many ICMPs get dropped on busy
	 * servers this needs to be solved differently.
	 * We do take care of PMTU discovery (RFC1191) special case :
	 * we can receive locally generated ICMP messages while socket is held.
	 */
	if (sock_owned_by_user(sk)) {
		if (!(type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED))
			NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS);
	}
	if (sk->sk_state == TCP_CLOSE)
		goto out;

	if (unlikely(iph->ttl < inet_sk(sk)->min_ttl)) {
		NET_INC_STATS_BH(net, LINUX_MIB_TCPMINTTLDROP);
		goto out;
	}

	icsk = inet_csk(sk);
	tp = tcp_sk(sk);
	req = tp->fastopen_rsk;
	seq = ntohl(th->seq);
	if (sk->sk_state != TCP_LISTEN &&
	    !between(seq, tp->snd_una, tp->snd_nxt) &&
	    (req == NULL || seq != tcp_rsk(req)->snt_isn)) {
		/* For a Fast Open socket, allow seq to be snt_isn. */
		NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
		goto out;
	}

	switch (type) {
	case ICMP_REDIRECT:
		do_redirect(icmp_skb, sk);
		goto out;
	case ICMP_SOURCE_QUENCH:
		/* Just silently ignore these. */
		goto out;
	case ICMP_PARAMETERPROB:
		err = EPROTO;
		break;
	case ICMP_DEST_UNREACH:
		if (code > NR_ICMP_UNREACH)
			goto out;

		if (code == ICMP_FRAG_NEEDED) { /* PMTU discovery (RFC1191) */
			/* We are not interested in TCP_LISTEN and open_requests
			 * (SYN-ACKs send out by Linux are always <576bytes so
			 * they should go through unfragmented).
			 */
			if (sk->sk_state == TCP_LISTEN)
				goto out;

			tp->mtu_info = info;
			if (!sock_owned_by_user(sk)) {
				tcp_v4_mtu_reduced(sk);
			} else {
				if (!test_and_set_bit(TCP_MTU_REDUCED_DEFERRED, &tp->tsq_flags))
					sock_hold(sk);
			}
			goto out;
		}

		err = icmp_err_convert[code].errno;
		/* check if icmp_skb allows revert of backoff
		 * (see draft-zimmermann-tcp-lcd) */
		if (code != ICMP_NET_UNREACH && code != ICMP_HOST_UNREACH)
			break;
		if (seq != tp->snd_una  || !icsk->icsk_retransmits ||
		    !icsk->icsk_backoff)
			break;

		/* XXX (TFO) - revisit the following logic for TFO */

		if (sock_owned_by_user(sk))
			break;

		icsk->icsk_backoff--;
		inet_csk(sk)->icsk_rto = (tp->srtt ? __tcp_set_rto(tp) :
			TCP_TIMEOUT_INIT) << icsk->icsk_backoff;
		tcp_bound_rto(sk);

		skb = tcp_write_queue_head(sk);
		BUG_ON(!skb);

		remaining = icsk->icsk_rto - min(icsk->icsk_rto,
				tcp_time_stamp - TCP_SKB_CB(skb)->when);

		if (remaining) {
			inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
						  remaining, TCP_RTO_MAX);
		} else {
			/* RTO revert clocked out retransmission.
			 * Will retransmit now */
			tcp_retransmit_timer(sk);
		}

		break;
	case ICMP_TIME_EXCEEDED:
		err = EHOSTUNREACH;
		break;
	default:
		goto out;
	}

	/* XXX (TFO) - if it's a TFO socket and has been accepted, rather
	 * than following the TCP_SYN_RECV case and closing the socket,
	 * we ignore the ICMP error and keep trying like a fully established
	 * socket. Is this the right thing to do?
	 */
	if (req && req->sk == NULL)
		goto out;

	switch (sk->sk_state) {
		struct request_sock *req, **prev;
	case TCP_LISTEN:
		if (sock_owned_by_user(sk))
			goto out;

		req = inet_csk_search_req(sk, &prev, th->dest,
					  iph->daddr, iph->saddr);
		if (!req)
			goto out;

		/* ICMPs are not backlogged, hence we cannot get
		   an established socket here.
		 */
		WARN_ON(req->sk);

		if (seq != tcp_rsk(req)->snt_isn) {
			NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
			goto out;
		}

		/*
		 * Still in SYN_RECV, just remove it silently.
		 * There is no good way to pass the error to the newly
		 * created socket, and POSIX does not want network
		 * errors returned from accept().
		 */
		inet_csk_reqsk_queue_drop(sk, req, prev);
		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
		goto out;

	case TCP_SYN_SENT:
	case TCP_SYN_RECV:  /* Cannot happen.
			       It can f.e. if SYNs crossed,
			       or Fast Open.
			     */
		if (!sock_owned_by_user(sk)) {
			sk->sk_err = err;

			sk->sk_error_report(sk);

			tcp_done(sk);
		} else {
			sk->sk_err_soft = err;
		}
		goto out;
	}

	/* If we've already connected we will keep trying
	 * until we time out, or the user gives up.
	 *
	 * rfc1122 4.2.3.9 allows to consider as hard errors
	 * only PROTO_UNREACH and PORT_UNREACH (well, FRAG_FAILED too,
	 * but it is obsoleted by pmtu discovery).
	 *
	 * Note, that in modern internet, where routing is unreliable
	 * and in each dark corner broken firewalls sit, sending random
	 * errors ordered by their masters even this two messages finally lose
	 * their original sense (even Linux sends invalid PORT_UNREACHs)
	 *
	 * Now we are in compliance with RFCs.
	 *							--ANK (980905)
	 */

	inet = inet_sk(sk);
	if (!sock_owned_by_user(sk) && inet->recverr) {
		sk->sk_err = err;
		sk->sk_error_report(sk);
	} else	{ /* Only an error on timeout */
		sk->sk_err_soft = err;
	}

out:
	bh_unlock_sock(sk);
	sock_put(sk);
}

void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr)
{
	struct tcphdr *th = tcp_hdr(skb);

	if (skb->ip_summed == CHECKSUM_PARTIAL) {
		th->check = ~tcp_v4_check(skb->len, saddr, daddr, 0);
		skb->csum_start = skb_transport_header(skb) - skb->head;
		skb->csum_offset = offsetof(struct tcphdr, check);
	} else {
		th->check = tcp_v4_check(skb->len, saddr, daddr,
					 csum_partial(th,
						      th->doff << 2,
						      skb->csum));
	}
}

/* This routine computes an IPv4 TCP checksum. */
void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb)
{
	const struct inet_sock *inet = inet_sk(sk);

	__tcp_v4_send_check(skb, inet->inet_saddr, inet->inet_daddr);
}
EXPORT_SYMBOL(tcp_v4_send_check);

/*
 *	This routine will send an RST to the other tcp.
 *
 *	Someone asks: why I NEVER use socket parameters (TOS, TTL etc.)
 *		      for reset.
 *	Answer: if a packet caused RST, it is not for a socket
 *		existing in our system, if it is matched to a socket,
 *		it is just duplicate segment or bug in other side's TCP.
 *		So that we build reply only basing on parameters
 *		arrived with segment.
 *	Exception: precedence violation. We do not implement it in any case.
 */

static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
{
	const struct tcphdr *th = tcp_hdr(skb);
	struct {
		struct tcphdr th;
#ifdef CONFIG_TCP_MD5SIG
		__be32 opt[(TCPOLEN_MD5SIG_ALIGNED >> 2)];
#endif
	} rep;
	struct ip_reply_arg arg;
#ifdef CONFIG_TCP_MD5SIG
	struct tcp_md5sig_key *key;
	const __u8 *hash_location = NULL;
	unsigned char newhash[16];
	int genhash;
	struct sock *sk1 = NULL;
#endif
	struct net *net;

	/* Never send a reset in response to a reset. */
	if (th->rst)
		return;

	if (skb_rtable(skb)->rt_type != RTN_LOCAL)
		return;

	/* Swap the send and the receive. */
	memset(&rep, 0, sizeof(rep));
	rep.th.dest   = th->source;
	rep.th.source = th->dest;
	rep.th.doff   = sizeof(struct tcphdr) / 4;
	rep.th.rst    = 1;

	if (th->ack) {
		rep.th.seq = th->ack_seq;
	} else {
		rep.th.ack = 1;
		rep.th.ack_seq = htonl(ntohl(th->seq) + th->syn + th->fin +
				       skb->len - (th->doff << 2));
	}

	memset(&arg, 0, sizeof(arg));
	arg.iov[0].iov_base = (unsigned char *)&rep;
	arg.iov[0].iov_len  = sizeof(rep.th);

#ifdef CONFIG_TCP_MD5SIG
	hash_location = tcp_parse_md5sig_option(th);
	if (!sk && hash_location) {
		/*
		 * active side is lost. Try to find listening socket through
		 * source port, and then find md5 key through listening socket.
		 * we are not loose security here:
		 * Incoming packet is checked with md5 hash with finding key,
		 * no RST generated if md5 hash doesn't match.
		 */
		sk1 = __inet_lookup_listener(dev_net(skb_dst(skb)->dev),
					     &tcp_hashinfo, ip_hdr(skb)->saddr,
					     th->source, ip_hdr(skb)->daddr,
					     ntohs(th->source), inet_iif(skb));
		/* don't send rst if it can't find key */
		if (!sk1)
			return;
		rcu_read_lock();
		key = tcp_md5_do_lookup(sk1, (union tcp_md5_addr *)
					&ip_hdr(skb)->saddr, AF_INET);
		if (!key)
			goto release_sk1;

		genhash = tcp_v4_md5_hash_skb(newhash, key, NULL, NULL, skb);
		if (genhash || memcmp(hash_location, newhash, 16) != 0)
			goto release_sk1;
	} else {
		key = sk ? tcp_md5_do_lookup(sk, (union tcp_md5_addr *)
					     &ip_hdr(skb)->saddr,
					     AF_INET) : NULL;
	}

	if (key) {
		rep.opt[0] = htonl((TCPOPT_NOP << 24) |
				   (TCPOPT_NOP << 16) |
				   (TCPOPT_MD5SIG << 8) |
				   TCPOLEN_MD5SIG);
		/* Update length and the length the header thinks exists */
		arg.iov[0].iov_len += TCPOLEN_MD5SIG_ALIGNED;
		rep.th.doff = arg.iov[0].iov_len / 4;

		tcp_v4_md5_hash_hdr((__u8 *) &rep.opt[1],
				     key, ip_hdr(skb)->saddr,
				     ip_hdr(skb)->daddr, &rep.th);
	}
#endif
	arg.csum = csum_tcpudp_nofold(ip_hdr(skb)->daddr,
				      ip_hdr(skb)->saddr, /* XXX */
				      arg.iov[0].iov_len, IPPROTO_TCP, 0);
	arg.csumoffset = offsetof(struct tcphdr, check) / 2;
	arg.flags = (sk && inet_sk(sk)->transparent) ? IP_REPLY_ARG_NOSRCCHECK : 0;
	/* When socket is gone, all binding information is lost.
	 * routing might fail in this case. No choice here, if we choose to force
	 * input interface, we will misroute in case of asymmetric route.
	 */
	if (sk)
		arg.bound_dev_if = sk->sk_bound_dev_if;

	net = dev_net(skb_dst(skb)->dev);
	arg.tos = ip_hdr(skb)->tos;
	ip_send_unicast_reply(net, skb, ip_hdr(skb)->saddr,
			      ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len);

	TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS);
	TCP_INC_STATS_BH(net, TCP_MIB_OUTRSTS);

#ifdef CONFIG_TCP_MD5SIG
release_sk1:
	if (sk1) {
		rcu_read_unlock();
		sock_put(sk1);
	}
#endif
}

/* The code following below sending ACKs in SYN-RECV and TIME-WAIT states
   outside socket context is ugly, certainly. What can I do?
 */

static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
			    u32 win, u32 tsval, u32 tsecr, int oif,
			    struct tcp_md5sig_key *key,
			    int reply_flags, u8 tos)
{
	const struct tcphdr *th = tcp_hdr(skb);
	struct {
		struct tcphdr th;
		__be32 opt[(TCPOLEN_TSTAMP_ALIGNED >> 2)
#ifdef CONFIG_TCP_MD5SIG
			   + (TCPOLEN_MD5SIG_ALIGNED >> 2)
#endif
			];
	} rep;
	struct ip_reply_arg arg;
	struct net *net = dev_net(skb_dst(skb)->dev);

	memset(&rep.th, 0, sizeof(struct tcphdr));
	memset(&arg, 0, sizeof(arg));

	arg.iov[0].iov_base = (unsigned char *)&rep;
	arg.iov[0].iov_len  = sizeof(rep.th);
	if (tsecr) {
		rep.opt[0] = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
				   (TCPOPT_TIMESTAMP << 8) |
				   TCPOLEN_TIMESTAMP);
		rep.opt[1] = htonl(tsval);
		rep.opt[2] = htonl(tsecr);
		arg.iov[0].iov_len += TCPOLEN_TSTAMP_ALIGNED;
	}

	/* Swap the send and the receive. */
	rep.th.dest    = th->source;
	rep.th.source  = th->dest;
	rep.th.doff    = arg.iov[0].iov_len / 4;
	rep.th.seq     = htonl(seq);
	rep.th.ack_seq = htonl(ack);
	rep.th.ack     = 1;
	rep.th.window  = htons(win);

#ifdef CONFIG_TCP_MD5SIG
	if (key) {
		int offset = (tsecr) ? 3 : 0;

		rep.opt[offset++] = htonl((TCPOPT_NOP << 24) |
					  (TCPOPT_NOP << 16) |
					  (TCPOPT_MD5SIG << 8) |
					  TCPOLEN_MD5SIG);
		arg.iov[0].iov_len += TCPOLEN_MD5SIG_ALIGNED;
		rep.th.doff = arg.iov[0].iov_len/4;

		tcp_v4_md5_hash_hdr((__u8 *) &rep.opt[offset],
				    key, ip_hdr(skb)->saddr,
				    ip_hdr(skb)->daddr, &rep.th);
	}
#endif
	arg.flags = reply_flags;
	arg.csum = csum_tcpudp_nofold(ip_hdr(skb)->daddr,
				      ip_hdr(skb)->saddr, /* XXX */
				      arg.iov[0].iov_len, IPPROTO_TCP, 0);
	arg.csumoffset = offsetof(struct tcphdr, check) / 2;
	if (oif)
		arg.bound_dev_if = oif;
	arg.tos = tos;
	ip_send_unicast_reply(net, skb, ip_hdr(skb)->saddr,
			      ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len);

	TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS);
}

static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
{
	struct inet_timewait_sock *tw = inet_twsk(sk);
	struct tcp_timewait_sock *tcptw = tcp_twsk(sk);

	tcp_v4_send_ack(skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
			tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
			tcp_time_stamp + tcptw->tw_ts_offset,
			tcptw->tw_ts_recent,
			tw->tw_bound_dev_if,
			tcp_twsk_md5_key(tcptw),
			tw->tw_transparent ? IP_REPLY_ARG_NOSRCCHECK : 0,
			tw->tw_tos
			);

	inet_twsk_put(tw);
}

static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
				  struct request_sock *req)
{
	/* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV
	 * sk->sk_state == TCP_SYN_RECV -> for Fast Open.
	 */
	tcp_v4_send_ack(skb, (sk->sk_state == TCP_LISTEN) ?
			tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt,
			tcp_rsk(req)->rcv_nxt, req->rcv_wnd,
			tcp_time_stamp,
			req->ts_recent,
			0,
			tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->daddr,
					  AF_INET),
			inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0,
			ip_hdr(skb)->tos);
}

/*
 *	Send a SYN-ACK after having received a SYN.
 *	This still operates on a request_sock only, not on a big
 *	socket.
 */
static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst,
			      struct request_sock *req,
			      u16 queue_mapping)
{
	const struct inet_request_sock *ireq = inet_rsk(req);
	struct flowi4 fl4;
	int err = -1;
	struct sk_buff * skb;

	/* First, grab a route. */
	if (!dst && (dst = inet_csk_route_req(sk, &fl4, req)) == NULL)
		return -1;

	skb = tcp_make_synack(sk, dst, req, NULL);

	if (skb) {
		__tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr);

		skb_set_queue_mapping(skb, queue_mapping);
		err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
					    ireq->ir_rmt_addr,
					    ireq->opt);
		err = net_xmit_eval(err);
		if (!tcp_rsk(req)->snt_synack && !err)
			tcp_rsk(req)->snt_synack = tcp_time_stamp;
	}

	return err;
}

static int tcp_v4_rtx_synack(struct sock *sk, struct request_sock *req)
{
	int res = tcp_v4_send_synack(sk, NULL, req, 0);

	if (!res)
		TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS);
	return res;
}

/*
 *	IPv4 request_sock destructor.
 */
static void tcp_v4_reqsk_destructor(struct request_sock *req)
{
	kfree(inet_rsk(req)->opt);
}

/*
 * Return true if a syncookie should be sent
 */
bool tcp_syn_flood_action(struct sock *sk,
			 const struct sk_buff *skb,
			 const char *proto)
{
	const char *msg = "Dropping request";
	bool want_cookie = false;
	struct listen_sock *lopt;



#ifdef CONFIG_SYN_COOKIES
	if (sysctl_tcp_syncookies) {
		msg = "Sending cookies";
		want_cookie = true;
		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPREQQFULLDOCOOKIES);
	} else
#endif
		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPREQQFULLDROP);

	lopt = inet_csk(sk)->icsk_accept_queue.listen_opt;
	if (!lopt->synflood_warned && sysctl_tcp_syncookies != 2) {
		lopt->synflood_warned = 1;
		pr_info("%s: Possible SYN flooding on port %d. %s.  Check SNMP counters.\n",
			proto, ntohs(tcp_hdr(skb)->dest), msg);
	}
	return want_cookie;
}
EXPORT_SYMBOL(tcp_syn_flood_action);

/*
 * Save and compile IPv4 options into the request_sock if needed.
 */
static struct ip_options_rcu *tcp_v4_save_options(struct sk_buff *skb)
{
	const struct ip_options *opt = &(IPCB(skb)->opt);
	struct ip_options_rcu *dopt = NULL;

	if (opt && opt->optlen) {
		int opt_size = sizeof(*dopt) + opt->optlen;

		dopt = kmalloc(opt_size, GFP_ATOMIC);
		if (dopt) {
			if (ip_options_echo(&dopt->opt, skb)) {
				kfree(dopt);
				dopt = NULL;
			}
		}
	}
	return dopt;
}

#ifdef CONFIG_TCP_MD5SIG
/*
 * RFC2385 MD5 checksumming requires a mapping of
 * IP address->MD5 Key.
 * We need to maintain these in the sk structure.
 */

/* Find the Key structure for an address.  */
struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk,
					 const union tcp_md5_addr *addr,
					 int family)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct tcp_md5sig_key *key;
	unsigned int size = sizeof(struct in_addr);
	struct tcp_md5sig_info *md5sig;

	/* caller either holds rcu_read_lock() or socket lock */
	md5sig = rcu_dereference_check(tp->md5sig_info,
				       sock_owned_by_user(sk) ||
				       lockdep_is_held(&sk->sk_lock.slock));
	if (!md5sig)
		return NULL;
#if IS_ENABLED(CONFIG_IPV6)
	if (family == AF_INET6)
		size = sizeof(struct in6_addr);
#endif
	hlist_for_each_entry_rcu(key, &md5sig->head, node) {
		if (key->family != family)
			continue;
		if (!memcmp(&key->addr, addr, size))
			return key;
	}
	return NULL;
}
EXPORT_SYMBOL(tcp_md5_do_lookup);

struct tcp_md5sig_key *tcp_v4_md5_lookup(struct sock *sk,
					 struct sock *addr_sk)
{
	union tcp_md5_addr *addr;

	addr = (union tcp_md5_addr *)&inet_sk(addr_sk)->inet_daddr;
	return tcp_md5_do_lookup(sk, addr, AF_INET);
}
EXPORT_SYMBOL(tcp_v4_md5_lookup);

static struct tcp_md5sig_key *tcp_v4_reqsk_md5_lookup(struct sock *sk,
						      struct request_sock *req)
{
	union tcp_md5_addr *addr;

	addr = (union tcp_md5_addr *)&inet_rsk(req)->ir_rmt_addr;
	return tcp_md5_do_lookup(sk, addr, AF_INET);
}

/* This can be called on a newly created socket, from other files */
int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
		   int family, const u8 *newkey, u8 newkeylen, gfp_t gfp)
{
	/* Add Key to the list */
	struct tcp_md5sig_key *key;
	struct tcp_sock *tp = tcp_sk(sk);
	struct tcp_md5sig_info *md5sig;

	key = tcp_md5_do_lookup(sk, addr, family);
	if (key) {
		/* Pre-existing entry - just update that one. */
		memcpy(key->key, newkey, newkeylen);
		key->keylen = newkeylen;
		return 0;
	}

	md5sig = rcu_dereference_protected(tp->md5sig_info,
					   sock_owned_by_user(sk));
	if (!md5sig) {
		md5sig = kmalloc(sizeof(*md5sig), gfp);
		if (!md5sig)
			return -ENOMEM;

		sk_nocaps_add(sk, NETIF_F_GSO_MASK);
		INIT_HLIST_HEAD(&md5sig->head);
		rcu_assign_pointer(tp->md5sig_info, md5sig);
	}

	key = sock_kmalloc(sk, sizeof(*key), gfp);
	if (!key)
		return -ENOMEM;
	if (!tcp_alloc_md5sig_pool()) {
		sock_kfree_s(sk, key, sizeof(*key));
		return -ENOMEM;
	}

	memcpy(key->key, newkey, newkeylen);
	key->keylen = newkeylen;
	key->family = family;
	memcpy(&key->addr, addr,
	       (family == AF_INET6) ? sizeof(struct in6_addr) :
				      sizeof(struct in_addr));
	hlist_add_head_rcu(&key->node, &md5sig->head);
	return 0;
}
EXPORT_SYMBOL(tcp_md5_do_add);

int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family)
{
	struct tcp_md5sig_key *key;

	key = tcp_md5_do_lookup(sk, addr, family);
	if (!key)
		return -ENOENT;
	hlist_del_rcu(&key->node);
	atomic_sub(sizeof(*key), &sk->sk_omem_alloc);
	kfree_rcu(key, rcu);
	return 0;
}
EXPORT_SYMBOL(tcp_md5_do_del);

static void tcp_clear_md5_list(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct tcp_md5sig_key *key;
	struct hlist_node *n;
	struct tcp_md5sig_info *md5sig;

	md5sig = rcu_dereference_protected(tp->md5sig_info, 1);

	hlist_for_each_entry_safe(key, n, &md5sig->head, node) {
		hlist_del_rcu(&key->node);
		atomic_sub(sizeof(*key), &sk->sk_omem_alloc);
		kfree_rcu(key, rcu);
	}
}

static int tcp_v4_parse_md5_keys(struct sock *sk, char __user *optval,
				 int optlen)
{
	struct tcp_md5sig cmd;
	struct sockaddr_in *sin = (struct sockaddr_in *)&cmd.tcpm_addr;

	if (optlen < sizeof(cmd))
		return -EINVAL;

	if (copy_from_user(&cmd, optval, sizeof(cmd)))
		return -EFAULT;

	if (sin->sin_family != AF_INET)
		return -EINVAL;

	if (!cmd.tcpm_key || !cmd.tcpm_keylen)
		return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin->sin_addr.s_addr,
				      AF_INET);

	if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN)
		return -EINVAL;

	return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin->sin_addr.s_addr,
			      AF_INET, cmd.tcpm_key, cmd.tcpm_keylen,
			      GFP_KERNEL);
}

static int tcp_v4_md5_hash_pseudoheader(struct tcp_md5sig_pool *hp,
					__be32 daddr, __be32 saddr, int nbytes)
{
	struct tcp4_pseudohdr *bp;
	struct scatterlist sg;

	bp = &hp->md5_blk.ip4;

	/*
	 * 1. the TCP pseudo-header (in the order: source IP address,
	 * destination IP address, zero-padded protocol number, and
	 * segment length)
	 */
	bp->saddr = saddr;
	bp->daddr = daddr;
	bp->pad = 0;
	bp->protocol = IPPROTO_TCP;
	bp->len = cpu_to_be16(nbytes);

	sg_init_one(&sg, bp, sizeof(*bp));
	return crypto_hash_update(&hp->md5_desc, &sg, sizeof(*bp));
}

static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
			       __be32 daddr, __be32 saddr, const struct tcphdr *th)
{
	struct tcp_md5sig_pool *hp;
	struct hash_desc *desc;

	hp = tcp_get_md5sig_pool();
	if (!hp)
		goto clear_hash_noput;
	desc = &hp->md5_desc;

	if (crypto_hash_init(desc))
		goto clear_hash;
	if (tcp_v4_md5_hash_pseudoheader(hp, daddr, saddr, th->doff << 2))
		goto clear_hash;
	if (tcp_md5_hash_header(hp, th))
		goto clear_hash;
	if (tcp_md5_hash_key(hp, key))
		goto clear_hash;
	if (crypto_hash_final(desc, md5_hash))
		goto clear_hash;

	tcp_put_md5sig_pool();
	return 0;

clear_hash:
	tcp_put_md5sig_pool();
clear_hash_noput:
	memset(md5_hash, 0, 16);
	return 1;
}

int tcp_v4_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key,
			const struct sock *sk, const struct request_sock *req,
			const struct sk_buff *skb)
{
	struct tcp_md5sig_pool *hp;
	struct hash_desc *desc;
	const struct tcphdr *th = tcp_hdr(skb);
	__be32 saddr, daddr;

	if (sk) {
		saddr = inet_sk(sk)->inet_saddr;
		daddr = inet_sk(sk)->inet_daddr;
	} else if (req) {
		saddr = inet_rsk(req)->ir_loc_addr;
		daddr = inet_rsk(req)->ir_rmt_addr;
	} else {
		const struct iphdr *iph = ip_hdr(skb);
		saddr = iph->saddr;
		daddr = iph->daddr;
	}

	hp = tcp_get_md5sig_pool();
	if (!hp)
		goto clear_hash_noput;
	desc = &hp->md5_desc;

	if (crypto_hash_init(desc))
		goto clear_hash;

	if (tcp_v4_md5_hash_pseudoheader(hp, daddr, saddr, skb->len))
		goto clear_hash;
	if (tcp_md5_hash_header(hp, th))
		goto clear_hash;
	if (tcp_md5_hash_skb_data(hp, skb, th->doff << 2))
		goto clear_hash;
	if (tcp_md5_hash_key(hp, key))
		goto clear_hash;
	if (crypto_hash_final(desc, md5_hash))
		goto clear_hash;

	tcp_put_md5sig_pool();
	return 0;

clear_hash:
	tcp_put_md5sig_pool();
clear_hash_noput:
	memset(md5_hash, 0, 16);
	return 1;
}
EXPORT_SYMBOL(tcp_v4_md5_hash_skb);

static bool tcp_v4_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb)
{
	/*
	 * This gets called for each TCP segment that arrives
	 * so we want to be efficient.
	 * We have 3 drop cases:
	 * o No MD5 hash and one expected.
	 * o MD5 hash and we're not expecting one.
	 * o MD5 hash and its wrong.
	 */
	const __u8 *hash_location = NULL;
	struct tcp_md5sig_key *hash_expected;
	const struct iphdr *iph = ip_hdr(skb);
	const struct tcphdr *th = tcp_hdr(skb);
	int genhash;
	unsigned char newhash[16];

	hash_expected = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&iph->saddr,
					  AF_INET);
	hash_location = tcp_parse_md5sig_option(th);

	/* We've parsed the options - do we have a hash? */
	if (!hash_expected && !hash_location)
		return false;

	if (hash_expected && !hash_location) {
		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND);
		return true;
	}

	if (!hash_expected && hash_location) {
		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED);
		return true;
	}

	/* Okay, so this is hash_expected and hash_location -
	 * so we need to calculate the checksum.
	 */
	genhash = tcp_v4_md5_hash_skb(newhash,
				      hash_expected,
				      NULL, NULL, skb);

	if (genhash || memcmp(hash_location, newhash, 16) != 0) {
		net_info_ratelimited("MD5 Hash failed for (%pI4, %d)->(%pI4, %d)%s\n",
				     &iph->saddr, ntohs(th->source),
				     &iph->daddr, ntohs(th->dest),
				     genhash ? " tcp_v4_calc_md5_hash failed"
				     : "");
		return true;
	}
	return false;
}

#endif

struct request_sock_ops tcp_request_sock_ops __read_mostly = {
	.family		=	PF_INET,
	.obj_size	=	sizeof(struct tcp_request_sock),
	.rtx_syn_ack	=	tcp_v4_rtx_synack,
	.send_ack	=	tcp_v4_reqsk_send_ack,
	.destructor	=	tcp_v4_reqsk_destructor,
	.send_reset	=	tcp_v4_send_reset,
	.syn_ack_timeout = 	tcp_syn_ack_timeout,
};

#ifdef CONFIG_TCP_MD5SIG
static const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = {
	.md5_lookup	=	tcp_v4_reqsk_md5_lookup,
	.calc_md5_hash	=	tcp_v4_md5_hash_skb,
};
#endif

static bool tcp_fastopen_check(struct sock *sk, struct sk_buff *skb,
			       struct request_sock *req,
			       struct tcp_fastopen_cookie *foc,
			       struct tcp_fastopen_cookie *valid_foc)
{
	bool skip_cookie = false;
	struct fastopen_queue *fastopenq;

	if (likely(!fastopen_cookie_present(foc))) {
		/* See include/net/tcp.h for the meaning of these knobs */
		if ((sysctl_tcp_fastopen & TFO_SERVER_ALWAYS) ||
		    ((sysctl_tcp_fastopen & TFO_SERVER_COOKIE_NOT_REQD) &&
		    (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1)))
			skip_cookie = true; /* no cookie to validate */
		else
			return false;
	}
	fastopenq = inet_csk(sk)->icsk_accept_queue.fastopenq;
	/* A FO option is present; bump the counter. */
	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENPASSIVE);

	/* Make sure the listener has enabled fastopen, and we don't
	 * exceed the max # of pending TFO requests allowed before trying
	 * to validating the cookie in order to avoid burning CPU cycles
	 * unnecessarily.
	 *
	 * XXX (TFO) - The implication of checking the max_qlen before
	 * processing a cookie request is that clients can't differentiate
	 * between qlen overflow causing Fast Open to be disabled
	 * temporarily vs a server not supporting Fast Open at all.
	 */
	if ((sysctl_tcp_fastopen & TFO_SERVER_ENABLE) == 0 ||
	    fastopenq == NULL || fastopenq->max_qlen == 0)
		return false;

	if (fastopenq->qlen >= fastopenq->max_qlen) {
		struct request_sock *req1;
		spin_lock(&fastopenq->lock);
		req1 = fastopenq->rskq_rst_head;
		if ((req1 == NULL) || time_after(req1->expires, jiffies)) {
			spin_unlock(&fastopenq->lock);
			NET_INC_STATS_BH(sock_net(sk),
			    LINUX_MIB_TCPFASTOPENLISTENOVERFLOW);
			/* Avoid bumping LINUX_MIB_TCPFASTOPENPASSIVEFAIL*/
			foc->len = -1;
			return false;
		}
		fastopenq->rskq_rst_head = req1->dl_next;
		fastopenq->qlen--;
		spin_unlock(&fastopenq->lock);
		reqsk_free(req1);
	}
	if (skip_cookie) {
		tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
		return true;
	}

	if (foc->len == TCP_FASTOPEN_COOKIE_SIZE) {
		if ((sysctl_tcp_fastopen & TFO_SERVER_COOKIE_NOT_CHKED) == 0) {
			tcp_fastopen_cookie_gen(ip_hdr(skb)->saddr,
						ip_hdr(skb)->daddr, valid_foc);
			if ((valid_foc->len != TCP_FASTOPEN_COOKIE_SIZE) ||
			    memcmp(&foc->val[0], &valid_foc->val[0],
			    TCP_FASTOPEN_COOKIE_SIZE) != 0)
				return false;
			valid_foc->len = -1;
		}
		/* Acknowledge the data received from the peer. */
		tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
		return true;
	} else if (foc->len == 0) { /* Client requesting a cookie */
		tcp_fastopen_cookie_gen(ip_hdr(skb)->saddr,
					ip_hdr(skb)->daddr, valid_foc);
		NET_INC_STATS_BH(sock_net(sk),
		    LINUX_MIB_TCPFASTOPENCOOKIEREQD);
	} else {
		/* Client sent a cookie with wrong size. Treat it
		 * the same as invalid and return a valid one.
		 */
		tcp_fastopen_cookie_gen(ip_hdr(skb)->saddr,
					ip_hdr(skb)->daddr, valid_foc);
	}
	return false;
}

static int tcp_v4_conn_req_fastopen(struct sock *sk,
				    struct sk_buff *skb,
				    struct sk_buff *skb_synack,
				    struct request_sock *req)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
	const struct inet_request_sock *ireq = inet_rsk(req);
	struct sock *child;
	int err;

	req->num_retrans = 0;
	req->num_timeout = 0;
	req->sk = NULL;

	child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL);
	if (child == NULL) {
		NET_INC_STATS_BH(sock_net(sk),
				 LINUX_MIB_TCPFASTOPENPASSIVEFAIL);
		kfree_skb(skb_synack);
		return -1;
	}
	err = ip_build_and_send_pkt(skb_synack, sk, ireq->ir_loc_addr,
				    ireq->ir_rmt_addr, ireq->opt);
	err = net_xmit_eval(err);
	if (!err)
		tcp_rsk(req)->snt_synack = tcp_time_stamp;
	/* XXX (TFO) - is it ok to ignore error and continue? */

	spin_lock(&queue->fastopenq->lock);
	queue->fastopenq->qlen++;
	spin_unlock(&queue->fastopenq->lock);

	/* Initialize the child socket. Have to fix some values to take
	 * into account the child is a Fast Open socket and is created
	 * only out of the bits carried in the SYN packet.
	 */
	tp = tcp_sk(child);

	tp->fastopen_rsk = req;
	/* Do a hold on the listner sk so that if the listener is being
	 * closed, the child that has been accepted can live on and still
	 * access listen_lock.
	 */
	sock_hold(sk);
	tcp_rsk(req)->listener = sk;

	/* RFC1323: The window in SYN & SYN/ACK segments is never
	 * scaled. So correct it appropriately.
	 */
	tp->snd_wnd = ntohs(tcp_hdr(skb)->window);

	/* Activate the retrans timer so that SYNACK can be retransmitted.
	 * The request socket is not added to the SYN table of the parent
	 * because it's been added to the accept queue directly.
	 */
	inet_csk_reset_xmit_timer(child, ICSK_TIME_RETRANS,
	    TCP_TIMEOUT_INIT, TCP_RTO_MAX);

	/* Add the child socket directly into the accept queue */
	inet_csk_reqsk_queue_add(sk, req, child);

	/* Now finish processing the fastopen child socket. */
	inet_csk(child)->icsk_af_ops->rebuild_header(child);
	tcp_init_congestion_control(child);
	tcp_mtup_init(child);
	tcp_init_metrics(child);
	tcp_init_buffer_space(child);

	/* Queue the data carried in the SYN packet. We need to first
	 * bump skb's refcnt because the caller will attempt to free it.
	 *
	 * XXX (TFO) - we honor a zero-payload TFO request for now.
	 * (Any reason not to?)
	 */
	if (TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq + 1) {
		/* Don't queue the skb if there is no payload in SYN.
		 * XXX (TFO) - How about SYN+FIN?
		 */
		tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
	} else {
		skb = skb_get(skb);
		skb_dst_drop(skb);
		__skb_pull(skb, tcp_hdr(skb)->doff * 4);
		skb_set_owner_r(skb, child);
		__skb_queue_tail(&child->sk_receive_queue, skb);
		tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
		tp->syn_data_acked = 1;
	}
	sk->sk_data_ready(sk, 0);
	bh_unlock_sock(child);
	sock_put(child);
	WARN_ON(req->sk == NULL);
	return 0;
}

int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
{
	struct tcp_options_received tmp_opt;
	struct request_sock *req;
	struct inet_request_sock *ireq;
	struct tcp_sock *tp = tcp_sk(sk);
	struct dst_entry *dst = NULL;
	__be32 saddr = ip_hdr(skb)->saddr;
	__be32 daddr = ip_hdr(skb)->daddr;
	__u32 isn = TCP_SKB_CB(skb)->when;
	bool want_cookie = false;
	struct flowi4 fl4;
	struct tcp_fastopen_cookie foc = { .len = -1 };
	struct tcp_fastopen_cookie valid_foc = { .len = -1 };
	struct sk_buff *skb_synack;
	int do_fastopen;

	/* Never answer to SYNs send to broadcast or multicast */
	if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
		goto drop;

	/* TW buckets are converted to open requests without
	 * limitations, they conserve resources and peer is
	 * evidently real one.
	 */
	if ((sysctl_tcp_syncookies == 2 ||
	     inet_csk_reqsk_queue_is_full(sk)) && !isn) {
		want_cookie = tcp_syn_flood_action(sk, skb, "TCP");
		if (!want_cookie)
			goto drop;
	}

	/* Accept backlog is full. If we have already queued enough
	 * of warm entries in syn queue, drop request. It is better than
	 * clogging syn queue with openreqs with exponentially increasing
	 * timeout.
	 */
	if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) {
		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS);
		goto drop;
	}

	req = inet_reqsk_alloc(&tcp_request_sock_ops);
	if (!req)
		goto drop;

#ifdef CONFIG_TCP_MD5SIG
	tcp_rsk(req)->af_specific = &tcp_request_sock_ipv4_ops;
#endif

	tcp_clear_options(&tmp_opt);
	tmp_opt.mss_clamp = TCP_MSS_DEFAULT;
	tmp_opt.user_mss  = tp->rx_opt.user_mss;
	tcp_parse_options(skb, &tmp_opt, 0, want_cookie ? NULL : &foc);

	if (want_cookie && !tmp_opt.saw_tstamp)
		tcp_clear_options(&tmp_opt);

	tmp_opt.tstamp_ok = tmp_opt.saw_tstamp;
	tcp_openreq_init(req, &tmp_opt, skb);

	ireq = inet_rsk(req);
	ireq->ir_loc_addr = daddr;
	ireq->ir_rmt_addr = saddr;
	ireq->no_srccheck = inet_sk(sk)->transparent;
	ireq->opt = tcp_v4_save_options(skb);

	if (security_inet_conn_request(sk, skb, req))
		goto drop_and_free;

	if (!want_cookie || tmp_opt.tstamp_ok)
		TCP_ECN_create_request(req, skb, sock_net(sk));

	if (want_cookie) {
		isn = cookie_v4_init_sequence(sk, skb, &req->mss);
		req->cookie_ts = tmp_opt.tstamp_ok;
	} else if (!isn) {
		/* VJ's idea. We save last timestamp seen
		 * from the destination in peer table, when entering
		 * state TIME-WAIT, and check against it before
		 * accepting new connection request.
		 *
		 * If "isn" is not zero, this request hit alive
		 * timewait bucket, so that all the necessary checks
		 * are made in the function processing timewait state.
		 */
		if (tmp_opt.saw_tstamp &&
		    tcp_death_row.sysctl_tw_recycle &&
		    (dst = inet_csk_route_req(sk, &fl4, req)) != NULL &&
		    fl4.daddr == saddr) {
			if (!tcp_peer_is_proven(req, dst, true)) {
				NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSPASSIVEREJECTED);
				goto drop_and_release;
			}
		}
		/* Kill the following clause, if you dislike this way. */
		else if (!sysctl_tcp_syncookies &&
			 (sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) <
			  (sysctl_max_syn_backlog >> 2)) &&
			 !tcp_peer_is_proven(req, dst, false)) {
			/* Without syncookies last quarter of
			 * backlog is filled with destinations,
			 * proven to be alive.
			 * It means that we continue to communicate
			 * to destinations, already remembered
			 * to the moment of synflood.
			 */
			LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("drop open request from %pI4/%u\n"),
				       &saddr, ntohs(tcp_hdr(skb)->source));
			goto drop_and_release;
		}

		isn = tcp_v4_init_sequence(skb);
	}
	tcp_rsk(req)->snt_isn = isn;

	if (dst == NULL) {
		dst = inet_csk_route_req(sk, &fl4, req);
		if (dst == NULL)
			goto drop_and_free;
	}
	do_fastopen = tcp_fastopen_check(sk, skb, req, &foc, &valid_foc);

	/* We don't call tcp_v4_send_synack() directly because we need
	 * to make sure a child socket can be created successfully before
	 * sending back synack!
	 *
	 * XXX (TFO) - Ideally one would simply call tcp_v4_send_synack()
	 * (or better yet, call tcp_send_synack() in the child context
	 * directly, but will have to fix bunch of other code first)
	 * after syn_recv_sock() except one will need to first fix the
	 * latter to remove its dependency on the current implementation
	 * of tcp_v4_send_synack()->tcp_select_initial_window().
	 */
	skb_synack = tcp_make_synack(sk, dst, req,
	    fastopen_cookie_present(&valid_foc) ? &valid_foc : NULL);

	if (skb_synack) {
		__tcp_v4_send_check(skb_synack, ireq->ir_loc_addr, ireq->ir_rmt_addr);
		skb_set_queue_mapping(skb_synack, skb_get_queue_mapping(skb));


context:
space:
mode: