kernel-fxtec-pro1x/net/ipv4/tcp_ipv4.c

2657 lines
67 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).
*
* 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.
*/
#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 cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h 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>
2010-03-24 02:04:11 -06:00
#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 <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 struct tcp_md5sig_key *tcp_v4_md5_do_lookup(struct sock *sk,
__be32 addr);
static int tcp_v4_md5_hash_hdr(char *md5_hash, struct tcp_md5sig_key *key,
__be32 daddr, __be32 saddr, struct tcphdr *th);
#else
static inline
struct tcp_md5sig_key *tcp_v4_md5_do_lookup(struct sock *sk, __be32 addr)
{
return NULL;
}
#endif
struct inet_hashinfo tcp_hashinfo;
EXPORT_SYMBOL(tcp_hashinfo);
static inline __u32 tcp_v4_init_sequence(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 inet_sock *inet = inet_sk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct sockaddr_in *usin = (struct sockaddr_in *)uaddr;
struct rtable *rt;
__be32 daddr, nexthop;
int tmp;
int err;
if (addr_len < sizeof(struct sockaddr_in))
return -EINVAL;
if (usin->sin_family != AF_INET)
return -EAFNOSUPPORT;
nexthop = daddr = usin->sin_addr.s_addr;
if (inet->opt && inet->opt->srr) {
if (!daddr)
return -EINVAL;
nexthop = inet->opt->faddr;
}
tmp = ip_route_connect(&rt, nexthop, inet->inet_saddr,
RT_CONN_FLAGS(sk), sk->sk_bound_dev_if,
IPPROTO_TCP,
inet->inet_sport, usin->sin_port, sk, 1);
if (tmp < 0) {
if (tmp == -ENETUNREACH)
IP_INC_STATS_BH(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
return tmp;
}
if (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST)) {
ip_rt_put(rt);
return -ENETUNREACH;
}
if (!inet->opt || !inet->opt->srr)
daddr = rt->rt_dst;
if (!inet->inet_saddr)
inet->inet_saddr = rt->rt_src;
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;
tp->write_seq = 0;
}
if (tcp_death_row.sysctl_tw_recycle &&
!tp->rx_opt.ts_recent_stamp && rt->rt_dst == daddr) {
struct inet_peer *peer = rt_get_peer(rt);
/*
* VJ's idea. We save last timestamp seen from
* the destination in peer table, when entering state
* TIME-WAIT * and initialize rx_opt.ts_recent from it,
* when trying new connection.
*/
if (peer) {
inet_peer_refcheck(peer);
if ((u32)get_seconds() - peer->tcp_ts_stamp <= TCP_PAWS_MSL) {
tp->rx_opt.ts_recent_stamp = peer->tcp_ts_stamp;
tp->rx_opt.ts_recent = peer->tcp_ts;
}
}
}
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->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;
err = ip_route_newports(&rt, IPPROTO_TCP,
inet->inet_sport, inet->inet_dport, sk);
if (err)
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)
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 does path mtu discovery as defined in RFC1191.
*/
static void do_pmtu_discovery(struct sock *sk, struct iphdr *iph, u32 mtu)
{
struct dst_entry *dst;
struct inet_sock *inet = inet_sk(sk);
/* 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)
return;
/* We don't check in the destentry if pmtu discovery is forbidden
* on this route. We just assume that no packet_to_big packets
* are send back when pmtu discovery is not active.
* There is a small race when the user changes this flag in the
* route, but I think that's acceptable.
*/
if ((dst = __sk_dst_check(sk, 0)) == NULL)
return;
dst->ops->update_pmtu(dst, mtu);
/* 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 &&
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 */
}
/*
* 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)
{
struct iphdr *iph = (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;
__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.
*/
if (sock_owned_by_user(sk))
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);
seq = ntohl(th->seq);
if (sk->sk_state != TCP_LISTEN &&
!between(seq, tp->snd_una, tp->snd_nxt)) {
NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
goto out;
}
switch (type) {
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) */
if (!sock_owned_by_user(sk))
do_pmtu_discovery(sk, iph, info);
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;
icsk->icsk_backoff--;
inet_csk(sk)->icsk_rto = __tcp_set_rto(tp) <<
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 if (sock_owned_by_user(sk)) {
/* RTO revert clocked out retransmission,
* but socket is locked. Will defer. */
inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
HZ/20, 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;
}
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);
goto out;
case TCP_SYN_SENT:
case TCP_SYN_RECV: /* Cannot happen.
It can f.e. if SYNs crossed.
*/
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);
}
static 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)
{
struct inet_sock *inet = inet_sk(sk);
__tcp_v4_send_check(skb, inet->inet_saddr, inet->inet_daddr);
}
EXPORT_SYMBOL(tcp_v4_send_check);
int tcp_v4_gso_send_check(struct sk_buff *skb)
{
const struct iphdr *iph;
struct tcphdr *th;
if (!pskb_may_pull(skb, sizeof(*th)))
return -EINVAL;
iph = ip_hdr(skb);
th = tcp_hdr(skb);
th->check = 0;
skb->ip_summed = CHECKSUM_PARTIAL;
__tcp_v4_send_check(skb, iph->saddr, iph->daddr);
return 0;
}
/*
* 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)
{
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;
#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
key = sk ? tcp_v4_md5_do_lookup(sk, ip_hdr(skb)->daddr) : 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;
net = dev_net(skb_dst(skb)->dev);
ip_send_reply(net->ipv4.tcp_sock, skb,
&arg, arg.iov[0].iov_len);
TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS);
TCP_INC_STATS_BH(net, TCP_MIB_OUTRSTS);
}
/* 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 ts, int oif,
struct tcp_md5sig_key *key,
int reply_flags)
{
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 (ts) {
rep.opt[0] = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
(TCPOPT_TIMESTAMP << 8) |
TCPOLEN_TIMESTAMP);
rep.opt[1] = htonl(tcp_time_stamp);
rep.opt[2] = htonl(ts);
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 = (ts) ? 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;
ip_send_reply(net->ipv4.tcp_sock, skb,
&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,
tcptw->tw_ts_recent,
tw->tw_bound_dev_if,
tcp_twsk_md5_key(tcptw),
tw->tw_transparent ? IP_REPLY_ARG_NOSRCCHECK : 0
);
inet_twsk_put(tw);
}
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 00:50:04 -06:00
static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
struct request_sock *req)
{
tcp_v4_send_ack(skb, tcp_rsk(req)->snt_isn + 1,
tcp_rsk(req)->rcv_isn + 1, req->rcv_wnd,
req->ts_recent,
0,
tcp_v4_md5_do_lookup(sk, ip_hdr(skb)->daddr),
inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0);
}
/*
* 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,
struct request_values *rvp)
{
const struct inet_request_sock *ireq = inet_rsk(req);
int err = -1;
struct sk_buff * skb;
/* First, grab a route. */
if (!dst && (dst = inet_csk_route_req(sk, req)) == NULL)
return -1;
skb = tcp_make_synack(sk, dst, req, rvp);
if (skb) {
__tcp_v4_send_check(skb, ireq->loc_addr, ireq->rmt_addr);
err = ip_build_and_send_pkt(skb, sk, ireq->loc_addr,
ireq->rmt_addr,
ireq->opt);
err = net_xmit_eval(err);
}
dst_release(dst);
return err;
}
static int tcp_v4_rtx_synack(struct sock *sk, struct request_sock *req,
struct request_values *rvp)
{
TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS);
return tcp_v4_send_synack(sk, NULL, req, rvp);
}
/*
* IPv4 request_sock destructor.
*/
static void tcp_v4_reqsk_destructor(struct request_sock *req)
{
kfree(inet_rsk(req)->opt);
}
static void syn_flood_warning(const struct sk_buff *skb)
{
const char *msg;
#ifdef CONFIG_SYN_COOKIES
if (sysctl_tcp_syncookies)
msg = "Sending cookies";
else
#endif
msg = "Dropping request";
pr_info("TCP: Possible SYN flooding on port %d. %s.\n",
ntohs(tcp_hdr(skb)->dest), msg);
}
/*
* Save and compile IPv4 options into the request_sock if needed.
*/
static struct ip_options *tcp_v4_save_options(struct sock *sk,
struct sk_buff *skb)
{
struct ip_options *opt = &(IPCB(skb)->opt);
struct ip_options *dopt = NULL;
if (opt && opt->optlen) {
int opt_size = optlength(opt);
dopt = kmalloc(opt_size, GFP_ATOMIC);
if (dopt) {
if (ip_options_echo(dopt, 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. */
static struct tcp_md5sig_key *
tcp_v4_md5_do_lookup(struct sock *sk, __be32 addr)
{
struct tcp_sock *tp = tcp_sk(sk);
int i;
if (!tp->md5sig_info || !tp->md5sig_info->entries4)
return NULL;
for (i = 0; i < tp->md5sig_info->entries4; i++) {
if (tp->md5sig_info->keys4[i].addr == addr)
return &tp->md5sig_info->keys4[i].base;
}
return NULL;
}
struct tcp_md5sig_key *tcp_v4_md5_lookup(struct sock *sk,
struct sock *addr_sk)
{
return tcp_v4_md5_do_lookup(sk, inet_sk(addr_sk)->inet_daddr);
}
EXPORT_SYMBOL(tcp_v4_md5_lookup);
static struct tcp_md5sig_key *tcp_v4_reqsk_md5_lookup(struct sock *sk,
struct request_sock *req)
{
return tcp_v4_md5_do_lookup(sk, inet_rsk(req)->rmt_addr);
}
/* This can be called on a newly created socket, from other files */
int tcp_v4_md5_do_add(struct sock *sk, __be32 addr,
u8 *newkey, u8 newkeylen)
{
/* Add Key to the list */
struct tcp_md5sig_key *key;
struct tcp_sock *tp = tcp_sk(sk);
struct tcp4_md5sig_key *keys;
key = tcp_v4_md5_do_lookup(sk, addr);
if (key) {
/* Pre-existing entry - just update that one. */
kfree(key->key);
key->key = newkey;
key->keylen = newkeylen;
} else {
struct tcp_md5sig_info *md5sig;
if (!tp->md5sig_info) {
tp->md5sig_info = kzalloc(sizeof(*tp->md5sig_info),
GFP_ATOMIC);
if (!tp->md5sig_info) {
kfree(newkey);
return -ENOMEM;
}
sk_nocaps_add(sk, NETIF_F_GSO_MASK);
}
if (tcp_alloc_md5sig_pool(sk) == NULL) {
kfree(newkey);
return -ENOMEM;
}
md5sig = tp->md5sig_info;
if (md5sig->alloced4 == md5sig->entries4) {
keys = kmalloc((sizeof(*keys) *
(md5sig->entries4 + 1)), GFP_ATOMIC);
if (!keys) {
kfree(newkey);
tcp_free_md5sig_pool();
return -ENOMEM;
}
if (md5sig->entries4)
memcpy(keys, md5sig->keys4,
sizeof(*keys) * md5sig->entries4);
/* Free old key list, and reference new one */
kfree(md5sig->keys4);
md5sig->keys4 = keys;
md5sig->alloced4++;
}
md5sig->entries4++;
md5sig->keys4[md5sig->entries4 - 1].addr = addr;
md5sig->keys4[md5sig->entries4 - 1].base.key = newkey;
md5sig->keys4[md5sig->entries4 - 1].base.keylen = newkeylen;
}
return 0;
}
EXPORT_SYMBOL(tcp_v4_md5_do_add);
static int tcp_v4_md5_add_func(struct sock *sk, struct sock *addr_sk,
u8 *newkey, u8 newkeylen)
{
return tcp_v4_md5_do_add(sk, inet_sk(addr_sk)->inet_daddr,
newkey, newkeylen);
}
int tcp_v4_md5_do_del(struct sock *sk, __be32 addr)
{
struct tcp_sock *tp = tcp_sk(sk);
int i;
for (i = 0; i < tp->md5sig_info->entries4; i++) {
if (tp->md5sig_info->keys4[i].addr == addr) {
/* Free the key */
kfree(tp->md5sig_info->keys4[i].base.key);
tp->md5sig_info->entries4--;
if (tp->md5sig_info->entries4 == 0) {
kfree(tp->md5sig_info->keys4);
tp->md5sig_info->keys4 = NULL;
tp->md5sig_info->alloced4 = 0;
} else if (tp->md5sig_info->entries4 != i) {
/* Need to do some manipulation */
memmove(&tp->md5sig_info->keys4[i],
&tp->md5sig_info->keys4[i+1],
(tp->md5sig_info->entries4 - i) *
sizeof(struct tcp4_md5sig_key));
}
tcp_free_md5sig_pool();
return 0;
}
}
return -ENOENT;
}
EXPORT_SYMBOL(tcp_v4_md5_do_del);
static void tcp_v4_clear_md5_list(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
/* Free each key, then the set of key keys,
* the crypto element, and then decrement our
* hold on the last resort crypto.
*/
if (tp->md5sig_info->entries4) {
int i;
for (i = 0; i < tp->md5sig_info->entries4; i++)
kfree(tp->md5sig_info->keys4[i].base.key);
tp->md5sig_info->entries4 = 0;
tcp_free_md5sig_pool();
}
if (tp->md5sig_info->keys4) {
kfree(tp->md5sig_info->keys4);
tp->md5sig_info->keys4 = NULL;
tp->md5sig_info->alloced4 = 0;
}
}
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;
u8 *newkey;
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) {
if (!tcp_sk(sk)->md5sig_info)
return -ENOENT;
return tcp_v4_md5_do_del(sk, sin->sin_addr.s_addr);
}
if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN)
return -EINVAL;
if (!tcp_sk(sk)->md5sig_info) {
struct tcp_sock *tp = tcp_sk(sk);
struct tcp_md5sig_info *p;
p = kzalloc(sizeof(*p), sk->sk_allocation);
if (!p)
return -EINVAL;
tp->md5sig_info = p;
sk_nocaps_add(sk, NETIF_F_GSO_MASK);
}
newkey = kmemdup(cmd.tcpm_key, cmd.tcpm_keylen, sk->sk_allocation);
if (!newkey)
return -ENOMEM;
return tcp_v4_md5_do_add(sk, sin->sin_addr.s_addr,
newkey, cmd.tcpm_keylen);
}
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, struct tcp_md5sig_key *key,
__be32 daddr, __be32 saddr, 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,
struct sock *sk, struct request_sock *req,
struct sk_buff *skb)
{
struct tcp_md5sig_pool *hp;
struct hash_desc *desc;
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)->loc_addr;
daddr = inet_rsk(req)->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 int tcp_v4_inbound_md5_hash(struct sock *sk, 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.
*/
__u8 *hash_location = NULL;
struct tcp_md5sig_key *hash_expected;
const struct iphdr *iph = ip_hdr(skb);
struct tcphdr *th = tcp_hdr(skb);
int genhash;
unsigned char newhash[16];
hash_expected = tcp_v4_md5_do_lookup(sk, iph->saddr);
hash_location = tcp_parse_md5sig_option(th);
/* We've parsed the options - do we have a hash? */
if (!hash_expected && !hash_location)
return 0;
if (hash_expected && !hash_location) {
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND);
return 1;
}
if (!hash_expected && hash_location) {
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED);
return 1;
}
/* 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) {
if (net_ratelimit()) {
printk(KERN_INFO "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 1;
}
return 0;
}
#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 struct timewait_sock_ops tcp_timewait_sock_ops = {
.twsk_obj_size = sizeof(struct tcp_timewait_sock),
.twsk_unique = tcp_twsk_unique,
.twsk_destructor= tcp_twsk_destructor,
};
int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
{
struct tcp_extend_values tmp_ext;
struct tcp_options_received tmp_opt;
u8 *hash_location;
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;
#ifdef CONFIG_SYN_COOKIES
int want_cookie = 0;
#else
#define want_cookie 0 /* Argh, why doesn't gcc optimize this :( */
#endif
/* 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 (inet_csk_reqsk_queue_is_full(sk) && !isn) {
if (net_ratelimit())
syn_flood_warning(skb);
#ifdef CONFIG_SYN_COOKIES
if (sysctl_tcp_syncookies) {
want_cookie = 1;
} else
#endif
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)
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, &hash_location, 0);
if (tmp_opt.cookie_plus > 0 &&
tmp_opt.saw_tstamp &&
!tp->rx_opt.cookie_out_never &&
(sysctl_tcp_cookie_size > 0 ||
(tp->cookie_values != NULL &&
tp->cookie_values->cookie_desired > 0))) {
u8 *c;
u32 *mess = &tmp_ext.cookie_bakery[COOKIE_DIGEST_WORDS];
int l = tmp_opt.cookie_plus - TCPOLEN_COOKIE_BASE;
if (tcp_cookie_generator(&tmp_ext.cookie_bakery[0]) != 0)
goto drop_and_release;
/* Secret recipe starts with IP addresses */
*mess++ ^= (__force u32)daddr;
*mess++ ^= (__force u32)saddr;
/* plus variable length Initiator Cookie */
c = (u8 *)mess;
while (l-- > 0)
*c++ ^= *hash_location++;
#ifdef CONFIG_SYN_COOKIES
want_cookie = 0; /* not our kind of cookie */
#endif
tmp_ext.cookie_out_never = 0; /* false */
tmp_ext.cookie_plus = tmp_opt.cookie_plus;
} else if (!tp->rx_opt.cookie_in_always) {
/* redundant indications, but ensure initialization. */
tmp_ext.cookie_out_never = 1; /* true */
tmp_ext.cookie_plus = 0;
} else {
goto drop_and_release;
}
tmp_ext.cookie_in_always = tp->rx_opt.cookie_in_always;
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->loc_addr = daddr;
ireq->rmt_addr = saddr;
ireq->no_srccheck = inet_sk(sk)->transparent;
ireq->opt = tcp_v4_save_options(sk, 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, tcp_hdr(skb));
if (want_cookie) {
isn = cookie_v4_init_sequence(sk, skb, &req->mss);
req->cookie_ts = tmp_opt.tstamp_ok;
} else if (!isn) {
struct inet_peer *peer = NULL;
/* 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, req)) != NULL &&
(peer = rt_get_peer((struct rtable *)dst)) != NULL &&
peer->v4daddr == saddr) {
inet_peer_refcheck(peer);
if ((u32)get_seconds() - peer->tcp_ts_stamp < TCP_PAWS_MSL &&
(s32)(peer->tcp_ts - req->ts_recent) >
TCP_PAWS_WINDOW) {
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)) &&
(!peer || !peer->tcp_ts_stamp) &&
(!dst || !dst_metric(dst, RTAX_RTT))) {
/* 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 "TCP: 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 (tcp_v4_send_synack(sk, dst, req,
(struct request_values *)&tmp_ext) ||
want_cookie)
goto drop_and_free;
inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
return 0;
drop_and_release:
dst_release(dst);
drop_and_free:
reqsk_free(req);
drop:
return 0;
}
EXPORT_SYMBOL(tcp_v4_conn_request);
/*
* The three way handshake has completed - we got a valid synack -
* now create the new socket.
*/
struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
struct request_sock *req,
struct dst_entry *dst)
{
struct inet_request_sock *ireq;
struct inet_sock *newinet;
struct tcp_sock *newtp;
struct sock *newsk;
#ifdef CONFIG_TCP_MD5SIG
struct tcp_md5sig_key *key;
#endif
if (sk_acceptq_is_full(sk))
goto exit_overflow;
if (!dst && (dst = inet_csk_route_req(sk, req)) == NULL)
goto exit;
newsk = tcp_create_openreq_child(sk, req, skb);
if (!newsk)
goto exit;
newsk->sk_gso_type = SKB_GSO_TCPV4;
sk_setup_caps(newsk, dst);
newtp = tcp_sk(newsk);
newinet = inet_sk(newsk);
ireq = inet_rsk(req);
newinet->inet_daddr = ireq->rmt_addr;
newinet->inet_rcv_saddr = ireq->loc_addr;
newinet->inet_saddr = ireq->loc_addr;
newinet->opt = ireq->opt;
ireq->opt = NULL;
newinet->mc_index = inet_iif(skb);
newinet->mc_ttl = ip_hdr(skb)->ttl;
inet_csk(newsk)->icsk_ext_hdr_len = 0;
if (newinet->opt)
inet_csk(newsk)->icsk_ext_hdr_len = newinet->opt->optlen;
newinet->inet_id = newtp->write_seq ^ jiffies;
tcp_mtup_init(newsk);
tcp_sync_mss(newsk, dst_mtu(dst));
newtp->advmss = dst_metric(dst, RTAX_ADVMSS);
if (tcp_sk(sk)->rx_opt.user_mss &&
tcp_sk(sk)->rx_opt.user_mss < newtp->advmss)
newtp->advmss = tcp_sk(sk)->rx_opt.user_mss;
tcp_initialize_rcv_mss(newsk);
#ifdef CONFIG_TCP_MD5SIG
/* Copy over the MD5 key from the original socket */
key = tcp_v4_md5_do_lookup(sk, newinet->inet_daddr);
if (key != NULL) {
/*
* We're using one, so create a matching key
* on the newsk structure. If we fail to get
* memory, then we end up not copying the key
* across. Shucks.
*/
char *newkey = kmemdup(key->key, key->keylen, GFP_ATOMIC);
if (newkey != NULL)
tcp_v4_md5_do_add(newsk, newinet->inet_daddr,
newkey, key->keylen);
sk_nocaps_add(newsk, NETIF_F_GSO_MASK);
}
#endif
__inet_hash_nolisten(newsk, NULL);
[SOCK] proto: Add hashinfo member to struct proto This way we can remove TCP and DCCP specific versions of sk->sk_prot->get_port: both v4 and v6 use inet_csk_get_port sk->sk_prot->hash: inet_hash is directly used, only v6 need a specific version to deal with mapped sockets sk->sk_prot->unhash: both v4 and v6 use inet_hash directly struct inet_connection_sock_af_ops also gets a new member, bind_conflict, so that inet_csk_get_port can find the per family routine. Now only the lookup routines receive as a parameter a struct inet_hashtable. With this we further reuse code, reducing the difference among INET transport protocols. Eventually work has to be done on UDP and SCTP to make them share this infrastructure and get as a bonus inet_diag interfaces so that iproute can be used with these protocols. net-2.6/net/ipv4/inet_hashtables.c: struct proto | +8 struct inet_connection_sock_af_ops | +8 2 structs changed __inet_hash_nolisten | +18 __inet_hash | -210 inet_put_port | +8 inet_bind_bucket_create | +1 __inet_hash_connect | -8 5 functions changed, 27 bytes added, 218 bytes removed, diff: -191 net-2.6/net/core/sock.c: proto_seq_show | +3 1 function changed, 3 bytes added, diff: +3 net-2.6/net/ipv4/inet_connection_sock.c: inet_csk_get_port | +15 1 function changed, 15 bytes added, diff: +15 net-2.6/net/ipv4/tcp.c: tcp_set_state | -7 1 function changed, 7 bytes removed, diff: -7 net-2.6/net/ipv4/tcp_ipv4.c: tcp_v4_get_port | -31 tcp_v4_hash | -48 tcp_v4_destroy_sock | -7 tcp_v4_syn_recv_sock | -2 tcp_unhash | -179 5 functions changed, 267 bytes removed, diff: -267 net-2.6/net/ipv6/inet6_hashtables.c: __inet6_hash | +8 1 function changed, 8 bytes added, diff: +8 net-2.6/net/ipv4/inet_hashtables.c: inet_unhash | +190 inet_hash | +242 2 functions changed, 432 bytes added, diff: +432 vmlinux: 16 functions changed, 485 bytes added, 492 bytes removed, diff: -7 /home/acme/git/net-2.6/net/ipv6/tcp_ipv6.c: tcp_v6_get_port | -31 tcp_v6_hash | -7 tcp_v6_syn_recv_sock | -9 3 functions changed, 47 bytes removed, diff: -47 /home/acme/git/net-2.6/net/dccp/proto.c: dccp_destroy_sock | -7 dccp_unhash | -179 dccp_hash | -49 dccp_set_state | -7 dccp_done | +1 5 functions changed, 1 bytes added, 242 bytes removed, diff: -241 /home/acme/git/net-2.6/net/dccp/ipv4.c: dccp_v4_get_port | -31 dccp_v4_request_recv_sock | -2 2 functions changed, 33 bytes removed, diff: -33 /home/acme/git/net-2.6/net/dccp/ipv6.c: dccp_v6_get_port | -31 dccp_v6_hash | -7 dccp_v6_request_recv_sock | +5 3 functions changed, 5 bytes added, 38 bytes removed, diff: -33 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-02-03 05:06:04 -07:00
__inet_inherit_port(sk, newsk);
return newsk;
exit_overflow:
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS);
exit:
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
dst_release(dst);
return NULL;
}
EXPORT_SYMBOL(tcp_v4_syn_recv_sock);
static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb)
{
struct tcphdr *th = tcp_hdr(skb);
const struct iphdr *iph = ip_hdr(skb);
struct sock *nsk;
struct request_sock **prev;
/* Find possible connection requests. */
struct request_sock *req = inet_csk_search_req(sk, &prev, th->source,
iph->saddr, iph->daddr);
if (req)
return tcp_check_req(sk, skb, req, prev);
nsk = inet_lookup_established(sock_net(sk), &tcp_hashinfo, iph->saddr,
th->source, iph->daddr, th->dest, inet_iif(skb));
if (nsk) {
if (nsk->sk_state != TCP_TIME_WAIT) {
bh_lock_sock(nsk);
return nsk;
}
inet_twsk_put(inet_twsk(nsk));
return NULL;
}
#ifdef CONFIG_SYN_COOKIES
if (!th->syn)
sk = cookie_v4_check(sk, skb, &(IPCB(skb)->opt));
#endif
return sk;
}
static __sum16 tcp_v4_checksum_init(struct sk_buff *skb)
{
const struct iphdr *iph = ip_hdr(skb);
if (skb->ip_summed == CHECKSUM_COMPLETE) {
if (!tcp_v4_check(skb->len, iph->saddr,
iph->daddr, skb->csum)) {
skb->ip_summed = CHECKSUM_UNNECESSARY;
return 0;
}
}
skb->csum = csum_tcpudp_nofold(iph->saddr, iph->daddr,
skb->len, IPPROTO_TCP, 0);
if (skb->len <= 76) {
return __skb_checksum_complete(skb);
}
return 0;
}
/* The socket must have it's spinlock held when we get
* here.
*
* We have a potential double-lock case here, so even when
* doing backlog processing we use the BH locking scheme.
* This is because we cannot sleep with the original spinlock
* held.
*/
int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
{
struct sock *rsk;
#ifdef CONFIG_TCP_MD5SIG
/*
* We really want to reject the packet as early as possible
* if:
* o We're expecting an MD5'd packet and this is no MD5 tcp option
* o There is an MD5 option and we're not expecting one
*/
if (tcp_v4_inbound_md5_hash(sk, skb))
goto discard;
#endif
if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
sock_rps_save_rxhash(sk, skb->rxhash);
TCP_CHECK_TIMER(sk);
if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len)) {
rsk = sk;
goto reset;
}
TCP_CHECK_TIMER(sk);
return 0;
}
if (skb->len < tcp_hdrlen(skb) || tcp_checksum_complete(skb))
goto csum_err;
if (sk->sk_state == TCP_LISTEN) {
struct sock *nsk = tcp_v4_hnd_req(sk, skb);
if (!nsk)
goto discard;
if (nsk != sk) {
if (tcp_child_process(sk, nsk, skb)) {
rsk = nsk;
goto reset;
}
return 0;
}
} else
sock_rps_save_rxhash(sk, skb->rxhash);
TCP_CHECK_TIMER(sk);
if (tcp_rcv_state_process(sk, skb, tcp_hdr(skb), skb->len)) {
rsk = sk;
goto reset;
}
TCP_CHECK_TIMER(sk);
return 0;
reset:
tcp_v4_send_reset(rsk, skb);
discard:
kfree_skb(skb);
/* Be careful here. If this function gets more complicated and
* gcc suffers from register pressure on the x86, sk (in %ebx)
* might be destroyed here. This current version compiles correctly,
* but you have been warned.
*/
return 0;
csum_err:
TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_INERRS);
goto discard;
}
EXPORT_SYMBOL(tcp_v4_do_rcv);
/*
* From tcp_input.c
*/
int tcp_v4_rcv(struct sk_buff *skb)
{
const struct iphdr *iph;
struct tcphdr *th;
struct sock *sk;
int ret;
struct net *net = dev_net(skb->dev);
if (skb->pkt_type != PACKET_HOST)
goto discard_it;
/* Count it even if it's bad */
TCP_INC_STATS_BH(net, TCP_MIB_INSEGS);
if (!pskb_may_pull(skb, sizeof(struct tcphdr)))
goto discard_it;
th = tcp_hdr(skb);
if (th->doff < sizeof(struct tcphdr) / 4)
goto bad_packet;
if (!pskb_may_pull(skb, th->doff * 4))
goto discard_it;
/* An explanation is required here, I think.
* Packet length and doff are validated by header prediction,
* provided case of th->doff==0 is eliminated.
* So, we defer the checks. */
if (!skb_csum_unnecessary(skb) && tcp_v4_checksum_init(skb))
goto bad_packet;
th = tcp_hdr(skb);
iph = ip_hdr(skb);
TCP_SKB_CB(skb)->seq = ntohl(th->seq);
TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
skb->len - th->doff * 4);
TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
TCP_SKB_CB(skb)->when = 0;
TCP_SKB_CB(skb)->flags = iph->tos;
TCP_SKB_CB(skb)->sacked = 0;
sk = __inet_lookup_skb(&tcp_hashinfo, skb, th->source, th->dest);
if (!sk)
goto no_tcp_socket;
process:
if (sk->sk_state == TCP_TIME_WAIT)
goto do_time_wait;
if (unlikely(iph->ttl < inet_sk(sk)->min_ttl)) {
NET_INC_STATS_BH(net, LINUX_MIB_TCPMINTTLDROP);
goto discard_and_relse;
}
if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
goto discard_and_relse;
nf_reset(skb);
if (sk_filter(sk, skb))
goto discard_and_relse;
skb->dev = NULL;
bh_lock_sock_nested(sk);
ret = 0;
if (!sock_owned_by_user(sk)) {
#ifdef CONFIG_NET_DMA
struct tcp_sock *tp = tcp_sk(sk);
if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
tp->ucopy.dma_chan = dma_find_channel(DMA_MEMCPY);
if (tp->ucopy.dma_chan)
ret = tcp_v4_do_rcv(sk, skb);
else
#endif
{
if (!tcp_prequeue(sk, skb))
ret = tcp_v4_do_rcv(sk, skb);
}
} else if (unlikely(sk_add_backlog(sk, skb))) {
bh_unlock_sock(sk);
NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP);
goto discard_and_relse;
}
bh_unlock_sock(sk);
sock_put(sk);
return ret;
no_tcp_socket:
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
goto discard_it;
if (skb->len < (th->doff << 2) || tcp_checksum_complete(skb)) {
bad_packet:
TCP_INC_STATS_BH(net, TCP_MIB_INERRS);
} else {
tcp_v4_send_reset(NULL, skb);
}
discard_it:
/* Discard frame. */
kfree_skb(skb);
return 0;
discard_and_relse:
sock_put(sk);
goto discard_it;
do_time_wait:
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
inet_twsk_put(inet_twsk(sk));
goto discard_it;
}
if (skb->len < (th->doff << 2) || tcp_checksum_complete(skb)) {
TCP_INC_STATS_BH(net, TCP_MIB_INERRS);
inet_twsk_put(inet_twsk(sk));
goto discard_it;
}
switch (tcp_timewait_state_process(inet_twsk(sk), skb, th)) {
case TCP_TW_SYN: {
struct sock *sk2 = inet_lookup_listener(dev_net(skb->dev),
&tcp_hashinfo,
iph->daddr, th->dest,
inet_iif(skb));
if (sk2) {
inet_twsk_deschedule(inet_twsk(sk), &tcp_death_row);
inet_twsk_put(inet_twsk(sk));
sk = sk2;
goto process;
}
/* Fall through to ACK */
}
case TCP_TW_ACK:
tcp_v4_timewait_ack(sk, skb);
break;
case TCP_TW_RST:
goto no_tcp_socket;
case TCP_TW_SUCCESS:;
}
goto discard_it;
}
/* VJ's idea. Save last timestamp seen from this destination
* and hold it at least for normal timewait interval to use for duplicate
* segment detection in subsequent connections, before they enter synchronized
* state.
*/
int tcp_v4_remember_stamp(struct sock *sk)
{
struct inet_sock *inet = inet_sk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct rtable *rt = (struct rtable *)__sk_dst_get(sk);
struct inet_peer *peer = NULL;
int release_it = 0;
if (!rt || rt->rt_dst != inet->inet_daddr) {
peer = inet_getpeer(inet->inet_daddr, 1);
release_it = 1;
} else {
if (!rt->peer)
rt_bind_peer(rt, 1);
peer = rt->peer;
}
if (peer) {
if ((s32)(peer->tcp_ts - tp->rx_opt.ts_recent) <= 0 ||
((u32)get_seconds() - peer->tcp_ts_stamp > TCP_PAWS_MSL &&
peer->tcp_ts_stamp <= (u32)tp->rx_opt.ts_recent_stamp)) {
peer->tcp_ts_stamp = (u32)tp->rx_opt.ts_recent_stamp;
peer->tcp_ts = tp->rx_opt.ts_recent;
}
if (release_it)
inet_putpeer(peer);
return 1;
}
return 0;
}
EXPORT_SYMBOL(tcp_v4_remember_stamp);
int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw)
{
struct inet_peer *peer = inet_getpeer(tw->tw_daddr, 1);
if (peer) {
const struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw);
if ((s32)(peer->tcp_ts - tcptw->tw_ts_recent) <= 0 ||
((u32)get_seconds() - peer->tcp_ts_stamp > TCP_PAWS_MSL &&
peer->tcp_ts_stamp <= (u32)tcptw->tw_ts_recent_stamp)) {
peer->tcp_ts_stamp = (u32)tcptw->tw_ts_recent_stamp;
peer->tcp_ts = tcptw->tw_ts_recent;
}
inet_putpeer(peer);
return 1;
}
return 0;
}
const struct inet_connection_sock_af_ops ipv4_specific = {
.queue_xmit = ip_queue_xmit,
.send_check = tcp_v4_send_check,
.rebuild_header = inet_sk_rebuild_header,
.conn_request = tcp_v4_conn_request,
.syn_recv_sock = tcp_v4_syn_recv_sock,
.remember_stamp = tcp_v4_remember_stamp,
.net_header_len = sizeof(struct iphdr),
.setsockopt = ip_setsockopt,
.getsockopt = ip_getsockopt,
.addr2sockaddr = inet_csk_addr2sockaddr,
.sockaddr_len = sizeof(struct sockaddr_in),
[SOCK] proto: Add hashinfo member to struct proto This way we can remove TCP and DCCP specific versions of sk->sk_prot->get_port: both v4 and v6 use inet_csk_get_port sk->sk_prot->hash: inet_hash is directly used, only v6 need a specific version to deal with mapped sockets sk->sk_prot->unhash: both v4 and v6 use inet_hash directly struct inet_connection_sock_af_ops also gets a new member, bind_conflict, so that inet_csk_get_port can find the per family routine. Now only the lookup routines receive as a parameter a struct inet_hashtable. With this we further reuse code, reducing the difference among INET transport protocols. Eventually work has to be done on UDP and SCTP to make them share this infrastructure and get as a bonus inet_diag interfaces so that iproute can be used with these protocols. net-2.6/net/ipv4/inet_hashtables.c: struct proto | +8 struct inet_connection_sock_af_ops | +8 2 structs changed __inet_hash_nolisten | +18 __inet_hash | -210 inet_put_port | +8 inet_bind_bucket_create | +1 __inet_hash_connect | -8 5 functions changed, 27 bytes added, 218 bytes removed, diff: -191 net-2.6/net/core/sock.c: proto_seq_show | +3 1 function changed, 3 bytes added, diff: +3 net-2.6/net/ipv4/inet_connection_sock.c: inet_csk_get_port | +15 1 function changed, 15 bytes added, diff: +15 net-2.6/net/ipv4/tcp.c: tcp_set_state | -7 1 function changed, 7 bytes removed, diff: -7 net-2.6/net/ipv4/tcp_ipv4.c: tcp_v4_get_port | -31 tcp_v4_hash | -48 tcp_v4_destroy_sock | -7 tcp_v4_syn_recv_sock | -2 tcp_unhash | -179 5 functions changed, 267 bytes removed, diff: -267 net-2.6/net/ipv6/inet6_hashtables.c: __inet6_hash | +8 1 function changed, 8 bytes added, diff: +8 net-2.6/net/ipv4/inet_hashtables.c: inet_unhash | +190 inet_hash | +242 2 functions changed, 432 bytes added, diff: +432 vmlinux: 16 functions changed, 485 bytes added, 492 bytes removed, diff: -7 /home/acme/git/net-2.6/net/ipv6/tcp_ipv6.c: tcp_v6_get_port | -31 tcp_v6_hash | -7 tcp_v6_syn_recv_sock | -9 3 functions changed, 47 bytes removed, diff: -47 /home/acme/git/net-2.6/net/dccp/proto.c: dccp_destroy_sock | -7 dccp_unhash | -179 dccp_hash | -49 dccp_set_state | -7 dccp_done | +1 5 functions changed, 1 bytes added, 242 bytes removed, diff: -241 /home/acme/git/net-2.6/net/dccp/ipv4.c: dccp_v4_get_port | -31 dccp_v4_request_recv_sock | -2 2 functions changed, 33 bytes removed, diff: -33 /home/acme/git/net-2.6/net/dccp/ipv6.c: dccp_v6_get_port | -31 dccp_v6_hash | -7 dccp_v6_request_recv_sock | +5 3 functions changed, 5 bytes added, 38 bytes removed, diff: -33 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-02-03 05:06:04 -07:00
.bind_conflict = inet_csk_bind_conflict,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_ip_setsockopt,
.compat_getsockopt = compat_ip_getsockopt,
#endif
};
EXPORT_SYMBOL(ipv4_specific);
#ifdef CONFIG_TCP_MD5SIG
static const struct tcp_sock_af_ops tcp_sock_ipv4_specific = {
.md5_lookup = tcp_v4_md5_lookup,
.calc_md5_hash = tcp_v4_md5_hash_skb,
.md5_add = tcp_v4_md5_add_func,
.md5_parse = tcp_v4_parse_md5_keys,
};
#endif
/* NOTE: A lot of things set to zero explicitly by call to
* sk_alloc() so need not be done here.
*/
static int tcp_v4_init_sock(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
skb_queue_head_init(&tp->out_of_order_queue);
tcp_init_xmit_timers(sk);
tcp_prequeue_init(tp);
icsk->icsk_rto = TCP_TIMEOUT_INIT;
tp->mdev = TCP_TIMEOUT_INIT;
/* 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
*/
tp->snd_cwnd = 2;
/* See draft-stevens-tcpca-spec-01 for discussion of the
* initialization of these values.
*/
tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
tp->snd_cwnd_clamp = ~0;
tp->mss_cache = TCP_MSS_DEFAULT;
tp->reordering = sysctl_tcp_reordering;
icsk->icsk_ca_ops = &tcp_init_congestion_ops;
sk->sk_state = TCP_CLOSE;
sk->sk_write_space = sk_stream_write_space;
sock_set_flag(sk, SOCK_USE_WRITE_QUEUE);
icsk->icsk_af_ops = &ipv4_specific;
icsk->icsk_sync_mss = tcp_sync_mss;
#ifdef CONFIG_TCP_MD5SIG
tp->af_specific = &tcp_sock_ipv4_specific;
#endif
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>
2009-12-02 11:17:05 -07:00
/* TCP Cookie Transactions */
if (sysctl_tcp_cookie_size > 0) {
/* Default, cookies without s_data_payload. */
tp->cookie_values =
kzalloc(sizeof(*tp->cookie_values),
sk->sk_allocation);
if (tp->cookie_values != NULL)
kref_init(&tp->cookie_values->kref);
}
/* Presumed zeroed, in order of appearance:
* cookie_in_always, cookie_out_never,
* s_data_constant, s_data_in, s_data_out
*/
sk->sk_sndbuf = sysctl_tcp_wmem[1];
sk->sk_rcvbuf = sysctl_tcp_rmem[1];
local_bh_disable();
percpu_counter_inc(&tcp_sockets_allocated);
local_bh_enable();
return 0;
}
void tcp_v4_destroy_sock(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
tcp_clear_xmit_timers(sk);
tcp_cleanup_congestion_control(sk);
/* Cleanup up the write buffer. */
tcp_write_queue_purge(sk);
/* Cleans up our, hopefully empty, out_of_order_queue. */
__skb_queue_purge(&tp->out_of_order_queue);
#ifdef CONFIG_TCP_MD5SIG
/* Clean up the MD5 key list, if any */
if (tp->md5sig_info) {
tcp_v4_clear_md5_list(sk);
kfree(tp->md5sig_info);
tp->md5sig_info = NULL;
}
#endif
#ifdef CONFIG_NET_DMA
/* Cleans up our sk_async_wait_queue */
__skb_queue_purge(&sk->sk_async_wait_queue);
#endif
/* Clean prequeue, it must be empty really */
__skb_queue_purge(&tp->ucopy.prequeue);
/* Clean up a referenced TCP bind bucket. */
if (inet_csk(sk)->icsk_bind_hash)
[SOCK] proto: Add hashinfo member to struct proto This way we can remove TCP and DCCP specific versions of sk->sk_prot->get_port: both v4 and v6 use inet_csk_get_port sk->sk_prot->hash: inet_hash is directly used, only v6 need a specific version to deal with mapped sockets sk->sk_prot->unhash: both v4 and v6 use inet_hash directly struct inet_connection_sock_af_ops also gets a new member, bind_conflict, so that inet_csk_get_port can find the per family routine. Now only the lookup routines receive as a parameter a struct inet_hashtable. With this we further reuse code, reducing the difference among INET transport protocols. Eventually work has to be done on UDP and SCTP to make them share this infrastructure and get as a bonus inet_diag interfaces so that iproute can be used with these protocols. net-2.6/net/ipv4/inet_hashtables.c: struct proto | +8 struct inet_connection_sock_af_ops | +8 2 structs changed __inet_hash_nolisten | +18 __inet_hash | -210 inet_put_port | +8 inet_bind_bucket_create | +1 __inet_hash_connect | -8 5 functions changed, 27 bytes added, 218 bytes removed, diff: -191 net-2.6/net/core/sock.c: proto_seq_show | +3 1 function changed, 3 bytes added, diff: +3 net-2.6/net/ipv4/inet_connection_sock.c: inet_csk_get_port | +15 1 function changed, 15 bytes added, diff: +15 net-2.6/net/ipv4/tcp.c: tcp_set_state | -7 1 function changed, 7 bytes removed, diff: -7 net-2.6/net/ipv4/tcp_ipv4.c: tcp_v4_get_port | -31 tcp_v4_hash | -48 tcp_v4_destroy_sock | -7 tcp_v4_syn_recv_sock | -2 tcp_unhash | -179 5 functions changed, 267 bytes removed, diff: -267 net-2.6/net/ipv6/inet6_hashtables.c: __inet6_hash | +8 1 function changed, 8 bytes added, diff: +8 net-2.6/net/ipv4/inet_hashtables.c: inet_unhash | +190 inet_hash | +242 2 functions changed, 432 bytes added, diff: +432 vmlinux: 16 functions changed, 485 bytes added, 492 bytes removed, diff: -7 /home/acme/git/net-2.6/net/ipv6/tcp_ipv6.c: tcp_v6_get_port | -31 tcp_v6_hash | -7 tcp_v6_syn_recv_sock | -9 3 functions changed, 47 bytes removed, diff: -47 /home/acme/git/net-2.6/net/dccp/proto.c: dccp_destroy_sock | -7 dccp_unhash | -179 dccp_hash | -49 dccp_set_state | -7 dccp_done | +1 5 functions changed, 1 bytes added, 242 bytes removed, diff: -241 /home/acme/git/net-2.6/net/dccp/ipv4.c: dccp_v4_get_port | -31 dccp_v4_request_recv_sock | -2 2 functions changed, 33 bytes removed, diff: -33 /home/acme/git/net-2.6/net/dccp/ipv6.c: dccp_v6_get_port | -31 dccp_v6_hash | -7 dccp_v6_request_recv_sock | +5 3 functions changed, 5 bytes added, 38 bytes removed, diff: -33 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-02-03 05:06:04 -07:00
inet_put_port(sk);
/*
* If sendmsg cached page exists, toss it.
*/
if (sk->sk_sndmsg_page) {
__free_page(sk->sk_sndmsg_page);
sk->sk_sndmsg_page = NULL;
}
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>
2009-12-02 11:17:05 -07:00
/* TCP Cookie Transactions */
if (tp->cookie_values != NULL) {
kref_put(&tp->cookie_values->kref,
tcp_cookie_values_release);
tp->cookie_values = NULL;
}
percpu_counter_dec(&tcp_sockets_allocated);
}
EXPORT_SYMBOL(tcp_v4_destroy_sock);
#ifdef CONFIG_PROC_FS
/* Proc filesystem TCP sock list dumping. */
static inline struct inet_timewait_sock *tw_head(struct hlist_nulls_head *head)
{
return hlist_nulls_empty(head) ? NULL :
list_entry(head->first, struct inet_timewait_sock, tw_node);
}
static inline struct inet_timewait_sock *tw_next(struct inet_timewait_sock *tw)
{
return !is_a_nulls(tw->tw_node.next) ?
hlist_nulls_entry(tw->tw_node.next, typeof(*tw), tw_node) : NULL;
}
/*
* Get next listener socket follow cur. If cur is NULL, get first socket
* starting from bucket given in st->bucket; when st->bucket is zero the
* very first socket in the hash table is returned.
*/
static void *listening_get_next(struct seq_file *seq, void *cur)
{
struct inet_connection_sock *icsk;
struct hlist_nulls_node *node;
struct sock *sk = cur;
struct inet_listen_hashbucket *ilb;
struct tcp_iter_state *st = seq->private;
struct net *net = seq_file_net(seq);
if (!sk) {
ilb = &tcp_hashinfo.listening_hash[st->bucket];
spin_lock_bh(&ilb->lock);
sk = sk_nulls_head(&ilb->head);
st->offset = 0;
goto get_sk;
}
ilb = &tcp_hashinfo.listening_hash[st->bucket];
++st->num;
++st->offset;
if (st->state == TCP_SEQ_STATE_OPENREQ) {
struct request_sock *req = cur;
icsk = inet_csk(st->syn_wait_sk);
req = req->dl_next;
while (1) {
while (req) {
tcp: fix kernel panic with listening_get_next # BUG: unable to handle kernel NULL pointer dereference at 0000000000000038 IP: [<ffffffff821ed01e>] listening_get_next+0x50/0x1b3 PGD 11e4b9067 PUD 11d16c067 PMD 0 Oops: 0000 [1] SMP last sysfs file: /sys/devices/system/cpu/cpu3/cache/index2/shared_cpu_map CPU 3 Modules linked in: bridge ipv6 button battery ac loop dm_mod tg3 ext3 jbd edd fan thermal processor thermal_sys hwmon sg sata_svw libata dock serverworks sd_mod scsi_mod ide_disk ide_core [last unloaded: freq_table] Pid: 3368, comm: slpd Not tainted 2.6.26-rc2-mm1-lxc4 #1 RIP: 0010:[<ffffffff821ed01e>] [<ffffffff821ed01e>] listening_get_next+0x50/0x1b3 RSP: 0018:ffff81011e1fbe18 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff8100be0ad3c0 RCX: ffff8100619f50c0 RDX: ffffffff82475be0 RSI: ffff81011d9ae6c0 RDI: ffff8100be0ad508 RBP: ffff81011f4f1240 R08: 00000000ffffffff R09: ffff8101185b6780 R10: 000000000000002d R11: ffffffff820fdbfa R12: ffff8100be0ad3c8 R13: ffff8100be0ad6a0 R14: ffff8100be0ad3c0 R15: ffffffff825b8ce0 FS: 00007f6a0ebd16d0(0000) GS:ffff81011f424540(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 0000000000000038 CR3: 000000011dc20000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process slpd (pid: 3368, threadinfo ffff81011e1fa000, task ffff81011f4b8660) Stack: 00000000000002ee ffff81011f5a57c0 ffff81011f4f1240 ffff81011e1fbe90 0000000000001000 0000000000000000 00007fff16bf2590 ffffffff821ed9c8 ffff81011f5a57c0 ffff81011d9ae6c0 000000000000041a ffffffff820b0abd Call Trace: [<ffffffff821ed9c8>] ? tcp_seq_next+0x34/0x7e [<ffffffff820b0abd>] ? seq_read+0x1aa/0x29d [<ffffffff820d21b4>] ? proc_reg_read+0x73/0x8e [<ffffffff8209769c>] ? vfs_read+0xaa/0x152 [<ffffffff82097a7d>] ? sys_read+0x45/0x6e [<ffffffff8200bd2b>] ? system_call_after_swapgs+0x7b/0x80 Code: 31 a9 25 00 e9 b5 00 00 00 ff 45 20 83 7d 0c 01 75 79 4c 8b 75 10 48 8b 0e eb 1d 48 8b 51 20 0f b7 45 08 39 02 75 0e 48 8b 41 28 <4c> 39 78 38 0f 84 93 00 00 00 48 8b 09 48 85 c9 75 de 8b 55 1c RIP [<ffffffff821ed01e>] listening_get_next+0x50/0x1b3 RSP <ffff81011e1fbe18> CR2: 0000000000000038 This kernel panic appears with CONFIG_NET_NS=y. How to reproduce ? On the buggy host (host A) * ip addr add 1.2.3.4/24 dev eth0 On a remote host (host B) * ip addr add 1.2.3.5/24 dev eth0 * iptables -A INPUT -p tcp -s 1.2.3.4 -j DROP * ssh 1.2.3.4 On host A: * netstat -ta or cat /proc/net/tcp This bug happens when reading /proc/net/tcp[6] when there is a req_sock at the SYN_RECV state. When a SYN is received the minisock is created and the sk field is set to NULL. In the listening_get_next function, we try to look at the field req->sk->sk_net. When looking at how to fix this bug, I noticed that is useless to do the check for the minisock belonging to the namespace. A minisock belongs to a listen point and this one is per namespace, so when browsing the minisock they are always per namespace. Signed-off-by: Daniel Lezcano <dlezcano@fr.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-19 01:15:13 -06:00
if (req->rsk_ops->family == st->family) {
cur = req;
goto out;
}
req = req->dl_next;
}
st->offset = 0;
if (++st->sbucket >= icsk->icsk_accept_queue.listen_opt->nr_table_entries)
break;
get_req:
req = icsk->icsk_accept_queue.listen_opt->syn_table[st->sbucket];
}
sk = sk_next(st->syn_wait_sk);
st->state = TCP_SEQ_STATE_LISTENING;
read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
} else {
icsk = inet_csk(sk);
read_lock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
if (reqsk_queue_len(&icsk->icsk_accept_queue))
goto start_req;
read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
sk = sk_next(sk);
}
get_sk:
sk_nulls_for_each_from(sk, node) {
if (sk->sk_family == st->family && net_eq(sock_net(sk), net)) {
cur = sk;
goto out;
}
icsk = inet_csk(sk);
read_lock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
if (reqsk_queue_len(&icsk->icsk_accept_queue)) {
start_req:
st->uid = sock_i_uid(sk);
st->syn_wait_sk = sk;
st->state = TCP_SEQ_STATE_OPENREQ;
st->sbucket = 0;
goto get_req;
}
read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
}
spin_unlock_bh(&ilb->lock);
st->offset = 0;
if (++st->bucket < INET_LHTABLE_SIZE) {
ilb = &tcp_hashinfo.listening_hash[st->bucket];
spin_lock_bh(&ilb->lock);
sk = sk_nulls_head(&ilb->head);
goto get_sk;
}
cur = NULL;
out:
return cur;
}
static void *listening_get_idx(struct seq_file *seq, loff_t *pos)
{
struct tcp_iter_state *st = seq->private;
void *rc;
st->bucket = 0;
st->offset = 0;
rc = listening_get_next(seq, NULL);
while (rc && *pos) {
rc = listening_get_next(seq, rc);
--*pos;
}
return rc;
}
static inline int empty_bucket(struct tcp_iter_state *st)
{
return hlist_nulls_empty(&tcp_hashinfo.ehash[st->bucket].chain) &&
hlist_nulls_empty(&tcp_hashinfo.ehash[st->bucket].twchain);
}
/*
* Get first established socket starting from bucket given in st->bucket.
* If st->bucket is zero, the very first socket in the hash is returned.
*/
static void *established_get_first(struct seq_file *seq)
{
struct tcp_iter_state *st = seq->private;
struct net *net = seq_file_net(seq);
void *rc = NULL;
st->offset = 0;
for (; st->bucket <= tcp_hashinfo.ehash_mask; ++st->bucket) {
struct sock *sk;
struct hlist_nulls_node *node;
struct inet_timewait_sock *tw;
spinlock_t *lock = inet_ehash_lockp(&tcp_hashinfo, st->bucket);
/* Lockless fast path for the common case of empty buckets */
if (empty_bucket(st))
continue;
spin_lock_bh(lock);
sk_nulls_for_each(sk, node, &tcp_hashinfo.ehash[st->bucket].chain) {
if (sk->sk_family != st->family ||
!net_eq(sock_net(sk), net)) {
continue;
}
rc = sk;
goto out;
}
st->state = TCP_SEQ_STATE_TIME_WAIT;
inet_twsk_for_each(tw, node,
[NET]: change layout of ehash table ehash table layout is currently this one : First half of this table is used by sockets not in TIME_WAIT state Second half of it is used by sockets in TIME_WAIT state. This is non optimal because of for a given hash or socket, the two chain heads are located in separate cache lines. Moreover the locks of the second half are never used. If instead of this halving, we use two list heads in inet_ehash_bucket instead of only one, we probably can avoid one cache miss, and reduce ram usage, particularly if sizeof(rwlock_t) is big (various CONFIG_DEBUG_SPINLOCK, CONFIG_DEBUG_LOCK_ALLOC settings). So we still halves the table but we keep together related chains to speedup lookups and socket state change. In this patch I did not try to align struct inet_ehash_bucket, but a future patch could try to make this structure have a convenient size (a power of two or a multiple of L1_CACHE_SIZE). I guess rwlock will just vanish as soon as RCU is plugged into ehash :) , so maybe we dont need to scratch our heads to align the bucket... Note : In case struct inet_ehash_bucket is not a power of two, we could probably change alloc_large_system_hash() (in case it use __get_free_pages()) to free the unused space. It currently allocates a big zone, but the last quarter of it could be freed. Again, this should be a temporary 'problem'. Patch tested on ipv4 tcp only, but should be OK for IPV6 and DCCP. Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-02-08 15:16:46 -07:00
&tcp_hashinfo.ehash[st->bucket].twchain) {
if (tw->tw_family != st->family ||
!net_eq(twsk_net(tw), net)) {
continue;
}
rc = tw;
goto out;
}
spin_unlock_bh(lock);
st->state = TCP_SEQ_STATE_ESTABLISHED;
}
out:
return rc;
}
static void *established_get_next(struct seq_file *seq, void *cur)
{
struct sock *sk = cur;
struct inet_timewait_sock *tw;
struct hlist_nulls_node *node;
struct tcp_iter_state *st = seq->private;
struct net *net = seq_file_net(seq);
++st->num;
++st->offset;
if (st->state == TCP_SEQ_STATE_TIME_WAIT) {
tw = cur;
tw = tw_next(tw);
get_tw:
while (tw && (tw->tw_family != st->family || !net_eq(twsk_net(tw), net))) {
tw = tw_next(tw);
}
if (tw) {
cur = tw;
goto out;
}
spin_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket));
st->state = TCP_SEQ_STATE_ESTABLISHED;
/* Look for next non empty bucket */
st->offset = 0;
while (++st->bucket <= tcp_hashinfo.ehash_mask &&
empty_bucket(st))
;
if (st->bucket > tcp_hashinfo.ehash_mask)
return NULL;
spin_lock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket));
sk = sk_nulls_head(&tcp_hashinfo.ehash[st->bucket].chain);
} else
sk = sk_nulls_next(sk);
sk_nulls_for_each_from(sk, node) {
if (sk->sk_family == st->family && net_eq(sock_net(sk), net))
goto found;
}
st->state = TCP_SEQ_STATE_TIME_WAIT;
[NET]: change layout of ehash table ehash table layout is currently this one : First half of this table is used by sockets not in TIME_WAIT state Second half of it is used by sockets in TIME_WAIT state. This is non optimal because of for a given hash or socket, the two chain heads are located in separate cache lines. Moreover the locks of the second half are never used. If instead of this halving, we use two list heads in inet_ehash_bucket instead of only one, we probably can avoid one cache miss, and reduce ram usage, particularly if sizeof(rwlock_t) is big (various CONFIG_DEBUG_SPINLOCK, CONFIG_DEBUG_LOCK_ALLOC settings). So we still halves the table but we keep together related chains to speedup lookups and socket state change. In this patch I did not try to align struct inet_ehash_bucket, but a future patch could try to make this structure have a convenient size (a power of two or a multiple of L1_CACHE_SIZE). I guess rwlock will just vanish as soon as RCU is plugged into ehash :) , so maybe we dont need to scratch our heads to align the bucket... Note : In case struct inet_ehash_bucket is not a power of two, we could probably change alloc_large_system_hash() (in case it use __get_free_pages()) to free the unused space. It currently allocates a big zone, but the last quarter of it could be freed. Again, this should be a temporary 'problem'. Patch tested on ipv4 tcp only, but should be OK for IPV6 and DCCP. Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-02-08 15:16:46 -07:00
tw = tw_head(&tcp_hashinfo.ehash[st->bucket].twchain);
goto get_tw;
found:
cur = sk;
out:
return cur;
}
static void *established_get_idx(struct seq_file *seq, loff_t pos)
{
struct tcp_iter_state *st = seq->private;
void *rc;
st->bucket = 0;
rc = established_get_first(seq);
while (rc && pos) {
rc = established_get_next(seq, rc);
--pos;
}
return rc;
}
static void *tcp_get_idx(struct seq_file *seq, loff_t pos)
{
void *rc;
struct tcp_iter_state *st = seq->private;
st->state = TCP_SEQ_STATE_LISTENING;
rc = listening_get_idx(seq, &pos);
if (!rc) {
st->state = TCP_SEQ_STATE_ESTABLISHED;
rc = established_get_idx(seq, pos);
}
return rc;
}
static void *tcp_seek_last_pos(struct seq_file *seq)
{
struct tcp_iter_state *st = seq->private;
int offset = st->offset;
int orig_num = st->num;
void *rc = NULL;
switch (st->state) {
case TCP_SEQ_STATE_OPENREQ:
case TCP_SEQ_STATE_LISTENING:
if (st->bucket >= INET_LHTABLE_SIZE)
break;
st->state = TCP_SEQ_STATE_LISTENING;
rc = listening_get_next(seq, NULL);
while (offset-- && rc)
rc = listening_get_next(seq, rc);
if (rc)
break;
st->bucket = 0;
/* Fallthrough */
case TCP_SEQ_STATE_ESTABLISHED:
case TCP_SEQ_STATE_TIME_WAIT:
st->state = TCP_SEQ_STATE_ESTABLISHED;
if (st->bucket > tcp_hashinfo.ehash_mask)
break;
rc = established_get_first(seq);
while (offset-- && rc)
rc = established_get_next(seq, rc);
}
st->num = orig_num;
return rc;
}
static void *tcp_seq_start(struct seq_file *seq, loff_t *pos)
{
struct tcp_iter_state *st = seq->private;
void *rc;
if (*pos && *pos == st->last_pos) {
rc = tcp_seek_last_pos(seq);
if (rc)
goto out;
}
st->state = TCP_SEQ_STATE_LISTENING;
st->num = 0;
st->bucket = 0;
st->offset = 0;
rc = *pos ? tcp_get_idx(seq, *pos - 1) : SEQ_START_TOKEN;
out:
st->last_pos = *pos;
return rc;
}
static void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
struct tcp_iter_state *st = seq->private;
void *rc = NULL;
if (v == SEQ_START_TOKEN) {
rc = tcp_get_idx(seq, 0);
goto out;
}
switch (st->state) {
case TCP_SEQ_STATE_OPENREQ:
case TCP_SEQ_STATE_LISTENING:
rc = listening_get_next(seq, v);
if (!rc) {
st->state = TCP_SEQ_STATE_ESTABLISHED;
st->bucket = 0;
st->offset = 0;
rc = established_get_first(seq);
}
break;
case TCP_SEQ_STATE_ESTABLISHED:
case TCP_SEQ_STATE_TIME_WAIT:
rc = established_get_next(seq, v);
break;
}
out:
++*pos;
st->last_pos = *pos;
return rc;
}
static void tcp_seq_stop(struct seq_file *seq, void *v)
{
struct tcp_iter_state *st = seq->private;
switch (st->state) {
case TCP_SEQ_STATE_OPENREQ:
if (v) {
struct inet_connection_sock *icsk = inet_csk(st->syn_wait_sk);
read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
}
case TCP_SEQ_STATE_LISTENING:
if (v != SEQ_START_TOKEN)
spin_unlock_bh(&tcp_hashinfo.listening_hash[st->bucket].lock);
break;
case TCP_SEQ_STATE_TIME_WAIT:
case TCP_SEQ_STATE_ESTABLISHED:
if (v)
spin_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket));
break;
}
}
static int tcp_seq_open(struct inode *inode, struct file *file)
{
struct tcp_seq_afinfo *afinfo = PDE(inode)->data;
struct tcp_iter_state *s;
int err;
err = seq_open_net(inode, file, &afinfo->seq_ops,
sizeof(struct tcp_iter_state));
if (err < 0)
return err;
s = ((struct seq_file *)file->private_data)->private;
s->family = afinfo->family;
s->last_pos = 0;
return 0;
}
int tcp_proc_register(struct net *net, struct tcp_seq_afinfo *afinfo)
{
int rc = 0;
struct proc_dir_entry *p;
afinfo->seq_fops.open = tcp_seq_open;
afinfo->seq_fops.read = seq_read;
afinfo->seq_fops.llseek = seq_lseek;
afinfo->seq_fops.release = seq_release_net;
afinfo->seq_ops.start = tcp_seq_start;
afinfo->seq_ops.next = tcp_seq_next;
afinfo->seq_ops.stop = tcp_seq_stop;
p = proc_create_data(afinfo->name, S_IRUGO, net->proc_net,
&afinfo->seq_fops, afinfo);
if (!p)
rc = -ENOMEM;
return rc;
}
EXPORT_SYMBOL(tcp_proc_register);
void tcp_proc_unregister(struct net *net, struct tcp_seq_afinfo *afinfo)
{
proc_net_remove(net, afinfo->name);
}
EXPORT_SYMBOL(tcp_proc_unregister);
static void get_openreq4(struct sock *sk, struct request_sock *req,
struct seq_file *f, int i, int uid, int *len)
{
const struct inet_request_sock *ireq = inet_rsk(req);
int ttd = req->expires - jiffies;
seq_printf(f, "%4d: %08X:%04X %08X:%04X"
" %02X %08X:%08X %02X:%08lX %08X %5d %8d %u %d %p%n",
i,
ireq->loc_addr,
ntohs(inet_sk(sk)->inet_sport),
ireq->rmt_addr,
ntohs(ireq->rmt_port),
TCP_SYN_RECV,
0, 0, /* could print option size, but that is af dependent. */
1, /* timers active (only the expire timer) */
jiffies_to_clock_t(ttd),
req->retrans,
uid,
0, /* non standard timer */
0, /* open_requests have no inode */
atomic_read(&sk->sk_refcnt),
req,
len);
}
static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i, int *len)
{
int timer_active;
unsigned long timer_expires;
struct tcp_sock *tp = tcp_sk(sk);
const struct inet_connection_sock *icsk = inet_csk(sk);
struct inet_sock *inet = inet_sk(sk);
__be32 dest = inet->inet_daddr;
__be32 src = inet->inet_rcv_saddr;
__u16 destp = ntohs(inet->inet_dport);
__u16 srcp = ntohs(inet->inet_sport);
int rx_queue;
if (icsk->icsk_pending == ICSK_TIME_RETRANS) {
timer_active = 1;
timer_expires = icsk->icsk_timeout;
} else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
timer_active = 4;
timer_expires = icsk->icsk_timeout;
} else if (timer_pending(&sk->sk_timer)) {
timer_active = 2;
timer_expires = sk->sk_timer.expires;
} else {
timer_active = 0;
timer_expires = jiffies;
}
if (sk->sk_state == TCP_LISTEN)
rx_queue = sk->sk_ack_backlog;
else
/*
* because we dont lock socket, we might find a transient negative value
*/
rx_queue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0);
seq_printf(f, "%4d: %08X:%04X %08X:%04X %02X %08X:%08X %02X:%08lX "
"%08X %5d %8d %lu %d %p %lu %lu %u %u %d%n",
i, src, srcp, dest, destp, sk->sk_state,
tp->write_seq - tp->snd_una,
rx_queue,
timer_active,
jiffies_to_clock_t(timer_expires - jiffies),
icsk->icsk_retransmits,
sock_i_uid(sk),
icsk->icsk_probes_out,
sock_i_ino(sk),
atomic_read(&sk->sk_refcnt), sk,
jiffies_to_clock_t(icsk->icsk_rto),
jiffies_to_clock_t(icsk->icsk_ack.ato),
(icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong,
tp->snd_cwnd,
tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh,
len);
}
static void get_timewait4_sock(struct inet_timewait_sock *tw,
struct seq_file *f, int i, int *len)
{
__be32 dest, src;
__u16 destp, srcp;
int ttd = tw->tw_ttd - jiffies;
if (ttd < 0)
ttd = 0;
dest = tw->tw_daddr;
src = tw->tw_rcv_saddr;
destp = ntohs(tw->tw_dport);
srcp = ntohs(tw->tw_sport);
seq_printf(f, "%4d: %08X:%04X %08X:%04X"
" %02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %p%n",
i, src, srcp, dest, destp, tw->tw_substate, 0, 0,
3, jiffies_to_clock_t(ttd), 0, 0, 0, 0,
atomic_read(&tw->tw_refcnt), tw, len);
}
#define TMPSZ 150
static int tcp4_seq_show(struct seq_file *seq, void *v)
{
struct tcp_iter_state *st;
int len;
if (v == SEQ_START_TOKEN) {
seq_printf(seq, "%-*s\n", TMPSZ - 1,
" sl local_address rem_address st tx_queue "
"rx_queue tr tm->when retrnsmt uid timeout "
"inode");
goto out;
}
st = seq->private;
switch (st->state) {
case TCP_SEQ_STATE_LISTENING:
case TCP_SEQ_STATE_ESTABLISHED:
get_tcp4_sock(v, seq, st->num, &len);
break;
case TCP_SEQ_STATE_OPENREQ:
get_openreq4(st->syn_wait_sk, v, seq, st->num, st->uid, &len);
break;
case TCP_SEQ_STATE_TIME_WAIT:
get_timewait4_sock(v, seq, st->num, &len);
break;
}
seq_printf(seq, "%*s\n", TMPSZ - 1 - len, "");
out:
return 0;
}
static struct tcp_seq_afinfo tcp4_seq_afinfo = {
.name = "tcp",
.family = AF_INET,
.seq_fops = {
.owner = THIS_MODULE,
},
.seq_ops = {
.show = tcp4_seq_show,
},
};
static int __net_init tcp4_proc_init_net(struct net *net)
{
return tcp_proc_register(net, &tcp4_seq_afinfo);
}
static void __net_exit tcp4_proc_exit_net(struct net *net)
{
tcp_proc_unregister(net, &tcp4_seq_afinfo);
}
static struct pernet_operations tcp4_net_ops = {
.init = tcp4_proc_init_net,
.exit = tcp4_proc_exit_net,
};
int __init tcp4_proc_init(void)
{
return register_pernet_subsys(&tcp4_net_ops);
}
void tcp4_proc_exit(void)
{
unregister_pernet_subsys(&tcp4_net_ops);
}
#endif /* CONFIG_PROC_FS */
struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *skb)
{
struct iphdr *iph = skb_gro_network_header(skb);
switch (skb->ip_summed) {
case CHECKSUM_COMPLETE:
if (!tcp_v4_check(skb_gro_len(skb), iph->saddr, iph->daddr,
skb->csum)) {
skb->ip_summed = CHECKSUM_UNNECESSARY;
break;
}
/* fall through */
case CHECKSUM_NONE:
NAPI_GRO_CB(skb)->flush = 1;
return NULL;
}
return tcp_gro_receive(head, skb);
}
EXPORT_SYMBOL(tcp4_gro_receive);
int tcp4_gro_complete(struct sk_buff *skb)
{
struct iphdr *iph = ip_hdr(skb);
struct tcphdr *th = tcp_hdr(skb);
th->check = ~tcp_v4_check(skb->len - skb_transport_offset(skb),
iph->saddr, iph->daddr, 0);
skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
return tcp_gro_complete(skb);
}
EXPORT_SYMBOL(tcp4_gro_complete);
struct proto tcp_prot = {
.name = "TCP",
.owner = THIS_MODULE,
.close = tcp_close,
.connect = tcp_v4_connect,
.disconnect = tcp_disconnect,
.accept = inet_csk_accept,
.ioctl = tcp_ioctl,
.init = tcp_v4_init_sock,
.destroy = tcp_v4_destroy_sock,
.shutdown = tcp_shutdown,
.setsockopt = tcp_setsockopt,
.getsockopt = tcp_getsockopt,
.recvmsg = tcp_recvmsg,
.backlog_rcv = tcp_v4_do_rcv,
[SOCK] proto: Add hashinfo member to struct proto This way we can remove TCP and DCCP specific versions of sk->sk_prot->get_port: both v4 and v6 use inet_csk_get_port sk->sk_prot->hash: inet_hash is directly used, only v6 need a specific version to deal with mapped sockets sk->sk_prot->unhash: both v4 and v6 use inet_hash directly struct inet_connection_sock_af_ops also gets a new member, bind_conflict, so that inet_csk_get_port can find the per family routine. Now only the lookup routines receive as a parameter a struct inet_hashtable. With this we further reuse code, reducing the difference among INET transport protocols. Eventually work has to be done on UDP and SCTP to make them share this infrastructure and get as a bonus inet_diag interfaces so that iproute can be used with these protocols. net-2.6/net/ipv4/inet_hashtables.c: struct proto | +8 struct inet_connection_sock_af_ops | +8 2 structs changed __inet_hash_nolisten | +18 __inet_hash | -210 inet_put_port | +8 inet_bind_bucket_create | +1 __inet_hash_connect | -8 5 functions changed, 27 bytes added, 218 bytes removed, diff: -191 net-2.6/net/core/sock.c: proto_seq_show | +3 1 function changed, 3 bytes added, diff: +3 net-2.6/net/ipv4/inet_connection_sock.c: inet_csk_get_port | +15 1 function changed, 15 bytes added, diff: +15 net-2.6/net/ipv4/tcp.c: tcp_set_state | -7 1 function changed, 7 bytes removed, diff: -7 net-2.6/net/ipv4/tcp_ipv4.c: tcp_v4_get_port | -31 tcp_v4_hash | -48 tcp_v4_destroy_sock | -7 tcp_v4_syn_recv_sock | -2 tcp_unhash | -179 5 functions changed, 267 bytes removed, diff: -267 net-2.6/net/ipv6/inet6_hashtables.c: __inet6_hash | +8 1 function changed, 8 bytes added, diff: +8 net-2.6/net/ipv4/inet_hashtables.c: inet_unhash | +190 inet_hash | +242 2 functions changed, 432 bytes added, diff: +432 vmlinux: 16 functions changed, 485 bytes added, 492 bytes removed, diff: -7 /home/acme/git/net-2.6/net/ipv6/tcp_ipv6.c: tcp_v6_get_port | -31 tcp_v6_hash | -7 tcp_v6_syn_recv_sock | -9 3 functions changed, 47 bytes removed, diff: -47 /home/acme/git/net-2.6/net/dccp/proto.c: dccp_destroy_sock | -7 dccp_unhash | -179 dccp_hash | -49 dccp_set_state | -7 dccp_done | +1 5 functions changed, 1 bytes added, 242 bytes removed, diff: -241 /home/acme/git/net-2.6/net/dccp/ipv4.c: dccp_v4_get_port | -31 dccp_v4_request_recv_sock | -2 2 functions changed, 33 bytes removed, diff: -33 /home/acme/git/net-2.6/net/dccp/ipv6.c: dccp_v6_get_port | -31 dccp_v6_hash | -7 dccp_v6_request_recv_sock | +5 3 functions changed, 5 bytes added, 38 bytes removed, diff: -33 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-02-03 05:06:04 -07:00
.hash = inet_hash,
.unhash = inet_unhash,
.get_port = inet_csk_get_port,
.enter_memory_pressure = tcp_enter_memory_pressure,
.sockets_allocated = &tcp_sockets_allocated,
.orphan_count = &tcp_orphan_count,
.memory_allocated = &tcp_memory_allocated,
.memory_pressure = &tcp_memory_pressure,
.sysctl_mem = sysctl_tcp_mem,
.sysctl_wmem = sysctl_tcp_wmem,
.sysctl_rmem = sysctl_tcp_rmem,
.max_header = MAX_TCP_HEADER,
.obj_size = sizeof(struct tcp_sock),
.slab_flags = SLAB_DESTROY_BY_RCU,
.twsk_prot = &tcp_timewait_sock_ops,
.rsk_prot = &tcp_request_sock_ops,
.h.hashinfo = &tcp_hashinfo,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_tcp_setsockopt,
.compat_getsockopt = compat_tcp_getsockopt,
#endif
};
EXPORT_SYMBOL(tcp_prot);
static int __net_init tcp_sk_init(struct net *net)
{
return inet_ctl_sock_create(&net->ipv4.tcp_sock,
PF_INET, SOCK_RAW, IPPROTO_TCP, net);
}
static void __net_exit tcp_sk_exit(struct net *net)
{
inet_ctl_sock_destroy(net->ipv4.tcp_sock);
}
static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list)
{
inet_twsk_purge(&tcp_hashinfo, &tcp_death_row, AF_INET);
}
static struct pernet_operations __net_initdata tcp_sk_ops = {
.init = tcp_sk_init,
.exit = tcp_sk_exit,
.exit_batch = tcp_sk_exit_batch,
};
void __init tcp_v4_init(void)
{
inet_hashinfo_init(&tcp_hashinfo);
if (register_pernet_subsys(&tcp_sk_ops))
panic("Failed to create the TCP control socket.\n");
}