OpenCloudOS-Kernel/net/ipv6/tcp_ipv6.c

2165 lines
53 KiB
C
Raw Normal View History

/*
* TCP over IPv6
* Linux INET6 implementation
*
* Authors:
* Pedro Roque <roque@di.fc.ul.pt>
*
* Based on:
* linux/net/ipv4/tcp.c
* linux/net/ipv4/tcp_input.c
* linux/net/ipv4/tcp_output.c
*
* Fixes:
* Hideaki YOSHIFUJI : sin6_scope_id support
* 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.
* YOSHIFUJI Hideaki @USAGI: convert /proc/net/tcp6 to seq_file.
*
* 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.
*/
#include <linux/bottom_half.h>
#include <linux/module.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/jiffies.h>
#include <linux/in.h>
#include <linux/in6.h>
#include <linux/netdevice.h>
#include <linux/init.h>
#include <linux/jhash.h>
#include <linux/ipsec.h>
#include <linux/times.h>
#include <linux/ipv6.h>
#include <linux/icmpv6.h>
#include <linux/random.h>
#include <net/tcp.h>
#include <net/ndisc.h>
#include <net/inet6_hashtables.h>
#include <net/inet6_connection_sock.h>
#include <net/ipv6.h>
#include <net/transp_v6.h>
#include <net/addrconf.h>
#include <net/ip6_route.h>
#include <net/ip6_checksum.h>
#include <net/inet_ecn.h>
#include <net/protocol.h>
#include <net/xfrm.h>
#include <net/snmp.h>
#include <net/dsfield.h>
#include <net/timewait_sock.h>
#include <net/netdma.h>
#include <net/inet_common.h>
#include <asm/uaccess.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/crypto.h>
#include <linux/scatterlist.h>
static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb);
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 14:50:04 +08:00
static void tcp_v6_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
struct request_sock *req);
static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb);
static struct inet_connection_sock_af_ops ipv6_mapped;
static struct inet_connection_sock_af_ops ipv6_specific;
#ifdef CONFIG_TCP_MD5SIG
static struct tcp_sock_af_ops tcp_sock_ipv6_specific;
static struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific;
#else
static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(struct sock *sk,
struct in6_addr *addr)
{
return NULL;
}
#endif
static void tcp_v6_hash(struct sock *sk)
{
if (sk->sk_state != TCP_CLOSE) {
if (inet_csk(sk)->icsk_af_ops == &ipv6_mapped) {
tcp_prot.hash(sk);
return;
}
local_bh_disable();
[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 20:06:04 +08:00
__inet6_hash(sk);
local_bh_enable();
}
}
static __inline__ __sum16 tcp_v6_check(int len,
struct in6_addr *saddr,
struct in6_addr *daddr,
__wsum base)
{
return csum_ipv6_magic(saddr, daddr, len, IPPROTO_TCP, base);
}
static __u32 tcp_v6_init_sequence(struct sk_buff *skb)
{
return secure_tcpv6_sequence_number(ipv6_hdr(skb)->daddr.s6_addr32,
ipv6_hdr(skb)->saddr.s6_addr32,
tcp_hdr(skb)->dest,
tcp_hdr(skb)->source);
}
static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
int addr_len)
{
struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr;
struct inet_sock *inet = inet_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct in6_addr *saddr = NULL, *final_p = NULL, final;
struct flowi fl;
struct dst_entry *dst;
int addr_type;
int err;
if (addr_len < SIN6_LEN_RFC2133)
return -EINVAL;
if (usin->sin6_family != AF_INET6)
return(-EAFNOSUPPORT);
memset(&fl, 0, sizeof(fl));
if (np->sndflow) {
fl.fl6_flowlabel = usin->sin6_flowinfo&IPV6_FLOWINFO_MASK;
IP6_ECN_flow_init(fl.fl6_flowlabel);
if (fl.fl6_flowlabel&IPV6_FLOWLABEL_MASK) {
struct ip6_flowlabel *flowlabel;
flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel);
if (flowlabel == NULL)
return -EINVAL;
ipv6_addr_copy(&usin->sin6_addr, &flowlabel->dst);
fl6_sock_release(flowlabel);
}
}
/*
* connect() to INADDR_ANY means loopback (BSD'ism).
*/
if(ipv6_addr_any(&usin->sin6_addr))
usin->sin6_addr.s6_addr[15] = 0x1;
addr_type = ipv6_addr_type(&usin->sin6_addr);
if(addr_type & IPV6_ADDR_MULTICAST)
return -ENETUNREACH;
if (addr_type&IPV6_ADDR_LINKLOCAL) {
if (addr_len >= sizeof(struct sockaddr_in6) &&
usin->sin6_scope_id) {
/* If interface is set while binding, indices
* must coincide.
*/
if (sk->sk_bound_dev_if &&
sk->sk_bound_dev_if != usin->sin6_scope_id)
return -EINVAL;
sk->sk_bound_dev_if = usin->sin6_scope_id;
}
/* Connect to link-local address requires an interface */
if (!sk->sk_bound_dev_if)
return -EINVAL;
}
if (tp->rx_opt.ts_recent_stamp &&
!ipv6_addr_equal(&np->daddr, &usin->sin6_addr)) {
tp->rx_opt.ts_recent = 0;
tp->rx_opt.ts_recent_stamp = 0;
tp->write_seq = 0;
}
ipv6_addr_copy(&np->daddr, &usin->sin6_addr);
np->flow_label = fl.fl6_flowlabel;
/*
* TCP over IPv4
*/
if (addr_type == IPV6_ADDR_MAPPED) {
u32 exthdrlen = icsk->icsk_ext_hdr_len;
struct sockaddr_in sin;
SOCK_DEBUG(sk, "connect: ipv4 mapped\n");
if (__ipv6_only_sock(sk))
return -ENETUNREACH;
sin.sin_family = AF_INET;
sin.sin_port = usin->sin6_port;
sin.sin_addr.s_addr = usin->sin6_addr.s6_addr32[3];
icsk->icsk_af_ops = &ipv6_mapped;
sk->sk_backlog_rcv = tcp_v4_do_rcv;
#ifdef CONFIG_TCP_MD5SIG
tp->af_specific = &tcp_sock_ipv6_mapped_specific;
#endif
err = tcp_v4_connect(sk, (struct sockaddr *)&sin, sizeof(sin));
if (err) {
icsk->icsk_ext_hdr_len = exthdrlen;
icsk->icsk_af_ops = &ipv6_specific;
sk->sk_backlog_rcv = tcp_v6_do_rcv;
#ifdef CONFIG_TCP_MD5SIG
tp->af_specific = &tcp_sock_ipv6_specific;
#endif
goto failure;
} else {
ipv6_addr_set(&np->saddr, 0, 0, htonl(0x0000FFFF),
inet->saddr);
ipv6_addr_set(&np->rcv_saddr, 0, 0, htonl(0x0000FFFF),
inet->rcv_saddr);
}
return err;
}
if (!ipv6_addr_any(&np->rcv_saddr))
saddr = &np->rcv_saddr;
fl.proto = IPPROTO_TCP;
ipv6_addr_copy(&fl.fl6_dst, &np->daddr);
ipv6_addr_copy(&fl.fl6_src,
(saddr ? saddr : &np->saddr));
fl.oif = sk->sk_bound_dev_if;
fl.fl_ip_dport = usin->sin6_port;
fl.fl_ip_sport = inet->sport;
if (np->opt && np->opt->srcrt) {
struct rt0_hdr *rt0 = (struct rt0_hdr *)np->opt->srcrt;
ipv6_addr_copy(&final, &fl.fl6_dst);
ipv6_addr_copy(&fl.fl6_dst, rt0->addr);
final_p = &final;
}
security_sk_classify_flow(sk, &fl);
err = ip6_dst_lookup(sk, &dst, &fl);
if (err)
goto failure;
if (final_p)
ipv6_addr_copy(&fl.fl6_dst, final_p);
err = __xfrm_lookup(sock_net(sk), &dst, &fl, sk, XFRM_LOOKUP_WAIT);
if (err < 0) {
if (err == -EREMOTE)
err = ip6_dst_blackhole(sk, &dst, &fl);
if (err < 0)
goto failure;
}
if (saddr == NULL) {
saddr = &fl.fl6_src;
ipv6_addr_copy(&np->rcv_saddr, saddr);
}
/* set the source address */
ipv6_addr_copy(&np->saddr, saddr);
inet->rcv_saddr = LOOPBACK4_IPV6;
[IPV6]: Added GSO support for TCPv6 This patch adds GSO support for IPv6 and TCPv6. This is based on a patch by Ananda Raju <Ananda.Raju@neterion.com>. His original description is: This patch enables TSO over IPv6. Currently Linux network stacks restricts TSO over IPv6 by clearing of the NETIF_F_TSO bit from "dev->features". This patch will remove this restriction. This patch will introduce a new flag NETIF_F_TSO6 which will be used to check whether device supports TSO over IPv6. If device support TSO over IPv6 then we don't clear of NETIF_F_TSO and which will make the TCP layer to create TSO packets. Any device supporting TSO over IPv6 will set NETIF_F_TSO6 flag in "dev->features" along with NETIF_F_TSO. In case when user disables TSO using ethtool, NETIF_F_TSO will get cleared from "dev->features". So even if we have NETIF_F_TSO6 we don't get TSO packets created by TCP layer. SKB_GSO_TCPV4 renamed to SKB_GSO_TCP to make it generic GSO packet. SKB_GSO_UDPV4 renamed to SKB_GSO_UDP as UFO is not a IPv4 feature. UFO is supported over IPv6 also The following table shows there is significant improvement in throughput with normal frames and CPU usage for both normal and jumbo. -------------------------------------------------- | | 1500 | 9600 | | ------------------|-------------------| | | thru CPU | thru CPU | -------------------------------------------------- | TSO OFF | 2.00 5.5% id | 5.66 20.0% id | -------------------------------------------------- | TSO ON | 2.63 78.0 id | 5.67 39.0% id | -------------------------------------------------- Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-07-01 04:37:03 +08:00
sk->sk_gso_type = SKB_GSO_TCPV6;
__ip6_dst_store(sk, dst, NULL, NULL);
icsk->icsk_ext_hdr_len = 0;
if (np->opt)
icsk->icsk_ext_hdr_len = (np->opt->opt_flen +
np->opt->opt_nflen);
tp->rx_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr);
inet->dport = usin->sin6_port;
tcp_set_state(sk, TCP_SYN_SENT);
err = inet6_hash_connect(&tcp_death_row, sk);
if (err)
goto late_failure;
if (!tp->write_seq)
tp->write_seq = secure_tcpv6_sequence_number(np->saddr.s6_addr32,
np->daddr.s6_addr32,
inet->sport,
inet->dport);
err = tcp_connect(sk);
if (err)
goto late_failure;
return 0;
late_failure:
tcp_set_state(sk, TCP_CLOSE);
__sk_dst_reset(sk);
failure:
inet->dport = 0;
sk->sk_route_caps = 0;
return err;
}
static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
struct ipv6hdr *hdr = (struct ipv6hdr*)skb->data;
const struct tcphdr *th = (struct tcphdr *)(skb->data+offset);
struct ipv6_pinfo *np;
struct sock *sk;
int err;
struct tcp_sock *tp;
__u32 seq;
struct net *net = dev_net(skb->dev);
sk = inet6_lookup(net, &tcp_hashinfo, &hdr->daddr,
th->dest, &hdr->saddr, th->source, skb->dev->ifindex);
if (sk == NULL) {
ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev),
ICMP6_MIB_INERRORS);
return;
}
if (sk->sk_state == TCP_TIME_WAIT) {
inet_twsk_put(inet_twsk(sk));
return;
}
bh_lock_sock(sk);
if (sock_owned_by_user(sk))
NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS);
if (sk->sk_state == TCP_CLOSE)
goto out;
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;
}
np = inet6_sk(sk);
if (type == ICMPV6_PKT_TOOBIG) {
struct dst_entry *dst = NULL;
if (sock_owned_by_user(sk))
goto out;
if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))
goto out;
/* icmp should have updated the destination cache entry */
dst = __sk_dst_check(sk, np->dst_cookie);
if (dst == NULL) {
struct inet_sock *inet = inet_sk(sk);
struct flowi fl;
/* BUGGG_FUTURE: Again, it is not clear how
to handle rthdr case. Ignore this complexity
for now.
*/
memset(&fl, 0, sizeof(fl));
fl.proto = IPPROTO_TCP;
ipv6_addr_copy(&fl.fl6_dst, &np->daddr);
ipv6_addr_copy(&fl.fl6_src, &np->saddr);
fl.oif = sk->sk_bound_dev_if;
fl.fl_ip_dport = inet->dport;
fl.fl_ip_sport = inet->sport;
security_skb_classify_flow(skb, &fl);
if ((err = ip6_dst_lookup(sk, &dst, &fl))) {
sk->sk_err_soft = -err;
goto out;
}
if ((err = xfrm_lookup(net, &dst, &fl, sk, 0)) < 0) {
sk->sk_err_soft = -err;
goto out;
}
} else
dst_hold(dst);
if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) {
tcp_sync_mss(sk, dst_mtu(dst));
tcp_simple_retransmit(sk);
} /* else let the usual retransmit timer handle it */
dst_release(dst);
goto out;
}
icmpv6_err_convert(type, code, &err);
/* Might be for an request_sock */
switch (sk->sk_state) {
struct request_sock *req, **prev;
case TCP_LISTEN:
if (sock_owned_by_user(sk))
goto out;
req = inet6_csk_search_req(sk, &prev, th->dest, &hdr->daddr,
&hdr->saddr, inet6_iif(skb));
if (!req)
goto out;
/* ICMPs are not backlogged, hence we cannot get
* an established socket here.
*/
WARN_ON(req->sk != NULL);
if (seq != tcp_rsk(req)->snt_isn) {
NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
goto out;
}
inet_csk_reqsk_queue_drop(sk, req, prev);
goto out;
case TCP_SYN_SENT:
case TCP_SYN_RECV: /* Cannot happen.
It can, it SYNs are crossed. --ANK */
if (!sock_owned_by_user(sk)) {
sk->sk_err = err;
sk->sk_error_report(sk); /* Wake people up to see the error (see connect in sock.c) */
tcp_done(sk);
} else
sk->sk_err_soft = err;
goto out;
}
if (!sock_owned_by_user(sk) && np->recverr) {
sk->sk_err = err;
sk->sk_error_report(sk);
} else
sk->sk_err_soft = err;
out:
bh_unlock_sock(sk);
sock_put(sk);
}
static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req)
{
struct inet6_request_sock *treq = inet6_rsk(req);
struct ipv6_pinfo *np = inet6_sk(sk);
struct sk_buff * skb;
struct ipv6_txoptions *opt = NULL;
struct in6_addr * final_p = NULL, final;
struct flowi fl;
struct dst_entry *dst;
int err = -1;
memset(&fl, 0, sizeof(fl));
fl.proto = IPPROTO_TCP;
ipv6_addr_copy(&fl.fl6_dst, &treq->rmt_addr);
ipv6_addr_copy(&fl.fl6_src, &treq->loc_addr);
fl.fl6_flowlabel = 0;
fl.oif = treq->iif;
fl.fl_ip_dport = inet_rsk(req)->rmt_port;
fl.fl_ip_sport = inet_rsk(req)->loc_port;
security_req_classify_flow(req, &fl);
opt = np->opt;
if (opt && opt->srcrt) {
struct rt0_hdr *rt0 = (struct rt0_hdr *) opt->srcrt;
ipv6_addr_copy(&final, &fl.fl6_dst);
ipv6_addr_copy(&fl.fl6_dst, rt0->addr);
final_p = &final;
}
err = ip6_dst_lookup(sk, &dst, &fl);
if (err)
goto done;
if (final_p)
ipv6_addr_copy(&fl.fl6_dst, final_p);
if ((err = xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0)) < 0)
goto done;
skb = tcp_make_synack(sk, dst, req);
if (skb) {
struct tcphdr *th = tcp_hdr(skb);
th->check = tcp_v6_check(skb->len,
&treq->loc_addr, &treq->rmt_addr,
csum_partial(th, skb->len, skb->csum));
ipv6_addr_copy(&fl.fl6_dst, &treq->rmt_addr);
err = ip6_xmit(sk, skb, &fl, opt, 0);
err = net_xmit_eval(err);
}
done:
if (opt && opt != np->opt)
sock_kfree_s(sk, opt, opt->tot_len);
dst_release(dst);
return err;
}
static inline void syn_flood_warning(struct sk_buff *skb)
{
#ifdef CONFIG_SYN_COOKIES
if (sysctl_tcp_syncookies)
printk(KERN_INFO
"TCPv6: Possible SYN flooding on port %d. "
"Sending cookies.\n", ntohs(tcp_hdr(skb)->dest));
else
#endif
printk(KERN_INFO
"TCPv6: Possible SYN flooding on port %d. "
"Dropping request.\n", ntohs(tcp_hdr(skb)->dest));
}
static void tcp_v6_reqsk_destructor(struct request_sock *req)
{
kfree_skb(inet6_rsk(req)->pktopts);
}
#ifdef CONFIG_TCP_MD5SIG
static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(struct sock *sk,
struct in6_addr *addr)
{
struct tcp_sock *tp = tcp_sk(sk);
int i;
BUG_ON(tp == NULL);
if (!tp->md5sig_info || !tp->md5sig_info->entries6)
return NULL;
for (i = 0; i < tp->md5sig_info->entries6; i++) {
if (ipv6_addr_equal(&tp->md5sig_info->keys6[i].addr, addr))
return &tp->md5sig_info->keys6[i].base;
}
return NULL;
}
static struct tcp_md5sig_key *tcp_v6_md5_lookup(struct sock *sk,
struct sock *addr_sk)
{
return tcp_v6_md5_do_lookup(sk, &inet6_sk(addr_sk)->daddr);
}
static struct tcp_md5sig_key *tcp_v6_reqsk_md5_lookup(struct sock *sk,
struct request_sock *req)
{
return tcp_v6_md5_do_lookup(sk, &inet6_rsk(req)->rmt_addr);
}
static int tcp_v6_md5_do_add(struct sock *sk, struct in6_addr *peer,
char *newkey, u8 newkeylen)
{
/* Add key to the list */
struct tcp_md5sig_key *key;
struct tcp_sock *tp = tcp_sk(sk);
struct tcp6_md5sig_key *keys;
key = tcp_v6_md5_do_lookup(sk, peer);
if (key) {
/* modify existing entry - just update that one */
kfree(key->key);
key->key = newkey;
key->keylen = newkeylen;
} else {
/* reallocate new list if current one is full. */
if (!tp->md5sig_info) {
tp->md5sig_info = kzalloc(sizeof(*tp->md5sig_info), GFP_ATOMIC);
if (!tp->md5sig_info) {
kfree(newkey);
return -ENOMEM;
}
sk->sk_route_caps &= ~NETIF_F_GSO_MASK;
}
if (tcp_alloc_md5sig_pool() == NULL) {
kfree(newkey);
return -ENOMEM;
}
if (tp->md5sig_info->alloced6 == tp->md5sig_info->entries6) {
keys = kmalloc((sizeof (tp->md5sig_info->keys6[0]) *
(tp->md5sig_info->entries6 + 1)), GFP_ATOMIC);
if (!keys) {
tcp_free_md5sig_pool();
kfree(newkey);
return -ENOMEM;
}
if (tp->md5sig_info->entries6)
memmove(keys, tp->md5sig_info->keys6,
(sizeof (tp->md5sig_info->keys6[0]) *
tp->md5sig_info->entries6));
kfree(tp->md5sig_info->keys6);
tp->md5sig_info->keys6 = keys;
tp->md5sig_info->alloced6++;
}
ipv6_addr_copy(&tp->md5sig_info->keys6[tp->md5sig_info->entries6].addr,
peer);
tp->md5sig_info->keys6[tp->md5sig_info->entries6].base.key = newkey;
tp->md5sig_info->keys6[tp->md5sig_info->entries6].base.keylen = newkeylen;
tp->md5sig_info->entries6++;
}
return 0;
}
static int tcp_v6_md5_add_func(struct sock *sk, struct sock *addr_sk,
u8 *newkey, __u8 newkeylen)
{
return tcp_v6_md5_do_add(sk, &inet6_sk(addr_sk)->daddr,
newkey, newkeylen);
}
static int tcp_v6_md5_do_del(struct sock *sk, struct in6_addr *peer)
{
struct tcp_sock *tp = tcp_sk(sk);
int i;
for (i = 0; i < tp->md5sig_info->entries6; i++) {
if (ipv6_addr_equal(&tp->md5sig_info->keys6[i].addr, peer)) {
/* Free the key */
kfree(tp->md5sig_info->keys6[i].base.key);
tp->md5sig_info->entries6--;
if (tp->md5sig_info->entries6 == 0) {
kfree(tp->md5sig_info->keys6);
tp->md5sig_info->keys6 = NULL;
tp->md5sig_info->alloced6 = 0;
} else {
/* shrink the database */
if (tp->md5sig_info->entries6 != i)
memmove(&tp->md5sig_info->keys6[i],
&tp->md5sig_info->keys6[i+1],
(tp->md5sig_info->entries6 - i)
* sizeof (tp->md5sig_info->keys6[0]));
}
tcp_free_md5sig_pool();
return 0;
}
}
return -ENOENT;
}
static void tcp_v6_clear_md5_list (struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
int i;
if (tp->md5sig_info->entries6) {
for (i = 0; i < tp->md5sig_info->entries6; i++)
kfree(tp->md5sig_info->keys6[i].base.key);
tp->md5sig_info->entries6 = 0;
tcp_free_md5sig_pool();
}
kfree(tp->md5sig_info->keys6);
tp->md5sig_info->keys6 = NULL;
tp->md5sig_info->alloced6 = 0;
if (tp->md5sig_info->entries4) {
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();
}
kfree(tp->md5sig_info->keys4);
tp->md5sig_info->keys4 = NULL;
tp->md5sig_info->alloced4 = 0;
}
static int tcp_v6_parse_md5_keys (struct sock *sk, char __user *optval,
int optlen)
{
struct tcp_md5sig cmd;
struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)&cmd.tcpm_addr;
u8 *newkey;
if (optlen < sizeof(cmd))
return -EINVAL;
if (copy_from_user(&cmd, optval, sizeof(cmd)))
return -EFAULT;
if (sin6->sin6_family != AF_INET6)
return -EINVAL;
if (!cmd.tcpm_keylen) {
if (!tcp_sk(sk)->md5sig_info)
return -ENOENT;
if (ipv6_addr_v4mapped(&sin6->sin6_addr))
return tcp_v4_md5_do_del(sk, sin6->sin6_addr.s6_addr32[3]);
return tcp_v6_md5_do_del(sk, &sin6->sin6_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(struct tcp_md5sig_info), GFP_KERNEL);
if (!p)
return -ENOMEM;
tp->md5sig_info = p;
sk->sk_route_caps &= ~NETIF_F_GSO_MASK;
}
newkey = kmemdup(cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL);
if (!newkey)
return -ENOMEM;
if (ipv6_addr_v4mapped(&sin6->sin6_addr)) {
return tcp_v4_md5_do_add(sk, sin6->sin6_addr.s6_addr32[3],
newkey, cmd.tcpm_keylen);
}
return tcp_v6_md5_do_add(sk, &sin6->sin6_addr, newkey, cmd.tcpm_keylen);
}
static int tcp_v6_md5_hash_pseudoheader(struct tcp_md5sig_pool *hp,
struct in6_addr *daddr,
struct in6_addr *saddr, int nbytes)
{
struct tcp6_pseudohdr *bp;
struct scatterlist sg;
bp = &hp->md5_blk.ip6;
/* 1. TCP pseudo-header (RFC2460) */
ipv6_addr_copy(&bp->saddr, saddr);
ipv6_addr_copy(&bp->daddr, daddr);
bp->protocol = cpu_to_be32(IPPROTO_TCP);
bp->len = cpu_to_be32(nbytes);
sg_init_one(&sg, bp, sizeof(*bp));
return crypto_hash_update(&hp->md5_desc, &sg, sizeof(*bp));
}
static int tcp_v6_md5_hash_hdr(char *md5_hash, struct tcp_md5sig_key *key,
struct in6_addr *daddr, struct in6_addr *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_v6_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;
}
static int tcp_v6_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key,
struct sock *sk, struct request_sock *req,
struct sk_buff *skb)
{
struct in6_addr *saddr, *daddr;
struct tcp_md5sig_pool *hp;
struct hash_desc *desc;
struct tcphdr *th = tcp_hdr(skb);
if (sk) {
saddr = &inet6_sk(sk)->saddr;
daddr = &inet6_sk(sk)->daddr;
} else if (req) {
saddr = &inet6_rsk(req)->loc_addr;
daddr = &inet6_rsk(req)->rmt_addr;
} else {
struct ipv6hdr *ip6h = ipv6_hdr(skb);
saddr = &ip6h->saddr;
daddr = &ip6h->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_v6_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;
}
static int tcp_v6_inbound_md5_hash (struct sock *sk, struct sk_buff *skb)
{
__u8 *hash_location = NULL;
struct tcp_md5sig_key *hash_expected;
struct ipv6hdr *ip6h = ipv6_hdr(skb);
struct tcphdr *th = tcp_hdr(skb);
int genhash;
u8 newhash[16];
hash_expected = tcp_v6_md5_do_lookup(sk, &ip6h->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;
}
/* check the signature */
genhash = tcp_v6_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 %s for (%pI6, %u)->(%pI6, %u)\n",
genhash ? "failed" : "mismatch",
&ip6h->saddr, ntohs(th->source),
&ip6h->daddr, ntohs(th->dest));
}
return 1;
}
return 0;
}
#endif
struct request_sock_ops tcp6_request_sock_ops __read_mostly = {
.family = AF_INET6,
.obj_size = sizeof(struct tcp6_request_sock),
.rtx_syn_ack = tcp_v6_send_synack,
.send_ack = tcp_v6_reqsk_send_ack,
.destructor = tcp_v6_reqsk_destructor,
.send_reset = tcp_v6_send_reset
};
#ifdef CONFIG_TCP_MD5SIG
static struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = {
.md5_lookup = tcp_v6_reqsk_md5_lookup,
.calc_md5_hash = tcp_v6_md5_hash_skb,
};
#endif
static struct timewait_sock_ops tcp6_timewait_sock_ops = {
.twsk_obj_size = sizeof(struct tcp6_timewait_sock),
.twsk_unique = tcp_twsk_unique,
.twsk_destructor= tcp_twsk_destructor,
};
static void tcp_v6_send_check(struct sock *sk, int len, struct sk_buff *skb)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct tcphdr *th = tcp_hdr(skb);
if (skb->ip_summed == CHECKSUM_PARTIAL) {
th->check = ~csum_ipv6_magic(&np->saddr, &np->daddr, len, IPPROTO_TCP, 0);
skb->csum_start = skb_transport_header(skb) - skb->head;
skb->csum_offset = offsetof(struct tcphdr, check);
} else {
th->check = csum_ipv6_magic(&np->saddr, &np->daddr, len, IPPROTO_TCP,
csum_partial(th, th->doff<<2,
skb->csum));
}
}
static int tcp_v6_gso_send_check(struct sk_buff *skb)
{
struct ipv6hdr *ipv6h;
struct tcphdr *th;
if (!pskb_may_pull(skb, sizeof(*th)))
return -EINVAL;
ipv6h = ipv6_hdr(skb);
th = tcp_hdr(skb);
th->check = 0;
th->check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, skb->len,
IPPROTO_TCP, 0);
skb->csum_start = skb_transport_header(skb) - skb->head;
skb->csum_offset = offsetof(struct tcphdr, check);
skb->ip_summed = CHECKSUM_PARTIAL;
return 0;
}
static struct sk_buff **tcp6_gro_receive(struct sk_buff **head,
struct sk_buff *skb)
{
struct ipv6hdr *iph = skb_gro_network_header(skb);
switch (skb->ip_summed) {
case CHECKSUM_COMPLETE:
if (!tcp_v6_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);
}
static int tcp6_gro_complete(struct sk_buff *skb)
{
struct ipv6hdr *iph = ipv6_hdr(skb);
struct tcphdr *th = tcp_hdr(skb);
th->check = ~tcp_v6_check(skb->len - skb_transport_offset(skb),
&iph->saddr, &iph->daddr, 0);
skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
return tcp_gro_complete(skb);
}
static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win,
u32 ts, struct tcp_md5sig_key *key, int rst)
{
struct tcphdr *th = tcp_hdr(skb), *t1;
struct sk_buff *buff;
struct flowi fl;
struct net *net = dev_net(skb_dst(skb)->dev);
struct sock *ctl_sk = net->ipv6.tcp_sk;
unsigned int tot_len = sizeof(struct tcphdr);
struct dst_entry *dst;
tcpv6: convert opt[] -> topt in tcp_v6_send_reset after this I get: $ diff-funcs tcp_v6_send_reset tcp_ipv6.c tcp_ipv6.c tcp_v6_send_ack --- tcp_ipv6.c:tcp_v6_send_reset() +++ tcp_ipv6.c:tcp_v6_send_ack() @@ -1,4 +1,5 @@ -static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb) +static void tcp_v6_send_ack(struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 ts, + struct tcp_md5sig_key *key) { struct tcphdr *th = tcp_hdr(skb), *t1; struct sk_buff *buff; @@ -7,31 +8,14 @@ struct sock *ctl_sk = net->ipv6.tcp_sk; unsigned int tot_len = sizeof(struct tcphdr); __be32 *topt; -#ifdef CONFIG_TCP_MD5SIG - struct tcp_md5sig_key *key; -#endif - - if (th->rst) - return; - - if (!ipv6_unicast_destination(skb)) - return; + if (ts) + tot_len += TCPOLEN_TSTAMP_ALIGNED; #ifdef CONFIG_TCP_MD5SIG - if (sk) - key = tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr); - else - key = NULL; - if (key) tot_len += TCPOLEN_MD5SIG_ALIGNED; #endif - /* - * We need to grab some memory, and put together an RST, - * and then put it into the queue to be sent. - */ - buff = alloc_skb(MAX_HEADER + sizeof(struct ipv6hdr) + tot_len, GFP_ATOMIC); if (buff == NULL) @@ -46,18 +30,20 @@ t1->dest = th->source; t1->source = th->dest; t1->doff = tot_len / 4; - t1->rst = 1; - - if(th->ack) { - t1->seq = th->ack_seq; - } else { - t1->ack = 1; - t1->ack_seq = htonl(ntohl(th->seq) + th->syn + th->fin - + skb->len - (th->doff<<2)); - } + t1->seq = htonl(seq); + t1->ack_seq = htonl(ack); + t1->ack = 1; + t1->window = htons(win); topt = (__be32 *)(t1 + 1); + if (ts) { + *topt++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | + (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP); + *topt++ = htonl(tcp_time_stamp); + *topt++ = htonl(ts); + } + #ifdef CONFIG_TCP_MD5SIG if (key) { *topt++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | @@ -84,15 +70,10 @@ fl.fl_ip_sport = t1->source; security_skb_classify_flow(skb, &fl); - /* Pass a socket to ip6_dst_lookup either it is for RST - * Underlying function will use this to retrieve the network - * namespace - */ if (!ip6_dst_lookup(ctl_sk, &buff->dst, &fl)) { if (xfrm_lookup(&buff->dst, &fl, NULL, 0) >= 0) { ip6_xmit(ctl_sk, buff, &fl, NULL, 0); TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); - TCP_INC_STATS_BH(net, TCP_MIB_OUTRSTS); return; } } ...which starts to be trivial to combine. Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-10-10 05:42:01 +08:00
__be32 *topt;
if (ts)
tot_len += TCPOLEN_TSTAMP_ALIGNED;
#ifdef CONFIG_TCP_MD5SIG
if (key)
tot_len += TCPOLEN_MD5SIG_ALIGNED;
#endif
buff = alloc_skb(MAX_HEADER + sizeof(struct ipv6hdr) + tot_len,
GFP_ATOMIC);
if (buff == NULL)
return;
skb_reserve(buff, MAX_HEADER + sizeof(struct ipv6hdr) + tot_len);
t1 = (struct tcphdr *) skb_push(buff, tot_len);
/* Swap the send and the receive. */
memset(t1, 0, sizeof(*t1));
t1->dest = th->source;
t1->source = th->dest;
t1->doff = tot_len / 4;
t1->seq = htonl(seq);
t1->ack_seq = htonl(ack);
t1->ack = !rst || !th->ack;
t1->rst = rst;
t1->window = htons(win);
tcpv6: convert opt[] -> topt in tcp_v6_send_reset after this I get: $ diff-funcs tcp_v6_send_reset tcp_ipv6.c tcp_ipv6.c tcp_v6_send_ack --- tcp_ipv6.c:tcp_v6_send_reset() +++ tcp_ipv6.c:tcp_v6_send_ack() @@ -1,4 +1,5 @@ -static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb) +static void tcp_v6_send_ack(struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 ts, + struct tcp_md5sig_key *key) { struct tcphdr *th = tcp_hdr(skb), *t1; struct sk_buff *buff; @@ -7,31 +8,14 @@ struct sock *ctl_sk = net->ipv6.tcp_sk; unsigned int tot_len = sizeof(struct tcphdr); __be32 *topt; -#ifdef CONFIG_TCP_MD5SIG - struct tcp_md5sig_key *key; -#endif - - if (th->rst) - return; - - if (!ipv6_unicast_destination(skb)) - return; + if (ts) + tot_len += TCPOLEN_TSTAMP_ALIGNED; #ifdef CONFIG_TCP_MD5SIG - if (sk) - key = tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr); - else - key = NULL; - if (key) tot_len += TCPOLEN_MD5SIG_ALIGNED; #endif - /* - * We need to grab some memory, and put together an RST, - * and then put it into the queue to be sent. - */ - buff = alloc_skb(MAX_HEADER + sizeof(struct ipv6hdr) + tot_len, GFP_ATOMIC); if (buff == NULL) @@ -46,18 +30,20 @@ t1->dest = th->source; t1->source = th->dest; t1->doff = tot_len / 4; - t1->rst = 1; - - if(th->ack) { - t1->seq = th->ack_seq; - } else { - t1->ack = 1; - t1->ack_seq = htonl(ntohl(th->seq) + th->syn + th->fin - + skb->len - (th->doff<<2)); - } + t1->seq = htonl(seq); + t1->ack_seq = htonl(ack); + t1->ack = 1; + t1->window = htons(win); topt = (__be32 *)(t1 + 1); + if (ts) { + *topt++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | + (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP); + *topt++ = htonl(tcp_time_stamp); + *topt++ = htonl(ts); + } + #ifdef CONFIG_TCP_MD5SIG if (key) { *topt++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | @@ -84,15 +70,10 @@ fl.fl_ip_sport = t1->source; security_skb_classify_flow(skb, &fl); - /* Pass a socket to ip6_dst_lookup either it is for RST - * Underlying function will use this to retrieve the network - * namespace - */ if (!ip6_dst_lookup(ctl_sk, &buff->dst, &fl)) { if (xfrm_lookup(&buff->dst, &fl, NULL, 0) >= 0) { ip6_xmit(ctl_sk, buff, &fl, NULL, 0); TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); - TCP_INC_STATS_BH(net, TCP_MIB_OUTRSTS); return; } } ...which starts to be trivial to combine. Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-10-10 05:42:01 +08:00
topt = (__be32 *)(t1 + 1);
if (ts) {
*topt++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
(TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP);
*topt++ = htonl(tcp_time_stamp);
*topt++ = htonl(ts);
}
#ifdef CONFIG_TCP_MD5SIG
if (key) {
tcpv6: convert opt[] -> topt in tcp_v6_send_reset after this I get: $ diff-funcs tcp_v6_send_reset tcp_ipv6.c tcp_ipv6.c tcp_v6_send_ack --- tcp_ipv6.c:tcp_v6_send_reset() +++ tcp_ipv6.c:tcp_v6_send_ack() @@ -1,4 +1,5 @@ -static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb) +static void tcp_v6_send_ack(struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 ts, + struct tcp_md5sig_key *key) { struct tcphdr *th = tcp_hdr(skb), *t1; struct sk_buff *buff; @@ -7,31 +8,14 @@ struct sock *ctl_sk = net->ipv6.tcp_sk; unsigned int tot_len = sizeof(struct tcphdr); __be32 *topt; -#ifdef CONFIG_TCP_MD5SIG - struct tcp_md5sig_key *key; -#endif - - if (th->rst) - return; - - if (!ipv6_unicast_destination(skb)) - return; + if (ts) + tot_len += TCPOLEN_TSTAMP_ALIGNED; #ifdef CONFIG_TCP_MD5SIG - if (sk) - key = tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr); - else - key = NULL; - if (key) tot_len += TCPOLEN_MD5SIG_ALIGNED; #endif - /* - * We need to grab some memory, and put together an RST, - * and then put it into the queue to be sent. - */ - buff = alloc_skb(MAX_HEADER + sizeof(struct ipv6hdr) + tot_len, GFP_ATOMIC); if (buff == NULL) @@ -46,18 +30,20 @@ t1->dest = th->source; t1->source = th->dest; t1->doff = tot_len / 4; - t1->rst = 1; - - if(th->ack) { - t1->seq = th->ack_seq; - } else { - t1->ack = 1; - t1->ack_seq = htonl(ntohl(th->seq) + th->syn + th->fin - + skb->len - (th->doff<<2)); - } + t1->seq = htonl(seq); + t1->ack_seq = htonl(ack); + t1->ack = 1; + t1->window = htons(win); topt = (__be32 *)(t1 + 1); + if (ts) { + *topt++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | + (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP); + *topt++ = htonl(tcp_time_stamp); + *topt++ = htonl(ts); + } + #ifdef CONFIG_TCP_MD5SIG if (key) { *topt++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | @@ -84,15 +70,10 @@ fl.fl_ip_sport = t1->source; security_skb_classify_flow(skb, &fl); - /* Pass a socket to ip6_dst_lookup either it is for RST - * Underlying function will use this to retrieve the network - * namespace - */ if (!ip6_dst_lookup(ctl_sk, &buff->dst, &fl)) { if (xfrm_lookup(&buff->dst, &fl, NULL, 0) >= 0) { ip6_xmit(ctl_sk, buff, &fl, NULL, 0); TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); - TCP_INC_STATS_BH(net, TCP_MIB_OUTRSTS); return; } } ...which starts to be trivial to combine. Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-10-10 05:42:01 +08:00
*topt++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
(TCPOPT_MD5SIG << 8) | TCPOLEN_MD5SIG);
tcp_v6_md5_hash_hdr((__u8 *)topt, key,
&ipv6_hdr(skb)->saddr,
&ipv6_hdr(skb)->daddr, t1);
}
#endif
buff->csum = csum_partial(t1, tot_len, 0);
memset(&fl, 0, sizeof(fl));
ipv6_addr_copy(&fl.fl6_dst, &ipv6_hdr(skb)->saddr);
ipv6_addr_copy(&fl.fl6_src, &ipv6_hdr(skb)->daddr);
t1->check = csum_ipv6_magic(&fl.fl6_src, &fl.fl6_dst,
tot_len, IPPROTO_TCP,
buff->csum);
fl.proto = IPPROTO_TCP;
fl.oif = inet6_iif(skb);
fl.fl_ip_dport = t1->dest;
fl.fl_ip_sport = t1->source;
security_skb_classify_flow(skb, &fl);
/* Pass a socket to ip6_dst_lookup either it is for RST
* Underlying function will use this to retrieve the network
* namespace
*/
if (!ip6_dst_lookup(ctl_sk, &dst, &fl)) {
if (xfrm_lookup(net, &dst, &fl, NULL, 0) >= 0) {
skb_dst_set(buff, dst);
ip6_xmit(ctl_sk, buff, &fl, NULL, 0);
TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS);
if (rst)
TCP_INC_STATS_BH(net, TCP_MIB_OUTRSTS);
return;
}
}
kfree_skb(buff);
}
static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb)
{
struct tcphdr *th = tcp_hdr(skb);
u32 seq = 0, ack_seq = 0;
struct tcp_md5sig_key *key = NULL;
if (th->rst)
return;
if (!ipv6_unicast_destination(skb))
return;
#ifdef CONFIG_TCP_MD5SIG
if (sk)
key = tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr);
#endif
if (th->ack)
seq = ntohl(th->ack_seq);
else
ack_seq = ntohl(th->seq) + th->syn + th->fin + skb->len -
(th->doff << 2);
tcp_v6_send_response(skb, seq, ack_seq, 0, 0, key, 1);
}
static void tcp_v6_send_ack(struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 ts,
struct tcp_md5sig_key *key)
{
tcp_v6_send_response(skb, seq, ack, win, ts, key, 0);
}
static void tcp_v6_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_v6_send_ack(skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
tcptw->tw_ts_recent, tcp_twsk_md5_key(tcptw));
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 14:50:04 +08:00
static void tcp_v6_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
struct request_sock *req)
{
tcp_v6_send_ack(skb, tcp_rsk(req)->snt_isn + 1, tcp_rsk(req)->rcv_isn + 1, req->rcv_wnd, req->ts_recent,
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 14:50:04 +08:00
tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr));
}
static struct sock *tcp_v6_hnd_req(struct sock *sk,struct sk_buff *skb)
{
struct request_sock *req, **prev;
const struct tcphdr *th = tcp_hdr(skb);
struct sock *nsk;
/* Find possible connection requests. */
req = inet6_csk_search_req(sk, &prev, th->source,
&ipv6_hdr(skb)->saddr,
&ipv6_hdr(skb)->daddr, inet6_iif(skb));
if (req)
return tcp_check_req(sk, skb, req, prev);
nsk = __inet6_lookup_established(sock_net(sk), &tcp_hashinfo,
&ipv6_hdr(skb)->saddr, th->source,
&ipv6_hdr(skb)->daddr, ntohs(th->dest), inet6_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->rst && !th->syn && th->ack)
sk = cookie_v6_check(sk, skb);
#endif
return sk;
}
/* FIXME: this is substantially similar to the ipv4 code.
* Can some kind of merge be done? -- erics
*/
static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
{
struct inet6_request_sock *treq;
struct ipv6_pinfo *np = inet6_sk(sk);
struct tcp_options_received tmp_opt;
struct tcp_sock *tp = tcp_sk(sk);
struct request_sock *req = NULL;
__u32 isn = TCP_SKB_CB(skb)->when;
#ifdef CONFIG_SYN_COOKIES
int want_cookie = 0;
#else
#define want_cookie 0
#endif
if (skb->protocol == htons(ETH_P_IP))
return tcp_v4_conn_request(sk, skb);
if (!ipv6_unicast_destination(skb))
goto drop;
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;
}
if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1)
goto drop;
req = inet6_reqsk_alloc(&tcp6_request_sock_ops);
if (req == NULL)
goto drop;
#ifdef CONFIG_TCP_MD5SIG
tcp_rsk(req)->af_specific = &tcp_request_sock_ipv6_ops;
#endif
tcp_clear_options(&tmp_opt);
tmp_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr);
tmp_opt.user_mss = tp->rx_opt.user_mss;
tcp_parse_options(skb, &tmp_opt, 0);
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);
treq = inet6_rsk(req);
ipv6_addr_copy(&treq->rmt_addr, &ipv6_hdr(skb)->saddr);
ipv6_addr_copy(&treq->loc_addr, &ipv6_hdr(skb)->daddr);
if (!want_cookie)
TCP_ECN_create_request(req, tcp_hdr(skb));
if (want_cookie) {
isn = cookie_v6_init_sequence(sk, skb, &req->mss);
req->cookie_ts = tmp_opt.tstamp_ok;
} else if (!isn) {
if (ipv6_opt_accepted(sk, skb) ||
np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) {
atomic_inc(&skb->users);
treq->pktopts = skb;
}
treq->iif = sk->sk_bound_dev_if;
/* So that link locals have meaning */
if (!sk->sk_bound_dev_if &&
ipv6_addr_type(&treq->rmt_addr) & IPV6_ADDR_LINKLOCAL)
treq->iif = inet6_iif(skb);
isn = tcp_v6_init_sequence(skb);
}
tcp_rsk(req)->snt_isn = isn;
security_inet_conn_request(sk, skb, req);
if (tcp_v6_send_synack(sk, req))
goto drop;
if (!want_cookie) {
inet6_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
return 0;
}
drop:
if (req)
reqsk_free(req);
return 0; /* don't send reset */
}
static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
struct request_sock *req,
struct dst_entry *dst)
{
struct inet6_request_sock *treq;
struct ipv6_pinfo *newnp, *np = inet6_sk(sk);
struct tcp6_sock *newtcp6sk;
struct inet_sock *newinet;
struct tcp_sock *newtp;
struct sock *newsk;
struct ipv6_txoptions *opt;
#ifdef CONFIG_TCP_MD5SIG
struct tcp_md5sig_key *key;
#endif
if (skb->protocol == htons(ETH_P_IP)) {
/*
* v6 mapped
*/
newsk = tcp_v4_syn_recv_sock(sk, skb, req, dst);
if (newsk == NULL)
return NULL;
newtcp6sk = (struct tcp6_sock *)newsk;
inet_sk(newsk)->pinet6 = &newtcp6sk->inet6;
newinet = inet_sk(newsk);
newnp = inet6_sk(newsk);
newtp = tcp_sk(newsk);
memcpy(newnp, np, sizeof(struct ipv6_pinfo));
ipv6_addr_set(&newnp->daddr, 0, 0, htonl(0x0000FFFF),
newinet->daddr);
ipv6_addr_set(&newnp->saddr, 0, 0, htonl(0x0000FFFF),
newinet->saddr);
ipv6_addr_copy(&newnp->rcv_saddr, &newnp->saddr);
inet_csk(newsk)->icsk_af_ops = &ipv6_mapped;
newsk->sk_backlog_rcv = tcp_v4_do_rcv;
#ifdef CONFIG_TCP_MD5SIG
newtp->af_specific = &tcp_sock_ipv6_mapped_specific;
#endif
newnp->pktoptions = NULL;
newnp->opt = NULL;
newnp->mcast_oif = inet6_iif(skb);
newnp->mcast_hops = ipv6_hdr(skb)->hop_limit;
/*
* No need to charge this sock to the relevant IPv6 refcnt debug socks count
* here, tcp_create_openreq_child now does this for us, see the comment in
* that function for the gory details. -acme
*/
/* It is tricky place. Until this moment IPv4 tcp
worked with IPv6 icsk.icsk_af_ops.
Sync it now.
*/
tcp_sync_mss(newsk, inet_csk(newsk)->icsk_pmtu_cookie);
return newsk;
}
treq = inet6_rsk(req);
opt = np->opt;
if (sk_acceptq_is_full(sk))
goto out_overflow;
if (dst == NULL) {
struct in6_addr *final_p = NULL, final;
struct flowi fl;
memset(&fl, 0, sizeof(fl));
fl.proto = IPPROTO_TCP;
ipv6_addr_copy(&fl.fl6_dst, &treq->rmt_addr);
if (opt && opt->srcrt) {
struct rt0_hdr *rt0 = (struct rt0_hdr *) opt->srcrt;
ipv6_addr_copy(&final, &fl.fl6_dst);
ipv6_addr_copy(&fl.fl6_dst, rt0->addr);
final_p = &final;
}
ipv6_addr_copy(&fl.fl6_src, &treq->loc_addr);
fl.oif = sk->sk_bound_dev_if;
fl.fl_ip_dport = inet_rsk(req)->rmt_port;
fl.fl_ip_sport = inet_rsk(req)->loc_port;
security_req_classify_flow(req, &fl);
if (ip6_dst_lookup(sk, &dst, &fl))
goto out;
if (final_p)
ipv6_addr_copy(&fl.fl6_dst, final_p);
if ((xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0)) < 0)
goto out;
}
newsk = tcp_create_openreq_child(sk, req, skb);
if (newsk == NULL)
goto out;
/*
* No need to charge this sock to the relevant IPv6 refcnt debug socks
* count here, tcp_create_openreq_child now does this for us, see the
* comment in that function for the gory details. -acme
*/
newsk->sk_gso_type = SKB_GSO_TCPV6;
__ip6_dst_store(newsk, dst, NULL, NULL);
newtcp6sk = (struct tcp6_sock *)newsk;
inet_sk(newsk)->pinet6 = &newtcp6sk->inet6;
newtp = tcp_sk(newsk);
newinet = inet_sk(newsk);
newnp = inet6_sk(newsk);
memcpy(newnp, np, sizeof(struct ipv6_pinfo));
ipv6_addr_copy(&newnp->daddr, &treq->rmt_addr);
ipv6_addr_copy(&newnp->saddr, &treq->loc_addr);
ipv6_addr_copy(&newnp->rcv_saddr, &treq->loc_addr);
newsk->sk_bound_dev_if = treq->iif;
/* Now IPv6 options...
First: no IPv4 options.
*/
newinet->opt = NULL;
newnp->ipv6_fl_list = NULL;
/* Clone RX bits */
newnp->rxopt.all = np->rxopt.all;
/* Clone pktoptions received with SYN */
newnp->pktoptions = NULL;
if (treq->pktopts != NULL) {
newnp->pktoptions = skb_clone(treq->pktopts, GFP_ATOMIC);
kfree_skb(treq->pktopts);
treq->pktopts = NULL;
if (newnp->pktoptions)
skb_set_owner_r(newnp->pktoptions, newsk);
}
newnp->opt = NULL;
newnp->mcast_oif = inet6_iif(skb);
newnp->mcast_hops = ipv6_hdr(skb)->hop_limit;
/* Clone native IPv6 options from listening socket (if any)
Yes, keeping reference count would be much more clever,
but we make one more one thing there: reattach optmem
to newsk.
*/
if (opt) {
newnp->opt = ipv6_dup_options(newsk, opt);
if (opt != np->opt)
sock_kfree_s(sk, opt, opt->tot_len);
}
inet_csk(newsk)->icsk_ext_hdr_len = 0;
if (newnp->opt)
inet_csk(newsk)->icsk_ext_hdr_len = (newnp->opt->opt_nflen +
newnp->opt->opt_flen);
tcp_mtup_init(newsk);
tcp_sync_mss(newsk, dst_mtu(dst));
newtp->advmss = dst_metric(dst, RTAX_ADVMSS);
tcp_initialize_rcv_mss(newsk);
newinet->daddr = newinet->saddr = newinet->rcv_saddr = LOOPBACK4_IPV6;
#ifdef CONFIG_TCP_MD5SIG
/* Copy over the MD5 key from the original socket */
if ((key = tcp_v6_md5_do_lookup(sk, &newnp->daddr)) != 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_v6_md5_do_add(newsk, &newnp->daddr,
newkey, key->keylen);
}
#endif
[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 20:06:04 +08:00
__inet6_hash(newsk);
__inet_inherit_port(sk, newsk);
return newsk;
out_overflow:
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS);
out:
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
if (opt && opt != np->opt)
sock_kfree_s(sk, opt, opt->tot_len);
dst_release(dst);
return NULL;
}
static __sum16 tcp_v6_checksum_init(struct sk_buff *skb)
{
if (skb->ip_summed == CHECKSUM_COMPLETE) {
if (!tcp_v6_check(skb->len, &ipv6_hdr(skb)->saddr,
&ipv6_hdr(skb)->daddr, skb->csum)) {
skb->ip_summed = CHECKSUM_UNNECESSARY;
return 0;
}
}
skb->csum = ~csum_unfold(tcp_v6_check(skb->len,
&ipv6_hdr(skb)->saddr,
&ipv6_hdr(skb)->daddr, 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.
*/
static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct tcp_sock *tp;
struct sk_buff *opt_skb = NULL;
/* Imagine: socket is IPv6. IPv4 packet arrives,
goes to IPv4 receive handler and backlogged.
From backlog it always goes here. Kerboom...
Fortunately, tcp_rcv_established and rcv_established
handle them correctly, but it is not case with
tcp_v6_hnd_req and tcp_v6_send_reset(). --ANK
*/
if (skb->protocol == htons(ETH_P_IP))
return tcp_v4_do_rcv(sk, skb);
#ifdef CONFIG_TCP_MD5SIG
if (tcp_v6_inbound_md5_hash (sk, skb))
goto discard;
#endif
if (sk_filter(sk, skb))
goto discard;
/*
* socket locking is here for SMP purposes as backlog rcv
* is currently called with bh processing disabled.
*/
/* Do Stevens' IPV6_PKTOPTIONS.
Yes, guys, it is the only place in our code, where we
may make it not affecting IPv4.
The rest of code is protocol independent,
and I do not like idea to uglify IPv4.
Actually, all the idea behind IPV6_PKTOPTIONS
looks not very well thought. For now we latch
options, received in the last packet, enqueued
by tcp. Feel free to propose better solution.
--ANK (980728)
*/
if (np->rxopt.all)
opt_skb = skb_clone(skb, GFP_ATOMIC);
if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
TCP_CHECK_TIMER(sk);
if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len))
goto reset;
TCP_CHECK_TIMER(sk);
if (opt_skb)
goto ipv6_pktoptions;
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_v6_hnd_req(sk, skb);
if (!nsk)
goto discard;
/*
* Queue it on the new socket if the new socket is active,
* otherwise we just shortcircuit this and continue with
* the new socket..
*/
if(nsk != sk) {
if (tcp_child_process(sk, nsk, skb))
goto reset;
if (opt_skb)
__kfree_skb(opt_skb);
return 0;
}
}
TCP_CHECK_TIMER(sk);
if (tcp_rcv_state_process(sk, skb, tcp_hdr(skb), skb->len))
goto reset;
TCP_CHECK_TIMER(sk);
if (opt_skb)
goto ipv6_pktoptions;
return 0;
reset:
tcp_v6_send_reset(sk, skb);
discard:
if (opt_skb)
__kfree_skb(opt_skb);
kfree_skb(skb);
return 0;
csum_err:
TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_INERRS);
goto discard;
ipv6_pktoptions:
/* Do you ask, what is it?
1. skb was enqueued by tcp.
2. skb is added to tail of read queue, rather than out of order.
3. socket is not in passive state.
4. Finally, it really contains options, which user wants to receive.
*/
tp = tcp_sk(sk);
if (TCP_SKB_CB(opt_skb)->end_seq == tp->rcv_nxt &&
!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) {
if (np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo)
np->mcast_oif = inet6_iif(opt_skb);
if (np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim)
np->mcast_hops = ipv6_hdr(opt_skb)->hop_limit;
if (ipv6_opt_accepted(sk, opt_skb)) {
skb_set_owner_r(opt_skb, sk);
opt_skb = xchg(&np->pktoptions, opt_skb);
} else {
__kfree_skb(opt_skb);
opt_skb = xchg(&np->pktoptions, NULL);
}
}
kfree_skb(opt_skb);
return 0;
}
static int tcp_v6_rcv(struct sk_buff *skb)
{
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;
if (!skb_csum_unnecessary(skb) && tcp_v6_checksum_init(skb))
goto bad_packet;
th = tcp_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 = ipv6_get_dsfield(ipv6_hdr(skb));
TCP_SKB_CB(skb)->sacked = 0;
sk = __inet6_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 (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb))
goto discard_and_relse;
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_v6_do_rcv(sk, skb);
else
#endif
{
if (!tcp_prequeue(sk, skb))
ret = tcp_v6_do_rcv(sk, skb);
}
} else
sk_add_backlog(sk, skb);
bh_unlock_sock(sk);
sock_put(sk);
return ret ? -1 : 0;
no_tcp_socket:
if (!xfrm6_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_v6_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 (!xfrm6_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;
sk2 = inet6_lookup_listener(dev_net(skb->dev), &tcp_hashinfo,
&ipv6_hdr(skb)->daddr,
ntohs(th->dest), inet6_iif(skb));
if (sk2 != NULL) {
struct inet_timewait_sock *tw = inet_twsk(sk);
inet_twsk_deschedule(tw, &tcp_death_row);
inet_twsk_put(tw);
sk = sk2;
goto process;
}
/* Fall through to ACK */
}
case TCP_TW_ACK:
tcp_v6_timewait_ack(sk, skb);
break;
case TCP_TW_RST:
goto no_tcp_socket;
case TCP_TW_SUCCESS:;
}
goto discard_it;
}
static int tcp_v6_remember_stamp(struct sock *sk)
{
/* Alas, not yet... */
return 0;
}
static struct inet_connection_sock_af_ops ipv6_specific = {
.queue_xmit = inet6_csk_xmit,
.send_check = tcp_v6_send_check,
.rebuild_header = inet6_sk_rebuild_header,
.conn_request = tcp_v6_conn_request,
.syn_recv_sock = tcp_v6_syn_recv_sock,
.remember_stamp = tcp_v6_remember_stamp,
.net_header_len = sizeof(struct ipv6hdr),
.setsockopt = ipv6_setsockopt,
.getsockopt = ipv6_getsockopt,
.addr2sockaddr = inet6_csk_addr2sockaddr,
.sockaddr_len = sizeof(struct sockaddr_in6),
[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 20:06:04 +08:00
.bind_conflict = inet6_csk_bind_conflict,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_ipv6_setsockopt,
.compat_getsockopt = compat_ipv6_getsockopt,
#endif
};
#ifdef CONFIG_TCP_MD5SIG
static struct tcp_sock_af_ops tcp_sock_ipv6_specific = {
.md5_lookup = tcp_v6_md5_lookup,
.calc_md5_hash = tcp_v6_md5_hash_skb,
.md5_add = tcp_v6_md5_add_func,
.md5_parse = tcp_v6_parse_md5_keys,
};
#endif
/*
* TCP over IPv4 via INET6 API
*/
static struct inet_connection_sock_af_ops ipv6_mapped = {
.queue_xmit = ip_queue_xmit,
.send_check = tcp_v4_send_check,
.rebuild_header = inet_sk_rebuild_header,
.conn_request = tcp_v6_conn_request,
.syn_recv_sock = tcp_v6_syn_recv_sock,
.remember_stamp = tcp_v4_remember_stamp,
.net_header_len = sizeof(struct iphdr),
.setsockopt = ipv6_setsockopt,
.getsockopt = ipv6_getsockopt,
.addr2sockaddr = inet6_csk_addr2sockaddr,
.sockaddr_len = sizeof(struct sockaddr_in6),
[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 20:06:04 +08:00
.bind_conflict = inet6_csk_bind_conflict,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_ipv6_setsockopt,
.compat_getsockopt = compat_ipv6_getsockopt,
#endif
};
#ifdef CONFIG_TCP_MD5SIG
static struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific = {
.md5_lookup = tcp_v4_md5_lookup,
.calc_md5_hash = tcp_v4_md5_hash_skb,
.md5_add = tcp_v6_md5_add_func,
.md5_parse = tcp_v6_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_v6_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 = 0x7fffffff;
tp->snd_cwnd_clamp = ~0;
tp->mss_cache = 536;
tp->reordering = sysctl_tcp_reordering;
sk->sk_state = TCP_CLOSE;
icsk->icsk_af_ops = &ipv6_specific;
icsk->icsk_ca_ops = &tcp_init_congestion_ops;
icsk->icsk_sync_mss = tcp_sync_mss;
sk->sk_write_space = sk_stream_write_space;
sock_set_flag(sk, SOCK_USE_WRITE_QUEUE);
#ifdef CONFIG_TCP_MD5SIG
tp->af_specific = &tcp_sock_ipv6_specific;
#endif
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;
}
static void tcp_v6_destroy_sock(struct sock *sk)
{
#ifdef CONFIG_TCP_MD5SIG
/* Clean up the MD5 key list */
if (tcp_sk(sk)->md5sig_info)
tcp_v6_clear_md5_list(sk);
#endif
tcp_v4_destroy_sock(sk);
inet6_destroy_sock(sk);
}
#ifdef CONFIG_PROC_FS
/* Proc filesystem TCPv6 sock list dumping. */
static void get_openreq6(struct seq_file *seq,
struct sock *sk, struct request_sock *req, int i, int uid)
{
int ttd = req->expires - jiffies;
struct in6_addr *src = &inet6_rsk(req)->loc_addr;
struct in6_addr *dest = &inet6_rsk(req)->rmt_addr;
if (ttd < 0)
ttd = 0;
seq_printf(seq,
"%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X "
"%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %p\n",
i,
src->s6_addr32[0], src->s6_addr32[1],
src->s6_addr32[2], src->s6_addr32[3],
ntohs(inet_rsk(req)->loc_port),
dest->s6_addr32[0], dest->s6_addr32[1],
dest->s6_addr32[2], dest->s6_addr32[3],
ntohs(inet_rsk(req)->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 */
0, req);
}
static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
{
struct in6_addr *dest, *src;
__u16 destp, srcp;
int timer_active;
unsigned long timer_expires;
struct inet_sock *inet = inet_sk(sp);
struct tcp_sock *tp = tcp_sk(sp);
const struct inet_connection_sock *icsk = inet_csk(sp);
struct ipv6_pinfo *np = inet6_sk(sp);
dest = &np->daddr;
src = &np->rcv_saddr;
destp = ntohs(inet->dport);
srcp = ntohs(inet->sport);
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(&sp->sk_timer)) {
timer_active = 2;
timer_expires = sp->sk_timer.expires;
} else {
timer_active = 0;
timer_expires = jiffies;
}
seq_printf(seq,
"%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X "
"%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %lu %lu %u %u %d\n",
i,
src->s6_addr32[0], src->s6_addr32[1],
src->s6_addr32[2], src->s6_addr32[3], srcp,
dest->s6_addr32[0], dest->s6_addr32[1],
dest->s6_addr32[2], dest->s6_addr32[3], destp,
sp->sk_state,
tp->write_seq-tp->snd_una,
(sp->sk_state == TCP_LISTEN) ? sp->sk_ack_backlog : (tp->rcv_nxt - tp->copied_seq),
timer_active,
jiffies_to_clock_t(timer_expires - jiffies),
icsk->icsk_retransmits,
sock_i_uid(sp),
icsk->icsk_probes_out,
sock_i_ino(sp),
atomic_read(&sp->sk_refcnt), sp,
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, tp->snd_ssthresh>=0xFFFF?-1:tp->snd_ssthresh
);
}
static void get_timewait6_sock(struct seq_file *seq,
struct inet_timewait_sock *tw, int i)
{
struct in6_addr *dest, *src;
__u16 destp, srcp;
struct inet6_timewait_sock *tw6 = inet6_twsk((struct sock *)tw);
int ttd = tw->tw_ttd - jiffies;
if (ttd < 0)
ttd = 0;
dest = &tw6->tw_v6_daddr;
src = &tw6->tw_v6_rcv_saddr;
destp = ntohs(tw->tw_dport);
srcp = ntohs(tw->tw_sport);
seq_printf(seq,
"%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X "
"%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %p\n",
i,
src->s6_addr32[0], src->s6_addr32[1],
src->s6_addr32[2], src->s6_addr32[3], srcp,
dest->s6_addr32[0], dest->s6_addr32[1],
dest->s6_addr32[2], dest->s6_addr32[3], destp,
tw->tw_substate, 0, 0,
3, jiffies_to_clock_t(ttd), 0, 0, 0, 0,
atomic_read(&tw->tw_refcnt), tw);
}
static int tcp6_seq_show(struct seq_file *seq, void *v)
{
struct tcp_iter_state *st;
if (v == SEQ_START_TOKEN) {
seq_puts(seq,
" sl "
"local_address "
"remote_address "
"st tx_queue rx_queue tr tm->when retrnsmt"
" uid timeout inode\n");
goto out;
}
st = seq->private;
switch (st->state) {
case TCP_SEQ_STATE_LISTENING:
case TCP_SEQ_STATE_ESTABLISHED:
get_tcp6_sock(seq, v, st->num);
break;
case TCP_SEQ_STATE_OPENREQ:
get_openreq6(seq, st->syn_wait_sk, v, st->num, st->uid);
break;
case TCP_SEQ_STATE_TIME_WAIT:
get_timewait6_sock(seq, v, st->num);
break;
}
out:
return 0;
}
static struct tcp_seq_afinfo tcp6_seq_afinfo = {
.name = "tcp6",
.family = AF_INET6,
.seq_fops = {
.owner = THIS_MODULE,
},
.seq_ops = {
.show = tcp6_seq_show,
},
};
int tcp6_proc_init(struct net *net)
{
return tcp_proc_register(net, &tcp6_seq_afinfo);
}
void tcp6_proc_exit(struct net *net)
{
tcp_proc_unregister(net, &tcp6_seq_afinfo);
}
#endif
struct proto tcpv6_prot = {
.name = "TCPv6",
.owner = THIS_MODULE,
.close = tcp_close,
.connect = tcp_v6_connect,
.disconnect = tcp_disconnect,
.accept = inet_csk_accept,
.ioctl = tcp_ioctl,
.init = tcp_v6_init_sock,
.destroy = tcp_v6_destroy_sock,
.shutdown = tcp_shutdown,
.setsockopt = tcp_setsockopt,
.getsockopt = tcp_getsockopt,
.recvmsg = tcp_recvmsg,
.backlog_rcv = tcp_v6_do_rcv,
.hash = tcp_v6_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 20:06:04 +08:00
.unhash = inet_unhash,
.get_port = inet_csk_get_port,
.enter_memory_pressure = tcp_enter_memory_pressure,
.sockets_allocated = &tcp_sockets_allocated,
.memory_allocated = &tcp_memory_allocated,
.memory_pressure = &tcp_memory_pressure,
.orphan_count = &tcp_orphan_count,
.sysctl_mem = sysctl_tcp_mem,
.sysctl_wmem = sysctl_tcp_wmem,
.sysctl_rmem = sysctl_tcp_rmem,
.max_header = MAX_TCP_HEADER,
.obj_size = sizeof(struct tcp6_sock),
.slab_flags = SLAB_DESTROY_BY_RCU,
.twsk_prot = &tcp6_timewait_sock_ops,
.rsk_prot = &tcp6_request_sock_ops,
.h.hashinfo = &tcp_hashinfo,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_tcp_setsockopt,
.compat_getsockopt = compat_tcp_getsockopt,
#endif
};
static struct inet6_protocol tcpv6_protocol = {
.handler = tcp_v6_rcv,
.err_handler = tcp_v6_err,
.gso_send_check = tcp_v6_gso_send_check,
.gso_segment = tcp_tso_segment,
.gro_receive = tcp6_gro_receive,
.gro_complete = tcp6_gro_complete,
.flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,
};
static struct inet_protosw tcpv6_protosw = {
.type = SOCK_STREAM,
.protocol = IPPROTO_TCP,
.prot = &tcpv6_prot,
.ops = &inet6_stream_ops,
.capability = -1,
.no_check = 0,
.flags = INET_PROTOSW_PERMANENT |
INET_PROTOSW_ICSK,
};
static int tcpv6_net_init(struct net *net)
{
return inet_ctl_sock_create(&net->ipv6.tcp_sk, PF_INET6,
SOCK_RAW, IPPROTO_TCP, net);
}
static void tcpv6_net_exit(struct net *net)
{
inet_ctl_sock_destroy(net->ipv6.tcp_sk);
netns : fix kernel panic in timewait socket destruction How to reproduce ? - create a network namespace - use tcp protocol and get timewait socket - exit the network namespace - after a moment (when the timewait socket is destroyed), the kernel panics. # BUG: unable to handle kernel NULL pointer dereference at 0000000000000007 IP: [<ffffffff821e394d>] inet_twdr_do_twkill_work+0x6e/0xb8 PGD 119985067 PUD 11c5c0067 PMD 0 Oops: 0000 [1] SMP CPU 1 Modules linked in: ipv6 button battery ac loop dm_mod tg3 libphy ext3 jbd edd fan thermal processor thermal_sys sg sata_svw libata dock serverworks sd_mod scsi_mod ide_disk ide_core [last unloaded: freq_table] Pid: 0, comm: swapper Not tainted 2.6.27-rc2 #3 RIP: 0010:[<ffffffff821e394d>] [<ffffffff821e394d>] inet_twdr_do_twkill_work+0x6e/0xb8 RSP: 0018:ffff88011ff7fed0 EFLAGS: 00010246 RAX: ffffffffffffffff RBX: ffffffff82339420 RCX: ffff88011ff7ff30 RDX: 0000000000000001 RSI: ffff88011a4d03c0 RDI: ffff88011ac2fc00 RBP: ffffffff823392e0 R08: 0000000000000000 R09: ffff88002802a200 R10: ffff8800a5c4b000 R11: ffffffff823e4080 R12: ffff88011ac2fc00 R13: 0000000000000001 R14: 0000000000000001 R15: 0000000000000000 FS: 0000000041cbd940(0000) GS:ffff8800bff839c0(0000) knlGS:0000000000000000 CS: 0010 DS: 0018 ES: 0018 CR0: 000000008005003b CR2: 0000000000000007 CR3: 00000000bd87c000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process swapper (pid: 0, threadinfo ffff8800bff9e000, task ffff88011ff76690) Stack: ffffffff823392e0 0000000000000100 ffffffff821e3a3a 0000000000000008 0000000000000000 ffffffff821e3a61 ffff8800bff7c000 ffffffff8203c7e7 ffff88011ff7ff10 ffff88011ff7ff10 0000000000000021 ffffffff82351108 Call Trace: <IRQ> [<ffffffff821e3a3a>] ? inet_twdr_hangman+0x0/0x9e [<ffffffff821e3a61>] ? inet_twdr_hangman+0x27/0x9e [<ffffffff8203c7e7>] ? run_timer_softirq+0x12c/0x193 [<ffffffff820390d1>] ? __do_softirq+0x5e/0xcd [<ffffffff8200d08c>] ? call_softirq+0x1c/0x28 [<ffffffff8200e611>] ? do_softirq+0x2c/0x68 [<ffffffff8201a055>] ? smp_apic_timer_interrupt+0x8e/0xa9 [<ffffffff8200cad6>] ? apic_timer_interrupt+0x66/0x70 <EOI> [<ffffffff82011f4c>] ? default_idle+0x27/0x3b [<ffffffff8200abbd>] ? cpu_idle+0x5f/0x7d Code: e8 01 00 00 4c 89 e7 41 ff c5 e8 8d fd ff ff 49 8b 44 24 38 4c 89 e7 65 8b 14 25 24 00 00 00 89 d2 48 8b 80 e8 00 00 00 48 f7 d0 <48> 8b 04 d0 48 ff 40 58 e8 fc fc ff ff 48 89 df e8 c0 5f 04 00 RIP [<ffffffff821e394d>] inet_twdr_do_twkill_work+0x6e/0xb8 RSP <ffff88011ff7fed0> CR2: 0000000000000007 This patch provides a function to purge all timewait sockets related to a network namespace. The timewait sockets life cycle is not tied with the network namespace, that means the timewait sockets stay alive while the network namespace dies. The timewait sockets are for avoiding to receive a duplicate packet from the network, if the network namespace is freed, the network stack is removed, so no chance to receive any packets from the outside world. Furthermore, having a pending destruction timer on these sockets with a network namespace freed is not safe and will lead to an oops if the timer callback which try to access data belonging to the namespace like for example in: inet_twdr_do_twkill_work -> NET_INC_STATS_BH(twsk_net(tw), LINUX_MIB_TIMEWAITED); Purging the timewait sockets at the network namespace destruction will: 1) speed up memory freeing for the namespace 2) fix kernel panic on asynchronous timewait destruction Signed-off-by: Daniel Lezcano <dlezcano@fr.ibm.com> Acked-by: Denis V. Lunev <den@openvz.org> Acked-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-09 04:17:27 +08:00
inet_twsk_purge(net, &tcp_hashinfo, &tcp_death_row, AF_INET6);
}
static struct pernet_operations tcpv6_net_ops = {
.init = tcpv6_net_init,
.exit = tcpv6_net_exit,
};
int __init tcpv6_init(void)
{
int ret;
ret = inet6_add_protocol(&tcpv6_protocol, IPPROTO_TCP);
if (ret)
goto out;
/* register inet6 protocol */
ret = inet6_register_protosw(&tcpv6_protosw);
if (ret)
goto out_tcpv6_protocol;
ret = register_pernet_subsys(&tcpv6_net_ops);
if (ret)
goto out_tcpv6_protosw;
out:
return ret;
out_tcpv6_protocol:
inet6_del_protocol(&tcpv6_protocol, IPPROTO_TCP);
out_tcpv6_protosw:
inet6_unregister_protosw(&tcpv6_protosw);
goto out;
}
void tcpv6_exit(void)
{
unregister_pernet_subsys(&tcpv6_net_ops);
inet6_unregister_protosw(&tcpv6_protosw);
inet6_del_protocol(&tcpv6_protocol, IPPROTO_TCP);
}