/*
* TCP over IPv6
- * Linux INET6 implementation
+ * Linux INET6 implementation
*
* Authors:
- * Pedro Roque <roque@di.fc.ul.pt>
+ * Pedro Roque <roque@di.fc.ul.pt>
*
* $Id: tcp_ipv6.c,v 1.144 2002/02/01 22:01:04 davem Exp $
*
- * Based on:
+ * Based on:
* linux/net/ipv4/tcp.c
* linux/net/ipv4/tcp_input.c
* linux/net/ipv4/tcp_output.c
#include <net/inet_ecn.h>
#include <net/protocol.h>
#include <net/xfrm.h>
-#include <net/addrconf.h>
#include <net/snmp.h>
#include <net/dsfield.h>
#include <net/timewait_sock.h>
+#include <net/netdma.h>
#include <asm/uaccess.h>
#include <linux/crypto.h>
#include <linux/scatterlist.h>
-/* Socket used for sending RSTs and ACKs */
-static struct socket *tcp6_socket;
-
static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb);
static void tcp_v6_reqsk_send_ack(struct sk_buff *skb, struct request_sock *req);
-static void tcp_v6_send_check(struct sock *sk, int len,
+static void tcp_v6_send_check(struct sock *sk, int len,
struct sk_buff *skb);
static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb);
static struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific;
#endif
-static int tcp_v6_get_port(struct sock *sk, unsigned short snum)
-{
- return inet_csk_get_port(&tcp_hashinfo, sk, snum,
- inet6_csk_bind_conflict);
-}
-
static void tcp_v6_hash(struct sock *sk)
{
if (sk->sk_state != TCP_CLOSE) {
return;
}
local_bh_disable();
- __inet6_hash(&tcp_hashinfo, sk);
+ __inet6_hash(sk);
local_bh_enable();
}
}
static __inline__ __sum16 tcp_v6_check(struct tcphdr *th, int len,
- struct in6_addr *saddr,
- struct in6_addr *daddr,
+ 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(skb->nh.ipv6h->daddr.s6_addr32,
- skb->nh.ipv6h->saddr.s6_addr32,
- skb->h.th->dest,
- skb->h.th->source);
+ 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,
+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_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);
int addr_type;
int err;
- if (addr_len < SIN6_LEN_RFC2133)
+ if (addr_len < SIN6_LEN_RFC2133)
return -EINVAL;
- if (usin->sin6_family != AF_INET6)
+ if (usin->sin6_family != AF_INET6)
return(-EAFNOSUPPORT);
memset(&fl, 0, sizeof(fl));
}
/*
- * connect() to INADDR_ANY means loopback (BSD'ism).
- */
-
- if(ipv6_addr_any(&usin->sin6_addr))
- usin->sin6_addr.s6_addr[15] = 0x1;
+ * 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 (final_p)
ipv6_addr_copy(&fl.fl6_dst, final_p);
- if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0)
- goto failure;
+ if ((err = __xfrm_lookup(&dst, &fl, sk, XFRM_LOOKUP_WAIT)) < 0) {
+ if (err == -EREMOTE)
+ err = ip6_dst_blackhole(sk, &dst, &fl);
+ if (err < 0)
+ goto failure;
+ }
if (saddr == NULL) {
saddr = &fl.fl6_src;
struct ipv6_pinfo *np;
struct sock *sk;
int err;
- struct tcp_sock *tp;
+ struct tcp_sock *tp;
__u32 seq;
- sk = inet6_lookup(&tcp_hashinfo, &hdr->daddr, th->dest, &hdr->saddr,
- th->source, skb->dev->ifindex);
+ sk = inet6_lookup(skb->dev->nd_net, &tcp_hashinfo, &hdr->daddr,
+ th->dest, &hdr->saddr, th->source, skb->dev->ifindex);
if (sk == NULL) {
ICMP6_INC_STATS_BH(__in6_dev_get(skb->dev), ICMP6_MIB_INERRORS);
goto out;
tp = tcp_sk(sk);
- seq = ntohl(th->seq);
+ seq = ntohl(th->seq);
if (sk->sk_state != TCP_LISTEN &&
!between(seq, tp->snd_una, tp->snd_nxt)) {
NET_INC_STATS_BH(LINUX_MIB_OUTOFWINDOWICMPS);
case TCP_SYN_SENT:
case TCP_SYN_RECV: /* Cannot happen.
- It can, it SYNs are crossed. --ANK */
+ 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) */
}
-static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req,
- struct dst_entry *dst)
+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 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.fl_ip_sport = inet_sk(sk)->sport;
security_req_classify_flow(req, &fl);
- if (dst == NULL) {
- opt = np->opt;
- if (opt == NULL &&
- np->rxopt.bits.osrcrt == 2 &&
- treq->pktopts) {
- struct sk_buff *pktopts = treq->pktopts;
- struct inet6_skb_parm *rxopt = IP6CB(pktopts);
- if (rxopt->srcrt)
- opt = ipv6_invert_rthdr(sk, (struct ipv6_rt_hdr*)(pktopts->nh.raw + rxopt->srcrt));
- }
-
- 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(&dst, &fl, sk, 0)) < 0)
- goto done;
+ 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(&dst, &fl, sk, 0)) < 0)
+ goto done;
+
skb = tcp_make_synack(sk, dst, req);
if (skb) {
- struct tcphdr *th = skb->h.th;
+ struct tcphdr *th = tcp_hdr(skb);
th->check = tcp_v6_check(th, skb->len,
&treq->loc_addr, &treq->rmt_addr,
}
done:
- if (opt && opt != np->opt)
+ 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)
{
if (inet6_rsk(req)->pktopts)
for (i = 0; i < tp->md5sig_info->entries6; i++) {
if (ipv6_addr_cmp(&tp->md5sig_info->keys6[i].addr, addr) == 0)
- return (struct tcp_md5sig_key *)&tp->md5sig_info->keys6[i];
+ return &tp->md5sig_info->keys6[i].base;
}
return NULL;
}
char *newkey, u8 newkeylen)
{
/* Add key to the list */
- struct tcp6_md5sig_key *key;
+ struct tcp_md5sig_key *key;
struct tcp_sock *tp = tcp_sk(sk);
struct tcp6_md5sig_key *keys;
- key = (struct tcp6_md5sig_key*) tcp_v6_md5_do_lookup(sk, peer);
+ key = tcp_v6_md5_do_lookup(sk, peer);
if (key) {
/* modify existing entry - just update that one */
kfree(key->key);
kfree(newkey);
return -ENOMEM;
}
+ sk->sk_route_caps &= ~NETIF_F_GSO_MASK;
+ }
+ if (tcp_alloc_md5sig_pool() == NULL) {
+ kfree(newkey);
+ return -ENOMEM;
}
- tcp_alloc_md5sig_pool();
if (tp->md5sig_info->alloced6 == tp->md5sig_info->entries6) {
keys = kmalloc((sizeof (tp->md5sig_info->keys6[0]) *
(tp->md5sig_info->entries6 + 1)), GFP_ATOMIC);
ipv6_addr_copy(&tp->md5sig_info->keys6[tp->md5sig_info->entries6].addr,
peer);
- tp->md5sig_info->keys6[tp->md5sig_info->entries6].key = newkey;
- tp->md5sig_info->keys6[tp->md5sig_info->entries6].keylen = newkeylen;
+ 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++;
}
for (i = 0; i < tp->md5sig_info->entries6; i++) {
if (ipv6_addr_cmp(&tp->md5sig_info->keys6[i].addr, peer) == 0) {
/* Free the key */
- kfree(tp->md5sig_info->keys6[i].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;
-
- tcp_free_md5sig_pool();
-
- return 0;
+ tp->md5sig_info->alloced6 = 0;
} else {
/* shrink the database */
if (tp->md5sig_info->entries6 != i)
(tp->md5sig_info->entries6 - i)
* sizeof (tp->md5sig_info->keys6[0]));
}
+ tcp_free_md5sig_pool();
+ return 0;
}
}
return -ENOENT;
if (tp->md5sig_info->entries6) {
for (i = 0; i < tp->md5sig_info->entries6; i++)
- kfree(tp->md5sig_info->keys6[i].key);
+ kfree(tp->md5sig_info->keys6[i].base.key);
tp->md5sig_info->entries6 = 0;
tcp_free_md5sig_pool();
}
if (tp->md5sig_info->entries4) {
for (i = 0; i < tp->md5sig_info->entries4; i++)
- kfree(tp->md5sig_info->keys4[i].key);
+ kfree(tp->md5sig_info->keys4[i].base.key);
tp->md5sig_info->entries4 = 0;
tcp_free_md5sig_pool();
}
if (!cmd.tcpm_keylen) {
if (!tcp_sk(sk)->md5sig_info)
return -ENOENT;
- if (ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_MAPPED)
+ 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);
}
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_type(&sin6->sin6_addr) & IPV6_ADDR_MAPPED) {
+ if (ipv6_addr_v4mapped(&sin6->sin6_addr)) {
return tcp_v4_md5_do_add(sk, sin6->sin6_addr.s6_addr32[3],
newkey, cmd.tcpm_keylen);
}
struct in6_addr *saddr,
struct in6_addr *daddr,
struct tcphdr *th, int protocol,
- int tcplen)
+ unsigned int tcplen)
{
struct scatterlist sg[4];
__u16 data_len;
hp = tcp_get_md5sig_pool();
if (!hp) {
- printk(KERN_WARNING "%s(): hash pool not found...\n", __FUNCTION__);
+ printk(KERN_WARNING "%s(): hash pool not found...\n", __func__);
goto clear_hash_noput;
}
bp = &hp->md5_blk.ip6;
bp->len = htonl(tcplen);
bp->protocol = htonl(protocol);
+ sg_init_table(sg, 4);
+
sg_set_buf(&sg[block++], bp, sizeof(*bp));
nbytes += sizeof(*bp);
sg_set_buf(&sg[block++], key->key, key->keylen);
nbytes += key->keylen;
+ sg_mark_end(&sg[block - 1]);
+
/* Now store the hash into the packet */
err = crypto_hash_init(desc);
if (err) {
- printk(KERN_WARNING "%s(): hash_init failed\n", __FUNCTION__);
+ printk(KERN_WARNING "%s(): hash_init failed\n", __func__);
goto clear_hash;
}
err = crypto_hash_update(desc, sg, nbytes);
if (err) {
- printk(KERN_WARNING "%s(): hash_update failed\n", __FUNCTION__);
+ printk(KERN_WARNING "%s(): hash_update failed\n", __func__);
goto clear_hash;
}
err = crypto_hash_final(desc, md5_hash);
if (err) {
- printk(KERN_WARNING "%s(): hash_final failed\n", __FUNCTION__);
+ printk(KERN_WARNING "%s(): hash_final failed\n", __func__);
goto clear_hash;
}
struct dst_entry *dst,
struct request_sock *req,
struct tcphdr *th, int protocol,
- int tcplen)
+ unsigned int tcplen)
{
struct in6_addr *saddr, *daddr;
{
__u8 *hash_location = NULL;
struct tcp_md5sig_key *hash_expected;
- struct ipv6hdr *ip6h = skb->nh.ipv6h;
- struct tcphdr *th = skb->h.th;
+ struct ipv6hdr *ip6h = ipv6_hdr(skb);
+ struct tcphdr *th = tcp_hdr(skb);
int length = (th->doff << 2) - sizeof (*th);
int genhash;
u8 *ptr;
}
#endif
-static struct request_sock_ops tcp6_request_sock_ops __read_mostly = {
+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_reset = tcp_v6_send_reset
};
-struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = {
#ifdef CONFIG_TCP_MD5SIG
+static struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = {
.md5_lookup = tcp_v6_reqsk_md5_lookup,
-#endif
};
+#endif
static struct timewait_sock_ops tcp6_timewait_sock_ops = {
.twsk_obj_size = sizeof(struct tcp6_timewait_sock),
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 = skb->h.th;
+ 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((char *)th, th->doff<<2,
+ th->check = csum_ipv6_magic(&np->saddr, &np->daddr, len, IPPROTO_TCP,
+ csum_partial((char *)th, th->doff<<2,
skb->csum));
}
}
if (!pskb_may_pull(skb, sizeof(*th)))
return -EINVAL;
- ipv6h = skb->nh.ipv6h;
- th = skb->h.th;
+ 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 void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb)
{
- struct tcphdr *th = skb->h.th, *t1;
+ struct tcphdr *th = tcp_hdr(skb), *t1;
struct sk_buff *buff;
struct flowi fl;
- int tot_len = sizeof(*th);
+ struct net *net = skb->dst->dev->nd_net;
+ struct sock *ctl_sk = net->ipv6.tcp_sk;
+ unsigned int tot_len = sizeof(*th);
#ifdef CONFIG_TCP_MD5SIG
struct tcp_md5sig_key *key;
#endif
return;
if (!ipv6_unicast_destination(skb))
- return;
+ return;
#ifdef CONFIG_TCP_MD5SIG
if (sk)
- key = tcp_v6_md5_do_lookup(sk, &skb->nh.ipv6h->daddr);
+ key = tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr);
else
key = NULL;
buff = alloc_skb(MAX_HEADER + sizeof(struct ipv6hdr) + tot_len,
GFP_ATOMIC);
- if (buff == NULL)
- return;
+ if (buff == NULL)
+ return;
skb_reserve(buff, MAX_HEADER + sizeof(struct ipv6hdr) + tot_len);
t1->source = th->dest;
t1->doff = tot_len / 4;
t1->rst = 1;
-
+
if(th->ack) {
- t1->seq = th->ack_seq;
+ t1->seq = th->ack_seq;
} else {
t1->ack = 1;
t1->ack_seq = htonl(ntohl(th->seq) + th->syn + th->fin
(TCPOPT_NOP << 16) |
(TCPOPT_MD5SIG << 8) |
TCPOLEN_MD5SIG);
- tcp_v6_do_calc_md5_hash((__u8*)&opt[1],
- key,
- &skb->nh.ipv6h->daddr,
- &skb->nh.ipv6h->saddr,
- t1, IPPROTO_TCP,
- tot_len);
+ tcp_v6_do_calc_md5_hash((__u8 *)&opt[1], key,
+ &ipv6_hdr(skb)->daddr,
+ &ipv6_hdr(skb)->saddr,
+ t1, IPPROTO_TCP, tot_len);
}
#endif
buff->csum = csum_partial((char *)t1, sizeof(*t1), 0);
memset(&fl, 0, sizeof(fl));
- ipv6_addr_copy(&fl.fl6_dst, &skb->nh.ipv6h->saddr);
- ipv6_addr_copy(&fl.fl6_src, &skb->nh.ipv6h->daddr);
+ 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,
sizeof(*t1), IPPROTO_TCP,
fl.fl_ip_sport = t1->source;
security_skb_classify_flow(skb, &fl);
- /* sk = NULL, but it is safe for now. RST socket required. */
- if (!ip6_dst_lookup(NULL, &buff->dst, &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(tcp6_socket->sk, buff, &fl, NULL, 0);
+ ip6_xmit(ctl_sk, buff, &fl, NULL, 0);
TCP_INC_STATS_BH(TCP_MIB_OUTSEGS);
TCP_INC_STATS_BH(TCP_MIB_OUTRSTS);
return;
static void tcp_v6_send_ack(struct tcp_timewait_sock *tw,
struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 ts)
{
- struct tcphdr *th = skb->h.th, *t1;
+ struct tcphdr *th = tcp_hdr(skb), *t1;
struct sk_buff *buff;
struct flowi fl;
- int tot_len = sizeof(struct tcphdr);
+ struct net *net = skb->dev->nd_net;
+ 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;
#ifdef CONFIG_TCP_MD5SIG
if (!tw && skb->sk) {
- key = tcp_v6_md5_do_lookup(skb->sk, &skb->nh.ipv6h->daddr);
+ key = tcp_v6_md5_do_lookup(skb->sk, &ipv6_hdr(skb)->daddr);
} else if (tw && tw->tw_md5_keylen) {
tw_key.key = tw->tw_md5_key;
tw_key.keylen = tw->tw_md5_keylen;
t1->window = htons(win);
topt = (__be32 *)(t1 + 1);
-
+
if (ts) {
*topt++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
(TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP);
if (key) {
*topt++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
(TCPOPT_MD5SIG << 8) | TCPOLEN_MD5SIG);
- tcp_v6_do_calc_md5_hash((__u8 *)topt,
- key,
- &skb->nh.ipv6h->daddr,
- &skb->nh.ipv6h->saddr,
- t1, IPPROTO_TCP,
- tot_len);
+ tcp_v6_do_calc_md5_hash((__u8 *)topt, key,
+ &ipv6_hdr(skb)->daddr,
+ &ipv6_hdr(skb)->saddr,
+ t1, IPPROTO_TCP, tot_len);
}
#endif
buff->csum = csum_partial((char *)t1, tot_len, 0);
memset(&fl, 0, sizeof(fl));
- ipv6_addr_copy(&fl.fl6_dst, &skb->nh.ipv6h->saddr);
- ipv6_addr_copy(&fl.fl6_src, &skb->nh.ipv6h->daddr);
+ 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,
fl.fl_ip_sport = t1->source;
security_skb_classify_flow(skb, &fl);
- if (!ip6_dst_lookup(NULL, &buff->dst, &fl)) {
+ if (!ip6_dst_lookup(ctl_sk, &buff->dst, &fl)) {
if (xfrm_lookup(&buff->dst, &fl, NULL, 0) >= 0) {
- ip6_xmit(tcp6_socket->sk, buff, &fl, NULL, 0);
+ ip6_xmit(ctl_sk, buff, &fl, NULL, 0);
TCP_INC_STATS_BH(TCP_MIB_OUTSEGS);
return;
}
static struct sock *tcp_v6_hnd_req(struct sock *sk,struct sk_buff *skb)
{
struct request_sock *req, **prev;
- const struct tcphdr *th = skb->h.th;
+ const struct tcphdr *th = tcp_hdr(skb);
struct sock *nsk;
/* Find possible connection requests. */
req = inet6_csk_search_req(sk, &prev, th->source,
- &skb->nh.ipv6h->saddr,
- &skb->nh.ipv6h->daddr, inet6_iif(skb));
+ &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(&tcp_hashinfo, &skb->nh.ipv6h->saddr,
- th->source, &skb->nh.ipv6h->daddr,
- ntohs(th->dest), inet6_iif(skb));
+ nsk = __inet6_lookup_established(sk->sk_net, &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) {
return NULL;
}
-#if 0 /*def CONFIG_SYN_COOKIES*/
+#ifdef CONFIG_SYN_COOKIES
if (!th->rst && !th->syn && th->ack)
- sk = cookie_v6_check(sk, skb, &(IPCB(skb)->opt));
+ sk = cookie_v6_check(sk, skb);
#endif
return sk;
}
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;
+ goto drop;
- /*
- * There are no SYN attacks on IPv6, yet...
- */
if (inet_csk_reqsk_queue_is_full(sk) && !isn) {
if (net_ratelimit())
- printk(KERN_INFO "TCPv6: dropping request, synflood is possible\n");
- goto drop;
+ 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)
tcp_parse_options(skb, &tmp_opt, 0);
+ if (want_cookie) {
+ tcp_clear_options(&tmp_opt);
+ tmp_opt.saw_tstamp = 0;
+ }
+
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, &skb->nh.ipv6h->saddr);
- ipv6_addr_copy(&treq->loc_addr, &skb->nh.ipv6h->daddr);
- TCP_ECN_create_request(req, skb->h.th);
+ ipv6_addr_copy(&treq->rmt_addr, &ipv6_hdr(skb)->saddr);
+ ipv6_addr_copy(&treq->loc_addr, &ipv6_hdr(skb)->daddr);
treq->pktopts = NULL;
- 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;
+ if (!want_cookie)
+ TCP_ECN_create_request(req, tcp_hdr(skb));
+
+ if (want_cookie) {
+ isn = cookie_v6_init_sequence(sk, skb, &req->mss);
+ } 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);
+ /* 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);
- if (isn == 0)
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, NULL))
+ if (tcp_v6_send_synack(sk, req))
goto drop;
- inet6_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
- return 0;
+ if (!want_cookie) {
+ inet6_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
+ return 0;
+ }
drop:
if (req)
newsk = tcp_v4_syn_recv_sock(sk, skb, req, dst);
- if (newsk == NULL)
+ if (newsk == NULL)
return NULL;
newtcp6sk = (struct tcp6_sock *)newsk;
newnp->pktoptions = NULL;
newnp->opt = NULL;
newnp->mcast_oif = inet6_iif(skb);
- newnp->mcast_hops = skb->nh.ipv6h->hop_limit;
+ newnp->mcast_hops = ipv6_hdr(skb)->hop_limit;
/*
* No need to charge this sock to the relevant IPv6 refcnt debug socks count
if (sk_acceptq_is_full(sk))
goto out_overflow;
- if (np->rxopt.bits.osrcrt == 2 &&
- opt == NULL && treq->pktopts) {
- struct inet6_skb_parm *rxopt = IP6CB(treq->pktopts);
- if (rxopt->srcrt)
- opt = ipv6_invert_rthdr(sk, (struct ipv6_rt_hdr *)(treq->pktopts->nh.raw + rxopt->srcrt));
- }
-
if (dst == NULL) {
struct in6_addr *final_p = NULL, final;
struct flowi fl;
if ((xfrm_lookup(&dst, &fl, sk, 0)) < 0)
goto out;
- }
+ }
newsk = tcp_create_openreq_child(sk, req, skb);
if (newsk == NULL)
ipv6_addr_copy(&newnp->rcv_saddr, &treq->loc_addr);
newsk->sk_bound_dev_if = treq->iif;
- /* Now IPv6 options...
+ /* Now IPv6 options...
First: no IPv4 options.
*/
newinet->opt = NULL;
+ newnp->ipv6_fl_list = NULL;
/* Clone RX bits */
newnp->rxopt.all = np->rxopt.all;
}
newnp->opt = NULL;
newnp->mcast_oif = inet6_iif(skb);
- newnp->mcast_hops = skb->nh.ipv6h->hop_limit;
+ newnp->mcast_hops = ipv6_hdr(skb)->hop_limit;
/* Clone native IPv6 options from listening socket (if any)
}
#endif
- __inet6_hash(&tcp_hashinfo, newsk);
- inet_inherit_port(&tcp_hashinfo, sk, newsk);
+ __inet6_hash(newsk);
+ inet_inherit_port(sk, newsk);
return newsk;
static __sum16 tcp_v6_checksum_init(struct sk_buff *skb)
{
if (skb->ip_summed == CHECKSUM_COMPLETE) {
- if (!tcp_v6_check(skb->h.th,skb->len,&skb->nh.ipv6h->saddr,
- &skb->nh.ipv6h->daddr,skb->csum)) {
+ if (!tcp_v6_check(tcp_hdr(skb), 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->h.th,skb->len,&skb->nh.ipv6h->saddr,
- &skb->nh.ipv6h->daddr, 0));
+ skb->csum = ~csum_unfold(tcp_v6_check(tcp_hdr(skb), skb->len,
+ &ipv6_hdr(skb)->saddr,
+ &ipv6_hdr(skb)->daddr, 0));
if (skb->len <= 76) {
return __skb_checksum_complete(skb);
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)
+ --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, skb->h.th, skb->len))
+ if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len))
goto reset;
TCP_CHECK_TIMER(sk);
if (opt_skb)
return 0;
}
- if (skb->len < (skb->h.th->doff<<2) || tcp_checksum_complete(skb))
+ if (skb->len < tcp_hdrlen(skb) || tcp_checksum_complete(skb))
goto csum_err;
- if (sk->sk_state == TCP_LISTEN) {
+ if (sk->sk_state == TCP_LISTEN) {
struct sock *nsk = tcp_v6_hnd_req(sk, skb);
if (!nsk)
goto discard;
* otherwise we just shortcircuit this and continue with
* the new socket..
*/
- if(nsk != sk) {
+ if(nsk != sk) {
if (tcp_child_process(sk, nsk, skb))
goto reset;
if (opt_skb)
}
TCP_CHECK_TIMER(sk);
- if (tcp_rcv_state_process(sk, skb, skb->h.th, skb->len))
+ if (tcp_rcv_state_process(sk, skb, tcp_hdr(skb), skb->len))
goto reset;
TCP_CHECK_TIMER(sk);
if (opt_skb)
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 = opt_skb->nh.ipv6h->hop_limit;
+ 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);
return 0;
}
-static int tcp_v6_rcv(struct sk_buff **pskb)
+static int tcp_v6_rcv(struct sk_buff *skb)
{
- struct sk_buff *skb = *pskb;
- struct tcphdr *th;
+ struct tcphdr *th;
struct sock *sk;
int ret;
if (!pskb_may_pull(skb, sizeof(struct tcphdr)))
goto discard_it;
- th = skb->h.th;
+ 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->ip_summed != CHECKSUM_UNNECESSARY &&
- tcp_v6_checksum_init(skb)))
+ if (!skb_csum_unnecessary(skb) && tcp_v6_checksum_init(skb))
goto bad_packet;
- th = skb->h.th;
+ 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(skb->nh.ipv6h);
+ TCP_SKB_CB(skb)->flags = ipv6_get_dsfield(ipv6_hdr(skb));
TCP_SKB_CB(skb)->sacked = 0;
- sk = __inet6_lookup(&tcp_hashinfo, &skb->nh.ipv6h->saddr, th->source,
- &skb->nh.ipv6h->daddr, ntohs(th->dest),
- inet6_iif(skb));
+ sk = __inet6_lookup(skb->dev->nd_net, &tcp_hashinfo,
+ &ipv6_hdr(skb)->saddr, th->source,
+ &ipv6_hdr(skb)->daddr, ntohs(th->dest),
+ inet6_iif(skb));
if (!sk)
goto no_tcp_socket;
ret = 0;
if (!sock_owned_by_user(sk)) {
#ifdef CONFIG_NET_DMA
- struct tcp_sock *tp = tcp_sk(sk);
- if (tp->ucopy.dma_chan)
- ret = tcp_v6_do_rcv(sk, skb);
- else
+ struct tcp_sock *tp = tcp_sk(sk);
+ if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
+ tp->ucopy.dma_chan = get_softnet_dma();
+ if (tp->ucopy.dma_chan)
+ ret = tcp_v6_do_rcv(sk, skb);
+ else
#endif
{
if (!tcp_prequeue(sk, skb))
{
struct sock *sk2;
- sk2 = inet6_lookup_listener(&tcp_hashinfo,
- &skb->nh.ipv6h->daddr,
+ sk2 = inet6_lookup_listener(skb->dev->nd_net, &tcp_hashinfo,
+ &ipv6_hdr(skb)->daddr,
ntohs(th->dest), inet6_iif(skb));
if (sk2 != NULL) {
struct inet_timewait_sock *tw = inet_twsk(sk);
.getsockopt = ipv6_getsockopt,
.addr2sockaddr = inet6_csk_addr2sockaddr,
.sockaddr_len = sizeof(struct sockaddr_in6),
+ .bind_conflict = inet6_csk_bind_conflict,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_ipv6_setsockopt,
.compat_getsockopt = compat_ipv6_getsockopt,
.getsockopt = ipv6_getsockopt,
.addr2sockaddr = inet6_csk_addr2sockaddr,
.sockaddr_len = sizeof(struct sockaddr_in6),
+ .bind_conflict = inet6_csk_bind_conflict,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_ipv6_setsockopt,
.compat_getsockopt = compat_ipv6_getsockopt,
return inet6_destroy_sock(sk);
}
+#ifdef CONFIG_PROC_FS
/* Proc filesystem TCPv6 sock list dumping. */
-static void get_openreq6(struct seq_file *seq,
+static void get_openreq6(struct seq_file *seq,
struct sock *sk, struct request_sock *req, int i, int uid)
{
int ttd = req->expires - jiffies;
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),
+ 1, /* timers active (only the expire timer) */
+ jiffies_to_clock_t(ttd),
req->retrans,
uid,
- 0, /* non standard timer */
+ 0, /* non standard timer */
0, /* open_requests have no inode */
0, req);
}
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,
+ 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,
);
}
-static void get_timewait6_sock(struct seq_file *seq,
+static void get_timewait6_sock(struct seq_file *seq,
struct inet_timewait_sock *tw, int i)
{
struct in6_addr *dest, *src;
atomic_read(&tw->tw_refcnt), tw);
}
-#ifdef CONFIG_PROC_FS
static int tcp6_seq_show(struct seq_file *seq, void *v)
{
struct tcp_iter_state *st;
.seq_fops = &tcp6_seq_fops,
};
-int __init tcp6_proc_init(void)
+int tcp6_proc_init(struct net *net)
{
- return tcp_proc_register(&tcp6_seq_afinfo);
+ return tcp_proc_register(net, &tcp6_seq_afinfo);
}
-void tcp6_proc_exit(void)
+void tcp6_proc_exit(struct net *net)
{
- tcp_proc_unregister(&tcp6_seq_afinfo);
+ tcp_proc_unregister(net, &tcp6_seq_afinfo);
}
#endif
+DEFINE_PROTO_INUSE(tcpv6)
+
struct proto tcpv6_prot = {
.name = "TCPv6",
.owner = THIS_MODULE,
.shutdown = tcp_shutdown,
.setsockopt = tcp_setsockopt,
.getsockopt = tcp_getsockopt,
- .sendmsg = tcp_sendmsg,
.recvmsg = tcp_recvmsg,
.backlog_rcv = tcp_v6_do_rcv,
.hash = tcp_v6_hash,
- .unhash = tcp_unhash,
- .get_port = tcp_v6_get_port,
+ .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,
.obj_size = sizeof(struct tcp6_sock),
.twsk_prot = &tcp6_timewait_sock_ops,
.rsk_prot = &tcp6_request_sock_ops,
+ .hashinfo = &tcp_hashinfo,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_tcp_setsockopt,
.compat_getsockopt = compat_tcp_getsockopt,
#endif
+ REF_PROTO_INUSE(tcpv6)
};
static struct inet6_protocol tcpv6_protocol = {
INET_PROTOSW_ICSK,
};
-void __init tcpv6_init(void)
+static int tcpv6_net_init(struct net *net)
+{
+ int err;
+ struct socket *sock;
+ struct sock *sk;
+
+ err = inet_csk_ctl_sock_create(&sock, PF_INET6, SOCK_RAW, IPPROTO_TCP);
+ if (err)
+ return err;
+
+ net->ipv6.tcp_sk = sk = sock->sk;
+ sk_change_net(sk, net);
+ return err;
+}
+
+static void tcpv6_net_exit(struct net *net)
+{
+ sk_release_kernel(net->ipv6.tcp_sk);
+}
+
+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 */
- if (inet6_add_protocol(&tcpv6_protocol, IPPROTO_TCP) < 0)
- printk(KERN_ERR "tcpv6_init: Could not register protocol\n");
- inet6_register_protosw(&tcpv6_protosw);
+ ret = inet6_register_protosw(&tcpv6_protosw);
+ if (ret)
+ goto out_tcpv6_protocol;
- if (inet_csk_ctl_sock_create(&tcp6_socket, PF_INET6, SOCK_RAW,
- IPPROTO_TCP) < 0)
- panic("Failed to create the TCPv6 control socket.\n");
+ 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);
}