aboutsummaryrefslogtreecommitdiff
path: root/net/ipv6/tcp_ipv6.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6/tcp_ipv6.c')
-rw-r--r--net/ipv6/tcp_ipv6.c1087
1 files changed, 415 insertions, 672 deletions
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 3edd05ae438..229239ad96b 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -39,7 +39,7 @@
#include <linux/ipsec.h>
#include <linux/times.h>
#include <linux/slab.h>
-
+#include <linux/uaccess.h>
#include <linux/ipv6.h>
#include <linux/icmpv6.h>
#include <linux/random.h>
@@ -63,8 +63,7 @@
#include <net/inet_common.h>
#include <net/secure_seq.h>
#include <net/tcp_memcontrol.h>
-
-#include <asm/uaccess.h>
+#include <net/busy_poll.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
@@ -77,9 +76,6 @@ 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 void __tcp_v6_send_check(struct sk_buff *skb,
- const struct in6_addr *saddr,
- const struct in6_addr *daddr);
static const struct inet_connection_sock_af_ops ipv6_mapped;
static const struct inet_connection_sock_af_ops ipv6_specific;
@@ -94,6 +90,18 @@ static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(struct sock *sk,
}
#endif
+static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
+{
+ struct dst_entry *dst = skb_dst(skb);
+ const struct rt6_info *rt = (const struct rt6_info *)dst;
+
+ dst_hold(dst);
+ sk->sk_rx_dst = dst;
+ inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
+ if (rt->rt6i_node)
+ inet6_sk(sk)->rx_dst_cookie = rt->rt6i_node->fn_sernum;
+}
+
static void tcp_v6_hash(struct sock *sk)
{
if (sk->sk_state != TCP_CLOSE) {
@@ -107,14 +115,6 @@ static void tcp_v6_hash(struct sock *sk)
}
}
-static __inline__ __sum16 tcp_v6_check(int len,
- const struct in6_addr *saddr,
- const struct in6_addr *daddr,
- __wsum base)
-{
- return csum_ipv6_magic(saddr, daddr, len, IPPROTO_TCP, base);
-}
-
static __u32 tcp_v6_init_sequence(const struct sk_buff *skb)
{
return secure_tcpv6_sequence_number(ipv6_hdr(skb)->daddr.s6_addr32,
@@ -154,7 +154,6 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
if (flowlabel == NULL)
return -EINVAL;
- usin->sin6_addr = flowlabel->dst;
fl6_sock_release(flowlabel);
}
}
@@ -163,12 +162,12 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
* connect() to INADDR_ANY means loopback (BSD'ism).
*/
- if(ipv6_addr_any(&usin->sin6_addr))
+ 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)
+ if (addr_type & IPV6_ADDR_MULTICAST)
return -ENETUNREACH;
if (addr_type&IPV6_ADDR_LINKLOCAL) {
@@ -190,13 +189,13 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
}
if (tp->rx_opt.ts_recent_stamp &&
- !ipv6_addr_equal(&np->daddr, &usin->sin6_addr)) {
+ !ipv6_addr_equal(&sk->sk_v6_daddr, &usin->sin6_addr)) {
tp->rx_opt.ts_recent = 0;
tp->rx_opt.ts_recent_stamp = 0;
tp->write_seq = 0;
}
- np->daddr = usin->sin6_addr;
+ sk->sk_v6_daddr = usin->sin6_addr;
np->flow_label = fl6.flowlabel;
/*
@@ -235,17 +234,17 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
} else {
ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr);
ipv6_addr_set_v4mapped(inet->inet_rcv_saddr,
- &np->rcv_saddr);
+ &sk->sk_v6_rcv_saddr);
}
return err;
}
- if (!ipv6_addr_any(&np->rcv_saddr))
- saddr = &np->rcv_saddr;
+ if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr))
+ saddr = &sk->sk_v6_rcv_saddr;
fl6.flowi6_proto = IPPROTO_TCP;
- fl6.daddr = np->daddr;
+ fl6.daddr = sk->sk_v6_daddr;
fl6.saddr = saddr ? *saddr : np->saddr;
fl6.flowi6_oif = sk->sk_bound_dev_if;
fl6.flowi6_mark = sk->sk_mark;
@@ -256,7 +255,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
- dst = ip6_dst_lookup_flow(sk, &fl6, final_p, true);
+ dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
if (IS_ERR(dst)) {
err = PTR_ERR(dst);
goto failure;
@@ -264,7 +263,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
if (saddr == NULL) {
saddr = &fl6.saddr;
- np->rcv_saddr = *saddr;
+ sk->sk_v6_rcv_saddr = *saddr;
}
/* set the source address */
@@ -277,22 +276,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
rt = (struct rt6_info *) dst;
if (tcp_death_row.sysctl_tw_recycle &&
!tp->rx_opt.ts_recent_stamp &&
- ipv6_addr_equal(&rt->rt6i_dst.addr, &np->daddr)) {
- struct inet_peer *peer = rt6_get_peer(rt);
- /*
- * VJ's idea. We save last timestamp seen from
- * the destination in peer table, when entering state
- * TIME-WAIT * and initialize rx_opt.ts_recent from it,
- * when trying new connection.
- */
- if (peer) {
- inet_peer_refcheck(peer);
- if ((u32)get_seconds() - peer->tcp_ts_stamp <= TCP_PAWS_MSL) {
- tp->rx_opt.ts_recent_stamp = peer->tcp_ts_stamp;
- tp->rx_opt.ts_recent = peer->tcp_ts;
- }
- }
- }
+ ipv6_addr_equal(&rt->rt6i_dst.addr, &sk->sk_v6_daddr))
+ tcp_fetch_timewait_stamp(sk, dst);
icsk->icsk_ext_hdr_len = 0;
if (np->opt)
@@ -308,9 +293,9 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
if (err)
goto late_failure;
- if (!tp->write_seq)
+ if (!tp->write_seq && likely(!tp->repair))
tp->write_seq = secure_tcpv6_sequence_number(np->saddr.s6_addr32,
- np->daddr.s6_addr32,
+ sk->sk_v6_daddr.s6_addr32,
inet->inet_sport,
inet->inet_dport);
@@ -329,16 +314,34 @@ failure:
return err;
}
+static void tcp_v6_mtu_reduced(struct sock *sk)
+{
+ struct dst_entry *dst;
+
+ if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))
+ return;
+
+ dst = inet6_csk_update_pmtu(sk, tcp_sk(sk)->mtu_info);
+ if (!dst)
+ return;
+
+ if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) {
+ tcp_sync_mss(sk, dst_mtu(dst));
+ tcp_simple_retransmit(sk);
+ }
+}
+
static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
- const struct ipv6hdr *hdr = (const struct ipv6hdr*)skb->data;
+ const struct ipv6hdr *hdr = (const 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 request_sock *fastopen;
+ __u32 seq, snd_una;
struct net *net = dev_net(skb->dev);
sk = inet6_lookup(net, &tcp_hashinfo, &hdr->daddr,
@@ -356,7 +359,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
}
bh_lock_sock(sk);
- if (sock_owned_by_user(sk))
+ if (sock_owned_by_user(sk) && type != ICMPV6_PKT_TOOBIG)
NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS);
if (sk->sk_state == TCP_CLOSE)
@@ -369,57 +372,42 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
tp = tcp_sk(sk);
seq = ntohl(th->seq);
+ /* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */
+ fastopen = tp->fastopen_rsk;
+ snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una;
if (sk->sk_state != TCP_LISTEN &&
- !between(seq, tp->snd_una, tp->snd_nxt)) {
+ !between(seq, 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;
-
- 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 (type == NDISC_REDIRECT) {
+ struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
- if (dst == NULL) {
- struct inet_sock *inet = inet_sk(sk);
- struct flowi6 fl6;
+ if (dst)
+ dst->ops->redirect(dst, sk, skb);
+ goto out;
+ }
- /* BUGGG_FUTURE: Again, it is not clear how
- to handle rthdr case. Ignore this complexity
- for now.
- */
- memset(&fl6, 0, sizeof(fl6));
- fl6.flowi6_proto = IPPROTO_TCP;
- fl6.daddr = np->daddr;
- fl6.saddr = np->saddr;
- fl6.flowi6_oif = sk->sk_bound_dev_if;
- fl6.flowi6_mark = sk->sk_mark;
- fl6.fl6_dport = inet->inet_dport;
- fl6.fl6_sport = inet->inet_sport;
- security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
-
- dst = ip6_dst_lookup_flow(sk, &fl6, NULL, false);
- if (IS_ERR(dst)) {
- sk->sk_err_soft = -PTR_ERR(dst);
- goto out;
- }
+ if (type == ICMPV6_PKT_TOOBIG) {
+ /* We are not interested in TCP_LISTEN and open_requests
+ * (SYN-ACKs send out by Linux are always <576bytes so
+ * they should go through unfragmented).
+ */
+ if (sk->sk_state == TCP_LISTEN)
+ goto out;
- } else
- dst_hold(dst);
+ if (!ip6_sk_accept_pmtu(sk))
+ goto out;
- 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);
+ tp->mtu_info = ntohl(info);
+ if (!sock_owned_by_user(sk))
+ tcp_v6_mtu_reduced(sk);
+ else if (!test_and_set_bit(TCP_MTU_REDUCED_DEFERRED,
+ &tp->tsq_flags))
+ sock_hold(sk);
goto out;
}
@@ -448,11 +436,17 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
}
inet_csk_reqsk_queue_drop(sk, req, prev);
+ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
goto out;
case TCP_SYN_SENT:
- case TCP_SYN_RECV: /* Cannot happen.
- It can, it SYNs are crossed. --ANK */
+ case TCP_SYN_RECV:
+ /* Only in fast or simultaneous open. If a fast open socket is
+ * is already accepted it is treated as a connected one below.
+ */
+ if (fastopen && fastopen->sk == NULL)
+ break;
+
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) */
@@ -475,228 +469,82 @@ out:
}
-static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req,
- struct request_values *rvp)
+static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst,
+ struct flowi6 *fl6,
+ struct request_sock *req,
+ u16 queue_mapping,
+ struct tcp_fastopen_cookie *foc)
{
- struct inet6_request_sock *treq = inet6_rsk(req);
+ struct inet_request_sock *ireq = inet_rsk(req);
struct ipv6_pinfo *np = inet6_sk(sk);
- struct sk_buff * skb;
- struct ipv6_txoptions *opt = NULL;
- struct in6_addr * final_p, final;
- struct flowi6 fl6;
- struct dst_entry *dst;
- int err;
+ struct sk_buff *skb;
+ int err = -ENOMEM;
- memset(&fl6, 0, sizeof(fl6));
- fl6.flowi6_proto = IPPROTO_TCP;
- fl6.daddr = treq->rmt_addr;
- fl6.saddr = treq->loc_addr;
- fl6.flowlabel = 0;
- fl6.flowi6_oif = treq->iif;
- fl6.flowi6_mark = sk->sk_mark;
- fl6.fl6_dport = inet_rsk(req)->rmt_port;
- fl6.fl6_sport = inet_rsk(req)->loc_port;
- security_req_classify_flow(req, flowi6_to_flowi(&fl6));
+ /* First, grab a route. */
+ if (!dst && (dst = inet6_csk_route_req(sk, fl6, req)) == NULL)
+ goto done;
- opt = np->opt;
- final_p = fl6_update_dst(&fl6, opt, &final);
+ skb = tcp_make_synack(sk, dst, req, foc);
- dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false);
- if (IS_ERR(dst)) {
- err = PTR_ERR(dst);
- dst = NULL;
- goto done;
- }
- skb = tcp_make_synack(sk, dst, req, rvp);
- err = -ENOMEM;
if (skb) {
- __tcp_v6_send_check(skb, &treq->loc_addr, &treq->rmt_addr);
+ __tcp_v6_send_check(skb, &ireq->ir_v6_loc_addr,
+ &ireq->ir_v6_rmt_addr);
+
+ fl6->daddr = ireq->ir_v6_rmt_addr;
+ if (np->repflow && (ireq->pktopts != NULL))
+ fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts));
- fl6.daddr = treq->rmt_addr;
- err = ip6_xmit(sk, skb, &fl6, opt, np->tclass);
+ skb_set_queue_mapping(skb, queue_mapping);
+ err = ip6_xmit(sk, skb, fl6, np->opt, np->tclass);
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 int tcp_v6_rtx_synack(struct sock *sk, struct request_sock *req,
- struct request_values *rvp)
+static int tcp_v6_rtx_synack(struct sock *sk, struct request_sock *req)
{
- TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS);
- return tcp_v6_send_synack(sk, req, rvp);
+ struct flowi6 fl6;
+ int res;
+
+ res = tcp_v6_send_synack(sk, NULL, &fl6, req, 0, NULL);
+ if (!res) {
+ TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS);
+ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSYNRETRANS);
+ }
+ return res;
}
static void tcp_v6_reqsk_destructor(struct request_sock *req)
{
- kfree_skb(inet6_rsk(req)->pktopts);
+ kfree_skb(inet_rsk(req)->pktopts);
}
#ifdef CONFIG_TCP_MD5SIG
static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(struct sock *sk,
const 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;
+ return tcp_md5_do_lookup(sk, (union tcp_md5_addr *)addr, AF_INET6);
}
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);
+ return tcp_v6_md5_do_lookup(sk, &addr_sk->sk_v6_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);
+ return tcp_v6_md5_do_lookup(sk, &inet_rsk(req)->ir_v6_rmt_addr);
}
-static int tcp_v6_md5_do_add(struct sock *sk, const 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_nocaps_add(sk, NETIF_F_GSO_MASK);
- }
- if (tp->md5sig_info->entries6 == 0 &&
- tcp_alloc_md5sig_pool(sk) == 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) {
- kfree(newkey);
- if (tp->md5sig_info->entries6 == 0)
- tcp_free_md5sig_pool();
- 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++;
- }
-
- 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, const 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;
- tcp_free_md5sig_pool();
- } 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]));
- }
- 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)
+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;
@@ -708,36 +556,22 @@ static int tcp_v6_parse_md5_keys (struct sock *sk, char __user *optval,
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);
+ return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3],
+ AF_INET);
+ return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr,
+ AF_INET6);
}
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_nocaps_add(sk, NETIF_F_GSO_MASK);
- }
+ if (ipv6_addr_v4mapped(&sin6->sin6_addr))
+ return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3],
+ AF_INET, cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL);
- 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);
+ return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin6->sin6_addr,
+ AF_INET6, cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL);
}
static int tcp_v6_md5_hash_pseudoheader(struct tcp_md5sig_pool *hp,
@@ -803,10 +637,10 @@ static int tcp_v6_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key,
if (sk) {
saddr = &inet6_sk(sk)->saddr;
- daddr = &inet6_sk(sk)->daddr;
+ daddr = &sk->sk_v6_daddr;
} else if (req) {
- saddr = &inet6_rsk(req)->loc_addr;
- daddr = &inet6_rsk(req)->rmt_addr;
+ saddr = &inet_rsk(req)->ir_v6_loc_addr;
+ daddr = &inet_rsk(req)->ir_v6_rmt_addr;
} else {
const struct ipv6hdr *ip6h = ipv6_hdr(skb);
saddr = &ip6h->saddr;
@@ -874,12 +708,10 @@ static int tcp_v6_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb)
NULL, NULL, skb);
if (genhash || memcmp(hash_location, newhash, 16) != 0) {
- if (net_ratelimit()) {
- printk(KERN_INFO "MD5 Hash %s for [%pI6c]:%u->[%pI6c]:%u\n",
- genhash ? "failed" : "mismatch",
- &ip6h->saddr, ntohs(th->source),
- &ip6h->daddr, ntohs(th->dest));
- }
+ net_info_ratelimited("MD5 Hash %s for [%pI6c]:%u->[%pI6c]:%u\n",
+ genhash ? "failed" : "mismatch",
+ &ip6h->saddr, ntohs(th->source),
+ &ip6h->daddr, ntohs(th->dest));
return 1;
}
return 0;
@@ -893,7 +725,7 @@ struct request_sock_ops tcp6_request_sock_ops __read_mostly = {
.send_ack = tcp_v6_reqsk_send_ack,
.destructor = tcp_v6_reqsk_destructor,
.send_reset = tcp_v6_send_reset,
- .syn_ack_timeout = tcp_syn_ack_timeout,
+ .syn_ack_timeout = tcp_syn_ack_timeout,
};
#ifdef CONFIG_TCP_MD5SIG
@@ -903,82 +735,10 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = {
};
#endif
-static void __tcp_v6_send_check(struct sk_buff *skb,
- const struct in6_addr *saddr, const struct in6_addr *daddr)
-{
- struct tcphdr *th = tcp_hdr(skb);
-
- if (skb->ip_summed == CHECKSUM_PARTIAL) {
- th->check = ~tcp_v6_check(skb->len, saddr, daddr, 0);
- skb->csum_start = skb_transport_header(skb) - skb->head;
- skb->csum_offset = offsetof(struct tcphdr, check);
- } else {
- th->check = tcp_v6_check(skb->len, saddr, daddr,
- csum_partial(th, th->doff << 2,
- skb->csum));
- }
-}
-
-static void tcp_v6_send_check(struct sock *sk, struct sk_buff *skb)
-{
- struct ipv6_pinfo *np = inet6_sk(sk);
-
- __tcp_v6_send_check(skb, &np->saddr, &np->daddr);
-}
-
-static int tcp_v6_gso_send_check(struct sk_buff *skb)
-{
- const 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;
- skb->ip_summed = CHECKSUM_PARTIAL;
- __tcp_v6_send_check(skb, &ipv6h->saddr, &ipv6h->daddr);
- return 0;
-}
-
-static struct sk_buff **tcp6_gro_receive(struct sk_buff **head,
- struct sk_buff *skb)
-{
- const 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)
-{
- const 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, u8 tclass)
+ u32 tsval, u32 tsecr, int oif,
+ struct tcp_md5sig_key *key, int rst, u8 tclass,
+ u32 label)
{
const struct tcphdr *th = tcp_hdr(skb);
struct tcphdr *t1;
@@ -990,7 +750,7 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win,
struct dst_entry *dst;
__be32 *topt;
- if (ts)
+ if (tsecr)
tot_len += TCPOLEN_TSTAMP_ALIGNED;
#ifdef CONFIG_TCP_MD5SIG
if (key)
@@ -1020,11 +780,11 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win,
topt = (__be32 *)(t1 + 1);
- if (ts) {
+ if (tsecr) {
*topt++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
(TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP);
- *topt++ = htonl(tcp_time_stamp);
- *topt++ = htonl(ts);
+ *topt++ = htonl(tsval);
+ *topt++ = htonl(tsecr);
}
#ifdef CONFIG_TCP_MD5SIG
@@ -1040,6 +800,7 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win,
memset(&fl6, 0, sizeof(fl6));
fl6.daddr = ipv6_hdr(skb)->saddr;
fl6.saddr = ipv6_hdr(skb)->daddr;
+ fl6.flowlabel = label;
buff->ip_summed = CHECKSUM_PARTIAL;
buff->csum = 0;
@@ -1047,7 +808,11 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win,
__tcp_v6_send_check(buff, &fl6.saddr, &fl6.daddr);
fl6.flowi6_proto = IPPROTO_TCP;
- fl6.flowi6_oif = inet6_iif(skb);
+ if (rt6_need_strict(&fl6.daddr) && !oif)
+ fl6.flowi6_oif = inet6_iif(skb);
+ else
+ fl6.flowi6_oif = oif;
+ fl6.flowi6_mark = IP6_REPLY_MARK(net, skb->mark);
fl6.fl6_dport = t1->dest;
fl6.fl6_sport = t1->source;
security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
@@ -1056,7 +821,7 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win,
* Underlying function will use this to retrieve the network
* namespace
*/
- dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL, false);
+ dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL);
if (!IS_ERR(dst)) {
skb_dst_set(buff, dst);
ip6_xmit(ctl_sk, buff, &fl6, NULL, tclass);
@@ -1074,6 +839,14 @@ static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb)
const struct tcphdr *th = tcp_hdr(skb);
u32 seq = 0, ack_seq = 0;
struct tcp_md5sig_key *key = NULL;
+#ifdef CONFIG_TCP_MD5SIG
+ const __u8 *hash_location = NULL;
+ struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+ unsigned char newhash[16];
+ int genhash;
+ struct sock *sk1 = NULL;
+#endif
+ int oif;
if (th->rst)
return;
@@ -1082,8 +855,33 @@ static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb)
return;
#ifdef CONFIG_TCP_MD5SIG
- if (sk)
- key = tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr);
+ hash_location = tcp_parse_md5sig_option(th);
+ if (!sk && hash_location) {
+ /*
+ * active side is lost. Try to find listening socket through
+ * source port, and then find md5 key through listening socket.
+ * we are not loose security here:
+ * Incoming packet is checked with md5 hash with finding key,
+ * no RST generated if md5 hash doesn't match.
+ */
+ sk1 = inet6_lookup_listener(dev_net(skb_dst(skb)->dev),
+ &tcp_hashinfo, &ipv6h->saddr,
+ th->source, &ipv6h->daddr,
+ ntohs(th->source), inet6_iif(skb));
+ if (!sk1)
+ return;
+
+ rcu_read_lock();
+ key = tcp_v6_md5_do_lookup(sk1, &ipv6h->saddr);
+ if (!key)
+ goto release_sk1;
+
+ genhash = tcp_v6_md5_hash_skb(newhash, key, NULL, NULL, skb);
+ if (genhash || memcmp(hash_location, newhash, 16) != 0)
+ goto release_sk1;
+ } else {
+ key = sk ? tcp_v6_md5_do_lookup(sk, &ipv6h->saddr) : NULL;
+ }
#endif
if (th->ack)
@@ -1092,13 +890,25 @@ static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb)
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, 0);
+ oif = sk ? sk->sk_bound_dev_if : 0;
+ tcp_v6_send_response(skb, seq, ack_seq, 0, 0, 0, oif, key, 1, 0, 0);
+
+#ifdef CONFIG_TCP_MD5SIG
+release_sk1:
+ if (sk1) {
+ rcu_read_unlock();
+ sock_put(sk1);
+ }
+#endif
}
-static void tcp_v6_send_ack(struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 ts,
- struct tcp_md5sig_key *key, u8 tclass)
+static void tcp_v6_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
+ u32 win, u32 tsval, u32 tsecr, int oif,
+ struct tcp_md5sig_key *key, u8 tclass,
+ u32 label)
{
- tcp_v6_send_response(skb, seq, ack, win, ts, key, 0, tclass);
+ tcp_v6_send_response(skb, seq, ack, win, tsval, tsecr, oif, key, 0, tclass,
+ label);
}
static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb)
@@ -1108,8 +918,9 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb)
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),
- tw->tw_tclass);
+ tcp_time_stamp + tcptw->tw_ts_offset,
+ tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw),
+ tw->tw_tclass, (tw->tw_flowlabel << 12));
inet_twsk_put(tw);
}
@@ -1117,12 +928,19 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb)
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_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr), 0);
+ /* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV
+ * sk->sk_state == TCP_SYN_RECV -> for Fast Open.
+ */
+ tcp_v6_send_ack(skb, (sk->sk_state == TCP_LISTEN) ?
+ tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt,
+ tcp_rsk(req)->rcv_nxt,
+ req->rcv_wnd, tcp_time_stamp, req->ts_recent, sk->sk_bound_dev_if,
+ tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr),
+ 0, 0);
}
-static struct sock *tcp_v6_hnd_req(struct sock *sk,struct sk_buff *skb)
+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);
@@ -1133,7 +951,7 @@ static struct sock *tcp_v6_hnd_req(struct sock *sk,struct sk_buff *skb)
&ipv6_hdr(skb)->saddr,
&ipv6_hdr(skb)->daddr, inet6_iif(skb));
if (req)
- return tcp_check_req(sk, skb, req, prev);
+ return tcp_check_req(sk, skb, req, prev, false);
nsk = __inet6_lookup_established(sock_net(sk), &tcp_hashinfo,
&ipv6_hdr(skb)->saddr, th->source,
@@ -1160,16 +978,17 @@ static struct sock *tcp_v6_hnd_req(struct sock *sk,struct sk_buff *skb)
*/
static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
{
- struct tcp_extend_values tmp_ext;
struct tcp_options_received tmp_opt;
- const u8 *hash_location;
struct request_sock *req;
- struct inet6_request_sock *treq;
+ struct inet_request_sock *ireq;
struct ipv6_pinfo *np = inet6_sk(sk);
struct tcp_sock *tp = tcp_sk(sk);
__u32 isn = TCP_SKB_CB(skb)->when;
struct dst_entry *dst = NULL;
- int want_cookie = 0;
+ struct tcp_fastopen_cookie foc = { .len = -1 };
+ bool want_cookie = false, fastopen;
+ struct flowi6 fl6;
+ int err;
if (skb->protocol == htons(ETH_P_IP))
return tcp_v4_conn_request(sk, skb);
@@ -1177,14 +996,17 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
if (!ipv6_unicast_destination(skb))
goto drop;
- if (inet_csk_reqsk_queue_is_full(sk) && !isn) {
+ if ((sysctl_tcp_syncookies == 2 ||
+ inet_csk_reqsk_queue_is_full(sk)) && !isn) {
want_cookie = tcp_syn_flood_action(sk, skb, "TCPv6");
if (!want_cookie)
goto drop;
}
- if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1)
+ if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) {
+ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS);
goto drop;
+ }
req = inet6_reqsk_alloc(&tcp6_request_sock_ops);
if (req == NULL)
@@ -1197,50 +1019,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
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, &hash_location, 0);
-
- if (tmp_opt.cookie_plus > 0 &&
- tmp_opt.saw_tstamp &&
- !tp->rx_opt.cookie_out_never &&
- (sysctl_tcp_cookie_size > 0 ||
- (tp->cookie_values != NULL &&
- tp->cookie_values->cookie_desired > 0))) {
- u8 *c;
- u32 *d;
- u32 *mess = &tmp_ext.cookie_bakery[COOKIE_DIGEST_WORDS];
- int l = tmp_opt.cookie_plus - TCPOLEN_COOKIE_BASE;
-
- if (tcp_cookie_generator(&tmp_ext.cookie_bakery[0]) != 0)
- goto drop_and_free;
-
- /* Secret recipe starts with IP addresses */
- d = (__force u32 *)&ipv6_hdr(skb)->daddr.s6_addr32[0];
- *mess++ ^= *d++;
- *mess++ ^= *d++;
- *mess++ ^= *d++;
- *mess++ ^= *d++;
- d = (__force u32 *)&ipv6_hdr(skb)->saddr.s6_addr32[0];
- *mess++ ^= *d++;
- *mess++ ^= *d++;
- *mess++ ^= *d++;
- *mess++ ^= *d++;
-
- /* plus variable length Initiator Cookie */
- c = (u8 *)mess;
- while (l-- > 0)
- *c++ ^= *hash_location++;
-
- want_cookie = 0; /* not our kind of cookie */
- tmp_ext.cookie_out_never = 0; /* false */
- tmp_ext.cookie_plus = tmp_opt.cookie_plus;
- } else if (!tp->rx_opt.cookie_in_always) {
- /* redundant indications, but ensure initialization. */
- tmp_ext.cookie_out_never = 1; /* true */
- tmp_ext.cookie_plus = 0;
- } else {
- goto drop_and_free;
- }
- tmp_ext.cookie_in_always = tp->rx_opt.cookie_in_always;
+ tcp_parse_options(skb, &tmp_opt, 0, want_cookie ? NULL : &foc);
if (want_cookie && !tmp_opt.saw_tstamp)
tcp_clear_options(&tmp_opt);
@@ -1248,27 +1027,27 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
tmp_opt.tstamp_ok = tmp_opt.saw_tstamp;
tcp_openreq_init(req, &tmp_opt, skb);
- treq = inet6_rsk(req);
- treq->rmt_addr = ipv6_hdr(skb)->saddr;
- treq->loc_addr = ipv6_hdr(skb)->daddr;
+ ireq = inet_rsk(req);
+ ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
+ ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
if (!want_cookie || tmp_opt.tstamp_ok)
- TCP_ECN_create_request(req, tcp_hdr(skb));
+ TCP_ECN_create_request(req, skb, sock_net(sk));
- treq->iif = sk->sk_bound_dev_if;
+ ireq->ir_iif = sk->sk_bound_dev_if;
+ ireq->ir_mark = inet_request_mark(sk, 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);
+ ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL)
+ ireq->ir_iif = inet6_iif(skb);
if (!isn) {
- struct inet_peer *peer = NULL;
-
if (ipv6_opt_accepted(sk, skb) ||
np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
- np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) {
+ np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim ||
+ np->repflow) {
atomic_inc(&skb->users);
- treq->pktopts = skb;
+ ireq->pktopts = skb;
}
if (want_cookie) {
@@ -1288,14 +1067,8 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
*/
if (tmp_opt.saw_tstamp &&
tcp_death_row.sysctl_tw_recycle &&
- (dst = inet6_csk_route_req(sk, req)) != NULL &&
- (peer = rt6_get_peer((struct rt6_info *)dst)) != NULL &&
- ipv6_addr_equal((struct in6_addr *)peer->daddr.addr.a6,
- &treq->rmt_addr)) {
- inet_peer_refcheck(peer);
- if ((u32)get_seconds() - peer->tcp_ts_stamp < TCP_PAWS_MSL &&
- (s32)(peer->tcp_ts - req->ts_recent) >
- TCP_PAWS_WINDOW) {
+ (dst = inet6_csk_route_req(sk, &fl6, req)) != NULL) {
+ if (!tcp_peer_is_proven(req, dst, true)) {
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSPASSIVEREJECTED);
goto drop_and_release;
}
@@ -1304,8 +1077,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
else if (!sysctl_tcp_syncookies &&
(sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) <
(sysctl_max_syn_backlog >> 2)) &&
- (!peer || !peer->tcp_ts_stamp) &&
- (!dst || !dst_metric(dst, RTAX_RTT))) {
+ !tcp_peer_is_proven(req, dst, false)) {
/* Without syncookies last quarter of
* backlog is filled with destinations,
* proven to be alive.
@@ -1314,24 +1086,34 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
* to the moment of synflood.
*/
LIMIT_NETDEBUG(KERN_DEBUG "TCP: drop open request from %pI6/%u\n",
- &treq->rmt_addr, ntohs(tcp_hdr(skb)->source));
+ &ireq->ir_v6_rmt_addr, ntohs(tcp_hdr(skb)->source));
goto drop_and_release;
}
isn = tcp_v6_init_sequence(skb);
}
have_isn:
- tcp_rsk(req)->snt_isn = isn;
- tcp_rsk(req)->snt_synack = tcp_time_stamp;
- security_inet_conn_request(sk, skb, req);
+ if (security_inet_conn_request(sk, skb, req))
+ goto drop_and_release;
- if (tcp_v6_send_synack(sk, req,
- (struct request_values *)&tmp_ext) ||
- want_cookie)
+ if (!dst && (dst = inet6_csk_route_req(sk, &fl6, req)) == NULL)
goto drop_and_free;
- inet6_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
+ tcp_rsk(req)->snt_isn = isn;
+ tcp_rsk(req)->snt_synack = tcp_time_stamp;
+ tcp_openreq_init_rwin(req, sk, dst);
+ fastopen = !want_cookie &&
+ tcp_try_fastopen(sk, skb, req, &foc, dst);
+ err = tcp_v6_send_synack(sk, dst, &fl6, req,
+ skb_get_queue_mapping(skb), &foc);
+ if (!fastopen) {
+ if (err || want_cookie)
+ goto drop_and_free;
+
+ tcp_rsk(req)->listener = NULL;
+ inet6_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
+ }
return 0;
drop_and_release:
@@ -1339,23 +1121,24 @@ drop_and_release:
drop_and_free:
reqsk_free(req);
drop:
+ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
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)
+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 inet_request_sock *ireq;
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
+ struct flowi6 fl6;
if (skb->protocol == htons(ETH_P_IP)) {
/*
@@ -1376,11 +1159,11 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
memcpy(newnp, np, sizeof(struct ipv6_pinfo));
- ipv6_addr_set_v4mapped(newinet->inet_daddr, &newnp->daddr);
+ ipv6_addr_set_v4mapped(newinet->inet_daddr, &newsk->sk_v6_daddr);
ipv6_addr_set_v4mapped(newinet->inet_saddr, &newnp->saddr);
- newnp->rcv_saddr = newnp->saddr;
+ newsk->sk_v6_rcv_saddr = newnp->saddr;
inet_csk(newsk)->icsk_af_ops = &ipv6_mapped;
newsk->sk_backlog_rcv = tcp_v4_do_rcv;
@@ -1394,6 +1177,9 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
newnp->opt = NULL;
newnp->mcast_oif = inet6_iif(skb);
newnp->mcast_hops = ipv6_hdr(skb)->hop_limit;
+ newnp->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(skb));
+ if (np->repflow)
+ newnp->flow_label = ip6_flowlabel(ipv6_hdr(skb));
/*
* No need to charge this sock to the relevant IPv6 refcnt debug socks count
@@ -1410,14 +1196,13 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
return newsk;
}
- treq = inet6_rsk(req);
- opt = np->opt;
+ ireq = inet_rsk(req);
if (sk_acceptq_is_full(sk))
goto out_overflow;
if (!dst) {
- dst = inet6_csk_route_req(sk, req);
+ dst = inet6_csk_route_req(sk, &fl6, req);
if (!dst)
goto out;
}
@@ -1434,6 +1219,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
newsk->sk_gso_type = SKB_GSO_TCPV6;
__ip6_dst_store(newsk, dst, NULL, NULL);
+ inet6_sk_rx_dst_set(newsk, skb);
newtcp6sk = (struct tcp6_sock *)newsk;
inet_sk(newsk)->pinet6 = &newtcp6sk->inet6;
@@ -1444,10 +1230,10 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
memcpy(newnp, np, sizeof(struct ipv6_pinfo));
- newnp->daddr = treq->rmt_addr;
- newnp->saddr = treq->loc_addr;
- newnp->rcv_saddr = treq->loc_addr;
- newsk->sk_bound_dev_if = treq->iif;
+ newsk->sk_v6_daddr = ireq->ir_v6_rmt_addr;
+ newnp->saddr = ireq->ir_v6_loc_addr;
+ newsk->sk_v6_rcv_saddr = ireq->ir_v6_loc_addr;
+ newsk->sk_bound_dev_if = ireq->ir_iif;
/* Now IPv6 options...
@@ -1462,16 +1248,20 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
/* 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 (ireq->pktopts != NULL) {
+ newnp->pktoptions = skb_clone(ireq->pktopts,
+ sk_gfp_atomic(sk, GFP_ATOMIC));
+ consume_skb(ireq->pktopts);
+ ireq->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;
+ newnp->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(skb));
+ if (np->repflow)
+ newnp->flow_label = ip6_flowlabel(ipv6_hdr(skb));
/* Clone native IPv6 options from listening socket (if any)
@@ -1479,46 +1269,43 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
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);
- }
+ if (np->opt)
+ newnp->opt = ipv6_dup_options(newsk, np->opt);
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_advmss(dst);
+ if (tcp_sk(sk)->rx_opt.user_mss &&
+ tcp_sk(sk)->rx_opt.user_mss < newtp->advmss)
+ newtp->advmss = tcp_sk(sk)->rx_opt.user_mss;
+
tcp_initialize_rcv_mss(newsk);
- if (tcp_rsk(req)->snt_synack)
- tcp_valid_rtt_meas(newsk,
- tcp_time_stamp - tcp_rsk(req)->snt_synack);
- newtp->total_retrans = req->retrans;
newinet->inet_daddr = newinet->inet_saddr = LOOPBACK4_IPV6;
newinet->inet_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) {
+ key = tcp_v6_md5_do_lookup(sk, &newsk->sk_v6_daddr);
+ if (key != NULL) {
/* We're using one, so create a matching key
* on the newsk structure. If we fail to get
* memory, then we end up not copying the key
* across. Shucks.
*/
- char *newkey = kmemdup(key->key, key->keylen, GFP_ATOMIC);
- if (newkey != NULL)
- tcp_v6_md5_do_add(newsk, &newnp->daddr,
- newkey, key->keylen);
+ tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newsk->sk_v6_daddr,
+ AF_INET6, key->key, key->keylen,
+ sk_gfp_atomic(sk, GFP_ATOMIC));
}
#endif
if (__inet_inherit_port(sk, newsk) < 0) {
- sock_put(newsk);
+ inet_csk_prepare_forced_close(newsk);
+ tcp_done(newsk);
goto out;
}
__inet6_hash(newsk, NULL);
@@ -1528,34 +1315,12 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
out_overflow:
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS);
out_nonewsk:
- if (opt && opt != np->opt)
- sock_kfree_s(sk, opt, opt->tot_len);
dst_release(dst);
out:
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
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.
*
@@ -1582,7 +1347,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
return tcp_v4_do_rcv(sk, skb);
#ifdef CONFIG_TCP_MD5SIG
- if (tcp_v6_inbound_md5_hash (sk, skb))
+ if (tcp_v6_inbound_md5_hash(sk, skb))
goto discard;
#endif
@@ -1608,12 +1373,21 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
--ANK (980728)
*/
if (np->rxopt.all)
- opt_skb = skb_clone(skb, GFP_ATOMIC);
+ opt_skb = skb_clone(skb, sk_gfp_atomic(sk, GFP_ATOMIC));
if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
+ struct dst_entry *dst = sk->sk_rx_dst;
+
sock_rps_save_rxhash(sk, skb);
- if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len))
- goto reset;
+ if (dst) {
+ if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif ||
+ dst->ops->check(dst, np->rx_dst_cookie) == NULL) {
+ dst_release(dst);
+ sk->sk_rx_dst = NULL;
+ }
+ }
+
+ tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len);
if (opt_skb)
goto ipv6_pktoptions;
return 0;
@@ -1632,7 +1406,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
* otherwise we just shortcircuit this and continue with
* the new socket..
*/
- if(nsk != sk) {
+ if (nsk != sk) {
sock_rps_save_rxhash(nsk, skb);
if (tcp_child_process(sk, nsk, skb))
goto reset;
@@ -1657,6 +1431,7 @@ discard:
kfree_skb(skb);
return 0;
csum_err:
+ TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_CSUMERRORS);
TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_INERRS);
goto discard;
@@ -1676,6 +1451,10 @@ ipv6_pktoptions:
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 (np->rxopt.bits.rxflow || np->rxopt.bits.rxtclass)
+ np->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(opt_skb));
+ if (np->repflow)
+ np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb));
if (ipv6_opt_accepted(sk, opt_skb)) {
skb_set_owner_r(opt_skb, sk);
opt_skb = xchg(&np->pktoptions, opt_skb);
@@ -1715,8 +1494,8 @@ static int tcp_v6_rcv(struct sk_buff *skb)
if (!pskb_may_pull(skb, th->doff*4))
goto discard_it;
- if (!skb_csum_unnecessary(skb) && tcp_v6_checksum_init(skb))
- goto bad_packet;
+ if (skb_checksum_init(skb, IPPROTO_TCP, ip6_compute_pseudo))
+ goto csum_error;
th = tcp_hdr(skb);
hdr = ipv6_hdr(skb);
@@ -1747,6 +1526,7 @@ process:
if (sk_filter(sk, skb))
goto discard_and_relse;
+ sk_mark_napi_id(sk, skb);
skb->dev = NULL;
bh_lock_sock_nested(sk);
@@ -1755,7 +1535,7 @@ process:
#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);
+ tp->ucopy.dma_chan = net_dma_find_channel();
if (tp->ucopy.dma_chan)
ret = tcp_v6_do_rcv(sk, skb);
else
@@ -1764,7 +1544,8 @@ process:
if (!tcp_prequeue(sk, skb))
ret = tcp_v6_do_rcv(sk, skb);
}
- } else if (unlikely(sk_add_backlog(sk, skb))) {
+ } else if (unlikely(sk_add_backlog(sk, skb,
+ sk->sk_rcvbuf + sk->sk_sndbuf))) {
bh_unlock_sock(sk);
NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP);
goto discard_and_relse;
@@ -1779,6 +1560,8 @@ no_tcp_socket:
goto discard_it;
if (skb->len < (th->doff<<2) || tcp_checksum_complete(skb)) {
+csum_error:
+ TCP_INC_STATS_BH(net, TCP_MIB_CSUMERRORS);
bad_packet:
TCP_INC_STATS_BH(net, TCP_MIB_INERRS);
} else {
@@ -1786,11 +1569,6 @@ bad_packet:
}
discard_it:
-
- /*
- * Discard frame
- */
-
kfree_skb(skb);
return 0;
@@ -1804,10 +1582,13 @@ do_time_wait:
goto discard_it;
}
- if (skb->len < (th->doff<<2) || tcp_checksum_complete(skb)) {
- TCP_INC_STATS_BH(net, TCP_MIB_INERRS);
+ if (skb->len < (th->doff<<2)) {
inet_twsk_put(inet_twsk(sk));
- goto discard_it;
+ goto bad_packet;
+ }
+ if (tcp_checksum_complete(skb)) {
+ inet_twsk_put(inet_twsk(sk));
+ goto csum_error;
}
switch (tcp_timewait_state_process(inet_twsk(sk), skb, th)) {
@@ -1816,6 +1597,7 @@ do_time_wait:
struct sock *sk2;
sk2 = inet6_lookup_listener(dev_net(skb->dev), &tcp_hashinfo,
+ &ipv6_hdr(skb)->saddr, th->source,
&ipv6_hdr(skb)->daddr,
ntohs(th->dest), inet6_iif(skb));
if (sk2 != NULL) {
@@ -1832,57 +1614,64 @@ do_time_wait:
break;
case TCP_TW_RST:
goto no_tcp_socket;
- case TCP_TW_SUCCESS:;
+ case TCP_TW_SUCCESS:
+ ;
}
goto discard_it;
}
-static struct inet_peer *tcp_v6_get_peer(struct sock *sk, bool *release_it)
+static void tcp_v6_early_demux(struct sk_buff *skb)
{
- struct rt6_info *rt = (struct rt6_info *) __sk_dst_get(sk);
- struct ipv6_pinfo *np = inet6_sk(sk);
- struct inet_peer *peer;
+ const struct ipv6hdr *hdr;
+ const struct tcphdr *th;
+ struct sock *sk;
- if (!rt ||
- !ipv6_addr_equal(&np->daddr, &rt->rt6i_dst.addr)) {
- peer = inet_getpeer_v6(&np->daddr, 1);
- *release_it = true;
- } else {
- if (!rt->rt6i_peer)
- rt6_bind_peer(rt, 1);
- peer = rt->rt6i_peer;
- *release_it = false;
- }
+ if (skb->pkt_type != PACKET_HOST)
+ return;
- return peer;
-}
+ if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct tcphdr)))
+ return;
-static void *tcp_v6_tw_get_peer(struct sock *sk)
-{
- const struct inet6_timewait_sock *tw6 = inet6_twsk(sk);
- const struct inet_timewait_sock *tw = inet_twsk(sk);
+ hdr = ipv6_hdr(skb);
+ th = tcp_hdr(skb);
- if (tw->tw_family == AF_INET)
- return tcp_v4_tw_get_peer(sk);
+ if (th->doff < sizeof(struct tcphdr) / 4)
+ return;
- return inet_getpeer_v6(&tw6->tw_v6_daddr, 1);
+ sk = __inet6_lookup_established(dev_net(skb->dev), &tcp_hashinfo,
+ &hdr->saddr, th->source,
+ &hdr->daddr, ntohs(th->dest),
+ inet6_iif(skb));
+ if (sk) {
+ skb->sk = sk;
+ skb->destructor = sock_edemux;
+ if (sk->sk_state != TCP_TIME_WAIT) {
+ struct dst_entry *dst = sk->sk_rx_dst;
+
+ if (dst)
+ dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie);
+ if (dst &&
+ inet_sk(sk)->rx_dst_ifindex == skb->skb_iif)
+ skb_dst_set_noref(skb, dst);
+ }
+ }
}
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,
- .twsk_getpeer = tcp_v6_tw_get_peer,
+ .twsk_destructor = tcp_twsk_destructor,
};
static const 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,
+ .sk_rx_dst_set = inet6_sk_rx_dst_set,
.conn_request = tcp_v6_conn_request,
.syn_recv_sock = tcp_v6_syn_recv_sock,
- .get_peer = tcp_v6_get_peer,
.net_header_len = sizeof(struct ipv6hdr),
+ .net_frag_header_len = sizeof(struct frag_hdr),
.setsockopt = ipv6_setsockopt,
.getsockopt = ipv6_getsockopt,
.addr2sockaddr = inet6_csk_addr2sockaddr,
@@ -1898,7 +1687,6 @@ static const struct inet_connection_sock_af_ops ipv6_specific = {
static const 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
@@ -1906,14 +1694,13 @@ static const struct tcp_sock_af_ops tcp_sock_ipv6_specific = {
/*
* TCP over IPv4 via INET6 API
*/
-
static const 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,
+ .sk_rx_dst_set = inet_sk_rx_dst_set,
.conn_request = tcp_v6_conn_request,
.syn_recv_sock = tcp_v6_syn_recv_sock,
- .get_peer = tcp_v4_get_peer,
.net_header_len = sizeof(struct iphdr),
.setsockopt = ipv6_setsockopt,
.getsockopt = ipv6_getsockopt,
@@ -1930,7 +1717,6 @@ static const struct inet_connection_sock_af_ops ipv6_mapped = {
static const 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
@@ -1941,74 +1727,20 @@ static const struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific = {
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 = TCP_INFINITE_SSTHRESH;
- tp->snd_cwnd_clamp = ~0;
- tp->mss_cache = TCP_MSS_DEFAULT;
-
- tp->reordering = sysctl_tcp_reordering;
- sk->sk_state = TCP_CLOSE;
+ tcp_init_sock(sk);
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;
+ tcp_sk(sk)->af_specific = &tcp_sock_ipv6_specific;
#endif
- /* TCP Cookie Transactions */
- if (sysctl_tcp_cookie_size > 0) {
- /* Default, cookies without s_data_payload. */
- tp->cookie_values =
- kzalloc(sizeof(*tp->cookie_values),
- sk->sk_allocation);
- if (tp->cookie_values != NULL)
- kref_init(&tp->cookie_values->kref);
- }
- /* Presumed zeroed, in order of appearance:
- * cookie_in_always, cookie_out_never,
- * s_data_constant, s_data_in, s_data_out
- */
- sk->sk_sndbuf = sysctl_tcp_wmem[1];
- sk->sk_rcvbuf = sysctl_tcp_rmem[1];
-
- local_bh_disable();
- sock_update_memcg(sk);
- sk_sockets_allocated_inc(sk);
- 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);
}
@@ -2016,31 +1748,31 @@ static void tcp_v6_destroy_sock(struct sock *sk)
#ifdef CONFIG_PROC_FS
/* Proc filesystem TCPv6 sock list dumping. */
static void get_openreq6(struct seq_file *seq,
- const struct sock *sk, struct request_sock *req, int i, int uid)
+ const struct sock *sk, struct request_sock *req, int i, kuid_t uid)
{
int ttd = req->expires - jiffies;
- const struct in6_addr *src = &inet6_rsk(req)->loc_addr;
- const struct in6_addr *dest = &inet6_rsk(req)->rmt_addr;
+ const struct in6_addr *src = &inet_rsk(req)->ir_v6_loc_addr;
+ const struct in6_addr *dest = &inet_rsk(req)->ir_v6_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 %pK\n",
+ "%02X %08X:%08X %02X:%08lX %08X %5u %8d %d %d %pK\n",
i,
src->s6_addr32[0], src->s6_addr32[1],
src->s6_addr32[2], src->s6_addr32[3],
- ntohs(inet_rsk(req)->loc_port),
+ inet_rsk(req)->ir_num,
dest->s6_addr32[0], dest->s6_addr32[1],
dest->s6_addr32[2], dest->s6_addr32[3],
- ntohs(inet_rsk(req)->rmt_port),
+ ntohs(inet_rsk(req)->ir_rmt_port),
TCP_SYN_RECV,
- 0,0, /* could print option size, but that is af dependent. */
+ 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,
+ req->num_timeout,
+ from_kuid_munged(seq_user_ns(seq), uid),
0, /* non standard timer */
0, /* open_requests have no inode */
0, req);
@@ -2055,10 +1787,10 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
const struct inet_sock *inet = inet_sk(sp);
const struct tcp_sock *tp = tcp_sk(sp);
const struct inet_connection_sock *icsk = inet_csk(sp);
- const struct ipv6_pinfo *np = inet6_sk(sp);
+ struct fastopen_queue *fastopenq = icsk->icsk_accept_queue.fastopenq;
- dest = &np->daddr;
- src = &np->rcv_saddr;
+ dest = &sp->sk_v6_daddr;
+ src = &sp->sk_v6_rcv_saddr;
destp = ntohs(inet->inet_dport);
srcp = ntohs(inet->inet_sport);
@@ -2078,7 +1810,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
seq_printf(seq,
"%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X "
- "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %pK %lu %lu %u %u %d\n",
+ "%02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %lu %lu %u %u %d\n",
i,
src->s6_addr32[0], src->s6_addr32[1],
src->s6_addr32[2], src->s6_addr32[3], srcp,
@@ -2088,17 +1820,19 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
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),
+ jiffies_delta_to_clock_t(timer_expires - jiffies),
icsk->icsk_retransmits,
- sock_i_uid(sp),
+ from_kuid_munged(seq_user_ns(seq), 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,
+ (icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong,
tp->snd_cwnd,
- tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh
+ sp->sk_state == TCP_LISTEN ?
+ (fastopenq ? fastopenq->max_qlen : 0) :
+ (tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh)
);
}
@@ -2107,14 +1841,10 @@ static void get_timewait6_sock(struct seq_file *seq,
{
const struct in6_addr *dest, *src;
__u16 destp, srcp;
- const struct inet6_timewait_sock *tw6 = inet6_twsk((struct sock *)tw);
- int ttd = tw->tw_ttd - jiffies;
-
- if (ttd < 0)
- ttd = 0;
+ s32 delta = tw->tw_ttd - inet_tw_time_stamp();
- dest = &tw6->tw_v6_daddr;
- src = &tw6->tw_v6_rcv_saddr;
+ dest = &tw->tw_v6_daddr;
+ src = &tw->tw_v6_rcv_saddr;
destp = ntohs(tw->tw_dport);
srcp = ntohs(tw->tw_sport);
@@ -2127,13 +1857,14 @@ static void get_timewait6_sock(struct seq_file *seq,
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,
+ 3, jiffies_delta_to_clock_t(delta), 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;
+ struct sock *sk = v;
if (v == SEQ_START_TOKEN) {
seq_puts(seq,
@@ -2149,14 +1880,14 @@ static int tcp6_seq_show(struct seq_file *seq, void *v)
switch (st->state) {
case TCP_SEQ_STATE_LISTENING:
case TCP_SEQ_STATE_ESTABLISHED:
- get_tcp6_sock(seq, v, st->num);
+ if (sk->sk_state == TCP_TIME_WAIT)
+ get_timewait6_sock(seq, v, st->num);
+ else
+ 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;
@@ -2190,6 +1921,17 @@ void tcp6_proc_exit(struct net *net)
}
#endif
+static void tcp_v6_clear_sk(struct sock *sk, int size)
+{
+ struct inet_sock *inet = inet_sk(sk);
+
+ /* we do not want to clear pinet6 field, because of RCU lookups */
+ sk_prot_clear_nulls(sk, offsetof(struct inet_sock, pinet6));
+
+ size -= offsetof(struct inet_sock, pinet6) + sizeof(inet->pinet6);
+ memset(&inet->pinet6 + 1, 0, size);
+}
+
struct proto tcpv6_prot = {
.name = "TCPv6",
.owner = THIS_MODULE,
@@ -2207,14 +1949,18 @@ struct proto tcpv6_prot = {
.sendmsg = tcp_sendmsg,
.sendpage = tcp_sendpage,
.backlog_rcv = tcp_v6_do_rcv,
+ .release_cb = tcp_release_cb,
+ .mtu_reduced = tcp_v6_mtu_reduced,
.hash = tcp_v6_hash,
.unhash = inet_unhash,
.get_port = inet_csk_get_port,
.enter_memory_pressure = tcp_enter_memory_pressure,
+ .stream_memory_free = tcp_stream_memory_free,
.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,
@@ -2228,18 +1974,16 @@ struct proto tcpv6_prot = {
.compat_setsockopt = compat_tcp_setsockopt,
.compat_getsockopt = compat_tcp_getsockopt,
#endif
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+#ifdef CONFIG_MEMCG_KMEM
.proto_cgroup = tcp_proto_cgroup,
#endif
+ .clear_sk = tcp_v6_clear_sk,
};
static const struct inet6_protocol tcpv6_protocol = {
+ .early_demux = tcp_v6_early_demux,
.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,
};
@@ -2248,7 +1992,6 @@ static struct inet_protosw tcpv6_protosw = {
.protocol = IPPROTO_TCP,
.prot = &tcpv6_prot,
.ops = &inet6_stream_ops,
- .no_check = 0,
.flags = INET_PROTOSW_PERMANENT |
INET_PROTOSW_ICSK,
};
@@ -2294,10 +2037,10 @@ int __init tcpv6_init(void)
out:
return ret;
-out_tcpv6_protocol:
- inet6_del_protocol(&tcpv6_protocol, IPPROTO_TCP);
out_tcpv6_protosw:
inet6_unregister_protosw(&tcpv6_protosw);
+out_tcpv6_protocol:
+ inet6_del_protocol(&tcpv6_protocol, IPPROTO_TCP);
goto out;
}
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-09 20:39:03 +0000