| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20230614230947.3954084-10-dima@arista.com>
Date: Thu, 15 Jun 2023 00:09:34 +0100
From: Dmitry Safonov <dima@...sta.com>
To: David Ahern <dsahern@...nel.org>,
Eric Dumazet <edumazet@...gle.com>,
Paolo Abeni <pabeni@...hat.com>,
Jakub Kicinski <kuba@...nel.org>,
"David S. Miller" <davem@...emloft.net>
Cc: linux-kernel@...r.kernel.org, Dmitry Safonov <dima@...sta.com>,
Andy Lutomirski <luto@...capital.net>,
Ard Biesheuvel <ardb@...nel.org>,
Bob Gilligan <gilligan@...sta.com>,
Dan Carpenter <error27@...il.com>,
David Laight <David.Laight@...lab.com>,
Dmitry Safonov <0x7f454c46@...il.com>,
Donald Cassidy <dcassidy@...hat.com>,
Eric Biggers <ebiggers@...nel.org>,
"Eric W. Biederman" <ebiederm@...ssion.com>,
Francesco Ruggeri <fruggeri05@...il.com>,
Herbert Xu <herbert@...dor.apana.org.au>,
Hideaki YOSHIFUJI <yoshfuji@...ux-ipv6.org>,
Ivan Delalande <colona@...sta.com>,
Leonard Crestez <cdleonard@...il.com>,
Salam Noureddine <noureddine@...sta.com>,
netdev@...r.kernel.org
Subject: [PATCH v7 09/22] net/tcp: Add TCP-AO sign to twsk
Add support for sockets in time-wait state.
ao_info as well as all keys are inherited on transition to time-wait
socket. The lifetime of ao_info is now protected by ref counter, so
that tcp_ao_destroy_sock() will destruct it only when the last user is
gone.
Co-developed-by: Francesco Ruggeri <fruggeri@...sta.com>
Signed-off-by: Francesco Ruggeri <fruggeri@...sta.com>
Co-developed-by: Salam Noureddine <noureddine@...sta.com>
Signed-off-by: Salam Noureddine <noureddine@...sta.com>
Signed-off-by: Dmitry Safonov <dima@...sta.com>
---
include/linux/tcp.h | 3 ++
include/net/tcp_ao.h | 11 +++++--
net/ipv4/tcp_ao.c | 46 ++++++++++++++++++++++-----
net/ipv4/tcp_ipv4.c | 68 ++++++++++++++++++++++++++++++++++++----
net/ipv4/tcp_minisocks.c | 4 ++-
net/ipv4/tcp_output.c | 2 +-
net/ipv6/tcp_ipv6.c | 44 +++++++++++++++++++++++---
7 files changed, 157 insertions(+), 21 deletions(-)
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 673b32e47c30..0c50a9aaa780 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -500,6 +500,9 @@ struct tcp_timewait_sock {
#ifdef CONFIG_TCP_MD5SIG
struct tcp_md5sig_key *tw_md5_key;
#endif
+#ifdef CONFIG_TCP_AO
+ struct tcp_ao_info *ao_info;
+#endif
};
static inline struct tcp_timewait_sock *tcp_twsk(const struct sock *sk)
diff --git a/include/net/tcp_ao.h b/include/net/tcp_ao.h
index 010c77c4456e..c518452af09a 100644
--- a/include/net/tcp_ao.h
+++ b/include/net/tcp_ao.h
@@ -91,6 +91,7 @@ struct tcp_ao_info {
u32 snd_sne_seq;
u32 rcv_sne;
u32 rcv_sne_seq;
+ atomic_t refcnt; /* Protects twsk destruction */
struct rcu_head rcu;
};
@@ -125,8 +126,9 @@ struct tcp_ao_key *tcp_ao_established_key(struct tcp_ao_info *ao,
int sndid, int rcvid);
int tcp_ao_calc_traffic_key(struct tcp_ao_key *mkt, u8 *key, void *ctx,
unsigned int len);
-void tcp_ao_destroy_sock(struct sock *sk);
+void tcp_ao_destroy_sock(struct sock *sk, bool twsk);
u32 tcp_ao_compute_sne(u32 sne, u32 seq, u32 new_seq);
+void tcp_ao_time_wait(struct tcp_timewait_sock *tcptw, struct tcp_sock *tp);
struct tcp_ao_key *tcp_ao_do_lookup(const struct sock *sk,
const union tcp_ao_addr *addr,
int family, int sndid, int rcvid, u16 port);
@@ -180,7 +182,7 @@ static inline struct tcp_ao_key *tcp_ao_do_lookup(const struct sock *sk,
return NULL;
}
-static inline void tcp_ao_destroy_sock(struct sock *sk)
+static inline void tcp_ao_destroy_sock(struct sock *sk, bool twsk)
{
}
@@ -188,6 +190,11 @@ static inline void tcp_ao_finish_connect(struct sock *sk, struct sk_buff *skb)
{
}
+static inline void tcp_ao_time_wait(struct tcp_timewait_sock *tcptw,
+ struct tcp_sock *tp)
+{
+}
+
static inline void tcp_ao_connect_init(struct sock *sk)
{
}
diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c
index a45ab30265bf..9a3bb06e1046 100644
--- a/net/ipv4/tcp_ao.c
+++ b/net/ipv4/tcp_ao.c
@@ -171,6 +171,7 @@ static struct tcp_ao_info *tcp_ao_alloc_info(gfp_t flags)
if (!ao)
return NULL;
INIT_HLIST_HEAD(&ao->head);
+ atomic_set(&ao->refcnt, 1);
return ao;
}
@@ -188,27 +189,54 @@ static void tcp_ao_key_free_rcu(struct rcu_head *head)
kfree(key);
}
-void tcp_ao_destroy_sock(struct sock *sk)
+void tcp_ao_destroy_sock(struct sock *sk, bool twsk)
{
struct tcp_ao_info *ao;
struct tcp_ao_key *key;
struct hlist_node *n;
- ao = rcu_dereference_protected(tcp_sk(sk)->ao_info, 1);
- tcp_sk(sk)->ao_info = NULL;
+ if (twsk) {
+ ao = rcu_dereference_protected(tcp_twsk(sk)->ao_info, 1);
+ tcp_twsk(sk)->ao_info = NULL;
+ } else {
+ ao = rcu_dereference_protected(tcp_sk(sk)->ao_info, 1);
+ tcp_sk(sk)->ao_info = NULL;
+ }
- if (!ao)
+ if (!ao || !atomic_dec_and_test(&ao->refcnt))
return;
hlist_for_each_entry_safe(key, n, &ao->head, node) {
hlist_del_rcu(&key->node);
- atomic_sub(tcp_ao_sizeof_key(key), &sk->sk_omem_alloc);
+ if (!twsk)
+ atomic_sub(tcp_ao_sizeof_key(key), &sk->sk_omem_alloc);
call_rcu(&key->rcu, tcp_ao_key_free_rcu);
}
kfree_rcu(ao, rcu);
}
+void tcp_ao_time_wait(struct tcp_timewait_sock *tcptw, struct tcp_sock *tp)
+{
+ struct tcp_ao_info *ao_info = rcu_dereference_protected(tp->ao_info, 1);
+
+ if (ao_info) {
+ struct tcp_ao_key *key;
+ struct hlist_node *n;
+ int omem = 0;
+
+ hlist_for_each_entry_safe(key, n, &ao_info->head, node) {
+ omem += tcp_ao_sizeof_key(key);
+ }
+
+ atomic_inc(&ao_info->refcnt);
+ atomic_sub(omem, &(((struct sock *)tp)->sk_omem_alloc));
+ rcu_assign_pointer(tcptw->ao_info, ao_info);
+ } else {
+ tcptw->ao_info = NULL;
+ }
+}
+
/* 4 tuple and ISNs are expected in NBO */
static int tcp_v4_ao_calc_key(struct tcp_ao_key *mkt, u8 *key,
__be32 saddr, __be32 daddr,
@@ -529,8 +557,9 @@ int tcp_ao_prepare_reset(const struct sock *sk, struct sk_buff *skb,
struct tcp_ao_key *rnext_key;
if (sk->sk_state == TCP_TIME_WAIT)
- return -1;
- ao_info = rcu_dereference(tcp_sk(sk)->ao_info);
+ ao_info = rcu_dereference(tcp_twsk(sk)->ao_info);
+ else
+ ao_info = rcu_dereference(tcp_sk(sk)->ao_info);
if (!ao_info)
return -ENOENT;
@@ -914,6 +943,9 @@ static struct tcp_ao_info *setsockopt_ao_info(struct sock *sk)
if (sk_fullsock(sk)) {
return rcu_dereference_protected(tcp_sk(sk)->ao_info,
lockdep_sock_is_held(sk));
+ } else if (sk->sk_state == TCP_TIME_WAIT) {
+ return rcu_dereference_protected(tcp_twsk(sk)->ao_info,
+ lockdep_sock_is_held(sk));
}
return ERR_PTR(-ESOCKTNOSUPPORT);
}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 9638bab8ed92..0d310d0613b5 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -904,16 +904,16 @@ static void tcp_v4_send_ack(const struct sock *sk,
struct sk_buff *skb, u32 seq, u32 ack,
u32 win, u32 tsval, u32 tsecr, int oif,
struct tcp_md5sig_key *key,
+ struct tcp_ao_key *ao_key,
+ u8 *traffic_key,
+ u8 rcv_next,
+ u32 ao_sne,
int reply_flags, u8 tos)
{
const struct tcphdr *th = tcp_hdr(skb);
struct {
struct tcphdr th;
- __be32 opt[(TCPOLEN_TSTAMP_ALIGNED >> 2)
-#ifdef CONFIG_TCP_MD5SIG
- + (TCPOLEN_MD5SIG_ALIGNED >> 2)
-#endif
- ];
+ __be32 opt[(MAX_TCP_OPTION_SPACE >> 2)];
} rep;
struct net *net = sock_net(sk);
struct ip_reply_arg arg;
@@ -958,6 +958,24 @@ static void tcp_v4_send_ack(const struct sock *sk,
key, ip_hdr(skb)->saddr,
ip_hdr(skb)->daddr, &rep.th);
}
+#endif
+#ifdef CONFIG_TCP_AO
+ if (ao_key) {
+ int offset = (tsecr) ? 3 : 0;
+
+ rep.opt[offset++] = htonl((TCPOPT_AO << 24) |
+ (tcp_ao_len(ao_key) << 16) |
+ (ao_key->sndid << 8) | rcv_next);
+ arg.iov[0].iov_len += round_up(tcp_ao_len(ao_key), 4);
+ rep.th.doff = arg.iov[0].iov_len / 4;
+
+ tcp_ao_hash_hdr(AF_INET, (char *)&rep.opt[offset],
+ ao_key, traffic_key,
+ (union tcp_ao_addr *)&ip_hdr(skb)->saddr,
+ (union tcp_ao_addr *)&ip_hdr(skb)->daddr,
+ &rep.th, ao_sne);
+ }
+ WARN_ON_ONCE(key && ao_key);
#endif
arg.flags = reply_flags;
arg.csum = csum_tcpudp_nofold(ip_hdr(skb)->daddr,
@@ -991,6 +1009,39 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
{
struct inet_timewait_sock *tw = inet_twsk(sk);
struct tcp_timewait_sock *tcptw = tcp_twsk(sk);
+ struct tcp_ao_key *ao_key = NULL;
+ u8 *traffic_key = NULL;
+ u8 rcv_next = 0;
+ u32 ao_sne = 0;
+#ifdef CONFIG_TCP_AO
+ struct tcp_ao_info *ao_info;
+
+ /* FIXME: the segment to-be-acked is not verified yet */
+ ao_info = rcu_dereference(tcptw->ao_info);
+ if (ao_info) {
+ const struct tcp_ao_hdr *aoh;
+
+ if (tcp_parse_auth_options(tcp_hdr(skb), NULL, &aoh))
+ goto out; /* something is wrong with the sign */
+
+ if (aoh)
+ ao_key = tcp_ao_established_key(ao_info, aoh->rnext_keyid, -1);
+ }
+ if (ao_key) {
+ struct tcp_ao_key *rnext_key;
+
+ traffic_key = snd_other_key(ao_key);
+ /* It's possible we can get rid of computing the sne
+ * below since sne probably doesn't change once we are
+ * in timewait state.
+ */
+ ao_sne = tcp_ao_compute_sne(ao_info->snd_sne,
+ ao_info->snd_sne_seq,
+ tcptw->tw_snd_nxt);
+ rnext_key = READ_ONCE(ao_info->rnext_key);
+ rcv_next = rnext_key->rcvid;
+ }
+#endif
tcp_v4_send_ack(sk, skb,
tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
@@ -999,10 +1050,14 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
tcptw->tw_ts_recent,
tw->tw_bound_dev_if,
tcp_twsk_md5_key(tcptw),
+ ao_key, traffic_key, rcv_next, ao_sne,
tw->tw_transparent ? IP_REPLY_ARG_NOSRCCHECK : 0,
tw->tw_tos
);
+#ifdef CONFIG_TCP_AO
+out:
+#endif
inet_twsk_put(tw);
}
@@ -1032,6 +1087,7 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
req->ts_recent,
0,
tcp_md5_do_lookup(sk, l3index, addr, AF_INET),
+ NULL, NULL, 0, 0,
inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0,
ip_hdr(skb)->tos);
}
@@ -2392,7 +2448,7 @@ void tcp_v4_destroy_sock(struct sock *sk)
rcu_assign_pointer(tp->md5sig_info, NULL);
}
#endif
- tcp_ao_destroy_sock(sk);
+ tcp_ao_destroy_sock(sk, false);
/* Clean up a referenced TCP bind bucket. */
if (inet_csk(sk)->icsk_bind_hash)
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 63b5c5f42a87..ea6e5c97c66a 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -279,7 +279,7 @@ static void tcp_time_wait_init(struct sock *sk, struct tcp_timewait_sock *tcptw)
void tcp_time_wait(struct sock *sk, int state, int timeo)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
- const struct tcp_sock *tp = tcp_sk(sk);
+ struct tcp_sock *tp = tcp_sk(sk);
struct net *net = sock_net(sk);
struct inet_timewait_sock *tw;
@@ -316,6 +316,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
#endif
tcp_time_wait_init(sk, tcptw);
+ tcp_ao_time_wait(tcptw, tp);
/* Get the TIME_WAIT timeout firing. */
if (timeo < rto)
@@ -370,6 +371,7 @@ void tcp_twsk_destructor(struct sock *sk)
call_rcu(&twsk->tw_md5_key->rcu, tcp_md5_twsk_free_rcu);
}
#endif
+ tcp_ao_destroy_sock(sk, true);
}
EXPORT_SYMBOL_GPL(tcp_twsk_destructor);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index d4c7ca5d5cf1..c08dae53b03b 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3968,7 +3968,7 @@ int tcp_connect(struct sock *sk)
* then free up ao_info if allocated.
*/
if (needs_md5) {
- tcp_ao_destroy_sock(sk);
+ tcp_ao_destroy_sock(sk, false);
} else if (needs_ao) {
tcp_clear_md5_list(sk);
kfree(rcu_replace_pointer(tp->md5sig_info, NULL,
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 282603cb009c..5bf1ba48ca68 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1140,24 +1140,60 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
static void tcp_v6_send_ack(const struct sock *sk, struct sk_buff *skb, u32 seq,
u32 ack, u32 win, u32 tsval, u32 tsecr, int oif,
struct tcp_md5sig_key *key, u8 tclass,
- __be32 label, u32 priority, u32 txhash)
+ __be32 label, u32 priority, u32 txhash,
+ struct tcp_ao_key *ao_key, char *tkey,
+ u8 rcv_next, u32 ao_sne)
{
tcp_v6_send_response(sk, skb, seq, ack, win, tsval, tsecr, oif, key, 0,
- tclass, label, priority, txhash, NULL, NULL, 0, 0);
+ tclass, label, priority, txhash,
+ ao_key, tkey, rcv_next, ao_sne);
}
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);
+ struct tcp_ao_key *ao_key = NULL;
+ u8 *traffic_key = NULL;
+ u8 rcv_next = 0;
+ u32 ao_sne = 0;
+#ifdef CONFIG_TCP_AO
+ struct tcp_ao_info *ao_info;
+
+ /* FIXME: the segment to-be-acked is not verified yet */
+ ao_info = rcu_dereference(tcptw->ao_info);
+ if (ao_info) {
+ const struct tcp_ao_hdr *aoh;
+
+ /* Invalid TCP option size or twice included auth */
+ if (tcp_parse_auth_options(tcp_hdr(skb), NULL, &aoh))
+ goto out;
+ if (aoh)
+ ao_key = tcp_ao_established_key(ao_info, aoh->rnext_keyid, -1);
+ }
+ if (ao_key) {
+ struct tcp_ao_key *rnext_key;
+
+ traffic_key = snd_other_key(ao_key);
+ /* rcv_next switches to our rcv_next */
+ rnext_key = READ_ONCE(ao_info->rnext_key);
+ rcv_next = rnext_key->rcvid;
+ ao_sne = tcp_ao_compute_sne(ao_info->snd_sne,
+ ao_info->snd_sne_seq,
+ tcptw->tw_snd_nxt);
+ }
+#endif
tcp_v6_send_ack(sk, skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
tcp_time_stamp_raw() + tcptw->tw_ts_offset,
tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw),
tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel), tw->tw_priority,
- tw->tw_txhash);
+ tw->tw_txhash, ao_key, traffic_key, rcv_next, ao_sne);
+#ifdef CONFIG_TCP_AO
+out:
+#endif
inet_twsk_put(tw);
}
@@ -1184,7 +1220,7 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
req->ts_recent, sk->sk_bound_dev_if,
tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr, l3index),
ipv6_get_dsfield(ipv6_hdr(skb)), 0, sk->sk_priority,
- tcp_rsk(req)->txhash);
+ tcp_rsk(req)->txhash, NULL, NULL, 0, 0);
}
--
2.40.0
Powered by blists - more mailing lists