summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/igmp.c6
-rw-r--r--net/ipv4/inet_diag.c1
-rw-r--r--net/ipv4/inet_hashtables.c2
-rw-r--r--net/ipv4/ip_gre.c11
-rw-r--r--net/ipv4/raw_diag.c1
-rw-r--r--net/ipv4/route.c2
-rw-r--r--net/ipv4/tcp.c28
-rw-r--r--net/ipv4/tcp_ao.c17
-rw-r--r--net/ipv4/tcp_diag.c1
-rw-r--r--net/ipv4/tcp_input.c33
-rw-r--r--net/ipv4/tcp_ipv4.c4
-rw-r--r--net/ipv4/tcp_minisocks.c2
-rw-r--r--net/ipv4/tcp_output.c21
-rw-r--r--net/ipv4/tcp_sigpool.c5
-rw-r--r--net/ipv4/udp_diag.c1
15 files changed, 100 insertions, 35 deletions
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 76c3ea75b8dd..efeeca2b1328 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -216,8 +216,10 @@ static void igmp_start_timer(struct ip_mc_list *im, int max_delay)
int tv = get_random_u32_below(max_delay);
im->tm_running = 1;
- if (!mod_timer(&im->timer, jiffies+tv+2))
- refcount_inc(&im->refcnt);
+ if (refcount_inc_not_zero(&im->refcnt)) {
+ if (mod_timer(&im->timer, jiffies + tv + 2))
+ ip_ma_put(im);
+ }
}
static void igmp_gq_start_timer(struct in_device *in_dev)
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index f01aee832aab..7d0e7aaa71e0 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -1481,5 +1481,6 @@ static void __exit inet_diag_exit(void)
module_init(inet_diag_init);
module_exit(inet_diag_exit);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("INET/INET6: socket monitoring via SOCK_DIAG");
MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2 /* AF_INET */);
MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 10 /* AF_INET6 */);
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 598c1b114d2c..a532f749e477 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -751,12 +751,12 @@ int __inet_hash(struct sock *sk, struct sock *osk)
if (err)
goto unlock;
}
+ sock_set_flag(sk, SOCK_RCU_FREE);
if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport &&
sk->sk_family == AF_INET6)
__sk_nulls_add_node_tail_rcu(sk, &ilb2->nulls_head);
else
__sk_nulls_add_node_rcu(sk, &ilb2->nulls_head);
- sock_set_flag(sk, SOCK_RCU_FREE);
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
unlock:
spin_unlock(&ilb2->lock);
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 22a26d1d29a0..5169c3c72cff 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -635,15 +635,18 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb,
}
if (dev->header_ops) {
+ int pull_len = tunnel->hlen + sizeof(struct iphdr);
+
if (skb_cow_head(skb, 0))
goto free_skb;
tnl_params = (const struct iphdr *)skb->data;
- /* Pull skb since ip_tunnel_xmit() needs skb->data pointing
- * to gre header.
- */
- skb_pull(skb, tunnel->hlen + sizeof(struct iphdr));
+ if (!pskb_network_may_pull(skb, pull_len))
+ goto free_skb;
+
+ /* ip_tunnel_xmit() needs skb->data pointing to gre header. */
+ skb_pull(skb, pull_len);
skb_reset_mac_header(skb);
if (skb->ip_summed == CHECKSUM_PARTIAL &&
diff --git a/net/ipv4/raw_diag.c b/net/ipv4/raw_diag.c
index 63a40e4b678f..fe2140c8375c 100644
--- a/net/ipv4/raw_diag.c
+++ b/net/ipv4/raw_diag.c
@@ -257,5 +257,6 @@ static void __exit raw_diag_exit(void)
module_init(raw_diag_init);
module_exit(raw_diag_exit);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("RAW socket monitoring via SOCK_DIAG");
MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-255 /* AF_INET - IPPROTO_RAW */);
MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 10-255 /* AF_INET6 - IPPROTO_RAW */);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 3290a4442b4a..16615d107cf0 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -780,7 +780,7 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow
goto reject_redirect;
}
- n = __ipv4_neigh_lookup(rt->dst.dev, new_gw);
+ n = __ipv4_neigh_lookup(rt->dst.dev, (__force u32)new_gw);
if (!n)
n = neigh_create(&arp_tbl, &new_gw, rt->dst.dev);
if (!IS_ERR(n)) {
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 54d3c762d400..fce5668a6a3d 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3366,9 +3366,25 @@ int tcp_set_window_clamp(struct sock *sk, int val)
return -EINVAL;
tp->window_clamp = 0;
} else {
- tp->window_clamp = val < SOCK_MIN_RCVBUF / 2 ?
- SOCK_MIN_RCVBUF / 2 : val;
- tp->rcv_ssthresh = min(tp->rcv_wnd, tp->window_clamp);
+ u32 new_rcv_ssthresh, old_window_clamp = tp->window_clamp;
+ u32 new_window_clamp = val < SOCK_MIN_RCVBUF / 2 ?
+ SOCK_MIN_RCVBUF / 2 : val;
+
+ if (new_window_clamp == old_window_clamp)
+ return 0;
+
+ tp->window_clamp = new_window_clamp;
+ if (new_window_clamp < old_window_clamp) {
+ /* need to apply the reserved mem provisioning only
+ * when shrinking the window clamp
+ */
+ __tcp_adjust_rcv_ssthresh(sk, tp->window_clamp);
+
+ } else {
+ new_rcv_ssthresh = min(tp->rcv_wnd, tp->window_clamp);
+ tp->rcv_ssthresh = max(new_rcv_ssthresh,
+ tp->rcv_ssthresh);
+ }
}
return 0;
}
@@ -3592,6 +3608,10 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
break;
case TCP_AO_REPAIR:
+ if (!tcp_can_repair_sock(sk)) {
+ err = -EPERM;
+ break;
+ }
err = tcp_ao_set_repair(sk, optval, optlen);
break;
#ifdef CONFIG_TCP_AO
@@ -4291,6 +4311,8 @@ zerocopy_rcv_out:
}
#endif
case TCP_AO_REPAIR:
+ if (!tcp_can_repair_sock(sk))
+ return -EPERM;
return tcp_ao_get_repair(sk, optval, optlen);
case TCP_AO_GET_KEYS:
case TCP_AO_INFO: {
diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c
index 7696417d0640..f8308d3f565e 100644
--- a/net/ipv4/tcp_ao.c
+++ b/net/ipv4/tcp_ao.c
@@ -851,7 +851,7 @@ void tcp_ao_syncookie(struct sock *sk, const struct sk_buff *skb,
const struct tcp_ao_hdr *aoh;
struct tcp_ao_key *key;
- treq->maclen = 0;
+ treq->used_tcp_ao = false;
if (tcp_parse_auth_options(th, NULL, &aoh) || !aoh)
return;
@@ -863,7 +863,7 @@ void tcp_ao_syncookie(struct sock *sk, const struct sk_buff *skb,
treq->ao_rcv_next = aoh->keyid;
treq->ao_keyid = aoh->rnext_keyid;
- treq->maclen = tcp_ao_maclen(key);
+ treq->used_tcp_ao = true;
}
static enum skb_drop_reason
@@ -1100,7 +1100,7 @@ void tcp_ao_connect_init(struct sock *sk)
ao_info->current_key = key;
if (!ao_info->rnext_key)
ao_info->rnext_key = key;
- tp->tcp_header_len += tcp_ao_len(key);
+ tp->tcp_header_len += tcp_ao_len_aligned(key);
ao_info->lisn = htonl(tp->write_seq);
ao_info->snd_sne = 0;
@@ -1346,7 +1346,7 @@ static int tcp_ao_parse_crypto(struct tcp_ao_add *cmd, struct tcp_ao_key *key)
syn_tcp_option_space -= TCPOLEN_MSS_ALIGNED;
syn_tcp_option_space -= TCPOLEN_TSTAMP_ALIGNED;
syn_tcp_option_space -= TCPOLEN_WSCALE_ALIGNED;
- if (tcp_ao_len(key) > syn_tcp_option_space) {
+ if (tcp_ao_len_aligned(key) > syn_tcp_option_space) {
err = -EMSGSIZE;
goto err_kfree;
}
@@ -1608,6 +1608,15 @@ static int tcp_ao_add_cmd(struct sock *sk, unsigned short int family,
if (!dev || !l3index)
return -EINVAL;
+ if (!bound_dev_if || bound_dev_if != cmd.ifindex) {
+ /* tcp_ao_established_key() doesn't expect having
+ * non peer-matching key on an established TCP-AO
+ * connection.
+ */
+ if (!((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)))
+ return -EINVAL;
+ }
+
/* It's still possible to bind after adding keys or even
* re-bind to a different dev (with CAP_NET_RAW).
* So, no reason to return error here, rather try to be
diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c
index 01b50fa79189..4cbe4b44425a 100644
--- a/net/ipv4/tcp_diag.c
+++ b/net/ipv4/tcp_diag.c
@@ -247,4 +247,5 @@ static void __exit tcp_diag_exit(void)
module_init(tcp_diag_init);
module_exit(tcp_diag_exit);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("TCP socket monitoring via SOCK_DIAG");
MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-6 /* AF_INET - IPPROTO_TCP */);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index bcb55d98004c..701cb87043f2 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3871,8 +3871,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
* then we can probably ignore it.
*/
if (before(ack, prior_snd_una)) {
+ u32 max_window;
+
+ /* do not accept ACK for bytes we never sent. */
+ max_window = min_t(u64, tp->max_window, tp->bytes_acked);
/* RFC 5961 5.2 [Blind Data Injection Attack].[Mitigation] */
- if (before(ack, prior_snd_una - tp->max_window)) {
+ if (before(ack, prior_snd_una - max_window)) {
if (!(flag & FLAG_NO_CHALLENGE_ACK))
tcp_send_challenge_ack(sk);
return -SKB_DROP_REASON_TCP_TOO_OLD_ACK;
@@ -4364,6 +4368,23 @@ EXPORT_SYMBOL(tcp_do_parse_auth_options);
* up to bandwidth of 18Gigabit/sec. 8) ]
*/
+/* Estimates max number of increments of remote peer TSval in
+ * a replay window (based on our current RTO estimation).
+ */
+static u32 tcp_tsval_replay(const struct sock *sk)
+{
+ /* If we use usec TS resolution,
+ * then expect the remote peer to use the same resolution.
+ */
+ if (tcp_sk(sk)->tcp_usec_ts)
+ return inet_csk(sk)->icsk_rto * (USEC_PER_SEC / HZ);
+
+ /* RFC 7323 recommends a TSval clock between 1ms and 1sec.
+ * We know that some OS (including old linux) can use 1200 Hz.
+ */
+ return inet_csk(sk)->icsk_rto * 1200 / HZ;
+}
+
static int tcp_disordered_ack(const struct sock *sk, const struct sk_buff *skb)
{
const struct tcp_sock *tp = tcp_sk(sk);
@@ -4371,7 +4392,7 @@ static int tcp_disordered_ack(const struct sock *sk, const struct sk_buff *skb)
u32 seq = TCP_SKB_CB(skb)->seq;
u32 ack = TCP_SKB_CB(skb)->ack_seq;
- return (/* 1. Pure ACK with correct sequence number. */
+ return /* 1. Pure ACK with correct sequence number. */
(th->ack && seq == TCP_SKB_CB(skb)->end_seq && seq == tp->rcv_nxt) &&
/* 2. ... and duplicate ACK. */
@@ -4381,7 +4402,8 @@ static int tcp_disordered_ack(const struct sock *sk, const struct sk_buff *skb)
!tcp_may_update_window(tp, ack, seq, ntohs(th->window) << tp->rx_opt.snd_wscale) &&
/* 4. ... and sits in replay window. */
- (s32)(tp->rx_opt.ts_recent - tp->rx_opt.rcv_tsval) <= (inet_csk(sk)->icsk_rto * 1024) / HZ);
+ (s32)(tp->rx_opt.ts_recent - tp->rx_opt.rcv_tsval) <=
+ tcp_tsval_replay(sk);
}
static inline bool tcp_paws_discard(const struct sock *sk,
@@ -7182,11 +7204,12 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
if (tcp_parse_auth_options(tcp_hdr(skb), NULL, &aoh))
goto drop_and_release; /* Invalid TCP options */
if (aoh) {
- tcp_rsk(req)->maclen = aoh->length - sizeof(struct tcp_ao_hdr);
+ tcp_rsk(req)->used_tcp_ao = true;
tcp_rsk(req)->ao_rcv_next = aoh->keyid;
tcp_rsk(req)->ao_keyid = aoh->rnext_keyid;
+
} else {
- tcp_rsk(req)->maclen = 0;
+ tcp_rsk(req)->used_tcp_ao = false;
}
#endif
tcp_rsk(req)->snt_isn = isn;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 5f693bbd578d..0c50c5a32b84 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -690,7 +690,7 @@ static bool tcp_v4_ao_sign_reset(const struct sock *sk, struct sk_buff *skb,
reply_options[0] = htonl((TCPOPT_AO << 24) | (tcp_ao_len(key) << 16) |
(aoh->rnext_keyid << 8) | keyid);
- arg->iov[0].iov_len += round_up(tcp_ao_len(key), 4);
+ arg->iov[0].iov_len += tcp_ao_len_aligned(key);
reply->doff = arg->iov[0].iov_len / 4;
if (tcp_ao_hash_hdr(AF_INET, (char *)&reply_options[1],
@@ -978,7 +978,7 @@ static void tcp_v4_send_ack(const struct sock *sk,
(tcp_ao_len(key->ao_key) << 16) |
(key->ao_key->sndid << 8) |
key->rcv_next);
- arg.iov[0].iov_len += round_up(tcp_ao_len(key->ao_key), 4);
+ arg.iov[0].iov_len += tcp_ao_len_aligned(key->ao_key);
rep.th.doff = arg.iov[0].iov_len / 4;
tcp_ao_hash_hdr(AF_INET, (char *)&rep.opt[offset],
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index a9807eeb311c..9e85f2a0bddd 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -615,7 +615,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
ao_key = treq->af_specific->ao_lookup(sk, req,
tcp_rsk(req)->ao_keyid, -1);
if (ao_key)
- newtp->tcp_header_len += tcp_ao_len(ao_key);
+ newtp->tcp_header_len += tcp_ao_len_aligned(ao_key);
#endif
if (skb->len >= TCP_MSS_DEFAULT + newtp->tcp_header_len)
newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index eb13a55d660c..e3167ad96567 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -825,7 +825,7 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
timestamps = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_timestamps);
if (tcp_key_is_ao(key)) {
opts->options |= OPTION_AO;
- remaining -= tcp_ao_len(key->ao_key);
+ remaining -= tcp_ao_len_aligned(key->ao_key);
}
}
@@ -915,7 +915,7 @@ static unsigned int tcp_synack_options(const struct sock *sk,
ireq->tstamp_ok &= !ireq->sack_ok;
} else if (tcp_key_is_ao(key)) {
opts->options |= OPTION_AO;
- remaining -= tcp_ao_len(key->ao_key);
+ remaining -= tcp_ao_len_aligned(key->ao_key);
ireq->tstamp_ok &= !ireq->sack_ok;
}
@@ -982,7 +982,7 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb
size += TCPOLEN_MD5SIG_ALIGNED;
} else if (tcp_key_is_ao(key)) {
opts->options |= OPTION_AO;
- size += tcp_ao_len(key->ao_key);
+ size += tcp_ao_len_aligned(key->ao_key);
}
if (likely(tp->rx_opt.tstamp_ok)) {
@@ -3293,7 +3293,13 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
if (skb_still_in_host_queue(sk, skb))
return -EBUSY;
+start:
if (before(TCP_SKB_CB(skb)->seq, tp->snd_una)) {
+ if (unlikely(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) {
+ TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_SYN;
+ TCP_SKB_CB(skb)->seq++;
+ goto start;
+ }
if (unlikely(before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))) {
WARN_ON_ONCE(1);
return -EINVAL;
@@ -3720,7 +3726,6 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
if (tcp_rsk_used_ao(req)) {
#ifdef CONFIG_TCP_AO
struct tcp_ao_key *ao_key = NULL;
- u8 maclen = tcp_rsk(req)->maclen;
u8 keyid = tcp_rsk(req)->ao_keyid;
ao_key = tcp_sk(sk)->af_specific->ao_lookup(sk, req_to_sk(req),
@@ -3730,13 +3735,11 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
* for another peer-matching key, but the peer has requested
* ao_keyid (RFC5925 RNextKeyID), so let's keep it simple here.
*/
- if (unlikely(!ao_key || tcp_ao_maclen(ao_key) != maclen)) {
- u8 key_maclen = ao_key ? tcp_ao_maclen(ao_key) : 0;
-
+ if (unlikely(!ao_key)) {
rcu_read_unlock();
kfree_skb(skb);
- net_warn_ratelimited("TCP-AO: the keyid %u with maclen %u|%u from SYN packet is not present - not sending SYNACK\n",
- keyid, maclen, key_maclen);
+ net_warn_ratelimited("TCP-AO: the keyid %u from SYN packet is not present - not sending SYNACK\n",
+ keyid);
return NULL;
}
key.ao_key = ao_key;
diff --git a/net/ipv4/tcp_sigpool.c b/net/ipv4/tcp_sigpool.c
index 55b310a722c7..8512cb09ebc0 100644
--- a/net/ipv4/tcp_sigpool.c
+++ b/net/ipv4/tcp_sigpool.c
@@ -162,9 +162,8 @@ int tcp_sigpool_alloc_ahash(const char *alg, size_t scratch_size)
if (strcmp(cpool[i].alg, alg))
continue;
- if (kref_read(&cpool[i].kref) > 0)
- kref_get(&cpool[i].kref);
- else
+ /* pairs with tcp_sigpool_release() */
+ if (!kref_get_unless_zero(&cpool[i].kref))
kref_init(&cpool[i].kref);
ret = i;
goto out;
diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c
index de3f2d31f510..dc41a22ee80e 100644
--- a/net/ipv4/udp_diag.c
+++ b/net/ipv4/udp_diag.c
@@ -296,5 +296,6 @@ static void __exit udp_diag_exit(void)
module_init(udp_diag_init);
module_exit(udp_diag_exit);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("UDP socket monitoring via SOCK_DIAG");
MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-17 /* AF_INET - IPPROTO_UDP */);
MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-136 /* AF_INET - IPPROTO_UDPLITE */);
generated by cgit (git 2.34.1) at 2024-05-21 15:41:33 +0000