summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/datagram.c8
-rw-r--r--net/ipv4/icmp.c3
-rw-r--r--net/ipv4/ip_tunnel.c6
-rw-r--r--net/ipv4/ipmr.c2
-rw-r--r--net/ipv4/route.c4
-rw-r--r--net/ipv4/tcp_bpf.c25
-rw-r--r--net/ipv4/tcp_input.c1
-rw-r--r--net/ipv4/tcp_ipv4.c2
-rw-r--r--net/ipv4/tcp_minisocks.c4
-rw-r--r--net/ipv4/tcp_output.c6
-rw-r--r--net/ipv4/udp.c60
11 files changed, 67 insertions, 54 deletions
diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c
index cc6d0bd7b0a9..4aca1f05edd3 100644
--- a/net/ipv4/datagram.c
+++ b/net/ipv4/datagram.c
@@ -61,15 +61,17 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len
err = -EACCES;
goto out;
}
+
+ /* Update addresses before rehashing */
+ inet->inet_daddr = fl4->daddr;
+ inet->inet_dport = usin->sin_port;
if (!inet->inet_saddr)
- inet->inet_saddr = fl4->saddr; /* Update source address */
+ inet->inet_saddr = fl4->saddr;
if (!inet->inet_rcv_saddr) {
inet->inet_rcv_saddr = fl4->saddr;
if (sk->sk_prot->rehash)
sk->sk_prot->rehash(sk);
}
- inet->inet_daddr = fl4->daddr;
- inet->inet_dport = usin->sin_port;
reuseport_has_conns_set(sk);
sk->sk_state = TCP_ESTABLISHED;
sk_set_txhash(sk);
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 4f088fa1c2f2..963a89ae9c26 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -517,6 +517,9 @@ static struct rtable *icmp_route_lookup(struct net *net, struct flowi4 *fl4,
if (!IS_ERR(dst)) {
if (rt != rt2)
return rt;
+ if (inet_addr_type_dev_table(net, route_lookup_dev,
+ fl4->daddr) == RTN_LOCAL)
+ return rt;
} else if (PTR_ERR(dst) == -EPERM) {
rt = NULL;
} else {
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 25505f9b724c..09b73acf037a 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -294,7 +294,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
ip_tunnel_init_flow(&fl4, iph->protocol, iph->daddr,
iph->saddr, tunnel->parms.o_key,
- iph->tos & INET_DSCP_MASK, dev_net(dev),
+ iph->tos & INET_DSCP_MASK, tunnel->net,
tunnel->parms.link, tunnel->fwmark, 0, 0);
rt = ip_route_output_key(tunnel->net, &fl4);
@@ -611,7 +611,7 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
}
ip_tunnel_init_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src,
tunnel_id_to_key32(key->tun_id),
- tos & INET_DSCP_MASK, dev_net(dev), 0, skb->mark,
+ tos & INET_DSCP_MASK, tunnel->net, 0, skb->mark,
skb_get_hash(skb), key->flow_flags);
if (!tunnel_hlen)
@@ -774,7 +774,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
ip_tunnel_init_flow(&fl4, protocol, dst, tnl_params->saddr,
tunnel->parms.o_key, tos & INET_DSCP_MASK,
- dev_net(dev), READ_ONCE(tunnel->parms.link),
+ tunnel->net, READ_ONCE(tunnel->parms.link),
tunnel->fwmark, skb_get_hash(skb), 0);
if (ip_tunnel_encap(skb, &tunnel->encap, &protocol, &fl4) < 0)
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index c5b8ec5c0a8c..99d8faa508e5 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -122,7 +122,7 @@ static void ipmr_expire_process(struct timer_list *t);
static bool ipmr_can_free_table(struct net *net)
{
- return !check_net(net) || !net->ipv4.mr_rules_ops;
+ return !check_net(net) || !net_initialized(net);
}
static struct mr_table *ipmr_mr_table_iter(struct net *net,
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index e5603e84b20d..e1564b95fab0 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2445,6 +2445,7 @@ martian_destination:
net_warn_ratelimited("martian destination %pI4 from %pI4, dev %s\n",
&daddr, &saddr, dev->name);
#endif
+ goto out;
e_nobufs:
reason = SKB_DROP_REASON_NOMEM;
@@ -2478,7 +2479,8 @@ ip_route_input_rcu(struct sk_buff *skb, __be32 daddr, __be32 saddr,
int our = 0;
if (!in_dev)
- return -EINVAL;
+ return reason;
+
our = ip_check_mc_rcu(in_dev, daddr, saddr,
ip_hdr(skb)->protocol);
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 370993c03d31..47f65b1b70ca 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -49,13 +49,14 @@ static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock,
sge = sk_msg_elem(msg, i);
size = (apply && apply_bytes < sge->length) ?
apply_bytes : sge->length;
- if (!sk_wmem_schedule(sk, size)) {
+ if (!__sk_rmem_schedule(sk, size, false)) {
if (!copied)
ret = -ENOMEM;
break;
}
sk_mem_charge(sk, size);
+ atomic_add(size, &sk->sk_rmem_alloc);
sk_msg_xfer(tmp, msg, i, size);
copied += size;
if (sge->length)
@@ -74,7 +75,8 @@ static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock,
if (!ret) {
msg->sg.start = i;
- sk_psock_queue_msg(psock, tmp);
+ if (!sk_psock_queue_msg(psock, tmp))
+ atomic_sub(copied, &sk->sk_rmem_alloc);
sk_psock_data_ready(sk, psock);
} else {
sk_msg_free(sk, tmp);
@@ -441,7 +443,6 @@ more_data:
cork = true;
psock->cork = NULL;
}
- sk_msg_return(sk, msg, tosend);
release_sock(sk);
origsize = msg->sg.size;
@@ -453,8 +454,9 @@ more_data:
sock_put(sk_redir);
lock_sock(sk);
+ sk_mem_uncharge(sk, sent);
if (unlikely(ret < 0)) {
- int free = sk_msg_free_nocharge(sk, msg);
+ int free = sk_msg_free(sk, msg);
if (!cork)
*copied -= free;
@@ -468,7 +470,7 @@ more_data:
break;
case __SK_DROP:
default:
- sk_msg_free_partial(sk, msg, tosend);
+ sk_msg_free(sk, msg);
sk_msg_apply_bytes(psock, tosend);
*copied -= (tosend + delta);
return -EACCES;
@@ -484,11 +486,8 @@ more_data:
}
if (msg &&
msg->sg.data[msg->sg.start].page_link &&
- msg->sg.data[msg->sg.start].length) {
- if (eval == __SK_REDIRECT)
- sk_mem_charge(sk, tosend - sent);
+ msg->sg.data[msg->sg.start].length)
goto more_data;
- }
}
return ret;
}
@@ -496,7 +495,7 @@ more_data:
static int tcp_bpf_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
{
struct sk_msg tmp, *msg_tx = NULL;
- int copied = 0, err = 0;
+ int copied = 0, err = 0, ret = 0;
struct sk_psock *psock;
long timeo;
int flags;
@@ -539,14 +538,14 @@ static int tcp_bpf_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
copy = msg_tx->sg.size - osize;
}
- err = sk_msg_memcopy_from_iter(sk, &msg->msg_iter, msg_tx,
+ ret = sk_msg_memcopy_from_iter(sk, &msg->msg_iter, msg_tx,
copy);
- if (err < 0) {
+ if (ret < 0) {
sk_msg_trim(sk, msg_tx, osize);
goto out_err;
}
- copied += copy;
+ copied += ret;
if (psock->cork_bytes) {
if (size > psock->cork_bytes)
psock->cork_bytes = 0;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 5bdf13ac26ef..4811727b8a02 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -7328,6 +7328,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
if (unlikely(!inet_csk_reqsk_queue_hash_add(sk, req,
req->timeout))) {
reqsk_free(req);
+ dst_release(dst);
return 0;
}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index a38c8b1f44db..c26f6c4b7bb4 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -896,7 +896,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb,
sock_net_set(ctl_sk, net);
if (sk) {
ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ?
- inet_twsk(sk)->tw_mark : sk->sk_mark;
+ inet_twsk(sk)->tw_mark : READ_ONCE(sk->sk_mark);
ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ?
inet_twsk(sk)->tw_priority : READ_ONCE(sk->sk_priority);
transmit_time = tcp_transmit_time(sk);
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index bb1fe1ba867a..7121d8573928 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -326,6 +326,10 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
tcptw->tw_last_oow_ack_time = 0;
tcptw->tw_tx_delay = tp->tcp_tx_delay;
tw->tw_txhash = sk->sk_txhash;
+ tw->tw_tx_queue_mapping = sk->sk_tx_queue_mapping;
+#ifdef CONFIG_SOCK_RX_QUEUE_MAPPING
+ tw->tw_rx_queue_mapping = sk->sk_rx_queue_mapping;
+#endif
#if IS_ENABLED(CONFIG_IPV6)
if (tw->tw_family == PF_INET6) {
struct ipv6_pinfo *np = inet6_sk(sk);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 5485a70b5fe5..0e5b9a654254 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -883,8 +883,10 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
unsigned int size;
if (mptcp_syn_options(sk, skb, &size, &opts->mptcp)) {
- opts->options |= OPTION_MPTCP;
- remaining -= size;
+ if (remaining >= size) {
+ opts->options |= OPTION_MPTCP;
+ remaining -= size;
+ }
}
}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 6a01905d379f..86d282618515 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -533,7 +533,7 @@ begin:
return NULL;
}
-/* In hash4, rehash can happen in connect(), where hash4_cnt keeps unchanged. */
+/* udp_rehash4() only checks hslot4, and hash4_cnt is not processed. */
static void udp_rehash4(struct udp_table *udptable, struct sock *sk,
u16 newhash4)
{
@@ -582,15 +582,13 @@ void udp_lib_hash4(struct sock *sk, u16 hash)
struct net *net = sock_net(sk);
struct udp_table *udptable;
- /* Connected udp socket can re-connect to another remote address,
- * so rehash4 is needed.
+ /* Connected udp socket can re-connect to another remote address, which
+ * will be handled by rehash. Thus no need to redo hash4 here.
*/
- udptable = net->ipv4.udp_table;
- if (udp_hashed4(sk)) {
- udp_rehash4(udptable, sk, hash);
+ if (udp_hashed4(sk))
return;
- }
+ udptable = net->ipv4.udp_table;
hslot = udp_hashslot(udptable, net, udp_sk(sk)->udp_port_hash);
hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash);
hslot4 = udp_hashslot4(udptable, hash);
@@ -1674,7 +1672,6 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb)
struct sk_buff_head *list = &sk->sk_receive_queue;
int rmem, err = -ENOMEM;
spinlock_t *busy = NULL;
- bool becomes_readable;
int size, rcvbuf;
/* Immediately drop when the receive queue is full.
@@ -1715,19 +1712,12 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb)
*/
sock_skb_set_dropcount(sk, skb);
- becomes_readable = skb_queue_empty(list);
__skb_queue_tail(list, skb);
spin_unlock(&list->lock);
- if (!sock_flag(sk, SOCK_DEAD)) {
- if (becomes_readable ||
- sk->sk_data_ready != sock_def_readable ||
- READ_ONCE(sk->sk_peek_off) >= 0)
- INDIRECT_CALL_1(sk->sk_data_ready,
- sock_def_readable, sk);
- else
- sk_wake_async_rcu(sk, SOCK_WAKE_WAITD, POLL_IN);
- }
+ if (!sock_flag(sk, SOCK_DEAD))
+ INDIRECT_CALL_1(sk->sk_data_ready, sock_def_readable, sk);
+
busylock_release(busy);
return 0;
@@ -2181,14 +2171,14 @@ void udp_lib_rehash(struct sock *sk, u16 newhash, u16 newhash4)
struct udp_table *udptable = udp_get_table_prot(sk);
struct udp_hslot *hslot, *hslot2, *nhslot2;
+ hslot = udp_hashslot(udptable, sock_net(sk),
+ udp_sk(sk)->udp_port_hash);
hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash);
nhslot2 = udp_hashslot2(udptable, newhash);
udp_sk(sk)->udp_portaddr_hash = newhash;
if (hslot2 != nhslot2 ||
rcu_access_pointer(sk->sk_reuseport_cb)) {
- hslot = udp_hashslot(udptable, sock_net(sk),
- udp_sk(sk)->udp_port_hash);
/* we must lock primary chain too */
spin_lock_bh(&hslot->lock);
if (rcu_access_pointer(sk->sk_reuseport_cb))
@@ -2207,19 +2197,29 @@ void udp_lib_rehash(struct sock *sk, u16 newhash, u16 newhash4)
spin_unlock(&nhslot2->lock);
}
- if (udp_hashed4(sk)) {
- udp_rehash4(udptable, sk, newhash4);
+ spin_unlock_bh(&hslot->lock);
+ }
- if (hslot2 != nhslot2) {
- spin_lock(&hslot2->lock);
- udp_hash4_dec(hslot2);
- spin_unlock(&hslot2->lock);
+ /* Now process hash4 if necessary:
+ * (1) update hslot4;
+ * (2) update hslot2->hash4_cnt.
+ * Note that hslot2/hslot4 should be checked separately, as
+ * either of them may change with the other unchanged.
+ */
+ if (udp_hashed4(sk)) {
+ spin_lock_bh(&hslot->lock);
- spin_lock(&nhslot2->lock);
- udp_hash4_inc(nhslot2);
- spin_unlock(&nhslot2->lock);
- }
+ udp_rehash4(udptable, sk, newhash4);
+ if (hslot2 != nhslot2) {
+ spin_lock(&hslot2->lock);
+ udp_hash4_dec(hslot2);
+ spin_unlock(&hslot2->lock);
+
+ spin_lock(&nhslot2->lock);
+ udp_hash4_inc(nhslot2);
+ spin_unlock(&nhslot2->lock);
}
+
spin_unlock_bh(&hslot->lock);
}
}
generated by cgit v1.2.3 (git 2.51.0) at 2025-09-18 09:12:22 +0000