summaryrefslogtreecommitdiffstats
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/af_inet.c4
-rw-r--r--net/ipv4/esp4_offload.c3
-rw-r--r--net/ipv4/inet_connection_sock.c1
-rw-r--r--net/ipv4/ip_gre.c6
-rw-r--r--net/ipv4/ip_output.c16
-rw-r--r--net/ipv4/ip_sockglue.c12
-rw-r--r--net/ipv4/netfilter/nft_dup_ipv4.c18
-rw-r--r--net/ipv4/raw.c5
-rw-r--r--net/ipv4/tcp.c36
-rw-r--r--net/ipv4/tcp_input.c4
-rw-r--r--net/ipv4/udplite.c2
11 files changed, 76 insertions, 31 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 4b26ae525..7c902a1ef 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -578,6 +578,7 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias)
add_wait_queue(sk_sleep(sk), &wait);
sk->sk_write_pending += writebias;
+ sk->sk_wait_pending++;
/* Basic assumption: if someone sets sk->sk_err, he _must_
* change state of the socket from TCP_SYN_*.
@@ -593,6 +594,7 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias)
}
remove_wait_queue(sk_sleep(sk), &wait);
sk->sk_write_pending -= writebias;
+ sk->sk_wait_pending--;
return timeo;
}
@@ -865,7 +867,7 @@ int inet_shutdown(struct socket *sock, int how)
EPOLLHUP, even on eg. unconnected UDP sockets -- RR */
/* fall through */
default:
- sk->sk_shutdown |= how;
+ WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | how);
if (sk->sk_prot->shutdown)
sk->sk_prot->shutdown(sk, how);
break;
diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index 58834a10c..93045373e 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -237,6 +237,9 @@ static int esp_xmit(struct xfrm_state *x, struct sk_buff *skb, netdev_features_
secpath_reset(skb);
+ if (skb_needs_linearize(skb, skb->dev->features) &&
+ __skb_linearize(skb))
+ return -ENOMEM;
return 0;
}
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 0f9085220..7392a744c 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -826,6 +826,7 @@ struct sock *inet_csk_clone_lock(const struct sock *sk,
if (newsk) {
struct inet_connection_sock *newicsk = inet_csk(newsk);
+ newsk->sk_wait_pending = 0;
inet_sk_set_state(newsk, TCP_SYN_RECV);
newicsk->icsk_bind_hash = NULL;
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 898753328..e16373640 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -440,7 +440,7 @@ static void __gre_xmit(struct sk_buff *skb, struct net_device *dev,
/* Push GRE header. */
gre_build_header(skb, tunnel->tun_hlen,
flags, proto, tunnel->parms.o_key,
- (flags & TUNNEL_SEQ) ? htonl(tunnel->o_seqno++) : 0);
+ (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0);
ip_tunnel_xmit(skb, dev, tnl_params, tnl_params->protocol);
}
@@ -546,7 +546,7 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev,
(TUNNEL_CSUM | TUNNEL_KEY | TUNNEL_SEQ);
gre_build_header(skb, tunnel_hlen, flags, proto,
tunnel_id_to_key32(tun_info->key.tun_id),
- (flags & TUNNEL_SEQ) ? htonl(tunnel->o_seqno++) : 0);
+ (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0);
df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0;
@@ -635,7 +635,7 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev)
}
gre_build_header(skb, 8, TUNNEL_SEQ,
- proto, 0, htonl(tunnel->o_seqno++));
+ proto, 0, htonl(atomic_fetch_inc(&tunnel->o_seqno)));
df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 06a981676..92fa11e75 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1443,9 +1443,19 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
cork->dst = NULL;
skb_dst_set(skb, &rt->dst);
- if (iph->protocol == IPPROTO_ICMP)
- icmp_out_count(net, ((struct icmphdr *)
- skb_transport_header(skb))->type);
+ if (iph->protocol == IPPROTO_ICMP) {
+ u8 icmp_type;
+
+ /* For such sockets, transhdrlen is zero when do ip_append_data(),
+ * so icmphdr does not in skb linear region and can not get icmp_type
+ * by icmp_hdr(skb)->type.
+ */
+ if (sk->sk_type == SOCK_RAW && !inet_sk(sk)->hdrincl)
+ icmp_type = fl4->fl4_icmp_type;
+ else
+ icmp_type = icmp_hdr(skb)->type;
+ icmp_out_count(net, icmp_type);
+ }
ip_cork_release(cork);
out:
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 82f341e84..fbf39077f 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -316,7 +316,14 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc,
ipc->tos = val;
ipc->priority = rt_tos2priority(ipc->tos);
break;
-
+ case IP_PROTOCOL:
+ if (cmsg->cmsg_len != CMSG_LEN(sizeof(int)))
+ return -EINVAL;
+ val = *(int *)CMSG_DATA(cmsg);
+ if (val < 1 || val > 255)
+ return -EINVAL;
+ ipc->protocol = val;
+ break;
default:
return -EINVAL;
}
@@ -1522,6 +1529,9 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname,
case IP_MINTTL:
val = inet->min_ttl;
break;
+ case IP_PROTOCOL:
+ val = inet_sk(sk)->inet_num;
+ break;
default:
release_sock(sk);
return -ENOPROTOOPT;
diff --git a/net/ipv4/netfilter/nft_dup_ipv4.c b/net/ipv4/netfilter/nft_dup_ipv4.c
index 0af3d8df7..157bca240 100644
--- a/net/ipv4/netfilter/nft_dup_ipv4.c
+++ b/net/ipv4/netfilter/nft_dup_ipv4.c
@@ -16,8 +16,8 @@
#include <net/netfilter/ipv4/nf_dup_ipv4.h>
struct nft_dup_ipv4 {
- enum nft_registers sreg_addr:8;
- enum nft_registers sreg_dev:8;
+ u8 sreg_addr;
+ u8 sreg_dev;
};
static void nft_dup_ipv4_eval(const struct nft_expr *expr,
@@ -43,16 +43,16 @@ static int nft_dup_ipv4_init(const struct nft_ctx *ctx,
if (tb[NFTA_DUP_SREG_ADDR] == NULL)
return -EINVAL;
- priv->sreg_addr = nft_parse_register(tb[NFTA_DUP_SREG_ADDR]);
- err = nft_validate_register_load(priv->sreg_addr, sizeof(struct in_addr));
+ err = nft_parse_register_load(tb[NFTA_DUP_SREG_ADDR], &priv->sreg_addr,
+ sizeof(struct in_addr));
if (err < 0)
return err;
- if (tb[NFTA_DUP_SREG_DEV] != NULL) {
- priv->sreg_dev = nft_parse_register(tb[NFTA_DUP_SREG_DEV]);
- return nft_validate_register_load(priv->sreg_dev, sizeof(int));
- }
- return 0;
+ if (tb[NFTA_DUP_SREG_DEV])
+ err = nft_parse_register_load(tb[NFTA_DUP_SREG_DEV],
+ &priv->sreg_dev, sizeof(int));
+
+ return err;
}
static int nft_dup_ipv4_dump(struct sk_buff *skb, const struct nft_expr *expr)
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 654f586fc..8ad120c07 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -563,6 +563,9 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
}
ipcm_init_sk(&ipc, inet);
+ /* Keep backward compat */
+ if (hdrincl)
+ ipc.protocol = IPPROTO_RAW;
if (msg->msg_controllen) {
err = ip_cmsg_send(sk, msg, &ipc, false);
@@ -630,7 +633,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos,
RT_SCOPE_UNIVERSE,
- hdrincl ? IPPROTO_RAW : sk->sk_protocol,
+ hdrincl ? ipc.protocol : sk->sk_protocol,
inet_sk_flowi_flags(sk) |
(hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
daddr, saddr, 0, 0, sk->sk_uid);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 68f89fe7f..cb96775fc 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -515,6 +515,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
__poll_t mask;
struct sock *sk = sock->sk;
const struct tcp_sock *tp = tcp_sk(sk);
+ u8 shutdown;
int state;
sock_poll_wait(file, sock, wait);
@@ -557,9 +558,10 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
* NOTE. Check for TCP_CLOSE is added. The goal is to prevent
* blocking on fresh not-connected or disconnected socket. --ANK
*/
- if (sk->sk_shutdown == SHUTDOWN_MASK || state == TCP_CLOSE)
+ shutdown = READ_ONCE(sk->sk_shutdown);
+ if (shutdown == SHUTDOWN_MASK || state == TCP_CLOSE)
mask |= EPOLLHUP;
- if (sk->sk_shutdown & RCV_SHUTDOWN)
+ if (shutdown & RCV_SHUTDOWN)
mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP;
/* Connected or passive Fast Open socket? */
@@ -575,8 +577,8 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
if (tcp_stream_is_readable(tp, target, sk))
mask |= EPOLLIN | EPOLLRDNORM;
- if (!(sk->sk_shutdown & SEND_SHUTDOWN)) {
- if (sk_stream_is_writeable(sk)) {
+ if (!(shutdown & SEND_SHUTDOWN)) {
+ if (__sk_stream_is_writeable(sk, 1)) {
mask |= EPOLLOUT | EPOLLWRNORM;
} else { /* send SIGIO later */
sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
@@ -588,7 +590,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
* pairs with the input side.
*/
smp_mb__after_atomic();
- if (sk_stream_is_writeable(sk))
+ if (__sk_stream_is_writeable(sk, 1))
mask |= EPOLLOUT | EPOLLWRNORM;
}
} else
@@ -2338,14 +2340,13 @@ bool tcp_check_oom(struct sock *sk, int shift)
return too_many_orphans || out_of_socket_memory;
}
-void tcp_close(struct sock *sk, long timeout)
+void __tcp_close(struct sock *sk, long timeout)
{
struct sk_buff *skb;
int data_was_unread = 0;
int state;
- lock_sock(sk);
- sk->sk_shutdown = SHUTDOWN_MASK;
+ WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK);
if (sk->sk_state == TCP_LISTEN) {
tcp_set_state(sk, TCP_CLOSE);
@@ -2505,6 +2506,12 @@ adjudge_to_death:
out:
bh_unlock_sock(sk);
local_bh_enable();
+}
+
+void tcp_close(struct sock *sk, long timeout)
+{
+ lock_sock(sk);
+ __tcp_close(sk, timeout);
release_sock(sk);
sock_put(sk);
}
@@ -2561,6 +2568,12 @@ int tcp_disconnect(struct sock *sk, int flags)
int old_state = sk->sk_state;
u32 seq;
+ /* Deny disconnect if other threads are blocked in sk_wait_event()
+ * or inet_wait_for_connect().
+ */
+ if (sk->sk_wait_pending)
+ return -EBUSY;
+
if (old_state != TCP_CLOSE)
tcp_set_state(sk, TCP_CLOSE);
@@ -2593,7 +2606,7 @@ int tcp_disconnect(struct sock *sk, int flags)
if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
inet_reset_saddr(sk);
- sk->sk_shutdown = 0;
+ WRITE_ONCE(sk->sk_shutdown, 0);
sock_reset_flag(sk, SOCK_DONE);
tp->srtt_us = 0;
tp->rcv_rtt_last_tsecr = 0;
@@ -3363,7 +3376,8 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
switch (optname) {
case TCP_MAXSEG:
val = tp->mss_cache;
- if (!val && ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)))
+ if (tp->rx_opt.user_mss &&
+ ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)))
val = tp->rx_opt.user_mss;
if (tp->repair)
val = tp->rx_opt.mss_clamp;
@@ -3802,7 +3816,7 @@ void tcp_done(struct sock *sk)
if (req)
reqsk_fastopen_remove(sk, req, false);
- sk->sk_shutdown = SHUTDOWN_MASK;
+ WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK);
if (!sock_flag(sk, SOCK_DEAD))
sk->sk_state_change(sk);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 117167806..bd921fa7b 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4130,7 +4130,7 @@ void tcp_fin(struct sock *sk)
inet_csk_schedule_ack(sk);
- sk->sk_shutdown |= RCV_SHUTDOWN;
+ WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | RCV_SHUTDOWN);
sock_set_flag(sk, SOCK_DONE);
switch (sk->sk_state) {
@@ -6209,7 +6209,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
break;
tcp_set_state(sk, TCP_FIN_WAIT2);
- sk->sk_shutdown |= SEND_SHUTDOWN;
+ WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | SEND_SHUTDOWN);
sk_dst_confirm(sk);
diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c
index 6beab353b..27173549b 100644
--- a/net/ipv4/udplite.c
+++ b/net/ipv4/udplite.c
@@ -64,6 +64,8 @@ struct proto udplite_prot = {
.get_port = udp_v4_get_port,
.memory_allocated = &udp_memory_allocated,
.sysctl_mem = sysctl_udp_mem,
+ .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_udp_wmem_min),
+ .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_udp_rmem_min),
.obj_size = sizeof(struct udp_sock),
.h.udp_table = &udplite_table,
#ifdef CONFIG_COMPAT
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-28 08:17:35 +0000