summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/af_inet.c2
-rw-r--r--net/ipv4/inet_connection_sock.c1
-rw-r--r--net/ipv4/ip_sockglue.c12
-rw-r--r--net/ipv4/raw.c5
-rw-r--r--net/ipv4/sysctl_net_ipv4.c8
-rw-r--r--net/ipv4/tcp.c20
-rw-r--r--net/ipv4/tcp_bpf.c79
-rw-r--r--net/ipv4/tcp_input.c2
-rw-r--r--net/ipv4/tcp_ipv4.c5
-rw-r--r--net/ipv4/tcp_offload.c19
-rw-r--r--net/ipv4/tcp_timer.c16
-rw-r--r--net/ipv4/udp.c7
-rw-r--r--net/ipv4/udplite.c4
13 files changed, 141 insertions, 39 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index c4aab3aacbd8..4a76ebf793b8 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -586,6 +586,7 @@ 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_*.
@@ -601,6 +602,7 @@ 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;
}
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 65ad4251f6fd..1386787eaf1a 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -1142,6 +1142,7 @@ 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;
newicsk->icsk_bind2_hash = NULL;
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index b511ff0adc0a..8e97d8d4cc9d 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -317,7 +317,14 @@ 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;
}
@@ -1761,6 +1768,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
case IP_LOCAL_PORT_RANGE:
val = inet->local_port_range.hi << 16 | inet->local_port_range.lo;
break;
+ case IP_PROTOCOL:
+ val = inet_sk(sk)->inet_num;
+ break;
default:
sockopt_release_sock(sk);
return -ENOPROTOOPT;
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index ff712bf2a98d..eadf1c9ef7e4 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -532,6 +532,9 @@ 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);
@@ -599,7 +602,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
flowi4_init_output(&fl4, ipc.oif, ipc.sockc.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/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 40fe70fc2015..88dfe51e68f3 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -34,8 +34,8 @@ static int ip_ttl_min = 1;
static int ip_ttl_max = 255;
static int tcp_syn_retries_min = 1;
static int tcp_syn_retries_max = MAX_TCP_SYNCNT;
-static int ip_ping_group_range_min[] = { 0, 0 };
-static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX };
+static unsigned long ip_ping_group_range_min[] = { 0, 0 };
+static unsigned long ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX };
static u32 u32_max_div_HZ = UINT_MAX / HZ;
static int one_day_secs = 24 * 3600;
static u32 fib_multipath_hash_fields_all_mask __maybe_unused =
@@ -165,7 +165,7 @@ static int ipv4_ping_group_range(struct ctl_table *table, int write,
{
struct user_namespace *user_ns = current_user_ns();
int ret;
- gid_t urange[2];
+ unsigned long urange[2];
kgid_t low, high;
struct ctl_table tmp = {
.data = &urange,
@@ -178,7 +178,7 @@ static int ipv4_ping_group_range(struct ctl_table *table, int write,
inet_get_ping_group_range_table(table, &low, &high);
urange[0] = from_kgid_munged(user_ns, low);
urange[1] = from_kgid_munged(user_ns, high);
- ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
+ ret = proc_doulongvec_minmax(&tmp, write, buffer, lenp, ppos);
if (write && ret == 0) {
low = make_kgid(user_ns, urange[0]);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 4d6392c16b7a..8d20d9221238 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1571,7 +1571,7 @@ static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len)
* calculation of whether or not we must ACK for the sake of
* a window update.
*/
-static void __tcp_cleanup_rbuf(struct sock *sk, int copied)
+void __tcp_cleanup_rbuf(struct sock *sk, int copied)
{
struct tcp_sock *tp = tcp_sk(sk);
bool time_to_ack = false;
@@ -1773,7 +1773,6 @@ int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
WARN_ON_ONCE(!skb_set_owner_sk_safe(skb, sk));
tcp_flags = TCP_SKB_CB(skb)->tcp_flags;
used = recv_actor(sk, skb);
- consume_skb(skb);
if (used < 0) {
if (!copied)
copied = used;
@@ -1787,14 +1786,6 @@ int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
break;
}
}
- WRITE_ONCE(tp->copied_seq, seq);
-
- tcp_rcv_space_adjust(sk);
-
- /* Clean up data we have read: This will do ACK frames. */
- if (copied > 0)
- __tcp_cleanup_rbuf(sk, copied);
-
return copied;
}
EXPORT_SYMBOL(tcp_read_skb);
@@ -3090,6 +3081,12 @@ 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);
@@ -4081,7 +4078,8 @@ 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;
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 2e9547467edb..5f93918c063c 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -11,6 +11,24 @@
#include <net/inet_common.h>
#include <net/tls.h>
+void tcp_eat_skb(struct sock *sk, struct sk_buff *skb)
+{
+ struct tcp_sock *tcp;
+ int copied;
+
+ if (!skb || !skb->len || !sk_is_tcp(sk))
+ return;
+
+ if (skb_bpf_strparser(skb))
+ return;
+
+ tcp = tcp_sk(sk);
+ copied = tcp->copied_seq + skb->len;
+ WRITE_ONCE(tcp->copied_seq, copied);
+ tcp_rcv_space_adjust(sk);
+ __tcp_cleanup_rbuf(sk, skb->len);
+}
+
static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock,
struct sk_msg *msg, u32 apply_bytes, int flags)
{
@@ -174,14 +192,34 @@ static int tcp_msg_wait_data(struct sock *sk, struct sk_psock *psock,
return ret;
}
+static bool is_next_msg_fin(struct sk_psock *psock)
+{
+ struct scatterlist *sge;
+ struct sk_msg *msg_rx;
+ int i;
+
+ msg_rx = sk_psock_peek_msg(psock);
+ i = msg_rx->sg.start;
+ sge = sk_msg_elem(msg_rx, i);
+ if (!sge->length) {
+ struct sk_buff *skb = msg_rx->skb;
+
+ if (skb && TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
+ return true;
+ }
+ return false;
+}
+
static int tcp_bpf_recvmsg_parser(struct sock *sk,
struct msghdr *msg,
size_t len,
int flags,
int *addr_len)
{
+ struct tcp_sock *tcp = tcp_sk(sk);
+ u32 seq = tcp->copied_seq;
struct sk_psock *psock;
- int copied;
+ int copied = 0;
if (unlikely(flags & MSG_ERRQUEUE))
return inet_recv_error(sk, msg, len, addr_len);
@@ -194,8 +232,43 @@ static int tcp_bpf_recvmsg_parser(struct sock *sk,
return tcp_recvmsg(sk, msg, len, flags, addr_len);
lock_sock(sk);
+
+ /* We may have received data on the sk_receive_queue pre-accept and
+ * then we can not use read_skb in this context because we haven't
+ * assigned a sk_socket yet so have no link to the ops. The work-around
+ * is to check the sk_receive_queue and in these cases read skbs off
+ * queue again. The read_skb hook is not running at this point because
+ * of lock_sock so we avoid having multiple runners in read_skb.
+ */
+ if (unlikely(!skb_queue_empty(&sk->sk_receive_queue))) {
+ tcp_data_ready(sk);
+ /* This handles the ENOMEM errors if we both receive data
+ * pre accept and are already under memory pressure. At least
+ * let user know to retry.
+ */
+ if (unlikely(!skb_queue_empty(&sk->sk_receive_queue))) {
+ copied = -EAGAIN;
+ goto out;
+ }
+ }
+
msg_bytes_ready:
copied = sk_msg_recvmsg(sk, psock, msg, len, flags);
+ /* The typical case for EFAULT is the socket was gracefully
+ * shutdown with a FIN pkt. So check here the other case is
+ * some error on copy_page_to_iter which would be unexpected.
+ * On fin return correct return code to zero.
+ */
+ if (copied == -EFAULT) {
+ bool is_fin = is_next_msg_fin(psock);
+
+ if (is_fin) {
+ copied = 0;
+ seq++;
+ goto out;
+ }
+ }
+ seq += copied;
if (!copied) {
long timeo;
int data;
@@ -233,6 +306,10 @@ msg_bytes_ready:
copied = -EAGAIN;
}
out:
+ WRITE_ONCE(tcp->copied_seq, seq);
+ tcp_rcv_space_adjust(sk);
+ if (copied > 0)
+ __tcp_cleanup_rbuf(sk, copied);
release_sock(sk);
sk_psock_put(sk, psock);
return copied;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 61b6710f337a..bf8b22218dd4 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4530,7 +4530,7 @@ static void tcp_sack_maybe_coalesce(struct tcp_sock *tp)
}
}
-static void tcp_sack_compress_send_ack(struct sock *sk)
+void tcp_sack_compress_send_ack(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 39bda2b1066e..06d2573685ca 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -829,6 +829,9 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
inet_twsk(sk)->tw_priority : sk->sk_priority;
transmit_time = tcp_transmit_time(sk);
xfrm_sk_clone_policy(ctl_sk, sk);
+ } else {
+ ctl_sk->sk_mark = 0;
+ ctl_sk->sk_priority = 0;
}
ip_send_unicast_reply(ctl_sk,
skb, &TCP_SKB_CB(skb)->header.h4.opt,
@@ -836,7 +839,6 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
&arg, arg.iov[0].iov_len,
transmit_time);
- ctl_sk->sk_mark = 0;
xfrm_sk_free_policy(ctl_sk);
sock_net_set(ctl_sk, &init_net);
__TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
@@ -935,7 +937,6 @@ static void tcp_v4_send_ack(const struct sock *sk,
&arg, arg.iov[0].iov_len,
transmit_time);
- ctl_sk->sk_mark = 0;
sock_net_set(ctl_sk, &init_net);
__TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
local_bh_enable();
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 45dda7889387..4851211aa60d 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -60,12 +60,12 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
struct tcphdr *th;
unsigned int thlen;
unsigned int seq;
- __be32 delta;
unsigned int oldlen;
unsigned int mss;
struct sk_buff *gso_skb = skb;
__sum16 newcheck;
bool ooo_okay, copy_destructor;
+ __wsum delta;
th = tcp_hdr(skb);
thlen = th->doff * 4;
@@ -75,7 +75,7 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
if (!pskb_may_pull(skb, thlen))
goto out;
- oldlen = (u16)~skb->len;
+ oldlen = ~skb->len;
__skb_pull(skb, thlen);
mss = skb_shinfo(skb)->gso_size;
@@ -110,7 +110,7 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
if (skb_is_gso(segs))
mss *= skb_shinfo(segs)->gso_segs;
- delta = htonl(oldlen + (thlen + mss));
+ delta = (__force __wsum)htonl(oldlen + thlen + mss);
skb = segs;
th = tcp_hdr(skb);
@@ -119,8 +119,7 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
if (unlikely(skb_shinfo(gso_skb)->tx_flags & SKBTX_SW_TSTAMP))
tcp_gso_tstamp(segs, skb_shinfo(gso_skb)->tskey, seq, mss);
- newcheck = ~csum_fold((__force __wsum)((__force u32)th->check +
- (__force u32)delta));
+ newcheck = ~csum_fold(csum_add(csum_unfold(th->check), delta));
while (skb->next) {
th->fin = th->psh = 0;
@@ -165,11 +164,11 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
WARN_ON_ONCE(refcount_sub_and_test(-delta, &skb->sk->sk_wmem_alloc));
}
- delta = htonl(oldlen + (skb_tail_pointer(skb) -
- skb_transport_header(skb)) +
- skb->data_len);
- th->check = ~csum_fold((__force __wsum)((__force u32)th->check +
- (__force u32)delta));
+ delta = (__force __wsum)htonl(oldlen +
+ (skb_tail_pointer(skb) -
+ skb_transport_header(skb)) +
+ skb->data_len);
+ th->check = ~csum_fold(csum_add(csum_unfold(th->check), delta));
if (skb->ip_summed == CHECKSUM_PARTIAL)
gso_reset_checksum(skb, ~th->check);
else
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index b839c2f91292..39eb947fe392 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -290,9 +290,19 @@ static int tcp_write_timeout(struct sock *sk)
void tcp_delack_timer_handler(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
+ struct tcp_sock *tp = tcp_sk(sk);
- if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) ||
- !(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
+ if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))
+ return;
+
+ /* Handling the sack compression case */
+ if (tp->compressed_ack) {
+ tcp_mstamp_refresh(tp);
+ tcp_sack_compress_send_ack(sk);
+ return;
+ }
+
+ if (!(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
return;
if (time_after(icsk->icsk_ack.timeout, jiffies)) {
@@ -312,7 +322,7 @@ void tcp_delack_timer_handler(struct sock *sk)
inet_csk_exit_pingpong_mode(sk);
icsk->icsk_ack.ato = TCP_ATO_MIN;
}
- tcp_mstamp_refresh(tcp_sk(sk));
+ tcp_mstamp_refresh(tp);
tcp_send_ack(sk);
__NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKS);
}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index aa32afd871ee..9482def1f310 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1818,7 +1818,7 @@ EXPORT_SYMBOL(__skb_recv_udp);
int udp_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
{
struct sk_buff *skb;
- int err, copied;
+ int err;
try_again:
skb = skb_recv_udp(sk, MSG_DONTWAIT, &err);
@@ -1837,10 +1837,7 @@ try_again:
}
WARN_ON_ONCE(!skb_set_owner_sk_safe(skb, sk));
- copied = recv_actor(sk, skb);
- kfree_skb(skb);
-
- return copied;
+ return recv_actor(sk, skb);
}
EXPORT_SYMBOL(udp_read_skb);
diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c
index e0c9cc39b81e..143f93a12f25 100644
--- a/net/ipv4/udplite.c
+++ b/net/ipv4/udplite.c
@@ -22,6 +22,8 @@ static int udplite_sk_init(struct sock *sk)
{
udp_init_sock(sk);
udp_sk(sk)->pcflag = UDPLITE_BIT;
+ pr_warn_once("UDP-Lite is deprecated and scheduled to be removed in 2025, "
+ "please contact the netdev mailing list\n");
return 0;
}
@@ -64,6 +66,8 @@ struct proto udplite_prot = {
.per_cpu_fw_alloc = &udp_memory_per_cpu_fw_alloc,
.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,
};
generated by cgit v1.2.3-58-ga151 (git 2.39.0) at 2024-12-03 17:33:00 +0000