summaryrefslogtreecommitdiff
path: root/net/ipv4/tcp.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4/tcp.c')
-rw-r--r--net/ipv4/tcp.c114
1 files changed, 81 insertions, 33 deletions
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 141acd92e58a..10c6246396cc 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -494,21 +494,32 @@ static inline bool tcp_stream_is_readable(const struct tcp_sock *tp,
}
/*
- * Socket is not locked. We are protected from async events by poll logic and
- * correct handling of state changes made by other threads is impossible in
- * any case.
+ * Wait for a TCP event.
+ *
+ * Note that we don't need to lock the socket, as the upper poll layers
+ * take care of normal races (between the test and the event) and we don't
+ * go look at any of the socket buffers directly.
*/
-__poll_t tcp_poll_mask(struct socket *sock, __poll_t events)
+__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);
- __poll_t mask = 0;
int state;
+ sock_poll_wait(file, wait);
+
state = inet_sk_state_load(sk);
if (state == TCP_LISTEN)
return inet_csk_listen_poll(sk);
+ /* Socket is not locked. We are protected from async events
+ * by poll logic and correct handling of state changes
+ * made by other threads is impossible in any case.
+ */
+
+ mask = 0;
+
/*
* EPOLLHUP is certainly not done right. But poll() doesn't
* have a notion of HUP in just one direction, and for a
@@ -589,7 +600,7 @@ __poll_t tcp_poll_mask(struct socket *sock, __poll_t events)
return mask;
}
-EXPORT_SYMBOL(tcp_poll_mask);
+EXPORT_SYMBOL(tcp_poll);
int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
{
@@ -806,8 +817,7 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos,
* This occurs when user tries to read
* from never connected socket.
*/
- if (!sock_flag(sk, SOCK_DONE))
- ret = -ENOTCONN;
+ ret = -ENOTCONN;
break;
}
if (!timeo) {
@@ -1175,7 +1185,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
flags = msg->msg_flags;
- if (flags & MSG_ZEROCOPY && size) {
+ if (flags & MSG_ZEROCOPY && size && sock_flag(sk, SOCK_ZEROCOPY)) {
if (sk->sk_state != TCP_ESTABLISHED) {
err = -EINVAL;
goto out_err;
@@ -1230,7 +1240,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
/* 'common' sending to sendq */
}
- sockc.tsflags = sk->sk_tsflags;
+ sockcm_init(&sockc, sk);
if (msg->msg_controllen) {
err = sock_cmsg_send(sk, msg, &sockc);
if (unlikely(err)) {
@@ -1264,9 +1274,6 @@ restart:
int linear;
new_segment:
- /* Allocate new segment. If the interface is SG,
- * allocate skb fitting to single page.
- */
if (!sk_stream_memory_free(sk))
goto wait_for_sndbuf;
@@ -1987,7 +1994,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
* shouldn't happen.
*/
if (WARN(before(*seq, TCP_SKB_CB(skb)->seq),
- "recvmsg bug: copied %X seq %X rcvnxt %X fl %X\n",
+ "TCP recvmsg seq # bug: copied %X, seq %X, rcvnxt %X, fl %X\n",
*seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt,
flags))
break;
@@ -2002,7 +2009,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
goto found_fin_ok;
WARN(!(flags & MSG_PEEK),
- "recvmsg bug 2: copied %X seq %X rcvnxt %X fl %X\n",
+ "TCP recvmsg seq # bug 2: copied %X, seq %X, rcvnxt %X, fl %X\n",
*seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt, flags);
}
@@ -2031,13 +2038,10 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
break;
if (sk->sk_state == TCP_CLOSE) {
- if (!sock_flag(sk, SOCK_DONE)) {
- /* This occurs when user tries to read
- * from never connected socket.
- */
- copied = -ENOTCONN;
- break;
- }
+ /* This occurs when user tries to read
+ * from never connected socket.
+ */
+ copied = -ENOTCONN;
break;
}
@@ -2527,7 +2531,6 @@ int tcp_disconnect(struct sock *sk, int flags)
struct inet_sock *inet = inet_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
- int err = 0;
int old_state = sk->sk_state;
if (old_state != TCP_CLOSE)
@@ -2551,6 +2554,8 @@ int tcp_disconnect(struct sock *sk, int flags)
tcp_clear_xmit_timers(sk);
__skb_queue_purge(&sk->sk_receive_queue);
+ tp->copied_seq = tp->rcv_nxt;
+ tp->urg_data = 0;
tcp_write_queue_purge(sk);
tcp_fastopen_active_disable_ofo_check(sk);
skb_rbtree_purge(&tp->out_of_order_queue);
@@ -2563,6 +2568,7 @@ int tcp_disconnect(struct sock *sk, int flags)
sk->sk_shutdown = 0;
sock_reset_flag(sk, SOCK_DONE);
tp->srtt_us = 0;
+ tp->rcv_rtt_last_tsecr = 0;
tp->write_seq += tp->max_window + 2;
if (tp->write_seq == 0)
tp->write_seq = 1;
@@ -2587,6 +2593,10 @@ int tcp_disconnect(struct sock *sk, int flags)
sk->sk_rx_dst = NULL;
tcp_saved_syn_free(tp);
tp->compressed_ack = 0;
+ tp->bytes_sent = 0;
+ tp->bytes_retrans = 0;
+ tp->dsack_dups = 0;
+ tp->reord_seen = 0;
/* Clean up fastopen related fields */
tcp_free_fastopen_req(tp);
@@ -2601,7 +2611,7 @@ int tcp_disconnect(struct sock *sk, int flags)
}
sk->sk_error_report(sk);
- return err;
+ return 0;
}
EXPORT_SYMBOL(tcp_disconnect);
@@ -2810,14 +2820,17 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
case TCP_REPAIR:
if (!tcp_can_repair_sock(sk))
err = -EPERM;
- else if (val == 1) {
+ else if (val == TCP_REPAIR_ON) {
tp->repair = 1;
sk->sk_reuse = SK_FORCE_REUSE;
tp->repair_queue = TCP_NO_QUEUE;
- } else if (val == 0) {
+ } else if (val == TCP_REPAIR_OFF) {
tp->repair = 0;
sk->sk_reuse = SK_NO_REUSE;
tcp_send_window_probe(sk);
+ } else if (val == TCP_REPAIR_OFF_NO_WP) {
+ tp->repair = 0;
+ sk->sk_reuse = SK_NO_REUSE;
} else
err = -EINVAL;
@@ -2979,7 +2992,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
if (val < 0)
err = -EINVAL;
else
- icsk->icsk_user_timeout = msecs_to_jiffies(val);
+ icsk->icsk_user_timeout = val;
break;
case TCP_FASTOPEN:
@@ -3191,10 +3204,41 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
info->tcpi_delivery_rate = rate64;
info->tcpi_delivered = tp->delivered;
info->tcpi_delivered_ce = tp->delivered_ce;
+ info->tcpi_bytes_sent = tp->bytes_sent;
+ info->tcpi_bytes_retrans = tp->bytes_retrans;
+ info->tcpi_dsack_dups = tp->dsack_dups;
+ info->tcpi_reord_seen = tp->reord_seen;
unlock_sock_fast(sk, slow);
}
EXPORT_SYMBOL_GPL(tcp_get_info);
+static size_t tcp_opt_stats_get_size(void)
+{
+ return
+ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BUSY */
+ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_RWND_LIMITED */
+ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_SNDBUF_LIMITED */
+ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_DATA_SEGS_OUT */
+ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_TOTAL_RETRANS */
+ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_PACING_RATE */
+ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_DELIVERY_RATE */
+ nla_total_size(sizeof(u32)) + /* TCP_NLA_SND_CWND */
+ nla_total_size(sizeof(u32)) + /* TCP_NLA_REORDERING */
+ nla_total_size(sizeof(u32)) + /* TCP_NLA_MIN_RTT */
+ nla_total_size(sizeof(u8)) + /* TCP_NLA_RECUR_RETRANS */
+ nla_total_size(sizeof(u8)) + /* TCP_NLA_DELIVERY_RATE_APP_LMT */
+ nla_total_size(sizeof(u32)) + /* TCP_NLA_SNDQ_SIZE */
+ nla_total_size(sizeof(u8)) + /* TCP_NLA_CA_STATE */
+ nla_total_size(sizeof(u32)) + /* TCP_NLA_SND_SSTHRESH */
+ nla_total_size(sizeof(u32)) + /* TCP_NLA_DELIVERED */
+ nla_total_size(sizeof(u32)) + /* TCP_NLA_DELIVERED_CE */
+ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BYTES_SENT */
+ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BYTES_RETRANS */
+ nla_total_size(sizeof(u32)) + /* TCP_NLA_DSACK_DUPS */
+ nla_total_size(sizeof(u32)) + /* TCP_NLA_REORD_SEEN */
+ 0;
+}
+
struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk)
{
const struct tcp_sock *tp = tcp_sk(sk);
@@ -3203,9 +3247,7 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk)
u64 rate64;
u32 rate;
- stats = alloc_skb(7 * nla_total_size_64bit(sizeof(u64)) +
- 7 * nla_total_size(sizeof(u32)) +
- 3 * nla_total_size(sizeof(u8)), GFP_ATOMIC);
+ stats = alloc_skb(tcp_opt_stats_get_size(), GFP_ATOMIC);
if (!stats)
return NULL;
@@ -3241,6 +3283,13 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk)
nla_put_u32(stats, TCP_NLA_SNDQ_SIZE, tp->write_seq - tp->snd_una);
nla_put_u8(stats, TCP_NLA_CA_STATE, inet_csk(sk)->icsk_ca_state);
+ nla_put_u64_64bit(stats, TCP_NLA_BYTES_SENT, tp->bytes_sent,
+ TCP_NLA_PAD);
+ nla_put_u64_64bit(stats, TCP_NLA_BYTES_RETRANS, tp->bytes_retrans,
+ TCP_NLA_PAD);
+ nla_put_u32(stats, TCP_NLA_DSACK_DUPS, tp->dsack_dups);
+ nla_put_u32(stats, TCP_NLA_REORD_SEEN, tp->reord_seen);
+
return stats;
}
@@ -3435,7 +3484,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
break;
case TCP_USER_TIMEOUT:
- val = jiffies_to_msecs(icsk->icsk_user_timeout);
+ val = icsk->icsk_user_timeout;
break;
case TCP_FASTOPEN:
@@ -3709,8 +3758,7 @@ int tcp_abort(struct sock *sk, int err)
struct request_sock *req = inet_reqsk(sk);
local_bh_disable();
- inet_csk_reqsk_queue_drop_and_put(req->rsk_listener,
- req);
+ inet_csk_reqsk_queue_drop(req->rsk_listener, req);
local_bh_enable();
return 0;
}
generated by cgit v1.2.3 (git 2.46.0) at 2025-07-30 15:59:24 +0000