summaryrefslogtreecommitdiffstats
path: root/net/ipv4/tcp.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4/tcp.c')
-rw-r--r--net/ipv4/tcp.c112
1 files changed, 70 insertions, 42 deletions
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 9d72a0fcd928..f1377f2a0472 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -252,6 +252,7 @@
#include <linux/types.h>
#include <linux/fcntl.h>
#include <linux/poll.h>
+#include <linux/inet_diag.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/skbuff.h>
@@ -401,6 +402,7 @@ void tcp_init_sock(struct sock *sk)
tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
tp->snd_cwnd_clamp = ~0;
tp->mss_cache = TCP_MSS_DEFAULT;
+ u64_stats_init(&tp->syncp);
tp->reordering = sysctl_tcp_reordering;
tcp_enable_early_retrans(tp);
@@ -496,7 +498,7 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
/* Connected or passive Fast Open socket? */
if (sk->sk_state != TCP_SYN_SENT &&
- (sk->sk_state != TCP_SYN_RECV || tp->fastopen_rsk != NULL)) {
+ (sk->sk_state != TCP_SYN_RECV || tp->fastopen_rsk)) {
int target = sock_rcvlowat(sk, 0, INT_MAX);
if (tp->urg_seq == tp->copied_seq &&
@@ -520,8 +522,10 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
/* Race breaker. If space is freed after
* wspace test but before the flags are set,
- * IO signal will be lost.
+ * IO signal will be lost. Memory barrier
+ * pairs with the input side.
*/
+ smp_mb__after_atomic();
if (sk_stream_is_writeable(sk))
mask |= POLLOUT | POLLWRNORM;
}
@@ -835,17 +839,13 @@ static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now,
int large_allowed)
{
struct tcp_sock *tp = tcp_sk(sk);
- u32 new_size_goal, size_goal, hlen;
+ u32 new_size_goal, size_goal;
if (!large_allowed || !sk_can_gso(sk))
return mss_now;
- /* Maybe we should/could use sk->sk_prot->max_header here ? */
- hlen = inet_csk(sk)->icsk_af_ops->net_header_len +
- inet_csk(sk)->icsk_ext_hdr_len +
- tp->tcp_header_len;
-
- new_size_goal = sk->sk_gso_max_size - 1 - hlen;
+ /* Note : tcp_tso_autosize() will eventually split this later */
+ new_size_goal = sk->sk_gso_max_size - 1 - MAX_TCP_HEADER;
new_size_goal = tcp_bound_to_half_wnd(tp, new_size_goal);
/* We try hard to avoid divides here */
@@ -1032,7 +1032,7 @@ static inline int select_size(const struct sock *sk, bool sg)
void tcp_free_fastopen_req(struct tcp_sock *tp)
{
- if (tp->fastopen_req != NULL) {
+ if (tp->fastopen_req) {
kfree(tp->fastopen_req);
tp->fastopen_req = NULL;
}
@@ -1046,12 +1046,12 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
if (!(sysctl_tcp_fastopen & TFO_CLIENT_ENABLE))
return -EOPNOTSUPP;
- if (tp->fastopen_req != NULL)
+ if (tp->fastopen_req)
return -EALREADY; /* Another Fast Open is in progress */
tp->fastopen_req = kzalloc(sizeof(struct tcp_fastopen_request),
sk->sk_allocation);
- if (unlikely(tp->fastopen_req == NULL))
+ if (unlikely(!tp->fastopen_req))
return -ENOBUFS;
tp->fastopen_req->data = msg;
tp->fastopen_req->size = size;
@@ -1064,8 +1064,7 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
return err;
}
-int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
- size_t size)
+int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
@@ -1124,7 +1123,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
sg = !!(sk->sk_route_caps & NETIF_F_SG);
- while (iov_iter_count(&msg->msg_iter)) {
+ while (msg_data_left(msg)) {
int copy = 0;
int max = size_goal;
@@ -1168,8 +1167,8 @@ new_segment:
}
/* Try to append data to the end of skb. */
- if (copy > iov_iter_count(&msg->msg_iter))
- copy = iov_iter_count(&msg->msg_iter);
+ if (copy > msg_data_left(msg))
+ copy = msg_data_left(msg);
/* Where to copy to? */
if (skb_availroom(skb) > 0) {
@@ -1226,7 +1225,7 @@ new_segment:
tcp_skb_pcount_set(skb, 0);
copied += copy;
- if (!iov_iter_count(&msg->msg_iter)) {
+ if (!msg_data_left(msg)) {
tcp_tx_timestamp(sk, skb);
goto out;
}
@@ -1543,8 +1542,8 @@ EXPORT_SYMBOL(tcp_read_sock);
* Probably, code can be easily improved even more.
*/
-int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
- size_t len, int nonblock, int flags, int *addr_len)
+int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
+ int flags, int *addr_len)
{
struct tcp_sock *tp = tcp_sk(sk);
int copied = 0;
@@ -1918,18 +1917,19 @@ EXPORT_SYMBOL_GPL(tcp_set_state);
static const unsigned char new_state[16] = {
/* current state: new state: action: */
- /* (Invalid) */ TCP_CLOSE,
- /* TCP_ESTABLISHED */ TCP_FIN_WAIT1 | TCP_ACTION_FIN,
- /* TCP_SYN_SENT */ TCP_CLOSE,
- /* TCP_SYN_RECV */ TCP_FIN_WAIT1 | TCP_ACTION_FIN,
- /* TCP_FIN_WAIT1 */ TCP_FIN_WAIT1,
- /* TCP_FIN_WAIT2 */ TCP_FIN_WAIT2,
- /* TCP_TIME_WAIT */ TCP_CLOSE,
- /* TCP_CLOSE */ TCP_CLOSE,
- /* TCP_CLOSE_WAIT */ TCP_LAST_ACK | TCP_ACTION_FIN,
- /* TCP_LAST_ACK */ TCP_LAST_ACK,
- /* TCP_LISTEN */ TCP_CLOSE,
- /* TCP_CLOSING */ TCP_CLOSING,
+ [0 /* (Invalid) */] = TCP_CLOSE,
+ [TCP_ESTABLISHED] = TCP_FIN_WAIT1 | TCP_ACTION_FIN,
+ [TCP_SYN_SENT] = TCP_CLOSE,
+ [TCP_SYN_RECV] = TCP_FIN_WAIT1 | TCP_ACTION_FIN,
+ [TCP_FIN_WAIT1] = TCP_FIN_WAIT1,
+ [TCP_FIN_WAIT2] = TCP_FIN_WAIT2,
+ [TCP_TIME_WAIT] = TCP_CLOSE,
+ [TCP_CLOSE] = TCP_CLOSE,
+ [TCP_CLOSE_WAIT] = TCP_LAST_ACK | TCP_ACTION_FIN,
+ [TCP_LAST_ACK] = TCP_LAST_ACK,
+ [TCP_LISTEN] = TCP_CLOSE,
+ [TCP_CLOSING] = TCP_CLOSING,
+ [TCP_NEW_SYN_RECV] = TCP_CLOSE, /* should not happen ! */
};
static int tcp_close_state(struct sock *sk)
@@ -2142,7 +2142,7 @@ adjudge_to_death:
* aborted (e.g., closed with unread data) before 3WHS
* finishes.
*/
- if (req != NULL)
+ if (req)
reqsk_fastopen_remove(sk, req, false);
inet_csk_destroy_sock(sk);
}
@@ -2594,11 +2594,13 @@ EXPORT_SYMBOL(compat_tcp_setsockopt);
#endif
/* Return information about state of tcp endpoint in API format. */
-void tcp_get_info(const struct sock *sk, struct tcp_info *info)
+void tcp_get_info(struct sock *sk, struct tcp_info *info)
{
const struct tcp_sock *tp = tcp_sk(sk);
const struct inet_connection_sock *icsk = inet_csk(sk);
u32 now = tcp_time_stamp;
+ unsigned int start;
+ u32 rate;
memset(info, 0, sizeof(*info));
@@ -2659,10 +2661,17 @@ void tcp_get_info(const struct sock *sk, struct tcp_info *info)
info->tcpi_total_retrans = tp->total_retrans;
- info->tcpi_pacing_rate = sk->sk_pacing_rate != ~0U ?
- sk->sk_pacing_rate : ~0ULL;
- info->tcpi_max_pacing_rate = sk->sk_max_pacing_rate != ~0U ?
- sk->sk_max_pacing_rate : ~0ULL;
+ rate = READ_ONCE(sk->sk_pacing_rate);
+ info->tcpi_pacing_rate = rate != ~0U ? rate : ~0ULL;
+
+ rate = READ_ONCE(sk->sk_max_pacing_rate);
+ info->tcpi_max_pacing_rate = rate != ~0U ? rate : ~0ULL;
+
+ do {
+ start = u64_stats_fetch_begin_irq(&tp->syncp);
+ info->tcpi_bytes_acked = tp->bytes_acked;
+ info->tcpi_bytes_received = tp->bytes_received;
+ } while (u64_stats_fetch_retry_irq(&tp->syncp, start));
}
EXPORT_SYMBOL_GPL(tcp_get_info);
@@ -2734,6 +2743,26 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
return -EFAULT;
return 0;
}
+ case TCP_CC_INFO: {
+ const struct tcp_congestion_ops *ca_ops;
+ union tcp_cc_info info;
+ size_t sz = 0;
+ int attr;
+
+ if (get_user(len, optlen))
+ return -EFAULT;
+
+ ca_ops = icsk->icsk_ca_ops;
+ if (ca_ops && ca_ops->get_info)
+ sz = ca_ops->get_info(sk, ~0U, &attr, &info);
+
+ len = min_t(unsigned int, len, sz);
+ if (put_user(len, optlen))
+ return -EFAULT;
+ if (copy_to_user(optval, &info, len))
+ return -EFAULT;
+ return 0;
+ }
case TCP_QUICKACK:
val = !icsk->icsk_ack.pingpong;
break;
@@ -2780,7 +2809,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
break;
case TCP_FASTOPEN:
- if (icsk->icsk_accept_queue.fastopenq != NULL)
+ if (icsk->icsk_accept_queue.fastopenq)
val = icsk->icsk_accept_queue.fastopenq->max_qlen;
else
val = 0;
@@ -2964,7 +2993,7 @@ void tcp_done(struct sock *sk)
tcp_set_state(sk, TCP_CLOSE);
tcp_clear_xmit_timers(sk);
- if (req != NULL)
+ if (req)
reqsk_fastopen_remove(sk, req, false);
sk->sk_shutdown = SHUTDOWN_MASK;
@@ -3005,12 +3034,11 @@ static void __init tcp_init_mem(void)
void __init tcp_init(void)
{
- struct sk_buff *skb = NULL;
unsigned long limit;
int max_rshare, max_wshare, cnt;
unsigned int i;
- BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb));
+ sock_skb_cb_check_size(sizeof(struct tcp_skb_cb));
percpu_counter_init(&tcp_sockets_allocated, 0, GFP_KERNEL);
percpu_counter_init(&tcp_orphan_count, 0, GFP_KERNEL);
OpenPOWER on IntegriCloud