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.c79
1 files changed, 52 insertions, 27 deletions
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 77ee1eda3f..ec69110341 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -272,13 +272,16 @@
#include <net/inet_common.h>
#include <net/tcp.h>
#include <net/mptcp.h>
+#include <net/proto_memory.h>
#include <net/xfrm.h>
#include <net/ip.h>
#include <net/sock.h>
+#include <net/rstreason.h>
#include <linux/uaccess.h>
#include <asm/ioctls.h>
#include <net/busy_poll.h>
+#include <net/hotdata.h>
#include <net/rps.h>
/* Track pending CMSGs. */
@@ -290,6 +293,9 @@ enum {
DEFINE_PER_CPU(unsigned int, tcp_orphan_count);
EXPORT_PER_CPU_SYMBOL_GPL(tcp_orphan_count);
+DEFINE_PER_CPU(u32, tcp_tw_isn);
+EXPORT_PER_CPU_SYMBOL_GPL(tcp_tw_isn);
+
long sysctl_tcp_mem[3] __read_mostly;
EXPORT_SYMBOL(sysctl_tcp_mem);
@@ -592,7 +598,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
*/
mask |= EPOLLOUT | EPOLLWRNORM;
}
- /* This barrier is coupled with smp_wmb() in tcp_reset() */
+ /* This barrier is coupled with smp_wmb() in tcp_done_with_error() */
smp_rmb();
if (READ_ONCE(sk->sk_err) ||
!skb_queue_empty_lockless(&sk->sk_error_queue))
@@ -1187,7 +1193,7 @@ new_segment:
if (!skb_can_coalesce(skb, i, pfrag->page,
pfrag->offset)) {
- if (i >= READ_ONCE(sysctl_max_skb_frags)) {
+ if (i >= READ_ONCE(net_hotdata.sysctl_max_skb_frags)) {
tcp_mark_push(tp, skb);
goto new_segment;
}
@@ -1419,8 +1425,6 @@ static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len)
struct sk_buff *skb;
int copied = 0, err = 0;
- /* XXX -- need to support SO_PEEK_OFF */
-
skb_rbtree_walk(skb, &sk->tcp_rtx_queue) {
err = skb_copy_datagram_msg(skb, 0, msg, skb->len);
if (err)
@@ -1724,7 +1728,7 @@ int tcp_set_rcvlowat(struct sock *sk, int val)
space = tcp_space_from_win(sk, val);
if (space > sk->sk_rcvbuf) {
WRITE_ONCE(sk->sk_rcvbuf, space);
- tcp_sk(sk)->window_clamp = val;
+ WRITE_ONCE(tcp_sk(sk)->window_clamp, val);
}
return 0;
}
@@ -2331,6 +2335,7 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
int target; /* Read at least this many bytes */
long timeo;
struct sk_buff *skb, *last;
+ u32 peek_offset = 0;
u32 urg_hole = 0;
err = -ENOTCONN;
@@ -2364,7 +2369,8 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
seq = &tp->copied_seq;
if (flags & MSG_PEEK) {
- peek_seq = tp->copied_seq;
+ peek_offset = max(sk_peek_offset(sk, flags), 0);
+ peek_seq = tp->copied_seq + peek_offset;
seq = &peek_seq;
}
@@ -2467,11 +2473,11 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
}
if ((flags & MSG_PEEK) &&
- (peek_seq - copied - urg_hole != tp->copied_seq)) {
+ (peek_seq - peek_offset - copied - urg_hole != tp->copied_seq)) {
net_dbg_ratelimited("TCP(%s:%d): Application bug, race in MSG_PEEK\n",
current->comm,
task_pid_nr(current));
- peek_seq = tp->copied_seq;
+ peek_seq = tp->copied_seq + peek_offset;
}
continue;
@@ -2512,7 +2518,10 @@ found_ok_skb:
WRITE_ONCE(*seq, *seq + used);
copied += used;
len -= used;
-
+ if (flags & MSG_PEEK)
+ sk_peek_offset_fwd(sk, used);
+ else
+ sk_peek_offset_bwd(sk, used);
tcp_rcv_space_adjust(sk);
skip_copy:
@@ -2751,7 +2760,15 @@ static bool tcp_too_many_orphans(int shift)
READ_ONCE(sysctl_tcp_max_orphans);
}
-bool tcp_check_oom(struct sock *sk, int shift)
+static bool tcp_out_of_memory(const struct sock *sk)
+{
+ if (sk->sk_wmem_queued > SOCK_MIN_SNDBUF &&
+ sk_memory_allocated(sk) > sk_prot_mem_limits(sk, 2))
+ return true;
+ return false;
+}
+
+bool tcp_check_oom(const struct sock *sk, int shift)
{
bool too_many_orphans, out_of_socket_memory;
@@ -2812,7 +2829,8 @@ void __tcp_close(struct sock *sk, long timeout)
/* Unread data was tossed, zap the connection. */
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONCLOSE);
tcp_set_state(sk, TCP_CLOSE);
- tcp_send_active_reset(sk, sk->sk_allocation);
+ tcp_send_active_reset(sk, sk->sk_allocation,
+ SK_RST_REASON_NOT_SPECIFIED);
} else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) {
/* Check zero linger _after_ checking for unread data. */
sk->sk_prot->disconnect(sk, 0);
@@ -2886,7 +2904,8 @@ adjudge_to_death:
struct tcp_sock *tp = tcp_sk(sk);
if (READ_ONCE(tp->linger2) < 0) {
tcp_set_state(sk, TCP_CLOSE);
- tcp_send_active_reset(sk, GFP_ATOMIC);
+ tcp_send_active_reset(sk, GFP_ATOMIC,
+ SK_RST_REASON_NOT_SPECIFIED);
__NET_INC_STATS(sock_net(sk),
LINUX_MIB_TCPABORTONLINGER);
} else {
@@ -2904,7 +2923,8 @@ adjudge_to_death:
if (sk->sk_state != TCP_CLOSE) {
if (tcp_check_oom(sk, 0)) {
tcp_set_state(sk, TCP_CLOSE);
- tcp_send_active_reset(sk, GFP_ATOMIC);
+ tcp_send_active_reset(sk, GFP_ATOMIC,
+ SK_RST_REASON_NOT_SPECIFIED);
__NET_INC_STATS(sock_net(sk),
LINUX_MIB_TCPABORTONMEMORY);
} else if (!check_net(sock_net(sk))) {
@@ -3008,7 +3028,7 @@ int tcp_disconnect(struct sock *sk, int flags)
/* The last check adjusts for discrepancy of Linux wrt. RFC
* states
*/
- tcp_send_active_reset(sk, gfp_any());
+ tcp_send_active_reset(sk, gfp_any(), SK_RST_REASON_NOT_SPECIFIED);
WRITE_ONCE(sk->sk_err, ECONNRESET);
} else if (old_state == TCP_SYN_SENT)
WRITE_ONCE(sk->sk_err, ECONNRESET);
@@ -3017,6 +3037,7 @@ int tcp_disconnect(struct sock *sk, int flags)
__skb_queue_purge(&sk->sk_receive_queue);
WRITE_ONCE(tp->copied_seq, tp->rcv_nxt);
WRITE_ONCE(tp->urg_data, 0);
+ sk_set_peek_off(sk, -1);
tcp_write_queue_purge(sk);
tcp_fastopen_active_disable_ofo_check(sk);
skb_rbtree_purge(&tp->out_of_order_queue);
@@ -3386,7 +3407,7 @@ int tcp_set_window_clamp(struct sock *sk, int val)
if (!val) {
if (sk->sk_state != TCP_CLOSE)
return -EINVAL;
- tp->window_clamp = 0;
+ WRITE_ONCE(tp->window_clamp, 0);
} else {
u32 new_rcv_ssthresh, old_window_clamp = tp->window_clamp;
u32 new_window_clamp = val < SOCK_MIN_RCVBUF / 2 ?
@@ -3395,7 +3416,7 @@ int tcp_set_window_clamp(struct sock *sk, int val)
if (new_window_clamp == old_window_clamp)
return 0;
- tp->window_clamp = new_window_clamp;
+ WRITE_ONCE(tp->window_clamp, new_window_clamp);
if (new_window_clamp < old_window_clamp) {
/* need to apply the reserved mem provisioning only
* when shrinking the window clamp
@@ -4064,7 +4085,7 @@ int do_tcp_getsockopt(struct sock *sk, int level,
TCP_RTO_MAX / HZ);
break;
case TCP_WINDOW_CLAMP:
- val = tp->window_clamp;
+ val = READ_ONCE(tp->window_clamp);
break;
case TCP_INFO: {
struct tcp_info info;
@@ -4349,6 +4370,9 @@ zerocopy_rcv_out:
return err;
}
+ case TCP_IS_MPTCP:
+ val = 0;
+ break;
default:
return -ENOPROTOOPT;
}
@@ -4559,13 +4583,10 @@ int tcp_abort(struct sock *sk, int err)
bh_lock_sock(sk);
if (!sock_flag(sk, SOCK_DEAD)) {
- WRITE_ONCE(sk->sk_err, err);
- /* This barrier is coupled with smp_rmb() in tcp_poll() */
- smp_wmb();
- sk_error_report(sk);
if (tcp_need_reset(sk->sk_state))
- tcp_send_active_reset(sk, GFP_ATOMIC);
- tcp_done(sk);
+ tcp_send_active_reset(sk, GFP_ATOMIC,
+ SK_RST_REASON_NOT_SPECIFIED);
+ tcp_done_with_error(sk, err);
}
bh_unlock_sock(sk);
@@ -4655,16 +4676,16 @@ static void __init tcp_struct_check(void)
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, lsndtime);
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, mdev_us);
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tcp_wstamp_ns);
- CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tcp_clock_cache);
- CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tcp_mstamp);
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, rtt_seq);
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tsorted_sent_queue);
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, highest_sack);
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, ecn_flags);
- CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_tx, 105);
+ CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_tx, 89);
/* TXRX read-write hotpath cache lines */
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, pred_flags);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, tcp_clock_cache);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, tcp_mstamp);
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rcv_nxt);
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, snd_nxt);
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, snd_una);
@@ -4677,7 +4698,11 @@ static void __init tcp_struct_check(void)
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, app_limited);
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rcv_wnd);
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rx_opt);
- CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_txrx, 76);
+
+ /* 32bit arches with 8byte alignment on u64 fields might need padding
+ * before tcp_clock_cache.
+ */
+ CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_txrx, 92 + 4);
/* RX read-write hotpath cache lines */
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, bytes_received);
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-27 08:23:46 +0000