summaryrefslogtreecommitdiff
path: root/net/mptcp/protocol.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/mptcp/protocol.c')
-rw-r--r--net/mptcp/protocol.c69
1 files changed, 45 insertions, 24 deletions
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 886ab689a8ae..1dacc072dcca 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -121,8 +121,6 @@ struct sock *__mptcp_nmpc_sk(struct mptcp_sock *msk)
ret = __mptcp_socket_create(msk);
if (ret)
return ERR_PTR(ret);
-
- mptcp_sockopt_sync(msk, msk->first);
}
return msk->first;
@@ -863,9 +861,8 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk)
/* Wake-up the reader only for in-sequence data */
mptcp_data_lock(sk);
- if (move_skbs_to_msk(msk, ssk))
+ if (move_skbs_to_msk(msk, ssk) && mptcp_epollin_ready(sk))
sk->sk_data_ready(sk);
-
mptcp_data_unlock(sk);
}
@@ -893,6 +890,7 @@ static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk)
mptcp_sockopt_sync_locked(msk, ssk);
mptcp_subflow_joined(msk, ssk);
mptcp_stop_tout_timer(sk);
+ __mptcp_propagate_sndbuf(sk, ssk);
return true;
}
@@ -1079,15 +1077,16 @@ static void mptcp_enter_memory_pressure(struct sock *sk)
struct mptcp_sock *msk = mptcp_sk(sk);
bool first = true;
- sk_stream_moderate_sndbuf(sk);
mptcp_for_each_subflow(msk, subflow) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
if (first)
tcp_enter_memory_pressure(ssk);
sk_stream_moderate_sndbuf(ssk);
+
first = false;
}
+ __mptcp_sync_sndbuf(sk);
}
/* ensure we get enough memory for the frag hdr, beyond some minimal amount of
@@ -1761,6 +1760,18 @@ static int mptcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
return ret;
}
+static int do_copy_data_nocache(struct sock *sk, int copy,
+ struct iov_iter *from, char *to)
+{
+ if (sk->sk_route_caps & NETIF_F_NOCACHE_COPY) {
+ if (!copy_from_iter_full_nocache(to, copy, from))
+ return -EFAULT;
+ } else if (!copy_from_iter_full(to, copy, from)) {
+ return -EFAULT;
+ }
+ return 0;
+}
+
static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
{
struct mptcp_sock *msk = mptcp_sk(sk);
@@ -1834,11 +1845,10 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
if (!sk_wmem_schedule(sk, total_ts))
goto wait_for_memory;
- if (copy_page_from_iter(dfrag->page, offset, psize,
- &msg->msg_iter) != psize) {
- ret = -EFAULT;
+ ret = do_copy_data_nocache(sk, psize, &msg->msg_iter,
+ page_address(dfrag->page) + offset);
+ if (ret)
goto do_error;
- }
/* data successfully copied into the write queue */
sk_forward_alloc_add(sk, -total_ts);
@@ -1922,6 +1932,7 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk,
if (!(flags & MSG_PEEK)) {
MPTCP_SKB_CB(skb)->offset += count;
MPTCP_SKB_CB(skb)->map_seq += count;
+ msk->bytes_consumed += count;
}
break;
}
@@ -1932,6 +1943,7 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk,
WRITE_ONCE(msk->rmem_released, msk->rmem_released + skb->truesize);
__skb_unlink(skb, &msk->receive_queue);
__kfree_skb(skb);
+ msk->bytes_consumed += count;
}
if (copied >= len)
@@ -2391,8 +2403,8 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
if (msk->in_accept_queue && msk->first == ssk &&
(sock_flag(sk, SOCK_DEAD) || sock_flag(ssk, SOCK_DEAD))) {
/* ensure later check in mptcp_worker() will dispose the msk */
- mptcp_set_close_tout(sk, tcp_jiffies32 - (TCP_TIMEWAIT_LEN + 1));
sock_set_flag(sk, SOCK_DEAD);
+ mptcp_set_close_tout(sk, tcp_jiffies32 - (mptcp_close_timeout(sk) + 1));
lock_sock_nested(ssk, SINGLE_DEPTH_NESTING);
mptcp_subflow_drop_ctx(ssk);
goto out_release;
@@ -2448,6 +2460,7 @@ out_release:
WRITE_ONCE(msk->first, NULL);
out:
+ __mptcp_sync_sndbuf(sk);
if (need_push)
__mptcp_push_pending(sk, 0);
@@ -2516,7 +2529,7 @@ static bool mptcp_close_tout_expired(const struct sock *sk)
return false;
return time_after32(tcp_jiffies32,
- inet_csk(sk)->icsk_mtup.probe_timestamp + TCP_TIMEWAIT_LEN);
+ inet_csk(sk)->icsk_mtup.probe_timestamp + mptcp_close_timeout(sk));
}
static void mptcp_check_fastclose(struct mptcp_sock *msk)
@@ -2659,7 +2672,7 @@ void mptcp_reset_tout_timer(struct mptcp_sock *msk, unsigned long fail_tout)
return;
close_timeout = inet_csk(sk)->icsk_mtup.probe_timestamp - tcp_jiffies32 + jiffies +
- TCP_TIMEWAIT_LEN;
+ mptcp_close_timeout(sk);
/* the close timeout takes precedence on the fail one, and here at least one of
* them is active
@@ -2755,6 +2768,7 @@ static void __mptcp_init_sock(struct sock *sk)
msk->rmem_fwd_alloc = 0;
WRITE_ONCE(msk->rmem_released, 0);
msk->timer_ival = TCP_RTO_MIN;
+ msk->scaling_ratio = TCP_DEFAULT_SCALING_RATIO;
WRITE_ONCE(msk->first, NULL);
inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss;
@@ -2964,16 +2978,9 @@ void __mptcp_unaccepted_force_close(struct sock *sk)
__mptcp_destroy_sock(sk);
}
-static __poll_t mptcp_check_readable(struct mptcp_sock *msk)
+static __poll_t mptcp_check_readable(struct sock *sk)
{
- /* Concurrent splices from sk_receive_queue into receive_queue will
- * always show at least one non-empty queue when checked in this order.
- */
- if (skb_queue_empty_lockless(&((struct sock *)msk)->sk_receive_queue) &&
- skb_queue_empty_lockless(&msk->receive_queue))
- return 0;
-
- return EPOLLIN | EPOLLRDNORM;
+ return mptcp_epollin_ready(sk) ? EPOLLIN | EPOLLRDNORM : 0;
}
static void mptcp_check_listen_stop(struct sock *sk)
@@ -3011,7 +3018,7 @@ bool __mptcp_close(struct sock *sk, long timeout)
goto cleanup;
}
- if (mptcp_check_readable(msk) || timeout < 0) {
+ if (mptcp_data_avail(msk) || timeout < 0) {
/* If the msk has read data, or the caller explicitly ask it,
* do the MPTCP equivalent of TCP reset, aka MPTCP fastclose
*/
@@ -3138,6 +3145,7 @@ static int mptcp_disconnect(struct sock *sk, int flags)
msk->snd_data_fin_enable = false;
msk->rcv_fastclose = false;
msk->use_64bit_ack = false;
+ msk->bytes_consumed = 0;
WRITE_ONCE(msk->csum_enabled, mptcp_is_checksum_enabled(sock_net(sk)));
mptcp_pm_data_reset(msk);
mptcp_ca_reset(sk);
@@ -3219,7 +3227,7 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
* uses the correct data
*/
mptcp_copy_inaddrs(nsk, ssk);
- mptcp_propagate_sndbuf(nsk, ssk);
+ __mptcp_propagate_sndbuf(nsk, ssk);
mptcp_rcv_space_init(msk, ssk);
bh_unlock_sock(nsk);
@@ -3397,6 +3405,8 @@ static void mptcp_release_cb(struct sock *sk)
__mptcp_set_connected(sk);
if (__test_and_clear_bit(MPTCP_ERROR_REPORT, &msk->cb_flags))
__mptcp_error_report(sk);
+ if (__test_and_clear_bit(MPTCP_SYNC_SNDBUF, &msk->cb_flags))
+ __mptcp_sync_sndbuf(sk);
}
__mptcp_update_rmem(sk);
@@ -3441,6 +3451,14 @@ void mptcp_subflow_process_delegated(struct sock *ssk, long status)
__set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->cb_flags);
mptcp_data_unlock(sk);
}
+ if (status & BIT(MPTCP_DELEGATE_SNDBUF)) {
+ mptcp_data_lock(sk);
+ if (!sock_owned_by_user(sk))
+ __mptcp_sync_sndbuf(sk);
+ else
+ __set_bit(MPTCP_SYNC_SNDBUF, &mptcp_sk(sk)->cb_flags);
+ mptcp_data_unlock(sk);
+ }
if (status & BIT(MPTCP_DELEGATE_ACK))
schedule_3rdack_retransmission(ssk);
}
@@ -3525,6 +3543,7 @@ bool mptcp_finish_join(struct sock *ssk)
/* active subflow, already present inside the conn_list */
if (!list_empty(&subflow->node)) {
mptcp_subflow_joined(msk, ssk);
+ mptcp_propagate_sndbuf(parent, ssk);
return true;
}
@@ -3909,7 +3928,7 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock,
mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP;
if (state != TCP_SYN_SENT && state != TCP_SYN_RECV) {
- mask |= mptcp_check_readable(msk);
+ mask |= mptcp_check_readable(sk);
if (shutdown & SEND_SHUTDOWN)
mask |= EPOLLOUT | EPOLLWRNORM;
else
@@ -3947,6 +3966,7 @@ static const struct proto_ops mptcp_stream_ops = {
.sendmsg = inet_sendmsg,
.recvmsg = inet_recvmsg,
.mmap = sock_no_mmap,
+ .set_rcvlowat = mptcp_set_rcvlowat,
};
static struct inet_protosw mptcp_protosw = {
@@ -4048,6 +4068,7 @@ static const struct proto_ops mptcp_v6_stream_ops = {
#ifdef CONFIG_COMPAT
.compat_ioctl = inet6_compat_ioctl,
#endif
+ .set_rcvlowat = mptcp_set_rcvlowat,
};
static struct proto mptcp_v6_prot;
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-20 18:20:12 +0000