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.c86
1 files changed, 44 insertions, 42 deletions
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 3ed4709a7509..c7af62c057bc 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -410,6 +410,7 @@ static void mptcp_close_wake_up(struct sock *sk)
sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
}
+/* called under the msk socket lock */
static bool mptcp_pending_data_fin_ack(struct sock *sk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
@@ -441,16 +442,17 @@ static void mptcp_check_data_fin_ack(struct sock *sk)
}
}
+/* can be called with no lock acquired */
static bool mptcp_pending_data_fin(struct sock *sk, u64 *seq)
{
struct mptcp_sock *msk = mptcp_sk(sk);
if (READ_ONCE(msk->rcv_data_fin) &&
- ((1 << sk->sk_state) &
+ ((1 << inet_sk_state_load(sk)) &
(TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2))) {
u64 rcv_data_fin_seq = READ_ONCE(msk->rcv_data_fin_seq);
- if (msk->ack_seq == rcv_data_fin_seq) {
+ if (READ_ONCE(msk->ack_seq) == rcv_data_fin_seq) {
if (seq)
*seq = rcv_data_fin_seq;
@@ -748,7 +750,7 @@ static bool __mptcp_ofo_queue(struct mptcp_sock *msk)
__skb_queue_tail(&sk->sk_receive_queue, skb);
}
msk->bytes_received += end_seq - msk->ack_seq;
- msk->ack_seq = end_seq;
+ WRITE_ONCE(msk->ack_seq, end_seq);
moved = true;
}
return moved;
@@ -985,6 +987,7 @@ static void dfrag_clear(struct sock *sk, struct mptcp_data_frag *dfrag)
put_page(dfrag->page);
}
+/* called under both the msk socket lock and the data lock */
static void __mptcp_clean_una(struct sock *sk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
@@ -1033,13 +1036,15 @@ static void __mptcp_clean_una(struct sock *sk)
msk->recovery = false;
out:
- if (snd_una == READ_ONCE(msk->snd_nxt) &&
- snd_una == READ_ONCE(msk->write_seq)) {
+ if (snd_una == msk->snd_nxt && snd_una == msk->write_seq) {
if (mptcp_rtx_timer_pending(sk) && !mptcp_data_fin_enabled(msk))
mptcp_stop_rtx_timer(sk);
} else {
mptcp_reset_rtx_timer(sk);
}
+
+ if (mptcp_pending_data_fin_ack(sk))
+ mptcp_schedule_work(sk);
}
static void __mptcp_clean_una_wakeup(struct sock *sk)
@@ -1499,14 +1504,17 @@ static void mptcp_update_post_push(struct mptcp_sock *msk,
*/
if (likely(after64(snd_nxt_new, msk->snd_nxt))) {
msk->bytes_sent += snd_nxt_new - msk->snd_nxt;
- msk->snd_nxt = snd_nxt_new;
+ WRITE_ONCE(msk->snd_nxt, snd_nxt_new);
}
}
void mptcp_check_and_set_pending(struct sock *sk)
{
- if (mptcp_send_head(sk))
- mptcp_sk(sk)->push_pending |= BIT(MPTCP_PUSH_PENDING);
+ if (mptcp_send_head(sk)) {
+ mptcp_data_lock(sk);
+ mptcp_sk(sk)->cb_flags |= BIT(MPTCP_PUSH_PENDING);
+ mptcp_data_unlock(sk);
+ }
}
static int __subflow_push_pending(struct sock *sk, struct sock *ssk,
@@ -1960,6 +1968,9 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)
if (copied <= 0)
return;
+ if (!msk->rcvspace_init)
+ mptcp_rcv_space_init(msk, msk->first);
+
msk->rcvq_space.copied += copied;
mstamp = div_u64(tcp_clock_ns(), NSEC_PER_USEC);
@@ -2108,7 +2119,7 @@ static unsigned int mptcp_inq_hint(const struct sock *sk)
skb = skb_peek(&msk->receive_queue);
if (skb) {
- u64 hint_val = msk->ack_seq - MPTCP_SKB_CB(skb)->map_seq;
+ u64 hint_val = READ_ONCE(msk->ack_seq) - MPTCP_SKB_CB(skb)->map_seq;
if (hint_val >= INT_MAX)
return INT_MAX;
@@ -2314,9 +2325,6 @@ bool __mptcp_retransmit_pending_data(struct sock *sk)
if (__mptcp_check_fallback(msk))
return false;
- if (tcp_rtx_and_write_queues_empty(sk))
- return false;
-
/* the closing socket has some data untransmitted and/or unacked:
* some data in the mptcp rtx queue has not really xmitted yet.
* keep it simple and re-inject the whole mptcp level rtx queue
@@ -2755,7 +2763,7 @@ static void __mptcp_init_sock(struct sock *sk)
__skb_queue_head_init(&msk->receive_queue);
msk->out_of_order_queue = RB_ROOT;
msk->first_pending = NULL;
- msk->rmem_fwd_alloc = 0;
+ WRITE_ONCE(msk->rmem_fwd_alloc, 0);
WRITE_ONCE(msk->rmem_released, 0);
msk->timer_ival = TCP_RTO_MIN;
msk->scaling_ratio = TCP_DEFAULT_SCALING_RATIO;
@@ -2971,7 +2979,7 @@ static void __mptcp_destroy_sock(struct sock *sk)
sk->sk_prot->destroy(sk);
- WARN_ON_ONCE(msk->rmem_fwd_alloc);
+ WARN_ON_ONCE(READ_ONCE(msk->rmem_fwd_alloc));
WARN_ON_ONCE(msk->rmem_released);
sk_stream_kill_queues(sk);
xfrm_sk_free_policy(sk);
@@ -3145,22 +3153,22 @@ static int mptcp_disconnect(struct sock *sk, int flags)
mptcp_destroy_common(msk, MPTCP_CF_FASTCLOSE);
WRITE_ONCE(msk->flags, 0);
msk->cb_flags = 0;
- msk->push_pending = 0;
msk->recovery = false;
- msk->can_ack = false;
- msk->fully_established = false;
- msk->rcv_data_fin = false;
- msk->snd_data_fin_enable = false;
- msk->rcv_fastclose = false;
- msk->use_64bit_ack = false;
- msk->bytes_consumed = 0;
+ WRITE_ONCE(msk->can_ack, false);
+ WRITE_ONCE(msk->fully_established, false);
+ WRITE_ONCE(msk->rcv_data_fin, false);
+ WRITE_ONCE(msk->snd_data_fin_enable, false);
+ WRITE_ONCE(msk->rcv_fastclose, false);
+ WRITE_ONCE(msk->use_64bit_ack, false);
WRITE_ONCE(msk->csum_enabled, mptcp_is_checksum_enabled(sock_net(sk)));
mptcp_pm_data_reset(msk);
mptcp_ca_reset(sk);
+ msk->bytes_consumed = 0;
msk->bytes_acked = 0;
msk->bytes_received = 0;
msk->bytes_sent = 0;
msk->bytes_retrans = 0;
+ msk->rcvspace_init = 0;
WRITE_ONCE(sk->sk_shutdown, 0);
sk_error_report(sk);
@@ -3183,6 +3191,7 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
{
struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
struct sock *nsk = sk_clone_lock(sk, GFP_ATOMIC);
+ struct mptcp_subflow_context *subflow;
struct mptcp_sock *msk;
if (!nsk)
@@ -3196,17 +3205,17 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
__mptcp_init_sock(nsk);
msk = mptcp_sk(nsk);
- msk->local_key = subflow_req->local_key;
- msk->token = subflow_req->token;
+ WRITE_ONCE(msk->local_key, subflow_req->local_key);
+ WRITE_ONCE(msk->token, subflow_req->token);
msk->in_accept_queue = 1;
WRITE_ONCE(msk->fully_established, false);
if (mp_opt->suboptions & OPTION_MPTCP_CSUMREQD)
WRITE_ONCE(msk->csum_enabled, true);
- msk->write_seq = subflow_req->idsn + 1;
- msk->snd_nxt = msk->write_seq;
- msk->snd_una = msk->write_seq;
- msk->wnd_end = msk->snd_nxt + req->rsk_rcv_wnd;
+ WRITE_ONCE(msk->write_seq, subflow_req->idsn + 1);
+ WRITE_ONCE(msk->snd_nxt, msk->write_seq);
+ WRITE_ONCE(msk->snd_una, msk->write_seq);
+ WRITE_ONCE(msk->wnd_end, msk->snd_nxt + req->rsk_rcv_wnd);
msk->setsockopt_seq = mptcp_sk(sk)->setsockopt_seq;
mptcp_init_sched(msk, mptcp_sk(sk)->sched);
@@ -3223,7 +3232,8 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
/* The msk maintain a ref to each subflow in the connections list */
WRITE_ONCE(msk->first, ssk);
- list_add(&mptcp_subflow_ctx(ssk)->node, &msk->conn_list);
+ subflow = mptcp_subflow_ctx(ssk);
+ list_add(&subflow->node, &msk->conn_list);
sock_hold(ssk);
/* new mpc subflow takes ownership of the newly
@@ -3238,6 +3248,9 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
__mptcp_propagate_sndbuf(nsk, ssk);
mptcp_rcv_space_init(msk, ssk);
+
+ if (mp_opt->suboptions & OPTION_MPTCP_MPC_ACK)
+ __mptcp_subflow_fully_established(msk, subflow, mp_opt);
bh_unlock_sock(nsk);
/* note: the newly allocated socket refcount is 2 now */
@@ -3248,6 +3261,7 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk)
{
const struct tcp_sock *tp = tcp_sk(ssk);
+ msk->rcvspace_init = 1;
msk->rcvq_space.copied = 0;
msk->rcvq_space.rtt_us = 0;
@@ -3258,8 +3272,6 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk)
TCP_INIT_CWND * tp->advmss);
if (msk->rcvq_space.space == 0)
msk->rcvq_space.space = TCP_INIT_CWND * TCP_MSS_DEFAULT;
-
- WRITE_ONCE(msk->wnd_end, msk->snd_nxt + tcp_sk(ssk)->snd_wnd);
}
void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags)
@@ -3306,9 +3318,6 @@ void __mptcp_data_acked(struct sock *sk)
__mptcp_clean_una(sk);
else
__set_bit(MPTCP_CLEAN_UNA, &mptcp_sk(sk)->cb_flags);
-
- if (mptcp_pending_data_fin_ack(sk))
- mptcp_schedule_work(sk);
}
void __mptcp_check_push(struct sock *sk, struct sock *ssk)
@@ -3333,8 +3342,7 @@ static void mptcp_release_cb(struct sock *sk)
struct mptcp_sock *msk = mptcp_sk(sk);
for (;;) {
- unsigned long flags = (msk->cb_flags & MPTCP_FLAGS_PROCESS_CTX_NEED) |
- msk->push_pending;
+ unsigned long flags = (msk->cb_flags & MPTCP_FLAGS_PROCESS_CTX_NEED);
struct list_head join_list;
if (!flags)
@@ -3350,7 +3358,6 @@ static void mptcp_release_cb(struct sock *sk)
* datapath acquires the msk socket spinlock while helding
* the subflow socket lock
*/
- msk->push_pending = 0;
msk->cb_flags &= ~flags;
spin_unlock_bh(&sk->sk_lock.slock);
@@ -3478,13 +3485,8 @@ void mptcp_finish_connect(struct sock *ssk)
* accessing the field below
*/
WRITE_ONCE(msk->local_key, subflow->local_key);
- WRITE_ONCE(msk->write_seq, subflow->idsn + 1);
- WRITE_ONCE(msk->snd_nxt, msk->write_seq);
- WRITE_ONCE(msk->snd_una, msk->write_seq);
mptcp_pm_new_connection(msk, ssk, 0);
-
- mptcp_rcv_space_init(msk, ssk);
}
void mptcp_sock_graft(struct sock *sk, struct socket *parent)
generated by cgit v1.2.3 (git 2.46.0) at 2025-09-07 22:49:24 +0000