summaryrefslogtreecommitdiff
path: root/net/mptcp
diff options
context:
space:
mode:
authorJakub Kicinski <kuba@kernel.org>2023-06-22 18:40:38 -0700
committerJakub Kicinski <kuba@kernel.org>2023-06-22 18:40:38 -0700
commita7384f3918756c193e3fcd7e3111fc4bd3686013 (patch)
tree156fda862edf0154225e6a5d8d092b0f6fe35728 /net/mptcp
parent98e95872f2b818c74872d073eaa4c937579d41fc (diff)
parent8a28a0b6f1a1dcbf5a834600a9acfbe2ba51e5eb (diff)
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Cross-merge networking fixes after downstream PR. Conflicts: tools/testing/selftests/net/fcnal-test.sh d7a2fc1437f7 ("selftests: net: fcnal-test: check if FIPS mode is enabled") dd017c72dde6 ("selftests: fcnal: Test SO_DONTROUTE on TCP sockets.") https://lore.kernel.org/all/5007b52c-dd16-dbf6-8d64-b9701bfa498b@tessares.net/ https://lore.kernel.org/all/20230619105427.4a0df9b3@canb.auug.org.au/ No adjacent changes. Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'net/mptcp')
-rw-r--r--net/mptcp/pm_netlink.c1
-rw-r--r--net/mptcp/protocol.c160
-rw-r--r--net/mptcp/protocol.h5
-rw-r--r--net/mptcp/subflow.c17
4 files changed, 76 insertions, 107 deletions
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 547e51c65480..5692daf57a4d 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -1046,6 +1046,7 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk,
if (err)
return err;
+ inet_sk_state_store(newsk, TCP_LISTEN);
err = kernel_listen(ssock, backlog);
if (err)
return err;
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index f65eec3e0d22..bd023debedc8 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -44,7 +44,7 @@ enum {
static struct percpu_counter mptcp_sockets_allocated ____cacheline_aligned_in_smp;
static void __mptcp_destroy_sock(struct sock *sk);
-static void __mptcp_check_send_data_fin(struct sock *sk);
+static void mptcp_check_send_data_fin(struct sock *sk);
DEFINE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions);
static struct net_device mptcp_napi_dev;
@@ -426,8 +426,7 @@ static bool mptcp_pending_data_fin_ack(struct sock *sk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
- return !__mptcp_check_fallback(msk) &&
- ((1 << sk->sk_state) &
+ return ((1 << sk->sk_state) &
(TCPF_FIN_WAIT1 | TCPF_CLOSING | TCPF_LAST_ACK)) &&
msk->write_seq == READ_ONCE(msk->snd_una);
}
@@ -585,9 +584,6 @@ static bool mptcp_check_data_fin(struct sock *sk)
u64 rcv_data_fin_seq;
bool ret = false;
- if (__mptcp_check_fallback(msk))
- return ret;
-
/* Need to ack a DATA_FIN received from a peer while this side
* of the connection is in ESTABLISHED, FIN_WAIT1, or FIN_WAIT2.
* msk->rcv_data_fin was set when parsing the incoming options
@@ -625,7 +621,8 @@ static bool mptcp_check_data_fin(struct sock *sk)
}
ret = true;
- mptcp_send_ack(msk);
+ if (!__mptcp_check_fallback(msk))
+ mptcp_send_ack(msk);
mptcp_close_wake_up(sk);
}
return ret;
@@ -854,12 +851,12 @@ static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk)
return true;
}
-static void __mptcp_flush_join_list(struct sock *sk)
+static void __mptcp_flush_join_list(struct sock *sk, struct list_head *join_list)
{
struct mptcp_subflow_context *tmp, *subflow;
struct mptcp_sock *msk = mptcp_sk(sk);
- list_for_each_entry_safe(subflow, tmp, &msk->join_list, node) {
+ list_for_each_entry_safe(subflow, tmp, join_list, node) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
bool slow = lock_sock_fast(ssk);
@@ -901,49 +898,6 @@ bool mptcp_schedule_work(struct sock *sk)
return false;
}
-void mptcp_subflow_eof(struct sock *sk)
-{
- if (!test_and_set_bit(MPTCP_WORK_EOF, &mptcp_sk(sk)->flags))
- mptcp_schedule_work(sk);
-}
-
-static void mptcp_check_for_eof(struct mptcp_sock *msk)
-{
- struct mptcp_subflow_context *subflow;
- struct sock *sk = (struct sock *)msk;
- int receivers = 0;
-
- mptcp_for_each_subflow(msk, subflow)
- receivers += !subflow->rx_eof;
- if (receivers)
- return;
-
- if (!(sk->sk_shutdown & RCV_SHUTDOWN)) {
- /* hopefully temporary hack: propagate shutdown status
- * to msk, when all subflows agree on it
- */
- WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | RCV_SHUTDOWN);
-
- smp_mb__before_atomic(); /* SHUTDOWN must be visible first */
- sk->sk_data_ready(sk);
- }
-
- switch (sk->sk_state) {
- case TCP_ESTABLISHED:
- inet_sk_state_store(sk, TCP_CLOSE_WAIT);
- break;
- case TCP_FIN_WAIT1:
- inet_sk_state_store(sk, TCP_CLOSING);
- break;
- case TCP_FIN_WAIT2:
- inet_sk_state_store(sk, TCP_CLOSE);
- break;
- default:
- return;
- }
- mptcp_close_wake_up(sk);
-}
-
static struct sock *mptcp_subflow_recv_lookup(const struct mptcp_sock *msk)
{
struct mptcp_subflow_context *subflow;
@@ -1609,7 +1563,7 @@ out:
if (!mptcp_timer_pending(sk))
mptcp_reset_timer(sk);
if (do_check_data_fin)
- __mptcp_check_send_data_fin(sk);
+ mptcp_check_send_data_fin(sk);
}
static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk, bool first)
@@ -1727,7 +1681,13 @@ static int mptcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
if (ret && ret != -EINPROGRESS && ret != -ERESTARTSYS && ret != -EINTR)
*copied_syn = 0;
} else if (ret && ret != -EINPROGRESS) {
- mptcp_disconnect(sk, 0);
+ /* The disconnect() op called by tcp_sendmsg_fastopen()/
+ * __inet_stream_connect() can fail, due to looking check,
+ * see mptcp_disconnect().
+ * Attempt it again outside the problematic scope.
+ */
+ if (!mptcp_disconnect(sk, 0))
+ sk->sk_socket->state = SS_UNCONNECTED;
}
inet_sk(sk)->defer_connect = 0;
@@ -2158,9 +2118,6 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
break;
}
- if (test_and_clear_bit(MPTCP_WORK_EOF, &msk->flags))
- mptcp_check_for_eof(msk);
-
if (sk->sk_shutdown & RCV_SHUTDOWN) {
/* race breaker: the shutdown could be after the
* previous receive queue check
@@ -2389,7 +2346,10 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
need_push = (flags & MPTCP_CF_PUSH) && __mptcp_retransmit_pending_data(sk);
if (!dispose_it) {
- tcp_disconnect(ssk, 0);
+ /* The MPTCP code never wait on the subflow sockets, TCP-level
+ * disconnect should never fail
+ */
+ WARN_ON_ONCE(tcp_disconnect(ssk, 0));
msk->subflow->state = SS_UNCONNECTED;
mptcp_subflow_ctx_reset(subflow);
release_sock(ssk);
@@ -2408,13 +2368,6 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
kfree_rcu(subflow, rcu);
} else {
/* otherwise tcp will dispose of the ssk and subflow ctx */
- if (ssk->sk_state == TCP_LISTEN) {
- tcp_set_state(ssk, TCP_CLOSE);
- mptcp_subflow_queue_clean(sk, ssk);
- inet_csk_listen_stop(ssk);
- mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CLOSED);
- }
-
__tcp_close(ssk, 0);
/* close acquired an extra ref */
@@ -2673,16 +2626,12 @@ static void mptcp_worker(struct work_struct *work)
if (unlikely((1 << state) & (TCPF_CLOSE | TCPF_LISTEN)))
goto unlock;
- mptcp_check_data_fin_ack(sk);
-
mptcp_check_fastclose(msk);
mptcp_pm_nl_work(msk);
- if (test_and_clear_bit(MPTCP_WORK_EOF, &msk->flags))
- mptcp_check_for_eof(msk);
-
- __mptcp_check_send_data_fin(sk);
+ mptcp_check_send_data_fin(sk);
+ mptcp_check_data_fin_ack(sk);
mptcp_check_data_fin(sk);
if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags))
@@ -2814,13 +2763,19 @@ void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how)
break;
fallthrough;
case TCP_SYN_SENT:
- tcp_disconnect(ssk, O_NONBLOCK);
+ WARN_ON_ONCE(tcp_disconnect(ssk, O_NONBLOCK));
break;
default:
if (__mptcp_check_fallback(mptcp_sk(sk))) {
pr_debug("Fallback");
ssk->sk_shutdown |= how;
tcp_shutdown(ssk, how);
+
+ /* simulate the data_fin ack reception to let the state
+ * machine move forward
+ */
+ WRITE_ONCE(mptcp_sk(sk)->snd_una, mptcp_sk(sk)->snd_nxt);
+ mptcp_schedule_work(sk);
} else {
pr_debug("Sending DATA_FIN on subflow %p", ssk);
tcp_send_ack(ssk);
@@ -2860,7 +2815,7 @@ static int mptcp_close_state(struct sock *sk)
return next & TCP_ACTION_FIN;
}
-static void __mptcp_check_send_data_fin(struct sock *sk)
+static void mptcp_check_send_data_fin(struct sock *sk)
{
struct mptcp_subflow_context *subflow;
struct mptcp_sock *msk = mptcp_sk(sk);
@@ -2878,19 +2833,6 @@ static void __mptcp_check_send_data_fin(struct sock *sk)
WRITE_ONCE(msk->snd_nxt, msk->write_seq);
- /* fallback socket will not get data_fin/ack, can move to the next
- * state now
- */
- if (__mptcp_check_fallback(msk)) {
- WRITE_ONCE(msk->snd_una, msk->write_seq);
- if ((1 << sk->sk_state) & (TCPF_CLOSING | TCPF_LAST_ACK)) {
- inet_sk_state_store(sk, TCP_CLOSE);
- mptcp_close_wake_up(sk);
- } else if (sk->sk_state == TCP_FIN_WAIT1) {
- inet_sk_state_store(sk, TCP_FIN_WAIT2);
- }
- }
-
mptcp_for_each_subflow(msk, subflow) {
struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow);
@@ -2910,7 +2852,7 @@ static void __mptcp_wr_shutdown(struct sock *sk)
WRITE_ONCE(msk->write_seq, msk->write_seq + 1);
WRITE_ONCE(msk->snd_data_fin_enable, 1);
- __mptcp_check_send_data_fin(sk);
+ mptcp_check_send_data_fin(sk);
}
static void __mptcp_destroy_sock(struct sock *sk)
@@ -2954,10 +2896,24 @@ static __poll_t mptcp_check_readable(struct mptcp_sock *msk)
return EPOLLIN | EPOLLRDNORM;
}
-static void mptcp_listen_inuse_dec(struct sock *sk)
+static void mptcp_check_listen_stop(struct sock *sk)
{
- if (inet_sk_state_load(sk) == TCP_LISTEN)
- sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
+ struct sock *ssk;
+
+ if (inet_sk_state_load(sk) != TCP_LISTEN)
+ return;
+
+ sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
+ ssk = mptcp_sk(sk)->first;
+ if (WARN_ON_ONCE(!ssk || inet_sk_state_load(ssk) != TCP_LISTEN))
+ return;
+
+ lock_sock_nested(ssk, SINGLE_DEPTH_NESTING);
+ mptcp_subflow_queue_clean(sk, ssk);
+ inet_csk_listen_stop(ssk);
+ mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CLOSED);
+ tcp_set_state(ssk, TCP_CLOSE);
+ release_sock(ssk);
}
bool __mptcp_close(struct sock *sk, long timeout)
@@ -2970,7 +2926,7 @@ bool __mptcp_close(struct sock *sk, long timeout)
WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK);
if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) {
- mptcp_listen_inuse_dec(sk);
+ mptcp_check_listen_stop(sk);
inet_sk_state_store(sk, TCP_CLOSE);
goto cleanup;
}
@@ -3073,15 +3029,20 @@ static int mptcp_disconnect(struct sock *sk, int flags)
{
struct mptcp_sock *msk = mptcp_sk(sk);
+ /* Deny disconnect if other threads are blocked in sk_wait_event()
+ * or inet_wait_for_connect().
+ */
+ if (sk->sk_wait_pending)
+ return -EBUSY;
+
/* We are on the fastopen error path. We can't call straight into the
* subflows cleanup code due to lock nesting (we are already under
- * msk->firstsocket lock). Do nothing and leave the cleanup to the
- * caller.
+ * msk->firstsocket lock).
*/
if (msk->fastopening)
- return 0;
+ return -EBUSY;
- mptcp_listen_inuse_dec(sk);
+ mptcp_check_listen_stop(sk);
inet_sk_state_store(sk, TCP_CLOSE);
mptcp_stop_timer(sk);
@@ -3144,6 +3105,7 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
inet_sk(nsk)->pinet6 = mptcp_inet6_sk(nsk);
#endif
+ nsk->sk_wait_pending = 0;
__mptcp_init_sock(nsk);
msk = mptcp_sk(nsk);
@@ -3334,9 +3296,14 @@ static void mptcp_release_cb(struct sock *sk)
for (;;) {
unsigned long flags = (msk->cb_flags & MPTCP_FLAGS_PROCESS_CTX_NEED) |
msk->push_pending;
+ struct list_head join_list;
+
if (!flags)
break;
+ INIT_LIST_HEAD(&join_list);
+ list_splice_init(&msk->join_list, &join_list);
+
/* the following actions acquire the subflow socket lock
*
* 1) can't be invoked in atomic scope
@@ -3347,8 +3314,9 @@ static void mptcp_release_cb(struct sock *sk)
msk->push_pending = 0;
msk->cb_flags &= ~flags;
spin_unlock_bh(&sk->sk_lock.slock);
+
if (flags & BIT(MPTCP_FLUSH_JOIN_LIST))
- __mptcp_flush_join_list(sk);
+ __mptcp_flush_join_list(sk, &join_list);
if (flags & BIT(MPTCP_PUSH_PENDING))
__mptcp_push_pending(sk, 0);
if (flags & BIT(MPTCP_RETRANSMIT))
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 3a1a64cdeba6..37fbe22e2433 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -113,7 +113,6 @@
/* MPTCP socket atomic flags */
#define MPTCP_NOSPACE 1
#define MPTCP_WORK_RTX 2
-#define MPTCP_WORK_EOF 3
#define MPTCP_FALLBACK_DONE 4
#define MPTCP_WORK_CLOSE_SUBFLOW 5
@@ -481,14 +480,13 @@ struct mptcp_subflow_context {
send_mp_fail : 1,
send_fastclose : 1,
send_infinite_map : 1,
- rx_eof : 1,
remote_key_valid : 1, /* received the peer key from */
disposable : 1, /* ctx can be free at ulp release time */
stale : 1, /* unable to snd/rcv data, do not use for xmit */
local_id_valid : 1, /* local_id is correctly initialized */
valid_csum_seen : 1, /* at least one csum validated */
is_mptfo : 1, /* subflow is doing TFO */
- __unused : 8;
+ __unused : 9;
enum mptcp_data_avail data_avail;
u32 remote_nonce;
u64 thmac;
@@ -728,7 +726,6 @@ static inline u64 mptcp_expand_seq(u64 old_seq, u64 cur_seq, bool use_64bit)
void __mptcp_check_push(struct sock *sk, struct sock *ssk);
void __mptcp_data_acked(struct sock *sk);
void __mptcp_error_report(struct sock *sk);
-void mptcp_subflow_eof(struct sock *sk);
bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq, bool use_64bit);
static inline bool mptcp_data_fin_enabled(const struct mptcp_sock *msk)
{
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 222dfcdadf2e..285e8ff74277 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -1751,14 +1751,16 @@ static void subflow_state_change(struct sock *sk)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
struct sock *parent = subflow->conn;
+ struct mptcp_sock *msk;
__subflow_state_change(sk);
+ msk = mptcp_sk(parent);
if (subflow_simultaneous_connect(sk)) {
mptcp_propagate_sndbuf(parent, sk);
mptcp_do_fallback(sk);
- mptcp_rcv_space_init(mptcp_sk(parent), sk);
- pr_fallback(mptcp_sk(parent));
+ mptcp_rcv_space_init(msk, sk);
+ pr_fallback(msk);
subflow->conn_finished = 1;
mptcp_set_connected(parent);
}
@@ -1774,11 +1776,12 @@ static void subflow_state_change(struct sock *sk)
subflow_sched_work_if_closed(mptcp_sk(parent), sk);
- if (__mptcp_check_fallback(mptcp_sk(parent)) &&
- !subflow->rx_eof && subflow_is_done(sk)) {
- subflow->rx_eof = 1;
- mptcp_subflow_eof(parent);
- }
+ /* when the fallback subflow closes the rx side, trigger a 'dummy'
+ * ingress data fin, so that the msk state will follow along
+ */
+ if (__mptcp_check_fallback(msk) && subflow_is_done(sk) && msk->first == sk &&
+ mptcp_update_rcv_data_fin(msk, READ_ONCE(msk->ack_seq), true))
+ mptcp_schedule_work(parent);
}
void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_ssk)