#include <net/transp_v6.h>
#endif
#include <net/mptcp.h>
+#include <net/xfrm.h>
#include "protocol.h"
#include "mib.h"
static struct percpu_counter mptcp_sockets_allocated;
+static void __mptcp_destroy_sock(struct sock *sk);
+
/* If msk has an initial subflow socket, and the MP_CAPABLE handshake has not
* completed yet or has failed, return the subflow socket.
* Otherwise return NULL.
msk->subflow = ssock;
subflow = mptcp_subflow_ctx(ssock->sk);
list_add(&subflow->node, &msk->conn_list);
+ sock_hold(ssock->sk);
subflow->request_mptcp = 1;
/* accept() will wait on first subflow sk_wq, and we always wakes up
mptcp_sk(sk)->timer_ival = 0;
}
+static void mptcp_close_wake_up(struct sock *sk)
+{
+ if (sock_flag(sk, SOCK_DEAD))
+ return;
+
+ sk->sk_state_change(sk);
+ if (sk->sk_shutdown == SHUTDOWN_MASK ||
+ sk->sk_state == TCP_CLOSE)
+ sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP);
+ else
+ sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
+}
+
static void mptcp_check_data_fin_ack(struct sock *sk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
switch (sk->sk_state) {
case TCP_FIN_WAIT1:
inet_sk_state_store(sk, TCP_FIN_WAIT2);
- sk->sk_state_change(sk);
break;
case TCP_CLOSING:
case TCP_LAST_ACK:
inet_sk_state_store(sk, TCP_CLOSE);
- sk->sk_state_change(sk);
break;
}
- if (sk->sk_shutdown == SHUTDOWN_MASK ||
- sk->sk_state == TCP_CLOSE)
- sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP);
- else
- sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
+ mptcp_close_wake_up(sk);
}
}
break;
case TCP_FIN_WAIT2:
inet_sk_state_store(sk, TCP_CLOSE);
- // @@ Close subflows now?
break;
default:
/* Other states not expected */
release_sock(ssk);
}
- sk->sk_state_change(sk);
-
- if (sk->sk_shutdown == SHUTDOWN_MASK ||
- sk->sk_state == TCP_CLOSE)
- sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP);
- else
- sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
+ mptcp_close_wake_up(sk);
}
}
struct inet_connection_sock *icsk = inet_csk(sk);
unsigned long tout;
+ /* prevent rescheduling on close */
+ if (unlikely(inet_sk_state_load(sk) == TCP_CLOSE))
+ return;
+
/* should never be called with mptcp level timer cleared */
tout = READ_ONCE(mptcp_sk(sk)->timer_ival);
if (WARN_ON_ONCE(!tout))
mptcp_for_each_subflow(msk, subflow)
receivers += !subflow->rx_eof;
+ if (receivers)
+ return;
- if (!receivers && !(sk->sk_shutdown & RCV_SHUTDOWN)) {
+ if (!(sk->sk_shutdown & RCV_SHUTDOWN)) {
/* hopefully temporary hack: propagate shutdown status
* to msk, when all subflows agree on it
*/
set_bit(MPTCP_DATA_READY, &msk->flags);
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:
+ /* fallback sockets skip TCP_CLOSING - TCP will take care */
+ inet_sk_state_store(sk, TCP_CLOSE);
+ break;
+ default:
+ return;
+ }
+ mptcp_close_wake_up(sk);
}
static bool mptcp_ext_cache_refill(struct mptcp_sock *msk)
sock_put(sk);
}
+static void mptcp_timeout_timer(struct timer_list *t)
+{
+ struct sock *sk = from_timer(sk, t, sk_timer);
+
+ mptcp_schedule_work(sk);
+}
+
/* Find an idle subflow. Return NULL if there is unacked data at tcp
* level.
*
* parent socket.
*/
void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
- struct mptcp_subflow_context *subflow,
- long timeout)
+ struct mptcp_subflow_context *subflow)
{
- struct socket *sock = READ_ONCE(ssk->sk_socket);
+ bool dispose_socket = false;
+ struct socket *sock;
list_del(&subflow->node);
- if (sock && sock != sk->sk_socket) {
- /* outgoing subflow */
- sock_release(sock);
+ lock_sock(ssk);
+
+ /* if we are invoked by the msk cleanup code, the subflow is
+ * already orphaned
+ */
+ sock = ssk->sk_socket;
+ if (sock) {
+ dispose_socket = sock != sk->sk_socket;
+ sock_orphan(ssk);
+ }
+
+ /* if ssk hit tcp_done(), tcp_cleanup_ulp() cleared the related ops
+ * the ssk has been already destroyed, we just need to release the
+ * reference owned by msk;
+ */
+ if (!inet_csk(ssk)->icsk_ulp_ops) {
+ kfree_rcu(subflow, rcu);
} else {
- /* incoming subflow */
- tcp_close(ssk, timeout);
+ /* otherwise ask tcp do dispose of ssk and subflow ctx */
+ subflow->disposable = 1;
+ __tcp_close(ssk, 0);
+
+ /* close acquired an extra ref */
+ __sock_put(ssk);
}
+ release_sock(ssk);
+ if (dispose_socket)
+ iput(SOCK_INODE(sock));
+
+ sock_put(ssk);
}
static unsigned int mptcp_sync_mss(struct sock *sk, u32 pmtu)
if (inet_sk_state_load(ssk) != TCP_CLOSE)
continue;
- __mptcp_close_ssk((struct sock *)msk, ssk, subflow, 0);
+ __mptcp_close_ssk((struct sock *)msk, ssk, subflow);
}
}
+static bool mptcp_check_close_timeout(const struct sock *sk)
+{
+ s32 delta = tcp_jiffies32 - inet_csk(sk)->icsk_mtup.probe_timestamp;
+ struct mptcp_subflow_context *subflow;
+
+ if (delta >= TCP_TIMEWAIT_LEN)
+ return true;
+
+ /* if all subflows are in closed status don't bother with additional
+ * timeout
+ */
+ mptcp_for_each_subflow(mptcp_sk(sk), subflow) {
+ if (inet_sk_state_load(mptcp_subflow_tcp_sock(subflow)) !=
+ TCP_CLOSE)
+ return false;
+ }
+ return true;
+}
+
static void mptcp_worker(struct work_struct *work)
{
struct mptcp_sock *msk = container_of(work, struct mptcp_sock, work);
struct msghdr msg = {
.msg_flags = MSG_DONTWAIT,
};
- int ret;
+ int state, ret;
lock_sock(sk);
+ set_bit(MPTCP_WORKER_RUNNING, &msk->flags);
+ state = sk->sk_state;
+ if (unlikely(state == TCP_CLOSE))
+ goto unlock;
+
mptcp_clean_una_wakeup(sk);
mptcp_check_data_fin_ack(sk);
__mptcp_flush_join_list(msk);
mptcp_check_data_fin(sk);
+ /* if the msk data is completely acked, or the socket timedout,
+ * there is no point in keeping around an orphaned sk
+ */
+ if (sock_flag(sk, SOCK_DEAD) &&
+ (mptcp_check_close_timeout(sk) ||
+ (state != sk->sk_state &&
+ ((1 << inet_sk_state_load(sk)) & (TCPF_CLOSE | TCPF_FIN_WAIT2))))) {
+ inet_sk_state_store(sk, TCP_CLOSE);
+ __mptcp_destroy_sock(sk);
+ goto unlock;
+ }
+
if (!test_and_clear_bit(MPTCP_WORK_RTX, &msk->flags))
goto unlock;
mptcp_reset_timer(sk);
unlock:
+ clear_bit(MPTCP_WORKER_RUNNING, &msk->flags);
release_sock(sk);
sock_put(sk);
}
/* re-use the csk retrans timer for MPTCP-level retrans */
timer_setup(&msk->sk.icsk_retransmit_timer, mptcp_retransmit_timer, 0);
-
+ timer_setup(&sk->sk_timer, mptcp_timeout_timer, 0);
return 0;
}
{
struct mptcp_sock *msk = mptcp_sk(sk);
- if (cancel_work_sync(&msk->work))
- sock_put(sk);
+ /* if called by the work itself, do not try to cancel the work, or
+ * we will hang.
+ */
+ if (!test_bit(MPTCP_WORKER_RUNNING, &msk->flags) &&
+ cancel_work_sync(&msk->work))
+ __sock_put(sk);
}
void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how)
return next & TCP_ACTION_FIN;
}
-static void mptcp_close(struct sock *sk, long timeout)
+static void __mptcp_check_send_data_fin(struct sock *sk)
{
- struct mptcp_subflow_context *subflow, *tmp;
+ struct mptcp_subflow_context *subflow;
struct mptcp_sock *msk = mptcp_sk(sk);
- LIST_HEAD(conn_list);
- lock_sock(sk);
- sk->sk_shutdown = SHUTDOWN_MASK;
+ pr_debug("msk=%p snd_data_fin_enable=%d pending=%d snd_nxt=%llu write_seq=%llu",
+ msk, msk->snd_data_fin_enable, !!mptcp_send_head(sk),
+ msk->snd_nxt, msk->write_seq);
- if (sk->sk_state == TCP_LISTEN) {
+ /* we still need to enqueue subflows or not really shutting down,
+ * skip this
+ */
+ if (!msk->snd_data_fin_enable || msk->snd_nxt + 1 != msk->write_seq ||
+ mptcp_send_head(sk))
+ return;
+
+ WRITE_ONCE(msk->snd_nxt, msk->write_seq);
+
+ /* fallback socket will not get data_fin/ack, can move to close now */
+ if (__mptcp_check_fallback(msk) && sk->sk_state == TCP_LAST_ACK) {
inet_sk_state_store(sk, TCP_CLOSE);
- goto cleanup;
- } else if (sk->sk_state == TCP_CLOSE) {
- goto cleanup;
+ mptcp_close_wake_up(sk);
}
- if (__mptcp_check_fallback(msk)) {
- goto update_state;
- } else if (mptcp_close_state(sk)) {
- pr_debug("Sending DATA_FIN sk=%p", sk);
- WRITE_ONCE(msk->write_seq, msk->write_seq + 1);
- WRITE_ONCE(msk->snd_data_fin_enable, 1);
-
- mptcp_for_each_subflow(msk, subflow) {
- struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow);
+ __mptcp_flush_join_list(msk);
+ mptcp_for_each_subflow(msk, subflow) {
+ struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow);
- mptcp_subflow_shutdown(sk, tcp_sk, SHUTDOWN_MASK);
- }
+ mptcp_subflow_shutdown(sk, tcp_sk, SEND_SHUTDOWN);
}
+}
- sk_stream_wait_close(sk, timeout);
+static void __mptcp_wr_shutdown(struct sock *sk)
+{
+ struct mptcp_sock *msk = mptcp_sk(sk);
-update_state:
- inet_sk_state_store(sk, TCP_CLOSE);
+ pr_debug("msk=%p snd_data_fin_enable=%d shutdown=%x state=%d pending=%d",
+ msk, msk->snd_data_fin_enable, sk->sk_shutdown, sk->sk_state,
+ !!mptcp_send_head(sk));
+
+ /* will be ignored by fallback sockets */
+ WRITE_ONCE(msk->write_seq, msk->write_seq + 1);
+ WRITE_ONCE(msk->snd_data_fin_enable, 1);
+
+ __mptcp_check_send_data_fin(sk);
+}
+
+static void __mptcp_destroy_sock(struct sock *sk)
+{
+ struct mptcp_subflow_context *subflow, *tmp;
+ struct mptcp_sock *msk = mptcp_sk(sk);
+ LIST_HEAD(conn_list);
+
+ pr_debug("msk=%p", msk);
-cleanup:
/* be sure to always acquire the join list lock, to sync vs
* mptcp_finish_join().
*/
list_splice_init(&msk->conn_list, &conn_list);
__mptcp_clear_xmit(sk);
-
- release_sock(sk);
+ sk_stop_timer(sk, &sk->sk_timer);
+ msk->pm.status = 0;
list_for_each_entry_safe(subflow, tmp, &conn_list, node) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
- __mptcp_close_ssk(sk, ssk, subflow, timeout);
+ __mptcp_close_ssk(sk, ssk, subflow);
}
- mptcp_cancel_work(sk);
+ sk->sk_prot->destroy(sk);
- __skb_queue_purge(&sk->sk_receive_queue);
+ sk_stream_kill_queues(sk);
+ xfrm_sk_free_policy(sk);
+ sk_refcnt_debug_release(sk);
+ sock_put(sk);
+}
+
+static void mptcp_close(struct sock *sk, long timeout)
+{
+ struct mptcp_subflow_context *subflow;
+ bool do_cancel_work = false;
+
+ lock_sock(sk);
+ sk->sk_shutdown = SHUTDOWN_MASK;
+
+ if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) {
+ inet_sk_state_store(sk, TCP_CLOSE);
+ goto cleanup;
+ }
- sk_common_release(sk);
+ if (mptcp_close_state(sk))
+ __mptcp_wr_shutdown(sk);
+
+ sk_stream_wait_close(sk, timeout);
+
+cleanup:
+ /* orphan all the subflows */
+ inet_csk(sk)->icsk_mtup.probe_timestamp = tcp_jiffies32;
+ list_for_each_entry(subflow, &mptcp_sk(sk)->conn_list, node) {
+ struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+ bool slow, dispose_socket;
+ struct socket *sock;
+
+ slow = lock_sock_fast(ssk);
+ sock = ssk->sk_socket;
+ dispose_socket = sock && sock != sk->sk_socket;
+ sock_orphan(ssk);
+ unlock_sock_fast(ssk, slow);
+
+ /* for the outgoing subflows we additionally need to free
+ * the associated socket
+ */
+ if (dispose_socket)
+ iput(SOCK_INODE(sock));
+ }
+ sock_orphan(sk);
+
+ sock_hold(sk);
+ pr_debug("msk=%p state=%d", sk, sk->sk_state);
+ if (sk->sk_state == TCP_CLOSE) {
+ __mptcp_destroy_sock(sk);
+ do_cancel_work = true;
+ } else {
+ sk_reset_timer(sk, &sk->sk_timer, jiffies + TCP_TIMEWAIT_LEN);
+ }
+ release_sock(sk);
+ if (do_cancel_work)
+ mptcp_cancel_work(sk);
+ sock_put(sk);
}
static void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk)
newsk = new_mptcp_sock;
mptcp_copy_inaddrs(newsk, ssk);
list_add(&subflow->node, &msk->conn_list);
+ sock_hold(ssk);
mptcp_rcv_space_init(msk, ssk);
bh_unlock_sock(new_mptcp_sock);
write_unlock_bh(&sk->sk_callback_lock);
}
-bool mptcp_finish_join(struct sock *sk)
+bool mptcp_finish_join(struct sock *ssk)
{
- struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
struct mptcp_sock *msk = mptcp_sk(subflow->conn);
struct sock *parent = (void *)msk;
struct socket *parent_sock;
/* active connections are already on conn_list, and we can't acquire
* msk lock here.
* use the join list lock as synchronization point and double-check
- * msk status to avoid racing with mptcp_close()
+ * msk status to avoid racing with __mptcp_destroy_sock()
*/
spin_lock_bh(&msk->join_list_lock);
ret = inet_sk_state_load(parent) == TCP_ESTABLISHED;
- if (ret && !WARN_ON_ONCE(!list_empty(&subflow->node)))
+ if (ret && !WARN_ON_ONCE(!list_empty(&subflow->node))) {
list_add_tail(&subflow->node, &msk->join_list);
+ sock_hold(ssk);
+ }
spin_unlock_bh(&msk->join_list_lock);
if (!ret)
return false;
* at close time
*/
parent_sock = READ_ONCE(parent->sk_socket);
- if (parent_sock && !sk->sk_socket)
- mptcp_sock_graft(sk, parent_sock);
+ if (parent_sock && !ssk->sk_socket)
+ mptcp_sock_graft(ssk, parent_sock);
subflow->map_seq = READ_ONCE(msk->ack_seq);
return true;
}
static int mptcp_shutdown(struct socket *sock, int how)
{
struct mptcp_sock *msk = mptcp_sk(sock->sk);
- struct mptcp_subflow_context *subflow;
+ struct sock *sk = sock->sk;
int ret = 0;
pr_debug("sk=%p, how=%d", msk, how);
- lock_sock(sock->sk);
+ lock_sock(sk);
how++;
if ((how & ~SHUTDOWN_MASK) || !how) {
}
if (sock->state == SS_CONNECTING) {
- if ((1 << sock->sk->sk_state) &
+ if ((1 << sk->sk_state) &
(TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_CLOSE))
sock->state = SS_DISCONNECTING;
else
sock->state = SS_CONNECTED;
}
- /* If we've already sent a FIN, or it's a closed state, skip this. */
- if (__mptcp_check_fallback(msk)) {
- if (how == SHUT_WR || how == SHUT_RDWR)
- inet_sk_state_store(sock->sk, TCP_FIN_WAIT1);
-
- mptcp_for_each_subflow(msk, subflow) {
- struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow);
-
- mptcp_subflow_shutdown(sock->sk, tcp_sk, how);
- }
- } else if ((how & SEND_SHUTDOWN) &&
- ((1 << sock->sk->sk_state) &
- (TCPF_ESTABLISHED | TCPF_SYN_SENT |
- TCPF_SYN_RECV | TCPF_CLOSE_WAIT)) &&
- mptcp_close_state(sock->sk)) {
- __mptcp_flush_join_list(msk);
-
- WRITE_ONCE(msk->write_seq, msk->write_seq + 1);
- WRITE_ONCE(msk->snd_data_fin_enable, 1);
-
- mptcp_for_each_subflow(msk, subflow) {
- struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow);
-
- mptcp_subflow_shutdown(sock->sk, tcp_sk, how);
- }
- }
+ sk->sk_shutdown |= how;
+ if ((how & SEND_SHUTDOWN) && mptcp_close_state(sk))
+ __mptcp_wr_shutdown(sk);
/* Wake up anyone sleeping in poll. */
- sock->sk->sk_state_change(sock->sk);
+ sk->sk_state_change(sk);
out_unlock:
- release_sock(sock->sk);
+ release_sock(sk);
return ret;
}
OSDN Git Service
