1 files changed, 59 insertions, 29 deletions

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 29a2d690d8d5..632350018fb6 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -280,11 +280,13 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,
 
 	/* try to fetch required memory from subflow */
 	if (!sk_rmem_schedule(sk, skb, skb->truesize)) {
-		if (ssk->sk_forward_alloc < skb->truesize)
-			goto drop;
-		__sk_mem_reclaim(ssk, skb->truesize);
-		if (!sk_rmem_schedule(sk, skb, skb->truesize))
+		int amount = sk_mem_pages(skb->truesize) << SK_MEM_QUANTUM_SHIFT;
+
+		if (ssk->sk_forward_alloc < amount)
 			goto drop;
+
+		ssk->sk_forward_alloc -= amount;
+		sk->sk_forward_alloc += amount;
 	}
 
 	/* the skb map_seq accounts for the skb offset:
@@ -668,18 +670,22 @@ static bool __mptcp_ofo_queue(struct mptcp_sock *msk)
 /* In most cases we will be able to lock the mptcp socket.  If its already
  * owned, we need to defer to the work queue to avoid ABBA deadlock.
  */
-static void move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk)
+static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk)
 {
 	struct sock *sk = (struct sock *)msk;
 	unsigned int moved = 0;
 
 	if (inet_sk_state_load(sk) == TCP_CLOSE)
-		return;
-
-	mptcp_data_lock(sk);
+		return false;
 
 	__mptcp_move_skbs_from_subflow(msk, ssk, &moved);
 	__mptcp_ofo_queue(msk);
+	if (unlikely(ssk->sk_err)) {
+		if (!sock_owned_by_user(sk))
+			__mptcp_error_report(sk);
+		else
+			set_bit(MPTCP_ERROR_REPORT,  &msk->flags);
+	}
 
 	/* If the moves have caught up with the DATA_FIN sequence number
 	 * it's time to ack the DATA_FIN and change socket state, but
@@ -688,7 +694,7 @@ static void move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk)
 	 */
 	if (mptcp_pending_data_fin(sk, NULL))
 		mptcp_schedule_work(sk);
-	mptcp_data_unlock(sk);
+	return moved > 0;
 }
 
 void mptcp_data_ready(struct sock *sk, struct sock *ssk)
@@ -696,7 +702,6 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk)
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	int sk_rbuf, ssk_rbuf;
-	bool wake;
 
 	/* The peer can send data while we are shutting down this
 	 * subflow at msk destruction time, but we must avoid enqueuing
@@ -705,28 +710,22 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk)
 	if (unlikely(subflow->disposable))
 		return;
 
-	/* move_skbs_to_msk below can legitly clear the data_avail flag,
-	 * but we will need later to properly woke the reader, cache its
-	 * value
-	 */
-	wake = subflow->data_avail == MPTCP_SUBFLOW_DATA_AVAIL;
-	if (wake)
-		set_bit(MPTCP_DATA_READY, &msk->flags);
-
 	ssk_rbuf = READ_ONCE(ssk->sk_rcvbuf);
 	sk_rbuf = READ_ONCE(sk->sk_rcvbuf);
 	if (unlikely(ssk_rbuf > sk_rbuf))
 		sk_rbuf = ssk_rbuf;
 
-	/* over limit? can't append more skbs to msk */
+	/* over limit? can't append more skbs to msk, Also, no need to wake-up*/
 	if (atomic_read(&sk->sk_rmem_alloc) > sk_rbuf)
-		goto wake;
-
-	move_skbs_to_msk(msk, ssk);
+		return;
 
-wake:
-	if (wake)
+	/* Wake-up the reader only for in-sequence data */
+	mptcp_data_lock(sk);
+	if (move_skbs_to_msk(msk, ssk)) {
+		set_bit(MPTCP_DATA_READY, &msk->flags);
 		sk->sk_data_ready(sk);
+	}
+	mptcp_data_unlock(sk);
 }
 
 static bool mptcp_do_flush_join_list(struct mptcp_sock *msk)
@@ -858,7 +857,7 @@ static struct sock *mptcp_subflow_recv_lookup(const struct mptcp_sock *msk)
 	sock_owned_by_me(sk);
 
 	mptcp_for_each_subflow(msk, subflow) {
-		if (subflow->data_avail)
+		if (READ_ONCE(subflow->data_avail))
 			return mptcp_subflow_tcp_sock(subflow);
 	}
 
@@ -879,12 +878,18 @@ static bool mptcp_skb_can_collapse_to(u64 write_seq,
 	       !mpext->frozen;
 }
 
+/* we can append data to the given data frag if:
+ * - there is space available in the backing page_frag
+ * - the data frag tail matches the current page_frag free offset
+ * - the data frag end sequence number matches the current write seq
+ */
 static bool mptcp_frag_can_collapse_to(const struct mptcp_sock *msk,
 				       const struct page_frag *pfrag,
 				       const struct mptcp_data_frag *df)
 {
 	return df && pfrag->page == df->page &&
 		pfrag->size - pfrag->offset > 0 &&
+		pfrag->offset == (df->offset + df->data_len) &&
 		df->data_seq + df->data_len == msk->write_seq;
 }
 
@@ -941,6 +946,10 @@ static void __mptcp_update_wmem(struct sock *sk)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
+#ifdef CONFIG_LOCKDEP
+	WARN_ON_ONCE(!lockdep_is_held(&sk->sk_lock.slock));
+#endif
+
 	if (!msk->wmem_reserved)
 		return;
 
@@ -1079,10 +1088,20 @@ out:
 
 static void __mptcp_clean_una_wakeup(struct sock *sk)
 {
+#ifdef CONFIG_LOCKDEP
+	WARN_ON_ONCE(!lockdep_is_held(&sk->sk_lock.slock));
+#endif
 	__mptcp_clean_una(sk);
 	mptcp_write_space(sk);
 }
 
+static void mptcp_clean_una_wakeup(struct sock *sk)
+{
+	mptcp_data_lock(sk);
+	__mptcp_clean_una_wakeup(sk);
+	mptcp_data_unlock(sk);
+}
+
 static void mptcp_enter_memory_pressure(struct sock *sk)
 {
 	struct mptcp_subflow_context *subflow;
@@ -1935,6 +1954,9 @@ static bool __mptcp_move_skbs(struct mptcp_sock *msk)
 		done = __mptcp_move_skbs_from_subflow(msk, ssk, &moved);
 		mptcp_data_unlock(sk);
 		tcp_cleanup_rbuf(ssk, moved);
+
+		if (unlikely(ssk->sk_err))
+			__mptcp_error_report(sk);
 		unlock_sock_fast(ssk, slowpath);
 	} while (!done);
 
@@ -2293,7 +2315,7 @@ static void __mptcp_retrans(struct sock *sk)
 	struct sock *ssk;
 	int ret;
 
-	__mptcp_clean_una_wakeup(sk);
+	mptcp_clean_una_wakeup(sk);
 	dfrag = mptcp_rtx_head(sk);
 	if (!dfrag) {
 		if (mptcp_data_fin_enabled(msk)) {
@@ -2418,13 +2440,12 @@ static int __mptcp_init_sock(struct sock *sk)
 	timer_setup(&msk->sk.icsk_retransmit_timer, mptcp_retransmit_timer, 0);
 	timer_setup(&sk->sk_timer, mptcp_timeout_timer, 0);
 
-	tcp_assign_congestion_control(sk);
-
 	return 0;
 }
 
 static int mptcp_init_sock(struct sock *sk)
 {
+	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct net *net = sock_net(sk);
 	int ret;
 
@@ -2442,6 +2463,16 @@ static int mptcp_init_sock(struct sock *sk)
 	if (ret)
 		return ret;
 
+	/* fetch the ca name; do it outside __mptcp_init_sock(), so that clone will
+	 * propagate the correct value
+	 */
+	tcp_assign_congestion_control(sk);
+	strcpy(mptcp_sk(sk)->ca_name, icsk->icsk_ca_ops->name);
+
+	/* no need to keep a reference to the ops, the name will suffice */
+	tcp_cleanup_congestion_control(sk);
+	icsk->icsk_ca_ops = NULL;
+
 	sk_sockets_allocated_inc(sk);
 	sk->sk_rcvbuf = sock_net(sk)->ipv4.sysctl_tcp_rmem[1];
 	sk->sk_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[1];
@@ -2616,7 +2647,6 @@ static void __mptcp_destroy_sock(struct sock *sk)
 	sk_stream_kill_queues(sk);
 	xfrm_sk_free_policy(sk);
 
-	tcp_cleanup_congestion_control(sk);
 	sk_refcnt_debug_release(sk);
 	mptcp_dispose_initial_subflow(msk);
 	sock_put(sk);