Merge branch 'mptcp-fixes'

Mat Martineau says:

====================
mptcp: Miscellaneous fixes

Here are five changes we've collected and tested in the mptcp-tree:

Patch 1 changes handling of the MPTCP-level snd_next value during the
recovery phase after a subflow link failure.

Patches 2 and 3 are some small refactoring changes to replace some
open-coded bits.

Patch 4 removes an unused field in struct mptcp_sock.

Patch 5 restarts the MPTCP retransmit timer when there is
not-yet-transmitted data to send and all previously sent data has been
acknowledged. This prevents some sending stalls.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 56 insertions, 35 deletions

diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index c41273cefc51..422f4acfb3e6 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -748,9 +748,7 @@ static bool mptcp_established_options_mp_prio(struct sock *sk,
 	/* can't send MP_PRIO with MPC, as they share the same option space:
 	 * 'backup'. Also it makes no sense at all
 	 */
-	if (!subflow->send_mp_prio ||
-	    ((OPTION_MPTCP_MPC_SYN | OPTION_MPTCP_MPC_SYNACK |
-	      OPTION_MPTCP_MPC_ACK) & opts->suboptions))
+	if (!subflow->send_mp_prio || (opts->suboptions & OPTIONS_MPTCP_MPC))
 		return false;
 
 	/* account for the trailing 'nop' option */
@@ -1019,11 +1017,9 @@ static void ack_update_msk(struct mptcp_sock *msk,
 	old_snd_una = msk->snd_una;
 	new_snd_una = mptcp_expand_seq(old_snd_una, mp_opt->data_ack, mp_opt->ack64);
 
-	/* ACK for data not even sent yet and even above recovery bound? Ignore.*/
-	if (unlikely(after64(new_snd_una, snd_nxt))) {
-		if (!msk->recovery || after64(new_snd_una, msk->recovery_snd_nxt))
-			new_snd_una = old_snd_una;
-	}
+	/* ACK for data not even sent yet? Ignore.*/
+	if (unlikely(after64(new_snd_una, snd_nxt)))
+		new_snd_una = old_snd_una;
 
 	new_wnd_end = new_snd_una + tcp_sk(ssk)->snd_wnd;
 
@@ -1329,8 +1325,7 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
 						   TCPOPT_NOP << 8 | TCPOPT_NOP, ptr);
 			}
 		}
-	} else if ((OPTION_MPTCP_MPC_SYN | OPTION_MPTCP_MPC_SYNACK |
-		    OPTION_MPTCP_MPC_ACK) & opts->suboptions) {
+	} else if (OPTIONS_MPTCP_MPC & opts->suboptions) {
 		u8 len, flag = MPTCP_CAP_HMAC_SHA256;
 
 		if (OPTION_MPTCP_MPC_SYN & opts->suboptions) {
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 7e5f76092b64..8029bbbe1c9e 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -956,9 +956,7 @@ 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
+	lockdep_assert_held_once(&sk->sk_lock.slock);
 
 	if (!msk->wmem_reserved)
 		return;
@@ -1107,7 +1105,8 @@ out:
 	if (cleaned && tcp_under_memory_pressure(sk))
 		__mptcp_mem_reclaim_partial(sk);
 
-	if (snd_una == READ_ONCE(msk->snd_nxt) && !msk->recovery) {
+	if (snd_una == READ_ONCE(msk->snd_nxt) &&
+	    snd_una == READ_ONCE(msk->write_seq)) {
 		if (mptcp_timer_pending(sk) && !mptcp_data_fin_enabled(msk))
 			mptcp_stop_timer(sk);
 	} else {
@@ -1117,9 +1116,8 @@ out:
 
 static void __mptcp_clean_una_wakeup(struct sock *sk)
 {
-#ifdef CONFIG_LOCKDEP
-	WARN_ON_ONCE(!lockdep_is_held(&sk->sk_lock.slock));
-#endif
+	lockdep_assert_held_once(&sk->sk_lock.slock);
+
 	__mptcp_clean_una(sk);
 	mptcp_write_space(sk);
 }
@@ -1525,6 +1523,38 @@ static void mptcp_push_release(struct sock *sk, struct sock *ssk,
 	release_sock(ssk);
 }
 
+static void mptcp_update_post_push(struct mptcp_sock *msk,
+				   struct mptcp_data_frag *dfrag,
+				   u32 sent)
+{
+	u64 snd_nxt_new = dfrag->data_seq;
+
+	dfrag->already_sent += sent;
+
+	msk->snd_burst -= sent;
+
+	snd_nxt_new += dfrag->already_sent;
+
+	/* snd_nxt_new can be smaller than snd_nxt in case mptcp
+	 * is recovering after a failover. In that event, this re-sends
+	 * old segments.
+	 *
+	 * Thus compute snd_nxt_new candidate based on
+	 * the dfrag->data_seq that was sent and the data
+	 * that has been handed to the subflow for transmission
+	 * and skip update in case it was old dfrag.
+	 */
+	if (likely(after64(snd_nxt_new, msk->snd_nxt)))
+		msk->snd_nxt = snd_nxt_new;
+}
+
+static void mptcp_check_and_set_pending(struct sock *sk)
+{
+	if (mptcp_send_head(sk) &&
+	    !test_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags))
+		set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags);
+}
+
 void __mptcp_push_pending(struct sock *sk, unsigned int flags)
 {
 	struct sock *prev_ssk = NULL, *ssk = NULL;
@@ -1568,12 +1598,10 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags)
 			}
 
 			info.sent += ret;
-			dfrag->already_sent += ret;
-			msk->snd_nxt += ret;
-			msk->snd_burst -= ret;
-			msk->tx_pending_data -= ret;
 			copied += ret;
 			len -= ret;
+
+			mptcp_update_post_push(msk, dfrag, ret);
 		}
 		WRITE_ONCE(msk->first_pending, mptcp_send_next(sk));
 	}
@@ -1626,13 +1654,11 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk)
 				goto out;
 
 			info.sent += ret;
-			dfrag->already_sent += ret;
-			msk->snd_nxt += ret;
-			msk->snd_burst -= ret;
-			msk->tx_pending_data -= ret;
 			copied += ret;
 			len -= ret;
 			first = false;
+
+			mptcp_update_post_push(msk, dfrag, ret);
 		}
 		WRITE_ONCE(msk->first_pending, mptcp_send_next(sk));
 	}
@@ -1742,7 +1768,6 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		frag_truesize += psize;
 		pfrag->offset += frag_truesize;
 		WRITE_ONCE(msk->write_seq, msk->write_seq + psize);
-		msk->tx_pending_data += psize;
 
 		/* charge data on mptcp pending queue to the msk socket
 		 * Note: we charge such data both to sk and ssk
@@ -2230,15 +2255,11 @@ bool __mptcp_retransmit_pending_data(struct sock *sk)
 		return false;
 	}
 
-	/* will accept ack for reijected data before re-sending them */
-	if (!msk->recovery || after64(msk->snd_nxt, msk->recovery_snd_nxt))
-		msk->recovery_snd_nxt = msk->snd_nxt;
+	msk->recovery_snd_nxt = msk->snd_nxt;
 	msk->recovery = true;
 	mptcp_data_unlock(sk);
 
 	msk->first_pending = rtx_head;
-	msk->tx_pending_data += msk->snd_nxt - rtx_head->data_seq;
-	msk->snd_nxt = rtx_head->data_seq;
 	msk->snd_burst = 0;
 
 	/* be sure to clear the "sent status" on all re-injected fragments */
@@ -2401,6 +2422,9 @@ static void __mptcp_retrans(struct sock *sk)
 	int ret;
 
 	mptcp_clean_una_wakeup(sk);
+
+	/* first check ssk: need to kick "stale" logic */
+	ssk = mptcp_subflow_get_retrans(msk);
 	dfrag = mptcp_rtx_head(sk);
 	if (!dfrag) {
 		if (mptcp_data_fin_enabled(msk)) {
@@ -2413,10 +2437,12 @@ static void __mptcp_retrans(struct sock *sk)
 			goto reset_timer;
 		}
 
-		return;
+		if (!mptcp_send_head(sk))
+			return;
+
+		goto reset_timer;
 	}
 
-	ssk = mptcp_subflow_get_retrans(msk);
 	if (!ssk)
 		goto reset_timer;
 
@@ -2443,6 +2469,8 @@ static void __mptcp_retrans(struct sock *sk)
 	release_sock(ssk);
 
 reset_timer:
+	mptcp_check_and_set_pending(sk);
+
 	if (!mptcp_timer_pending(sk))
 		mptcp_reset_timer(sk);
 }
@@ -2509,7 +2537,6 @@ static int __mptcp_init_sock(struct sock *sk)
 	msk->first_pending = NULL;
 	msk->wmem_reserved = 0;
 	WRITE_ONCE(msk->rmem_released, 0);
-	msk->tx_pending_data = 0;
 	msk->timer_ival = TCP_RTO_MIN;
 
 	msk->first = NULL;
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index d3e6fd1615f1..d516fb6578cc 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -254,7 +254,6 @@ struct mptcp_sock {
 	struct sk_buff  *ooo_last_skb;
 	struct rb_root  out_of_order_queue;
 	struct sk_buff_head receive_queue;
-	int		tx_pending_data;
 	struct list_head conn_list;
 	struct list_head rtx_queue;
 	struct mptcp_data_frag *first_pending;