Merge branch 'mptcp-various-rare-sending-issues'

Matthieu Baerts says:

====================
mptcp: various rare sending issues

Here are various fixes from Paolo, addressing very occasional issues on
the sending side:

- Patch 1: drop an optimisation that could lead to timeout in case of
  race conditions. A fix for up to v5.11.

- Patch 2: fix stream corruption under very specific conditions.
  A fix for up to v5.13.

- Patch 3: restore MPTCP-level zero window probe after a recent fix.
  A fix for up to v5.16.

- Patch 4: new MIB counter to track MPTCP-level zero windows probe to
  help catching issues similar to the one fixed by the previous patch.
====================

Link: https://patch.msgid.link/20251028-net-mptcp-send-timeout-v1-0-38ffff5a9ec8@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

4 files changed, 39 insertions, 22 deletions

diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c
index 6003e47c770a..171643815076 100644
--- a/net/mptcp/mib.c
+++ b/net/mptcp/mib.c
@@ -85,6 +85,7 @@ static const struct snmp_mib mptcp_snmp_list[] = {
 	SNMP_MIB_ITEM("DssFallback", MPTCP_MIB_DSSFALLBACK),
 	SNMP_MIB_ITEM("SimultConnectFallback", MPTCP_MIB_SIMULTCONNFALLBACK),
 	SNMP_MIB_ITEM("FallbackFailed", MPTCP_MIB_FALLBACKFAILED),
+	SNMP_MIB_ITEM("WinProbe", MPTCP_MIB_WINPROBE),
 };
 
 /* mptcp_mib_alloc - allocate percpu mib counters
diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h
index 309bac6fea32..a1d3e9369fbb 100644
--- a/net/mptcp/mib.h
+++ b/net/mptcp/mib.h
@@ -88,6 +88,7 @@ enum linux_mptcp_mib_field {
 	MPTCP_MIB_DSSFALLBACK,		/* Bad or missing DSS */
 	MPTCP_MIB_SIMULTCONNFALLBACK,	/* Simultaneous connect */
 	MPTCP_MIB_FALLBACKFAILED,	/* Can't fallback due to msk status */
+	MPTCP_MIB_WINPROBE,		/* MPTCP-level zero window probe */
 	__MPTCP_MIB_MAX
 };
 
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 875027b9319c..2d6b8de35c44 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1007,7 +1007,7 @@ static void __mptcp_clean_una(struct sock *sk)
 			if (WARN_ON_ONCE(!msk->recovery))
 				break;
 
-			WRITE_ONCE(msk->first_pending, mptcp_send_next(sk));
+			msk->first_pending = mptcp_send_next(sk);
 		}
 
 		dfrag_clear(sk, dfrag);
@@ -1299,7 +1299,12 @@ alloc_skb:
 	if (copy == 0) {
 		u64 snd_una = READ_ONCE(msk->snd_una);
 
-		if (snd_una != msk->snd_nxt || tcp_write_queue_tail(ssk)) {
+		/* No need for zero probe if there are any data pending
+		 * either at the msk or ssk level; skb is the current write
+		 * queue tail and can be empty at this point.
+		 */
+		if (snd_una != msk->snd_nxt || skb->len ||
+		    skb != tcp_send_head(ssk)) {
 			tcp_remove_empty_skb(ssk);
 			return 0;
 		}
@@ -1350,6 +1355,7 @@ alloc_skb:
 		 mpext->dsn64);
 
 	if (zero_window_probe) {
+		MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_WINPROBE);
 		mptcp_subflow_ctx(ssk)->rel_write_seq += copy;
 		mpext->frozen = 1;
 		if (READ_ONCE(msk->csum_enabled))
@@ -1552,7 +1558,7 @@ static int __subflow_push_pending(struct sock *sk, struct sock *ssk,
 
 			mptcp_update_post_push(msk, dfrag, ret);
 		}
-		WRITE_ONCE(msk->first_pending, mptcp_send_next(sk));
+		msk->first_pending = mptcp_send_next(sk);
 
 		if (msk->snd_burst <= 0 ||
 		    !sk_stream_memory_free(ssk) ||
@@ -1912,7 +1918,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 			get_page(dfrag->page);
 			list_add_tail(&dfrag->list, &msk->rtx_queue);
 			if (!msk->first_pending)
-				WRITE_ONCE(msk->first_pending, dfrag);
+				msk->first_pending = dfrag;
 		}
 		pr_debug("msk=%p dfrag at seq=%llu len=%u sent=%u new=%d\n", msk,
 			 dfrag->data_seq, dfrag->data_len, dfrag->already_sent,
@@ -1945,22 +1951,36 @@ do_error:
 
 static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied);
 
-static int __mptcp_recvmsg_mskq(struct sock *sk,
-				struct msghdr *msg,
-				size_t len, int flags,
+static int __mptcp_recvmsg_mskq(struct sock *sk, struct msghdr *msg,
+				size_t len, int flags, int copied_total,
 				struct scm_timestamping_internal *tss,
 				int *cmsg_flags)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	struct sk_buff *skb, *tmp;
+	int total_data_len = 0;
 	int copied = 0;
 
 	skb_queue_walk_safe(&sk->sk_receive_queue, skb, tmp) {
-		u32 offset = MPTCP_SKB_CB(skb)->offset;
+		u32 delta, offset = MPTCP_SKB_CB(skb)->offset;
 		u32 data_len = skb->len - offset;
-		u32 count = min_t(size_t, len - copied, data_len);
+		u32 count;
 		int err;
 
+		if (flags & MSG_PEEK) {
+			/* skip already peeked skbs */
+			if (total_data_len + data_len <= copied_total) {
+				total_data_len += data_len;
+				continue;
+			}
+
+			/* skip the already peeked data in the current skb */
+			delta = copied_total - total_data_len;
+			offset += delta;
+			data_len -= delta;
+		}
+
+		count = min_t(size_t, len - copied, data_len);
 		if (!(flags & MSG_TRUNC)) {
 			err = skb_copy_datagram_msg(skb, offset, msg, count);
 			if (unlikely(err < 0)) {
@@ -1977,16 +1997,14 @@ static int __mptcp_recvmsg_mskq(struct sock *sk,
 
 		copied += count;
 
-		if (count < data_len) {
-			if (!(flags & MSG_PEEK)) {
+		if (!(flags & MSG_PEEK)) {
+			msk->bytes_consumed += count;
+			if (count < data_len) {
 				MPTCP_SKB_CB(skb)->offset += count;
 				MPTCP_SKB_CB(skb)->map_seq += count;
-				msk->bytes_consumed += count;
+				break;
 			}
-			break;
-		}
 
-		if (!(flags & MSG_PEEK)) {
 			/* avoid the indirect call, we know the destructor is sock_rfree */
 			skb->destructor = NULL;
 			skb->sk = NULL;
@@ -1994,7 +2012,6 @@ static int __mptcp_recvmsg_mskq(struct sock *sk,
 			sk_mem_uncharge(sk, skb->truesize);
 			__skb_unlink(skb, &sk->sk_receive_queue);
 			skb_attempt_defer_free(skb);
-			msk->bytes_consumed += count;
 		}
 
 		if (copied >= len)
@@ -2191,7 +2208,8 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 	while (copied < len) {
 		int err, bytes_read;
 
-		bytes_read = __mptcp_recvmsg_mskq(sk, msg, len - copied, flags, &tss, &cmsg_flags);
+		bytes_read = __mptcp_recvmsg_mskq(sk, msg, len - copied, flags,
+						  copied, &tss, &cmsg_flags);
 		if (unlikely(bytes_read < 0)) {
 			if (!copied)
 				copied = bytes_read;
@@ -2882,7 +2900,7 @@ static void __mptcp_clear_xmit(struct sock *sk)
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	struct mptcp_data_frag *dtmp, *dfrag;
 
-	WRITE_ONCE(msk->first_pending, NULL);
+	msk->first_pending = NULL;
 	list_for_each_entry_safe(dfrag, dtmp, &msk->rtx_queue, list)
 		dfrag_clear(sk, dfrag);
 }
@@ -3422,9 +3440,6 @@ void __mptcp_data_acked(struct sock *sk)
 
 void __mptcp_check_push(struct sock *sk, struct sock *ssk)
 {
-	if (!mptcp_send_head(sk))
-		return;
-
 	if (!sock_owned_by_user(sk))
 		__mptcp_subflow_push_pending(sk, ssk, false);
 	else
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 52f9cfa4ce95..379a88e14e8d 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -414,7 +414,7 @@ static inline struct mptcp_data_frag *mptcp_send_head(const struct sock *sk)
 {
 	const struct mptcp_sock *msk = mptcp_sk(sk);
 
-	return READ_ONCE(msk->first_pending);
+	return msk->first_pending;
 }
 
 static inline struct mptcp_data_frag *mptcp_send_next(struct sock *sk)