Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Cross-merge networking fixes after downstream PR (net-6.18-rc4).

No conflicts, adjacent changes:

drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
  ded9813d17d3 ("net: stmmac: Consider Tx VLAN offload tag length for maxSDU")
  26ab9830beab ("net: stmmac: replace has_xxxx with core_type")

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 53 insertions, 30 deletions

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 94a5f6dcc577..d568575cdcb5 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -194,17 +194,26 @@ static bool mptcp_ooo_try_coalesce(struct mptcp_sock *msk, struct sk_buff *to,
  * - mptcp does not maintain a msk-level window clamp
  * - returns true when  the receive buffer is actually updated
  */
-static bool mptcp_rcvbuf_grow(struct sock *sk)
+static bool mptcp_rcvbuf_grow(struct sock *sk, u32 newval)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	const struct net *net = sock_net(sk);
-	int rcvwin, rcvbuf, cap;
+	u32 rcvwin, rcvbuf, cap, oldval;
+	u64 grow;
 
+	oldval = msk->rcvq_space.space;
+	msk->rcvq_space.space = newval;
 	if (!READ_ONCE(net->ipv4.sysctl_tcp_moderate_rcvbuf) ||
 	    (sk->sk_userlocks & SOCK_RCVBUF_LOCK))
 		return false;
 
-	rcvwin = msk->rcvq_space.space << 1;
+	/* DRS is always one RTT late. */
+	rcvwin = newval << 1;
+
+	/* slow start: allow the sender to double its rate. */
+	grow = (u64)rcvwin * (newval - oldval);
+	do_div(grow, oldval);
+	rcvwin += grow << 1;
 
 	if (!RB_EMPTY_ROOT(&msk->out_of_order_queue))
 		rcvwin += MPTCP_SKB_CB(msk->ooo_last_skb)->end_seq - msk->ack_seq;
@@ -334,7 +343,7 @@ end:
 	skb_set_owner_r(skb, sk);
 	/* do not grow rcvbuf for not-yet-accepted or orphaned sockets. */
 	if (sk->sk_socket)
-		mptcp_rcvbuf_grow(sk);
+		mptcp_rcvbuf_grow(sk, msk->rcvq_space.space);
 }
 
 static void mptcp_init_skb(struct sock *ssk, struct sk_buff *skb, int offset,
@@ -998,7 +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);
@@ -1291,7 +1300,12 @@ 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;
 		}
@@ -1342,6 +1356,7 @@ 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))
@@ -1544,7 +1559,7 @@ 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) ||
@@ -1904,7 +1919,7 @@ 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,
@@ -1937,22 +1952,36 @@ 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)) {
@@ -1969,16 +1998,14 @@ 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;
@@ -1986,7 +2013,6 @@ 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)
@@ -2050,9 +2076,7 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)
 	if (msk->rcvq_space.copied <= msk->rcvq_space.space)
 		goto new_measure;
 
-	msk->rcvq_space.space = msk->rcvq_space.copied;
-	if (mptcp_rcvbuf_grow(sk)) {
-
+	if (mptcp_rcvbuf_grow(sk, msk->rcvq_space.copied)) {
 		/* Make subflows follow along.  If we do not do this, we
 		 * get drops at subflow level if skbs can't be moved to
 		 * the mptcp rx queue fast enough (announced rcv_win can
@@ -2064,8 +2088,9 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)
 
 			ssk = mptcp_subflow_tcp_sock(subflow);
 			slow = lock_sock_fast(ssk);
-			tcp_sk(ssk)->rcvq_space.space = msk->rcvq_space.copied;
-			tcp_rcvbuf_grow(ssk);
+			/* subflows can be added before tcp_init_transfer() */
+			if (tcp_sk(ssk)->rcvq_space.space)
+				tcp_rcvbuf_grow(ssk, msk->rcvq_space.copied);
 			unlock_sock_fast(ssk, slow);
 		}
 	}
@@ -2184,7 +2209,8 @@ 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;
@@ -2875,7 +2901,7 @@ 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);
 }
@@ -3415,9 +3441,6 @@ 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